diff options
181 files changed, 1214 insertions, 2397 deletions
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 304bf22bb83c..fc1c884fea10 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -75,3 +75,4 @@ stable kernels. | Qualcomm Tech. | Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | | Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | +| Qualcomm Tech. | Falkor v{1,2} | E1041 | QCOM_FALKOR_ERRATUM_1041 | diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 779211fbb69f..2cddab7efb20 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -898,6 +898,13 @@ controller implements weight and absolute bandwidth limit models for normal scheduling policy and absolute bandwidth allocation model for realtime scheduling policy. +WARNING: cgroup2 doesn't yet support control of realtime processes and +the cpu controller can only be enabled when all RT processes are in +the root cgroup. Be aware that system management software may already +have placed RT processes into nonroot cgroups during the system boot +process, and these processes may need to be moved to the root cgroup +before the cpu controller can be enabled. + CPU Interface Files ~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 8caa60734647..e6a5f4912b6d 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -156,6 +156,40 @@ handle it in two different ways: root of the overlay. Finally the directory is moved to the new location. +There are several ways to tune the "redirect_dir" feature. + +Kernel config options: + +- OVERLAY_FS_REDIRECT_DIR: + If this is enabled, then redirect_dir is turned on by default. +- OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW: + If this is enabled, then redirects are always followed by default. Enabling + this results in a less secure configuration. Enable this option only when + worried about backward compatibility with kernels that have the redirect_dir + feature and follow redirects even if turned off. + +Module options (can also be changed through /sys/module/overlay/parameters/*): + +- "redirect_dir=BOOL": + See OVERLAY_FS_REDIRECT_DIR kernel config option above. +- "redirect_always_follow=BOOL": + See OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW kernel config option above. +- "redirect_max=NUM": + The maximum number of bytes in an absolute redirect (default is 256). + +Mount options: + +- "redirect_dir=on": + Redirects are enabled. +- "redirect_dir=follow": + Redirects are not created, but followed. +- "redirect_dir=off": + Redirects are not created and only followed if "redirect_always_follow" + feature is enabled in the kernel/module config. +- "redirect_dir=nofollow": + Redirects are not created and not followed (equivalent to "redirect_dir=off" + if "redirect_always_follow" feature is not enabled). + Non-directories --------------- diff --git a/Documentation/locking/crossrelease.txt b/Documentation/locking/crossrelease.txt deleted file mode 100644 index bdf1423d5f99..000000000000 --- a/Documentation/locking/crossrelease.txt +++ /dev/null @@ -1,874 +0,0 @@ -Crossrelease -============ - -Started by Byungchul Park <byungchul.park@lge.com> - -Contents: - - (*) Background - - - What causes deadlock - - How lockdep works - - (*) Limitation - - - Limit lockdep - - Pros from the limitation - - Cons from the limitation - - Relax the limitation - - (*) Crossrelease - - - Introduce crossrelease - - Introduce commit - - (*) Implementation - - - Data structures - - How crossrelease works - - (*) Optimizations - - - Avoid duplication - - Lockless for hot paths - - (*) APPENDIX A: What lockdep does to work aggresively - - (*) APPENDIX B: How to avoid adding false dependencies - - -========== -Background -========== - -What causes deadlock --------------------- - -A deadlock occurs when a context is waiting for an event to happen, -which is impossible because another (or the) context who can trigger the -event is also waiting for another (or the) event to happen, which is -also impossible due to the same reason. - -For example: - - A context going to trigger event C is waiting for event A to happen. - A context going to trigger event A is waiting for event B to happen. - A context going to trigger event B is waiting for event C to happen. - -A deadlock occurs when these three wait operations run at the same time, -because event C cannot be triggered if event A does not happen, which in -turn cannot be triggered if event B does not happen, which in turn -cannot be triggered if event C does not happen. After all, no event can -be triggered since any of them never meets its condition to wake up. - -A dependency might exist between two waiters and a deadlock might happen -due to an incorrect releationship between dependencies. Thus, we must -define what a dependency is first. A dependency exists between them if: - - 1. There are two waiters waiting for each event at a given time. - 2. The only way to wake up each waiter is to trigger its event. - 3. Whether one can be woken up depends on whether the other can. - -Each wait in the example creates its dependency like: - - Event C depends on event A. - Event A depends on event B. - Event B depends on event C. - - NOTE: Precisely speaking, a dependency is one between whether a - waiter for an event can be woken up and whether another waiter for - another event can be woken up. However from now on, we will describe - a dependency as if it's one between an event and another event for - simplicity. - -And they form circular dependencies like: - - -> C -> A -> B - - / \ - \ / - ---------------- - - where 'A -> B' means that event A depends on event B. - -Such circular dependencies lead to a deadlock since no waiter can meet -its condition to wake up as described. - -CONCLUSION - -Circular dependencies cause a deadlock. - - -How lockdep works ------------------ - -Lockdep tries to detect a deadlock by checking dependencies created by -lock operations, acquire and release. Waiting for a lock corresponds to -waiting for an event, and releasing a lock corresponds to triggering an -event in the previous section. - -In short, lockdep does: - - 1. Detect a new dependency. - 2. Add the dependency into a global graph. - 3. Check if that makes dependencies circular. - 4. Report a deadlock or its possibility if so. - -For example, consider a graph built by lockdep that looks like: - - A -> B - - \ - -> E - / - C -> D - - - where A, B,..., E are different lock classes. - -Lockdep will add a dependency into the graph on detection of a new -dependency. For example, it will add a dependency 'E -> C' when a new -dependency between lock E and lock C is detected. Then the graph will be: - - A -> B - - \ - -> E - - / \ - -> C -> D - \ - / / - \ / - ------------------ - - where A, B,..., E are different lock classes. - -This graph contains a subgraph which demonstrates circular dependencies: - - -> E - - / \ - -> C -> D - \ - / / - \ / - ------------------ - - where C, D and E are different lock classes. - -This is the condition under which a deadlock might occur. Lockdep -reports it on detection after adding a new dependency. This is the way -how lockdep works. - -CONCLUSION - -Lockdep detects a deadlock or its possibility by checking if circular -dependencies were created after adding each new dependency. - - -========== -Limitation -========== - -Limit lockdep -------------- - -Limiting lockdep to work on only typical locks e.g. spin locks and -mutexes, which are released within the acquire context, the -implementation becomes simple but its capacity for detection becomes -limited. Let's check pros and cons in next section. - - -Pros from the limitation ------------------------- - -Given the limitation, when acquiring a lock, locks in a held_locks -cannot be released if the context cannot acquire it so has to wait to -acquire it, which means all waiters for the locks in the held_locks are -stuck. It's an exact case to create dependencies between each lock in -the held_locks and the lock to acquire. - -For example: - - CONTEXT X - --------- - acquire A - acquire B /* Add a dependency 'A -> B' */ - release B - release A - - where A and B are different lock classes. - -When acquiring lock A, the held_locks of CONTEXT X is empty thus no -dependency is added. But when acquiring lock B, lockdep detects and adds -a new dependency 'A -> B' between lock A in the held_locks and lock B. -They can be simply added whenever acquiring each lock. - -And data required by lockdep exists in a local structure, held_locks -embedded in task_struct. Forcing to access the data within the context, -lockdep can avoid racy problems without explicit locks while handling -the local data. - -Lastly, lockdep only needs to keep locks currently being held, to build -a dependency graph. However, relaxing the limitation, it needs to keep -even locks already released, because a decision whether they created -dependencies might be long-deferred. - -To sum up, we can expect several advantages from the limitation: - - 1. Lockdep can easily identify a dependency when acquiring a lock. - 2. Races are avoidable while accessing local locks in a held_locks. - 3. Lockdep only needs to keep locks currently being held. - -CONCLUSION - -Given the limitation, the implementation becomes simple and efficient. - - -Cons from the limitation ------------------------- - -Given the limitation, lockdep is applicable only to typical locks. For -example, page locks for page access or completions for synchronization -cannot work with lockdep. - -Can we detect deadlocks below, under the limitation? - -Example 1: - - CONTEXT X CONTEXT Y CONTEXT Z - --------- --------- ---------- - mutex_lock A - lock_page B - lock_page B - mutex_lock A /* DEADLOCK */ - unlock_page B held by X - unlock_page B - mutex_unlock A - mutex_unlock A - - where A and B are different lock classes. - -No, we cannot. - -Example 2: - - CONTEXT X CONTEXT Y - --------- --------- - mutex_lock A - mutex_lock A - wait_for_complete B /* DEADLOCK */ - complete B - mutex_unlock A - mutex_unlock A - - where A is a lock class and B is a completion variable. - -No, we cannot. - -CONCLUSION - -Given the limitation, lockdep cannot detect a deadlock or its -possibility caused by page locks or completions. - - -Relax the limitation --------------------- - -Under the limitation, things to create dependencies are limited to -typical locks. However, synchronization primitives like page locks and -completions, which are allowed to be released in any context, also -create dependencies and can cause a deadlock. So lockdep should track -these locks to do a better job. We have to relax the limitation for -these locks to work with lockdep. - -Detecting dependencies is very important for lockdep to work because -adding a dependency means adding an opportunity to check whether it -causes a deadlock. The more lockdep adds dependencies, the more it -thoroughly works. Thus Lockdep has to do its best to detect and add as -many true dependencies into a graph as possible. - -For example, considering only typical locks, lockdep builds a graph like: - - A -> B - - \ - -> E - / - C -> D - - - where A, B,..., E are different lock classes. - -On the other hand, under the relaxation, additional dependencies might -be created and added. Assuming additional 'FX -> C' and 'E -> GX' are -added thanks to the relaxation, the graph will be: - - A -> B - - \ - -> E -> GX - / - FX -> C -> D - - - where A, B,..., E, FX and GX are different lock classes, and a suffix - 'X' is added on non-typical locks. - -The latter graph gives us more chances to check circular dependencies -than the former. However, it might suffer performance degradation since -relaxing the limitation, with which design and implementation of lockdep -can be efficient, might introduce inefficiency inevitably. So lockdep -should provide two options, strong detection and efficient detection. - -Choosing efficient detection: - - Lockdep works with only locks restricted to be released within the - acquire context. However, lockdep works efficiently. - -Choosing strong detection: - - Lockdep works with all synchronization primitives. However, lockdep - suffers performance degradation. - -CONCLUSION - -Relaxing the limitation, lockdep can add additional dependencies giving -additional opportunities to check circular dependencies. - - -============ -Crossrelease -============ - -Introduce crossrelease ----------------------- - -In order to allow lockdep to handle additional dependencies by what -might be released in any context, namely 'crosslock', we have to be able -to identify those created by crosslocks. The proposed 'crossrelease' -feature provoides a way to do that. - -Crossrelease feature has to do: - - 1. Identify dependencies created by crosslocks. - 2. Add the dependencies into a dependency graph. - -That's all. Once a meaningful dependency is added into graph, then -lockdep would work with the graph as it did. The most important thing -crossrelease feature has to do is to correctly identify and add true -dependencies into the global graph. - -A dependency e.g. 'A -> B' can be identified only in the A's release -context because a decision required to identify the dependency can be -made only in the release context. That is to decide whether A can be -released so that a waiter for A can be woken up. It cannot be made in -other than the A's release context. - -It's no matter for typical locks because each acquire context is same as -its release context, thus lockdep can decide whether a lock can be -released in the acquire context. However for crosslocks, lockdep cannot -make the decision in the acquire context but has to wait until the -release context is identified. - -Therefore, deadlocks by crosslocks cannot be detected just when it -happens, because those cannot be identified until the crosslocks are -released. However, deadlock possibilities can be detected and it's very -worth. See 'APPENDIX A' section to check why. - -CONCLUSION - -Using crossrelease feature, lockdep can work with what might be released -in any context, namely crosslock. - - -Introduce commit ----------------- - -Since crossrelease defers the work adding true dependencies of -crosslocks until they are actually released, crossrelease has to queue -all acquisitions which might create dependencies with the crosslocks. -Then it identifies dependencies using the queued data in batches at a -proper time. We call it 'commit'. - -There are four types of dependencies: - -1. TT type: 'typical lock A -> typical lock B' - - Just when acquiring B, lockdep can see it's in the A's release - context. So the dependency between A and B can be identified - immediately. Commit is unnecessary. - -2. TC type: 'typical lock A -> crosslock BX' - - Just when acquiring BX, lockdep can see it's in the A's release - context. So the dependency between A and BX can be identified - immediately. Commit is unnecessary, too. - -3. CT type: 'crosslock AX -> typical lock B' - - When acquiring B, lockdep cannot identify the dependency because - there's no way to know if it's in the AX's release context. It has - to wait until the decision can be made. Commit is necessary. - -4. CC type: 'crosslock AX -> crosslock BX' - - When acquiring BX, lockdep cannot identify the dependency because - there's no way to know if it's in the AX's release context. It has - to wait until the decision can be made. Commit is necessary. - But, handling CC type is not implemented yet. It's a future work. - -Lockdep can work without commit for typical locks, but commit step is -necessary once crosslocks are involved. Introducing commit, lockdep -performs three steps. What lockdep does in each step is: - -1. Acquisition: For typical locks, lockdep does what it originally did - and queues the lock so that CT type dependencies can be checked using - it at the commit step. For crosslocks, it saves data which will be - used at the commit step and increases a reference count for it. - -2. Commit: No action is reauired for typical locks. For crosslocks, - lockdep adds CT type dependencies using the data saved at the - acquisition step. - -3. Release: No changes are required for typical locks. When a crosslock - is released, it decreases a reference count for it. - -CONCLUSION - -Crossrelease introduces commit step to handle dependencies of crosslocks -in batches at a proper time. - - -============== -Implementation -============== - -Data structures ---------------- - -Crossrelease introduces two main data structures. - -1. hist_lock - - This is an array embedded in task_struct, for keeping lock history so - that dependencies can be added using them at the commit step. Since - it's local data, it can be accessed locklessly in the owner context. - The array is filled at the acquisition step and consumed at the - commit step. And it's managed in circular manner. - -2. cross_lock - - One per lockdep_map exists. This is for keeping data of crosslocks - and used at the commit step. - - -How crossrelease works ----------------------- - -It's the key of how crossrelease works, to defer necessary works to an -appropriate point in time and perform in at once at the commit step. -Let's take a look with examples step by step, starting from how lockdep -works without crossrelease for typical locks. - - acquire A /* Push A onto held_locks */ - acquire B /* Push B onto held_locks and add 'A -> B' */ - acquire C /* Push C onto held_locks and add 'B -> C' */ - release C /* Pop C from held_locks */ - release B /* Pop B from held_locks */ - release A /* Pop A from held_locks */ - - where A, B and C are different lock classes. - - NOTE: This document assumes that readers already understand how - lockdep works without crossrelease thus omits details. But there's - one thing to note. Lockdep pretends to pop a lock from held_locks - when releasing it. But it's subtly different from the original pop - operation because lockdep allows other than the top to be poped. - -In this case, lockdep adds 'the top of held_locks -> the lock to acquire' -dependency every time acquiring a lock. - -After adding 'A -> B', a dependency graph will be: - - A -> B - - where A and B are different lock classes. - -And after adding 'B -> C', the graph will be: - - A -> B -> C - - where A, B and C are different lock classes. - -Let's performs commit step even for typical locks to add dependencies. -Of course, commit step is not necessary for them, however, it would work -well because this is a more general way. - - acquire A - /* - * Queue A into hist_locks - * - * In hist_locks: A - * In graph: Empty - */ - - acquire B - /* - * Queue B into hist_locks - * - * In hist_locks: A, B - * In graph: Empty - */ - - acquire C - /* - * Queue C into hist_locks - * - * In hist_locks: A, B, C - * In graph: Empty - */ - - commit C - /* - * Add 'C -> ?' - * Answer the following to decide '?' - * What has been queued since acquire C: Nothing - * - * In hist_locks: A, B, C - * In graph: Empty - */ - - release C - - commit B - /* - * Add 'B -> ?' - * Answer the following to decide '?' - * What has been queued since acquire B: C - * - * In hist_locks: A, B, C - * In graph: 'B -> C' - */ - - release B - - commit A - /* - * Add 'A -> ?' - * Answer the following to decide '?' - * What has been queued since acquire A: B, C - * - * In hist_locks: A, B, C - * In graph: 'B -> C', 'A -> B', 'A -> C' - */ - - release A - - where A, B and C are different lock classes. - -In this case, dependencies are added at the commit step as described. - -After commits for A, B and C, the graph will be: - - A -> B -> C - - where A, B and C are different lock classes. - - NOTE: A dependency 'A -> C' is optimized out. - -We can see the former graph built without commit step is same as the -latter graph built using commit steps. Of course the former way leads to -earlier finish for building the graph, which means we can detect a -deadlock or its possibility sooner. So the former way would be prefered -when possible. But we cannot avoid using the latter way for crosslocks. - -Let's look at how commit steps work for crosslocks. In this case, the -commit step is performed only on crosslock AX as real. And it assumes -that the AX release context is different from the AX acquire context. - - BX RELEASE CONTEXT BX ACQUIRE CONTEXT - ------------------ ------------------ - acquire A - /* - * Push A onto held_locks - * Queue A into hist_locks - * - * In held_locks: A - * In hist_locks: A - * In graph: Empty - */ - - acquire BX - /* - * Add 'the top of held_locks -> BX' - * - * In held_locks: A - * In hist_locks: A - * In graph: 'A -> BX' - */ - - ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - It must be guaranteed that the following operations are seen after - acquiring BX globally. It can be done by things like barrier. - ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - - acquire C - /* - * Push C onto held_locks - * Queue C into hist_locks - * - * In held_locks: C - * In hist_locks: C - * In graph: 'A -> BX' - */ - - release C - /* - * Pop C from held_locks - * - * In held_locks: Empty - * In hist_locks: C - * In graph: 'A -> BX' - */ - acquire D - /* - * Push D onto held_locks - * Queue D into hist_locks - * Add 'the top of held_locks -> D' - * - * In held_locks: A, D - * In hist_locks: A, D - * In graph: 'A -> BX', 'A -> D' - */ - acquire E - /* - * Push E onto held_locks - * Queue E into hist_locks - * - * In held_locks: E - * In hist_locks: C, E - * In graph: 'A -> BX', 'A -> D' - */ - - release E - /* - * Pop E from held_locks - * - * In held_locks: Empty - * In hist_locks: D, E - * In graph: 'A -> BX', 'A -> D' - */ - release D - /* - * Pop D from held_locks - * - * In held_locks: A - * In hist_locks: A, D - * In graph: 'A -> BX', 'A -> D' - */ - commit BX - /* - * Add 'BX -> ?' - * What has been queued since acquire BX: C, E - * - * In held_locks: Empty - * In hist_locks: D, E - * In graph: 'A -> BX', 'A -> D', - * 'BX -> C', 'BX -> E' - */ - - release BX - /* - * In held_locks: Empty - * In hist_locks: D, E - * In graph: 'A -> BX', 'A -> D', - * 'BX -> C', 'BX -> E' - */ - release A - /* - * Pop A from held_locks - * - * In held_locks: Empty - * In hist_locks: A, D - * In graph: 'A -> BX', 'A -> D', - * 'BX -> C', 'BX -> E' - */ - - where A, BX, C,..., E are different lock classes, and a suffix 'X' is - added on crosslocks. - -Crossrelease considers all acquisitions after acqiuring BX are -candidates which might create dependencies with BX. True dependencies -will be determined when identifying the release context of BX. Meanwhile, -all typical locks are queued so that they can be used at the commit step. -And then two dependencies 'BX -> C' and 'BX -> E' are added at the -commit step when identifying the release context. - -The final graph will be, with crossrelease: - - -> C - / - -> BX - - / \ - A - -> E - \ - -> D - - where A, BX, C,..., E are different lock classes, and a suffix 'X' is - added on crosslocks. - -However, the final graph will be, without crossrelease: - - A -> D - - where A and D are different lock classes. - -The former graph has three more dependencies, 'A -> BX', 'BX -> C' and -'BX -> E' giving additional opportunities to check if they cause -deadlocks. This way lockdep can detect a deadlock or its possibility -caused by crosslocks. - -CONCLUSION - -We checked how crossrelease works with several examples. - - -============= -Optimizations -============= - -Avoid duplication ------------------ - -Crossrelease feature uses a cache like what lockdep already uses for -dependency chains, but this time it's for caching CT type dependencies. -Once that dependency is cached, the same will never be added again. - - -Lockless for hot paths ----------------------- - -To keep all locks for later use at the commit step, crossrelease adopts -a local array embedded in task_struct, which makes access to the data -lockless by forcing it to happen only within the owner context. It's -like how lockdep handles held_locks. Lockless implmentation is important -since typical locks are very frequently acquired and released. - - -================================================= -APPENDIX A: What lockdep does to work aggresively -================================================= - -A deadlock actually occurs when all wait operations creating circular -dependencies run at the same time. Even though they don't, a potential -deadlock exists if the problematic dependencies exist. Thus it's -meaningful to detect not only an actual deadlock but also its potential -possibility. The latter is rather valuable. When a deadlock occurs -actually, we can identify what happens in the system by some means or -other even without lockdep. However, there's no way to detect possiblity -without lockdep unless the whole code is parsed in head. It's terrible. -Lockdep does the both, and crossrelease only focuses on the latter. - -Whether or not a deadlock actually occurs depends on several factors. -For