diff options
299 files changed, 5126 insertions, 3185 deletions
diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd index bf9c16b64c3..cf11736acb7 100644 --- a/Documentation/ABI/testing/debugfs-pktcdvd +++ b/Documentation/ABI/testing/debugfs-pktcdvd @@ -1,4 +1,4 @@ -What: /debug/pktcdvd/pktcdvd[0-7] +What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7] Date: Oct. 2006 KernelVersion: 2.6.20 Contact: Thomas Maier <balagi@justmail.de> @@ -10,10 +10,10 @@ debugfs interface The pktcdvd module (packet writing driver) creates these files in debugfs: -/debug/pktcdvd/pktcdvd[0-7]/ +/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/ info (0444) Lots of driver statistics and infos. Example: ------- -cat /debug/pktcdvd/pktcdvd0/info +cat /sys/kernel/debug/pktcdvd/pktcdvd0/info diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index ecad6ee7570..6fab97ea7e6 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -1040,23 +1040,21 @@ Front merges are handled by the binary trees in AS and deadline schedulers. iii. Plugging the queue to batch requests in anticipation of opportunities for merge/sort optimizations -This is just the same as in 2.4 so far, though per-device unplugging -support is anticipated for 2.5. Also with a priority-based i/o scheduler, -such decisions could be based on request priorities. - Plugging is an approach that the current i/o scheduling algorithm resorts to so that it collects up enough requests in the queue to be able to take advantage of the sorting/merging logic in the elevator. If the queue is empty when a request comes in, then it plugs the request queue -(sort of like plugging the bottom of a vessel to get fluid to build up) +(sort of like plugging the bath tub of a vessel to get fluid to build up) till it fills up with a few more requests, before starting to service the requests. This provides an opportunity to merge/sort the requests before passing them down to the device. There are various conditions when the queue is unplugged (to open up the flow again), either through a scheduled task or could be on demand. For example wait_on_buffer sets the unplugging going -(by running tq_disk) so the read gets satisfied soon. So in the read case, -the queue gets explicitly unplugged as part of waiting for completion, -in fact all queues get unplugged as a side-effect. +through sync_buffer() running blk_run_address_space(mapping). Or the caller +can do it explicity through blk_unplug(bdev). So in the read case, +the queue gets explicitly unplugged as part of waiting for completion on that +buffer. For page driven IO, the address space ->sync_page() takes care of +doing the blk_run_address_space(). Aside: This is kind of controversial territory, as it's not clear if plugging is @@ -1067,11 +1065,6 @@ Aside: multi-page bios being queued in one shot, we may not need to wait to merge a big request from the broken up pieces coming by. - Per-queue granularity unplugging (still a Todo) may help reduce some of the - concerns with just a single tq_disk flush approach. Something like - blk_kick_queue() to unplug a specific queue (right away ?) - or optionally, all queues, is in the plan. - 4.4 I/O contexts I/O contexts provide a dynamically allocated per process data area. They may be used in I/O schedulers, and in the block layer (could be used for IO statis, diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index a98a7fe7aab..1a608877b14 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -6,15 +6,14 @@ used here with the memory controller that is used in hardware. Salient features -a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages +a. Enable control of Anonymous, Page Cache (mapped and unmapped) and + Swap Cache memory pages. b. The infrastructure allows easy addition of other types of memory to control c. Provides *zero overhead* for non memory controller users d. Provides a double LRU: global memory pressure causes reclaim from the global LRU; a cgroup on hitting a limit, reclaims from the per cgroup LRU -NOTE: Swap Cache (unmapped) is not accounted now. - Benefits and Purpose of the memory controller The memory controller isolates the memory behaviour of a group of tasks @@ -290,34 +289,44 @@ will be charged as a new owner of it. moved to the parent. If you want to avoid that, force_empty will be useful. 5.2 stat file - memory.stat file includes following statistics (now) - cache - # of pages from page-cache and shmem. - rss - # of pages from anonymous memory. - pgpgin - # of event of charging - pgpgout - # of event of uncharging - active_anon - # of pages on active lru of anon, shmem. - inactive_anon - # of pages on active lru of anon, shmem - active_file - # of pages on active lru of file-cache - inactive_file - # of pages on inactive lru of file cache - unevictable - # of pages cannot be reclaimed.(mlocked etc) - - Below is depend on CONFIG_DEBUG_VM. - inactive_ratio - VM internal parameter. (see mm/page_alloc.c) - recent_rotated_anon - VM internal parameter. (see mm/vmscan.c) - recent_rotated_file - VM internal parameter. (see mm/vmscan.c) - recent_scanned_anon - VM internal parameter. (see mm/vmscan.c) - recent_scanned_file - VM internal parameter. (see mm/vmscan.c) - - Memo: + +memory.stat file includes following statistics + +cache - # of bytes of page cache memory. +rss - # of bytes of anonymous and swap cache memory. +pgpgin - # of pages paged in (equivalent to # of charging events). +pgpgout - # of pages paged out (equivalent to # of uncharging events). +active_anon - # of bytes of anonymous and swap cache memory on active + lru list. +inactive_anon - # of bytes of anonymous memory and swap cache memory on + inactive lru list. +active_file - # of bytes of file-backed memory on active lru list. +inactive_file - # of bytes of file-backed memory on inactive lru list. +unevictable - # of bytes of memory that cannot be reclaimed (mlocked etc). + +The following additional stats are dependent on CONFIG_DEBUG_VM. + +inactive_ratio - VM internal parameter. (see mm/page_alloc.c) +recent_rotated_anon - VM internal parameter. (see mm/vmscan.c) +recent_rotated_file - VM internal parameter. (see mm/vmscan.c) +recent_scanned_anon - VM internal parameter. (see mm/vmscan.c) +recent_scanned_file - VM internal parameter. (see mm/vmscan.c) + +Memo: recent_rotated means recent frequency of lru rotation. recent_scanned means recent # of scans to lru. showing for better debug please see the code for meanings. +Note: + Only anonymous and swap cache memory is listed as part of 'rss' stat. + This should not be confused with the true 'resident set size' or the + amount of physical memory used by the cgroup. Per-cgroup rss + accounting is not done yet. 5.3 swappiness Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. - Following cgroup's swapiness can't be changed. + Following cgroups' swapiness can't be changed. - root cgroup (uses /proc/sys/vm/swappiness). - a cgroup which uses hierarchy and it has child cgroup. - a cgroup which uses hierarchy and not the root of hierarchy. diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt index f196ac1d7d2..95b24d766ea 100644 --- a/Documentation/cgroups/resource_counter.txt +++ b/Documentation/cgroups/resource_counter.txt @@ -47,13 +47,18 @@ to work with it. 2. Basic accounting routines - a. void res_counter_init(struct res_counter *rc) + a. void res_counter_init(struct res_counter *rc, + struct res_counter *rc_parent) Initializes the resource counter. As usual, should be the first routine called for a new counter. - b. int res_counter_charge[_locked] - (struct res_counter *rc, unsigned long val) + The struct res_counter *parent can be used to define a hierarchical + child -> parent relationship directly in the res_counter structure, + NULL can be used to define no relationship. + + c. int res_counter_charge(struct res_counter *rc, unsigned long val, + struct res_counter **limit_fail_at) When a resource is about to be allocated it has to be accounted with the appropriate resource counter (controller should determine @@ -67,15 +72,25 @@ to work with it. * if the charging is performed first, then it should be uncharged on error path (if the one is called). - c. void res_counter_uncharge[_locked] + If the charging fails and a hierarchical dependency exists, the + limit_fail_at parameter is set to the particular res_counter element + where the charging failed. + + d. int res_counter_charge_locked + (struct res_counter *rc, unsigned long val) + + The same as res_counter_charge(), but it must not acquire/release the + res_counter->lock internally (it must be called with res_counter->lock + held). + + e. void res_counter_uncharge[_locked] (struct res_counter *rc, unsigned long val) When a resource is released (freed) it should be de-accounted from the resource counter it was accounted to. This is called "uncharging". - The _locked routines imply that the res_counter->lock is taken. - + The _locked routines imply that the res_counter->lock is taken. 2.1 Other accounting routines diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt index d0ab33e21fe..b6d2e21474f 100644 --- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt +++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt @@ -7,8 +7,10 @@ Required properties : Recommended properties : - - compatible : Should be "fsl-i2c" for parts compatible with - Freescale I2C specifications. + - compatible : compatibility list with 2 entries, the first should + be "fsl,CHIP-i2c" where CHIP is the name of a compatible processor, + e.g. mpc8313, mpc8543, mpc8544, mpc5200 or mpc5200b. The second one + should be "fsl-i2c". - interrupts : <a b> where a is the interrupt number and b is a field that represents an encoding of the sense and level information for the interrupt. This should be encoded based on @@ -16,17 +18,31 @@ Recommended properties : controller you have. - interrupt-parent : the phandle for the interrupt controller that services interrupts for this device. - - dfsrr : boolean; if defined, indicates that this I2C device has - a digital filter sampling rate register - - fsl5200-clocking : boolean; if defined, indicated that this device - uses the FSL 5200 clocking mechanism. - -Example : - i2c@3000 { - interrupt-parent = <40000>; - interrupts = <1b 3>; - reg = <3000 18>; - device_type = "i2c"; - compatible = "fsl-i2c"; - dfsrr; + - fsl,preserve-clocking : boolean; if defined, the clock settings + from the bootloader are preserved (not touched). + - clock-frequency : desired I2C bus clock frequency in Hz. + +Examples : + + i2c@3d00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c"; + cell-index = <0>; + reg = <0x3d00 0x40>; + interrupts = <2 15 0>; + interrupt-parent = <&mpc5200_pic>; + fsl,preserve-clocking; }; + + i2c@3100 { + #address-cells = <1>; + #size-cells = <0>; + cell-index = <1>; + compatible = "fsl,mpc8544-i2c", "fsl-i2c"; + reg = <0x3100 0x100>; + interrupts = <43 2>; + interrupt-parent = <&mpic>; + clock-frequency = <400000>; + }; + diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt index c5948f2f9a2..88b7433d2f1 100644 --- a/Documentation/sound/alsa/HD-Audio.txt +++ b/Documentation/sound/alsa/HD-Audio.txt @@ -169,7 +169,7 @@ PCI SSID look-up. What `model` option values are available depends on the codec chip. Check your codec chip from the codec proc file (see "Codec Proc-File" section below). It will show the vendor/product name of your codec -chip. Then, see Documentation/sound/alsa/HD-Audio-Modelstxt file, +chip. Then, see Documentation/sound/alsa/HD-Audio-Models.txt file, the section of HD-audio driver. You can find a list of codecs and `model` options belonging to each codec. For example, for Realtek ALC262 codec chip, pass `model=ultra` for devices that are compatible @@ -177,7 +177,7 @@ with Samsung Q1 Ultra. Thus, the first thing you can do for any brand-new, unsupported and non-working HD-audio hardware is to check HD-audio codec and several -different `model` option values. If you have a luck, some of them +different `model` option values. If you have any luck, some of them might suit with your device well. Some codecs such as ALC880 have a special model option `model=test`. diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index a34d55b6544..df38ef046f8 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -95,7 +95,7 @@ of struct cmsghdr structures with appended data. There is only one file in this directory. unix_dgram_qlen limits the max number of datagrams queued in Unix domain -socket's buffer. It will not take effect unless PF_UNIX flag is spicified. +socket's buffer. It will not take effect unless PF_UNIX flag is specified. 3. /proc/sys/net/ipv4 - IPV4 settings diff --git a/Documentation/tomoyo.txt b/Documentation/tomoyo.txt new file mode 100644 index 00000000000..b3a232cae7f --- /dev/null +++ b/Documentation/tomoyo.txt @@ -0,0 +1,55 @@ +--- What is TOMOYO? --- + +TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel. + +LiveCD-based tutorials are available at +http://tomoyo.sourceforge.jp/en/1.6.x/1st-step/ubuntu8.04-live/ +http://tomoyo.sourceforge.jp/en/1.6.x/1st-step/centos5-live/ . +Though these tutorials use non-LSM version of TOMOYO, they are useful for you +to know what TOMOYO is. + +--- How to enable TOMOYO? --- + +Build the kernel with CONFIG_SECURITY_TOMOYO=y and pass "security=tomoyo" on +kernel's command line. + +Please see http://tomoyo.sourceforge.jp/en/2.2.x/ for details. + +--- Where is documentation? --- + +User <-> Kernel interface documentation is available at +http://tomoyo.sourceforge.jp/en/2.2.x/policy-reference.html . + +Materials we prepared for seminars and symposiums are available at +http://sourceforge.jp/projects/tomoyo/docs/?category_id=532&language_id=1 . +Below lists are chosen from three aspects. + +What is TOMOYO? + TOMOYO Linux Overview + http://sourceforge.jp/projects/tomoyo/docs/lca2009-takeda.pdf + TOMOYO Linux: pragmatic and manageable security for Linux + http://sourceforge.jp/projects/tomoyo/docs/freedomhectaipei-tomoyo.pdf + TOMOYO Linux: A Practical Method to Understand and Protect Your Own Linux Box + http://sourceforge.jp/projects/tomoyo/docs/PacSec2007-en-no-demo.pdf + +What can TOMOYO do? + Deep inside TOMOYO Linux + http://sourceforge.jp/projects/tomoyo/docs/lca2009-kumaneko.pdf + The role of "pathname based access control" in security. + http://sourceforge.jp/projects/tomoyo/docs/lfj2008-bof.pdf + +History of TOMOYO? + Realities of Mainlining + http://sourceforge.jp/projects/tomoyo/docs/lfj2008.pdf + +--- What is future plan? --- + +We believe that inode based security and name based security are complementary +and both should be used together. But unfortunately, so far, we cannot enable +multiple LSM modules at the same time. We feel sorry that you have to give up +SELinux/SMACK/AppArmor etc. when you want to use TOMOYO. + +We hope that LSM becomes stackable in future. Meanwhile, you can use non-LSM +version of TOMOYO, available at http://tomoyo.sourceforge.jp/en/1.6.x/ . +LSM version of TOMOYO is a subset of non-LSM version of TOMOYO. We are planning +to port non-LSM version's functionalities to LSM versions. diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX index 2131b00b63f..2f77ced35df 100644 --- a/Documentation/vm/00-INDEX +++ b/Documentation/vm/00-INDEX @@ -1,5 +1,7 @@ 00-INDEX - this file. +active_mm.txt + - An explanation from Linus about tsk->active_mm vs tsk->mm. balance - various information on memory balancing. hugetlbpage.txt diff --git a/Documentation/vm/active_mm.txt b/Documentation/vm/active_mm.txt new file mode 100644 index 00000000000..4ee1f643d89 --- /dev/null +++ b/Documentation/vm/active_mm.txt @@ -0,0 +1,83 @@ +List: linux-kernel +Subject: Re: active_mm +From: Linus Torvalds <torvalds () transmeta ! com> +Date: 1999-07-30 21:36:24 + +Cc'd to linux-kernel, because I don't write explanations all that often, +and when I do I feel better about more people reading them. + +On Fri, 30 Jul 1999, David Mosberger wrote: +> +> Is there a brief description someplace on how "mm" vs. "active_mm" in +> the task_struct are supposed to be used? (My apologies if this was +> discussed on the mailing lists---I just returned from vacation and +> wasn't able to follow linux-kernel for a while). + +Basically, the new setup is: + + - we have "real address spaces" and "anonymous address spaces". The + difference is that an anonymous address space doesn't care about the + user-level page tables at all, so when we do a context switch into an + anonymous address space we just leave the previous address space + active. + + The obvious use for a "anonymous address space" is any thread that + doesn't need any user mappings - all kernel threads basically fall into + this category, but even "real" threads can temporarily say that for + some amount of time they are not going to be interested in user space, + and that the scheduler might as well try to avoid wasting time on + switching the VM state around. Currently only the old-style bdflush + sync does that. + + - "tsk->mm" points to the "real address space". For an anonymous process, + tsk->mm will be NULL, for the logical reason that an anonymous process + really doesn't _have_ a real address space at all. + + - however, we obviously need to keep track of which address space we + "stole" for such an anonymous user. For that, we have "tsk->active_mm", + which shows what the currently active address space is. + + The rule is that for a process with a real address space (ie tsk->mm is + non-NULL) the active_mm obviously always has to be the same as the real + one. + + For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the + "borrowed" mm while the anonymous process is running. When the + anonymous process gets scheduled away, the borrowed address space is + returned and cleared. + +To support all that, the "struct mm_struct" now has two counters: a +"mm_users" counter that is how many "real address space users" there are, +and a "mm_count" counter that is the number of "lazy" users (ie anonymous +users) plus one if there are any real users. + +Usually there is at least one real user, but it could be that the real +user exited on another CPU while a lazy user was still active, so you do +actually get cases where you have a address space that is _only_ used by +lazy users. That is often a short-lived state, because once that thread +gets scheduled away in favour of a real thread, the "zombie" mm gets +released because "mm_users" becomes zero. + +Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any +more. "init_mm" should be considered just a "lazy context when no other +context is available", and in fact it is mainly used just at bootup when +no real VM has yet been created. So code that used to check + + if (current->mm == &init_mm) + +should generally just do + + if (!current->mm) + +instead (which makes more sense anyway - the test is basically one of "do +we have a user context", and is generally done by the page fault handler +and things like that). + +Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago, +because it slightly changes the interfaces to accomodate the alpha (who +would have thought it, but the alpha actually ends up having one of the +ugliest context switch codes - unlike the other architectures where the MM +and register state is separate, the alpha PALcode joins the two, and you +need to switch both together). + +(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2) diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt index 0706a7282a8..2d70d0d9510 100644 --- a/Documentation/vm/unevictable-lru.txt +++ b/Documentation/vm/unevictable-lru.txt @@ -1,588 +1,691 @@ - -This document describes the Linux memory management "Unevictable LRU" -infrastructure and the use of this infrastructure to manage several types -of "unevictable" pages. The document attempts to provide the overall -rationale behind this mechanism and the rationale for some of the design -decisions that drove the implementation. The latter design rationale is -discussed in the context of an implementation description. Admittedly, one -can obtain the implementation details--the "what does it do?"--by reading the -code. One hopes that the descriptions below add value by provide the answer -to "why does it do that?". - -Unevictable LRU Infrastructure: - -The Unevictable LRU adds an additional LRU list to track unevictable pages -and to hide these pages from vmscan. This mechanism is based on a patch by -Larry Woodman of Red Hat to address several scalability problems with page + ============================== + UNEVICTABLE LRU INFRASTRUCTURE + ============================== + +======== +CONTENTS +======== + + (*) The Unevictable LRU + + - The unevictable page list. + - Memory control group interaction. + - Marking address spaces unevictable. + - Detecting Unevictable Pages. + - vmscan's handling of unevictable pages. + + (*) mlock()'d pages. + + - History. + - Basic management. + - mlock()/mlockall() system call handling. + - Filtering special vmas. + - munlock()/munlockall() system call handling. + - Migrating mlocked pages. + - mmap(MAP_LOCKED) system call handling. + - munmap()/exit()/exec() system call handling. + - try_to_unmap(). + - try_to_munlock() reverse map scan. + - Page reclaim in shrink_*_list(). + + +============ +INTRODUCTION +============ + +This document describes the Linux memory manager's "Unevictable LRU" +infrastructure and the use of this to manage several types of "unevictable" +pages. + +The document attempts to provide the overall rationale behind this mechanism +and the rationale for some of the design decisions that drove the +implementation. The latter design rationale is discussed in the context of an +implementation description. Admittedly, one can obtain the implementation +details - the "what does it do?" - by reading the code. One hopes that the +descriptions below add value by provide the answer to "why does it do that?". + + +=================== +THE UNEVICTABLE LRU +=================== + +The Unevictable LRU facility adds an additional LRU list to track unevictable +pages and to hide these pages from vmscan. This mechanism is based on a patch +by Larry Woodman of Red Hat to address several scalability problems with page reclaim in Linux. The problems have been observed at customer sites on large -memory x86_64 systems. For example, a non-numal x86_64 platform with 128GB -of main memory will have over 32 million 4k pages in a single zone. When a -large fraction of these pages are not evictable for any reason [see below], -vmscan will spend a lot of time scanning the LRU lists looking for the small -fraction of pages that are evictable. This can result in a situation where -all cpus are spending 100% of their time in vmscan for hours or days on end, -with the system completely unresponsive. - -The Unevictable LRU infrastructure addresses the following classes of -unevictable pages: - -+ page owned by ramfs -+ page mapped into SHM_LOCKed shared memory regions -+ page mapped into VM_LOCKED [mlock()ed] vmas - -The infrastructure might be able to handle other conditions that make pages +memory x86_64 systems. + +To illustrate this with an example, a non-NUMA x86_64 platform with 128GB of +main memory will have over 32 million 4k pages in a single zone. When a large +fraction of these pages are not evictable for any reason [see below], vmscan +will spend a lot of time scanning the LRU lists looking for the small fraction +of pages that are evictable. This can result in a situation where all CPUs are +spending 100% of their time in vmscan for hours or days on end, with the system +completely unresponsive. + +The unevictable list addresses the following classes of unevictable pages: + + (*) Those owned by ramfs. + + (*) Those mapped into SHM_LOCK'd shared memory regions. + + (*) Those mapped into VM_LOCKED [mlock()ed] VMAs. + +The infrastructure may also be able to handle other conditions that make pages unevictable, either by definition or by circumstance, in the future. -The Unevictable LRU List +THE UNEVICTABLE PAGE LIST +------------------------- The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list called the "unevictable" list and an associated page flag, PG_unevictable, to -indicate that the page is being managed on the unevictable list. The -PG_unevictable flag is analogous to, and mutually exclusive with, the PG_active -flag in that it indicates on which LRU list a page resides when PG_lru is set. -The unevictable LRU list is source configurable based on the UNEVICTABLE_LRU -Kconfig option. +indicate that the page is being managed on the unevictable list. + +The PG_unevictable flag is analogous to, and mutually exclusive with, the +PG_active flag in that it indicates on which LRU list a page resides when +PG_lru is set. The unevictable list is compile-time configurable based on the +UNEVICTABLE_LRU Kconfig option. The Unevictable LRU infrastructure maintains unevictable pages on an additional LRU list for a few reasons: -1) We get to "treat unevictable pages just like we treat other pages in the - system, which means we get to use the same code to manipulate them, the - same code to isolate them (for migrate, etc.), the same code to keep track - of the statistics, etc..." [Rik van Riel] + (1) We get to "treat unevictable pages just like we treat other pages in the + system - which means we get to use the same code to manipulate them, the + same code to isolate them (for migrate, etc.), the same code to keep track + of the statistics, etc..." [Rik van Riel] + + (2) We want to be able to migrate unevictable pages between nodes for memory + defragmentation, workload management and memory hotplug. The linux kernel + can only migrate pages that it can successfully isolate from the LRU + lists. If we were to maintain pages elsewhere than on an LRU-like list, + where they can be found by isolate_lru_page(), we would prevent their + migration, unless we reworked migration code to find the unevictable pages + itself. -2) We want to be able to migrate unevictable pages between nodes--for memory - defragmentation, workload management and memory hotplug. The linux kernel - can only migrate pages that it can successfully isolate from the lru lists. - If we were to maintain pages elsewise than on an lru-like list, where they - can be found by isolate_lru_page(), we would prevent their migration, unless - we reworked migration code to find the unevictable pages. +The unevictable list does not differentiate between file-backed and anonymous, +swap-backed pages. This differentiation is only important while the pages are, +in fact, evictable. -The unevictable LRU list does not differentiate between file backed and swap -backed [anon] pages. This differentiation is only important while the pages -are, in fact, evictable. +The unevictable list benefits from the "arrayification" of the per-zone LRU +lists and statistics originally proposed and posted by Christoph Lameter. -The unevictable LRU list benefits from the "arrayification" of the per-zone -LRU lists and statistics originally proposed and posted by Christoph Lameter. +The unevictable list does not use the LRU pagevec mechanism. Rather, +unevictable pages are placed directly on the page's zone's unevictable list +under the zone lru_lock. This allows us to prevent the stranding of pages on +the unevictable list when one task has the page isolated from the LRU and other +tasks are changing the "evictability" state of the page. -The unevictable list does not use the lru pagevec mechanism. Rather, -unevictable pages are placed directly on the page's zone's unevictable -list under the zone lru_lock. The reason for this is to prevent stranding -of pages on the unevictable list when one task has the page isolated from the -lru and other tasks are changing the "evictability" state of the page. +MEMORY CONTROL GROUP INTERACTION +-------------------------------- -Unevictable LRU and Memory Controller Interaction +The unevictable LRU facility interacts with the memory control group [aka +memory controller; see Documentation/cgroups/memory.txt] by extending the +lru_list enum. + +The memory controller data structure automatically gets a per-zone unevictable +list as a result of the "arrayification" of the per-zone LRU lists (one per +lru_list enum element). The memory controller tracks the movement of pages to +and from the unevictable list. -The memory controller data structure automatically gets a per zone unevictable -lru list as a result of the "arrayification" of the per-zone LRU lists. The -memory controller tracks the movement of pages to and from the unevictable list. When a memory control group comes under memory pressure, the controller will not attempt to reclaim pages on the unevictable list. This has a couple of -effects. Because the pages are "hidden" from reclaim on the unevictable list, -the reclaim process can be more efficient, dealing only with pages that have -a chance of being reclaimed. On the other hand, if too many of the pages -charged to the control group are unevictable, the evictable portion of the -working set of the tasks in the control group may not fit into the available -memory. This can cause the control group to thrash or to oom-kill tasks. - - -Unevictable LRU: Detecting Unevictable Pages - -The function page_evictable(page, vma) in vmscan.c determines whether a -page is evictable or not. For ramfs pages and pages in SHM_LOCKed regions, -page_evictable() tests a new address space flag, AS_UNEVICTABLE, in the page's -address space using a wrapper function. Wrapper functions are used to set, -clear and test the flag to reduce the requirement for #ifdef's throughout the -source code. AS_UNEVICTABLE is set on ramfs inode/mapping when it is created. -This flag remains for the life of the inode. - -For shared memory regions, AS_UNEVICTABLE is set when an application -successfully SHM_LOCKs the region and is removed when the region is -SHM_UNLOCKed. Note that shmctl(SHM_LOCK, ...) does not populate the page -tables for the region as does, for example, mlock(). So, we make no special -effort to push any pages in the SHM_LOCKed region to the unevictable list. -Vmscan will do this when/if it encounters the pages during reclaim. On -SHM_UNLOCK, shmctl() scans the pages in the region and "rescues" them from the -unevictable list if no other condition keeps them unevictable. If a SHM_LOCKed -region is destroyed, the pages are also "rescued" from the unevictable list in -the process of freeing them. - -page_evictable() detects mlock()ed pages by testing an additional page flag, -PG_mlocked via the PageMlocked() wrapper. If the page is NOT mlocked, and a -non-NULL vma is supplied, page_evictable() will check whether the vma is +effects: + + (1) Because the pages are "hidden" from reclaim on the unevictable list, the + reclaim process can be more efficient, dealing only with pages that have a + chance of being reclaimed. + + (2) On the other hand, if too many of the pages charged to the control group + are unevictable, the evictable portion of the working set of the tasks in + the control group may not fit into the available memory. This can cause + the control group to thrash or to OOM-kill tasks. + + +MARKING ADDRESS SPACES UNEVICTABLE +---------------------------------- + +For facilities such as ramfs none of the pages attached to the address space +may be evicted. To prevent eviction of any such pages, the AS_UNEVICTABLE +address space flag is provided, and this can be manipulated by a filesystem +using a number of wrapper functions: + + (*) void mapping_set_unevictable(struct address_space *mapping); + + Mark the address space as being completely unevictable. + + (*) void mapping_clear_unevictable(struct address_space *mapping); + + Mark the address space as being evictable. + + (*) int mapping_unevictable(struct address_space *mapping); + + Query the address space, and return true if it is completely + unevictable. + +These are currently used in two places in the kernel: + + (1) By ramfs to mark the address spaces of its inodes when they are created, + and this mark remains for the life of the inode. + + (2) By SYSV SHM to mark SHM_LOCK'd address spaces until SHM_UNLOCK is called. + + Note that SHM_LOCK is not required to page in the locked pages if they're + swapped out; the application must touch the pages manually if it wants to + ensure they're in memory. + + +DETECTING UNEVICTABLE PAGES +--------------------------- + +The function page_evictable() in vmscan.c determines whether a page is +evictable or not using the query function outlined above [see section "Marking +address spaces unevictable"] to check the AS_UNEVICTABLE flag. + +For address spaces that are so marked after being populated (as SHM regions +might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate +the page tables for the region as does, for example, mlock(), nor need it make +any special effort to push any pages in the SHM_LOCK'd area to the unevictable +list. Instead, vmscan will do this if and when it encounters the pages during +a reclamation scan. + +On an unlock action (such as SHM_UNLOCK), the unlocker (eg: shmctl()) must scan +the pages in the region and "rescue" them from the unevictable list if no other +condition is keeping them unevictable. If an unevictable region is destroyed, +the pages are also "rescued" from the unevictable list in the process of +freeing them. + +page_evictable() also checks for mlocked pages by testing an additional page +flag, PG_mlocked (as wrapped by PageMlocked()). If the page is NOT mlocked, +and a non-NULL VMA is supplied, page_evictable() will check whether the VMA is VM_LOCKED via is_mlocked_vma(). is_mlocked_vma() will SetPageMlocked() and update the appropriate statistics if the vma is VM_LOCKED. This method allows efficient "culling" of pages in the fault path that are being faulted in to -VM_LOCKED vmas. +VM_LOCKED VMAs. -Unevictable Pages and Vmscan [shrink_*_list()] +VMSCAN'S HANDLING OF UNEVICTABLE PAGES +-------------------------------------- If unevictable pages are culled in the fault path, or moved to the unevictable -list at mlock() or mmap() time, vmscan will never encounter the pages until -they have become evictable again, for example, via munlock() and have been -"rescued" from the unevictable list. However, there may be situations where we -decide, for the sake of expediency, to leave a unevictable page on one of the -regular active/inactive LRU lists for vmscan to deal with. Vmscan checks for -such pages in all of the shrink_{active|inactive|page}_list() functions and -will "cull" such pages that it encounters--that is, it diverts those pages to -the unevictable list for the zone being scanned. - -There may be situations where a page is mapped into a VM_LOCKED vma, but the -page is not marked as PageMlocked. Such pages will make it all the way to +list at mlock() or mmap() time, vmscan will not encounter the pages until they +have become evictable again (via munlock() for example) and have been "rescued" +from the unevictable list. However, there may be situations where we decide, +for the sake of expediency, to leave a unevictable page on one of the regular +active/inactive LRU lists for vmscan to deal with. vmscan checks for such +pages in all of the shrink_{active|inactive|page}_list() functions and will +"cull" such pages that it encounters: that is, it diverts those pages to the +unevictable list for the zone being scanned. + +There may be situations where a page is mapped into a VM_LOCKED VMA, but the +page is not marked as PG_mlocked. Such pages will make it all the way to shrink_page_list() where they will be detected when vmscan walks the reverse -map in try_to_unmap(). If try_to_unmap() returns SWAP_MLOCK, shrink_page_list() -will cull the page at that point. +map in try_to_unmap(). If try_to_unmap() returns SWAP_MLOCK, +shrink_page_list() will cull the page at that point. -To "cull" an unevictable page, vmscan simply puts the page back on the lru -list using putback_lru_page()--the inverse operation to isolate_lru_page()-- -after dropping the page lock. Because the condition which makes the page -unevictable may change once the page is unlocked, putback_lru_page() will -recheck the unevictable state of a page that it places on the unevictable lru -list. If the page has become unevictable, putback_lru_page() removes it from -the list and retries, including the page_unevictable() test. Because such a -race is a rare event and movement of pages onto the unevictable list should be -rare, these extra evictabilty checks should not occur in the majority of calls -to putback_lru_page(). +To "cull" an unevictable page, vmscan simply puts the page back on the LRU list +using putback_lru_page() - the inverse operation to isolate_lru_page() - after +dropping the page lock. Because the condition which makes the page unevictable +may change once the page is unlocked, putback_lru_page() will recheck the +unevictable state of a page that it places on the unevictable list. If the +page has become unevictable, putback_lru_page() removes it from the list and +retries, including the page_unevictable() test. Because such a race is a rare +event and movement of pages onto the unevictable list should be rare, these +extra evictabilty checks should not occur in the majority of calls to +putback_lru_page(). -Mlocked Page: Prior Work +============= +MLOCKED PAGES +============= -The "Unevictable Mlocked Pages" infrastructure is based on work originally +The unevictable page list is also useful for mlock(), in addition to ramfs and +SYSV SHM. Note that mlock() is only available in CONFIG_MMU=y situations; in +NOMMU situations, all mappings are effectively mlocked. + + +HISTORY +------- + +The "Unevictable mlocked Pages" infrastructure is based on work originally posted by Nick Piggin in an RFC patch entitled "mm: mlocked pages off LRU". -Nick posted his patch as an alternative to a patch posted by Christoph -Lameter to achieve the same objective--hiding mlocked pages from vmscan. -In Nick's patch, he used one of the struct page lru list link fields as a count -of VM_LOCKED vmas that map the page. This use of the link field for a count -prevented the management of the pages on an LRU list. Thus, mlocked pages were -not migratable as isolate_lru_page() could not find them and the lru list link -field was not available to the migration subsystem. Nick resolved this by -putting mlocked pages back on the lru list before attempting to isolate them, -thus abandoning the count of VM_LOCKED vmas. When Nick's patch was integrated -with the Unevictable LRU work, the count was replaced by walking the reverse -map to determine whether any VM_LOCKED vmas mapped the page. More on this -below. - - -Mlocked Pages: Basic Management - -Mlocked pages--pages mapped into a VM_LOCKED vma--represent one class of -unevictable pages. When such a page has been "noticed" by the memory -management subsystem, the page is marked with the PG_mlocked [PageMlocked()] -flag. A PageMlocked() page will be placed on the unevictable LRU list when -it is added to the LRU. Pages can be "noticed" by memory management in -several places: - -1) in the mlock()/mlockall() system call handlers. -2) in the mmap() system call handler when mmap()ing a region with the - MAP_LOCKED flag, or mmap()ing a region in a task that has called - mlockall() with the MCL_FUTURE flag. Both of these conditions result - in the VM_LOCKED flag being set for the vma. -3) in the fault path, if mlocked pages are "culled" in the fault path, - and when a VM_LOCKED stack segment is expanded. -4) as mentioned above, in vmscan:shrink_page_list() when attempting to - reclaim a page in a VM_LOCKED vma via try_to_unmap(). - -Mlocked pages become unlocked and rescued from the unevictable list when: - -1) mapped in a range unlocked via the munlock()/munlockall() system calls. -2) munmapped() out of the last VM_LOCKED vma that maps the page, including - unmapping at task exit. -3) when the page is truncated from the last VM_LOCKED vma of an mmap()ed file. -4) before a page is COWed in a VM_LOCKED vma. - - -Mlocked Pages: mlock()/mlockall() System Call Handling +Nick posted his patch as an alternative to a patch posted by Christoph Lameter +to achieve the same objective: hiding mlocked pages from vmscan. + +In Nick's patch, he used one of the struct page LRU list link fields as a count +of VM_LOCKED VMAs that map the page. This use of the link field for a count +prevented the management of the pages on an LRU list, and thus mlocked pages +were not migratable as isolate_lru_page() could not find them, and the LRU list +link field was not available to the migration subsystem. + +Nick resolved this by putting mlocked pages back on the lru list before +attempting to isolate them, thus abandoning the count of VM_LOCKED VMAs. When +Nick's patch was integrated with the Unevictable LRU work, the count was +replaced by walking the reverse map to determine whether any VM_LOCKED VMAs +mapped the page. More on this below. + + +BASIC MANAGEMENT +---------------- + +mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable +pages. When such a page has been "noticed" by the memory management subsystem, +the page is marked with the PG_mlocked flag. This can be manipulated using the +PageMlocked() functions. + +A PG_mlocked page will be placed on the unevictable list when it is added to +the LRU. Such pages can be "noticed" by memory management in several places: + + (1) in the mlock()/mlockall() system call handlers; + + (2) in the mmap() system call handler when mmapping a region with the + MAP_LOCKED flag; + + (3) mmapping a region in a task that has called mlockall() with the MCL_FUTURE + flag + + (4) in the fault path, if mlocked pages are "culled" in the fault path, + and when a VM_LOCKED stack segment is expanded; or + + (5) as mentioned above, in vmscan:shrink_page_list() when attempting to + reclaim a page in a VM_LOCKED VMA via try_to_unmap() + +all of which result in the VM_LOCKED flag being set for the VMA if it doesn't +already have it set. + +mlocked pages become unlocked and rescued from the unevictable list when: + + (1) mapped in a range unlocked via the munlock()/munlockall() system calls; + + (2) munmap()'d out of the last VM_LOCKED VMA that maps the page, including + unmapping at task exit; + + (3) when the page is truncated from the last VM_LOCKED VMA of an mmapped file; + or + + (4) before a page is COW'd in a VM_LOCKED VMA. + + +mlock()/mlockall() SYSTEM CALL HANDLING +--------------------------------------- Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup() -for each vma in the range specified by the call. In the case of mlockall(), +for each VMA in the range specified by the call. In the case of mlockall(), this is the entire active address space of the task. Note that mlock_fixup() -is used for both mlock()ing and munlock()ing a range of memory. A call to -mlock() an already VM_LOCKED vma, or to munlock() a vma that is not VM_LOCKED -is treated as a no-op--mlock_fixup() simply returns. - -If the vma passes some filtering described in "Mlocked Pages: Filtering Vmas" -below, mlock_fixup() will attempt to merge the vma with its neighbors or split -off a subset of the vma if the range does not cover the entire vma. Once the -vma has been merged or split or neither, mlock_fixup() will call -__mlock_vma_pages_range() to fault in the pages via get_user_pages() and -to mark the pages as mlocked via mlock_vma_page(). - -Note that the vma being mlocked might be mapped with PROT_NONE. In this case, -get_user_pages() will be unable to fault in the pages. That's OK. If pages -do end up getting faulted into this VM_LOCKED vma, we'll handle them in the +is used for both mlocking and munlocking a range of memory. A call to mlock() +an already VM_LOCKED VMA, or to munlock() a VMA that is not VM_LOCKED is +treated as a no-op, and mlock_fixup() simply returns. + +If the VMA passes some filtering as described in "Filtering Special Vmas" +below, mlock_fixup() will attempt to merge the VMA with its neighbors or split +off a subset of the VMA if the range does not cover the entire VMA. Once the +VMA has been merged or split or neither, mlock_fixup() will call +__mlock_vma_pages_range() to fault in the pages via get_user_pages() and to +mark the pages as mlocked via mlock_vma_page(). + +Note that the VMA being mlocked might be mapped with PROT_NONE. In this case, +get_user_pages() will be unable to fault in the pages. That's okay. If pages +do end up getting faulted into this VM_LOCKED VMA, we'll handle them in the fault path or in vmscan. Also note that a page returned by get_user_pages() could be truncated or -migrated out from under us, while we're trying to mlock it. To detect -this, __mlock_vma_pages_range() tests the page_mapping after acquiring -the page lock. If the page is still associated with its mapping, we'll -go ahead and call mlock_vma_page(). If the mapping is gone, we just -unlock the page and move on. Worse case, this results in page mapped -in a VM_LOCKED vma remaining on a normal LRU list without being -PageMlocked(). Again, vmscan will detect and cull such pages. - -mlock_vma_page(), called with the page locked [N.B., not "mlocked"], will -TestSetPageMlocked() for each page returned by get_user_pages(). We use -TestSetPageMlocked() because the page might already be mlocked by another -task/vma and we don't want to do extra work. We especially do not want to -count an mlocked page more than once in the statistics. If the page was -already mlocked, mlock_vma_page() is done. +migrated out from under us, while we're trying to mlock it. To detect this, +__mlock_vma_pages_range() checks page_mapping() after acquiring the page lock. +If the page is still associated with its mapping, we'll go ahead and call +mlock_vma_page(). If the mapping is gone, we just unlock the page and move on. +In the worst case, this will result in a page mapped in a VM_LOCKED VMA +remaining on a normal LRU list without being PageMlocked(). Again, vmscan will +detect and cull such pages. + +mlock_vma_page() will call TestSetPageMlocked() for each page returned by +get_user_pages(). We use TestSetPageMlocked() because the page might already +be mlocked by another task/VMA and we don't want to do extra work. We +especially do not want to count an mlocked page more than once in the +statistics. If the page was already mlocked, mlock_vma_page() need do nothing +more. If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the page from the LRU, as it is likely on the appropriate active or inactive list -at that time. If the isolate_lru_page() succeeds, mlock_vma_page() will -putback the page--putback_lru_page()--which will notice that the page is now -mlocked and divert the page to the zone's unevictable LRU list. If +at that time. If the isolate_lru_page() succeeds, mlock_vma_page() will put +back the page - by calling putback_lru_page() - which will notice that the page +is now mlocked and divert the page to the zone's unevictable list. If mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle -it later if/when it attempts to reclaim the page. +it later if and when it attempts to reclaim the page. -Mlocked Pages: Filtering Special Vmas +FILTERING SPECIAL VMAS +---------------------- -mlock_fixup() filters several classes of "special" vmas: +mlock_fixup() filters several classes of "special" VMAs: -1) vmas with VM_IO|VM_PFNMAP set are skipped entirely. The pages behind +1) VMAs with VM_IO or VM_PFNMAP set are skipped entirely. The pages behind these mappings are inherently pinned, so we don't need to mark them as - mlocked. In any case, most of the pages have no struct page in which to - so mark the page. Because of this, get_user_pages() will fail for these - vmas, so there is no sense in attempting to visit them. - -2) vmas mapping hugetlbfs page are already effectively pinned into memory. - We don't need nor want to mlock() these pages. However, to preserve the - prior behavior of mlock()--before the unevictable/mlock changes-- - mlock_fixup() will call make_pages_present() in the hugetlbfs vma range - to allocate the huge pages and populate the ptes. - -3) vmas with VM_DONTEXPAND|VM_RESERVED are generally user space mappings of - kernel pages, such as the vdso page, relay channel pages, etc. These pages + mlocked. In any case, most of the pages have no struct page in which to so + mark the page. Because of this, get_user_pages() will fail for these VMAs, + so there is no sense in attempting to visit them. + +2) VMAs mapping hugetlbfs page are already effectively pinned into memory. We + neither need nor want to mlock() these pages. However, to preserve the + prior behavior of mlock() - before the unevictable/mlock changes - + mlock_fixup() will call make_pages_present() in the hugetlbfs VMA range to + allocate the huge pages and populate the ptes. + +3) VMAs with VM_DONTEXPAND or VM_RESERVED are generally userspace mappings of + kernel pages, such as the VDSO page, relay channel pages, etc. These pages are inherently unevictable and are not managed on the LRU lists. - mlock_fixup() treats these vmas the same as hugetlbfs vmas. It calls + mlock_fixup() treats these VMAs the same as hugetlbfs VMAs. It calls make_pages_present() to populate the ptes. -Note that for all of these special vmas, mlock_fixup() does not set the +Note that for all of these special VMAs, mlock_fixup() does not set the VM_LOCKED flag. Therefore, we won't have to deal with them later during -munlock() or munmap()--for example, at task exit. Neither does mlock_fixup() -account these vmas against the task's "locked_vm". - -Mlocked Pages: Downgrading the Mmap Semaphore. - -mlock_fixup() must be called with the mmap semaphore held for write, because -it may have to merge or split vmas. However, mlocking a large region of -memory can take a long time--especially if vmscan must reclaim pages to -satisfy the regions requirements. Faulting in a large region with the mmap -semaphore held for write can hold off other faults on the address space, in -the case of a multi-threaded task. It can also hold off scans of the task's -address space via /proc. While testing under heavy load, it was observed that -the ps(1) command could be held off for many minutes while a large segment was -mlock()ed down. - -To address this issue, and to make the system more responsive during mlock()ing -of large segments, mlock_fixup() downgrades the mmap semaphore to read mode -during the call to __mlock_vma_pages_range(). This works fine. However, the -callers of mlock_fixup() expect the semaphore to be returned in write mode. -So, mlock_fixup() "upgrades" the semphore to write mode. Linux does not -support an atomic upgrade_sem() call, so mlock_fixup() must drop the semaphore -and reacquire it in write mode. In a multi-threaded task, it is possible for -the task memory map to change while the semaphore is dropped. Therefore, -mlock_fixup() looks up the vma at the range start address after reacquiring -the semaphore in write mode and verifies that it still covers the original -range. If not, mlock_fixup() returns an error [-EAGAIN]. All callers of -mlock_fixup() have been changed to deal with this new error condition. - -Note: when munlocking a region, all of the pages should already be resident-- -unless we have racing threads mlocking() and munlocking() regions. So, -unlocking should not have to wait for page allocations nor faults of any kind. -Therefore mlock_fixup() does not downgrade the semaphore for munlock(). - - -Mlocked Pages: munlock()/munlockall() System Call Handling - -The munlock() and munlockall() system calls are handled by the same functions-- -do_mlock[all]()--as the mlock() and mlockall() system calls with the unlock -vs lock operation indicated by an argument. So, these system calls are also -handled by mlock_fixup(). Again, if called for an already munlock()ed vma, -mlock_fixup() simply returns. Because of the vma filtering discussed above, -VM_LOCKED will not be set in any "special" vmas. So, these vmas will be +munlock(), munmap() or task exit. Neither does mlock_fixup() account these +VMAs against the task's "locked_vm". + + +munlock()/munlockall() SYSTEM CALL HANDLING +------------------------------------------- + +The munlock() and munlockall() system calls are handled by the same functions - +do_mlock[all]() - as the mlock() and mlockall() system calls with the unlock vs +lock operation indicated by an argument. So, these system calls are also +handled by mlock_fixup(). Again, if called for an already munlocked VMA, +mlock_fixup() simply returns. Because of the VMA filtering discussed above, +VM_LOCKED will not be set in any "special" VMAs. So, these VMAs will be ignored for munlock. -If the vma is VM_LOCKED, mlock_fixup() again attempts to merge or split off -the specified range. The range is then munlocked via the function -__mlock_vma_pages_range()--the same function used to mlock a vma range-- +If the VMA is VM_LOCKED, mlock_fixup() again attempts to merge or split off the +specified range. The range is then munlocked via the function +__mlock_vma_pages_range() - the same function used to mlock a VMA range - passing a flag to indicate that munlock() is being performed. -Because the vma access protections could have been changed to PROT_NONE after +Because the VMA access protections could have been changed to PROT_NONE after faulting in and mlocking pages, get_user_pages() was unreliable for visiting -these pages for munlocking. Because we don't want to leave pages mlocked(), +these pages for munlocking. Because we don't want to leave pages mlocked, get_user_pages() was enhanced to accept a flag to ignore the permissions when -fetching the pages--all of which should be resident as a result of previous -mlock()ing. +fetching the pages - all of which should be resident as a result of previous +mlocking. For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling munlock_vma_page(). munlock_vma_page() unconditionally clears the PG_mlocked -flag using TestClearPageMlocked(). As with mlock_vma_page(), munlock_vma_page() -use the Test*PageMlocked() function to handle the case where the page might -have already been unlocked by another task. If the page was mlocked, -munlock_vma_page() updates that zone statistics for the number of mlocked -pages. Note, however, that at this point we haven't checked whether the page -is mapped by other VM_LOCKED vmas. - -We can't call try_to_munlock(), the function that walks the reverse map to check -for other VM_LOCKED vmas, without first isolating the page from the LRU. +flag using TestClearPageMlocked(). As with mlock_vma_page(), +munlock_vma_page() use the Test*PageMlocked() function to handle the case where +the page might have already been unlocked by another task. If the page was +mlocked, munlock_vma_page() updates that zone statistics for the number of +mlocked pages. Note, however, that at this point we haven't checked whether +the page is mapped by other VM_LOCKED VMAs. + +We can't call try_to_munlock(), the function that walks the reverse map to +check for other VM_LOCKED VMAs, without first isolating the page from the LRU. try_to_munlock() is a variant of try_to_unmap() and thus requires that the page -not be on an lru list. [More on these below.] However, the call to -isolate_lru_page() could fail, in which case we couldn't try_to_munlock(). -So, we go ahead and clear PG_mlocked up front, as this might be the only chance -we have. If we can successfully isolate the page, we go ahead and +not be on an LRU list [more on these below]. However, the call to +isolate_lru_page() could fail, in which case we couldn't try_to_munlock(). So, +we go ahead and clear PG_mlocked up front, as this might be the only chance we +have. If we can successfully isolate the page, we go ahead and try_to_munlock(), which will restore the PG_mlocked flag and update the zone -page statistics if it finds another vma holding the page mlocked. If we fail +page statistics if it finds another VMA holding the page mlocked. If we fail to isolate the page, we'll have left a potentially mlocked page on the LRU. -This is fine, because we'll catch it later when/if vmscan tries to reclaim the -page. This should be relatively rare. - -Mlocked Pages: Migrating Them... - -A page that is being migrated has been isolated from the lru lists and is -held locked across unmapping of the page, updating the page's mapping -[address_space] entry and copying the contents and state, until the -page table entry has been replaced with an entry that refers to the new -page. Linux supports migration of mlocked pages and other unevictable -pages. This involves simply moving the PageMlocked and PageUnevictable states -from the old page to the new page. - -Note that page migration can race with mlocking or munlocking of the same -page. This has been discussed from the mlock/munlock perspective in the -respective sections above. Both processes [migration, m[un]locking], hold -the page locked. This provides the first level of synchronization. Page -migration zeros out the page_mapping of the old page before unlocking it, -so m[un]lock can skip these pages by testing the page mapping under page -lock. - -When completing page migration, we place the new and old pages back onto the -lru after dropping the page lock. The "unneeded" page--old page on success, -new page on failure--will be freed when the reference count held by the -migration process is released. To ensure that we don't strand pages on the -unevictable list because of a race between munlock and migration, page -migration uses the putback_lru_page() function to add migrated pages back to -the lru. - - -Mlocked Pages: mmap(MAP_LOCKED) System Call Handling +This is fine, because we'll catch it later if and if vmscan tries to reclaim +the page. This should be relatively rare. + + +MIGRATING MLOCKED PAGES +----------------------- + +A page that is being migrated has been isolated from the LRU lists and is held +locked across unmapping of the page, updating the page's address space entry +and copying the contents and state, until the page table entry has been +replaced with an entry that refers to the new page. Linux supports migration +of mlocked pages and other unevictable pages. This involves simply moving the +PG_mlocked and PG_unevictable states from the old page to the new page. + +Note that page migration can race with mlocking or munlocking of the same page. +This has been discussed from the mlock/munlock perspective in the respective +sections above. Both processes (migration and m[un]locking) hold the page +locked. This provides the first level of synchronization. Page migration +zeros out the page_mapping of the old page before unlocking it, so m[un]lock +can skip these pages by testing the page mapping under page lock. + +To complete page migration, we place the new and old pages back onto the LRU +after dropping the page lock. The "unneeded" page - old page on success, new +page on failure - will be freed when the reference count held by the migration +process is released. To ensure that we don't strand pages on the unevictable +list because of a race between munlock and migration, page migration uses the +putback_lru_page() function to add migrated pages back to the LRU. + + +mmap(MAP_LOCKED) SYSTEM CALL HANDLING +------------------------------------- In addition the the mlock()/mlockall() system calls, an application can request -that a region of memory be mlocked using the MAP_LOCKED flag with the mmap() +that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap() call. Furthermore, any mmap() call or brk() call that expands the heap by a task that has previously called mlockall() with the MCL_FUTURE flag will result -in the newly mapped memory being mlocked. Before the unevictable/mlock changes, -the kernel simply called make_pages_present() to allocate pages and populate -the page table. +in the newly mapped memory being mlocked. Before the unevictable/mlock +changes, the kernel simply called make_pages_present() to allocate pages and +populate the page table. To mlock a range of memory under the unevictable/mlock infrastructure, the mmap() handler and task address space expansion functions call mlock_vma_pages_range() specifying the vma and the address range to mlock. -mlock_vma_pages_range() filters vmas like mlock_fixup(), as described above in -"Mlocked Pages: Filtering Vmas". It will clear the VM_LOCKED flag, which will -have already been set by the caller, in filtered vmas. Thus these vma's need -not be visited for munlock when the region is unmapped. +mlock_vma_pages_range() filters VMAs like mlock_fixup(), as