diff options
420 files changed, 3366 insertions, 3449 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/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt index 376fa2f50e6b..956bb046e599 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt @@ -13,7 +13,6 @@ Required properties: at25df321a at25df641 at26df081a - en25s64 mr25h128 mr25h256 mr25h10 @@ -33,7 +32,6 @@ Required properties: s25fl008k s25fl064k sst25vf040b - sst25wf040b m25p40 m25p80 m25p16 diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt index 5bf13960f7f4..e3c48b20b1a6 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt @@ -12,24 +12,30 @@ Required properties: - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc - reg : Offset and length of the register set for the device - interrupts : Should contain CSPI/eCSPI interrupt -- cs-gpios : Specifies the gpio pins to be used for chipselects. - clocks : Clock specifiers for both ipg and per clocks. - clock-names : Clock names should include both "ipg" and "per" See the clock consumer binding, Documentation/devicetree/bindings/clock/clock-bindings.txt -- dmas: DMA specifiers for tx and rx dma. See the DMA client binding, - Documentation/devicetree/bindings/dma/dma.txt -- dma-names: DMA request names should include "tx" and "rx" if present. -Obsolete properties: -- fsl,spi-num-chipselects : Contains the number of the chipselect +Recommended properties: +- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt. While the native chip +select lines can be used, they appear to always generate a pulse between each +word of a transfer. Most use cases will require GPIO based chip selects to +generate a valid transaction. Optional properties: +- num-cs : Number of total chip selects, see spi-bus.txt. +- dmas: DMA specifiers for tx and rx dma. See the DMA client binding, +Documentation/devicetree/bindings/dma/dma.txt. +- dma-names: DMA request names, if present, should include "tx" and "rx". - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register controlling the SPI_READY handling. Note that to enable the DRCTL consideration, the SPI_READY mode-flag needs to be set too. Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst). +Obsolete properties: +- fsl,spi-num-chipselects : Contains the number of the chipselect + Example: ecspi@70010000 { 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..a6e86e20761e 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/ @@ -13117,6 +13117,7 @@ F: drivers/dma/dw/ SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER M: Jie Deng <jiedeng@synopsys.com> +M: Jose Abreu <Jose.Abreu@synopsys.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/synopsys/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts index fbb3758ca2e3..4b8edc8982cf 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts @@ -121,7 +121,7 @@ switch0port10: port@10 { reg = <10>; label = "dsa"; - phy-mode = "xgmii"; + phy-mode = "xaui"; link = <&switch1port10>; }; }; @@ -208,7 +208,7 @@ switch1port10: port@10 { reg = <10>; label = "dsa"; - phy-mode = "xgmii"; + phy-mode = "xaui"; link = <&switch0port10>; }; }; diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S index 1712f132b80d..b83fdc06286a 100644 --- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -85,7 +85,11 @@ .pushsection .text.fixup,"ax" .align 4 9001: mov r4, #-EFAULT +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + ldr r5, [sp, #9*4] @ *err_ptr +#else ldr r5, [sp, #8*4] @ *err_ptr +#endif str r4, [r5] ldmia sp, {r1, r2} @ retrieve dst, len add r2, r2, r1 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/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 9345b44b86f0..f57118e1f6b4 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -123,8 +123,8 @@ int puts(const char *s) while ((nuline = strchr(s, '\n')) != NULL) { if (nuline != s) pdc_iodc_print(s, nuline - s); - pdc_iodc_print("\r\n", 2); - s = nuline + 1; + pdc_iodc_print("\r\n", 2); + s = nuline + 1; } if (*s != '\0') pdc_iodc_print(s, strlen(s)); diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index c980a02a52bc..598c8d60fa5e 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -35,7 +35,12 @@ struct thread_info { /* thread information allocation */ +#ifdef CONFIG_IRQSTACKS +#define THREAD_SIZE_ORDER 2 /* PA-RISC requires at least 16k stack */ +#else #define THREAD_SIZE_ORDER 3 /* PA-RISC requires at least 32k stack */ +#endif + /* Be sure to hunt all references to this down when you change the size of * the kernel stack */ #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index a4fd296c958e..f3cecf5117cf 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -878,9 +878,6 @@ ENTRY_CFI(syscall_exit_rfi) STREG %r19,PT_SR7(%r16) intr_return: - /* NOTE: Need to enable interrupts incase we schedule. */ - ssm PSW_SM_I, %r0 - /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -907,6 +904,11 @@ intr_check_sig: LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ + /* NOTE: We need to enable interrupts if we have to deliver + * signals. We used to do this earlier but it caused kernel + * stack overflows. */ + ssm PSW_SM_I, %r0 + copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -958,6 +960,10 @@ intr_do_resched: cmpib,COND(=) 0, %r20, intr_do_preempt nop + /* NOTE: We need to enable interrupts if we schedule. We used + * to do this earlier but it caused kernel stack overflows. */ + ssm PSW_SM_I, %r0 + #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index e3a8e5e4d5de..8d072c44f300 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc) __INITRODATA + .align 4 .export os_hpmc_size os_hpmc_size: .word .os_hpmc_end-.os_hpmc diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 5a657986ebbf..143f90e2f9f3 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include <linux/kallsyms.h> #include <linux/sort.h> -#include <linux/sched.h> #include <linux/uaccess.h> #include <asm/assembly.h> diff --git a/arch/parisc/lib/delay.c b/arch/parisc/lib/delay.c index 7eab4bb8abe6..66e506520505 100644 --- a/arch/parisc/lib/delay.c +++ b/arch/parisc/lib/delay.c @@ -16,9 +16,7 @@ #include <linux/preempt.h> #include <linux/init.h> -#include <asm/processor.h> #include <asm/delay.h> - #include <asm/special_insns.h> /* for mfctl() */ #include <asm/processor.h> /* for boot_cpu_data */ 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/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 57d7bc92e0b8..0a6b0286c32e 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1264,12 +1264,6 @@ static inline pud_t pud_mkwrite(pud_t pud) return pud; } -#define pud_write pud_write -static inline int pud_write(pud_t pud) -{ - return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0; -} - static inline pud_t pud_mkclean(pud_t pud) { if (pud_large(pud)) { 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/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index be3136f142a9..a8103a84b4ac 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->pc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 815c03d7a765..41363f46797b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->tpc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 33c0f8bb0f33..5335ba3c850e 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -75,7 +75,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, if (!(pmd_val(pmd) & _PAGE_VALID)) return 0; - if (!pmd_access_permitted(pmd, write)) + if (write && !pmd_write(pmd)) return 0; refs = 0; @@ -114,7 +114,7 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, if (!(pud_val(pud) & _PAGE_VALID)) return 0; - if (!pud_access_permitted(pud, write)) + if (write && !pud_write(pud)) return 0; refs = 0; diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 50a32c33d729..73c57f614c9e 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,4 +1,5 @@ generic-y += barrier.h +generic-y += bpf_perf_event.h generic-y += bug.h generic-y += clkdev.h generic-y += current.h diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 4e6fcb32620f..428644175956 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs) if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi), (void *)UPT_IP(regs), (void *)UPT_SP(regs), 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/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4838037f97f6..bd8b57a5c874 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -941,7 +941,8 @@ ENTRY(debug) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Ldebug_from_sysenter_stack @@ -984,7 +985,8 @@ ENTRY(nmi) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Lnmi_from_sysenter_stack diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f81d50d7ceac..423885bee398 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -140,6 +140,64 @@ END(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ + .pushsection .entry_trampoline, "ax" + +/* + * The code in here gets remapped into cpu_entry_area's trampoline. This means + * that the assembler and linker have the wrong idea as to where this code + * lives (and, in fact, it's mapped more than once, so it's not even at a + * fixed address). So we can't reference any symbols outside the entry + * trampoline and expect it to work. + * + * Instead, we carefully abuse %rip-relative addressing. + * _entry_trampoline(%rip) refers to the start of the remapped) entry + * trampoline. We can thus find cpu_entry_area with this macro: + */ + +#define CPU_ENTRY_AREA \ + _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) + +/* The top word of the SYSENTER stack is hot and is usable as scratch space. */ +#define RSP_SCRATCH CPU_ENTRY_AREA_SYSENTER_stack + \ + SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA + +ENTRY(entry_SYSCALL_64_trampoline) + UNWIND_HINT_EMPTY + swapgs + + /* Stash the user RSP. */ + movq %rsp, RSP_SCRATCH + + /* Load the top of the task stack into RSP */ + movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp + + /* Start building the simulated IRET frame. */ + pushq $__USER_DS /* pt_regs->ss */ + pushq RSP_SCRATCH /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + + /* + * x86 lacks a near absolute jump, and we can't jump to the real + * entry text with a relative jump. We could push the target + * address and then use retq, but this destroys the pipeline on + * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead, + * spill RDI and restore it in a second-stage trampoline. + */ + pushq %rdi + movq $entry_SYSCALL_64_stage2, %rdi + jmp *%rdi +END(entry_SYSCALL_64_trampoline) + + .popsection + +ENTRY(entry_SYSCALL_64_stage2) + UNWIND_HINT_EMPTY + popq %rdi + jmp entry_SYSCALL_64_after_hwframe +END(entry_SYSCALL_64_stage2) + ENTRY(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* @@ -330,8 +388,24 @@ syscall_return_via_sysret: popq %rsi /* skip rcx */ popq %rdx popq %rsi + + /* + * Now all regs are restored except RSP and RDI. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + pushq RSP-RDI(%rdi) /* RSP */ + pushq (%rdi) /* RDI */ + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + popq %rdi - movq RSP-ORIG_RAX(%rsp), %rsp + popq %rsp USERGS_SYSRET64 END(entry_SYSCALL_64) @@ -466,12 +540,13 @@ END(irq_entries_start) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY - pushfq - testl $X86_EFLAGS_IF, (%rsp) + pushq %rax + SAVE_FLAGS(CLBR_RAX) + testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 .Lokay_\@: - addq $8, %rsp + popq %rax #endif .endm @@ -563,6 +638,13 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS @@ -572,12 +654,8 @@ END(irq_entries_start) jz 1f /* - * IRQ from user mode. Switch to kernel gsbase and inform context - * tracking that we're in kernel mode. - */ - SWAPGS - - /* + * IRQ from user mode. + * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode * (which can take locks). Since TRACE_IRQS_OFF idempotent, @@ -630,10 +708,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - SWAPGS POP_EXTRA_REGS - POP_C_REGS - addq $8, %rsp /* skip regs->orig_ax */ + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + + /* + * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + /* Copy the IRET frame to the trampoline stack. */ + pushq 6*8(%rdi) /* SS */ + pushq 5*8(%rdi) /* RSP */ + pushq 4*8(%rdi) /* EFLAGS */ + pushq 3*8(%rdi) /* CS */ + pushq 2*8(%rdi) /* RIP */ + + /* Push user RDI on the trampoline stack. */ + pushq (%rdi) + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + + /* Restore RDI. */ + popq %rdi + SWAPGS INTERRUPT_RETURN @@ -829,7 +938,33 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) + +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +ENTRY(switch_to_thread_stack) + UNWIND_HINT_FUNC + + pushq %rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi + ret +END(switch_to_thread_stack) .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) @@ -848,11 +983,12 @@ ENTRY(\sym) ALLOC_PT_GPREGS_ON_STACK - .if \paranoid - .if \paranoid == 1 + .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ - jnz 1f + jnz .Lfrom_usermode_switch_stack_\@ .endif + + .if \paranoid call paranoid_entry .else call error_entry @@ -894,20 +1030,15 @@ ENTRY(\sym) jmp error_exit .endif - .if \paranoid == 1 + .if \paranoid < 2 /* - * Paranoid entry from userspace. Switch stacks and treat it + * Entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ -1: +.Lfrom_usermode_switch_stack_\@: call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - call sync_regs - movq %rax, %rsp /* switch stack */ - movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code @@ -1170,6 +1301,14 @@ ENTRY(error_entry) SWAPGS .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ + popq %r12 /* save return addr in %12 */ + movq %rsp, %rdi /* arg0 = pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ + ENCODE_FRAME_POINTER + pushq %r12 + /* * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 568e130d932c..95ad40eb7eff 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -48,7 +48,7 @@ */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + SWAPGS movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -306,8 +306,11 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax - /* Construct struct pt_regs on stack (iret frame is already on stack) */ pushq %rax /* pt_regs->orig_ax */ + + /* switch to thread stack expects orig_ax to be pushed */ + call switch_to_thread_stack + pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index bf6a76202a77..ea9a7dde62e5 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4011cb03ef08..aab4fe9f49f8 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -60,17 +60,10 @@ static inline struct desc_struct *get_current_gdt_rw(void) return this_cpu_ptr(&gdt_page)->gdt; } -/* Get the fixmap index for a specific processor */ -static inline unsigned int get_cpu_gdt_ro_index(int cpu) -{ - return FIX_GDT_REMAP_BEGIN + cpu; -} - /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { - unsigned int idx = get_cpu_gdt_ro_index(cpu); - return (struct desc_struct *)__fix_to_virt(idx); + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ @@ -185,7 +178,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, #endif } -static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b0c505fe9a95..94fc4fa14127 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -44,6 +44,45 @@ extern unsigned long __FIXADDR_TOP; PAGE_SIZE) #endif +/* + * cpu_entry_area is a percpu region in the fixmap that contains things + * needed by the CPU and early entry/exit code. Real types aren't used + * for all fields here to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct SYSENTER_stack_page SYSENTER_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries. + * + * In the future, this should have a separate slot for each stack + * with guard pages between them. + */ + char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; +#endif +}; + +#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE) + +extern void setup_cpu_entry_areas(void); /* * Here we define all the compile-time 'special' virtual @@ -101,8 +140,8 @@ enum fixed_addresses { FIX_LNW_VRTC, #endif /* Fixmap entries to remap the GDTs, one per processor. */ - FIX_GDT_REMAP_BEGIN, - FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, + FIX_CPU_ENTRY_AREA_TOP, + FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1, #ifdef CONFIG_ACPI_APEI_GHES /* Used for GHES mapping from assorted contexts */ @@ -191,5 +230,30 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, void __early_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags); +static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page) +{ + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page; +} + +#define __get_cpu_entry_area_offset_index(cpu, offset) ({ \ + BUILD_BUG_ON(offset % PAGE_SIZE != 0); \ + __get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE); \ + }) + +#define get_cpu_entry_area_index(cpu, field) \ + __get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field)) + +static inline struct cpu_entry_area *get_cpu_entry_area(int cpu) +{ + return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0)); +} + +static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 1b0a5abcd8ae..96aa6b9884dc 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -20,16 +20,7 @@ #ifndef _ASM_X86_HYPERVISOR_H #define _ASM_X86_HYPERVISOR_H -#ifdef CONFIG_HYPERVISOR_GUEST - -#include <asm/kvm_para.h> -#include <asm/x86_init.h> -#include <asm/xen/hypervisor.h> - -/* - * x86 hypervisor information - */ - +/* x86 hypervisor types */ enum x86_hypervisor_type { X86_HYPER_NATIVE = 0, X86_HYPER_VMWARE, @@ -39,6 +30,12 @@ enum x86_hypervisor_type { X86_HYPER_KVM, }; +#ifdef CONFIG_HYPERVISOR_GUEST + +#include <asm/kvm_para.h> +#include <asm/x86_init.h> +#include <asm/xen/hypervisor.h> + struct hypervisor_x86 { /* Hypervisor name */ const char *name; @@ -58,7 +55,15 @@ struct hypervisor_x86 { extern enum x86_hypervisor_type x86_hyper_type; extern void init_hypervisor_platform(void); +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return x86_hyper_type == type; +} #else static inline void init_hypervisor_platform(void) { } +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return type == X86_HYPER_NATIVE; +} #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c8ef23f2c28f..89f08955fff7 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void) swapgs; \ sysretl +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(x) pushfq; popq %rax +#endif #else #define INTERRUPT_RETURN iret #define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index f86a8caa561e..395c9631e000 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); +extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 283efcaac8af..892df375b615 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -927,6 +927,15 @@ extern void default_banner(void); PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(clobbers) \ + PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +#endif + #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cc16fa882e3e..1f2434ee9f80 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -163,9 +163,9 @@ enum cpuid_regs_idx { extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; -extern struct tss_struct doublefault_tss; -extern __u32 cpu_caps_cleared[NCAPINTS]; -extern __u32 cpu_caps_set[NCAPINTS]; +extern struct x86_hw_tss doublefault_tss; +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); @@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir) write_cr3(__sme_pa(pgdir)); } +/* + * Note that while the legacy 'TSS' name comes from 'Task State Segment', + * on modern x86 CPUs the TSS also holds information important to 64-bit mode, + * unrelated to the task-switch mechanism: + */ #ifdef CONFIG_X86_32 /* This is the TSS defined by the hardware. */ struct x86_hw_tss { @@ -305,7 +310,13 @@ struct x86_hw_tss { struct x86_hw_tss { u32 reserved1; u64 sp0; + + /* + * We store cpu_current_top_of_stack in sp1 so it's always accessible. + * Linux does not use ring 1, so sp1 is not otherwise needed. + */ u64 sp1; + u64 sp2; u64 reserved2; u64 ist[7]; @@ -323,12 +334,22 @@ struct x86_hw_tss { #define IO_BITMAP_BITS 65536 #define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) +#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 +struct SYSENTER_stack { + unsigned long words[64]; +}; + +struct SYSENTER_stack_page { + struct SYSENTER_stack stack; +} __aligned(PAGE_SIZE); + struct tss_struct { /* - * The hardware state: + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. */ struct x86_hw_tss x86_tss; @@ -339,18 +360,9 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __aligned(PAGE_SIZE); -#ifdef CONFIG_X86_32 - /* - * Space for the temporary SYSENTER stack. - */ - unsigned long SYSENTER_stack_canary; - unsigned long SYSENTER_stack[64]; -#endif - -} ____cacheline_aligned; - -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* * sizeof(unsigned long) coming from an extra "long" at the end @@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#else +/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ +#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif /* @@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask) static inline void native_load_sp0(unsigned long sp0) { - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static inline void native_swapgs(void) @@ -535,12 +550,12 @@ static inline void native_swapgs(void) static inline unsigned long current_top_of_stack(void) { -#ifdef CONFIG_X86_64 - return this_cpu_read_stable(cpu_tss.x86_tss.sp0); -#else - /* sp0 on x86_32 is special in and around vm86 mode. */ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ return this_cpu_read_stable(cpu_current_top_of_stack); -#endif } static inline bool on_thread_stack(void) diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 8da111b3c342..f8062bfd43a0 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -16,6 +16,7 @@ enum stack_type { STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, + STACK_TYPE_SYSENTER, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -28,6 +29,8 @@ struct stack_info { bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); +bool in_sysenter_stack(unsigned long *stack, struct stack_info *info); + int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); 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/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8c6bd6863db9..9b6df68d8fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,10 +79,10 @@ do { \ static inline void refresh_sysenter_cs(struct thread_struct *thread) { /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs)) + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) return; - this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs); + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); } #endif @@ -90,10 +90,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) /* This is used when switching tasks or entering/exiting vm86 mode. */ static inline void update_sp0(struct task_struct *task) { + /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 load_sp0(task->thread.sp0); #else - load_sp0(task_top_of_stack(task)); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task_top_of_stack(task)); #endif } diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 70f425947dc5..00223333821a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack, #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) #endif #endif diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 1fadd310ff68..31051f35cbb7 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9cc6fe1fc6f..c1688c2d0a12 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -7,6 +7,9 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) + struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; @@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) +/* + * WARNING: The entire pt_regs may not be safe to dereference. In some cases, + * only the iret frame registers are accessible. Use with caution! + */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 8ea78275480d..cd360a5e0dca 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -93,4 +93,10 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + + /* Layout