example, what order contexts are switched in is a factor. Assuming -circular dependencies exist, a deadlock would occur when contexts are -switched so that all wait operations creating the dependencies run -simultaneously. Thus to detect a deadlock possibility even in the case -that it has not occured yet, lockdep should consider all possible -combinations of dependencies, trying to: - -1. Use a global dependency graph. - - Lockdep combines all dependencies into one global graph and uses them, - regardless of which context generates them or what order contexts are - switched in. Aggregated dependencies are only considered so they are - prone to be circular if a problem exists. - -2. Check dependencies between classes instead of instances. - - What actually causes a deadlock are instances of lock. However, - lockdep checks dependencies between classes instead of instances. - This way lockdep can detect a deadlock which has not happened but - might happen in future by others but the same class. - -3. Assume all acquisitions lead to waiting. - - Although locks might be acquired without waiting which is essential - to create dependencies, lockdep assumes all acquisitions lead to - waiting since it might be true some time or another. - -CONCLUSION - -Lockdep detects not only an actual deadlock but also its possibility, -and the latter is more valuable. - - -================================================== -APPENDIX B: How to avoid adding false dependencies -================================================== - -Remind what a dependency is. A dependency exists if: - - 1. There are two waiters waiting for each event at a given time. - 2. The only way to wake up each waiter is to trigger its event. - 3. Whether one can be woken up depends on whether the other can. - -For example: - - acquire A - acquire B /* A dependency 'A -> B' exists */ - release B - release A - - where A and B are different lock classes. - -A depedency 'A -> B' exists since: - - 1. A waiter for A and a waiter for B might exist when acquiring B. - 2. Only way to wake up each is to release what it waits for. - 3. Whether the waiter for A can be woken up depends on whether the - other can. IOW, TASK X cannot release A if it fails to acquire B. - -For another example: - - TASK X TASK Y - ------ ------ - acquire AX - acquire B /* A dependency 'AX -> B' exists */ - release B - release AX held by Y - - where AX and B are different lock classes, and a suffix 'X' is added - on crosslocks. - -Even in this case involving crosslocks, the same rule can be applied. A -depedency 'AX -> B' exists since: - - 1. A waiter for AX and a waiter for B might exist when acquiring B. - 2. Only way to wake up each is to release what it waits for. - 3. Whether the waiter for AX can be woken up depends on whether the - other can. IOW, TASK X cannot release AX if it fails to acquire B. - -Let's take a look at more complicated example: - - TASK X TASK Y - ------ ------ - acquire B - release B - fork Y - acquire AX - acquire C /* A dependency 'AX -> C' exists */ - release C - release AX held by Y - - where AX, B and C are different lock classes, and a suffix 'X' is - added on crosslocks. - -Does a dependency 'AX -> B' exist? Nope. - -Two waiters are essential to create a dependency. However, waiters for -AX and B to create 'AX -> B' cannot exist at the same time in this -example. Thus the dependency 'AX -> B' cannot be created. - -It would be ideal if the full set of true ones can be considered. But -we can ensure nothing but what actually happened. Relying on what -actually happens at runtime, we can anyway add only true ones, though -they might be a subset of true ones. It's similar to how lockdep works -for typical locks. There might be more true dependencies than what -lockdep has detected in runtime. Lockdep has no choice but to rely on -what actually happens. Crossrelease also relies on it. - -CONCLUSION - -Relying on what actually happens, lockdep can avoid adding false -dependencies. diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt index 89fff7d611cc..0b3a1148f9f0 100644 --- a/Documentation/vm/zswap.txt +++ b/Documentation/vm/zswap.txt @@ -98,5 +98,25 @@ request is made for a page in an old zpool, it is uncompressed using its original compressor. Once all pages are removed from an old zpool, the zpool and its compressor are freed. +Some of the pages in zswap are same-value filled pages (i.e. contents of the +page have same value or repetitive pattern). These pages include zero-filled +pages and they are handled differently. During store operation, a page is +checked if it is a same-value filled page before compressing it. If true, the +compressed length of the page is set to zero and the pattern or same-filled +value is stored. + +Same-value filled pages identification feature is enabled by default and can be +disabled at boot time by setting the "same_filled_pages_enabled" attribute to 0, +e.g. zswap.same_filled_pages_enabled=0. It can also be enabled and disabled at +runtime using the sysfs "same_filled_pages_enabled" attribute, e.g. + +echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled + +When zswap same-filled page identification is disabled at runtime, it will stop +checking for the same-value filled pages during store operation. However, the +existing pages which are marked as same-value filled pages remain stored +unchanged in zswap until they are either loaded or invalidated. + A debugfs interface is provided for various statistic about pool size, number -of pages stored, and various counters for the reasons pages are rejected. +of pages stored, same-value filled pages and various counters for the reasons +pages are rejected. diff --git a/MAINTAINERS b/MAINTAINERS index 82ad0eabce4f..e626cb622dca 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5431,7 +5431,7 @@ F: drivers/media/tuners/fc2580* FCOE SUBSYSTEM (libfc, libfcoe, fcoe) M: Johannes Thumshirn <jth@kernel.org> -L: fcoe-devel@open-fcoe.org +L: linux-scsi@vger.kernel.org W: www.Open-FCoE.org S: Supported F: drivers/scsi/libfc/ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a93339f5178f..c9a7e9e1414f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -557,7 +557,6 @@ config QCOM_QDF2400_ERRATUM_0065 If unsure, say Y. - config SOCIONEXT_SYNQUACER_PREITS bool "Socionext Synquacer: Workaround for GICv3 pre-ITS" default y @@ -576,6 +575,17 @@ config HISILICON_ERRATUM_161600802 a 128kB offset to be applied to the target address in this commands. If unsure, say Y. + +config QCOM_FALKOR_ERRATUM_E1041 + bool "Falkor E1041: Speculative instruction fetches might cause errant memory access" + default y + help + Falkor CPU may speculatively fetch instructions from an improper + memory location when MMU translation is changed from SCTLR_ELn[M]=1 + to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem. + + If unsure, say Y. + endmenu diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index aef72d886677..8b168280976f 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -512,4 +512,14 @@ alternative_else_nop_endif #endif .endm +/** + * Errata workaround prior to disable MMU. Insert an ISB immediately prior + * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. + */ + .macro pre_disable_mmu_workaround +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041 + isb +#endif + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ac67cfc2585a..060e3a4008ab 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -60,6 +60,9 @@ enum ftr_type { #define FTR_VISIBLE true /* Feature visible to the user space */ #define FTR_HIDDEN false /* Feature is hidden from the user */ +#define FTR_VISIBLE_IF_IS_ENABLED(config) \ + (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN) + struct arm64_ftr_bits { bool sign; /* Value is signed ? */ bool visible; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 235e77d98261..cbf08d7cbf30 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -91,6 +91,7 @@ #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 +#define QCOM_CPU_PART_FALKOR 0xC00 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -99,6 +100,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) +#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 149d05fb9421..bdcc7f1c9d06 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -42,6 +42,8 @@ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <linux/mmdebug.h> +#include <linux/mm_types.h> +#include <linux/sched.h> extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); @@ -149,12 +151,20 @@ static inline pte_t pte_mkwrite(pte_t pte) static inline pte_t pte_mkclean(pte_t pte) { - return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkdirty(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); + + if (pte_write(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkold(pte_t pte) @@ -207,9 +217,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } } -struct mm_struct; -struct vm_area_struct; - extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); /* @@ -238,7 +245,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (pte_valid(*ptep) && pte_valid(pte)) { + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(*ptep), pte_val(pte)); @@ -641,28 +649,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * ptep_set_wrprotect - mark read-only while preserving the hardware update of - * the Access Flag. + * ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; - /* - * ptep_set_wrprotect() is only called on CoW mappings which are - * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE && - * PTE_RDONLY) or writable and software-dirty (PTE_WRITE && - * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and - * protection_map[]. There is no race with the hardware update of the - * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM) - * is set. - */ - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep), - "%s: potential race with hardware DBM", __func__); pte = READ_ONCE(*ptep); do { old_pte = pte; + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 65f42d257414..2a752cb2a0f3 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart) mrs x12, sctlr_el1 ldr x13, =SCTLR_ELx_FLAGS bic x12, x12, x13 + pre_disable_mmu_workaround msr sctlr_el1, x12 isb diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c5ba0097887f..a73a5928f09b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -145,7 +145,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index 4e6ad355bd05..6b9736c3fb56 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -96,6 +96,7 @@ ENTRY(entry) mrs x0, sctlr_el2 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el2, x0 isb b 2f @@ -103,6 +104,7 @@ ENTRY(entry) mrs x0, sctlr_el1 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el1, x0 isb 2: diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 540a1e010eb5..fae81f7964b4 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1043,7 +1043,7 @@ void fpsimd_update_current_state(struct fpsimd_state *state) local_bh_disable(); - current->thread.fpsimd_state = *state; + current->thread.fpsimd_state.user_fpsimd = state->user_fpsimd; if (system_supports_sve() && test_thread_flag(TIF_SVE)) fpsimd_to_sve(current); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 67e86a0f57ac..e3cb9fbf96b6 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -750,6 +750,7 @@ __primary_switch: * to take into account by discarding the current kernel mapping and * creating a new one. */ + pre_disable_mmu_workaround msr sctlr_el1, x20 // disable the MMU isb bl __create_page_tables // recreate kernel mapping diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 749f81779420..74bb56f656ef 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -28,6 +28,7 @@ #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/smp.h> +#include <linux/uaccess.h> #include <asm/compat.h> #include <asm/current.h> @@ -36,7 +37,6 @@ #include <asm/traps.h> #include <asm/cputype.h> #include <asm/system_misc.h> -#include <asm/uaccess.h> /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index ce704a4aeadd..f407e422a720 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel) mrs x0, sctlr_el2 ldr x1, =SCTLR_ELx_FLAGS bic x0, x0, x1 + pre_disable_mmu_workaround msr sctlr_el2, x0 isb 1: diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 3f9615582377..870828c364c5 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -151,6 +151,7 @@ reset: mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc + pre_disable_mmu_workaround msr sctlr_el2, x5 isb diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index ca74a2aace42..7b60d62ac593 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -389,7 +389,7 @@ void ptdump_check_wx(void) .check_wx = true, }; - walk_pgd(&st, &init_mm, 0); + walk_pgd(&st, &init_mm, VA_START); note_page(&st, 0, 0, 0); if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 22168cd0dde7..9b7f89df49db 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -574,7 +574,6 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) { struct siginfo info; const struct fault_info *inf; - int ret = 0; inf = esr_to_fault_info(esr); pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n", @@ -589,7 +588,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) if (interrupts_enabled(regs)) nmi_enter(); - ret = ghes_notify_sea(); + ghes_notify_sea(); if (interrupts_enabled(regs)) nmi_exit(); @@ -604,7 +603,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) info.si_addr = (void __user *)addr; arm64_notify_die("", regs, &info, esr); - return ret; + return 0; } static const struct fault_info fault_info[] = { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 5960bef0170d..00e7b900ca41 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -476,6 +476,8 @@ void __init arm64_memblock_init(void) reserve_elfcorehdr(); + high_memory = __va(memblock_end_of_DRAM() - 1) + 1; + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); @@ -502,7 +504,6 @@ void __init bootmem_init(void) sparse_init(); zone_sizes_init(min, max); - high_memory = __va((max << PAGE_SHIFT) - 1) + 1; memblock_dump_all(); } diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 773c4e039cd7..c0319cbf1eec 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -38,6 +38,25 @@ #define smp_rmb() RISCV_FENCE(r,r) #define smp_wmb() RISCV_FENCE(w,w) +/* + * This is a very specific barrier: it's currently only used in two places in + * the kernel, both in the scheduler. See include/linux/spinlock.h for the two + * orderings it guarantees, but the "critical section is RCsc" guarantee + * mandates a barrier on RISC-V. The sequence looks like: + * + * lr.aq lock + * sc lock <= LOCKED + * smp_mb__after_spinlock() + * // critical section + * lr lock + * sc.rl lock <= UNLOCKED + * + * The AQ/RL pair provides a RCpc critical section, but there's not really any + * way we can take advantage of that here because the ordering is only enforced + * on that one lock. Thus, we're just doing a full fence. + */ +#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) + #include <asm-generic/barrier.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 8fbb6749910d..cb7b0c63014e 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -38,10 +38,6 @@ #include <asm/tlbflush.h> #include <asm/thread_info.h> -#ifdef CONFIG_HVC_RISCV_SBI -#include <asm/hvc_riscv_sbi.h> -#endif - #ifdef CONFIG_DUMMY_CONSOLE struct screen_info screen_info = { .orig_video_lines = 30, @@ -212,13 +208,6 @@ static void __init setup_bootmem(void) void __init setup_arch(char **cmdline_p) { -#if defined(CONFIG_HVC_RISCV_SBI) - if (likely(early_console == NULL)) { - early_console = &riscv_sbi_early_console_dev; - register_console(early_console); - } -#endif - #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index a2ae936a093e..79c78668258e 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -70,7 +70,7 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0; /* Check the reserved flags. */ - if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL)) + if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) return -EINVAL; flush_icache_mm(mm, local); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index f04db3779b34..59eea9c65d3e 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -263,6 +263,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis return retval; } + groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 6293a8768a91..672441c008c7 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -400,6 +400,7 @@ config UNWINDER_FRAME_POINTER config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT + depends on !STACKDEPOT ---help--- This option enables the "guess" unwinder for unwinding kernel stack traces. It scans the stack and reports every kernel text address it diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 1e9c322e973a..f25e1530e064 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -80,6 +80,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o vmlinux-objs-y += $(obj)/mem_encrypt.o + vmlinux-objs-y += $(obj)/pgtable_64.o endif $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 20919b4f3133..fc313e29fe2c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -305,10 +305,18 @@ ENTRY(startup_64) leaq boot_stack_end(%rbx), %rsp #ifdef CONFIG_X86_5LEVEL - /* Check if 5-level paging has already enabled */ - movq %cr4, %rax - testl $X86_CR4_LA57, %eax - jnz lvl5 + /* + * Check if we need to enable 5-level paging. + * RSI holds real mode data and need to be preserved across + * a function call. + */ + pushq %rsi + call l5_paging_required + popq %rsi + + /* If l5_paging_required() returned zero, we're done here. */ + cmpq $0, %rax + je lvl5 /* * At this point we are in long mode with 4-level paging enabled, diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b50c42455e25..98761a1576ce 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -169,6 +169,16 @@ void __puthex(unsigned long value) } } +static bool l5_supported(void) +{ + /* Check if leaf 7 is supported. */ + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)); +} + #if CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) @@ -362,6 +372,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, console_init(); debug_putstr("early console in extract_kernel\n"); + if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) { + error("This linux kernel as configured requires 5-level paging\n" + "This CPU does not support the required 'cr4.la57' feature\n" + "Unable to boot - please use a kernel appropriate for your CPU\n"); + } + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c new file mode 100644 index 000000000000..b4469a37e9a1 --- /dev/null +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -0,0 +1,28 @@ +#include <asm/processor.h> + +/* + * __force_order is used by special_insns.h asm code to force instruction + * serialization. + * + * It is not referenced from the code, but GCC < 5 with -fPIE would fail + * due to an undefined symbol. Define it to make these ancient GCCs work. + */ +unsigned long __force_order; + +int l5_paging_required(void) +{ + /* Check if leaf 7 is supported. */ + + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return 0; + + /* Check if 5-level paging has already been enabled. */ + if (native_read_cr4() & X86_CR4_LA57) + return 0; + + return 1; +} diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index 49f4970f693b..c9e8499fbfe7 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -44,9 +44,9 @@ FDINITRD=$6 # Make sure the files actually exist verify "$FBZIMAGE" -verify "$MTOOLSRC" genbzdisk() { + verify "$MTOOLSRC" mformat a: syslinux $FIMAGE echo "$KCMDLINE" | mcopy - a:syslinux.cfg @@ -57,6 +57,7 @@ genbzdisk() { } genfdimage144() { + verify "$MTOOLSRC" dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null mformat v: syslinux $FIMAGE @@ -68,6 +69,7 @@ genfdimage144() { } genfdimage288() { + verify "$MTOOLSRC" dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null mformat w: syslinux $FIMAGE diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c index 399a29d067d6..cb91a64a99e7 100644 --- a/arch/x86/crypto/salsa20_glue.c +++ b/arch/x86/crypto/salsa20_glue.c @@ -59,13 +59,6 @@ static int encrypt(struct blkcipher_desc *desc, salsa20_ivsetup(ctx, walk.iv); - if (likely(walk.nbytes == nbytes)) - { - salsa20_encrypt_bytes(ctx, walk.src.virt.addr, - walk.dst.virt.addr, nbytes); - return blkcipher_walk_done(desc, &walk, 0); - } - while (walk.nbytes >= 64) { salsa20_encrypt_bytes(ctx, walk.src.virt.addr, walk.dst.virt.addr, diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 982c325dad33..8be6afb58471 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,7 +12,13 @@ /* image of the saved processor state */ struct saved_context { - u16 es, fs, gs, ss; + /* + * On x86_32, all segment registers, with the possible exception of + * gs, are saved at kernel entry in pt_regs. + */ +#ifdef CONFIG_X86_32_LAZY_GS + u16 gs; +#endif unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7306e911faee..a7af9f53c0cb 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -20,8 +20,20 @@ */ struct saved_context { struct pt_regs regs; - u16 ds, es, fs, gs, ss; - unsigned long gs_base, gs_kernel_base, fs_base; + + /* + * User CS and SS are saved in current_pt_regs(). The rest of the + * segment selectors need to be saved and restored here. + */ + u16 ds, es, fs, gs; + + /* + * Usermode FSBASE and GSBASE may not match the fs and gs selectors, + * so we save them separately. We save the kernelmode GSBASE to + * restore percpu access after resume. + */ + unsigned long kernelmode_gs_base, usermode_gs_base, fs_base; + unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; @@ -30,8 +42,7 @@ struct saved_context { u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; u16 idt_pad; - u16 idt_limit; - unsigned long idt_base; + struct desc_ptr idt; u16 ldt; u16 tss; unsigned long tr; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 05a97d5fe298..35cb20994e32 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -106,7 +106,7 @@ EXPORT_SYMBOL(__max_logical_packages); static unsigned int logical_packages __read_mostly; /* Maximum number of SMT threads on any online core */ -int __max_smt_threads __read_mostly; +int __read_mostly __max_smt_threads = 1; /* Flag to indicate if a complete sched domain rebuild is required */ bool x86_topology_update; @@ -1304,7 +1304,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus) * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. */ - ncpus = cpu_data(0).booted_cores * smp_num_siblings; + ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index c4d55919fac1..e0b85930dd77 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 6e4573b1da34..c45b6ec5357b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr) return; } + mmiotrace_iounmap(addr); + addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); - mmiotrace_iounmap(addr); - /* Use the vm area unlocked, assuming the caller ensures there isn't another iounmap for the same address in parallel. Reuse of the virtual address is prevented by diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index c21c2ed04612..58477ec3d66d 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p) unsigned long flags; int ret = 0; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); unsigned int l; pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); - if (get_kmmio_probe(p->addr)) { + if (get_kmmio_probe(addr)) { ret = -EEXIST; goto out; } - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) { ret = -EINVAL; goto out; @@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p) kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { - if (add_kmmio_fault_page(p->addr + size)) + if (add_kmmio_fault_page(addr + size)) pr_err("Unable to set page fault.