diff options
205 files changed, 6251 insertions, 2032 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/DocBook/Makefile b/Documentation/DocBook/Makefile index a3a83d38f96..8918a32c6b3 100644 --- a/Documentation/DocBook/Makefile +++ b/Documentation/DocBook/Makefile @@ -31,7 +31,7 @@ PS_METHOD = $(prefer-db2x) ### # The targets that may be used. -PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs +PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs BOOKS := $(addprefix $(obj)/,$(DOCBOOKS)) xmldocs: $(BOOKS) @@ -213,11 +213,12 @@ silent_gen_xml = : dochelp: @echo ' Linux kernel internal documentation in different formats:' @echo ' htmldocs - HTML' - @echo ' installmandocs - install man pages generated by mandocs' - @echo ' mandocs - man pages' @echo ' pdfdocs - PDF' @echo ' psdocs - Postscript' @echo ' xmldocs - XML DocBook' + @echo ' mandocs - man pages' + @echo ' installmandocs - install man pages generated by mandocs' + @echo ' cleandocs - clean all generated DocBook files' ### # Temporary files left by various tools @@ -235,6 +236,10 @@ clean-files := $(DOCBOOKS) \ clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man +cleandocs: + $(Q)rm -f $(call objectify, $(clean-files)) + $(Q)rm -rf $(call objectify, $(clean-dirs)) + # Declare the contents of the .PHONY variable as phony. We keep that # information in a variable se we can use it in if_changed and friends. 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/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt new file mode 100644 index 00000000000..435102a26d9 --- /dev/null +++ b/Documentation/input/rotary-encoder.txt @@ -0,0 +1,101 @@ +rotary-encoder - a generic driver for GPIO connected devices +Daniel Mack <daniel@caiaq.de>, Feb 2009 + +0. Function +----------- + +Rotary encoders are devices which are connected to the CPU or other +peripherals with two wires. The outputs are phase-shifted by 90 degrees +and by triggering on falling and rising edges, the turn direction can +be determined. + +The phase diagram of these two outputs look like this: + + _____ _____ _____ + | | | | | | + Channel A ____| |_____| |_____| |____ + + : : : : : : : : : : : : + __ _____ _____ _____ + | | | | | | | + Channel B |_____| |_____| |_____| |__ + + : : : : : : : : : : : : + Event a b c d a b c d a b c d + + |<-------->| + one step + + +For more information, please see + http://en.wikipedia.org/wiki/Rotary_encoder + + +1. Events / state machine +------------------------- + +a) Rising edge on channel A, channel B in low state + This state is used to recognize a clockwise turn + +b) Rising edge on channel B, channel A in high state + When entering this state, the encoder is put into 'armed' state, + meaning that there it has seen half the way of a one-step transition. + +c) Falling edge on channel A, channel B in high state + This state is used to recognize a counter-clockwise turn + +d) Falling edge on channel B, channel A in low state + Parking position. If the encoder enters this state, a full transition + should have happend, unless it flipped back on half the way. The + 'armed' state tells us about that. + +2. Platform requirements +------------------------ + +As there is no hardware dependent call in this driver, the platform it is +used with must support gpiolib. Another requirement is that IRQs must be +able to fire on both edges. + + +3. Board integration +-------------------- + +To use this driver in your system, register a platform_device with the +name 'rotary-encoder' and associate the IRQs and some specific platform +data with it. + +struct rotary_encoder_platform_data is declared in +include/linux/rotary-encoder.h and needs to be filled with the number of +steps the encoder has and can carry information about externally inverted +signals (because of used invertig buffer or other reasons). + +Because GPIO to IRQ mapping is platform specific, this information must +be given in seperately to the driver. See the example below. + +---------<snip>--------- + +/* board support file example */ + +#include <linux/input.h> +#include <linux/rotary_encoder.h> + +#define GPIO_ROTARY_A 1 +#define GPIO_ROTARY_B 2 + +static struct rotary_encoder_platform_data my_rotary_encoder_info = { + .steps = 24, + .axis = ABS_X, + .gpio_a = GPIO_ROTARY_A, + .gpio_b = GPIO_ROTARY_B, + .inverted_a = 0, + .inverted_b = 0, +}; + +static struct platform_device rotary_encoder_device = { + .name = "rotary-encoder", + .id = 0, + .dev = { + .platform_data = &my_rotary_encoder_info, + } +}; + diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index 51104f9194a..d4b05672f9f 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -40,10 +40,16 @@ This document describes the Linux kernel Makefiles. --- 6.7 Custom kbuild commands --- 6.8 Preprocessing linker scripts - === 7 Kbuild Variables - === 8 Makefile language - === 9 Credits - === 10 TODO + === 7 Kbuild syntax for exported headers + --- 7.1 header-y + --- 7.2 objhdr-y + --- 7.3 destination-y + --- 7.4 unifdef-y (deprecated) + + === 8 Kbuild Variables + === 9 Makefile language + === 10 Credits + === 11 TODO === 1 Overview @@ -1143,8 +1149,69 @@ When kbuild executes, the following steps are followed (roughly): The kbuild infrastructure for *lds file are used in several architecture-specific files. +=== 7 Kbuild syntax for exported headers + +The kernel include a set of headers that is exported to userspace. +Many headers can be exported as-is but other headers requires a +minimal pre-processing before they are ready for user-space. +The pre-processing does: +- drop kernel specific annotations +- drop include of compiler.h +- drop all sections that is kernel internat (guarded by ifdef __KERNEL__) + +Each relevant directory contain a file name "Kbuild" which specify the +headers to be exported. +See subsequent chapter for the syntax of the Kbuild file. + + --- 7.1 header-y + + header-y specify header files to be exported. + + Example: + #include/linux/Kbuild + header-y += usb/ + header-y += aio_abi.h + + The convention is to list one file per line and + preferably in alphabetic order. + + header-y also specify which subdirectories to visit. + A subdirectory is identified by a trailing '/' which + can be seen in the example above for the usb subdirectory. + + Subdirectories are visited before their parent directories. + + --- 7.2 objhdr-y + + objhdr-y specifies generated files to be exported. + Generated files are special as they need to be looked + up in another directory when doing 'make O=...' builds. + + Example: + #include/linux/Kbuild + objhdr-y += version.h + + --- 7.3 destination-y + + When an architecture have a set of exported headers that needs to be + exported to a different directory destination-y is used. + destination-y specify the destination directory for all exported + headers in the file where it is present. + + Example: + #arch/xtensa/platforms/s6105/include/platform/Kbuild + destination-y := include/linux + + In the example above all exported headers in the Kbuild file + will be located in the directory "include/linux" when exported. + + + --- 7.4 unifdef-y (deprecated) + + unifdef-y is deprecated. A direct replacement is header-y. + -=== 7 Kbuild Variables +=== 8 Kbuild Variables The top Makefile exports the following variables: @@ -1206,7 +1273,7 @@ The top Makefile exports the following variables: INSTALL_MOD_STRIP will used as the option(s) to the strip command. -=== 8 Makefile language +=== 9 Makefile language The kernel Makefiles are designed to be run with GNU Make. The Makefiles use only the documented features of GNU Make, but they do use many @@ -1225,14 +1292,14 @@ time the left-hand side is used. There are some cases where "=" is appropriate. Usually, though, ":=" is the right choice. -=== 9 Credits +=== 10 Credits Original version made by Michael Elizabeth Chastain, <mailto:mec@shout.net> Updates by Kai Germaschewski <kai@tp1.ruhr-uni-bochum.de> Updates by Sam Ravnborg <sam@ravnborg.org> Language QA by Jan Engelhardt <jengelh@gmx.de> -=== 10 TODO +=== 11 TODO - Describe how kbuild supports shipped files with _shipped. - Generating offset header files. diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt index 42f43fa59f2..34c76a55bc0 100644 --- a/Documentation/sparse.txt +++ b/Documentation/sparse.txt @@ -42,6 +42,14 @@ sure that bitwise types don't get mixed up (little-endian vs big-endian vs cpu-endian vs whatever), and there the constant "0" really _is_ special. +__bitwise__ - to be used for relatively compact stuff (gfp_t, etc.) that +is mostly warning-free and is supposed to stay that way. Warnings will +be generated without __CHECK_ENDIAN__. + +__bitwise - noisy stuff; in particular, __le*/__be* are that. We really +don't want to drown in noise unless we'd explicitly asked for it. + + Getting sparse ~~~~~~~~~~~~~~ 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 782ea4f0ca2..0cb20d82169 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 @@ -4979,8 +4979,8 @@ 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/ @@ -5314,7 +5314,9 @@ 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 @@ -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) @@ -567,7 +572,7 @@ KBUILD_CFLAGS += $(call cc-option,-Wdeclaration-after-statement,) # disable pointer signed / unsigned warnings in gcc 4.0 KBUILD_CFLAGS += $(call cc-option,-Wno-pointer-sign,) -# disable invalid "can't wrap" optimzations for signed / pointers +# disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fwrapv) # revert to pre-gcc-4.4 behaviour of .eh_frame @@ -597,6 +602,10 @@ LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\ LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID) LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID) +ifeq ($(CONFIG_STRIP_ASM_SYMS),y) +LDFLAGS_vmlinux += -X +endif + # Default kernel image to build when no specific target is given. # KBUILD_IMAGE may be overruled on the command line or # set in the environment @@ -1587,5 +1596,5 @@ PHONY += FORCE FORCE: # Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. +# information in a variable so we can use it in if_changed and friends. .PHONY: $(PHONY) 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/mips/include/asm/mach-rc32434/gpio.h b/arch/mips/include/asm/mach-rc32434/gpio.h index 3cb50d17b62..12ee8d51016 100644 --- a/arch/mips/include/asm/mach-rc32434/gpio.h +++ b/arch/mips/include/asm/mach-rc32434/gpio.h @@ -80,6 +80,9 @@ struct rb532_gpio_reg { /* Compact Flash GPIO pin */ #define CF_GPIO_NUM 13 +/* S1 button GPIO (shared with UART0_SIN) */ +#define GPIO_BTN_S1 1 + extern void rb532_gpio_set_ilevel(int bit, unsigned gpio); extern void rb532_gpio_set_istat(int bit, unsigned gpio); extern void rb532_gpio_set_func(unsigned gpio); diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c index 4a5f05b662a..9f40e1ff9b4 100644 --- a/arch/mips/rb532/devices.c +++ b/arch/mips/rb532/devices.c @@ -200,26 +200,9 @@ static struct platform_device rb532_led = { .id = -1, }; -static struct gpio_keys_button rb532_gpio_btn[] = { - { - .gpio = 1, - .code = BTN_0, - .desc = "S1", - .active_low = 1, - } -}; - -static struct gpio_keys_platform_data rb532_gpio_btn_data = { - .buttons = rb532_gpio_btn, - .nbuttons = ARRAY_SIZE(rb532_gpio_btn), -}; - static struct platform_device rb532_button = { - .name = "gpio-keys", + .name = "rb532-button", .id = -1, - .dev = { - .platform_data = &rb532_gpio_btn_data, - } }; static struct resource rb532_wdt_res[] = { 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/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/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/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e5383e3d2f8..73739322b6d 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -193,8 +193,10 @@ extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); */ extern void early_ioremap_init(void); extern void early_ioremap_reset(void); -extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); -extern void __iomem *early_memremap(unsigned long offset, unsigned long size); +extern void __iomem *early_ioremap(resource_size_t phys_addr, + unsigned long size); +extern void __iomem *early_memremap(resource_size_t phys_addr, + unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 34c52370f2f..fcf4d92e7e0 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -352,6 +352,11 @@ struct i387_soft_struct { u32 entry_eip; }; +struct ymmh_struct { + /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ + u32 ymmh_space[64]; +}; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -361,6 +366,7 @@ struct xsave_hdr_struct { struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; + struct ymmh_struct ymmh; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); 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/sigcontext.h b/arch/x86/include/asm/sigcontext.h index ec666491aaa..72e5a449166 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -269,6 +269,11 @@ struct _xsave_hdr { __u64 reserved2[5]; }; +struct _ymmh_state { + /* 16 * 16 bytes for each YMMH-reg */ + __u32 ymmh_space[64]; +}; + /* * Extended state pointed by the fpstate pointer in the sigcontext. * In addition to the fpstate, information encoded in the xstate_hdr @@ -278,6 +283,7 @@ struct _xsave_hdr { struct _xstate { struct _fpstate fpstate; struct _xsave_hdr xstate_hdr; + struct _ymmh_state ymmh; /* new processor state extensions go here */ }; 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/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 08e9a1ac07a..727acc15234 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -7,6 +7,7 @@ #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -15,7 +16,7 @@ /* * These are the features that the OS can handle currently. */ -#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE) +#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 767fe7e46d6..a2789e42e16 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2524,7 +2524,6 @@ static void irq_complete_move(struct irq_desc **descp) static inline void irq_complete_move(struct irq_desc **descp) {} #endif -#ifdef CONFIG_X86_X2APIC static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { int apic, pin; @@ -2558,6 +2557,7 @@ eoi_ioapic_irq(struct irq_desc *desc) spin_unlock_irqrestore(&ioapic_lock, flags); } +#ifdef CONFIG_X86_X2APIC static void ack_x2apic_level(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -2634,6 +2634,9 @@ static void ack_apic_level(unsigned int irq) */ ack_APIC_irq(); + if (irq_remapped(irq)) + eoi_ioapic_irq(desc); + /* Now we can move and renable the irq */ if (unlikely(do_unmask_irq)) { /* Only migrate the irq if the ack has been received. diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 9d3af380c6b..837c2c4cc20 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -153,7 +153,8 @@ struct drv_cmd { u32 val; }; -static long do_drv_read(void *_cmd) +/* Called via smp_call_function_single(), on the target CPU */ +static void do_drv_read(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 h; @@ -170,10 +171,10 @@ static long do_drv_read(void *_cmd) default: break; } - return 0; } -static long do_drv_write(void *_cmd) +/* Called via smp_call_function_many(), on the target CPUs */ +static void do_drv_write(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 lo, hi; @@ -192,23 +193,18 @@ static long do_drv_write(void *_cmd) default: break; } - return 0; } static void drv_read(struct drv_cmd *cmd) { cmd->val = 0; - work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd); + smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); } static void drv_write(struct drv_cmd *cmd) { - unsigned int i; - - for_each_cpu(i, cmd->mask) { - work_on_cpu(i, do_drv_write, cmd); - } + smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); } static u32 get_cur_val(const struct cpumask *mask) @@ -252,15 +248,13 @@ struct perf_pair { } aperf, mperf; }; - -static long read_measured_perf_ctrs(void *_cur) +/* Called via smp_call_function_single(), on the target CPU */ +static void read_measured_perf_ctrs(void *_cur) { struct perf_pair *cur = _cur; rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi); rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi); - - return 0; } /* @@ -283,7 +277,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int perf_percent; unsigned int retval; - if (!work_on_cpu(cpu, read_measured_perf_ctrs, &readin)) + 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/mpparse.c b/arch/x86/kernel/mpparse.c index dce99dca6cf..70fd7e414c1 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -679,7 +679,7 @@ void __init get_smp_config(void) __get_smp_config(0); } -static void smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_bootmem(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); #ifdef CONFIG_X86_32 @@ -838,7 +838,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m) static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; -static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) +static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) { int i; @@ -866,7 +866,8 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) } } #else /* CONFIG_X86_IO_APIC */ -static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +static +inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} #endif /* CONFIG_X86_IO_APIC */ static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 2b54fe002e9..0a5b04aa98f 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -324,7 +324,7 @@ void __ref xsave_cntxt_init(void) } /* - * for now OS knows only about FP/SSE + * Support only the state known to OS. */ pcntxt_mask = pcntxt_mask & XCNTXT_MASK; xsave_init(); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index be54176e9eb..6340cef6798 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -219,6 +219,22 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +/** + * 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 get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0dfa09d69e8..09daebfdb11 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -547,7 +547,7 @@ void __init early_ioremap_reset(void) } static void __init __early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; @@ -566,7 +566,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, } static inline void __init early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot) { if (after_paging_init) __set_fixmap(idx, phys, prot); @@ -607,9 +607,10 @@ static int __init check_early_ioremap_leak(void) late_initcall(check_early_ioremap_leak); static void __init __iomem * -__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) { - unsigned long offset, last_addr; + unsigned long offset; + resource_size_t last_addr; unsigned int nrpages; enum fixed_addresses idx0, idx; int i, slot; @@ -625,15 +626,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } if (slot < 0) { - printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n", - phys_addr, size); + printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n", + (u64)phys_addr, size); WARN_ON(1); return NULL; } if (early_ioremap_debug) { - printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ", - phys_addr, size, slot); + printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ", + (u64)phys_addr, size, slot); dump_stack(); } @@ -680,13 +681,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } /* Remap an IO device */ -void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); } /* Remap memory */ -void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_memremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL); } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339ee4fb..c009a241d56 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,7 +31,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(const char *reason) +static inline void pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); 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/drivers/ata/ahci.c b/drivers/ata/ahci.c index 57be6bea48e..08186ecbaf8 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -114,6 +114,7 @@ enum { board_ahci_sb700 = 5, /* for SB700 and SB800 */ board_ahci_mcp65 = 6, board_ahci_nopmp = 7, + board_ahci_yesncq = 8, /* global controller registers */ HOST_CAP = 0x00, /* host capabilities */ @@ -469,6 +470,14 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + /* board_ahci_yesncq */ + { + AHCI_HFLAGS (AHCI_HFLAG_YES_NCQ), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, }; static const struct pci_device_id ahci_pci_tbl[] = { @@ -535,30 +544,30 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(NVIDIA, 0x045d), board_ahci_mcp65 }, /* MCP65 */ { PCI_VDEVICE(NVIDIA, 0x045e), board_ahci_mcp65 }, /* MCP65 */ { PCI_VDEVICE(NVIDIA, 0x045f), board_ahci_mcp65 }, /* MCP65 */ - { PCI_VDEVICE(NVIDIA, 0x0550), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0551), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0552), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0553), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0554), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0555), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0556), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0557), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0558), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x0559), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x055a), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x055b), board_ahci }, /* MCP67 */ - { PCI_VDEVICE(NVIDIA, 0x07f0), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f1), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f2), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f3), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f4), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f5), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f6), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f7), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f8), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07f9), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07fa), board_ahci }, /* MCP73 */ - { PCI_VDEVICE(NVIDIA, 0x07fb), board_ahci }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x0550), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0551), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0552), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0553), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0554), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0555), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0556), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0557), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0558), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x0559), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x055a), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x055b), board_ahci_yesncq }, /* MCP67 */ + { PCI_VDEVICE(NVIDIA, 0x07f0), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f1), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f2), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f3), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f4), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f5), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f6), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f7), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f8), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07f9), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07fa), board_ahci_yesncq }, /* MCP73 */ + { PCI_VDEVICE(NVIDIA, 0x07fb), board_ahci_yesncq }, /* MCP73 */ { PCI_VDEVICE(NVIDIA, 0x0ad0), board_ahci }, /* MCP77 */ { PCI_VDEVICE(NVIDIA, 0x0ad1), board_ahci }, /* MCP77 */ { PCI_VDEVICE(NVIDIA, 0x0ad2), board_ahci }, /* MCP77 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e7ea77cf606..065507c4664 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6110,13 +6110,11 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) ata_port_printk(ap, KERN_INFO, "DUMMY\n"); } - /* perform each probe synchronously */ - DPRINTK("probe begin\n"); + /* perform each probe asynchronously */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; async_schedule(async_port_probe, ap); } - DPRINTK("probe end\n"); return 0; } diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c index 98e8c50703b..bdd43c7f432 100644 --- a/drivers/ata/sata_via.c +++ b/drivers/ata/sata_via.c @@ -566,7 +566,7 @@ static int svia_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) static int printed_version; unsigned int i; int rc; - struct ata_host *host; + struct ata_host *host = NULL; int board_id = (int) ent->driver_data; const unsigned *bar_sizes; 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/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/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/input/input.c b/drivers/input/input.c index ec3db3ade11..d44065d2e66 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -132,6 +132,11 @@ static void input_start_autorepeat(struct input_dev *dev, int code) } } +static void input_stop_autorepeat(struct input_dev *dev) +{ + del_timer(&dev->timer); +} + #define INPUT_IGNORE_EVENT 0 #define INPUT_PASS_TO_HANDLERS 1 #define INPUT_PASS_TO_DEVICE 2 @@ -167,6 +172,8 @@ static void input_handle_event(struct input_dev *dev, __change_bit(code, dev->key); if (value) input_start_autorepeat(dev, code); + else + input_stop_autorepeat(dev); } disposition = INPUT_PASS_TO_HANDLERS; @@ -737,11 +744,11 @@ static inline void input_wakeup_procfs_readers(void) static unsigned int input_proc_devices_poll(struct file *file, poll_table *wait) { - int state = input_devices_state; - poll_wait(file, &input_devices_poll_wait, wait); - if (state != input_devices_state) + if (file->f_version != input_devices_state) { + file->f_version = input_devices_state; return POLLIN | POLLRDNORM; + } return 0; } diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 45470f18d7e..f999dc60c3b 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -229,7 +229,8 @@ struct atkbd { /* * System-specific ketymap fixup routine */ -static void (*atkbd_platform_fixup)(struct atkbd *); +static void (*atkbd_platform_fixup)(struct atkbd *, const void *data); +static void *atkbd_platform_fixup_data; static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf, ssize_t (*handler)(struct atkbd *, char *)); @@ -834,87 +835,64 @@ static void atkbd_disconnect(struct serio *serio) } /* - * Most special keys (Fn+F?) on Dell laptops do not generate release - * events so we have to do it ourselves. + * generate release events for the keycodes given in data */ -static void atkbd_dell_laptop_keymap_fixup(struct atkbd *atkbd) +static void atkbd_apply_forced_release_keylist(struct atkbd* atkbd, + const void *data) { - static const unsigned int forced_release_keys[] = { - 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8f, 0x93, - }; - int i; + const unsigned int *keys = data; + unsigned int i; if (atkbd->set == 2) - for (i = 0; i < ARRAY_SIZE(forced_release_keys); i++) - __set_bit(forced_release_keys[i], - atkbd->force_release_mask); + for (i = 0; keys[i] != -1U; i++) + __set_bit(keys[i], atkbd->force_release_mask); } /* + * Most special keys (Fn+F?) on Dell laptops do not generate release + * events so we have to do it ourselves. + */ +static unsigned int atkbd_dell_laptop_forced_release_keys[] = { + 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8f, 0x93, -1U +}; + +/* * Perform fixup for HP system that doesn't generate release * for its video switch */ -static void atkbd_hp_keymap_fixup(struct atkbd *atkbd) -{ - static const unsigned int forced_release_keys[] = { - 0x94, - }; - int i; - - if (atkbd->set == 2) - for (i = 0; i < ARRAY_SIZE(forced_release_keys); i++) - __set_bit(forced_release_keys[i], - atkbd->force_release_mask); -} +static unsigned int atkbd_hp_forced_release_keys[] = { + 0x94, -1U +}; /* * Inventec system with broken key release on volume keys */ -static void atkbd_inventec_keymap_fixup(struct atkbd *atkbd) -{ - const unsigned int forced_release_keys[] = { - 0xae, 0xb0, - }; - int i; - - if (atkbd->set == 2) - for (i = 0; i < ARRAY_SIZE(forced_release_keys); i++) - __set_bit(forced_release_keys[i], - atkbd->force_release_mask); -} +static unsigned int atkbd_inventec_forced_release_keys[] = { + 0xae, 0xb0, -1U +}; /* * Perform fixup for HP Pavilion ZV6100 laptop that doesn't generate release * for its volume buttons */ -static void atkbd_hp_zv6100_keymap_fixup(struct atkbd *atkbd) -{ - const unsigned int forced_release_keys[] = { - 0xae, 0xb0, - }; - int i; - - if (atkbd->set == 2) - for (i = 0; i < ARRAY_SIZE(forced_release_keys); i++) - __set_bit(forced_release_keys[i], - atkbd->force_release_mask); -} +static unsigned int atkbd_hp_zv6100_forced_release_keys[] = { + 0xae, 0xb0, -1U +}; /* * Samsung NC10 with Fn+F? key release not working */ -static void atkbd_samsung_keymap_fixup(struct atkbd *atkbd) -{ - const unsigned int forced_release_keys[] = { - 0x82, 0x83, 0x84, 0x86, 0x88, 0x89, 0xb3, 0xf7, 0xf9, - }; - int i; +static unsigned int atkbd_samsung_forced_release_keys[] = { + 0x82, 0x83, 0x84, 0x86, 0x88, 0x89, 0xb3, 0xf7, 0xf9, -1U +}; - if (atkbd->set == 2) - for (i = 0; i < ARRAY_SIZE(forced_release_keys); i++) - __set_bit(forced_release_keys[i], - atkbd->force_release_mask); -} +/* + * The volume up and volume down special keys on a Fujitsu Amilo PA 1510 laptop + * do not generate release events so we have to do it ourselves. + */ +static unsigned int atkbd_amilo_pa1510_forced_release_keys[] = { + 0xb0, 0xae, -1U +}; /* * atkbd_set_keycode_table() initializes keyboard's keycode table @@ -967,7 +945,7 @@ static void atkbd_set_keycode_table(struct atkbd *atkbd) * Perform additional fixups */ if (atkbd_platform_fixup) - atkbd_platform_fixup(atkbd); + atkbd_platform_fixup(atkbd, atkbd_platform_fixup_data); } /* @@ -1492,9 +1470,11 @@ static ssize_t atkbd_show_err_count(struct atkbd *atkbd, char *buf) return sprintf(buf, "%lu\n", atkbd->err_count); } -static int __init atkbd_setup_fixup(const struct dmi_system_id *id) +static int __init atkbd_setup_forced_release(const struct dmi_system_id *id) { - atkbd_platform_fixup = id->driver_data; + atkbd_platform_fixup = atkbd_apply_forced_release_keylist; + atkbd_platform_fixup_data = id->driver_data; + return 0; } @@ -1505,8 +1485,8 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_dell_laptop_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_dell_laptop_forced_release_keys, }, { .ident = "Dell Laptop", @@ -1514,8 +1494,8 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_dell_laptop_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_dell_laptop_forced_release_keys, }, { .ident = "HP 2133", @@ -1523,8 +1503,8 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_PRODUCT_NAME, "HP 2133"), }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_hp_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_hp_forced_release_keys, }, { .ident = "HP Pavilion ZV6100", @@ -1532,8 +1512,8 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion ZV6100"), }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_hp_zv6100_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_hp_zv6100_forced_release_keys, }, { .ident = "Inventec Symphony", @@ -1541,8 +1521,8 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "INVENTEC"), DMI_MATCH(DMI_PRODUCT_NAME, "SYMPHONY 6.0/7.0"), }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_inventec_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_inventec_forced_release_keys, }, { .ident = "Samsung NC10", @@ -1550,8 +1530,17 @@ static struct dmi_system_id atkbd_dmi_quirk_table[] __initdata = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), DMI_MATCH(DMI_PRODUCT_NAME, "NC10"), }, - .callback = atkbd_setup_fixup, - .driver_data = atkbd_samsung_keymap_fixup, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_samsung_forced_release_keys, + }, + { + .ident = "Fujitsu Amilo PA 1510", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pa 1510"), + }, + .callback = atkbd_setup_forced_release, + .driver_data = atkbd_amilo_pa1510_forced_release_keys, }, { } }; diff --git a/drivers/input/keyboard/bf54x-keys.c b/drivers/input/keyboard/bf54x-keys.c index ee855c5202e..e94b7d735ac 100644 --- a/drivers/input/keyboard/bf54x-keys.c +++ b/drivers/input/keyboard/bf54x-keys.c @@ -211,8 +211,8 @@ static int __devinit bfin_kpad_probe(struct platform_device *pdev) if (!pdata->debounce_time || pdata->debounce_time > MAX_MULT || !pdata->coldrive_time || pdata->coldrive_time > MAX_MULT) { - printk(KERN_ERR DRV_NAME - ": Invalid Debounce/Columdrive Time from pdata\n"); + printk(KERN_WARNING DRV_NAME + ": Invalid Debounce/Columndrive Time in platform data\n"); bfin_write_KPAD_MSEL(0xFF0); /* Default MSEL */ } else { bfin_write_KPAD_MSEL( diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c index aacf71f3cd4..e9d639ec283 100644 --- a/drivers/input/keyboard/hilkbd.c +++ b/drivers/input/keyboard/hilkbd.c @@ -198,45 +198,28 @@ static void hil_do(unsigned char cmd, unsigned char *data, unsigned int len) } -/* initialise HIL */ -static int __init -hil_keyb_init(void) +/* initialize HIL */ +static int __devinit hil_keyb_init(void) { unsigned char c; unsigned int i, kbid; wait_queue_head_t hil_wait; int err; - if (hil_dev.dev) { + if (hil_dev.dev) return -ENODEV; /* already initialized */ - } + init_waitqueue_head(&hil_wait); spin_lock_init(&hil_dev.lock); + hil_dev.dev = input_allocate_device(); if (!hil_dev.dev) return -ENOMEM; -#if defined(CONFIG_HP300) - if (!MACH_IS_HP300) { - err = -ENODEV; - goto err1; - } - if (!hwreg_present((void *)(HILBASE + HIL_DATA))) { - printk(KERN_ERR "HIL: hardware register was not found\n"); - err = -ENODEV; - goto