described above in +"Filtering Special VMAs". It will clear the VM_LOCKED flag, which will have +already been set by the caller, in filtered VMAs. Thus these VMA's need not be +visited for munlock when the region is unmapped. -For "normal" vmas, mlock_vma_pages_range() calls __mlock_vma_pages_range() to +For "normal" VMAs, mlock_vma_pages_range() calls __mlock_vma_pages_range() to fault/allocate the pages and mlock them. Again, like mlock_fixup(), mlock_vma_pages_range() downgrades the mmap semaphore to read mode before -attempting to fault/allocate and mlock the pages; and "upgrades" the semaphore +attempting to fault/allocate and mlock the pages and "upgrades" the semaphore back to write mode before returning. -The callers of mlock_vma_pages_range() will have already added the memory -range to be mlocked to the task's "locked_vm". To account for filtered vmas, +The callers of mlock_vma_pages_range() will have already added the memory range +to be mlocked to the task's "locked_vm". To account for filtered VMAs, mlock_vma_pages_range() returns the number of pages NOT mlocked. All of the -callers then subtract a non-negative return value from the task's locked_vm. -A negative return value represent an error--for example, from get_user_pages() -attempting to fault in a vma with PROT_NONE access. In this case, we leave -the memory range accounted as locked_vm, as the protections could be changed -later and pages allocated into that region. +callers then subtract a non-negative return value from the task's locked_vm. A +negative return value represent an error - for example, from get_user_pages() +attempting to fault in a VMA with PROT_NONE access. In this case, we leave the +memory range accounted as locked_vm, as the protections could be changed later +and pages allocated into that region. -Mlocked Pages: munmap()/exit()/exec() System Call Handling +munmap()/exit()/exec() SYSTEM CALL HANDLING +------------------------------------------- When unmapping an mlocked region of memory, whether by an explicit call to munmap() or via an internal unmap from exit() or exec() processing, we must -munlock the pages if we're removing the last VM_LOCKED vma that maps the pages. +munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages. Before the unevictable/mlock changes, mlocking did not mark the pages in any way, so unmapping them required no processing. To munlock a range of memory under the unevictable/mlock infrastructure, the -munmap() hander and task address space tear down function call +munmap() handler and task address space call tear down function munlock_vma_pages_all(). The name reflects the observation that one always -specifies the entire vma range when munlock()ing during unmap of a region. -Because of the vma filtering when mlocking() regions, only "normal" vmas that +specifies the entire VMA range when munlock()ing during unmap of a region. +Because of the VMA filtering when mlocking() regions, only "normal" VMAs that actually contain mlocked pages will be passed to munlock_vma_pages_all(). -munlock_vma_pages_all() clears the VM_LOCKED vma flag and, like mlock_fixup() +munlock_vma_pages_all() clears the VM_LOCKED VMA flag and, like mlock_fixup() for the munlock case, calls __munlock_vma_pages_range() to walk the page table -for the vma's memory range and munlock_vma_page() each resident page mapped by -the vma. This effectively munlocks the page, only if this is the last -VM_LOCKED vma that maps the page. - +for the VMA's memory range and munlock_vma_page() each resident page mapped by +the VMA. This effectively munlocks the page, only if this is the last +VM_LOCKED VMA that maps the page. -Mlocked Page: try_to_unmap() -[Note: the code changes represented by this section are really quite small -compared to the text to describe what happening and why, and to discuss the -implications.] +try_to_unmap() +-------------- -Pages can, of course, be mapped into multiple vmas. Some of these vmas may +Pages can, of course, be mapped into multiple VMAs. Some of these VMAs may have VM_LOCKED flag set. It is possible for a page mapped into one or more -VM_LOCKED vmas not to have the PG_mlocked flag set and therefore reside on one -of the active or inactive LRU lists. This could happen if, for example, a -task in the process of munlock()ing the page could not isolate the page from -the LRU. As a result, vmscan/shrink_page_list() might encounter such a page -as described in "Unevictable Pages and Vmscan [shrink_*_list()]". To -handle this situation, try_to_unmap() has been enhanced to check for VM_LOCKED -vmas while it is walking a page's reverse map. +VM_LOCKED VMAs not to have the PG_mlocked flag set and therefore reside on one +of the active or inactive LRU lists. This could happen if, for example, a task +in the process of munlocking the page could not isolate the page from the LRU. +As a result, vmscan/shrink_page_list() might encounter such a page as described +in section "vmscan's handling of unevictable pages". To handle this situation, +try_to_unmap() checks for VM_LOCKED VMAs while it is walking a page's reverse +map. try_to_unmap() is always called, by either vmscan for reclaim or for page -migration, with the argument page locked and isolated from the LRU. BUG_ON() -assertions enforce this requirement. Separate functions handle anonymous and -mapped file pages, as these types of pages have different reverse map -mechanisms. - - try_to_unmap_anon() - -To unmap anonymous pages, each vma in the list anchored in the anon_vma must be -visited--at least until a VM_LOCKED vma is encountered. If the page is being -unmapped for migration, VM_LOCKED vmas do not stop the process because mlocked -pages are migratable. However, for reclaim, if the page is mapped into a -VM_LOCKED vma, the scan stops. try_to_unmap() attempts to acquire the mmap -semphore of the mm_struct to which the vma belongs in read mode. If this is -successful, try_to_unmap() will mlock the page via mlock_vma_page()--we -wouldn't have gotten to try_to_unmap() if the page were already mlocked--and -will return SWAP_MLOCK, indicating that the page is unevictable. If the -mmap semaphore cannot be acquired, we are not sure whether the page is really -unevictable or not. In this case, try_to_unmap() will return SWAP_AGAIN. - - try_to_unmap_file() -- linear mappings - -Unmapping of a mapped file page works the same, except that the scan visits -all vmas that maps the page's index/page offset in the page's mapping's -reverse map priority search tree. It must also visit each vma in the page's -mapping's non-linear list, if the list is non-empty. As for anonymous pages, -on encountering a VM_LOCKED vma for a mapped file page, try_to_unmap() will -attempt to acquire the associated mm_struct's mmap semaphore to mlock the page, -returning SWAP_MLOCK if this is successful, and SWAP_AGAIN, if not. - - try_to_unmap_file() -- non-linear mappings - -If a page's mapping contains a non-empty non-linear mapping vma list, then -try_to_un{map|lock}() must also visit each vma in that list to determine -whether the page is mapped in a VM_LOCKED vma. Again, the scan must visit -all vmas in the non-linear list to ensure that the pages is not/should not be -mlocked. If a VM_LOCKED vma is found in the list, the scan could terminate. -However, there is no easy way to determine whether the page is actually mapped -in a given vma--either for unmapping or testing whether the VM_LOCKED vma -actually pins the page. - -So, try_to_unmap_file() handles non-linear mappings by scanning a certain -number of pages--a "cluster"--in each non-linear vma associated with the page's -mapping, for each file mapped page that vmscan tries to unmap. If this happens -to unmap the page we're trying to unmap, try_to_unmap() will notice this on -return--(page_mapcount(page) == 0)--and return SWAP_SUCCESS. Otherwise, it -will return SWAP_AGAIN, causing vmscan to recirculate this page. We take -advantage of the cluster scan in try_to_unmap_cluster() as follows: - -For each non-linear vma, try_to_unmap_cluster() attempts to acquire the mmap -semaphore of the associated mm_struct for read without blocking. If this -attempt is successful and the vma is VM_LOCKED, try_to_unmap_cluster() will -retain the mmap semaphore for the scan; otherwise it drops it here. Then, -for each page in the cluster, if we're holding the mmap semaphore for a locked -vma, try_to_unmap_cluster() calls mlock_vma_page() to mlock the page. This -call is a no-op if the page is already locked, but will mlock any pages in -the non-linear mapping that happen to be unlocked. If one of the pages so -mlocked is the page passed in to try_to_unmap(), try_to_unmap_cluster() will -return SWAP_MLOCK, rather than the default SWAP_AGAIN. This will allow vmscan -to cull the page, rather than recirculating it on the inactive list. Again, -if try_to_unmap_cluster() cannot acquire the vma's mmap sem, it returns -SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED vma, but -couldn't be mlocked. - - -Mlocked pages: try_to_munlock() Reverse Map Scan - -TODO/FIXME: a better name might be page_mlocked()--analogous to the -page_referenced() reverse map walker. - -When munlock_vma_page()--see "Mlocked Pages: munlock()/munlockall() -System Call Handling" above--tries to munlock a page, it needs to -determine whether or not the page is mapped by any VM_LOCKED vma, without -actually attempting to unmap all ptes from the page. For this purpose, the -unevictable/mlock infrastructure introduced a variant of try_to_unmap() called -try_to_munlock(). +migration, with the argument page locked and isolated from the LRU. Separate +functions handle anonymous and mapped file pages, as these types of pages have +different reverse map mechanisms. + + (*) try_to_unmap_anon() + + To unmap anonymous pages, each VMA in the list anchored in the anon_vma + must be visited - at least until a VM_LOCKED VMA is encountered. If the + page is being unmapped for migration, VM_LOCKED VMAs do not stop the + process because mlocked pages are migratable. However, for reclaim, if + the page is mapped into a VM_LOCKED VMA, the scan stops. + + try_to_unmap_anon() attempts to acquire in read mode the mmap semphore of + the mm_struct to which the VMA belongs. If this is successful, it will + mlock the page via mlock_vma_page() - we wouldn't have gotten to + try_to_unmap_anon() if the page were already mlocked - and will return + SWAP_MLOCK, indicating that the page is unevictable. + + If the mmap semaphore cannot be acquired, we are not sure whether the page + is really unevictable or not. In this case, try_to_unmap_anon() will + return SWAP_AGAIN. + + (*) try_to_unmap_file() - linear mappings + + Unmapping of a mapped file page works the same as for anonymous mappings, + except that the scan visits all VMAs that map the page's index/page offset + in the page's mapping's reverse map priority search tree. It also visits + each VMA in the page's mapping's non-linear list, if the list is + non-empty. + + As for anonymous pages, on encountering a VM_LOCKED VMA for a mapped file + page, try_to_unmap_file() will attempt to acquire the associated + mm_struct's mmap semaphore to mlock the page, returning SWAP_MLOCK if this + is successful, and SWAP_AGAIN, if not. + + (*) try_to_unmap_file() - non-linear mappings + + If a page's mapping contains a non-empty non-linear mapping VMA list, then + try_to_un{map|lock}() must also visit each VMA in that list to determine + whether the page is mapped in a VM_LOCKED VMA. Again, the scan must visit + all VMAs in the non-linear list to ensure that the pages is not/should not + be mlocked. + + If a VM_LOCKED VMA is found in the list, the scan could terminate. + However, there is no easy way to determine whether the page is actually + mapped in a given VMA - either for unmapping or testing whether the + VM_LOCKED VMA actually pins the page. + + try_to_unmap_file() handles non-linear mappings by scanning a certain + number of pages - a "cluster" - in each non-linear VMA associated with the + page's mapping, for each file mapped page that vmscan tries to unmap. If + this happens to unmap the page we're trying to unmap, try_to_unmap() will + notice this on return (page_mapcount(page) will be 0) and return + SWAP_SUCCESS. Otherwise, it will return SWAP_AGAIN, causing vmscan to + recirculate this page. We take advantage of the cluster scan in + try_to_unmap_cluster() as follows: + + For each non-linear VMA, try_to_unmap_cluster() attempts to acquire the + mmap semaphore of the associated mm_struct for read without blocking. + + If this attempt is successful and the VMA is VM_LOCKED, + try_to_unmap_cluster() will retain the mmap semaphore for the scan; + otherwise it drops it here. + + Then, for each page in the cluster, if we're holding the mmap semaphore + for a locked VMA, try_to_unmap_cluster() calls mlock_vma_page() to + mlock the page. This call is a no-op if the page is already locked, + but will mlock any pages in the non-linear mapping that happen to be + unlocked. + + If one of the pages so mlocked is the page passed in to try_to_unmap(), + try_to_unmap_cluster() will return SWAP_MLOCK, rather than the default + SWAP_AGAIN. This will allow vmscan to cull the page, rather than + recirculating it on the inactive list. + + Again, if try_to_unmap_cluster() cannot acquire the VMA's mmap sem, it + returns SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED + VMA, but couldn't be mlocked. + + +try_to_munlock() REVERSE MAP SCAN +--------------------------------- + + [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the + page_referenced() reverse map walker. + +When munlock_vma_page() [see section "munlock()/munlockall() System Call +Handling" above] tries to munlock a page, it needs to determine whether or not +the page is mapped by any VM_LOCKED VMA without actually attempting to unmap +all PTEs from the page. For this purpose, the unevictable/mlock infrastructure +introduced a variant of try_to_unmap() called try_to_munlock(). try_to_munlock() calls the same functions as try_to_unmap() for anonymous and mapped file pages with an additional argument specifing unlock versus unmap processing. Again, these functions walk the respective reverse maps looking -for VM_LOCKED vmas. When such a vma is found for anonymous pages and file +for VM_LOCKED VMAs. When such a VMA is found for anonymous pages and file pages mapped in linear VMAs, as in the try_to_unmap() case, the functions attempt to acquire the associated mmap semphore, mlock the page via mlock_vma_page() and return SWAP_MLOCK. This effectively undoes the pre-clearing of the page's PG_mlocked done by munlock_vma_page. -If try_to_unmap() is unable to acquire a VM_LOCKED vma's associated mmap -semaphore, it will return SWAP_AGAIN. This will allow shrink_page_list() -to recycle the page on the inactive list and hope that it has better luck -with the page next time. - -For file pages mapped into non-linear vmas, the try_to_munlock() logic works -slightly differently. On encountering a VM_LOCKED non-linear vma that might -map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking -the page. munlock_vma_page() will just leave the page unlocked and let -vmscan deal with it--the usual fallback position. - -Note that try_to_munlock()'s reverse map walk must visit every vma in a pages' -reverse map to determine that a page is NOT mapped into any VM_LOCKED vma. -However, the scan can terminate when it encounters a VM_LOCKED vma and can -successfully acquire the vma's mmap semphore for read and mlock the page. -Although try_to_munlock() can be called many [very many!] times when -munlock()ing a large region or tearing down a large address space that has been -mlocked via mlockall(), overall this is a fairly rare event. - -Mlocked Page: Page Reclaim in shrink_*_list() - -shrink_active_list() culls any obviously unevictable pages--i.e., -!page_evictable(page, NULL)--diverting these to the unevictable lru -list. However, shrink_active_list() only sees unevictable pages that -made it onto the active/inactive lru lists. Note that these pages do not -have PageUnevictable set--otherwise, they would be on the unevictable list and -shrink_active_list would never see them. +If try_to_unmap() is unable to acquire a VM_LOCKED VMA's associated mmap +semaphore, it will return SWAP_AGAIN. This will allow shrink_page_list() to +recycle the page on the inactive list and hope that it has better luck with the +page next time. + +For file pages mapped into non-linear VMAs, the try_to_munlock() logic works +slightly differently. On encountering a VM_LOCKED non-linear VMA that might +map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking the +page. munlock_vma_page() will just leave the page unlocked and let vmscan deal +with it - the usual fallback position. + +Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's +reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA. +However, the scan can terminate when it encounters a VM_LOCKED VMA and can +successfully acquire the VMA's mmap semphore for read and mlock the page. +Although try_to_munlock() might be called a great many times when munlocking a +large region or tearing down a large address space that has been mlocked via +mlockall(), overall this is a fairly rare event. + + +PAGE RECLAIM IN shrink_*_list() +------------------------------- + +shrink_active_list() culls any obviously unevictable pages - i.e. +!page_evictable(page, NULL) - diverting these to the unevictable list. +However, shrink_active_list() only sees unevictable pages that made it onto the +active/inactive lru lists. Note that these pages do not have PageUnevictable +set - otherwise they would be on the unevictable list and shrink_active_list +would never see them. Some examples of these unevictable pages on the LRU lists are: -1) ramfs pages that have been placed on the lru lists when first allocated. + (1) ramfs pages that have been placed on the LRU lists when first allocated. + + (2) SHM_LOCK'd shared memory pages. shmctl(SHM_LOCK) does not attempt to + allocate or fault in the pages in the shared memory region. This happens + when an application accesses the page the first time after SHM_LOCK'ing + the segment. -2) SHM_LOCKed shared memory pages. shmctl(SHM_LOCK) does not attempt to - allocate or fault in the pages in the shared memory region. This happens - when an application accesses the page the first time after SHM_LOCKing - the segment. + (3) mlocked pages that could not be isolated from the LRU and moved to the + unevictable list in mlock_vma_page(). -3) Mlocked pages that could not be isolated from the lru and moved to the - unevictable list in mlock_vma_page(). + (4) Pages mapped into multiple VM_LOCKED VMAs, but try_to_munlock() couldn't + acquire the VMA's mmap semaphore to test the flags and set PageMlocked. + munlock_vma_page() was forced to let the page back on to the normal LRU + list for vmscan to handle. -3) Pages mapped into multiple VM_LOCKED vmas, but try_to_munlock() couldn't - acquire the vma's mmap semaphore to test the flags and set PageMlocked. - munlock_vma_page() was forced to let the page back on to the normal - LRU list for vmscan to handle. +shrink_inactive_list() also diverts any unevictable pages that it finds on the +inactive lists to the appropriate zone's unevictable list. -shrink_inactive_list() also culls any unevictable pages that it finds on -the inactive lists, again diverting them to the appropriate zone's unevictable -lru list. shrink_inactive_list() should only see SHM_LOCKed pages that became -SHM_LOCKed after shrink_active_list() had moved them to the inactive list, or -pages mapped into VM_LOCKED vmas that munlock_vma_page() couldn't isolate from -the lru to recheck via try_to_munlock(). shrink_inactive_list() won't notice -the latter, but will pass on to shrink_page_list(). +shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd +after shrink_active_list() had moved them to the inactive list, or pages mapped +into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to +recheck via try_to_munlock(). shrink_inactive_list() won't notice the latter, +but will pass on to shrink_page_list(). shrink_page_list() again culls obviously unevictable pages that it could encounter for similar reason to shrink_inactive_list(). Pages mapped into -VM_LOCKED vmas but without PG_mlocked set will make it all the way to +VM_LOCKED VMAs but without PG_mlocked set will make it all the way to try_to_unmap(). shrink_page_list() will divert them to the unevictable list when try_to_unmap() returns SWAP_MLOCK, as discussed above. diff --git a/MAINTAINERS b/MAINTAINERS index abedca58d8b..abbedb658c2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -461,7 +461,7 @@ F: arch/x86/include/asm/amd_iommu*.h AMD MICROCODE UPDATE SUPPORT P: Andreas Herrmann -M: andeas.herrmann3@amd.com +M: andreas.herrmann3@amd.com L: amd64-microcode@amd64.org S: Supported F: arch/x86/kernel/microcode_amd.c @@ -1894,7 +1894,7 @@ F: fs/ecryptfs/ EDAC-CORE P: Doug Thompson M: dougthompson@xmission.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Supported F: Documentation/edac.txt @@ -1906,7 +1906,7 @@ P: Mark Gross P: Doug Thompson M: mark.gross@intel.com M: dougthompson@xmission.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/e752x_edac.c @@ -1914,7 +1914,7 @@ F: drivers/edac/e752x_edac.c EDAC-E7XXX P: Doug Thompson M: dougthompson@xmission.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/e7xxx_edac.c @@ -1922,7 +1922,7 @@ F: drivers/edac/e7xxx_edac.c EDAC-I82443BXGX P: Tim Small M: tim@buttersideup.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/i82443bxgx_edac.c @@ -1930,7 +1930,7 @@ F: drivers/edac/i82443bxgx_edac.c EDAC-I3000 P: Jason Uhlenkott M: juhlenko@akamai.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/i3000_edac.c @@ -1938,7 +1938,7 @@ F: drivers/edac/i3000_edac.c EDAC-I5000 P: Doug Thompson M: dougthompson@xmission.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/i5000_edac.c @@ -1946,7 +1946,7 @@ F: drivers/edac/i5000_edac.c EDAC-I5400 P: Mauro Carvalho Chehab M: mchehab@redhat.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/i5400_edac.c @@ -1956,7 +1956,7 @@ P: Ranganathan Desikan P: Arvind R. M: rdesikan@jetzbroadband.com M: arvind@acarlab.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/i82975x_edac.c @@ -1964,7 +1964,7 @@ F: drivers/edac/i82975x_edac.c EDAC-PASEMI P: Egor Martovetsky M: egor@pasemi.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/pasemi_edac.c @@ -1972,7 +1972,7 @@ F: drivers/edac/pasemi_edac.c EDAC-R82600 P: Tim Small M: tim@buttersideup.com -L: bluesmoke-devel@lists.sourceforge.net +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net S: Maintained F: drivers/edac/r82600_edac.c @@ -2592,8 +2592,8 @@ S: Maintained F: fs/hpfs/ HSO 3G MODEM DRIVER -P: Denis Joseph Barrow -M: d.barow@option.com +P: Jan Dumon +M: j.dumon@option.com W: http://www.pharscape.org S: Maintained F: drivers/net/usb/hso.c @@ -3680,6 +3680,7 @@ L: microblaze-uclinux@itee.uq.edu.au W: http://www.monstr.eu/fdt/ T: git git://git.monstr.eu/linux-2.6-microblaze.git S: Supported +F: arch/microblaze/ MICROTEK X6 SCANNER P: Oliver Neukum @@ -4971,8 +4972,8 @@ S: Maintained for 2.6. F: Documentation/sgi-visws.txt SGI XP/XPC/XPNET DRIVER -P: Dean Nelson -M: dcn@sgi.com +P: Robin Holt +M: holt@sgi.com S: Maintained F: drivers/misc/sgi-xp/ @@ -5306,7 +5307,9 @@ L: linux-sh@vger.kernel.org W: http://www.linux-sh.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6.git S: Supported +F: Documentation/sh/ F: arch/sh/ +F: drivers/sh/ SUSPEND TO RAM P: Len Brown @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 30 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Temporary Tasmanian Devil # *DOCUMENTATION* @@ -169,7 +169,7 @@ SUBARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh.*/sh/ ) + -e s/sh[234].*/sh/ ) # Cross compiling and selecting different set of gcc/bin-utils # --------------------------------------------------------------------------- @@ -210,6 +210,11 @@ ifeq ($(ARCH),sparc64) SRCARCH := sparc endif +# Additional ARCH settings for sh +ifeq ($(ARCH),sh64) + SRCARCH := sh +endif + # Where to locate arch specific headers hdr-arch := $(SRCARCH) diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c index fc74e913c41..34a56a136ef 100644 --- a/arch/arm/mach-omap2/usb-musb.c +++ b/arch/arm/mach-omap2/usb-musb.c @@ -131,14 +131,14 @@ static struct musb_hdrc_platform_data musb_plat = { .power = 50, /* up to 100 mA */ }; -static u64 musb_dmamask = DMA_32BIT_MASK; +static u64 musb_dmamask = DMA_BIT_MASK(32); static struct platform_device musb_device = { .name = "musb_hdrc", .id = -1, .dev = { .dma_mask = &musb_dmamask, - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &musb_plat, }, .num_resources = ARRAY_SIZE(musb_resources), @@ -146,14 +146,14 @@ static struct platform_device musb_device = { }; #ifdef CONFIG_NOP_USB_XCEIV -static u64 nop_xceiv_dmamask = DMA_32BIT_MASK; +static u64 nop_xceiv_dmamask = DMA_BIT_MASK(32); static struct platform_device nop_xceiv_device = { .name = "nop_usb_xceiv", .id = -1, .dev = { .dma_mask = &nop_xceiv_dmamask, - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = NULL, }, }; diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index 573f02c39a0..285aae8431c 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -16,7 +16,7 @@ EXPORT_SYMBOL(swiotlb); static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - if (dev->coherent_dma_mask != DMA_64BIT_MASK) + if (dev->coherent_dma_mask != DMA_BIT_MASK(64)) gfp |= GFP_DMA; return swiotlb_alloc_coherent(dev, size, dma_handle, gfp); } diff --git a/arch/microblaze/include/asm/auxvec.h b/arch/microblaze/include/asm/auxvec.h index e69de29bb2d..8b137891791 100644 --- a/arch/microblaze/include/asm/auxvec.h +++ b/arch/microblaze/include/asm/auxvec.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/include/asm/cputable.h b/arch/microblaze/include/asm/cputable.h index e69de29bb2d..8b137891791 100644 --- a/arch/microblaze/include/asm/cputable.h +++ b/arch/microblaze/include/asm/cputable.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/include/asm/ftrace.h b/arch/microblaze/include/asm/ftrace.h new file mode 100644 index 00000000000..8b137891791 --- /dev/null +++ b/arch/microblaze/include/asm/ftrace.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/include/asm/hw_irq.h b/arch/microblaze/include/asm/hw_irq.h index e69de29bb2d..8b137891791 100644 --- a/arch/microblaze/include/asm/hw_irq.h +++ b/arch/microblaze/include/asm/hw_irq.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index cfab0342588..8b5853ee6b5 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -12,7 +12,6 @@ #include <asm/byteorder.h> #include <asm/page.h> #include <linux/types.h> -#include <asm/page.h> #define IO_SPACE_LIMIT (0xFFFFFFFF) diff --git a/arch/microblaze/include/asm/socket.h b/arch/microblaze/include/asm/socket.h index f919b6b540a..82593686031 100644 --- a/arch/microblaze/include/asm/socket.h +++ b/arch/microblaze/include/asm/socket.h @@ -63,4 +63,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_MICROBLAZE_SOCKET_H */ diff --git a/arch/microblaze/include/asm/user.h b/arch/microblaze/include/asm/user.h index e69de29bb2d..8b137891791 100644 --- a/arch/microblaze/include/asm/user.h +++ b/arch/microblaze/include/asm/user.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/include/asm/vga.h b/arch/microblaze/include/asm/vga.h index e69de29bb2d..8b137891791 100644 --- a/arch/microblaze/include/asm/vga.h +++ b/arch/microblaze/include/asm/vga.h @@ -0,0 +1 @@ + diff --git a/arch/microblaze/kernel/of_device.c b/arch/microblaze/kernel/of_device.c index 717edf4ad0b..9a0f7632c47 100644 --- a/arch/microblaze/kernel/of_device.c +++ b/arch/microblaze/kernel/of_device.c @@ -13,7 +13,6 @@ void of_device_make_bus_id(struct of_device *dev) { static atomic_t bus_no_reg_magic; struct device_node *node = dev->node; - char *name = dev->dev.bus_id; const u32 *reg; u64 addr; int magic; @@ -25,9 +24,8 @@ void of_device_make_bus_id(struct of_device *dev) if (reg) { addr = of_translate_address(node, reg); if (addr != OF_BAD_ADDR) { - snprintf(name, BUS_ID_SIZE, - "%llx.%s", (unsigned long long)addr, - node->name); + dev_set_name(&dev->dev, "%llx.%s", + (unsigned long long)addr, node->name); return; } } @@ -37,7 +35,7 @@ void of_device_make_bus_id(struct of_device *dev) * counter (and pray...) */ magic = atomic_add_return(1, &bus_no_reg_magic); - snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1); + dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); } EXPORT_SYMBOL(of_device_make_bus_id); @@ -58,7 +56,7 @@ struct of_device *of_device_alloc(struct device_node *np, dev->dev.archdata.of_node = np; if (bus_id) - strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE); + dev_set_name(&dev->dev, bus_id); else of_device_make_bus_id(dev); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 60e9ed7d313..436f26ccbfa 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -115,8 +115,7 @@ void flush_thread(void) { } -/* FIXME - here will be a proposed change -> remove nr parameter */ -int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, +int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c index 475b1fac5cf..34c48718061 100644 --- a/arch/microblaze/kernel/prom.c +++ b/arch/microblaze/kernel/prom.c @@ -39,7 +39,6 @@ #include <asm/system.h> #include <asm/mmu.h> #include <asm/pgtable.h> -#include <linux/pci.h> #include <asm/sections.h> #include <asm/pci-bridge.h> diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c index 3171e39e322..b86aa623e36 100644 --- a/arch/microblaze/kernel/ptrace.c +++ b/arch/microblaze/kernel/ptrace.c @@ -32,7 +32,6 @@ #include <linux/signal.h> #include <linux/errno.h> -#include <linux/ptrace.h> #include <asm/processor.h> #include <linux/uaccess.h> #include <asm/asm-offsets.h> diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index ff347b98863..3889cf45fa7 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -37,7 +37,6 @@ #include <linux/uaccess.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> -#include <linux/signal.h> #include <linux/syscalls.h> #include <asm/cacheflush.h> #include <asm/syscalls.h> diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index d90b548fb1b..ba0568c2cc1 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -29,9 +29,7 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/fs.h> -#include <linux/ipc.h> #include <linux/semaphore.h> -#include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/unistd.h> diff --git a/arch/mn10300/include/asm/bug.h b/arch/mn10300/include/asm/bug.h index 4fcf3384e25..aa6a3888639 100644 --- a/arch/mn10300/include/asm/bug.h +++ b/arch/mn10300/include/asm/bug.h @@ -11,10 +11,12 @@ #ifndef _ASM_BUG_H #define _ASM_BUG_H +#ifdef CONFIG_BUG + /* * Tell the user there is some problem. */ -#define _debug_bug_trap() \ +#define BUG() \ do { \ asm volatile( \ " syscall 15 \n" \ @@ -25,11 +27,11 @@ do { \ : \ : "i"(__FILE__), "i"(__LINE__) \ ); \ -} while (0) - -#define BUG() _debug_bug_trap() +} while (1) #define HAVE_ARCH_BUG +#endif /* CONFIG_BUG */ + #include <asm-generic/bug.h> #endif /* _ASM_BUG_H */ diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h index 543a4f98695..fef5b434dad 100644 --- a/arch/mn10300/include/asm/unistd.h +++ b/arch/mn10300/include/asm/unistd.h @@ -344,6 +344,8 @@ #define __NR_dup3 331 #define __NR_pipe2 332 #define __NR_inotify_init1 333 +#define __NR_preadv 334 +#define __NR_pwritev 335 #ifdef __KERNEL__ diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S index 34ab5a29315..3dc3e462f92 100644 --- a/arch/mn10300/kernel/entry.S +++ b/arch/mn10300/kernel/entry.S @@ -723,6 +723,8 @@ ENTRY(sys_call_table) .long sys_dup3 .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_pwritev /* 335 */ nr_syscalls=(.-sys_call_table)/4 diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c index 71414e19fd1..79890edfd67 100644 --- a/arch/mn10300/kernel/setup.c +++ b/arch/mn10300/kernel/setup.c @@ -136,10 +136,6 @@ void __init setup_arch(char **cmdline_p) data_resource.start = virt_to_bus(&_etext); data_resource.end = virt_to_bus(&_edata)-1; -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) - start_pfn = (CONFIG_KERNEL_RAM_BASE_ADDRESS >> PAGE_SHIFT); kstart_pfn = PFN_UP(__pa(&_text)); free_pfn = PFN_UP(__pa(&_end)); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5b50e1ac617..4c780455136 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -462,7 +462,7 @@ config PPC_64K_PAGES config PPC_256K_PAGES bool "256k page size" if 44x - depends on !STDBINUTILS && (!SHMEM || BROKEN) + depends on !STDBINUTILS help Make the page size 256k. diff --git a/arch/powerpc/boot/dts/tqm8540.dts b/arch/powerpc/boot/dts/tqm8540.dts index 231bae75663..b6f1fc6eb96 100644 --- a/arch/powerpc/boot/dts/tqm8540.dts +++ b/arch/powerpc/boot/dts/tqm8540.dts @@ -84,9 +84,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { diff --git a/arch/powerpc/boot/dts/tqm8541.dts b/arch/powerpc/boot/dts/tqm8541.dts index 4356a1f0829..fa6a3d54a8a 100644 --- a/arch/powerpc/boot/dts/tqm8541.dts +++ b/arch/powerpc/boot/dts/tqm8541.dts @@ -83,9 +83,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { diff --git a/arch/powerpc/boot/dts/tqm8548-bigflash.dts b/arch/powerpc/boot/dts/tqm8548-bigflash.dts index 19aa72301c8..00f7ed7a245 100644 --- a/arch/powerpc/boot/dts/tqm8548-bigflash.dts +++ b/arch/powerpc/boot/dts/tqm8548-bigflash.dts @@ -85,9 +85,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { @@ -247,7 +247,7 @@ interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; tbi-handle = <&tbi2>; - phy-handle = <&phy3>; + phy-handle = <&phy4>; mdio@520 { #address-cells = <1>; @@ -275,7 +275,7 @@ interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; tbi-handle = <&tbi3>; - phy-handle = <&phy4>; + phy-handle = <&phy5>; mdio@520 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/tqm8548.dts b/arch/powerpc/boot/dts/tqm8548.dts index 49145a04fc6..673e4a778ac 100644 --- a/arch/powerpc/boot/dts/tqm8548.dts +++ b/arch/powerpc/boot/dts/tqm8548.dts @@ -85,9 +85,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { @@ -247,7 +247,7 @@ interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; tbi-handle = <&tbi2>; - phy-handle = <&phy3>; + phy-handle = <&phy4>; mdio@520 { #address-cells = <1>; @@ -275,7 +275,7 @@ interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; tbi-handle = <&tbi3>; - phy-handle = <&phy4>; + phy-handle = <&phy5>; mdio@520 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/tqm8555.dts b/arch/powerpc/boot/dts/tqm8555.dts index 06d366ebbda..6a99f1eef7a 100644 --- a/arch/powerpc/boot/dts/tqm8555.dts +++ b/arch/powerpc/boot/dts/tqm8555.dts @@ -83,9 +83,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { diff --git a/arch/powerpc/boot/dts/tqm8560.dts b/arch/powerpc/boot/dts/tqm8560.dts index feff915e049..b6c2d71defd 100644 --- a/arch/powerpc/boot/dts/tqm8560.dts +++ b/arch/powerpc/boot/dts/tqm8560.dts @@ -85,9 +85,9 @@ interrupt-parent = <&mpic>; dfsrr; - dtt@50 { + dtt@48 { compatible = "national,lm75"; - reg = <0x50>; + reg = <0x48>; }; rtc@68 { diff --git a/arch/powerpc/configs/85xx/tqm8548_defconfig b/arch/powerpc/configs/85xx/tqm8548_defconfig index 0bc45975911..43030fea2ee 100644 --- a/arch/powerpc/configs/85xx/tqm8548_defconfig +++ b/arch/powerpc/configs/85xx/tqm8548_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.29-rc2 -# Mon Jan 26 15:36:20 2009 +# Linux kernel version: 2.6.29-rc7 +# Mon Mar 16 09:03:28 2009 # # CONFIG_PPC64 is not set @@ -22,6 +22,7 @@ CONFIG_FSL_EMB_PERFMON=y # CONFIG_PHYS_64BIT is not set CONFIG_SPE=y CONFIG_PPC_MMU_NOHASH=y +CONFIG_PPC_BOOK3E_MMU=y # CONFIG_PPC_MM_SLICES is not set # CONFIG_SMP is not set CONFIG_PPC32=y @@ -75,6 +76,15 @@ CONFIG_SYSVIPC_SYSCTL=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set # CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_GROUP_SCHED=y @@ -152,11 +162,6 @@ CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="anticipatory" -CONFIG_CLASSIC_RCU=y -# CONFIG_TREE_RCU is not set -# CONFIG_PREEMPT_RCU is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_PREEMPT_RCU_TRACE is not set # CONFIG_FREEZER is not set # @@ -202,7 +207,7 @@ CONFIG_MPIC=y # # Kernel options # -# CONFIG_HIGHMEM is not set +CONFIG_HIGHMEM=y CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -244,6 +249,7 @@ CONFIG_UNEVICTABLE_LRU=y CONFIG_PPC_4K_PAGES=y # CONFIG_PPC_16K_PAGES is not set # CONFIG_PPC_64K_PAGES is not set +# CONFIG_PPC_256K_PAGES is not set CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set @@ -259,6 +265,7 @@ CONFIG_ZONE_DMA=y CONFIG_PPC_INDIRECT_PCI=y CONFIG_FSL_SOC=y CONFIG_FSL_PCI=y +CONFIG_FSL_LBC=y CONFIG_PPC_PCI_CHOICE=y CONFIG_PCI=y CONFIG_PCI_DOMAINS=y @@ -284,10 +291,11 @@ CONFIG_ARCH_SUPPORTS_MSI=y # Default settings for advanced configuration options are used # CONFIG_LOWMEM_SIZE=0x30000000 +CONFIG_LOWMEM_CAM_NUM=3 CONFIG_PAGE_OFFSET=0xc0000000 CONFIG_KERNEL_START=0xc0000000 CONFIG_PHYSICAL_START=0x00000000 -CONFIG_PHYSICAL_ALIGN=0x10000000 +CONFIG_PHYSICAL_ALIGN=0x04000000 CONFIG_TASK_SIZE=0xc0000000 CONFIG_NET=y @@ -363,12 +371,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_BT is not set # CONFIG_AF_RXRPC is not set # CONFIG_PHONET is not set -CONFIG_WIRELESS=y -# CONFIG_CFG80211 is not set -CONFIG_WIRELESS_OLD_REGULATORY=y -# CONFIG_WIRELESS_EXT is not set -# CONFIG_LIB80211 is not set -# CONFIG_MAC80211 is not set +# CONFIG_WIRELESS is not set # CONFIG_WIMAX is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -471,27 +474,18 @@ CONFIG_MTD_NAND_IDS=y # CONFIG_MTD_NAND_NANDSIM is not set # CONFIG_MTD_NAND_PLATFORM is not set # CONFIG_MTD_NAND_FSL_ELBC is not set -# CONFIG_MTD_NAND_FSL_UPM is not set +CONFIG_MTD_NAND_FSL_UPM=y # CONFIG_MTD_ONENAND is not set # # LPDDR flash memory drivers # # CONFIG_MTD_LPDDR is not set -# CONFIG_MTD_QINFO_PROBE is not set # # UBI - Unsorted block images # -CONFIG_MTD_UBI=m -CONFIG_MTD_UBI_WL_THRESHOLD=4096 -CONFIG_MTD_UBI_BEB_RESERVE=1 -# CONFIG_MTD_UBI_GLUEBI is not set - -# -# UBI debugging options -# -# CONFIG_MTD_UBI_DEBUG is not set +# CONFIG_MTD_UBI is not set CONFIG_OF_DEVICE=y CONFIG_OF_I2C=y # CONFIG_PARPORT is not set @@ -515,69 +509,21 @@ CONFIG_BLK_DEV_RAM_SIZE=32768 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_PHANTOM is not set -# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set # CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set # CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y -CONFIG_IDE=y - -# -# Please see Documentation/ide/ide.txt for help/info on IDE drives -# -CONFIG_IDE_TIMINGS=y -# CONFIG_BLK_DEV_IDE_SATA is not set -CONFIG_IDE_GD=y -CONFIG_IDE_GD_ATA=y -# CONFIG_IDE_GD_ATAPI is not set -# CONFIG_BLK_DEV_IDECD is not set -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_IDE_TASK_IOCTL is not set -CONFIG_IDE_PROC_FS=y - -# -# IDE chipset support/bugfixes -# -# CONFIG_BLK_DEV_PLATFORM is not set -CONFIG_BLK_DEV_IDEDMA_SFF=y - -# -# PCI IDE chipsets support -# -CONFIG_BLK_DEV_IDEPCI=y -CONFIG_IDEPCI_PCIBUS_ORDER=y -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -# CONFIG_BLK_DEV_OPTI621 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -# CONFIG_BLK_DEV_AMD74XX is not set -# CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_JMICRON is not set -# CONFIG_BLK_DEV_SC1200 is not set -# CONFIG_BLK_DEV_PIIX is not set -# CONFIG_BLK_DEV_IT8172 is not set -# CONFIG_BLK_DEV_IT8213 is not set -# CONFIG_BLK_DEV_IT821X is not set -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -# CONFIG_BLK_DEV_PDC202XX_NEW is not set -# CONFIG_BLK_DEV_SVWKS is not set -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SL82C105 is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -CONFIG_BLK_DEV_VIA82CXXX=y -# CONFIG_BLK_DEV_TC86C001 is not set -CONFIG_BLK_DEV_IDEDMA=y +# CONFIG_IDE is not set # # SCSI device support @@ -650,7 +596,7 @@ CONFIG_MII=y CONFIG_NETDEV_1000=y # CONFIG_ACENIC is not set # CONFIG_DL2K is not set -CONFIG_E1000=y +# CONFIG_E1000 is not set # CONFIG_E1000E is not set # CONFIG_IP1000 is not set # CONFIG_IGB is not set @@ -668,6 +614,7 @@ CONFIG_GIANFAR=y # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set # CONFIG_ATL1E is not set +# CONFIG_ATL1C is not set # CONFIG_JME is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set @@ -835,8 +782,6 @@ CONFIG_I2C_MPC=y # Miscellaneous I2C Chip support # # CONFIG_DS1682 is not set -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set @@ -975,26 +920,7 @@ CONFIG_HID=y # Special HID drivers # CONFIG_HID_COMPAT=y -CONFIG_USB_SUPPORT=y -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB_ARCH_HAS_EHCI=y -# CONFIG_USB is not set -# CONFIG_USB_OTG_WHITELIST is not set -# CONFIG_USB_OTG_BLACKLIST_HUB is not set - -# -# Enable Host or Gadget support to see Inventra options -# - -# -# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed; -# -# CONFIG_USB_GADGET is not set - -# -# OTG and related infrastructure -# +# CONFIG_USB_SUPPORT is not set # CONFIG_UWB is not set # CONFIG_MMC is not set # CONFIG_MEMSTICK is not set @@ -1064,16 +990,9 @@ CONFIG_RTC_DRV_DS1307=y # # File systems # -CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set -# CONFIG_EXT2_FS_XIP is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set +# CONFIG_EXT2_FS is not set +# CONFIG_EXT3_FS is not set # CONFIG_EXT4_FS is not set -CONFIG_JBD=y -CONFIG_FS_MBCACHE=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set # CONFIG_FS_POSIX_ACL is not set @@ -1122,8 +1041,17 @@ CONFIG_MISC_FILESYSTEMS=y # CONFIG_BEFS_FS is not set # CONFIG_BFS_FS is not set # CONFIG_EFS_FS is not set -# CONFIG_JFFS2_FS is not set -# CONFIG_UBIFS_FS is not set +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_DEBUG=0 +CONFIG_JFFS2_FS_WRITEBUFFER=y +# CONFIG_JFFS2_FS_WBUF_VERIFY is not set +# CONFIG_JFFS2_SUMMARY is not set +# CONFIG_JFFS2_FS_XATTR is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set +CONFIG_JFFS2_ZLIB=y +# CONFIG_JFFS2_LZO is not set +CONFIG_JFFS2_RTIME=y +# CONFIG_JFFS2_RUBIN is not set # CONFIG_CRAMFS is not set # CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set @@ -1184,6 +1112,8 @@ CONFIG_GENERIC_FIND_LAST_BIT=y CONFIG_CRC32=y # CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=y CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y @@ -1219,6 +1149,7 @@ CONFIG_DEBUG_MUTEXES=y # CONFIG_DEBUG_SPINLOCK_SLEEP is not set # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set # CONFIG_DEBUG_BUGVERBOSE is not set # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set @@ -1236,6 +1167,7 @@ CONFIG_DEBUG_MUTEXES=y # CONFIG_LATENCYTOP is not set CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y CONFIG_HAVE_DYNAMIC_FTRACE=y CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 6d406c5c5de..9696cc36d2d 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -27,7 +27,7 @@ PPC_LONG "1b,4b,2b,4b\n" \ ".previous" \ : "=&r" (oldval), "=&r" (ret) \ - : "b" (uaddr), "i" (-EFAULT), "1" (oparg) \ + : "b" (uaddr), "i" (-EFAULT), "r" (oparg) \ : "cr0", "memory") static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) @@ -47,19 +47,19 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("", ret, oldval, uaddr, oparg); + __futex_atomic_op("mr %1,%4\n", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %1,%0,%1\n", ret, oldval, uaddr, oparg); + __futex_atomic_op("add %1,%0,%4\n", ret, oldval, uaddr, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("or %1,%0,%1\n", ret, oldval, uaddr, oparg); + __futex_atomic_op("or %1,%0,%4\n", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("andc %1,%0,%1\n", ret, oldval, uaddr, oparg); + __futex_atomic_op("andc %1,%0,%4\n", ret, oldval, uaddr, oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("xor %1,%0,%1\n", ret, oldval, uaddr, oparg); + __futex_atomic_op("xor %1,%0,%4\n", ret, oldval, uaddr, oparg); break; default: ret = -ENOSYS; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index cbf15438709..86d2366ab6a 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -52,6 +52,12 @@ */ #define MMU_FTR_NEED_DTLB_SW_LRU ASM_CONST(0x00200000) +/* This indicates that the processor uses the wrong opcode for tlbilx + * instructions. During the ISA 2.06 development the opcode for tlbilx + * changed and some early implementations used to old opcode + */ +#define MMU_FTR_TLBILX_EARLY_OPCODE ASM_CONST(0x00400000) + #ifndef __ASSEMBLY__ #include <asm/cputable.h> diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index 414c50e2e88..94942d60ddf 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -29,7 +29,7 @@ static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma) prop = of_get_property(np, "interrupts", NULL); if (!prop) continue; - if (parport_pc_probe_port(io1, io2, prop[0], autodma, NULL) != NULL) + if (parport_pc_probe_port(io1, io2, prop[0], autodma, NULL, 0) != NULL) count++; } return count; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index f4a4db8d555..ef4da37f3c1 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -43,7 +43,8 @@ #define PPC_INST_STSWI 0x7c0005aa #define PPC_INST_STSWX 0x7c00052a -#define PPC_INST_TLBILX 0x7c000626 +#define PPC_INST_TLBILX 0x7c000024 +#define PPC_INST_TLBILX_EARLY 0x7c000626 #define PPC_INST_WAIT 0x7c00007c /* macros to insert fields into opcodes */ @@ -63,10 +64,18 @@ #define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI) #define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI) #define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_INST_TLBILX | \ - __PPC_T_TLB(t) | __PPC_RA(a) | __PPC_RB(b)) + __PPC_T_TLB(t) | \ + __PPC_RA(a) | __PPC_RB(b)) #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) + +#define PPC_TLBILX_EARLY(t, a, b) stringify_in_c(.long PPC_INST_TLBILX_EARLY | \ + __PPC_T_TLB(t) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_TLBILX_ALL_EARLY(a, b) PPC_TLBILX_EARLY(0, a, b) +#define PPC_TLBILX_PID_EARLY(a, b) PPC_TLBILX_EARLY(1, a, b) +#define PPC_TLBILX_VA_EARLY(a, b) PPC_TLBILX_EARLY(3, a, b) #define PPC_WAIT(w) stringify_in_c(.long PPC_INST_WAIT | \ __PPC_WC(w)) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index cd1b687544f..57db50f4028 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1766,7 +1766,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_E500MC, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, + MMU_FTR_USE_TLBILX | MMU_FTR_TLBILX_EARLY_OPCODE, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 7af72970fae..ad2eb4d34dd 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -125,7 +125,6 @@ static void do_flush_tlb_page_ipi(void *param) void flush_tlb_mm(struct mm_struct *mm) { - cpumask_t cpu_mask; unsigned int pid; preempt_disable(); diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index 788b87c36f7..45fed369834 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -138,7 +138,11 @@ BEGIN_MMU_FTR_SECTION andi. r3,r3,MMUCSR0_TLBFI@l bne 1b MMU_FTR_SECTION_ELSE - PPC_TLBILX_ALL(0,0) + BEGIN_MMU_FTR_SECTION_NESTED(96) + PPC_TLBILX_ALL(0,r3) + MMU_FTR_SECTION_ELSE_NESTED(96) + PPC_TLBILX_ALL_EARLY(0,r3) + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_TLBILX_EARLY_OPCODE, 96) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX) msync isync @@ -151,7 +155,11 @@ BEGIN_MMU_FTR_SECTION wrteei 0 mfspr r4,SPRN_MAS6 /* save MAS6 */ mtspr SPRN_MAS6,r3 + BEGIN_MMU_FTR_SECTION_NESTED(96) PPC_TLBILX_PID(0,0) + MMU_FTR_SECTION_ELSE_NESTED(96) + PPC_TLBILX_PID_EARLY(0,0) + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_TLBILX_EARLY_OPCODE, 96) mtspr SPRN_MAS6,r4 /* restore MAS6 */ wrtee r10 MMU_FTR_SECTION_ELSE @@ -185,7 +193,11 @@ BEGIN_MMU_FTR_SECTION mtspr SPRN_MAS1,r4 tlbwe MMU_FTR_SECTION_ELSE + BEGIN_MMU_FTR_SECTION_NESTED(96) PPC_TLBILX_VA(0,r3) + MMU_FTR_SECTION_ELSE_NESTED(96) + PPC_TLBILX_VA_EARLY(0,r3) + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_TLBILX_EARLY_OPCODE, 96) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX) msync isync diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index fafcaa0e81e..ab69925d579 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -25,6 +25,7 @@ #include <asm/smp.h> #include <asm/system.h> #include <asm/uaccess.h> +#include <asm/firmware.h> #include "plpar_wrappers.h" diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c index 380420f8c40..9a2a6e32f00 100644 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ b/arch/powerpc/platforms/pseries/eeh_driver.c @@ -182,6 +182,8 @@ static void eeh_report_reset(struct pci_dev *dev, void *userdata) if (!driver) return; + dev->error_state = pci_channel_io_normal; + eeh_enable_irq(dev); if (!driver->err_handler || diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 27b70d8a359..aeb3cff95f6 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -176,7 +176,7 @@ static void __appldata_mod_vtimer_wrap(void *p) { struct vtimer_list *timer; u64 expires; } *args = p; - mod_virt_timer(args->timer, args->expires); + mod_virt_timer_periodic(args->timer, args->expires); } #define APPLDATA_ADD_TIMER 0 diff --git a/arch/s390/include/asm/cpuid.h b/arch/s390/include/asm/cpuid.h new file mode 100644 index 00000000000..07836a2e522 --- /dev/null +++ b/arch/s390/include/asm/cpuid.h @@ -0,0 +1,25 @@ +/* + * Copyright IBM Corp. 2000,2009 + * Author(s): Hartmut Penner <hp@de.ibm.com>, + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> + */ + +#ifndef _ASM_S390_CPUID_H_ +#define _ASM_S390_CPUID_H_ + +/* + * CPU type and hardware bug flags. Kept separately for each CPU. + * Members of this structure are referenced in head.S, so think twice + * before touching them. [mj] + */ + +typedef struct +{ + unsigned int version : 8; + unsigned int ident : 24; + unsigned int machine : 16; + unsigned int unused : 16; +} __attribute__ ((packed)) cpuid_t; + +#endif /* _ASM_S390_CPUID_H_ */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c6e674f5fca..54ea39f96ec 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -15,6 +15,7 @@ #define ASM_KVM_HOST_H #include <linux/kvm_host.h> #include <asm/debug.h> +#include <asm/cpuid.h> #define KVM_MAX_VCPUS 64 #define KVM_MEMORY_SLOTS 32 diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index b349f1c7fdf..3aeca492b14 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -66,6 +66,7 @@ #define __LC_USER_EXEC_ASCE 0x02ac #define __LC_CPUID 0x02b0 #define __LC_INT_CLOCK 0x02c8 +#define __LC_MACHINE_FLAGS 0x02d8 #define __LC_IRB 0x0300 #define __LC_PFAULT_INTPARM 0x0080 #define __LC_CPU_TIMER_SAVE_AREA 0x00d8 @@ -110,6 +111,7 @@ #define __LC_CPUID 0x0320 #define __LC_INT_CLOCK 0x0340 #define __LC_VDSO_PER_CPU 0x0350 +#define __LC_MACHINE_FLAGS 0x0358 #define __LC_IRB 0x0380 #define __LC_PASTE 0x03c0 #define __LC_PFAULT_INTPARM 0x11b8 @@ -127,9 +129,9 @@ #ifndef __ASSEMBLY__ -#include <asm/processor.h> +#include <asm/cpuid.h> +#include <asm/ptrace.h> #include <linux/types.h> -#include <asm/sigp.h> void restart_int_handler(void); void ext_int_handler(void); @@ -277,7 +279,8 @@ struct _lowcore __u32 ext_call_fast; /* 0x02c4 */ __u64 int_clock; /* 0x02c8 */ __u64 clock_comparator; /* 0x02d0 */ - __u8 pad_0x02d8[0x0300-0x02d8]; /* 0x02d8 */ + __u32 machine_flags; /* 0x02d8 */ + __u8 pad_0x02dc[0x0300-0x02dc]; /* 0x02dc */ /* Interrupt response block */ __u8 irb[64]; /* 0x0300 */ @@ -381,7 +384,8 @@ struct _lowcore __u64 int_clock; /* 0x0340 */ __u64 clock_comparator; /* 0x0348 */ __u64 vdso_per_cpu_data; /* 0x0350 */ - __u8 pad_0x0358[0x0380-0x0358]; /* 0x0358 */ + __u64 machine_flags; /* 0x0358 */ + __u8 pad_0x0360[0x0380-0x0360]; /* 0x0360 */ /* Interrupt response block. */ __u8 irb[64]; /* 0x0380 */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 61862b3ac79..c139fa7b8e8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -14,7 +14,10 @@ #define __ASM_S390_PROCESSOR_H #include <linux/linkage.h> +#include <asm/cpuid.h> +#include <asm/page.h> #include <asm/ptrace.h> +#include <asm/setup.h> #ifdef __KERNEL__ /* @@ -23,20 +26,6 @@ */ #define current_text_addr() ({ void *pc; asm("basr %0,0" : "=a" (pc)); pc; }) -/* - * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head.S, so think twice - * before touching them. [mj] - */ - -typedef struct -{ - unsigned int version : 8; - unsigned int ident : 24; - unsigned int machine : 16; - unsigned int unused : 16; -} __attribute__ ((packed)) cpuid_t; - static inline void get_cpu_id(cpuid_t *ptr) { asm volatile("stidp 0(%1)" : "=m" (*ptr) : "a" (ptr)); diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index f1b051630c5..539263fc9ab 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -313,8 +313,6 @@ typedef struct #ifdef __KERNEL__ -#include <asm/setup.h> -#include <asm/page.h> /* * The pt_regs struct defines the way the registers are stored on diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index e8bd6ac22c9..38b0fc221ed 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -14,6 +14,7 @@ #ifdef __KERNEL__ +#include <asm/lowcore.h> #include <asm/types.h> #define PARMAREA 0x10400 @@ -63,7 +64,6 @@ extern unsigned int s390_noexec; /* * Machine features detected in head.S */ -extern unsigned long machine_flags; #define MACHINE_FLAG_VM (1UL << 0) #define MACHINE_FLAG_IEEE (1UL << 1) @@ -77,28 +77,28 @@ extern unsigned long machine_flags; #define MACHINE_FLAG_HPAGE (1UL << 10) #define MACHINE_FLAG_PFMF (1UL << 11) -#define MACHINE_IS_VM (machine_flags & MACHINE_FLAG_VM) -#define MACHINE_IS_KVM (machine_flags & MACHINE_FLAG_KVM) -#define MACHINE_HAS_DIAG9C (machine_flags & MACHINE_FLAG_DIAG9C) +#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) +#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) +#define MACHINE_HAS_DIAG9C (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C) #ifndef __s390x__ -#define MACHINE_HAS_IEEE (machine_flags & MACHINE_FLAG_IEEE) -#define MACHINE_HAS_CSP (machine_flags & MACHINE_FLAG_CSP) +#define MACHINE_HAS_IEEE (S390_lowcore.machine_flags & MACHINE_FLAG_IEEE) +#define MACHINE_HAS_CSP (S390_lowcore.machine_flags & MACHINE_FLAG_CSP) #define MACHINE_HAS_IDTE (0) #define MACHINE_HAS_DIAG44 (1) -#define MACHINE_HAS_MVPG (machine_flags & MACHINE_FLAG_MVPG) +#define MACHINE_HAS_MVPG (S390_lowcore.machine_flags & MACHINE_FLAG_MVPG) #define MACHINE_HAS_MVCOS (0) #define MACHINE_HAS_HPAGE (0) #define MACHINE_HAS_PFMF (0) #else /* __s390x__ */ #define MACHINE_HAS_IEEE (1) #define MACHINE_HAS_CSP (1) -#define MACHINE_HAS_IDTE (machine_flags & MACHINE_FLAG_IDTE) -#define MACHINE_HAS_DIAG44 (machine_flags & MACHINE_FLAG_DIAG44) +#define MACHINE_HAS_IDTE (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE) +#define MACHINE_HAS_DIAG44 (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44) #define MACHINE_HAS_MVPG (1) -#define MACHINE_HAS_MVCOS (machine_flags & MACHINE_FLAG_MVCOS) -#define MACHINE_HAS_HPAGE (machine_flags & MACHINE_FLAG_HPAGE) -#define MACHINE_HAS_PFMF (machine_flags & MACHINE_FLAG_PFMF) +#define MACHINE_HAS_MVCOS (S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS) +#define MACHINE_HAS_HPAGE (S390_lowcore.machine_flags & MACHINE_FLAG_HPAGE) +#define MACHINE_HAS_PFMF (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF) #endif /* __s390x__ */ #define ZFCPDUMP_HSA_SIZE (32UL<<20) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index c544aa52453..461f2abd2e6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -31,8 +31,9 @@ #define ASYNC_SIZE (PAGE_SIZE << ASYNC_ORDER) #ifndef __ASSEMBLY__ -#include <asm/processor.h> #include <asm/lowcore.h> +#include <asm/page.h> +#include <asm/processor.h> /* * low level task data that entry.S needs immediate access to diff --git a/arch/s390/include/asm/timer.h b/arch/s390/include/asm/timer.h index e4bcab739c1..814243cafdf 100644 --- a/arch/s390/include/asm/timer.h +++ b/arch/s390/include/asm/timer.h @@ -41,6 +41,7 @@ extern void init_virt_timer(struct vtimer_list *timer); extern void add_virt_timer(void *new); extern void add_virt_timer_periodic(void *new); extern int mod_virt_timer(struct vtimer_list *timer, __u64 expires); +extern int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires); extern int del_virt_timer(struct vtimer_list *timer); extern void init_cpu_vtimer(void); diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index d744c3d62de..cc21e3e20fd 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -11,6 +11,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H +/* The value of the TOD clock for 1.1.1970. */ +#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL + /* Inline functions for clock register access. */ static inline int set_clock(__u64 time) { @@ -85,4 +88,6 @@ int get_sync_clock(unsigned long long *clock); void init_cpu_timer(void); unsigned long long monotonic_clock(void); +extern u64 sched_clock_base_cc; + #endif diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index c8ad350d144..f0f19e6ace6 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -265,7 +265,9 @@ #define __NR_pipe2 325 #define __NR_dup3 326 #define __NR_epoll_create1 327 -#define NR_syscalls 328 +#define __NR_preadv 328 +#define __NR_pwritev 329 +#define NR_syscalls 330 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 67a60016bab..fa9905ce7d0 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -27,6 +27,8 @@ int main(void) DEFINE(__TI_flags, offsetof(struct thread_info, flags)); DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); + DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); + DEFINE(__TI_system_timer, offsetof(struct thread_info, system_timer)); BLANK(); DEFINE(__PT_ARGS, offsetof(struct pt_regs, args)); DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 87cf5a79a35..fb38af6316b 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1805,3 +1805,21 @@ compat_sys_keyctl_wrapper: llgfr %r5,%r5 # u32 llgfr %r6,%r6 # u32 jg compat_sys_keyctl # branch to system call + + .globl compat_sys_preadv_wrapper +compat_sys_preadv_wrapper: + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_preadv # branch to system call + + .globl compat_sys_pwritev_wrapper +compat_sys_pwritev_wrapper: + llgfr %r2,%r2 # unsigned long + llgtr %r3,%r3 # compat_iovec * + llgfr %r4,%r4 # unsigned long + llgfr %r5,%r5 # u32 + llgfr %r6,%r6 # u32 + jg compat_sys_pwritev # branch to system call diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 4d221c81c84..cf09948faad 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -34,8 +34,25 @@ char kernel_nss_name[NSS_NAME_SIZE + 1]; +static unsigned long machine_flags; + static void __init setup_boot_command_line(void); +/* + * Get the TOD clock running. + */ +static void __init reset_tod_clock(void) +{ + u64 time; + + if (store_clock(&time) == 0) + return; + /* TOD clock not running. Set the clock to Unix Epoch. */ + if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) + disabled_wait(0); + + sched_clock_base_cc = TOD_UNIX_EPOCH; +} #ifdef CONFIG_SHARED_KERNEL int __init savesys_ipl_nss(char *cmd, const int cmdlen); @@ -370,6 +387,7 @@ static void __init setup_boot_command_line(void) */ void __init startup_init(void) { + reset_tod_clock(); ipl_save_parameters(); rescue_initrd(); clear_bss_section(); @@ -391,5 +409,6 @@ void __init startup_init(void) setup_hpage(); sclp_facilities_detect(); detect_memory_layout(memory_chunk); + S390_lowcore.machine_flags = machine_flags; lockdep_on(); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 1268aa2991b..f3e27593421 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -837,16 +837,29 @@ mcck_return: __CPUINIT .globl restart_int_handler restart_int_handler: + basr %r1,0 +restart_base: + spt restart_vtime-restart_base(%r1) + stck __LC_LAST_UPDATE_CLOCK + mvc __LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1) + mvc __LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1) l %r15,__LC_SAVE_AREA+60 # load ksp lctl %c0,%c15,__LC_CREGS_SAVE_AREA # get new ctl regs lam %a0,%a15,__LC_AREGS_SAVE_AREA lm %r6,%r15,__SF_GPRS(%r15) # load registers from clone + l %r1,__LC_THREAD_INFO + mvc __LC_USER_TIMER(8),__TI_user_timer(%r1) + mvc __LC_SYSTEM_TIMER(8),__TI_system_timer(%r1) + xc __LC_STEAL_TIMER(8),__LC_STEAL_TIMER stosm __SF_EMPTY(%r15),0x04 # now we can turn dat on basr %r14,0 l %r14,restart_addr-.