\n"); size += page_level_size(l); } @@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p) { unsigned long flags; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; unsigned int l; pte_t *pte; - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { - release_kmmio_fault_page(p->addr + size, &release_list); + release_kmmio_fault_page(addr + size, &release_list); size += page_level_size(l); } list_del_rcu(&p->list); diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 1e996df687a3..e663d6bf1328 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -665,6 +665,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) unsigned i; u32 base, limit, high; struct resource *res, *conflict; + struct pci_dev *other; + + /* Check that we are the only device of that type */ + other = pci_get_device(dev->vendor, dev->device, NULL); + if (other != dev || + (other = pci_get_device(dev->vendor, dev->device, other))) { + /* This is a multi-socket system, don't touch it for now */ + pci_dev_put(other); + return; + } for (i = 0; i < 8; i++) { pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base); @@ -696,8 +706,13 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) res->end = 0xfd00000000ull - 1; /* Just grab the free area behind system memory for this */ - while ((conflict = request_resource_conflict(&iomem_resource, res))) + while ((conflict = request_resource_conflict(&iomem_resource, res))) { + if (conflict->end >= res->end) { + kfree(res); + return; + } res->start = conflict->end + 1; + } dev_info(&dev->dev, "adding root bus resource %pR\n", res); @@ -714,10 +729,10 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_bus_add_resource(dev->bus, res, 0); } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 5191de14f4df..36a28eddb435 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt) /* * descriptor tables */ -#ifdef CONFIG_X86_32 store_idt(&ctxt->idt); -#else -/* CONFIG_X86_64 */ - store_idt((struct desc_ptr *)&ctxt->idt_limit); -#endif + /* * We save it here, but restore it only in the hibernate case. * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit @@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt) /* * segment registers */ -#ifdef CONFIG_X86_32 - savesegment(es, ctxt->es); - savesegment(fs, ctxt->fs); +#ifdef CONFIG_X86_32_LAZY_GS savesegment(gs, ctxt->gs); - savesegment(ss, ctxt->ss); -#else -/* CONFIG_X86_64 */ - asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds)); - asm volatile ("movw %%es, %0" : "=m" (ctxt->es)); - asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs)); - asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs)); - asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss)); +#endif +#ifdef CONFIG_X86_64 + savesegment(gs, ctxt->gs); + savesegment(fs, ctxt->fs); + savesegment(ds, ctxt->ds); + savesegment(es, ctxt->es); rdmsrl(MSR_FS_BASE, ctxt->fs_base); - rdmsrl(MSR_GS_BASE, ctxt->gs_base); - rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); + rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); mtrr_save_fixed_ranges(NULL); rdmsrl(MSR_EFER, ctxt->efer); @@ -178,6 +170,9 @@ static void fix_processor_context(void) write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS); syscall_init(); /* This sets MSR_*STAR and related */ +#else + if (boot_cpu_has(X86_FEATURE_SEP)) + enable_sep_cpu(); #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ @@ -190,9 +185,12 @@ static void fix_processor_context(void) } /** - * __restore_processor_state - restore the contents of CPU registers saved - * by __save_processor_state() - * @ctxt - structure to load the registers contents from + * __restore_processor_state - restore the contents of CPU registers saved + * by __save_processor_state() + * @ctxt - structure to load the registers contents from + * + * The asm code that gets us here will have restored a usable GDT, although + * it will be pointing to the wrong alias. */ static void notrace __restore_processor_state(struct saved_context *ctxt) { @@ -215,57 +213,50 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) write_cr2(ctxt->cr2); write_cr0(ctxt->cr0); + /* Restore the IDT. */ + load_idt(&ctxt->idt); + /* - * now restore the descriptor tables to their proper values - * ltr is done i fix_processor_context(). + * Just in case the asm code got us here with the SS, DS, or ES + * out of sync with the GDT, update them. */ -#ifdef CONFIG_X86_32 - load_idt(&ctxt->idt); -#else -/* CONFIG_X86_64 */ - load_idt((const struct desc_ptr *)&ctxt->idt_limit); -#endif + loadsegment(ss, __KERNEL_DS); + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); -#ifdef CONFIG_X86_64 /* - * We need GSBASE restored before percpu access can work. - * percpu access can happen in exception handlers or in complicated - * helpers like load_gs_index(). + * Restore percpu access. Percpu access can happen in exception + * handlers or in complicated helpers like load_gs_index(). */ - wrmsrl(MSR_GS_BASE, ctxt->gs_base); +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); +#else + loadsegment(fs, __KERNEL_PERCPU); + loadsegment(gs, __KERNEL_STACK_CANARY); #endif + /* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */ fix_processor_context(); /* - * Restore segment registers. This happens after restoring the GDT - * and LDT, which happen in fix_processor_context(). + * Now that we have descriptor tables fully restored and working + * exception handling, restore the usermode segments. */ -#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_64 + loadsegment(ds, ctxt->es); loadsegment(es, ctxt->es); loadsegment(fs, ctxt->fs); - loadsegment(gs, ctxt->gs); - loadsegment(ss, ctxt->ss); - - /* - * sysenter MSRs - */ - if (boot_cpu_has(X86_FEATURE_SEP)) - enable_sep_cpu(); -#else -/* CONFIG_X86_64 */ - asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds)); - asm volatile ("movw %0, %%es" :: "r" (ctxt->es)); - asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs)); load_gs_index(ctxt->gs); - asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss)); /* - * Restore FSBASE and user GSBASE after reloading the respective - * segment selectors. + * Restore FSBASE and GSBASE after restoring the selectors, since + * restoring the selectors clobbers the bases. Keep in mind + * that MSR_KERNEL_GS_BASE is horribly misnamed. */ wrmsrl(MSR_FS_BASE, ctxt->fs_base); - wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); + wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); +#elif defined(CONFIG_X86_32_LAZY_GS) + loadsegment(gs, ctxt->gs); #endif do_fpu_end(); diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 6b830d4cb4c8..de58533d3664 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -57,7 +57,7 @@ static u32 xen_apic_read(u32 reg) return 0; if (reg == APIC_LVR) - return 0x10; + return 0x14; #ifdef CONFIG_X86_32 if (reg == APIC_LDR) return SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 358749c38894..415a54ced4d6 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -672,14 +672,15 @@ void af_alg_free_areq_sgls(struct af_alg_async_req *areq) } tsgl = areq->tsgl; - for_each_sg(tsgl, sg, areq->tsgl_entries, i) { - if (!sg_page(sg)) - continue; - put_page(sg_page(sg)); - } + if (tsgl) { + for_each_sg(tsgl, sg, areq->tsgl_entries, i) { + if (!sg_page(sg)) + continue; + put_page(sg_page(sg)); + } - if (areq->tsgl && areq->tsgl_entries) sock_kfree_s(sk, tsgl, areq->tsgl_entries * sizeof(*tsgl)); + } } EXPORT_SYMBOL_GPL(af_alg_free_areq_sgls); diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 805f485ddf1b..48b34e9c6834 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -503,6 +503,7 @@ static void aead_release(void *private) struct aead_tfm *tfm = private; crypto_free_aead(tfm->aead); + crypto_put_default_null_skcipher2(); kfree(tfm); } @@ -535,7 +536,6 @@ static void aead_sock_destruct(struct sock *sk) unsigned int ivlen = crypto_aead_ivsize(tfm); af_alg_pull_tsgl(sk, ctx->used, NULL, 0); - crypto_put_default_null_skcipher2(); sock_kzfree_s(sk, ctx->iv, ivlen); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); diff --git a/crypto/hmac.c b/crypto/hmac.c index 92871dc2a63e..e74730224f0a 100644 --- a/crypto/hmac.c +++ b/crypto/hmac.c @@ -195,11 +195,15 @@ static int hmac_create(struct crypto_template *tmpl, struct rtattr **tb) salg = shash_attr_alg(tb[1], 0, 0); if (IS_ERR(salg)) return PTR_ERR(salg); + alg = &salg->base; + /* The underlying hash algorithm must be unkeyed */ err = -EINVAL; + if (crypto_shash_alg_has_setkey(salg)) + goto out_put_alg; + ds = salg->digestsize; ss = salg->statesize; - alg = &salg->base; if (ds > alg->cra_blocksize || ss < alg->cra_blocksize) goto out_put_alg; diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c index 0b66dc824606..cad395d70d78 100644 --- a/crypto/rsa_helper.c +++ b/crypto/rsa_helper.c @@ -30,7 +30,7 @@ int rsa_get_n(void *context, size_t hdrlen, unsigned char tag, return -EINVAL; if (fips_enabled) { - while (!*ptr && n_sz) { + while (n_sz && !*ptr) { ptr++; n_sz--; } diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c index f550b5d94630..d7da0eea5622 100644 --- a/crypto/salsa20_generic.c +++ b/crypto/salsa20_generic.c @@ -188,13 +188,6 @@ static int encrypt(struct blkcipher_desc *desc, salsa20_ivsetup(ctx, walk.iv); - if (likely(walk.nbytes == nbytes)) - { - salsa20_encrypt_bytes(ctx, walk.dst.virt.addr, - walk.src.virt.addr, nbytes); - return blkcipher_walk_done(desc, &walk, 0); - } - while (walk.nbytes >= 64) { salsa20_encrypt_bytes(ctx, walk.dst.virt.addr, walk.src.virt.addr, diff --git a/crypto/shash.c b/crypto/shash.c index 325a14da5827..e849d3ee2e27 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -25,11 +25,12 @@ static const struct crypto_type crypto_shash_type; -static int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) +int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, + unsigned int keylen) { return -ENOSYS; } +EXPORT_SYMBOL_GPL(shash_no_setkey); static int shash_setkey_unaligned(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index e4ffaeec9ec2..a4c8ad98560d 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1138,7 +1138,7 @@ int acpi_subsys_thaw_noirq(struct device *dev) * skip all of the subsequent "thaw" callbacks for the device. */ if (dev_pm_smart_suspend_and_suspended(dev)) { - dev->power.direct_complete = true; + dev_pm_skip_next_resume_phases(dev); return 0; } diff --git a/drivers/ata/ahci_mtk.c b/drivers/ata/ahci_mtk.c index 80854f71559a..0ae6971c2a4c 100644 --- a/drivers/ata/ahci_mtk.c +++ b/drivers/ata/ahci_mtk.c @@ -1,5 +1,5 @@ /* - * MeidaTek AHCI SATA driver + * MediaTek AHCI SATA driver * * Copyright (c) 2017 MediaTek Inc. * Author: Ryder Lee <ryder.lee@mediatek.com> @@ -25,7 +25,7 @@ #include <linux/reset.h> #include "ahci.h" -#define DRV_NAME "ahci" +#define DRV_NAME "ahci-mtk" #define SYS_CFG 0x14 #define SYS_CFG_SATA_MSK GENMASK(31, 30) @@ -192,5 +192,5 @@ static struct platform_driver mtk_ahci_driver = { }; module_platform_driver(mtk_ahci_driver); -MODULE_DESCRIPTION("MeidaTek SATA AHCI Driver"); +MODULE_DESCRIPTION("MediaTek SATA AHCI Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index b6b0bf76dfc7..2685f28160f7 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -35,6 +35,8 @@ /* port register default value */ #define AHCI_PORT_PHY_1_CFG 0xa003fffe +#define AHCI_PORT_PHY2_CFG 0x28184d1f +#define AHCI_PORT_PHY3_CFG 0x0e081509 #define AHCI_PORT_TRANS_CFG 0x08000029 #define AHCI_PORT_AXICC_CFG 0x3fffffff @@ -183,6 +185,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2, qpriv->ecc_addr); writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); + writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2); + writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC); @@ -190,6 +194,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) case AHCI_LS2080A: writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); + writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2); + writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC); @@ -201,6 +207,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2, qpriv->ecc_addr); writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); + writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2); + writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC); @@ -212,6 +220,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) writel(readl(qpriv->ecc_addr) | ECC_DIS_LS1088A, qpriv->ecc_addr); writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); + writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2); + writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC); @@ -219,6 +229,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv) case AHCI_LS2088A: writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1); + writel(AHCI_PORT_PHY2_CFG, reg_base + PORT_PHY2); + writel(AHCI_PORT_PHY3_CFG, reg_base + PORT_PHY3); writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS); if (qpriv->is_dmacoherent) writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 2a882929de4a..8193b38a1cae 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3082,13 +3082,19 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) bit = fls(mask) - 1; mask &= ~(1 << bit); - /* Mask off all speeds higher than or equal to the current - * one. Force 1.5Gbps if current SPD is not available. + /* + * Mask off all speeds higher than or equal to the current one. At + * this point, if current SPD is not available and we previously + * recorded the link speed from SStatus, the driver has already + * masked off the highest bit so mask should already be 1 or 0. + * Otherwise, we should not force 1.5Gbps on a link where we have + * not previously recorded speed from SStatus. Just return in this + * case. */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; else - mask &= 1; + return -EINVAL; /* were we already at the bottom? */ if (!mask) diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c index ffd8d33c6e0f..6db2e34bd52f 100644 --- a/drivers/ata/pata_pdc2027x.c +++ b/drivers/ata/pata_pdc2027x.c @@ -82,7 +82,7 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed * is issued to the device. However, if the controller clock is 133MHz, * the following tables must be used. */ -static struct pdc2027x_pio_timing { +static const struct pdc2027x_pio_timing { u8 value0, value1, value2; } pdc2027x_pio_timing_tbl[] = { { 0xfb, 0x2b, 0xac }, /* PIO mode 0 */ @@ -92,7 +92,7 @@ static struct pdc2027x_pio_timing { { 0x23, 0x09, 0x25 }, /* PIO mode 4, IORDY on, Prefetch off */ }; -static struct pdc2027x_mdma_timing { +static const struct pdc2027x_mdma_timing { u8 value0, value1; } pdc2027x_mdma_timing_tbl[] = { { 0xdf, 0x5f }, /* MDMA mode 0 */ @@ -100,7 +100,7 @@ static struct pdc2027x_mdma_timing { { 0x69, 0x25 }, /* MDMA mode 2 */ }; -static struct pdc2027x_udma_timing { +static const struct pdc2027x_udma_timing { u8 value0, value1, value2; } pdc2027x_udma_timing_tbl[] = { { 0x4a, 0x0f, 0xd5 }, /* UDMA mode 0 */ @@ -649,7 +649,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) * @host: target ATA host * @board_idx: board identifier */ -static int pdc_hardware_init(struct ata_host *host, unsigned int board_idx) +static void pdc_hardware_init(struct ata_host *host, unsigned int board_idx) { long pll_clock; @@ -665,8 +665,6 @@ static int pdc_hardware_init(struct ata_host *host, unsigned int board_idx) /* Adjust PLL control register */ pdc_adjust_pll(host, pll_clock, board_idx); - - return 0; } /** @@ -753,8 +751,7 @@ static int pdc2027x_init_one(struct pci_dev *pdev, //pci_enable_intx(pdev); /* initialize adapter */ - if (pdc_hardware_init(host, board_idx) != 0) - return -EIO; + pdc_hardware_init(host, board_idx); pci_set_master(pdev); return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt, @@ -778,8 +775,7 @@ static int pdc2027x_reinit_one(struct pci_dev *pdev) else board_idx = PDC_UDMA_133; - if (pdc_hardware_init(host, board_idx)) - return -EIO; + pdc_hardware_init(host, board_idx); ata_host_resume(host); return 0; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index db2f04415927..08744b572af6 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -526,6 +526,21 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd) /*------------------------- Resume routines -------------------------*/ /** + * dev_pm_skip_next_resume_phases - Skip next system resume phases for device. + * @dev: Target device. + * + * Make the core skip the "early resume" and "resume" phases for @dev. + * + * This function can be called by middle-layer code during the "noirq" phase of + * system resume if necessary, but not by device drivers. + */ +void dev_pm_skip_next_resume_phases(struct device *dev) +{ + dev->power.is_late_suspended = false; + dev->power.is_suspended = false; +} + +/** * device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 779869ed32b1..71fad747c0c7 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -199,6 +199,9 @@ struct smi_info { /* The timer for this si. */ struct timer_list si_timer; + /* This flag is set, if the timer can be set */ + bool timer_can_start; + /* This flag is set, if the timer is running (timer_pending() isn't enough) */ bool timer_running; @@ -355,6 +358,8 @@ out: static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) { + if (!smi_info->timer_can_start) + return; smi_info->last_timeout_jiffies = jiffies; mod_timer(&smi_info->si_timer, new_val); smi_info->timer_running = true; @@ -374,21 +379,18 @@ static void start_new_msg(struct smi_info *smi_info, unsigned char *msg, smi_info->handlers->start_transaction(smi_info->si_sm, msg, size); } -static void start_check_enables(struct smi_info *smi_info, bool start_timer) +static void start_check_enables(struct smi_info *smi_info) { unsigned char msg[2]; msg[0] = (IPMI_NETFN_APP_REQUEST << 2); msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD; - if (start_timer) - start_new_msg(smi_info, msg, 2); - else - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2); + start_new_msg(smi_info, msg, 2); smi_info->si_state = SI_CHECKING_ENABLES; } -static void start_clear_flags(struct smi_info *smi_info, bool start_timer) +static void start_clear_flags(struct smi_info *smi_info) { unsigned char msg[3]; @@ -397,10 +399,7 @@ static void start_clear_flags(struct smi_info *smi_info, bool start_timer) msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD; msg[2] = WDT_PRE_TIMEOUT_INT; - if (start_timer) - start_new_msg(smi_info, msg, 3); - else - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3); + start_new_msg(smi_info, msg, 3); smi_info->si_state = SI_CLEARING_FLAGS; } @@ -435,11 +434,11 @@ static void start_getting_events(struct smi_info *smi_info) * Note that we cannot just use disable_irq(), since the interrupt may * be shared. */ -static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer) +static inline bool disable_si_irq(struct smi_info *smi_info) { if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = true; - start_check_enables(smi_info, start_timer); + start_check_enables(smi_info); return true; } return false; @@ -449,7 +448,7 @@ static inline bool enable_si_irq(struct smi_info *smi_info) { if ((smi_info->io.irq) && (smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = false; - start_check_enables(smi_info, true); + start_check_enables(smi_info); return true; } return false; @@ -467,7 +466,7 @@ static struct ipmi_smi_msg *alloc_msg_handle_irq(struct smi_info *smi_info) msg = ipmi_alloc_smi_msg(); if (!msg) { - if (!disable_si_irq(smi_info, true)) + if (!disable_si_irq(smi_info)) smi_info->si_state = SI_NORMAL; } else if (enable_si_irq(smi_info)) { ipmi_free_smi_msg(msg); @@ -483,7 +482,7 @@ retry: /* Watchdog pre-timeout */ smi_inc_stat(smi_info, watchdog_pretimeouts); - start_clear_flags(smi_info, true); + start_clear_flags(smi_info); smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT; if (smi_info->intf) ipmi_smi_watchdog_pretimeout(smi_info->intf); @@ -866,7 +865,7 @@ restart: * disable and messages disabled. */ if (smi_info->supports_event_msg_buff || smi_info->io.irq) { - start_check_enables(smi_info, true); + start_check_enables(smi_info); } else { smi_info->curr_msg = alloc_msg_handle_irq(smi_info); if (!smi_info->curr_msg) @@ -1167,6 +1166,7 @@ static int smi_start_processing(void *send_info, /* Set up the timer that drives the interface. */ timer_setup(&new_smi->si_timer, smi_timeout, 0); + new_smi->timer_can_start = true; smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES); /* Try to claim any interrupts. */ @@ -1936,10 +1936,12 @@ static void check_for_broken_irqs(struct smi_info *smi_info) check_set_rcv_irq(smi_info); } -static inline void wait_for_timer_and_thread(struct smi_info *smi_info) +static inline void stop_timer_and_thread(struct smi_info *smi_info) { if (smi_info->thread != NULL) kthread_stop(smi_info->thread); + + smi_info->timer_can_start = false; if (smi_info->timer_running) del_timer_sync(&smi_info->si_timer); } @@ -2152,7 +2154,7 @@ static int try_smi_init(struct smi_info *new_smi) * Start clearing the flags before we enable interrupts or the * timer to avoid racing with the timer. */ - start_clear_flags(new_smi, false); + start_clear_flags(new_smi); /* * IRQ is defined to be set when non-zero. req_events will @@ -2238,7 +2240,7 @@ out_err_remove_attrs: dev_set_drvdata(new_smi->io.dev, NULL); out_err_stop_timer: - wait_for_timer_and_thread(new_smi); + stop_timer_and_thread(new_smi); out_err: new_smi->interrupt_disabled = true; @@ -2388,7 +2390,7 @@ static void cleanup_one_si(struct smi_info *to_clean) */ if (to_clean->io.irq_cleanup) to_clean->io.irq_cleanup(&to_clean->io); - wait_for_timer_and_thread(to_clean); + stop_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off @@ -2400,7 +2402,7 @@ static void cleanup_one_si(struct smi_info *to_clean) schedule_timeout_uninterruptible(1); } if (to_clean->handlers) - disable_si_irq(to_clean, false); + disable_si_irq(to_clean); while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); diff --git a/drivers/char/ipmi/ipmi_si_parisc.c b/drivers/char/ipmi/ipmi_si_parisc.c index 090b073ab441..6b10f0e18a95 100644 --- a/drivers/char/ipmi/ipmi_si_parisc.c +++ b/drivers/char/ipmi/ipmi_si_parisc.c @@ -10,6 +10,8 @@ static int __init ipmi_parisc_probe(struct parisc_device *dev) { struct si_sm_io io; + memset(&io, 0, sizeof(io)); + io.si_type = SI_KCS; io.addr_source = SI_DEVICETREE; io.addr_type = IPMI_MEM_ADDR_SPACE; diff --git a/drivers/char/ipmi/ipmi_si_pci.c b/drivers/char/ipmi/ipmi_si_pci.c index 99771f5cad07..27dd11c49d21 100644 --- a/drivers/char/ipmi/ipmi_si_pci.c +++ b/drivers/char/ipmi/ipmi_si_pci.c @@ -103,10 +103,13 @@ static int ipmi_pci_probe(struct pci_dev *pdev, io.addr_source_cleanup = ipmi_pci_cleanup; io.addr_source_data = pdev; - if (pci_resource_flags(pdev, 0) & IORESOURCE_IO) + if (pci_resource_flags(pdev, 0) & IORESOURCE_IO) { io.addr_type = IPMI_IO_ADDR_SPACE; - else + io.io_setup = ipmi_si_port_setup; + } else { io.addr_type = IPMI_MEM_ADDR_SPACE; + io.io_setup = ipmi_si_mem_setup; + } io.addr_data = pci_resource_start(pdev, 0); io.regspacing = ipmi_pci_probe_regspacing(&io); diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 482014137953..9ae236036e32 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -152,14 +152,23 @@ static void drm_connector_free(struct kref *kref) connector->funcs->destroy(connector); } -static void drm_connector_free_work_fn(struct work_struct *work) +void drm_connector_free_work_fn(struct work_struct *work) { - struct drm_connector *connector = - container_of(work, struct drm_connector, free_work); - struct drm_device *dev = connector->dev; + struct drm_connector *connector, *n; + struct drm_device *dev = + container_of(work, struct drm_device, mode_config.connector_free_work); + struct drm_mode_config *config = &dev->mode_config; + unsigned long flags; + struct llist_node *freed; - drm_mode_object_unregister(dev, &connector->base); - connector->funcs->destroy(connector); + spin_lock_irqsave(&config->connector_list_lock, flags); + freed = llist_del_all(&config->connector_free_list); + spin_unlock_irqrestore(&config->connector_list_lock, flags); + + llist_for_each_entry_safe(connector, n, freed, free_node) { + drm_mode_object_unregister(dev, &connector->base); + connector->funcs->destroy(connector); + } } /** @@ -191,8 +200,6 @@ int drm_connector_init(struct drm_device *dev, if (ret) return ret; - INIT_WORK(&connector->free_work, drm_connector_free_work_fn); - connector->base.properties = &connector->properties; connector->dev = dev; connector->funcs = funcs; @@ -547,10 +554,17 @@ EXPORT_SYMBOL(drm_connector_list_iter_begin); * actually release the connector when dropping our final reference. */ static void -drm_connector_put_safe(struct drm_connector *conn) +__drm_connector_put_safe(struct drm_connector *conn) { - if (refcount_dec_and_test(&conn->base.refcount.refcount)) - schedule_work(&conn->free_work); + struct drm_mode_config *config = &conn->dev->mode_config; + + lockdep_assert_held(&config->connector_list_lock); + + if (!refcount_dec_and_test(&conn->base.refcount.refcount)) + return; + + llist_add(&conn->free_node, &config->connector_free_list); + schedule_work(&config->connector_free_work); } /** @@ -582,10 +596,10 @@ drm_connector_list_iter_next(struct drm_connector_list_iter *iter) /* loop until it's not a zombie connector */ } while (!kref_get_unless_zero(&iter->conn->base.refcount)); - spin_unlock_irqrestore(&config->connector_list_lock, flags); if (old_conn) - drm_connector_put_safe(old_conn); + __drm_connector_put_safe(old_conn); + spin_unlock_irqrestore(&config->connector_list_lock, flags); return iter->conn; } @@ -602,9 +616,15 @@ EXPORT_SYMBOL(drm_connector_list_iter_next); */ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter) { + struct drm_mode_config *config = &iter->dev->mode_config; + unsigned long flags; + iter->dev = NULL; - if (iter->conn) - drm_connector_put_safe(iter->conn); + if (iter->conn) { + spin_lock_irqsave(&config->connector_list_lock, flags); + __drm_connector_put_safe(iter->conn); + spin_unlock_irqrestore(&config->connector_list_lock, flags); + } lock_release(&connector_list_iter_dep_map, 0, _RET_IP_); } EXPORT_SYMBOL(drm_connector_list_iter_end); @@ -1231,6 +1251,19 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector, if (edid) size = EDID_LENGTH * (1 + edid->extensions); + /* Set the display info, using edid if available, otherwise + * reseting the values to defaults. This duplicates the work + * done in drm_add_edid_modes, but that function is not + * consistently called before this one in all drivers and the + * computation is cheap enough that it seems better to + * duplicate it rather than attempt to ensure some arbitrary + * ordering of calls. + */ + if (edid) + drm_add_display_info(connector, edid); + else + drm_reset_display_info(connector); + drm_object_property_set_value(&connector->base, dev->mode_config.non_desktop_property, connector->display_info.non_desktop); diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h index 9ebb8841778c..af00f42ba269 100644 --- a/drivers/gpu/drm/drm_crtc_internal.h +++ b/drivers/gpu/drm/drm_crtc_internal.h @@ -142,6 +142,7 @@ int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj, uint64_t value); int drm_connector_create_standard_properties(struct drm_device *dev); const char *drm_get_connector_force_name(enum drm_connector_force force); +void drm_connector_free_work_fn(struct work_struct *work); /* IOCTL */ int drm_mode_connector_property_set_ioctl(struct drm_device *dev, diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 5dfe14763871..cb487148359a 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -1731,7 +1731,7 @@ EXPORT_SYMBOL(drm_edid_duplicate); * * Returns true if @vendor is in @edid, false otherwise */ -static bool edid_vendor(struct edid *edid, const char *vendor) +static bool edid_vendor(const struct edid *edid, const char *vendor) { char edid_vendor[3]; @@ -1749,7 +1749,7 @@ static bool edid_vendor(struct edid *edid, const char *vendor) * * This tells subsequent routines what fixes they need to apply. */ -static u32 edid_get_quirks(struct edid *edid) +static u32 edid_get_quirks(const struct edid *edid) { const struct edid_quirk *quirk; int i; @@ -2813,7 +2813,7 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid, /* * Search EDID for CEA extension block. */ -static u8 *drm_find_edid_extension(struct edid *edid, int ext_id) +static u8 *drm_find_edid_extension(const struct edid *edid, int ext_id) { u8 *edid_ext = NULL; int i; @@ -2835,12 +2835,12 @@ static u8 *drm_find_edid_extension(struct edid *edid, int ext_id) return edid_ext; } -static u8 *drm_find_cea_extension(struct edid *edid) +static u8 *drm_find_cea_extension(const struct edid *edid) { return drm_find_edid_extension(edid, CEA_EXT); } -static u8 *drm_find_displayid_extension(struct edid *edid) +static u8 *drm_find_displayid_extension(const struct edid *edid) { return drm_find_edid_extension(edid, DISPLAYID_EXT); } @@ -4363,7 +4363,7 @@ drm_parse_hdmi_vsdb_video(struct drm_connector *connector, const u8 *db) } static void drm_parse_cea_ext(struct drm_connector *connector, - struct edid *edid) + const struct edid *edid) { struct drm_display_info *info = &connector->display_info; const u8 *edid_ext; @@ -4397,11 +4397,33 @@ static void drm_parse_cea_ext(struct drm_connector *connector, } } -static void drm_add_display_info(struct drm_connector *connector, - struct edid *edid, u32 quirks) +/* A connector has no EDID information, so we've got no EDID to compute quirks from. Reset + * all of the values which would have been set from EDID + */ +void +drm_reset_display_info(struct drm_connector *connector) { struct drm_display_info *info = &connector->display_info; + info->width_mm = 0; + info->height_mm = 0; + + info->bpc = 0; + info->color_formats = 0; + info->cea_rev = 0; + info->max_tmds_clock = 0; + info->dvi_dual = false; + + info->non_desktop = 0; +} +EXPORT_SYMBOL_GPL(drm_reset_display_info); + +u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid) +{ + struct drm_display_info *info = &connector->display_info; + + u32 quirks = edid_get_quirks(edid); + info->width_mm = edid->width_cm * 10; info->height_mm = edid->height_cm * 10; @@ -4414,11 +4436,13 @@ static void drm_add_display_info(struct drm_connector *connector, info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP); + DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop); + if (edid->revision < 3) - return; + return quirks; if (!(edid->input & DRM_EDID_INPUT_DIGITAL)) - return; + return quirks; drm_parse_cea_ext(connector, edid); @@ -4438,7 +4462,7 @@ static void drm_add_display_info(struct drm_connector *connector, /* Only defined for 1.4 with digital displays */ if (edid->revision < 4) - return; + return quirks; switch (edid->input & DRM_EDID_DIGITAL_DEPTH_MASK) { case DRM_EDID_DIGITAL_DEPTH_6: @@ -4473,7 +4497,9 @@ static void drm_add_display_info(struct drm_connector *connector, info->color_formats |= DRM_COLOR_FORMAT_YCRCB444; if (edid->features & DRM_EDID_FEATURE_RGB_YCRCB422) info->color_formats |= DRM_COLOR_FORMAT_YCRCB422; + return quirks; } +EXPORT_SYMBOL_GPL(drm_add_display_info); static int validate_displayid(u8 *displayid, int length, int idx) { @@ -4627,14 +4653,12 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) return 0; } - quirks = edid_get_quirks(edid); - /* * CEA-861-F adds ycbcr capability map block, for HDMI 2.0 sinks. * To avoid multiple parsing of same block, lets parse that map * from sink info, before parsing CEA modes. */ - drm_add_display_info(connector, edid, quirks); + quirks = drm_add_display_info(connector, edid); /* * EDID spec says modes should be preferred in this order: diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index d1eb56a1eff4..59849f02e2ad 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -254,10 +254,10 @@ static struct drm_master *drm_lease_create(struct drm_master *lessor, struct idr return lessee; out_lessee: - drm_master_put(&lessee); - mutex_unlock(&dev->mode_config.idr_mutex); + drm_master_put(&lessee); + return ERR_PTR(error); } diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 61a1c8ea74bc..c3c79ee6119e 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -575,21 +575,23 @@ EXPORT_SYMBOL(drm_mm_remove_node); */ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) { + struct drm_mm *mm = old->mm; + DRM_MM_BUG_ON(!old->allocated); *new = *old; list_replace(&old->node_list, &new->node_list); - rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree.rb_root); + rb_replace_node_cached(&old->rb, &new->rb, &mm->interval_tree); if (drm_mm_hole_follows(old)) { list_replace(&old->hole_stack, &new->hole_stack); rb_replace_node(&old->rb_hole_size, &new->rb_hole_size, - &old->mm->holes_size); + &mm->holes_size); rb_replace_node(&old->rb_hole_addr, &new->rb_hole_addr, - &old->mm->holes_addr); + &mm->holes_addr); } old->allocated = false; diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index cc78b3d9e5e4..256de7313612 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -382,6 +382,9 @@ void drm_mode_config_init(struct drm_device *dev) ida_init(&dev->mode_config.connector_ida); spin_lock_init(&dev->mode_config.connector_list_lock); + init_llist_head(&dev->mode_config.connector_free_list); + INIT_WORK(&dev->mode_config.connector_free_work, drm_connector_free_work_fn); + drm_mode_create_standard_properties(dev); /* Just to be sure */ @@ -432,7 +435,7 @@ void drm_mode_config_cleanup(struct drm_device *dev) } drm_connector_list_iter_end(&conn_iter); /* connector_iter drops references in a work item. */ - flush_scheduled_work(); + flush_work(&dev->mode_config.connector_free_work); if (WARN_ON(!list_empty(&dev->mode_config.connector_list))) { drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 6c32c89a83a9..638540943c61 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -888,8 +888,10 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) /* If we got force-completed because of GPU reset rather than * through our IRQ handler, signal the fence now. */ - if (exec->fence) + if (exec->fence) { dma_fence_signal(exec->fence); + dma_fence_put(exec->fence); + } if (exec->bo) { for (i = 0; i < exec->bo_count; i++) { diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 61b2e5377993..26eddbb62893 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -139,6 +139,7 @@ vc4_irq_finish_render_job(struct drm_device *dev) list_move_tail(&exec->head, &vc4->job_done_list); if (exec->fence) { dma_fence_signal_locked(exec->fence); + dma_fence_put(exec->fence); exec->fence = NULL; } vc4_submit_next_render_job(dev); diff --git a/drivers/hwtracing/stm/ftrace.c b/drivers/hwtracing/stm/ftrace.c index bd126a7c6da2..7da75644c750 100644 --- a/drivers/hwtracing/stm/ftrace.c +++ b/drivers/hwtracing/stm/ftrace.c @@ -42,9 +42,11 @@ static struct stm_ftrace { * @len: length of the data packet */ static void notrace -stm_ftrace_write(const void *buf, unsigned int len) +stm_ftrace_write(struct trace_export *export, const void *buf, unsigned int len) { - stm_source_write(&stm_ftrace.data, STM_FTRACE_CHAN, buf, len); + struct stm_ftrace *stm = container_of(export, struct stm_ftrace, ftrace); + + stm_source_write(&stm->data, STM_FTRACE_CHAN, buf, len); } static int stm_ftrace_link(struct stm_source_data *data) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index b8ac591aaaa7..c546b567f3b5 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1611,7 +1611,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, int l; struct dm_buffer *b, *tmp; unsigned long freed = 0; - unsigned long count = nr_to_scan; + unsigned long count = c->n_buffers[LIST_CLEAN] + + c->n_buffers[LIST_DIRTY]; unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { @@ -1647,8 +1648,11 @@ static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker); + unsigned long count = READ_ONCE(c->n_buffers[LIST_CLEAN]) + + READ_ONCE(c->n_buffers[LIST_DIRTY]); + unsigned long retain_target = get_retain_buffers(c); - return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]); + return (count < retain_target) ? 0 : (count - retain_target); } /* diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index cf23a14f9c6a..47407e43b96a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3472,18 +3472,18 @@ static int __init dm_cache_init(void) { int r; - r = dm_register_target(&cache_target); - if (r) { - DMERR("cache target registration failed: %d", r); - return r; - } - migration_cache = KMEM_CACHE(dm_cache_migration, 0); if (!migration_cache) { dm_unregister_target(&cache_target); return -ENOMEM; } + r = dm_register_target(&cache_target); + if (r) { + DMERR("cache target registration failed: %d", r); + return r; + } + return 0; } diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index c8faa2b85842..f7810cc869ac 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -458,6 +458,38 @@ do { \ } while (0) /* + * Check whether bios must be queued in the device-mapper core rather + * than here in the target. + * + * If MPATHF_QUEUE_IF_NO_PATH and MPATHF_SAVED_QUEUE_IF_NO_PATH hold + * the same value then we are not between multipath_presuspend() + * and multipath_resume() calls and we have no need to check + * for the DMF_NOFLUSH_SUSPENDING flag. + */ +static bool __must_push_back(struct multipath *m, unsigned long flags) +{ + return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) != + test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &flags)) && + dm_noflush_suspending(m->ti)); +} + +/* + * Following functions use READ_ONCE to get atomic access to + * all m->flags to avoid taking spinlock + */ +static bool must_push_back_rq(struct multipath *m) +{ + unsigned long flags = READ_ONCE(m->flags); + return test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) || __must_push_back(m, flags); +} + +static bool must_push_back_bio(struct multipath *m) +{ + unsigned long flags = READ_ONCE(m->flags); + return __must_push_back(m, flags); +} + +/* * Map cloned requests (request-based multipath) */ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, @@ -478,7 +510,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, pgpath = choose_pgpath(m, nr_bytes); if (!pgpath) { - if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) + if (must_push_back_rq(m)) return DM_MAPIO_DELAY_REQUEUE; dm_report_EIO(m); /* Failed */ return DM_MAPIO_KILL; @@ -553,7 +585,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m } if (!pgpath) { - if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) + if (must_push_back_bio(m)) return DM_MAPIO_REQUEUE; dm_report_EIO(m); return DM_MAPIO_KILL; @@ -651,8 +683,7 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path, assign_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags, (save_old_value && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) || (!save_old_value && queue_if_no_path)); - assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, - queue_if_no_path || dm_noflush_suspending(m->ti)); + assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, queue_if_no_path); spin_unlock_irqrestore(&m->lock, flags); if (!queue_if_no_path) { @@ -1486,7 +1517,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, fail_path(pgpath); if (atomic_read(&m->nr_valid_paths) == 0 && - !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { + !must_push_back_rq(m)) { if (error == BLK_STS_IOERR) dm_report_EIO(m); /* complete with the original error */ @@ -1521,8 +1552,12 @@ static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { - dm_report_EIO(m); - *error = BLK_STS_IOERR; + if (must_push_back_bio(m)) { + r = DM_ENDIO_REQUEUE; + } else { + dm_report_EIO(m); + *error = BLK_STS_IOERR; + } goto done; } @@ -1957,13 +1992,6 @@ static int __init dm_multipath_init(void) { int r; - r = dm_register_target(&multipath_target); - if (r < 0) { - DMERR("request-based register failed %d", r); - r = -EINVAL; - goto bad_register_target; - } - kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0); if (!kmultipathd) { DMERR("failed to create workqueue kmpathd"); @@ -1985,13 +2013,20 @@ static int __init dm_multipath_init(void) goto bad_alloc_kmpath_handlerd; } + r = dm_register_target(&multipath_target); + if (r < 0) { + DMERR("request-based register failed %d", r); + r = -EINVAL; + goto bad_register_target; + } + return 0; +bad_register_target: + destroy_workqueue(kmpath_handlerd); bad_alloc_kmpath_handlerd: destroy_workqueue(kmultipathd); bad_alloc_kmultipathd: - dm_unregister_target(&multipath_target); -bad_register_target: return r; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 1113b42e1eda..a0613bd8ed00 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -2411,24 +2411,6 @@ static int __init dm_snapshot_init(void) return r; } - r = dm_register_target(&snapshot_target); - if (r < 0) { - DMERR("snapshot target register failed %d", r); - goto bad_register_snapshot_target; - } - - r = dm_register_target(&origin_target); - if (r < 0) { - DMERR("Origin target register failed %d", r); - goto bad_register_origin_target; - } - - r = dm_register_target(&merge_target); - if (r < 0) { - DMERR("Merge target register failed %d", r); - goto bad_register_merge_target; - } - r = init_origin_hash(); if (r) { DMERR("init_origin_hash failed."); @@ -2449,19 +2431,37 @@ static int __init dm_snapshot_init(void) goto bad_pending_cache; } + r = dm_register_target(&snapshot_target); + if (r < 0) { + DMERR("snapshot target register failed %d", r); + goto bad_register_snapshot_target; + } + + r = dm_register_target(&origin_target); + if (r < 0) { + DMERR("Origin target register failed %d", r); + goto bad_register_origin_target; + } + + r = dm_register_target(&merge_target); + if (r < 0) { + DMERR("Merge target register failed %d", r); + goto bad_register_merge_target; + } + return 0; -bad_pending_cache: - kmem_cache_destroy(exception_cache); -bad_exception_cache: - exit_origin_hash(); -bad_origin_hash: - dm_unregister_target(&merge_target); bad_register_merge_target: dm_unregister_target(&origin_target); bad_register_origin_target: dm_unregister_target(&snapshot_target); bad_register_snapshot_target: + kmem_cache_destroy(pending_cache); +bad_pending_cache: + kmem_cache_destroy(exception_cache); +bad_exception_cache: + exit_origin_hash(); +bad_origin_hash: dm_exception_store_exit(); return r; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 88130b5d95f9..aaffd0c0ee9a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -453,14 +453,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, refcount_set(&dd->count, 1); list_add(&dd->list, &t->devices); + goto out; } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) return r; - refcount_inc(&dd->count); } - + refcount_inc(&dd->count); +out: *result = dd->dm_dev; return 0; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 89e5dff9b4cf..f91d771fff4b 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -4355,30 +4355,28 @@ static struct target_type thin_target = { static int __init dm_thin_init(void) { - int r; + int r = -ENOMEM; pool_table_init(); + _new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0); + if (!_new_mapping_cache) + return r; + r = dm_register_target(&thin_target); if (r) - return r; + goto bad_new_mapping_cache; r = dm_register_target(&pool_target); if (r) - goto bad_pool_target; - - r = -ENOMEM; - - _new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0); - if (!_new_mapping_cache) - goto bad_new_mapping_cache; + goto bad_thin_target; return 0; -bad_new_mapping_cache: - dm_unregister_target(&pool_target); -bad_pool_target: +bad_thin_target: dm_unregister_target(&thin_target); +bad_new_mapping_cache: + kmem_cache_destroy(_new_mapping_cache); return r; } diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index f06cd91964ce..79a5b985ccf5 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -75,9 +75,11 @@ struct mmc_fixup { #define EXT_CSD_REV_ANY (-1u) #define CID_MANFID_SANDISK 0x2 +#define CID_MANFID_ATP 0x9 #define CID_MANFID_TOSHIBA 0x11 #define CID_MANFID_MICRON 0x13 #define CID_MANFID_SAMSUNG 0x15 +#define CID_MANFID_APACER 0x27 #define CID_MANFID_KINGSTON 0x70 #define CID_MANFID_HYNIX 0x90 diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index d209fb466979..208a762b87ef 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1290,7 +1290,7 @@ out_err: static void mmc_select_driver_type(struct mmc_card *card) { - int card_drv_type, drive_strength, drv_type; + int card_drv_type, drive_strength, drv_type = 0; int fixed_drv_type = card->host->fixed_drv_type; card_drv_type = card->ext_csd.raw_driver_strength | diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index f664e9cbc9f8..75d317623852 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -53,6 +53,14 @@ static const struct mmc_fixup mmc_blk_fixups[] = { MMC_QUIRK_BLK_NO_CMD23), /* + * Some SD cards lockup while using CMD23 multiblock transfers. + */ + MMC_FIXUP("AF SD", CID_MANFID_ATP, CID_OEMID_ANY, add_quirk_sd, + MMC_QUIRK_BLK_NO_CMD23), + MMC_FIXUP("APUSD", CID_MANFID_APACER, 0x5048, add_quirk_sd, + MMC_QUIRK_BLK_NO_CMD23), + + /* * Some MMC cards need longer data read timeout than indicated in CSD. */ MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc, diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index 12796eccb2be..52ab3cb0a0bf 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -1128,12 +1128,12 @@ static int rcar_pcie_probe(struct platform_device *pdev) err = rcar_pcie_get_resources(pcie); if (err < 0) { dev_err(dev, "failed to request resources: %d\n", err); - goto err_free_bridge; + goto err_free_resource_list; } err = rcar_pcie_parse_map_dma_ranges(pcie, dev->of_node); if (err) - goto err_free_bridge; + goto err_free_resource_list; pm_runtime_enable(dev); err = pm_runtime_get_sync(dev); @@ -1176,9 +1176,9 @@ err_pm_put: err_pm_disable: pm_runtime_disable(dev); -err_free_bridge: - pci_free_host_bridge(bridge); +err_free_resource_list: pci_free_resource_list(&pcie->resources); + pci_free_host_bridge(bridge); return err; } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 7f47bb72bf30..945099d49f8f 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -999,7 +999,7 @@ static int pci_pm_thaw_noirq(struct device *dev) * the subsequent "thaw" callbacks for the device. */ if (dev_pm_smart_suspend_and_suspended(dev)) { - dev->power.direct_complete = true; + dev_pm_skip_next_resume_phases(dev); return 0; } diff --git a/drivers/platform/x86/asus-wireless.c b/drivers/platform/x86/asus-wireless.c index f3796164329e..d4aeac3477f5 100644 --- a/drivers/platform/x86/asus-wireless.c +++ b/drivers/platform/x86/asus-wireless.c @@ -118,6 +118,7 @@ static void asus_wireless_notify(struct acpi_device *adev, u32 event) return; } input_report_key(data->idev, KEY_RFKILL, 1); + input_sync(data->idev); input_report_key(data->idev, KEY_RFKILL, 0); input_sync(data->idev); } diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index bf897b1832b1..cd4725e7e0b5 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -37,6 +37,7 @@ struct quirk_entry { u8 touchpad_led; + u8 kbd_led_levels_off_1; int needs_kbd_timeouts; /* @@ -67,6 +68,10 @@ static struct quirk_entry quirk_dell_xps13_9333 = { .kbd_timeouts = { 0, 5, 15, 60, 5 * 60, 15 * 60, -1 }, }; +static struct quirk_entry quirk_dell_latitude_e6410 = { + .kbd_led_levels_off_1 = 1, +}; + static struct platform_driver platform_driver = { .driver = { .name = "dell-laptop", @@ -269,6 +274,15 @@ static const struct dmi_system_id dell_quirks[] __initconst = { }, .driver_data = &quirk_dell_xps13_9333, }, + { + .callback = dmi_matched, + .ident = "Dell Latitude E6410", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6410"), + }, + .driver_data = &quirk_dell_latitude_e6410, + }, { } }; @@ -1149,6 +1163,9 @@ static int kbd_get_info(struct kbd_info *info) units = (buffer->output[2] >> 8) & 0xFF; info->levels = (buffer->output[2] >> 16) & 0xFF; + if (quirks && quirks->kbd_led_levels_off_1 && info->levels) + info->levels--; + if (units & BIT(0)) info->seconds = (buffer->output[3] >> 0) & 0xFF; if (units & BIT(1)) diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 39d2f4518483..fb25b20df316 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -639,6 +639,8 @@ static int dell_wmi_events_set_enabled(bool enable) int ret; buffer = kzalloc(sizeof(struct calling_interface_buffer), GFP_KERNEL); + if (!buffer) + return -ENOMEM; buffer->cmd_class = CLASS_INFO; buffer->cmd_select = SELECT_APP_REGISTRATION; buffer->input[0] = 0x10000; diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index bec9f3193f60..80a8cb26cdea 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -2482,8 +2482,8 @@ int aac_command_thread(void *data) /* Synchronize our watches */ if (((NSEC_PER_SEC - (NSEC_PER_SEC / HZ)) > now.tv_nsec) && (now.tv_nsec > (NSEC_PER_SEC / HZ))) - difference = (((NSEC_PER_SEC - now.tv_nsec) * HZ) - + NSEC_PER_SEC / 2) / NSEC_PER_SEC; + difference = HZ + HZ / 2 - + now.tv_nsec / (NSEC_PER_SEC / HZ); else { if (now.tv_nsec > NSEC_PER_SEC / 2) ++now.tv_sec; @@ -2507,6 +2507,10 @@ int aac_command_thread(void *data) if (kthread_should_stop()) break; + /* + * we probably want usleep_range() here instead of the + * jiffies computation + */ schedule_timeout(difference); if (kthread_should_stop()) diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c index 72ca2a2e08e2..b2fa195adc7a 100644 --- a/drivers/scsi/bfa/bfad_bsg.c +++ b/drivers/scsi/bfa/bfad_bsg.c @@ -3135,7 +3135,8 @@ bfad_im_bsg_vendor_request(struct bsg_job *job) struct fc_bsg_request *bsg_request = job->request; struct fc_bsg_reply *bsg_reply = job->reply; uint32_t vendor_cmd = bsg_request->rqst_data.h_vendor.vendor_cmd[0]; - struct bfad_im_port_s *im_port = shost_priv(fc_bsg_to_shost(job)); + struct Scsi_Host *shost = fc_bsg_to_shost(job); + struct bfad_im_port_s *im_port = bfad_get_im_port(shost); struct bfad_s *bfad = im_port->bfad; void *payload_kbuf; int rc = -EINVAL; @@ -3350,7 +3351,8 @@ int bfad_im_bsg_els_ct_request(struct bsg_job *job) { struct bfa_bsg_data *bsg_data; - struct bfad_im_port_s *im_port = shost_priv(fc_bsg_to_shost(job)); + struct Scsi_Host *shost = fc_bsg_to_shost(job); + struct bfad_im_port_s *im_port = bfad_get_im_port(shost); struct bfad_s *bfad = im_port->bfad; bfa_bsg_fcpt_t *bsg_fcpt; struct bfad_fcxp *drv_fcxp; diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c index 24e657a4ec80..c05d6e91e4bd 100644 --- a/drivers/scsi/bfa/bfad_im.c +++ b/drivers/scsi/bfa/bfad_im.c @@ -546,6 +546,7 @@ int bfad_im_scsi_host_alloc(struct bfad_s *bfad, struct bfad_im_port_s *im_port, struct device *dev) { + struct bfad_im_port_pointer *im_portp; int error = 1; mutex_lock(&bfad_mutex); @@ -564,7 +565,8 @@ bfad_im_scsi_host_alloc(struct bfad_s *bfad, struct bfad_im_port_s *im_port, goto out_free_idr; } - im_port->shost->hostdata[0] = (unsigned long)im_port; + im_portp = shost_priv(im_port->shost); + im_portp->p = im_port; im_port->shost->unique_id = im_port->idr_id; im_port->shost->this_id = -1; im_port->shost->max_id = MAX_FCP_TARGET; @@ -748,7 +750,7 @@ bfad_scsi_host_alloc(struct bfad_im_port_s *im_port, struct bfad_s *bfad) sht->sg_tablesize = bfad->cfg_data.io_max_sge; - return scsi_host_alloc(sht, sizeof(unsigned long)); + return scsi_host_alloc(sht, sizeof(struct bfad_im_port_pointer)); } void diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h index c81ec2a77ef5..06ce4ba2b7bc 100644 --- a/drivers/scsi/bfa/bfad_im.h +++ b/drivers/scsi/bfa/bfad_im.h @@ -69,6 +69,16 @@ struct bfad_im_port_s { struct fc_vport *fc_vport; }; +struct bfad_im_port_pointer { + struct bfad_im_port_s *p; +}; + +static inline struct bfad_im_port_s *bfad_get_im_port(struct Scsi_Host *host) +{ + struct bfad_im_port_pointer *im_portp = shost_priv(host); + return im_portp->p; +} + enum bfad_itnim_state { ITNIM_STATE_NONE, ITNIM_STATE_ONLINE, diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 5da46052e179..21be672679fb 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -904,10 +904,14 @@ static void fc_lport_recv_els_req(struct fc_lport *lport, case ELS_FLOGI: if (!lport->point_to_multipoint) fc_lport_recv_flogi_req(lport, fp); + else + fc_rport_recv_req(lport, fp); break; case ELS_LOGO: if (fc_frame_sid(fp) == FC_FID_FLOGI) fc_lport_recv_logo_req(lport, fp); + else + fc_rport_recv_req(lport, fp); break; case ELS_RSCN: lport->tt.disc_recv_req(lport, fp); diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index ca1566237ae7..3183d63de4da 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -2145,7 +2145,7 @@ void sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost, struct sas_rphy *rphy) { struct domain_device *dev; - unsigned int reslen = 0; + unsigned int rcvlen = 0; int ret = -EINVAL; /* no rphy means no smp target support (ie aic94xx host) */ @@ -2179,12 +2179,12 @@ void sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost, ret = smp_execute_task_sg(dev, job->request_payload.sg_list, job->reply_payload.sg_list); - if (ret > 0) { - /* positive number is the untransferred residual */ - reslen = ret; + if (ret >= 0) { + /* bsg_job_done() requires the length received */ + rcvlen = job->reply_payload.payload_len - ret; ret = 0; } out: - bsg_job_done(job, ret, reslen); + bsg_job_done(job, ret, rcvlen); } diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c index 56faeb049b4a..87c08ff37ddd 100644 --- a/drivers/scsi/lpfc/lpfc_mem.c +++ b/drivers/scsi/lpfc/lpfc_mem.c @@ -753,12 +753,12 @@ lpfc_rq_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp) drqe.address_hi = putPaddrHigh(rqb_entry->dbuf.phys); rc = lpfc_sli4_rq_put(rqb_entry->hrq, rqb_entry->drq, &hrqe, &drqe); if (rc < 0) { - (rqbp->rqb_free_buffer)(phba, rqb_entry); lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "6409 Cannot post to RQ %d: %x %x\n", rqb_entry->hrq->queue_id, rqb_entry->hrq->host_index, rqb_entry->hrq->hba_index); + (rqbp->rqb_free_buffer)(phba, rqb_entry); } else { list_add_tail(&rqb_entry->hbuf.list, &rqbp->rqb_buffer_list); rqbp->buffer_count++; diff --git a/drivers/scsi/scsi_debugfs.c b/drivers/scsi/scsi_debugfs.c index 01f08c03f2c1..c3765d29fd3f 100644 --- a/drivers/scsi/scsi_debugfs.c +++ b/drivers/scsi/scsi_debugfs.c @@ -8,9 +8,11 @@ void scsi_show_rq(struct seq_file *m, struct request *rq) { struct scsi_cmnd *cmd = container_of(scsi_req(rq), typeof(*cmd), req); int msecs = jiffies_to_msecs(jiffies - cmd->jiffies_at_alloc); - char buf[80]; + const u8 *const cdb = READ_ONCE(cmd->cmnd); + char buf[80] = "(?)"; - __scsi_format_command(buf, sizeof(buf), cmd->cmnd, cmd->cmd_len); + if (cdb) + __scsi_format_command(buf, sizeof(buf), cdb, cmd->cmd_len); seq_printf(m, ", .cmd=%s, .retries=%d, allocated %d.