err1; - } - if (!request_region(HILBASE + HIL_DATA, 2, "hil")) { - printk(KERN_ERR "HIL: IOPORT region already used\n"); - err = -EIO; - goto err1; - } -#endif - err = request_irq(HIL_IRQ, hil_interrupt, 0, "hil", hil_dev.dev_id); if (err) { printk(KERN_ERR "HIL: Can't get IRQ\n"); - goto err2; + goto err1; } /* Turn on interrupts */ @@ -246,11 +229,9 @@ hil_keyb_init(void) hil_dev.valid = 0; /* clear any pending data */ hil_do(HIL_READKBDSADR, NULL, 0); - init_waitqueue_head(&hil_wait); - wait_event_interruptible_timeout(hil_wait, hil_dev.valid, 3*HZ); - if (!hil_dev.valid) { + wait_event_interruptible_timeout(hil_wait, hil_dev.valid, 3 * HZ); + if (!hil_dev.valid) printk(KERN_WARNING "HIL: timed out, assuming no keyboard present\n"); - } c = hil_dev.c; hil_dev.valid = 0; @@ -268,7 +249,7 @@ hil_keyb_init(void) for (i = 0; i < HIL_KEYCODES_SET1_TBLSIZE; i++) if (hphilkeyb_keycode[i] != KEY_RESERVED) - set_bit(hphilkeyb_keycode[i], hil_dev.dev->keybit); + __set_bit(hphilkeyb_keycode[i], hil_dev.dev->keybit); hil_dev.dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP); hil_dev.dev->ledbit[0] = BIT_MASK(LED_NUML) | BIT_MASK(LED_CAPSL) | @@ -287,34 +268,45 @@ hil_keyb_init(void) err = input_register_device(hil_dev.dev); if (err) { printk(KERN_ERR "HIL: Can't register device\n"); - goto err3; + goto err2; } + printk(KERN_INFO "input: %s, ID %d at 0x%08lx (irq %d) found and attached\n", hil_dev.dev->name, kbid, HILBASE, HIL_IRQ); return 0; -err3: +err2: hil_do(HIL_INTOFF, NULL, 0); - disable_irq(HIL_IRQ); free_irq(HIL_IRQ, hil_dev.dev_id); -err2: -#if defined(CONFIG_HP300) - release_region(HILBASE + HIL_DATA, 2); err1: -#endif input_free_device(hil_dev.dev); hil_dev.dev = NULL; return err; } +static void __devexit hil_keyb_exit(void) +{ + if (HIL_IRQ) + free_irq(HIL_IRQ, hil_dev.dev_id); + + /* Turn off interrupts */ + hil_do(HIL_INTOFF, NULL, 0); + + input_unregister_device(hil_dev.dev); + hil_dev.dev = NULL; +} #if defined(CONFIG_PARISC) -static int __init -hil_init_chip(struct parisc_device *dev) +static int __devinit hil_probe_chip(struct parisc_device *dev) { + /* Only allow one HIL keyboard */ + if (hil_dev.dev) + return -ENODEV; + if (!dev->irq) { - printk(KERN_WARNING "HIL: IRQ not found for HIL bus at 0x%08lx\n", dev->hpa.start); + printk(KERN_WARNING "HIL: IRQ not found for HIL bus at 0x%p\n", + (void *)dev->hpa.start); return -ENODEV; } @@ -327,51 +319,79 @@ hil_init_chip(struct parisc_device *dev) return hil_keyb_init(); } +static int __devexit hil_remove_chip(struct parisc_device *dev) +{ + hil_keyb_exit(); + + return 0; +} + static struct parisc_device_id hil_tbl[] = { { HPHW_FIO, HVERSION_REV_ANY_ID, HVERSION_ANY_ID, 0x00073 }, { 0, } }; +#if 0 +/* Disabled to avoid conflicts with the HP SDC HIL drivers */ MODULE_DEVICE_TABLE(parisc, hil_tbl); +#endif static struct parisc_driver hil_driver = { - .name = "hil", - .id_table = hil_tbl, - .probe = hil_init_chip, + .name = "hil", + .id_table = hil_tbl, + .probe = hil_probe_chip, + .remove = __devexit_p(hil_remove_chip), }; -#endif /* CONFIG_PARISC */ - static int __init hil_init(void) { -#if defined(CONFIG_PARISC) return register_parisc_driver(&hil_driver); -#else - return hil_keyb_init(); -#endif } - static void __exit hil_exit(void) { - if (HIL_IRQ) { - disable_irq(HIL_IRQ); - free_irq(HIL_IRQ, hil_dev.dev_id); + unregister_parisc_driver(&hil_driver); +} + +#else /* !CONFIG_PARISC */ + +static int __init hil_init(void) +{ + int error; + + /* Only allow one HIL keyboard */ + if (hil_dev.dev) + return -EBUSY; + + if (!MACH_IS_HP300) + return -ENODEV; + + if (!hwreg_present((void *)(HILBASE + HIL_DATA))) { + printk(KERN_ERR "HIL: hardware register was not found\n"); + return -ENODEV; } - /* Turn off interrupts */ - hil_do(HIL_INTOFF, NULL, 0); + if (!request_region(HILBASE + HIL_DATA, 2, "hil")) { + printk(KERN_ERR "HIL: IOPORT region already used\n"); + return -EIO; + } - input_unregister_device(hil_dev.dev); + error = hil_keyb_init(); + if (error) { + release_region(HILBASE + HIL_DATA, 2); + return error; + } - hil_dev.dev = NULL; + return 0; +} -#if defined(CONFIG_PARISC) - unregister_parisc_driver(&hil_driver); -#else - release_region(HILBASE+HIL_DATA, 2); -#endif +static void __exit hil_exit(void) +{ + hil_keyb_exit(); + release_region(HILBASE + HIL_DATA, 2); } +#endif /* CONFIG_PARISC */ + module_init(hil_init); module_exit(hil_exit); diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 67e5553f699..203abac1e23 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -227,4 +227,27 @@ config INPUT_PCF50633_PMU Say Y to include support for delivering PMU events via input layer on NXP PCF50633. +config INPUT_GPIO_ROTARY_ENCODER + tristate "Rotary encoders connected to GPIO pins" + depends on GPIOLIB && GENERIC_GPIO + help + Say Y here to add support for rotary encoders connected to GPIO lines. + Check file:Documentation/incput/rotary_encoder.txt for more + information. + + To compile this driver as a module, choose M here: the + module will be called rotary_encoder. + +config INPUT_RB532_BUTTON + tristate "Mikrotik Routerboard 532 button interface" + depends on MIKROTIK_RB532 + depends on GPIOLIB && GENERIC_GPIO + select INPUT_POLLDEV + help + Say Y here if you want support for the S1 button built into + Mikrotik's Routerboard 532. + + To compile this driver as a module, choose M here: the + module will be called rb532_button. + endif diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index bb62e6efacf..eb3f407baed 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -4,21 +4,23 @@ # Each configuration option enables a list of files. -obj-$(CONFIG_INPUT_SPARCSPKR) += sparcspkr.o -obj-$(CONFIG_INPUT_PCSPKR) += pcspkr.o -obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.o -obj-$(CONFIG_INPUT_IXP4XX_BEEPER) += ixp4xx-beeper.o -obj-$(CONFIG_INPUT_COBALT_BTNS) += cobalt_btns.o -obj-$(CONFIG_INPUT_WISTRON_BTNS) += wistron_btns.o -obj-$(CONFIG_INPUT_ATLAS_BTNS) += atlas_btns.o +obj-$(CONFIG_INPUT_APANEL) += apanel.o obj-$(CONFIG_INPUT_ATI_REMOTE) += ati_remote.o obj-$(CONFIG_INPUT_ATI_REMOTE2) += ati_remote2.o -obj-$(CONFIG_INPUT_KEYSPAN_REMOTE) += keyspan_remote.o -obj-$(CONFIG_INPUT_POWERMATE) += powermate.o -obj-$(CONFIG_INPUT_YEALINK) += yealink.o +obj-$(CONFIG_INPUT_ATLAS_BTNS) += atlas_btns.o obj-$(CONFIG_INPUT_CM109) += cm109.o +obj-$(CONFIG_INPUT_COBALT_BTNS) += cobalt_btns.o obj-$(CONFIG_HP_SDC_RTC) += hp_sdc_rtc.o -obj-$(CONFIG_INPUT_UINPUT) += uinput.o -obj-$(CONFIG_INPUT_APANEL) += apanel.o -obj-$(CONFIG_INPUT_SGI_BTNS) += sgi_btns.o +obj-$(CONFIG_INPUT_IXP4XX_BEEPER) += ixp4xx-beeper.o +obj-$(CONFIG_INPUT_KEYSPAN_REMOTE) += keyspan_remote.o +obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.o obj-$(CONFIG_INPUT_PCF50633_PMU) += pcf50633-input.o +obj-$(CONFIG_INPUT_PCSPKR) += pcspkr.o +obj-$(CONFIG_INPUT_POWERMATE) += powermate.o +obj-$(CONFIG_INPUT_RB532_BUTTON) += rb532_button.o +obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER) += rotary_encoder.o +obj-$(CONFIG_INPUT_SGI_BTNS) += sgi_btns.o +obj-$(CONFIG_INPUT_SPARCSPKR) += sparcspkr.o +obj-$(CONFIG_INPUT_UINPUT) += uinput.o +obj-$(CONFIG_INPUT_WISTRON_BTNS) += wistron_btns.o +obj-$(CONFIG_INPUT_YEALINK) += yealink.o diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c index 3c9988dc0e9..922c0514158 100644 --- a/drivers/input/misc/ati_remote2.c +++ b/drivers/input/misc/ati_remote2.c @@ -31,12 +31,73 @@ MODULE_LICENSE("GPL"); * newly configured "channel". */ -static unsigned int channel_mask = 0xFFFF; -module_param(channel_mask, uint, 0644); +enum { + ATI_REMOTE2_MAX_CHANNEL_MASK = 0xFFFF, + ATI_REMOTE2_MAX_MODE_MASK = 0x1F, +}; + +static int ati_remote2_set_mask(const char *val, + struct kernel_param *kp, unsigned int max) +{ + unsigned long mask; + int ret; + + if (!val) + return -EINVAL; + + ret = strict_strtoul(val, 0, &mask); + if (ret) + return ret; + + if (mask & ~max) + return -EINVAL; + + *(unsigned int *)kp->arg = mask; + + return 0; +} + +static int ati_remote2_set_channel_mask(const char *val, + struct kernel_param *kp) +{ + pr_debug("%s()\n", __func__); + + return ati_remote2_set_mask(val, kp, ATI_REMOTE2_MAX_CHANNEL_MASK); +} + +static int ati_remote2_get_channel_mask(char *buffer, struct kernel_param *kp) +{ + pr_debug("%s()\n", __func__); + + return sprintf(buffer, "0x%04x", *(unsigned int *)kp->arg); +} + +static int ati_remote2_set_mode_mask(const char *val, struct kernel_param *kp) +{ + pr_debug("%s()\n", __func__); + + return ati_remote2_set_mask(val, kp, ATI_REMOTE2_MAX_MODE_MASK); +} + +static int ati_remote2_get_mode_mask(char *buffer, struct kernel_param *kp) +{ + pr_debug("%s()\n", __func__); + + return sprintf(buffer, "0x%02x", *(unsigned int *)kp->arg); +} + +static unsigned int channel_mask = ATI_REMOTE2_MAX_CHANNEL_MASK; +#define param_check_channel_mask(name, p) __param_check(name, p, unsigned int) +#define param_set_channel_mask ati_remote2_set_channel_mask +#define param_get_channel_mask ati_remote2_get_channel_mask +module_param(channel_mask, channel_mask, 0644); MODULE_PARM_DESC(channel_mask, "Bitmask of channels to accept <15:Channel16>...<1:Channel2><0:Channel1>"); -static unsigned int mode_mask = 0x1F; -module_param(mode_mask, uint, 0644); +static unsigned int mode_mask = ATI_REMOTE2_MAX_MODE_MASK; +#define param_check_mode_mask(name, p) __param_check(name, p, unsigned int) +#define param_set_mode_mask ati_remote2_set_mode_mask +#define param_get_mode_mask ati_remote2_get_mode_mask +module_param(mode_mask, mode_mask, 0644); MODULE_PARM_DESC(mode_mask, "Bitmask of modes to accept <4:PC><3:AUX4><2:AUX3><1:AUX2><0:AUX1>"); static struct usb_device_id ati_remote2_id_table[] = { @@ -133,12 +194,18 @@ struct ati_remote2 { u16 keycode[ATI_REMOTE2_MODES][ARRAY_SIZE(ati_remote2_key_table)]; unsigned int flags; + + unsigned int channel_mask; + unsigned int mode_mask; }; static int ati_remote2_probe(struct usb_interface *interface, const struct usb_device_id *id); static void ati_remote2_disconnect(struct usb_interface *interface); static int ati_remote2_suspend(struct usb_interface *interface, pm_message_t message); static int ati_remote2_resume(struct usb_interface *interface); +static int ati_remote2_reset_resume(struct usb_interface *interface); +static int ati_remote2_pre_reset(struct usb_interface *interface); +static int ati_remote2_post_reset(struct usb_interface *interface); static struct usb_driver ati_remote2_driver = { .name = "ati_remote2", @@ -147,6 +214,9 @@ static struct usb_driver ati_remote2_driver = { .id_table = ati_remote2_id_table, .suspend = ati_remote2_suspend, .resume = ati_remote2_resume, + .reset_resume = ati_remote2_reset_resume, + .pre_reset = ati_remote2_pre_reset, + .post_reset = ati_remote2_post_reset, .supports_autosuspend = 1, }; @@ -238,7 +308,7 @@ static void ati_remote2_input_mouse(struct ati_remote2 *ar2) channel = data[0] >> 4; - if (!((1 << channel) & channel_mask)) + if (!((1 << channel) & ar2->channel_mask)) return; mode = data[0] & 0x0F; @@ -250,7 +320,7 @@ static void ati_remote2_input_mouse(struct ati_remote2 *ar2) return; } - if (!((1 << mode) & mode_mask)) + if (!((1 << mode) & ar2->mode_mask)) return; input_event(idev, EV_REL, REL_X, (s8) data[1]); @@ -277,7 +347,7 @@ static void ati_remote2_input_key(struct ati_remote2 *ar2) channel = data[0] >> 4; - if (!((1 << channel) & channel_mask)) + if (!((1 << channel) & ar2->channel_mask)) return; mode = data[0] & 0x0F; @@ -305,7 +375,7 @@ static void ati_remote2_input_key(struct ati_remote2 *ar2) ar2->mode = mode; } - if (!((1 << mode) & mode_mask)) + if (!((1 << mode) & ar2->mode_mask)) return; index = ati_remote2_lookup(hw_code); @@ -410,7 +480,7 @@ static int ati_remote2_getkeycode(struct input_dev *idev, int index, mode; mode = scancode >> 8; - if (mode > ATI_REMOTE2_PC || !((1 << mode) & mode_mask)) + if (mode > ATI_REMOTE2_PC || !((1 << mode) & ar2->mode_mask)) return -EINVAL; index = ati_remote2_lookup(scancode & 0xFF); @@ -427,7 +497,7 @@ static int ati_remote2_setkeycode(struct input_dev *idev, int scancode, int keyc int index, mode, old_keycode; mode = scancode >> 8; - if (mode > ATI_REMOTE2_PC || !((1 << mode) & mode_mask)) + if (mode > ATI_REMOTE2_PC || !((1 << mode) & ar2->mode_mask)) return -EINVAL; index = ati_remote2_lookup(scancode & 0xFF); @@ -550,7 +620,7 @@ static void ati_remote2_urb_cleanup(struct ati_remote2 *ar2) } } -static int ati_remote2_setup(struct ati_remote2 *ar2) +static int ati_remote2_setup(struct ati_remote2 *ar2, unsigned int ch_mask) { int r, i, channel; @@ -565,8 +635,8 @@ static int ati_remote2_setup(struct ati_remote2 *ar2) channel = 0; for (i = 0; i < 16; i++) { - if ((1 << i) & channel_mask) { - if (!(~(1 << i) & 0xFFFF & channel_mask)) + if ((1 << i) & ch_mask) { + if (!(~(1 << i) & ch_mask)) channel = i + 1; break; } @@ -585,6 +655,99 @@ static int ati_remote2_setup(struct ati_remote2 *ar2) return 0; } +static ssize_t ati_remote2_show_channel_mask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct usb_device *udev = to_usb_device(dev); + struct usb_interface *intf = usb_ifnum_to_if(udev, 0); + struct ati_remote2 *ar2 = usb_get_intfdata(intf); + + return sprintf(buf, "0x%04x\n", ar2->channel_mask); +} + +static ssize_t ati_remote2_store_channel_mask(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct usb_device *udev = to_usb_device(dev); + struct usb_interface *intf = usb_ifnum_to_if(udev, 0); + struct ati_remote2 *ar2 = usb_get_intfdata(intf); + unsigned long mask; + int r; + + if (strict_strtoul(buf, 0, &mask)) + return -EINVAL; + + if (mask & ~ATI_REMOTE2_MAX_CHANNEL_MASK) + return -EINVAL; + + r = usb_autopm_get_interface(ar2->intf[0]); + if (r) { + dev_err(&ar2->intf[0]->dev, + "%s(): usb_autopm_get_interface() = %d\n", __func__, r); + return r; + } + + mutex_lock(&ati_remote2_mutex); + + if (mask != ar2->channel_mask && !ati_remote2_setup(ar2, mask)) + ar2->channel_mask = mask; + + mutex_unlock(&ati_remote2_mutex); + + usb_autopm_put_interface(ar2->intf[0]); + + return count; +} + +static ssize_t ati_remote2_show_mode_mask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct usb_device *udev = to_usb_device(dev); + struct usb_interface *intf = usb_ifnum_to_if(udev, 0); + struct ati_remote2 *ar2 = usb_get_intfdata(intf); + + return sprintf(buf, "0x%02x\n", ar2->mode_mask); +} + +static ssize_t ati_remote2_store_mode_mask(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct usb_device *udev = to_usb_device(dev); + struct usb_interface *intf = usb_ifnum_to_if(udev, 0); + struct ati_remote2 *ar2 = usb_get_intfdata(intf); + unsigned long mask; + + if (strict_strtoul(buf, 0, &mask)) + return -EINVAL; + + if (mask & ~ATI_REMOTE2_MAX_MODE_MASK) + return -EINVAL; + + ar2->mode_mask = mask; + + return count; +} + +static DEVICE_ATTR(channel_mask, 0644, ati_remote2_show_channel_mask, + ati_remote2_store_channel_mask); + +static DEVICE_ATTR(mode_mask, 0644, ati_remote2_show_mode_mask, + ati_remote2_store_mode_mask); + +static struct attribute *ati_remote2_attrs[] = { + &dev_attr_channel_mask.attr, + &dev_attr_mode_mask.attr, + NULL, +}; + +static struct attribute_group ati_remote2_attr_group = { + .attrs = ati_remote2_attrs, +}; + static int ati_remote2_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(interface); @@ -615,7 +778,10 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d if (r) goto fail2; - r = ati_remote2_setup(ar2); + ar2->channel_mask = channel_mask; + ar2->mode_mask = mode_mask; + + r = ati_remote2_setup(ar2, ar2->channel_mask); if (r) goto fail2; @@ -624,19 +790,24 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d strlcat(ar2->name, "ATI Remote Wonder II", sizeof(ar2->name)); - r = ati_remote2_input_init(ar2); + r = sysfs_create_group(&udev->dev.kobj, &ati_remote2_attr_group); if (r) goto fail2; + r = ati_remote2_input_init(ar2); + if (r) + goto fail3; + usb_set_intfdata(interface, ar2); interface->needs_remote_wakeup = 1; return 0; + fail3: + sysfs_remove_group(&udev->dev.kobj, &ati_remote2_attr_group); fail2: ati_remote2_urb_cleanup(ar2); - usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]); fail1: kfree(ar2); @@ -657,6 +828,8 @@ static void ati_remote2_disconnect(struct usb_interface *interface) input_unregister_device(ar2->idev); + sysfs_remove_group(&ar2->udev->dev.kobj, &ati_remote2_attr_group); + ati_remote2_urb_cleanup(ar2); usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]); @@ -715,6 +888,78 @@ static int ati_remote2_resume(struct usb_interface *interface) return r; } +static int ati_remote2_reset_resume(struct usb_interface *interface) +{ + struct ati_remote2 *ar2; + struct usb_host_interface *alt = interface->cur_altsetting; + int r = 0; + + if (alt->desc.bInterfaceNumber) + return 0; + + ar2 = usb_get_intfdata(interface); + + dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); + + mutex_lock(&ati_remote2_mutex); + + r = ati_remote2_setup(ar2, ar2->channel_mask); + if (r) + goto out; + + if (ar2->flags & ATI_REMOTE2_OPENED) + r = ati_remote2_submit_urbs(ar2); + + if (!r) + ar2->flags &= ~ATI_REMOTE2_SUSPENDED; + + out: + mutex_unlock(&ati_remote2_mutex); + + return r; +} + +static int ati_remote2_pre_reset(struct usb_interface *interface) +{ + struct ati_remote2 *ar2; + struct usb_host_interface *alt = interface->cur_altsetting; + + if (alt->desc.bInterfaceNumber) + return 0; + + ar2 = usb_get_intfdata(interface); + + dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); + + mutex_lock(&ati_remote2_mutex); + + if (ar2->flags == ATI_REMOTE2_OPENED) + ati_remote2_kill_urbs(ar2); + + return 0; +} + +static int ati_remote2_post_reset(struct usb_interface *interface) +{ + struct ati_remote2 *ar2; + struct usb_host_interface *alt = interface->cur_altsetting; + int r = 0; + + if (alt->desc.bInterfaceNumber) + return 0; + + ar2 = usb_get_intfdata(interface); + + dev_dbg(&ar2->intf[0]->dev, "%s()\n", __func__); + + if (ar2->flags == ATI_REMOTE2_OPENED) + r = ati_remote2_submit_urbs(ar2); + + mutex_unlock(&ati_remote2_mutex); + + return r; +} + static int __init ati_remote2_init(void) { int r; diff --git a/drivers/input/misc/rb532_button.c b/drivers/input/misc/rb532_button.c new file mode 100644 index 00000000000..e2c7f622a0b --- /dev/null +++ b/drivers/input/misc/rb532_button.c @@ -0,0 +1,120 @@ +/* + * Support for the S1 button on Routerboard 532 + * + * Copyright (C) 2009 Phil Sutter <n0-1@freewrt.org> + */ + +#include <linux/input-polldev.