info for cpu_entry_area */ + OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); + OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); + OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page); + DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index dedf428b20b6..7d20d9c0b3d6 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -47,13 +47,8 @@ void foo(void) BLANK(); /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - offsetofend(struct tss_struct, SYSENTER_stack)); - - /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 630212fa9b9d..bf51e51d808d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,6 +23,9 @@ int main(void) #ifdef CONFIG_PARAVIRT OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); +#ifdef CONFIG_DEBUG_ENTRY + OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl); +#endif BLANK(); #endif @@ -63,6 +66,7 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fa998ca8aa5a..7416da3ec4df 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -490,27 +490,116 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } -/* Setup the fixmap mapping only once per-processor */ -static inline void setup_fixmap_gdt(int cpu) +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +#endif + +#ifdef CONFIG_X86_64 +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; + +static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +#endif + +static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page, + SYSENTER_stack_storage); + +static void __init +set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) +{ + for ( ; pages; pages--, idx--, ptr += PAGE_SIZE) + __set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot); +} + +/* Setup the fixmap mappings only once per-processor */ +static void __init setup_cpu_entry_area(int cpu) { #ifdef CONFIG_X86_64 - /* On 64-bit systems, we use a read-only fixmap GDT. */ - pgprot_t prot = PAGE_KERNEL_RO; + extern char _entry_trampoline[]; + + /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ + pgprot_t gdt_prot = PAGE_KERNEL_RO; + pgprot_t tss_prot = PAGE_KERNEL_RO; #else /* * On native 32-bit systems, the GDT cannot be read-only because * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. + * a task gate needs to change an available TSS to busy. If the + * GDT is read-only, that will triple fault. The TSS cannot be + * read-only because the CPU writes to it on task switches. * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. + * On Xen PV, the GDT must be read-only because the hypervisor + * requires it. */ - pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? + pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t tss_prot = PAGE_KERNEL; #endif - __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); + __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page), + per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1, + PAGE_KERNEL); + + /* + * The Intel SDM says (Volume 3, 7.2.1): + * + * Avoid placing a page boundary in the part of the TSS that the + * processor reads during a task switch (the first 104 bytes). The + * processor may not correctly perform address translations if a + * boundary occurs in this area. During a task switch, the processor + * reads and writes into the first 104 bytes of each TSS (using + * contiguous physical addresses beginning with the physical address + * of the first byte of the TSS). So, after TSS access begins, if + * part of the 104 bytes is not physically contiguous, the processor + * will access incorrect information without generating a page-fault + * exception. + * + * There are also a lot of errata involving the TSS spanning a page + * boundary. Assert that we're not doing that. + */ + BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ + offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); + BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss), + &per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct) / PAGE_SIZE, + tss_prot); + +#ifdef CONFIG_X86_32 + per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); +#endif + +#ifdef CONFIG_X86_64 + BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0); + BUILD_BUG_ON(sizeof(exception_stacks) != + sizeof(((struct cpu_entry_area *)0)->exception_stacks)); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks), + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, + PAGE_KERNEL); + + __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif +} + +void __init setup_cpu_entry_areas(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + setup_cpu_entry_area(cpu); } /* Load the original GDT from the per-cpu structure */ @@ -747,7 +836,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) { int i; - for (i = 0; i < NCAPINTS; i++) { + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; } @@ -1250,7 +1339,7 @@ void enable_sep_cpu(void) return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1259,11 +1348,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1357,25 +1442,19 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -/* - * Special IST stacks which the CPU switches to when it calls - * an IST-marked descriptor entry. Up to 7 stacks (hardware - * limit), all of them are 4K, except the debug stack which - * is 8K. - */ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ -}; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1386,7 +1465,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1530,7 +1609,7 @@ void cpu_init(void) if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1569,7 +1648,7 @@ void cpu_init(void) * set up and load the per-CPU TSS */ if (!oist->ist[0]) { - char *estacks = per_cpu(exception_stacks, cpu); + char *estacks = get_cpu_entry_area(cpu)->exception_stacks; for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; @@ -1580,7 +1659,7 @@ void cpu_init(void) } } - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; /* * <= is required because the CPU will access up to @@ -1596,11 +1675,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, me); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); load_mm_ldt(&init_mm); @@ -1612,7 +1692,6 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } @@ -1622,7 +1701,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); @@ -1657,12 +1736,12 @@ void cpu_init(void) * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ @@ -1674,7 +1753,6 @@ void cpu_init(void) fpu__init_cpu(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 0e662c55ae90..0b8cedb20d6d 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -50,25 +50,23 @@ static void doublefault_fn(void) cpu_relax(); } -struct tss_struct doublefault_tss __cacheline_aligned = { - .x86_tss = { - .sp0 = STACK_START, - .ss0 = __KERNEL_DS, - .ldt = 0, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, - - .ip = (unsigned long) doublefault_fn, - /* 0x2 bit is always set */ - .flags = X86_EFLAGS_SF | 0x2, - .sp = STACK_START, - .es = __USER_DS, - .cs = __KERNEL_CS, - .ss = __KERNEL_DS, - .ds = __USER_DS, - .fs = __KERNEL_PERCPU, - - .__cr3 = __pa_nodebug(swapper_pg_dir), - } +struct x86_hw_tss doublefault_tss __cacheline_aligned = { + .sp0 = STACK_START, + .ss0 = __KERNEL_DS, + .ldt = 0, + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, + + .ip = (unsigned long) doublefault_fn, + /* 0x2 bit is always set */ + .flags = X86_EFLAGS_SF | 0x2, + .sp = STACK_START, + .es = __USER_DS, + .cs = __KERNEL_CS, + .ss = __KERNEL_DS, + .ds = __USER_DS, + .fs = __KERNEL_PERCPU, + + .__cr3 = __pa_nodebug(swapper_pg_dir), }; /* dummy for do_double_fault() call */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f13b4c00a5de..bbd6d986e2d0 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -43,6 +43,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } +bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) +{ + struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id()); + + void *begin = ss; + void *end = ss + 1; + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_SYSENTER; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, char *log_lvl) { @@ -50,6 +68,28 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +void show_iret_regs(struct pt_regs *regs) +{ + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, + regs->sp, regs->flags); +} + +static void show_regs_safe(struct stack_info *info, struct pt_regs *regs) +{ + if (on_stack(info, regs, sizeof(*regs))) + __show_regs(regs, 0); + else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET, + IRET_FRAME_SIZE)) { + /* + * When an interrupt or exception occurs in entry code, the + * full pt_regs might not have been saved yet. In that case + * just print the iret frame. + */ + show_iret_regs(regs); + } +} + void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl) { @@ -71,31 +111,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - task stack * - interrupt stack * - HW exception stacks (double fault, nmi, debug, mce) + * - SYSENTER stack * - * x86-32 can have up to three stacks: + * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack + * - SYSENTER stack */ for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; - /* - * If we overflowed the task stack into a guard page, jump back - * to the bottom of the usable stack. - */ - if (task_stack_page(task) - (void *)stack < PAGE_SIZE) - stack = task_stack_page(task); - - if (get_stack_info(stack, task, &stack_info, &visit_mask)) - break; + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) + break; + } stack_name = stack_type_name(stack_info.type); if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); /* * Scan the stack, printing any text addresses we find. At the @@ -119,7 +163,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* * Don't print regs->ip again if it was already printed - * by __show_regs() below. + * by show_regs_safe() below. */ if (regs && stack == ®s->ip) goto next; @@ -155,8 +199,8 @@ next: /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); } if (stack_name) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index daefae83a3aa..5ff13a6b3680 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; + if (type == STACK_TYPE_SYSENTER) + return "SYSENTER"; + return NULL; } @@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (task != current) goto unknown; + if (in_sysenter_stack(stack, info)) + goto recursion_check; + if (in_hardirq_stack(stack, info)) goto recursion_check; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 88ce2ffdb110..abc828f8c297 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -37,6 +37,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_SYSENTER) + return "SYSENTER"; + if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -115,6 +118,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (in_irq_stack(stack, info)) goto recursion_check; + if (in_sysenter_stack(stack, info)) + goto recursion_check; + goto unknown; recursion_check: diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 3feb648781c4..2f723301eb58 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(cpu_tss, get_cpu()); + tss = &per_cpu(cpu_tss_rw, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 49cfd9fe7589..68e1867cca80 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - /* - * NB: Unlike exception entries, IRQ entries do not reliably - * handle context tracking in the low-level entry code. This is - * because syscall entries execute briefly with IRQs on before - * updating context tracking state, so we can take an IRQ from - * kernel mode with CONTEXT_USER. The low-level entry code only - * updates the context if we came from user mode, so we won't - * switch to CONTEXT_KERNEL. We'll fix that once the syscall - * code is cleaned up enough that we can cleanly defer enabling - * IRQs. - */ - entering_irq(); /* entering_irq() tells RCU that we're not quiescent. Check it. */ diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 020efbf5786b..d86e344f5b3d 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs) if (regs->sp >= estack_top && regs->sp <= estack_bottom) return; - WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n", + WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n", current->comm, curbase, regs->sp, irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom); + estack_top, estack_bottom, (void *)regs->ip); if (sysctl_panic_on_stackoverflow) panic("low stack detected by irq handler - check messages\n"); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index ac0be8283325..9edadabf04f6 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); @@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index bb988a24db92..aed9d94bd46f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -47,7 +47,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss_rw) = { .x86_tss = { /* * .sp0 is only used when entering ring 0 from a lower @@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { * Poison it. */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, + +#ifdef CONFIG_X86_64 + /* + * .sp1 is cpu_current_top_of_stack. The init task never + * runs user code, but cpu_current_top_of_stack should still + * be well defined before the first context switch. + */ + .sp1 = TOP_OF_INIT_STACK, +#endif + #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, @@ -71,11 +81,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif -#ifdef CONFIG_X86_32 - .SYSENTER_stack_canary = STACK_END_MAGIC, -#endif }; -EXPORT_PER_CPU_SYMBOL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); DEFINE_PER_CPU(bool, __tss_limit_invalid); EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); @@ -104,7 +111,7 @@ void exit_thread(struct task_struct *tsk) struct fpu *fpu = &t->fpu; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 45bf0c5f93e1..5224c6099184 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index eeeb34f85c25..c75466232016 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); - printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, - regs->sp, regs->flags); + show_iret_regs(regs); + if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else @@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); + if (!all) + return; + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); @@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all) rdmsrl(MSR_GS_BASE, gs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - if (!all) - return; - cr0 = read_cr0(); cr2 = read_cr2(); cr3 = __read_cr3(); @@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); @@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); + this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ update_sp0(next_p); 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/kernel/traps.c b/arch/x86/kernel/traps.c index 989514c94a55..e98f8b66a460 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -348,9 +348,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) /* * If IRET takes a non-IST fault on the espfix64 stack, then we - * end up promoting it to a doublefault. In that case, modify - * the stack to make it look like we just entered the #GP - * handler from user space, similar to bad_iret. + * end up promoting it to a doublefault. In that case, take + * advantage of the fact that we're not using the normal (TSS.sp0) + * stack right now. We can write a fake #GP(0) frame at TSS.sp0 + * and then modify our own IRET frame so that, when we return, + * we land directly at the #GP(0) vector with the stack already + * set up according to its expectations. + * + * The net result is that our #GP handler will think that we + * entered from usermode with the bad user context. * * No need for ist_enter here because we don't use RCU. */ @@ -358,13 +364,26 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { - struct pt_regs *normal_regs = task_pt_regs(current); + struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* Fake a #GP(0) from userspace. */ - memmove(&normal_regs->ip, (void *)regs->sp, 5*8); - normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + /* + * regs->sp points to the failing IRET frame on the + * ESPFIX64 stack. Copy it to the entry stack. This fills + * in gpregs->ss through gpregs->ip. + * + */ + memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ + + /* + * Adjust our frame so that we return straight to the #GP + * vector with the expected RSP value. This is safe because + * we won't enable interupts or schedule before we invoke + * general_protection, so nothing will clobber the stack + * frame we just set up. + */ regs->ip = (unsigned long)general_protection; - regs->sp = (unsigned long)&normal_regs->orig_ax; + regs->sp = (unsigned long)&gpregs->orig_ax; return; } @@ -389,7 +408,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * * Processors update CR2 whenever a page fault is detected. If a * second page fault occurs while an earlier page fault is being - * deliv- ered, the faulting linear address of the second fault will + * delivered, the faulting linear address of the second fault will * overwrite the contents of CR2 (replacing the previous * address). These updates to CR2 occur even if the page fault * results in a double fault or occurs during the delivery of a @@ -605,14 +624,15 @@ NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* - * Help handler running on IST stack to switch off the IST stack if the - * interrupted code was in user mode. The actual stack switch is done in - * entry_64.S + * Help handler running on a per-cpu (IST or entry trampoline) stack + * to switch to the normal thread stack if the interrupted code was in + * user mode. The actual stack switch is done in entry_64.S */ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = task_pt_regs(current); - *regs = *eregs; + struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; + if (regs != eregs) + *regs = *eregs; return regs; } NOKPROBE_SYMBOL(sync_regs); @@ -628,13 +648,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault - * correctly, we want move our stack frame to task_pt_regs - * and we want to pretend that the exception came from the - * iret target. + * correctly, we want to move our stack frame to where it would + * be had we entered directly on the entry stack (rather than + * just below the IRET frame) and we want to pretend that the + * exception came from the IRET target. */ struct bad_iret_stack *new_stack = - container_of(task_pt_regs(current), - struct bad_iret_stack, regs); + (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the new stack. */ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); @@ -795,14 +815,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: -#if defined(CONFIG_X86_32) - /* - * This is the most likely code path that involves non-trivial use - * of the SYSENTER stack. Check that we haven't overrun it. - */ - WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, - "Overran or corrupted SYSENTER stack\n"); -#endif ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -929,6 +941,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) void __init trap_init(void) { + /* Init cpu_entry_area before IST entries are set up */ + setup_cpu_entry_areas(); + idt_setup_traps(); /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a3f973b2c97a..be86a865087a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) return NULL; } -static bool stack_access_ok(struct unwind_state *state, unsigned long addr, +static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, size_t len) { struct stack_info *info = &state->stack_info; + void *addr = (void *)_addr; - /* - * If the address isn't on the current stack, switch to the next one. - * - * We may have to traverse multiple stacks to deal with the possibility - * that info->next_sp could point to an empty stack and the address - * could be on a subsequent stack. - */ - while (!on_stack(info, (void *)addr, len)) - if (get_stack_info(info->next_sp, state->task, info, - &state->stack_mask)) - return false; + if (!on_stack(info, addr, len) && + (get_stack_info(addr, state->task, info, &state->stack_mask))) + return false; return true; } @@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, return true; } -#define REGS_SIZE (sizeof(struct pt_regs)) -#define SP_OFFSET (offsetof(struct pt_regs, sp)) -#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip)) -#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip)) - static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, - unsigned long *ip, unsigned long *sp, bool full) + unsigned long *ip, unsigned long *sp) { - size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE; - size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET; - struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE); - - if (IS_ENABLED(CONFIG_X86_64)) { - if (!stack_access_ok(state, addr, regs_size)) - return false; + struct pt_regs *regs = (struct pt_regs *)addr; - *ip = regs->ip; - *sp = regs->sp; + /* x86-32 support will be more complicated due to the ®s->sp hack */ + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32)); - return true; - } - - if (!stack_access_ok(state, addr, sp_offset)) + if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; *ip = regs->ip; + *sp = regs->sp; + return true; +} - if (user_mode(regs)) { - if (!stack_access_ok(state, addr + sp_offset, - REGS_SIZE - SP_OFFSET)) - return false; +static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr, + unsigned long *ip, unsigned long *sp) +{ + struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET; - *sp = regs->sp; - } else - *sp = (unsigned long)®s->sp; + if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) + return false; + *ip = regs->ip; + *sp = regs->sp; return true; } @@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state) unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; - struct pt_regs *ptregs; bool indirect = false; if (unwind_done(state)) @@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { + if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; @@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS_IRET: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { + if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } - ptregs = container_of((void *)sp, struct pt_regs, ip); - if ((unsigned long)ptregs >= prev_sp && - on_stack(&state->stack_info, ptregs, REGS_SIZE)) { - state->regs = ptregs; - state->full_regs = false; - } else - state->regs = NULL; - + state->regs = (void *)sp - IRET_FRAME_OFFSET; + state->full_regs = false; state->signal = true; break; @@ -553,8 +529,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } if (get_stack_info((unsigned long *)state->sp, state->task, - &state->stack_info, &state->stack_mask)) - return; + &state->stack_info, &state->stack_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + if (get_stack_info(next_page, state->task, &state->stack_info, + &state->stack_mask)) + return; + } /* * The caller can provide the address of the first frame directly diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a4009fb9be87..d2a8b5a24a44 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -107,6 +107,15 @@ SECTIONS SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_X86_64 + . = ALIGN(PAGE_SIZE); + _entry_trampoline = .; + *(.entry_trampoline) + . = ALIGN(PAGE_SIZE); + ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8eba631c4dbd..023afa0c8887 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2302,7 +2302,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, - (unsigned long)this_cpu_ptr(&cpu_tss)); + (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 553f8fd23cc4..4846eff7e4c8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops) delay = min_t(u64, MWAITX_MAX_LOOPS, loops); /* - * Use cpu_tss as a cacheline-aligned, seldomly + * Use cpu_tss_rw as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf 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/fault.c b/arch/x86/mm/fault.c index febf6980e653..06fe3d51d385 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -860,7 +860,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); 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/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 