%03d s ago", buf, cmd->retries, msecs / 1000, msecs % 1000); } diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 78d4aa8df675..449ef5adbb2b 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -34,7 +34,6 @@ struct scsi_dev_info_list_table { }; -static const char spaces[] = " "; /* 16 of them */ static blist_flags_t scsi_default_dev_flags; static LIST_HEAD(scsi_dev_info_list); static char scsi_dev_flags[256]; @@ -298,20 +297,13 @@ static void scsi_strcpy_devinfo(char *name, char *to, size_t to_length, size_t from_length; from_length = strlen(from); - strncpy(to, from, min(to_length, from_length)); - if (from_length < to_length) { - if (compatible) { - /* - * NUL terminate the string if it is short. - */ - to[from_length] = '\0'; - } else { - /* - * space pad the string if it is short. - */ - strncpy(&to[from_length], spaces, - to_length - from_length); - } + /* This zero-pads the destination */ + strncpy(to, from, to_length); + if (from_length < to_length && !compatible) { + /* + * space pad the string if it is short. + */ + memset(&to[from_length], ' ', to_length - from_length); } if (from_length > to_length) printk(KERN_WARNING "%s: %s string '%s' is too long\n", @@ -458,7 +450,8 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, /* * vendor strings must be an exact match */ - if (vmax != strlen(devinfo->vendor) || + if (vmax != strnlen(devinfo->vendor, + sizeof(devinfo->vendor)) || memcmp(devinfo->vendor, vskip, vmax)) continue; @@ -466,7 +459,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * @model specifies the full string, and * must be larger or equal to devinfo->model */ - mlen = strlen(devinfo->model); + mlen = strnlen(devinfo->model, sizeof(devinfo->model)); if (mmax < mlen || memcmp(devinfo->model, mskip, mlen)) continue; return devinfo; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 00742c50cd44..d9ca1dfab154 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1967,6 +1967,8 @@ static bool scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx) out_put_device: put_device(&sdev->sdev_gendev); out: + if (atomic_read(&sdev->device_busy) == 0 && !scsi_device_blocked(sdev)) + blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY); return false; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 24fe68522716..a028ab3322a9 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1312,6 +1312,7 @@ static int sd_init_command(struct scsi_cmnd *cmd) static void sd_uninit_command(struct scsi_cmnd *SCpnt) { struct request *rq = SCpnt->request; + u8 *cmnd; if (SCpnt->flags & SCMD_ZONE_WRITE_LOCK) sd_zbc_write_unlock_zone(SCpnt); @@ -1320,9 +1321,10 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) __free_page(rq->special_vec.bv_page); if (SCpnt->cmnd != scsi_req(rq)->cmd) { - mempool_free(SCpnt->cmnd, sd_cdb_pool); + cmnd = SCpnt->cmnd; SCpnt->cmnd = NULL; SCpnt->cmd_len = 0; + mempool_free(cmnd, sd_cdb_pool); } } diff --git a/drivers/staging/ccree/ssi_hash.c b/drivers/staging/ccree/ssi_hash.c index 1799d3f26a9e..2035835b62dc 100644 --- a/drivers/staging/ccree/ssi_hash.c +++ b/drivers/staging/ccree/ssi_hash.c @@ -1769,7 +1769,7 @@ static int ssi_ahash_import(struct ahash_request *req, const void *in) struct device *dev = drvdata_to_dev(ctx->drvdata); struct ahash_req_ctx *state = ahash_request_ctx(req); u32 tmp; - int rc; + int rc = 0; memcpy(&tmp, in, sizeof(u32)); if (tmp != CC_EXPORT_MAGIC) { diff --git a/drivers/staging/pi433/rf69.c b/drivers/staging/pi433/rf69.c index e69a2153c999..12c9df9cddde 100644 --- a/drivers/staging/pi433/rf69.c +++ b/drivers/staging/pi433/rf69.c @@ -102,7 +102,7 @@ enum modulation rf69_get_modulation(struct spi_device *spi) currentValue = READ_REG(REG_DATAMODUL); - switch (currentValue & MASK_DATAMODUL_MODULATION_TYPE >> 3) { // TODO improvement: change 3 to define + switch (currentValue & MASK_DATAMODUL_MODULATION_TYPE) { case DATAMODUL_MODULATION_TYPE_OOK: return OOK; case DATAMODUL_MODULATION_TYPE_FSK: return FSK; default: return undefined; diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index a9192fe4f345..c92131edfaba 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -522,10 +522,8 @@ static int virtio_mmio_probe(struct platform_device *pdev) return -EBUSY; vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL); - if (!vm_dev) { - rc = -ENOMEM; - goto free_mem; - } + if (!vm_dev) + return -ENOMEM; vm_dev->vdev.dev.parent = &pdev->dev; vm_dev->vdev.dev.release = virtio_mmio_release_dev; @@ -535,17 +533,14 @@ static int virtio_mmio_probe(struct platform_device *pdev) spin_lock_init(&vm_dev->lock); vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem)); - if (vm_dev->base == NULL) { - rc = -EFAULT; - goto free_vmdev; - } + if (vm_dev->base == NULL) + return -EFAULT; /* Check magic value */ magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE); if (magic != ('v' | 'i' << 8 | 'r' << 16 | 't' << 24)) { dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic); - rc = -ENODEV; - goto unmap; + return -ENODEV; } /* Check device version */ @@ -553,8 +548,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) if (vm_dev->version < 1 || vm_dev->version > 2) { dev_err(&pdev->dev, "Version %ld not supported!\n", vm_dev->version); - rc = -ENXIO; - goto unmap; + return -ENXIO; } vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID); @@ -563,8 +557,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) * virtio-mmio device with an ID 0 is a (dummy) placeholder * with no function. End probing now with no error reported. */ - rc = -ENODEV; - goto unmap; + return -ENODEV; } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); @@ -590,33 +583,15 @@ static int virtio_mmio_probe(struct platform_device *pdev) platform_set_drvdata(pdev, vm_dev); rc = register_virtio_device(&vm_dev->vdev); - if (rc) { - iounmap(vm_dev->base); - devm_release_mem_region(&pdev->dev, mem->start, - resource_size(mem)); + if (rc) put_device(&vm_dev->vdev.dev); - } - return rc; -unmap: - iounmap(vm_dev->base); -free_mem: - devm_release_mem_region(&pdev->dev, mem->start, - resource_size(mem)); -free_vmdev: - devm_kfree(&pdev->dev, vm_dev); + return rc; } static int virtio_mmio_remove(struct platform_device *pdev) { struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev); - struct resource *mem; - - iounmap(vm_dev->base); - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (mem) - devm_release_mem_region(&pdev->dev, mem->start, - resource_size(mem)); unregister_virtio_device(&vm_dev->vdev); return 0; diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index d8dd54678ab7..e5d0c28372ea 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -269,7 +269,7 @@ config XEN_ACPI_HOTPLUG_CPU config XEN_ACPI_PROCESSOR tristate "Xen ACPI processor" - depends on XEN && X86 && ACPI_PROCESSOR && CPU_FREQ + depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ default m help This ACPI processor uploads Power Management information to the Xen diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 8fc41705c7cd..961a12dc6dc8 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -170,7 +170,6 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, mutex_unlock(&sbi->wq_mutex); - if (autofs4_write(sbi, pipe, &pkt, pktsz)) switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) { case 0: break; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ab69dcb70e8a..1b468250e947 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1440,6 +1440,29 @@ static int __close_session(struct ceph_mds_client *mdsc, return request_close_session(mdsc, session); } +static bool drop_negative_children(struct dentry *dentry) +{ + struct dentry *child; + bool all_negative = true; + + if (!d_is_dir(dentry)) + goto out; + + spin_lock(&dentry->d_lock); + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + if (d_really_is_positive(child)) { + all_negative = false; + break; + } + } + spin_unlock(&dentry->d_lock); + + if (all_negative) + shrink_dcache_parent(dentry); +out: + return all_negative; +} + /* * Trim old(er) caps. * @@ -1490,16 +1513,27 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) if ((used | wanted) & ~oissued & mine) goto out; /* we need these caps */ - session->s_trim_caps--; if (oissued) { /* we aren't the only cap.. just remove us */ __ceph_remove_cap(cap, true); + session->s_trim_caps--; } else { + struct dentry *dentry; /* try dropping referring dentries */ spin_unlock(&ci->i_ceph_lock); - d_prune_aliases(inode); - dout("trim_caps_cb %p cap %p pruned, count now %d\n", - inode, cap, atomic_read(&inode->i_count)); + dentry = d_find_any_alias(inode); + if (dentry && drop_negative_children(dentry)) { + int count; + dput(dentry); + d_prune_aliases(inode); + count = atomic_read(&inode->i_count); + if (count == 1) + session->s_trim_caps--; + dout("trim_caps_cb %p cap %p pruned, count now %d\n", + inode, cap, count); + } else { + dput(dentry); + } return 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e06740436b92..ed88ab8a4774 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1406,7 +1406,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, } while (rc == -EAGAIN); if (rc) { - cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); + if (rc != -ENOENT) + cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); goto out; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5331631386a2..01346b8b6edb 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2678,27 +2678,27 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, cifs_small_buf_release(req); rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; - shdr = get_sync_hdr(rsp); - if (shdr->Status == STATUS_END_OF_FILE) { + if (rc) { + if (rc != -ENODATA) { + cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); + cifs_dbg(VFS, "Send error in read = %d\n", rc); + } free_rsp_buf(resp_buftype, rsp_iov.iov_base); - return 0; + return rc == -ENODATA ? 0 : rc; } - if (rc) { - cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); - cifs_dbg(VFS, "Send error in read = %d\n", rc); - } else { - *nbytes = le32_to_cpu(rsp->DataLength); - if ((*nbytes > CIFS_MAX_MSGSIZE) || - (*nbytes > io_parms->length)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - *nbytes, io_parms->length); - rc = -EIO; - *nbytes = 0; - } + *nbytes = le32_to_cpu(rsp->DataLength); + if ((*nbytes > CIFS_MAX_MSGSIZE) || + (*nbytes > io_parms->length)) { + cifs_dbg(FYI, "bad length %d for count %d\n", + *nbytes, io_parms->length); + rc = -EIO; + *nbytes = 0; } + shdr = get_sync_hdr(rsp); + if (*buf) { memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes); free_rsp_buf(resp_buftype, rsp_iov.iov_base); diff --git a/fs/exec.c b/fs/exec.c index 6be2aa0ab26f..156f56acfe8e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1216,15 +1216,14 @@ killed: return -EAGAIN; } -char *get_task_comm(char *buf, struct task_struct *tsk) +char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); - strncpy(buf, tsk->comm, sizeof(tsk->comm)); + strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } -EXPORT_SYMBOL_GPL(get_task_comm); +EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 697f8ae7792d..f650e475d8f0 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -60,6 +60,9 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) gi->gid[i] = exp->ex_anon_gid; else gi->gid[i] = rqgi->gid[i]; + + /* Each thread allocates its own gi, no race */ + groups_sort(gi); } } else { gi = get_group_info(rqgi); diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index cbfc196e5dc5..5ac415466861 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -24,6 +24,16 @@ config OVERLAY_FS_REDIRECT_DIR an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. +config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW + bool "Overlayfs: follow redirects even if redirects are turned off" + default y + depends on OVERLAY_FS + help + Disable this to get a possibly more secure configuration, but that + might not be backward compatible with previous kernels. + + For more information, see Documentation/filesystems/overlayfs.txt + config OVERLAY_FS_INDEX bool "Overlayfs: turn on inodes index feature by default" depends on OVERLAY_FS diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index e13921824c70..f9788bc116a8 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -887,7 +887,8 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) spin_unlock(&dentry->d_lock); } else { kfree(redirect); - pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err); + pr_warn_ratelimited("overlayfs: failed to set redirect (%i)\n", + err); /* Fall back to userspace copy-up */ err = -EXDEV; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 625ed8066570..beb945e1963c 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -435,7 +435,7 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower, /* Check if index is orphan and don't warn before cleaning it */ if (d_inode(index)->i_nlink == 1 && - ovl_get_nlink(index, origin.dentry, 0) == 0) + ovl_get_nlink(origin.dentry, index, 0) == 0) err = -ENOENT; dput(origin.dentry); @@ -681,6 +681,22 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (d.stop) break; + /* + * Following redirects can have security consequences: it's like + * a symlink into the lower layer without the permission checks. + * This is only a problem if the upper layer is untrusted (e.g + * comes from an USB drive). This can allow a non-readable file + * or directory to become readable. + * + * Only following redirects when redirects are enabled disables + * this attack vector when not necessary. + */ + err = -EPERM; + if (d.redirect && !ofs->config.redirect_follow) { + pr_warn_ratelimited("overlay: refusing to follow redirect for (%pd2)\n", dentry); + goto out_put; + } + if (d.redirect && d.redirect[0] == '/' && poe != roe) { poe = roe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 13eab09a6b6f..b489099ccd49 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -180,7 +180,7 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode) { struct dentry *ret = vfs_tmpfile(dentry, mode, 0); - int err = IS_ERR(ret) ? PTR_ERR(ret) : 0; + int err = PTR_ERR_OR_ZERO(ret); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); return ret; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 752bab645879..9d0bc03bf6e4 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -14,6 +14,8 @@ struct ovl_config { char *workdir; bool default_permissions; bool redirect_dir; + bool redirect_follow; + const char *redirect_mode; bool index; }; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 0daa4354fec4..8c98578d27a1 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -499,7 +499,7 @@ out: return err; fail: - pr_warn_ratelimited("overlay: failed to look up (%s) for ino (%i)\n", + pr_warn_ratelimited("overlayfs: failed to look up (%s) for ino (%i)\n", p->name, err); goto out; } @@ -663,7 +663,10 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) return PTR_ERR(rdt.cache); } - return iterate_dir(od->realfile, &rdt.ctx); + err = iterate_dir(od->realfile, &rdt.ctx); + ctx->pos = rdt.ctx.pos; + + return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 288d20f9a55a..76440feb79f6 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -33,6 +33,13 @@ module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); MODULE_PARM_DESC(ovl_redirect_dir_def, "Default to on or off for the redirect_dir feature"); +static bool ovl_redirect_always_follow = + IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); +module_param_named(redirect_always_follow, ovl_redirect_always_follow, + bool, 0644); +MODULE_PARM_DESC(ovl_redirect_always_follow, + "Follow redirects even if redirect_dir feature is turned off"); + static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); module_param_named(index, ovl_index_def, bool, 0644); MODULE_PARM_DESC(ovl_index_def, @@ -232,6 +239,7 @@ static void ovl_free_fs(struct ovl_fs *ofs) kfree(ofs->config.lowerdir); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); + kfree(ofs->config.redirect_mode); if (ofs->creator_cred) put_cred(ofs->creator_cred); kfree(ofs); @@ -244,6 +252,7 @@ static void ovl_put_super(struct super_block *sb) ovl_free_fs(ofs); } +/* Sync real dirty inodes in upper filesystem (if it exists) */ static int ovl_sync_fs(struct super_block *sb, int wait) { struct ovl_fs *ofs = sb->s_fs_info; @@ -252,14 +261,24 @@ static int ovl_sync_fs(struct super_block *sb, int wait) if (!ofs->upper_mnt) return 0; - upper_sb = ofs->upper_mnt->mnt_sb; - if (!upper_sb->s_op->sync_fs) + + /* + * If this is a sync(2) call or an emergency sync, all the super blocks + * will be iterated, including upper_sb, so no need to do anything. + * + * If this is a syncfs(2) call, then we do need to call + * sync_filesystem() on upper_sb, but enough if we do it when being + * called with wait == 1. + */ + if (!wait) return 0; - /* real inodes have already been synced by sync_filesystem(ovl_sb) */ + upper_sb = ofs->upper_mnt->mnt_sb; + down_read(&upper_sb->s_umount); - ret = upper_sb->s_op->sync_fs(upper_sb, wait); + ret = sync_filesystem(upper_sb); up_read(&upper_sb->s_umount); + return ret; } @@ -295,6 +314,11 @@ static bool ovl_force_readonly(struct ovl_fs *ofs) return (!ofs->upper_mnt || !ofs->workdir); } +static const char *ovl_redirect_mode_def(void) +{ + return ovl_redirect_dir_def ? "on" : "off"; +} + /** * ovl_show_options * @@ -313,12 +337,10 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) } if (ofs->config.default_permissions) seq_puts(m, ",default_permissions"); - if (ofs->config.redirect_dir != ovl_redirect_dir_def) - seq_printf(m, ",redirect_dir=%s", - ofs->config.redirect_dir ? "on" : "off"); + if (strcmp(ofs->config.redirect_mode, ovl_redirect_mode_def()) != 0) + seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode); if (ofs->config.index != ovl_index_def) - seq_printf(m, ",index=%s", - ofs->config.index ? "on" : "off"); + seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); return 0; } @@ -348,8 +370,7 @@ enum { OPT_UPPERDIR, OPT_WORKDIR, OPT_DEFAULT_PERMISSIONS, - OPT_REDIRECT_DIR_ON, - OPT_REDIRECT_DIR_OFF, + OPT_REDIRECT_DIR, OPT_INDEX_ON, OPT_INDEX_OFF, OPT_ERR, @@ -360,8 +381,7 @@ static const match_table_t ovl_tokens = { {OPT_UPPERDIR, "upperdir=%s"}, {OPT_WORKDIR, "workdir=%s"}, {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, - {OPT_REDIRECT_DIR_ON, "redirect_dir=on"}, - {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"}, + {OPT_REDIRECT_DIR, "redirect_dir=%s"}, {OPT_INDEX_ON, "index=on"}, {OPT_INDEX_OFF, "index=off"}, {OPT_ERR, NULL} @@ -390,10 +410,37 @@ static char *ovl_next_opt(char **s) return sbegin; } +static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode) +{ + if (strcmp(mode, "on") == 0) { + config->redirect_dir = true; + /* + * Does not make sense to have redirect creation without + * redirect following. + */ + config->redirect_follow = true; + } else if (strcmp(mode, "follow") == 0) { + config->redirect_follow = true; + } else if (strcmp(mode, "off") == 0) { + if (ovl_redirect_always_follow) + config->redirect_follow = true; + } else if (strcmp(mode, "nofollow") != 0) { + pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n", + mode); + return -EINVAL; + } + + return 0; +} + static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; + config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL); + if (!config->redirect_mode) + return -ENOMEM; + while ((p = ovl_next_opt(&opt)) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -428,12 +475,11 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->default_permissions = true; break; - case OPT_REDIRECT_DIR_ON: - config->redirect_dir = true; - break; - - case OPT_REDIRECT_DIR_OFF: - config->redirect_dir = false; + case OPT_REDIRECT_DIR: + kfree(config->redirect_mode); + config->redirect_mode = match_strdup(&args[0]); + if (!config->redirect_mode) + return -ENOMEM; break; case OPT_INDEX_ON: @@ -458,7 +504,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->workdir = NULL; } - return 0; + return ovl_parse_redirect_mode(config, config->redirect_mode); } #define OVL_WORKDIR_NAME "work" @@ -1160,7 +1206,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!cred) goto out_err; - ofs->config.redirect_dir = ovl_redirect_dir_def; ofs->config.index = ovl_index_def; err = ovl_parse_opt((char *) data, &ofs->config); if (err) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index de3f04a98656..3b57ef0f2f76 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -920,8 +920,7 @@ STATIC xfs_agnumber_t xfs_ialloc_ag_select( xfs_trans_t *tp, /* transaction pointer */ xfs_ino_t parent, /* parent directory inode number */ - umode_t mode, /* bits set to indicate file type */ - int okalloc) /* ok to allocate more space */ + umode_t mode) /* bits set to indicate file type */ { xfs_agnumber_t agcount; /* number of ag's in the filesystem */ xfs_agnumber_t agno; /* current ag number */ @@ -978,9 +977,6 @@ xfs_ialloc_ag_select( return agno; } - if (!okalloc) - goto nextag; - if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, tp, agno, flags); if (error) @@ -1680,7 +1676,6 @@ xfs_dialloc( struct xfs_trans *tp, xfs_ino_t parent, umode_t mode, - int okalloc, struct xfs_buf **IO_agbp, xfs_ino_t *inop) { @@ -1692,6 +1687,7 @@ xfs_dialloc( int noroom = 0; xfs_agnumber_t start_agno; struct xfs_perag *pag; + int okalloc = 1; if (*IO_agbp) { /* @@ -1707,7 +1703,7 @@ xfs_dialloc( * We do not have an agbp, so select an initial allocation * group for inode allocation. */ - start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc); + start_agno = xfs_ialloc_ag_select(tp, parent, mode); if (start_agno == NULLAGNUMBER) { *inop = NULLFSINO; return 0; diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index d2bdcd5e7312..66a8de0b1caa 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -81,7 +81,6 @@ xfs_dialloc( struct xfs_trans *tp, /* transaction pointer */ xfs_ino_t parent, /* parent inode (directory) */ umode_t mode, /* mode bits for new inode */ - int okalloc, /* ok to allocate more space */ struct xfs_buf **agbp, /* buf for a.g. inode header */ xfs_ino_t *inop); /* inode number allocated */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 9c42c4efd01e..ab3aef2ae823 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -46,7 +46,6 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -#include "scrub/scrub.h" #include "scrub/btree.h" /* diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 472080e75788..86daed0e3a45 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -26,7 +26,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 801274126648..b41952a4ddd8 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -749,7 +749,6 @@ xfs_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, - int okalloc, xfs_buf_t **ialloc_context, xfs_inode_t **ipp) { @@ -765,7 +764,7 @@ xfs_ialloc( * Call the space management code to pick * the on-disk inode to be allocated. */ - error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc, + error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, ialloc_context, &ino); if (error) return error; @@ -957,7 +956,6 @@ xfs_dir_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, /* project id */ - int okalloc, /* ok to allocate new space */ xfs_inode_t **ipp, /* pointer to inode; it will be locked. */ int *committed) @@ -988,8 +986,8 @@ xfs_dir_ialloc( * transaction commit so that no other process can steal * the inode(s) that we've just allocated. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc, - &ialloc_context, &ip); + code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context, + &ip); /* * Return an error if we were unable to allocate a new inode. @@ -1061,7 +1059,7 @@ xfs_dir_ialloc( * this call should always succeed. */ code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, - okalloc, &ialloc_context, &ip); + &ialloc_context, &ip); /* * If we get an error at this point, return to the caller @@ -1182,11 +1180,6 @@ xfs_create( xfs_flush_inodes(mp); error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); } - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1203,19 +1196,13 @@ xfs_create( if (error) goto out_trans_cancel; - if (!resblks) { - error = xfs_dir_canenter(tp, dp, name); - if (error) - goto out_trans_cancel; - } - /* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip, + NULL); if (error) goto out_trans_cancel; @@ -1340,11 +1327,6 @@ xfs_create_tmpfile( tres = &M_RES(mp)->tr_create_tmpfile; error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1353,8 +1335,7 @@ xfs_create_tmpfile( if (error) goto out_trans_cancel; - error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, prid, &ip, NULL); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index cc13c3763721..b2136af9289f 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -428,7 +428,7 @@ xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); int xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t, - xfs_nlink_t, dev_t, prid_t, int, + xfs_nlink_t, dev_t, prid_t, struct xfs_inode **, int *); /* from xfs_file.c */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 33eb4fb2e3fd..7ab52a8bc0a9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1213,7 +1213,7 @@ xfs_xattr_iomap_begin( ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, - &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK); + &nimaps, XFS_BMAPI_ATTRFORK); out_unlock: xfs_iunlock(ip, lockmode); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 010a13a201aa..ec952dfad359 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -793,8 +793,8 @@ xfs_qm_qino_alloc( return error; if (need_alloc) { - error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, - &committed); + error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ip, + &committed); if (error) { xfs_trans_cancel(tp); return error; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cc041a29eb70..cf7c8f81bebb 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -49,8 +49,6 @@ #include "xfs_alloc.h" #include "xfs_quota_defs.h" #include "xfs_quota.h" -#include "xfs_btree.h" -#include "xfs_bmap_btree.h" #include "xfs_reflink.h" #include "xfs_iomap.h" #include "xfs_rmap_btree.h" diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 68d3ca2c4968..2e9e793a8f9d 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -232,11 +232,6 @@ xfs_symlink( resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp); - if (error == -ENOSPC && fs_blocks == 0) { - resblks = 0; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, 0, 0, 0, - &tp); - } if (error) goto out_release_inode; @@ -260,14 +255,6 @@ xfs_symlink( goto out_trans_cancel; /* - * Check for ability to enter directory entry, if no space reserved. - */ - if (!resblks) { - error = xfs_dir_canenter(tp, dp, link_name); - if (error) - goto out_trans_cancel; - } - /* * Initialize the bmap freelist prior to calling either * bmapi or the directory create code. */ @@ -277,7 +264,7 @@ xfs_symlink( * Allocate an inode for the symlink. */ error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, - prid, resblks > 0, &ip, NULL); + prid, &ip, NULL); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 5d95fe348294..35f3546b6af5 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -24,7 +24,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_da_btree.h" diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index f0b44c16e88f..c2bae8da642c 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -82,6 +82,14 @@ int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); void ahash_free_instance(struct crypto_instance *inst); +int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, + unsigned int keylen); + +static inline bool crypto_shash_alg_has_setkey(struct shash_alg *alg) +{ + return alg->setkey != shash_no_setkey; +} + int crypto_init_ahash_spawn(struct crypto_ahash_spawn *spawn, struct hash_alg_common *alg, struct crypto_instance *inst); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index a4649c56ca2f..5971577016a2 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -24,6 +24,7 @@ #define __DRM_CONNECTOR_H__ #include <linux/list.h> +#include <linux/llist.h> #include <linux/ctype.h> #include <linux/hdmi.h> #include <drm/drm_mode_object.h> @@ -918,12 +919,13 @@ struct drm_connector { uint16_t tile_h_size, tile_v_size; /** - * @free_work: + * @free_node: * - * Work used only by &drm_connector_iter to be able to clean up a - * connector from any context. + * List used only by &drm_connector_iter to be able to clean up a + * connector from any context, in conjunction with + * &drm_mode_config.connector_free_work. */ - struct work_struct free_work; + struct llist_node free_node; }; #define obj_to_connector(x) container_of(x, struct drm_connector, base) diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 2ec41d032e56..efe6d5a8e834 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -465,6 +465,8 @@ struct edid *drm_get_edid(struct drm_connector *connector, struct edid *drm_get_edid_switcheroo(struct drm_connector *connector, struct i2c_adapter *adapter); struct edid *drm_edid_duplicate(const struct edid *edid); +void drm_reset_display_info(struct drm_connector *connector); +u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid); int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid); u8 drm_match_cea_mode(const struct drm_display_mode *to_match); diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index b21e827c5c78..b0ce26d71296 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -27,6 +27,7 @@ #include <linux/types.h> #include <linux/idr.h> #include <linux/workqueue.h> +#include <linux/llist.h> #include <drm/drm_modeset_lock.h> @@ -393,7 +394,7 @@ struct drm_mode_config { /** * @connector_list_lock: Protects @num_connector and - * @connector_list. + * @connector_list and @connector_free_list. */ spinlock_t connector_list_lock; /** @@ -414,6 +415,21 @@ struct drm_mode_config { */ struct list_head connector_list; /** + * @connector_free_list: + * + * List of connector objects linked with &drm_connector.free_head. + * Protected by @connector_list_lock. Used by + * drm_for_each_connector_iter() and + * &struct drm_connector_list_iter to savely free connectors using + * @connector_free_work. + */ + struct llist_head connector_free_list; + /** + * @connector_free_work: Work to clean up @connector_free_list. + */ + struct work_struct connector_free_work; + + /** * @num_encoder: * * Number of encoders on this device. This is invariant over the diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 188ed9f65517..52e611ab9a6c 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -220,21 +220,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of - * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the - * compiler is aware of some particular ordering. One way to make the - * compiler aware of ordering is to put the two invocations of READ_ONCE, - * WRITE_ONCE or ACCESS_ONCE() in different C statements. + * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some + * particular ordering. One way to make the compiler aware of ordering is to + * put the two invocations of READ_ONCE or WRITE_ONCE in different C + * statements. * - * In contrast to ACCESS_ONCE these two macros will also work on aggregate - * data types like structs or unions. If the size of the accessed data - * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at - * least two memcpy()s: one for the __builtin_memcpy() and then one for - * the macro doing the copy of variable - '__u' allocated on the stack. + * These two macros will also work on aggregate data types like structs or + * unions. If the size of the accessed data type exceeds the word size of + * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will + * fall back to memcpy(). There's at least two memcpy()s: one for the + * __builtin_memcpy() and then one for the macro doing the copy of variable + * - '__u' allocated on the stack. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. @@ -327,29 +327,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") -/* - * Prevent the compiler from merging or refetching accesses. The compiler - * is also forbidden from reordering successive instances of ACCESS_ONCE(), - * but only when the compiler is aware of some particular ordering. One way - * to make the compiler aware of ordering is to put the two invocations of - * ACCESS_ONCE() in different C statements. - * - * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE - * on a union member will work as long as the size of the member matches the - * size of the union and the size is smaller than word size. - * - * The major use cases of ACCESS_ONCE used to be (1) Mediating communication - * between process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise - * mutilate accesses that either do not require ordering or that interact - * with an explicit memory barrier or atomic instruction that provides the - * required ordering. - * - * If possible use READ_ONCE()/WRITE_ONCE() instead. - */ -#define __ACCESS_ONCE(x) ({ \ - __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \ - (volatile typeof(x) *)&(x); }) -#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) - #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/completion.h b/include/linux/completion.h index 0662a417febe..94a59ba7d422 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -10,9 +10,6 @@ */ #include <linux/wait.h> -#ifdef CONFIG_LOCKDEP_COMPLETIONS -#include <linux/lockdep.h> -#endif /* * struct completion - structure used to maintain state for a "completion" @@ -29,58 +26,16 @@ struct completion { unsigned int done; wait_queue_head_t wait; -#ifdef CONFIG_LOCKDEP_COMPLETIONS - struct lockdep_map_cross map; -#endif }; -#ifdef CONFIG_LOCKDEP_COMPLETIONS -static inline void complete_acquire(struct completion *x) -{ - lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_); -} - -static inline void complete_release(struct completion *x) -{ - lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_); -} - -static inline void complete_release_commit(struct completion *x) -{ - lock_commit_crosslock((struct lockdep_map *)&x->map); -} - -#define init_completion_map(x, m) \ -do { \ - lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ - (m)->name, (m)->key, 0); \ - __init_completion(x); \ -} while (0) - -#define init_completion(x) \ -do { \ - static struct lock_class_key __key; \ - lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ - "(completion)" #x, \ - &__key, 0); \ - __init_completion(x); \ -} while (0) -#else #define init_completion_map(x, m) __init_completion(x) #define init_completion(x) __init_completion(x) static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} static inline void complete_release_commit(struct completion *x) {} -#endif -#ifdef CONFIG_LOCKDEP_COMPLETIONS -#define COMPLETION_INITIALIZER(work) \ - { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \ - STATIC_CROSS_LOCKDEP_MAP_INIT("(completion)" #work, &(work)) } -#else #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } -#endif #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \ (*({ init_completion_map(&(work), &(map)); &(work); })) diff --git a/include/linux/cred.h b/include/linux/cred.h index 099058e1178b..631286535d0f 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -83,6 +83,7 @@ extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); extern bool may_setgroups(void); +extern void groups_sort(struct group_info *); /* * The security context of a task diff --git a/include/linux/idr.h b/include/linux/idr.h index 7c3a365f7e12..fa14f834e4ed 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -15,6 +15,7 @@ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> +#include <linux/bug.h> struct idr { struct radix_tree_root idr_rt; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index a842551fe044..2e75dc34bff5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -158,12 +158,6 @@ struct lockdep_map { int cpu; unsigned long ip; #endif -#ifdef CONFIG_LOCKDEP_CROSSRELEASE - /* - * Whether it's a crosslock. - */ - int cross; -#endif }; static inline void lockdep_copy_map(struct lockdep_map *to, @@ -267,96 +261,9 @@ struct held_lock { unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; -#ifdef CONFIG_LOCKDEP_CROSSRELEASE - /* - * Generation id. - * - * A value of cross_gen_id will be stored when holding this, - * which is globally increased whenever each crosslock is held. - */ - unsigned int gen_id; -#endif -}; - -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -#define MAX_XHLOCK_TRACE_ENTRIES 5 - -/* - * This is for keeping locks waiting for commit so that true dependencies - * can be added at commit step. - */ -struct hist_lock { - /* - * Id for each entry in the ring buffer. This is used to - * decide whether the ring buffer was overwritten or not. - * - * For example, - * - * |<----------- hist_lock ring buffer size ------->| - * pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii - * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii....................... - * - * where 'p' represents an acquisition in process - * context, 'i' represents an acquisition in irq - * context. - * - * In this example, the ring buffer was overwritten by - * acquisitions in irq context, that should be detected on - * rollback or commit. - */ - unsigned int hist_id; - - /* - * Seperate stack_trace data. This will be used at commit step. - */ - struct stack_trace trace; - unsigned long trace_entries[MAX_XHLOCK_TRACE_ENTRIES]; - - /* - * Seperate hlock instance. This will be used at commit step. - * - * TODO: Use a smaller data structure containing only necessary - * data. However, we should make lockdep code able to handle the - * smaller one first. - */ - struct held_lock hlock; }; /* - * To initialize a lock as crosslock, lockdep_init_map_crosslock() should - * be called instead of lockdep_init_map(). - */ -struct cross_lock { - /* - * When more than one acquisition of crosslocks are overlapped, - * we have to perform commit for them based on cross_gen_id of - * the first acquisition, which allows us to add more true - * dependencies. - * - * Moreover, when no acquisition of a crosslock is in progress, - * we should not perform commit because the lock might not exist - * any more, which might cause incorrect memory access. So we - * have to track the number of acquisitions of a crosslock. - */ - int nr_acquire; - - /* - * Seperate hlock instance. This will be used at commit step. - * - * TODO: Use a smaller data structure containing only necessary - * data. However, we should make lockdep code able to handle the - * smaller one first. - */ - struct held_lock hlock; -}; - -struct lockdep_map_cross { - struct lockdep_map map; - struct cross_lock xlock; -}; -#endif - -/* * Initialization, self-test and debugging-output methods: */ extern void lockdep_info(void); @@ -560,37 +467,6 @@ enum xhlock_context_t { XHLOCK_CTX_NR, }; -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -extern void lockdep_init_map_crosslock(struct lockdep_map *lock, - const char *name, - struct lock_class_key *key, - int subclass); -extern void lock_commit_crosslock(struct lockdep_map *lock); - -/* - * What we essencially have to initialize is 'nr_acquire'. Other members - * will be initialized in add_xlock(). - */ -#define STATIC_CROSS_LOCK_INIT() \ - { .nr_acquire = 0,} - -#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \ - { .map.name = (_name), .map.key = (void *)(_key), \ - .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), } - -/* - * To initialize a lockdep_map statically use this macro. - * Note that _name must not be NULL. - */ -#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ - { .name = (_name), .key = (void *)(_key), .cross = 0, } - -extern void crossrelease_hist_start(enum xhlock_context_t c); -extern void crossrelease_hist_end(enum xhlock_context_t c); -extern void lockdep_invariant_state(bool force); -extern void lockdep_init_task(struct task_struct *task); -extern void lockdep_free_task(struct task_struct *task); -#else /* !CROSSRELEASE */ #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. @@ -604,7 +480,6 @@ static inline void crossrelease_hist_end(enum xhlock_context_t c) {} static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} -#endif /* CROSSRELEASE */ #ifdef CONFIG_LOCK_STAT diff --git a/include/linux/oom.h b/include/linux/oom.h index 01c91d874a57..5bad038ac012 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -67,6 +67,15 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) } /* + * Use this helper if tsk->mm != mm and the victim mm needs a special + * handling. This is guaranteed to stay true after once set. + */ +static inline bool mm_is_oom_victim(struct mm_struct *mm) +{ + return test_bit(MMF_OOM_VICTIM, &mm->flags); +} + +/* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in diff --git a/include/linux/pci.h b/include/linux/pci.h index 0403894147a3..c170c9250c8b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1674,6 +1674,9 @@ static inline struct pci_dev *pci_get_slot(struct pci_bus *bus, static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn) { return NULL; } +static inline struct pci_dev *pci_get_domain_bus_and_slot(int domain, + unsigned int bus, unsigned int devfn) +{ return NULL; } static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) { return NULL; } diff --git a/include/linux/pm.h b/include/linux/pm.h index 65d39115f06d..492ed473ba7e 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -765,6 +765,7 @@ extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); +extern void dev_pm_skip_next_resume_phases(struct device *dev); extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); #else /* !CONFIG_PM_SLEEP */ diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index d574361943ea..fcbeed4053ef 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -99,6 +99,8 @@ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); +extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, + struct rb_root_cached *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index cc0072e93e36..857a72ceb794 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -10,9 +10,6 @@ */ typedef struct { arch_rwlock_t raw_lock; -#ifdef CONFIG_GENERIC_LOCKBREAK - unsigned int break_lock; -#endif #ifdef CONFIG_DEBUG_SPINLOCK unsigned int magic, owner_cpu; void *owner; diff --git a/include/linux/sched.h b/include/linux/sched.h index 21991d668d35..d2588263a989 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -849,17 +849,6 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -#define MAX_XHLOCKS_NR 64UL - struct hist_lock *xhlocks; /* Crossrelease history locks */ - unsigned int xhlock_idx; - /* For restoring at history boundaries */ - unsigned int xhlock_idx_hist[XHLOCK_CTX_NR]; - unsigned int hist_id; - /* For overwrite check at each context exit */ - unsigned int hist_id_save[XHLOCK_CTX_NR]; -#endif - #ifdef CONFIG_UBSAN unsigned int in_ubsan; #endif @@ -1503,7 +1492,11 @@ static inline void set_task_comm(struct task_struct *tsk, const char *from) __set_task_comm(tsk, from, false); } -extern char *get_task_comm(char *to, struct task_struct *tsk); +extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); +#define get_task_comm(buf, tsk) ({ \ + BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \ + __get_task_comm(buf, sizeof(buf), tsk); \ +}) #ifdef CONFIG_SMP void scheduler_ipi(void); diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 9c8847395b5e..ec912d01126f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -70,6 +70,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index a39186194cd6..3bf273538840 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -107,16 +107,11 @@ do { \ #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) -#ifdef CONFIG_GENERIC_LOCKBREAK -#define raw_spin_is_contended(lock) ((lock)->break_lock) -#else - #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ -#endif /* * This barrier must provide two things: diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 73548eb13a5d..24b4e6f2c1a2 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -19,9 +19,6 @@ typedef struct raw_spinlock { arch_spinlock_t raw_lock; -#ifdef CONFIG_GENERIC_LOCKBREAK - unsigned int break_lock; -#endif #ifdef CONFIG_DEBUG_SPINLOCK unsigned int magic, owner_cpu; void *owner; diff --git a/include/linux/string.h b/include/linux/string.h index 410ecf17de3c..cfd83eb2f926 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -259,7 +259,10 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 0); - if (p_size == (size_t)-1) + + /* Work around gcc excess stack consumption issue */ + if (p_size == (size_t)-1 || + (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) return __builtin_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) diff --git a/include/linux/trace.h b/include/linux/trace.h index d24991c1fef3..b95ffb2188ab 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -18,7 +18,7 @@ */ struct trace_export { struct trace_export __rcu *next; - void (*write)(const void *, unsigned int); + void (*write)(struct trace_export *, const void *, unsigned int); }; int register_ftrace_export(struct trace_export *export); diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h index f5024c560d8f..9c4eb33c5a1d 100644 --- a/include/trace/events/preemptirq.h +++ b/include/trace/events/preemptirq.h @@ -56,15 +56,18 @@ DEFINE_EVENT(preemptirq_template, preempt_enable, #include <trace/define_trace.h> -#else /* !CONFIG_PREEMPTIRQ_EVENTS */ +#endif /* !CONFIG_PREEMPTIRQ_EVENTS */ +#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || defined(CONFIG_PROVE_LOCKING) #define trace_irq_enable(...) #define trace_irq_disable(...) -#define trace_preempt_enable(...) -#define trace_preempt_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) +#endif + +#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || !defined(CONFIG_DEBUG_PREEMPT) +#define trace_preempt_enable(...) +#define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) - #endif diff --git a/init/main.c b/init/main.c index dfec3809e740..e96e3a14533c 100644 --- a/init/main.c +++ b/init/main.c @@ -589,6 +589,12 @@ asmlinkage __visible void __init start_kernel(void) radix_tree_init(); /* + * Set up housekeeping before setting up workqueues to allow the unbound + * workqueue to take non-housekeeping into account. + */ + housekeeping_init(); + + /* * Allow workqueue creation and work item queueing/cancelling * early. Work item execution depends on kthreads and starts after * workqueue_init(). @@ -605,7 +611,6 @@ asmlinkage __visible void __init start_kernel(void) early_irq_init(); init_IRQ(); tick_init(); - housekeeping_init(); rcu_init_nohz(); init_timers(); hrtimers_init(); diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c