(%r14) br %r14 # branch to start_secondary restart_addr: .long start_secondary + .align 8 +restart_vtime: + .long 0x7fffffff,0xffffffff .previous #else /* diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index c6fbde13971..84a105838e0 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -831,14 +831,27 @@ mcck_return: __CPUINIT .globl restart_int_handler restart_int_handler: + basr %r1,0 +restart_base: + spt restart_vtime-restart_base(%r1) + stck __LC_LAST_UPDATE_CLOCK + mvc __LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1) + mvc __LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1) lg %r15,__LC_SAVE_AREA+120 # load ksp lghi %r10,__LC_CREGS_SAVE_AREA lctlg %c0,%c15,0(%r10) # get new ctl regs lghi %r10,__LC_AREGS_SAVE_AREA lam %a0,%a15,0(%r10) lmg %r6,%r15,__SF_GPRS(%r15) # load registers from clone + lg %r1,__LC_THREAD_INFO + mvc __LC_USER_TIMER(8),__TI_user_timer(%r1) + mvc __LC_SYSTEM_TIMER(8),__TI_system_timer(%r1) + xc __LC_STEAL_TIMER(8),__LC_STEAL_TIMER stosm __SF_EMPTY(%r15),0x04 # now we can turn dat on jg start_secondary + .align 8 +restart_vtime: + .long 0x7fffffff,0xffffffff .previous #else /* diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 1046c2c9f8d..bba14494ee0 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -471,7 +471,12 @@ startup:basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore xc 0x300(256),0x300 - + l %r1,5f-.LPG0(%r13) + stck 0(%r1) + spt 6f-.LPG0(%r13) + mvc __LC_LAST_UPDATE_CLOCK(8),0(%r1) + mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13) + mvc __LC_EXIT_TIMER(8),5f-.LPG0(%r13) #ifndef CONFIG_MARCH_G5 # check processor version against MARCH_{G5,Z900,Z990,Z9_109,Z10} stidp __LC_CPUID # store cpuid @@ -496,9 +501,13 @@ startup:basr %r13,0 # get base brct %r0,0b #endif - l %r13,0f-.LPG0(%r13) + l %r13,4f-.LPG0(%r13) b 0(%r13) -0: .long startup_continue + .align 4 +4: .long startup_continue +5: .long sched_clock_base_cc + .align 8 +6: .long 0x7fffffff,0xffffffff # # params at 10400 (setup.h) diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 4bfdc421d7e..28cf196ba77 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/errno.h> +#include <linux/hardirq.h> #include <linux/time.h> #include <linux/module.h> #include <asm/lowcore.h> @@ -253,7 +254,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) struct mci *mci; int umode; - lockdep_off(); + nmi_enter(); s390_idle_check(); mci = (struct mci *) &S390_lowcore.mcck_interruption_code; @@ -363,7 +364,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->warning = 1; set_thread_flag(TIF_MCCK_PENDING); } - lockdep_on(); + nmi_exit(); } static int __init machine_check_init(void) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 06201b93cbb..7402b6a39ea 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -82,9 +82,6 @@ EXPORT_SYMBOL(console_devno); unsigned int console_irq = -1; EXPORT_SYMBOL(console_irq); -unsigned long machine_flags; -EXPORT_SYMBOL(machine_flags); - unsigned long elf_hwcap = 0; char elf_platform[ELF_PLATFORM_SIZE]; @@ -426,6 +423,7 @@ setup_lowcore(void) __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; + lc->machine_flags = S390_lowcore.machine_flags; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { lc->extended_save_area_addr = (__u32) @@ -436,6 +434,14 @@ setup_lowcore(void) #else lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0]; #endif + lc->sync_enter_timer = S390_lowcore.sync_enter_timer; + lc->async_enter_timer = S390_lowcore.async_enter_timer; + lc->exit_timer = S390_lowcore.exit_timer; + lc->user_timer = S390_lowcore.user_timer; + lc->system_timer = S390_lowcore.system_timer; + lc->steal_timer = S390_lowcore.steal_timer; + lc->last_update_timer = S390_lowcore.last_update_timer; + lc->last_update_clock = S390_lowcore.last_update_clock; set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 006ed5016eb..a985a3ba440 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -571,6 +571,7 @@ int __cpuinit __cpu_up(unsigned int cpu) cpu_lowcore->current_task = (unsigned long) idle; cpu_lowcore->cpu_nr = cpu; cpu_lowcore->kernel_asce = S390_lowcore.kernel_asce; + cpu_lowcore->machine_flags = S390_lowcore.machine_flags; eieio(); while (signal_processor(cpu, sigp_restart) == sigp_busy) @@ -590,7 +591,8 @@ static int __init setup_possible_cpus(char *s) int pcpus, cpu; pcpus = simple_strtoul(s, NULL, 0); - for (cpu = 0; cpu < pcpus && cpu < nr_cpu_ids; cpu++) + init_cpu_possible(cpumask_of(0)); + for (cpu = 1; cpu < pcpus && cpu < nr_cpu_ids; cpu++) set_cpu_possible(cpu, true); return 0; } diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index fe5b25a988a..2c7739fe70b 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -336,3 +336,5 @@ SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper) SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */ SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper) SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper) +SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv_wrapper) +SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index f72d41068dc..6ded50dfa75 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -52,9 +52,6 @@ #define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) #define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12) -/* The value of the TOD clock for 1.1.1970. */ -#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL - /* * Create a small time difference between the timer interrupts * on the different cpus to avoid lock contention. @@ -63,9 +60,10 @@ #define TICK_SIZE tick +u64 sched_clock_base_cc = -1; /* Force to data section. */ + static ext_int_info_t ext_int_info_cc; static ext_int_info_t ext_int_etr_cc; -static u64 sched_clock_base_cc; static DEFINE_PER_CPU(struct clock_event_device, comparators); @@ -195,22 +193,12 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -/* - * Get the TOD clock running. - */ -static u64 __init reset_tod_clock(void) +unsigned long read_persistent_clock(void) { - u64 time; - - etr_reset(); - stp_reset(); - if (store_clock(&time) == 0) - return time; - /* TOD clock not running. Set the clock to Unix Epoch. */ - if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) - panic("TOD clock not operational."); + struct timespec ts; - return TOD_UNIX_EPOCH; + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts); + return ts.tv_sec; } static cycle_t read_tod_clock(void) @@ -265,12 +253,13 @@ void update_vsyscall_tz(void) */ void __init time_init(void) { - sched_clock_base_cc = reset_tod_clock(); + struct timespec ts; + unsigned long flags; + cycle_t now; - /* set xtime */ - tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &xtime); - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); + /* Reset time synchronization interfaces. */ + etr_reset(); + stp_reset(); /* request the clock comparator external interrupt */ if (register_early_external_interrupt(0x1004, @@ -278,17 +267,38 @@ void __init time_init(void) &ext_int_info_cc) != 0) panic("Couldn't request external interrupt 0x1004"); - if (clocksource_register(&clocksource_tod) != 0) - panic("Could not register TOD clock source"); - /* request the timing alert external interrupt */ if (register_early_external_interrupt(0x1406, timing_alert_interrupt, &ext_int_etr_cc) != 0) panic("Couldn't request external interrupt 0x1406"); + if (clocksource_register(&clocksource_tod) != 0) + panic("Could not register TOD clock source"); + + /* + * The TOD clock is an accurate clock. The xtime should be + * initialized in a way that the difference between TOD and + * xtime is reasonably small. Too bad that timekeeping_init + * sets xtime.tv_nsec to zero. In addition the clock source + * change from the jiffies clock source to the TOD clock + * source add another error of up to 1/HZ second. The same + * function sets wall_to_monotonic to a value that is too + * small for /proc/uptime to be accurate. + * Reset xtime and wall_to_monotonic to sane values. + */ + write_seqlock_irqsave(&xtime_lock, flags); + now = get_clock(); + tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime); + clocksource_tod.cycle_last = now; + clocksource_tod.raw_time = xtime; + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts); + set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec); + write_sequnlock_irqrestore(&xtime_lock, flags); + /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); + /* Enable cpu timer interrupts on the boot cpu. */ vtime_init(); } @@ -1423,6 +1433,7 @@ static void *stp_page; static void stp_work_fn(struct work_struct *work); static DEFINE_MUTEX(stp_work_mutex); static DECLARE_WORK(stp_work, stp_work_fn); +static struct timer_list stp_timer; static int __init early_parse_stp(char *p) { @@ -1454,10 +1465,16 @@ static void __init stp_reset(void) } } +static void stp_timeout(unsigned long dummy) +{ + queue_work(time_sync_wq, &stp_work); +} + static int __init stp_init(void) { if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) return 0; + setup_timer(&stp_timer, stp_timeout, 0UL); time_init_wq(); if (!stp_online) return 0; @@ -1565,6 +1582,7 @@ static void stp_work_fn(struct work_struct *work) if (!stp_online) { chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000); + del_timer_sync(&stp_timer); goto out_unlock; } @@ -1586,6 +1604,13 @@ static void stp_work_fn(struct work_struct *work) stop_machine(stp_sync_clock, &stp_sync, &cpu_online_map); put_online_cpus(); + if (!check_sync_clock()) + /* + * There is a usable clock but the synchonization failed. + * Retry after a second. + */ + mod_timer(&stp_timer, jiffies + HZ); + out_unlock: mutex_unlock(&stp_work_mutex); } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index ecf0304e61c..38ea92ff04f 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -134,6 +134,8 @@ void vtime_start_cpu(void) /* Account time spent with enabled wait psw loaded as idle time. */ idle_time = S390_lowcore.int_clock - idle->idle_enter; account_idle_time(idle_time); + S390_lowcore.steal_timer += + idle->idle_enter - S390_lowcore.last_update_clock; S390_lowcore.last_update_clock = S390_lowcore.int_clock; /* Account system time spent going idle. */ @@ -425,17 +427,7 @@ void add_virt_timer_periodic(void *new) } EXPORT_SYMBOL(add_virt_timer_periodic); -/* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on, e.g. by smp_call_function_single() - * - * The original mod_timer adds the timer if it is not pending. For - * compatibility we do the same. The timer will be added on the current - * CPU as a oneshot timer. - * - * returns whether it has modified a pending timer (1) or not (0) - */ -int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) { struct vtimer_queue *vq; unsigned long flags; @@ -444,39 +436,35 @@ int mod_virt_timer(struct vtimer_list *timer, __u64 expires) BUG_ON(!timer->function); BUG_ON(!expires || expires > VTIMER_MAX_SLICE); - /* - * This is a common optimization triggered by the - * networking code - if the timer is re-modified - * to be the same thing then just return: - */ if (timer->expires == expires && vtimer_pending(timer)) return 1; cpu = get_cpu(); vq = &per_cpu(virt_cpu_timer, cpu); - /* check if we run on the right CPU */ - BUG_ON(timer->cpu != cpu); - /* disable interrupts before test if timer is pending */ spin_lock_irqsave(&vq->lock, flags); /* if timer isn't pending add it on the current CPU */ if (!vtimer_pending(timer)) { spin_unlock_irqrestore(&vq->lock, flags); - /* we do not activate an interval timer with mod_virt_timer */ - timer->interval = 0; + + if (periodic) + timer->interval = expires; + else + timer->interval = 0; timer->expires = expires; timer->cpu = cpu; internal_add_vtimer(timer); return 0; } + /* check if we run on the right CPU */ + BUG_ON(timer->cpu != cpu); + list_del_init(&timer->entry); timer->expires = expires; - - /* also change the interval if we have an interval timer */ - if (timer->interval) + if (periodic) timer->interval = expires; /* the timer can't expire anymore so we can release the lock */ @@ -484,9 +472,32 @@ int mod_virt_timer(struct vtimer_list *timer, __u64 expires) internal_add_vtimer(timer); return 1; } + +/* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 0); +} EXPORT_SYMBOL(mod_virt_timer); /* + * If we change a pending timer the function must be called on the CPU + * where the timer is running on. + * + * returns whether it has modified a pending timer (1) or not (0) + */ +int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires) +{ + return __mod_vtimer(timer, expires, 1); +} +EXPORT_SYMBOL(mod_virt_timer_periodic); + +/* * delete a virtual timer * * returns whether the deleted timer was pending (1) or not (0) @@ -516,16 +527,8 @@ EXPORT_SYMBOL(del_virt_timer); */ void init_cpu_vtimer(void) { - struct thread_info *ti = current_thread_info(); struct vtimer_queue *vq; - S390_lowcore.user_timer = ti->user_timer; - S390_lowcore.system_timer = ti->system_timer; - - /* kick the virtual timer */ - asm volatile ("STCK %0" : "=m" (S390_lowcore.last_update_clock)); - asm volatile ("STPT %0" : "=m" (S390_lowcore.last_update_timer)); - /* initialize per cpu vtimer structure */ vq = &__get_cpu_var(virt_cpu_timer); INIT_LIST_HEAD(&vq->list); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5e4babecf93..e7390dd0283 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -14,6 +14,7 @@ config SUPERH select HAVE_GENERIC_DMA_COHERENT select HAVE_IOREMAP_PROT if MMU select HAVE_ARCH_TRACEHOOK + select HAVE_DMA_API_DEBUG help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast @@ -21,7 +22,7 @@ config SUPERH <http://www.linux-sh.org/>. config SUPERH32 - def_bool !SUPERH64 + def_bool ARCH = "sh" select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_FUNCTION_TRACER @@ -31,7 +32,7 @@ config SUPERH32 select ARCH_HIBERNATION_POSSIBLE if MMU config SUPERH64 - def_bool y if CPU_SH5 + def_bool ARCH = "sh64" config ARCH_DEFCONFIG string @@ -187,6 +188,8 @@ config ARCH_SHMOBILE bool select ARCH_SUSPEND_POSSIBLE +if SUPERH32 + choice prompt "Processor sub-type selection" @@ -408,6 +411,15 @@ config CPU_SUBTYPE_SH7366 select SYS_SUPPORTS_NUMA select SYS_SUPPORTS_CMT +endchoice + +endif + +if SUPERH64 + +choice + prompt "Processor sub-type selection" + # SH-5 Processor Support config CPU_SUBTYPE_SH5_101 @@ -420,6 +432,8 @@ config CPU_SUBTYPE_SH5_103 endchoice +endif + source "arch/sh/mm/Kconfig" source "arch/sh/Kconfig.cpu" diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index 912458f666e..39e46919df1 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -349,6 +349,7 @@ static int ov7725_power(struct device *dev, int mode) static struct ov772x_camera_info ov7725_info = { .buswidth = SOCAM_DATAWIDTH_8, .flags = OV772X_FLAG_VFLIP | OV772X_FLAG_HFLIP, + .edgectrl = OV772X_AUTO_EDGECTRL(0xf, 0), .link = { .power = ov7725_power, }, diff --git a/arch/sh/boards/board-urquell.c b/arch/sh/boards/board-urquell.c index 8367d1d789c..beb88c4da2c 100644 --- a/arch/sh/boards/board-urquell.c +++ b/arch/sh/boards/board-urquell.c @@ -2,6 +2,8 @@ * Renesas Technology Corp. SH7786 Urquell Support. * * Copyright (C) 2008 Kuninori Morimoto <morimoto.kuninori@renesas.com> + * + * Based on board-sh7785lcr.c * Copyright (C) 2008 Yoshihiro Shimoda * * This file is subject to the terms and conditions of the GNU General Public @@ -21,6 +23,32 @@ #include <asm/heartbeat.h> #include <asm/sizes.h> +/* + * bit 1234 5678 + *---------------------------- + * SW1 0101 0010 -> Pck 33MHz version + * (1101 0010) Pck 66MHz version + * SW2 0x1x xxxx -> little endian + * 29bit mode + * SW47 0001 1000 -> CS0 : on-board flash + * CS1 : SRAM, registers, LAN, PCMCIA + * 38400 bps for SCIF1 + * + * Address + * 0x00000000 - 0x04000000 (CS0) Nor Flash + * 0x04000000 - 0x04200000 (CS1) SRAM + * 0x05000000 - 0x05800000 (CS1) on board register + * 0x05800000 - 0x06000000 (CS1) LAN91C111 + * 0x06000000 - 0x06400000 (CS1) PCMCIA + * 0x08000000 - 0x10000000 (CS2-CS3) DDR3 + * 0x10000000 - 0x14000000 (CS4) PCIe + * 0x14000000 - 0x14800000 (CS5) Core0 LRAM/URAM + * 0x14800000 - 0x15000000 (CS5) Core1 LRAM/URAM + * 0x18000000 - 0x1C000000 (CS6) ATA/NAND-Flash + * 0x1C000000 - (CS7) SH7786 Control register + */ + +/* HeartBeat */ static struct resource heartbeat_resources[] = { [0] = { .start = BOARDREG(SLEDR), @@ -43,6 +71,7 @@ static struct platform_device heartbeat_device = { .resource = heartbeat_resources, }; +/* LAN91C111 */ static struct smc91x_platdata smc91x_info = { .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, }; @@ -69,6 +98,7 @@ static struct platform_device smc91x_eth_device = { }, }; +/* Nor Flash */ static struct mtd_partition nor_flash_partitions[] = { { .name = "loader", diff --git a/arch/sh/drivers/pci/ops-sh7785lcr.c b/arch/sh/drivers/pci/ops-sh7785lcr.c index e8b7446a7c2..fb0869f0bef 100644 --- a/arch/sh/drivers/pci/ops-sh7785lcr.c +++ b/arch/sh/drivers/pci/ops-sh7785lcr.c @@ -48,8 +48,13 @@ EXPORT_SYMBOL(board_pci_channels); static struct sh4_pci_address_map sh7785_pci_map = { .window0 = { +#if defined(CONFIG_32BIT) + .base = SH7780_32BIT_DDR_BASE_ADDR, + .size = 0x40000000, +#else .base = SH7780_CS0_BASE_ADDR, .size = 0x20000000, +#endif }, .flags = SH4_PCIC_NO_RESET, diff --git a/arch/sh/drivers/pci/pci-sh7780.h b/arch/sh/drivers/pci/pci-sh7780.h index 97b2c98f05c..93adc7119b7 100644 --- a/arch/sh/drivers/pci/pci-sh7780.h +++ b/arch/sh/drivers/pci/pci-sh7780.h @@ -104,6 +104,8 @@ #define SH7780_CS5_BASE_ADDR (SH7780_CS4_BASE_ADDR + SH7780_MEM_REGION_SIZE) #define SH7780_CS6_BASE_ADDR (SH7780_CS5_BASE_ADDR + SH7780_MEM_REGION_SIZE) +#define SH7780_32BIT_DDR_BASE_ADDR 0x40000000 + struct sh4_pci_address_map; /* arch/sh/drivers/pci/pci-sh7780.c */ diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index e36c7b87086..0d6ac7a1db4 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/init.h> +#include <linux/dma-debug.h> #include <asm/io.h> static int __init pcibios_init(void) @@ -43,6 +44,8 @@ static int __init pcibios_init(void) pci_fixup_irqs(pci_common_swizzle, pcibios_map_platform_irq); + dma_debug_add_bus(&pci_bus_type); + return 0; } subsys_initcall(pcibios_init); diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h index 627315ecdb5..ea9d4f41c9d 100644 --- a/arch/sh/include/asm/dma-mapping.h +++ b/arch/sh/include/asm/dma-mapping.h @@ -3,6 +3,7 @@ #include <linux/mm.h> #include <linux/scatterlist.h> +#include <linux/dma-debug.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <asm-generic/dma-coherent.h> @@ -38,16 +39,26 @@ static inline dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir) { + dma_addr_t addr = virt_to_phys(ptr); + #if defined(CONFIG_PCI) && !defined(CONFIG_SH_PCIDMA_NONCOHERENT) if (dev->bus == &pci_bus_type) - return virt_to_phys(ptr); + return addr; #endif dma_cache_sync(dev, ptr, size, dir); - return virt_to_phys(ptr); + debug_dma_map_page(dev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, addr, true); + + return addr; } -#define dma_unmap_single(dev, addr, size, dir) do { } while (0) +static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + debug_dma_unmap_page(dev, addr, size, dir, true); +} static inline int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) @@ -59,12 +70,19 @@ static inline int dma_map_sg(struct device *dev, struct scatterlist *sg, dma_cache_sync(dev, sg_virt(&sg[i]), sg[i].length, dir); #endif sg[i].dma_address = sg_phys(&sg[i]); + sg[i].dma_length = sg[i].length; } + debug_dma_map_sg(dev, sg, nents, i, dir); + return nents; } -#define dma_unmap_sg(dev, sg, nents, dir) do { } while (0) +static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + debug_dma_unmap_sg(dev, sg, nents, dir); +} static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, @@ -111,6 +129,7 @@ static inline void dma_sync_sg(struct device *dev, struct scatterlist *sg, dma_cache_sync(dev, sg_virt(&sg[i]), sg[i].length, dir); #endif sg[i].dma_address = sg_phys(&sg[i]); + sg[i].dma_length = sg[i].length; } } @@ -119,6 +138,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev, enum dma_data_direction dir) { dma_sync_single(dev, dma_handle, size, dir); + debug_dma_sync_single_for_cpu(dev, dma_handle, size, dir); } static inline void dma_sync_single_for_device(struct device *dev, @@ -127,6 +147,7 @@ static inline void dma_sync_single_for_device(struct device *dev, enum dma_data_direction dir) { dma_sync_single(dev, dma_handle, size, dir); + debug_dma_sync_single_for_device(dev, dma_handle, size, dir); } static inline void dma_sync_single_range_for_cpu(struct device *dev, @@ -136,6 +157,8 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev, enum dma_data_direction direction) { dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction); + debug_dma_sync_single_range_for_cpu(dev, dma_handle, + offset, size, direction); } static inline void dma_sync_single_range_for_device(struct device *dev, @@ -145,6 +168,8 @@ static inline void dma_sync_single_range_for_device(struct device *dev, enum dma_data_direction direction) { dma_sync_single_for_device(dev, dma_handle+offset, size, direction); + debug_dma_sync_single_range_for_device(dev, dma_handle, + offset, size, direction); } @@ -153,6 +178,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev, enum dma_data_direction dir) { dma_sync_sg(dev, sg, nelems, dir); + debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); } static inline void dma_sync_sg_for_device(struct device *dev, @@ -160,9 +186,9 @@ static inline void dma_sync_sg_for_device(struct device *dev, enum dma_data_direction dir) { dma_sync_sg(dev, sg, nelems, dir); + debug_dma_sync_sg_for_device(dev, sg, nelems, dir); } - static inline int dma_get_cache_alignment(void) { /* diff --git a/arch/sh/include/asm/scatterlist.h b/arch/sh/include/asm/scatterlist.h index 2084d037369..c693d268a41 100644 --- a/arch/sh/include/asm/scatterlist.h +++ b/arch/sh/include/asm/scatterlist.h @@ -5,12 +5,13 @@ struct scatterlist { #ifdef CONFIG_DEBUG_SG - unsigned long sg_magic; + unsigned long sg_magic; #endif - unsigned long page_link; - unsigned int offset;/* for highmem, page offset */ - dma_addr_t dma_address; - unsigned int length; + unsigned long page_link; + unsigned int offset; /* for highmem, page offset */ + unsigned int length; + dma_addr_t dma_address; + unsigned int dma_length; }; #define ISA_DMA_THRESHOLD PHYS_ADDR_MASK diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h index a3f23954589..8489a0905a8 100644 --- a/arch/sh/include/asm/topology.h +++ b/arch/sh/include/asm/topology.h @@ -37,8 +37,11 @@ #define pcibus_to_node(bus) ((void)(bus), -1) #define pcibus_to_cpumask(bus) (pcibus_to_node(bus) == -1 ? \ CPU_MASK_ALL : \ - node_to_cpumask(pcibus_to_node(bus)) \ - ) + node_to_cpumask(pcibus_to_node(bus))) +#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \ + CPU_MASK_ALL_PTR : \ + cpumask_of_node(pcibus_to_node(bus))) + #endif #include <asm-generic/topology.h> diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index d52c000cf92..2efb819e2db 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -341,8 +341,10 @@ #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334 -#define NR_syscalls 333 +#define NR_syscalls 335 #ifdef __KERNEL__ diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h index 7c54e91753c..6eb9d2934c0 100644 --- a/arch/sh/include/asm/unistd_64.h +++ b/arch/sh/include/asm/unistd_64.h @@ -381,10 +381,12 @@ #define __NR_dup3 358 #define __NR_pipe2 359 #define __NR_inotify_init1 360 +#define __NR_preadv 361 +#define __NR_pwritev 362 #ifdef __KERNEL__ -#define NR_syscalls 361 +#define NR_syscalls 363 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c index 5a47e1cf442..90e8cfff55f 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c @@ -143,14 +143,14 @@ static void __init sh7786_usb_setup(void) * Set the PHY and PLL enable bit */ __raw_writel(PHY_ENB | PLL_ENB, USBPCTL1); - while (i-- && - ((__raw_readl(USBST) & ACT_PLL_STATUS) != ACT_PLL_STATUS)) + while (i--) { + if (ACT_PLL_STATUS == (__raw_readl(USBST) & ACT_PLL_STATUS)) { + /* Set the PHY RST bit */ + __raw_writel(PHY_ENB | PLL_ENB | PHY_RST, USBPCTL1); + printk(KERN_INFO "sh7786 usb setup done\n"); + break; + } cpu_relax(); - - if (i) { - /* Set the PHY RST bit */ - __raw_writel(PHY_ENB | PLL_ENB | PHY_RST, USBPCTL1); - printk(KERN_INFO "sh7786 usb setup done\n"); } } diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S index e67c1733e1b..05202edd8e2 100644 --- a/arch/sh/kernel/syscalls_32.S +++ b/arch/sh/kernel/syscalls_32.S @@ -349,3 +349,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_writev diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S index 557cb91f5ca..a083609f928 100644 --- a/arch/sh/kernel/syscalls_64.S +++ b/arch/sh/kernel/syscalls_64.S @@ -387,3 +387,5 @@ sys_call_table: .long sys_dup3 .long sys_pipe2 .long sys_inotify_init1 /* 360 */ + .long sys_preadv + .long sys_pwritev diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index edcd5fbf965..e098ec158dd 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -10,11 +10,22 @@ * for more details. */ #include <linux/mm.h> +#include <linux/init.h> #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/dma-debug.h> +#include <linux/io.h> #include <asm/cacheflush.h> #include <asm/addrspace.h> -#include <asm/io.h> + +#define PREALLOC_DMA_DEBUG_ENTRIES 4096 + +static int __init dma_init(void) +{ + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + return 0; +} +fs_initcall(dma_init); void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) @@ -45,6 +56,9 @@ void *dma_alloc_coherent(struct device *dev, size_t size, split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order); *dma_handle = virt_to_phys(ret); + + debug_dma_alloc_coherent(dev, size, *dma_handle, ret_nocache); + return ret_nocache; } EXPORT_SYMBOL(dma_alloc_coherent); @@ -56,12 +70,15 @@ void dma_free_coherent(struct device *dev, size_t size, unsigned long pfn = dma_handle >> PAGE_SHIFT; int k; - if (!dma_release_from_coherent(dev, order, vaddr)) { - WARN_ON(irqs_disabled()); /* for portability */ - for (k = 0; k < (1 << order); k++) - __free_pages(pfn_to_page(pfn + k), 0); - iounmap(vaddr); - } + WARN_ON(irqs_disabled()); /* for portability */ + + if (dma_release_from_coherent(dev, order, vaddr)) + return; + + debug_dma_free_coherent(dev, size, vaddr, dma_handle); + for (k = 0; k < (1 << order); k++) + __free_pages(pfn_to_page(pfn + k), 0); + iounmap(vaddr); } EXPORT_SYMBOL(dma_free_coherent); diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index ce465975a6a..bb91b1248cd 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -15,6 +15,8 @@ #ifdef __KERNEL__ +#include <asm/system.h> + #define ATOMIC_INIT(i) { (i) } extern int __atomic_add_return(int, atomic_t *); diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index dff3f0253aa..ff9ead640c4 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -117,7 +117,7 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id if (!strcmp(parent->name, "dma")) { p = parport_pc_probe_port(base, base + 0x400, op->irqs[0], PARPORT_DMA_NOFIFO, - op->dev.parent->parent); + op->dev.parent->parent, 0); if (!p) return -ENOMEM; dev_set_drvdata(&op->dev, p); @@ -168,7 +168,8 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id p = parport_pc_probe_port(base, base + 0x400, op->irqs[0], slot, - op->dev.parent); + op->dev.parent, + 0); err = -ENOMEM; if (!p) goto out_disable_irq; diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 6ce5d2598a0..adf5f273868 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -1183,8 +1183,7 @@ out_free_txq: free_queue(lp->tx_num_entries, lp->tx_base); out_free_mssbuf: - if (mssbuf) - kfree(mssbuf); + kfree(mssbuf); out_free_iommu: ldc_iommu_release(lp); @@ -1217,8 +1216,7 @@ void ldc_free(struct ldc_channel *lp) hlist_del(&lp->list); - if (lp->mssbuf) - kfree(lp->mssbuf); + kfree(lp->mssbuf); ldc_iommu_release(lp); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 708e12a26b0..f7642e5a94d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -118,9 +118,9 @@ void __cpuinit smp_callin(void) while (!cpu_isset(cpuid, smp_commenced_mask)) rmb(); - ipi_call_lock(); + ipi_call_lock_irq(); cpu_set(cpuid, cpu_online_map); - ipi_call_unlock(); + ipi_call_unlock_irq(); /* idle thread is expected to have preempt disabled */ preempt_disable(); diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d5cd6c58688..a4737dddfd5 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -50,7 +50,7 @@ #ifdef CONFIG_X86_64 #define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) -#define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) +#define NEED_PGE 0 #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) #define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) #define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a918dde46b..018a0a40079 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) static inline unsigned long pte_mfn(pte_t pte) diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 3e3cd3db7a0..ecdb682ab51 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -204,7 +204,13 @@ static void drv_read(struct drv_cmd *cmd) static void drv_write(struct drv_cmd *cmd) { + int this_cpu; + + this_cpu = get_cpu(); + if (cpumask_test_cpu(this_cpu, cmd->mask)) + do_drv_write(cmd); smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); + put_cpu(); } static u32 get_cur_val(const struct cpumask *mask) @@ -277,7 +283,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int perf_percent; unsigned int retval; - if (smp_call_function_single(cpu, read_measured_perf_ctrs, &cur, 1)) + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1)) return 0; cur.aperf.whole = readin.aperf.whole - diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index a0f3851ef31..2e0eb414095 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -108,40 +108,29 @@ struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE -struct update_for_cpu { - const void __user *buf; - size_t size; -}; - -static long update_for_cpu(void *_ufc) -{ - struct update_for_cpu *ufc = _ufc; - int error; - - error = microcode_ops->request_microcode_user(smp_processor_id(), - ufc->buf, ufc->size); - if (error < 0) - return error; - if (!error) - microcode_ops->apply_microcode(smp_processor_id()); - return error; -} - static int do_microcode_update(const void __user *buf, size_t size) { + cpumask_t old; int error = 0; int cpu; - struct update_for_cpu ufc = { .buf = buf, .size = size }; + + old = current->cpus_allowed; for_each_online_cpu(cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!uci->valid) continue; - error = work_on_cpu(cpu, update_for_cpu, &ufc); + + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); + error = microcode_ops->request_microcode_user(cpu, buf, size); if (error < 0) - break; + goto out; + if (!error) + microcode_ops->apply_microcode(cpu); } +out: + set_cpus_allowed_ptr(current, &old); return error; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 82cd39a6cbd..f09e8c36ee8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -42,6 +42,7 @@ #include <asm/xen/hypervisor.h> #include <asm/fixmap.h> #include <asm/processor.h> +#include <asm/proto.h> #include <asm/msr-index.h> #include <asm/setup.h> #include <asm/desc.h> @@ -168,21 +169,23 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { + unsigned maskecx = ~0; unsigned maskedx = ~0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ - if (*ax == 1) - maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ - (1 << X86_FEATURE_ACPI) | /* disable ACPI */ - (1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + if (*ax == 1) { + maskecx = cpuid_leaf1_ecx_mask; + maskedx = cpuid_leaf1_edx_mask; + } asm(XEN_EMULATE_PREFIX "cpuid" : "=a" (*ax), @@ -190,9 +193,43 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, "=c" (*cx), "=d" (*dx) : "0" (*ax), "2" (*cx)); + + *cx &= maskecx; *dx &= maskedx; } +static __init void xen_init_cpuid_mask(void) +{ + unsigned int ax, bx, cx, dx; + + cpuid_leaf1_edx_mask = + ~((1 << X86_FEATURE_MCE) | /* disable MCE */ + (1 << X86_FEATURE_MCA) | /* disable MCA */ + (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + + if (!xen_initial_domain()) + cpuid_leaf1_edx_mask &= + ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ + (1 << X86_FEATURE_ACPI)); /* disable ACPI */ + + ax = 1; + xen_cpuid(&ax, &bx, &cx, &dx); + + /* cpuid claims we support xsave; try enabling it to see what happens */ + if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { + unsigned long cr4; + + set_in_cr4(X86_CR4_OSXSAVE); + + cr4 = read_cr4(); + + if ((cr4 & X86_CR4_OSXSAVE) == 0) + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); + + clear_in_cr4(X86_CR4_OSXSAVE); + } +} + static void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); @@ -284,12 +321,11 @@ static void xen_set_ldt(const void *addr, unsigned entries) static void xen_load_gdt(const struct desc_ptr *dtr) { - unsigned long *frames; unsigned long va = dtr->address; unsigned int size = dtr->size + 1; unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE; + unsigned long frames[pages]; int f; - struct multicall_space mcs; /* A GDT can be up to 64k in size, which corresponds to 8192 8-byte entries, or 16 4k pages.. */ @@ -297,19 +333,26 @@ static void xen_load_gdt(const struct desc_ptr *dtr) BUG_ON(size > 65536); BUG_ON(va & ~PAGE_MASK); - mcs = xen_mc_entry(sizeof(*frames) * pages); - frames = mcs.args; - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = arbitrary_virt_to_mfn((void *)va); + int level; + pte_t *ptep = lookup_address(va, &level); + unsigned long pfn, mfn; + void *virt; + + BUG_ON(ptep == NULL); + + pfn = pte_pfn(*ptep); + mfn = pfn_to_mfn(pfn); + virt = __va(PFN_PHYS(pfn)); + + frames[f] = mfn; make_lowmem_page_readonly((void *)va); - make_lowmem_page_readonly(mfn_to_virt(frames[f])); + make_lowmem_page_readonly(virt); } - MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); - - xen_mc_issue(PARAVIRT_LAZY_CPU); + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); } static void load_TLS_descriptor(struct thread_struct *t, @@ -385,7 +428,7 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { - if (val->type != 0xf && val->type != 0xe) + if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) return 0; info->vector = vector; @@ -393,8 +436,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, info->cs = gate_segment(*val); info->flags = val->dpl; /* interrupt gates clear IF */ - if (val->type == 0xe) - info->flags |= 4; + if (val->type == GATE_INTERRUPT) + info->flags |= 1 << 2; return 1; } @@ -872,7 +915,6 @@ static const struct machine_ops __initdata xen_machine_ops = { .emergency_restart = xen_emergency_restart, }; - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -897,6 +939,8 @@ asmlinkage void __init xen_start_kernel(void) xen_init_irq_ops(); + xen_init_cpuid_mask(); + #ifdef CONFIG_X86_LOCAL_APIC /* * set up the basic apic ops. @@ -938,6 +982,11 @@ asmlinkage void __init xen_start_kernel(void) if (!xen_initial_domain()) __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2a81838a9ab..9842b121240 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -184,7 +184,7 @@ static inline unsigned p2m_index(unsigned long pfn) } /* Build the parallel p2m_top_mfn structures */ -void xen_setup_mfn_list_list(void) +static void __init xen_build_mfn_list_list(void) { unsigned pfn, idx; @@ -198,7 +198,10 @@ void xen_setup_mfn_list_list(void) unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); } +} +void xen_setup_mfn_list_list(void) +{ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = @@ -218,6 +221,8 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top[topidx] = &mfn_list[pfn]; } + + xen_build_mfn_list_list(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -233,47 +238,74 @@ unsigned long get_phys_to_machine(unsigned long pfn) } EXPORT_SYMBOL_GPL(get_phys_to_machine); -static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +/* install a new p2m_top page */ +bool install_p2mtop_page(unsigned long pfn, unsigned long *p) { - unsigned long *p; + unsigned topidx = p2m_top_index(pfn); + unsigned long **pfnp, *mfnp; unsigned i; - p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); - BUG_ON(p == NULL); + pfnp = &p2m_top[topidx]; + mfnp = &p2m_top_mfn[topidx]; for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++) p[i] = INVALID_P2M_ENTRY; - if (cmpxchg(pp, p2m_missing, p) != p2m_missing) - free_page((unsigned long)p); - else + if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) { *mfnp = virt_to_mfn(p); + return true; + } + + return false; } -void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +static void alloc_p2m(unsigned long pfn) { - unsigned topidx, idx; + unsigned long *p; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + if (!install_p2mtop_page(pfn, p)) + free_page((unsigned long)p); +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { BUG_ON(mfn != INVALID_P2M_ENTRY); - return; + return true; } topidx = p2m_top_index(pfn); if (p2m_top[topidx] == p2m_missing) { - /* no need to allocate a page to store an invalid entry */ if (mfn == INVALID_P2M_ENTRY) - return; - alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + return true; + return false; } idx = p2m_index(pfn); p2m_top[topidx][idx] = mfn; + + return true; +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + alloc_p2m(pfn); + + if (!__set_phys_to_machine(pfn, mfn)) + BUG(); + } } unsigned long arbitrary_virt_to_mfn(void *vaddr) @@ -987,7 +1019,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -void __init xen_mark_init_mm_pinned(void) +static void __init xen_mark_init_mm_pinned(void) { xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1270,8 +1302,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - BUG_ON(cpumask_empty(cpus)); - BUG_ON(!mm); + if (cpumask_empty(cpus)) + return; /* nothing to do */ mcs = xen_mc_entry(sizeof(*args)); args = mcs.args; @@ -1438,6 +1470,15 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) } #endif +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1446,22 +1487,29 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) BUG_ON(mem_map); /* should only be used early */ #endif make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); +} + +/* Used for pmd and pud */ +static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn) +{ +#ifdef CONFIG_FLATMEM + BUG_ON(mem_map); /* should only be used early */ +#endif + make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); } /* Early release_pte assumes that all pts are pinned, since there's only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) +static __init void xen_release_pte_init(unsigned long pfn) { + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static __init void xen_release_pmd_init(unsigned long pfn) { - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } /* This needs to make sure the new pte page is pinned iff its being @@ -1773,6 +1821,9 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #ifdef CONFIG_X86_LOCAL_APIC case FIX_APIC_BASE: /* maps dummy local APIC */ #endif + case FIX_TEXT_POKE0: + case FIX_TEXT_POKE1: + /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -1819,7 +1870,6 @@ __init void xen_post_allocator_init(void) xen_mark_init_mm_pinned(); } - const struct pv_mmu_ops xen_mmu_ops __initdata = { .pagetable_setup_start = xen_pagetable_setup_start, .pagetable_setup_done = xen_pagetable_setup_done, @@ -1843,9 +1893,9 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pte = xen_alloc_pte_init, .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd = xen_alloc_pmd_init, .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, + .release_pmd = xen_release_pmd_init, #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = xen_kmap_atomic_pte, @@ -1883,8 +1933,8 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_pgd = xen_set_pgd_hyper, - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #endif /* PAGETABLE_LEVELS == 4 */ .activate_mm = xen_activate_mm, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 24d1b44a337..da730262489 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -11,6 +11,9 @@ enum pt_level { }; +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool install_p2mtop_page(unsigned long pfn, unsigned long *p); + void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 585a6e33083..429834ec168 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -317,7 +317,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) BUG_ON(rc); while(per_cpu(cpu_state, cpu) != CPU_ONLINE) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); barrier(); } @@ -422,7 +422,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask) /* Make sure other vcpus get a chance to run if they need to. */ for_each_cpu(cpu, mask) { if (xen_vcpu_stolen(cpu)) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); break; } } diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 2f5ef2632ea..20139464943 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -57,8 +57,6 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -void xen_mark_init_mm_pinned(void); - void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP diff --git a/block/as-iosched.c b/block/as-iosched.c index 631f6f44460..c48fa670d22 100644 --- a/block/as-iosched.c +++ b/block/as-iosched.c @@ -17,9 +17,6 @@ #include <linux/rbtree.h> #include <linux/interrupt.h> -#define REQ_SYNC 1 -#define REQ_ASYNC 0 - /* * See Documentation/block/as-iosched.txt */ @@ -93,7 +90,7 @@ struct as_data { struct list_head fifo_list[2]; struct request *next_rq[2]; /* next in sort order */ - sector_t last_sector[2]; /* last REQ_SYNC & REQ_ASYNC sectors */ + sector_t last_sector[2]; /* last SYNC & ASYNC sectors */ unsigned long exit_prob; /* probability a task will exit while being waited on */ @@ -109,7 +106,7 @@ struct as_data { unsigned long last_check_fifo[2]; int changed_batch; /* 1: waiting for old batch to end */ int new_batch; /* 1: waiting on first read complete */ - int batch_data_dir; /* current batch REQ_SYNC / REQ_ASYNC */ + int batch_data_dir; /* current batch SYNC / ASYNC */ int write_batch_count; /* max # of reqs in a write batch */ int current_write_count; /* how many requests left this batch */ int write_batch_idled; /* has the write batch gone idle? */ @@ -554,7 +551,7 @@ static void as_update_iohist(struct as_data *ad, struct as_io_context *aic, if (aic == NULL) return; - if (data_dir == REQ_SYNC) { + if (data_dir == BLK_RW_SYNC) { unsigned long in_flight = atomic_read(&aic->nr_queued) + atomic_read(&aic->nr_dispatched); spin_lock(&aic->lock); @@ -811,7 +808,7 @@ static void as_update_rq(struct as_data *ad, struct request *rq) */ static void update_write_batch(struct as_data *ad) { - unsigned long batch = ad->batch_expire[REQ_ASYNC]; + unsigned long batch = ad->batch_expire[BLK_RW_ASYNC]; long write_time; write_time = (jiffies - ad->current_batch_expires) + batch; @@ -855,7 +852,7 @@ static void as_completed_request(struct request_queue *q, struct request *rq) kblockd_schedule_work(q, &ad->antic_work); ad->changed_batch = 0; - if (ad->batch_data_dir == REQ_SYNC) + if (ad->batch_data_dir == BLK_RW_SYNC) ad->new_batch = 1; } WARN_ON(ad->nr_dispatched == 0); @@ -869,7 +866,7 @@ static void as_completed_request(struct request_queue *q, struct request *rq) if (ad->new_batch && ad->batch_data_dir == rq_is_sync(rq)) { update_write_batch(ad); ad->current_batch_expires = jiffies + - ad->batch_expire[REQ_SYNC]; + ad->batch_expire[BLK_RW_SYNC]; ad->new_batch = 0; } @@ -960,7 +957,7 @@ static inline int as_batch_expired(struct as_data *ad) if (ad->changed_batch || ad->new_batch) return 0; - if (ad->batch_data_dir == REQ_SYNC) + if (ad->batch_data_dir == BLK_RW_SYNC) /* TODO! add a check so a complete fifo gets written? */ return time_after(jiffies, ad->current_batch_expires); @@ -986,7 +983,7 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq) */ ad->last_sector[data_dir] = rq->sector + rq->nr_sectors; - if (data_dir == REQ_SYNC) { + if (data_dir == BLK_RW_SYNC) { struct io_context *ioc = RQ_IOC(rq); /* In case we have to anticipate after this */ copy_io_context(&ad->io_context, &ioc); @@ -1025,41 +1022,41 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq) static int as_dispatch_request(struct request_queue *q, int force) { struct as_data *ad = q->elevator->elevator_data; - const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]); - const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]); + const int reads = !list_empty(&ad->fifo_list[BLK_RW_SYNC]); + const int writes = !list_empty(&ad->fifo_list[BLK_RW_ASYNC]); struct request *rq; if (unlikely(force)) { /* * Forced dispatch, accounting is useless. Reset * accounting states and dump fifo_lists. Note that - * batch_data_dir is reset to REQ_SYNC to avoid + * batch_data_dir is reset to BLK_RW_SYNC to avoid * screwing write batch accounting as write batch * accounting occurs on W->R transition. */ int dispatched = 0; - ad->batch_data_dir = REQ_SYNC; + ad->batch_data_dir = BLK_RW_SYNC; ad->changed_batch = 0; ad->new_batch = 0; - while (ad->next_rq[REQ_SYNC]) { - as_move_to_dispatch(ad, ad->next_rq[REQ_SYNC]); + while (ad->next_rq[BLK_RW_SYNC]) { + as_move_to_dispatch(ad, ad->next_rq[BLK_RW_SYNC]); dispatched++; } - ad->last_check_fifo[REQ_SYNC] = jiffies; + ad->last_check_fifo[BLK_RW_SYNC] = jiffies; - while (ad->next_rq[REQ_ASYNC]) { - as_move_to_dispatch(ad, ad->next_rq[REQ_ASYNC]); + while (ad->next_rq[BLK_RW_ASYNC]) { + as_move_to_dispatch(ad, ad->next_rq[BLK_RW_ASYNC]); dispatched++; } - ad->last_check_fifo[REQ_ASYNC] = jiffies; + ad->last_check_fifo[BLK_RW_ASYNC] = jiffies; return dispatched; } /* Signal that the write batch was uncontended, so we can't time it */ - if (ad->batch_data_dir == REQ_ASYNC && !reads) { + if (ad->batch_data_dir == BLK_RW_ASYNC && !reads) { if (ad->current_write_count == 0 || !writes) ad->write_batch_idled = 1; } @@ -1076,8 +1073,8 @@ static int as_dispatch_request(struct request_queue *q, int force) */ rq = ad->next_rq[ad->batch_data_dir]; - if (ad->batch_data_dir == REQ_SYNC && ad->antic_expire) { - if (as_fifo_expired(ad, REQ_SYNC)) + if (ad->batch_data_dir == BLK_RW_SYNC && ad->antic_expire) { + if (as_fifo_expired(ad, BLK_RW_SYNC)) goto fifo_expired; if (as_can_anticipate(ad, rq)) { @@ -1090,7 +1087,7 @@ static int as_dispatch_request(struct request_queue *q, int force) /* we have a "next request" */ if (reads && !writes) ad->current_batch_expires = - jiffies + ad->batch_expire[REQ_SYNC]; + jiffies + ad->batch_expire[BLK_RW_SYNC]; goto dispatch_request; } } @@ -1101,20 +1098,20 @@ static int as_dispatch_request(struct request_queue *q, int force) */ if (reads) { - BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_SYNC])); + BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_SYNC])); - if (writes && ad->batch_data_dir == REQ_SYNC) + if (writes && ad->batch_data_dir == BLK_RW_SYNC) /* * Last batch was a read, switch to writes */ goto dispatch_writes; - if (ad->batch_data_dir == REQ_ASYNC) { + if (ad->batch_data_dir == BLK_RW_ASYNC) { WARN_ON(ad->new_batch); ad->changed_batch = 1; } - ad->batch_data_dir = REQ_SYNC; - rq = rq_entry_fifo(ad->fifo_list[REQ_SYNC].next); + ad->batch_data_dir = BLK_RW_SYNC; + rq = rq_entry_fifo(ad->fifo_list[BLK_RW_SYNC].next); ad->last_check_fifo[ad->batch_data_dir] = jiffies; goto dispatch_request; } @@ -1125,9 +1122,9 @@ static int as_dispatch_request(struct request_queue *q, int force) if (writes) { dispatch_writes: - BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_ASYNC])); + BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_ASYNC])); - if (ad->batch_data_dir == REQ_SYNC) { + if (ad->batch_data_dir == BLK_RW_SYNC) { ad->changed_batch = 1; /* @@ -1137,11 +1134,11 @@ dispatch_writes: */ ad->new_batch = 0; } - ad->batch_data_dir = REQ_ASYNC; + ad->batch_data_dir = BLK_RW_ASYNC; ad->current_write_count = ad->write_batch_count; ad->write_batch_idled = 0; - rq = rq_entry_fifo(ad->fifo_list[REQ_ASYNC].next); - ad->last_check_fifo[REQ_ASYNC] = jiffies; + rq = rq_entry_fifo(ad->fifo_list[BLK_RW_ASYNC].next); + ad->last_check_fifo[BLK_RW_ASYNC] = jiffies; goto dispatch_request; } @@ -1164,9 +1161,9 @@ fifo_expired: if (ad->nr_dispatched) return 0; - if (ad->batch_data_dir == REQ_ASYNC) + if (ad->batch_data_dir == BLK_RW_ASYNC) ad->current_batch_expires = jiffies + - ad->batch_expire[REQ_ASYNC]; + ad->batch_expire[BLK_RW_ASYNC]; else ad->new_batch = 1; @@ -1238,8 +1235,8 @@ static int as_queue_empty(struct request_queue *q) { struct as_data *ad = q->elevator->elevator_data; - return list_empty(&ad->fifo_list[REQ_ASYNC]) - && list_empty(&ad->fifo_list[REQ_SYNC]); + return list_empty(&ad->fifo_list[BLK_RW_ASYNC]) + && list_empty(&ad->fifo_list[BLK_RW_SYNC]); } static int @@ -1346,8 +1343,8 @@ static void as_exit_queue(struct elevator_queue *e) del_timer_sync(&ad->antic_timer); cancel_work_sync(&ad->antic_work); - BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC])); - BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC])); + BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_SYNC])); + BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_ASYNC])); put_io_context(ad->io_context); kfree(ad); @@ -1372,18 +1369,18 @@ static void *as_init_queue(struct request_queue *q) init_timer(&ad->antic_timer); INIT_WORK(&ad->antic_work, as_work_handler); - INIT_LIST_HEAD(&ad->fifo_list[REQ_SYNC]); - INIT_LIST_HEAD(&ad->fifo_list[REQ_ASYNC]); - ad->sort_list[REQ_SYNC] = RB_ROOT; - ad->sort_list[REQ_ASYNC] = RB_ROOT; - ad->fifo_expire[REQ_SYNC] = default_read_expire; - ad->fifo_expire[REQ_ASYNC] = default_write_expire; + INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_SYNC]); + INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_ASYNC]); + ad->sort_list[BLK_RW_SYNC] = RB_ROOT; + ad->sort_list[BLK_RW_ASYNC] = RB_ROOT; + ad->fifo_expire[BLK_RW_SYNC] = default_read_expire; + ad->fifo_expire[BLK_RW_ASYNC] = default_write_expire; ad->antic_expire = default_antic_expire; - ad->batch_expire[REQ_SYNC] = default_read_batch_expire; - ad->batch_expire[REQ_ASYNC] = default_write_batch_expire; + ad->batch_expire[BLK_RW_SYNC] = default_read_batch_expire; + ad->batch_expire[BLK_RW_ASYNC] = default_write_batch_expire; - ad->current_batch_expires = jiffies + ad->batch_expire[REQ_SYNC]; - ad->write_batch_count = ad->batch_expire[REQ_ASYNC] / 10; + ad->current_batch_expires = jiffies + ad->batch_expire[BLK_RW_SYNC]; + ad->write_batch_count = ad->batch_expire[BLK_RW_ASYNC] / 10; if (ad->write_batch_count < 2) ad->write_batch_count = 2; @@ -1432,11 +1429,11 @@ static ssize_t __FUNC(struct elevator_queue *e, char *page) \ struct as_data *ad = e->elevator_data; \ return as_var_show(jiffies_to_msecs((__VAR)), (page)); \ } -SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[REQ_SYNC]); -SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[REQ_ASYNC]); +SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[BLK_RW_SYNC]); +SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[BLK_RW_ASYNC]); SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire); -SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[REQ_SYNC]); -SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[REQ_ASYNC]); +SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[BLK_RW_SYNC]); +SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[BLK_RW_ASYNC]); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \ @@ -1451,13 +1448,14 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) *(__PTR) = msecs_to_jiffies(*(__PTR)); \ return ret; \ } -STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX); -STORE_FUNCTION(as_write_expire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX); +STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[BLK_RW_SYNC], 0, INT_MAX); +STORE_FUNCTION(as_write_expire_store, + &ad->fifo_expire[BLK_RW_ASYNC], 0, INT_MAX); STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX); STORE_FUNCTION(as_read_batch_expire_store, - &ad->batch_expire[REQ_SYNC], 0, INT_MAX); + &ad->batch_expire[BLK_RW_SYNC], 0, INT_MAX); STORE_FUNCTION(as_write_batch_expire_store, - &ad->batch_expire[REQ_ASYNC], 0, INT_MAX); + &ad->batch_expire[BLK_RW_ASYNC], 0, INT_MAX); #undef STORE_FUNCTION #define AS_ATTR(name) \ diff --git a/block/blk-barrier.c b/block/blk-barrier.c index f7dae57e6ca..20b4111fa05 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -319,9 +319,6 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) return -ENXIO; bio = bio_alloc(GFP_KERNEL, 0); - if (!bio) - return -ENOMEM; - bio->bi_end_io = bio_end_empty_barrier; bio->bi_private = &wait; bio->bi_bdev = bdev; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 73f36beff5c..cac4e9febe6 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -209,14 +209,14 @@ static ssize_t queue_iostats_store(struct request_queue *q, const char *page, ssize_t ret = queue_var_store(&stats, page, count); spin_lock_irq(q->queue_lock); - elv_quisce_start(q); + elv_quiesce_start(q); if (stats) queue_flag_set(QUEUE_FLAG_IO_STAT, q); else queue_flag_clear(QUEUE_FLAG_IO_STAT, q); - elv_quisce_end(q); + elv_quiesce_end(q); spin_unlock_irq(q->queue_lock); return ret; diff --git a/block/blk.h b/block/blk.h index 24fcaeeaf62..5dfc41267a0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -70,8 +70,8 @@ void blk_queue_congestion_threshold(struct request_queue *q); int blk_dev_init(void); -void elv_quisce_start(struct request_queue *q); -void elv_quisce_end(struct request_queue *q); +void elv_quiesce_start(struct request_queue *q); +void elv_quiesce_end(struct request_queue *q); /* diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index a4809de6fea..0d3b70de3d8 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -56,9 +56,6 @@ static DEFINE_SPINLOCK(ioc_gone_lock); #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE) #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) -#define ASYNC (0) -#define SYNC (1) - #define sample_valid(samples) ((samples) > 80) /* @@ -83,6 +80,14 @@ struct cfq_data { * rr list of queues with requests and the count of them */ struct cfq_rb_root service_tree; + + /* + * Each priority tree is sorted by next_request position. These + * trees are used when determining if two or more queues are + * interleaving requests (see cfq_close_cooperator). + */ + struct rb_root prio_trees[CFQ_PRIO_LISTS]; + unsigned int busy_queues; /* * Used to track any pending rt requests so we can pre-empt current @@ -147,6 +152,8 @@ struct cfq_queue { struct rb_node rb_node; /* service_tree key */ unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; /* sorted list of pending requests */ struct rb_root sort_list; /* if fifo isn't expired, next request to serve */ @@ -185,6 +192,7 @@ enum cfqq_state_flags { CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */ CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */ CFQ_CFQQ_FLAG_sync, /* synchronous queue */ + CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */ }; #define CFQ_CFQQ_FNS(name) \ @@ -211,6 +219,7 @@ CFQ_CFQQ_FNS(idle_window); CFQ_CFQQ_FNS(prio_changed); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); +CFQ_CFQQ_FNS(coop); #undef CFQ_CFQQ_FNS #define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ @@ -419,13 +428,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) return NULL; } +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) { if (root->left == n) root->left = NULL; - - rb_erase(n, &root->rb); - RB_CLEAR_NODE(n); + rb_erase_init(n, &root->rb); } /* @@ -470,8 +483,8 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd, * requests waiting to be processed. It is sorted in the order that * we will service the queues. */ -static void cfq_service_tree_add(struct cfq_data *cfqd, - struct cfq_queue *cfqq, int add_front) +static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, + int add_front) { struct rb_node **p, *parent; struct cfq_queue *__cfqq; @@ -544,6 +557,63 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb); } +static struct cfq_queue * +cfq_prio_tree_lookup(struct cfq_data *cfqd, int ioprio, sector_t sector, + struct rb_node **ret_parent, struct rb_node ***rb_link) +{ + struct rb_root *root = &cfqd->prio_trees[ioprio]; + struct rb_node **p, *parent; + struct cfq_queue *cfqq = NULL; + + parent = NULL; + p = &root->rb_node; + while (*p) { + struct rb_node **n; + + parent = *p; + cfqq = rb_entry(parent, struct cfq_queue, p_node); + + /* + * Sort strictly based on sector. Smallest to the left, + * largest to the right. + */ + if (sector > cfqq->next_rq->sector) + n = &(*p)->rb_right; + else if (sector < cfqq->next_rq->sector) + n = &(*p)->rb_left; + else + break; + p = n; + } + + *ret_parent = parent; + if (rb_link) + *rb_link = p; + return NULL; +} + +static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct rb_root *root = &cfqd->prio_trees[cfqq->ioprio]; + struct rb_node **p, *parent; + struct cfq_queue *__cfqq; + + if (!RB_EMPTY_NODE(&cfqq->p_node)) + rb_erase_init(&cfqq->p_node, root); + + if (cfq_class_idle(cfqq)) + return; + if (!cfqq->next_rq) + return; + + __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->ioprio, cfqq->next_rq->sector, + &parent, &p); + BUG_ON(__cfqq); + + rb_link_node(&cfqq->p_node, parent, p); + rb_insert_color(&cfqq->p_node, root); +} + /* * Update cfqq's position in the service tree. */ @@ -552,8 +622,10 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq) /* * Resorting requires the cfqq to be on the RR list already. */ - if (cfq_cfqq_on_rr(cfqq)) + if (cfq_cfqq_on_rr(cfqq)) { cfq_service_tree_add(cfqd, cfqq, 0); + cfq_prio_tree_add(cfqd, cfqq); + } } /* @@ -584,6 +656,8 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) if (!RB_EMPTY_NODE(&cfqq->rb_node)) cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + if (!RB_EMPTY_NODE(&cfqq->p_node)) + rb_erase_init(&cfqq->p_node, &cfqd->prio_trees[cfqq->ioprio]); BUG_ON(!cfqd->busy_queues); cfqd->busy_queues--; @@ -613,7 +687,7 @@ static void cfq_add_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); struct cfq_data *cfqd = cfqq->cfqd; - struct request *__alias; + struct request *__alias, *prev; cfqq->queued[rq_is_sync(rq)]++; @@ -630,7 +704,15 @@ static void cfq_add_rq_rb(struct request *rq) /* * check if this request is a better next-serve candidate */ + prev = cfqq->next_rq; cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq); + + /* + * adjust priority tree position, if ->next_rq changes + */ + if (prev != cfqq->next_rq) + cfq_prio_tree_add(cfqd, cfqq); + BUG_ON(!cfqq->next_rq); } @@ -843,11 +925,15 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) /* * Get and set a new active queue for service. */ -static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) +static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, + struct cfq_queue *cfqq) { - struct cfq_queue *cfqq; + if (!cfqq) { + cfqq = cfq_get_next_queue(cfqd); + if (cfqq) + cfq_clear_cfqq_coop(cfqq); + } - cfqq = cfq_get_next_queue(cfqd); __cfq_set_active_queue(cfqd, cfqq); return cfqq; } @@ -871,17 +957,89 @@ static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq) return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean; } -static int cfq_close_cooperator(struct cfq_data *cfq_data, - struct cfq_queue *cfqq) +static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq) +{ + struct rb_root *root = &cfqd->prio_trees[cur_cfqq->ioprio]; + struct rb_node *parent, *node; + struct cfq_queue *__cfqq; + sector_t sector = cfqd->last_position; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __cfqq = cfq_prio_tree_lookup(cfqd, cur_cfqq->ioprio, + sector, &parent, NULL); + if (__cfqq) + return __cfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector. + */ + __cfqq = rb_entry(parent, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; + + if (__cfqq->next_rq->sector < sector) + node = rb_next(&__cfqq->p_node); + else + node = rb_prev(&__cfqq->p_node); + if (!node) + return NULL; + + __cfqq = rb_entry(node, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; + + return NULL; +} + +/* + * cfqd - obvious + * cur_cfqq - passed in so that we don't decide that the current queue is + * closely cooperating with itself. + * + * So, basically we're assuming that that cur_cfqq has dispatched at least + * one request, and that cfqd->last_position reflects a position on the disk + * associated with the I/O issued by cur_cfqq. I'm not sure this is a valid + * assumption. + */ +static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq, + int probe) { + struct cfq_queue *cfqq; + + /* + * A valid cfq_io_context is necessary to compare requests against + * the seek_mean of the current cfqq. + */ + if (!cfqd->active_cic) + return NULL; + /* * We should notice if some of the queues are cooperating, eg * working closely on the same area of the disk. In that case, * we can group them together and don't waste time idling. */ - return 0; + cfqq = cfqq_close(cfqd, cur_cfqq); + if (!cfqq) + return NULL; + + if (cfq_cfqq_coop(cfqq)) + return NULL; + + if (!probe) + cfq_mark_cfqq_coop(cfqq); + return cfqq; } + #define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024)) static void cfq_arm_slice_timer(struct cfq_data *cfqd) @@ -920,13 +1078,6 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) if (!cic || !atomic_read(&cic->ioc->nr_tasks)) return; - /* - * See if this prio level has a good candidate - */ - if (cfq_close_cooperator(cfqd, cfqq) && - (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2)) - return; - cfq_mark_cfqq_wait_request(cfqq); /* @@ -939,7 +1090,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT)); mod_timer(&cfqd->idle_slice_timer, jiffies + sl); - cfq_log(cfqd, "arm_idle: %lu", sl); + cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); } /* @@ -1003,7 +1154,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) { - struct cfq_queue *cfqq; + struct cfq_queue *cfqq, *new_cfqq = NULL; cfqq = cfqd->active_queue; if (!cfqq) @@ -1037,6 +1188,16 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) goto keep_queue; /* + * If another queue has a request waiting within our mean seek + * distance, let it run. The expire code will check for close + * cooperators and put the close queue at the front of the service + * tree. + */ + new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0); + if (new_cfqq) + goto expire; + + /* * No requests pending. If the active queue still has requests in * flight or is idling for a new request, allow either of these * conditions to happen (or time out) before selecting a new queue. @@ -1050,7 +1211,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) expire: cfq_slice_expired(cfqd, 0); new_queue: - cfqq = cfq_set_active_queue(cfqd); + cfqq = cfq_set_active_queue(cfqd, new_cfqq); keep_queue: return cfqq; } @@ -1333,14 +1494,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, if (ioc->ioc_data == cic) rcu_assign_pointer(ioc->ioc_data, NULL); - if (cic->cfqq[ASYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]); - cic->cfqq[ASYNC] = NULL; + if (cic->cfqq[BLK_RW_ASYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); + cic->cfqq[BLK_RW_ASYNC] = NULL; } - if (cic->cfqq[SYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]); - cic->cfqq[SYNC] = NULL; + if (cic->cfqq[BLK_RW_SYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]); + cic->cfqq[BLK_RW_SYNC] = NULL; } } @@ -1449,17 +1610,18 @@ static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic) spin_lock_irqsave(cfqd->queue->queue_lock, flags); - cfqq = cic->cfqq[ASYNC]; + cfqq = cic->cfqq[BLK_RW_ASYNC]; if (cfqq) { struct cfq_queue *new_cfqq; - new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC); + new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc, + GFP_ATOMIC); if (new_cfqq) { - cic->cfqq[ASYNC] = new_cfqq; + cic->cfqq[BLK_RW_ASYNC] = new_cfqq; cfq_put_queue(cfqq); } } - cfqq = cic->cfqq[SYNC]; + cfqq = cic->cfqq[BLK_RW_SYNC]; if (cfqq) cfq_mark_cfqq_prio_changed(cfqq); @@ -1510,6 +1672,7 @@ retry: } RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); INIT_LIST_HEAD(&cfqq->fifo); atomic_set(&cfqq->ref, 0); @@ -1905,10 +2068,20 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, * Remember that we saw a request from this process, but * don't start queuing just yet. Otherwise we risk seeing lots * of tiny requests, because we disrupt the normal plugging - * and merging. + * and merging. If the request is already larger than a single + * page, let it rip immediately. For that case we assume that + * merging is already done. Ditto for a busy system that + * has other work pending, don't risk delaying until the + * idle timer unplug to continue working. */ - if (cfq_cfqq_wait_request(cfqq)) + if (cfq_cfqq_wait_request(cfqq)) { + if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || + cfqd->busy_queues > 1) { + del_timer(&cfqd->idle_slice_timer); + blk_start_queueing(cfqd->queue); + } cfq_mark_cfqq_must_dispatch(cfqq); + } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* * not the active queue - expire current slice if it is @@ -1992,16 +2165,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) * or if we want to idle in case it has no pending requests. */ if (cfqd->active_queue == cfqq) { + const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list); + if (cfq_cfqq_slice_new(cfqq)) { cfq_set_prio_slice(cfqd, cfqq); cfq_clear_cfqq_slice_new(cfqq); } + /* + * If there are no requests waiting in this queue, and + * there are other queues ready to issue requests, AND + * those other queues are issuing requests within our + * mean seek distance, give them a chance to run instead + * of idling. + */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) cfq_slice_expired(cfqd, 1); - else if (sync && !rq_noidle(rq) && - RB_EMPTY_ROOT(&cfqq->sort_list)) { + else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) && + sync && !rq_noidle(rq)) cfq_arm_slice_timer(cfqd); - } } if (!cfqd->rq_in_driver) @@ -2062,7 +2243,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) if (!cic) return ELV_MQUEUE_MAY; - cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC); + cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { cfq_init_prio_data(cfqq, cic->ioc); cfq_prio_boost(cfqq); @@ -2152,11 +2333,10 @@ static void cfq_kick_queue(struct work_struct *work) struct cfq_data *cfqd = container_of(work, struct cfq_data, unplug_work); struct request_queue *q = cfqd->queue; - unsigned long flags; - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irq(q->queue_lock); blk_start_queueing(q); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irq(q->queue_lock); } /* diff --git a/block/elevator.c b/block/elevator.c index fb81bcc14a8..7073a907257 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -590,7 +590,7 @@ void elv_drain_elevator(struct request_queue *q) /* * Call with queue lock held, interrupts disabled */ -void elv_quisce_start(struct request_queue *q) +void elv_quiesce_start(struct request_queue *q) { queue_flag_set(QUEUE_FLAG_ELVSWITCH, q); @@ -607,7 +607,7 @@ void elv_quisce_start(struct request_queue *q) } } -void elv_quisce_end(struct request_queue *q) +void elv_quiesce_end(struct request_queue *q) { queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q); } @@ -1126,7 +1126,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) * Turn on BYPASS and drain all requests w/ elevator private data */ spin_lock_irq(q->queue_lock); - elv_quisce_start(q); + elv_quiesce_start(q); /* * Remember old elevator. @@ -1150,7 +1150,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) */ elevator_exit(old_elevator); spin_lock_irq(q->queue_lock); - elv_quisce_end(q); + elv_quiesce_end(q); spin_unlock_irq(q->queue_lock); blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name); diff --git a/block/ioctl.c b/block/ioctl.c index 0f22e629b13..ad474d4bbcc 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -146,8 +146,6 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, struct bio *bio; bio = bio_alloc(GFP_KERNEL, 0); - if (!bio) - return -ENOMEM; bio->bi_end_io = blk_ioc_discard_endio; bio->bi_bdev = bdev; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 626ee274c5c..84b7f8709f4 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -217,7 +217,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, struct bio *bio) { - int ret = 0; + int r, ret = 0; /* * fill in all the output members @@ -242,7 +242,9 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, ret = -EFAULT; } - blk_rq_unmap_user(bio); + r = blk_rq_unmap_user(bio); + if (!ret) + ret = r; blk_put_request(rq); return ret; diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index be204308cc1..9359613addc 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -1059,7 +1059,7 @@ static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id) goto out; } - err = pci_set_dma_mask(dev, DMA_32BIT_MASK); + err = pci_set_dma_mask(dev, DMA_BIT_MASK(32)); if (err) { dev_warn(&dev->dev, "Failed to set 32-bit DMA mask\n"); goto out; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bdd4f5f4557..5f7e64ba87e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -275,8 +275,10 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page, if (rw == READ) { copy_from_brd(mem + off, brd, sector, len); flush_dcache_page(page); - } else + } else { + flush_dcache_page(page); copy_to_brd(brd, mem + off, sector, len); + } kunmap_atomic(mem, KM_USER0); out: @@ -436,6 +438,7 @@ static struct brd_device *brd_alloc(int i) if (!brd->brd_queue) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); + blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG, NULL); blk_queue_max_sectors(brd->brd_queue, 1024); blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 0ef6f08aa6e..4d4d5e0d3fa 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -3505,7 +3505,7 @@ static __devinit int cciss_message(struct pci_dev *pdev, unsigned char opcode, u /* The Inbound Post Queue only accepts 32-bit physical addresses for the CCISS commands, so they must be allocated from the lower 4GiB of memory. */ - err = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (err) { iounmap(vaddr); return -ENOMEM; diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 9d9490e22e0..3686912427b 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -2131,6 +2131,8 @@ static const struct intel_driver_description { { PCI_DEVICE_ID_INTEL_82845G_HB, PCI_DEVICE_ID_INTEL_82845G_IG, 0, "830M", &intel_845_driver, &intel_830_driver }, { PCI_DEVICE_ID_INTEL_82850_HB, 0, 0, "i850", &intel_850_driver, NULL }, + { PCI_DEVICE_ID_INTEL_82854_HB, PCI_DEVICE_ID_INTEL_82854_IG, 0, "854", + &intel_845_driver, &intel_830_driver }, { PCI_DEVICE_ID_INTEL_82855PM_HB, 0, 0, "855PM", &intel_845_driver, NULL }, { PCI_DEVICE_ID_INTEL_82855GM_HB, PCI_DEVICE_ID_INTEL_82855GM_IG, 0, "855GM", &intel_845_driver, &intel_830_driver }, @@ -2355,6 +2357,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_82845_HB), ID(PCI_DEVICE_ID_INTEL_82845G_HB), ID(PCI_DEVICE_ID_INTEL_82850_HB), + ID(PCI_DEVICE_ID_INTEL_82854_HB), ID(PCI_DEVICE_ID_INTEL_82855PM_HB), ID(PCI_DEVICE_ID_INTEL_82855GM_HB), ID(PCI_DEVICE_ID_INTEL_82860_HB), diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index 6de020d078e..b0a6a3e5192 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -35,7 +35,6 @@ #include <linux/vt_kern.h> #include <linux/workqueue.h> #include <linux/kexec.h> -#include <linux/interrupt.h> #include <linux/hrtimer.h> #include <linux/oom.h> diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 28f2c3f959b..6ad95c8d636 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -767,11 +767,19 @@ static inline void pci_write_bits16(struct pci_dev *pdev, int offset, pci_write_config_word(pdev, offset, value); } -/* write all or some bits in a dword-register*/ +/* + * pci_write_bits32 + * + * edac local routine to do pci_write_config_dword, but adds + * a mask parameter. If mask is all ones, ignore the mask. + * Otherwise utilize the mask to isolate specified bits + * + * write all or some bits in a dword-register + */ static inline void pci_write_bits32(struct pci_dev *pdev, int offset, u32 value, u32 mask) { - if (mask != 0xffff) { + if (mask != 0xffffffff) { u32 buf; pci_read_config_dword(pdev, offset, &buf); diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index ca9113e1c10..a7d2c717d03 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -389,7 +389,7 @@ static void del_edac_device_from_global_list(struct edac_device_ctl_info */ static void edac_device_workq_function(struct work_struct *work_req) { - struct delayed_work *d_work = (struct delayed_work *)work_req; + struct delayed_work *d_work = to_delayed_work(work_req); struct edac_device_ctl_info *edac_dev = to_edac_device_ctl_work(d_work); mutex_lock(&device_ctls_mutex); diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 25d66940b4f..335b7ebdb11 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -260,7 +260,7 @@ static int edac_mc_assert_error_check_and_clear(void) */ static void edac_mc_workq_function(struct work_struct *work_req) { - struct delayed_work *d_work = (struct delayed_work *)work_req; + struct delayed_work *d_work = to_delayed_work(work_req); struct mem_ctl_info *mci = to_edac_mem_ctl_work(d_work); mutex_lock(&mem_ctls_mutex); diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 5b150aea703..30b585b1d60 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(edac_pci_find); */ static void edac_pci_workq_function(struct work_struct *work_req) { - struct delayed_work *d_work = (struct delayed_work *)work_req; + struct delayed_work *d_work = to_delayed_work(work_req); struct edac_pci_ctl_info *pci = to_edac_pci_ctl_work(d_work); int msec; unsigned long delay; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 3750d800304..473a8f7fbdb 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -446,6 +446,9 @@ struct drm_i915_gem_object { uint32_t tiling_mode; uint32_t stride; + /** Record of address bit 17 of each page at last unbind. */ + long *bit_17; + /** AGP mapping type (AGP_USER_MEMORY or AGP_USER_CACHED_MEMORY */ uint32_t agp_type; @@ -635,9 +638,13 @@ int i915_gem_attach_phys_object(struct drm_device *dev, void i915_gem_detach_phys_object(struct drm_device *dev, struct drm_gem_object *obj); void i915_gem_free_all_phys_object(struct drm_device *dev); +int i915_gem_object_get_pages(struct drm_gem_object *obj); +void i915_gem_object_put_pages(struct drm_gem_object *obj); /* i915_gem_tiling.c */ void i915_gem_detect_bit_6_swizzle(struct drm_device *dev); +void i915_gem_object_do_bit_17_swizzle(struct drm_gem_object *obj); +void i915_gem_object_save_bit_17_swizzle(struct drm_gem_object *obj); /* i915_gem_debug.c */ void i915_gem_dump_object(struct drm_gem_object *obj, int len, diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 1449b452cc6..4642115902d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -43,8 +43,6 @@ static int i915_gem_object_set_cpu_read_domain_range(struct drm_gem_object *obj, uint64_t offset, uint64_t size); static void i915_gem_object_set_to_full_cpu_read_domain(struct drm_gem_object *obj); -static int i915_gem_object_get_pages(struct drm_gem_object *obj); -static void i915_gem_object_put_pages(struct drm_gem_object *obj); static int i915_gem_object_wait_rendering(struct drm_gem_object *obj); static int i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment); @@ -143,15 +141,27 @@ fast_shmem_read(struct page **pages, int length) { char __iomem *vaddr; - int ret; + int unwritten; vaddr = kmap_atomic(pages[page_base >> PAGE_SHIFT], KM_USER0); if (vaddr == NULL) return -ENOMEM; - ret = __copy_to_user_inatomic(data, vaddr + page_offset, length); + unwritten = __copy_to_user_inatomic(data, vaddr + page_offset, length); kunmap_atomic(vaddr, KM_USER0); - return ret; + if (unwritten) + return -EFAULT; + + return 0; +} + +static int i915_gem_object_needs_bit17_swizzle(struct drm_gem_object *obj) +{ + drm_i915_private_t *dev_priv = obj->dev->dev_private; + struct drm_i915_gem_object *obj_priv = obj->driver_private; + + return dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 && + obj_priv->tiling_mode != I915_TILING_NONE; } static inline int @@ -181,6 +191,64 @@ slow_shmem_copy(struct page *dst_page, return 0; } +static inline int +slow_shmem_bit17_copy(struct page *gpu_page, + int gpu_offset, + struct page *cpu_page, + int cpu_offset, + int length, + int is_read) +{ + char *gpu_vaddr, *cpu_vaddr; + + /* Use the unswizzled path if this page isn't affected. */ + if ((page_to_phys(gpu_page) & (1 << 17)) == 0) { + if (is_read) + return slow_shmem_copy(cpu_page, cpu_offset, + gpu_page, gpu_offset, length); + else + return slow_shmem_copy(gpu_page, gpu_offset, + cpu_page, cpu_offset, length); + } + + gpu_vaddr = kmap_atomic(gpu_page, KM_USER0); + if (gpu_vaddr == NULL) + return -ENOMEM; + + cpu_vaddr = kmap_atomic(cpu_page, KM_USER1); + if (cpu_vaddr == NULL) { + kunmap_atomic(gpu_vaddr, KM_USER0); + return -ENOMEM; + } + + /* Copy the data, XORing A6 with A17 (1). The user already knows he's + * XORing with the other bits (A9 for Y, A9 and A10 for X) + */ + while (length > 0) { + int cacheline_end = ALIGN(gpu_offset + 1, 64); + int this_length = min(cacheline_end - gpu_offset, length); + int swizzled_gpu_offset = gpu_offset ^ 64; + + if (is_read) { + memcpy(cpu_vaddr + cpu_offset, + gpu_vaddr + swizzled_gpu_offset, + this_length); + } else { + memcpy(gpu_vaddr + swizzled_gpu_offset, + cpu_vaddr + cpu_offset, + this_length); + } + cpu_offset += this_length; + gpu_offset += this_length; + length -= this_length; + } + + kunmap_atomic(cpu_vaddr, KM_USER1); + kunmap_atomic(gpu_vaddr, KM_USER0); + + return 0; +} + /** * This is the fast shmem pread path, which attempts to copy_from_user directly * from the backing pages of the object to the user's address space. On a @@ -269,6 +337,7 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, struct drm_gem_object *obj, int page_length; int ret; uint64_t data_ptr = args->data_ptr; + int do_bit17_swizzling; remain = args->size; @@ -286,13 +355,15 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, struct drm_gem_object *obj, down_read(&mm->mmap_sem); pinned_pages = get_user_pages(current, mm, (uintptr_t)args->data_ptr, - num_pages, 0, 0, user_pages, NULL); + num_pages, 1, 0, user_pages, NULL); up_read(&mm->mmap_sem); if (pinned_pages < num_pages) { ret = -EFAULT; goto fail_put_user_pages; } + do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); + mutex_lock(&dev->struct_mutex); ret = i915_gem_object_get_pages(obj); @@ -327,11 +398,20 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, struct drm_gem_object *obj, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - ret = slow_shmem_copy(user_pages[data_page_index], - data_page_offset, - obj_priv->pages[shmem_page_index], - shmem_page_offset, - page_length); + if (do_bit17_swizzling) { + ret = slow_shmem_bit17_copy(obj_priv->pages[shmem_page_index], + shmem_page_offset, + user_pages[data_page_index], + data_page_offset, + page_length, + 1); + } else { + ret = slow_shmem_copy(user_pages[data_page_index], + data_page_offset, + obj_priv->pages[shmem_page_index], + shmem_page_offset, + page_length); + } if (ret) goto fail_put_pages; @@ -383,9 +463,14 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - ret = i915_gem_shmem_pread_fast(dev, obj, args, file_priv); - if (ret != 0) + if (i915_gem_object_needs_bit17_swizzle(obj)) { ret = i915_gem_shmem_pread_slow(dev, obj, args, file_priv); + } else { + ret = i915_gem_shmem_pread_fast(dev, obj, args, file_priv); + if (ret != 0) + ret = i915_gem_shmem_pread_slow(dev, obj, args, + file_priv); + } drm_gem_object_unreference(obj); @@ -727,6 +812,7 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, struct drm_gem_object *obj, int page_length; int ret; uint64_t data_ptr = args->data_ptr; + int do_bit17_swizzling; remain = args->size; @@ -751,6 +837,8 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, struct drm_gem_object *obj, goto fail_put_user_pages; } + do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); + mutex_lock(&dev->struct_mutex); ret = i915_gem_object_get_pages(obj); @@ -785,11 +873,20 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, struct drm_gem_object *obj, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - ret = slow_shmem_copy(obj_priv->pages[shmem_page_index], - shmem_page_offset, - user_pages[data_page_index], - data_page_offset, - page_length); + if (do_bit17_swizzling) { + ret = slow_shmem_bit17_copy(obj_priv->pages[shmem_page_index], + shmem_page_offset, + user_pages[data_page_index], + data_page_offset, + page_length, + 0); + } else { + ret = slow_shmem_copy(obj_priv->pages[shmem_page_index], + shmem_page_offset, + user_pages[data_page_index], + data_page_offset, + page_length); + } if (ret) goto fail_put_pages; @@ -854,6 +951,8 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, ret = i915_gem_gtt_pwrite_slow(dev, obj, args, file_priv); } + } else if (i915_gem_object_needs_bit17_swizzle(obj)) { + ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file_priv); } else { ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file_priv); if (ret == -EFAULT) { @@ -1285,7 +1384,7 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data, return 0; } -static void +void i915_gem_object_put_pages(struct drm_gem_object *obj) { struct drm_i915_gem_object *obj_priv = obj->driver_private; @@ -1297,6 +1396,9 @@ i915_gem_object_put_pages(struct drm_gem_object *obj) if (--obj_priv->pages_refcount != 0) return; + if (obj_priv->tiling_mode != I915_TILING_NONE) + i915_gem_object_save_bit_17_swizzle(obj); + for (i = 0; i < page_count; i++) if (obj_priv->pages[i] != NULL) { if (obj_priv->dirty) @@ -1494,8 +1596,19 @@ i915_gem_retire_request(struct drm_device *dev, if (obj->write_domain != 0) i915_gem_object_move_to_flushing(obj); - else + else { + /* Take a reference on the object so it won't be + * freed while the spinlock is held. The list + * protection for this spinlock is safe when breaking + * the lock like this since the next thing we do + * is just get the head of the list again. + */ + drm_gem_object_reference(obj); i915_gem_object_move_to_inactive(obj); + spin_unlock(&dev_priv->mm.active_list_lock); + drm_gem_object_unreference(obj); + spin_lock(&dev_priv->mm.active_list_lock); + } } out: spin_unlock(&dev_priv->mm.active_list_lock); @@ -1884,7 +1997,7 @@ i915_gem_evict_everything(struct drm_device *dev) return ret; } -static int +int i915_gem_object_get_pages(struct drm_gem_object *obj) { struct drm_i915_gem_object *obj_priv = obj->driver_private; @@ -1922,6 +2035,10 @@ i915_gem_object_get_pages(struct drm_gem_object *obj) } obj_priv->pages[i] = page; } + + if (obj_priv->tiling_mode != I915_TILING_NONE) + i915_gem_object_do_bit_17_swizzle(obj); + return 0; } @@ -3002,13 +3119,13 @@ i915_gem_get_relocs_from_user(struct drm_i915_gem_exec_object *exec_list, drm_free(*relocs, reloc_count * sizeof(**relocs), DRM_MEM_DRIVER); *relocs = NULL; - return ret; + return -EFAULT; } reloc_index += exec_list[i].relocation_count; } - return ret; + return 0; } static int @@ -3017,23 +3134,28 @@ i915_gem_put_relocs_to_user(struct drm_i915_gem_exec_object *exec_list, struct drm_i915_gem_relocation_entry *relocs) { uint32_t reloc_count = 0, i; - int ret; + int ret = 0; for (i = 0; i < buffer_count; i++) { struct drm_i915_gem_relocation_entry __user *user_relocs; + int unwritten; user_relocs = (void __user *)(uintptr_t)exec_list[i].relocs_ptr; - if (ret == 0) { - ret = copy_to_user(user_relocs, - &relocs[reloc_count], - exec_list[i].relocation_count * - sizeof(*relocs)); + unwritten = copy_to_user(user_relocs, + &relocs[reloc_count], + exec_list[i].relocation_count * + sizeof(*relocs)); + + if (unwritten) { + ret = -EFAULT; + goto err; } reloc_count += exec_list[i].relocation_count; } +err: drm_free(relocs, reloc_count * sizeof(*relocs), DRM_MEM_DRIVER); return ret; @@ -3243,7 +3365,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec_offset = exec_list[args->buffer_count - 1].offset; #if WATCH_EXEC - i915_gem_dump_object(object_list[args->buffer_count - 1], + i915_gem_dump_object(batch_obj, args->batch_len, __func__, ~0); @@ -3308,10 +3430,12 @@ err: (uintptr_t) args->buffers_ptr, exec_list, sizeof(*exec_list) * args->buffer_count); - if (ret) + if (ret) { + ret = -EFAULT; DRM_ERROR("failed to copy %d exec entries " "back to user (%d)\n", args->buffer_count, ret); + } } /* Copy the updated relocations out regardless of current error @@ -3593,6 +3717,7 @@ void i915_gem_free_object(struct drm_gem_object *obj) i915_gem_free_mmap_offset(obj); drm_free(obj_priv->page_cpu_valid, 1, DRM_MEM_DRIVER); + kfree(obj_priv->bit_17); drm_free(obj->driver_private, 1, DRM_MEM_DRIVER); } diff --git a/drivers/gpu/drm/i915/i915_gem_debugfs.c b/drivers/gpu/drm/i915/i915_gem_debugfs.c index a1ac0c5e730..986f1082c59 100644 --- a/drivers/gpu/drm/i915/i915_gem_debugfs.c +++ b/drivers/gpu/drm/i915/i915_gem_debugfs.c @@ -234,6 +234,96 @@ static int i915_hws_info(struct seq_file *m, void *data) return 0; } +static void i915_dump_pages(struct seq_file *m, struct page **pages, int page_count) +{ + int page, i; + uint32_t *mem; + + for (page = 0; page < page_count; page++) { + mem = kmap(pages[page]); + for (i = 0; i < PAGE_SIZE; i += 4) + seq_printf(m, "%08x : %08x\n", i, mem[i / 4]); + kunmap(pages[page]); + } +} + +static int i915_batchbuffer_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_gem_object *obj; + struct drm_i915_gem_object *obj_priv; + int ret; + + spin_lock(&dev_priv->mm.active_list_lock); + + list_for_each_entry(obj_priv, &dev_priv->mm.active_list, list) { + obj = obj_priv->obj; + if (obj->read_domains & I915_GEM_DOMAIN_COMMAND) { + ret = i915_gem_object_get_pages(obj); + if (ret) { + DRM_ERROR("Failed to get pages: %d\n", ret); + spin_unlock(&dev_priv->mm.active_list_lock); + return ret; + } + + seq_printf(m, "--- gtt_offset = 0x%08x\n", obj_priv->gtt_offset); + i915_dump_pages(m, obj_priv->pages, obj->size / PAGE_SIZE); + + i915_gem_object_put_pages(obj); + } + } + + spin_unlock(&dev_priv->mm.active_list_lock); + + return 0; +} + +static int i915_ringbuffer_data(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + u8 *virt; + uint32_t *ptr, off; + + if (!dev_priv->ring.ring_obj) { + seq_printf(m, "No ringbuffer setup\n"); + return 0; + } + + virt = dev_priv->ring.virtual_start; + + for (off = 0; off < dev_priv->ring.Size; off += 4) { + ptr = (uint32_t *)(virt + off); + seq_printf(m, "%08x : %08x\n", off, *ptr); + } + + return 0; +} + +static int i915_ringbuffer_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + unsigned int head, tail, mask; + + head = I915_READ(PRB0_HEAD) & HEAD_ADDR; + tail = I915_READ(PRB0_TAIL) & TAIL_ADDR; + mask = dev_priv->ring.tail_mask; + + seq_printf(m, "RingHead : %08x\n", head); + seq_printf(m, "RingTail : %08x\n", tail); + seq_printf(m, "RingMask : %08x\n", mask); + seq_printf(m, "RingSize : %08lx\n", dev_priv->ring.Size); + seq_printf(m, "Acthd : %08x\n", I915_READ(IS_I965G(dev) ? ACTHD_I965 : ACTHD)); + + return 0; +} + + static struct drm_info_list i915_gem_debugfs_list[] = { {"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST}, {"i915_gem_flushing", i915_gem_object_list_info, 0, (void *) FLUSHING_LIST}, @@ -243,6 +333,9 @@ static struct drm_info_list i915_gem_debugfs_list[] = { {"i915_gem_fence_regs", i915_gem_fence_regs_info, 0}, {"i915_gem_interrupt", i915_interrupt_info, 0}, {"i915_gem_hws", i915_hws_info, 0}, + {"i915_ringbuffer_data", i915_ringbuffer_data, 0}, + {"i915_ringbuffer_info", i915_ringbuffer_info, 0}, + {"i915_batchbuffers", i915_batchbuffer_info, 0}, }; #define I915_GEM_DEBUGFS_ENTRIES ARRAY_SIZE(i915_gem_debugfs_list) diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 6be3f927c86..f27e523c764 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -25,6 +25,8 @@ * */ +#include "linux/string.h" +#include "linux/bitops.h" #include "drmP.h" #include "drm.h" #include "i915_drm.h" @@ -127,8 +129,8 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) swizzle_y = I915_BIT_6_SWIZZLE_9_11; } else { /* Bit 17 swizzling by the CPU in addition. */ - swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN; - swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN; + swizzle_x = I915_BIT_6_SWIZZLE_9_10_17; + swizzle_y = I915_BIT_6_SWIZZLE_9_17; } break; } @@ -288,6 +290,19 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, args->swizzle_mode = dev_priv->mm.bit_6_swizzle_x; else args->swizzle_mode = dev_priv->mm.bit_6_swizzle_y; + + /* Hide bit 17 swizzling from the user. This prevents old Mesa + * from aborting the application on sw fallbacks to bit 17, + * and we use the pread/pwrite bit17 paths to swizzle for it. + * If there was a user that was relying on the swizzle + * information for drm_intel_bo_map()ed reads/writes this would + * break it, but we don't have any of those. + */ + if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17) + args->swizzle_mode = I915_BIT_6_SWIZZLE_9; + if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17) + args->swizzle_mode = I915_BIT_6_SWIZZLE_9_10; + /* If we can't handle the swizzling, make it untiled. */ if (args->swizzle_mode == I915_BIT_6_SWIZZLE_UNKNOWN) { args->tiling_mode = I915_TILING_NONE; @@ -354,8 +369,100 @@ i915_gem_get_tiling(struct drm_device *dev, void *data, DRM_ERROR("unknown tiling mode\n"); } + /* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */ + if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17) + args->swizzle_mode = I915_BIT_6_SWIZZLE_9; + if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17) + args->swizzle_mode = I915_BIT_6_SWIZZLE_9_10; + drm_gem_object_unreference(obj); mutex_unlock(&dev->struct_mutex); return 0; } + +/** + * Swap every 64 bytes of this page around, to account for it having a new + * bit 17 of its physical address and therefore being interpreted differently + * by the GPU. + */ +static int +i915_gem_swizzle_page(struct page *page) +{ + char *vaddr; + int i; + char temp[64]; + + vaddr = kmap(page); + if (vaddr == NULL) + return -ENOMEM; + + for (i = 0; i < PAGE_SIZE; i += 128) { + memcpy(temp, &vaddr[i], 64); + memcpy(&vaddr[i], &vaddr[i + 64], 64); + memcpy(&vaddr[i + 64], temp, 64); + } + + kunmap(page); + + return 0; +} + +void +i915_gem_object_do_bit_17_swizzle(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_gem_object *obj_priv = obj->driver_private; + int page_count = obj->size >> PAGE_SHIFT; + int i; + + if (dev_priv->mm.bit_6_swizzle_x != I915_BIT_6_SWIZZLE_9_10_17) + return; + + if (obj_priv->bit_17 == NULL) + return; + + for (i = 0; i < page_count; i++) { + char new_bit_17 = page_to_phys(obj_priv->pages[i]) >> 17; + if ((new_bit_17 & 0x1) != + (test_bit(i, obj_priv->bit_17) != 0)) { + int ret = i915_gem_swizzle_page(obj_priv->pages[i]); + if (ret != 0) { + DRM_ERROR("Failed to swizzle page\n"); + return; + } + set_page_dirty(obj_priv->pages[i]); + } + } +} + +void +i915_gem_object_save_bit_17_swizzle(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_gem_object *obj_priv = obj->driver_private; + int page_count = obj->size >> PAGE_SHIFT; + int i; + + if (dev_priv->mm.bit_6_swizzle_x != I915_BIT_6_SWIZZLE_9_10_17) + return; + + if (obj_priv->bit_17 == NULL) { + obj_priv->bit_17 = kmalloc(BITS_TO_LONGS(page_count) * + sizeof(long), GFP_KERNEL); + if (obj_priv->bit_17 == NULL) { + DRM_ERROR("Failed to allocate memory for bit 17 " + "record\n"); + return; + } + } + + for (i = 0; i < page_count; i++) { + if (page_to_phys(obj_priv->pages[i]) & (1 << 17)) + __set_bit(i, obj_priv->bit_17); + else + __clear_bit(i, obj_priv->bit_17); + } +} diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 64773ce5296..c2c8e95ff14 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -367,6 +367,7 @@ static const intel_limit_t intel_limits[] = { .p1 = { .min = I9XX_P1_MIN, .max = I9XX_P1_MAX }, .p2 = { .dot_limit = I9XX_P2_SDVO_DAC_SLOW_LIMIT, .p2_slow = I9XX_P2_SDVO_DAC_SLOW, .p2_fast = I9XX_P2_SDVO_DAC_FAST }, + .find_pll = intel_find_best_PLL, }, { /* INTEL_LIMIT_IGD_LVDS */ .dot = { .min = I9XX_DOT_MIN, .max = I9XX_DOT_MAX }, @@ -380,6 +381,7 @@ static const intel_limit_t intel_limits[] = { /* IGD only supports single-channel mode. */ .p2 = { .dot_limit = I9XX_P2_LVDS_SLOW_LIMIT, .p2_slow = I9XX_P2_LVDS_SLOW, .p2_fast = I9XX_P2_LVDS_SLOW }, + .find_pll = intel_find_best_PLL, }, }; diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index b7f0ebe9f81..3e094beecb9 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -864,8 +864,8 @@ static void intelfb_sysrq(int dummy1, struct tty_struct *dummy3) static struct sysrq_key_op sysrq_intelfb_restore_op = { .handler = intelfb_sysrq, - .help_msg = "force fb", - .action_msg = "force restore of fb console", + .help_msg = "force-fb(G)", + .action_msg = "Restore framebuffer console", }; int intelfb_probe(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index b06a4a3ff08..55037422538 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -38,7 +38,7 @@ struct intel_hdmi_priv { u32 sdvox_reg; u32 save_SDVOX; - int has_hdmi_sink; + bool has_hdmi_sink; }; static void intel_hdmi_mode_set(struct drm_encoder *encoder, @@ -128,6 +128,22 @@ static bool intel_hdmi_mode_fixup(struct drm_encoder *encoder, return true; } +static void +intel_hdmi_sink_detect(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; + struct edid *edid = NULL; + + edid = drm_get_edid(&intel_output->base, + &intel_output->ddc_bus->adapter); + if (edid != NULL) { + hdmi_priv->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + kfree(edid); + intel_output->base.display_info.raw_edid = NULL; + } +} + static enum drm_connector_status intel_hdmi_detect(struct drm_connector *connector) { @@ -158,9 +174,10 @@ intel_hdmi_detect(struct drm_connector *connector) return connector_status_unknown; } - if ((I915_READ(PORT_HOTPLUG_STAT) & bit) != 0) + if ((I915_READ(PORT_HOTPLUG_STAT) & bit) != 0) { + intel_hdmi_sink_detect(connector); return connector_status_connected; - else + } else return connector_status_disconnected; } diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 7b31f55f55c..9913651c1e1 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1357,6 +1357,23 @@ void intel_sdvo_set_hotplug(struct drm_connector *connector, int on) intel_sdvo_read_response(intel_output, &response, 2); } +static void +intel_sdvo_hdmi_sink_detect(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; + struct edid *edid = NULL; + + intel_sdvo_set_control_bus_switch(intel_output, sdvo_priv->ddc_bus); + edid = drm_get_edid(&intel_output->base, + &intel_output->ddc_bus->adapter); + if (edid != NULL) { + sdvo_priv->is_hdmi = drm_detect_hdmi_monitor(edid); + kfree(edid); + intel_output->base.display_info.raw_edid = NULL; + } +} + static enum drm_connector_status intel_sdvo_detect(struct drm_connector *connector) { u8 response[2]; @@ -1371,9 +1388,10 @@ static enum drm_connector_status intel_sdvo_detect(struct drm_connector *connect if (status != SDVO_CMD_STATUS_SUCCESS) return connector_status_unknown; - if ((response[0] != 0) || (response[1] != 0)) + if ((response[0] != 0) || (response[1] != 0)) { + intel_sdvo_hdmi_sink_detect(connector); return connector_status_connected; - else + } else return connector_status_disconnected; } diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 0e8a9185f67..d73f5f473e3 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -692,6 +692,16 @@ config SENSORS_PCF8591 These devices are hard to detect and rarely found on mainstream hardware. If unsure, say N. +config SENSORS_SHT15 + tristate "Sensiron humidity and temperature sensors. SHT15 and compat." + depends on GENERIC_GPIO + help + If you say yes here you get support for the Sensiron SHT10, SHT11, + SHT15, SHT71, SHT75 humidity and temperature sensors. + + This driver can also be built as a module. If so, the module + will be called sht15. + config SENSORS_SIS5595 tristate "Silicon Integrated Systems Corp. SiS5595" depends on PCI diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 1d3757837b4..0ae26984ba4 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_SENSORS_MAX6650) += max6650.o obj-$(CONFIG_SENSORS_PC87360) += pc87360.o obj-$(CONFIG_SENSORS_PC87427) += pc87427.o obj-$(CONFIG_SENSORS_PCF8591) += pcf8591.o +obj-$(CONFIG_SENSORS_SHT15) += sht15.o obj-$(CONFIG_SENSORS_SIS5595) += sis5595.o obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o obj-$(CONFIG_SENSORS_SMSC47M1) += smsc47m1.o diff --git a/drivers/hwmon/hp_accel.c b/drivers/hwmon/hp_accel.c index 55d3dc565be..abca7e9f953 100644 --- a/drivers/hwmon/hp_accel.c +++ b/drivers/hwmon/hp_accel.c @@ -34,7 +34,6 @@ #include <linux/wait.h> #include <linux/poll.h> #include <linux/freezer.h> -#include <linux/version.h> #include <linux/uaccess.h> #include <linux/leds.h> #include <acpi/acpi_drivers.h> diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c new file mode 100644 index 00000000000..6cbdc2fea73 --- /dev/null +++ b/drivers/hwmon/sht15.c @@ -0,0 +1,692 @@ +/* + * sht15.c - support for the SHT15 Temperature and Humidity Sensor + * + * Copyright (c) 2009 Jonathan Cameron + * + * Copyright (c) 2007 Wouter Horre + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Currently ignoring checksum on readings. + * Default resolution only (14bit temp, 12bit humidity) + * Ignoring battery status. + * Heater not enabled. + * Timings are all conservative. + * + * Data sheet available (1/2009) at + * http://www.sensirion.ch/en/pdf/product_information/Datasheet-humidity-sensor-SHT1x.pdf + * + * Regulator supply name = vcc + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/gpio.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/mutex.h> +#include <linux/platform_device.h> +#include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/err.h> +#include <linux/sht15.h> +#include <linux/regulator/consumer.h> +#include <asm/atomic.h> + +#define SHT15_MEASURE_TEMP 3 +#define SHT15_MEASURE_RH 5 + +#define SHT15_READING_NOTHING 0 +#define SHT15_READING_TEMP 1 +#define SHT15_READING_HUMID 2 + +/* Min timings in nsecs */ +#define SHT15_TSCKL 100 /* clock low */ +#define SHT15_TSCKH 100 /* clock high */ +#define SHT15_TSU 150 /* data setup time */ + +/** + * struct sht15_temppair - elements of voltage dependant temp calc + * @vdd: supply voltage in microvolts + * @d1: see data sheet + */ +struct sht15_temppair { + int vdd; /* microvolts */ + int d1; +}; + +/* Table 9 from data sheet - relates temperature calculation + * to supply voltage. + */ +static const struct sht15_temppair temppoints[] = { + { 2500000, -39400 }, + { 3000000, -39600 }, + { 3500000, -39700 }, + { 4000000, -39800 }, + { 5000000, -40100 }, +}; + +/** + * struct sht15_data - device instance specific data + * @pdata: platform data (gpio's etc) + * @read_work: bh of interrupt handler + * @wait_queue: wait queue for getting values from device + * @val_temp: last temperature value read from device + * @val_humid: last humidity value read from device + * @flag: status flag used to identify what the last request was + * @valid: are the current stored values valid (start condition) + * @last_updat: time of last update + * @read_lock: mutex to ensure only one read in progress + * at a time. + * @dev: associate device structure + * @hwmon_dev: device associated with hwmon subsystem + * @reg: associated regulator (if specified) + * @nb: notifier block to handle notifications of voltage changes + * @supply_uV: local copy of supply voltage used to allow + * use of regulator consumer if available + * @supply_uV_valid: indicates that an updated value has not yet + * been obtained from the regulator and so any calculations + * based upon it will be invalid. + * @update_supply_work: work struct that is used to update the supply_uV + * @interrupt_handled: flag used to indicate a hander has been scheduled + */ +struct sht15_data { + struct sht15_platform_data *pdata; + struct work_struct read_work; + wait_queue_head_t wait_queue; + uint16_t val_temp; + uint16_t val_humid; + u8 flag; + u8 valid; + unsigned long last_updat; + struct mutex read_lock; + struct device *dev; + struct device *hwmon_dev; + struct regulator *reg; + struct notifier_block nb; + int supply_uV; + int supply_uV_valid; + struct work_struct update_supply_work; + atomic_t interrupt_handled; +}; + +/** + * sht15_connection_reset() - reset the comms interface + * @data: sht15 specific data + * + * This implements section 3.4 of the data sheet + */ +static void sht15_connection_reset(struct sht15_data *data) +{ + int i; + gpio_direction_output(data->pdata->gpio_data, 1); + ndelay(SHT15_TSCKL); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + for (i = 0; i < 9; ++i) { + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + } +} +/** + * sht15_send_bit() - send an individual bit to the device + * @data: device state data + * @val: value of bit to be sent + **/ +static inline void sht15_send_bit(struct sht15_data *data, int val) +{ + + gpio_set_value(data->pdata->gpio_data, val); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); /* clock low time */ +} + +/** + * sht15_transmission_start() - specific sequence for new transmission + * + * @data: device state data + * Timings for this are not documented on the data sheet, so very + * conservative ones used in implementation. This implements + * figure 12 on the data sheet. + **/ +static void sht15_transmission_start(struct sht15_data *data) +{ + /* ensure data is high and output */ + gpio_direction_output(data->pdata->gpio_data, 1); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + gpio_set_value(data->pdata->gpio_data, 0); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + gpio_set_value(data->pdata->gpio_data, 1); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); +} +/** + * sht15_send_byte() - send a single byte to the device + * @data: device state + * @byte: value to be sent + **/ +static void sht15_send_byte(struct sht15_data *data, u8 byte) +{ + int i; + for (i = 0; i < 8; i++) { + sht15_send_bit(data, !!(byte & 0x80)); + byte <<= 1; + } +} +/** + * sht15_wait_for_response() - checks for ack from device + * @data: device state + **/ +static int sht15_wait_for_response(struct sht15_data *data) +{ + gpio_direction_input(data->pdata->gpio_data); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + if (gpio_get_value(data->pdata->gpio_data)) { + gpio_set_value(data->pdata->gpio_sck, 0); + dev_err(data->dev, "Command not acknowledged\n"); + sht15_connection_reset(data); + return -EIO; + } + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + return 0; +} + +/** + * sht15_send_cmd() - Sends a command to the device. + * @data: device state + * @cmd: command byte to be sent + * + * On entry, sck is output low, data is output pull high + * and the interrupt disabled. + **/ +static int sht15_send_cmd(struct sht15_data *data, u8 cmd) +{ + int ret = 0; + sht15_transmission_start(data); + sht15_send_byte(data, cmd); + ret = sht15_wait_for_response(data); + return ret; +} +/** + * sht15_update_single_val() - get a new value from device + * @data: device instance specific data + * @command: command sent to request value + * @timeout_msecs: timeout after which comms are assumed + * to have failed are reset. + **/ +static inline int sht15_update_single_val(struct sht15_data *data, + int command, + int timeout_msecs) +{ + int ret; + ret = sht15_send_cmd(data, command); + if (ret) + return ret; + + gpio_direction_input(data->pdata->gpio_data); + atomic_set(&data->interrupt_handled, 0); + + enable_irq(gpio_to_irq(data->pdata->gpio_data)); + if (gpio_get_value(data->pdata->gpio_data) == 0) { + disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data)); + /* Only relevant if the interrupt hasn't occured. */ + if (!atomic_read(&data->interrupt_handled)) + schedule_work(&data->read_work); + } + ret = wait_event_timeout(data->wait_queue, + (data->flag == SHT15_READING_NOTHING), + msecs_to_jiffies(timeout_msecs)); + if (ret == 0) {/* timeout occurred */ + disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data));; + sht15_connection_reset(data); + return -ETIME; + } + return 0; +} + +/** + * sht15_update_vals() - get updated readings from device if too old + * @data: device state + **/ +static int sht15_update_vals(struct sht15_data *data) +{ + int ret = 0; + int timeout = HZ; + + mutex_lock(&data->read_lock); + if (time_after(jiffies, data->last_updat + timeout) + || !data->valid) { + data->flag = SHT15_READING_HUMID; + ret = sht15_update_single_val(data, SHT15_MEASURE_RH, 160); + if (ret) + goto error_ret; + data->flag = SHT15_READING_TEMP; + ret = sht15_update_single_val(data, SHT15_MEASURE_TEMP, 400); + if (ret) + goto error_ret; + data->valid = 1; + data->last_updat = jiffies; + } +error_ret: + mutex_unlock(&data->read_lock); + + return ret; +} + +/** + * sht15_calc_temp() - convert the raw reading to a temperature + * @data: device state + * + * As per section 4.3 of the data sheet. + **/ +static inline int sht15_calc_temp(struct sht15_data *data) +{ + int d1 = 0; + int i; + + for (i = 1; i < ARRAY_SIZE(temppoints) - 1; i++) + /* Find pointer to interpolate */ + if (data->supply_uV > temppoints[i - 1].vdd) { + d1 = (data->supply_uV/1000 - temppoints[i - 1].vdd) + * (temppoints[i].d1 - temppoints[i - 1].d1) + / (temppoints[i].vdd - temppoints[i - 1].vdd) + + temppoints[i - 1].d1; + break; + } + + return data->val_temp*10 + d1; +} + +/** + * sht15_calc_humid() - using last temperature convert raw to humid + * @data: device state + * + * This is the temperature compensated version as per section 4.2 of + * the data sheet. + **/ +static inline int sht15_calc_humid(struct sht15_data *data) +{ + int RHlinear; /* milli percent */ + int temp = sht15_calc_temp(data); + + const int c1 = -4; + const int c2 = 40500; /* x 10 ^ -6 */ + const int c3 = 2800; /* x10 ^ -9 */ + + RHlinear = c1*1000 + + c2 * data->val_humid/1000 + + (data->val_humid * data->val_humid * c3)/1000000; + return (temp - 25000) * (10000 + 800 * data->val_humid) + / 1000000 + RHlinear; +} + +static ssize_t sht15_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int ret; + struct sht15_data *data = dev_get_drvdata(dev); + + /* Technically no need to read humidity as well */ + ret = sht15_update_vals(data); + + return ret ? ret : sprintf(buf, "%d\n", + sht15_calc_temp(data)); +} + +static ssize_t sht15_show_humidity(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int ret; + struct sht15_data *data = dev_get_drvdata(dev); + + ret = sht15_update_vals(data); + + return ret ? ret : sprintf(buf, "%d\n", sht15_calc_humid(data)); + +}; +static ssize_t show_name(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct platform_device *pdev = to_platform_device(dev); + return sprintf(buf, "%s\n", pdev->name); +} + +static SENSOR_DEVICE_ATTR(temp1_input, + S_IRUGO, sht15_show_temp, + NULL, 0); +static SENSOR_DEVICE_ATTR(humidity1_input, + S_IRUGO, sht15_show_humidity, + NULL, 0); +static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); +static struct attribute *sht15_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_humidity1_input.dev_attr.attr, + &dev_attr_name.attr, + NULL, +}; + +static const struct attribute_group sht15_attr_group = { + .attrs = sht15_attrs, +}; + +static irqreturn_t sht15_interrupt_fired(int irq, void *d) +{ + struct sht15_data *data = d; + /* First disable the interrupt */ + disable_irq_nosync(irq); + atomic_inc(&data->interrupt_handled); + /* Then schedule a reading work struct */ + if (data->flag != SHT15_READING_NOTHING) + schedule_work(&data->read_work); + return IRQ_HANDLED; +} + +/* Each byte of data is acknowledged by pulling the data line + * low for one clock pulse. + */ +static void sht15_ack(struct sht15_data *data) +{ + gpio_direction_output(data->pdata->gpio_data, 0); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_data, 1); + + gpio_direction_input(data->pdata->gpio_data); +} +/** + * sht15_end_transmission() - notify device of end of transmission + * @data: device state + * + * This is basically a NAK. (single clock pulse, data high) + **/ +static void sht15_end_transmission(struct sht15_data *data) +{ + gpio_direction_output(data->pdata->gpio_data, 1); + ndelay(SHT15_TSU); + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); +} + +static void sht15_bh_read_data(struct work_struct *work_s) +{ + int i; + uint16_t val = 0; + struct sht15_data *data + = container_of(work_s, struct sht15_data, + read_work); + /* Firstly, verify the line is low */ + if (gpio_get_value(data->pdata->gpio_data)) { + /* If not, then start the interrupt again - care + here as could have gone low in meantime so verify + it hasn't! + */ + atomic_set(&data->interrupt_handled, 0); + enable_irq(gpio_to_irq(data->pdata->gpio_data)); + /* If still not occured or another handler has been scheduled */ + if (gpio_get_value(data->pdata->gpio_data) + || atomic_read(&data->interrupt_handled)) + return; + } + /* Read the data back from the device */ + for (i = 0; i < 16; ++i) { + val <<= 1; + gpio_set_value(data->pdata->gpio_sck, 1); + ndelay(SHT15_TSCKH); + val |= !!gpio_get_value(data->pdata->gpio_data); + gpio_set_value(data->pdata->gpio_sck, 0); + ndelay(SHT15_TSCKL); + if (i == 7) + sht15_ack(data); + } + /* Tell the device we are done */ + sht15_end_transmission(data); + + switch (data->flag) { + case SHT15_READING_TEMP: + data->val_temp = val; + break; + case SHT15_READING_HUMID: + data->val_humid = val; + break; + } + + data->flag = SHT15_READING_NOTHING; + wake_up(&data->wait_queue); +} + +static void sht15_update_voltage(struct work_struct *work_s) +{ + struct sht15_data *data + = container_of(work_s, struct sht15_data, + update_supply_work); + data->supply_uV = regulator_get_voltage(data->reg); +} + +/** + * sht15_invalidate_voltage() - mark supply voltage invalid when notified by reg + * @nb: associated notification structure + * @event: voltage regulator state change event code + * @ignored: function parameter - ignored here + * + * Note that as the notification code holds the regulator lock, we have + * to schedule an update of the supply voltage rather than getting it directly. + **/ +static int sht15_invalidate_voltage(struct notifier_block *nb, + unsigned long event, + void *ignored) +{ + struct sht15_data *data = container_of(nb, struct sht15_data, nb); + + if (event == REGULATOR_EVENT_VOLTAGE_CHANGE) + data->supply_uV_valid = false; + schedule_work(&data->update_supply_work); + + return NOTIFY_OK; +} + +static int __devinit sht15_probe(struct platform_device *pdev) +{ + int ret = 0; + struct sht15_data *data = kzalloc(sizeof(*data), GFP_KERNEL); + + if (!data) { + ret = -ENOMEM; + dev_err(&pdev->dev, "kzalloc failed"); + goto error_ret; + } + + INIT_WORK(&data->read_work, sht15_bh_read_data); + INIT_WORK(&data->update_supply_work, sht15_update_voltage); + platform_set_drvdata(pdev, data); + mutex_init(&data->read_lock); + data->dev = &pdev->dev; + init_waitqueue_head(&data->wait_queue); + + if (pdev->dev.platform_data == NULL) { + dev_err(&pdev->dev, "no platform data supplied"); + goto err_free_data; + } + data->pdata = pdev->dev.platform_data; + data->supply_uV = data->pdata->supply_mv*1000; + +/* If a regulator is available, query what the supply voltage actually is!*/ + data->reg = regulator_get(data->dev, "vcc"); + if (!IS_ERR(data->reg)) { + data->supply_uV = regulator_get_voltage(data->reg); + regulator_enable(data->reg); + /* setup a notifier block to update this if another device + * causes the voltage to change */ + data->nb.notifier_call = &sht15_invalidate_voltage; + ret = regulator_register_notifier(data->reg, &data->nb); + } +/* Try requesting the GPIOs */ + ret = gpio_request(data->pdata->gpio_sck, "SHT15 sck"); + if (ret) { + dev_err(&pdev->dev, "gpio request failed"); + goto err_free_data; + } + gpio_direction_output(data->pdata->gpio_sck, 0); + ret = gpio_request(data->pdata->gpio_data, "SHT15 data"); + if (ret) { + dev_err(&pdev->dev, "gpio request failed"); + goto err_release_gpio_sck; + } + ret = sysfs_create_group(&pdev->dev.kobj, &sht15_attr_group); + if (ret) { + dev_err(&pdev->dev, "sysfs create failed"); + goto err_free_data; + } + + ret = request_irq(gpio_to_irq(data->pdata->gpio_data), + sht15_interrupt_fired, + IRQF_TRIGGER_FALLING, + "sht15 data", + data); + if (ret) { + dev_err(&pdev->dev, "failed to get irq for data line"); + goto err_release_gpio_data; + } + disable_irq_nosync(gpio_to_irq(data->pdata->gpio_data)); + sht15_connection_reset(data); + sht15_send_cmd(data, 0x1E); + + data->hwmon_dev = hwmon_device_register(data->dev); + if (IS_ERR(data->hwmon_dev)) { + ret = PTR_ERR(data->hwmon_dev); + goto err_release_gpio_data; + } + return 0; + +err_release_gpio_data: + gpio_free(data->pdata->gpio_data); +err_release_gpio_sck: + gpio_free(data->pdata->gpio_sck); +err_free_data: + kfree(data); +error_ret: + + return ret; +} + +static int __devexit sht15_remove(struct platform_device *pdev) +{ + struct sht15_data *data = platform_get_drvdata(pdev); + + /* Make sure any reads from the device are done and + * prevent new ones beginnning */ + mutex_lock(&data->read_lock); + hwmon_device_unregister(data->hwmon_dev); + sysfs_remove_group(&pdev->dev.kobj, &sht15_attr_group); + if (!IS_ERR(data->reg)) { + regulator_unregister_notifier(data->reg, &data->nb); + regulator_disable(data->reg); + regulator_put(data->reg); + } + + free_irq(gpio_to_irq(data->pdata->gpio_data), data); + gpio_free(data->pdata->gpio_data); + gpio_free(data->pdata->gpio_sck); + mutex_unlock(&data->read_lock); + kfree(data); + return 0; +} + + +static struct platform_driver sht_drivers[] = { + { + .driver = { + .name = "sht10", + .owner = THIS_MODULE, + }, + .probe = sht15_probe, + .remove = sht15_remove, + }, { + .driver = { + .name = "sht11", + .owner = THIS_MODULE, + }, + .probe = sht15_probe, + .remove = sht15_remove, + }, { + .driver = { + .name = "sht15", + .owner = THIS_MODULE, + }, + .probe = sht15_probe, + .remove = sht15_remove, + }, { + .driver = { + .name = "sht71", + .owner = THIS_MODULE, + }, + .probe = sht15_probe, + .remove = sht15_remove, + }, { + .driver = { + .name = "sht75", + .owner = THIS_MODULE, + }, + .probe = sht15_probe, + .remove = sht15_remove, + }, +}; + + +static int __init sht15_init(void) +{ + int ret; + int i; + + for (i = 0; i < ARRAY_SIZE(sht_drivers); i++) { + ret = platform_driver_register(&sht_drivers[i]); + if (ret) + goto error_unreg; + } + + return 0; + +error_unreg: + while (--i >= 0) + platform_driver_unregister(&sht_drivers[i]); + + return ret; +} +module_init(sht15_init); + +static void __exit sht15_exit(void) +{ + int i; + for (i = ARRAY_SIZE(sht_drivers) - 1; i >= 0; i--) + platform_driver_unregister(&sht_drivers[i]); +} +module_exit(sht15_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-bio-list.h b/drivers/md/dm-bio-list.h deleted file mode 100644 index 345098b4ca7..00000000000 --- a/drivers/md/dm-bio-list.h +++ /dev/null @@ -1,117 +0,0 @@ -/* - * Copyright (C) 2004 Red Hat UK Ltd. - * - * This file is released under the GPL. - */ - -#ifndef DM_BIO_LIST_H -#define DM_BIO_LIST_H - -#include <linux/bio.h> - -#ifdef CONFIG_BLOCK - -struct bio_list { - struct bio *head; - struct bio *tail; -}; - -static inline int bio_list_empty(const struct bio_list *bl) -{ - return bl->head == NULL; -} - -static inline void bio_list_init(struct bio_list *bl) -{ - bl->head = bl->tail = NULL; -} - -#define bio_list_for_each(bio, bl) \ - for (bio = (bl)->head; bio; bio = bio->bi_next) - -static inline unsigned bio_list_size(const struct bio_list *bl) -{ - unsigned sz = 0; - struct bio *bio; - - bio_list_for_each(bio, bl) - sz++; - - return sz; -} - -static inline void bio_list_add(struct bio_list *bl, struct bio *bio) -{ - bio->bi_next = NULL; - - if (bl->tail) - bl->tail->bi_next = bio; - else - bl->head = bio; - - bl->tail = bio; -} - -static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) -{ - bio->bi_next = bl->head; - - bl->head = bio; - - if (!bl->tail) - bl->tail = bio; -} - -static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) -{ - if (!bl2->head) - return; - - if (bl->tail) - bl->tail->bi_next = bl2->head; - else - bl->head = bl2->head; - - bl->tail = bl2->tail; -} - -static inline void bio_list_merge_head(struct bio_list *bl, - struct bio_list *bl2) -{ - if (!bl2->head) - return; - - if (bl->head) - bl2->tail->bi_next = bl->head; - else - bl->tail = bl2->tail; - - bl->head = bl2->head; -} - -static inline struct bio *bio_list_pop(struct bio_list *bl) -{ - struct bio *bio = bl->head; - - if (bio) { - bl->head = bl->head->bi_next; - if (!bl->head) - bl->tail = NULL; - - bio->bi_next = NULL; - } - - return bio; -} - -static inline struct bio *bio_list_get(struct bio_list *bl) -{ - struct bio *bio = bl->head; - - bl->head = bl->tail = NULL; - - return bio; -} - -#endif /* CONFIG_BLOCK */ -#endif diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 59ee1b015d2..559dbb52bc8 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -15,8 +15,6 @@ #include <linux/device-mapper.h> -#include "dm-bio-list.h" - #define DM_MSG_PREFIX "delay" struct delay_c { diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 095f77bf968..6a386ab4f7e 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -8,7 +8,6 @@ #include <linux/device-mapper.h> #include "dm-path-selector.h" -#include "dm-bio-list.h" #include "dm-bio-record.h" #include "dm-uevent.h" diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 536ef0bef15..076fbb4e967 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -5,7 +5,6 @@ * This file is released under the GPL. */ -#include "dm-bio-list.h" #include "dm-bio-record.h" #include <linux/init.h> diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 59f8d9df9e1..7b899be0b08 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -14,7 +14,6 @@ #include <linux/vmalloc.h> #include "dm.h" -#include "dm-bio-list.h" #define DM_MSG_PREFIX "region hash" diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 981a0413068..d73f17fc777 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -22,7 +22,6 @@ #include <linux/workqueue.h> #include "dm-exception-store.h" -#include "dm-bio-list.h" #define DM_MSG_PREFIX "snapshots" diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8a994be035b..424f7b048c3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -6,7 +6,6 @@ */ #include "dm.h" -#include "dm-bio-list.h" #include "dm-uevent.h" #include <linux/init.h> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 274b491a11c..36df9109cde 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -35,7 +35,6 @@ #include <linux/blkdev.h> #include <linux/seq_file.h> #include "md.h" -#include "dm-bio-list.h" #include "raid1.h" #include "bitmap.h" diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index e293d92641a..81a54f17417 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -22,7 +22,6 @@ #include <linux/blkdev.h> #include <linux/seq_file.h> #include "md.h" -#include "dm-bio-list.h" #include "raid10.h" #include "bitmap.h" diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index d184dfab963..db39f4a52f5 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -278,7 +278,7 @@ static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr, * We only use page mode writes; the alternative is sloooow. This routine * writes at most one page. */ -static ssize_t at24_eeprom_write(struct at24_data *at24, char *buf, +static ssize_t at24_eeprom_write(struct at24_data *at24, const char *buf, unsigned offset, size_t count) { struct i2c_client *client; @@ -347,8 +347,8 @@ static ssize_t at24_eeprom_write(struct at24_data *at24, char *buf, return -ETIMEDOUT; } -static ssize_t at24_write(struct at24_data *at24, - char *buf, loff_t off, size_t count) +static ssize_t at24_write(struct at24_data *at24, const char *buf, loff_t off, + size_t count) { ssize_t retval = 0; @@ -406,7 +406,7 @@ static ssize_t at24_macc_read(struct memory_accessor *macc, char *buf, return at24_read(at24, buf, offset, count); } -static ssize_t at24_macc_write(struct memory_accessor *macc, char *buf, +static ssize_t at24_macc_write(struct memory_accessor *macc, const char *buf, off_t offset, size_t count) { struct at24_data *at24 = container_of(macc, struct at24_data, macc); diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 6bc0dac5c1e..b34cb5f79ee 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -140,7 +140,8 @@ at25_bin_read(struct kobject *kobj, struct bin_attribute *bin_attr, static ssize_t -at25_ee_write(struct at25_data *at25, char *buf, loff_t off, size_t count) +at25_ee_write(struct at25_data *at25, const char *buf, loff_t off, + size_t count) { ssize_t status = 0; unsigned written = 0; @@ -276,7 +277,7 @@ static ssize_t at25_mem_read(struct memory_accessor *mem, char *buf, return at25_ee_read(at25, buf, offset, count); } -static ssize_t at25_mem_write(struct memory_accessor *mem, char *buf, +static ssize_t at25_mem_write(struct memory_accessor *mem, const char *buf, off_t offset, size_t count) { struct at25_data *at25 = container_of(mem, struct at25_data, mem); diff --git a/drivers/misc/sgi-xp/xpc.h b/drivers/misc/sgi-xp/xpc.h index 114444cfd49..b94d5f76770 100644 --- a/drivers/misc/sgi-xp/xpc.h +++ b/drivers/misc/sgi-xp/xpc.h @@ -90,18 +90,21 @@ struct xpc_rsvd_page { short max_npartitions; /* value of XPC_MAX_PARTITIONS */ u8 version; u8 pad1[3]; /* align to next u64 in 1st 64-byte cacheline */ + unsigned long ts_jiffies; /* timestamp when rsvd pg was setup by XPC */ union { - unsigned long vars_pa; /* phys address of struct xpc_vars */ - unsigned long activate_gru_mq_desc_gpa; /* phys addr of */ - /* activate mq's */ - /* gru mq descriptor */ + struct { + unsigned long vars_pa; /* phys addr */ + } sn2; + struct { + unsigned long heartbeat_gpa; /* phys addr */ + unsigned long activate_gru_mq_desc_gpa; /* phys addr */ + } uv; } sn; - unsigned long ts_jiffies; /* timestamp when rsvd pg was setup by XPC */ - u64 pad2[10]; /* align to last u64 in 2nd 64-byte cacheline */ + u64 pad2[9]; /* align to last u64 in 2nd 64-byte cacheline */ u64 SAL_nasids_size; /* SAL: size of each nasid mask in bytes */ }; -#define XPC_RP_VERSION _XPC_VERSION(2, 0) /* version 2.0 of the reserved page */ +#define XPC_RP_VERSION _XPC_VERSION(3, 0) /* version 3.0 of the reserved page */ /* * Define the structures by which XPC variables can be exported to other @@ -182,6 +185,17 @@ struct xpc_vars_part_sn2 { (XPC_RP_MACH_NASIDS(_rp) + \ xpc_nasid_mask_nlongs)) + +/* + * The following structure describes the partition's heartbeat info which + * will be periodically read by other partitions to determine whether this + * XPC is still 'alive'. + */ +struct xpc_heartbeat_uv { + unsigned long value; + unsigned long offline; /* if 0, heartbeat