diff options
105 files changed, 2599 insertions, 1646 deletions
diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd index bf9c16b64c34..cf11736acb76 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/cgroups/memory.txt b/Documentation/cgroups/memory.txt index a98a7fe7aabb..1a608877b14e 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 f196ac1d7d25..95b24d766eab 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/sysctl/net.txt b/Documentation/sysctl/net.txt index a34d55b65441..df38ef046f8d 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/vm/00-INDEX b/Documentation/vm/00-INDEX index 2131b00b63f6..2f77ced35df7 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 000000000000..4ee1f643d897 --- /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 0706a7282a8c..2d70d0d95108 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 ca2997a45766..29d74f47ba86 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 @@ -4978,8 +4978,8 @@ 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/ diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c index fc74e913c415..34a56a136efd 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 573f02c39a00..285aae8431c6 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/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d5cd6c586881..a4737dddfd58 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -50,7 +50,7 @@ #ifdef CONFIG_X86_64 #define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) -#define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) +#define NEED_PGE 0 #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) #define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) #define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a918dde46b5..018a0a400799 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) static inline unsigned long pte_mfn(pte_t pte) diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 3e3cd3db7a0c..837c2c4cc203 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -277,7 +277,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int perf_percent; unsigned int retval; - if (smp_call_function_single(cpu, read_measured_perf_ctrs, &cur, 1)) + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1)) return 0; cur.aperf.whole = readin.aperf.whole - diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 82cd39a6cbd3..f09e8c36ee80 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 2a81838a9ab7..9842b1212407 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 24d1b44a337d..da7302624897 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 585a6e330837..429834ec1687 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 2f5ef2632ea2..20139464943c 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/atm/solos-pci.c b/drivers/atm/solos-pci.c index be204308cc1b..9359613addc5 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 0ef6f08aa6ea..4d4d5e0d3fa6 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 9d9490e22e07..3686912427ba 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 6de020d078e1..b0a6a3e51924 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 28f2c3f959b5..6ad95c8d6363 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 ca9113e1c106..a7d2c717d033 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 25d66940b4fa..335b7ebdb11c 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 5b150aea703a..30b585b1d60b 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 0e8a9185f676..d73f5f473e38 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 1d3757837b4f..0ae26984ba45 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 55d3dc565be6..abca7e9f953b 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 000000000000..6cbdc2fea734 --- /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/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index d184dfab9631..db39f4a52f53 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 6bc0dac5c1e8..b34cb5f79eea 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 114444cfd496..b94d5f767703 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 99a2534c38a1..652593fc486d 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 1ab9fda87fab..fd3688a3e23f 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 6722f6fe4dc7..65877bc5edaa 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 eaaa964942de..915a3b495da5 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 f7fff4727edb..9172fcdee4e2 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 deb7b53167ee..83a12125b94e 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 9b75aa630062..30d0c81c989e 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 ece35040288c..621a7c0c46ba 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 6dbc58580abb..168411d322a2 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 e3569a0a952d..b1610ea4bb3d 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/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index fdb14ec4fd47..8b7983aba8f7 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 280261c451d6..2a889853a106 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/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index 