99dfed6dfef8..9ec70d780f1f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -277,6 +277,7 @@ void __init kasan_early_init(void) void __init kasan_init(void) { int i; + void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; #ifdef CONFIG_KASAN_INLINE register_die_notifier(&kasan_die_notifier); @@ -329,8 +330,23 @@ void __init kasan_init(void) (unsigned long)kasan_mem_to_shadow(_end), early_pfn_to_nid(__pa(_stext))); + shadow_cpu_entry_begin = (void *)__fix_to_virt(FIX_CPU_ENTRY_AREA_BOTTOM); + shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); + shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin, + PAGE_SIZE); + + shadow_cpu_entry_end = (void *)(__fix_to_virt(FIX_CPU_ENTRY_AREA_TOP) + PAGE_SIZE); + shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); + shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end, + PAGE_SIZE); + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), - (void *)KASAN_SHADOW_END); + shadow_cpu_entry_begin); + + kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, + (unsigned long)shadow_cpu_entry_end, 0); + + kasan_populate_zero_shadow(shadow_cpu_entry_end, (void *)KASAN_SHADOW_END); load_cr3(init_top_pgt); __flush_tlb_all(); 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..a7d966964c6f 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); @@ -160,17 +152,19 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif - set_tss_desc(cpu, t); /* - * This just modifies memory; should not be - * necessary. But... This is necessary, because - * 386 hardware has concept of busy TSS or some - * similar stupidity. - */ + + /* + * We need to reload TR, which requires that we change the + * GDT entry to indicate "available" first. + * + * XXX: This could probably all be replaced by a call to + * force_reload_TR(). + */ + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); #ifdef CONFIG_X86_64 memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); @@ -178,6 +172,9 @@ 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 +187,12 @@ 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 +215,50 @@ 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/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index f2414c6c5e7c..7beeee1443b3 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -826,7 +826,7 @@ static void xen_load_sp0(unsigned long sp0) mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } void xen_set_iopl_mask(unsigned mask) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index fc048ec686e7..6cf801ca1142 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2272,7 +2272,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: - case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END: + case FIX_CPU_ENTRY_AREA_TOP ... FIX_CPU_ENTRY_AREA_BOTTOM: /* All local page mappings */ pte = pfn_pte(phys, prot); break; 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/apei/erst.c b/drivers/acpi/apei/erst.c index 6742f6c68034..9bff853e85f3 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -1007,7 +1007,7 @@ skip: /* The record may be cleared by others, try read next record */ if (len == -ENOENT) goto skip; - else if (len < sizeof(*rcd)) { + else if (len < 0 || len < sizeof(*rcd)) { rc = -EIO; goto out; } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 30e84cc600ae..06ea4749ebd9 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1171,7 +1171,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu); struct cpc_register_resource *desired_reg; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); - struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id]; + struct cppc_pcc_data *pcc_ss_data; int ret = 0; if (!cpc_desc || pcc_ss_id < 0) { 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/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 58d4f4e1ad6a..ca38229b045a 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -22,6 +22,8 @@ #include "cpufreq_governor.h" +#define CPUFREQ_DBS_MIN_SAMPLING_INTERVAL (2 * TICK_NSEC / NSEC_PER_USEC) + static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs); static DEFINE_MUTEX(gov_dbs_data_mutex); @@ -47,11 +49,15 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, { struct dbs_data *dbs_data = to_dbs_data(attr_set); struct policy_dbs_info *policy_dbs; + unsigned int sampling_interval; int ret; - ret = sscanf(buf, "%u", &dbs_data->sampling_rate); - if (ret != 1) + + ret = sscanf(buf, "%u", &sampling_interval); + if (ret != 1 || sampling_interval < CPUFREQ_DBS_MIN_SAMPLING_INTERVAL) return -EINVAL; + dbs_data->sampling_rate = sampling_interval; + /* * We are operating under dbs_data->mutex and so the list and its * entries can't be freed concurrently. @@ -430,7 +436,14 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) if (ret) goto free_policy_dbs_info; - dbs_data->sampling_rate = cpufreq_policy_transition_delay_us(policy); + /* + * The sampling interval should not be less than the transition latency + * of the CPU and it also cannot be too small for dbs_update() to work + * correctly. + */ + dbs_data->sampling_rate = max_t(unsigned int, + CPUFREQ_DBS_MIN_SAMPLING_INTERVAL, + cpufreq_policy_transition_delay_us(policy)); if (!have_governor_per_policy()) gov->gdbs_data = dbs_data; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 628fe899cb48..d9b2c2de49c4 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -226,17 +226,18 @@ static void imx6q_opp_check_speed_grading(struct device *dev) val >>= OCOTP_CFG3_SPEED_SHIFT; val &= 0x3; - if ((val != OCOTP_CFG3_SPEED_1P2GHZ) && - of_machine_is_compatible("fsl,imx6q")) - if (dev_pm_opp_disable(dev, 1200000000)) - dev_warn(dev, "failed to disable 1.2GHz OPP\n"); if (val < OCOTP_CFG3_SPEED_996MHZ) if (dev_pm_opp_disable(dev, 996000000)) dev_warn(dev, "failed to disable 996MHz OPP\n"); - if (of_machine_is_compatible("fsl,imx6q")) { + + if (of_machine_is_compatible("fsl,imx6q") || + of_machine_is_compatible("fsl,imx6qp")) { if (val != OCOTP_CFG3_SPEED_852MHZ) if (dev_pm_opp_disable(dev, 852000000)) dev_warn(dev, "failed to disable 852MHz OPP\n"); + if (val != OCOTP_CFG3_SPEED_1P2GHZ) + if (dev_pm_opp_disable(dev, 1200000000)) + dev_warn(dev, "failed to disable 1.2GHz OPP\n"); } iounmap(base); put_node: diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index fbab271b3bf9..a861b5b4d443 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -708,7 +708,7 @@ atc_prep_dma_interleaved(struct dma_chan *chan, unsigned long flags) { struct at_dma_chan *atchan = to_at_dma_chan(chan); - struct data_chunk *first = xt->sgl; + struct data_chunk *first; struct at_desc *desc = NULL; size_t xfer_count; unsigned int dwidth; @@ -720,6 +720,8 @@ atc_prep_dma_interleaved(struct dma_chan *chan, if (unlikely(!xt || xt->numf != 1 || !xt->frame_size)) return NULL; + first = xt->sgl; + dev_info(chan2dev(chan), "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n", __func__, &xt->src_start, &xt->dst_start, xt->numf, diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c index d50273fed715..afd5e10f8927 100644 --- a/drivers/dma/dma-jz4740.c +++ b/drivers/dma/dma-jz4740.c @@ -555,7 +555,7 @@ static int jz4740_dma_probe(struct platform_device *pdev) ret = dma_async_device_register(dd); if (ret) - return ret; + goto err_clk; irq = platform_get_irq(pdev, 0); ret = request_irq(irq, jz4740_dma_irq, 0, dev_name(&pdev->dev), dmadev); @@ -568,6 +568,8 @@ static int jz4740_dma_probe(struct platform_device *pdev) err_unregister: dma_async_device_unregister(dd); +err_clk: + clk_disable_unprepare(dmadev->clk); return ret; } diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 47edc7fbf91f..ec5f9d2bc820 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -155,6 +155,12 @@ MODULE_PARM_DESC(run, "Run the test (default: false)"); #define PATTERN_COUNT_MASK 0x1f #define PATTERN_MEMSET_IDX 0x01 +/* poor man's completion - we want to use wait_event_freezable() on it */ +struct dmatest_done { + bool done; + wait_queue_head_t *wait; +}; + struct dmatest_thread { struct list_head node; struct dmatest_info *info; @@ -165,6 +171,8 @@ struct dmatest_thread { u8 **dsts; u8 **udsts; enum dma_transaction_type type; + wait_queue_head_t done_wait; + struct dmatest_done test_done; bool done; }; @@ -342,18 +350,25 @@ static unsigned int dmatest_verify(u8 **bufs, unsigned int start, return error_count; } -/* poor man's completion - we want to use wait_event_freezable() on it */ -struct dmatest_done { - bool done; - wait_queue_head_t *wait; -}; static void dmatest_callback(void *arg) { struct dmatest_done *done = arg; - - done->done = true; - wake_up_all(done->wait); + struct dmatest_thread *thread = + container_of(arg, struct dmatest_thread, done_wait); + if (!thread->done) { + done->done = true; + wake_up_all(done->wait); + } else { + /* + * If thread->done, it means that this callback occurred + * after the parent thread has cleaned up. This can + * happen in the case that driver doesn't implement + * the terminate_all() functionality and a dma operation + * did not occur within the timeout period + */ + WARN(1, "dmatest: Kernel memory may be corrupted!!\n"); + } } static unsigned int min_odd(unsigned int x, unsigned int y) @@ -424,9 +439,8 @@ static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len) */ static int dmatest_func(void *data) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(done_wait); struct dmatest_thread *thread = data; - struct dmatest_done done = { .wait = &done_wait }; + struct dmatest_done *done = &thread->test_done; struct dmatest_info *info; struct dmatest_params *params; struct dma_chan *chan; @@ -673,9 +687,9 @@ static int dmatest_func(void *data) continue; } - done.done = false; + done->done = false; tx->callback = dmatest_callback; - tx->callback_param = &done; + tx->callback_param = done; cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { @@ -688,21 +702,12 @@ static int dmatest_func(void *data) } dma_async_issue_pending(chan); - wait_event_freezable_timeout(done_wait, done.done, + wait_event_freezable_timeout(thread->done_wait, done->done, msecs_to_jiffies(params->timeout)); status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - if (!done.done) { - /* - * We're leaving the timed out dma operation with - * dangling pointer to done_wait. To make this - * correct, we'll need to allocate wait_done for - * each test iteration and perform "who's gonna - * free it this time?" dancing. For now, just - * leave it dangling. - */ - WARN(1, "dmatest: Kernel stack may be corrupted!!\n"); + if (!done->done) { dmaengine_unmap_put(um); result("test timed out", total_tests, src_off, dst_off, len, 0); @@ -789,7 +794,7 @@ err_thread_type: dmatest_KBs(runtime, total_len), ret); /* terminate all transfers on specified channels */ - if (ret) + if (ret || failed_tests) dmaengine_terminate_all(chan); thread->done = true; @@ -849,6 +854,8 @@ static int dmatest_add_threads(struct dmatest_info *info, thread->info = info; thread->chan = dtc->chan; thread->type = type; + thread->test_done.wait = &thread->done_wait; + init_waitqueue_head(&thread->done_wait); smp_wmb(); thread->task = kthread_create(dmatest_func, thread, "%s-%s%u", dma_chan_name(chan), op, i); diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c index 6775f2c74e25..c7568869284e 100644 --- a/drivers/dma/fsl-edma.c +++ b/drivers/dma/fsl-edma.c @@ -863,11 +863,11 @@ static void fsl_edma_irq_exit( } } -static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma) +static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma, int nr_clocks) { int i; - for (i = 0; i < DMAMUX_NR; i++) + for (i = 0; i < nr_clocks; i++) clk_disable_unprepare(fsl_edma->muxclk[i]); } @@ -904,25 +904,25 @@ static int fsl_edma_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i); fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(fsl_edma->muxbase[i])) + if (IS_ERR(fsl_edma->muxbase[i])) { + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i); return PTR_ERR(fsl_edma->muxbase[i]); + } sprintf(clkname, "dmamux%d", i); fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname); if (IS_ERR(fsl_edma->muxclk[i])) { dev_err(&pdev->dev, "Missing DMAMUX block clock.\n"); + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i); return PTR_ERR(fsl_edma->muxclk[i]); } ret = clk_prepare_enable(fsl_edma->muxclk[i]); - if (ret) { - /* disable only clks which were enabled on error */ - for (; i >= 0; i--) - clk_disable_unprepare(fsl_edma->muxclk[i]); - - dev_err(&pdev->dev, "DMAMUX clk block failed.\n"); - return ret; - } + if (ret) + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i); } @@ -976,7 +976,7 @@ static int fsl_edma_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Can't register Freescale eDMA engine. (%d)\n", ret); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR); return ret; } @@ -985,7 +985,7 @@ static int fsl_edma_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Can't register Freescale eDMA of_dma. (%d)\n", ret); dma_async_device_unregister(&fsl_edma->dma_dev); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR); return ret; } @@ -1015,7 +1015,7 @@ static int fsl_edma_remove(struct platform_device *pdev) fsl_edma_cleanup_vchan(&fsl_edma->dma_dev); of_dma_controller_free(np); dma_async_device_unregister(&fsl_edma->dma_dev); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR); return 0; } diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 2f31d3d0caa6..7792a9186f9c 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -390,7 +390,7 @@ static int ioat_dma_self_test(struct ioatdma_device *ioat_dma) if (memcmp(src, dest, IOAT_TEST_SIZE)) { dev_err(dev, "Self-test copy failed compare, disabling\n"); err = -ENODEV; - goto free_resources; + goto unmap_dma; } unmap_dma: 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/i2c/busses/i2c-cht-wc.c b/drivers/i2c/busses/i2c-cht-wc.c index 0d05dadb2dc5..44cffad43701 100644 --- a/drivers/i2c/busses/i2c-cht-wc.c +++ b/drivers/i2c/busses/i2c-cht-wc.c @@ -379,7 +379,7 @@ static int cht_wc_i2c_adap_i2c_remove(struct platform_device *pdev) return 0; } -static struct platform_device_id cht_wc_i2c_adap_id_table[] = { +static const struct platform_device_id cht_wc_i2c_adap_id_table[] = { { .name = "cht_wcove_ext_chgr" }, {}, }; diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 174579d32e5f..462948e2c535 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -983,7 +983,7 @@ static void piix4_adap_remove(struct i2c_adapter *adap) if (adapdata->smba) { i2c_del_adapter(adap); - if (adapdata->port == (0 << 1)) { + if (adapdata->port == (0 << piix4_port_shift_sb800)) { release_region(adapdata->smba, SMBIOSIZE); if (adapdata->sb800_main) release_region(SB800_PIIX4_SMB_IDX, 2); diff --git a/drivers/i2c/busses/i2c-stm32.h b/drivers/i2c/busses/i2c-stm32.h index dab51761f8c5..d4f9cef251ac 100644 --- a/drivers/i2c/busses/i2c-stm32.h +++ b/drivers/i2c/busses/i2c-stm32.h @@ -1,10 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 /* * i2c-stm32.h * * Copyright (C) M'boumba Cedric Madianga 2017 + * Copyright (C) STMicroelectronics 2017 * Author: M'boumba Cedric Madianga <cedric.madianga@gmail.com> * - * License terms: GNU General Public License (GPL), version 2 */ #ifndef _I2C_STM32_H diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c index 4ec108496f15..47c8d00de53f 100644 --- a/drivers/i2c/busses/i2c-stm32f4.c +++ b/drivers/i2c/busses/i2c-stm32f4.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Driver for STMicroelectronics STM32 I2C controller * @@ -6,11 +7,11 @@ * http://www.st.com/resource/en/reference_manual/DM00031020.pdf * * Copyright (C) M'boumba Cedric Madianga 2016 + * Copyright (C) STMicroelectronics 2017 * Author: M'boumba Cedric Madianga <cedric.madianga@gmail.com> * * This driver is based on i2c-st.c * - * License terms: GNU General Public License (GPL), version 2 */ #include <linux/clk.h> diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index d4a6e9c2e9aa..b445b3bb0bb1 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Driver for STMicroelectronics STM32F7 I2C controller * @@ -7,11 +8,11 @@ * http://www.st.com/resource/en/reference_manual/dm00124865.pdf * * Copyright (C) M'boumba Cedric Madianga 2017 + * Copyright (C) STMicroelectronics 2017 * Author: M'boumba Cedric Madianga <cedric.madianga@gmail.com> * * This driver is based on i2c-stm32f4.c * - * License terms: GNU General Public License (GPL), version 2 */ #include <linux/clk.h> #include <linux/delay.h> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f6983357145d..6294a7001d33 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4458,7 +4458,7 @@ out: return skb->len; } -static const struct rdma_nl_cbs cma_cb_table[] = { +static const struct rdma_nl_cbs cma_cb_table[RDMA_NL_RDMA_CM_NUM_OPS] = { [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats}, }; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 5e1be4949d5f..30914f3baa5f 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1146,7 +1146,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, } EXPORT_SYMBOL(ib_get_net_dev_by_params); -static const struct rdma_nl_cbs ibnl_ls_cb_table[] = { +static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { [RDMA_NL_LS_OP_RESOLVE] = { .doit = ib_nl_handle_resolve_resp, .flags = RDMA_NL_ADMIN_PERM, diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index e9e189ec7502..5d676cff41f4 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason) } EXPORT_SYMBOL(iwcm_reject_msg); -static struct rdma_nl_cbs iwcm_nl_cb_table[] = { +static struct rdma_nl_cbs iwcm_nl_cb_table[RDMA_NL_IWPM_NUM_OPS] = { [RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb}, [RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb}, [RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb}, diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 2fae850a3eff..9a05245a1acf 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -303,7 +303,7 @@ out: cb->args[0] = idx; return skb->len; } -static const struct rdma_nl_cbs nldev_cb_table[] = { +static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { [RDMA_NLDEV_CMD_GET] = { .doit = nldev_get_doit, .dump = nldev_get_dumpit, diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index a337386652b0..feafdb961c48 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -739,8 +739,11 @@ int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index) if (!rdma_protocol_ib(map->agent.device, map->agent.port_num)) return 0; - if (map->agent.qp->qp_type == IB_QPT_SMI && !map->agent.smp_allowed) - return -EACCES; + if (map->agent.qp->qp_type == IB_QPT_SMI) { + if (!map->agent.smp_allowed) + return -EACCES; + return 0; + } return ib_security_pkey_access(map->agent.device, map->agent.port_num, diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 16d55710b116..d0202bb176a4 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1971,6 +1971,12 @@ static int modify_qp(struct ib_uverbs_file *file, goto release_qp; } + if ((cmd->base.attr_mask & IB_QP_ALT_PATH) && + !rdma_is_port_valid(qp->device, cmd->base.alt_port_num)) { + ret = -EINVAL; + goto release_qp; + } + attr->qp_state = cmd->base.qp_state; attr->cur_qp_state = cmd->base.cur_qp_state; attr->path_mtu = cmd->base.path_mtu; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index ea55e95cd2c5..b7bfc536e00f 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -395,6 +395,11 @@ next_cqe: static int cqe_completes_wr(struct t4_cqe *cqe, struct t4_wq *wq) { + if (CQE_OPCODE(cqe) == C4IW_DRAIN_OPCODE) { + WARN_ONCE(1, "Unexpected DRAIN CQE qp id %u!\n", wq->sq.qid); + return 0; + } + if (CQE_OPCODE(cqe) == FW_RI_TERMINATE) return 0; diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 5ee7fe433136..38bddd02a943 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -868,7 +868,12 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, qhp = to_c4iw_qp(ibqp); spin_lock_irqsave(&qhp->lock, flag); - if (t4_wq_in_error(&qhp->wq)) { + + /* + * If the qp has been flushed, then just insert a special + * drain cqe. + */ + if (qhp->wq.flushed) { spin_unlock_irqrestore(&qhp->lock, flag); complete_sq_drain_wr(qhp, wr); return err; @@ -1011,7 +1016,12 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, qhp = to_c4iw_qp(ibqp); spin_lock_irqsave(&qhp->lock, flag); - if (t4_wq_in_error(&qhp->wq)) { + + /* + * If the qp has been flushed, then just insert a special + * drain cqe. + */ + if (qhp->wq.flushed) { spin_unlock_irqrestore(&qhp->lock, flag); complete_rq_drain_wr(qhp, wr); return err; @@ -1285,21 +1295,21 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp, spin_unlock_irqrestore(&rchp->lock, flag); if (schp == rchp) { - if (t4_clear_cq_armed(&rchp->cq) && - (rq_flushed || sq_flushed)) { + if ((rq_flushed || sq_flushed) && + t4_clear_cq_armed(&rchp->cq)) { spin_lock_irqsave(&rchp->comp_handler_lock, flag); (*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context); spin_unlock_irqrestore(&rchp->comp_handler_lock, flag); } } else { - if (t4_clear_cq_armed(&rchp->cq) && rq_flushed) { + if (rq_flushed && t4_clear_cq_armed(&rchp->cq)) { spin_lock_irqsave(&rchp->comp_handler_lock, flag); (*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context); spin_unlock_irqrestore(&rchp->comp_handler_lock, flag); } - if (t4_clear_cq_armed(&schp->cq) && sq_flushed) { + if (sq_flushed && t4_clear_cq_armed(&schp->cq)) { spin_lock_irqsave(&schp->comp_handler_lock, flag); (*schp->ibcq.comp_handler)(&schp->ibcq, schp->ibcq.cq_context); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 013049bcdb53..caf490ab24c8 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -666,6 +666,19 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx, return (-EOPNOTSUPP); } + if (ucmd->rx_hash_fields_mask & ~(MLX4_IB_RX_HASH_SRC_IPV4 | + MLX4_IB_RX_HASH_DST_IPV4 | + MLX4_IB_RX_HASH_SRC_IPV6 | + MLX4_IB_RX_HASH_DST_IPV6 | + MLX4_IB_RX_HASH_SRC_PORT_TCP | + MLX4_IB_RX_HASH_DST_PORT_TCP | + MLX4_IB_RX_HASH_SRC_PORT_UDP | + MLX4_IB_RX_HASH_DST_PORT_UDP)) { + pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n", + ucmd->rx_hash_fields_mask); + return (-EOPNOTSUPP); + } + if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) && (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) { rss_ctx->flags = MLX4_RSS_IPV4; @@ -691,11 +704,11 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx, return (-EOPNOTSUPP); } - if (rss_ctx->flags & MLX4_RSS_IPV4) { + if (rss_ctx->flags & MLX4_RSS_IPV4) rss_ctx->flags |= MLX4_RSS_UDP_IPV4; - } else if (rss_ctx->flags & MLX4_RSS_IPV6) { + if (rss_ctx->flags & MLX4_RSS_IPV6) rss_ctx->flags |= MLX4_RSS_UDP_IPV6; - } else { + if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) { pr_debug("RX Hash fields_mask is not supported - UDP must be set with IPv4 or IPv6\n"); return (-EOPNOTSUPP); } @@ -707,15 +720,14 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx, if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) && (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) { - if (rss_ctx->flags & MLX4_RSS_IPV4) { + if (rss_ctx->flags & MLX4_RSS_IPV4) rss_ctx->flags |= MLX4_RSS_TCP_IPV4; - } else if (rss_ctx->flags & MLX4_RSS_IPV6) { + if (rss_ctx->flags & MLX4_RSS_IPV6) rss_ctx->flags |= MLX4_RSS_TCP_IPV6; - } else { + if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) { pr_debug("RX Hash fields_mask is not supported - TCP must be set with IPv4 or IPv6\n"); return (-EOPNOTSUPP); } - } else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) || (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) { pr_debug("RX Hash fields_mask is not supported - both TCP SRC and DST must be set\n"); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 87f4bd99cdf7..2c13123bfd69 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1145,6 +1145,7 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn, noio_flag = memalloc_noio_save(); p->tx_ring = vzalloc(ipoib_sendq_size * sizeof(*p->tx_ring)); if (!p->tx_ring) { + memalloc_noio_restore(noio_flag); ret = -ENOMEM; goto err_tx; } 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/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c index c9714072e224..59c82cdcf48d 100644 --- a/drivers/mfd/cros_ec_spi.c +++ b/drivers/mfd/cros_ec_spi.c @@ -377,6 +377,7 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, u8 *ptr; u8 *rx_buf; u8 sum; + u8 rx_byte; int ret = 0, final_ret; len = cros_ec_prepare_tx(ec_dev, ec_msg); @@ -421,25 +422,22 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, if (!ret) { /* Verify that EC can process command */ for (i = 0; i < len; i++) { - switch (rx_buf[i]) { - case EC_SPI_PAST_END: - case EC_SPI_RX_BAD_DATA: - case EC_SPI_NOT_READY: - ret = -EAGAIN; - ec_msg->result = EC_RES_IN_PROGRESS; - default: + rx_byte = rx_buf[i]; + if (rx_byte == EC_SPI_PAST_END || + rx_byte == EC_SPI_RX_BAD_DATA || + rx_byte == EC_SPI_NOT_READY) { + ret = -EREMOTEIO; break; } - if (ret) - break; } - if (!ret) - ret = cros_ec_spi_receive_packet(ec_dev, - ec_msg->insize + sizeof(*response)); - } else { - dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); } + if (!ret) + ret = cros_ec_spi_receive_packet(ec_dev, + ec_msg->insize + sizeof(*response)); + else + dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); + final_ret = terminate_request(ec_dev); spi_bus_unlock(ec_spi->spi->master); @@ -508,6 +506,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, int i, len; u8 *ptr; u8 *rx_buf; + u8 rx_byte; int sum; int ret = 0, final_ret; @@ -544,25 +543,22 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, if (!ret) { /* Verify that EC can process command */ for (i = 0; i < len; i++) { - switch (rx_buf[i]) { - case EC_SPI_PAST_END: - case EC_SPI_RX_BAD_DATA: - case EC_SPI_NOT_READY: - ret = -EAGAIN; - ec_msg->result = EC_RES_IN_PROGRESS; - default: + rx_byte = rx_buf[i]; + if (rx_byte == EC_SPI_PAST_END || + rx_byte == EC_SPI_RX_BAD_DATA || + rx_byte == EC_SPI_NOT_READY) { + ret = -EREMOTEIO; break; } - if (ret) - break; } - if (!ret) - ret = cros_ec_spi_receive_response(ec_dev, - ec_msg->insize + EC_MSG_TX_PROTO_BYTES); - } else { - dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); } + if (!ret) + ret = cros_ec_spi_receive_response(ec_dev, + ec_msg->insize + EC_MSG_TX_PROTO_BYTES); + else + dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); + final_ret = terminate_request(ec_dev); spi_bus_unlock(ec_spi->spi->master); @@ -667,6 +663,7 @@ static int cros_ec_spi_probe(struct spi_device *spi) sizeof(struct ec_response_get_protocol_info); ec_dev->dout_size = sizeof(struct ec_host_request); + ec_spi->last_transfer_ns = ktime_get_ns(); err = cros_ec_register(ec_dev); if (err) { diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c index da16bf45fab4..dc94ffc6321a 100644 --- a/drivers/mfd/twl4030-audio.c +++ b/drivers/mfd/twl4030-audio.c @@ -159,13 +159,18 @@ unsigned int twl4030_audio_get_mclk(void) EXPORT_SYMBOL_GPL(twl4030_audio_get_mclk); static bool twl4030_audio_has_codec(struct twl4030_audio_data *pdata, - struct device_node *node) + struct device_node *parent) { + struct device_node *node; + if (pdata && pdata->codec) return true; - if (of_find_node_by_name(node, "codec")) + node = of_get_child_by_name(parent, "codec"); + if (node) { + of_node_put(node); return true; + } return false; } diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c index d66502d36ba0..dd19f17a1b63 100644 --- a/drivers/mfd/twl6040.c +++ b/drivers/mfd/twl6040.c @@ -97,12 +97,16 @@ static struct reg_sequence twl6040_patch[] = { }; -static bool twl6040_has_vibra(struct device_node *node) +static bool twl6040_has_vibra(struct device_node *parent) { -#ifdef CONFIG_OF - if (of_find_node_by_name(node, "vibra")) + struct device_node *node; + + node = of_get_child_by_name(parent, "vibra"); + if (node) { + of_node_put(node); return true; -#endif + } + return false; } diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 305a7a464d09..4d63ac8a82e0 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -562,7 +562,7 @@ static ssize_t at24_eeprom_write_i2c(struct at24_data *at24, const char *buf, static int at24_read(void *priv, unsigned int off, void *val, size_t count) { struct at24_data *at24 = priv; - struct i2c_client *client; + struct device *dev = &at24->client[0]->dev; char *buf = val; int ret; @@ -572,11 +572,9 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count) if (off + count > at24->chip.byte_len) return -EINVAL; - client = at24_translate_offset(at24, &off); - - ret = pm_runtime_get_sync(&client->dev); + ret = pm_runtime_get_sync(dev); if (ret < 0) { - pm_runtime_put_noidle(&client->dev); + pm_runtime_put_noidle(dev); return ret; } @@ -592,7 +590,7 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count) status = at24->read_func(at24, buf, off, count); if (status < 0) { mutex_unlock(&at24->lock); - pm_runtime_put(&client->dev); + pm_runtime_put(dev); return status; } buf += status; @@ -602,7 +600,7 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count) mutex_unlock(&at24->lock); - pm_runtime_put(&client->dev); + pm_runtime_put(dev); return 0; } @@ -610,7 +608,7 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count) static int at24_write(void *priv, unsigned int off, void *val, size_t count) { struct at24_data *at24 = priv; - struct i2c_client *client; + struct device *dev = &at24->client[0]->dev; char *buf = val; int ret; @@ -620,11 +618,9 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count) if (off + count > at24->chip.byte_len) return -EINVAL; - client = at24_translate_offset(at24, &off); - - ret = pm_runtime_get_sync(&client->dev); + ret = pm_runtime_get_sync(dev); if (ret < 0) { - pm_runtime_put_noidle(&client->dev); + pm_runtime_put_noidle(dev); return ret; } @@ -640,7 +636,7 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count) status = at24->write_func(at24, buf, off, count); if (status < 0) { mutex_unlock(&at24->lock); - pm_runtime_put(&client->dev); + pm_runtime_put(dev); return status; } buf += status; @@ -650,7 +646,7 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count) mutex_unlock(&at24->lock); - pm_runtime_put(&client->dev); + pm_runtime_put(dev); return 0; } @@ -880,7 +876,7 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) at24->nvmem_config.reg_read = at24_read; at24->nvmem_config.reg_write = at24_write; at24->nvmem_config.priv = at24; - at24->nvmem_config.stride = 4; + at24->nvmem_config.stride = 1; at24->nvmem_config.word_size = 1; at24->nvmem_config.size = chip.byte_len; diff --git a/drivers/misc/pti.c b/drivers/misc/pti.c index eda38cbe8530..41f2a9f6851d 100644 --- a/drivers/misc/pti.c +++ b/drivers/misc/pti.c @@ -32,7 +32,7 @@ #include <linux/pci.h> #include <linux/mutex.h> #include <linux/miscdevice.h> -#include <linux/pti.h> +#include <linux/intel-pti.h> #include <linux/slab.h> #include <linux/uaccess.h> 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/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index f80e911b8843..73b605577447 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1114,7 +1114,7 @@ static int mtd_check_oob_ops(struct mtd_info *mtd, loff_t offs, if (!ops->oobbuf) ops->ooblen = 0; - if (offs < 0 || offs + ops->len >= mtd->size) + if (offs < 0 || offs + ops->len > mtd->size) return -EINVAL; if (ops->ooblen) { diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c index e0eb51d8c012..dd56a671ea42 100644 --- a/drivers/mtd/nand/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/brcmnand/brcmnand.c @@ -1763,7 +1763,7 @@ try_dmaread: err = brcmstb_nand_verify_erased_page(mtd, chip, buf, addr); /* erased page bitflips corrected */ - if (err > 0) + if (err >= 0) return err; } diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c index 484f7fbc3f7d..a8bde6665c24 100644 --- a/drivers/mtd/nand/gpio.c +++ b/drivers/mtd/nand/gpio.c @@ -253,9 +253,9 @@ static int gpio_nand_probe(struct platform_device *pdev) goto out_ce; } - gpiomtd->nwp = devm_gpiod_get(dev, "ale", GPIOD_OUT_LOW); - if (IS_ERR(gpiomtd->nwp)) { - ret = PTR_ERR(gpiomtd->nwp); + gpiomtd->ale = devm_gpiod_get(dev, "ale", GPIOD_OUT_LOW); + if (IS_ERR(gpiomtd->ale)) { + ret = PTR_ERR(gpiomtd->ale); goto out_ce; } diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 50f8d4a1b983..d4d824ef64e9 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -1067,9 +1067,6 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip, return ret; } - /* handle the block mark swapping */ - block_mark_swapping(this, payload_virt, auxiliary_virt); - /* Loop over status bytes, accumulating ECC status. */ status = auxiliary_virt + nfc_geo->auxiliary_status_offset; @@ -1158,6 +1155,9 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip, max_bitflips = max_t(unsigned int, max_bitflips, *status); } + /* handle the block mark swapping */ + block_mark_swapping(this, buf, auxiliary_virt); + if (oob_required) { /* * It's time to deliver the OOB bytes. See gpmi_ecc_read_oob() diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index a7801f6668a5..6315774d72b3 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -338,6 +338,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, cmode = MV88E6XXX_PORT_STS_CMODE_2500BASEX; break; case PHY_INTERFACE_MODE_XGMII: + case PHY_INTERFACE_MODE_XAUI: cmode = MV88E6XXX_PORT_STS_CMODE_XAUI; break; case PHY_INTERFACE_MODE_RXAUI: diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index 57e796870595..105fdb958cef 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -50,7 +50,7 @@ #define AQ_CFG_PCI_FUNC_MSIX_IRQS 9U #define AQ_CFG_PCI_FUNC_PORTS 2U -#define AQ_CFG_SERVICE_TIMER_INTERVAL (2 * HZ) +#define AQ_CFG_SERVICE_TIMER_INTERVAL (1 * HZ) #define AQ_CFG_POLLING_TIMER_INTERVAL ((unsigned int)(2 * HZ)) #define AQ_CFG_SKB_FRAGS_MAX 32U @@ -80,6 +80,7 @@ #define AQ_CFG_DRV_VERSION __stringify(NIC_MAJOR_DRIVER_VERSION)"."\ __stringify(NIC_MINOR_DRIVER_VERSION)"."\ __stringify(NIC_BUILD_DRIVER_VERSION)"."\ - __stringify(NIC_REVISION_DRIVER_VERSION) + __stringify(NIC_REVISION_DRIVER_VERSION) \ + AQ_CFG_DRV_VERSION_SUFFIX #endif /* AQ_CFG_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 70efb7467bf3..f2d8063a2cef 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -66,14 +66,14 @@ static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = { "OutUCast", "OutMCast", "OutBCast", - "InUCastOctects", - "OutUCastOctects", - "InMCastOctects", - "OutMCastOctects", - "InBCastOctects", - "OutBCastOctects", - "InOctects", - "OutOctects", + "InUCastOctets", + "OutUCastOctets", + "InMCastOctets", + "OutMCastOctets", + "InBCastOctets", + "OutBCastOctets", + "InOctets", + "OutOctets", "InPacketsDma", "OutPacketsDma", "InOctetsDma", diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 0207927dc8a6..b3825de6cdfb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -46,6 +46,28 @@ struct aq_hw_link_status_s { unsigned int mbps; }; +struct aq_stats_s { + u64 uprc; + u64 mprc; + u64 bprc; + u64 erpt; + u64 uptc; + u64 mptc; + u64 bptc; + u64 erpr; + u64 mbtc; + u64 bbtc; + u64 mbrc; + u64 bbrc; + u64 ubrc; + u64 ubtc; + u64 dpc; + u64 dma_pkt_rc; + u64 dma_pkt_tc; + u64 dma_oct_rc; + u64 dma_oct_tc; +}; + #define AQ_HW_IRQ_INVALID 0U #define AQ_HW_IRQ_LEGACY 1U #define AQ_HW_IRQ_MSI 2U @@ -85,7 +107,9 @@ struct aq_hw_ops { void (*destroy)(struct aq_hw_s *self); int (*get_hw_caps)(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps); + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device); int (*hw_ring_tx_xmit)(struct aq_hw_s *self, struct aq_ring_s *aq_ring, unsigned int frags); @@ -164,8 +188,7 @@ struct aq_hw_ops { int (*hw_update_stats)(struct aq_hw_s *self); - int (*hw_get_hw_stats)(struct aq_hw_s *self, u64 *data, - unsigned int *p_count); + struct aq_stats_s *(*hw_get_hw_stats)(struct aq_hw_s *self); int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 78dfb2ab78ce..75a894a9251c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -37,6 +37,8 @@ static unsigned int aq_itr_rx; module_param_named(aq_itr_rx, aq_itr_rx, uint, 0644); MODULE_PARM_DESC(aq_itr_rx, "RX interrupt throttle rate"); +static void aq_nic_update_ndev_stats(struct aq_nic_s *self); + static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues) { struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg; @@ -166,11 +168,8 @@ static int aq_nic_update_link_status(struct aq_nic_s *self) static void aq_nic_service_timer_cb(struct timer_list *t) { struct aq_nic_s *self = from_timer(self, t, service_timer); - struct net_device *ndev = aq_nic_get_ndev(self); + int ctimer = AQ_CFG_SERVICE_TIMER_INTERVAL; int err = 0; - unsigned int i = 0U; - struct aq_ring_stats_rx_s stats_rx; - struct aq_ring_stats_tx_s stats_tx; if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY)) goto err_exit; @@ -182,23 +181,14 @@ static void aq_nic_service_timer_cb(struct timer_list *t) if (self->aq_hw_ops.hw_update_stats) self->aq_hw_ops.hw_update_stats(self->aq_hw); - memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s)); - memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s)); - for (i = AQ_DIMOF(self->aq_vec); i--;) { - if (self->aq_vec[i]) - aq_vec_add_stats(self->aq_vec[i], &stats_rx, &stats_tx); - } + aq_nic_update_ndev_stats(self); - ndev->stats.rx_packets = stats_rx.packets; - ndev->stats.rx_bytes = stats_rx.bytes; - ndev->stats.rx_errors = stats_rx.errors; - ndev->stats.tx_packets = stats_tx.packets; - ndev->stats.tx_bytes = stats_tx.bytes; - ndev->stats.tx_errors = stats_tx.errors; + /* If no link - use faster timer rate to detect link up asap */ + if (!netif_carrier_ok(self->ndev)) + ctimer = max(ctimer / 2, 1); err_exit: - mod_timer(&self->service_timer, - jiffies + AQ_CFG_SERVICE_TIMER_INTERVAL); + mod_timer(&self->service_timer, jiffies + ctimer); } static void aq_nic_polling_timer_cb(struct timer_list *t) @@ -222,7 +212,7 @@ static struct net_device *aq_nic_ndev_alloc(void) struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, const struct ethtool_ops *et_ops, - struct device *dev, + struct pci_dev *pdev, struct aq_pci_func_s *aq_pci_func, unsigned int port, const struct aq_hw_ops *aq_hw_ops) @@ -242,7 +232,7 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, ndev->netdev_ops = ndev_ops; ndev->ethtool_ops = et_ops; - SET_NETDEV_DEV(ndev, dev); + SET_NETDEV_DEV(ndev, &pdev->dev); ndev->if_port = port; self->ndev = ndev; @@ -254,7 +244,8 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, self->aq_hw = self->aq_hw_ops.create(aq_pci_func, self->port, &self->aq_hw_ops); - err = self->aq_hw_ops.get_hw_caps(self->aq_hw, &self->aq_hw_caps); + err = self->aq_hw_ops.get_hw_caps(self->aq_hw, &self->aq_hw_caps, + pdev->device, pdev->subsystem_device); if (err < 0) goto err_exit; @@ -749,16 +740,40 @@ int aq_nic_get_regs_count(struct aq_nic_s *self) void aq_nic_get_stats(struct aq_nic_s *self, u64 *data) { - struct aq_vec_s *aq_vec = NULL; unsigned int i = 0U; unsigned int count = 0U; - int err = 0; + struct aq_vec_s *aq_vec = NULL; + struct aq_stats_s *stats = self->aq_hw_ops.hw_get_hw_stats(self->aq_hw); - err = self->aq_hw_ops.hw_get_hw_stats(self->aq_hw, data, &count); - if (err < 0) + if (!stats) goto err_exit; - data += count; + data[i] = stats->uprc + stats->mprc + stats->bprc; + data[++i] = stats->uprc; + data[++i] = stats->mprc; + data[++i] = stats->bprc; + data[++i] = stats->erpt; + data[++i] = stats->uptc + stats->mptc + stats->bptc; + data[++i] = stats->uptc; + data[++i] = stats->mptc; + data[++i] = stats->bptc; + data[++i] = stats->ubrc; + data[++i] = stats->ubtc; + data[++i] = stats->mbrc; + data[++i] = stats->mbtc; + data[++i] = stats->bbrc; + data[++i] = stats->bbtc; + data[++i] = stats->ubrc + stats->mbrc + stats->bbrc; + data[++i] = stats->ubtc + stats->mbtc + stats->bbtc; + data[++i] = stats->dma_pkt_rc; + data[++i] = stats->dma_pkt_tc; + data[++i] = stats->dma_oct_rc; + data[++i] = stats->dma_oct_tc; + data[++i] = stats->dpc; + + i++; + + data += i; count = 0U; for (i = 0U, aq_vec = self->aq_vec[0]; @@ -768,7 +783,20 @@ void aq_nic_get_stats(struct aq_nic_s *self, u64 *data) } err_exit:; - (void)err; +} + +static void aq_nic_update_ndev_stats(struct aq_nic_s *self) +{ + struct net_device *ndev = self->ndev; + struct aq_stats_s *stats = self->aq_hw_ops.hw_get_hw_stats(self->aq_hw); + + ndev->stats.rx_packets = stats->uprc + stats->mprc + stats->bprc; + ndev->stats.rx_bytes = stats->ubrc + stats->mbrc + stats->bbrc; + ndev->stats.rx_errors = stats->erpr; + ndev->stats.tx_packets = stats->uptc + stats->mptc + stats->bptc; + ndev->stats.tx_bytes = stats->ubtc + stats->mbtc + stats->bbtc; + ndev->stats.tx_errors = stats->erpt; + ndev->stats.multicast = stats->mprc; } void aq_nic_get_link_ksettings(struct aq_nic_s *self, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 4309983acdd6..3c9f8db03d5f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -71,7 +71,7 @@ struct aq_nic_cfg_s { struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, const struct ethtool_ops *et_ops, - struct device *dev, + struct pci_dev *pdev, struct aq_pci_func_s *aq_pci_func, unsigned int port, const struct aq_hw_ops *aq_hw_ops); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index cadaa646c89f..58c29d04b186 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -51,7 +51,8 @@ struct aq_pci_func_s *aq_pci_func_alloc(struct aq_hw_ops *aq_hw_ops, pci_set_drvdata(pdev, self); self->pdev = pdev; - err = aq_hw_ops->get_hw_caps(NULL, &self->aq_hw_caps); + err = aq_hw_ops->get_hw_caps(NULL, &self->aq_hw_caps, pdev->device, + pdev->subsystem_device); if (err < 0) goto err_exit; @@ -59,7 +60,7 @@ struct aq_pci_func_s *aq_pci_func_alloc(struct aq_hw_ops *aq_hw_ops, for (port = 0; port < self->ports; ++port) { struct aq_nic_s *aq_nic = aq_nic_alloc_cold(ndev_ops, eth_ops, - &pdev->dev, self, + pdev, self, port, aq_hw_ops); if (!aq_nic) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 07b3c49a16a4..f18dce14c93c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -18,9 +18,20 @@ #include "hw_atl_a0_internal.h" static int hw_atl_a0_get_hw_caps(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps) + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device) { memcpy(aq_hw_caps, &hw_atl_a0_hw_caps_, sizeof(*aq_hw_caps)); + + if (device == HW_ATL_DEVICE_ID_D108 && subsystem_device == 0x0001) + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_10G; + + if (device == HW_ATL_DEVICE_ID_D109 && subsystem_device == 0x0001) { + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_10G; + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_5G; + } + return 0; } @@ -333,6 +344,10 @@ static int hw_atl_a0_hw_init(struct aq_hw_s *self, hw_atl_a0_hw_rss_set(self, &aq_nic_cfg->aq_rss); hw_atl_a0_hw_rss_hash_set(self, &aq_nic_cfg->aq_rss); + /* Reset link status and read out initial hardware counters */ + self->aq_link_status.mbps = 0; + hw_atl_utils_update_stats(self); + err = aq_hw_err_from_flags(self); if (err < 0) goto err_exit; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index ec68c20efcbd..e4a22ce7bf09 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -16,11 +16,23 @@ #include "hw_atl_utils.h" #include "hw_atl_llh.h" #include "hw_atl_b0_internal.h" +#include "hw_atl_llh_internal.h" static int hw_atl_b0_get_hw_caps(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps) + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device) { memcpy(aq_hw_caps, &hw_atl_b0_hw_caps_, sizeof(*aq_hw_caps)); + + if (device == HW_ATL_DEVICE_ID_D108 && subsystem_device == 0x0001) + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_10G; + + if (device == HW_ATL_DEVICE_ID_D109 && subsystem_device == 0x0001) { + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_10G; + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_5G; + } + return 0; } @@ -357,6 +369,7 @@ static int hw_atl_b0_hw_init(struct aq_hw_s *self, }; int err = 0; + u32 val; self->aq_nic_cfg = aq_nic_cfg; @@ -374,6 +387,20 @@ static int hw_atl_b0_hw_init(struct aq_hw_s *self, hw_atl_b0_hw_rss_set(self, &aq_nic_cfg->aq_rss); hw_atl_b0_hw_rss_hash_set(self, &aq_nic_cfg->aq_rss); + /* Force limit MRRS on RDM/TDM to 2K */ + val = aq_hw_read_reg(self, pci_reg_control6_adr); + aq_hw_write_reg(self, pci_reg_control6_adr, (val & ~0x707) | 0x404); + + /* TX DMA total request limit. B0 hardware is not capable to + * handle more than (8K-MRRS) incoming DMA data. + * Value 24 in 256byte units + */ + aq_hw_write_reg(self, tx_dma_total_req_limit_adr, 24); + + /* Reset link status and read out initial hardware counters */ + self->aq_link_status.mbps = 0; + hw_atl_utils_update_stats(self); + err = aq_hw_err_from_flags(self); if (err < 0) goto err_exit; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 5527fc0e5942..93450ec930e8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -2343,6 +2343,9 @@ #define tx_dma_desc_base_addrmsw_adr(descriptor) \ (0x00007c04u + (descriptor) * 0x40) +/* tx dma total request limit */ +#define tx_dma_total_req_limit_adr 0x00007b20u + /* tx interrupt moderation control register definitions * Preprocessor definitions for TX Interrupt Moderation Control Register * Base Address: 0x00008980 @@ -2369,6 +2372,9 @@ /* default value of bitfield reg_res_dsbl */ #define pci_reg_res_dsbl_default 0x1 +/* PCI core control register */ +#define pci_reg_control6_adr 0x1014u + /* global microprocessor scratch pad definitions */ #define glb_cpu_scratch_scp_adr(scratch_scp) (0x00000300u + (scratch_scp) * 0x4) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 1fe016fc4bc7..f2ce12ed4218 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -503,73 +503,43 @@ int hw_atl_utils_update_stats(struct aq_hw_s *self) struct hw_atl_s *hw_self = PHAL_ATLANTIC; struct hw_aq_atl_utils_mbox mbox; - if (!self->aq_link_status.mbps) - return 0; - hw_atl_utils_mpi_read_stats(self, &mbox); #define AQ_SDELTA(_N_) (hw_self->curr_stats._N_ += \ mbox.stats._N_ - hw_self->last_stats._N_) - - AQ_SDELTA(uprc); - AQ_SDELTA(mprc); - AQ_SDELTA(bprc); - AQ_SDELTA(erpt); - - AQ_SDELTA(uptc); - AQ_SDELTA(mptc); - AQ_SDELTA(bptc); - AQ_SDELTA(erpr); - - AQ_SDELTA(ubrc); - AQ_SDELTA(ubtc); - AQ_SDELTA(mbrc); - AQ_SDELTA(mbtc); - AQ_SDELTA(bbrc); - AQ_SDELTA(bbtc); - AQ_SDELTA(dpc); - + if (self->aq_link_status.mbps) { + AQ_SDELTA(uprc); + AQ_SDELTA(mprc); + AQ_SDELTA(bprc); + AQ_SDELTA(erpt); + + AQ_SDELTA(uptc); + AQ_SDELTA(mptc); + AQ_SDELTA(bptc); + AQ_SDELTA(erpr); + + AQ_SDELTA(ubrc); + AQ_SDELTA(ubtc); + AQ_SDELTA(mbrc); + AQ_SDELTA(mbtc); + AQ_SDELTA(bbrc); + AQ_SDELTA(bbtc); + AQ_SDELTA(dpc); + } #undef AQ_SDELTA + hw_self->curr_stats.dma_pkt_rc = stats_rx_dma_good_pkt_counterlsw_get(self); + hw_self->curr_stats.dma_pkt_tc = stats_tx_dma_good_pkt_counterlsw_get(self); + hw_self->curr_stats.dma_oct_rc = stats_rx_dma_good_octet_counterlsw_get(self); + hw_self->curr_stats.dma_oct_tc = stats_tx_dma_good_octet_counterlsw_get(self); memcpy(&hw_self->last_stats, &mbox.stats, sizeof(mbox.stats)); return 0; } -int hw_atl_utils_get_hw_stats(struct aq_hw_s *self, - u64 *data, unsigned int *p_count) +struct aq_stats_s *hw_atl_utils_get_hw_stats(struct aq_hw_s *self) { - struct hw_atl_s *hw_self = PHAL_ATLANTIC; - struct hw_atl_stats_s *stats = &hw_self->curr_stats; - int i = 0; - - data[i] = stats->uprc + stats->mprc + stats->bprc; - data[++i] = stats->uprc; - data[++i] = stats->mprc; - data[++i] = stats->bprc; - data[++i] = stats->erpt; - data[++i] = stats->uptc + stats->mptc + stats->bptc; - data[++i] = stats->uptc; - data[++i] = stats->mptc; - data[++i] = stats->bptc; - data[++i] = stats->ubrc; - data[++i] = stats->ubtc; - data[++i] = stats->mbrc; - data[++i] = stats->mbtc; - data[++i] = stats->bbrc; - data[++i] = stats->bbtc; - data[++i] = stats->ubrc + stats->mbrc + stats->bbrc; - data[++i] = stats->ubtc + stats->mbtc + stats->bbtc; - data[++i] = stats_rx_dma_good_pkt_counterlsw_get(self); - data[++i] = stats_tx_dma_good_pkt_counterlsw_get(self); - data[++i] = stats_rx_dma_good_octet_counterlsw_get(self); - data[++i] = stats_tx_dma_good_octet_counterlsw_get(self); - data[++i] = stats->dpc; - - if (p_count) - *p_count = ++i; - - return 0; + return &PHAL_ATLANTIC->curr_stats; } static const u32 hw_atl_utils_hw_mac_regs[] = { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index c99cc690e425..21aeca6908d3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -129,7 +129,7 @@ struct __packed hw_aq_atl_utils_mbox { struct __packed hw_atl_s { struct aq_hw_s