should be changing */ +}; + /* * Info pertinent to a GRU message queue using a watch list for irq generation. */ @@ -198,7 +212,7 @@ struct xpc_gru_mq_uv { /* * The activate_mq is used to send/receive GRU messages that affect XPC's - * heartbeat, partition active state, and channel state. This is UV only. + * partition active state and channel state. This is uv only. */ struct xpc_activate_mq_msghdr_uv { unsigned int gru_msg_hdr; /* FOR GRU INTERNAL USE ONLY */ @@ -210,33 +224,27 @@ struct xpc_activate_mq_msghdr_uv { /* activate_mq defined message types */ #define XPC_ACTIVATE_MQ_MSG_SYNC_ACT_STATE_UV 0 -#define XPC_ACTIVATE_MQ_MSG_INC_HEARTBEAT_UV 1 -#define XPC_ACTIVATE_MQ_MSG_OFFLINE_HEARTBEAT_UV 2 -#define XPC_ACTIVATE_MQ_MSG_ONLINE_HEARTBEAT_UV 3 -#define XPC_ACTIVATE_MQ_MSG_ACTIVATE_REQ_UV 4 -#define XPC_ACTIVATE_MQ_MSG_DEACTIVATE_REQ_UV 5 +#define XPC_ACTIVATE_MQ_MSG_ACTIVATE_REQ_UV 1 +#define XPC_ACTIVATE_MQ_MSG_DEACTIVATE_REQ_UV 2 -#define XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREQUEST_UV 6 -#define XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREPLY_UV 7 -#define XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREQUEST_UV 8 -#define XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREPLY_UV 9 +#define XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREQUEST_UV 3 +#define XPC_ACTIVATE_MQ_MSG_CHCTL_CLOSEREPLY_UV 4 +#define XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREQUEST_UV 5 +#define XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREPLY_UV 6 +#define XPC_ACTIVATE_MQ_MSG_CHCTL_OPENCOMPLETE_UV 7 -#define XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV 10 -#define XPC_ACTIVATE_MQ_MSG_MARK_DISENGAGED_UV 11 +#define XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV 8 +#define XPC_ACTIVATE_MQ_MSG_MARK_DISENGAGED_UV 9 struct xpc_activate_mq_msg_uv { struct xpc_activate_mq_msghdr_uv hdr; }; -struct xpc_activate_mq_msg_heartbeat_req_uv { - struct xpc_activate_mq_msghdr_uv hdr; - u64 heartbeat; -}; - struct xpc_activate_mq_msg_activate_req_uv { struct xpc_activate_mq_msghdr_uv hdr; unsigned long rp_gpa; + unsigned long heartbeat_gpa; unsigned long activate_gru_mq_desc_gpa; }; @@ -271,6 +279,11 @@ struct xpc_activate_mq_msg_chctl_openreply_uv { unsigned long notify_gru_mq_desc_gpa; }; +struct xpc_activate_mq_msg_chctl_opencomplete_uv { + struct xpc_activate_mq_msghdr_uv hdr; + short ch_number; +}; + /* * Functions registered by add_timer() or called by kernel_thread() only * allow for a single 64-bit argument. The following macros can be used to @@ -576,30 +589,32 @@ struct xpc_channel { #define XPC_C_WASCONNECTED 0x00000001 /* channel was connected */ -#define XPC_C_ROPENREPLY 0x00000002 /* remote open channel reply */ -#define XPC_C_OPENREPLY 0x00000004 /* local open channel reply */ -#define XPC_C_ROPENREQUEST 0x00000008 /* remote open channel request */ -#define XPC_C_OPENREQUEST 0x00000010 /* local open channel request */ +#define XPC_C_ROPENCOMPLETE 0x00000002 /* remote open channel complete */ +#define XPC_C_OPENCOMPLETE 0x00000004 /* local open channel complete */ +#define XPC_C_ROPENREPLY 0x00000008 /* remote open channel reply */ +#define XPC_C_OPENREPLY 0x00000010 /* local open channel reply */ +#define XPC_C_ROPENREQUEST 0x00000020 /* remote open channel request */ +#define XPC_C_OPENREQUEST 0x00000040 /* local open channel request */ -#define XPC_C_SETUP 0x00000020 /* channel's msgqueues are alloc'd */ -#define XPC_C_CONNECTEDCALLOUT 0x00000040 /* connected callout initiated */ +#define XPC_C_SETUP 0x00000080 /* channel's msgqueues are alloc'd */ +#define XPC_C_CONNECTEDCALLOUT 0x00000100 /* connected callout initiated */ #define XPC_C_CONNECTEDCALLOUT_MADE \ - 0x00000080 /* connected callout completed */ -#define XPC_C_CONNECTED 0x00000100 /* local channel is connected */ -#define XPC_C_CONNECTING 0x00000200 /* channel is being connected */ + 0x00000200 /* connected callout completed */ +#define XPC_C_CONNECTED 0x00000400 /* local channel is connected */ +#define XPC_C_CONNECTING 0x00000800 /* channel is being connected */ -#define XPC_C_RCLOSEREPLY 0x00000400 /* remote close channel reply */ -#define XPC_C_CLOSEREPLY 0x00000800 /* local close channel reply */ -#define XPC_C_RCLOSEREQUEST 0x00001000 /* remote close channel request */ -#define XPC_C_CLOSEREQUEST 0x00002000 /* local close channel request */ +#define XPC_C_RCLOSEREPLY 0x00001000 /* remote close channel reply */ +#define XPC_C_CLOSEREPLY 0x00002000 /* local close channel reply */ +#define XPC_C_RCLOSEREQUEST 0x00004000 /* remote close channel request */ +#define XPC_C_CLOSEREQUEST 0x00008000 /* local close channel request */ -#define XPC_C_DISCONNECTED 0x00004000 /* channel is disconnected */ -#define XPC_C_DISCONNECTING 0x00008000 /* channel is being disconnected */ +#define XPC_C_DISCONNECTED 0x00010000 /* channel is disconnected */ +#define XPC_C_DISCONNECTING 0x00020000 /* channel is being disconnected */ #define XPC_C_DISCONNECTINGCALLOUT \ - 0x00010000 /* disconnecting callout initiated */ + 0x00040000 /* disconnecting callout initiated */ #define XPC_C_DISCONNECTINGCALLOUT_MADE \ - 0x00020000 /* disconnecting callout completed */ -#define XPC_C_WDISCONNECT 0x00040000 /* waiting for channel disconnect */ + 0x00080000 /* disconnecting callout completed */ +#define XPC_C_WDISCONNECT 0x00100000 /* waiting for channel disconnect */ /* * The channel control flags (chctl) union consists of a 64-bit variable which @@ -618,11 +633,13 @@ union xpc_channel_ctl_flags { #define XPC_CHCTL_CLOSEREPLY 0x02 #define XPC_CHCTL_OPENREQUEST 0x04 #define XPC_CHCTL_OPENREPLY 0x08 -#define XPC_CHCTL_MSGREQUEST 0x10 +#define XPC_CHCTL_OPENCOMPLETE 0x10 +#define XPC_CHCTL_MSGREQUEST 0x20 #define XPC_OPENCLOSE_CHCTL_FLAGS \ (XPC_CHCTL_CLOSEREQUEST | XPC_CHCTL_CLOSEREPLY | \ - XPC_CHCTL_OPENREQUEST | XPC_CHCTL_OPENREPLY) + XPC_CHCTL_OPENREQUEST | XPC_CHCTL_OPENREPLY | \ + XPC_CHCTL_OPENCOMPLETE) #define XPC_MSG_CHCTL_FLAGS XPC_CHCTL_MSGREQUEST static inline int @@ -687,6 +704,9 @@ struct xpc_partition_sn2 { }; struct xpc_partition_uv { + unsigned long heartbeat_gpa; /* phys addr of partition's heartbeat */ + struct xpc_heartbeat_uv cached_heartbeat; /* cached copy of */ + /* partition's heartbeat */ unsigned long activate_gru_mq_desc_gpa; /* phys addr of parititon's */ /* activate mq's gru mq */ /* descriptor */ @@ -698,14 +718,12 @@ struct xpc_partition_uv { u8 remote_act_state; /* remote partition's act_state */ u8 act_state_req; /* act_state request from remote partition */ enum xp_retval reason; /* reason for deactivate act_state request */ - u64 heartbeat; /* incremented by remote partition */ }; /* struct xpc_partition_uv flags */ -#define XPC_P_HEARTBEAT_OFFLINE_UV 0x00000001 +#define XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV 0x00000001 #define XPC_P_ENGAGED_UV 0x00000002 -#define XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV 0x00000004 /* struct xpc_partition_uv act_state change requests */ @@ -762,6 +780,62 @@ struct xpc_partition { } ____cacheline_aligned; +struct xpc_arch_operations { + int (*setup_partitions) (void); + void (*teardown_partitions) (void); + void (*process_activate_IRQ_rcvd) (void); + enum xp_retval (*get_partition_rsvd_page_pa) + (void *, u64 *, unsigned long *, size_t *); + int (*setup_rsvd_page) (struct xpc_rsvd_page *); + + void (*allow_hb) (short); + void (*disallow_hb) (short); + void (*disallow_all_hbs) (void); + void (*increment_heartbeat) (void); + void (*offline_heartbeat) (void); + void (*online_heartbeat) (void); + void (*heartbeat_init) (void); + void (*heartbeat_exit) (void); + enum xp_retval (*get_remote_heartbeat) (struct xpc_partition *); + + void (*request_partition_activation) (struct xpc_rsvd_page *, + unsigned long, int); + void (*request_partition_reactivation) (struct xpc_partition *); + void (*request_partition_deactivation) (struct xpc_partition *); + void (*cancel_partition_deactivation_request) (struct xpc_partition *); + enum xp_retval (*setup_ch_structures) (struct xpc_partition *); + void (*teardown_ch_structures) (struct xpc_partition *); + + enum xp_retval (*make_first_contact) (struct xpc_partition *); + + u64 (*get_chctl_all_flags) (struct xpc_partition *); + void (*send_chctl_closerequest) (struct xpc_channel *, unsigned long *); + void (*send_chctl_closereply) (struct xpc_channel *, unsigned long *); + void (*send_chctl_openrequest) (struct xpc_channel *, unsigned long *); + void (*send_chctl_openreply) (struct xpc_channel *, unsigned long *); + void (*send_chctl_opencomplete) (struct xpc_channel *, unsigned long *); + void (*process_msg_chctl_flags) (struct xpc_partition *, int); + + enum xp_retval (*save_remote_msgqueue_pa) (struct xpc_channel *, + unsigned long); + + enum xp_retval (*setup_msg_structures) (struct xpc_channel *); + void (*teardown_msg_structures) (struct xpc_channel *); + + void (*indicate_partition_engaged) (struct xpc_partition *); + void (*indicate_partition_disengaged) (struct xpc_partition *); + void (*assume_partition_disengaged) (short); + int (*partition_engaged) (short); + int (*any_partition_engaged) (void); + + int (*n_of_deliverable_payloads) (struct xpc_channel *); + enum xp_retval (*send_payload) (struct xpc_channel *, u32, void *, + u16, u8, xpc_notify_func, void *); + void *(*get_deliverable_payload) (struct xpc_channel *); + void (*received_payload) (struct xpc_channel *, void *); + void (*notify_senders_of_disconnect) (struct xpc_channel *); +}; + /* struct xpc_partition act_state values (for XPC HB) */ #define XPC_P_AS_INACTIVE 0x00 /* partition is not active */ @@ -802,67 +876,17 @@ extern struct xpc_registration xpc_registrations[]; /* found in xpc_main.c */ extern struct device *xpc_part; extern struct device *xpc_chan; +extern struct xpc_arch_operations xpc_arch_ops; extern int xpc_disengage_timelimit; extern int xpc_disengage_timedout; extern int xpc_activate_IRQ_rcvd; extern spinlock_t xpc_activate_IRQ_rcvd_lock; extern wait_queue_head_t xpc_activate_IRQ_wq; -extern void *xpc_heartbeating_to_mask; extern void *xpc_kzalloc_cacheline_aligned(size_t, gfp_t, void **); extern void xpc_activate_partition(struct xpc_partition *); extern void xpc_activate_kthreads(struct xpc_channel *, int); extern void xpc_create_kthreads(struct xpc_channel *, int, int); extern void xpc_disconnect_wait(int); -extern int (*xpc_setup_partitions_sn) (void); -extern void (*xpc_teardown_partitions_sn) (void); -extern enum xp_retval (*xpc_get_partition_rsvd_page_pa) (void *, u64 *, - unsigned long *, - size_t *); -extern int (*xpc_setup_rsvd_page_sn) (struct xpc_rsvd_page *); -extern void (*xpc_heartbeat_init) (void); -extern void (*xpc_heartbeat_exit) (void); -extern void (*xpc_increment_heartbeat) (void); -extern void (*xpc_offline_heartbeat) (void); -extern void (*xpc_online_heartbeat) (void); -extern enum xp_retval (*xpc_get_remote_heartbeat) (struct xpc_partition *); -extern enum xp_retval (*xpc_make_first_contact) (struct xpc_partition *); -extern u64 (*xpc_get_chctl_all_flags) (struct xpc_partition *); -extern enum xp_retval (*xpc_setup_msg_structures) (struct xpc_channel *); -extern void (*xpc_teardown_msg_structures) (struct xpc_channel *); -extern void (*xpc_notify_senders_of_disconnect) (struct xpc_channel *); -extern void (*xpc_process_msg_chctl_flags) (struct xpc_partition *, int); -extern int (*xpc_n_of_deliverable_payloads) (struct xpc_channel *); -extern void *(*xpc_get_deliverable_payload) (struct xpc_channel *); -extern void (*xpc_request_partition_activation) (struct xpc_rsvd_page *, - unsigned long, int); -extern void (*xpc_request_partition_reactivation) (struct xpc_partition *); -extern void (*xpc_request_partition_deactivation) (struct xpc_partition *); -extern void (*xpc_cancel_partition_deactivation_request) ( - struct xpc_partition *); -extern void (*xpc_process_activate_IRQ_rcvd) (void); -extern enum xp_retval (*xpc_setup_ch_structures_sn) (struct xpc_partition *); -extern void (*xpc_teardown_ch_structures_sn) (struct xpc_partition *); - -extern void (*xpc_indicate_partition_engaged) (struct xpc_partition *); -extern int (*xpc_partition_engaged) (short); -extern int (*xpc_any_partition_engaged) (void); -extern void (*xpc_indicate_partition_disengaged) (struct xpc_partition *); -extern void (*xpc_assume_partition_disengaged) (short); - -extern void (*xpc_send_chctl_closerequest) (struct xpc_channel *, - unsigned long *); -extern void (*xpc_send_chctl_closereply) (struct xpc_channel *, - unsigned long *); -extern void (*xpc_send_chctl_openrequest) (struct xpc_channel *, - unsigned long *); -extern void (*xpc_send_chctl_openreply) (struct xpc_channel *, unsigned long *); - -extern enum xp_retval (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *, - unsigned long); - -extern enum xp_retval (*xpc_send_payload) (struct xpc_channel *, u32, void *, - u16, u8, xpc_notify_func, void *); -extern void (*xpc_received_payload) (struct xpc_channel *, void *); /* found in xpc_sn2.c */ extern int xpc_init_sn2(void); @@ -909,40 +933,6 @@ extern void xpc_disconnect_channel(const int, struct xpc_channel *, extern void xpc_disconnect_callout(struct xpc_channel *, enum xp_retval); extern void xpc_partition_going_down(struct xpc_partition *, enum xp_retval); -static inline int -xpc_hb_allowed(short partid, void *heartbeating_to_mask) -{ - return test_bit(partid, heartbeating_to_mask); -} - -static inline int -xpc_any_hbs_allowed(void) -{ - DBUG_ON(xpc_heartbeating_to_mask == NULL); - return !bitmap_empty(xpc_heartbeating_to_mask, xp_max_npartitions); -} - -static inline void -xpc_allow_hb(short partid) -{ - DBUG_ON(xpc_heartbeating_to_mask == NULL); - set_bit(partid, xpc_heartbeating_to_mask); -} - -static inline void -xpc_disallow_hb(short partid) -{ - DBUG_ON(xpc_heartbeating_to_mask == NULL); - clear_bit(partid, xpc_heartbeating_to_mask); -} - -static inline void -xpc_disallow_all_hbs(void) -{ - DBUG_ON(xpc_heartbeating_to_mask == NULL); - bitmap_zero(xpc_heartbeating_to_mask, xp_max_npartitions); -} - static inline void xpc_wakeup_channel_mgr(struct xpc_partition *part) { diff --git a/drivers/misc/sgi-xp/xpc_channel.c b/drivers/misc/sgi-xp/xpc_channel.c index 99a2534c38a..652593fc486 100644 --- a/drivers/misc/sgi-xp/xpc_channel.c +++ b/drivers/misc/sgi-xp/xpc_channel.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2008 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2009 Silicon Graphics, Inc. All Rights Reserved. */ /* @@ -39,34 +39,38 @@ xpc_process_connect(struct xpc_channel *ch, unsigned long *irq_flags) if (!(ch->flags & XPC_C_SETUP)) { spin_unlock_irqrestore(&ch->lock, *irq_flags); - ret = xpc_setup_msg_structures(ch); + ret = xpc_arch_ops.setup_msg_structures(ch); spin_lock_irqsave(&ch->lock, *irq_flags); if (ret != xpSuccess) XPC_DISCONNECT_CHANNEL(ch, ret, irq_flags); + else + ch->flags |= XPC_C_SETUP; - ch->flags |= XPC_C_SETUP; - - if (ch->flags & (XPC_C_CONNECTED | XPC_C_DISCONNECTING)) + if (ch->flags & XPC_C_DISCONNECTING) return; } if (!(ch->flags & XPC_C_OPENREPLY)) { ch->flags |= XPC_C_OPENREPLY; - xpc_send_chctl_openreply(ch, irq_flags); + xpc_arch_ops.send_chctl_openreply(ch, irq_flags); } if (!(ch->flags & XPC_C_ROPENREPLY)) return; - ch->flags = (XPC_C_CONNECTED | XPC_C_SETUP); /* clear all else */ + if (!(ch->flags & XPC_C_OPENCOMPLETE)) { + ch->flags |= (XPC_C_OPENCOMPLETE | XPC_C_CONNECTED); + xpc_arch_ops.send_chctl_opencomplete(ch, irq_flags); + } + + if (!(ch->flags & XPC_C_ROPENCOMPLETE)) + return; dev_info(xpc_chan, "channel %d to partition %d connected\n", ch->number, ch->partid); - spin_unlock_irqrestore(&ch->lock, *irq_flags); - xpc_create_kthreads(ch, 1, 0); - spin_lock_irqsave(&ch->lock, *irq_flags); + ch->flags = (XPC_C_CONNECTED | XPC_C_SETUP); /* clear all else */ } /* @@ -96,7 +100,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) if (part->act_state == XPC_P_AS_DEACTIVATING) { /* can't proceed until the other side disengages from us */ - if (xpc_partition_engaged(ch->partid)) + if (xpc_arch_ops.partition_engaged(ch->partid)) return; } else { @@ -108,7 +112,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) if (!(ch->flags & XPC_C_CLOSEREPLY)) { ch->flags |= XPC_C_CLOSEREPLY; - xpc_send_chctl_closereply(ch, irq_flags); + xpc_arch_ops.send_chctl_closereply(ch, irq_flags); } if (!(ch->flags & XPC_C_RCLOSEREPLY)) @@ -118,7 +122,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) /* wake those waiting for notify completion */ if (atomic_read(&ch->n_to_notify) > 0) { /* we do callout while holding ch->lock, callout can't block */ - xpc_notify_senders_of_disconnect(ch); + xpc_arch_ops.notify_senders_of_disconnect(ch); } /* both sides are disconnected now */ @@ -132,7 +136,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) DBUG_ON(atomic_read(&ch->n_to_notify) != 0); /* it's now safe to free the channel's message queues */ - xpc_teardown_msg_structures(ch); + xpc_arch_ops.teardown_msg_structures(ch); ch->func = NULL; ch->key = NULL; @@ -144,8 +148,9 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) /* * Mark the channel disconnected and clear all other flags, including - * XPC_C_SETUP (because of call to xpc_teardown_msg_structures()) but - * not including XPC_C_WDISCONNECT (if it was set). + * XPC_C_SETUP (because of call to + * xpc_arch_ops.teardown_msg_structures()) but not including + * XPC_C_WDISCONNECT (if it was set). */ ch->flags = (XPC_C_DISCONNECTED | (ch->flags & XPC_C_WDISCONNECT)); @@ -184,6 +189,7 @@ xpc_process_openclose_chctl_flags(struct xpc_partition *part, int ch_number, struct xpc_channel *ch = &part->channels[ch_number]; enum xp_retval reason; enum xp_retval ret; + int create_kthread = 0; spin_lock_irqsave(&ch->lock, irq_flags); @@ -196,8 +202,7 @@ again: * has had a chance to see that the channel is disconnected. */ ch->delayed_chctl_flags |= chctl_flags; - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } if (chctl_flags & XPC_CHCTL_CLOSEREQUEST) { @@ -239,8 +244,7 @@ again: XPC_CHCTL_CLOSEREQUEST; spin_unlock(&part->chctl_lock); } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } XPC_SET_REASON(ch, 0, 0); @@ -250,7 +254,8 @@ again: ch->flags |= (XPC_C_CONNECTING | XPC_C_ROPENREQUEST); } - chctl_flags &= ~(XPC_CHCTL_OPENREQUEST | XPC_CHCTL_OPENREPLY); + chctl_flags &= ~(XPC_CHCTL_OPENREQUEST | XPC_CHCTL_OPENREPLY | + XPC_CHCTL_OPENCOMPLETE); /* * The meaningful CLOSEREQUEST connection state fields are: @@ -269,8 +274,7 @@ again: XPC_DISCONNECT_CHANNEL(ch, reason, &irq_flags); DBUG_ON(chctl_flags & XPC_CHCTL_CLOSEREPLY); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } xpc_process_disconnect(ch, &irq_flags); @@ -283,8 +287,7 @@ again: if (ch->flags & XPC_C_DISCONNECTED) { DBUG_ON(part->act_state != XPC_P_AS_DEACTIVATING); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } DBUG_ON(!(ch->flags & XPC_C_CLOSEREQUEST)); @@ -299,8 +302,7 @@ again: XPC_CHCTL_CLOSEREPLY; spin_unlock(&part->chctl_lock); } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } ch->flags |= XPC_C_RCLOSEREPLY; @@ -320,14 +322,12 @@ again: if (part->act_state == XPC_P_AS_DEACTIVATING || (ch->flags & XPC_C_ROPENREQUEST)) { - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_WDISCONNECT)) { ch->delayed_chctl_flags |= XPC_CHCTL_OPENREQUEST; - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } DBUG_ON(!(ch->flags & (XPC_C_DISCONNECTED | XPC_C_OPENREQUEST))); @@ -341,8 +341,7 @@ again: */ if (args->entry_size == 0 || args->local_nentries == 0) { /* assume OPENREQUEST was delayed by mistake */ - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } ch->flags |= (XPC_C_ROPENREQUEST | XPC_C_CONNECTING); @@ -352,8 +351,7 @@ again: if (args->entry_size != ch->entry_size) { XPC_DISCONNECT_CHANNEL(ch, xpUnequalMsgSizes, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } } else { ch->entry_size = args->entry_size; @@ -375,15 +373,13 @@ again: args->local_msgqueue_pa, args->local_nentries, args->remote_nentries, ch->partid, ch->number); - if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_DISCONNECTED)) { - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } + if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_DISCONNECTED)) + goto out; + if (!(ch->flags & XPC_C_OPENREQUEST)) { XPC_DISCONNECT_CHANNEL(ch, xpOpenCloseError, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } DBUG_ON(!(ch->flags & XPC_C_ROPENREQUEST)); @@ -400,11 +396,11 @@ again: DBUG_ON(args->local_nentries == 0); DBUG_ON(args->remote_nentries == 0); - ret = xpc_save_remote_msgqueue_pa(ch, args->local_msgqueue_pa); + ret = xpc_arch_ops.save_remote_msgqueue_pa(ch, + args->local_msgqueue_pa); if (ret != xpSuccess) { XPC_DISCONNECT_CHANNEL(ch, ret, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; + goto out; } ch->flags |= XPC_C_ROPENREPLY; @@ -430,7 +426,36 @@ again: xpc_process_connect(ch, &irq_flags); } + if (chctl_flags & XPC_CHCTL_OPENCOMPLETE) { + + dev_dbg(xpc_chan, "XPC_CHCTL_OPENCOMPLETE received from " + "partid=%d, channel=%d\n", ch->partid, ch->number); + + if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_DISCONNECTED)) + goto out; + + if (!(ch->flags & XPC_C_OPENREQUEST) || + !(ch->flags & XPC_C_OPENREPLY)) { + XPC_DISCONNECT_CHANNEL(ch, xpOpenCloseError, + &irq_flags); + goto out; + } + + DBUG_ON(!(ch->flags & XPC_C_ROPENREQUEST)); + DBUG_ON(!(ch->flags & XPC_C_ROPENREPLY)); + DBUG_ON(!(ch->flags & XPC_C_CONNECTED)); + + ch->flags |= XPC_C_ROPENCOMPLETE; + + xpc_process_connect(ch, &irq_flags); + create_kthread = 1; + } + +out: spin_unlock_irqrestore(&ch->lock, irq_flags); + + if (create_kthread) + xpc_create_kthreads(ch, 1, 0); } /* @@ -508,7 +533,7 @@ xpc_connect_channel(struct xpc_channel *ch) /* initiate the connection */ ch->flags |= (XPC_C_OPENREQUEST | XPC_C_CONNECTING); - xpc_send_chctl_openrequest(ch, &irq_flags); + xpc_arch_ops.send_chctl_openrequest(ch, &irq_flags); xpc_process_connect(ch, &irq_flags); @@ -526,7 +551,7 @@ xpc_process_sent_chctl_flags(struct xpc_partition *part) int ch_number; u32 ch_flags; - chctl.all_flags = xpc_get_chctl_all_flags(part); + chctl.all_flags = xpc_arch_ops.get_chctl_all_flags(part); /* * Initiate channel connections for registered channels. @@ -564,10 +589,6 @@ xpc_process_sent_chctl_flags(struct xpc_partition *part) if (!(ch_flags & XPC_C_OPENREQUEST)) { DBUG_ON(ch_flags & XPC_C_SETUP); (void)xpc_connect_channel(ch); - } else { - spin_lock_irqsave(&ch->lock, irq_flags); - xpc_process_connect(ch, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); } continue; } @@ -579,7 +600,7 @@ xpc_process_sent_chctl_flags(struct xpc_partition *part) */ if (chctl.flags[ch_number] & XPC_MSG_CHCTL_FLAGS) - xpc_process_msg_chctl_flags(part, ch_number); + xpc_arch_ops.process_msg_chctl_flags(part, ch_number); } } @@ -755,7 +776,7 @@ xpc_disconnect_channel(const int line, struct xpc_channel *ch, XPC_C_ROPENREQUEST | XPC_C_ROPENREPLY | XPC_C_CONNECTING | XPC_C_CONNECTED); - xpc_send_chctl_closerequest(ch, irq_flags); + xpc_arch_ops.send_chctl_closerequest(ch, irq_flags); if (channel_was_connected) ch->flags |= XPC_C_WASCONNECTED; @@ -862,8 +883,8 @@ xpc_initiate_send(short partid, int ch_number, u32 flags, void *payload, DBUG_ON(payload == NULL); if (xpc_part_ref(part)) { - ret = xpc_send_payload(&part->channels[ch_number], flags, - payload, payload_size, 0, NULL, NULL); + ret = xpc_arch_ops.send_payload(&part->channels[ch_number], + flags, payload, payload_size, 0, NULL, NULL); xpc_part_deref(part); } @@ -914,9 +935,8 @@ xpc_initiate_send_notify(short partid, int ch_number, u32 flags, void *payload, DBUG_ON(func == NULL); if (xpc_part_ref(part)) { - ret = xpc_send_payload(&part->channels[ch_number], flags, - payload, payload_size, XPC_N_CALL, func, - key); + ret = xpc_arch_ops.send_payload(&part->channels[ch_number], + flags, payload, payload_size, XPC_N_CALL, func, key); xpc_part_deref(part); } return ret; @@ -930,7 +950,7 @@ xpc_deliver_payload(struct xpc_channel *ch) { void *payload; - payload = xpc_get_deliverable_payload(ch); + payload = xpc_arch_ops.get_deliverable_payload(ch); if (payload != NULL) { /* @@ -984,7 +1004,7 @@ xpc_initiate_received(short partid, int ch_number, void *payload) DBUG_ON(ch_number < 0 || ch_number >= part->nchannels); ch = &part->channels[ch_number]; - xpc_received_payload(ch, payload); + xpc_arch_ops.received_payload(ch, payload); /* the call to xpc_msgqueue_ref() was done by xpc_deliver_payload() */ xpc_msgqueue_deref(ch); diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 1ab9fda87fa..fd3688a3e23 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2008 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2009 Silicon Graphics, Inc. All Rights Reserved. */ /* @@ -150,7 +150,6 @@ DECLARE_WAIT_QUEUE_HEAD(xpc_activate_IRQ_wq); static unsigned long xpc_hb_check_timeout; static struct timer_list xpc_hb_timer; -void *xpc_heartbeating_to_mask; /* notification that the xpc_hb_checker thread has exited */ static DECLARE_COMPLETION(xpc_hb_checker_exited); @@ -170,62 +169,7 @@ static struct notifier_block xpc_die_notifier = { .notifier_call = xpc_system_die, }; -int (*xpc_setup_partitions_sn) (void); -void (*xpc_teardown_partitions_sn) (void); -enum xp_retval (*xpc_get_partition_rsvd_page_pa) (void *buf, u64 *cookie, - unsigned long *rp_pa, - size_t *len); -int (*xpc_setup_rsvd_page_sn) (struct xpc_rsvd_page *rp); -void (*xpc_heartbeat_init) (void); -void (*xpc_heartbeat_exit) (void); -void (*xpc_increment_heartbeat) (void); -void (*xpc_offline_heartbeat) (void); -void (*xpc_online_heartbeat) (void); -enum xp_retval (*xpc_get_remote_heartbeat) (struct xpc_partition *part); - -enum xp_retval (*xpc_make_first_contact) (struct xpc_partition *part); -void (*xpc_notify_senders_of_disconnect) (struct xpc_channel *ch); -u64 (*xpc_get_chctl_all_flags) (struct xpc_partition *part); -enum xp_retval (*xpc_setup_msg_structures) (struct xpc_channel *ch); -void (*xpc_teardown_msg_structures) (struct xpc_channel *ch); -void (*xpc_process_msg_chctl_flags) (struct xpc_partition *part, int ch_number); -int (*xpc_n_of_deliverable_payloads) (struct xpc_channel *ch); -void *(*xpc_get_deliverable_payload) (struct xpc_channel *ch); - -void (*xpc_request_partition_activation) (struct xpc_rsvd_page *remote_rp, - unsigned long remote_rp_pa, - int nasid); -void (*xpc_request_partition_reactivation) (struct xpc_partition *part); -void (*xpc_request_partition_deactivation) (struct xpc_partition *part); -void (*xpc_cancel_partition_deactivation_request) (struct xpc_partition *part); - -void (*xpc_process_activate_IRQ_rcvd) (void); -enum xp_retval (*xpc_setup_ch_structures_sn) (struct xpc_partition *part); -void (*xpc_teardown_ch_structures_sn) (struct xpc_partition *part); - -void (*xpc_indicate_partition_engaged) (struct xpc_partition *part); -int (*xpc_partition_engaged) (short partid); -int (*xpc_any_partition_engaged) (void); -void (*xpc_indicate_partition_disengaged) (struct xpc_partition *part); -void (*xpc_assume_partition_disengaged) (short partid); - -void (*xpc_send_chctl_closerequest) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_send_chctl_closereply) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_send_chctl_openrequest) (struct xpc_channel *ch, - unsigned long *irq_flags); -void (*xpc_send_chctl_openreply) (struct xpc_channel *ch, - unsigned long *irq_flags); - -enum xp_retval (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *ch, - unsigned long msgqueue_pa); - -enum xp_retval (*xpc_send_payload) (struct xpc_channel *ch, u32 flags, - void *payload, u16 payload_size, - u8 notify_type, xpc_notify_func func, - void *key); -void (*xpc_received_payload) (struct xpc_channel *ch, void *payload); +struct xpc_arch_operations xpc_arch_ops; /* * Timer function to enforce the timelimit on the partition disengage. @@ -240,7 +184,7 @@ xpc_timeout_partition_disengage(unsigned long data) (void)xpc_partition_disengaged(part); DBUG_ON(part->disengage_timeout != 0); - DBUG_ON(xpc_partition_engaged(XPC_PARTID(part))); + DBUG_ON(xpc_arch_ops.partition_engaged(XPC_PARTID(part))); } /* @@ -251,7 +195,7 @@ xpc_timeout_partition_disengage(unsigned long data) static void xpc_hb_beater(unsigned long dummy) { - xpc_increment_heartbeat(); + xpc_arch_ops.increment_heartbeat(); if (time_is_before_eq_jiffies(xpc_hb_check_timeout)) wake_up_interruptible(&xpc_activate_IRQ_wq); @@ -263,7 +207,7 @@ xpc_hb_beater(unsigned long dummy) static void xpc_start_hb_beater(void) { - xpc_heartbeat_init(); + xpc_arch_ops.heartbeat_init(); init_timer(&xpc_hb_timer); xpc_hb_timer.function = xpc_hb_beater; xpc_hb_beater(0); @@ -273,7 +217,7 @@ static void xpc_stop_hb_beater(void) { del_timer_sync(&xpc_hb_timer); - xpc_heartbeat_exit(); + xpc_arch_ops.heartbeat_exit(); } /* @@ -302,7 +246,7 @@ xpc_check_remote_hb(void) continue; } - ret = xpc_get_remote_heartbeat(part); + ret = xpc_arch_ops.get_remote_heartbeat(part); if (ret != xpSuccess) XPC_DEACTIVATE_PARTITION(part, ret); } @@ -353,7 +297,7 @@ xpc_hb_checker(void *ignore) force_IRQ = 0; dev_dbg(xpc_part, "processing activate IRQs " "received\n"); - xpc_process_activate_IRQ_rcvd(); + xpc_arch_ops.process_activate_IRQ_rcvd(); } /* wait for IRQ or timeout */ @@ -528,7 +472,7 @@ xpc_setup_ch_structures(struct xpc_partition *part) init_waitqueue_head(&ch->idle_wq); } - ret = xpc_setup_ch_structures_sn(part); + ret = xpc_arch_ops.setup_ch_structures(part); if (ret != xpSuccess) goto out_2; @@ -572,7 +516,7 @@ xpc_teardown_ch_structures(struct xpc_partition *part) /* now we can begin tearing down the infrastructure */ - xpc_teardown_ch_structures_sn(part); + xpc_arch_ops.teardown_ch_structures(part); kfree(part->remote_openclose_args_base); part->remote_openclose_args = NULL; @@ -620,12 +564,12 @@ xpc_activating(void *__partid) dev_dbg(xpc_part, "activating partition %d\n", partid); - xpc_allow_hb(partid); + xpc_arch_ops.allow_hb(partid); if (xpc_setup_ch_structures(part) == xpSuccess) { (void)xpc_part_ref(part); /* this will always succeed */ - if (xpc_make_first_contact(part) == xpSuccess) { + if (xpc_arch_ops.make_first_contact(part) == xpSuccess) { xpc_mark_partition_active(part); xpc_channel_mgr(part); /* won't return until partition is deactivating */ @@ -635,12 +579,12 @@ xpc_activating(void *__partid) xpc_teardown_ch_structures(part); } - xpc_disallow_hb(partid); + xpc_arch_ops.disallow_hb(partid); xpc_mark_partition_inactive(part); if (part->reason == xpReactivating) { /* interrupting ourselves results in activating partition */ - xpc_request_partition_reactivation(part); + xpc_arch_ops.request_partition_reactivation(part); } return 0; @@ -713,10 +657,13 @@ xpc_activate_kthreads(struct xpc_channel *ch, int needed) static void xpc_kthread_waitmsgs(struct xpc_partition *part, struct xpc_channel *ch) { + int (*n_of_deliverable_payloads) (struct xpc_channel *) = + xpc_arch_ops.n_of_deliverable_payloads; + do { /* deliver messages to their intended recipients */ - while (xpc_n_of_deliverable_payloads(ch) > 0 && + while (n_of_deliverable_payloads(ch) > 0 && !(ch->flags & XPC_C_DISCONNECTING)) { xpc_deliver_payload(ch); } @@ -732,7 +679,7 @@ xpc_kthread_waitmsgs(struct xpc_partition *part, struct xpc_channel *ch) "wait_event_interruptible_exclusive()\n"); (void)wait_event_interruptible_exclusive(ch->idle_wq, - (xpc_n_of_deliverable_payloads(ch) > 0 || + (n_of_deliverable_payloads(ch) > 0 || (ch->flags & XPC_C_DISCONNECTING))); atomic_dec(&ch->kthreads_idle); @@ -749,6 +696,8 @@ xpc_kthread_start(void *args) struct xpc_channel *ch; int n_needed; unsigned long irq_flags; + int (*n_of_deliverable_payloads) (struct xpc_channel *) = + xpc_arch_ops.n_of_deliverable_payloads; dev_dbg(xpc_chan, "kthread starting, partid=%d, channel=%d\n", partid, ch_number); @@ -777,7 +726,7 @@ xpc_kthread_start(void *args) * additional kthreads to help deliver them. We only * need one less than total #of messages to deliver. */ - n_needed = xpc_n_of_deliverable_payloads(ch) - 1; + n_needed = n_of_deliverable_payloads(ch) - 1; if (n_needed > 0 && !(ch->flags & XPC_C_DISCONNECTING)) xpc_activate_kthreads(ch, n_needed); @@ -805,7 +754,7 @@ xpc_kthread_start(void *args) if (atomic_dec_return(&ch->kthreads_assigned) == 0 && atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_indicate_partition_disengaged(part); + xpc_arch_ops.indicate_partition_disengaged(part); } xpc_msgqueue_deref(ch); @@ -837,6 +786,8 @@ xpc_create_kthreads(struct xpc_channel *ch, int needed, u64 args = XPC_PACK_ARGS(ch->partid, ch->number); struct xpc_partition *part = &xpc_partitions[ch->partid]; struct task_struct *kthread; + void (*indicate_partition_disengaged) (struct xpc_partition *) = + xpc_arch_ops.indicate_partition_disengaged; while (needed-- > 0) { @@ -858,7 +809,7 @@ xpc_create_kthreads(struct xpc_channel *ch, int needed, } else if (atomic_inc_return(&ch->kthreads_assigned) == 1 && atomic_inc_return(&part->nchannels_engaged) == 1) { - xpc_indicate_partition_engaged(part); + xpc_arch_ops.indicate_partition_engaged(part); } (void)xpc_part_ref(part); xpc_msgqueue_ref(ch); @@ -880,7 +831,7 @@ xpc_create_kthreads(struct xpc_channel *ch, int needed, if (atomic_dec_return(&ch->kthreads_assigned) == 0 && atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_indicate_partition_disengaged(part); + indicate_partition_disengaged(part); } xpc_msgqueue_deref(ch); xpc_part_deref(part); @@ -993,13 +944,13 @@ xpc_setup_partitions(void) atomic_set(&part->references, 0); } - return xpc_setup_partitions_sn(); + return xpc_arch_ops.setup_partitions(); } static void xpc_teardown_partitions(void) { - xpc_teardown_partitions_sn(); + xpc_arch_ops.teardown_partitions(); kfree(xpc_partitions); } @@ -1055,7 +1006,7 @@ xpc_do_exit(enum xp_retval reason) disengage_timeout = part->disengage_timeout; } - if (xpc_any_partition_engaged()) { + if (xpc_arch_ops.any_partition_engaged()) { if (time_is_before_jiffies(printmsg_time)) { dev_info(xpc_part, "waiting for remote " "partitions to deactivate, timeout in " @@ -1086,8 +1037,7 @@ xpc_do_exit(enum xp_retval reason) } while (1); - DBUG_ON(xpc_any_partition_engaged()); - DBUG_ON(xpc_any_hbs_allowed() != 0); + DBUG_ON(xpc_arch_ops.any_partition_engaged()); xpc_teardown_rsvd_page(); @@ -1152,15 +1102,15 @@ xpc_die_deactivate(void) /* keep xpc_hb_checker thread from doing anything (just in case) */ xpc_exiting = 1; - xpc_disallow_all_hbs(); /*indicate we're deactivated */ + xpc_arch_ops.disallow_all_hbs(); /*indicate we're deactivated */ for (partid = 0; partid < xp_max_npartitions; partid++) { part = &xpc_partitions[partid]; - if (xpc_partition_engaged(partid) || + if (xpc_arch_ops.partition_engaged(partid) || part->act_state != XPC_P_AS_INACTIVE) { - xpc_request_partition_deactivation(part); - xpc_indicate_partition_disengaged(part); + xpc_arch_ops.request_partition_deactivation(part); + xpc_arch_ops.indicate_partition_disengaged(part); } } @@ -1177,7 +1127,7 @@ xpc_die_deactivate(void) wait_to_print = XPC_DEACTIVATE_PRINTMSG_INTERVAL * 1000 * 5; while (1) { - any_engaged = xpc_any_partition_engaged(); + any_engaged = xpc_arch_ops.any_partition_engaged(); if (!any_engaged) { dev_info(xpc_part, "all partitions have deactivated\n"); break; @@ -1186,7 +1136,7 @@ xpc_die_deactivate(void) if (!keep_waiting--) { for (partid = 0; partid < xp_max_npartitions; partid++) { - if (xpc_partition_engaged(partid)) { + if (xpc_arch_ops.partition_engaged(partid)) { dev_info(xpc_part, "deactivate from " "remote partition %d timed " "out\n", partid); @@ -1233,7 +1183,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused) /* fall through */ case DIE_MCA_MONARCH_ENTER: case DIE_INIT_MONARCH_ENTER: - xpc_offline_heartbeat(); + xpc_arch_ops.offline_heartbeat(); break; case DIE_KDEBUG_LEAVE: @@ -1244,7 +1194,7 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused) /* fall through */ case DIE_MCA_MONARCH_LEAVE: case DIE_INIT_MONARCH_LEAVE: - xpc_online_heartbeat(); + xpc_arch_ops.online_heartbeat(); break; } #else diff --git a/drivers/misc/sgi-xp/xpc_partition.c b/drivers/misc/sgi-xp/xpc_partition.c index 6722f6fe4dc..65877bc5eda 100644 --- a/drivers/misc/sgi-xp/xpc_partition.c +++ b/drivers/misc/sgi-xp/xpc_partition.c @@ -70,6 +70,9 @@ xpc_get_rsvd_page_pa(int nasid) size_t buf_len = 0; void *buf = buf; void *buf_base = NULL; + enum xp_retval (*get_partition_rsvd_page_pa) + (void *, u64 *, unsigned long *, size_t *) = + xpc_arch_ops.get_partition_rsvd_page_pa; while (1) { @@ -79,8 +82,7 @@ xpc_get_rsvd_page_pa(int nasid) * ??? function or have two versions? Rename rp_pa for UV to * ??? rp_gpa? */ - ret = xpc_get_partition_rsvd_page_pa(buf, &cookie, &rp_pa, - &len); + ret = get_partition_rsvd_page_pa(buf, &cookie, &rp_pa, &len); dev_dbg(xpc_part, "SAL returned with ret=%d, cookie=0x%016lx, " "address=0x%016lx, len=0x%016lx\n", ret, @@ -172,7 +174,7 @@ xpc_setup_rsvd_page(void) xpc_part_nasids = XPC_RP_PART_NASIDS(rp); xpc_mach_nasids = XPC_RP_MACH_NASIDS(rp); - ret = xpc_setup_rsvd_page_sn(rp); + ret = xpc_arch_ops.setup_rsvd_page(rp); if (ret != 0) return ret; @@ -264,7 +266,7 @@ xpc_partition_disengaged(struct xpc_partition *part) short partid = XPC_PARTID(part); int disengaged; - disengaged = !xpc_partition_engaged(partid); + disengaged = !xpc_arch_ops.partition_engaged(partid); if (part->disengage_timeout) { if (!disengaged) { if (time_is_after_jiffies(part->disengage_timeout)) { @@ -280,7 +282,7 @@ xpc_partition_disengaged(struct xpc_partition *part) dev_info(xpc_part, "deactivate request to remote " "partition %d timed out\n", partid); xpc_disengage_timedout = 1; - xpc_assume_partition_disengaged(partid); + xpc_arch_ops.assume_partition_disengaged(partid); disengaged = 1; } part->disengage_timeout = 0; @@ -294,7 +296,7 @@ xpc_partition_disengaged(struct xpc_partition *part) if (part->act_state != XPC_P_AS_INACTIVE) xpc_wakeup_channel_mgr(part); - xpc_cancel_partition_deactivation_request(part); + xpc_arch_ops.cancel_partition_deactivation_request(part); } return disengaged; } @@ -339,7 +341,7 @@ xpc_deactivate_partition(const int line, struct xpc_partition *part, spin_unlock_irqrestore(&part->act_lock, irq_flags); if (reason == xpReactivating) { /* we interrupt ourselves to reactivate partition */ - xpc_request_partition_reactivation(part); + xpc_arch_ops.request_partition_reactivation(part); } return; } @@ -358,7 +360,7 @@ xpc_deactivate_partition(const int line, struct xpc_partition *part, spin_unlock_irqrestore(&part->act_lock, irq_flags); /* ask remote partition to deactivate with regard to us */ - xpc_request_partition_deactivation(part); + xpc_arch_ops.request_partition_deactivation(part); /* set a timelimit on the disengage phase of the deactivation request */ part->disengage_timeout = jiffies + (xpc_disengage_timelimit * HZ); @@ -496,7 +498,7 @@ xpc_discovery(void) continue; } - xpc_request_partition_activation(remote_rp, + xpc_arch_ops.request_partition_activation(remote_rp, remote_rp_pa, nasid); } } diff --git a/drivers/misc/sgi-xp/xpc_sn2.c b/drivers/misc/sgi-xp/xpc_sn2.c index eaaa964942d..915a3b495da 100644 --- a/drivers/misc/sgi-xp/xpc_sn2.c +++ b/drivers/misc/sgi-xp/xpc_sn2.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2008 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2008-2009 Silicon Graphics, Inc. All Rights Reserved. */ /* @@ -60,14 +60,14 @@ static struct xpc_vars_sn2 *xpc_vars_sn2; static struct xpc_vars_part_sn2 *xpc_vars_part_sn2; static int -xpc_setup_partitions_sn_sn2(void) +xpc_setup_partitions_sn2(void) { /* nothing needs to be done */ return 0; } static void -xpc_teardown_partitions_sn_sn2(void) +xpc_teardown_partitions_sn2(void) { /* nothing needs to be done */ } @@ -431,6 +431,13 @@ xpc_send_chctl_openreply_sn2(struct xpc_channel *ch, unsigned long *irq_flags) } static void +xpc_send_chctl_opencomplete_sn2(struct xpc_channel *ch, + unsigned long *irq_flags) +{ + XPC_SEND_NOTIFY_IRQ_SN2(ch, XPC_CHCTL_OPENCOMPLETE, irq_flags); +} + +static void xpc_send_chctl_msgrequest_sn2(struct xpc_channel *ch) { XPC_SEND_NOTIFY_IRQ_SN2(ch, XPC_CHCTL_MSGREQUEST, NULL); @@ -621,7 +628,7 @@ xpc_get_partition_rsvd_page_pa_sn2(void *buf, u64 *cookie, unsigned long *rp_pa, static int -xpc_setup_rsvd_page_sn_sn2(struct xpc_rsvd_page *rp) +xpc_setup_rsvd_page_sn2(struct xpc_rsvd_page *rp) { struct amo *amos_page; int i; @@ -629,7 +636,7 @@ xpc_setup_rsvd_page_sn_sn2(struct xpc_rsvd_page *rp) xpc_vars_sn2 = XPC_RP_VARS(rp); - rp->sn.vars_pa = xp_pa(xpc_vars_sn2); + rp->sn.sn2.vars_pa = xp_pa(xpc_vars_sn2); /* vars_part array follows immediately after vars */ xpc_vars_part_sn2 = (struct xpc_vars_part_sn2 *)((u8 *)XPC_RP_VARS(rp) + @@ -693,6 +700,33 @@ xpc_setup_rsvd_page_sn_sn2(struct xpc_rsvd_page *rp) return 0; } +static int +xpc_hb_allowed_sn2(short partid, void *heartbeating_to_mask) +{ + return test_bit(partid, heartbeating_to_mask); +} + +static void +xpc_allow_hb_sn2(short partid) +{ + DBUG_ON(xpc_vars_sn2 == NULL); + set_bit(partid, xpc_vars_sn2->heartbeating_to_mask); +} + +static void +xpc_disallow_hb_sn2(short partid) +{ + DBUG_ON(xpc_vars_sn2 == NULL); + clear_bit(partid, xpc_vars_sn2->heartbeating_to_mask); +} + +static void +xpc_disallow_all_hbs_sn2(void) +{ + DBUG_ON(xpc_vars_sn2 == NULL); + bitmap_zero(xpc_vars_sn2->heartbeating_to_mask, xp_max_npartitions); +} + static void xpc_increment_heartbeat_sn2(void) { @@ -719,7 +753,6 @@ xpc_heartbeat_init_sn2(void) DBUG_ON(xpc_vars_sn2 == NULL); bitmap_zero(xpc_vars_sn2->heartbeating_to_mask, XP_MAX_NPARTITIONS_SN2); - xpc_heartbeating_to_mask = &xpc_vars_sn2->heartbeating_to_mask[0]; xpc_online_heartbeat_sn2(); } @@ -751,9 +784,9 @@ xpc_get_remote_heartbeat_sn2(struct xpc_partition *part) remote_vars->heartbeating_to_mask[0]); if ((remote_vars->heartbeat == part->last_heartbeat && - remote_vars->heartbeat_offline == 0) || - !xpc_hb_allowed(sn_partition_id, - &remote_vars->heartbeating_to_mask)) { + !remote_vars->heartbeat_offline) || + !xpc_hb_allowed_sn2(sn_partition_id, + remote_vars->heartbeating_to_mask)) { ret = xpNoHeartbeat; } else { part->last_heartbeat = remote_vars->heartbeat; @@ -972,7 +1005,7 @@ xpc_identify_activate_IRQ_req_sn2(int nasid) return; } - remote_vars_pa = remote_rp->sn.vars_pa; + remote_vars_pa = remote_rp->sn.sn2.vars_pa; remote_rp_version = remote_rp->version; remote_rp_ts_jiffies = remote_rp->ts_jiffies; @@ -1129,7 +1162,7 @@ xpc_process_activate_IRQ_rcvd_sn2(void) * Setup the channel structures that are sn2 specific. */ static enum xp_retval -xpc_setup_ch_structures_sn_sn2(struct xpc_partition *part) +xpc_setup_ch_structures_sn2(struct xpc_partition *part) { struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; struct xpc_channel_sn2 *ch_sn2; @@ -1251,7 +1284,7 @@ out_1: * Teardown the channel structures that are sn2 specific. */ static void -xpc_teardown_ch_structures_sn_sn2(struct xpc_partition *part) +xpc_teardown_ch_structures_sn2(struct xpc_partition *part) { struct xpc_partition_sn2 *part_sn2 = &part->sn.sn2; short partid = XPC_PARTID(part); @@ -2315,61 +2348,70 @@ xpc_received_payload_sn2(struct xpc_channel *ch, void *payload) xpc_acknowledge_msgs_sn2(ch, get, msg->flags); } +static struct xpc_arch_operations xpc_arch_ops_sn2 = { + .setup_partitions = xpc_setup_partitions_sn2, + .teardown_partitions = xpc_teardown_partitions_sn2, + .process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_sn2, + .get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_sn2, + .setup_rsvd_page = xpc_setup_rsvd_page_sn2, + + .allow_hb = xpc_allow_hb_sn2, + .disallow_hb = xpc_disallow_hb_sn2, + .disallow_all_hbs = xpc_disallow_all_hbs_sn2, + .increment_heartbeat = xpc_increment_heartbeat_sn2, + .offline_heartbeat = xpc_offline_heartbeat_sn2, + .online_heartbeat = xpc_online_heartbeat_sn2, + .heartbeat_init = xpc_heartbeat_init_sn2, + .heartbeat_exit = xpc_heartbeat_exit_sn2, + .get_remote_heartbeat = xpc_get_remote_heartbeat_sn2, + + .request_partition_activation = + xpc_request_partition_activation_sn2, + .request_partition_reactivation = + xpc_request_partition_reactivation_sn2, + .request_partition_deactivation = + xpc_request_partition_deactivation_sn2, + .cancel_partition_deactivation_request = + xpc_cancel_partition_deactivation_request_sn2, + + .setup_ch_structures = xpc_setup_ch_structures_sn2, + .teardown_ch_structures = xpc_teardown_ch_structures_sn2, + + .make_first_contact = xpc_make_first_contact_sn2, + + .get_chctl_all_flags = xpc_get_chctl_all_flags_sn2, + .send_chctl_closerequest = xpc_send_chctl_closerequest_sn2, + .send_chctl_closereply = xpc_send_chctl_closereply_sn2, + .send_chctl_openrequest = xpc_send_chctl_openrequest_sn2, + .send_chctl_openreply = xpc_send_chctl_openreply_sn2, + .send_chctl_opencomplete = xpc_send_chctl_opencomplete_sn2, + .process_msg_chctl_flags = xpc_process_msg_chctl_flags_sn2, + + .save_remote_msgqueue_pa = xpc_save_remote_msgqueue_pa_sn2, + + .setup_msg_structures = xpc_setup_msg_structures_sn2, + .teardown_msg_structures = xpc_teardown_msg_structures_sn2, + + .indicate_partition_engaged = xpc_indicate_partition_engaged_sn2, + .indicate_partition_disengaged = xpc_indicate_partition_disengaged_sn2, + .partition_engaged = xpc_partition_engaged_sn2, + .any_partition_engaged = xpc_any_partition_engaged_sn2, + .assume_partition_disengaged = xpc_assume_partition_disengaged_sn2, + + .n_of_deliverable_payloads = xpc_n_of_deliverable_payloads_sn2, + .send_payload = xpc_send_payload_sn2, + .get_deliverable_payload = xpc_get_deliverable_payload_sn2, + .received_payload = xpc_received_payload_sn2, + .notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_sn2, +}; + int xpc_init_sn2(void) { int ret; size_t buf_size; - xpc_setup_partitions_sn = xpc_setup_partitions_sn_sn2; - xpc_teardown_partitions_sn = xpc_teardown_partitions_sn_sn2; - xpc_get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_sn2; - xpc_setup_rsvd_page_sn = xpc_setup_rsvd_page_sn_sn2; - xpc_increment_heartbeat = xpc_increment_heartbeat_sn2; - xpc_offline_heartbeat = xpc_offline_heartbeat_sn2; - xpc_online_heartbeat = xpc_online_heartbeat_sn2; - xpc_heartbeat_init = xpc_heartbeat_init_sn2; - xpc_heartbeat_exit = xpc_heartbeat_exit_sn2; - xpc_get_remote_heartbeat = xpc_get_remote_heartbeat_sn2; - - xpc_request_partition_activation = xpc_request_partition_activation_sn2; - xpc_request_partition_reactivation = - xpc_request_partition_reactivation_sn2; - xpc_request_partition_deactivation = - xpc_request_partition_deactivation_sn2; - xpc_cancel_partition_deactivation_request = - xpc_cancel_partition_deactivation_request_sn2; - - xpc_process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_sn2; - xpc_setup_ch_structures_sn = xpc_setup_ch_structures_sn_sn2; - xpc_teardown_ch_structures_sn = xpc_teardown_ch_structures_sn_sn2; - xpc_make_first_contact = xpc_make_first_contact_sn2; - - xpc_get_chctl_all_flags = xpc_get_chctl_all_flags_sn2; - xpc_send_chctl_closerequest = xpc_send_chctl_closerequest_sn2; - xpc_send_chctl_closereply = xpc_send_chctl_closereply_sn2; - xpc_send_chctl_openrequest = xpc_send_chctl_openrequest_sn2; - xpc_send_chctl_openreply = xpc_send_chctl_openreply_sn2; - - xpc_save_remote_msgqueue_pa = xpc_save_remote_msgqueue_pa_sn2; - - xpc_setup_msg_structures = xpc_setup_msg_structures_sn2; - xpc_teardown_msg_structures = xpc_teardown_msg_structures_sn2; - - xpc_notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_sn2; - xpc_process_msg_chctl_flags = xpc_process_msg_chctl_flags_sn2; - xpc_n_of_deliverable_payloads = xpc_n_of_deliverable_payloads_sn2; - xpc_get_deliverable_payload = xpc_get_deliverable_payload_sn2; - - xpc_indicate_partition_engaged = xpc_indicate_partition_engaged_sn2; - xpc_indicate_partition_disengaged = - xpc_indicate_partition_disengaged_sn2; - xpc_partition_engaged = xpc_partition_engaged_sn2; - xpc_any_partition_engaged = xpc_any_partition_engaged_sn2; - xpc_assume_partition_disengaged = xpc_assume_partition_disengaged_sn2; - - xpc_send_payload = xpc_send_payload_sn2; - xpc_received_payload = xpc_received_payload_sn2; + xpc_arch_ops = xpc_arch_ops_sn2; if (offsetof(struct xpc_msg_sn2, payload) > XPC_MSG_HDR_MAX_SIZE) { dev_err(xpc_part, "header portion of struct xpc_msg_sn2 is " diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index f7fff4727ed..9172fcdee4e 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -46,8 +46,7 @@ struct uv_IO_APIC_route_entry { }; #endif -static atomic64_t xpc_heartbeat_uv; -static DECLARE_BITMAP(xpc_heartbeating_to_mask_uv, XP_MAX_NPARTITIONS_UV); +static struct xpc_heartbeat_uv *xpc_heartbeat_uv; #define XPC_ACTIVATE_MSG_SIZE_UV (1 * GRU_CACHE_LINE_BYTES) #define XPC_ACTIVATE_MQ_SIZE_UV (4 * XP_MAX_NPARTITIONS_UV * \ @@ -63,7 +62,7 @@ static struct xpc_gru_mq_uv *xpc_activate_mq_uv; static struct xpc_gru_mq_uv *xpc_notify_mq_uv; static int -xpc_setup_partitions_sn_uv(void) +xpc_setup_partitions_uv(void) { short partid; struct xpc_partition_uv *part_uv; @@ -79,7 +78,7 @@ xpc_setup_partitions_sn_uv(void) } static void -xpc_teardown_partitions_sn_uv(void) +xpc_teardown_partitions_uv(void) { short partid; struct xpc_partition_uv *part_uv; @@ -423,41 +422,6 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, /* syncing of remote_act_state was just done above */ break; - case XPC_ACTIVATE_MQ_MSG_INC_HEARTBEAT_UV: { - struct xpc_activate_mq_msg_heartbeat_req_uv *msg; - - msg = container_of(msg_hdr, - struct xpc_activate_mq_msg_heartbeat_req_uv, - hdr); - part_uv->heartbeat = msg->heartbeat; - break; - } - case XPC_ACTIVATE_MQ_MSG_OFFLINE_HEARTBEAT_UV: { - struct xpc_activate_mq_msg_heartbeat_req_uv *msg; - - msg = container_of(msg_hdr, - struct xpc_activate_mq_msg_heartbeat_req_uv, - hdr); - part_uv->heartbeat = msg->heartbeat; - - spin_lock_irqsave(&part_uv->flags_lock, irq_flags); - part_uv->flags |= XPC_P_HEARTBEAT_OFFLINE_UV; - spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags); - break; - } - case XPC_ACTIVATE_MQ_MSG_ONLINE_HEARTBEAT_UV: { - struct xpc_activate_mq_msg_heartbeat_req_uv *msg; - - msg = container_of(msg_hdr, - struct xpc_activate_mq_msg_heartbeat_req_uv, - hdr); - part_uv->heartbeat = msg->heartbeat; - - spin_lock_irqsave(&part_uv->flags_lock, irq_flags); - part_uv->flags &= ~XPC_P_HEARTBEAT_OFFLINE_UV; - spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags); - break; - } case XPC_ACTIVATE_MQ_MSG_ACTIVATE_REQ_UV: { struct xpc_activate_mq_msg_activate_req_uv *msg; @@ -475,6 +439,7 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, part_uv->act_state_req = XPC_P_ASR_ACTIVATE_UV; part->remote_rp_pa = msg->rp_gpa; /* !!! _pa is _gpa */ part->remote_rp_ts_jiffies = msg_hdr->rp_ts_jiffies; + part_uv->heartbeat_gpa = msg->heartbeat_gpa; if (msg->activate_gru_mq_desc_gpa != part_uv->activate_gru_mq_desc_gpa) { @@ -569,6 +534,17 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, xpc_wakeup_channel_mgr(part); break; } + case XPC_ACTIVATE_MQ_MSG_CHCTL_OPENCOMPLETE_UV: { + struct xpc_activate_mq_msg_chctl_opencomplete_uv *msg; + + msg = container_of(msg_hdr, struct + xpc_activate_mq_msg_chctl_opencomplete_uv, hdr); + spin_lock_irqsave(&part->chctl_lock, irq_flags); + part->chctl.flags[msg->ch_number] |= XPC_CHCTL_OPENCOMPLETE; + spin_unlock_irqrestore(&part->chctl_lock, irq_flags); + + xpc_wakeup_channel_mgr(part); + } case XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV: spin_lock_irqsave(&part_uv->flags_lock, irq_flags); part_uv->flags |= XPC_P_ENGAGED_UV; @@ -759,7 +735,7 @@ xpc_send_local_activate_IRQ_uv(struct xpc_partition *part, int act_state_req) /* * !!! Make our side think that the remote partition sent an activate - * !!! message our way by doing what the activate IRQ handler would + * !!! mq message our way by doing what the activate IRQ handler would * !!! do had one really been sent. */ @@ -806,90 +782,82 @@ xpc_get_partition_rsvd_page_pa_uv(void *buf, u64 *cookie, unsigned long *rp_pa, } static int -xpc_setup_rsvd_page_sn_uv(struct xpc_rsvd_page *rp) +xpc_setup_rsvd_page_uv(struct xpc_rsvd_page *rp) { - rp->sn.activate_gru_mq_desc_gpa = + xpc_heartbeat_uv = + &xpc_partitions[sn_partition_id].sn.uv.cached_heartbeat; + rp->sn.uv.heartbeat_gpa = uv_gpa(xpc_heartbeat_uv); + rp->sn.uv.activate_gru_mq_desc_gpa = uv_gpa(xpc_activate_mq_uv->gru_mq_desc); return 0; } static void -xpc_send_heartbeat_uv(int msg_type) +xpc_allow_hb_uv(short partid) { - short partid; - struct xpc_partition *part; - struct xpc_activate_mq_msg_heartbeat_req_uv msg; - - /* - * !!! On uv we're broadcasting a heartbeat message every 5 seconds. - * !!! Whereas on sn2 we're bte_copy'ng the heartbeat info every 20 - * !!! seconds. This is an increase in numalink traffic. - * ??? Is this good? - */ - - msg.heartbeat = atomic64_inc_return(&xpc_heartbeat_uv); - - partid = find_first_bit(xpc_heartbeating_to_mask_uv, - XP_MAX_NPARTITIONS_UV); - - while (partid < XP_MAX_NPARTITIONS_UV) { - part = &xpc_partitions[partid]; +} - xpc_send_activate_IRQ_part_uv(part, &msg, sizeof(msg), - msg_type); +static void +xpc_disallow_hb_uv(short partid) +{ +} - partid = find_next_bit(xpc_heartbeating_to_mask_uv, - XP_MAX_NPARTITIONS_UV, partid + 1); - } +static void +xpc_disallow_all_hbs_uv(void) +{ } static void xpc_increment_heartbeat_uv(void) { - xpc_send_heartbeat_uv(XPC_ACTIVATE_MQ_MSG_INC_HEARTBEAT_UV); + xpc_heartbeat_uv->value++; } static void xpc_offline_heartbeat_uv(void) { - xpc_send_heartbeat_uv(XPC_ACTIVATE_MQ_MSG_OFFLINE_HEARTBEAT_UV); + xpc_increment_heartbeat_uv(); + xpc_heartbeat_uv->offline = 1; } static void xpc_online_heartbeat_uv(void) { - xpc_send_heartbeat_uv(XPC_ACTIVATE_MQ_MSG_ONLINE_HEARTBEAT_UV); + xpc_increment_heartbeat_uv(); + xpc_heartbeat_uv->offline = 0; } static void xpc_heartbeat_init_uv(void) { - atomic64_set(&xpc_heartbeat_uv, 0); - bitmap_zero(xpc_heartbeating_to_mask_uv, XP_MAX_NPARTITIONS_UV); - xpc_heartbeating_to_mask = &xpc_heartbeating_to_mask_uv[0]; + xpc_heartbeat_uv->value = 1; + xpc_heartbeat_uv->offline = 0; } static void xpc_heartbeat_exit_uv(void) { - xpc_send_heartbeat_uv(XPC_ACTIVATE_MQ_MSG_OFFLINE_HEARTBEAT_UV); + xpc_offline_heartbeat_uv(); } static enum xp_retval xpc_get_remote_heartbeat_uv(struct xpc_partition *part) { struct xpc_partition_uv *part_uv = &part->sn.uv; - enum xp_retval ret = xpNoHeartbeat; + enum xp_retval ret; - if (part_uv->remote_act_state != XPC_P_AS_INACTIVE && - part_uv->remote_act_state != XPC_P_AS_DEACTIVATING) { + ret = xp_remote_memcpy(uv_gpa(&part_uv->cached_heartbeat), + part_uv->heartbeat_gpa, + sizeof(struct xpc_heartbeat_uv)); + if (ret != xpSuccess) + return ret; - if (part_uv->heartbeat != part->last_heartbeat || - (part_uv->flags & XPC_P_HEARTBEAT_OFFLINE_UV)) { + if (part_uv->cached_heartbeat.value == part->last_heartbeat && + !part_uv->cached_heartbeat.offline) { - part->last_heartbeat = part_uv->heartbeat; - ret = xpSuccess; - } + ret = xpNoHeartbeat; + } else { + part->last_heartbeat = part_uv->cached_heartbeat.value; } return ret; } @@ -904,8 +872,9 @@ xpc_request_partition_activation_uv(struct xpc_rsvd_page *remote_rp, part->remote_rp_pa = remote_rp_gpa; /* !!! _pa here is really _gpa */ part->remote_rp_ts_jiffies = remote_rp->ts_jiffies; + part->sn.uv.heartbeat_gpa = remote_rp->sn.uv.heartbeat_gpa; part->sn.uv.activate_gru_mq_desc_gpa = - remote_rp->sn.activate_gru_mq_desc_gpa; + remote_rp->sn.uv.activate_gru_mq_desc_gpa; /* * ??? Is it a good idea to make this conditional on what is @@ -913,8 +882,9 @@ xpc_request_partition_activation_uv(struct xpc_rsvd_page *remote_rp, */ if (part->sn.uv.remote_act_state == XPC_P_AS_INACTIVE) { msg.rp_gpa = uv_gpa(xpc_rsvd_page); + msg.heartbeat_gpa = xpc_rsvd_page->sn.uv.heartbeat_gpa; msg.activate_gru_mq_desc_gpa = - xpc_rsvd_page->sn.activate_gru_mq_desc_gpa; + xpc_rsvd_page->sn.uv.activate_gru_mq_desc_gpa; xpc_send_activate_IRQ_part_uv(part, &msg, sizeof(msg), XPC_ACTIVATE_MQ_MSG_ACTIVATE_REQ_UV); } @@ -1010,7 +980,7 @@ xpc_n_of_fifo_entries_uv(struct xpc_fifo_head_uv *head) * Setup the channel structures that are uv specific. */ static enum xp_retval -xpc_setup_ch_structures_sn_uv(struct xpc_partition *part) +xpc_setup_ch_structures_uv(struct xpc_partition *part) { struct xpc_channel_uv *ch_uv; int ch_number; @@ -1029,7 +999,7 @@ xpc_setup_ch_structures_sn_uv(struct xpc_partition *part) * Teardown the channel structures that are uv specific. */ static void -xpc_teardown_ch_structures_sn_uv(struct xpc_partition *part) +xpc_teardown_ch_structures_uv(struct xpc_partition *part) { /* nothing needs to be done */ return; @@ -1243,6 +1213,16 @@ xpc_send_chctl_openreply_uv(struct xpc_channel *ch, unsigned long *irq_flags) } static void +xpc_send_chctl_opencomplete_uv(struct xpc_channel *ch, unsigned long *irq_flags) +{ + struct xpc_activate_mq_msg_chctl_opencomplete_uv msg; + + msg.ch_number = ch->number; + xpc_send_activate_IRQ_ch_uv(ch, irq_flags, &msg, sizeof(msg), + XPC_ACTIVATE_MQ_MSG_CHCTL_OPENCOMPLETE_UV); +} + +static void xpc_send_chctl_local_msgrequest_uv(struct xpc_partition *part, int ch_number) { unsigned long irq_flags; @@ -1669,58 +1649,67 @@ xpc_received_payload_uv(struct xpc_channel *ch, void *payload) msg->hdr.msg_slot_number += ch->remote_nentries; } +static struct xpc_arch_operations xpc_arch_ops_uv = { + .setup_partitions = xpc_setup_partitions_uv, + .teardown_partitions = xpc_teardown_partitions_uv, + .process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_uv, + .get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_uv, + .setup_rsvd_page = xpc_setup_rsvd_page_uv, + + .allow_hb = xpc_allow_hb_uv, + .disallow_hb = xpc_disallow_hb_uv, + .disallow_all_hbs = xpc_disallow_all_hbs_uv, + .increment_heartbeat = xpc_increment_heartbeat_uv, + .offline_heartbeat = xpc_offline_heartbeat_uv, + .online_heartbeat = xpc_online_heartbeat_uv, + .heartbeat_init = xpc_heartbeat_init_uv, + .heartbeat_exit = xpc_heartbeat_exit_uv, + .get_remote_heartbeat = xpc_get_remote_heartbeat_uv, + + .request_partition_activation = + xpc_request_partition_activation_uv, + .request_partition_reactivation = + xpc_request_partition_reactivation_uv, + .request_partition_deactivation = + xpc_request_partition_deactivation_uv, + .cancel_partition_deactivation_request = + xpc_cancel_partition_deactivation_request_uv, + + .setup_ch_structures = xpc_setup_ch_structures_uv, + .teardown_ch_structures = xpc_teardown_ch_structures_uv, + + .make_first_contact = xpc_make_first_contact_uv, + + .get_chctl_all_flags = xpc_get_chctl_all_flags_uv, + .send_chctl_closerequest = xpc_send_chctl_closerequest_uv, + .send_chctl_closereply = xpc_send_chctl_closereply_uv, + .send_chctl_openrequest = xpc_send_chctl_openrequest_uv, + .send_chctl_openreply = xpc_send_chctl_openreply_uv, + .send_chctl_opencomplete = xpc_send_chctl_opencomplete_uv, + .process_msg_chctl_flags = xpc_process_msg_chctl_flags_uv, + + .save_remote_msgqueue_pa = xpc_save_remote_msgqueue_pa_uv, + + .setup_msg_structures = xpc_setup_msg_structures_uv, + .teardown_msg_structures = xpc_teardown_msg_structures_uv, + + .indicate_partition_engaged = xpc_indicate_partition_engaged_uv, + .indicate_partition_disengaged = xpc_indicate_partition_disengaged_uv, + .assume_partition_disengaged = xpc_assume_partition_disengaged_uv, + .partition_engaged = xpc_partition_engaged_uv, + .any_partition_engaged = xpc_any_partition_engaged_uv, + + .n_of_deliverable_payloads = xpc_n_of_deliverable_payloads_uv, + .send_payload = xpc_send_payload_uv, + .get_deliverable_payload = xpc_get_deliverable_payload_uv, + .received_payload = xpc_received_payload_uv, + .notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_uv, +}; + int xpc_init_uv(void) { - xpc_setup_partitions_sn = xpc_setup_partitions_sn_uv; - xpc_teardown_partitions_sn = xpc_teardown_partitions_sn_uv; - xpc_process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_uv; - xpc_get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_uv; - xpc_setup_rsvd_page_sn = xpc_setup_rsvd_page_sn_uv; - xpc_increment_heartbeat = xpc_increment_heartbeat_uv; - xpc_offline_heartbeat = xpc_offline_heartbeat_uv; - xpc_online_heartbeat = xpc_online_heartbeat_uv; - xpc_heartbeat_init = xpc_heartbeat_init_uv; - xpc_heartbeat_exit = xpc_heartbeat_exit_uv; - xpc_get_remote_heartbeat = xpc_get_remote_heartbeat_uv; - - xpc_request_partition_activation = xpc_request_partition_activation_uv; - xpc_request_partition_reactivation = - xpc_request_partition_reactivation_uv; - xpc_request_partition_deactivation = - xpc_request_partition_deactivation_uv; - xpc_cancel_partition_deactivation_request = - xpc_cancel_partition_deactivation_request_uv; - - xpc_setup_ch_structures_sn = xpc_setup_ch_structures_sn_uv; - xpc_teardown_ch_structures_sn = xpc_teardown_ch_structures_sn_uv; - - xpc_make_first_contact = xpc_make_first_contact_uv; - - xpc_get_chctl_all_flags = xpc_get_chctl_all_flags_uv; - xpc_send_chctl_closerequest = xpc_send_chctl_closerequest_uv; - xpc_send_chctl_closereply = xpc_send_chctl_closereply_uv; - xpc_send_chctl_openrequest = xpc_send_chctl_openrequest_uv; - xpc_send_chctl_openreply = xpc_send_chctl_openreply_uv; - - xpc_save_remote_msgqueue_pa = xpc_save_remote_msgqueue_pa_uv; - - xpc_setup_msg_structures = xpc_setup_msg_structures_uv; - xpc_teardown_msg_structures = xpc_teardown_msg_structures_uv; - - xpc_indicate_partition_engaged = xpc_indicate_partition_engaged_uv; - xpc_indicate_partition_disengaged = - xpc_indicate_partition_disengaged_uv; - xpc_assume_partition_disengaged = xpc_assume_partition_disengaged_uv; - xpc_partition_engaged = xpc_partition_engaged_uv; - xpc_any_partition_engaged = xpc_any_partition_engaged_uv; - - xpc_n_of_deliverable_payloads = xpc_n_of_deliverable_payloads_uv; - xpc_process_msg_chctl_flags = xpc_process_msg_chctl_flags_uv; - xpc_send_payload = xpc_send_payload_uv; - xpc_notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_uv; - xpc_get_deliverable_payload = xpc_get_deliverable_payload_uv; - xpc_received_payload = xpc_received_payload_uv; + xpc_arch_ops = xpc_arch_ops_uv; if (sizeof(struct xpc_notify_mq_msghdr_uv) > XPC_MSG_HDR_MAX_SIZE) { dev_err(xpc_part, "xpc_notify_mq_msghdr_uv is larger than %d\n", diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c index deb7b53167e..83a12125b94 100644 --- a/drivers/net/atl1c/atl1c_main.c +++ b/drivers/net/atl1c/atl1c_main.c @@ -2532,8 +2532,8 @@ static int __devinit atl1c_probe(struct pci_dev *pdev, * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((pci_set_dma_mask(pdev, DMA_32BIT_MASK) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK) != 0)) { + if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || + (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 9b75aa63006..30d0c81c989 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -1821,11 +1821,11 @@ static int __devinit be_probe(struct pci_dev *pdev, be_msix_enable(adapter); - status = pci_set_dma_mask(pdev, DMA_64BIT_MASK); + status = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); if (!status) { netdev->features |= NETIF_F_HIGHDMA; } else { - status = pci_set_dma_mask(pdev, DMA_32BIT_MASK); + status = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (status) { dev_err(&pdev->dev, "Could not set PCI DMA Mask\n"); goto free_netdev; diff --git a/drivers/net/jme.c b/drivers/net/jme.c index ece35040288..621a7c0c46b 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -2591,13 +2591,13 @@ static int jme_pci_dma64(struct pci_dev *pdev) { if (pdev->device == PCI_DEVICE_ID_JMICRON_JMC250 && - !pci_set_dma_mask(pdev, DMA_64BIT_MASK)) - if (!pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK)) + !