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#include <asm/mach-rc32434/gpio.h> +#include <asm/mach-rc32434/rb.h> + +#define DRV_NAME "rb532-button" + +#define RB532_BTN_RATE 100 /* msec */ +#define RB532_BTN_KSYM BTN_0 + +/* The S1 button state is provided by GPIO pin 1. But as this + * pin is also used for uart input as alternate function, the + * operational modes must be switched first: + * 1) disable uart using set_latch_u5() + * 2) turn off alternate function implicitly through + * gpio_direction_input() + * 3) read the GPIO's current value + * 4) undo step 2 by enabling alternate function (in this + * mode the GPIO direction is fixed, so no change needed) + * 5) turn on uart again + * The GPIO value occurs to be inverted, so pin high means + * button is not pressed. + */ +static bool rb532_button_pressed(void) +{ + int val; + + set_latch_u5(0, LO_FOFF); + gpio_direction_input(GPIO_BTN_S1); + + val = gpio_get_value(GPIO_BTN_S1); + + rb532_gpio_set_func(GPIO_BTN_S1); + set_latch_u5(LO_FOFF, 0); + + return !val; +} + +static void rb532_button_poll(struct input_polled_dev *poll_dev) +{ + input_report_key(poll_dev->input, RB532_BTN_KSYM, + rb532_button_pressed()); + input_sync(poll_dev->input); +} + +static int __devinit rb532_button_probe(struct platform_device *pdev) +{ + struct input_polled_dev *poll_dev; + int error; + + poll_dev = input_allocate_polled_device(); + if (!poll_dev) + return -ENOMEM; + + poll_dev->poll = rb532_button_poll; + poll_dev->poll_interval = RB532_BTN_RATE; + + poll_dev->input->name = "rb532 button"; + poll_dev->input->phys = "rb532/button0"; + poll_dev->input->id.bustype = BUS_HOST; + poll_dev->input->dev.parent = &pdev->dev; + + dev_set_drvdata(&pdev->dev, poll_dev); + + input_set_capability(poll_dev->input, EV_KEY, RB532_BTN_KSYM); + + error = input_register_polled_device(poll_dev); + if (error) { + input_free_polled_device(poll_dev); + return error; + } + + return 0; +} + +static int __devexit rb532_button_remove(struct platform_device *pdev) +{ + struct input_polled_dev *poll_dev = dev_get_drvdata(&pdev->dev); + + input_unregister_polled_device(poll_dev); + input_free_polled_device(poll_dev); + dev_set_drvdata(&pdev->dev, NULL); + + return 0; +} + +static struct platform_driver rb532_button_driver = { + .probe = rb532_button_probe, + .remove = __devexit_p(rb532_button_remove), + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + }, +}; + +static int __init rb532_button_init(void) +{ + return platform_driver_register(&rb532_button_driver); +} + +static void __exit rb532_button_exit(void) +{ + platform_driver_unregister(&rb532_button_driver); +} + +module_init(rb532_button_init); +module_exit(rb532_button_exit); + +MODULE_AUTHOR("Phil Sutter <n0-1@freewrt.org>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Support for S1 button on Routerboard 532"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c new file mode 100644 index 00000000000..5bb3ab51b8c --- /dev/null +++ b/drivers/input/misc/rotary_encoder.c @@ -0,0 +1,221 @@ +/* + * rotary_encoder.c + * + * (c) 2009 Daniel Mack <daniel@caiaq.de> + * + * state machine code inspired by code from Tim Ruetz + * + * A generic driver for rotary encoders connected to GPIO lines. + * See file:Documentation/input/rotary_encoder.txt for more information + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/input.h> +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> +#include <linux/rotary_encoder.h> + +#define DRV_NAME "rotary-encoder" + +struct rotary_encoder { + unsigned int irq_a; + unsigned int irq_b; + unsigned int pos; + unsigned int armed; + unsigned int dir; + struct input_dev *input; + struct rotary_encoder_platform_data *pdata; +}; + +static irqreturn_t rotary_encoder_irq(int irq, void *dev_id) +{ + struct rotary_encoder *encoder = dev_id; + struct rotary_encoder_platform_data *pdata = encoder->pdata; + int a = !!gpio_get_value(pdata->gpio_a); + int b = !!gpio_get_value(pdata->gpio_b); + int state; + + a ^= pdata->inverted_a; + b ^= pdata->inverted_b; + state = (a << 1) | b; + + switch (state) { + + case 0x0: + if (!encoder->armed) + break; + + if (encoder->dir) { + /* turning counter-clockwise */ + encoder->pos += pdata->steps; + encoder->pos--; + encoder->pos %= pdata->steps; + } else { + /* turning clockwise */ + encoder->pos++; + encoder->pos %= pdata->steps; + } + + input_report_abs(encoder->input, pdata->axis, encoder->pos); + input_sync(encoder->input); + + encoder->armed = 0; + break; + + case 0x1: + case 0x2: + if (encoder->armed) + encoder->dir = state - 1; + break; + + case 0x3: + encoder->armed = 1; + break; + } + + return IRQ_HANDLED; +} + +static int __devinit rotary_encoder_probe(struct platform_device *pdev) +{ + struct rotary_encoder_platform_data *pdata = pdev->dev.platform_data; + struct rotary_encoder *encoder; + struct input_dev *input; + int err; + + if (!pdata || !pdata->steps) { + dev_err(&pdev->dev, "invalid platform data\n"); + return -ENOENT; + } + + encoder = kzalloc(sizeof(struct rotary_encoder), GFP_KERNEL); + input = input_allocate_device(); + if (!encoder || !input) { + dev_err(&pdev->dev, "failed to allocate memory for device\n"); + err = -ENOMEM; + goto exit_free_mem; + } + + encoder->input = input; + encoder->pdata = pdata; + encoder->irq_a = gpio_to_irq(pdata->gpio_a); + encoder->irq_b = gpio_to_irq(pdata->gpio_b); + + /* create and register the input driver */ + input->name = pdev->name; + input->id.bustype = BUS_HOST; + input->dev.parent = &pdev->dev; + input->evbit[0] = BIT_MASK(EV_ABS); + input_set_abs_params(encoder->input, + pdata->axis, 0, pdata->steps, 0, 1); + + err = input_register_device(input); + if (err) { + dev_err(&pdev->dev, "failed to register input device\n"); + goto exit_free_mem; + } + + /* request the GPIOs */ + err = gpio_request(pdata->gpio_a, DRV_NAME); + if (err) { + dev_err(&pdev->dev, "unable to request GPIO %d\n", + pdata->gpio_a); + goto exit_unregister_input; + } + + err = gpio_request(pdata->gpio_b, DRV_NAME); + if (err) { + dev_err(&pdev->dev, "unable to request GPIO %d\n", + pdata->gpio_b); + goto exit_free_gpio_a; + } + + /* request the IRQs */ + err = request_irq(encoder->irq_a, &rotary_encoder_irq, + IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE, + DRV_NAME, encoder); + if (err) { + dev_err(&pdev->dev, "unable to request IRQ %d\n", + encoder->irq_a); + goto exit_free_gpio_b; + } + + err = request_irq(encoder->irq_b, &rotary_encoder_irq, + IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE, + DRV_NAME, encoder); + if (err) { + dev_err(&pdev->dev, "unable to request IRQ %d\n", + encoder->irq_b); + goto exit_free_irq_a; + } + + platform_set_drvdata(pdev, encoder); + + return 0; + +exit_free_irq_a: + free_irq(encoder->irq_a, encoder); +exit_free_gpio_b: + gpio_free(pdata->gpio_b); +exit_free_gpio_a: + gpio_free(pdata->gpio_a); +exit_unregister_input: + input_unregister_device(input); + input = NULL; /* so we don't try to free it */ +exit_free_mem: + input_free_device(input); + kfree(encoder); + return err; +} + +static int __devexit rotary_encoder_remove(struct platform_device *pdev) +{ + struct rotary_encoder *encoder = platform_get_drvdata(pdev); + struct rotary_encoder_platform_data *pdata = pdev->dev.platform_data; + + free_irq(encoder->irq_a, encoder); + free_irq(encoder->irq_b, encoder); + gpio_free(pdata->gpio_a); + gpio_free(pdata->gpio_b); + input_unregister_device(encoder->input); + platform_set_drvdata(pdev, NULL); + kfree(encoder); + + return 0; +} + +static struct platform_driver rotary_encoder_driver = { + .probe = rotary_encoder_probe, + .remove = __devexit_p(rotary_encoder_remove), + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + } +}; + +static int __init rotary_encoder_init(void) +{ + return platform_driver_register(&rotary_encoder_driver); +} + +static void __exit rotary_encoder_exit(void) +{ + platform_driver_unregister(&rotary_encoder_driver); +} + +module_init(rotary_encoder_init); +module_exit(rotary_encoder_exit); + +MODULE_ALIAS("platform:" DRV_NAME); +MODULE_DESCRIPTION("GPIO rotary encoder driver"); +MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>"); +MODULE_LICENSE("GPL v2"); + diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig index 4f38e6f7dfd..c66cc3d08c2 100644 --- a/drivers/input/mouse/Kconfig +++ b/drivers/input/mouse/Kconfig @@ -292,4 +292,15 @@ config MOUSE_PXA930_TRKBALL help Say Y here to support PXA930 Trackball mouse. +config MOUSE_MAPLE + tristate "Maple mouse (for the Dreamcast)" + depends on MAPLE + help + This driver supports the Maple mouse on the SEGA Dreamcast. + + Most Dreamcast users, who have a mouse, will say Y here. + + To compile this driver as a module choose M here: the module will be + called maplemouse. + endif diff --git a/drivers/input/mouse/Makefile b/drivers/input/mouse/Makefile index 8c8a1f236e2..472189468d6 100644 --- a/drivers/input/mouse/Makefile +++ b/drivers/input/mouse/Makefile @@ -6,18 +6,19 @@ obj-$(CONFIG_MOUSE_AMIGA) += amimouse.o obj-$(CONFIG_MOUSE_APPLETOUCH) += appletouch.o -obj-$(CONFIG_MOUSE_BCM5974) += bcm5974.o obj-$(CONFIG_MOUSE_ATARI) += atarimouse.o -obj-$(CONFIG_MOUSE_RISCPC) += rpcmouse.o +obj-$(CONFIG_MOUSE_BCM5974) += bcm5974.o +obj-$(CONFIG_MOUSE_GPIO) += gpio_mouse.o +obj-$(CONFIG_MOUSE_HIL) += hil_ptr.o obj-$(CONFIG_MOUSE_INPORT) += inport.o obj-$(CONFIG_MOUSE_LOGIBM) += logibm.o +obj-$(CONFIG_MOUSE_MAPLE) += maplemouse.o obj-$(CONFIG_MOUSE_PC110PAD) += pc110pad.o obj-$(CONFIG_MOUSE_PS2) += psmouse.o obj-$(CONFIG_MOUSE_PXA930_TRKBALL) += pxa930_trkball.o +obj-$(CONFIG_MOUSE_RISCPC) += rpcmouse.o obj-$(CONFIG_MOUSE_SERIAL) += sermouse.o -obj-$(CONFIG_MOUSE_HIL) += hil_ptr.o obj-$(CONFIG_MOUSE_VSXXXAA) += vsxxxaa.o -obj-$(CONFIG_MOUSE_GPIO) += gpio_mouse.o psmouse-objs := psmouse-base.o synaptics.o diff --git a/drivers/input/mouse/hgpk.c b/drivers/input/mouse/hgpk.c index 55cd0fa6833..a1ad2f1a7bb 100644 --- a/drivers/input/mouse/hgpk.c +++ b/drivers/input/mouse/hgpk.c @@ -472,7 +472,7 @@ static enum hgpk_model_t hgpk_get_model(struct psmouse *psmouse) return -EIO; } - hgpk_dbg(psmouse, "ID: %02x %02x %02x", param[0], param[1], param[2]); + hgpk_dbg(psmouse, "ID: %02x %02x %02x\n", param[0], param[1], param[2]); /* HGPK signature: 0x67, 0x00, 0x<model> */ if (param[0] != 0x67 || param[1] != 0x00) diff --git a/drivers/input/mouse/maplemouse.c b/drivers/input/mouse/maplemouse.c new file mode 100644 index 00000000000..d196abfb68b --- /dev/null +++ b/drivers/input/mouse/maplemouse.c @@ -0,0 +1,147 @@ +/* + * SEGA Dreamcast mouse driver + * Based on drivers/usb/usbmouse.c + * + * Copyright Yaegashi Takeshi, 2001 + * Adrian McMenamin, 2008 + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/input.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/timer.h> +#include <linux/maple.h> + +MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>"); +MODULE_DESCRIPTION("SEGA Dreamcast mouse driver"); +MODULE_LICENSE("GPL"); + +struct dc_mouse { + struct input_dev *dev; + struct maple_device *mdev; +}; + +static void dc_mouse_callback(struct mapleq *mq) +{ + int buttons, relx, rely, relz; + struct maple_device *mapledev = mq->dev; + struct dc_mouse *mse = maple_get_drvdata(mapledev); + struct input_dev *dev = mse->dev; + unsigned char *res = mq->recvbuf; + + buttons = ~res[8]; + relx = *(unsigned short *)(res + 12) - 512; + rely = *(unsigned short *)(res + 14) - 512; + relz = *(unsigned short *)(res + 16) - 512; + + input_report_key(dev, BTN_LEFT, buttons & 4); + input_report_key(dev, BTN_MIDDLE, buttons & 9); + input_report_key(dev, BTN_RIGHT, buttons & 2); + input_report_rel(dev, REL_X, relx); + input_report_rel(dev, REL_Y, rely); + input_report_rel(dev, REL_WHEEL, relz); + input_sync(dev); +} + +static int dc_mouse_open(struct input_dev *dev) +{ + struct dc_mouse *mse = dev->dev.platform_data; + + maple_getcond_callback(mse->mdev, dc_mouse_callback, HZ/50, + MAPLE_FUNC_MOUSE); + + return 0; +} + +static void dc_mouse_close(struct input_dev *dev) +{ + struct dc_mouse *mse = dev->dev.platform_data; + + maple_getcond_callback(mse->mdev, dc_mouse_callback, 0, + MAPLE_FUNC_MOUSE); +} + + +static int __devinit probe_maple_mouse(struct device *dev) +{ + struct maple_device *mdev = to_maple_dev(dev); + struct maple_driver *mdrv = to_maple_driver(dev->driver); + struct input_dev *input_dev; + struct dc_mouse *mse; + int error; + + mse = kzalloc(sizeof(struct dc_mouse), GFP_KERNEL); + input_dev = input_allocate_device(); + + if (!mse || !input_dev) { + error = -ENOMEM; + goto fail; + } + + mse->dev = input_dev; + mse->mdev = mdev; + + input_set_drvdata(input_dev, mse); + input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REL); + input_dev->keybit[BIT_WORD(BTN_MOUSE)] = BIT_MASK(BTN_LEFT) | + BIT_MASK(BTN_RIGHT) | BIT_MASK(BTN_MIDDLE); + input_dev->relbit[0] = BIT_MASK(REL_X) | BIT_MASK(REL_Y) | + BIT_MASK(REL_WHEEL); + input_dev->name = mdev->product_name; + input_dev->id.bustype = BUS_HOST; + input_dev->open = dc_mouse_open; + input_dev->close = dc_mouse_close; + + mdev->driver = mdrv; + maple_set_drvdata(mdev, mse); + + error = input_register_device(input_dev); + if (error) + goto fail; + + return 0; + +fail: + input_free_device(input_dev); + maple_set_drvdata(mdev, NULL); + kfree(mse); + mdev->driver = NULL; + return error; +} + +static int __devexit remove_maple_mouse(struct device *dev) +{ + struct maple_device *mdev = to_maple_dev(dev); + struct dc_mouse *mse = maple_get_drvdata(mdev); + + mdev->callback = NULL; + input_unregister_device(mse->dev); + maple_set_drvdata(mdev, NULL); + kfree(mse); + + return 0; +} + +static struct maple_driver dc_mouse_driver = { + .function = MAPLE_FUNC_MOUSE, + .drv = { + .name = "Dreamcast_mouse", + .probe = probe_maple_mouse, + .remove = __devexit_p(remove_maple_mouse), + }, +}; + +static int __init dc_mouse_init(void) +{ + return maple_driver_register(&dc_mouse_driver); +} + +static void __exit dc_mouse_exit(void) +{ + maple_driver_unregister(&dc_mouse_driver); +} + +module_init(dc_mouse_init); +module_exit(dc_mouse_exit); diff --git a/drivers/input/mouse/pc110pad.c b/drivers/input/mouse/pc110pad.c index fd09c8df81f..f63995f854f 100644 --- a/drivers/input/mouse/pc110pad.c +++ b/drivers/input/mouse/pc110pad.c @@ -111,11 +111,8 @@ static int __init pc110pad_init(void) struct pci_dev *dev; int err; - dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL); - if (dev) { - pci_dev_put(dev); + if (!no_pci_devices()) return -ENODEV; - } if (!request_region(pc110pad_io, 4, "pc110pad")) { printk(KERN_ERR "pc110pad: I/O area %#x-%#x in use.