base; struct hw_atl_stats_s last_stats; - struct hw_atl_stats_s curr_stats; + struct aq_stats_s curr_stats; u64 speed; unsigned int chip_features; u32 fw_ver_actual; @@ -207,8 +207,6 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version); int hw_atl_utils_update_stats(struct aq_hw_s *self); -int hw_atl_utils_get_hw_stats(struct aq_hw_s *self, - u64 *data, - unsigned int *p_count); +struct aq_stats_s *hw_atl_utils_get_hw_stats(struct aq_hw_s *self); #endif /* HW_ATL_UTILS_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h index 0de858d215c2..9009f2651e70 100644 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ b/drivers/net/ethernet/aquantia/atlantic/ver.h @@ -11,8 +11,10 @@ #define VER_H #define NIC_MAJOR_DRIVER_VERSION 1 -#define NIC_MINOR_DRIVER_VERSION 5 -#define NIC_BUILD_DRIVER_VERSION 345 +#define NIC_MINOR_DRIVER_VERSION 6 +#define NIC_BUILD_DRIVER_VERSION 13 #define NIC_REVISION_DRIVER_VERSION 0 +#define AQ_CFG_DRV_VERSION_SUFFIX "-kern" + #endif /* VER_H */ diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index c6163874e4e7..16f9bee992fe 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -199,9 +199,11 @@ static int emac_rockchip_probe(struct platform_device *pdev) /* RMII interface needs always a rate of 50MHz */ err = clk_set_rate(priv->refclk, 50000000); - if (err) + if (err) { dev_err(dev, "failed to change reference clock rate (%d)\n", err); + goto out_regulator_disable; + } if (priv->soc_data->need_div_macclk) { priv->macclk = devm_clk_get(dev, "macclk"); @@ -230,12 +232,14 @@ static int emac_rockchip_probe(struct platform_device *pdev) err = arc_emac_probe(ndev, interface); if (err) { dev_err(dev, "failed to probe arc emac (%d)\n", err); - goto out_regulator_disable; + goto out_clk_disable_macclk; } return 0; + out_clk_disable_macclk: - clk_disable_unprepare(priv->macclk); + if (priv->soc_data->need_div_macclk) + clk_disable_unprepare(priv->macclk); out_regulator_disable: if (priv->regulator) regulator_disable(priv->regulator); diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 6e423f098a60..31efc47c847e 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -4081,7 +4081,6 @@ static void skge_remove(struct pci_dev *pdev) if (hw->ports > 1) { skge_write32(hw, B0_IMSK, 0); skge_read32(hw, B0_IMSK); - free_irq(pdev->irq, hw); } spin_unlock_irq(&hw->hw_lock); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index e0eb695318e6..1fa4849a6f56 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -188,7 +188,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) struct net_device *dev = mdev->pndev[port]; struct mlx4_en_priv *priv = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; - struct mlx4_cmd_mailbox *mailbox; + struct mlx4_cmd_mailbox *mailbox, *mailbox_priority; u64 in_mod = reset << 8 | port; int err; int i, counter_index; @@ -198,6 +198,13 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) mailbox = mlx4_alloc_cmd_mailbox(mdev->dev); if (IS_ERR(mailbox)) return PTR_ERR(mailbox); + + mailbox_priority = mlx4_alloc_cmd_mailbox(mdev->dev); + if (IS_ERR(mailbox_priority)) { + mlx4_free_cmd_mailbox(mdev->dev, mailbox); + return PTR_ERR(mailbox_priority); + } + err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0, MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); @@ -206,6 +213,28 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) mlx4_en_stats = mailbox->buf; + memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats)); + counter_index = mlx4_get_default_counter_index(mdev->dev, port); + err = mlx4_get_counter_stats(mdev->dev, counter_index, + &tmp_counter_stats, reset); + + /* 0xffs indicates invalid value */ + memset(mailbox_priority->buf, 0xff, + sizeof(*flowstats) * MLX4_NUM_PRIORITIES); + + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN) { + memset(mailbox_priority->buf, 0, + sizeof(*flowstats) * MLX4_NUM_PRIORITIES); + err = mlx4_cmd_box(mdev->dev, 0, mailbox_priority->dma, + in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL, + 0, MLX4_CMD_DUMP_ETH_STATS, + MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); + if (err) + goto out; + } + + flowstats = mailbox_priority->buf; + spin_lock_bh(&priv->stats_lock); mlx4_en_fold_software_stats(dev); @@ -345,31 +374,6 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->pkstats.tx_prio[8][0] = be64_to_cpu(mlx4_en_stats->TTOT_novlan); priv->pkstats.tx_prio[8][1] = be64_to_cpu(mlx4_en_stats->TOCT_novlan); - spin_unlock_bh(&priv->stats_lock); - - memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats)); - counter_index = mlx4_get_default_counter_index(mdev->dev, port); - err = mlx4_get_counter_stats(mdev->dev, counter_index, - &tmp_counter_stats, reset); - - /* 0xffs indicates invalid value */ - memset(mailbox->buf, 0xff, sizeof(*flowstats) * MLX4_NUM_PRIORITIES); - - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN) { - memset(mailbox->buf, 0, - sizeof(*flowstats) * MLX4_NUM_PRIORITIES); - err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, - in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL, - 0, MLX4_CMD_DUMP_ETH_STATS, - MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); - if (err) - goto out; - } - - flowstats = mailbox->buf; - - spin_lock_bh(&priv->stats_lock); - if (tmp_counter_stats.counter_mode == 0) { priv->pf_stats.rx_bytes = be64_to_cpu(tmp_counter_stats.rx_bytes); priv->pf_stats.tx_bytes = be64_to_cpu(tmp_counter_stats.tx_bytes); @@ -410,6 +414,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) out: mlx4_free_cmd_mailbox(mdev->dev, mailbox); + mlx4_free_cmd_mailbox(mdev->dev, mailbox_priority); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index 88699b181946..946d9db7c8c2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -185,7 +185,7 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf) if (priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UC_LOOPBACK) { buf[3] = mlx4_en_test_registers(priv); - if (priv->port_up) + if (priv->port_up && dev->mtu >= MLX4_SELFTEST_LB_MIN_MTU) buf[4] = mlx4_en_test_loopback(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 1856e279a7e0..2b72677eccd4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -153,6 +153,9 @@ #define SMALL_PACKET_SIZE (256 - NET_IP_ALIGN) #define HEADER_COPY_SIZE (128 - NET_IP_ALIGN) #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN) +#define PREAMBLE_LEN 8 +#define MLX4_SELFTEST_LB_MIN_MTU (MLX4_LOOPBACK_TEST_PAYLOAD + NET_IP_ALIGN + \ + ETH_HLEN + PREAMBLE_LEN) #define MLX4_EN_MIN_MTU 46 /* VLAN_HLEN is added twice,to support skb vlan tagged with multiple diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 04304dd894c6..606a0e0beeae 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -611,7 +611,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) MLX4_MAX_PORTS; else res_alloc->guaranteed[t] = 0; - res_alloc->res_free -= res_alloc->guaranteed[t]; break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 2d0897b7d860..9bd8d28de152 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4300,6 +4300,7 @@ static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port) { + u16 vid = 1; int err; err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true); @@ -4312,8 +4313,19 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port) true, false); if (err) goto err_port_vlan_set; + + for (; vid <= VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, + vid, false); + if (err) + goto err_vid_learning_set; + } + return 0; +err_vid_learning_set: + for (vid--; vid >= 1; vid--) + mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); err_port_vlan_set: mlxsw_sp_port_stp_set(mlxsw_sp_port, false); err_port_stp_set: @@ -4323,6 +4335,12 @@ err_port_stp_set: static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port) { + u16 vid; + + for (vid = VLAN_N_VID - 1; vid >= 1; vid--) + mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, + vid, true); + mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1, false, false); mlxsw_sp_port_stp_set(mlxsw_sp_port, false); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c index 18461fcb9815..53dbf1e163a8 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c @@ -47,6 +47,7 @@ #define MDIO_CLK_25_28 7 #define MDIO_WAIT_TIMES 1000 +#define MDIO_STATUS_DELAY_TIME 1 static int emac_mdio_read(struct mii_bus *bus, int addr, int regnum) { @@ -65,7 +66,7 @@ static int emac_mdio_read(struct mii_bus *bus, int addr, int regnum) if (readl_poll_timeout(adpt->base + EMAC_MDIO_CTRL, reg, !(reg & (MDIO_START | MDIO_BUSY)), - 100, MDIO_WAIT_TIMES * 100)) + MDIO_STATUS_DELAY_TIME, MDIO_WAIT_TIMES * 100)) return -EIO; return (reg >> MDIO_DATA_SHFT) & MDIO_DATA_BMSK; @@ -88,8 +89,8 @@ static int emac_mdio_write(struct mii_bus *bus, int addr, int regnum, u16 val) writel(reg, adpt->base + EMAC_MDIO_CTRL); if (readl_poll_timeout(adpt->base + EMAC_MDIO_CTRL, reg, - !(reg & (MDIO_START | MDIO_BUSY)), 100, - MDIO_WAIT_TIMES * 100)) + !(reg & (MDIO_START | MDIO_BUSY)), + MDIO_STATUS_DELAY_TIME, MDIO_WAIT_TIMES * 100)) return -EIO; return 0; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 2b962d349f5f..009780df664b 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2308,32 +2308,9 @@ static int __maybe_unused ravb_resume(struct device *dev) struct ravb_private *priv = netdev_priv(ndev); int ret = 0; - if (priv->wol_enabled) { - /* Reduce the usecount of the clock to zero and then - * restore it to its original value. This is done to force - * the clock to be re-enabled which is a workaround - * for renesas-cpg-mssr driver which do not enable clocks - * when resuming from PSCI suspend/resume. - * - * Without this workaround the driver fails to communicate - * with the hardware if WoL was enabled when the system - * entered PSCI suspend. This is due to that if WoL is enabled - * we explicitly keep the clock from being turned off when - * suspending, but in PSCI sleep power is cut so the clock - * is disabled anyhow, the clock driver is not aware of this - * so the clock is not turned back on when resuming. - * - * TODO: once the renesas-cpg-mssr suspend/resume is working - * this clock dance should be removed. - */ - clk_disable(priv->clk); - clk_disable(priv->clk); - clk_enable(priv->clk); - clk_enable(priv->clk); - - /* Set reset mode to rearm the WoL logic */ + /* If WoL is enabled set reset mode to rearm the WoL logic */ + if (priv->wol_enabled) ravb_write(ndev, CCC_OPC_RESET, CCC); - } /* All register have been reset to default values. * Restore all registers which where setup at probe time and diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index db72d13cebb9..75323000c364 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1892,6 +1892,16 @@ static int sh_eth_phy_init(struct net_device *ndev) return PTR_ERR(phydev); } + /* mask with MAC supported features */ + if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) { + int err = phy_set_max_speed(phydev, SPEED_100); + if (err) { + netdev_err(ndev, "failed to limit PHY to 100 Mbit/s\n"); + phy_disconnect(phydev); + return err; + } + } + phy_attached_info(phydev); return 0; diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 8483f03d5a41..1ab97d99b9ba 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1379,8 +1379,8 @@ static int rr_close(struct net_device *dev) rrpriv->info_dma); rrpriv->info = NULL; - free_irq(pdev->irq, dev); spin_unlock_irqrestore(&rrpriv->lock, flags); + free_irq(pdev->irq, dev); return 0; } diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 5f93e6add563..e911e4990b20 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -239,14 +239,10 @@ static int at803x_resume(struct phy_device *phydev) { int value; - mutex_lock(&phydev->lock); - value = phy_read(phydev, MII_BMCR); value &= ~(BMCR_PDOWN | BMCR_ISOLATE); phy_write(phydev, MII_BMCR, value); - mutex_unlock(&phydev->lock); - return 0; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 4d02b27df044..b5a8f750e433 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -637,6 +637,10 @@ static int m88e1510_config_aneg(struct phy_device *phydev) if (err < 0) goto error; + /* Do not touch the fiber page if we're in copper->sgmii mode */ + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) + return 0; + /* Then the fiber link */ err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE); if (err < 0) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 2df7b62c1a36..54d00a1d2bef 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -270,6 +270,7 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus, if (addr == mdiodev->addr) { dev->of_node = child; + dev->fwnode = of_fwnode_handle(child); return; } } diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 1ea69b7585d9..842eb871a6e3 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -22,6 +22,7 @@ #include <linux/ethtool.h> #include <linux/phy.h> #include <linux/netdevice.h> +#include <linux/bitfield.h> static int meson_gxl_config_init(struct phy_device *phydev) { @@ -50,6 +51,77 @@ static int meson_gxl_config_init(struct phy_device *phydev) return 0; } +/* This function is provided to cope with the possible failures of this phy + * during aneg process. When aneg fails, the PHY reports that aneg is done + * but the value found in MII_LPA is wrong: + * - Early failures: MII_LPA is just 0x0001. if MII_EXPANSION reports that + * the link partner (LP) supports aneg but the LP never acked our base + * code word, it is likely that we never sent it to begin with. + * - Late failures: MII_LPA is filled with a value which seems to make sense + * but it actually is not what the LP is advertising. It seems that we + * can detect this using a magic bit in the WOL bank (reg 12 - bit 12). + * If this particular bit is not set when aneg is reported being done, + * it means MII_LPA is likely to be wrong. + * + * In both case, forcing a restart of the aneg process solve the problem. + * When this failure happens, the first retry is usually successful but, + * in some cases, it may take up to 6 retries to get a decent result + */ +static int meson_gxl_read_status(struct phy_device *phydev) +{ + int ret, wol, lpa, exp; + + if (phydev->autoneg == AUTONEG_ENABLE) { + ret = genphy_aneg_done(phydev); + if (ret < 0) + return ret; + else if (!ret) + goto read_status_continue; + + /* Need to access WOL bank, make sure the access is open */ + ret = phy_write(phydev, 0x14, 0x0000); + if (ret) + return ret; + ret = phy_write(phydev, 0x14, 0x0400); + if (ret) + return ret; + ret = phy_write(phydev, 0x14, 0x0000); + if (ret) + return ret; + ret = phy_write(phydev, 0x14, 0x0400); + if (ret) + return ret; + + /* Request LPI_STATUS WOL register */ + ret = phy_write(phydev, 0x14, 0x8D80); + if (ret) + return ret; + + /* Read LPI_STATUS value */ + wol = phy_read(phydev, 0x15); + if (wol < 0) + return wol; + + lpa = phy_read(phydev, MII_LPA); + if (lpa < 0) + return lpa; + + exp = phy_read(phydev, MII_EXPANSION); + if (exp < 0) + return exp; + + if (!(wol & BIT(12)) || + ((exp & EXPANSION_NWAY) && !(lpa & LPA_LPACK))) { + /* Looks like aneg failed after all */ + phydev_dbg(phydev, "LPA corruption - aneg restart\n"); + return genphy_restart_aneg(phydev); + } + } + +read_status_continue: + return genphy_read_status(phydev); +} + static struct phy_driver meson_gxl_phy[] = { { .phy_id = 0x01814400, @@ -60,7 +132,7 @@ static struct phy_driver meson_gxl_phy[] = { .config_init = meson_gxl_config_init, .config_aneg = genphy_config_aneg, .aneg_done = genphy_aneg_done, - .read_status = genphy_read_status, + .read_status = meson_gxl_read_status, .suspend = genphy_suspend, .resume = genphy_resume, }, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 2b1e67bc1e73..ed10d1fc8f59 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -828,7 +828,6 @@ EXPORT_SYMBOL(phy_stop); */ void phy_start(struct phy_device *phydev) { - bool do_resume = false; int err = 0; mutex_lock(&phydev->lock); @@ -841,6 +840,9 @@ void phy_start(struct phy_device *phydev) phydev->state = PHY_UP; break; case PHY_HALTED: + /* if phy was suspended, bring the physical link up again */ + phy_resume(phydev); + /* make sure interrupts are re-enabled for the PHY */ if (phydev->irq != PHY_POLL) { err = phy_enable_interrupts(phydev); @@ -849,17 +851,12 @@ void phy_start(struct phy_device *phydev) } phydev->state = PHY_RESUMING; - do_resume = true; break; default: break; } mutex_unlock(&phydev->lock); - /* if phy was suspended, bring the physical link up again */ - if (do_resume) - phy_resume(phydev); - phy_trigger_machine(phydev, true); } EXPORT_SYMBOL(phy_start); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 67f25ac29025..b15b31ca2618 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -135,7 +135,9 @@ static int mdio_bus_phy_resume(struct device *dev) if (!mdio_bus_phy_may_suspend(phydev)) goto no_resume; + mutex_lock(&phydev->lock); ret = phy_resume(phydev); + mutex_unlock(&phydev->lock); if (ret < 0) return ret; @@ -1026,7 +1028,9 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (err) goto error; + mutex_lock(&phydev->lock); phy_resume(phydev); + mutex_unlock(&phydev->lock); phy_led_triggers_register(phydev); return err; @@ -1157,6 +1161,8 @@ int phy_resume(struct phy_device *phydev) struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver); int ret = 0; + WARN_ON(!mutex_is_locked(&phydev->lock)); + if (phydev->drv && phydrv->resume) ret = phydrv->resume(phydev); @@ -1639,13 +1645,9 @@ int genphy_resume(struct phy_device *phydev) { int value; - mutex_lock(&phydev->lock); - value = phy_read(phydev, MII_BMCR); phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); - mutex_unlock(&phydev->lock); - return 0; } EXPORT_SYMBOL(genphy_resume); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 304ec6555cd8..3000ddd1c7e2 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1204,12 +1204,14 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ + {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ {QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */ diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 98258583abb0..3481e69738b5 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -81,6 +81,7 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, * can be looked up later */ of_node_get(child); phy->mdio.dev.of_node = child; + phy->mdio.dev.fwnode = of_fwnode_handle(child); /* All data is now stored in the phy struct; * register it */ @@ -111,6 +112,7 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, */ of_node_get(child); mdiodev->dev.of_node = child; + mdiodev->dev.fwnode = of_fwnode_handle(child); /* All data is now stored in the mdiodev struct; register it. */ rc = mdio_device_register(mdiodev); @@ -206,6 +208,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) mdio->phy_mask = ~0; mdio->dev.of_node = np; + mdio->dev.fwnode = of_fwnode_handle(np); /* Get bus level PHY reset GPIO details */ mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY; diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index a25fed52f7e9..41b740aed3a3 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -1692,3 +1692,36 @@ void lba_set_iregs(struct parisc_device *lba, u32 ibase, u32 imask) iounmap(base_addr); } + +/* + * The design of the Diva management card in rp34x0 machines (rp3410, rp3440) + * seems rushed, so that many built-in components simply don't work. + * The following quirks disable the serial AUX port and the built-in ATI RV100 + * Radeon 7000 graphics card which both don't have any external connectors and + * thus are useless, and even worse, e.g. the AUX port occupies ttyS0 and as + * such makes those machines the only PARISC machines on which we can't use + * ttyS0 as boot console. + */ +static void quirk_diva_ati_card(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1292) + return; + + dev_info(&dev->dev, "Hiding Diva built-in ATI card"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RADEON_QY, + quirk_diva_ati_card); + +static void quirk_diva_aux_disable(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1291) + return; + + dev_info(&dev->dev, "Hiding Diva built-in AUX serial device"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX, + quirk_diva_aux_disable); 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..14fd865a5120 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; } @@ -1012,7 +1012,12 @@ static int pci_pm_thaw_noirq(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); - pci_update_current_state(pci_dev, PCI_D0); + /* + * pci_restore_state() requires the device to be in D0 (because of MSI + * restoration among other things), so force it into D0 in case the + * driver's "freeze" callbacks put it into a low-power state directly. + */ + pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); if (drv && drv->pm && drv->pm->thaw_noirq) 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/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 15015a24f8ad..badf42acbf95 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -565,9 +565,9 @@ enum qeth_cq { }; struct qeth_ipato { - int enabled; - int invert4; - int invert6; + bool enabled; + bool invert4; + bool invert6; struct list_head entries; }; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 430e3214f7e2..6c815207f4f5 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1480,9 +1480,9 @@ static int qeth_setup_card(struct qeth_card *card) qeth_set_intial_options(card); /* IP address takeover */ INIT_LIST_HEAD(&card->ipato.entries); - card->ipato.enabled = 0; - card->ipato.invert4 = 0; - card->ipato.invert6 = 0; + card->ipato.enabled = false; + card->ipato.invert4 = false; + card->ipato.invert6 = false; /* init QDIO stuff */ qeth_init_qdio_info(card); INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work); diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h index 194ae9b577cc..e5833837b799 100644 --- a/drivers/s390/net/qeth_l3.h +++ b/drivers/s390/net/qeth_l3.h @@ -82,7 +82,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *); int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *); void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions, const u8 *); -int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *); +void qeth_l3_update_ipato(struct qeth_card *card); struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions); int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *); int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 6a73894b0cb5..ef0961e18686 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -164,8 +164,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len) } } -int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card, - struct qeth_ipaddr *addr) +static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card, + struct qeth_ipaddr *addr) { struct qeth_ipato_entry *ipatoe; u8 addr_bits[128] = {0, }; @@ -174,6 +174,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card, if (!card->ipato.enabled) return 0; + if (addr->type != QETH_IP_TYPE_NORMAL) + return 0; qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits, (addr->proto == QETH_PROT_IPV4)? 4:16); @@ -290,8 +292,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr)); addr->ref_counter = 1; - if (addr->type == QETH_IP_TYPE_NORMAL && - qeth_l3_is_addr_covered_by_ipato(card, addr)) { + if (qeth_l3_is_addr_covered_by_ipato(card, addr)) { QETH_CARD_TEXT(card, 2, "tkovaddr"); addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG; } @@ -605,6 +606,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card) /* * IP address takeover related functions */ + +/** + * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs. + * + * Caller must hold ip_lock. + */ +void qeth_l3_update_ipato(struct qeth_card *card) +{ + struct qeth_ipaddr *addr; + unsigned int i; + + hash_for_each(card->ip_htable, i, addr, hnode) { + if (addr->type != QETH_IP_TYPE_NORMAL) + continue; + if (qeth_l3_is_addr_covered_by_ipato(card, addr)) + addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG; + else + addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG; + } +} + static void qeth_l3_clear_ipato_list(struct qeth_card *card) { struct qeth_ipato_entry *ipatoe, *tmp; @@ -616,6 +638,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card) kfree(ipatoe); } + qeth_l3_update_ipato(card); spin_unlock_bh(&card->ip_lock); } @@ -640,8 +663,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card, } } - if (!rc) + if (!rc) { list_add_tail(&new->entry, &card->ipato.entries); + qeth_l3_update_ipato(card); + } spin_unlock_bh(&card->ip_lock); @@ -664,6 +689,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card, (proto == QETH_PROT_IPV4)? 