index 5f780d8f6a9d..9caeda610249 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -50,7 +50,7 @@ static int current_css_set_read(struct seq_file *seq, void *v) spin_lock_irq(&css_set_lock); rcu_read_lock(); - cset = rcu_dereference(current->cgroups); + cset = task_css_set(current); refcnt = refcount_read(&cset->refcount); seq_printf(seq, "css_set %pK %d", cset, refcnt); if (refcnt > cset->nr_tasks) @@ -96,7 +96,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) spin_lock_irq(&css_set_lock); rcu_read_lock(); - cset = rcu_dereference(current->cgroups); + cset = task_css_set(current); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c index 133b465691d6..1e111dd455c4 100644 --- a/kernel/cgroup/stat.c +++ b/kernel/cgroup/stat.c @@ -296,8 +296,12 @@ int cgroup_stat_init(struct cgroup *cgrp) } /* ->updated_children list is self terminated */ - for_each_possible_cpu(cpu) - cgroup_cpu_stat(cgrp, cpu)->updated_children = cgrp; + for_each_possible_cpu(cpu) { + struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); + + cstat->updated_children = cgrp; + u64_stats_init(&cstat->sync); + } prev_cputime_init(&cgrp->stat.prev_cputime); diff --git a/kernel/exit.c b/kernel/exit.c index 6b4298a41167..df0c91d5606c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1755,3 +1755,11 @@ Efault: return -EFAULT; } #endif + +__weak void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} diff --git a/kernel/groups.c b/kernel/groups.c index e357bc800111..daae2f2dc6d4 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -86,11 +86,12 @@ static int gid_cmp(const void *_a, const void *_b) return gid_gt(a, b) - gid_lt(a, b); } -static void groups_sort(struct group_info *group_info) +void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } +EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) @@ -122,7 +123,6 @@ int groups_search(const struct group_info *group_info, kgid_t grp) void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); - groups_sort(group_info); get_group_info(group_info); new->group_info = group_info; } @@ -206,6 +206,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) return retval; } + groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); diff --git a/kernel/kcov.c b/kernel/kcov.c index 15f33faf4013..7594c033d98a 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -157,7 +157,7 @@ void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2) } EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2); -void notrace __sanitizer_cov_trace_cmp4(u16 arg1, u16 arg2) +void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2) { write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_); } @@ -183,7 +183,7 @@ void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2) } EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2); -void notrace __sanitizer_cov_trace_const_cmp4(u16 arg1, u16 arg2) +void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2) { write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2, _RET_IP_); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 670d8d7d8087..5fa1324a4f29 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -57,10 +57,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/lock.h> -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -#include <linux/slab.h> -#endif - #ifdef CONFIG_PROVE_LOCKING int prove_locking = 1; module_param(prove_locking, int, 0644); @@ -75,19 +71,6 @@ module_param(lock_stat, int, 0644); #define lock_stat 0 #endif -#ifdef CONFIG_BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK -static int crossrelease_fullstack = 1; -#else -static int crossrelease_fullstack; -#endif -static int __init allow_crossrelease_fullstack(char *str) -{ - crossrelease_fullstack = 1; - return 0; -} - -early_param("crossrelease_fullstack", allow_crossrelease_fullstack); - /* * lockdep_lock: protects the lockdep graph, the hashes and the * class/list/hash allocators. @@ -740,18 +723,6 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL); } -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -static void cross_init(struct lockdep_map *lock, int cross); -static int cross_lock(struct lockdep_map *lock); -static int lock_acquire_crosslock(struct held_lock *hlock); -static int lock_release_crosslock(struct lockdep_map *lock); -#else -static inline void cross_init(struct lockdep_map *lock, int cross) {} -static inline int cross_lock(struct lockdep_map *lock) { return 0; } -static inline int lock_acquire_crosslock(struct held_lock *hlock) { return 2; } -static inline int lock_release_crosslock(struct lockdep_map *lock) { return 2; } -#endif - /* * Register a lock's class in the hash-table, if the class is not present * yet. Otherwise we look it up. We cache the result in the lock object @@ -1151,41 +1122,22 @@ print_circular_lock_scenario(struct held_lock *src, printk(KERN_CONT "\n\n"); } - if (cross_lock(tgt->instance)) { - printk(" Possible unsafe locking scenario by crosslock:\n\n"); - printk(" CPU0 CPU1\n"); - printk(" ---- ----\n"); - printk(" lock("); - __print_lock_name(parent); - printk(KERN_CONT ");\n"); - printk(" lock("); - __print_lock_name(target); - printk(KERN_CONT ");\n"); - printk(" lock("); - __print_lock_name(source); - printk(KERN_CONT ");\n"); - printk(" unlock("); - __print_lock_name(target); - printk(KERN_CONT ");\n"); - printk("\n *** DEADLOCK ***\n\n"); - } else { - printk(" Possible unsafe locking scenario:\n\n"); - printk(" CPU0 CPU1\n"); - printk(" ---- ----\n"); - printk(" lock("); - __print_lock_name(target); - printk(KERN_CONT ");\n"); - printk(" lock("); - __print_lock_name(parent); - printk(KERN_CONT ");\n"); - printk(" lock("); - __print_lock_name(target); - printk(KERN_CONT ");\n"); - printk(" lock("); - __print_lock_name(source); - printk(KERN_CONT ");\n"); - printk("\n *** DEADLOCK ***\n\n"); - } + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0 CPU1\n"); + printk(" ---- ----\n"); + printk(" lock("); + __print_lock_name(target); + printk(KERN_CONT ");\n"); + printk(" lock("); + __print_lock_name(parent); + printk(KERN_CONT ");\n"); + printk(" lock("); + __print_lock_name(target); + printk(KERN_CONT ");\n"); + printk(" lock("); + __print_lock_name(source); + printk(KERN_CONT ");\n"); + printk("\n *** DEADLOCK ***\n\n"); } /* @@ -1211,10 +1163,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth, curr->comm, task_pid_nr(curr)); print_lock(check_src); - if (cross_lock(check_tgt->instance)) - pr_warn("\nbut now in release context of a crosslock acquired at the following:\n"); - else - pr_warn("\nbut task is already holding lock:\n"); + pr_warn("\nbut task is already holding lock:\n"); print_lock(check_tgt); pr_warn("\nwhich lock already depends on the new lock.\n\n"); @@ -1244,9 +1193,7 @@ static noinline int print_circular_bug(struct lock_list *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - if (cross_lock(check_tgt->instance)) - this->trace = *trace; - else if (!save_trace(&this->trace)) + if (!save_trace(&this->trace)) return 0; depth = get_lock_depth(target); @@ -1850,9 +1797,6 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, if (nest) return 2; - if (cross_lock(prev->instance)) - continue; - return print_deadlock_bug(curr, prev, next); } return 1; @@ -2018,31 +1962,26 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) for (;;) { int distance = curr->lockdep_depth - depth + 1; hlock = curr->held_locks + depth - 1; + /* - * Only non-crosslock entries get new dependencies added. - * Crosslock entries will be added by commit later: + * Only non-recursive-read entries get new dependencies + * added: */ - if (!cross_lock(hlock->instance)) { + if (hlock->read != 2 && hlock->check) { + int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace); + if (!ret) + return 0; + /* - * Only non-recursive-read entries get new dependencies - * added: + * Stop after the first non-trylock entry, + * as non-trylock entries have added their + * own direct dependencies already, so this + * lock is connected to them indirectly: */ - if (hlock->read != 2 && hlock->check) { - int ret = check_prev_add(curr, hlock, next, - distance, &trace, save_trace); - if (!ret) - return 0; - - /* - * Stop after the first non-trylock entry, - * as non-trylock entries have added their - * own direct dependencies already, so this - * lock is connected to them indirectly: - */ - if (!hlock->trylock) - break; - } + if (!hlock->trylock) + break; } + depth--; /* * End of lock-stack? @@ -3292,21 +3231,10 @@ static void __lockdep_init_map(struct lockdep_map *lock, const char *name, void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass) { - cross_init(lock, 0); __lockdep_init_map(lock, name, key, subclass); } EXPORT_SYMBOL_GPL(lockdep_init_map); -#ifdef CONFIG_LOCKDEP_CROSSRELEASE -void lockdep_init_map_crosslock(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass) -{ - cross_init(lock, 1); - __lockdep_init_map(lock, name, key, subclass); -} -EXPORT_SYMBOL_GPL(lockdep_init_map_crosslock); -#endif - struct lock_class_key __lockdep_no_validate__; EXPORT_SYMBOL_GPL(__lockdep_no_validate__); @@ -3362,7 +3290,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int chain_head = 0; int class_idx; u64 chain_key; - int ret; if (unlikely(!debug_locks)) return 0; @@ -3411,8 +3338,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, class_idx = class - lock_classes + 1; - /* TODO: nest_lock is not implemented for crosslock yet. */ - if (depth && !cross_lock(lock)) { + if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { if (hlock->references) { @@ -3500,14 +3426,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) return 0; - ret = lock_acquire_crosslock(hlock); - /* - * 2 means normal acquire operations are needed. Otherwise, it's - * ok just to return with '0:fail, 1:success'. - */ - if (ret != 2) - return ret; - curr->curr_chain_key = chain_key; curr->lockdep_depth++; check_chain_key(curr); @@ -3745,19 +3663,11 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip) struct task_struct *curr = current; struct held_lock *hlock; unsigned int depth; - int ret, i; + int i; if (unlikely(!debug_locks)) return 0; - ret = lock_release_crosslock(lock); - /* - * 2 means normal release operations are needed. Otherwise, it's - * ok just to return with '0:fail, 1:success'. - */ - if (ret != 2) - return ret; - depth = curr->lockdep_depth; /* * So we're all set to release this lock.. wait what lock? We don't @@ -4675,495 +4585,3 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) dump_stack(); } EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); - -#ifdef CONFIG_LOCKDEP_CROSSRELEASE - -/* - * Crossrelease works by recording a lock history for each thread and - * connecting those historic locks that were taken after the - * wait_for_completion() in the complete() context. - * - * Task-A Task-B - * - * mutex_lock(&A); - * mutex_unlock(&A); - * - * wait_for_completion(&C); - * lock_acquire_crosslock(); - * atomic_inc_return(&cross_gen_id); - * | - * | mutex_lock(&B); - * | mutex_unlock(&B); - * | - * | complete(&C); - * `-- lock_commit_crosslock(); - * - * Which will then add a dependency between B and C. - */ - -#define xhlock(i) (current->xhlocks[(i) % MAX_XHLOCKS_NR]) - -/* - * Whenever a crosslock is held, cross_gen_id will be increased. - */ -static atomic_t cross_gen_id; /* Can be wrapped */ - -/* - * Make an entry of the ring buffer invalid. - */ -static inline void invalidate_xhlock(struct hist_lock *xhlock) -{ - /* - * Normally, xhlock->hlock.instance must be !NULL. - */ - xhlock->hlock.instance = NULL; -} - -/* - * Lock history stacks; we have 2 nested lock history stacks: - * - * HARD(IRQ) - * SOFT(IRQ) - * - * The thing is that once we complete a HARD/SOFT IRQ the future task locks - * should not depend on any of the locks observed while running the IRQ. So - * what we do is rewind the history buffer and erase all our knowledge of that - * temporal event. - */ - -void crossrelease_hist_start(enum xhlock_context_t c) -{ - struct task_struct *cur = current; - - if (!cur->xhlocks) - return; - - cur->xhlock_idx_hist[c] = cur->xhlock_idx; - cur->hist_id_save[c] = cur->hist_id; -} - -void crossrelease_hist_end(enum xhlock_context_t c) -{ - struct task_struct *cur = current; - - if (cur->xhlocks) { - unsigned int idx = cur->xhlock_idx_hist[c]; - struct hist_lock *h = &xhlock(idx); - - cur->xhlock_idx = idx; - - /* Check if the ring was overwritten. */ - if (h->hist_id != cur->hist_id_save[c]) - invalidate_xhlock(h); - } -} - -/* - * lockdep_invariant_state() is used to annotate independence inside a task, to - * make one task look like multiple independent 'tasks'. - * - * Take for instance workqueues; each work is independent of the last. The - * completion of a future work does not depend on the completion of a past work - * (in general). Therefore we must not carry that (lock) dependency across - * works. - * - * This is true for many things; pretty much all kthreads fall into this - * pattern, where they have an invariant state and future completions do not - * depend on past completions. Its just that since they all have the 'same' - * form -- the kthread does the same over and over -- it doesn't typically - * matter. - * - * The same is true for system-calls, once a system call is completed (we've - * returned to userspace) the next system call does not depend on the lock - * history of the previous system call. - * - * They key property for independence, this invariant state, is that it must be - * a point where we hold no locks and have no history. Because if we were to - * hold locks, the restore at _end() would not necessarily recover it's history - * entry. Similarly, independence per-definition means it does not depend on - * prior state. - */ -void lockdep_invariant_state(bool force) -{ - /* - * We call this at an invariant point, no current state, no history. - * Verify the former, enforce the latter. - */ - WARN_ON_ONCE(!force && current->lockdep_depth); - if (current->xhlocks) - invalidate_xhlock(&xhlock(current->xhlock_idx)); -} - -static int cross_lock(struct lockdep_map *lock) -{ - return lock ? lock->cross : 0; -} - -/* - * This is needed to decide the relationship between wrapable variables. - */ -static inline int before(unsigned int a, unsigned int b) -{ - return (int)(a - b) < 0; -} - -static inline struct lock_class *xhlock_class(struct hist_lock *xhlock) -{ - return hlock_class(&xhlock->hlock); -} - -static inline struct lock_class *xlock_class(struct cross_lock *xlock) -{ - return hlock_class(&xlock->hlock); -} - -/* - * Should we check a dependency with previous one? - */ -static inline int depend_before(struct held_lock *hlock) -{ - return hlock->read != 2 && hlock->check && !hlock->trylock; -} - -/* - * Should we check a dependency with next one? - */ -static inline int depend_after(struct held_lock *hlock) -{ - return hlock->read != 2 && hlock->check; -} - -/* - * Check if the xhlock is valid, which would be false if, - * - * 1. Has not used after initializaion yet. - * 2. Got invalidated. - * - * Remind hist_lock is implemented as a ring buffer. - */ -static inline int xhlock_valid(struct hist_lock *xhlock) -{ - /* - * xhlock->hlock.instance must be !NULL. - */ - return !!xhlock->hlock.instance; -} - -/* - * Record a hist_lock entry. - * - * Irq disable is only required. - */ -static void add_xhlock(struct held_lock *hlock) -{ - unsigned int idx = ++current->xhlock_idx; - struct hist_lock *xhlock = &xhlock(idx); - -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * This can be done locklessly because they are all task-local - * state, we must however ensure IRQs are disabled. - */ - WARN_ON_ONCE(!irqs_disabled()); -#endif - - /* Initialize hist_lock's members */ - xhlock->hlock = *hlock; - xhlock->hist_id = ++current->hist_id; - - xhlock->trace.nr_entries = 0; - xhlock->trace.max_entries = MAX_XHLOCK_TRACE_ENTRIES; - xhlock->trace.entries = xhlock->trace_entries; - - if (crossrelease_fullstack) { - xhlock->trace.skip = 3; - save_stack_trace(&xhlock->trace); - } else { - xhlock->trace.nr_entries = 1; - xhlock->trace.entries[0] = hlock->acquire_ip; - } -} - -static inline int same_context_xhlock(struct hist_lock *xhlock) -{ - return xhlock->hlock.irq_context == task_irq_context(current); -} - -/* - * This should be lockless as far as possible because this would be - * called very frequently. - */ -static void check_add_xhlock(struct held_lock *hlock) -{ - /* - * Record a hist_lock, only in case that acquisitions ahead - * could depend on the held_lock. For example, if the held_lock - * is trylock then acquisitions ahead never depends on that. - * In that case, we don't need to record it. Just return. - */ - if (!current->xhlocks || !depend_before(hlock)) - return; - - add_xhlock(hlock); -} - -/* - * For crosslock. - */ -static int add_xlock(struct held_lock *hlock) -{ - struct cross_lock *xlock; - unsigned int gen_id; - - if (!graph_lock()) - return 0; - - xlock = &((struct lockdep_map_cross *)hlock->instance)->xlock; - - /* - * When acquisitions for a crosslock are overlapped, we use - * nr_acquire to perform commit for them, based on cross_gen_id - * of the first acquisition, which allows to add additional - * dependencies. - * - * Moreover, when no acquisition of a crosslock is in progress, - * we should not perform commit because the lock might not exist - * any more, which might cause incorrect memory access. So we - * have to track the number of acquisitions of a crosslock. - * - * depend_after() is necessary to initialize only the first - * valid xlock so that the xlock can be used on its commit. - */ - if (xlock->nr_acquire++ && depend_after(&xlock->hlock)) - goto unlock; - - gen_id = (unsigned int)atomic_inc_return(&cross_gen_id); - xlock->hlock = *hlock; - xlock->hlock.gen_id = gen_id; -unlock: - graph_unlock(); - return 1; -} - -/* - * Called for both normal and crosslock acquires. Normal locks will be - * pushed on the hist_lock queue. Cross locks will record state and - * stop regular lock_acquire() to avoid being placed on the held_lock - * stack. - * - * Return: 0 - failure; - * 1 - crosslock, done; - * 2 - normal lock, continue to held_lock[] ops. - */ -static int lock_acquire_crosslock(struct held_lock *hlock) -{ - /* - * CONTEXT 1 CONTEXT 2 - * --------- --------- - * lock A (cross) - * X = atomic_inc_return(&cross_gen_id) - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * Y = atomic_read_acquire(&cross_gen_id) - * lock B - * - * atomic_read_acquire() is for ordering between A and B, - * IOW, A happens before B, when CONTEXT 2 see Y >= X. - * - * Pairs with atomic_inc_return() in add_xlock(). - */ - hlock->gen_id = (unsigned int)atomic_read_acquire(&cross_gen_id); - - if (cross_lock(hlock->instance)) - return add_xlock(hlock); - - check_add_xhlock(hlock); - return 2; -} - -static int copy_trace(struct stack_trace *trace) -{ - unsigned long *buf = stack_trace + nr_stack_trace_entries; - unsigned int max_nr = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - unsigned int nr = min(max_nr, trace->nr_entries); - - trace->nr_entries = nr; - memcpy(buf, trace->entries, nr * sizeof(trace->entries[0])); - trace->entries = buf; - nr_stack_trace_entries += nr; - - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { - if (!debug_locks_off_graph_unlock()) - return 0; - - print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!"); - dump_stack(); - - return 0; - } - - return 1; -} - -static int commit_xhlock(struct cross_lock *xlock, struct hist_lock *xhlock) -{ - unsigned int xid, pid; - u64 chain_key; - - xid = xlock_class(xlock) - lock_classes; - chain_key = iterate_chain_key((u64)0, xid); - pid = xhlock_class(xhlock) - lock_classes; - chain_key = iterate_chain_key(chain_key, pid); - - if (lookup_chain_cache(chain_key)) - return 1; - - if (!add_chain_cache_classes(xid, pid, xhlock->hlock.irq_context, - chain_key)) - return 0; - - if (!check_prev_add(current, &xlock->hlock, &xhlock->hlock, 1, - &xhlock->trace, copy_trace)) - return 0; - - return 1; -} - -static void commit_xhlocks(struct cross_lock *xlock) -{ - unsigned int cur = current->xhlock_idx; - unsigned int prev_hist_id = xhlock(cur).hist_id; - unsigned int i; - - if (!graph_lock()) - return; - - if (xlock->nr_acquire) { - for (i = 0; i < MAX_XHLOCKS_NR; i++) { - struct hist_lock *xhlock = &xhlock(cur - i); - - if (!xhlock_valid(xhlock)) - break; - - if (before(xhlock->hlock.gen_id, xlock->hlock.gen_id)) - break; - - if (!same_context_xhlock(xhlock)) - break; - - /* - * Filter out the cases where the ring buffer was - * overwritten and the current entry has a bigger - * hist_id than the previous one, which is impossible - * otherwise: - */ - if (unlikely(before(prev_hist_id, xhlock->hist_id))) - break; - - prev_hist_id = xhlock->hist_id; - - /* - * commit_xhlock() returns 0 with graph_lock already - * released if fail. - */ - if (!commit_xhlock(xlock, xhlock)) - return; - } - } - - graph_unlock(); -} - -void lock_commit_crosslock(struct lockdep_map *lock) -{ - struct cross_lock *xlock; - unsigned long flags; - - if (unlikely(!debug_locks || current->lockdep_recursion)) - return; - - if (!current->xhlocks) - return; - - /* - * Do commit hist_locks with the cross_lock, only in case that - * the cross_lock could depend on acquisitions after that. - * - * For example, if the cross_lock does not have the 'check' flag - * then we don't need to check dependencies and commit for that. - * Just skip it. In that case, of course, the cross_lock does - * not depend on acquisitions ahead, either. - * - * WARNING: Don't do that in add_xlock() in advance. When an - * acquisition context is different from the commit context, - * invalid(skipped) cross_lock might be accessed. - */ - if (!depend_after(&((struct lockdep_map_cross *)lock)->xlock.hlock)) - return; - - raw_local_irq_save(flags); - check_flags(flags); - current->lockdep_recursion = 1; - xlock = &((struct lockdep_map_cross *)lock)->xlock; - commit_xhlocks(xlock); - current->lockdep_recursion = 0; - raw_local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(lock_commit_crosslock); - -/* - * Return: 0 - failure; - * 1 - crosslock, done; - * 2 - normal lock, continue to held_lock[] ops. - */ -static int lock_release_crosslock(struct lockdep_map *lock) -{ - if (cross_lock(lock)) { - if (!graph_lock()) - return 0; - ((struct lockdep_map_cross *)lock)->xlock.nr_acquire--; - graph_unlock(); - return 1; - } - return 2; -} - -static void cross_init(struct lockdep_map *lock, int cross) -{ - if (cross) - ((struct lockdep_map_cross *)lock)->xlock.nr_acquire = 0; - - lock->cross = cross; - - /* - * Crossrelease assumes that the ring buffer size of xhlocks - * is aligned with power of 2. So force it on build. - */ - BUILD_BUG_ON(MAX_XHLOCKS_NR & (MAX_XHLOCKS_NR - 1)); -} - -void lockdep_init_task(struct task_struct *task) -{ - int i; - - task->xhlock_idx = UINT_MAX; - task->hist_id = 0; - - for (i = 0; i < XHLOCK_CTX_NR; i++) { - task->xhlock_idx_hist[i] = UINT_MAX; - task->hist_id_save[i] = 0; - } - - task->xhlocks = kzalloc(sizeof(struct hist_lock) * MAX_XHLOCKS_NR, - GFP_KERNEL); -} - -void lockdep_free_task(struct task_struct *task) -{ - if (task->xhlocks) { - void *tmp = task->xhlocks; - /* Diable crossrelease for current */ - task->xhlocks = NULL; - kfree(tmp); - } -} -#endif diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 1fd1a7543cdd..936f3d14dd6b 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -66,12 +66,8 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock) \ break; \ preempt_enable(); \ \ - if (!(lock)->break_lock) \ - (lock)->break_lock = 1; \ - while ((lock)->break_lock) \ - arch_##op##_relax(&lock->raw_lock); \ + arch_##op##_relax(&lock->raw_lock); \ } \ - (lock)->break_lock = 0; \ } \ \ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \ @@ -86,12 +82,9 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \ local_irq_restore(flags); \ preempt_enable(); \ \ - if (!