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) + if (!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) return 1; if (pdev->device == PCI_DEVICE_ID_JMICRON_JMC250 && - !pci_set_dma_mask(pdev, DMA_40BIT_MASK)) - if (!pci_set_consistent_dma_mask(pdev, DMA_40BIT_MASK)) + !pci_set_dma_mask(pdev, DMA_BIT_MASK(40))) + if (!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40))) return 1; if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) diff --git a/drivers/net/wireless/ath9k/pci.c b/drivers/net/wireless/ath9k/pci.c index 6dbc58580ab..168411d322a 100644 --- a/drivers/net/wireless/ath9k/pci.c +++ b/drivers/net/wireless/ath9k/pci.c @@ -93,14 +93,14 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pci_enable_device(pdev)) return -EIO; - ret = pci_set_dma_mask(pdev, DMA_32BIT_MASK); + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (ret) { printk(KERN_ERR "ath9k: 32-bit DMA not available\n"); goto bad; } - ret = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (ret) { printk(KERN_ERR "ath9k: 32-bit DMA consistent " diff --git a/drivers/net/wireless/p54/p54pci.c b/drivers/net/wireless/p54/p54pci.c index e3569a0a952..b1610ea4bb3 100644 --- a/drivers/net/wireless/p54/p54pci.c +++ b/drivers/net/wireless/p54/p54pci.c @@ -492,8 +492,8 @@ static int __devinit p54p_probe(struct pci_dev *pdev, goto err_disable_dev; } - if (pci_set_dma_mask(pdev, DMA_32BIT_MASK) || - pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK)) { + if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) || + pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { dev_err(&pdev->dev, "No suitable DMA available\n"); goto err_free_reg; } diff --git a/drivers/parisc/superio.c b/drivers/parisc/superio.c index 4fa3bb2ddfe..33e5ade774c 100644 --- a/drivers/parisc/superio.c +++ b/drivers/parisc/superio.c @@ -434,7 +434,8 @@ static void __init superio_parport_init(void) 0 /*base_hi*/, PAR_IRQ, PARPORT_DMA_NONE /* dma */, - NULL /*struct pci_dev* */) ) + NULL /*struct pci_dev* */), + 0 /* shared irq flags */ ) printk(KERN_WARNING PFX "Probing parallel port failed.\n"); #endif /* CONFIG_PARPORT_PC */ diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 0570794ccf1..d1815272c43 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/hdreg.h> +#include <linux/async.h> #include <asm/ccwdev.h> #include <asm/ebcdic.h> @@ -480,8 +481,10 @@ static void dasd_change_state(struct dasd_device *device) if (rc && rc != -EAGAIN) device->target = device->state; - if (device->state == device->target) + if (device->state == device->target) { wake_up(&dasd_init_waitq); + dasd_put_device(device); + } /* let user-space know that the device status changed */ kobject_uevent(&device->cdev->dev.kobj, KOBJ_CHANGE); @@ -513,12 +516,15 @@ void dasd_kick_device(struct dasd_device *device) */ void dasd_set_target_state(struct dasd_device *device, int target) { + dasd_get_device(device); /* If we are in probeonly mode stop at DASD_STATE_READY. */ if (dasd_probeonly && target > DASD_STATE_READY) target = DASD_STATE_READY; if (device->target != target) { - if (device->state == target) + if (device->state == target) { wake_up(&dasd_init_waitq); + dasd_put_device(device); + } device->target = target; } if (device->state != device->target) @@ -2148,6 +2154,22 @@ dasd_exit(void) * SECTION: common functions for ccw_driver use */ +static void dasd_generic_auto_online(void *data, async_cookie_t cookie) +{ + struct ccw_device *cdev = data; + int ret; + + ret = ccw_device_set_online(cdev); + if (ret) + pr_warning("%s: Setting the DASD online failed with rc=%d\n", + dev_name(&cdev->dev), ret); + else { + struct dasd_device *device = dasd_device_from_cdev(cdev); + wait_event(dasd_init_waitq, _wait_for_device(device)); + dasd_put_device(device); + } +} + /* * Initial attempt at a probe function. this can be simplified once * the other detection code is gone. @@ -2180,10 +2202,7 @@ int dasd_generic_probe(struct ccw_device *cdev, */ if ((dasd_get_feature(cdev, DASD_FEATURE_INITIAL_ONLINE) > 0 ) || (dasd_autodetect && dasd_busid_known(dev_name(&cdev->dev)) != 0)) - ret = ccw_device_set_online(cdev); - if (ret) - pr_warning("%s: Setting the DASD online failed with rc=%d\n", - dev_name(&cdev->dev), ret); + async_schedule(dasd_generic_auto_online, cdev); return 0; } @@ -2290,13 +2309,7 @@ int dasd_generic_set_online(struct ccw_device *cdev, } else pr_debug("dasd_generic device %s found\n", dev_name(&cdev->dev)); - - /* FIXME: we have to wait for the root device but we don't want - * to wait for each single device but for all at once. */ - wait_event(dasd_init_waitq, _wait_for_device(device)); - dasd_put_device(device); - return rc; } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 21254793c60..cb52da033f0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2019,15 +2019,23 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track( ccw++; recid += count; new_track = 0; + /* first idaw for a ccw may start anywhere */ + if (!idaw_dst) + idaw_dst = dst; } - /* If we start a new idaw, everything is fine and the - * start of the new idaw is the start of this segment. + /* If we start a new idaw, we must make sure that it + * starts on an IDA_BLOCK_SIZE boundary. * If we continue an idaw, we must make sure that the * current segment begins where the so far accumulated * idaw ends */ - if (!idaw_dst) - idaw_dst = dst; + if (!idaw_dst) { + if (__pa(dst) & (IDA_BLOCK_SIZE-1)) { + dasd_sfree_request(cqr, startdev); + return ERR_PTR(-ERANGE); + } else + idaw_dst = dst; + } if ((idaw_dst + idaw_len) != dst) { dasd_sfree_request(cqr, startdev); return ERR_PTR(-ERANGE); diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 9e8a2914259..accd957454e 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -881,42 +881,6 @@ no_handler: qdio_set_state(irq_ptr, QDIO_IRQ_STATE_STOPPED); } -static void qdio_call_shutdown(struct work_struct *work) -{ - struct ccw_device_private *priv; - struct ccw_device *cdev; - - priv = container_of(work, struct ccw_device_private, kick_work); - cdev = priv->cdev; - qdio_shutdown(cdev, QDIO_FLAG_CLEANUP_USING_CLEAR); - put_device(&cdev->dev); -} - -static void qdio_int_error(struct ccw_device *cdev) -{ - struct qdio_irq *irq_ptr = cdev->private->qdio_data; - - switch (irq_ptr->state) { - case QDIO_IRQ_STATE_INACTIVE: - case QDIO_IRQ_STATE_CLEANUP: - qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); - break; - case QDIO_IRQ_STATE_ESTABLISHED: - case QDIO_IRQ_STATE_ACTIVE: - qdio_set_state(irq_ptr, QDIO_IRQ_STATE_STOPPED); - if (get_device(&cdev->dev)) { - /* Can't call shutdown from interrupt context. */ - PREPARE_WORK(&cdev->private->kick_work, - qdio_call_shutdown); - queue_work(ccw_device_work, &cdev->private->kick_work); - } - break; - default: - WARN_ON(1); - } - wake_up(&cdev->private->wait_q); -} - static int qdio_establish_check_errors(struct ccw_device *cdev, int cstat, int dstat) { @@ -973,10 +937,8 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, switch (PTR_ERR(irb)) { case -EIO: DBF_ERROR("%4x IO error", irq_ptr->schid.sch_no); - return; - case -ETIMEDOUT: - DBF_ERROR("%4x IO timeout", irq_ptr->schid.sch_no); - qdio_int_error(cdev); + qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + wake_up(&cdev->private->wait_q); return; default: WARN_ON(1); @@ -1001,7 +963,6 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, case QDIO_IRQ_STATE_ACTIVE: if (cstat & SCHN_STAT_PCI) { qdio_int_handler_pci(irq_ptr); - /* no state change so no need to wake up wait_q */ return; } if ((cstat & ~SCHN_STAT_PCI) || dstat) { diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c index e6d1fc8c54f..a85ad05e854 100644 --- a/drivers/sbus/char/jsflash.c +++ b/drivers/sbus/char/jsflash.c @@ -383,18 +383,22 @@ static int jsf_ioctl_program(void __user *arg) return 0; } -static int jsf_ioctl(struct inode *inode, struct file *f, unsigned int cmd, - unsigned long arg) +static long jsf_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { + lock_kernel(); int error = -ENOTTY; void __user *argp = (void __user *)arg; - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) { + unlock_kernel(); return -EPERM; + } switch (cmd) { case JSFLASH_IDENT: - if (copy_to_user(argp, &jsf0.id, JSFIDSZ)) + if (copy_to_user(argp, &jsf0.id, JSFIDSZ)) { + unlock_kernel(); return -EFAULT; + } break; case JSFLASH_ERASE: error = jsf_ioctl_erase(arg); @@ -404,6 +408,7 @@ static int jsf_ioctl(struct inode *inode, struct file *f, unsigned int cmd, break; } + unlock_kernel(); return error; } @@ -439,7 +444,7 @@ static const struct file_operations jsf_fops = { .llseek = jsf_lseek, .read = jsf_read, .write = jsf_write, - .ioctl = jsf_ioctl, + .unlocked_ioctl = jsf_ioctl, .mmap = jsf_mmap, .open = jsf_open, .release = jsf_release, diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c index 27993c37775..2c56fd56ec6 100644 --- a/drivers/sbus/char/uctrl.c +++ b/drivers/sbus/char/uctrl.c @@ -197,9 +197,8 @@ static struct uctrl_driver { static void uctrl_get_event_status(struct uctrl_driver *); static void uctrl_get_external_status(struct uctrl_driver *); -static int -uctrl_ioctl(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) +static long +uctrl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { default: @@ -226,7 +225,7 @@ static irqreturn_t uctrl_interrupt(int irq, void *dev_id) static const struct file_operations uctrl_fops = { .owner = THIS_MODULE, .llseek = no_llseek, - .ioctl = uctrl_ioctl, + .unlocked_ioctl = uctrl_ioctl, .open = uctrl_open, }; diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index fdb14ec4fd4..8b7983aba8f 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -2234,10 +2234,10 @@ static int twa_resume(struct pci_dev *pdev) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (pci_set_dma_mask(pdev, DMA_64BIT_MASK) - || pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK)) - if (pci_set_dma_mask(pdev, DMA_32BIT_MASK) - || pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK)) { + if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) + || pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) + if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) + || pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { TW_PRINTK(host, TW_DRIVER, 0x40, "Failed to set dma mask during resume"); retval = -ENODEV; goto out_disable_device; diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 280261c451d..2a889853a10 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -1378,7 +1378,7 @@ int aac_get_adapter_info(struct aac_dev* dev) if (dev->nondasd_support && !dev->in_reset) printk(KERN_INFO "%s%d: Non-DASD support enabled.\n",dev->name, dev->id); - if (dma_get_required_mask(&dev->pdev->dev) > DMA_32BIT_MASK) + if (dma_get_required_mask(&dev->pdev->dev) > DMA_BIT_MASK(32)) dev->needs_dac = 1; dev->dac_support = 0; if ((sizeof(dma_addr_t) > 4) && dev->needs_dac && diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index b1bd3fc7bae..36fd2e75da1 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1394,7 +1394,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd, */ cmd->sense_buffer[8] = 0; /* Information */ cmd->sense_buffer[9] = 0xa; /* Add. length */ - do_div(bghm, cmd->device->sector_size); + bghm /= cmd->device->sector_size; failing_sector = scsi_get_lba(cmd); failing_sector += bghm; diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index 52427a8324f..a91f5143cea 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -855,9 +855,9 @@ _base_config_dma_addressing(struct MPT2SAS_ADAPTER *ioc, struct pci_dev *pdev) if (sizeof(dma_addr_t) > 4) { const uint64_t required_mask = dma_get_required_mask(&pdev->dev); - if ((required_mask > DMA_32BIT_MASK) && !pci_set_dma_mask(pdev, - DMA_64BIT_MASK) && !pci_set_consistent_dma_mask(pdev, - DMA_64BIT_MASK)) { + if ((required_mask > DMA_BIT_MASK(32)) && !pci_set_dma_mask(pdev, + DMA_BIT_MASK(64)) && !pci_set_consistent_dma_mask(pdev, + DMA_BIT_MASK(64))) { ioc->base_add_sg_single = &_base_add_sg_single_64; ioc->sge_size = sizeof(Mpi2SGESimple64_t); desc = "64"; @@ -865,8 +865,8 @@ _base_config_dma_addressing(struct MPT2SAS_ADAPTER *ioc, struct pci_dev *pdev) } } - if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK) - && !pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK)) { + if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) + && !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { ioc->base_add_sg_single = &_base_add_sg_single_32; ioc->sge_size = sizeof(Mpi2SGESimple32_t); desc = "32"; diff --git a/drivers/sh/intc.c b/drivers/sh/intc.c index 7fb9b5c4669..12d13d99b6f 100644 --- a/drivers/sh/intc.c +++ b/drivers/sh/intc.c @@ -44,6 +44,7 @@ struct intc_handle_int { struct intc_desc_int { struct list_head list; struct sys_device sysdev; + pm_message_t state; unsigned long *reg; #ifdef CONFIG_SMP unsigned long *smp; @@ -786,18 +787,44 @@ static int intc_suspend(struct sys_device *dev, pm_message_t state) /* get intc controller associated with this sysdev */ d = container_of(dev, struct intc_desc_int, sysdev); - /* enable wakeup irqs belonging to this intc controller */ - for_each_irq_desc(irq, desc) { - if ((desc->status & IRQ_WAKEUP) && (desc->chip == &d->chip)) - intc_enable(irq); + switch (state.event) { + case PM_EVENT_ON: + if (d->state.event != PM_EVENT_FREEZE) + break; + for_each_irq_desc(irq, desc) { + if (desc->chip != &d->chip) + continue; + if (desc->status & IRQ_DISABLED) + intc_disable(irq); + else + intc_enable(irq); + } + break; + case PM_EVENT_FREEZE: + /* nothing has to be done */ + break; + case PM_EVENT_SUSPEND: + /* enable wakeup irqs belonging to this intc controller */ + for_each_irq_desc(irq, desc) { + if ((desc->status & IRQ_WAKEUP) && (desc->chip == &d->chip)) + intc_enable(irq); + } + break; } + d->state = state; return 0; } +static int intc_resume(struct sys_device *dev) +{ + return intc_suspend(dev, PMSG_ON); +} + static struct sysdev_class intc_sysdev_class = { .name = "intc", .suspend = intc_suspend, + .resume = intc_resume, }; /* register this intc as sysdev to allow suspend/resume */ diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 643908b74bc..8eba98c8ed1 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -658,7 +658,7 @@ int spi_write_then_read(struct spi_device *spi, int status; struct spi_message message; - struct spi_transfer x; + struct spi_transfer x[2]; u8 *local_buf; /* Use preallocated DMA-safe buffer. We can't avoid copying here, @@ -669,9 +669,15 @@ int spi_write_then_read(struct spi_device *spi, return -EINVAL; spi_message_init(&message); - memset(&x, 0, sizeof x); - x.len = n_tx + n_rx; - spi_message_add_tail(&x, &message); + memset(x, 0, sizeof x); + if (n_tx) { + x[0].len = n_tx; + spi_message_add_tail(&x[0], &message); + } + if (n_rx) { + x[1].len = n_rx; + spi_message_add_tail(&x[1], &message); + } /* ... unless someone else is using the pre-allocated buffer */ if (!mutex_trylock(&lock)) { @@ -682,15 +688,15 @@ int spi_write_then_read(struct spi_device *spi, local_buf = buf; memcpy(local_buf, txbuf, n_tx); - x.tx_buf = local_buf; - x.rx_buf = local_buf; + x[0].tx_buf = local_buf; + x[1].rx_buf = local_buf + n_tx; /* do the i/o */ status = spi_sync(spi, &message); if (status == 0) - memcpy(rxbuf, x.rx_buf + n_tx, n_rx); + memcpy(rxbuf, x[1].rx_buf, n_rx); - if (x.tx_buf == buf) + if (x[0].tx_buf == buf) mutex_unlock(&lock); else kfree(local_buf); diff --git a/drivers/staging/b3dfg/b3dfg.c b/drivers/staging/b3dfg/b3dfg.c index 0348072b3ab..75ebe338c6f 100644 --- a/drivers/staging/b3dfg/b3dfg.c +++ b/drivers/staging/b3dfg/b3dfg.c @@ -1000,7 +1000,7 @@ static int __devinit b3dfg_probe(struct pci_dev *pdev, pci_set_master(pdev); - r = pci_set_dma_mask(pdev, DMA_32BIT_MASK); + r = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (r) { dev_err(&pdev->dev, "no usable DMA configuration\n"); goto err_free_res; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 869d47cb6db..0a69c0977e3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -546,10 +546,6 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp) tty->driver_data = acm; acm->tty = tty; - /* force low_latency on so that our tty_push actually forces the data through, - otherwise it is scheduled, and with high data rates data can get lost. */ - tty->low_latency = 1; - if (usb_autopm_get_interface(acm->control) < 0) goto early_bail; else diff --git a/drivers/usb/otg/nop-usb-xceiv.c b/drivers/usb/otg/nop-usb-xceiv.c index 4b933f646f2..c567168f89a 100644 --- a/drivers/usb/otg/nop-usb-xceiv.c +++ b/drivers/usb/otg/nop-usb-xceiv.c @@ -36,14 +36,14 @@ struct nop_usb_xceiv { struct device *dev; }; -static u64 nop_xceiv_dmamask = DMA_32BIT_MASK; +static u64 nop_xceiv_dmamask = DMA_BIT_MASK(32); static struct platform_device nop_xceiv_device = { .name = "nop_usb_xceiv", .id = -1, .dev = { .dma_mask = &nop_xceiv_dmamask, - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = NULL, }, }; diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 2620bf6fe5e..9c4c700c7cc 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1215,20 +1215,22 @@ static void ti_bulk_in_callback(struct urb *urb) } tty = tty_port_tty_get(&port->port); - if (tty && urb->actual_length) { - usb_serial_debug_data(debug, dev, __func__, - urb->actual_length, urb->transfer_buffer); - - if (!tport->tp_is_open) - dbg("%s - port closed, dropping data", __func__); - else - ti_recv(&urb->dev->dev, tty, + if (tty) { + if (urb->actual_length) { + usb_serial_debug_data(debug, dev, __func__, + urb->actual_length, urb->transfer_buffer); + + if (!tport->tp_is_open) + dbg("%s - port closed, dropping data", + __func__); + else + ti_recv(&urb->dev->dev, tty, urb->transfer_buffer, urb->actual_length); - - spin_lock(&tport->tp_lock); - tport->tp_icount.rx += urb->actual_length; - spin_unlock(&tport->tp_lock); + spin_lock(&tport->tp_lock); + tport->tp_icount.rx += urb->actual_length; + spin_unlock(&tport->tp_lock); + } tty_kref_put(tty); } diff --git a/drivers/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c index 16bb7e3c031..6c37e8ee5ef 100644 --- a/drivers/video/aty/radeon_base.c +++ b/drivers/video/aty/radeon_base.c @@ -698,8 +698,8 @@ static void __devinit radeon_get_pllinfo(struct radeonfb_info *rinfo) found: /* * Some methods fail to retrieve SCLK and MCLK values, we apply default - * settings in this case (200Mhz). If that really happne often, we could - * fetch from registers instead... + * settings in this case (200Mhz). If that really happens often, we + * could fetch from registers instead... */ if (rinfo->pll.mclk == 0) rinfo->pll.mclk = 20000; diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index dd37cbcaf8c..157057c79ca 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -35,8 +35,6 @@ static int fb_notifier_callback(struct notifier_block *self, return 0; bd = container_of(self, struct backlight_device, fb_notif); - if (!lock_fb_info(evdata->info)) - return -ENODEV; mutex_lock(&bd->ops_lock); if (bd->ops) if (!bd->ops->check_fb || @@ -49,7 +47,6 @@ static int fb_notifier_callback(struct notifier_block *self, backlight_update_status(bd); } mutex_unlock(&bd->ops_lock); - unlock_fb_info(evdata->info); return 0; } diff --git a/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c index 0bb13df0fa8..b6449470106 100644 --- a/drivers/video/backlight/lcd.c +++ b/drivers/video/backlight/lcd.c @@ -40,8 +40,6 @@ static int fb_notifier_callback(struct notifier_block *self, if (!ld->ops) return 0; - if (!lock_fb_info(evdata->info)) - return -ENODEV; mutex_lock(&ld->ops_lock); if (!ld->ops->check_fb || ld->ops->check_fb(ld, evdata->info)) { if (event == FB_EVENT_BLANK) { @@ -53,7 +51,6 @@ static int fb_notifier_callback(struct notifier_block *self, } } mutex_unlock(&ld->ops_lock); - unlock_fb_info(evdata->info); return 0; } diff --git a/drivers/video/cirrusfb.c b/drivers/video/cirrusfb.c index d42e385f091..4c2bf923418 100644 --- a/drivers/video/cirrusfb.c +++ b/drivers/video/cirrusfb.c @@ -567,9 +567,7 @@ static int cirrusfb_check_var(struct fb_var_screeninfo *var, default: dev_dbg(info->device, "Unsupported bpp size: %d\n", var->bits_per_pixel); - assert(false); - /* should never occur */ - break; + return -EINVAL; } if (var->xres_virtual < var->xres) diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 2cd500a304f..471a9a60376 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -2263,9 +2263,12 @@ static void fbcon_generic_blank(struct vc_data *vc, struct fb_info *info, } + if (!lock_fb_info(info)) + return; event.info = info; event.data = ␣ fb_notifier_call_chain(FB_EVENT_CONBLANK, &event); + unlock_fb_info(info); } static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) @@ -2956,8 +2959,6 @@ static int fbcon_fb_unregistered(struct fb_info *info) { int i, idx; - if (!lock_fb_info(info)) - return -ENODEV; idx = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) @@ -2985,8 +2986,6 @@ static int fbcon_fb_unregistered(struct fb_info *info) if (primary_device == idx) primary_device = -1; - unlock_fb_info(info); - if (!num_registered_fb) unregister_con_driver(&fb_con); @@ -3027,11 +3026,8 @@ static int fbcon_fb_registered(struct fb_info *info) { int ret = 0, i, idx; - if (!lock_fb_info(info)) - return -ENODEV; idx = info->node; fbcon_select_primary(info); - unlock_fb_info(info); if (info_idx == -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { @@ -3152,53 +3148,23 @@ static int fbcon_event_notify(struct notifier_block *self, switch(action) { case FB_EVENT_SUSPEND: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_suspended(info); - unlock_fb_info(info); break; case FB_EVENT_RESUME: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_resumed(info); - unlock_fb_info(info); break; case FB_EVENT_MODE_CHANGE: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_modechanged(info); - unlock_fb_info(info); break; case FB_EVENT_MODE_CHANGE_ALL: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_set_all_vcs(info); - unlock_fb_info(info); break; case FB_EVENT_MODE_DELETE: mode = event->data; - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } ret = fbcon_mode_deleted(info, mode); - unlock_fb_info(info); break; case FB_EVENT_FB_UNBIND: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } idx = info->node; - unlock_fb_info(info); ret = fbcon_fb_unbind(idx); break; case FB_EVENT_FB_REGISTERED: @@ -3217,29 +3183,14 @@ static int fbcon_event_notify(struct notifier_block *self, con2fb->framebuffer = con2fb_map[con2fb->console - 1]; break; case FB_EVENT_BLANK: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_fb_blanked(info, *(int *)event->data); - unlock_fb_info(info); break; case FB_EVENT_NEW_MODELIST: - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_new_modelist(info); - unlock_fb_info(info); break; case FB_EVENT_GET_REQ: caps = event->data; - if (!lock_fb_info(info)) { - ret = -ENODEV; - goto done; - } fbcon_get_requirement(info, caps); - unlock_fb_info(info); break; } done: diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c index 0c5b9a9fd56..8dea2bc9270 100644 --- a/drivers/video/efifb.c +++ b/drivers/video/efifb.c @@ -210,12 +210,15 @@ static int __init efifb_probe(struct platform_device *dev) unsigned int size_total; int request_succeeded = 0; - printk(KERN_INFO "efifb: probing for efifb\n"); - if (!screen_info.lfb_depth) screen_info.lfb_depth = 32; if (!screen_info.pages) screen_info.pages = 1; + if (!screen_info.lfb_base) { + printk(KERN_DEBUG "efifb: invalid framebuffer address\n"); + return -ENODEV; + } + printk(KERN_INFO "efifb: probing for efifb\n"); /* just assume they're all unset if any are */ if (!screen_info.blue_size) { diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index 2ac32e6b595..d412a1ddc12 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1097,8 +1097,11 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, return -EINVAL; con2fb.framebuffer = -1; event.data = &con2fb; + if (!lock_fb_info(info)) + return -ENODEV; event.info = info; fb_notifier_call_chain(FB_EVENT_GET_CONSOLE_MAP, &event); + unlock_fb_info(info); ret = copy_to_user(argp, &con2fb, sizeof(con2fb)) ? -EFAULT : 0; break; case FBIOPUT_CON2FBMAP: @@ -1115,8 +1118,11 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, break; } event.data = &con2fb; + if (!lock_fb_info(info)) + return -ENODEV; event.info = info; ret = fb_notifier_call_chain(FB_EVENT_SET_CONSOLE_MAP, &event); + unlock_fb_info(info); break; case FBIOBLANK: if (!lock_fb_info(info)) @@ -1521,7 +1527,10 @@ register_framebuffer(struct fb_info *fb_info) registered_fb[i] = fb_info; event.info = fb_info; + if (!lock_fb_info(fb_info)) + return -ENODEV; fb_notifier_call_chain(FB_EVENT_FB_REGISTERED, &event); + unlock_fb_info(fb_info); return 0; } @@ -1555,8 +1564,12 @@ unregister_framebuffer(struct fb_info *fb_info) goto done; } + + if (!lock_fb_info(fb_info)) + return -ENODEV; event.info = fb_info; ret = fb_notifier_call_chain(FB_EVENT_FB_UNBIND, &event); + unlock_fb_info(fb_info); if (ret) { ret = -EINVAL; @@ -1590,6 +1603,8 @@ void fb_set_suspend(struct fb_info *info, int state) { struct fb_event event; + if (!lock_fb_info(info)) + return; event.info = info; if (state) { fb_notifier_call_chain(FB_EVENT_SUSPEND, &event); @@ -1598,6 +1613,7 @@ void fb_set_suspend(struct fb_info *info, int state) info->state = FBINFO_STATE_RUNNING; fb_notifier_call_chain(FB_EVENT_RESUME, &event); } + unlock_fb_info(info); } /** @@ -1667,8 +1683,11 @@ int fb_new_modelist(struct fb_info *info) err = 1; if (!list_empty(&info->modelist)) { + if (!lock_fb_info(info)) + return -ENODEV; event.info = info; err = fb_notifier_call_chain(FB_EVENT_NEW_MODELIST, &event); + unlock_fb_info(info); } return err; diff --git a/drivers/video/intelfb/intelfb.h b/drivers/video/intelfb/intelfb.h index a50bea61480..40984551c92 100644 --- a/drivers/video/intelfb/intelfb.h +++ b/drivers/video/intelfb/intelfb.h @@ -53,6 +53,7 @@ #define PCI_DEVICE_ID_INTEL_830M 0x3577 #define PCI_DEVICE_ID_INTEL_845G 0x2562 #define PCI_DEVICE_ID_INTEL_85XGM 0x3582 +#define PCI_DEVICE_ID_INTEL_854 0x358E #define PCI_DEVICE_ID_INTEL_865G 0x2572 #define PCI_DEVICE_ID_INTEL_915G 0x2582 #define PCI_DEVICE_ID_INTEL_915GM 0x2592 @@ -154,6 +155,7 @@ enum intel_chips { INTEL_85XGM, INTEL_852GM, INTEL_852GME, + INTEL_854, INTEL_855GM, INTEL_855GME, INTEL_865G, diff --git a/drivers/video/intelfb/intelfb_i2c.c b/drivers/video/intelfb/intelfb_i2c.c index b3065492bb2..487f2be4746 100644 --- a/drivers/video/intelfb/intelfb_i2c.c +++ b/drivers/video/intelfb/intelfb_i2c.c @@ -156,6 +156,7 @@ void intelfb_create_i2c_busses(struct intelfb_info *dinfo) switch(dinfo->chipset) { case INTEL_830M: case INTEL_845G: + case INTEL_854: case INTEL_855GM: case INTEL_865G: dinfo->output[i].type = INTELFB_OUTPUT_DVO; diff --git a/drivers/video/intelfb/intelfbdrv.c b/drivers/video/intelfb/intelfbdrv.c index 6d8e5415c80..ace14fe02fc 100644 --- a/drivers/video/intelfb/intelfbdrv.c +++ b/drivers/video/intelfb/intelfbdrv.c @@ -182,6 +182,7 @@ static struct pci_device_id intelfb_pci_table[] __devinitdata = { { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_845G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_845G }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_85XGM, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_85XGM }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_865G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_865G }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_854, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_854 }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_915G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_915G }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_915GM, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_915GM }, { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_945G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_945G }, diff --git a/drivers/video/intelfb/intelfbhw.c b/drivers/video/intelfb/intelfbhw.c index 8b26b27c2db..0689f97c523 100644 --- a/drivers/video/intelfb/intelfbhw.c +++ b/drivers/video/intelfb/intelfbhw.c @@ -84,6 +84,11 @@ int intelfbhw_get_chipset(struct pci_dev *pdev, struct intelfb_info *dinfo) dinfo->mobile = 0; dinfo->pll_index = PLLS_I8xx; return 0; + case PCI_DEVICE_ID_INTEL_854: + dinfo->mobile = 1; + dinfo->name = "Intel(R) 854"; + dinfo->chipset = INTEL_854; + return 0; case PCI_DEVICE_ID_INTEL_85XGM: tmp = 0; dinfo->mobile = 1; diff --git a/drivers/video/s3fb.c b/drivers/video/s3fb.c index 4dcec48a1d7..c3fad34309e 100644 --- a/drivers/video/s3fb.c +++ b/drivers/video/s3fb.c @@ -45,11 +45,11 @@ struct s3fb_info { static const struct svga_fb_format s3fb_formats[] = { { 0, {0, 6, 0}, {0, 6, 0}, {0, 6, 0}, {0, 0, 0}, 0, FB_TYPE_TEXT, FB_AUX_TEXT_SVGA_STEP4, FB_VISUAL_PSEUDOCOLOR, 8, 16}, - { 4, {0, 6, 0}, {0, 6, 0}, {0, 6, 0}, {0, 0, 0}, 0, + { 4, {0, 4, 0}, {0, 4, 0}, {0, 4, 0}, {0, 0, 0}, 0, FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 8, 16}, - { 4, {0, 6, 0}, {0, 6, 0}, {0, 6, 0}, {0, 0, 0}, 1, + { 4, {0, 4, 0}, {0, 4, 0}, {0, 4, 0}, {0, 0, 0}, 1, FB_TYPE_INTERLEAVED_PLANES, 1, FB_VISUAL_PSEUDOCOLOR, 8, 16}, - { 8, {0, 6, 0}, {0, 6, 0}, {0, 6, 0}, {0, 0, 0}, 0, + { 8, {0, 8, 0}, {0, 8, 0}, {0, 8, 0}, {0, 0, 0}, 0, FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_PSEUDOCOLOR, 4, 8}, {16, {10, 5, 0}, {5, 5, 0}, {0, 5, 0}, {0, 0, 0}, 0, FB_TYPE_PACKED_PIXELS, 0, FB_VISUAL_TRUECOLOR, 2, 4}, diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c index fad58cf9ef7..10ddad8e17d 100644 --- a/drivers/video/sa1100fb.c +++ b/drivers/video/sa1100fb.c @@ -199,16 +199,20 @@ extern void (*sa1100fb_backlight_power)(int on); extern void (*sa1100fb_lcd_power)(int on); -/* - * IMHO this looks wrong. In 8BPP, length should be 8. - */ -static struct sa1100fb_rgb rgb_8 = { +static struct sa1100fb_rgb rgb_4 = { .red = { .offset = 0, .length = 4, }, .green = { .offset = 0, .length = 4, }, .blue = { .offset = 0, .length = 4, }, .transp = { .offset = 0, .length = 0, }, }; +static struct sa1100fb_rgb rgb_8 = { + .red = { .offset = 0, .length = 8, }, + .green = { .offset = 0, .length = 8, }, + .blue = { .offset = 0, .length = 8, }, + .transp = { .offset = 0, .length = 0, }, +}; + static struct sa1100fb_rgb def_rgb_16 = { .red = { .offset = 11, .length = 5, }, .green = { .offset = 5, .length = 6, }, @@ -613,7 +617,7 @@ sa1100fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) DPRINTK("var->bits_per_pixel=%d\n", var->bits_per_pixel); switch (var->bits_per_pixel) { case 4: - rgbidx = RGB_8; + rgbidx = RGB_4; break; case 8: rgbidx = RGB_8; @@ -1382,6 +1386,7 @@ static struct sa1100fb_info * __init sa1100fb_init_fbinfo(struct device *dev) fbi->fb.monspecs = monspecs; fbi->fb.pseudo_palette = (fbi + 1); + fbi->rgb[RGB_4] = &rgb_4; fbi->rgb[RGB_8] = &rgb_8; fbi->rgb[RGB_16] = &def_rgb_16; diff --git a/drivers/video/sa1100fb.h b/drivers/video/sa1100fb.h index 86831db9a04..1c3b459865d 100644 --- a/drivers/video/sa1100fb.h +++ b/drivers/video/sa1100fb.h @@ -57,9 +57,10 @@ struct sa1100fb_lcd_reg { unsigned long lccr3; }; -#define RGB_8 (0) -#define RGB_16 (1) -#define NR_RGB 2 +#define RGB_4 (0) +#define RGB_8 (1) +#define RGB_16 (2) +#define NR_RGB 3 struct sa1100fb_info { struct fb_info fb; diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c index 346d6458cf7..7e17ee95a97 100644 --- a/drivers/video/sis/sis_main.c +++ b/drivers/video/sis/sis_main.c @@ -1129,7 +1129,7 @@ sisfb_bpp_to_var(struct sis_video_info *ivideo, struct fb_var_screeninfo *var) switch(var->bits_per_pixel) { case 8: var->red.offset = var->green.offset = var->blue.offset = 0; - var->red.length = var->green.length = var->blue.length = 6; + var->red.length = var->green.length = var->blue.length = 8; break; case 16: var->red.offset = 11; diff --git a/drivers/video/skeletonfb.c b/drivers/video/skeletonfb.c index a439159204a..89158bc71da 100644 --- a/drivers/video/skeletonfb.c +++ b/drivers/video/skeletonfb.c @@ -308,9 +308,11 @@ static int xxxfb_setcolreg(unsigned regno, unsigned red, unsigned green, * color depth = SUM(var->{color}.length) * * Pseudocolor: - * var->{color}.offset is 0 - * var->{color}.length contains width of DAC or the number of unique - * colors available (color depth) + * var->{color}.offset is 0 unless the palette index takes less than + * bits_per_pixel bits and is stored in the upper + * bits of the pixel value + * var->{color}.length is set so that 1 << length is the number of + * available palette entries * pseudo_palette is not used * RAMDAC[X] is programmed to (red, green, blue) * color depth = var->{color}.length diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c index 0b370aebdbf..421770b5e6a 100644 --- a/drivers/video/uvesafb.c +++ b/drivers/video/uvesafb.c @@ -55,6 +55,7 @@ static u16 maxvf __devinitdata; /* maximum vertical frequency */ static u16 maxhf __devinitdata; /* maximum horizontal frequency */ static u16 vbemode __devinitdata; /* force use of a specific VBE mode */ static char *mode_option __devinitdata; +static u8 dac_width = 6; static struct uvesafb_ktask *uvfb_tasks[UVESAFB_TASKS_MAX]; static DEFINE_MUTEX(uvfb_lock); @@ -303,22 +304,10 @@ static void uvesafb_setup_var(struct fb_var_screeninfo *var, var->blue.offset = 0; var->transp.offset = 0; - /* - * We're assuming that we can switch the DAC to 8 bits. If - * this proves to be incorrect, we'll update the fields - * later in set_par(). - */ - if (par->vbe_ib.capabilities & VBE_CAP_CAN_SWITCH_DAC) { - var->red.length = 8; - var->green.length = 8; - var->blue.length = 8; - var->transp.length = 0; - } else { - var->red.length = 6; - var->green.length = 6; - var->blue.length = 6; - var->transp.length = 0; - } + var->red.length = 8; + var->green.length = 8; + var->blue.length = 8; + var->transp.length = 0; } } @@ -1006,7 +995,7 @@ static int uvesafb_setcolreg(unsigned regno, unsigned red, unsigned green, struct fb_info *info) { struct uvesafb_pal_entry entry; - int shift = 16 - info->var.green.length; + int shift = 16 - dac_width; int err = 0; if (regno >= info->cmap.len) @@ -1055,7 +1044,7 @@ static int uvesafb_setcolreg(unsigned regno, unsigned red, unsigned green, static int uvesafb_setcmap(struct fb_cmap *cmap, struct fb_info *info) { struct uvesafb_pal_entry *entries; - int shift = 16 - info->var.green.length; + int shift = 16 - dac_width; int i, err = 0; if (info->var.bits_per_pixel == 8) { @@ -1317,13 +1306,9 @@ setmode: err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f || ((task->t.regs.ebx & 0xff00) >> 8) != 8) { - /* - * We've failed to set the DAC palette format - - * time to correct var. - */ - info->var.red.length = 6; - info->var.green.length = 6; - info->var.blue.length = 6; + dac_width = 6; + } else { + dac_width = 8; } } diff --git a/drivers/video/vfb.c b/drivers/video/vfb.c index cc919ae4657..050d432c7d9 100644 --- a/drivers/video/vfb.c +++ b/drivers/video/vfb.c @@ -318,13 +318,16 @@ static int vfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, * {hardwarespecific} contains width of RAMDAC * cmap[X] is programmed to (X << red.offset) | (X << green.offset) | (X << blue.offset) * RAMDAC[X] is programmed to (red, green, blue) - * + * * Pseudocolor: - * uses offset = 0 && length = RAMDAC register width. - * var->{color}.offset is 0 - * var->{color}.length contains widht of DAC + * var->{color}.offset is 0 unless the palette index takes less than + * bits_per_pixel bits and is stored in the upper + * bits of the pixel value + * var->{color}.length is set so that 1 << length is the number of available + * palette entries * cmap is not used * RAMDAC[X] is programmed to (red, green, blue) + * * Truecolor: * does not use DAC. Usually 3 are present. * var->{color}.offset contains start of bitfield diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index 5f54c01c156..bdfd584ad85 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -21,29 +21,41 @@ static void disable_hotplug_cpu(int cpu) set_cpu_present(cpu, false); } -static void vcpu_hotplug(unsigned int cpu) +static int vcpu_online(unsigned int cpu) { int err; char dir[32], state[32]; - if (!cpu_possible(cpu)) - return; - sprintf(dir, "cpu/%u", cpu); err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state); if (err != 1) { printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); - return; + return err; } - if (strcmp(state, "online") == 0) { + if (strcmp(state, "online") == 0) + return 1; + else if (strcmp(state, "offline") == 0) + return 0; + + printk(KERN_ERR "XENBUS: unknown state(%s) on CPU%d\n", state, cpu); + return -EINVAL; +} +static void vcpu_hotplug(unsigned int cpu) +{ + if (!cpu_possible(cpu)) + return; + + switch (vcpu_online(cpu)) { + case 1: enable_hotplug_cpu(cpu); - } else if (strcmp(state, "offline") == 0) { + break; + case 0: (void)cpu_down(cpu); disable_hotplug_cpu(cpu); - } else { - printk(KERN_ERR "XENBUS: unknown state(%s) on CPU%d\n", - state, cpu); + break; + default: + break; } } @@ -64,12 +76,20 @@ static void handle_vcpu_hotplug_event(struct xenbus_watch *watch, static int setup_cpu_watcher(struct notifier_block *notifier, unsigned long event, void *data) { + int cpu; static struct xenbus_watch cpu_watch = { .node = "cpu", .callback = handle_vcpu_hotplug_event}; (void)register_xenbus_watch(&cpu_watch); + for_each_possible_cpu(cpu) { + if (vcpu_online(cpu) == 0) { + (void)cpu_down(cpu); + cpu_clear(cpu, cpu_present_map); + } + } + return NOTIFY_DONE; } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 0d61db1e7b4..4b5b84837ee 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -62,14 +62,15 @@ static int xen_suspend(void *data) gnttab_resume(); xen_mm_unpin_all(); - sysdev_resume(); - if (!*cancelled) { xen_irq_resume(); xen_console_resume(); xen_timer_resume(); } + sysdev_resume(); + device_power_up(PMSG_RESUME); + return 0; } @@ -348,6 +348,24 @@ err: return NULL; } +/** + * bio_alloc - allocate a bio for I/O + * @gfp_mask: the GFP_ mask given to the slab allocator + * @nr_iovecs: number of iovecs to pre-allocate + * + * Description: + * bio_alloc will allocate a bio and associated bio_vec array that can hold + * at least @nr_iovecs entries. Allocations will be done from the + * fs_bio_set. Also see @bio_alloc_bioset. + * + * If %__GFP_WAIT is set, then bio_alloc will always be able to allocate + * a bio. This is due to the mempool guarantees. To make this work, callers + * must never allocate more than 1 bio at the time from this pool. Callers + * that need to allocate more than 1 bio must always submit the previously + * allocate bio for IO before attempting to allocate a new one. Failure to + * do so can cause livelocks under memory pressure. + * + **/ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs) { struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); diff --git a/fs/buffer.c b/fs/buffer.c index 13edf7ad3ff..ff8bb1f2333 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -547,7 +547,7 @@ repeat: return err; } -void do_thaw_all(unsigned long unused) +void do_thaw_all(struct work_struct *work) { struct super_block *sb; char b[BDEVNAME_SIZE]; @@ -567,6 +567,7 @@ restart: goto restart; } spin_unlock(&sb_lock); + kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } @@ -577,7 +578,13 @@ restart: */ void emergency_thaw_all(void) { - pdflush_operation(do_thaw_all, 0); + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_thaw_all); + schedule_work(work); + } } /** diff --git a/fs/direct-io.c b/fs/direct-io.c index da258e7249c..05763bbc205 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -307,8 +307,6 @@ dio_bio_alloc(struct dio *dio, struct block_device *bdev, struct bio *bio; bio = bio_alloc(GFP_KERNEL, nr_vecs); - if (bio == NULL) - return -ENOMEM; bio->bi_bdev = bdev; bio->bi_sector = first_sector; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b43b9556366..acf67883110 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -590,9 +590,8 @@ static int ext2_get_blocks(struct inode *inode, if (depth == 0) return (err); -reread: - partial = ext2_get_branch(inode, depth, offsets, chain, &err); + partial = ext2_get_branch(inode, depth, offsets, chain, &err); /* Simplest case - block found, no allocation needed */ if (!partial) { first_block = le32_to_cpu(chain[depth - 1].key); @@ -602,15 +601,16 @@ reread: while (count < maxblocks && count <= blocks_to_boundary) { ext2_fsblk_t blk; - if (!verify_chain(chain, partial)) { + if (!verify_chain(chain, chain + depth - 1)) { /* * Indirect block might be removed by * truncate while we were reading it. * Handling of that case: forget what we've * got now, go to reread. */ + err = -EAGAIN; count = 0; - goto changed; + break; } blk = le32_to_cpu(*(chain[depth-1].p + count)); if (blk == first_block + count) @@ -618,7 +618,8 @@ reread: else break; } - goto got_it; + if (err != -EAGAIN) + goto got_it; } /* Next simple case - plain lookup or failed read of indirect block */ @@ -626,6 +627,33 @@ reread: goto cleanup; mutex_lock(&ei->truncate_mutex); + /* + * If the indirect block is missing while we are reading + * the chain(ext3_get_branch() returns -EAGAIN err), or + * if the chain has been changed after we grab the semaphore, + * (either because another process truncated this branch, or + * another get_block allocated this branch) re-grab the chain to see if + * the request block has been allocated or not. + * + * Since we already block the truncate/other get_block + * at this point, we will have the current copy of the chain when we + * splice the branch into the tree. + */ + if (err == -EAGAIN || !verify_chain(chain, partial)) { + while (partial > chain) { + brelse(partial->bh); + partial--; + } + partial = ext2_get_branch(inode, depth, offsets, chain, &err); + if (!partial) { + count++; + mutex_unlock(&ei->truncate_mutex); + if (err) + goto cleanup; + clear_buffer_new(bh_result); + goto got_it; + } + } /* * Okay, we need to do block allocation. Lazily initialize the block @@ -683,12 +711,6 @@ cleanup: partial--; } return err; -changed: - while (partial > chain) { - brelse(partial->bh); - partial--; - } - goto reread; } int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6132353dcf6..2a1cb097976 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2416,8 +2416,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) len = ee_len; bio = bio_alloc(GFP_NOIO, len); - if (!bio) - return -ENOMEM; bio->bi_sector = ee_pblock; bio->bi_bdev = inode->i_sb->s_bdev; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 2b25133524a..06f30e96567 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -938,9 +938,9 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) } static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, - unsigned *nbytesp, int write) + size_t *nbytesp, int write) { - unsigned nbytes = *nbytesp; + size_t nbytes = *nbytesp; unsigned long user_addr = (unsigned long) buf; unsigned offset = user_addr & ~PAGE_MASK; int npages; @@ -955,7 +955,7 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, return 0; } - nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); + nbytes = min_t(size_t, nbytes, FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; npages = clamp(npages, 1, FUSE_MAX_PAGES_PER_REQ); down_read(¤t->mm->mmap_sem); @@ -1298,6 +1298,8 @@ static int fuse_direct_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_flags & VM_MAYSHARE) return -ENODEV; + invalidate_inode_pages2(file->f_mapping); + return generic_file_mmap(file, vma); } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 3984e47d1d3..1afd9f26bcb 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -597,7 +597,6 @@ __acquires(&gl->gl_spin) GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)); - down_read(&gfs2_umount_flush_sem); if (test_bit(GLF_DEMOTE, &gl->gl_flags) && gl->gl_demote_state != gl->gl_state) { if (find_first_holder(gl)) @@ -614,15 +613,14 @@ __acquires(&gl->gl_spin) if (ret == 0) goto out_unlock; if (ret == 2) - goto out_sem; + goto out; gh = find_first_waiter(gl); gl->gl_target = gh->gh_state; if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) do_error(gl, 0); /* Fail queued try locks */ } do_xmote(gl, gh, gl->gl_target); -out_sem: - up_read(&gfs2_umount_flush_sem); +out: return; out_sched: @@ -631,7 +629,7 @@ out_sched: gfs2_glock_put(gl); out_unlock: clear_bit(GLF_LOCK, &gl->gl_flags); - goto out_sem; + goto out; } static void glock_work_func(struct work_struct *work) @@ -641,6 +639,7 @@ static void glock_work_func(struct work_struct *work) if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) finish_xmote(gl, gl->gl_reply); + down_read(&gfs2_umount_flush_sem); spin_lock(&gl->gl_spin); if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && gl->gl_state != LM_ST_UNLOCKED && @@ -653,6 +652,7 @@ static void glock_work_func(struct work_struct *work) } run_queue(gl, 0); spin_unlock(&gl->gl_spin); + up_read(&gfs2_umount_flush_sem); if (!delay || queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 7b277d44915..5a31d426116 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -137,15 +137,15 @@ void gfs2_set_iop(struct inode *inode) if (S_ISREG(mode)) { inode->i_op = &gfs2_file_iops; if (gfs2_localflocks(sdp)) - inode->i_fop = gfs2_file_fops_nolock; + inode->i_fop = &gfs2_file_fops_nolock; else - inode->i_fop = gfs2_file_fops; + inode->i_fop = &gfs2_file_fops; } else if (S_ISDIR(mode)) { inode->i_op = &gfs2_dir_iops; if (gfs2_localflocks(sdp)) - inode->i_fop = gfs2_dir_fops_nolock; + inode->i_fop = &gfs2_dir_fops_nolock; else - inode->i_fop = gfs2_dir_fops; + inode->i_fop = &gfs2_dir_fops; } else if (S_ISLNK(mode)) { inode->i_op = &gfs2_symlink_iops; } else { diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index dca4fee3078..c30be2b6658 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -101,21 +101,23 @@ void gfs2_dinode_print(const struct gfs2_inode *ip); extern const struct inode_operations gfs2_file_iops; extern const struct inode_operations gfs2_dir_iops; extern const struct inode_operations gfs2_symlink_iops; -extern const struct file_operations *gfs2_file_fops_nolock; -extern const struct file_operations *gfs2_dir_fops_nolock; +extern const struct file_operations gfs2_file_fops_nolock; +extern const struct file_operations gfs2_dir_fops_nolock; extern void gfs2_set_inode_flags(struct inode *inode); #ifdef CONFIG_GFS2_FS_LOCKING_DLM -extern const struct file_operations *gfs2_file_fops; -extern const struct file_operations *gfs2_dir_fops; +extern const struct file_operations gfs2_file_fops; +extern const struct file_operations gfs2_dir_fops; + static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) { return sdp->sd_args.ar_localflocks; } #else /* Single node only */ -#define gfs2_file_fops NULL -#define gfs2_dir_fops NULL +#define gfs2_file_fops gfs2_file_fops_nolock +#define gfs2_dir_fops gfs2_dir_fops_nolock + static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) { return 1; diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c index 70b9b854894..101caf3ee86 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/ops_file.c @@ -705,7 +705,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) } } -const struct file_operations *gfs2_file_fops = &(const struct file_operations){ +const struct file_operations gfs2_file_fops = { .llseek = gfs2_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, @@ -723,7 +723,7 @@ const struct file_operations *gfs2_file_fops = &(const struct file_operations){ .setlease = gfs2_setlease, }; -const struct file_operations *gfs2_dir_fops = &(const struct file_operations){ +const struct file_operations gfs2_dir_fops = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, @@ -735,7 +735,7 @@ const struct file_operations *gfs2_dir_fops = &(const struct file_operations){ #endif /* CONFIG_GFS2_FS_LOCKING_DLM */ -const struct file_operations *gfs2_file_fops_nolock = &(const struct file_operations){ +const struct file_operations gfs2_file_fops_nolock = { .llseek = gfs2_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, @@ -751,7 +751,7 @@ const struct file_operations *gfs2_file_fops_nolock = &(const struct file_operat .setlease = generic_setlease, }; -const struct file_operations *gfs2_dir_fops_nolock = &(const struct file_operations){ +const struct file_operations gfs2_dir_fops_nolock = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 51883b3ad89..650a730707b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -272,11 +272,6 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector) lock_page(page); bio = bio_alloc(GFP_NOFS, 1); - if (unlikely(!bio)) { - __free_page(page); - return -ENOBUFS; - } - bio->bi_sector = sector * (sb->s_blocksize >> 9); bio->bi_bdev = sb->s_bdev; bio_add_page(bio, page, PAGE_SIZE, 0); diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index abd5429ae28..1c70fa5168d 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -371,6 +371,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry, ip = ghs[1].gh_gl->gl_object; ip->i_disksize = size; + i_size_write(inode, size); error = gfs2_meta_inode_buffer(ip, &dibh); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 8d53f66b5bc..152e6c4a0dc 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -81,7 +81,7 @@ struct gfs2_quota_change_host { static LIST_HEAD(qd_lru_list); static atomic_t qd_lru_count = ATOMIC_INIT(0); -static spinlock_t qd_lru_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(qd_lru_lock); int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask) { @@ -1364,7 +1364,7 @@ int gfs2_quotad(void *data) refrigerator(); t = min(quotad_timeo, statfs_timeo); - prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE); spin_lock(&sdp->sd_trunc_lock); empty = list_empty(&sdp->sd_trunc_list); spin_unlock(&sdp->sd_trunc_lock); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9435dda8f1e..a1cbff2b4d9 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -70,6 +70,10 @@ static int hfs_releasepage(struct page *page, gfp_t mask) BUG(); return 0; } + + if (!tree) + return 0; + if (tree->node_size >= PAGE_CACHE_SIZE) { nidx = page->index >> (tree->node_size_shift - PAGE_CACHE_SHIFT); spin_lock(&tree->hash_lock); diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 36ca2e1a4fa..7b6165f25fb 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -349,6 +349,7 @@ void hfs_mdb_put(struct super_block *sb) if (HFS_SB(sb)->nls_disk) unload_nls(HFS_SB(sb)->nls_disk); + free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0); kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } diff --git a/fs/inode.c b/fs/inode.c index d06d6d268de..6ad14a1cd8c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1470,42 +1470,6 @@ static void __wait_on_freeing_inode(struct inode *inode) spin_lock(&inode_lock); } -/* - * We rarely want to lock two inodes that do not have a parent/child - * relationship (such as directory, child inode) simultaneously. The - * vast majority of file systems should be able to get along fine - * without this. Do not use these functions except as a last resort. - */ -void inode_double_lock(struct inode *inode1, struct inode *inode2) -{ - if (inode1 == NULL || inode2 == NULL || inode1 == inode2) { - if (inode1) - mutex_lock(&inode1->i_mutex); - else if (inode2) - mutex_lock(&inode2->i_mutex); - return; - } - - if (inode1 < inode2) { - mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); - } -} -EXPORT_SYMBOL(inode_double_lock); - -void inode_double_unlock(struct inode *inode1, struct inode *inode2) -{ - if (inode1) - mutex_unlock(&inode1->i_mutex); - - if (inode2 && inode2 != inode1) - mutex_unlock(&inode2->i_mutex); -} -EXPORT_SYMBOL(inode_double_unlock); - static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c index c7bd649bbbd..3e9afc2a91d 100644 --- a/fs/jbd/revoke.c +++ b/fs/jbd/revoke.c @@ -55,6 +55,25 @@ * need do nothing. * RevokeValid set, Revoked set: * buffer has been revoked. + * + * Locking rules: + * We keep two hash tables of revoke records. One hashtable belongs to the + * running transaction (is pointed to by journal->j_revoke), the other one + * belongs to the committing transaction. Accesses to the second hash table + * happen only from the kjournald and no other thread touches this table. Also + * journal_switch_revoke_table() which switches which hashtable belongs to the + * running and which to the committing transaction is called only from + * kjournald. Therefore we need no locks when accessing the hashtable belonging + * to the committing transaction. + * + * All users operating on the hash table belonging to the running transaction + * have a handle to the transaction. Therefore they are safe from kjournald + * switching hash tables under them. For operations on the lists of entries in + * the hash table j_revoke_lock is used. + * + * Finally, also replay code uses the hash tables but at this moment noone else + * can touch them (filesystem isn't mounted yet) and hence no locking is + * needed. */ #ifndef __KERNEL__ @@ -402,8 +421,6 @@ int journal_revoke(handle_t *handle, unsigned long blocknr, * the second time we would still have a pending revoke to cancel. So, * do not trust the Revoked bit on buffers unless RevokeValid is also * set. - * - * The caller must have the journal locked. */ int journal_cancel_revoke(handle_t *handle, struct journal_head *jh) { @@ -481,10 +498,7 @@ void journal_switch_revoke_table(journal_t *journal) /* * Write revoke records to the journal for all entries in the current * revoke hash, deleting the entries as we go. - * - * Called with the journal lock held. */ - void journal_write_revoke_records(journal_t *journal, transaction_t *transaction) { diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 24638e059bf..064279e33bb 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -688,6 +688,8 @@ static const struct nilfs_bmap_ptr_operations nilfs_bmap_ptr_ops_gc = { .bpop_translate = NULL, }; +static struct lock_class_key nilfs_bmap_dat_lock_key; + /** * nilfs_bmap_read - read a bmap from an inode * @bmap: bmap @@ -715,6 +717,7 @@ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode) bmap->b_pops = &nilfs_bmap_ptr_ops_p; bmap->b_last_allocated_key = 0; /* XXX: use macro */ bmap->b_last_allocated_ptr = NILFS_BMAP_NEW_PTR_INIT; + lockdep_set_class(&bmap->b_sem, &nilfs_bmap_dat_lock_key); break; case NILFS_CPFILE_INO: case NILFS_SUFILE_INO: @@ -772,6 +775,7 @@ void nilfs_bmap_init_gcdat(struct nilfs_bmap *gcbmap, struct nilfs_bmap *bmap) { memcpy(gcbmap, bmap, sizeof(union nilfs_bmap_union)); init_rwsem(&gcbmap->b_sem); + lockdep_set_class(&bmap->b_sem, &nilfs_bmap_dat_lock_key); gcbmap->b_inode = &NILFS_BMAP_I(gcbmap)->vfs_inode; } @@ -779,5 +783,6 @@ void nilfs_bmap_commit_gcdat(struct nilfs_bmap *gcbmap, struct nilfs_bmap *bmap) { memcpy(bmap, gcbmap, sizeof(union nilfs_bmap_union)); init_rwsem(&bmap->b_sem); + lockdep_set_class(&bmap->b_sem, &nilfs_bmap_dat_lock_key); bmap->b_inode = &NILFS_BMAP_I(bmap)->vfs_inode; } diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 7558c977db0..3d0c18a16db 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -35,11 +35,6 @@ #include "bmap_union.h" /* - * NILFS filesystem version - */ -#define NILFS_VERSION "2.0.5" - -/* * nilfs inode data in memory */ struct nilfs_inode_info { diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 6ade0963fc1..4fc081e47d7 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -413,7 +413,6 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, struct nilfs_segment_entry *ent, *n; struct inode *sufile = nilfs->ns_sufile; __u64 segnum[4]; - time_t mtime; int err; int i; @@ -442,24 +441,13 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, * Collecting segments written after the latest super root. * These are marked dirty to avoid being reallocated in the next write. */ - mtime = get_seconds(); list_for_each_entry_safe(ent, n, head, list) { - if (ent->segnum == segnum[0]) { - list_del(&ent->list); - nilfs_free_segment_entry(ent); - continue; - } - err = nilfs_open_segment_entry(ent, sufile); - if (unlikely(err)) - goto failed; - if (!nilfs_segment_usage_dirty(ent->raw_su)) { - /* make the segment garbage */ - ent->raw_su->su_nblocks = cpu_to_le32(0); - ent->raw_su->su_lastmod = cpu_to_le32(mtime); - nilfs_segment_usage_set_dirty(ent->raw_su); + if (ent->segnum != segnum[0]) { + err = nilfs_sufile_scrap(sufile, ent->segnum); + if (unlikely(err)) + goto failed; } list_del(&ent->list); - nilfs_close_segment_entry(ent, sufile); nilfs_free_segment_entry(ent); } diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index c774cf397e2..98e68677f04 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -93,6 +93,52 @@ nilfs_sufile_get_segment_usage_block(struct inode *sufile, __u64 segnum, create, NULL, bhp); } +static void nilfs_sufile_mod_counter(struct buffer_head *header_bh, + u64 ncleanadd, u64 ndirtyadd) +{ + struct nilfs_sufile_header *header; + void *kaddr; + + kaddr = kmap_atomic(header_bh->b_page, KM_USER0); + header = kaddr + bh_offset(header_bh); + le64_add_cpu(&header->sh_ncleansegs, ncleanadd); + le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd); + kunmap_atomic(kaddr, KM_USER0); + + nilfs_mdt_mark_buffer_dirty(header_bh); +} + +int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create, + void (*dofunc)(struct inode *, __u64, + struct buffer_head *, + struct buffer_head *)) +{ + struct buffer_head *header_bh, *bh; + int ret; + + if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) { + printk(KERN_WARNING "%s: invalid segment number: %llu\n", + __func__, (unsigned long long)segnum); + return -EINVAL; + } + down_write(&NILFS_MDT(sufile)->mi_sem); + + ret = nilfs_sufile_get_header_block(sufile, &header_bh); + if (ret < 0) + goto out_sem; + + ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, create, &bh); + if (!ret) { + dofunc(sufile, segnum, header_bh, bh); + brelse(bh); + } + brelse(header_bh); + + out_sem: + up_write(&NILFS_MDT(sufile)->mi_sem); + return ret; +} + /** * nilfs_sufile_alloc - allocate a segment * @sufile: inode of segment usage file @@ -113,7 +159,6 @@ nilfs_sufile_get_segment_usage_block(struct inode *sufile, __u64 segnum, int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) { struct buffer_head *header_bh, *su_bh; - struct the_nilfs *nilfs; struct nilfs_sufile_header *header; struct nilfs_segment_usage *su; size_t susz = NILFS_MDT(sufile)->mi_entry_size; @@ -124,8 +169,6 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) down_write(&NILFS_MDT(sufile)->mi_sem); - nilfs = NILFS_MDT(sufile)->mi_nilfs; - ret = nilfs_sufile_get_header_block(sufile, &header_bh); if (ret < 0) goto out_sem; @@ -192,165 +235,84 