4:16) && (ipatoe->mask_bits == mask_bits)) { list_del(&ipatoe->entry); + qeth_l3_update_ipato(card); kfree(ipatoe); } } diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index bd12fdf678be..6ea2b528a64e 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -370,8 +370,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); - struct qeth_ipaddr *addr; - int i, rc = 0; + bool enable; + int rc = 0; if (!card) return -EINVAL; @@ -384,25 +384,18 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev, } if (sysfs_streq(buf, "toggle")) { - card->ipato.enabled = (card->ipato.enabled)? 0 : 1; - } else if (sysfs_streq(buf, "1")) { - card->ipato.enabled = 1; - hash_for_each(card->ip_htable, i, addr, hnode) { - if ((addr->type == QETH_IP_TYPE_NORMAL) && - qeth_l3_is_addr_covered_by_ipato(card, addr)) - addr->set_flags |= - QETH_IPA_SETIP_TAKEOVER_FLAG; - } - } else if (sysfs_streq(buf, "0")) { - card->ipato.enabled = 0; - hash_for_each(card->ip_htable, i, addr, hnode) { - if (addr->set_flags & - QETH_IPA_SETIP_TAKEOVER_FLAG) - addr->set_flags &= - ~QETH_IPA_SETIP_TAKEOVER_FLAG; - } - } else + enable = !card->ipato.enabled; + } else if (kstrtobool(buf, &enable)) { rc = -EINVAL; + goto out; + } + + if (card->ipato.enabled != enable) { + card->ipato.enabled = enable; + spin_lock_bh(&card->ip_lock); + qeth_l3_update_ipato(card); + spin_unlock_bh(&card->ip_lock); + } out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -428,20 +421,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + bool invert; int rc = 0; if (!card) return -EINVAL; mutex_lock(&card->conf_mutex); - if (sysfs_streq(buf, "toggle")) - card->ipato.invert4 = (card->ipato.invert4)? 0 : 1; - else if (sysfs_streq(buf, "1")) - card->ipato.invert4 = 1; - else if (sysfs_streq(buf, "0")) - card->ipato.invert4 = 0; - else + if (sysfs_streq(buf, "toggle")) { + invert = !card->ipato.invert4; + } else if (kstrtobool(buf, &invert)) { rc = -EINVAL; + goto out; + } + + if (card->ipato.invert4 != invert) { + card->ipato.invert4 = invert; + spin_lock_bh(&card->ip_lock); + qeth_l3_update_ipato(card); + spin_unlock_bh(&card->ip_lock); + } +out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; } @@ -607,20 +607,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + bool invert; int rc = 0; if (!card) return -EINVAL; mutex_lock(&card->conf_mutex); - if (sysfs_streq(buf, "toggle")) - card->ipato.invert6 = (card->ipato.invert6)? 0 : 1; - else if (sysfs_streq(buf, "1")) - card->ipato.invert6 = 1; - else if (sysfs_streq(buf, "0")) - card->ipato.invert6 = 0; - else + if (sysfs_streq(buf, "toggle")) { + invert = !card->ipato.invert6; + } else if (kstrtobool(buf, &invert)) { rc = -EINVAL; + goto out; + } + + if (card->ipato.invert6 != invert) { + card->ipato.invert6 = invert; + spin_lock_bh(&card->ip_lock); + qeth_l3_update_ipato(card); + spin_unlock_bh(&card->ip_lock); + } +out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; } diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 6e3d81969a77..d52265416da2 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1725,6 +1725,7 @@ struct aac_dev #define FIB_CONTEXT_FLAG_NATIVE_HBA (0x00000010) #define FIB_CONTEXT_FLAG_NATIVE_HBA_TMF (0x00000020) #define FIB_CONTEXT_FLAG_SCSI_CMD (0x00000040) +#define FIB_CONTEXT_FLAG_EH_RESET (0x00000080) /* * Define the command values 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/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index bdf127aaab41..d55332de08f9 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1037,7 +1037,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd) info = &aac->hba_map[bus][cid]; if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || info->devtype != AAC_DEVTYPE_NATIVE_RAW) { - fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT; + fib->flags |= FIB_CONTEXT_FLAG_EH_RESET; cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER; } } 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..dfb8da83fa50 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", @@ -382,10 +374,8 @@ int scsi_dev_info_list_add_keyed(int compatible, char *vendor, char *model, model, compatible); if (strflags) - devinfo->flags = simple_strtoul(strflags, NULL, 0); - else - devinfo->flags = flags; - + flags = (__force blist_flags_t)simple_strtoul(strflags, NULL, 0); + devinfo->flags = flags; devinfo->compatible = compatible; if (compatible) @@ -458,7 +448,8 @@ 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 +457,7 @@ 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/scsi_scan.c b/drivers/scsi/scsi_scan.c index be5e919db0e8..0880d975eed3 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -770,7 +770,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result, * SCSI_SCAN_LUN_PRESENT: a new scsi_device was allocated and initialized **/ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, - int *bflags, int async) + blist_flags_t *bflags, int async) { int ret; @@ -1049,14 +1049,15 @@ static unsigned char *scsi_inq_str(unsigned char *buf, unsigned char *inq, * - SCSI_SCAN_LUN_PRESENT: a new scsi_device was allocated and initialized **/ static int scsi_probe_and_add_lun(struct scsi_target *starget, - u64 lun, int *bflagsp, + u64 lun, blist_flags_t *bflagsp, struct scsi_device **sdevp, enum scsi_scan_mode rescan, void *hostdata) { struct scsi_device *sdev; unsigned char *result; - int bflags, res = SCSI_SCAN_NO_RESPONSE, result_len = 256; + blist_flags_t bflags; + int res = SCSI_SCAN_NO_RESPONSE, result_len = 256; struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); /* @@ -1201,7 +1202,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * Modifies sdevscan->lun. **/ static void scsi_sequential_lun_scan(struct scsi_target *starget, - int bflags, int scsi_level, + blist_flags_t bflags, int scsi_level, enum scsi_scan_mode rescan) { uint max_dev_lun; @@ -1292,7 +1293,7 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, * 0: scan completed (or no memory, so further scanning is futile) * 1: could not scan with REPORT LUN **/ -static int scsi_report_lun_scan(struct scsi_target *starget, int bflags, +static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflags, enum scsi_scan_mode rescan) { unsigned char scsi_cmd[MAX_COMMAND_SIZE]; @@ -1538,7 +1539,7 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel, unsigned int id, u64 lun, enum scsi_scan_mode rescan) { struct Scsi_Host *shost = dev_to_shost(parent); - int bflags = 0; + blist_flags_t bflags = 0; int res; struct scsi_target *starget; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 50e7d7e4a861..a9996c16f4ae 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -967,7 +967,8 @@ sdev_show_wwid(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(wwid, S_IRUGO, sdev_show_wwid, NULL); -#define BLIST_FLAG_NAME(name) [ilog2(BLIST_##name)] = #name +#define BLIST_FLAG_NAME(name) \ + [ilog2((__force unsigned int)BLIST_##name)] = #name static const char *const sdev_bflags_name[] = { #include "scsi_devinfo_tbl.c" }; @@ -984,7 +985,7 @@ sdev_show_blacklist(struct device *dev, struct device_attribute *attr, for (i = 0; i < sizeof(sdev->sdev_bflags) * BITS_PER_BYTE; i++) { const char *name = NULL; - if (!(sdev->sdev_bflags & BIT(i))) + if (!(sdev->sdev_bflags & (__force blist_flags_t)BIT(i))) continue; if (i < ARRAY_SIZE(sdev_bflags_name) && sdev_bflags_name[i]) name = sdev_bflags_name[i]; diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c index d0219e36080c..10ebb213ddb3 100644 --- a/drivers/scsi/scsi_transport_spi.c +++ b/drivers/scsi/scsi_transport_spi.c @@ -50,14 +50,14 @@ /* Our blacklist flags */ enum { - SPI_BLIST_NOIUS = 0x1, + SPI_BLIST_NOIUS = (__force blist_flags_t)0x1, }; /* blacklist table, modelled on scsi_devinfo.c */ static struct { char *vendor; char *model; - unsigned flags; + blist_flags_t flags; } spi_static_device_list[] __initdata = { {"HP", "Ultrium 3-SCSI", SPI_BLIST_NOIUS }, {"IBM", "ULTRIUM-TD3", SPI_BLIST_NOIUS }, @@ -221,9 +221,11 @@ static int spi_device_configure(struct transport_container *tc, { struct scsi_device *sdev = to_scsi_device(dev); struct scsi_target *starget = sdev->sdev_target; - unsigned bflags = scsi_get_device_flags_keyed(sdev, &sdev->inquiry[8], - &sdev->inquiry[16], - SCSI_DEVINFO_SPI); + blist_flags_t bflags; + + bflags = scsi_get_device_flags_keyed(sdev, &sdev->inquiry[8], + &sdev->inquiry[16], + SCSI_DEVINFO_SPI); /* Populate the target capability fields with the values * gleaned from the device inquiry */ 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/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c index 77fe55ce790c..d65345312527 100644 --- a/drivers/spi/spi-armada-3700.c +++ b/drivers/spi/spi-armada-3700.c @@ -79,6 +79,7 @@ #define A3700_SPI_BYTE_LEN BIT(5) #define A3700_SPI_CLK_PRESCALE BIT(0) #define A3700_SPI_CLK_PRESCALE_MASK (0x1f) +#define A3700_SPI_CLK_EVEN_OFFS (0x10) #define A3700_SPI_WFIFO_THRS_BIT 28 #define A3700_SPI_RFIFO_THRS_BIT 24 @@ -220,6 +221,13 @@ static void a3700_spi_clock_set(struct a3700_spi *a3700_spi, prescale = DIV_ROUND_UP(clk_get_rate(a3700_spi->clk), speed_hz); + /* For prescaler values over 15, we can only set it by steps of 2. + * Starting from A3700_SPI_CLK_EVEN_OFFS, we set values from 0 up to + * 30. We only use this range from 16 to 30. + */ + if (prescale > 15) + prescale = A3700_SPI_CLK_EVEN_OFFS + DIV_ROUND_UP(prescale, 2); + val = spireg_read(a3700_spi, A3700_SPI_IF_CFG_REG); val = val & ~A3700_SPI_CLK_PRESCALE_MASK; diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index f95da364c283..669470971023 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1661,12 +1661,12 @@ static int atmel_spi_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); /* reset the hardware and block queue progress */ - spin_lock_irq(&as->lock); if (as->use_dma) { atmel_spi_stop_dma(master); atmel_spi_release_dma(master); } + spin_lock_irq(&as->lock); spi_writel(as, CR, SPI_BIT(SWRST)); spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */ spi_readl(as, SR); diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 2ce875764ca6..0835a8d88fb8 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -377,8 +377,8 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size) /* Sets SPCMD */ rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0); - /* Enables SPI function in master mode */ - rspi_write8(rspi, SPCR_SPE | SPCR_MSTR, RSPI_SPCR); + /* Sets RSPI mode */ + rspi_write8(rspi, SPCR_MSTR, RSPI_SPCR); return 0; } diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index c5cd635c28f3..41410031f8e9 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -525,7 +525,7 @@ err_free_master: static int sun4i_spi_remove(struct platform_device *pdev) { - pm_runtime_disable(&pdev->dev); + pm_runtime_force_suspend(&pdev->dev); return 0; } diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c index bc7100b93dfc..e0b9fe1d0e37 100644 --- a/drivers/spi/spi-xilinx.c +++ b/drivers/spi/spi-xilinx.c @@ -271,6 +271,7 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) while (remaining_words) { int n_words, tx_words, rx_words; u32 sr; + int stalled; n_words = min(remaining_words, xspi->buffer_size); @@ -299,7 +300,17 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) /* Read out all the data from the Rx FIFO */ rx_words = n_words; + stalled = 10; while (rx_words) { + if (rx_words == n_words && !(stalled--) && + !(sr & XSPI_SR_TX_EMPTY_MASK) && + (sr & XSPI_SR_RX_EMPTY_MASK)) { + dev_err(&spi->dev, + "Detected stall. Check C_SPI_MODE and C_SPI_MEMORY\n"); + xspi_init_hw(xspi); + return -EIO; + } + if ((sr & XSPI_SR_TX_EMPTY_MASK) && (rx_words > 1)) { xilinx_spi_rx(xspi); rx_words--; 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/usb/core/config.c b/drivers/usb/core/config.c index 55b198ba629b..78e92d29f8d9 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -555,6 +555,9 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, unsigned iad_num = 0; memcpy(&config->desc, buffer, USB_DT_CONFIG_SIZE); + nintf = nintf_orig = config->desc.bNumInterfaces; + config->desc.bNumInterfaces = 0; // Adjusted later + if (config->desc.bDescriptorType != USB_DT_CONFIG || config->desc.bLength < USB_DT_CONFIG_SIZE || config->desc.bLength > size) { @@ -568,7 +571,6 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, buffer += config->desc.bLength; size -= config->desc.bLength; - nintf = nintf_orig = config->desc.bNumInterfaces; if (nintf > USB_MAXINTERFACES) { dev_warn(ddev, "config %d has too many interfaces: %d, " "using maximum allowed: %d\n", diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index f66c94130cac..31749c79045f 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -537,6 +537,7 @@ struct dwc2_core_params { * 2 - Internal DMA * @power_optimized Are power optimizations enabled? * @num_dev_ep Number of device endpoints available + * @num_dev_in_eps Number of device IN endpoints available * @num_dev_perio_in_ep Number of device periodic IN endpoints * available * @dev_token_q_depth Device Mode IN Token Sequence Learning Queue @@ -565,6 +566,7 @@ struct dwc2_core_params { * 2 - 8 or 16 bits * @snpsid: Value from SNPSID register * @dev_ep_dirs: Direction of device endpoints (GHWCFG1) + * @g_tx_fifo_size[] Power-on values of TxFIFO sizes */ struct dwc2_hw_params { unsigned op_mode:3; @@ -586,12 +588,14 @@ struct dwc2_hw_params { unsigned fs_phy_type:2; unsigned i2c_enable:1; unsigned num_dev_ep:4; + unsigned num_dev_in_eps : 4; unsigned num_dev_perio_in_ep:4; unsigned total_fifo_size:16; unsigned power_optimized:1; unsigned utmi_phy_data_width:2; u32 snpsid; u32 dev_ep_dirs; + u32 g_tx_fifo_size[MAX_EPS_CHANNELS]; }; /* Size of control and EP0 buffers */ diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 88529d092503..e4c3ce0de5de 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -195,55 +195,18 @@ int dwc2_hsotg_tx_fifo_count(struct dwc2_hsotg *hsotg) { if (hsotg->hw_params.en_multiple_tx_fifo) /* In dedicated FIFO mode we need count of IN EPs */ - return (dwc2_readl(hsotg->regs + GHWCFG4) & - GHWCFG4_NUM_IN_EPS_MASK) >> GHWCFG4_NUM_IN_EPS_SHIFT; + return hsotg->hw_params.num_dev_in_eps; else /* In shared FIFO mode we need count of Periodic IN EPs */ return hsotg->hw_params.num_dev_perio_in_ep; } /** - * dwc2_hsotg_ep_info_size - return Endpoint Info Control block size in DWORDs - */ -static int dwc2_hsotg_ep_info_size(struct dwc2_hsotg *hsotg) -{ - int val = 0; - int i; - u32 ep_dirs; - - /* - * Don't need additional space for ep info control registers in - * slave mode. - */ - if (!using_dma(hsotg)) { - dev_dbg(hsotg->dev, "Buffer DMA ep info size 0\n"); - return 0; - } - - /* - * Buffer DMA mode - 1 location per endpoit - * Descriptor DMA mode - 4 locations per endpoint - */ - ep_dirs = hsotg->hw_params.dev_ep_dirs; - - for (i = 0; i <= hsotg->hw_params.num_dev_ep; i++) { - val += ep_dirs & 3 ? 1 : 2; - ep_dirs >>= 2; - } - - if (using_desc_dma(hsotg)) - val = val * 4; - - return val; -} - -/** * dwc2_hsotg_tx_fifo_total_depth - return total FIFO depth available for * device mode TX FIFOs */ int dwc2_hsotg_tx_fifo_total_depth(struct dwc2_hsotg *hsotg) { - int ep_info_size; int addr; int tx_addr_max; u32 np_tx_fifo_size; @@ -252,8 +215,7 @@ int dwc2_hsotg_tx_fifo_total_depth(struct dwc2_hsotg *hsotg) hsotg->params.g_np_tx_fifo_size); /* Get Endpoint Info Control block size in DWORDs. */ - ep_info_size = dwc2_hsotg_ep_info_size(hsotg); - tx_addr_max = hsotg->hw_params.total_fifo_size - ep_info_size; + tx_addr_max = hsotg->hw_params.total_fifo_size; addr = hsotg->params.g_rx_fifo_size + np_tx_fifo_size; if (tx_addr_max <= addr) diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index ef73af6e03a9..03fd20f0b496 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -484,8 +484,7 @@ static void dwc2_check_param_tx_fifo_sizes(struct dwc2_hsotg *hsotg) } for (fifo = 1; fifo <= fifo_count; fifo++) { - dptxfszn = (dwc2_readl(hsotg->regs + DPTXFSIZN(fifo)) & - FIFOSIZE_DEPTH_MASK) >> FIFOSIZE_DEPTH_SHIFT; + dptxfszn = hsotg->hw_params.g_tx_fifo_size[fifo]; if (hsotg->params.g_tx_fifo_size[fifo] < min || hsotg->params.g_tx_fifo_size[fifo] > dptxfszn) { @@ -609,6 +608,7 @@ static void dwc2_get_dev_hwparams(struct dwc2_hsotg *hsotg) struct dwc2_hw_params *hw = &hsotg->hw_params; bool forced; u32 gnptxfsiz; + int fifo, fifo_count; if (hsotg->dr_mode == USB_DR_MODE_HOST) return; @@ -617,6 +617,14 @@ static void dwc2_get_dev_hwparams(struct dwc2_hsotg *hsotg) gnptxfsiz = dwc2_readl(hsotg->regs + GNPTXFSIZ); + fifo_count = dwc2_hsotg_tx_fifo_count(hsotg); + + for (fifo = 1; fifo <= fifo_count; fifo++) { + hw->g_tx_fifo_size[fifo] = + (dwc2_readl(hsotg->regs + DPTXFSIZN(fifo)) & + FIFOSIZE_DEPTH_MASK) >> FIFOSIZE_DEPTH_SHIFT; + } + if (forced) dwc2_clear_force_mode(hsotg); @@ -661,14 +669,6 @@ int dwc2_get_hwparams(struct dwc2_hsotg *hsotg) hwcfg4 = dwc2_readl(hsotg->regs + GHWCFG4); grxfsiz = dwc2_readl(hsotg->regs + GRXFSIZ); - /* - * Host specific hardware parameters. Reading these parameters - * requires the controller to be in host mode. The mode will - * be forced, if necessary, to read these values. - */ - dwc2_get_host_hwparams(hsotg); - dwc2_get_dev_hwparams(hsotg); - /* hwcfg1 */ hw->dev_ep_dirs = hwcfg1; @@ -711,6 +711,8 @@ int dwc2_get_hwparams(struct dwc2_hsotg *hsotg) hw->en_multiple_tx_fifo = !!(hwcfg4 & GHWCFG4_DED_FIFO_EN); hw->num_dev_perio_in_ep = (hwcfg4 & GHWCFG4_NUM_DEV_PERIO_IN_EP_MASK) >> GHWCFG4_NUM_DEV_PERIO_IN_EP_SHIFT; + hw->num_dev_in_eps = (hwcfg4 & GHWCFG4_NUM_IN_EPS_MASK) >> + GHWCFG4_NUM_IN_EPS_SHIFT; hw->dma_desc_enable = !!(hwcfg4 & GHWCFG4_DESC_DMA); hw->power_optimized = !!(hwcfg4 & GHWCFG4_POWER_OPTIMIZ); hw->utmi_phy_data_width = (hwcfg4 & GHWCFG4_UTMI_PHY_DATA_WIDTH_MASK) >> @@ -719,6 +721,13 @@ int dwc2_get_hwparams(struct dwc2_hsotg *hsotg) /* fifo sizes */ hw->rx_fifo_size = (grxfsiz & GRXFSIZ_DEPTH_MASK) >> GRXFSIZ_DEPTH_SHIFT; + /* + * Host specific hardware parameters. Reading these parameters + * requires the controller to be in host mode. The mode will + * be forced, if necessary, to read these values. + */ + dwc2_get_host_hwparams(hsotg); + dwc2_get_dev_hwparams(hsotg); return 0; } diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index c4a4d7bd2766..7ae0eefc7cc7 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -51,8 +51,10 @@ static int dwc3_of_simple_clk_init(struct dwc3_of_simple *simple, int count) clk = of_clk_get(np, i); if (IS_ERR(clk)) { - while (--i >= 0) + while (--i >= 0) { + clk_disable_unprepare(simple->clks[i]); clk_put(simple->clks[i]); + } return PTR_ERR(clk); } @@ -203,6 +205,7 @@ static struct platform_driver dwc3_of_simple_driver = { .driver = { .name = "dwc3-of-simple", .of_match_table = of_dwc3_simple_match, + .pm = &dwc3_of_simple_dev_pm_ops, }, }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 981fd986cf82..639dd1b163a0 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -259,7 +259,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd, { const struct usb_endpoint_descriptor *desc = dep->endpoint.desc; struct dwc3 *dwc = dep->dwc; - u32 timeout = 500; + u32 timeout = 1000; u32 reg; int cmd_status = 0; @@ -912,7 +912,7 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb, */ if (speed == USB_SPEED_HIGH) { struct usb_ep *ep = &dep->endpoint; - unsigned int mult = ep->mult - 1; + unsigned int mult = 2; unsigned int maxp = usb_endpoint_maxp(ep->desc); if (length <= (2 * maxp)) diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 0a19a76645ad..31cce7805eb2 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -508,8 +508,8 @@ choice controller, and the relevant drivers for each function declared by the device. -endchoice - source "drivers/usb/gadget/legacy/Kconfig" +endchoice + endif # USB_GADGET diff --git a/drivers/usb/gadget/legacy/Kconfig b/drivers/usb/gadget/legacy/Kconfig index 9570bbeced4f..784bf86dad4f 100644 --- a/drivers/usb/gadget/legacy/Kconfig +++ b/drivers/usb/gadget/legacy/Kconfig @@ -13,14 +13,6 @@ # both kinds of controller can also support "USB On-the-Go" (CONFIG_USB_OTG). # -menuconfig USB_GADGET_LEGACY - bool "Legacy USB Gadget Support" - help - Legacy USB gadgets are USB gadgets that do not use the USB gadget - configfs interface. - -if USB_GADGET_LEGACY - config USB_ZERO tristate "Gadget Zero (DEVELOPMENT)" select USB_LIBCOMPOSITE @@ -487,7 +479,7 @@ endif # or video class gadget drivers), or specific hardware, here. config USB_G_WEBCAM tristate "USB Webcam Gadget" - depends on VIDEO_DEV + depends on VIDEO_V4L2 select USB_LIBCOMPOSITE select VIDEOBUF2_VMALLOC select USB_F_UVC @@ -498,5 +490,3 @@ config USB_G_WEBCAM Say "y" to link the driver statically, or "m" to build a dynamically linked module called "g_webcam". - -endif diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 15f7d422885f..3a29b32a3bd0 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -971,10 +971,9 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, return 0; } - xhci->devs[slot_id] = kzalloc(sizeof(*xhci->devs[slot_id]), flags); - if (!xhci->devs[slot_id]) + dev = kzalloc(sizeof(*dev), flags); + if (!dev) return 0; - dev = xhci->devs[slot_id]; /* Allocate the (output) device context that will be used in the HC. */ dev->out_ctx = xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_DEVICE, flags); @@ -1015,9 +1014,17 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, trace_xhci_alloc_virt_device(dev); + xhci->devs[slot_id] = dev; + return 1; fail: - xhci_free_virt_device(xhci, slot_id); + + if (dev->in_ctx) + xhci_free_container_ctx(xhci, dev->in_ctx); + if (dev->out_ctx) + xhci_free_container_ctx(xhci, dev->out_ctx); + kfree(dev); + return 0; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 6eb87c6e4d24..c5cbc685c691 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3112,7 +3112,7 @@ static u32 xhci_td_remainder(struct xhci_hcd *xhci, int transferred, { u32 maxp, total_packet_count; - /* MTK xHCI is mostly 0.97 but contains some features from 1.0 */ + /* MTK xHCI 0.96 contains some features from 1.0 */ if (xhci->hci_version < 0x100 && !(xhci->quirks & XHCI_MTK_HOST)) return ((td_total_len - transferred) >> 10); @@ -3121,8 +3121,8 @@ static u32 xhci_td_remainder(struct xhci_hcd *xhci, int transferred, trb_buff_len == td_total_len) return 0; - /* for MTK xHCI, TD size doesn't include this TRB */ - if (xhci->quirks & XHCI_MTK_HOST) + /* for MTK xHCI 0.96, TD size include this TRB, but not in 1.x */ + if ((xhci->quirks & XHCI_MTK_HOST) && (xhci->hci_version < 0x100)) trb_buff_len = 0; maxp = usb_endpoint_maxp(&urb->ep->desc); diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index 0397606a211b..6c036de63272 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -284,7 +284,15 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci) musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE; portstate(musb->port1_status |= USB_PORT_STAT_POWER); del_timer(&musb->dev_timer); - } else { + } else if (!