(lock)->break_lock) \ - (lock)->break_lock = 1; \ - while ((lock)->break_lock) \ - arch_##op##_relax(&lock->raw_lock); \ + arch_##op##_relax(&lock->raw_lock); \ } \ - (lock)->break_lock = 0; \ + \ return flags; \ } \ \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 75554f366fd3..644fa2e3d993 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5097,17 +5097,6 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) return ret; } -/** - * sys_sched_rr_get_interval - return the default timeslice of a process. - * @pid: pid of the process. - * @interval: userspace pointer to the timeslice value. - * - * this syscall writes the default timeslice value of a given process - * into the user-space timespec buffer. A value of '0' means infinity. - * - * Return: On success, 0 and the timeslice is in @interval. Otherwise, - * an error code. - */ static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) { struct task_struct *p; @@ -5144,6 +5133,17 @@ out_unlock: return retval; } +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, struct timespec __user *, interval) { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 4056c19ca3f0..665ace2fc558 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2034,8 +2034,9 @@ static void pull_rt_task(struct rq *this_rq) bool resched = false; struct task_struct *p; struct rq *src_rq; + int rt_overload_count = rt_overloaded(this_rq); - if (likely(!rt_overloaded(this_rq))) + if (likely(!rt_overload_count)) return; /* @@ -2044,6 +2045,11 @@ static void pull_rt_task(struct rq *this_rq) */ smp_rmb(); + /* If we are the only overloaded CPU do nothing */ + if (rt_overload_count == 1 && + cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask)) + return; + #ifdef HAVE_RT_PUSH_IPI if (sched_feat(RT_PUSH_IPI)) { tell_cpu_to_push(this_rq); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index af7dad126c13..904c952ac383 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -164,6 +164,7 @@ config PREEMPTIRQ_EVENTS bool "Enable trace events for preempt and irq disable/enable" select TRACE_IRQFLAGS depends on DEBUG_PREEMPT || !PROVE_LOCKING + depends on TRACING default n help Enable tracing of disable and enable events for preemption and irqs. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 91874a95060d..c87766c1c204 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1799,12 +1799,6 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val) } EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite); -static __always_inline void * -__rb_data_page_index(struct buffer_data_page *bpage, unsigned index) -{ - return bpage->data + index; -} - static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index) { return bpage->page->data + index; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 73e67b68c53b..59518b8126d0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -362,7 +362,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct } /** - * trace_pid_filter_add_remove - Add or remove a task from a pid_list + * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove @@ -925,7 +925,7 @@ static void tracing_snapshot_instance(struct trace_array *tr) } /** - * trace_snapshot - take a snapshot of the current buffer. + * tracing_snapshot - take a snapshot of the current buffer. * * This causes a swap between the snapshot buffer and the current live * tracing buffer. You can use this to take snapshots of the live @@ -1004,9 +1004,9 @@ int tracing_alloc_snapshot(void) EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); /** - * trace_snapshot_alloc - allocate and take a snapshot of the current buffer. + * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer. * - * This is similar to trace_snapshot(), but it will allocate the + * This is similar to tracing_snapshot(), but it will allocate the * snapshot buffer if it isn't already allocated. Use this only * where it is safe to sleep, as the allocation may sleep. * @@ -1303,7 +1303,7 @@ unsigned long __read_mostly tracing_thresh; /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, - * for later retrieval via /sys/kernel/debug/tracing/latency_trace) + * for later retrieval via /sys/kernel/tracing/tracing_max_latency) */ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) @@ -2415,7 +2415,7 @@ trace_process_export(struct trace_export *export, entry = ring_buffer_event_data(event); size = ring_buffer_event_length(event); - export->write(entry, size); + export->write(export, entry, size); } static DEFINE_MUTEX(ftrace_export_lock); @@ -4178,37 +4178,30 @@ static const struct file_operations show_traces_fops = { .llseek = seq_lseek, }; -/* - * The tracer itself will not take this lock, but still we want - * to provide a consistent cpumask to user-space: - */ -static DEFINE_MUTEX(tracing_cpumask_update_lock); - -/* - * Temporary storage for the character representation of the - * CPU bitmask (and one more byte for the newline): - */ -static char mask_str[NR_CPUS + 1]; - static ssize_t tracing_cpumask_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; + char *mask_str; int len; - mutex_lock(&tracing_cpumask_update_lock); + len = snprintf(NULL, 0, "%*pb\n", + cpumask_pr_args(tr->tracing_cpumask)) + 1; + mask_str = kmalloc(len, GFP_KERNEL); + if (!mask_str) + return -ENOMEM; - len = snprintf(mask_str, count, "%*pb\n", + len = snprintf(mask_str, len, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)); if (len >= count) { count = -EINVAL; goto out_err; } - count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); + count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len); out_err: - mutex_unlock(&tracing_cpumask_update_lock); + kfree(mask_str); return count; } @@ -4228,8 +4221,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, if (err) goto err_unlock; - mutex_lock(&tracing_cpumask_update_lock); - local_irq_disable(); arch_spin_lock(&tr->max_lock); for_each_tracing_cpu(cpu) { @@ -4252,8 +4243,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, local_irq_enable(); cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); - - mutex_unlock(&tracing_cpumask_update_lock); free_cpumask_var(tracing_cpumask_new); return count; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 734accc02418..3c7bfc4bf5e9 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -209,6 +209,10 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, if (__this_cpu_read(disable_stack_tracer) != 1) goto out; + /* If rcu is not watching, then save stack trace can fail */ + if (!rcu_is_watching()) + goto out; + ip += MCOUNT_INSN_SIZE; check_stack(ip, &stack); diff --git a/kernel/uid16.c b/kernel/uid16.c index ce74a4901d2b..ef1da2a5f9bd 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -192,6 +192,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) return retval; } + groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8fdb710bfdd7..43d18cb46308 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -38,7 +38,6 @@ #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> -#include <linux/kallsyms.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> @@ -48,6 +47,7 @@ #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> +#include <linux/sched/isolation.h> #include "workqueue_internal.h" @@ -1634,7 +1634,7 @@ static void worker_enter_idle(struct worker *worker) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* - * Sanity check nr_running. Because wq_unbind_fn() releases + * Sanity check nr_running. Because unbind_workers() releases * pool->lock between setting %WORKER_UNBOUND and zapping * nr_running, the warning may trigger spuriously. Check iff * unbind is not in progress. @@ -4510,9 +4510,8 @@ void show_workqueue_state(void) * cpu comes back online. */ -static void wq_unbind_fn(struct work_struct *work) +static void unbind_workers(int cpu) { - int cpu = smp_processor_id(); struct worker_pool *pool; struct worker *worker; @@ -4589,16 +4588,6 @@ static void rebind_workers(struct worker_pool *pool) spin_lock_irq(&pool->lock); - /* - * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED - * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is - * being reworked and this can go away in time. - */ - if (!(pool->flags & POOL_DISASSOCIATED)) { - spin_unlock_irq(&pool->lock); - return; - } - pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { @@ -4709,12 +4698,13 @@ int workqueue_online_cpu(unsigned int cpu) int workqueue_offline_cpu(unsigned int cpu) { - struct work_struct unbind_work; struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ - INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); - queue_work_on(cpu, system_highpri_wq, &unbind_work); + if (WARN_ON(cpu != smp_processor_id())) + return -1; + + unbind_workers(cpu); /* update NUMA affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); @@ -4722,9 +4712,6 @@ int workqueue_offline_cpu(unsigned int cpu) wq_update_unbound_numa(wq, cpu, false); mutex_unlock(&wq_pool_mutex); - /* wait for per-cpu unbinding to finish */ - flush_work(&unbind_work); - destroy_work_on_stack(&unbind_work); return 0; } @@ -4957,6 +4944,10 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) return -ENOMEM; + /* + * Not excluding isolated cpus on purpose. + * If the user wishes to include them, we allow that. + */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { apply_wqattrs_lock(); @@ -5555,7 +5546,7 @@ int __init workqueue_init_early(void) WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); - cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); + cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 947d3e2ed5c2..9d5b78aad4c5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1099,8 +1099,6 @@ config PROVE_LOCKING select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC - select LOCKDEP_CROSSRELEASE - select LOCKDEP_COMPLETIONS select TRACE_IRQFLAGS default n help @@ -1170,37 +1168,6 @@ config LOCK_STAT CONFIG_LOCK_STAT defines "contended" and "acquired" lock events. (CONFIG_LOCKDEP defines "acquire" and "release" events.) -config LOCKDEP_CROSSRELEASE - bool - help - This makes lockdep work for crosslock which is a lock allowed to - be released in a different context from the acquisition context. - Normally a lock must be released in the context acquiring the lock. - However, relexing this constraint helps synchronization primitives - such as page locks or completions can use the lock correctness - detector, lockdep. - -config LOCKDEP_COMPLETIONS - bool - help - A deadlock caused by wait_for_completion() and complete() can be - detected by lockdep using crossrelease feature. - -config BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK - bool "Enable the boot parameter, crossrelease_fullstack" - depends on LOCKDEP_CROSSRELEASE - default n - help - The lockdep "cross-release" feature needs to record stack traces - (of calling functions) for all acquisitions, for eventual later - use during analysis. By default only a single caller is recorded, - because the unwind operation can be very expensive with deeper - stack chains. - - However a boot parameter, crossrelease_fullstack, was - introduced since sometimes deeper traces are required for full - analysis. This option turns on the boot parameter. - config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP diff --git a/lib/rbtree.c b/lib/rbtree.c index ba4a9d165f1b..d3ff682fd4b8 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -603,6 +603,16 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new, } EXPORT_SYMBOL(rb_replace_node); +void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, + struct rb_root_cached *root) +{ + rb_replace_node(victim, new, &root->rb_root); + + if (root->rb_leftmost == victim) + root->rb_leftmost = new; +} +EXPORT_SYMBOL(rb_replace_node_cached); + void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root) { diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c index d04ac1ec0559..1826f191e72c 100644 --- a/mm/early_ioremap.c +++ b/mm/early_ioremap.c @@ -111,7 +111,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) enum fixed_addresses idx; int i, slot; - WARN_ON(system_state != SYSTEM_BOOTING); + WARN_ON(system_state >= SYSTEM_RUNNING); slot = -1; for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { diff --git a/mm/frame_vector.c b/mm/frame_vector.c index 297c7238f7d4..c64dca6e27c2 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -62,8 +62,10 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, * get_user_pages_longterm() and disallow it for filesystem-dax * mappings. */ - if (vma_is_fsdax(vma)) - return -EOPNOTSUPP; + if (vma_is_fsdax(vma)) { + ret = -EOPNOTSUPP; + goto out; + } if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { vec->got_ref = true; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 3d4781756d50..d73c14294f3a 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1523,7 +1523,7 @@ static void kmemleak_scan(void) if (page_count(page) == 0) continue; scan_block(page, page + 1, NULL); - if (!(pfn % (MAX_SCAN_SIZE / sizeof(*page)))) + if (!(pfn & 63)) cond_resched(); } } diff --git a/mm/memory.c b/mm/memory.c index 5eb3d2524bdc..cfaba6287702 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3831,7 +3831,8 @@ static inline int create_huge_pmd(struct vm_fault *vmf) return VM_FAULT_FALLBACK; } -static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +/* `inline' is required to avoid gcc 4.1.2 build error */ +static inline int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_wp_page(vmf, orig_pmd); diff --git a/mm/mmap.c b/mm/mmap.c index a4d546821214..9efdc021ad22 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3019,20 +3019,20 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - set_bit(MMF_OOM_SKIP, &mm->flags); - if (unlikely(tsk_is_oom_victim(current))) { + if (unlikely(mm_is_oom_victim(mm))) { /* * Wait for oom_reap_task() to stop working on this * mm. Because MMF_OOM_SKIP is already set before * calling down_read(), oom_reap_task() will not run * on this "mm" post up_write(). * - * tsk_is_oom_victim() cannot be set from under us - * either because current->mm is already set to NULL + * mm_is_oom_victim() cannot be set from under us + * either because victim->mm is already set to NULL * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if current->mm + * set not NULL by the OOM killer only if victim->mm * is found not NULL while holding the task_lock. */ + set_bit(MMF_OOM_SKIP, &mm->flags); down_write(&mm->mmap_sem); up_write(&mm->mmap_sem); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c957be32b27a..29f855551efe 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -683,8 +683,10 @@ static void mark_oom_victim(struct task_struct *tsk) return; /* oom_mm is bound to the signal struct life time. */ - if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) + if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) { mmgrab(tsk->signal->oom_mm); + set_bit(MMF_OOM_VICTIM, &mm->flags); + } /* * Make sure that the task is woken up from uninterruptible sleep diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 73f5d4556b3d..7e5e775e97f4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2684,6 +2684,7 @@ void free_unref_page_list(struct list_head *list) { struct page *page, *next; unsigned long flags, pfn; + int batch_count = 0; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { @@ -2700,6 +2701,16 @@ void free_unref_page_list(struct list_head *list) set_page_private(page, 0); trace_mm_page_free_batched(page); free_unref_page_commit(page, pfn); + + /* + * Guard against excessive IRQ disabled times when we get + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { + local_irq_restore(flags); + batch_count = 0; + local_irq_save(flags); + } } local_irq_restore(flags); } diff --git a/mm/percpu.c b/mm/percpu.c index 79e3549cab0f..50e7fdf84055 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2719,7 +2719,11 @@ void __init setup_per_cpu_areas(void) if (pcpu_setup_first_chunk(ai, fc) < 0) panic("Failed to initialize percpu areas."); +#ifdef CONFIG_CRIS +#warning "the CRIS architecture has physical and virtual addresses confused" +#else pcpu_free_alloc_info(ai); +#endif } #endif /* CONFIG_SMP */ diff --git a/mm/slab.c b/mm/slab.c index 183e996dde5f..4e51ef954026 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1584,11 +1584,8 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) *dbg_redzone2(cachep, objp)); } - if (cachep->flags & SLAB_STORE_USER) { - pr_err("Last user: [<%p>](%pSR)\n", - *dbg_userword(cachep, objp), - *dbg_userword(cachep, objp)); - } + if (cachep->flags & SLAB_STORE_USER) + pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp)); realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; for (i = 0; i < size && lines; i += 16, lines--) { @@ -1621,7 +1618,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) /* Mismatch ! */ /* Print header */ if (lines == 0) { - pr_err("Slab corruption (%s): %s start=%p, len=%d\n", + pr_err("Slab corruption (%s): %s start=%px, len=%d\n", print_tainted(), cachep->name, realobj, size); print_objinfo(cachep, objp, 0); @@ -1650,13 +1647,13 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) if (objnr) { objp = index_to_obj(cachep, page, objnr - 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Prev obj: start=%p, len=%d\n", realobj, size); + pr_err("Prev obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } if (objnr + 1 < cachep->num) { objp = index_to_obj(cachep, page, objnr + 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Next obj: start=%p, len=%d\n", realobj, size); + pr_err("Next obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } } @@ -2608,7 +2605,7 @@ static void slab_put_obj(struct kmem_cache *cachep, /* Verify double free bug */ for (i = page->active; i < cachep->num; i++) { if (get_free_obj(page, i) == objnr) { - pr_err("slab: double free detected in cache '%s', objp %p\n", + pr_err("slab: double free detected in cache '%s', objp %px\n", cachep->name, objp); BUG(); } @@ -2772,7 +2769,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) else slab_error(cache, "memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", obj, redzone1, redzone2); } @@ -3078,7 +3075,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || *dbg_redzone2(cachep, objp) != RED_INACTIVE) { slab_error(cachep, "double free, or memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } @@ -3091,7 +3088,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, cachep->ctor(objp); if (ARCH_SLAB_MINALIGN && ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { - pr_err("0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", + pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", objp, (int)ARCH_SLAB_MINALIGN); } return objp; @@ -4283,7 +4280,7 @@ static void show_symbol(struct seq_file *m, unsigned long address) return; } #endif - seq_printf(m, "%p", (void *)address); + seq_printf(m, "%px", (void *)address); } static int leaks_show(struct seq_file *m, void *p) diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index c4778cae58ef..444380f968f1 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -231,6 +231,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, goto out_free_groups; creds->cr_group_info->gid[i] = kgid; } + groups_sort(creds->cr_group_info); return 0; out_free_groups: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5dd4e6c9fef2..26531193fce4 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -481,6 +481,7 @@ static int rsc_parse(struct cache_detail *cd, goto out; rsci.cred.cr_group_info->gid[i] = kgid; } + groups_sort(rsci.cred.cr_group_info); /* mech name */ len = qword_get(&mesg, buf, mlen); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 740b67d5a733..af7f28fb8102 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -520,6 +520,7 @@ static int unix_gid_parse(struct cache_detail *cd, ug.gi->gid[i] = kgid; } + groups_sort(ug.gi); ugp = unix_gid_lookup(cd, uid); if (ugp) { struct cache_head *ch; @@ -819,6 +820,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv)); cred->cr_group_info->gid[i] = kgid; } + groups_sort(cred->cr_group_info); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 040aa79e1d9d..31031f10fe56 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6233,28 +6233,6 @@ sub process { } } -# whine about ACCESS_ONCE - if ($^V && $^V ge 5.10.0 && - $line =~ /\bACCESS_ONCE\s*$balanced_parens\s*(=(?!=))?\s*($FuncArg)?/) { - my $par = $1; - my $eq = $2; - my $fun = $3; - $par =~ s/^\(\s*(.*)\s*\)$/$1/; - if (defined($eq)) { - if (WARN("PREFER_WRITE_ONCE", - "Prefer WRITE_ONCE(<FOO>, <BAR>) over ACCESS_ONCE(<FOO>) = <BAR>\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\bACCESS_ONCE\s*\(\s*\Q$par\E\s*\)\s*$eq\s*\Q$fun\E/WRITE_ONCE($par, $fun)/; - } - } else { - if (WARN("PREFER_READ_ONCE", - "Prefer READ_ONCE(<FOO>) over ACCESS_ONCE(<FOO>)\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\bACCESS_ONCE\s*\(\s*\Q$par\E\s*\)/READ_ONCE($par)/; - } - } - } - # check for mutex_trylock_recursive usage if ($line =~ /mutex_trylock_recursive/) { ERROR("LOCKING", diff --git a/scripts/faddr2line b/scripts/faddr2line index 39e07d8574dd..7721d5b2b0c0 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -44,10 +44,10 @@ set -o errexit set -o nounset -READELF="${CROSS_COMPILE}readelf" -ADDR2LINE="${CROSS_COMPILE}addr2line" -SIZE="${CROSS_COMPILE}size" -NM="${CROSS_COMPILE}nm" +READELF="${CROSS_COMPILE:-}readelf" +ADDR2LINE="${CROSS_COMPILE:-}addr2line" +SIZE="${CROSS_COMPILE:-}size" +NM="${CROSS_COMPILE:-}nm" command -v awk >/dev/null 2>&1 || die "awk isn't installed" command -v ${READELF} >/dev/null 2>&1 || die "readelf isn't installed" diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index c0b0e9e8aa66..800104c8a3ed 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -266,6 +266,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 07fd03c74a77..04e32f965ad7 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -84,8 +84,6 @@ #define uninitialized_var(x) x = *(&(x)) -#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) - #include <linux/types.h> /* @@ -135,20 +133,19 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of - * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the - * compiler is aware of some particular ordering. One way to make the - * compiler aware of ordering is to put the two invocations of READ_ONCE, - * WRITE_ONCE or ACCESS_ONCE() in different C statements. + * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some + * particular ordering. One way to make the compiler aware of ordering is to + * put the two invocations of READ_ONCE or WRITE_ONCE in different C + * statements. * - * In contrast to ACCESS_ONCE these two macros will also work on aggregate - * data types like structs or unions. If the size of the accessed data - * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a - * compile-time warning. + * These two macros will also work on aggregate data types like structs or + * unions. If the size of the accessed data type exceeds the word size of + * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will + * fall back to memcpy and print a compile-time warning. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 940c1b075659..6b0c36a58fcb 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -48,6 +48,7 @@ static inline int debug_locks_off(void) #define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define pr_warn pr_err +#define pr_cont pr_err #define list_del_rcu list_del diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 282d7613fce8..496e59a2738b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -630,9 +630,9 @@ struct kvm_s390_irq { struct kvm_s390_irq_state { __u64 buf; - __u32 flags; + __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; - __u32 reserved[4]; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ }; /* for KVM_SET_GUEST_DEBUG */ diff --git a/tools/objtool/arch/x86/lib/x86-opcode-map.txt b/tools/objtool/arch/x86/lib/x86-opcode-map.txt index 12e377184ee4..e0b85930dd77 100644 --- a/tools/objtool/arch/x86/lib/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/lib/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -896,7 +896,7 @@ EndTable GrpTable: Grp3_1 0: TEST Eb,Ib -1: +1: TEST Eb,Ib 2: NOT Eb 3: NEG Eb 4: MUL AL,Eb @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index c4d55919fac1..e0b85930dd77 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index efd78b827b05..3a5cb5a6e94a 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -70,7 +70,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md); static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; - u64 head = ACCESS_ONCE(pc->data_head); + u64 head = READ_ONCE(pc->data_head); rmb(); return head; } diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 38bb171aceba..e6e81305ef46 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -16,24 +16,41 @@ #define unlikely(x) (__builtin_expect(!!(x), 0)) #define likely(x) (__builtin_expect(!!(x), 1)) #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) +#define SIZE_MAX (~(size_t)0) + typedef pthread_spinlock_t spinlock_t; typedef int gfp_t; -static void *kmalloc(unsigned size, gfp_t gfp) -{ - return memalign(64, size); -} +#define __GFP_ZERO 0x1 -static void *kzalloc(unsigned size, gfp_t gfp) +static void *kmalloc(unsigned size, gfp_t gfp) { void *p = memalign(64, size); if (!p) return p; - memset(p, 0, size); + if (gfp & __GFP_ZERO) + memset(p, 0, size); return p; } +static inline void *kzalloc(unsigned size, gfp_t flags) +{ + return kmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) +{ + if (size != 0 && n > SIZE_MAX / size) + return NULL; + return kmalloc(n * size, flags); +} + +static inline void *kcalloc(size_t n, size_t size, gfp_t flags) +{ + return kmalloc_array(n, size, flags | __GFP_ZERO); +} + static void kfree(void *p) { if (p) diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh index 35b039864b77..0cf28aa6f21c 100644 --- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/vm/slabinfo-gnuplot.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # Sergey Senozhatsky, 2015 # sergey.senozhatsky.work@gmail.com |