\n", diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 6fa2deff744..83ed2d56b92 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -151,6 +151,14 @@ static struct dmi_system_id __initdata i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "01"), }, }, + { + .ident = "HP DV9700", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), + }, + }, { } }; diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index bb6486a8c07..b01fd61dadc 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -29,6 +29,51 @@ config TOUCHSCREEN_ADS7846 To compile this driver as a module, choose M here: the module will be called ads7846. +config TOUCHSCREEN_AD7877 + tristate "AD7877 based touchscreens" + depends on SPI_MASTER + help + Say Y here if you have a touchscreen interface using the + AD7877 controller, and your board-specific initialization + code includes that in its table of SPI devices. + + If unsure, say N (but it's safe to say "Y"). + + To compile this driver as a module, choose M here: the + module will be called ad7877. + +config TOUCHSCREEN_AD7879_I2C + tristate "AD7879 based touchscreens: AD7879-1 I2C Interface" + depends on I2C + select TOUCHSCREEN_AD7879 + help + Say Y here if you have a touchscreen interface using the + AD7879-1 controller, and your board-specific initialization + code includes that in its table of I2C devices. + + If unsure, say N (but it's safe to say "Y"). + + To compile this driver as a module, choose M here: the + module will be called ad7879. + +config TOUCHSCREEN_AD7879_SPI + tristate "AD7879 based touchscreens: AD7879 SPI Interface" + depends on SPI_MASTER && TOUCHSCREEN_AD7879_I2C = n + select TOUCHSCREEN_AD7879 + help + Say Y here if you have a touchscreen interface using the + AD7879 controller, and your board-specific initialization + code includes that in its table of SPI devices. + + If unsure, say N (but it's safe to say "Y"). + + To compile this driver as a module, choose M here: the + module will be called ad7879. + +config TOUCHSCREEN_AD7879 + tristate + default n + config TOUCHSCREEN_BITSY tristate "Compaq iPAQ H3600 (Bitsy) touchscreen" depends on SA1100_BITSY @@ -308,6 +353,19 @@ config TOUCHSCREEN_WM97XX_MAINSTONE To compile this driver as a module, choose M here: the module will be called mainstone-wm97xx. +config TOUCHSCREEN_WM97XX_ZYLONITE + tristate "Zylonite accelerated touch" + depends on TOUCHSCREEN_WM97XX && MACH_ZYLONITE + select TOUCHSCREEN_WM9713 + help + Say Y here for support for streaming mode with the touchscreen + on Zylonite systems. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called zylonite-wm97xx. + config TOUCHSCREEN_USB_COMPOSITE tristate "USB Touchscreen Driver" depends on USB_ARCH_HAS_HCD diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index d3375aff46f..6700f7b9d16 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -6,6 +6,8 @@ wm97xx-ts-y := wm97xx-core.o +obj-$(CONFIG_TOUCHSCREEN_AD7877) += ad7877.o +obj-$(CONFIG_TOUCHSCREEN_AD7879) += ad7879.o obj-$(CONFIG_TOUCHSCREEN_ADS7846) += ads7846.o obj-$(CONFIG_TOUCHSCREEN_ATMEL_TSADCC) += atmel_tsadcc.o obj-$(CONFIG_TOUCHSCREEN_BITSY) += h3600_ts_input.o @@ -34,3 +36,4 @@ wm97xx-ts-$(CONFIG_TOUCHSCREEN_WM9705) += wm9705.o wm97xx-ts-$(CONFIG_TOUCHSCREEN_WM9712) += wm9712.o wm97xx-ts-$(CONFIG_TOUCHSCREEN_WM9713) += wm9713.o obj-$(CONFIG_TOUCHSCREEN_WM97XX_MAINSTONE) += mainstone-wm97xx.o +obj-$(CONFIG_TOUCHSCREEN_WM97XX_ZYLONITE) += zylonite-wm97xx.o diff --git a/drivers/input/touchscreen/ad7877.c b/drivers/input/touchscreen/ad7877.c new file mode 100644 index 00000000000..e4728a28f49 --- /dev/null +++ b/drivers/input/touchscreen/ad7877.c @@ -0,0 +1,844 @@ +/* + * Copyright (C) 2006-2008 Michael Hennerich, Analog Devices Inc. + * + * Description: AD7877 based touchscreen, sensor (ADCs), DAC and GPIO driver + * Based on: ads7846.c + * + * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see the file COPYING, or write + * to the Free Software Foundation, Inc., + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + * History: + * Copyright (c) 2005 David Brownell + * Copyright (c) 2006 Nokia Corporation + * Various changes: Imre Deak <imre.deak@nokia.com> + * + * Using code from: + * - corgi_ts.c + * Copyright (C) 2004-2005 Richard Purdie + * - omap_ts.[hc], ads7846.h, ts_osk.c + * Copyright (C) 2002 MontaVista Software + * Copyright (C) 2004 Texas Instruments + * Copyright (C) 2005 Dirk Behme + */ + + +#include <linux/device.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/spi/spi.h> +#include <linux/spi/ad7877.h> +#include <asm/irq.h> + +#define TS_PEN_UP_TIMEOUT msecs_to_jiffies(50) + +#define MAX_SPI_FREQ_HZ 20000000 +#define MAX_12BIT ((1<<12)-1) + +#define AD7877_REG_ZEROS 0 +#define AD7877_REG_CTRL1 1 +#define AD7877_REG_CTRL2 2 +#define AD7877_REG_ALERT 3 +#define AD7877_REG_AUX1HIGH 4 +#define AD7877_REG_AUX1LOW 5 +#define AD7877_REG_BAT1HIGH 6 +#define AD7877_REG_BAT1LOW 7 +#define AD7877_REG_BAT2HIGH 8 +#define AD7877_REG_BAT2LOW 9 +#define AD7877_REG_TEMP1HIGH 10 +#define AD7877_REG_TEMP1LOW 11 +#define AD7877_REG_SEQ0 12 +#define AD7877_REG_SEQ1 13 +#define AD7877_REG_DAC 14 +#define AD7877_REG_NONE1 15 +#define AD7877_REG_EXTWRITE 15 +#define AD7877_REG_XPLUS 16 +#define AD7877_REG_YPLUS 17 +#define AD7877_REG_Z2 18 +#define AD7877_REG_aux1 19 +#define AD7877_REG_aux2 20 +#define AD7877_REG_aux3 21 +#define AD7877_REG_bat1 22 +#define AD7877_REG_bat2 23 +#define AD7877_REG_temp1 24 +#define AD7877_REG_temp2 25 +#define AD7877_REG_Z1 26 +#define AD7877_REG_GPIOCTRL1 27 +#define AD7877_REG_GPIOCTRL2 28 +#define AD7877_REG_GPIODATA 29 +#define AD7877_REG_NONE2 30 +#define AD7877_REG_NONE3 31 + +#define AD7877_SEQ_YPLUS_BIT (1<<11) +#define AD7877_SEQ_XPLUS_BIT (1<<10) +#define AD7877_SEQ_Z2_BIT (1<<9) +#define AD7877_SEQ_AUX1_BIT (1<<8) +#define AD7877_SEQ_AUX2_BIT (1<<7) +#define AD7877_SEQ_AUX3_BIT (1<<6) +#define AD7877_SEQ_BAT1_BIT (1<<5) +#define AD7877_SEQ_BAT2_BIT (1<<4) +#define AD7877_SEQ_TEMP1_BIT (1<<3) +#define AD7877_SEQ_TEMP2_BIT (1<<2) +#define AD7877_SEQ_Z1_BIT (1<<1) + +enum { + AD7877_SEQ_YPOS = 0, + AD7877_SEQ_XPOS = 1, + AD7877_SEQ_Z2 = 2, + AD7877_SEQ_AUX1 = 3, + AD7877_SEQ_AUX2 = 4, + AD7877_SEQ_AUX3 = 5, + AD7877_SEQ_BAT1 = 6, + AD7877_SEQ_BAT2 = 7, + AD7877_SEQ_TEMP1 = 8, + AD7877_SEQ_TEMP2 = 9, + AD7877_SEQ_Z1 = 10, + AD7877_NR_SENSE = 11, +}; + +/* DAC Register Default RANGE 0 to Vcc, Volatge Mode, DAC On */ +#define AD7877_DAC_CONF 0x1 + +/* If gpio3 is set AUX3/GPIO3 acts as GPIO Output */ +#define AD7877_EXTW_GPIO_3_CONF 0x1C4 +#define AD7877_EXTW_GPIO_DATA 0x200 + +/* Control REG 2 */ +#define AD7877_TMR(x) ((x & 0x3) << 0) +#define AD7877_REF(x) ((x & 0x1) << 2) +#define AD7877_POL(x) ((x & 0x1) << 3) +#define AD7877_FCD(x) ((x & 0x3) << 4) +#define AD7877_PM(x) ((x & 0x3) << 6) +#define AD7877_ACQ(x) ((x & 0x3) << 8) +#define AD7877_AVG(x) ((x & 0x3) << 10) + +/* Control REG 1 */ +#define AD7877_SER (1 << 11) /* non-differential */ +#define AD7877_DFR (0 << 11) /* differential */ + +#define AD7877_MODE_NOC (0) /* Do not convert */ +#define AD7877_MODE_SCC (1) /* Single channel conversion */ +#define AD7877_MODE_SEQ0 (2) /* Sequence 0 in Slave Mode */ +#define AD7877_MODE_SEQ1 (3) /* Sequence 1 in Master Mode */ + +#define AD7877_CHANADD(x) ((x&0xF)<<7) +#define AD7877_READADD(x) ((x)<<2) +#define AD7877_WRITEADD(x) ((x)<<12) + +#define AD7877_READ_CHAN(x) (AD7877_WRITEADD(AD7877_REG_CTRL1) | AD7877_SER | \ + AD7877_MODE_SCC | AD7877_CHANADD(AD7877_REG_ ## x) | \ + AD7877_READADD(AD7877_REG_ ## x)) + +#define AD7877_MM_SEQUENCE (AD7877_SEQ_YPLUS_BIT | AD7877_SEQ_XPLUS_BIT | \ + AD7877_SEQ_Z2_BIT | AD7877_SEQ_Z1_BIT) + +/* + * Non-touchscreen sensors only use single-ended conversions. + */ + +struct ser_req { + u16 reset; + u16 ref_on; + u16 command; + u16 sample; + struct spi_message msg; + struct spi_transfer xfer[6]; +}; + +struct ad7877 { + struct input_dev *input; + char phys[32]; + + struct spi_device *spi; + u16 model; + u16 vref_delay_usecs; + u16 x_plate_ohms; + u16 pressure_max; + + u16 cmd_crtl1; + u16 cmd_crtl2; + u16 cmd_dummy; + u16 dac; + + u8 stopacq_polarity; + u8 first_conversion_delay; + u8 acquisition_time; + u8 averaging; + u8 pen_down_acc_interval; + + u16 conversion_data[AD7877_NR_SENSE]; + + struct spi_transfer xfer[AD7877_NR_SENSE + 2]; + struct spi_message msg; + + struct mutex mutex; + unsigned disabled:1; /* P: mutex */ + unsigned gpio3:1; /* P: mutex */ + unsigned gpio4:1; /* P: mutex */ + + spinlock_t lock; + struct timer_list timer; /* P: lock */ + unsigned pending:1; /* P: lock */ +}; + +static int gpio3; +module_param(gpio3, int, 0); +MODULE_PARM_DESC(gpio3, "If gpio3 is set to 1 AUX3 acts as GPIO3"); + +/* + * ad7877_read/write are only used for initial setup and for sysfs controls. + * The main traffic is done using spi_async() in the interrupt handler. + */ + +static int ad7877_read(struct spi_device *spi, u16 reg) +{ + struct ser_req *req; + int status, ret; + + req = kzalloc(sizeof *req, GFP_KERNEL); + if (!req) + return -ENOMEM; + + spi_message_init(&req->msg); + + req->command = (u16) (AD7877_WRITEADD(AD7877_REG_CTRL1) | + AD7877_READADD(reg)); + req->xfer[0].tx_buf = &req->command; + req->xfer[0].len = 2; + + req->xfer[1].rx_buf = &req->sample; + req->xfer[1].len = 2; + + spi_message_add_tail(&req->xfer[0], &req->msg); + spi_message_add_tail(&req->xfer[1], &req->msg); + + status = spi_sync(spi, &req->msg); + ret = status ? : req->sample; + + kfree(req); + + return ret; +} + +static int ad7877_write(struct spi_device *spi, u16 reg, u16 val) +{ + struct ser_req *req; + int status; + + req = kzalloc(sizeof *req, GFP_KERNEL); + if (!req) + return -ENOMEM; + + spi_message_init(&req->msg); + + req->command = (u16) (AD7877_WRITEADD(reg) | (val & MAX_12BIT)); + req->xfer[0].tx_buf = &req->command; + req->xfer[0].len = 2; + + spi_message_add_tail(&req->xfer[0], &req->msg); + + status = spi_sync(spi, &req->msg); + + kfree(req); + + return status; +} + +static int ad7877_read_adc(struct spi_device *spi, unsigned command) +{ + struct ad7877 *ts = dev_get_drvdata(&spi->dev); + struct ser_req *req; + int status; + int sample; + int i; + + req = kzalloc(sizeof *req, GFP_KERNEL); + if (!req) + return -ENOMEM; + + spi_message_init(&req->msg); + + /* activate reference, so it has time to settle; */ + req->ref_on = AD7877_WRITEADD(AD7877_REG_CTRL2) | + AD7877_POL(ts->stopacq_polarity) | + AD7877_AVG(0) | AD7877_PM(2) | AD7877_TMR(0) | + AD7877_ACQ(ts->acquisition_time) | AD7877_FCD(0); + + req->reset = AD7877_WRITEADD(AD7877_REG_CTRL1) | AD7877_MODE_NOC; + + req->command = (u16) command; + + req->xfer[0].tx_buf = &req->reset; + req->xfer[0].len = 2; + + req->xfer[1].tx_buf = &req->ref_on; + req->xfer[1].len = 2; + req->xfer[1].delay_usecs = ts->vref_delay_usecs; + + req->xfer[2].tx_buf = &req->command; + req->xfer[2].len = 2; + req->xfer[2].delay_usecs = ts->vref_delay_usecs; + + req->xfer[3].rx_buf = &req->sample; + req->xfer[3].len = 2; + + req->xfer[4].tx_buf = &ts->cmd_crtl2; /*REF OFF*/ + req->xfer[4].len = 2; + + req->xfer[5].tx_buf = &ts->cmd_crtl1; /*DEFAULT*/ + req->xfer[5].len = 2; + + /* group all the transfers together, so we can't interfere with + * reading touchscreen state; disable penirq while sampling + */ + for (i = 0; i < 6; i++) + spi_message_add_tail(&req->xfer[i], &req->msg); + + status = spi_sync(spi, &req->msg); + sample = req->sample; + + kfree(req); + + return status ? : sample; +} + +static void ad7877_rx(struct ad7877 *ts) +{ + struct input_dev *input_dev = ts->input; + unsigned Rt; + u16 x, y, z1, z2; + + x = ts->conversion_data[AD7877_SEQ_XPOS] & MAX_12BIT; + y = ts->conversion_data[AD7877_SEQ_YPOS] & MAX_12BIT; + z1 = ts->conversion_data[AD7877_SEQ_Z1] & MAX_12BIT; + z2 = ts->conversion_data[AD7877_SEQ_Z2] & MAX_12BIT; + + /* + * The samples processed here are already preprocessed by the AD7877. + * The preprocessing function consists of an averaging filter. + * The combination of 'first conversion delay' and averaging provides a robust solution, + * discarding the spurious noise in the signal and keeping only the data of interest. + * The size of the averaging filter is programmable. (dev.platform_data, see linux/spi/ad7877.h) + * Other user-programmable conversion controls include variable acquisition time, + * and first conversion delay. Up to 16 averages can be taken per conversion. + */ + + if (likely(x && z1)) { + /* compute touch pressure resistance using equation #1 */ + Rt = (z2 - z1) * x * ts->x_plate_ohms; + Rt /= z1; + Rt = (Rt + 2047) >> 12; + + input_report_abs(input_dev, ABS_X, x); + input_report_abs(input_dev, ABS_Y, y); + input_report_abs(input_dev, ABS_PRESSURE, Rt); + input_sync(input_dev); + } +} + +static inline void ad7877_ts_event_release(struct ad7877 *ts) +{ + struct input_dev *input_dev = ts->input; + + input_report_abs(input_dev, ABS_PRESSURE, 0); + input_sync(input_dev); +} + +static void ad7877_timer(unsigned long handle) +{ + struct ad7877 *ts = (void *)handle; + + ad7877_ts_event_release(ts); +} + +static irqreturn_t ad7877_irq(int irq, void *handle) +{ + struct ad7877 *ts = handle; + unsigned long flags; + int status; + + /* + * The repeated conversion sequencer controlled by TMR kicked off + * too fast. We ignore the last and process the sample sequence + * currently in the queue. It can't be older than 9.4ms, and we + * need to avoid that ts->msg doesn't get issued twice while in work. + */ + + spin_lock_irqsave(&ts->lock, flags); + if (!ts->pending) { + ts->pending = 1; + + status = spi_async(ts->spi, &ts->msg); + if (status) + dev_err(&ts->spi->dev, "spi_sync --> %d\n", status); + } + spin_unlock_irqrestore(&ts->lock, flags); + + return IRQ_HANDLED; +} + +static void ad7877_callback(void *_ts) +{ + struct ad7877 *ts = _ts; + + spin_lock_irq(&ts->lock); + + ad7877_rx(ts); + ts->pending = 0; + mod_timer(&ts->timer, jiffies + TS_PEN_UP_TIMEOUT); + + spin_unlock_irq(&ts->lock); +} + +static void ad7877_disable(struct ad7877 *ts) +{ + mutex_lock(&ts->mutex); + + if (!ts->disabled) { + ts->disabled = 1; + disable_irq(ts->spi->irq); + + /* Wait for spi_async callback */ + while (ts->pending) + msleep(1); + + if (del_timer_sync(&ts->timer)) + ad7877_ts_event_release(ts); + } + + /* we know the chip's in lowpower mode since we always + * leave it that way after every request + */ + + mutex_unlock(&ts->mutex); +} + +static void ad7877_enable(struct ad7877 *ts) +{ + mutex_lock(&ts->mutex); + + if (ts->disabled) { + ts->disabled = 0; + enable_irq(ts->spi->irq); + } + + mutex_unlock(&ts->mutex); +} + +#define SHOW(name) static ssize_t \ +name ## _show(struct device *dev, struct device_attribute *attr, char *buf) \ +{ \ + struct ad7877 *ts = dev_get_drvdata(dev); \ + ssize_t v = ad7877_read_adc(ts->spi, \ + AD7877_READ_CHAN(name)); \ + if (v < 0) \ + return v; \ + return sprintf(buf, "%u\n", (unsigned) v); \ +} \ +static DEVICE_ATTR(name, S_IRUGO, name ## _show, NULL); + +SHOW(aux1) +SHOW(aux2) +SHOW(aux3) +SHOW(bat1) +SHOW(bat2) +SHOW(temp1) +SHOW(temp2) + +static ssize_t ad7877_disable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->disabled); +} + +static ssize_t ad7877_disable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + if (val) + ad7877_disable(ts); + else + ad7877_enable(ts); + + return count; +} + +static DEVICE_ATTR(disable, 0664, ad7877_disable_show, ad7877_disable_store); + +static ssize_t ad7877_dac_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->dac); +} + +static ssize_t ad7877_dac_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + mutex_lock(&ts->mutex); + ts->dac = val & 0xFF; + ad7877_write(ts->spi, AD7877_REG_DAC, (ts->dac << 4) | AD7877_DAC_CONF); + mutex_unlock(&ts->mutex); + + return count; +} + +static DEVICE_ATTR(dac, 0664, ad7877_dac_show, ad7877_dac_store); + +static ssize_t ad7877_gpio3_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->gpio3); +} + +static ssize_t ad7877_gpio3_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + mutex_lock(&ts->mutex); + ts->gpio3 = !!val; + ad7877_write(ts->spi, AD7877_REG_EXTWRITE, AD7877_EXTW_GPIO_DATA | + (ts->gpio4 << 4) | (ts->gpio3 << 5)); + mutex_unlock(&ts->mutex); + + return count; +} + +static DEVICE_ATTR(gpio3, 0664, ad7877_gpio3_show, ad7877_gpio3_store); + +static ssize_t ad7877_gpio4_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->gpio4); +} + +static ssize_t ad7877_gpio4_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7877 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + mutex_lock(&ts->mutex); + ts->gpio4 = !!val; + ad7877_write(ts->spi, AD7877_REG_EXTWRITE, AD7877_EXTW_GPIO_DATA | + (ts->gpio4 << 4) | (ts->gpio3 << 5)); + mutex_unlock(&ts->mutex); + + return count; +} + +static DEVICE_ATTR(gpio4, 0664, ad7877_gpio4_show, ad7877_gpio4_store); + +static struct attribute *ad7877_attributes[] = { + &dev_attr_temp1.attr, + &dev_attr_temp2.attr, + &dev_attr_aux1.attr, + &dev_attr_aux2.attr, + &dev_attr_bat1.attr, + &dev_attr_bat2.attr, + &dev_attr_disable.attr, + &dev_attr_dac.attr, + &dev_attr_gpio4.attr, + NULL +}; + +static const struct attribute_group ad7877_attr_group = { + .attrs = ad7877_attributes, +}; + +static void ad7877_setup_ts_def_msg(struct spi_device *spi, struct ad7877 *ts) +{ + struct spi_message *m; + int i; + + ts->cmd_crtl2 = AD7877_WRITEADD(AD7877_REG_CTRL2) | + AD7877_POL(ts->stopacq_polarity) | + AD7877_AVG(ts->averaging) | AD7877_PM(1) | + AD7877_TMR(ts->pen_down_acc_interval) | + AD7877_ACQ(ts->acquisition_time) | + AD7877_FCD(ts->first_conversion_delay); + + ad7877_write(spi, AD7877_REG_CTRL2, ts->cmd_crtl2); + + ts->cmd_crtl1 = AD7877_WRITEADD(AD7877_REG_CTRL1) | + AD7877_READADD(AD7877_REG_XPLUS-1) | + AD7877_MODE_SEQ1 | AD7877_DFR; + + ad7877_write(spi, AD7877_REG_CTRL1, ts->cmd_crtl1); + + ts->cmd_dummy = 0; + + m = &ts->msg; + + spi_message_init(m); + + m->complete = ad7877_callback; + m->context = ts; + + ts->xfer[0].tx_buf = &ts->cmd_crtl1; + ts->xfer[0].len = 2; + + spi_message_add_tail(&ts->xfer[0], m); + + ts->xfer[1].tx_buf = &ts->cmd_dummy; /* Send ZERO */ + ts->xfer[1].len = 2; + + spi_message_add_tail(&ts->xfer[1], m); + + for (i = 0; i < 11; i++) { + ts->xfer[i + 2].rx_buf = &ts->conversion_data[AD7877_SEQ_YPOS + i]; + ts->xfer[i + 2].len = 2; + spi_message_add_tail(&ts->xfer[i + 2], m); + } +} + +static int __devinit ad7877_probe(struct spi_device *spi) +{ + struct ad7877 *ts; + struct input_dev *input_dev; + struct ad7877_platform_data *pdata = spi->dev.platform_data; + int err; + u16 verify; + + if (!spi->irq) { + dev_dbg(&spi->dev, "no IRQ?