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) return ret; } -/** - * nilfs_sufile_cancel_free - - * @sufile: inode of segment usage file - * @segnum: segment number - * - * Description: - * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - */ -int nilfs_sufile_cancel_free(struct inode *sufile, __u64 segnum) +void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum, + struct buffer_head *header_bh, + struct buffer_head *su_bh) { - struct buffer_head *header_bh, *su_bh; - struct the_nilfs *nilfs; - struct nilfs_sufile_header *header; struct nilfs_segment_usage *su; void *kaddr; - int ret; - - down_write(&NILFS_MDT(sufile)->mi_sem); - - nilfs = NILFS_MDT(sufile)->mi_nilfs; - - ret = nilfs_sufile_get_header_block(sufile, &header_bh); - if (ret < 0) - goto out_sem; - - ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &su_bh); - if (ret < 0) - goto out_header; kaddr = kmap_atomic(su_bh->b_page, KM_USER0); - su = nilfs_sufile_block_get_segment_usage( - sufile, segnum, su_bh, kaddr); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); if (unlikely(!nilfs_segment_usage_clean(su))) { printk(KERN_WARNING "%s: segment %llu must be clean\n", __func__, (unsigned long long)segnum); kunmap_atomic(kaddr, KM_USER0); - goto out_su_bh; + return; } nilfs_segment_usage_set_dirty(su); kunmap_atomic(kaddr, KM_USER0); - kaddr = kmap_atomic(header_bh->b_page, KM_USER0); - header = nilfs_sufile_block_get_header(sufile, header_bh, kaddr); - le64_add_cpu(&header->sh_ncleansegs, -1); - le64_add_cpu(&header->sh_ndirtysegs, 1); - kunmap_atomic(kaddr, KM_USER0); - - nilfs_mdt_mark_buffer_dirty(header_bh); + nilfs_sufile_mod_counter(header_bh, -1, 1); nilfs_mdt_mark_buffer_dirty(su_bh); nilfs_mdt_mark_dirty(sufile); - - out_su_bh: - brelse(su_bh); - out_header: - brelse(header_bh); - out_sem: - up_write(&NILFS_MDT(sufile)->mi_sem); - return ret; } -/** - * nilfs_sufile_freev - free segments - * @sufile: inode of segment usage file - * @segnum: array of segment numbers - * @nsegs: number of segments - * - * Description: nilfs_sufile_freev() frees segments specified by @segnum and - * @nsegs, which must have been returned by a previous call to - * nilfs_sufile_alloc(). - * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - */ -#define NILFS_SUFILE_FREEV_PREALLOC 16 -int nilfs_sufile_freev(struct inode *sufile, __u64 *segnum, size_t nsegs) +void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum, + struct buffer_head *header_bh, + struct buffer_head *su_bh) { - struct buffer_head *header_bh, **su_bh, - *su_bh_prealloc[NILFS_SUFILE_FREEV_PREALLOC]; - struct the_nilfs *nilfs; - struct nilfs_sufile_header *header; struct nilfs_segment_usage *su; void *kaddr; - int ret, i; + int clean, dirty; - down_write(&NILFS_MDT(sufile)->mi_sem); - - nilfs = NILFS_MDT(sufile)->mi_nilfs; - - /* prepare resources */ - if (nsegs <= NILFS_SUFILE_FREEV_PREALLOC) - su_bh = su_bh_prealloc; - else { - su_bh = kmalloc(sizeof(*su_bh) * nsegs, GFP_NOFS); - if (su_bh == NULL) { - ret = -ENOMEM; - goto out_sem; - } - } - - ret = nilfs_sufile_get_header_block(sufile, &header_bh); - if (ret < 0) - goto out_su_bh; - for (i = 0; i < nsegs; i++) { - ret = nilfs_sufile_get_segment_usage_block(sufile, segnum[i], - 0, &su_bh[i]); - if (ret < 0) - goto out_bh; - } - - /* free segments */ - for (i = 0; i < nsegs; i++) { - kaddr = kmap_atomic(su_bh[i]->b_page, KM_USER0); - su = nilfs_sufile_block_get_segment_usage( - sufile, segnum[i], su_bh[i], kaddr); - WARN_ON(nilfs_segment_usage_error(su)); - nilfs_segment_usage_set_clean(su); + kaddr = kmap_atomic(su_bh->b_page, KM_USER0); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); + if (su->su_flags == cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY) && + su->su_nblocks == cpu_to_le32(0)) { kunmap_atomic(kaddr, KM_USER0); - nilfs_mdt_mark_buffer_dirty(su_bh[i]); + return; } - kaddr = kmap_atomic(header_bh->b_page, KM_USER0); - header = nilfs_sufile_block_get_header(sufile, header_bh, kaddr); - le64_add_cpu(&header->sh_ncleansegs, nsegs); - le64_add_cpu(&header->sh_ndirtysegs, -(u64)nsegs); + clean = nilfs_segment_usage_clean(su); + dirty = nilfs_segment_usage_dirty(su); + + /* make the segment garbage */ + su->su_lastmod = cpu_to_le64(0); + su->su_nblocks = cpu_to_le32(0); + su->su_flags = cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY); kunmap_atomic(kaddr, KM_USER0); - nilfs_mdt_mark_buffer_dirty(header_bh); + + nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1); + nilfs_mdt_mark_buffer_dirty(su_bh); nilfs_mdt_mark_dirty(sufile); +} - out_bh: - for (i--; i >= 0; i--) - brelse(su_bh[i]); - brelse(header_bh); +void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, + struct buffer_head *header_bh, + struct buffer_head *su_bh) +{ + struct nilfs_segment_usage *su; + void *kaddr; + int sudirty; - out_su_bh: - if (su_bh != su_bh_prealloc) - kfree(su_bh); + kaddr = kmap_atomic(su_bh->b_page, KM_USER0); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); + if (nilfs_segment_usage_clean(su)) { + printk(KERN_WARNING "%s: segment %llu is already clean\n", + __func__, (unsigned long long)segnum); + kunmap_atomic(kaddr, KM_USER0); + return; + } + WARN_ON(nilfs_segment_usage_error(su)); + WARN_ON(!nilfs_segment_usage_dirty(su)); - out_sem: - up_write(&NILFS_MDT(sufile)->mi_sem); - return ret; -} + sudirty = nilfs_segment_usage_dirty(su); + nilfs_segment_usage_set_clean(su); + kunmap_atomic(kaddr, KM_USER0); + nilfs_mdt_mark_buffer_dirty(su_bh); -/** - * nilfs_sufile_free - - * @sufile: - * @segnum: - */ -int nilfs_sufile_free(struct inode *sufile, __u64 segnum) -{ - return nilfs_sufile_freev(sufile, &segnum, 1); + nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0); + nilfs_mdt_mark_dirty(sufile); } /** @@ -500,72 +462,28 @@ int nilfs_sufile_get_ncleansegs(struct inode *sufile, unsigned long *nsegsp) return ret; } -/** - * nilfs_sufile_set_error - mark a segment as erroneous - * @sufile: inode of segment usage file - * @segnum: segment number - * - * Description: nilfs_sufile_set_error() marks the segment specified by - * @segnum as erroneous. The error segment will never be used again. - * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - Invalid segment usage number. - */ -int nilfs_sufile_set_error(struct inode *sufile, __u64 segnum) +void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum, + struct buffer_head *header_bh, + struct buffer_head *su_bh) { - struct buffer_head *header_bh, *su_bh; struct nilfs_segment_usage *su; - struct nilfs_sufile_header *header; void *kaddr; - int ret; - - if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) { - printk(KERN_WARNING "%s: invalid segment number: %llu\n", - __func__, (unsigned long long)segnum); - return -EINVAL; - } - down_write(&NILFS_MDT(sufile)->mi_sem); - - ret = nilfs_sufile_get_header_block(sufile, &header_bh); - if (ret < 0) - goto out_sem; - ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &su_bh); - if (ret < 0) - goto out_header; + int suclean; kaddr = kmap_atomic(su_bh->b_page, KM_USER0); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr); if (nilfs_segment_usage_error(su)) { kunmap_atomic(kaddr, KM_USER0); - brelse(su_bh); - goto out_header; + return; } - + suclean = nilfs_segment_usage_clean(su); nilfs_segment_usage_set_error(su); kunmap_atomic(kaddr, KM_USER0); - brelse(su_bh); - kaddr = kmap_atomic(header_bh->b_page, KM_USER0); - header = nilfs_sufile_block_get_header(sufile, header_bh, kaddr); - le64_add_cpu(&header->sh_ndirtysegs, -1); - kunmap_atomic(kaddr, KM_USER0); - nilfs_mdt_mark_buffer_dirty(header_bh); + if (suclean) + nilfs_sufile_mod_counter(header_bh, -1, 0); nilfs_mdt_mark_buffer_dirty(su_bh); nilfs_mdt_mark_dirty(sufile); - brelse(su_bh); - - out_header: - brelse(header_bh); - - out_sem: - up_write(&NILFS_MDT(sufile)->mi_sem); - return ret; } /** @@ -625,7 +543,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, si[i + j].sui_nblocks = le32_to_cpu(su->su_nblocks); si[i + j].sui_flags = le32_to_cpu(su->su_flags) & ~(1UL << NILFS_SEGMENT_USAGE_ACTIVE); - if (nilfs_segment_is_active(nilfs, segnum + i + j)) + if (nilfs_segment_is_active(nilfs, segnum + j)) si[i + j].sui_flags |= (1UL << NILFS_SEGMENT_USAGE_ACTIVE); } diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index d595f33a768..a2e2efd4ade 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -36,9 +36,6 @@ static inline unsigned long nilfs_sufile_get_nsegments(struct inode *sufile) } int nilfs_sufile_alloc(struct inode *, __u64 *); -int nilfs_sufile_cancel_free(struct inode *, __u64); -int nilfs_sufile_freev(struct inode *, __u64 *, size_t); -int nilfs_sufile_free(struct inode *, __u64); int nilfs_sufile_get_segment_usage(struct inode *, __u64, struct nilfs_segment_usage **, struct buffer_head **); @@ -46,9 +43,83 @@ void nilfs_sufile_put_segment_usage(struct inode *, __u64, struct buffer_head *); int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *); int nilfs_sufile_get_ncleansegs(struct inode *, unsigned long *); -int nilfs_sufile_set_error(struct inode *, __u64); ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, struct nilfs_suinfo *, size_t); +int nilfs_sufile_update(struct inode *, __u64, int, + void (*dofunc)(struct inode *, __u64, + struct buffer_head *, + struct buffer_head *)); +void nilfs_sufile_do_cancel_free(struct inode *, __u64, struct buffer_head *, + struct buffer_head *); +void nilfs_sufile_do_scrap(struct inode *, __u64, struct buffer_head *, + struct buffer_head *); +void nilfs_sufile_do_free(struct inode *, __u64, struct buffer_head *, + struct buffer_head *); +void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *, + struct buffer_head *); + +/** + * nilfs_sufile_cancel_free - + * @sufile: inode of segment usage file + * @segnum: segment number + * + * Description: + * + * Return Value: On success, 0 is returned. On error, one of the following + * negative error codes is returned. + * + * %-EIO - I/O error. + * + * %-ENOMEM - Insufficient amount of memory available. + */ +static inline int nilfs_sufile_cancel_free(struct inode *sufile, __u64 segnum) +{ + return nilfs_sufile_update(sufile, segnum, 0, + nilfs_sufile_do_cancel_free); +} + +/** + * nilfs_sufile_scrap - make a segment garbage + * @sufile: inode of segment usage file + * @segnum: segment number to be freed + */ +static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum) +{ + return nilfs_sufile_update(sufile, segnum, 1, nilfs_sufile_do_scrap); +} + +/** + * nilfs_sufile_free - free segment + * @sufile: inode of segment usage file + * @segnum: segment number to be freed + */ +static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum) +{ + return nilfs_sufile_update(sufile, segnum, 0, nilfs_sufile_do_free); +} + +/** + * nilfs_sufile_set_error - mark a segment as erroneous + * @sufile: inode of segment usage file + * @segnum: segment number + * + * Description: nilfs_sufile_set_error() marks the segment specified by + * @segnum as erroneous. The error segment will never be used again. + * + * Return Value: On success, 0 is returned. On error, one of the following + * negative error codes is returned. + * + * %-EIO - I/O error. + * + * %-ENOMEM - Insufficient amount of memory available. + * + * %-EINVAL - Invalid segment usage number. + */ +static inline int nilfs_sufile_set_error(struct inode *sufile, __u64 segnum) +{ + return nilfs_sufile_update(sufile, segnum, 0, + nilfs_sufile_do_set_error); +} #endif /* _NILFS_SUFILE_H */ diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index e117e1ea9bf..6989b03e97a 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -63,7 +63,6 @@ MODULE_AUTHOR("NTT Corp."); MODULE_DESCRIPTION("A New Implementation of the Log-structured Filesystem " "(NILFS)"); -MODULE_VERSION(NILFS_VERSION); MODULE_LICENSE("GPL"); static int nilfs_remount(struct super_block *sb, int *flags, char *data); @@ -476,11 +475,12 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct nilfs_sb_info *sbi = NILFS_SB(sb); + struct the_nilfs *nilfs = sbi->s_nilfs; + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); unsigned long long blocks; unsigned long overhead; unsigned long nrsvblocks; sector_t nfreeblocks; - struct the_nilfs *nilfs = sbi->s_nilfs; int err; /* @@ -514,6 +514,9 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_files = atomic_read(&sbi->s_inodes_count); buf->f_ffree = 0; /* nilfs_count_free_inodes(sb); */ buf->f_namelen = NILFS_NAME_LEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + return 0; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 33400cf0bbe..7f65b3be4aa 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -115,6 +115,7 @@ void put_nilfs(struct the_nilfs *nilfs) static int nilfs_load_super_root(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, sector_t sr_block) { + static struct lock_class_key dat_lock_key; struct buffer_head *bh_sr; struct nilfs_super_root *raw_sr; struct nilfs_super_block **sbp = nilfs->ns_sbp; @@ -163,6 +164,9 @@ static int nilfs_load_super_root(struct the_nilfs *nilfs, if (unlikely(err)) goto failed_sufile; + lockdep_set_class(&NILFS_MDT(nilfs->ns_dat)->mi_sem, &dat_lock_key); + lockdep_set_class(&NILFS_MDT(nilfs->ns_gc_dat)->mi_sem, &dat_lock_key); + nilfs_mdt_set_shadow(nilfs->ns_dat, nilfs->ns_gc_dat); nilfs_mdt_set_entry_size(nilfs->ns_cpfile, checkpoint_size, sizeof(struct nilfs_cpfile_header)); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8672b953603..c2a87c885b7 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1912,6 +1912,22 @@ out_sems: return written ? written : ret; } +static int ocfs2_splice_to_file(struct pipe_inode_info *pipe, + struct file *out, + struct splice_desc *sd) +{ + int ret; + + ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, &sd->pos, + sd->total_len, 0, NULL); + if (ret < 0) { + mlog_errno(ret); + return ret; + } + + return splice_from_pipe_feed(pipe, sd, pipe_to_file); +} + static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, @@ -1919,38 +1935,76 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, unsigned int flags) { int ret; - struct inode *inode = out->f_path.dentry->d_inode; + struct address_space *mapping = out->f_mapping; + struct inode *inode = mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", out, pipe, (unsigned int)len, out->f_path.dentry->d_name.len, out->f_path.dentry->d_name.name); - mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + if (pipe->inode) + mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_PARENT); - ret = ocfs2_rw_lock(inode, 1); - if (ret < 0) { - mlog_errno(ret); - goto out; - } + splice_from_pipe_begin(&sd); + do { + ret = splice_from_pipe_next(pipe, &sd); + if (ret <= 0) + break; - ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, ppos, len, 0, - NULL); - if (ret < 0) { - mlog_errno(ret); - goto out_unlock; - } + mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); + ret = ocfs2_rw_lock(inode, 1); + if (ret < 0) + mlog_errno(ret); + else { + ret = ocfs2_splice_to_file(pipe, out, &sd); + ocfs2_rw_unlock(inode, 1); + } + mutex_unlock(&inode->i_mutex); + } while (ret > 0); + splice_from_pipe_end(pipe, &sd); if (pipe->inode) - mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD); - ret = generic_file_splice_write_nolock(pipe, out, ppos, len, flags); - if (pipe->inode) mutex_unlock(&pipe->inode->i_mutex); -out_unlock: - ocfs2_rw_unlock(inode, 1); -out: - mutex_unlock(&inode->i_mutex); + if (sd.num_spliced) + ret = sd.num_spliced; + + if (ret > 0) { + unsigned long nr_pages; + + *ppos += ret; + nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + /* + * If file or inode is SYNC and we actually wrote some data, + * sync it. + */ + if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) { + int err; + + mutex_lock(&inode->i_mutex); + err = ocfs2_rw_lock(inode, 1); + if (err < 0) { + mlog_errno(err); + } else { + err = generic_osync_inode(inode, mapping, + OSYNC_METADATA|OSYNC_DATA); + ocfs2_rw_unlock(inode, 1); + } + mutex_unlock(&inode->i_mutex); + + if (err) + ret = err; + } + balance_dirty_pages_ratelimited_nr(mapping, nr_pages); + } mlog_exit(ret); return ret; diff --git a/fs/pipe.c b/fs/pipe.c index 4af7aa52181..13414ec45b8 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -37,6 +37,42 @@ * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ +static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass) +{ + if (pipe->inode) + mutex_lock_nested(&pipe->inode->i_mutex, subclass); +} + +void pipe_lock(struct pipe_inode_info *pipe) +{ + /* + * pipe_lock() nests non-pipe inode locks (for writing to a file) + */ + pipe_lock_nested(pipe, I_MUTEX_PARENT); +} +EXPORT_SYMBOL(pipe_lock); + +void pipe_unlock(struct pipe_inode_info *pipe) +{ + if (pipe->inode) + mutex_unlock(&pipe->inode->i_mutex); +} +EXPORT_SYMBOL(pipe_unlock); + +void pipe_double_lock(struct pipe_inode_info *pipe1, + struct pipe_inode_info *pipe2) +{ + BUG_ON(pipe1 == pipe2); + + if (pipe1 < pipe2) { + pipe_lock_nested(pipe1, I_MUTEX_PARENT); + pipe_lock_nested(pipe2, I_MUTEX_CHILD); + } else { + pipe_lock_nested(pipe2, I_MUTEX_CHILD); + pipe_lock_nested(pipe1, I_MUTEX_PARENT); + } +} + /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe) { @@ -47,12 +83,10 @@ void pipe_wait(struct pipe_inode_info *pipe) * is considered a noninteractive wait: */ prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); schedule(); finish_wait(&pipe->wait, &wait); - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); } static int diff --git a/fs/splice.c b/fs/splice.c index c18aa7e03e2..5384a90665d 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -182,8 +182,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, do_wakeup = 0; page_nr = 0; - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); for (;;) { if (!pipe->readers) { @@ -245,15 +244,13 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, pipe->waiting_writers--; } - if (pipe->inode) { - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); - if (do_wakeup) { - smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible(&pipe->wait); - kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); - } + if (do_wakeup) { + smp_mb(); + if (waitqueue_active(&pipe->wait)) + wake_up_interruptible(&pipe->wait); + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } while (page_nr < spd_pages) @@ -555,8 +552,8 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create * a new page in the output file page cache and fill/dirty that. */ -static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, - struct splice_desc *sd) +int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) { struct file *file = sd->u.file; struct address_space *mapping = file->f_mapping; @@ -600,108 +597,178 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, out: return ret; } +EXPORT_SYMBOL(pipe_to_file); + +static void wakeup_pipe_writers(struct pipe_inode_info *pipe) +{ + smp_mb(); + if (waitqueue_active(&pipe->wait)) + wake_up_interruptible(&pipe->wait); + kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); +} /** - * __splice_from_pipe - splice data from a pipe to given actor + * splice_from_pipe_feed - feed available data from a pipe to a file * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: - * This function does little more than loop over the pipe and call - * @actor to do the actual moving of a single struct pipe_buffer to - * the desired destination. See pipe_to_file, pipe_to_sendpage, or - * pipe_to_user. + + * This function loops over the pipe and calls @actor to do the + * actual moving of a single struct pipe_buffer to the desired + * destination. It returns when there's no more buffers left in + * the pipe or if the requested number of bytes (@sd->total_len) + * have been copied. It returns a positive number (one) if the + * pipe needs to be filled with more data, zero if the required + * number of bytes have been copied and -errno on error. * + * This, together with splice_from_pipe_{begin,end,next}, may be + * used to implement the functionality of __splice_from_pipe() when + * locking is required around copying the pipe buffers to the + * destination. */ -ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, - splice_actor *actor) +int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, + splice_actor *actor) { - int ret, do_wakeup, err; - - ret = 0; - do_wakeup = 0; - - for (;;) { - if (pipe->nrbufs) { - struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; - const struct pipe_buf_operations *ops = buf->ops; + int ret; - sd->len = buf->len; - if (sd->len > sd->total_len) - sd->len = sd->total_len; + while (pipe->nrbufs) { + struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; + const struct pipe_buf_operations *ops = buf->ops; - err = actor(pipe, buf, sd); - if (err <= 0) { - if (!ret && err != -ENODATA) - ret = err; + sd->len = buf->len; + if (sd->len > sd->total_len) + sd->len = sd->total_len; - break; - } + ret = actor(pipe, buf, sd); + if (ret <= 0) { + if (ret == -ENODATA) + ret = 0; + return ret; + } + buf->offset += ret; + buf->len -= ret; - ret += err; - buf->offset += err; - buf->len -= err; + sd->num_spliced += ret; + sd->len -= ret; + sd->pos += ret; + sd->total_len -= ret; - sd->len -= err; - sd->pos += err; - sd->total_len -= err; - if (sd->len) - continue; + if (!buf->len) { + buf->ops = NULL; + ops->release(pipe, buf); + pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1); + pipe->nrbufs--; + if (pipe->inode) + sd->need_wakeup = true; + } - if (!buf->len) { - buf->ops = NULL; - ops->release(pipe, buf); - pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1); - pipe->nrbufs--; - if (pipe->inode) - do_wakeup = 1; - } + if (!sd->total_len) + return 0; + } - if (!sd->total_len) - break; - } + return 1; +} +EXPORT_SYMBOL(splice_from_pipe_feed); - if (pipe->nrbufs) - continue; +/** + * splice_from_pipe_next - wait for some data to splice from + * @pipe: pipe to splice from + * @sd: information about the splice operation + * + * Description: + * This function will wait for some data and return a positive + * value (one) if pipe buffers are available. It will return zero + * or -errno if no more data needs to be spliced. + */ +int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) +{ + while (!pipe->nrbufs) { if (!pipe->writers) - break; - if (!pipe->waiting_writers) { - if (ret) - break; - } + return 0; - if (sd->flags & SPLICE_F_NONBLOCK) { - if (!ret) - ret = -EAGAIN; - break; - } + if (!pipe->waiting_writers && sd->num_spliced) + return 0; - if (signal_pending(current)) { - if (!ret) - ret = -ERESTARTSYS; - break; - } + if (sd->flags & SPLICE_F_NONBLOCK) + return -EAGAIN; - if (do_wakeup) { - smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible_sync(&pipe->wait); - kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); - do_wakeup = 0; + if (signal_pending(current)) + return -ERESTARTSYS; + + if (sd->need_wakeup) { + wakeup_pipe_writers(pipe); + sd->need_wakeup = false; } pipe_wait(pipe); } - if (do_wakeup) { - smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible(&pipe->wait); - kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); - } + return 1; +} +EXPORT_SYMBOL(splice_from_pipe_next); - return ret; +/** + * splice_from_pipe_begin - start splicing from pipe + * @pipe: pipe to splice from + * + * Description: + * This function should be called before a loop containing + * splice_from_pipe_next() and splice_from_pipe_feed() to + * initialize the necessary fields of @sd. + */ +void splice_from_pipe_begin(struct splice_desc *sd) +{ + sd->num_spliced = 0; + sd->need_wakeup = false; +} +EXPORT_SYMBOL(splice_from_pipe_begin); + +/** + * splice_from_pipe_end - finish splicing from pipe + * @pipe: pipe to splice from + * @sd: information about the splice operation + * + * Description: + * This function will wake up pipe writers if necessary. It should + * be called after a loop containing splice_from_pipe_next() and + * splice_from_pipe_feed(). + */ +void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) +{ + if (sd->need_wakeup) + wakeup_pipe_writers(pipe); +} +EXPORT_SYMBOL(splice_from_pipe_end); + +/** + * __splice_from_pipe - splice data from a pipe to given actor + * @pipe: pipe to splice from + * @sd: information to @actor + * @actor: handler that splices the data + * + * Description: + * This function does little more than loop over the pipe and call + * @actor to do the actual moving of a single struct pipe_buffer to + * the desired destination. See pipe_to_file, pipe_to_sendpage, or + * pipe_to_user. + * + */ +ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, + splice_actor *actor) +{ + int ret; + + splice_from_pipe_begin(sd); + do { + ret = splice_from_pipe_next(pipe, sd); + if (ret > 0) + ret = splice_from_pipe_feed(pipe, sd, actor); + } while (ret > 0); + splice_from_pipe_end(pipe, sd); + + return sd->num_spliced ? sd->num_spliced : ret; } EXPORT_SYMBOL(__splice_from_pipe); @@ -715,7 +782,7 @@ EXPORT_SYMBOL(__splice_from_pipe); * @actor: handler that splices the data * * Description: - * See __splice_from_pipe. This function locks the input and output inodes, + * See __splice_from_pipe. This function locks the pipe inode, * otherwise it's identical to __splice_from_pipe(). * */ @@ -724,7 +791,6 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, splice_actor *actor) { ssize_t ret; - struct inode *inode = out->f_mapping->host; struct splice_desc sd = { .total_len = len, .flags = flags, @@ -732,30 +798,15 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, .u.file = out, }; - /* - * The actor worker might be calling ->write_begin and - * ->write_end. Most of the time, these expect i_mutex to - * be held. Since this may result in an ABBA deadlock with - * pipe->inode, we have to order lock acquiry here. - * - * Outer lock must be inode->i_mutex, as pipe_wait() will - * release and reacquire pipe->inode->i_mutex, AND inode must - * never be a pipe. - */ - WARN_ON(S_ISFIFO(inode->i_mode)); - mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); - if (pipe->inode) - mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD); + pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, actor); - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); - mutex_unlock(&inode->i_mutex); + pipe_unlock(pipe); return ret; } /** - * generic_file_splice_write_nolock - generic_file_splice_write without mutexes + * generic_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to * @ppos: position in @out @@ -764,13 +815,12 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, * * Description: * Will either move or copy pages (determined by @flags options) from - * the given pipe inode to the given file. The caller is responsible - * for acquiring i_mutex on both inodes. + * the given pipe inode to the given file. * */ ssize_t -generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; @@ -781,76 +831,28 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, .u.file = out, }; ssize_t ret; - int err; - - err = file_remove_suid(out); - if (unlikely(err)) - return err; - - ret = __splice_from_pipe(pipe, &sd, pipe_to_file); - if (ret > 0) { - unsigned long nr_pages; - *ppos += ret; - nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + pipe_lock(pipe); - /* - * If file or inode is SYNC and we actually wrote some data, - * sync it. - */ - if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) { - err = generic_osync_inode(inode, mapping, - OSYNC_METADATA|OSYNC_DATA); - - if (err) - ret = err; - } - balance_dirty_pages_ratelimited_nr(mapping, nr_pages); - } + splice_from_pipe_begin(&sd); + do { + ret = splice_from_pipe_next(pipe, &sd); + if (ret <= 0) + break; - return ret; -} + mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); + ret = file_remove_suid(out); + if (!ret) + ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file); + mutex_unlock(&inode->i_mutex); + } while (ret > 0); + splice_from_pipe_end(pipe, &sd); -EXPORT_SYMBOL(generic_file_splice_write_nolock); + pipe_unlock(pipe); -/** - * generic_file_splice_write - splice data from a pipe to a file - * @pipe: pipe info - * @out: file to write to - * @ppos: position in @out - * @len: number of bytes to splice - * @flags: splice modifier flags - * - * Description: - * Will either move or copy pages (determined by @flags options) from - * the given pipe inode to the given file. - * - */ -ssize_t -generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) -{ - struct address_space *mapping = out->f_mapping; - struct inode *inode = mapping->host; - struct splice_desc sd = { - .total_len = len, - .flags = flags, - .pos = *ppos, - .u.file = out, - }; - ssize_t ret; + if (sd.num_spliced) + ret = sd.num_spliced; - WARN_ON(S_ISFIFO(inode->i_mode)); - mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); - ret = file_remove_suid(out); - if (likely(!ret)) { - if (pipe->inode) - mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD); - ret = __splice_from_pipe(pipe, &sd, pipe_to_file); - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); - } - mutex_unlock(&inode->i_mutex); if (ret > 0) { unsigned long nr_pages; @@ -1339,8 +1341,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *iov, if (!pipe) return -EBADF; - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); error = ret = 0; while (nr_segs) { @@ -1395,8 +1396,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *iov, iov++; } - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); if (!ret) ret = error; @@ -1524,7 +1524,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) return 0; ret = 0; - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); while (!pipe->nrbufs) { if (signal_pending(current)) { @@ -1542,7 +1542,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) pipe_wait(pipe); } - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); return ret; } @@ -1562,7 +1562,7 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) return 0; ret = 0; - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); while (pipe->nrbufs >= PIPE_BUFFERS) { if (!pipe->readers) { @@ -1583,7 +1583,7 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) pipe->waiting_writers--; } - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); return ret; } @@ -1599,10 +1599,10 @@ static int link_pipe(struct pipe_inode_info *ipipe, /* * Potential ABBA deadlock, work around it by ordering lock - * grabbing by inode address. Otherwise two different processes + * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ - inode_double_lock(ipipe->inode, opipe->inode); + pipe_double_lock(ipipe, opipe); do { if (!opipe->readers) { @@ -1653,7 +1653,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK)) ret = -EAGAIN; - inode_double_unlock(ipipe->inode, opipe->inode); + pipe_unlock(ipipe); + pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index c13f67300fe..7ec89fc05b2 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -153,23 +153,6 @@ xfs_find_bdev_for_inode( } /* - * Schedule IO completion handling on a xfsdatad if this was - * the final hold on this ioend. If we are asked to wait, - * flush the workqueue. - */ -STATIC void -xfs_finish_ioend( - xfs_ioend_t *ioend, - int wait) -{ - if (atomic_dec_and_test(&ioend->io_remaining)) { - queue_work(xfsdatad_workqueue, &ioend->io_work); - if (wait) - flush_workqueue(xfsdatad_workqueue); - } -} - -/* * We're now finished for good with this ioend structure. * Update the page state via the associated buffer_heads, * release holds on the inode and bio, and finally free @@ -310,6 +293,27 @@ xfs_end_bio_read( } /* + * Schedule IO completion handling on a xfsdatad if this was + * the final hold on this ioend. If we are asked to wait, + * flush the workqueue. + */ +STATIC void +xfs_finish_ioend( + xfs_ioend_t *ioend, + int wait) +{ + if (atomic_dec_and_test(&ioend->io_remaining)) { + struct workqueue_struct *wq = xfsdatad_workqueue; + if (ioend->io_work.func == xfs_end_bio_unwritten) + wq = xfsconvertd_workqueue; + + queue_work(wq, &ioend->io_work); + if (wait) + flush_workqueue(wq); + } +} + +/* * Allocate and initialise an IO completion structure. * We need to track unwritten extent write completion here initially. * We'll need to extend this for updating the ondisk inode size later diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h index 1dd52884975..221b3e66cee 100644 --- a/fs/xfs/linux-2.6/xfs_aops.h +++ b/fs/xfs/linux-2.6/xfs_aops.h @@ -19,6 +19,7 @@ #define __XFS_AOPS_H__ extern struct workqueue_struct *xfsdatad_workqueue; +extern struct workqueue_struct *xfsconvertd_workqueue; extern mempool_t *xfs_ioend_pool; /* diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index aa1016bb913..e28800a9f2b 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -51,6 +51,7 @@ static struct shrinker xfs_buf_shake = { static struct workqueue_struct *xfslogd_workqueue; struct workqueue_struct *xfsdatad_workqueue; +struct workqueue_struct *xfsconvertd_workqueue; #ifdef XFS_BUF_TRACE void @@ -1775,6 +1776,7 @@ xfs_flush_buftarg( xfs_buf_t *bp, *n; int pincount = 0; + xfs_buf_runall_queues(xfsconvertd_workqueue); xfs_buf_runall_queues(xfsdatad_workqueue); xfs_buf_runall_queues(xfslogd_workqueue); @@ -1831,9 +1833,15 @@ xfs_buf_init(void) if (!xfsdatad_workqueue) goto out_destroy_xfslogd_workqueue; + xfsconvertd_workqueue = create_workqueue("xfsconvertd"); + if (!xfsconvertd_workqueue) + goto out_destroy_xfsdatad_workqueue; + register_shrinker(&xfs_buf_shake); return 0; + out_destroy_xfsdatad_workqueue: + destroy_workqueue(xfsdatad_workqueue); out_destroy_xfslogd_workqueue: destroy_workqueue(xfslogd_workqueue); out_free_buf_zone: @@ -1849,6 +1857,7 @@ void xfs_buf_terminate(void) { unregister_shrinker(&xfs_buf_shake); + destroy_workqueue(xfsconvertd_workqueue); destroy_workqueue(xfsdatad_workqueue); destroy_workqueue(xfslogd_workqueue); kmem_zone_destroy(xfs_buf_zone); diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c index 5aeb7777696..08be36d7326 100644 --- a/fs/xfs/linux-2.6/xfs_fs_subr.c +++ b/fs/xfs/linux-2.6/xfs_fs_subr.c @@ -74,14 +74,14 @@ xfs_flush_pages( if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { xfs_iflags_clear(ip, XFS_ITRUNCATED); - ret = filemap_fdatawrite(mapping); - if (flags & XFS_B_ASYNC) - return -ret; - ret2 = filemap_fdatawait(mapping); - if (!ret) - ret = ret2; + ret = -filemap_fdatawrite(mapping); } - return -ret; + if (flags & XFS_B_ASYNC) + return ret; + ret2 = xfs_wait_on_pages(ip, first, last); + if (!ret) + ret = ret2; + return ret; } int diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 7e90daa0d1d..9142192ccbe 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -751,10 +751,26 @@ start: goto relock; } } else { + int enospc = 0; + ssize_t ret2 = 0; + +write_retry: xfs_rw_enter_trace(XFS_WRITE_ENTER, xip, (void *)iovp, segs, *offset, ioflags); - ret = generic_file_buffered_write(iocb, iovp, segs, + ret2 = generic_file_buffered_write(iocb, iovp, segs, pos, offset, count, ret); + /* + * if we just got an ENOSPC, flush the inode now we + * aren't holding any page locks and retry *once* + */ + if (ret2 == -ENOSPC && !enospc) { + error = xfs_flush_pages(xip, 0, -1, 0, FI_NONE); + if (error) + goto out_unlock_internal; + enospc = 1; + goto write_retry; + } + ret = ret2; } current->backing_dev_info = NULL; diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index a608e72fa40..f7ba76633c2 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -62,12 +62,6 @@ xfs_sync_inodes_ag( uint32_t first_index = 0; int error = 0; int last_error = 0; - int fflag = XFS_B_ASYNC; - - if (flags & SYNC_DELWRI) - fflag = XFS_B_DELWRI; - if (flags & SYNC_WAIT) - fflag = 0; /* synchronous overrides all */ do { struct inode *inode; @@ -128,11 +122,23 @@ xfs_sync_inodes_ag( * If we have to flush data or wait for I/O completion * we need to hold the iolock. */ - if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - lock_flags |= XFS_IOLOCK_SHARED; - error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE); - if (flags & SYNC_IOWAIT) + if (flags & SYNC_DELWRI) { + if (VN_DIRTY(inode)) { + if (flags & SYNC_TRYLOCK) { + if (xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) + lock_flags |= XFS_IOLOCK_SHARED; + } else { + xfs_ilock(ip, XFS_IOLOCK_SHARED); + lock_flags |= XFS_IOLOCK_SHARED; + } + if (lock_flags & XFS_IOLOCK_SHARED) { + error = xfs_flush_pages(ip, 0, -1, + (flags & SYNC_WAIT) ? 0 + : XFS_B_ASYNC, + FI_NONE); + } + } + if (VN_CACHED(inode) && (flags & SYNC_IOWAIT)) xfs_ioend_wait(ip); } xfs_ilock(ip, XFS_ILOCK_SHARED); @@ -398,15 +404,17 @@ STATIC void xfs_syncd_queue_work( struct xfs_mount *mp, void *data, - void (*syncer)(struct xfs_mount *, void *)) + void (*syncer)(struct xfs_mount *, void *), + struct completion *completion) { - struct bhv_vfs_sync_work *work; + struct xfs_sync_work *work; - work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP); + work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP); INIT_LIST_HEAD(&work->w_list); work->w_syncer = syncer; work->w_data = data; work->w_mount = mp; + work->w_completion = completion; spin_lock(&mp->m_sync_lock); list_add_tail(&work->w_list, &mp->m_sync_list); spin_unlock(&mp->m_sync_lock); @@ -420,49 +428,26 @@ xfs_syncd_queue_work( * heads, looking about for more room... */ STATIC void -xfs_flush_inode_work( - struct xfs_mount *mp, - void *arg) -{ - struct inode *inode = arg; - filemap_flush(inode->i_mapping); - iput(inode); -} - -void -xfs_flush_inode( - xfs_inode_t *ip) -{ - struct inode *inode = VFS_I(ip); - - igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work); - delay(msecs_to_jiffies(500)); -} - -/* - * This is the "bigger hammer" version of xfs_flush_inode_work... - * (IOW, "If at first you don't succeed, use a Bigger Hammer"). - */ -STATIC void -xfs_flush_device_work( +xfs_flush_inodes_work( struct xfs_mount *mp, void *arg) { struct inode *inode = arg; - sync_blockdev(mp->m_super->s_bdev); + xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK); + xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK | SYNC_IOWAIT); iput(inode); } void -xfs_flush_device( +xfs_flush_inodes( xfs_inode_t *ip) { struct inode *inode = VFS_I(ip); + DECLARE_COMPLETION_ONSTACK(completion); igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work); - delay(msecs_to_jiffies(500)); + xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion); + wait_for_completion(&completion); xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC); } @@ -497,7 +482,7 @@ xfssyncd( { struct xfs_mount *mp = arg; long timeleft; - bhv_vfs_sync_work_t *work, *n; + xfs_sync_work_t *work, *n; LIST_HEAD (tmp); set_freezable(); @@ -532,6 +517,8 @@ xfssyncd( list_del(&work->w_list); if (work == &mp->m_sync_work) continue; + if (work->w_completion) + complete(work->w_completion); kmem_free(work); } } @@ -545,6 +532,7 @@ xfs_syncd_init( { mp->m_sync_work.w_syncer = xfs_sync_worker; mp->m_sync_work.w_mount = mp; + mp->m_sync_work.w_completion = NULL; mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd"); if (IS_ERR(mp->m_sync_task)) return -PTR_ERR(mp->m_sync_task); diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index 04f058c848a..308d5bf6dfb 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -21,18 +21,20 @@ struct xfs_mount; struct xfs_perag; -typedef struct bhv_vfs_sync_work { +typedef struct xfs_sync_work { struct list_head w_list; struct xfs_mount *w_mount; void *w_data; /* syncer routine argument */ void (*w_syncer)(struct xfs_mount *, void *); -} bhv_vfs_sync_work_t; + struct completion *w_completion; +} xfs_sync_work_t; #define SYNC_ATTR 0x0001 /* sync attributes */ #define SYNC_DELWRI 0x0002 /* look at delayed writes */ #define SYNC_WAIT 0x0004 /* wait for i/o to complete */ #define SYNC_BDFLUSH 0x0008 /* BDFLUSH is calling -- don't block */ #define SYNC_IOWAIT 0x0010 /* wait for all I/O to complete */ +#define SYNC_TRYLOCK 0x0020 /* only try to lock inodes */ int xfs_syncd_init(struct xfs_mount *mp); void xfs_syncd_stop(struct xfs_mount *mp); @@ -43,8 +45,7 @@ int xfs_sync_fsdata(struct xfs_mount *mp, int flags); int xfs_quiesce_data(struct xfs_mount *mp); void xfs_quiesce_attr(struct xfs_mount *mp); -void xfs_flush_inode(struct xfs_inode *ip); -void xfs_flush_device(struct xfs_inode *ip); +void xfs_flush_inodes(struct xfs_inode *ip); int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode); int xfs_reclaim_inodes(struct xfs_mount *mp, int noblock, int mode); diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 478e587087f..89b81eedce6 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -69,15 +69,6 @@ xfs_inode_alloc( ASSERT(!spin_is_locked(&ip->i_flags_lock)); ASSERT(completion_done(&ip->i_flush)); - /* - * initialise the VFS inode here to get failures - * out of the way early. - */ - if (!inode_init_always(mp->m_super, VFS_I(ip))) { - kmem_zone_free(xfs_inode_zone, ip); - return NULL; - } - /* initialise the xfs inode */ ip->i_ino = ino; ip->i_mount = mp; @@ -113,6 +104,20 @@ xfs_inode_alloc( #ifdef XFS_DIR2_TRACE ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS); #endif + /* + * Now initialise the VFS inode. We do this after the xfs_inode + * initialisation as internal failures will result in ->destroy_inode + * being called and that will pass down through the reclaim path and + * free the XFS inode. This path requires the XFS inode to already be + * initialised. Hence if this call fails, the xfs_inode has already + * been freed and we should not reference it at all in the error + * handling. + */ + if (!inode_init_always(mp->m_super, VFS_I(ip))) + return NULL; + + /* prevent anyone from using this yet */ + VFS_I(ip)->i_state = I_NEW|I_LOCK; return ip; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 08ce72316bf..5aaa2d7ec15 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -338,38 +338,6 @@ xfs_iomap_eof_align_last_fsb( } STATIC int -xfs_flush_space( - xfs_inode_t *ip, - int *fsynced, - int *ioflags) -{ - switch (*fsynced) { - case 0: - if (ip->i_delayed_blks) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - xfs_flush_inode(ip); - xfs_ilock(ip, XFS_ILOCK_EXCL); - *fsynced = 1; - } else { - *ioflags |= BMAPI_SYNC; - *fsynced = 2; - } - return 0; - case 1: - *fsynced = 2; - *ioflags |= BMAPI_SYNC; - return 0; - case 2: - xfs_iunlock(ip, XFS_ILOCK_EXCL); - xfs_flush_device(ip); - xfs_ilock(ip, XFS_ILOCK_EXCL); - *fsynced = 3; - return 0; - } - return 1; -} - -STATIC int xfs_cmn_err_fsblock_zero( xfs_inode_t *ip, xfs_bmbt_irec_t *imap) @@ -538,15 +506,9 @@ error_out: } /* - * If the caller is doing a write at the end of the file, - * then extend the allocation out to the file system's write - * iosize. We clean up any extra space left over when the - * file is closed in xfs_inactive(). - * - * For sync writes, we are flushing delayed allocate space to - * try to make additional space available for allocation near - * the filesystem full boundary - preallocation hurts in that - * situation, of course. + * If the caller is doing a write at the end of the file, then extend the + * allocation out to the file system's write iosize. We clean up any extra + * space left over when the file is closed in xfs_inactive(). */ STATIC int xfs_iomap_eof_want_preallocate( @@ -565,7 +527,7 @@ xfs_iomap_eof_want_preallocate( int n, error, imaps; *prealloc = 0; - if ((ioflag & BMAPI_SYNC) || (offset + count) <= ip->i_size) + if ((offset + count) <= ip->i_size) return 0; /* @@ -611,7 +573,7 @@ xfs_iomap_write_delay( xfs_extlen_t extsz; int nimaps; xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS]; - int prealloc, fsynced = 0; + int prealloc, flushed = 0; int error; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -627,12 +589,12 @@ xfs_iomap_write_delay( extsz = xfs_get_extsz_hint(ip); offset_fsb = XFS_B_TO_FSBT(mp, offset); -retry: error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count, ioflag, imap, XFS_WRITE_IMAPS, &prealloc); if (error) return error; +retry: if (prealloc) { aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1)); ioalign = XFS_B_TO_FSBT(mp, aligned_offset); @@ -659,15 +621,22 @@ retry: /* * If bmapi returned us nothing, and if we didn't get back EDQUOT, - * then we must have run out of space - flush delalloc, and retry.. + * then we must have run out of space - flush all other inodes with + * delalloc blocks and retry without EOF preallocation. */ if (nimaps == 0) { xfs_iomap_enter_trace(XFS_IOMAP_WRITE_NOSPACE, ip, offset, count); - if (xfs_flush_space(ip, &fsynced, &ioflag)) + if (flushed) return XFS_ERROR(ENOSPC); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_flush_inodes(ip); + xfs_ilock(ip, XFS_ILOCK_EXCL); + + flushed = 1; error = 0; + prealloc = 0; goto retry; } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index a1cc1322fc0..fdcf7b82747 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -40,8 +40,7 @@ typedef enum { BMAPI_IGNSTATE = (1 << 4), /* ignore unwritten state on read */ BMAPI_DIRECT = (1 << 5), /* direct instead of buffered write */ BMAPI_MMAP = (1 << 6), /* allocate for mmap write */ - BMAPI_SYNC = (1 << 7), /* sync write to flush delalloc space */ - BMAPI_TRYLOCK = (1 << 8), /* non-blocking request */ + BMAPI_TRYLOCK = (1 << 7), /* non-blocking request */ } bmapi_flags_t; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f76c6d7cea2..3750f04ede0 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -562,9 +562,8 @@ xfs_log_mount( } mp->m_log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks); - if (!mp->m_log) { - cmn_err(CE_WARN, "XFS: Log allocation failed: No memory!"); - error = ENOMEM; + if (IS_ERR(mp->m_log)) { + error = -PTR_ERR(mp->m_log); goto out; } @@ -1180,10 +1179,13 @@ xlog_alloc_log(xfs_mount_t *mp, xfs_buf_t *bp; int i; int iclogsize; + int error = ENOMEM; log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL); - if (!log) - return NULL; + if (!log) { + xlog_warn("XFS: Log allocation failed: No memory!"); + goto out; + } log->l_mp = mp; log->l_targ = log_target; @@ -1201,19 +1203,35 @@ xlog_alloc_log(xfs_mount_t *mp, log->l_grant_reserve_cycle = 1; log->l_grant_write_cycle = 1; + error = EFSCORRUPTED; if (xfs_sb_version_hassector(&mp->m_sb)) { log->l_sectbb_log = mp->m_sb.sb_logsectlog - BBSHIFT; - ASSERT(log->l_sectbb_log <= mp->m_sectbb_log); + if (log->l_sectbb_log < 0 || + log->l_sectbb_log > mp->m_sectbb_log) { + xlog_warn("XFS: Log sector size (0x%x) out of range.", + log->l_sectbb_log); + goto out_free_log; + } + /* for larger sector sizes, must have v2 or external log */ - ASSERT(log->l_sectbb_log == 0 || - log->l_logBBstart == 0 || - xfs_sb_version_haslogv2(&mp->m_sb)); - ASSERT(mp->m_sb.sb_logsectlog >= BBSHIFT); + if (log->l_sectbb_log != 0 && + (log->l_logBBstart != 0 && + !xfs_sb_version_haslogv2(&mp->m_sb))) { + xlog_warn("XFS: log sector size (0x%x) invalid " + "for configuration.", log->l_sectbb_log); + goto out_free_log; + } + if (mp->m_sb.sb_logsectlog < BBSHIFT) { + xlog_warn("XFS: Log sector log (0x%x) too small.", + mp->m_sb.sb_logsectlog); + goto out_free_log; + } } log->l_sectbb_mask = (1 << log->l_sectbb_log) - 1; xlog_get_iclog_buffer_size(mp, log); + error = ENOMEM; bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp); if (!bp) goto out_free_log; @@ -1313,7 +1331,8 @@ out_free_iclog: xfs_buf_free(log->l_xbuf); out_free_log: kmem_free(log); - return NULL; +out: + return ERR_PTR(-error); } /* xlog_alloc_log */ @@ -2541,18 +2560,19 @@ redo: xlog_ins_ticketq(&log->l_reserve_headq, tic); xlog_trace_loggrant(log, tic, "xlog_grant_log_space: sleep 2"); + spin_unlock(&log->l_grant_lock); + xlog_grant_push_ail(log->l_mp, need_bytes); + spin_lock(&log->l_grant_lock); + XFS_STATS_INC(xs_sleep_logspace); sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s); - if (XLOG_FORCED_SHUTDOWN(log)) { - spin_lock(&log->l_grant_lock); + spin_lock(&log->l_grant_lock); + if (XLOG_FORCED_SHUTDOWN(log)) goto error_return; - } xlog_trace_loggrant(log, tic, "xlog_grant_log_space: wake 2"); - xlog_grant_push_ail(log->l_mp, need_bytes); - spin_lock(&log->l_grant_lock); goto redo; } else if (tic->t_flags & XLOG_TIC_IN_Q) xlog_del_ticketq(&log->l_reserve_headq, tic); @@ -2631,7 +2651,7 @@ xlog_regrant_write_log_space(xlog_t *log, * for more free space, otherwise try to get some space for * this transaction. */ - + need_bytes = tic->t_unit_res; if ((ntic = log->l_write_headq)) { free_bytes = xlog_space_left(log, log->l_grant_write_cycle, log->l_grant_write_bytes); @@ -2651,26 +2671,25 @@ xlog_regrant_write_log_space(xlog_t *log, xlog_trace_loggrant(log, tic, "xlog_regrant_write_log_space: sleep 1"); + spin_unlock(&log->l_grant_lock); + xlog_grant_push_ail(log->l_mp, need_bytes); + spin_lock(&log->l_grant_lock); + XFS_STATS_INC(xs_sleep_logspace); sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s); /* If we're shutting down, this tic is already * off the queue */ - if (XLOG_FORCED_SHUTDOWN(log)) { - spin_lock(&log->l_grant_lock); + spin_lock(&log->l_grant_lock); + if (XLOG_FORCED_SHUTDOWN(log)) goto error_return; - } xlog_trace_loggrant(log, tic, "xlog_regrant_write_log_space: wake 1"); - xlog_grant_push_ail(log->l_mp, tic->t_unit_res); - spin_lock(&log->l_grant_lock); } } - need_bytes = tic->t_unit_res; - redo: if (XLOG_FORCED_SHUTDOWN(log)) goto error_return; @@ -2680,19 +2699,20 @@ redo: if (free_bytes < need_bytes) { if ((tic->t_flags & XLOG_TIC_IN_Q) == 0) xlog_ins_ticketq(&log->l_write_headq, tic); + spin_unlock(&log->l_grant_lock); + xlog_grant_push_ail(log->l_mp, need_bytes); + spin_lock(&log->l_grant_lock); + XFS_STATS_INC(xs_sleep_logspace); sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s); /* If we're shutting down, this tic is already off the queue */ - if (XLOG_FORCED_SHUTDOWN(log)) { - spin_lock(&log->l_grant_lock); + spin_lock(&log->l_grant_lock); + if (XLOG_FORCED_SHUTDOWN(log)) goto error_return; - } xlog_trace_loggrant(log, tic, "xlog_regrant_write_log_space: wake 2"); - xlog_grant_push_ail(log->l_mp, need_bytes); - spin_lock(&log->l_grant_lock); goto redo; } else if (tic->t_flags & XLOG_TIC_IN_Q) xlog_del_ticketq(&log->l_write_headq, tic); diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 7af44adffc8..d6a64392f98 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -313,7 +313,7 @@ typedef struct xfs_mount { #endif struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ struct task_struct *m_sync_task; /* generalised sync thread */ - bhv_vfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */ + xfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */ struct list_head m_sync_list; /* sync thread work item list */ spinlock_t m_sync_lock; /* work item list lock */ int m_sync_seq; /* sync thread generation no. */ diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 7394c7af5de..19cf90a9c76 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -1457,6 +1457,13 @@ xfs_create( error = xfs_trans_reserve(tp, resblks, log_res, 0, XFS_TRANS_PERM_LOG_RES, log_count); if (error == ENOSPC) { + /* flush outstanding delalloc blocks and retry */ + xfs_flush_inodes(dp); + error = xfs_trans_reserve(tp, resblks, XFS_CREATE_LOG_RES(mp), 0, + XFS_TRANS_PERM_LOG_RES, XFS_CREATE_LOG_COUNT); + } + if (error == ENOSPC) { + /* No space at all so try a "no-allocation" reservation */ resblks = 0; error = xfs_trans_reserve(tp, 0, log_res, 0, XFS_TRANS_PERM_LOG_RES, log_count); diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 37b82cb96c8..e727fe0d145 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -88,7 +88,7 @@ extern void warn_slowpath(const char *file, const int line, #else /* !CONFIG_BUG */ #ifndef HAVE_ARCH_BUG -#define BUG() +#define BUG() do {} while(0) #endif #ifndef HAVE_ARCH_BUG_ON diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h index 35752dadd6d..c840719a8c5 100644 --- a/include/asm-generic/siginfo.h +++ b/include/asm-generic/siginfo.h @@ -201,7 +201,7 @@ typedef struct siginfo { #define TRAP_TRACE (__SI_FAULT|2) /* process trace trap */ #define TRAP_BRANCH (__SI_FAULT|3) /* process taken branch trap */ #define TRAP_HWBKPT (__SI_FAULT|4) /* hardware breakpoint/watchpoint */ -#define NSIGTRAP 2 +#define NSIGTRAP 4 /* * SIGCHLD si_codes diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 2df74eb0956..9477af01a63 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -472,6 +472,7 @@ {0x8086, 0x2562, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \ {0x8086, 0x3582, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \ {0x8086, 0x2572, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \ + {0x8086, 0x358e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \ {0, 0, 0} #define gamma_PCI_IDS \ @@ -533,4 +534,5 @@ {0x8086, 0x2e22, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, 0xffff00, 0}, \ {0x8086, 0xa001, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, 0xffff00, 0}, \ {0x8086, 0xa011, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, 0xffff00, 0}, \ + {0x8086, 0x35e8, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, 0xffff00, 0}, \ {0, 0, 0} diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 67e3353a56d..95962fa8398 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -594,6 +594,9 @@ struct drm_i915_gem_busy { #define I915_BIT_6_SWIZZLE_9_10_11 4 /* Not seen by userland */ #define I915_BIT_6_SWIZZLE_UNKNOWN 5 +/* Seen by userland. */ +#define I915_BIT_6_SWIZZLE_9_17 6 +#define I915_BIT_6_SWIZZLE_9_10_17 7 struct drm_i915_gem_set_tiling { /** Handle of the buffer to have its tiling state updated */ diff --git a/include/linux/bio.h b/include/linux/bio.h index b900d2c67d2..b89cf2d8289 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -504,6 +504,115 @@ static inline int bio_has_data(struct bio *bio) return bio && bio->bi_io_vec != NULL; } +/* + * BIO list managment for use by remapping drivers (e.g. DM or MD). + * + * A bio_list anchors a singly-linked list of bios chained through the bi_next + * member of the bio. The bio_list also caches the last list member to allow + * fast access to the tail. + */ +struct bio_list { + struct bio *head; + struct bio *tail; +}; + +static inline int bio_list_empty(const struct bio_list *bl) +{ + return bl->head == NULL; +} + +static inline void bio_list_init(struct bio_list *bl) +{ + bl->head = bl->tail = NULL; +} + +#define bio_list_for_each(bio, bl) \ + for (bio = (bl)->head; bio; bio = bio->bi_next) + +static inline unsigned bio_list_size(const struct bio_list *bl) +{ + unsigned sz = 0; + struct bio *bio; + + bio_list_for_each(bio, bl) + sz++; + + return sz; +} + +static inline void bio_list_add(struct bio_list *bl, struct bio *bio) +{ + bio->bi_next = NULL; + + if (bl->tail) + bl->tail->bi_next = bio; + else + bl->head = bio; + + bl->tail = bio; +} + +static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) +{ + bio->bi_next = bl->head; + + bl->head = bio; + + if (!bl->tail) + bl->tail = bio; +} + +static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) +{ + if (!bl2->head) + return; + + if (bl->tail) + bl->tail->bi_next = bl2->head; + else + bl->head = bl2->head; + + bl->tail = bl2->tail; +} + +static inline void bio_list_merge_head(struct bio_list *bl, + struct bio_list *bl2) +{ + if (!bl2->head) + return; + + if (bl->head) + bl2->tail->bi_next = bl->head; + else + bl->tail = bl2->tail; + + bl->head = bl2->head; +} + +static inline struct bio *bio_list_pop(struct bio_list *bl) +{ + struct bio *bio = bl->head; + + if (bio) { + bl->head = bl->head->bi_next; + if (!bl->head) + bl->tail = NULL; + + bio->bi_next = NULL; + } + + return bio; +} + +static inline struct bio *bio_list_get(struct bio_list *bl) +{ + struct bio *bio = bl->head; + + bl->head = bl->tail = NULL; + + return bio; +} + #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 493dedb7a67..29b3ce3f2a1 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <asm/atomic.h> +#include <asm/system.h> struct task_struct; diff --git a/include/linux/fb.h b/include/linux/fb.h index f563c501393..330c4b1bfca 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -173,8 +173,12 @@ struct fb_fix_screeninfo { /* Interpretation of offset for color fields: All offsets are from the right, * inside a "pixel" value, which is exactly 'bits_per_pixel' wide (means: you * can use the offset as right argument to <<). A pixel afterwards is a bit - * stream and is written to video memory as that unmodified. This implies - * big-endian byte order if bits_per_pixel is greater than 8. + * stream and is written to video memory as that unmodified. + * + * For pseudocolor: offset and length should be the same for all color + * components. Offset specifies the position of the least significant bit + * of the pallette index in a pixel value. Length indicates the number + * of available palette entries (i.e. # of entries = 1 << length). */ struct fb_bitfield { __u32 offset; /* beginning of bitfield */ diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index 671decbd2ae..934e22d6580 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -11,6 +11,8 @@ #ifndef _LINUX_FIEMAP_H #define _LINUX_FIEMAP_H +#include <linux/types.h> + struct fiemap_extent { __u64 fe_logical; /* logical offset in bytes for the start of * the extent from the beginning of the file */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 562d2855cf3..e766be0d432 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -87,6 +87,60 @@ struct inodes_stat_t { */ #define FMODE_NOCMTIME ((__force fmode_t)2048) +/* + * The below are the various read and write types that we support. Some of + * them include behavioral modifiers that send information down to the + * block layer and IO scheduler. Terminology: + * + * The block layer uses device plugging to defer IO a little bit, in + * the hope that we will see more IO very shortly. This increases + * coalescing of adjacent IO and thus reduces the number of IOs we + * have to send to the device. It also allows for better queuing, + * if the IO isn't mergeable. If the caller is going to be waiting + * for the IO, then he must ensure that the device is unplugged so + * that the IO is dispatched to the driver. + * + * All IO is handled async in Linux. This is fine for background + * writes, but for reads or writes that someone waits for completion + * on, we want to notify the block layer and IO scheduler so that they + * know about it. That allows them to make better scheduling + * decisions. So when the below references 'sync' and 'async', it + * is referencing this priority hint. + * + * With that in mind, the available types are: + * + * READ A normal read operation. Device will be plugged. + * READ_SYNC A synchronous read. Device is not plugged, caller can + * immediately wait on this read without caring about + * unplugging. + * READA Used for read-ahead operations. Lower priority, and the + * block layer could (in theory) choose to ignore this + * request if it runs into resource problems. + * WRITE A normal async write. Device will be plugged. + * SWRITE Like WRITE, but a special case for ll_rw_block() that + * tells it to lock the buffer first. Normally a buffer + * must be locked before doing IO. + * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down + * the hint that someone will be waiting on this IO + * shortly. The device must still be unplugged explicitly, + * WRITE_SYNC_PLUG does not do this as we could be + * submitting more writes before we actually wait on any + * of them. + * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device + * immediately after submission. The write equivalent + * of READ_SYNC. + * WRITE_ODIRECT Special case write for O_DIRECT only. + * SWRITE_SYNC + * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. + * See SWRITE. + * WRITE_BARRIER Like WRITE, but tells the block layer that all + * previously submitted writes must be safely on storage + * before this one is started. Also guarantees that when + * this write is complete, it itself is also safely on + * storage. Prevents reordering of writes on both sides + * of this IO. + * + */ #define RW_MASK 1 #define RWA_MASK 2 #define READ 0 @@ -102,6 +156,11 @@ struct inodes_stat_t { (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) #define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) + +/* + * These aren't really reads or writes, they pass down information about + * parts of device that are now unused by the file system. + */ #define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD) #define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER)) @@ -738,9 +797,6 @@ enum inode_i_mutex_lock_class I_MUTEX_QUOTA }; -extern void inode_double_lock(struct inode *inode1, struct inode *inode2); -extern void inode_double_unlock(struct inode *inode1, struct inode *inode2); - /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -2150,8 +2206,6 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t generic_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); -extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *, - struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index f2a78b5e8b5..43fc95d822d 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -43,10 +43,6 @@ * */ -/* Flags related to I2C device features */ -#define FSL_I2C_DEV_SEPARATE_DFSRR 0x00000001 -#define FSL_I2C_DEV_CLOCK_5200 0x00000002 - enum fsl_usb2_operating_modes { FSL_USB2_MPH_HOST, FSL_USB2_DR_HOST, diff --git a/include/linux/init_task.h b/include/linux/init_task.h index dcfb93337e9..d87247d2641 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -15,19 +15,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; -#define INIT_KIOCTX(name, which_mm) \ -{ \ - .users = ATOMIC_INIT(1), \ - .dead = 0, \ - .mm = &which_mm, \ - .user_id = 0, \ - .next = NULL, \ - .wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait), \ - .ctx_lock = __SPIN_LOCK_UNLOCKED(name.ctx_lock), \ - .reqs_active = 0U, \ - .max_reqs = ~0U, \ -} - #define INIT_MM(name) \ { \ .mm_rb = RB_ROOT, \ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ee98cd57088..06ba90c211a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2514,6 +2514,8 @@ #define PCI_DEVICE_ID_INTEL_IOAT_TBG3 0x3433 #define PCI_DEVICE_ID_INTEL_82830_HB 0x3575 #define PCI_DEVICE_ID_INTEL_82830_CGC 0x3577 +#define PCI_DEVICE_ID_INTEL_82854_HB 0x358c +#define PCI_DEVICE_ID_INTEL_82854_IG 0x358e #define PCI_DEVICE_ID_INTEL_82855GM_HB 0x3580 #define PCI_DEVICE_ID_INTEL_82855GM_IG 0x3582 #define PCI_DEVICE_ID_INTEL_E7520_MCH 0x3590 diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 8e4120285f7..c8f038554e8 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -134,6 +134,11 @@ struct pipe_buf_operations { memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE +/* Pipe lock and unlock operations */ +void pipe_lock(struct pipe_inode_info *); +void pipe_unlock(struct pipe_inode_info *); +void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); + /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe); diff --git a/include/linux/sht15.h b/include/linux/sht15.h new file mode 100644 index 00000000000..046bce05eca --- /dev/null +++ b/include/linux/sht15.h @@ -0,0 +1,24 @@ +/* + * sht15.h - support for the SHT15 Temperature and Humidity Sensor + * + * Copyright (c) 2009 Jonathan Cameron + * + * Copyright (c) 2007 Wouter Horre + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/** + * struct sht15_platform_data - sht15 connectivity info + * @gpio_data: no. of gpio to which bidirectional data line is connected + * @gpio_sck: no. of gpio to which the data clock is connected. + * @supply_mv: supply voltage in mv. Overridden by regulator if available. + **/ +struct sht15_platform_data { + int gpio_data; + int gpio_sck; + int supply_mv; +}; + diff --git a/include/linux/splice.h b/include/linux/splice.h index 528dcb93c2f..5f3faa9d15a 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -36,6 +36,8 @@ struct splice_desc { void *data; /* cookie */ } u; loff_t pos; /* file position */ + size_t num_spliced; /* number of bytes already spliced */ + bool need_wakeup; /* need to wake up writer */ }; struct partial_page { @@ -66,6 +68,16 @@ extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *, splice_actor *); extern ssize_t __splice_from_pipe(struct pipe_inode_info *, struct splice_desc *, splice_actor *); +extern int splice_from_pipe_feed(struct pipe_inode_info *, struct splice_desc *, + splice_actor *); +extern int splice_from_pipe_next(struct pipe_inode_info *, + struct splice_desc *); +extern void splice_from_pipe_begin(struct splice_desc *); +extern void splice_from_pipe_end(struct pipe_inode_info *, + struct splice_desc *); +extern int pipe_to_file(struct pipe_inode_info *, struct pipe_buffer *, + struct splice_desc *); + extern ssize_t splice_to_pipe(struct pipe_inode_info *, struct splice_pipe_desc *); extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index b9584254259..625e9e4639c 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -29,7 +29,7 @@ /** * usb_serial_port: structure for the specific ports of a device. * @serial: pointer back to the struct usb_serial owner of this port. - * @tty: pointer to the corresponding tty for this port. + * @port: pointer to the corresponding tty_port for this port. * @lock: spinlock to grab when updating portions of this structure. * @mutex: mutex used to synchronize serial_open() and serial_close() * access for this port. @@ -44,19 +44,22 @@ * @interrupt_out_endpointAddress: endpoint address for the interrupt out pipe * for this port. * @bulk_in_buffer: pointer to the bulk in buffer for this port. + * @bulk_in_size: the size of the bulk_in_buffer, in bytes. * @read_urb: pointer to the bulk in struct urb for this port. * @bulk_in_endpointAddress: endpoint address for the bulk in pipe for this * port. * @bulk_out_buffer: pointer to the bulk out buffer for this port. * @bulk_out_size: the size of the bulk_out_buffer, in bytes. * @write_urb: pointer to the bulk out struct urb for this port. + * @write_urb_busy: port`s writing status * @bulk_out_endpointAddress: endpoint address for the bulk out pipe for this * port. * @write_wait: a wait_queue_head_t used by the port. * @work: work queue entry for the line discipline waking up. - * @open_count: number of times this port has been opened. * @throttled: nonzero if the read urb is inactive to throttle the device * @throttle_req: nonzero if the tty wants to throttle us + * @console: attached usb serial console + * @dev: pointer to the serial device * * This structure is used by the usb-serial core and drivers for the specific * ports of a device. diff --git a/include/sound/jack.h b/include/sound/jack.h index 6b013c6f6a0..f236e426a70 100644 --- a/include/sound/jack.h +++ b/include/sound/jack.h @@ -50,6 +50,8 @@ struct snd_jack { int type; const char *id; char name[100]; + void *private_data; + void (*private_free)(struct snd_jack *); }; #ifdef CONFIG_SND_JACK diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 8904b1900d7..c1729689161 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -268,7 +268,8 @@ struct snd_pcm_runtime { int overrange; snd_pcm_uframes_t avail_max; snd_pcm_uframes_t hw_ptr_base; /* Position at buffer restart */ - snd_pcm_uframes_t hw_ptr_interrupt; /* Position at interrupt time*/ + snd_pcm_uframes_t hw_ptr_interrupt; /* Position at interrupt time */ + unsigned long hw_ptr_jiffies; /* Time when hw_ptr is updated */ /* -- HW params -- */ snd_pcm_access_t access; /* access mode */ diff --git a/include/video/cyblafb.h b/include/video/cyblafb.h deleted file mode 100644 index d3c1d4e2c8e..00000000000 --- a/include/video/cyblafb.h +++ /dev/null @@ -1,175 +0,0 @@ - -#ifndef CYBLAFB_DEBUG -#define CYBLAFB_DEBUG 0 -#endif - -#if CYBLAFB_DEBUG -#define debug(f,a...) printk("%s:" f, __func__ , ## a); -#else -#define debug(f,a...) -#endif - -#define output(f, a...) printk("cyblafb: " f, ## a) - -#define Kb (1024) -#define Mb (Kb*Kb) - -/* PCI IDS of supported cards temporarily here */ - -#define CYBERBLADEi1 0x8500 - -/* these defines are for 'lcd' variable */ -#define LCD_STRETCH 0 -#define LCD_CENTER 1 -#define LCD_BIOS 2 - -/* display types */ -#define DISPLAY_CRT 0 -#define DISPLAY_FP 1 - -#define ROP_S 0xCC - -#define point(x,y) ((y)<<16|(x)) - -// -// Attribute Regs, ARxx, 3c0/3c1 -// -#define AR00 0x00 -#define AR01 0x01 -#define AR02 0x02 -#define AR03 0x03 -#define AR04 0x04 -#define AR05 0x05 -#define AR06 0x06 -#define AR07 0x07 -#define AR08 0x08 -#define AR09 0x09 -#define AR0A 0x0A -#define AR0B 0x0B -#define AR0C 0x0C -#define AR0D 0x0D -#define AR0E 0x0E -#define AR0F 0x0F -#define AR10 0x10 -#define AR12 0x12 -#define AR13 0x13 - -// -// Sequencer Regs, SRxx, 3c4/3c5 -// -#define SR00 0x00 -#define SR01 0x01 -#define SR02 0x02 -#define SR03 0x03 -#define SR04 0x04 -#define SR0D 0x0D -#define SR0E 0x0E -#define SR11 0x11 -#define SR18 0x18 -#define SR19 0x19 - -// -// -// -#define CR00 0x00 -#define CR01 0x01 -#define CR02 0x02 -#define CR03 0x03 -#define CR04 0x04 -#define CR05 0x05 -#define CR06 0x06 -#define CR07 0x07 -#define CR08 0x08 -#define CR09 0x09 -#define CR0A 0x0A -#define CR0B 0x0B -#define CR0C 0x0C -#define CR0D 0x0D -#define CR0E 0x0E -#define CR0F 0x0F -#define CR10 0x10 -#define CR11 0x11 -#define CR12 0x12 -#define CR13 0x13 -#define CR14 0x14 -#define CR15 0x15 -#define CR16 0x16 -#define CR17 0x17 -#define CR18 0x18 -#define CR19 0x19 -#define CR1A 0x1A -#define CR1B 0x1B -#define CR1C 0x1C -#define CR1D 0x1D -#define CR1E 0x1E -#define CR1F 0x1F -#define CR20 0x20 -#define CR21 0x21 -#define CR27 0x27 -#define CR29 0x29 -#define CR2A 0x2A -#define CR2B 0x2B -#define CR2D 0x2D -#define CR2F 0x2F -#define CR36 0x36 -#define CR38 0x38 -#define CR39 0x39 -#define CR3A 0x3A -#define CR55 0x55 -#define CR56 0x56 -#define CR57 0x57 -#define CR58 0x58 - -// -// -// - -#define GR00 0x01 -#define GR01 0x01 -#define GR02 0x02 -#define GR03 0x03 -#define GR04 0x04 -#define GR05 0x05 -#define GR06 0x06 -#define GR07 0x07 -#define GR08 0x08 -#define GR0F 0x0F -#define GR20 0x20 -#define GR23 0x23 -#define GR2F 0x2F -#define GR30 0x30 -#define GR31 0x31 -#define GR33 0x33 -#define GR52 0x52 -#define GR53 0x53 -#define GR5D 0x5d - - -// -// Graphics Engine -// -#define GEBase 0x2100 // could be mapped elsewhere if we like it -#define GE00 (GEBase+0x00) // source 1, p 111 -#define GE04 (GEBase+0x04) // source 2, p 111 -#define GE08 (GEBase+0x08) // destination 1, p 111 -#define GE0C (GEBase+0x0C) // destination 2, p 112 -#define GE10 (GEBase+0x10) // right view base & enable, p 112 -#define GE13 (GEBase+0x13) // left view base & enable, p 112 -#define GE18 (GEBase+0x18) // block write start address, p 112 -#define GE1C (GEBase+0x1C) // block write end address, p 112 -#define GE20 (GEBase+0x20) // engine status, p 113 -#define GE24 (GEBase+0x24) // reset all GE pointers -#define GE44 (GEBase+0x44) // command register, p 126 -#define GE48 (GEBase+0x48) // raster operation, p 127 -#define GE60 (GEBase+0x60) // foreground color, p 128 -#define GE64 (GEBase+0x64) // background color, p 128 -#define GE6C (GEBase+0x6C) // Pattern and Style, p 129, ok -#define GE9C (GEBase+0x9C) // pixel engine data port, p 125 -#define GEB8 (GEBase+0xB8) // Destination Stride / Buffer Base 0, p 133 -#define GEBC (GEBase+0xBC) // Destination Stride / Buffer Base 1, p 133 -#define GEC0 (GEBase+0xC0) // Destination Stride / Buffer Base 2, p 133 -#define GEC4 (GEBase+0xC4) // Destination Stride / Buffer Base 3, p 133 -#define GEC8 (GEBase+0xC8) // Source Stride / Buffer Base 0, p 133 -#define GECC (GEBase+0xCC) // Source Stride / Buffer Base 1, p 133 -#define GED0 (GEBase+0xD0) // Source Stride / Buffer Base 2, p 133 -#define GED4 (GEBase+0xD4) // Source Stride / Buffer Base 3, p 133 diff --git a/init/initramfs.c b/init/initramfs.c index 80cd713f6cc..9ee7b781041 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -310,7 +310,8 @@ static int __init do_name(void) if (wfd >= 0) { sys_fchown(wfd, uid, gid); sys_fchmod(wfd, mode); - sys_ftruncate(wfd, body_len); + if (body_len) + sys_ftruncate(wfd, body_len); vcollected = kstrdup(collected, GFP_KERNEL); state = CopyFile; } @@ -515,6 +516,7 @@ skip: initrd_end = 0; } +#ifdef CONFIG_BLK_DEV_RAM #define BUF_SIZE 1024 static void __init clean_rootfs(void) { @@ -561,6 +563,7 @@ static void __init clean_rootfs(void) sys_close(fd); kfree(buf); } +#endif static int __init populate_rootfs(void) { diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 89f60ec8ee5..24ae46dfe45 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -22,6 +22,7 @@ #define MIN_MSGSIZEMAX 128 /* min value for msgsize_max */ #define MAX_MSGSIZEMAX (8192*128) /* max value for msgsize_max */ +#ifdef CONFIG_PROC_SYSCTL static void *get_mq(ctl_table *table) { char *which = table->data; @@ -30,7 +31,6 @@ static void *get_mq(ctl_table *table) return which; } -#ifdef CONFIG_PROC_SYSCTL static int proc_mq_dointvec(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 505f319e489..8ba052c86d4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -64,8 +64,6 @@ static int submit(int rw, pgoff_t page_off, struct page *page, struct bio *bio; bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); - if (!bio) - return -ENOMEM; bio->bi_sector = page_off * (PAGE_SIZE >> 9); bio->bi_bdev = resume_bdev; bio->bi_end_io = end_swap_bio_read; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 64191fa09b7..dfcd83ceee3 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -604,10 +604,11 @@ repeat: ret = security_ptrace_traceme(current->parent); /* - * Set the ptrace bit in the process ptrace flags. - * Then link us on our parent's ptraced list. + * Check PF_EXITING to ensure ->real_parent has not passed + * exit_ptrace(). Otherwise we don't report the error but + * pretend ->real_parent untraces us right after return. */ - if (!ret) { + if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace |= PT_PTRACED; __ptrace_link(current, current->real_parent); } diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 2c7b8457d0d..a967c9feb90 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -58,6 +58,10 @@ static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; int rcu_scheduler_active __read_mostly; +static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); +static struct rcu_head rcu_migrate_head[3]; +static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); + /* * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. @@ -122,7 +126,10 @@ static void rcu_barrier_func(void *type) } } -static inline void wait_migrated_callbacks(void); +static inline void wait_migrated_callbacks(void) +{ + wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); +} /* * Orchestrate the specified type of RCU barrier, waiting for all @@ -179,21 +186,12 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL_GPL(rcu_barrier_sched); -static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); -static struct rcu_head rcu_migrate_head[3]; -static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); - static void rcu_migrate_callback(struct rcu_head *notused) { if (atomic_dec_and_test(&rcu_migrate_type_count)) wake_up(&rcu_migrate_wq); } -static inline void wait_migrated_callbacks(void) -{ - wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); -} - static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, unsigned long action, void *hcpu) { diff --git a/kernel/sys.c b/kernel/sys.c index 51dbb55604e..e7998cf3149 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -360,6 +360,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg) { char buffer[256]; + int ret = 0; /* We only trust the superuser with rebooting the system. */ if (!capable(CAP_SYS_BOOT)) @@ -397,7 +398,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, kernel_halt(); unlock_kernel(); do_exit(0); - break; + panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); @@ -417,29 +418,22 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, #ifdef CONFIG_KEXEC case LINUX_REBOOT_CMD_KEXEC: - { - int ret; - ret = kernel_kexec(); - unlock_kernel(); - return ret; - } + ret = kernel_kexec(); + break; #endif #ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: - { - int ret = hibernate(); - unlock_kernel(); - return ret; - } + ret = hibernate(); + break; #endif default: - unlock_kernel(); - return -EINVAL; + ret = -EINVAL; + break; } unlock_kernel(); - return 0; + return ret; } static void deferred_cad(struct work_struct *dummy) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4286b62b34a..e3d2c7dd59b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -902,16 +902,6 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_UNEVICTABLE_LRU - { - .ctl_name = CTL_UNNUMBERED, - .procname = "scan_unevictable_pages", - .data = &scan_unevictable_pages, - .maxlen = sizeof(scan_unevictable_pages), - .mode = 0644, - .proc_handler = &scan_unevictable_handler, - }, -#endif #ifdef CONFIG_SLOW_WORK { .ctl_name = CTL_UNNUMBERED, @@ -1302,6 +1292,16 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_UNEVICTABLE_LRU + { + .ctl_name = CTL_UNNUMBERED, + .procname = "scan_unevictable_pages", + .data = &scan_unevictable_pages, + .maxlen = sizeof(scan_unevictable_pages), + .mode = 0644, + .proc_handler = &scan_unevictable_handler, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/mm/Kconfig b/mm/Kconfig index b53427ad30a..57971d2ab84 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -213,6 +213,8 @@ config UNEVICTABLE_LRU will use one page flag and increase the code size a little, say Y unless you know what you are doing. + See Documentation/vm/unevictable-lru.txt for more information. + config HAVE_MLOCK bool default y if MMU=y diff --git a/mm/filemap.c b/mm/filemap.c index 2e2d38ebda4..8bd498040f3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -567,8 +567,8 @@ EXPORT_SYMBOL(wait_on_page_bit); /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue - * @page - Page defining the wait queue of interest - * @waiter - Waiter to add to the queue + * @page: Page defining the wait queue of interest + * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2fc6d6c4823..e44fb0fbb80 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -932,7 +932,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (unlikely(!mem)) return 0; - VM_BUG_ON(mem_cgroup_is_obsolete(mem)); + VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem)); while (1) { int ret; diff --git a/mm/shmem.c b/mm/shmem.c index d94d2e9146b..f9cb20ebb99 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -24,6 +24,7 @@ #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> +#include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/module.h> @@ -43,7 +44,6 @@ static struct vfsmount *shm_mnt; #include <linux/exportfs.h> #include <linux/generic_acl.h> #include <linux/mman.h> -#include <linux/pagemap.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -65,13 +65,28 @@ static struct vfsmount *shm_mnt; #include <asm/div64.h> #include <asm/pgtable.h> +/* + * The maximum size of a shmem/tmpfs file is limited by the maximum size of + * its triple-indirect swap vector - see illustration at shmem_swp_entry(). + * + * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel, + * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum + * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, + * MAX_LFS_FILESIZE being then more restrictive than swap vector layout. + * + * We use / and * instead of shifts in the definitions below, so that the swap + * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE. + */ #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) -#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) +#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) -#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) -#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT) +#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) +#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT) +#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE) +#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT)) + +#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) /* info->flags needs VM_flags to handle pagein/truncate races efficiently */ @@ -2581,7 +2596,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) #define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -#define SHMEM_MAX_BYTES LLONG_MAX +#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE #endif /* CONFIG_SHMEM */ diff --git a/mm/util.c b/mm/util.c index 2599e83eea1..55bef160b9f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -223,6 +223,22 @@ void arch_pick_mmap_layout(struct mm_struct *mm) } #endif +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. + */ int __attribute__((weak)) get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index a0affd9cfca..d4d41b3efc7 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ @@ -1773,7 +1773,7 @@ void tomoyo_load_policy(const char *filename) envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, 1); - printk(KERN_INFO "TOMOYO: 2.2.0-pre 2009/02/01\n"); + printk(KERN_INFO "TOMOYO: 2.2.0 2009/04/01\n"); printk(KERN_INFO "Mandatory Access Control activated.\n"); tomoyo_policy_loaded = true; { /* Check all profiles currently assigned to domains are defined. */ @@ -1800,7 +1800,7 @@ void tomoyo_load_policy(const char *filename) static int tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->read_eof) { - tomoyo_io_printf(head, "2.2.0-pre"); + tomoyo_io_printf(head, "2.2.0"); head->read_eof = true; } return 0; diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index e77e6a6de0f..678f4ff16aa 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 2f2b449ffd2..2d6748741a2 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c index 65f50c1c5ee..2316da8ec5b 100644 --- a/security/tomoyo/file.c +++ b/security/tomoyo/file.c @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index 3bbe01a7a4b..bf8e2b45168 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/realpath.h b/security/tomoyo/realpath.h index 7ec9fc9cbc0..78217a37960 100644 --- a/security/tomoyo/realpath.h +++ b/security/tomoyo/realpath.h @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 3eeeae12c4d..5b481912752 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/security/tomoyo/tomoyo.h b/security/tomoyo/tomoyo.h index a0c8f6e0bea..41c6ebafb9c 100644 --- a/security/tomoyo/tomoyo.h +++ b/security/tomoyo/tomoyo.h @@ -5,7 +5,7 @@ * * Copyright (C) 2005-2009 NTT DATA CORPORATION * - * Version: 2.2.0-pre 2009/02/01 + * Version: 2.2.0 2009/04/01 * */ diff --git a/sound/core/control.c b/sound/core/control.c index 4b20fa2b7e6..17b8d47a5cd 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -723,14 +723,11 @@ static int snd_ctl_elem_read_user(struct snd_card *card, { struct snd_ctl_elem_value *control; int result; - - control = kmalloc(sizeof(*control), GFP_KERNEL); - if (control == NULL) - return -ENOMEM; - if (copy_from_user(control, _control, sizeof(*control))) { - kfree(control); - return -EFAULT; - } + + control = memdup_user(_control, sizeof(*control)); + if (IS_ERR(control)) + return PTR_ERR(control); + snd_power_lock(card); result = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (result >= 0) @@ -784,13 +781,10 @@ static int snd_ctl_elem_write_user(struct snd_ctl_file *file, struct snd_card *card; int result; - control = kmalloc(sizeof(*control), GFP_KERNEL); - if (control == NULL) - return -ENOMEM; - if (copy_from_user(control, _control, sizeof(*control))) { - kfree(control); - return -EFAULT; - } + control = memdup_user(_control, sizeof(*control)); + if (IS_ERR(control)) + return PTR_ERR(control); + card = file->card; snd_power_lock(card); result = snd_power_wait(card, SNDRV_CTL_POWER_D0); @@ -916,13 +910,10 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol, if (op_flag > 0) { if (size > 1024 * 128) /* sane value */ return -EINVAL; - new_data = kmalloc(size, GFP_KERNEL); - if (new_data == NULL) - return -ENOMEM; - if (copy_from_user(new_data, tlv, size)) { - kfree(new_data); - return -EFAULT; - } + + new_data = memdup_user(tlv, size); + if (IS_ERR(new_data)) + return PTR_ERR(new_data); change = ue->tlv_data_size != size; if (!change) change = memcmp(ue->tlv_data, new_data, size); diff --git a/sound/core/jack.c b/sound/core/jack.c index c8254c667c6..d54d1a05fe6 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -35,6 +35,9 @@ static int snd_jack_dev_free(struct snd_device *device) { struct snd_jack *jack = device->device_data; + if (jack->private_free) + jack->private_free(jack); + /* If the input device is registered with the input subsystem * then we need to use a different deallocator. */ if (jack->registered) diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 36d7a599823..08bfed594a8 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -232,14 +232,11 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, if (! (runtime = substream->runtime)) return -ENOTTY; - data = kmalloc(sizeof(*data), GFP_KERNEL); - if (data == NULL) - return -ENOMEM; /* only fifo_size is different, so just copy all */ - if (copy_from_user(data, data32, sizeof(*data32))) { - err = -EFAULT; - goto error; - } + data = memdup_user(data32, sizeof(*data32)); + if (IS_ERR(data)) + return PTR_ERR(data); + if (refine) err = snd_pcm_hw_refine(substream, data); else diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index fbb2e391591..63d088f2265 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -209,9 +209,11 @@ static int snd_pcm_update_hw_ptr_interrupt(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_uframes_t pos; - snd_pcm_uframes_t new_hw_ptr, hw_ptr_interrupt, hw_base; - snd_pcm_sframes_t delta; + snd_pcm_uframes_t old_hw_ptr, new_hw_ptr, hw_ptr_interrupt, hw_base; + snd_pcm_sframes_t hdelta, delta; + unsigned long jdelta; + old_hw_ptr = runtime->status->hw_ptr; pos = snd_pcm_update_hw_ptr_pos(substream, runtime); if (pos == SNDRV_PCM_POS_XRUN) { xrun(substream); @@ -247,7 +249,30 @@ static int snd_pcm_update_hw_ptr_interrupt(struct snd_pcm_substream *substream) new_hw_ptr = hw_base + pos; } } - if (delta > runtime->period_size) { + hdelta = new_hw_ptr - old_hw_ptr; + jdelta = jiffies - runtime->hw_ptr_jiffies; + if (((hdelta * HZ) / runtime->rate) > jdelta + HZ/100) { + delta = jdelta / + (((runtime->period_size * HZ) / runtime->rate) + + HZ/100); + hw_ptr_error(substream, + "hw_ptr skipping! [Q] " + "(pos=%ld, delta=%ld, period=%ld, " + "jdelta=%lu/%lu/%lu)\n", + (long)pos, (long)hdelta, + (long)runtime->period_size, jdelta, + ((hdelta * HZ) / runtime->rate), delta); + hw_ptr_interrupt = runtime->hw_ptr_interrupt + + runtime->period_size * delta; + if (hw_ptr_interrupt >= runtime->boundary) + hw_ptr_interrupt -= runtime->boundary; + /* rebase to interrupt position */ + hw_base = new_hw_ptr = hw_ptr_interrupt; + /* align hw_base to buffer_size */ + hw_base -= hw_base % runtime->buffer_size; + delta = 0; + } + if (delta > runtime->period_size + runtime->period_size / 2) { hw_ptr_error(substream, "Lost interrupts? " "(stream=%i, delta=%ld, intr_ptr=%ld)\n", @@ -263,6 +288,7 @@ static int snd_pcm_update_hw_ptr_interrupt(struct snd_pcm_substream *substream) runtime->hw_ptr_base = hw_base; runtime->status->hw_ptr = new_hw_ptr; + runtime->hw_ptr_jiffies = jiffies; runtime->hw_ptr_interrupt = hw_ptr_interrupt; return snd_pcm_update_hw_ptr_post(substream, runtime); @@ -275,6 +301,7 @@ int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream) snd_pcm_uframes_t pos; snd_pcm_uframes_t old_hw_ptr, new_hw_ptr, hw_base; snd_pcm_sframes_t delta; + unsigned long jdelta; old_hw_ptr = runtime->status->hw_ptr; pos = snd_pcm_update_hw_ptr_pos(substream, runtime); @@ -286,14 +313,15 @@ int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream) new_hw_ptr = hw_base + pos; delta = new_hw_ptr - old_hw_ptr; + jdelta = jiffies - runtime->hw_ptr_jiffies; if (delta < 0) { delta += runtime->buffer_size; if (delta < 0) { hw_ptr_error(substream, "Unexpected hw_pointer value [2] " - "(stream=%i, pos=%ld, old_ptr=%ld)\n", + "(stream=%i, pos=%ld, old_ptr=%ld, jdelta=%li)\n", substream->stream, (long)pos, - (long)old_hw_ptr); + (long)old_hw_ptr, jdelta); return 0; } hw_base += runtime->buffer_size; @@ -301,12 +329,13 @@ int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream) hw_base = 0; new_hw_ptr = hw_base + pos; } - if (delta > runtime->period_size && runtime->periods > 1) { + if (((delta * HZ) / runtime->rate) > jdelta + HZ/100) { hw_ptr_error(substream, "hw_ptr skipping! " - "(pos=%ld, delta=%ld, period=%ld)\n", + "(pos=%ld, delta=%ld, period=%ld, jdelta=%lu/%lu)\n", (long)pos, (long)delta, - (long)runtime->period_size); + (long)runtime->period_size, jdelta, + ((delta * HZ) / runtime->rate)); return 0; } if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && @@ -315,6 +344,7 @@ int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream) runtime->hw_ptr_base = hw_base; runtime->status->hw_ptr = new_hw_ptr; + runtime->hw_ptr_jiffies = jiffies; return snd_pcm_update_hw_ptr_post(substream, runtime); } @@ -1441,6 +1471,7 @@ static int snd_pcm_lib_ioctl_reset(struct snd_pcm_substream *substream, runtime->status->hw_ptr %= runtime->buffer_size; else runtime->status->hw_ptr = 0; + runtime->hw_ptr_jiffies = jiffies; snd_pcm_stream_unlock_irqrestore(substream, flags); return 0; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index a151fb01ba8..fc6f98e257d 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -327,21 +327,16 @@ static int snd_pcm_hw_refine_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params; int err; - params = kmalloc(sizeof(*params), GFP_KERNEL); - if (!params) { - err = -ENOMEM; - goto out; - } - if (copy_from_user(params, _params, sizeof(*params))) { - err = -EFAULT; - goto out; - } + params = memdup_user(_params, sizeof(*params)); + if (IS_ERR(params)) + return PTR_ERR(params); + err = snd_pcm_hw_refine(substream, params); if (copy_to_user(_params, params, sizeof(*params))) { if (!err) err = -EFAULT; } -out: + kfree(params); return err; } @@ -465,21 +460,16 @@ static int snd_pcm_hw_params_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params; int err; - params = kmalloc(sizeof(*params), GFP_KERNEL); - if (!params) { - err = -ENOMEM; - goto out; - } - if (copy_from_user(params, _params, sizeof(*params))) { - err = -EFAULT; - goto out; - } + params = memdup_user(_params, sizeof(*params)); + if (IS_ERR(params)) + return PTR_ERR(params); + err = snd_pcm_hw_params(substream, params); if (copy_to_user(_params, params, sizeof(*params))) { if (!err) err = -EFAULT; } -out: + kfree(params); return err; } @@ -2593,13 +2583,11 @@ static int snd_pcm_playback_ioctl1(struct file *file, return -EFAULT; if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; - bufs = kmalloc(sizeof(void *) * runtime->channels, GFP_KERNEL); - if (bufs == NULL) - return -ENOMEM; - if (copy_from_user(bufs, xfern.bufs, sizeof(void *) * runtime->channels)) { - kfree(bufs); - return -EFAULT; - } + + bufs = memdup_user(xfern.bufs, + sizeof(void *) * runtime->channels); + if (IS_ERR(bufs)) + return PTR_ERR(bufs); result = snd_pcm_lib_writev(substream, bufs, xfern.frames); kfree(bufs); __put_user(result, &_xfern->result); @@ -2675,13 +2663,11 @@ static int snd_pcm_capture_ioctl1(struct file *file, return -EFAULT; if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; - bufs = kmalloc(sizeof(void *) * runtime->channels, GFP_KERNEL); - if (bufs == NULL) - return -ENOMEM; - if (copy_from_user(bufs, xfern.bufs, sizeof(void *) * runtime->channels)) { - kfree(bufs); - return -EFAULT; - } + + bufs = memdup_user(xfern.bufs, + sizeof(void *) * runtime->channels); + if (IS_ERR(bufs)) + return PTR_ERR(bufs); result = snd_pcm_lib_readv(substream, bufs, xfern.frames); kfree(bufs); __put_user(result, &_xfern->result); @@ -3312,18 +3298,12 @@ static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, int err; params = kmalloc(sizeof(*params), GFP_KERNEL); - if (!params) { - err = -ENOMEM; - goto out; - } - oparams = kmalloc(sizeof(*oparams), GFP_KERNEL); - if (!oparams) { - err = -ENOMEM; - goto out; - } + if (!params) + return -ENOMEM; - if (copy_from_user(oparams, _oparams, sizeof(*oparams))) { - err = -EFAULT; + oparams = memdup_user(_oparams, sizeof(*oparams)); + if (IS_ERR(oparams)) { + err = PTR_ERR(oparams); goto out; } snd_pcm_hw_convert_from_old_params(params, oparams); @@ -3333,9 +3313,10 @@ static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, if (!err) err = -EFAULT; } + + kfree(oparams); out: kfree(params); - kfree(oparams); return err; } @@ -3347,17 +3328,12 @@ static int snd_pcm_hw_params_old_user(struct snd_pcm_substream *substream, int err; params = kmalloc(sizeof(*params), GFP_KERNEL); - if (!params) { - err = -ENOMEM; - goto out; - } - oparams = kmalloc(sizeof(*oparams), GFP_KERNEL); - if (!oparams) { - err = -ENOMEM; - goto out; - } - if (copy_from_user(oparams, _oparams, sizeof(*oparams))) { - err = -EFAULT; + if (!params) + return -ENOMEM; + + oparams = memdup_user(_oparams, sizeof(*oparams)); + if (IS_ERR(oparams)) { + err = PTR_ERR(oparams); goto out; } snd_pcm_hw_convert_from_old_params(params, oparams); @@ -3367,9 +3343,10 @@ static int snd_pcm_hw_params_old_user(struct snd_pcm_substream *substream, if (!err) err = -EFAULT; } + + kfree(oparams); out: kfree(params); - kfree(oparams); return err; } #endif /* CONFIG_SND_SUPPORT_OLD_API */ diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c index 38693f47c26..c956fe46256 100644 --- a/sound/core/seq/seq_compat.c +++ b/sound/core/seq/seq_compat.c @@ -48,12 +48,11 @@ static int snd_seq_call_port_info_ioctl(struct snd_seq_client *client, unsigned struct snd_seq_port_info *data; mm_segment_t fs; - data = kmalloc(sizeof(*data), GFP_KERNEL); - if (! data) - return -ENOMEM; + data = memdup_user(data32, sizeof(*data32)); + if (IS_ERR(data)) + return PTR_ERR(data); - if (copy_from_user(data, data32, sizeof(*data32)) || - get_user(data->flags, &data32->flags) || + if (get_user(data->flags, &data32->flags) || get_user(data->time_queue, &data32->time_queue)) goto error; data->kernel = NULL; diff --git a/sound/core/timer.c b/sound/core/timer.c index 3f0050d0b71..8f8b17ac074 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1395,13 +1395,10 @@ static int snd_timer_user_ginfo(struct file *file, struct list_head *p; int err = 0; - ginfo = kmalloc(sizeof(*ginfo), GFP_KERNEL); - if (! ginfo) - return -ENOMEM; - if (copy_from_user(ginfo, _ginfo, sizeof(*ginfo))) { - kfree(ginfo); - return -EFAULT; - } + ginfo = memdup_user(_ginfo, sizeof(*ginfo)); + if (IS_ERR(ginfo)) + return PTR_ERR(ginfo); + tid = ginfo->tid; memset(ginfo, 0, sizeof(*ginfo)); ginfo->tid = tid; diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c index 49037d074c7..bdc8dde4e4a 100644 --- a/sound/isa/sb/sb16_csp.c +++ b/sound/isa/sb/sb16_csp.c @@ -684,15 +684,16 @@ static int snd_sb_csp_load(struct snd_sb_csp * p, const unsigned char *buf, int static int snd_sb_csp_load_user(struct snd_sb_csp * p, const unsigned char __user *buf, int size, int load_flags) { - int err = -ENOMEM; - unsigned char *kbuf = kmalloc(size, GFP_KERNEL); - if (kbuf) { - if (copy_from_user(kbuf, buf, size)) - err = -EFAULT; - else - err = snd_sb_csp_load(p, kbuf, size, load_flags); - kfree(kbuf); - } + int err; + unsigned char *kbuf; + + kbuf = memdup_user(buf, size); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + err = snd_sb_csp_load(p, kbuf, size, load_flags); + + kfree(kbuf); return err; } diff --git a/sound/isa/wavefront/wavefront_fx.c b/sound/isa/wavefront/wavefront_fx.c index a4345fc0756..2bb1cee0925 100644 --- a/sound/isa/wavefront/wavefront_fx.c +++ b/sound/isa/wavefront/wavefront_fx.c @@ -202,15 +202,11 @@ snd_wavefront_fx_ioctl (struct snd_hwdep *sdev, struct file *file, "> 512 bytes to FX\n"); return -EIO; } - page_data = kmalloc(r.data[2] * sizeof(short), GFP_KERNEL); - if (!page_data) - return -ENOMEM; - if (copy_from_user (page_data, - (unsigned char __user *) r.data[3], - r.data[2] * sizeof(short))) { - kfree(page_data); - return -EFAULT; - } + page_data = memdup_user((unsigned char __user *) + r.data[3], + r.data[2] * sizeof(short)); + if (IS_ERR(page_data)) + return PTR_ERR(page_data); pd = page_data; } diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index beb312cca75..5d4ff48c434 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -1664,12 +1664,11 @@ snd_wavefront_synth_ioctl (struct snd_hwdep *hw, struct file *file, break; case WFCTL_WFCMD: - wc = kmalloc(sizeof(*wc), GFP_KERNEL); - if (! wc) - return -ENOMEM; - if (copy_from_user (wc, argp, sizeof (*wc))) - err = -EFAULT; - else if (wavefront_synth_control (acard, wc) < 0) + wc = memdup_user(argp, sizeof(*wc)); + if (IS_ERR(wc)) + return PTR_ERR(wc); + + if (wavefront_synth_control (acard, wc) < 0) err = -EIO; else if (copy_to_user (argp, wc, sizeof (*wc))) err = -EFAULT; diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index 191e1cd9997..4b302d86f5f 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -2493,24 +2493,17 @@ static int snd_emu10k1_fx8010_ioctl(struct snd_hwdep * hw, struct file *file, un case SNDRV_EMU10K1_IOCTL_CODE_POKE: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - icode = kmalloc(sizeof(*icode), GFP_KERNEL); - if (icode == NULL) - return -ENOMEM; - if (copy_from_user(icode, argp, sizeof(*icode))) { - kfree(icode); - return -EFAULT; - } + + icode = memdup_user(argp, sizeof(*icode)); + if (IS_ERR(icode)) + return PTR_ERR(icode); res = snd_emu10k1_icode_poke(emu, icode); kfree(icode); return res; case SNDRV_EMU10K1_IOCTL_CODE_PEEK: - icode = kmalloc(sizeof(*icode), GFP_KERNEL); - if (icode == NULL) - return -ENOMEM; - if (copy_from_user(icode, argp, sizeof(*icode))) { - kfree(icode); - return -EFAULT; - } + icode = memdup_user(argp, sizeof(*icode)); + if (IS_ERR(icode)) + return PTR_ERR(icode); res = snd_emu10k1_icode_peek(emu, icode); if (res == 0 && copy_to_user(argp, icode, sizeof(*icode))) { kfree(icode); @@ -2519,24 +2512,16 @@ static int snd_emu10k1_fx8010_ioctl(struct snd_hwdep * hw, struct file *file, un kfree(icode); return res; case SNDRV_EMU10K1_IOCTL_PCM_POKE: - ipcm = kmalloc(sizeof(*ipcm), GFP_KERNEL); - if (ipcm == NULL) - return -ENOMEM; - if (copy_from_user(ipcm, argp, sizeof(*ipcm))) { - kfree(ipcm); - return -EFAULT; - } + ipcm = memdup_user(argp, sizeof(*ipcm)); + if (IS_ERR(ipcm)) + return PTR_ERR(ipcm); res = snd_emu10k1_ipcm_poke(emu, ipcm); kfree(ipcm); return res; case SNDRV_EMU10K1_IOCTL_PCM_PEEK: - ipcm = kzalloc(sizeof(*ipcm), GFP_KERNEL); - if (ipcm == NULL) - return -ENOMEM; - if (copy_from_user(ipcm, argp, sizeof(*ipcm))) { - kfree(ipcm); - return -EFAULT; - } + ipcm = memdup_user(argp, sizeof(*ipcm)); + if (IS_ERR(ipcm)) + return PTR_ERR(ipcm); res = snd_emu10k1_ipcm_peek(emu, ipcm); if (res == 0 && copy_to_user(argp, ipcm, sizeof(*ipcm))) { kfree(ipcm); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index a4e5e595211..fd6e6f337d1 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2250,7 +2250,11 @@ int snd_hda_codec_write_cache(struct hda_codec *codec, hda_nid_t nid, err = bus->ops.command(bus, res); if (!err) { struct hda_cache_head *c; - u32 key = build_cmd_cache_key(nid, verb); + u32 key; + /* parm may contain the verb stuff for get/set amp */ + verb = verb | (parm >> 8); + parm &= 0xff; + key = build_cmd_cache_key(nid, verb); c = get_alloc_hash(&codec->cmd_cache, key); if (c) c->val = parm; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 30829ee920c..bc882f8f163 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -312,6 +312,9 @@ struct azx_dev { unsigned int period_bytes; /* size of the period in bytes */ unsigned int frags; /* number for period in the play buffer */ unsigned int fifo_size; /* FIFO size */ + unsigned int start_flag: 1; /* stream full start flag */ + unsigned long start_jiffies; /* start + minimum jiffies */ + unsigned long min_jiffies; /* minimum jiffies before position is valid */ void __iomem *sd_addr; /* stream descriptor pointer */ @@ -330,7 +333,6 @@ struct azx_dev { unsigned int opened :1; unsigned int running :1; unsigned int irq_pending :1; - unsigned int irq_ignore :1; /* * For VIA: * A flag to ensure DMA position is 0 @@ -975,7 +977,7 @@ static irqreturn_t azx_interrupt(int irq, void *dev_id) struct azx *chip = dev_id; struct azx_dev *azx_dev; u32 status; - int i; + int i, ok; spin_lock(&chip->reg_lock); @@ -991,18 +993,14 @@ static irqreturn_t azx_interrupt(int irq, void *dev_id) azx_sd_writeb(azx_dev, SD_STS, SD_INT_MASK); if (!azx_dev->substream || !azx_dev->running) continue; - /* ignore the first dummy IRQ (due to pos_adj) */ - if (azx_dev->irq_ignore) { - azx_dev->irq_ignore = 0; - continue; - } /* check whether this IRQ is really acceptable */ - if (azx_position_ok(chip, azx_dev)) { + ok = azx_position_ok(chip, azx_dev); + if (ok == 1) { azx_dev->irq_pending = 0; spin_unlock(&chip->reg_lock); snd_pcm_period_elapsed(azx_dev->substream); spin_lock(&chip->reg_lock); - } else if (chip->bus && chip->bus->workq) { + } else if (ok == 0 && chip->bus && chip->bus->workq) { /* bogus IRQ, process it later */ azx_dev->irq_pending = 1; queue_work(chip->bus->workq, @@ -1088,7 +1086,6 @@ static int azx_setup_periods(struct azx *chip, bdl = (u32 *)azx_dev->bdl.area; ofs = 0; azx_dev->frags = 0; - azx_dev->irq_ignore = 0; pos_adj = bdl_pos_adj[chip->dev_index]; if (pos_adj > 0) { struct snd_pcm_runtime *runtime = substream->runtime; @@ -1109,7 +1106,6 @@ static int azx_setup_periods(struct azx *chip, &bdl, ofs, pos_adj, 1); if (ofs < 0) goto error; - azx_dev->irq_ignore = 1; } } else pos_adj = 0; @@ -1155,6 +1151,9 @@ static void azx_stream_reset(struct azx *chip, struct azx_dev *azx_dev) while (((val = azx_sd_readb(azx_dev, SD_CTL)) & SD_CTL_STREAM_RESET) && --timeout) ; + + /* reset first position - may not be synced with hw at this time */ + *azx_dev->posbuf = 0; } /* @@ -1409,7 +1408,6 @@ static int azx_pcm_open(struct snd_pcm_substream *substream) snd_pcm_set_sync(substream); mutex_unlock(&chip->open_mutex); - azx_stream_reset(chip, azx_dev); return 0; } @@ -1474,6 +1472,7 @@ static int azx_pcm_prepare(struct snd_pcm_substream *substream) unsigned int bufsize, period_bytes, format_val; int err; + azx_stream_reset(chip, azx_dev); format_val = snd_hda_calc_stream_format(runtime->rate, runtime->channels, runtime->format, @@ -1502,6 +1501,8 @@ static int azx_pcm_prepare(struct snd_pcm_substream *substream) return err; } + azx_dev->min_jiffies = (runtime->period_size * HZ) / + (runtime->rate * 2); azx_setup_controller(chip, azx_dev); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) azx_dev->fifo_size = azx_sd_readw(azx_dev, SD_FIFOSIZE) + 1; @@ -1518,13 +1519,14 @@ static int azx_pcm_trigger(struct snd_pcm_substream *substream, int cmd) struct azx *chip = apcm->chip; struct azx_dev *azx_dev; struct snd_pcm_substream *s; - int start, nsync = 0, sbits = 0; + int rstart = 0, start, nsync = 0, sbits = 0; int nwait, timeout; switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + rstart = 1; case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: case SNDRV_PCM_TRIGGER_RESUME: - case SNDRV_PCM_TRIGGER_START: start = 1; break; case SNDRV_PCM_TRIGGER_PAUSE_PUSH: @@ -1554,6 +1556,10 @@ static int azx_pcm_trigger(struct snd_pcm_substream *substream, int cmd) if (s->pcm->card != substream->pcm->card) continue; azx_dev = get_azx_dev(s); + if (rstart) { + azx_dev->start_flag = 1; + azx_dev->start_jiffies = jiffies + azx_dev->min_jiffies; + } if (start) azx_stream_start(chip, azx_dev); else @@ -1703,6 +1709,11 @@ static int azx_position_ok(struct azx *chip, struct azx_dev *azx_dev) { unsigned int pos; + if (azx_dev->start_flag && + time_before_eq(jiffies, azx_dev->start_jiffies)) + return -1; /* bogus (too early) interrupt */ + azx_dev->start_flag = 0; + pos = azx_get_position(chip, azx_dev); if (chip->position_fix == POS_FIX_AUTO) { if (!pos) { @@ -2260,11 +2271,11 @@ static int __devinit azx_create(struct snd_card *card, struct pci_dev *pci, gcap &= ~0x01; /* allow 64bit DMA address if supported by H/W */ - if ((gcap & 0x01) && !pci_set_dma_mask(pci, DMA_64BIT_MASK)) - pci_set_consistent_dma_mask(pci, DMA_64BIT_MASK); + if ((gcap & 0x01) && !pci_set_dma_mask(pci, DMA_BIT_MASK(64))) + pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(64)); else { - pci_set_dma_mask(pci, DMA_32BIT_MASK); - pci_set_consistent_dma_mask(pci, DMA_32BIT_MASK); + pci_set_dma_mask(pci, DMA_BIT_MASK(32)); + pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(32)); } /* read number of streams from GCAP register instead of using diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 1f2ad76ca94..56ce19e68cb 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -350,12 +350,20 @@ static int conexant_mux_enum_put(struct snd_kcontrol *kcontrol, } #ifdef CONFIG_SND_JACK +static void conexant_free_jack_priv(struct snd_jack *jack) +{ + struct conexant_jack *jacks = jack->private_data; + jacks->nid = 0; + jacks->jack = NULL; +} + static int conexant_add_jack(struct hda_codec *codec, hda_nid_t nid, int type) { struct conexant_spec *spec; struct conexant_jack *jack; const char *name; + int err; spec = codec->spec; snd_array_init(&spec->jacks, sizeof(*jack), 32); @@ -368,7 +376,12 @@ static int conexant_add_jack(struct hda_codec *codec, jack->nid = nid; jack->type = type; - return snd_jack_new(codec->bus->card, name, type, &jack->jack); + err = snd_jack_new(codec->bus->card, name, type, &jack->jack); + if (err < 0) + return err; + jack->jack->private_data = jack; + jack->jack->private_free = conexant_free_jack_priv; + return 0; } static void conexant_report_jack(struct hda_codec *codec, hda_nid_t nid) @@ -455,8 +468,10 @@ static void conexant_free(struct hda_codec *codec) if (spec->jacks.list) { struct conexant_jack *jacks = spec->jacks.list; int i; - for (i = 0; i < spec->jacks.used; i++) - snd_device_free(codec->bus->card, &jacks[i].jack); + for (i = 0; i < spec->jacks.used; i++, jacks++) { + if (jacks->jack) + snd_device_free(codec->bus->card, jacks->jack); + } snd_array_free(&spec->jacks); } #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f35e58a2d92..6ed787eedd0 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8742,10 +8742,9 @@ static struct snd_pci_quirk alc883_cfg_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC883_LAPTOP_EAPD), SND_PCI_QUIRK(0x15d9, 0x8780, "Supermicro PDSBA", ALC883_3ST_6ch), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_MEDION), - SND_PCI_QUIRK(0x1734, 0x1107, "FSC AMILO Xi2550", + SND_PCI_QUIRK_MASK(0x1734, 0xfff0, 0x1100, "FSC AMILO Xi/Pi25xx", ALC883_FUJITSU_PI2515), - SND_PCI_QUIRK(0x1734, 0x1108, "Fujitsu AMILO Pi2515", ALC883_FUJITSU_PI2515), - SND_PCI_QUIRK(0x1734, 0x113d, "Fujitsu AMILO Xa3530", + SND_PCI_QUIRK_MASK(0x1734, 0xfff0, 0x1130, "Fujitsu AMILO Xa35xx", ALC888_FUJITSU_XA3530), SND_PCI_QUIRK(0x17aa, 0x101e, "Lenovo 101e", ALC883_LENOVO_101E_2ch), SND_PCI_QUIRK(0x17aa, 0x2085, "Lenovo NB0763", ALC883_LENOVO_NB0763), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 61996a2f45d..ce30b459aee 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -3851,6 +3851,15 @@ static void stac_gpio_set(struct hda_codec *codec, unsigned int mask, AC_VERB_SET_GPIO_DATA, gpiostate); /* sync */ } +#ifdef CONFIG_SND_JACK +static void stac92xx_free_jack_priv(struct snd_jack *jack) +{ + struct sigmatel_jack *jacks = jack->private_data; + jacks->nid = 0; + jacks->jack = NULL; +} +#endif + static int stac92xx_add_jack(struct hda_codec *codec, hda_nid_t nid, int type) { @@ -3860,6 +3869,7 @@ static int stac92xx_add_jack(struct hda_codec *codec, int def_conf = snd_hda_codec_get_pincfg(codec, nid); int connectivity = get_defcfg_connect(def_conf); char name[32]; + int err; if (connectivity && connectivity != AC_JACK_PORT_FIXED) return 0; @@ -3876,10 +3886,15 @@ static int stac92xx_add_jack(struct hda_codec *codec, snd_hda_get_jack_connectivity(def_conf), snd_hda_get_jack_location(def_conf)); - return snd_jack_new(codec->bus->card, name, type, &jack->jack); -#else - return 0; + err = snd_jack_new(codec->bus->card, name, type, &jack->jack); + if (err < 0) { + jack->nid = 0; + return err; + } + jack->jack->private_data = jack; + jack->jack->private_free = stac92xx_free_jack_priv; #endif + return 0; } static int stac_add_event(struct sigmatel_spec *spec, hda_nid_t nid, @@ -4138,8 +4153,10 @@ static void stac92xx_free_jacks(struct hda_codec *codec) if (!codec->bus->shutdown && spec->jacks.list) { struct sigmatel_jack *jacks = spec->jacks.list; int i; - for (i = 0; i < spec->jacks.used; i++) - snd_device_free(codec->bus->card, &jacks[i].jack); + for (i = 0; i < spec->jacks.used; i++, jacks++) { + if (jacks->jack) + snd_device_free(codec->bus->card, jacks->jack); + } } snd_array_free(&spec->jacks); #endif diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index 57648810eaf..5dced5b7938 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -355,6 +355,9 @@ struct ichdev { unsigned int fragsize1; unsigned int position; unsigned int pos_shift; + unsigned int last_pos; + unsigned long last_pos_jiffies; + unsigned int jiffy_to_bytes; int frags; int lvi; int lvi_frag; @@ -838,7 +841,10 @@ static int snd_intel8x0_pcm_trigger(struct snd_pcm_substream *substream, int cmd ichdev->suspended = 0; /* fallthru */ case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: val = ICH_IOCE | ICH_STARTBM; + ichdev->last_pos = ichdev->position; + ichdev->last_pos_jiffies = jiffies; break; case SNDRV_PCM_TRIGGER_SUSPEND: ichdev->suspended = 1; @@ -849,9 +855,6 @@ static int snd_intel8x0_pcm_trigger(struct snd_pcm_substream *substream, int cmd case SNDRV_PCM_TRIGGER_PAUSE_PUSH: val = ICH_IOCE; break; - case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - val = ICH_IOCE | ICH_STARTBM; - break; default: return -EINVAL; } @@ -1045,6 +1048,7 @@ static int snd_intel8x0_pcm_prepare(struct snd_pcm_substream *substream) ichdev->pos_shift = (runtime->sample_bits > 16) ? 2 : 1; } snd_intel8x0_setup_periods(chip, ichdev); + ichdev->jiffy_to_bytes = (runtime->rate * 4 * ichdev->pos_shift) / HZ; return 0; } @@ -1053,7 +1057,7 @@ static snd_pcm_uframes_t snd_intel8x0_pcm_pointer(struct snd_pcm_substream *subs struct intel8x0 *chip = snd_pcm_substream_chip(substream); struct ichdev *ichdev = get_ichdev(substream); size_t ptr1, ptr; - int civ, timeout = 100; + int civ, timeout = 10; unsigned int position; spin_lock(&chip->reg_lock); @@ -1069,9 +1073,19 @@ static snd_pcm_uframes_t snd_intel8x0_pcm_pointer(struct snd_pcm_substream *subs ptr1 == igetword(chip, ichdev->reg_offset + ichdev->roff_picb)) break; } while (timeout--); - ptr1 <<= ichdev->pos_shift; - ptr = ichdev->fragsize1 - ptr1; - ptr += position; + if (ptr1 != 0) { + ptr1 <<= ichdev->pos_shift; + ptr = ichdev->fragsize1 - ptr1; + ptr += position; + ichdev->last_pos = ptr; + ichdev->last_pos_jiffies = jiffies; + } else { + ptr1 = jiffies - ichdev->last_pos_jiffies; + if (ptr1) + ptr1 -= 1; + ptr = ichdev->last_pos + ptr1 * ichdev->jiffy_to_bytes; + ptr %= ichdev->size; + } spin_unlock(&chip->reg_lock); if (ptr >= ichdev->size) return 0; @@ -2661,12 +2675,14 @@ static void __devinit intel8x0_measure_ac97_clock(struct intel8x0 *chip) struct snd_pcm_substream *subs; struct ichdev *ichdev; unsigned long port; - unsigned long pos, t; - struct timeval start_time, stop_time; + unsigned long pos, pos1, t; + int civ, timeout = 1000, attempt = 1; + struct timespec start_time, stop_time; if (chip->ac97_bus->clock != 48000) return; /* specified in module option */ + __again: subs = chip->pcm[0]->streams[0].substream; if (! subs || subs->dma_buffer.bytes < INTEL8X0_TESTBUF_SIZE) { snd_printk(KERN_WARNING "no playback buffer allocated - aborting measure ac97 clock\n"); @@ -2674,7 +2690,7 @@ static void __devinit intel8x0_measure_ac97_clock(struct intel8x0 *chip) } ichdev = &chip->ichd[ICHD_PCMOUT]; ichdev->physbuf = subs->dma_buffer.addr; - ichdev->size = chip->ichd[ICHD_PCMOUT].fragsize = INTEL8X0_TESTBUF_SIZE; + ichdev->size = ichdev->fragsize = INTEL8X0_TESTBUF_SIZE; ichdev->substream = NULL; /* don't process interrupts */ /* set rate */ @@ -2693,16 +2709,31 @@ static void __devinit intel8x0_measure_ac97_clock(struct intel8x0 *chip) iputbyte(chip, port + ICH_REG_OFF_CR, ICH_IOCE); iputdword(chip, ICHREG(ALI_DMACR), 1 << ichdev->ali_slot); } - do_gettimeofday(&start_time); + do_posix_clock_monotonic_gettime(&start_time); spin_unlock_irq(&chip->reg_lock); msleep(50); spin_lock_irq(&chip->reg_lock); /* check the position */ - pos = ichdev->fragsize1; - pos -= igetword(chip, ichdev->reg_offset + ichdev->roff_picb) << ichdev->pos_shift; - pos += ichdev->position; + do { + civ = igetbyte(chip, ichdev->reg_offset + ICH_REG_OFF_CIV); + pos1 = igetword(chip, ichdev->reg_offset + ichdev->roff_picb); + if (pos1 == 0) { + udelay(10); + continue; + } + if (civ == igetbyte(chip, ichdev->reg_offset + ICH_REG_OFF_CIV) && + pos1 == igetword(chip, ichdev->reg_offset + ichdev->roff_picb)) + break; + } while (timeout--); + if (pos1 == 0) { /* oops, this value is not reliable */ + pos = 0; + } else { + pos = ichdev->fragsize1; + pos -= pos1 << ichdev->pos_shift; + pos += ichdev->position; + } chip->in_measurement = 0; - do_gettimeofday(&stop_time); + do_posix_clock_monotonic_gettime(&stop_time); /* stop */ if (chip->device_type == DEVICE_ALI) { iputdword(chip, ICHREG(ALI_DMACR), 1 << (ichdev->ali_slot + 16)); @@ -2717,19 +2748,37 @@ static void __devinit intel8x0_measure_ac97_clock(struct intel8x0 *chip) iputbyte(chip, port + ICH_REG_OFF_CR, ICH_RESETREGS); spin_unlock_irq(&chip->reg_lock); + if (pos == 0) { + snd_printk(KERN_ERR "intel8x0: measure - unreliable DMA position..\n"); + __retry: + if (attempt < 2) { + attempt++; + goto __again; + } + return; + } + + pos /= 4; t = stop_time.tv_sec - start_time.tv_sec; t *= 1000000; - t += stop_time.tv_usec - start_time.tv_usec; - printk(KERN_INFO "%s: measured %lu usecs\n", __func__, t); + t += (stop_time.tv_nsec - start_time.tv_nsec) / 1000; + printk(KERN_INFO "%s: measured %lu usecs (%lu samples)\n", __func__, t, pos); if (t == 0) { - snd_printk(KERN_ERR "?? calculation error..\n"); - return; + snd_printk(KERN_ERR "intel8x0: ?? calculation error..\n"); + goto __retry; } - pos = (pos / 4) * 1000; + pos *= 1000; pos = (pos / t) * 1000 + ((pos % t) * 1000) / t; - if (pos < 40000 || pos >= 60000) + if (pos < 40000 || pos >= 60000) { /* abnormal value. hw problem? */ printk(KERN_INFO "intel8x0: measured clock %ld rejected\n", pos); + goto __retry; + } else if (pos > 40500 && pos < 41500) + /* first exception - 41000Hz reference clock */ + chip->ac97_bus->clock = 41000; + else if (pos > 43600 && pos < 44600) + /* second exception - 44100HZ reference clock */ + chip->ac97_bus->clock = 44100; else if (pos < 47500 || pos > 48500) /* not 48000Hz, tuning the clock.. */ chip->ac97_bus->clock = (chip->ac97_bus->clock * 48000) / pos; diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c index f7c4544f785..0625c342a1c 100644 --- a/sound/soc/pxa/magician.c +++ b/sound/soc/pxa/magician.c @@ -27,8 +27,6 @@ #include <sound/soc.h> #include <sound/soc-dapm.h> -#include <mach/pxa-regs.h> -#include <mach/hardware.h> #include <mach/magician.h> #include <asm/mach-types.h> #include "../codecs/uda1380.h" diff --git a/sound/soc/s3c24xx/Kconfig b/sound/soc/s3c24xx/Kconfig index 2f3a21eee05..df494d1e346 100644 --- a/sound/soc/s3c24xx/Kconfig +++ b/sound/soc/s3c24xx/Kconfig @@ -1,10 +1,10 @@ config SND_S3C24XX_SOC tristate "SoC Audio for the Samsung S3CXXXX chips" - depends on ARCH_S3C2410 || ARCH_S3C64XX + depends on ARCH_S3C2410 help Say Y or M if you want to add support for codecs attached to - the S3C24XX and S3C64XX AC97, I2S or SSP interface. You will - also need to select the audio interfaces to support below. + the S3C24XX AC97 or I2S interfaces. You will also need to + select the audio interfaces to support below. config SND_S3C24XX_SOC_I2S tristate diff --git a/sound/usb/caiaq/Makefile b/sound/usb/caiaq/Makefile index 23dadd5a11c..388999653aa 100644 --- a/sound/usb/caiaq/Makefile +++ b/sound/usb/caiaq/Makefile @@ -1,4 +1,4 @@ -snd-usb-caiaq-y := caiaq-device.o caiaq-audio.o caiaq-midi.o caiaq-control.o -snd-usb-caiaq-$(CONFIG_SND_USB_CAIAQ_INPUT) += caiaq-input.o +snd-usb-caiaq-y := device.o audio.o midi.o control.o +snd-usb-caiaq-$(CONFIG_SND_USB_CAIAQ_INPUT) += input.o obj-$(CONFIG_SND_USB_CAIAQ) += snd-usb-caiaq.o diff --git a/sound/usb/caiaq/caiaq-audio.c b/sound/usb/caiaq/audio.c index 08d51e0c9fe..3f45c0fe61a 100644 --- a/sound/usb/caiaq/caiaq-audio.c +++ b/sound/usb/caiaq/audio.c @@ -16,20 +16,14 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/spinlock.h> #include <linux/init.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/interrupt.h> #include <linux/usb.h> -#include <linux/spinlock.h> #include <sound/core.h> -#include <sound/initval.h> #include <sound/pcm.h> -#include <sound/rawmidi.h> -#include <linux/input.h> -#include "caiaq-device.h" -#include "caiaq-audio.h" +#include "device.h" +#include "audio.h" #define N_URBS 32 #define CLOCK_DRIFT_TOLERANCE 5 diff --git a/sound/usb/caiaq/caiaq-audio.h b/sound/usb/caiaq/audio.h index 8ab1f8d9529..8ab1f8d9529 100644 --- a/sound/usb/caiaq/caiaq-audio.h +++ b/sound/usb/caiaq/audio.h diff --git a/sound/usb/caiaq/caiaq-control.c b/sound/usb/caiaq/control.c index e92c2bbf4fe..537102ba6b9 100644 --- a/sound/usb/caiaq/caiaq-control.c +++ b/sound/usb/caiaq/control.c @@ -18,17 +18,13 @@ */ #include <linux/init.h> -#include <linux/interrupt.h> #include <linux/usb.h> +#include <sound/control.h> #include <sound/core.h> -#include <sound/initval.h> #include <sound/pcm.h> -#include <sound/rawmidi.h> -#include <sound/control.h> -#include <linux/input.h> -#include "caiaq-device.h" -#include "caiaq-control.h" +#include "device.h" +#include "control.h" #define CNT_INTVAL 0x10000 diff --git a/sound/usb/caiaq/caiaq-control.h b/sound/usb/caiaq/control.h index 2e7ab1aa4fb..2e7ab1aa4fb 100644 --- a/sound/usb/caiaq/caiaq-control.h +++ b/sound/usb/caiaq/control.h diff --git a/sound/usb/caiaq/caiaq-device.c b/sound/usb/caiaq/device.c index cf573a982fd..6d517705da0 100644 --- a/sound/usb/caiaq/caiaq-device.c +++ b/sound/usb/caiaq/device.c @@ -19,27 +19,20 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/init.h> -#include <linux/module.h> #include <linux/moduleparam.h> #include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/init.h> #include <linux/usb.h> -#include <linux/input.h> -#include <linux/spinlock.h> -#include <sound/core.h> #include <sound/initval.h> +#include <sound/core.h> #include <sound/pcm.h> -#include <sound/rawmidi.h> -#include <sound/control.h> - -#include "caiaq-device.h" -#include "caiaq-audio.h" -#include "caiaq-midi.h" -#include "caiaq-control.h" -#ifdef CONFIG_SND_USB_CAIAQ_INPUT -#include "caiaq-input.h" -#endif +#include "device.h" +#include "audio.h" +#include "midi.h" +#include "control.h" +#include "input.h" MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>"); MODULE_DESCRIPTION("caiaq USB audio, version 1.3.13"); diff --git a/sound/usb/caiaq/caiaq-device.h b/sound/usb/caiaq/device.h index 4cce1ad7493..4cce1ad7493 100644 --- a/sound/usb/caiaq/caiaq-device.h +++ b/sound/usb/caiaq/device.h diff --git a/sound/usb/caiaq/caiaq-input.c b/sound/usb/caiaq/input.c index f743847a5e5..a48d309bd94 100644 --- a/sound/usb/caiaq/caiaq-input.c +++ b/sound/usb/caiaq/input.c @@ -17,17 +17,12 @@ */ #include <linux/init.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/input.h> #include <linux/usb.h> #include <linux/usb/input.h> -#include <linux/spinlock.h> -#include <sound/core.h> -#include <sound/rawmidi.h> #include <sound/pcm.h> -#include "caiaq-device.h" -#include "caiaq-input.h" + +#include "device.h" +#include "input.h" static unsigned short keycode_ak1[] = { KEY_C, KEY_B, KEY_A }; static unsigned short keycode_rk2[] = { KEY_1, KEY_2, KEY_3, KEY_4, diff --git a/sound/usb/caiaq/caiaq-input.h b/sound/usb/caiaq/input.h index ced53557786..ced53557786 100644 --- a/sound/usb/caiaq/caiaq-input.h +++ b/sound/usb/caiaq/input.h diff --git a/sound/usb/caiaq/caiaq-midi.c b/sound/usb/caiaq/midi.c index f19fd360c93..8fa8cd88d76 100644 --- a/sound/usb/caiaq/caiaq-midi.c +++ b/sound/usb/caiaq/midi.c @@ -16,20 +16,13 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/init.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/interrupt.h> #include <linux/usb.h> -#include <linux/input.h> -#include <linux/spinlock.h> -#include <sound/core.h> #include <sound/rawmidi.h> +#include <sound/core.h> #include <sound/pcm.h> -#include "caiaq-device.h" -#include "caiaq-midi.h" - +#include "device.h" +#include "midi.h" static int snd_usb_caiaq_midi_input_open(struct snd_rawmidi_substream *substream) { diff --git a/sound/usb/caiaq/caiaq-midi.h b/sound/usb/caiaq/midi.h index 9d16db027fc..9d16db027fc 100644 --- a/sound/usb/caiaq/caiaq-midi.h +++ b/sound/usb/caiaq/midi.h diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index 98276aafefe..012ff1f6f8a 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -349,14 +349,10 @@ static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file, if (cmd != SNDRV_USB_STREAM_IOCTL_SET_PARAMS) return -ENOTTY; - cfg = kmalloc(sizeof(*cfg), GFP_KERNEL); - if (!cfg) - return -ENOMEM; + cfg = memdup_user((void *)arg, sizeof(*cfg)); + if (IS_ERR(cfg)) + return PTR_ERR(cfg); - if (copy_from_user(cfg, (void *)arg, sizeof(*cfg))) { - err = -EFAULT; - goto free; - } if (cfg->version != USB_STREAM_INTERFACE_VERSION) { err = -ENXIO; goto free; diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index 4af8740db71..f3d8f71265d 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -203,13 +203,12 @@ static int snd_usX2Y_hwdep_dsp_load(struct snd_hwdep *hw, if (access_ok(VERIFY_READ, dsp->image, dsp->length)) { struct usb_device* dev = priv->chip.dev; - char *buf = kmalloc(dsp->length, GFP_KERNEL); - if (!buf) - return -ENOMEM; - if (copy_from_user(buf, dsp->image, dsp->length)) { - kfree(buf); - return -EFAULT; - } + char *buf; + + buf = memdup_user(dsp->image, dsp->length); + if (IS_ERR(buf)) + return PTR_ERR(buf); + err = usb_set_interface(dev, 0, 1); if (err) snd_printk(KERN_ERR "usb_set_interface error \n"); |