52427a8324f5..a91f5143ceac 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/spi/spi.c b/drivers/spi/spi.c index 643908b74bc0..8eba98c8ed1e 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 0348072b3ab5..75ebe338c6f2 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/otg/nop-usb-xceiv.c b/drivers/usb/otg/nop-usb-xceiv.c index 4b933f646f2e..c567168f89af 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/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c index 16bb7e3c0310..6c37e8ee5efe 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 dd37cbcaf8ce..157057c79ca3 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 0bb13df0fa89..b6449470106c 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 d42e385f091c..4c2bf923418c 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 2cd500a304f2..471a9a60376a 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 0c5b9a9fd56f..8dea2bc92705 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 2ac32e6b5953..d412a1ddc12f 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 a50bea614804..40984551c927 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 b3065492bb20..487f2be47460 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 6d8e5415c809..ace14fe02fc4 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 8b26b27c2db6..0689f97c5238 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 4dcec48a1d78..c3fad34309ed 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 fad58cf9ef73..10ddad8e17d6 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 86831db9a042..1c3b459865d8 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 346d6458cf76..7e17ee95a97a 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 a439159204a8..89158bc71da2 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 0b370aebdbfd..421770b5e6ab 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 cc919ae46571..050d432c7d95 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 5f54c01c1568..bdfd584ad853 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 0d61db1e7b49..4b5b84837ee1 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 b43b95563663..acf678831103 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 9435dda8f1e0..a1cbff2b4d99 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 36ca2e1a4fa3..7b6165f25fbe 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 c7bd649bbbdc..3e9afc2a91d2 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 c13f67300fe7..7ec89fc05b2b 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 1dd528849755..221b3e66ceef 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 aa1016bb9134..e28800a9f2b5 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 5aeb77776961..08be36d7326c 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 7e90daa0d1d1..9142192ccbe6 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 a608e72fa405..f7ba76633c29 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 04f058c848ae..308d5bf6dfbd 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 478e587087fe..89b81eedce6a 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 08ce72316bfe..5aaa2d7ec155 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 a1cc1322fc0f..fdcf7b82747f 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 f76c6d7cea21..3750f04ede0b 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 7af44adffc8f..d6a64392f983 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 7394c7af5de5..19cf90a9c762 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 35752dadd6df..c840719a8c59 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 2df74eb09563..9477af01a639 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/fb.h b/include/linux/fb.h index f563c5013932..330c4b1bfcaa 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 671decbd2aeb..934e22d65801 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 dcfb93337e9a..d87247d2641f 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 ee98cd570885..06ba90c211a5 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/sht15.h b/include/linux/sht15.h new file mode 100644 index 000000000000..046bce05ecab --- /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/video/cyblafb.h b/include/video/cyblafb.h deleted file mode 100644 index d3c1d4e2c8e3..000000000000 --- a/include/video/cyblafb.h +++ /dev/null @@ -1,175 +0,0 @@ - -#ifndef CYBLAFB_DEBUG -#define CYBLAFB_DEBUG 0 -#endif - -#if CYBLAFB_DEBUG -#define debug(f,a...) printk("%s:" f, __func__ , ## a); -#else -#define debug(f,a...) -#endif - -#define output(f, a...) printk("cyblafb: " f, ## a) - -#define Kb (1024) -#define Mb (Kb*Kb) - -/* PCI IDS of supported cards temporarily here */ - -#define CYBERBLADEi1 0x8500 - -/* these defines are for 'lcd' variable */ -#define LCD_STRETCH 0 -#define LCD_CENTER 1 -#define LCD_BIOS 2 - -/* display types */ -#define DISPLAY_CRT 0 -#define DISPLAY_FP 1 - -#define ROP_S 0xCC - -#define point(x,y) ((y)<<16|(x)) - -// -// Attribute Regs, ARxx, 3c0/3c1 -// -#define AR00 0x00 -#define AR01 0x01 -#define AR02 0x02 -#define AR03 0x03 -#define AR04 0x04 -#define AR05 0x05 -#define AR06 