\n"); + return -ENODEV; + } + + if (!pdata) { + dev_dbg(&spi->dev, "no platform data?\n"); + return -ENODEV; + } + + /* don't exceed max specified SPI CLK frequency */ + if (spi->max_speed_hz > MAX_SPI_FREQ_HZ) { + dev_dbg(&spi->dev, "SPI CLK %d Hz?\n",spi->max_speed_hz); + return -EINVAL; + } + + ts = kzalloc(sizeof(struct ad7877), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!ts || !input_dev) { + err = -ENOMEM; + goto err_free_mem; + } + + dev_set_drvdata(&spi->dev, ts); + ts->spi = spi; + ts->input = input_dev; + + setup_timer(&ts->timer, ad7877_timer, (unsigned long) ts); + mutex_init(&ts->mutex); + spin_lock_init(&ts->lock); + + ts->model = pdata->model ? : 7877; + ts->vref_delay_usecs = pdata->vref_delay_usecs ? : 100; + ts->x_plate_ohms = pdata->x_plate_ohms ? : 400; + ts->pressure_max = pdata->pressure_max ? : ~0; + + ts->stopacq_polarity = pdata->stopacq_polarity; + ts->first_conversion_delay = pdata->first_conversion_delay; + ts->acquisition_time = pdata->acquisition_time; + ts->averaging = pdata->averaging; + ts->pen_down_acc_interval = pdata->pen_down_acc_interval; + + snprintf(ts->phys, sizeof(ts->phys), "%s/input0", dev_name(&spi->dev)); + + input_dev->name = "AD7877 Touchscreen"; + input_dev->phys = ts->phys; + input_dev->dev.parent = &spi->dev; + + __set_bit(EV_ABS, input_dev->evbit); + __set_bit(ABS_X, input_dev->absbit); + __set_bit(ABS_Y, input_dev->absbit); + __set_bit(ABS_PRESSURE, input_dev->absbit); + + input_set_abs_params(input_dev, ABS_X, + pdata->x_min ? : 0, + pdata->x_max ? : MAX_12BIT, + 0, 0); + input_set_abs_params(input_dev, ABS_Y, + pdata->y_min ? : 0, + pdata->y_max ? : MAX_12BIT, + 0, 0); + input_set_abs_params(input_dev, ABS_PRESSURE, + pdata->pressure_min, pdata->pressure_max, 0, 0); + + ad7877_write(spi, AD7877_REG_SEQ1, AD7877_MM_SEQUENCE); + + verify = ad7877_read(spi, AD7877_REG_SEQ1); + + if (verify != AD7877_MM_SEQUENCE){ + dev_err(&spi->dev, "%s: Failed to probe %s\n", + dev_name(&spi->dev), input_dev->name); + err = -ENODEV; + goto err_free_mem; + } + + if (gpio3) + ad7877_write(spi, AD7877_REG_EXTWRITE, AD7877_EXTW_GPIO_3_CONF); + + ad7877_setup_ts_def_msg(spi, ts); + + /* Request AD7877 /DAV GPIO interrupt */ + + err = request_irq(spi->irq, ad7877_irq, IRQF_TRIGGER_FALLING | + IRQF_SAMPLE_RANDOM, spi->dev.driver->name, ts); + if (err) { + dev_dbg(&spi->dev, "irq %d busy?\n", spi->irq); + goto err_free_mem; + } + + err = sysfs_create_group(&spi->dev.kobj, &ad7877_attr_group); + if (err) + goto err_free_irq; + + err = device_create_file(&spi->dev, + gpio3 ? &dev_attr_gpio3 : &dev_attr_aux3); + if (err) + goto err_remove_attr_group; + + err = input_register_device(input_dev); + if (err) + goto err_remove_attr; + + return 0; + +err_remove_attr: + device_remove_file(&spi->dev, + gpio3 ? &dev_attr_gpio3 : &dev_attr_aux3); +err_remove_attr_group: + sysfs_remove_group(&spi->dev.kobj, &ad7877_attr_group); +err_free_irq: + free_irq(spi->irq, ts); +err_free_mem: + input_free_device(input_dev); + kfree(ts); + dev_set_drvdata(&spi->dev, NULL); + return err; +} + +static int __devexit ad7877_remove(struct spi_device *spi) +{ + struct ad7877 *ts = dev_get_drvdata(&spi->dev); + + sysfs_remove_group(&spi->dev.kobj, &ad7877_attr_group); + device_remove_file(&spi->dev, + gpio3 ? &dev_attr_gpio3 : &dev_attr_aux3); + + ad7877_disable(ts); + free_irq(ts->spi->irq, ts); + + input_unregister_device(ts->input); + kfree(ts); + + dev_dbg(&spi->dev, "unregistered touchscreen\n"); + dev_set_drvdata(&spi->dev, NULL); + + return 0; +} + +#ifdef CONFIG_PM +static int ad7877_suspend(struct spi_device *spi, pm_message_t message) +{ + struct ad7877 *ts = dev_get_drvdata(&spi->dev); + + ad7877_disable(ts); + + return 0; +} + +static int ad7877_resume(struct spi_device *spi) +{ + struct ad7877 *ts = dev_get_drvdata(&spi->dev); + + ad7877_enable(ts); + + return 0; +} +#else +#define ad7877_suspend NULL +#define ad7877_resume NULL +#endif + +static struct spi_driver ad7877_driver = { + .driver = { + .name = "ad7877", + .bus = &spi_bus_type, + .owner = THIS_MODULE, + }, + .probe = ad7877_probe, + .remove = __devexit_p(ad7877_remove), + .suspend = ad7877_suspend, + .resume = ad7877_resume, +}; + +static int __init ad7877_init(void) +{ + return spi_register_driver(&ad7877_driver); +} +module_init(ad7877_init); + +static void __exit ad7877_exit(void) +{ + spi_unregister_driver(&ad7877_driver); +} +module_exit(ad7877_exit); + +MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>"); +MODULE_DESCRIPTION("AD7877 touchscreen Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c new file mode 100644 index 00000000000..ea4c61d6868 --- /dev/null +++ b/drivers/input/touchscreen/ad7879.c @@ -0,0 +1,782 @@ +/* + * Copyright (C) 2008 Michael Hennerich, Analog Devices Inc. + * + * Description: AD7879 based touchscreen, and GPIO driver (I2C/SPI Interface) + * + * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see the file COPYING, or write + * to the Free Software Foundation, Inc., + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + * History: + * Copyright (c) 2005 David Brownell + * Copyright (c) 2006 Nokia Corporation + * Various changes: Imre Deak <imre.deak@nokia.com> + * + * Using code from: + * - corgi_ts.c + * Copyright (C) 2004-2005 Richard Purdie + * - omap_ts.[hc], ads7846.h, ts_osk.c + * Copyright (C) 2002 MontaVista Software + * Copyright (C) 2004 Texas Instruments + * Copyright (C) 2005 Dirk Behme + * - ad7877.c + * Copyright (C) 2006-2008 Analog Devices Inc. + */ + +#include <linux/device.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/slab.h> +#include <linux/workqueue.h> +#include <linux/spi/spi.h> +#include <linux/i2c.h> + +#include <linux/spi/ad7879.h> + +#define AD7879_REG_ZEROS 0 +#define AD7879_REG_CTRL1 1 +#define AD7879_REG_CTRL2 2 +#define AD7879_REG_CTRL3 3 +#define AD7879_REG_AUX1HIGH 4 +#define AD7879_REG_AUX1LOW 5 +#define AD7879_REG_TEMP1HIGH 6 +#define AD7879_REG_TEMP1LOW 7 +#define AD7879_REG_XPLUS 8 +#define AD7879_REG_YPLUS 9 +#define AD7879_REG_Z1 10 +#define AD7879_REG_Z2 11 +#define AD7879_REG_AUXVBAT 12 +#define AD7879_REG_TEMP 13 +#define AD7879_REG_REVID 14 + +/* Control REG 1 */ +#define AD7879_TMR(x) ((x & 0xFF) << 0) +#define AD7879_ACQ(x) ((x & 0x3) << 8) +#define AD7879_MODE_NOC (0 << 10) /* Do not convert */ +#define AD7879_MODE_SCC (1 << 10) /* Single channel conversion */ +#define AD7879_MODE_SEQ0 (2 << 10) /* Sequence 0 in Slave Mode */ +#define AD7879_MODE_SEQ1 (3 << 10) /* Sequence 1 in Master Mode */ +#define AD7879_MODE_INT (1 << 15) /* PENIRQ disabled INT enabled */ + +/* Control REG 2 */ +#define AD7879_FCD(x) ((x & 0x3) << 0) +#define AD7879_RESET (1 << 4) +#define AD7879_MFS(x) ((x & 0x3) << 5) +#define AD7879_AVG(x) ((x & 0x3) << 7) +#define AD7879_SER (1 << 9) /* non-differential */ +#define AD7879_DFR (0 << 9) /* differential */ +#define AD7879_GPIOPOL (1 << 10) +#define AD7879_GPIODIR (1 << 11) +#define AD7879_GPIO_DATA (1 << 12) +#define AD7879_GPIO_EN (1 << 13) +#define AD7879_PM(x) ((x & 0x3) << 14) +#define AD7879_PM_SHUTDOWN (0) +#define AD7879_PM_DYN (1) +#define AD7879_PM_FULLON (2) + +/* Control REG 3 */ +#define AD7879_TEMPMASK_BIT (1<<15) +#define AD7879_AUXVBATMASK_BIT (1<<14) +#define AD7879_INTMODE_BIT (1<<13) +#define AD7879_GPIOALERTMASK_BIT (1<<12) +#define AD7879_AUXLOW_BIT (1<<11) +#define AD7879_AUXHIGH_BIT (1<<10) +#define AD7879_TEMPLOW_BIT (1<<9) +#define AD7879_TEMPHIGH_BIT (1<<8) +#define AD7879_YPLUS_BIT (1<<7) +#define AD7879_XPLUS_BIT (1<<6) +#define AD7879_Z1_BIT (1<<5) +#define AD7879_Z2_BIT (1<<4) +#define AD7879_AUX_BIT (1<<3) +#define AD7879_VBAT_BIT (1<<2) +#define AD7879_TEMP_BIT (1<<1) + +enum { + AD7879_SEQ_XPOS = 0, + AD7879_SEQ_YPOS = 1, + AD7879_SEQ_Z1 = 2, + AD7879_SEQ_Z2 = 3, + AD7879_NR_SENSE = 4, +}; + +#define MAX_12BIT ((1<<12)-1) +#define TS_PEN_UP_TIMEOUT msecs_to_jiffies(50) + +#if defined(CONFIG_TOUCHSCREEN_AD7879_SPI) || defined(CONFIG_TOUCHSCREEN_AD7879_SPI_MODULE) +#define AD7879_DEVID 0x7A +typedef struct spi_device bus_device; +#elif defined(CONFIG_TOUCHSCREEN_AD7879_I2C) || defined(CONFIG_TOUCHSCREEN_AD7879_I2C_MODULE) +#define AD7879_DEVID 0x79 +typedef struct i2c_client bus_device; +#endif + +struct ad7879 { + bus_device *bus; + struct input_dev *input; + struct work_struct work; + struct timer_list timer; + + struct mutex mutex; + unsigned disabled:1; /* P: mutex */ + +#if defined(CONFIG_TOUCHSCREEN_AD7879_SPI) || defined(CONFIG_TOUCHSCREEN_AD7879_SPI_MODULE) + struct spi_message msg; + struct spi_transfer xfer[AD7879_NR_SENSE + 1]; + u16 cmd; +#endif + u16 conversion_data[AD7879_NR_SENSE]; + char phys[32]; + u8 first_conversion_delay; + u8 acquisition_time; + u8 averaging; + u8 pen_down_acc_interval; + u8 median; + u16 x_plate_ohms; + u16 pressure_max; + u16 gpio_init; + u16 cmd_crtl1; + u16 cmd_crtl2; + u16 cmd_crtl3; + unsigned gpio:1; +}; + +static int ad7879_read(bus_device *, u8); +static int ad7879_write(bus_device *, u8, u16); +static void ad7879_collect(struct ad7879 *); + +static void ad7879_report(struct ad7879 *ts) +{ + struct input_dev *input_dev = ts->input; + unsigned Rt; + u16 x, y, z1, z2; + + x = ts->conversion_data[AD7879_SEQ_XPOS] & MAX_12BIT; + y = ts->conversion_data[AD7879_SEQ_YPOS] & MAX_12BIT; + z1 = ts->conversion_data[AD7879_SEQ_Z1] & MAX_12BIT; + z2 = ts->conversion_data[AD7879_SEQ_Z2] & MAX_12BIT; + + /* + * The samples processed here are already preprocessed by the AD7879. + * The preprocessing function consists of a median and an averaging filter. + * The combination of these two techniques provides a robust solution, + * discarding the spurious noise in the signal and keeping only the data of interest. + * The size of both filters is programmable. (dev.platform_data, see linux/spi/ad7879.h) + * Other user-programmable conversion controls include variable acquisition time, + * and first conversion delay. Up to 16 averages can be taken per conversion. + */ + + if (likely(x && z1)) { + /* compute touch pressure resistance using equation #1 */ + Rt = (z2 - z1) * x * ts->x_plate_ohms; + Rt /= z1; + Rt = (Rt + 2047) >> 12; + + input_report_abs(input_dev, ABS_X, x); + input_report_abs(input_dev, ABS_Y, y); + input_report_abs(input_dev, ABS_PRESSURE, Rt); + input_sync(input_dev); + } +} + +static void ad7879_work(struct work_struct *work) +{ + struct ad7879 *ts = container_of(work, struct ad7879, work); + + /* use keventd context to read the result registers */ + ad7879_collect(ts); + ad7879_report(ts); + mod_timer(&ts->timer, jiffies + TS_PEN_UP_TIMEOUT); +} + +static void ad7879_ts_event_release(struct ad7879 *ts) +{ + struct input_dev *input_dev = ts->input; + + input_report_abs(input_dev, ABS_PRESSURE, 0); + input_sync(input_dev); +} + +static void ad7879_timer(unsigned long handle) +{ + struct ad7879 *ts = (void *)handle; + + ad7879_ts_event_release(ts); +} + +static irqreturn_t ad7879_irq(int irq, void *handle) +{ + struct ad7879 *ts = handle; + + /* The repeated conversion sequencer controlled by TMR kicked off too fast. + * We ignore the last and process the sample sequence currently in the queue. + * It can't be older than 9.4ms + */ + + if (!work_pending(&ts->work)) + schedule_work(&ts->work); + + return IRQ_HANDLED; +} + +static void ad7879_setup(struct ad7879 *ts) +{ + ts->cmd_crtl3 = AD7879_YPLUS_BIT | + AD7879_XPLUS_BIT | + AD7879_Z2_BIT | + AD7879_Z1_BIT | + AD7879_TEMPMASK_BIT | + AD7879_AUXVBATMASK_BIT | + AD7879_GPIOALERTMASK_BIT; + + ts->cmd_crtl2 = AD7879_PM(AD7879_PM_DYN) | AD7879_DFR | + AD7879_AVG(ts->averaging) | + AD7879_MFS(ts->median) | + AD7879_FCD(ts->first_conversion_delay) | + ts->gpio_init; + + ts->cmd_crtl1 = AD7879_MODE_INT | AD7879_MODE_SEQ1 | + AD7879_ACQ(ts->acquisition_time) | + AD7879_TMR(ts->pen_down_acc_interval); + + ad7879_write(ts->bus, AD7879_REG_CTRL2, ts->cmd_crtl2); + ad7879_write(ts->bus, AD7879_REG_CTRL3, ts->cmd_crtl3); + ad7879_write(ts->bus, AD7879_REG_CTRL1, ts->cmd_crtl1); +} + +static void ad7879_disable(struct ad7879 *ts) +{ + mutex_lock(&ts->mutex); + + if (!ts->disabled) { + + ts->disabled = 1; + disable_irq(ts->bus->irq); + + cancel_work_sync(&ts->work); + + if (del_timer_sync(&ts->timer)) + ad7879_ts_event_release(ts); + + ad7879_write(ts->bus, AD7879_REG_CTRL2, + AD7879_PM(AD7879_PM_SHUTDOWN)); + } + + mutex_unlock(&ts->mutex); +} + +static void ad7879_enable(struct ad7879 *ts) +{ + mutex_lock(&ts->mutex); + + if (ts->disabled) { + ad7879_setup(ts); + ts->disabled = 0; + enable_irq(ts->bus->irq); + } + + mutex_unlock(&ts->mutex); +} + +static ssize_t ad7879_disable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7879 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->disabled); +} + +static ssize_t ad7879_disable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7879 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + if (val) + ad7879_disable(ts); + else + ad7879_enable(ts); + + return count; +} + +static DEVICE_ATTR(disable, 0664, ad7879_disable_show, ad7879_disable_store); + +static ssize_t ad7879_gpio_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ad7879 *ts = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", ts->gpio); +} + +static ssize_t ad7879_gpio_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ad7879 *ts = dev_get_drvdata(dev); + unsigned long val; + int error; + + error = strict_strtoul(buf, 10, &val); + if (error) + return error; + + mutex_lock(&ts->mutex); + ts->gpio = !!val; + error = ad7879_write(ts->bus, AD7879_REG_CTRL2, + ts->gpio ? + ts->cmd_crtl2 & ~AD7879_GPIO_DATA : + ts->cmd_crtl2 | AD7879_GPIO_DATA); + mutex_unlock(&ts->mutex); + + return error ? : count; +} + +static DEVICE_ATTR(gpio, 0664, ad7879_gpio_show, ad7879_gpio_store); + +static struct attribute *ad7879_attributes[] = { + &dev_attr_disable.attr, + &dev_attr_gpio.attr, + NULL +}; + +static const struct attribute_group ad7879_attr_group = { + .attrs = ad7879_attributes, +}; + +static int __devinit ad7879_construct(bus_device *bus, struct ad7879 *ts) +{ + struct input_dev *input_dev; + struct ad7879_platform_data *pdata = bus->dev.platform_data; + int err; + u16 revid; + + if (!bus->irq) { + dev_err(&bus->dev, "no IRQ?\n"); + return -ENODEV; + } + + if (!pdata) { + dev_err(&bus->dev, "no platform data?\n"); + return -ENODEV; + } + + input_dev = input_allocate_device(); + if (!input_dev) + return -ENOMEM; + + ts->input = input_dev; + + setup_timer(&ts->timer, ad7879_timer, (unsigned long) ts); + INIT_WORK(&ts->work, ad7879_work); + mutex_init(&ts->mutex); + + ts->x_plate_ohms = pdata->x_plate_ohms ? : 400; + ts->pressure_max = pdata->pressure_max ? : ~0; + + ts->first_conversion_delay = pdata->first_conversion_delay; + ts->acquisition_time = pdata->acquisition_time; + ts->averaging = pdata->averaging; + ts->pen_down_acc_interval = pdata->pen_down_acc_interval; + ts->median = pdata->median; + + if (pdata->gpio_output) + ts->gpio_init = AD7879_GPIO_EN | + (pdata->gpio_default ? 0 : AD7879_GPIO_DATA); + else + ts->gpio_init = AD7879_GPIO_EN | AD7879_GPIODIR; + + snprintf(ts->phys, sizeof(ts->phys), "%s/input0", dev_name(&bus->dev)); + + input_dev->name = "AD7879 Touchscreen"; + input_dev->phys = ts->phys; + input_dev->dev.parent = &bus->dev; + + __set_bit(EV_ABS, input_dev->evbit); + __set_bit(ABS_X, input_dev->absbit); + __set_bit(ABS_Y, input_dev->absbit); + __set_bit(ABS_PRESSURE, input_dev->absbit); + + input_set_abs_params(input_dev, ABS_X, + pdata->x_min ? : 0, + pdata->x_max ? : MAX_12BIT, + 0, 0); + input_set_abs_params(input_dev, ABS_Y, + pdata->y_min ? : 0, + pdata->y_max ? : MAX_12BIT, + 0, 0); + input_set_abs_params(input_dev, ABS_PRESSURE, + pdata->pressure_min, pdata->pressure_max, 0, 0); + + err = ad7879_write(bus, AD7879_REG_CTRL2, AD7879_RESET); + + if (err < 0) { + dev_err(&bus->dev, "Failed to write %s\n", input_dev->name); + goto err_free_mem; + } + + revid = ad7879_read(bus, AD7879_REG_REVID); + + if ((revid & 0xFF) != AD7879_DEVID) { + dev_err(&bus->dev, "Failed to probe %s\n", input_dev->name); + err = -ENODEV; + goto err_free_mem; + } + + ad7879_setup(ts); + + err = request_irq(bus->irq, ad7879_irq, + IRQF_TRIGGER_FALLING | IRQF_SAMPLE_RANDOM, + bus->dev.driver->name, ts); + + if (err) { + dev_err(&bus->dev, "irq %d busy?\n", bus->irq); + goto err_free_mem; + } + + err = sysfs_create_group(&bus->dev.kobj, &ad7879_attr_group); + if (err) + goto err_free_irq; + + err = input_register_device(input_dev); + if (err) + goto err_remove_attr; + + dev_info(&bus->dev, "Rev.%d touchscreen, irq %d\n", + revid >> 8, bus->irq); + + return 0; + +err_remove_attr: + sysfs_remove_group(&bus->dev.kobj, &ad7879_attr_group); +err_free_irq: + free_irq(bus->irq, ts); +err_free_mem: + input_free_device(input_dev); + + return err; +} + +static int __devexit ad7879_destroy(bus_device *bus, struct ad7879 *ts) +{ + ad7879_disable(ts); + sysfs_remove_group(&ts->bus->dev.kobj, &ad7879_attr_group); + free_irq(ts->bus->irq, ts); + input_unregister_device(ts->input); + dev_dbg(&bus->dev, "unregistered touchscreen\n"); + + return 0; +} + +#ifdef CONFIG_PM +static int ad7879_suspend(bus_device *bus, pm_message_t message) +{ + struct ad7879 *ts = dev_get_drvdata(&bus->dev); + + ad7879_disable(ts); + + return 0; +} + +static int ad7879_resume(bus_device *bus) +{ + struct ad7879 *ts = dev_get_drvdata(&bus->dev); + + ad7879_enable(ts); + + return 0; +} +#else +#define ad7879_suspend NULL +#define ad7879_resume NULL +#endif + +#if defined(CONFIG_TOUCHSCREEN_AD7879_SPI) || defined(CONFIG_TOUCHSCREEN_AD7879_SPI_MODULE) +#define MAX_SPI_FREQ_HZ 5000000 +#define AD7879_CMD_MAGIC 0xE000 +#define AD7879_CMD_READ (1 << 10) +#define AD7879_WRITECMD(reg) (AD7879_CMD_MAGIC | (reg & 0xF)) +#define AD7879_READCMD(reg) (AD7879_CMD_MAGIC | AD7879_CMD_READ | (reg & 0xF)) + +struct ser_req { + u16 command; + u16 data; + struct spi_message msg; + struct spi_transfer xfer[2]; +}; + +/* + * ad7879_read/write are only used for initial setup and for sysfs controls. + * The main traffic is done in ad7879_collect(). + */ + +static int ad7879_read(struct spi_device *spi, u8 reg) +{ + struct ser_req *req; + int status, ret; + + req = kzalloc(sizeof *req, GFP_KERNEL); + if (!req) + return -ENOMEM; + + spi_message_init(&req->msg); + + req->command = (u16) AD7879_READCMD(reg); + req->xfer[0].tx_buf = &req->command; + req->xfer[0].len = 2; + + req->xfer[1].rx_buf = &req->data; + req->xfer[1].len = 2; + + spi_message_add_tail(&req->xfer[0], &req->msg); + spi_message_add_tail(&req->xfer[1], &req->msg); + + status = spi_sync(spi, &req->msg); + ret = status ? : req->data; + + kfree(req); + + return ret; +} + +static int ad7879_write(struct spi_device *spi, u8 reg, u16 val) +{ + struct ser_req *req; + int status; + + req = kzalloc(sizeof *req, GFP_KERNEL); + if (!req) + return -ENOMEM; + + spi_message_init(&req->msg); + + req->command = (u16) AD7879_WRITECMD(reg); + req->xfer[0].tx_buf = &req->command; + req->xfer[0].len = 2; + + req->data = val; + req->xfer[1].tx_buf = &req->data; + req->xfer[1].len = 2; + + spi_message_add_tail(&req->xfer[0], &req->msg); + spi_message_add_tail(&req->xfer[1], &req->msg); + + status = spi_sync(spi, &req->msg); + + kfree(req); + + return status; +} + +static void ad7879_collect(struct ad7879 *ts) +{ + int status = spi_sync(ts->bus, &ts->msg); + + if (status) + dev_err(&ts->bus->dev, "spi_sync --> %d\n", status); +} + +static void ad7879_setup_ts_def_msg(struct ad7879 *ts) +{ + struct spi_message *m; + int i; + + ts->cmd = (u16) AD7879_READCMD(AD7879_REG_XPLUS); + + m = &ts->msg; + spi_message_init(m); + ts->xfer[0].tx_buf = &ts->cmd; + ts->xfer[0].len = 2; + + spi_message_add_tail(&ts->xfer[0], m); + + for (i = 0; i < AD7879_NR_SENSE; i++) { + ts->xfer[i + 1].rx_buf = &ts->conversion_data[i]; + ts->xfer[i + 1].len = 2; + spi_message_add_tail(&ts->xfer[i + 1], m); + } +} + +static int __devinit ad7879_probe(struct spi_device *spi) +{ + struct ad7879 *ts; + int error; + + /* don't exceed max specified SPI CLK frequency */ + if (spi->max_speed_hz > MAX_SPI_FREQ_HZ) { + dev_err(&spi->dev, "SPI CLK %d Hz?\n", spi->max_speed_hz); + return -EINVAL; + } + + ts = kzalloc(sizeof(struct ad7879), GFP_KERNEL); + if (!ts) + return -ENOMEM; + + dev_set_drvdata(&spi->dev, ts); + ts->bus = spi; + + ad7879_setup_ts_def_msg(ts); + + error = ad7879_construct(spi, ts); + if (error) { + dev_set_drvdata(&spi->dev, NULL); + kfree(ts); + } + + return 0; +} + +static int __devexit ad7879_remove(struct spi_device *spi) +{ + struct ad7879 *ts = dev_get_drvdata(&spi->dev); + + ad7879_destroy(spi, ts); + dev_set_drvdata(&spi->dev, NULL); + kfree(ts); + + return 0; +} + +static struct spi_driver ad7879_driver = { + .driver = { + .name = "ad7879", + .bus = &spi_bus_type, + .owner = THIS_MODULE, + }, + .probe = ad7879_probe, + .remove = __devexit_p(ad7879_remove), + .suspend = ad7879_suspend, + .resume = ad7879_resume, +}; + +static int __init ad7879_init(void) +{ + return spi_register_driver(&ad7879_driver); +} +module_init(ad7879_init); + +static void __exit ad7879_exit(void) +{ + spi_unregister_driver(&ad7879_driver); +} +module_exit(ad7879_exit); + +#elif defined(CONFIG_TOUCHSCREEN_AD7879_I2C) || defined(CONFIG_TOUCHSCREEN_AD7879_I2C_MODULE) + +/* All registers are word-sized. + * AD7879 uses a high-byte first convention. + */ +static int ad7879_read(struct i2c_client *client, u8 reg) +{ + return swab16(i2c_smbus_read_word_data(client, reg)); +} + +static int ad7879_write(struct i2c_client *client, u8 reg, u16 val) +{ + return i2c_smbus_write_word_data(client, reg, swab16(val)); +} + +static void ad7879_collect(struct ad7879 *ts) +{ + int i; + + for (i = 0; i < AD7879_NR_SENSE; i++) + ts->conversion_data[i] = ad7879_read(ts->bus, + AD7879_REG_XPLUS + i); +} + +static int __devinit ad7879_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct ad7879 *ts; + int error; + + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_WORD_DATA)) { + dev_err(&client->dev, "SMBUS Word Data not Supported\n"); + return -EIO; + } + + ts = kzalloc(sizeof(struct ad7879), GFP_KERNEL); + if (!ts) + return -ENOMEM; + + i2c_set_clientdata(client, ts); + ts->bus = client; + + error = ad7879_construct(client, ts); + if (error) { + i2c_set_clientdata(client, NULL); + kfree(ts); + } + + return 0; +} + +static int __devexit ad7879_remove(struct i2c_client *client) +{ + struct ad7879 *ts = dev_get_drvdata(&client->dev); + + ad7879_destroy(client, ts); + i2c_set_clientdata(client, NULL); + kfree(ts); + + return 0; +} + +static const struct i2c_device_id ad7879_id[] = { + { "ad7879", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, ad7879_id); + +static struct i2c_driver ad7879_driver = { + .driver = { + .name = "ad7879", + .owner = THIS_MODULE, + }, + .probe = ad7879_probe, + .remove = __devexit_p(ad7879_remove), + .suspend = ad7879_suspend, + .resume = ad7879_resume, + .id_table = ad7879_id, +}; + +static int __init ad7879_init(void) +{ + return i2c_add_driver(&ad7879_driver); +} +module_init(ad7879_init); + +static void __exit ad7879_exit(void) +{ + i2c_del_driver(&ad7879_driver); +} +module_exit(ad7879_exit); +#endif + +MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>"); +MODULE_DESCRIPTION("AD7879(-1) touchscreen Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/touchscreen/mainstone-wm97xx.c b/drivers/input/touchscreen/mainstone-wm97xx.c index 1d11e2be9ef..dfa6a84ab50 100644 --- a/drivers/input/touchscreen/mainstone-wm97xx.c +++ b/drivers/input/touchscreen/mainstone-wm97xx.c @@ -162,6 +162,7 @@ static int wm97xx_acc_pen_down(struct wm97xx *wm) input_report_abs(wm->input_dev, ABS_X, x & 0xfff); input_report_abs(wm->input_dev, ABS_Y, y & 0xfff); input_report_abs(wm->input_dev, ABS_PRESSURE, p & 0xfff); + input_report_key(wm->input_dev, BTN_TOUCH, (p != 0)); input_sync(wm->input_dev); reads++; } while (reads < cinfo[sp_idx].reads); @@ -245,7 +246,7 @@ static void wm97xx_irq_enable(struct wm97xx *wm, int enable) if (enable) enable_irq(wm->pen_irq); else - disable_irq(wm->pen_irq); + disable_irq_nosync(wm->pen_irq); } static struct wm97xx_mach_ops mainstone_mach_ops = { diff --git a/drivers/input/touchscreen/ucb1400_ts.c b/drivers/input/touchscreen/ucb1400_ts.c index 54986627def..e868264fe79 100644 --- a/drivers/input/touchscreen/ucb1400_ts.c +++ b/drivers/input/touchscreen/ucb1400_ts.c @@ -151,12 +151,14 @@ static void ucb1400_ts_evt_add(struct input_dev *idev, u16 pressure, u16 x, u16 input_report_abs(idev, ABS_X, x); input_report_abs(idev, ABS_Y, y); input_report_abs(idev, ABS_PRESSURE, pressure); + input_report_key(idev, BTN_TOUCH, 1); input_sync(idev); } static void ucb1400_ts_event_release(struct input_dev *idev) { input_report_abs(idev, ABS_PRESSURE, 0); + input_report_key(idev, BTN_TOUCH, 0); input_sync(idev); } @@ -377,7 +379,8 @@ static int ucb1400_ts_probe(struct platform_device *dev) ucb->ts_idev->id.product = ucb->id; ucb->ts_idev->open = ucb1400_ts_open; ucb->ts_idev->close = ucb1400_ts_close; - ucb->ts_idev->evbit[0] = BIT_MASK(EV_ABS); + ucb->ts_idev->evbit[0] = BIT_MASK(EV_ABS) | BIT_MASK(EV_KEY); + ucb->ts_idev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); ucb1400_adc_enable(ucb->ac97); x_res = ucb1400_ts_read_xres(ucb); diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c index d15aa11d705..cec480bffe3 100644 --- a/drivers/input/touchscreen/wm97xx-core.c +++ b/drivers/input/touchscreen/wm97xx-core.c @@ -409,6 +409,7 @@ static int wm97xx_read_samples(struct wm97xx *wm) wm->pen_is_down = 0; dev_dbg(wm->dev, "pen up\n"); input_report_abs(wm->input_dev, ABS_PRESSURE, 0); + input_report_key(wm->input_dev, BTN_TOUCH, 0); input_sync(wm->input_dev); } else if (!(rc & RC_AGAIN)) { /* We need high frequency updates only while @@ -433,6 +434,7 @@ static int wm97xx_read_samples(struct wm97xx *wm) input_report_abs(wm->input_dev, ABS_X, data.x & 0xfff); input_report_abs(wm->input_dev, ABS_Y, data.y & 0xfff); input_report_abs(wm->input_dev, ABS_PRESSURE, data.p & 0xfff); + input_report_key(wm->input_dev, BTN_TOUCH, 1); input_sync(wm->input_dev); wm->pen_is_down = 1; wm->ts_reader_interval = wm->ts_reader_min_interval; @@ -628,18 +630,21 @@ static int wm97xx_probe(struct device *dev) wm->input_dev->phys = "wm97xx"; wm->input_dev->open = wm97xx_ts_input_open; wm->input_dev->close = wm97xx_ts_input_close; - set_bit(EV_ABS, wm->input_dev->evbit); - set_bit(ABS_X, wm->input_dev->absbit); - set_bit(ABS_Y, wm->input_dev->absbit); - set_bit(ABS_PRESSURE, wm->input_dev->absbit); + + __set_bit(EV_ABS, wm->input_dev->evbit); + __set_bit(EV_KEY, wm->input_dev->evbit); + __set_bit(BTN_TOUCH, wm->input_dev->keybit); + input_set_abs_params(wm->input_dev, ABS_X, abs_x[0], abs_x[1], abs_x[2], 0); input_set_abs_params(wm->input_dev, ABS_Y, abs_y[0], abs_y[1], abs_y[2], 0); input_set_abs_params(wm->input_dev, ABS_PRESSURE, abs_p[0], abs_p[1], abs_p[2], 0); + input_set_drvdata(wm->input_dev, wm); wm->input_dev->dev.parent = dev; + ret = input_register_device(wm->input_dev); if (ret < 0) goto dev_alloc_err; diff --git a/drivers/input/touchscreen/zylonite-wm97xx.c b/drivers/input/touchscreen/zylonite-wm97xx.c new file mode 100644 index 00000000000..41e4359c277 --- /dev/null +++ b/drivers/input/touchscreen/zylonite-wm97xx.c @@ -0,0 +1,240 @@ +/* + * zylonite-wm97xx.c -- Zylonite Continuous Touch screen driver + * + * Copyright 2004, 2007, 2008 Wolfson Microelectronics PLC. + * Author: Mark Brown <broonie@opensource.wolfsonmicro.com> + * Parts Copyright : Ian Molton <spyro@f2s.com> + * Andrew Zabolotny <zap@homelink.ru> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * Notes: + * This is a wm97xx extended touch driver supporting interrupt driven + * and continuous operation on Marvell Zylonite development systems + * (which have a WM9713 on board). + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/wm97xx.h> + +#include <mach/hardware.h> +#include <mach/mfp.h> +#include <mach/regs-ac97.h> + +struct continuous { + u16 id; /* codec id */ + u8 code; /* continuous code */ + u8 reads; /* number of coord reads per read cycle */ + u32 speed; /* number of coords per second */ +}; + +#define WM_READS(sp) ((sp / HZ) + 1) + +static const struct continuous cinfo[] = { + { WM9713_ID2, 0, WM_READS(94), 94 }, + { WM9713_ID2, 1, WM_READS(120), 120 }, + { WM9713_ID2, 2, WM_READS(154), 154 }, + { WM9713_ID2, 3, WM_READS(188), 188 }, +}; + +/* continuous speed index */ +static int sp_idx; + +/* + * Pen sampling frequency (Hz) in continuous mode. + */ +static int cont_rate = 200; +module_param(cont_rate, int, 0); +MODULE_PARM_DESC(cont_rate, "Sampling rate in continuous mode (Hz)"); + +/* + * Pressure readback. + * + * Set to 1 to read back pen down pressure + */ +static int pressure; +module_param(pressure, int, 0); +MODULE_PARM_DESC(pressure, "Pressure readback (1 = pressure, 0 = no pressure)"); + +/* + * AC97 touch data slot. + * + * Touch screen readback data ac97 slot + */ +static int ac97_touch_slot = 5; +module_param(ac97_touch_slot, int, 0); +MODULE_PARM_DESC(ac97_touch_slot, "Touch screen data slot AC97 number"); + + +/* flush AC97 slot 5 FIFO machines */ +static void wm97xx_acc_pen_up(struct wm97xx *wm) +{ + int i; + + msleep(1); + + for (i = 0; i < 16; i++) + MODR; +} + +static int wm97xx_acc_pen_down(struct wm97xx *wm) +{ + u16 x, y, p = 0x100 | WM97XX_ADCSEL_PRES; + int reads = 0; + static u16 last, tries; + + /* When the AC97 queue has been drained we need to allow time + * to buffer up samples otherwise we end up spinning polling + * for samples. The controller can't have a suitably low + * threashold set to use the notifications it gives. + */ + msleep(1); + + if (tries > 5) { + tries = 0; + return RC_PENUP; + } + + x = MODR; + if (x == last) { + tries++; + return RC_AGAIN; + } + last = x; + do { + if (reads) + x = MODR; + y = MODR; + if (pressure) + p = MODR; + + /* are samples valid */ + if ((x & WM97XX_ADCSRC_MASK) != WM97XX_ADCSEL_X || + (y & WM97XX_ADCSRC_MASK) != WM97XX_ADCSEL_Y || + (p & WM97XX_ADCSRC_MASK) != WM97XX_ADCSEL_PRES) + goto up; + + /* coordinate is good */ + tries = 0; + input_report_abs(wm->input_dev, ABS_X, x & 0xfff); + input_report_abs(wm->input_dev, ABS_Y, y & 0xfff); + input_report_abs(wm->input_dev, ABS_PRESSURE, p & 0xfff); + input_report_key(wm->input_dev, BTN_TOUCH, (p != 0)); + input_sync(wm->input_dev); + reads++; + } while (reads < cinfo[sp_idx].reads); +up: + return RC_PENDOWN | RC_AGAIN; +} + +static int wm97xx_acc_startup(struct wm97xx *wm) +{ + int idx; + + /* check we have a codec */ + if (wm->ac97 == NULL) + return -ENODEV; + + /* Go you big red fire engine */ + for (idx = 0; idx < ARRAY_SIZE(cinfo); idx++) { + if (wm->id != cinfo[idx].id) + continue; + sp_idx = idx; + if (cont_rate <= cinfo[idx].speed) + break; + } + wm->acc_rate = cinfo[sp_idx].code; + wm->acc_slot = ac97_touch_slot; + dev_info(wm->dev, + "zylonite accelerated touchscreen driver, %d samples/sec\n", + cinfo[sp_idx].speed); + + return 0; +} + +static void wm97xx_irq_enable(struct wm97xx *wm, int enable) +{ + if (enable) + enable_irq(wm->pen_irq); + else + disable_irq_nosync(wm->pen_irq); +} + +static struct wm97xx_mach_ops zylonite_mach_ops = { + .acc_enabled = 1, + .acc_pen_up = wm97xx_acc_pen_up, + .acc_pen_down = wm97xx_acc_pen_down, + .acc_startup = wm97xx_acc_startup, + .irq_enable = wm97xx_irq_enable, + .irq_gpio = WM97XX_GPIO_2, +}; + +static int zylonite_wm97xx_probe(struct platform_device *pdev) +{ + struct wm97xx *wm = platform_get_drvdata(pdev); + int gpio_touch_irq; + + if (cpu_is_pxa320()) + gpio_touch_irq = mfp_to_gpio(MFP_PIN_GPIO15); + else + gpio_touch_irq = mfp_to_gpio(MFP_PIN_GPIO26); + + wm->pen_irq = IRQ_GPIO(gpio_touch_irq); + set_irq_type(IRQ_GPIO(gpio_touch_irq), IRQ_TYPE_EDGE_BOTH); + + wm97xx_config_gpio(wm, WM97XX_GPIO_13, WM97XX_GPIO_IN, + WM97XX_GPIO_POL_HIGH, + WM97XX_GPIO_STICKY, + WM97XX_GPIO_WAKE); + wm97xx_config_gpio(wm, WM97XX_GPIO_2, WM97XX_GPIO_OUT, + WM97XX_GPIO_POL_HIGH, + WM97XX_GPIO_NOTSTICKY, + WM97XX_GPIO_NOWAKE); + + return wm97xx_register_mach_ops(wm, &zylonite_mach_ops); +} + +static int zylonite_wm97xx_remove(struct platform_device *pdev) +{ + struct wm97xx *wm = platform_get_drvdata(pdev); + + wm97xx_unregister_mach_ops(wm); + + return 0; +} + +static struct platform_driver zylonite_wm97xx_driver = { + .probe = zylonite_wm97xx_probe, + .remove = zylonite_wm97xx_remove, + .driver = { + .name = "wm97xx-touch", + }, +}; + +static int __init zylonite_wm97xx_init(void) +{ + return platform_driver_register(&zylonite_wm97xx_driver); +} + +static void __exit zylonite_wm97xx_exit(void) +{ + platform_driver_unregister(&zylonite_wm97xx_driver); +} + +module_init(zylonite_wm97xx_init); +module_exit(zylonite_wm97xx_exit); + +/* Module information */ +MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>"); +MODULE_DESCRIPTION("wm97xx continuous touch driver for Zylonite"); +MODULE_LICENSE("GPL"); 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/pci/dmar.c b/drivers/pci/dmar.c index 25a00ce4f24..fa3a11365ec 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -173,12 +173,21 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header) struct dmar_drhd_unit *dmaru; int ret = 0; + drhd = (struct acpi_dmar_hardware_unit *)header; + if (!drhd->address) { + /* Promote an attitude of violence to a BIOS engineer today */ + WARN(1, "Your BIOS is broken; DMAR reported at address zero!