0x06 -#define AR07 0x07 -#define AR08 0x08 -#define AR09 0x09 -#define AR0A 0x0A -#define AR0B 0x0B -#define AR0C 0x0C -#define AR0D 0x0D -#define AR0E 0x0E -#define AR0F 0x0F -#define AR10 0x10 -#define AR12 0x12 -#define AR13 0x13 - -// -// Sequencer Regs, SRxx, 3c4/3c5 -// -#define SR00 0x00 -#define SR01 0x01 -#define SR02 0x02 -#define SR03 0x03 -#define SR04 0x04 -#define SR0D 0x0D -#define SR0E 0x0E -#define SR11 0x11 -#define SR18 0x18 -#define SR19 0x19 - -// -// -// -#define CR00 0x00 -#define CR01 0x01 -#define CR02 0x02 -#define CR03 0x03 -#define CR04 0x04 -#define CR05 0x05 -#define CR06 0x06 -#define CR07 0x07 -#define CR08 0x08 -#define CR09 0x09 -#define CR0A 0x0A -#define CR0B 0x0B -#define CR0C 0x0C -#define CR0D 0x0D -#define CR0E 0x0E -#define CR0F 0x0F -#define CR10 0x10 -#define CR11 0x11 -#define CR12 0x12 -#define CR13 0x13 -#define CR14 0x14 -#define CR15 0x15 -#define CR16 0x16 -#define CR17 0x17 -#define CR18 0x18 -#define CR19 0x19 -#define CR1A 0x1A -#define CR1B 0x1B -#define CR1C 0x1C -#define CR1D 0x1D -#define CR1E 0x1E -#define CR1F 0x1F -#define CR20 0x20 -#define CR21 0x21 -#define CR27 0x27 -#define CR29 0x29 -#define CR2A 0x2A -#define CR2B 0x2B -#define CR2D 0x2D -#define CR2F 0x2F -#define CR36 0x36 -#define CR38 0x38 -#define CR39 0x39 -#define CR3A 0x3A -#define CR55 0x55 -#define CR56 0x56 -#define CR57 0x57 -#define CR58 0x58 - -// -// -// - -#define GR00 0x01 -#define GR01 0x01 -#define GR02 0x02 -#define GR03 0x03 -#define GR04 0x04 -#define GR05 0x05 -#define GR06 0x06 -#define GR07 0x07 -#define GR08 0x08 -#define GR0F 0x0F -#define GR20 0x20 -#define GR23 0x23 -#define GR2F 0x2F -#define GR30 0x30 -#define GR31 0x31 -#define GR33 0x33 -#define GR52 0x52 -#define GR53 0x53 -#define GR5D 0x5d - - -// -// Graphics Engine -// -#define GEBase 0x2100 // could be mapped elsewhere if we like it -#define GE00 (GEBase+0x00) // source 1, p 111 -#define GE04 (GEBase+0x04) // source 2, p 111 -#define GE08 (GEBase+0x08) // destination 1, p 111 -#define GE0C (GEBase+0x0C) // destination 2, p 112 -#define GE10 (GEBase+0x10) // right view base & enable, p 112 -#define GE13 (GEBase+0x13) // left view base & enable, p 112 -#define GE18 (GEBase+0x18) // block write start address, p 112 -#define GE1C (GEBase+0x1C) // block write end address, p 112 -#define GE20 (GEBase+0x20) // engine status, p 113 -#define GE24 (GEBase+0x24) // reset all GE pointers -#define GE44 (GEBase+0x44) // command register, p 126 -#define GE48 (GEBase+0x48) // raster operation, p 127 -#define GE60 (GEBase+0x60) // foreground color, p 128 -#define GE64 (GEBase+0x64) // background color, p 128 -#define GE6C (GEBase+0x6C) // Pattern and Style, p 129, ok -#define GE9C (GEBase+0x9C) // pixel engine data port, p 125 -#define GEB8 (GEBase+0xB8) // Destination Stride / Buffer Base 0, p 133 -#define GEBC (GEBase+0xBC) // Destination Stride / Buffer Base 1, p 133 -#define GEC0 (GEBase+0xC0) // Destination Stride / Buffer Base 2, p 133 -#define GEC4 (GEBase+0xC4) // Destination Stride / Buffer Base 3, p 133 -#define GEC8 (GEBase+0xC8) // Source Stride / Buffer Base 0, p 133 -#define GECC (GEBase+0xCC) // Source Stride / Buffer Base 1, p 133 -#define GED0 (GEBase+0xD0) // Source Stride / Buffer Base 2, p 133 -#define GED4 (GEBase+0xD4) // Source Stride / Buffer Base 3, p 133 diff --git a/init/initramfs.c b/init/initramfs.c index 80cd713f6cc5..9ee7b7810417 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 89f60ec8ee54..24ae46dfe45d 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/ptrace.c b/kernel/ptrace.c index 64191fa09b7e..dfcd83ceee3b 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 51dbb55604e8..e7998cf31498 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 4286b62b34a0..e3d2c7dd59b9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -902,16 +902,6 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_UNEVICTABLE_LRU - { - .ctl_name = CTL_UNNUMBERED, - .procname = "scan_unevictable_pages", - .data = &scan_unevictable_pages, - .maxlen = sizeof(scan_unevictable_pages), - .mode = 0644, - .proc_handler = &scan_unevictable_handler, - }, -#endif #ifdef CONFIG_SLOW_WORK { .ctl_name = CTL_UNNUMBERED, @@ -1302,6 +1292,16 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_UNEVICTABLE_LRU + { + .ctl_name = CTL_UNNUMBERED, + .procname = "scan_unevictable_pages", + .data = &scan_unevictable_pages, + .maxlen = sizeof(scan_unevictable_pages), + .mode = 0644, + .proc_handler = &scan_unevictable_handler, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/mm/Kconfig b/mm/Kconfig index b53427ad30a3..57971d2ab848 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 2e2d38ebda4b..8bd498040f32 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 2fc6d6c48238..e44fb0fbb80e 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 d94d2e9146bc..f9cb20ebb990 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 2599e83eea17..55bef160b9f1 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/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 30829ee920c3..7ba8db5d4c42 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 |