\n" + "BIOS vendor: %s; Ver: %s; Product Version: %s\n", + dmi_get_system_info(DMI_BIOS_VENDOR), + dmi_get_system_info(DMI_BIOS_VERSION), + dmi_get_system_info(DMI_PRODUCT_VERSION)); + return -ENODEV; + } dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL); if (!dmaru) return -ENOMEM; dmaru->hdr = header; - drhd = (struct acpi_dmar_hardware_unit *)header; dmaru->reg_base_addr = drhd->address; dmaru->segment = drhd->segment; dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */ diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index fb3a3f3fca7..001b328adf8 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -733,8 +733,8 @@ static void dma_pte_clear_range(struct dmar_domain *domain, u64 start, u64 end) start &= (((u64)1) << addr_width) - 1; end &= (((u64)1) << addr_width) - 1; /* in case it's partial page */ - start = PAGE_ALIGN(start); - end &= PAGE_MASK; + start &= PAGE_MASK; + end = PAGE_ALIGN(end); npages = (end - start) / VTD_PAGE_SIZE; /* we don't need lock here, nobody else touches the iova range */ 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/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index e1850904ff7..fbc83bebdd8 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -38,9 +38,6 @@ static inline void scsi_log_completion(struct scsi_cmnd *cmd, int disposition) { }; #endif -/* scsi_scan.c */ -int scsi_complete_async_scans(void); - /* scsi_devinfo.c */ extern int scsi_get_device_flags(struct scsi_device *sdev, const unsigned char *vendor, diff --git a/drivers/scsi/scsi_wait_scan.c b/drivers/scsi/scsi_wait_scan.c index 8a636103083..2f21af21269 100644 --- a/drivers/scsi/scsi_wait_scan.c +++ b/drivers/scsi/scsi_wait_scan.c @@ -11,7 +11,7 @@ */ #include <linux/module.h> -#include "scsi_priv.h" +#include <scsi/scsi_scan.h> static int __init wait_scan_init(void) { 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; } 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/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/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/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/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/linux/debug_locks.h b/include/linux/debug_locks.h index 096476f1fb3..493dedb7a67 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -2,12 +2,19 @@ #define __LINUX_DEBUG_LOCKING_H #include <linux/kernel.h> +#include <asm/atomic.h> struct task_struct; extern int debug_locks; extern int debug_locks_silent; + +static inline int __debug_locks_off(void) +{ + return xchg(&debug_locks, 0); +} + /* * Generic 'turn off all lock debugging' function: */ 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/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/rotary_encoder.h b/include/linux/rotary_encoder.h new file mode 100644 index 00000000000..12d63a30c34 --- /dev/null +++ b/include/linux/rotary_encoder.h @@ -0,0 +1,13 @@ +#ifndef __ROTARY_ENCODER_H__ +#define __ROTARY_ENCODER_H__ + +struct rotary_encoder_platform_data { + unsigned int steps; + unsigned int axis; + unsigned int gpio_a; + unsigned int gpio_b; + unsigned int inverted_a; + unsigned int inverted_b; +}; + +#endif /* __ROTARY_ENCODER_H__ */ 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/spi/ad7879.h b/include/linux/spi/ad7879.h new file mode 100644 index 00000000000..4231104c9af --- /dev/null +++ b/include/linux/spi/ad7879.h @@ -0,0 +1,35 @@ +/* linux/spi/ad7879.h */ + +/* Touchscreen characteristics vary between boards and models. The + * platform_data for the device's "struct device" holds this information. + * + * It's OK if the min/max values are zero. + */ +struct ad7879_platform_data { + u16 model; /* 7879 */ + u16 x_plate_ohms; + u16 x_min, x_max; + u16 y_min, y_max; + u16 pressure_min, pressure_max; + + /* [0..255] 0=OFF Starts at 1=550us and goes + * all the way to 9.440ms in steps of 35us. + */ + u8 pen_down_acc_interval; + /* [0..15] Starts at 0=128us and goes all the + * way to 4.096ms in steps of 128us. + */ + u8 first_conversion_delay; + /* [0..3] 0 = 2us, 1 = 4us, 2 = 8us, 3 = 16us */ + u8 acquisition_time; + /* [0..3] Average X middle samples 0 = 2, 1 = 4, 2 = 8, 3 = 16 */ + u8 averaging; + /* [0..3] Perform X measurements 0 = OFF, + * 1 = 4, 2 = 8, 3 = 16 (median > averaging) + */ + u8 median; + /* 1 = AUX/VBAT/GPIO set to GPIO Output */ + u8 gpio_output; + /* Initial GPIO pin state (valid if gpio_output = 1) */ + u8 gpio_default; +}; diff --git a/include/linux/stringify.h b/include/linux/stringify.h index 0b4388356c8..841cec8ed52 100644 --- a/include/linux/stringify.h +++ b/include/linux/stringify.h @@ -6,7 +6,7 @@ * converts to "bar". */ -#define __stringify_1(x) #x -#define __stringify(x) __stringify_1(x) +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) #endif /* !__LINUX_STRINGIFY_H */ 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/scsi/scsi_scan.h b/include/scsi/scsi_scan.h new file mode 100644 index 00000000000..78898889243 --- /dev/null +++ b/include/scsi/scsi_scan.h @@ -0,0 +1,11 @@ +#ifndef _SCSI_SCSI_SCAN_H +#define _SCSI_SCSI_SCAN_H + +#ifdef CONFIG_SCSI +/* drivers/scsi/scsi_scan.c */ +extern int scsi_complete_async_scans(void); +#else +static inline int scsi_complete_async_scans(void) { return 0; } +#endif + +#endif /* _SCSI_SCSI_SCAN_H */ 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/Kconfig b/init/Kconfig index f2f9b5362b4..7be4d383674 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -808,6 +808,14 @@ config KALLSYMS_EXTRA_PASS you wait for kallsyms to be fixed. +config STRIP_ASM_SYMS + bool "Strip assembler-generated symbols during link" + default n + help + Strip internal assembler-generated symbols during a link (symbols + that look like '.Lxxx') so they don't pollute the output of + get_wchan() and suchlike. + config HOTPLUG bool "Support for hot-pluggable devices" if EMBEDDED default y 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/panic.c b/kernel/panic.c index 3fd8c5bf8b3..934fb377f4b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -213,8 +213,16 @@ unsigned long get_taint(void) void add_taint(unsigned flag) { - /* can't trust the integrity of the kernel anymore: */ - debug_locks = 0; + /* + * Can't trust the integrity of the kernel anymore. + * We don't call directly debug_locks_off() because the issue + * is not necessarily serious enough to set oops_in_progress to 1 + * Also we want to keep up lockdep for staging development and + * post-warning case. + */ + if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off()) + printk(KERN_WARNING "Disabling lockdep due to kernel taint\n"); + set_bit(flag, &tainted_mask); } EXPORT_SYMBOL(add_taint); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 5f21ab2bbcd..0854770b63b 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -22,6 +22,7 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> +#include <scsi/scsi_scan.h> #include <asm/suspend.h> #include "power.h" @@ -645,6 +646,13 @@ static int software_resume(void) return 0; /* + * We can't depend on SCSI devices being available after loading one of + * their modules if scsi_complete_async_scans() is not called and the + * resume device usually is a SCSI one. + */ + scsi_complete_async_scans(); + + /* * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate * trigger path is via sysfs which takes a buffer mutex before diff --git a/kernel/power/user.c b/kernel/power/user.c index 6c85359364f..ed97375daae 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -24,6 +24,7 @@ #include <linux/cpu.h> #include <linux/freezer.h> #include <linux/smp_lock.h> +#include <scsi/scsi_scan.h> #include <asm/uaccess.h> @@ -92,6 +93,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) filp->private_data = data; memset(&data->handle, 0, sizeof(struct snapshot_handle)); if ((filp->f_flags & O_ACCMODE) == O_RDONLY) { + /* Hibernating. The image device should be accessible. */ data->swap = swsusp_resume_device ? swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; @@ -99,6 +101,13 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_HIBERNATION); } else { + /* + * Resuming. We may need to wait for the image device to + * appear. + */ + wait_for_device_probe(); + scsi_complete_async_scans(); + data->swap = -1; data->mode = O_WRONLY; error = pm_notifier_call_chain(PM_RESTORE_PREPARE); 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/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/kernel/trace/Kconfig b/kernel/trace/Kconfig index 2246141bda4..417d1985e29 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -312,7 +312,7 @@ config KMEMTRACE and profile kernel code. This requires an userspace application to use. See - Documentation/vm/kmemtrace.txt for more information. + Documentation/trace/kmemtrace.txt for more information. Saying Y will make the kernel somewhat larger and slower. However, if you disable kmemtrace at run-time or boot-time, the performance @@ -403,7 +403,7 @@ config MMIOTRACE implementation and works via page faults. Tracing is disabled by default and can be enabled at run-time. - See Documentation/tracers/mmiotrace.txt. + See Documentation/trace/mmiotrace.txt. If you are not helping to develop drivers, say N. config MMIOTRACE_TEST diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9d28476a985..1ce5dc6372b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3277,19 +3277,13 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) info->tr = &global_trace; info->cpu = cpu; - info->spare = ring_buffer_alloc_read_page(info->tr->buffer); + info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; - if (!info->spare) - goto out; filp->private_data = info; - return 0; - - out: - kfree(info); - return -ENOMEM; + return nonseekable_open(inode, filp); } static ssize_t @@ -3304,6 +3298,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (!count) return 0; + if (!info->spare) + info->spare = ring_buffer_alloc_read_page(info->tr->buffer); + if (!info->spare) + return -ENOMEM; + /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) goto read; @@ -3342,7 +3341,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; - ring_buffer_free_read_page(info->tr->buffer, info->spare); + if (info->spare) + ring_buffer_free_read_page(info->tr->buffer, info->spare); kfree(info); return 0; @@ -3428,14 +3428,19 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, int size, i; size_t ret; - /* - * We can't seek on a buffer input - */ - if (unlikely(*ppos)) - return -ESPIPE; + if (*ppos & (PAGE_SIZE - 1)) { + WARN_ONCE(1, "Ftrace: previous read must page-align\n"); + return -EINVAL; + } + if (len & (PAGE_SIZE - 1)) { + WARN_ONCE(1, "Ftrace: splice_read should page-align\n"); + if (len < PAGE_SIZE) + return -EINVAL; + len &= PAGE_MASK; + } - for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) { + for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) { struct page *page; int r; @@ -3474,6 +3479,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; + *ppos += PAGE_SIZE; } spd.nr_pages = i; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 64ec4d278ff..576f4fa2af0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -503,6 +503,7 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; pred = kzalloc(sizeof(*pred), GFP_KERNEL); if (!pred) @@ -520,9 +521,10 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } - if (filter_add_pred(call, pred)) { + err = filter_add_pred(call, pred); + if (err < 0) { filter_free_pred(pred); - return -EINVAL; + return err; } *ppos += cnt; @@ -569,6 +571,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; pred = kzalloc(sizeof(*pred), GFP_KERNEL); if (!pred) @@ -586,10 +589,11 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } - if (filter_add_subsystem_pred(system, pred)) { + err = filter_add_subsystem_pred(system, pred); + if (err < 0) { filter_free_subsystem_preds(system); filter_free_pred(pred); - return -EINVAL; + return err; } *ppos += cnt; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 026be412f35..e03cbf1e38f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -215,7 +215,7 @@ static int __filter_add_pred(struct ftrace_event_call *call, } } - return -ENOMEM; + return -ENOSPC; } static int is_string_field(const char *type) @@ -319,7 +319,7 @@ int filter_add_subsystem_pred(struct event_subsystem *system, } if (i == MAX_FILTER_PRED) - return -EINVAL; + return -ENOSPC; events_for_each(call) { int err; @@ -410,16 +410,22 @@ int filter_parse(char **pbuf, struct filter_pred *pred) } } + if (!val_str) { + pred->field_name = NULL; + return -EINVAL; + } + pred->field_name = kstrdup(pred->field_name, GFP_KERNEL); if (!pred->field_name) return -ENOMEM; - pred->val = simple_strtoull(val_str, &tmp, 10); + pred->val = simple_strtoull(val_str, &tmp, 0); if (tmp == val_str) { pred->str_val = kstrdup(val_str, GFP_KERNEL); if (!pred->str_val) return -ENOMEM; - } + } else if (*tmp != '\0') + return -EINVAL; return 0; } diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h index 30743f7d411..d363c6672c6 100644 --- a/kernel/trace/trace_events_stage_2.h +++ b/kernel/trace/trace_events_stage_2.h @@ -105,10 +105,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ return 0; #undef __entry -#define __entry "REC" +#define __entry REC #undef TP_printk -#define TP_printk(fmt, args...) "%s, %s\n", #fmt, #args +#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args) #undef TP_fast_assign #define TP_fast_assign(args...) args diff --git a/lib/debug_locks.c b/lib/debug_locks.c index 0218b4693dd..bc3b11731b9 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -36,7 +36,7 @@ int debug_locks_silent; */ int debug_locks_off(void) { - if (xchg(&debug_locks, 0)) { + if (__debug_locks_off()) { if (!debug_locks_silent) { oops_in_progress = 1; console_verbose(); 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/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index 612dc13ddd8..095cfc8b9db 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -14,6 +14,8 @@ _dst := $(if $(dst),$(dst),$(obj)) kbuild-file := $(srctree)/$(obj)/Kbuild include $(kbuild-file) +_dst := $(if $(destination-y),$(destination-y),$(_dst)) + include scripts/Kbuild.include install := $(INSTALL_HDR_PATH)/$(_dst) diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh index 3eea8f15131..76af5f9623e 100644 --- a/scripts/gen_initramfs_list.sh +++ b/scripts/gen_initramfs_list.sh @@ -97,7 +97,7 @@ print_mtime() { } list_parse() { - echo "$1 \\" + [ ! -L "$1" ] && echo "$1 \\" || : } # for each file print a line in following format diff --git a/scripts/headerdep.pl b/scripts/headerdep.pl index 97399da89ef..b7f6c560e24 100755 --- a/scripts/headerdep.pl +++ b/scripts/headerdep.pl @@ -19,7 +19,7 @@ my $opt_graph; version => \&version, all => \$opt_all, - I => \@opt_include, + "I=s" => \@opt_include, graph => \$opt_graph, ); diff --git a/scripts/kconfig/kxgettext.c b/scripts/kconfig/kxgettext.c index 6eb72a7f256..8d9ce22b0fc 100644 --- a/scripts/kconfig/kxgettext.c +++ b/scripts/kconfig/kxgettext.c @@ -43,6 +43,10 @@ static char *escape(const char* text, char *bf, int len) ++text; goto next; } + else if (*text == '\\') { + *bfp++ = '\\'; + len--; + } *bfp++ = *text++; next: --len; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 8cc70612984..df6e6286a06 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1913,7 +1913,7 @@ static void read_dump(const char *fname, unsigned int kernel) if (!mod) { if (is_vmlinux(modname)) have_vmlinux = 1; - mod = new_module(NOFAIL(strdup(modname))); + mod = new_module(modname); mod->skip = 1; } s = sym_add_exported(symname, mod, export_no(export)); @@ -1997,7 +1997,7 @@ static void read_markers(const char *fname) mod = find_module(modname); if (!mod) { - mod = new_module(NOFAIL(strdup(modname))); + mod = new_module(modname); mod->skip = 1; } if (is_vmlinux(modname)) { diff --git a/scripts/setlocalversion b/scripts/setlocalversion index f1c4b35bc32..47e75b69a2e 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -21,7 +21,7 @@ if head=`git rev-parse --verify --short HEAD 2>/dev/null`; then # Is this git on svn? if git config --get svn-remote.svn.url >/dev/null; then - printf -- '-svn%s' "`git-svn find-rev $head`" + printf -- '-svn%s' "`git svn find-rev $head`" fi # Are there uncommitted changes? 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/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 30829ee920c..7ba8db5d4c4 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2260,11 +2260,11 @@ 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 |