(musb->int_usb & MUSB_INTR_BABBLE)) { + /* + * When babble condition happens, drvvbus interrupt + * is also generated. Ignore this drvvbus interrupt + * and let babble interrupt handler recovers the + * controller; otherwise, the host-mode flag is lost + * due to the MUSB_DEV_MODE() call below and babble + * recovery logic will not be called. + */ musb->is_active = 0; MUSB_DEV_MODE(musb); otg->default_a = 0; diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 2968046e7c05..f72d045ee9ef 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2100,6 +2100,13 @@ UNUSUAL_DEV( 0x152d, 0x0567, 0x0114, 0x0116, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BROKEN_FUA ), +/* Reported by David Kozub <zub@linux.fjfi.cvut.cz> */ +UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999, + "JMicron", + "JMS567", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BROKEN_FUA), + /* * Reported by Alexandre Oliva <oliva@lsd.ic.unicamp.br> * JMicron responds to USN and several other SCSI ioctls with a diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index d520374a824e..e6127fb21c12 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -129,6 +129,13 @@ UNUSUAL_DEV(0x152d, 0x0567, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BROKEN_FUA | US_FL_NO_REPORT_OPCODES), +/* Reported-by: David Kozub <zub@linux.fjfi.cvut.cz> */ +UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999, + "JMicron", + "JMS567", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BROKEN_FUA), + /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, "VIA", diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 536e037f541f..493ac2928391 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -322,23 +322,34 @@ static struct stub_priv *stub_priv_alloc(struct stub_device *sdev, return priv; } -static int get_pipe(struct stub_device *sdev, int epnum, int dir) +static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu) { struct usb_device *udev = sdev->udev; struct usb_host_endpoint *ep; struct usb_endpoint_descriptor *epd = NULL; + int epnum = pdu->base.ep; + int dir = pdu->base.direction; + + if (epnum < 0 || epnum > 15) + goto err_ret; if (dir == USBIP_DIR_IN) ep = udev->ep_in[epnum & 0x7f]; else ep = udev->ep_out[epnum & 0x7f]; - if (!ep) { - dev_err(&sdev->udev->dev, "no such endpoint?, %d\n", - epnum); - BUG(); - } + if (!ep) + goto err_ret; epd = &ep->desc; + + /* validate transfer_buffer_length */ + if (pdu->u.cmd_submit.transfer_buffer_length > INT_MAX) { + dev_err(&sdev->udev->dev, + "CMD_SUBMIT: -EMSGSIZE transfer_buffer_length %d\n", + pdu->u.cmd_submit.transfer_buffer_length); + return -1; + } + if (usb_endpoint_xfer_control(epd)) { if (dir == USBIP_DIR_OUT) return usb_sndctrlpipe(udev, epnum); @@ -361,15 +372,31 @@ static int get_pipe(struct stub_device *sdev, int epnum, int dir) } if (usb_endpoint_xfer_isoc(epd)) { + /* validate packet size and number of packets */ + unsigned int maxp, packets, bytes; + + maxp = usb_endpoint_maxp(epd); + maxp *= usb_endpoint_maxp_mult(epd); + bytes = pdu->u.cmd_submit.transfer_buffer_length; + packets = DIV_ROUND_UP(bytes, maxp); + + if (pdu->u.cmd_submit.number_of_packets < 0 || + pdu->u.cmd_submit.number_of_packets > packets) { + dev_err(&sdev->udev->dev, + "CMD_SUBMIT: isoc invalid num packets %d\n", + pdu->u.cmd_submit.number_of_packets); + return -1; + } if (dir == USBIP_DIR_OUT) return usb_sndisocpipe(udev, epnum); else return usb_rcvisocpipe(udev, epnum); } +err_ret: /* NOT REACHED */ - dev_err(&sdev->udev->dev, "get pipe, epnum %d\n", epnum); - return 0; + dev_err(&sdev->udev->dev, "CMD_SUBMIT: invalid epnum %d\n", epnum); + return -1; } static void masking_bogus_flags(struct urb *urb) @@ -433,7 +460,10 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, struct stub_priv *priv; struct usbip_device *ud = &sdev->ud; struct usb_device *udev = sdev->udev; - int pipe = get_pipe(sdev, pdu->base.ep, pdu->base.direction); + int pipe = get_pipe(sdev, pdu); + + if (pipe == -1) + return; priv = stub_priv_alloc(sdev, pdu); if (!priv) @@ -452,7 +482,8 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, } /* allocate urb transfer buffer, if needed */ - if (pdu->u.cmd_submit.transfer_buffer_length > 0) { + if (pdu->u.cmd_submit.transfer_buffer_length > 0 && + pdu->u.cmd_submit.transfer_buffer_length <= INT_MAX) { priv->urb->transfer_buffer = kzalloc(pdu->u.cmd_submit.transfer_buffer_length, GFP_KERNEL); diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c index b18bce96c212..53172b1f6257 100644 --- a/drivers/usb/usbip/stub_tx.c +++ b/drivers/usb/usbip/stub_tx.c @@ -167,6 +167,13 @@ static int stub_send_ret_submit(struct stub_device *sdev) memset(&pdu_header, 0, sizeof(pdu_header)); memset(&msg, 0, sizeof(msg)); + if (urb->actual_length > 0 && !urb->transfer_buffer) { + dev_err(&sdev->udev->dev, + "urb: actual_length %d transfer_buffer null\n", + urb->actual_length); + return -1; + } + if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) iovnum = 2 + urb->number_of_packets; else diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index e5de35c8c505..473fb8a87289 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -256,6 +256,7 @@ struct usbip_device { /* lock for status */ spinlock_t lock; + int sockfd; struct socket *tcp_socket; struct task_struct *tcp_rx; diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c index e78f7472cac4..091f76b7196d 100644 --- a/drivers/usb/usbip/vhci_sysfs.c +++ b/drivers/usb/usbip/vhci_sysfs.c @@ -17,15 +17,20 @@ /* * output example: - * hub port sta spd dev socket local_busid - * hs 0000 004 000 00000000 c5a7bb80 1-2.3 + * hub port sta spd dev sockfd local_busid + * hs 0000 004 000 00000000 3 1-2.3 * ................................................ - * ss 0008 004 000 00000000 d8cee980 2-3.4 + * ss 0008 004 000 00000000 4 2-3.4 * ................................................ * - * IP address can be retrieved from a socket pointer address by looking - * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a - * port number and its peer IP address. + * Output includes socket fd instead of socket pointer address to avoid + * leaking kernel memory address in: + * /sys/devices/platform/vhci_hcd.0/status and in debug output. + * The socket pointer address is not used at the moment and it was made + * visible as a convenient way to find IP address from socket pointer + * address by looking up /proc/net/{tcp,tcp6}. As this opens a security + * hole, the change is made to use sockfd instead. + * */ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vdev) { @@ -39,8 +44,8 @@ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vd if (vdev->ud.status == VDEV_ST_USED) { *out += sprintf(*out, "%03u %08x ", vdev->speed, vdev->devid); - *out += sprintf(*out, "%16p %s", - vdev->ud.tcp_socket, + *out += sprintf(*out, "%u %s", + vdev->ud.sockfd, dev_name(&vdev->udev->dev)); } else { @@ -160,7 +165,8 @@ static ssize_t nports_show(struct device *dev, struct device_attribute *attr, char *s = out; /* - * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, thus the * 2. + * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, + * thus the * 2. */ out += sprintf(out, "%d\n", VHCI_PORTS * vhci_num_controllers); return out - s; @@ -366,6 +372,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr, vdev->devid = devid; vdev->speed = speed; + vdev->ud.sockfd = sockfd; vdev->ud.tcp_socket = socket; vdev->ud.status = VDEV_ST_NOTASSIGNED; 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/cramfs/Kconfig b/fs/cramfs/Kconfig index f937082f3244..58e2fe40b2a0 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -34,6 +34,7 @@ config CRAMFS_BLOCKDEV config CRAMFS_MTD bool "Support CramFs image directly mapped in physical memory" depends on CRAMFS && MTD + depends on CRAMFS=m || MTD=y default y if !CRAMFS_BLOCKDEV help This option allows the CramFs driver to load data directly from @@ -627,8 +627,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, if (pfn != pmd_pfn(*pmdp)) goto unlock_pmd; - if (!pmd_dirty(*pmdp) - && !pmd_access_permitted(*pmdp, WRITE)) + if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) goto unlock_pmd; flush_cache_page(vma, address, pfn); diff --git a/fs/exec.c b/fs/exec.c index 6be2aa0ab26f..5688b5e1b937 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 @@ -1340,15 +1339,10 @@ void setup_new_exec(struct linux_binprm * bprm) * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid - * races from other threads changing the limits. This also - * must be protected from races with prlimit() calls. + * needing to clean up the change on failure. */ - task_lock(current->group_leader); if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; - if (current->signal->rlim[RLIMIT_STACK].rlim_max > _STK_LIM) - current->signal->rlim[RLIMIT_STACK].rlim_max = _STK_LIM; - task_unlock(current->group_leader); } arch_pick_mmap_layout(current->mm); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 07bca11749d4..c941251ac0c0 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4722,6 +4722,7 @@ retry: EXT4_INODE_EOFBLOCKS); } ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); ret2 = ext4_journal_stop(handle); if (ret2) break; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b4267d72f249..b32cf263750d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -816,6 +816,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, #ifdef CONFIG_EXT4_FS_POSIX_ACL struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(p)) + return ERR_CAST(p); if (p) { int acl_size = p->a_count * sizeof(ext4_acl_entry); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7df2c5644e59..534a9130f625 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -149,6 +149,15 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, */ int ext4_inode_is_fast_symlink(struct inode *inode) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + int ea_blocks = EXT4_I(inode)->i_file_acl ? + EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; + + if (ext4_has_inline_data(inode)) + return 0; + + return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + } return S_ISLNK(inode->i_mode) && inode->i_size && (inode->i_size < EXT4_N_BLOCKS * 4); } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 798b3ac680db..e750d68fbcb5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1399,6 +1399,10 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, "falling back\n")); } nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); + if (!nblocks) { + ret = NULL; + goto cleanup_and_exit; + } start = EXT4_I(dir)->i_dir_start_lookup; if (start >= nblocks) start = 0; diff --git a/fs/namespace.c b/fs/namespace.c index e158ec6b527b..9d1374ab6e06 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2826,6 +2826,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, SB_DIRSYNC | SB_SILENT | SB_POSIXACL | + SB_LAZYTIME | SB_I_VERSION); if (flags & MS_REMOUNT) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 0ac2fb1c6b63..b9129e2befea 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -291,12 +291,23 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); +again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; /* Don't match clients that failed to initialise properly */ if (clp->cl_cons_state < 0) continue; + /* If a client is still initializing then we need to wait */ + if (clp->cl_cons_state > NFS_CS_READY) { + refcount_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + nfs_wait_client_init_complete(clp); + nfs_put_client(clp); + spin_lock(&nn->nfs_client_lock); + goto again; + } + /* Different NFS versions cannot share the same nfs_client */ if (clp->rpc_ops != data->nfs_mod->rpc_ops) continue; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 12bbab0becb4..65a7e5da508c 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -404,15 +404,19 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (error < 0) goto error; - if (!nfs4_has_session(clp)) - nfs_mark_client_ready(clp, NFS_CS_READY); - error = nfs4_discover_server_trunking(clp, &old); if (error < 0) goto error; - if (clp != old) + if (clp != old) { clp->cl_preserve_clid = true; + /* + * Mark the client as having failed initialization so other + * processes walking the nfs_client_list in nfs_match_client() + * won't try to use it. + */ + nfs_mark_client_ready(clp, -EPERM); + } nfs_put_client(clp); clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); return old; @@ -539,6 +543,9 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + if (pos == new) + goto found; + status = nfs4_match_client(pos, new, &prev, nn); if (status < 0) goto out_unlock; @@ -559,6 +566,7 @@ int nfs40_walk_client_list(struct nfs_client *new, * way that a SETCLIENTID_CONFIRM to pos can succeed is * if new and pos point to the same server: */ +found: refcount_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -572,6 +580,7 @@ int nfs40_walk_client_list(struct nfs_client *new, case 0: nfs4_swap_callback_idents(pos, new); pos->cl_confirm = new->cl_confirm; + nfs_mark_client_ready(pos, NFS_CS_READY); prev = NULL; *result = pos; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5b5f464f6f2a..4a379d7918f2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1890,6 +1890,8 @@ int nfs_commit_inode(struct inode *inode, int how) if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); nfs_commit_end(cinfo.mds); + if (res == 0) + return res; if (error < 0) goto out_error; if (!may_wait) 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/super.c b/fs/super.c index d4e33e8f1e6f..7ff1349609e4 100644 --- a/fs/super.c +++ b/fs/super.c @@ -191,6 +191,24 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); + init_rwsem(&s->s_umount); + lockdep_set_class(&s->s_umount, &type->s_umount_key); + /* + * sget() can have s_umount recursion. + * + * When it cannot find a suitable sb, it allocates a new + * one (this one), and tries again to find a suitable old + * one. + * + * In case that succeeds, it will acquire the s_umount + * lock of the old one. Since these are clearly distrinct + * locks, and this object isn't exposed yet, there's no + * risk of deadlocks. + * + * Annotate this by putting this lock in a different + * subclass. + */ + down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; @@ -218,25 +236,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, goto fail; if (list_lru_init_memcg(&s->s_inode_lru)) goto fail; - - init_rwsem(&s->s_umount); - lockdep_set_class(&s->s_umount, &type->s_umount_key); - /* - * sget() can have s_umount recursion. - * - * When it cannot find a suitable sb, it allocates a new - * one (this one), and tries again to find a suitable old - * one. - * - * In case that succeeds, it will acquire the s_umount - * lock of the old one. Since these are clearly distrinct - * locks, and this object isn't exposed yet, there's no - * risk of deadlocks. - * - * Annotate this by putting this lock in a different - * subclass. - */ - down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); 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/pti.h b/include/linux/intel-pti.h index b3ea01a3197e..2710d72de3c9 100644 --- a/include/linux/pti.h +++ b/include/linux/intel-pti.h @@ -22,8 +22,8 @@ * interface to write out it's contents for debugging a mobile system. */ -#ifndef PTI_H_ -#define PTI_H_ +#ifndef LINUX_INTEL_PTI_H_ +#define LINUX_INTEL_PTI_H_ /* offset for last dword of any PTI message. Part of MIPI P1149.7 */ #define PTI_LASTDWORD_DTS 0x30 @@ -40,4 +40,4 @@ struct pti_masterchannel *pti_request_masterchannel(u8 type, const char *thread_name); void pti_release_masterchannel(struct pti_masterchannel *mc); -#endif /*PTI_H_*/ +#endif /* LINUX_INTEL_PTI_H_ */ 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/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index a2a1318a3d0c..c3d3f04d8cc6 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -915,10 +915,10 @@ enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; #define LTR_L1SS_PWR_GATE_CHECK_CARD_EN BIT(6) enum dev_aspm_mode { - DEV_ASPM_DISABLE = 0, DEV_ASPM_DYNAMIC, DEV_ASPM_BACKDOOR, DEV_ASPM_STATIC, + DEV_ASPM_DISABLE, }; /* 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/ptr_ring.h b/include/linux/ptr_ring.h index 37b4bb2545b3..6866df4f31b5 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. + * Callers are responsible for making sure pointer that is being queued + * points to a valid data. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { if (unlikely(!r->size) || r->queue[r->producer]) return -ENOSPC; + /* Make sure the pointer we are storing points to a valid data. */ + /* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */ + smp_wmb(); + r->queue[r->producer++] = ptr; if (unlikely(r->producer >= r->size)) r->producer = 0; @@ -275,6 +281,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r) if (ptr) __ptr_ring_discard_one(r); + /* Make sure anyone accessing data through the pointer is up to date. */ + /* Pairs with smp_wmb in __ptr_ring_produce. */ + smp_read_barrier_depends(); return ptr; } 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/spi/spi.h b/include/linux/spi/spi.h index 7b2170bfd6e7..bc6bb325d1bf 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -126,7 +126,7 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when - * when not using a GPIO line) + * not using a GPIO line) * * @statistics: statistics for the spi_device * 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/net/gue.h b/include/net/gue.h index 2fdb29ca74c2..fdad41469b65 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -44,10 +44,10 @@ struct guehdr { #else #error "Please fix <asm/byteorder.h>" #endif - __u8 proto_ctype; - __u16 flags; + __u8 proto_ctype; + __be16 flags; }; - __u32 word; + __be32 word; }; }; @@ -84,11 +84,10 @@ static inline size_t guehdr_priv_flags_len(__be32 flags) * if there is an unknown standard or private flags, or the options length for * the flags exceeds the options length specific in hlen of the GUE header. */ -static inline int validate_gue_flags(struct guehdr *guehdr, - size_t optlen) +static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen) { + __be16 flags = guehdr->flags; size_t len; - __be32 flags = guehdr->flags; if (flags & ~GUE_FLAGS_ALL) return 1; @@ -101,12 +100,13 @@ static inline int validate_gue_flags(struct guehdr *guehdr, /* Private flags are last four bytes accounted in * guehdr_flags_len */ - flags = *(__be32 *)((void *)&guehdr[1] + len - GUE_LEN_PRIV); + __be32 pflags = *(__be32 *)((void *)&guehdr[1] + + len - GUE_LEN_PRIV); - if (flags & ~GUE_PFLAGS_ALL) + if (pflags & ~GUE_PFLAGS_ALL) return 1; - len += guehdr_priv_flags_len(flags); + len += guehdr_priv_flags_len(pflags); if (len > optlen) return 1; } diff --git a/include/net/ip.h b/include/net/ip.h index 9896f46cbbf1..af8addbaa3c1 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -34,6 +34,7 @@ #include <net/flow_dissector.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ +#define IPV4_MIN_MTU 68 /* RFC 791 */ struct sock; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 65d0d25f2648..83a3e47d5845 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -71,6 +71,7 @@ struct Qdisc { * qdisc_tree_decrease_qlen() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ +#define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; 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/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index af3cc2f4e1ad..37b5096ae97b 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -256,7 +256,6 @@ struct tc_red_qopt { #define TC_RED_ECN 1 #define TC_RED_HARDDROP 2 #define TC_RED_ADAPTATIVE 4 -#define TC_RED_OFFLOADED 8 }; struct tc_red_xstats { diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index d8b5f80c2ea6..843e29aa3cac 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -557,6 +557,7 @@ enum { TCA_PAD, TCA_DUMP_INVISIBLE, TCA_CHAIN, + TCA_HW_OFFLOAD, __TCA_MAX }; 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/bpf/hashtab.c b/kernel/bpf/hashtab.c index e469e05c8e83..3905d4bc5b80 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -114,6 +114,7 @@ static void htab_free_elems(struct bpf_htab *htab) pptr = htab_elem_get_ptr(get_htab_elem(htab, i), htab->map.key_size); free_percpu(pptr); + cond_resched(); } free_elems: bpf_map_area_free(htab->elems); @@ -159,6 +160,7 @@ static int prealloc_init(struct bpf_htab *htab) goto free_elems; htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, pptr); + cond_resched(); } skip_percpu_elems: 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/time/posix-timers.c b/kernel/time/posix-timers.c index 13d6881f908b..ec999f32c840 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -434,17 +434,22 @@ static struct pid *good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; - if ((event->sigev_notify & SIGEV_THREAD_ID ) && - (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || - !same_thread_group(rtn, current) || - (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL)) + switch (event->sigev_notify) { + case SIGEV_SIGNAL | SIGEV_THREAD_ID: + rtn = find_task_by_vpid(event->sigev_notify_thread_id); + if (!rtn || !same_thread_group(rtn, current)) + return NULL; + /* FALLTHRU */ + case SIGEV_SIGNAL: + case SIGEV_THREAD: + if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) + return NULL; + /* FALLTHRU */ + case SIGEV_NONE: + return task_pid(rtn); + default: return NULL; - - if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && - ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) - return NULL; - - return task_pid(rtn); + } } static struct k_itimer * alloc_posix_timer(void) @@ -669,7 +674,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) struct timespec64 ts64; bool sig_none; - sig_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE; + sig_none = timr->it_sigev_notify == SIGEV_NONE; iv = timr->it_interval; /* interval timer ? */ @@ -856,7 +861,7 @@ int common_timer_set(struct k_itimer *timr, int flags, timr->it_interval = timespec64_to_ktime(new_setting->it_interval); expires = timespec64_to_ktime(new_setting->it_value); - sigev_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE; + sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); timr->it_active = !sigev_none; 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/bpf_trace.c b/kernel/trace/bpf_trace.c index 0ce99c379c30..40207c2a4113 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -343,14 +343,13 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .arg4_type = ARG_CONST_SIZE, }; -static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); +static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd); static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, - u64 flags, struct perf_raw_record *raw) + u64 flags, struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); - struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; @@ -373,8 +372,6 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; - perf_sample_data_init(sd, 0, 0); - sd->raw = raw; perf_event_output(event, sd, regs); return 0; } @@ -382,6 +379,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { + struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd); struct perf_raw_record raw = { .frag = { .size = size, @@ -392,7 +390,10 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; - return __bpf_perf_event_output(regs, map, flags, &raw); + perf_sample_data_init(sd, 0, 0); + sd->raw = &raw; + + return __bpf_perf_event_output(regs, map, flags, sd); } static const struct bpf_func_proto bpf_perf_event_output_proto = { @@ -407,10 +408,12 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { }; static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); +static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { + struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd); struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); struct perf_raw_frag frag = { .copy = ctx_copy, @@ -428,8 +431,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; perf_fetch_caller_regs(regs); + perf_sample_data_init(sd, 0, 0); + sd->raw = &raw; - return __bpf_perf_event_output(regs, map, flags, &raw); + return __bpf_perf_event_output(regs, map, flags, sd); } BPF_CALL_0(bpf_get_current_task) 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; @@ -66,7 +66,7 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, */ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) { - return pte_access_permitted(pte, WRITE) || + return pte_write(pte) || ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); } @@ -391,11 +391,11 @@ again: if (pmd_protnone(pmd)) return hmm_vma_walk_clear(start, end, walk); - if (!pmd_access_permitted(pmd, write_fault)) + if (write_fault && !pmd_write(pmd)) return hmm_vma_walk_clear(start, end, walk); pfn = pmd_pfn(pmd) + pte_index(addr); - flag |= pmd_access_permitted(pmd, WRITE) ? HMM_PFN_WRITE : 0; + flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0; for (; addr < end; addr += PAGE_SIZE, i++, pfn++) pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag; return 0; @@ -456,11 +456,11 @@ again: continue; } - if (!pte_access_permitted(pte, write_fault)) + if (write_fault && !pte_write(pte)) goto fault; pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag; - pfns[i] |= pte_access_permitted(pte, WRITE) ? HMM_PFN_WRITE : 0; + pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0; continue; fault: diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2f2f5e774902..0e7ded98d114 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -870,7 +870,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, */ WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); - if (!pmd_access_permitted(*pmd, flags & FOLL_WRITE)) + if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; if (pmd_present(*pmd) && pmd_devmap(*pmd)) @@ -1012,7 +1012,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pud_lockptr(mm, pud)); - if (!pud_access_permitted(*pud, flags & FOLL_WRITE)) + if (flags & FOLL_WRITE && !pud_write(*pud)) return NULL; if (pud_present(*pud) && pud_devmap(*pud)) @@ -1386,7 +1386,7 @@ out_unlock: */ static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) { - return pmd_access_permitted(pmd, WRITE) || + return pmd_write(pmd) || ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); } 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..ca5674cbaff2 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); @@ -3948,7 +3949,7 @@ static int handle_pte_fault(struct vm_fault *vmf) if (unlikely(!pte_same(*vmf->pte, entry))) goto unlock; if (vmf->flags & FAULT_FLAG_WRITE) { - if (!pte_access_permitted(entry, WRITE)) + if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } @@ -4013,7 +4014,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, /* NUMA case for anonymous PUDs would go here */ - if (dirty && !pud_access_permitted(orig_pud, WRITE)) { + if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4046,7 +4047,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); - if (dirty && !pmd_access_permitted(orig_pmd, WRITE)) { + if (dirty && !pmd_write(orig_pmd)) { ret = wp_huge_pmd(&vmf, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4336,7 +4337,7 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = *ptep; - if (!pte_access_permitted(pte, flags & FOLL_WRITE)) + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); 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/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 1b659ab652fb..bbe8414b6ee7 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1214,7 +1214,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); if_num = if_incoming->if_num; orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); @@ -1224,7 +1224,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, } else { neigh_rq_count = 0; } - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ if (orig_eq_count > neigh_rq_count) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 341ceab8338d..e0e2bfcd6b3e 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -814,7 +814,7 @@ static bool batadv_v_gw_is_eligible(struct batadv_priv *bat_priv, } orig_gw = batadv_gw_node_get(bat_priv, orig_node); - if (!orig_node) + if (!orig_gw) goto out; if (batadv_v_gw_throughput_get(orig_gw, &orig_throughput) < 0) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index a98cf1104a30..ebe6e38934e4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -499,6 +499,8 @@ int batadv_frag_send_packet(struct sk_buff *skb, */ if (skb->priority >= 256 && skb->priority <= 263) frag_header.priority = skb->priority - 256; + else + frag_header.priority = 0; ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr); ether_addr_copy(frag_header.dest, orig_node->orig); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 15cd2139381e..ebc4e2241c77 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -482,7 +482,7 @@ static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars) /** * batadv_tp_sender_timeout - timer that fires in case of packet loss - * @arg: address of the related tp_vars + * @t: address to timer_list inside tp_vars * * If fired it means that there was packet loss. * Switch to Slow Start, set the ss_threshold to half of the current cwnd and @@ -1106,7 +1106,7 @@ static void batadv_tp_reset_receiver_timer(struct batadv_tp_vars *tp_vars) /** * batadv_tp_receiver_shutdown - stop a tp meter receiver when timeout is * reached without received ack - * @arg: address of the related tp_vars + * @t: address to timer_list inside tp_vars */ static void batadv_tp_receiver_shutdown(struct timer_list *t) { diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 1c4810919a0a..b9057478d69c 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> -#include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6b0ff396fa9d..a592ca025fc4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4293,7 +4293,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) - return; + goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. @@ -4302,7 +4302,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); + return; } + +err: + kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d6e7a642493b..a95a55f79137 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -16,7 +16,6 @@ #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> -#include <linux/list.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4573bccd6da..7a93359fbc72 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1428,7 +1428,7 @@ skip: static bool inetdev_valid_mtu(unsigned int mtu) { - return mtu >= 68; + return mtu >= IPV4_MIN_MTU; } static void inetdev_send_gratuitous_arp(struct net_device *dev, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d1f8f302dbf3..726f6b608274 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -89,6 +89,7 @@ #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> +#include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } +/* source address selection per RFC 3376 section 4.2.13 */ +static __be32 igmpv3_get_srcaddr(struct net_device *dev, + const struct flowi4 *fl4) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return htonl(INADDR_ANY); + + for_ifa(in_dev) { + if (inet_ifa_match(fl4->saddr, ifa)) + return fl4->saddr; + } endfor_ifa(in_dev); + + return htonl(INADDR_ANY); +} + static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; @@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; - pip->saddr = fl4.saddr; + pip->saddr = igmpv3_get_srcaddr(dev, &fl4); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); @@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, - int type, struct igmpv3_grec **ppgr) + int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; - if (!skb) - skb = igmpv3_newpack(dev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = igmpv3_newpack(dev, mtu); + if (!skb) + return NULL; + } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV4_MIN_MTU) + return skb; + isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || @@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); } } first = 1; @@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -538,7 +562,7 @@ empty_source: igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bb6239169b1a..9c1735632c8c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -266,7 +266,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, len = gre_hdr_len + sizeof(*ershdr); if (unlikely(!pskb_may_pull(skb, len))) - return -ENOMEM; + return PACKET_REJECT; iph = ip_hdr(skb); ershdr = (struct erspanhdr *)(skb->data + gre_hdr_len); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index fe6fee728ce4..5ddb1cb52bd4 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; mtu -= (dev->hard_header_len + t_hlen); - if (mtu < 68) - mtu = 68; + if (mtu < IPV4_MIN_MTU) + mtu = IPV4_MIN_MTU; return mtu; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f88221aebc9d..0c3c944a7b72 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -373,7 +373,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 4cbe5e80f3bf..2e0d339028bb 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -439,7 +439,6 @@ mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 17b4ca562944..69060e3abe85 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -813,12 +813,13 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { -#ifdef CONFIG_PROC_FS struct clusterip_net *cn = net_generic(net, clusterip_net_id); +#ifdef CONFIG_PROC_FS proc_remove(cn->procdir); cn->procdir = NULL; #endif nf_unregister_net_hook(net, &cip_arp_ops); + WARN_ON_ONCE(!list_empty(&cn->configs)); } static struct pernet_operations clusterip_net_ops = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 33b70bfd1122..125c1eab3eaa 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; + int hdrincl; err = -EMSGSIZE; if (len > 0xFFFF) goto out; + /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields + */ + hdrincl = inet->hdrincl; /* * Check the flags. */ @@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Linux does not mangle headers on raw sockets, * so that IP options + IP_HDRINCL is non-sense. */ - if (inet->hdrincl) + if (hdrincl) goto done; if (ipc.opt->opt.srr) { if (!daddr) @@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk) | - (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), + (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); - if (!inet->hdrincl) { + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; @@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto do_confirm; back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags, &ipc.sockc); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9550cc42de2d..45f750e85714 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -508,9 +508,6 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) u32 new_sample = tp->rcv_rtt_est.rtt_us; long m = sample; - if (m == 0) - m = 1; - if (new_sample != 0) { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially @@ -547,6 +544,8 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); + if (!delta_us) + delta_us = 1; tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -563,8 +562,11 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + u32 delta_us; + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); tcp_rcv_rtt_update(tp, delta_us, 0); } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 77ea45da0fe9..94e28350f420 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -848,7 +848,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 16df6dd44b98..968fda198376 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -264,6 +264,7 @@ void tcp_delack_timer_handler(struct sock *sk) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } + tcp_mstamp_refresh(tcp_sk(sk)); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } @@ -632,6 +633,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } + tcp_mstamp_refresh(tp); if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) { if (tp->linger2 >= 0) { const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index fc6d7d143f2c..844642682b83 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, - int type, struct mld2_grec **ppgr) + int type, struct mld2_grec **ppgr, unsigned int mtu) { - struct net_device *dev = pmc->idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr; - if (!skb) - skb = mld_newpack(pmc->idev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = mld_newpack(pmc->idev, mtu); + if (!skb) + return NULL; + } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV6_MIN_MTU) + return skb; + isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || @@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); } } first = 1; @@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -1814,7 +1819,7 @@ empty_source: mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index f06e25065a34..1d7ae9366335 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -458,7 +458,6 @@ mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 2b1a15846f9a..92c0047e7e33 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -33,13 +33,19 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; - return 0; + return nf_ct_netns_get(par->net, par->family); +} + +static void masquerade_tg6_destroy(const struct xt_tgdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_target masquerade_tg6_reg __read_mostly = { .name = "MASQUERADE", .family = NFPROTO_IPV6, .checkentry = masquerade_tg6_checkentry, + .destroy = masquerade_tg6_destroy, .target = masquerade_tg6, .targetsize = sizeof(struct nf_nat_range), .table = "nat", diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1f04ec0e4a7a..7178476b3d2f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -994,7 +994,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr), 0, 0); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 167f83b853e6..1621b6ab17ba 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -291,16 +291,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, int i; mutex_lock(&sta->ampdu_mlme.mtx); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_LEAVE_QBSS, reason != AGG_STOP_DESTROY_STA && reason != AGG_STOP_PEER_REQUEST); - } - mutex_unlock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_tx_ba_session(sta, i, reason); + mutex_unlock(&sta->ampdu_mlme.mtx); /* stopping might queue the work again - so cancel only afterwards */ cancel_work_sync(&sta->ampdu_mlme.work); diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index cf1bf2605c10..dc6347342e34 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -103,7 +103,6 @@ struct bitstr { #define INC_BIT(bs) if((++(bs)->bit)>7){(bs)->cur++;(bs)->bit=0;} #define INC_BITS(bs,b) if(((bs)->bit+=(b))>7){(bs)->cur+=(bs)->bit>>3;(bs)->bit&=7;} #define BYTE_ALIGN(bs) if((bs)->bit){(bs)->cur++;(bs)->bit=0;} -#define CHECK_BOUND(bs,n) if((bs)->cur+(n)>(bs)->end)return(H323_ERROR_BOUND) static unsigned int get_len(struct bitstr *bs); static unsigned int get_bit(struct bitstr *bs); static unsigned int get_bits(struct bitstr *bs, unsigned int b); @@ -165,6 +164,19 @@ static unsigned int get_len(struct bitstr *bs) return v; } +static int nf_h323_error_boundary(struct bitstr *bs, size_t bytes, size_t bits) +{ + bits += bs->bit; + bytes += bits / BITS_PER_BYTE; + if (bits % BITS_PER_BYTE > 0) + bytes++; + + if (*bs->cur + bytes > *bs->end) + return 1; + + return 0; +} + /****************************************************************************/ static unsigned int get_bit(struct bitstr *bs) { @@ -279,8 +291,8 @@ static int decode_bool(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); INC_BIT(bs); - - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -293,11 +305,14 @@ static int decode_oid(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; + len = *bs->cur++; bs->cur += len; + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; - CHECK_BOUND(bs, 0); return H323_ERROR_NONE; } @@ -319,6 +334,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, bs->cur += 2; break; case CONS: /* 64K < Range < 4G */ + if (nf_h323_error_boundary(bs, 0, 2)) + return H323_ERROR_BOUND; len = get_bits(bs, 2) + 1; BYTE_ALIGN(bs); if (base && (f->attr & DECODE)) { /* timeToLive */ @@ -330,7 +347,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, break; case UNCO: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); bs->cur += len; break; @@ -341,7 +359,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, PRINT("\n"); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -357,7 +376,8 @@ static int decode_enum(struct bitstr *bs, const struct field_t *f, INC_BITS(bs, f->sz); } - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -375,12 +395,14 @@ static int decode_bitstr(struct bitstr *bs, const struct field_t *f, len = f->lb; break; case WORD: /* 2-byte length */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) << 8; len += (*bs->cur++) + f->lb; break; case SEMI: - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); break; default: @@ -391,7 +413,8 @@ static int decode_bitstr(struct bitstr *bs, const struct field_t *f, bs->cur += len >> 3; bs->bit = len & 7; - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -404,12 +427,15 @@ static int decode_numstr(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); INC_BITS(bs, (len << 2)); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -440,15 +466,19 @@ static int decode_octstr(struct bitstr *bs, const struct field_t *f, break; case BYTE: /* Range == 256 */ BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) + f->lb; break; case SEMI: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs) + f->lb; break; default: /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); break; @@ -458,7 +488,8 @@ static int decode_octstr(struct bitstr *bs, const struct field_t *f, PRINT("\n"); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -473,10 +504,13 @@ static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, switch (f->sz) { case BYTE: /* Range == 256 */ BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) + f->lb; break; default: /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); break; @@ -484,7 +518,8 @@ static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, bs->cur += len << 1; - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -503,9 +538,13 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; /* Extensible? */ + if (nf_h323_error_boundary(bs, 0, 1)) + return H323_ERROR_BOUND; ext = (f->attr & EXT) ? get_bit(bs) : 0; /* Get fields bitmap */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -525,9 +564,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Decode */ if (son->attr & OPEN) { /* Open field */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -555,8 +596,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, return H323_ERROR_NONE; /* Get the extension bitmap */ + if (nf_h323_error_boundary(bs, 0, 7)) + return H323_ERROR_BOUND; bmp2_len = get_bits(bs, 7) + 1; - CHECK_BOUND(bs, (bmp2_len + 7) >> 3); + if (nf_h323_error_boundary(bs, 0, bmp2_len)) + return H323_ERROR_BOUND; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) @@ -567,9 +611,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, for (opt = 0; opt < bmp2_len; opt++, i++, son++) { /* Check Range */ if (i >= f->ub) { /* Newer Version? */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; bs->cur += len; continue; } @@ -583,9 +629,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, if (!((0x80000000 >> opt) & bmp2)) /* Not present */ continue; - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -623,22 +671,27 @@ static int decode_seqof(struct bitstr *bs, const struct field_t *f, switch (f->sz) { case BYTE: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; count = *bs->cur++; break; case WORD: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; count = *bs->cur++; count <<= 8; count += *bs->cur++; break; case SEMI: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; count = get_len(bs); break; default: + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; count = get_bits(bs, f->sz); break; } @@ -658,8 +711,11 @@ static int decode_seqof(struct bitstr *bs, const struct field_t *f, for (i = 0; i < count; i++) { if (son->attr & OPEN) { BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -710,11 +766,17 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; /* Decode the choice index number */ + if (nf_h323_error_boundary(bs, 0, 1)) + return H323_ERROR_BOUND; if ((f->attr & EXT) && get_bit(bs)) { ext = 1; + if (nf_h323_error_boundary(bs, 0, 7)) + return H323_ERROR_BOUND; type = get_bits(bs, 7) + f->lb; } else { ext = 0; + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; type = get_bits(bs, f->sz); if (type >= f->lb) return H323_ERROR_RANGE; @@ -727,8 +789,11 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, /* Check Range */ if (type >= f->ub) { /* Newer version? */ BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; bs->cur += len; return H323_ERROR_NONE; } @@ -742,8 +807,11 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, if (ext || (son->attr & OPEN)) { BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 59c08997bfdf..382d49792f42 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,6 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> -#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> @@ -1566,9 +1565,11 @@ static int ctnetlink_change_helper(struct nf_conn *ct, static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { - u_int32_t timeout = ntohl(nla_get_be32(cda[CTA_TIMEOUT])); + u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; - ct->timeout = nfct_time_stamp + timeout * HZ; + if (timeout > INT_MAX) + timeout = INT_MAX; + ct->timeout = nfct_time_stamp + (u32)timeout; if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; @@ -1768,6 +1769,7 @@ ctnetlink_create_conntrack(struct net *net, int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; + u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1776,7 +1778,10 @@ ctnetlink_create_conntrack(struct net *net, if (!cda[CTA_TIMEOUT]) goto err1; - ct->timeout = nfct_time_stamp + ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; + timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; + if (timeout > INT_MAX) + timeout = INT_MAX; + ct->timeout = (u32)timeout + nfct_time_stamp; rcu_read_lock(); if (cda[CTA_HELP]) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b12fc07111d0..37ef35b861f2 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1039,6 +1039,9 @@ static int tcp_packet(struct nf_conn *ct, IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; + else if (ct->proto.tcp.last_win == 0 && + timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) + timeout = timeouts[TCP_CONNTRACK_RETRANS]; else timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d8327b43e4dc..10798b357481 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5847,6 +5847,12 @@ static int __net_init nf_tables_init_net(struct net *net) return 0; } +static void __net_exit nf_tables_exit_net(struct net *net) +{ + WARN_ON_ONCE(!list_empty(&net->nft.af_info)); + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); +} + int __nft_release_basechain(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; @@ -5917,6 +5923,7 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi) static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, + .exit = nf_tables_exit_net, }; static int __init nf_tables_module_init(void) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 41628b393673..d33ce6d5ebce 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/errno.h> +#include <linux/capability.h> #include <net/netlink.h> #include <net/sock.h> @@ -407,6 +408,9 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; int ret = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) return -EINVAL; @@ -611,6 +615,9 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; bool tuple_set = false; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_cthelper_dump_table, @@ -678,6 +685,9 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth, *n; int j = 0, ret; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tb[NFCTH_NAME]) helper_name = nla_data(tb[NFCTH_NAME]); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e5afab86381c..e955bec0acc6 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1093,10 +1093,15 @@ static int __net_init nfnl_log_net_init(struct net *net) static void __net_exit nfnl_log_net_exit(struct net *net) { + struct nfnl_log_net *log = nfnl_log_pernet(net); + unsigned int i; + #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); + for (i = 0; i < INSTANCE_BUCKETS; i++) + WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index a16356cacec3..c09b36755ed7 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1512,10 +1512,15 @@ static int __net_init nfnl_queue_net_init(struct net *net) static void __net_exit nfnl_queue_net_exit(struct net *net) { + struct nfnl_queue_net *q = nfnl_queue_pernet(net); + unsigned int i; + nf_unregister_queue_handler(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif + for (i = 0; i < INSTANCE_BUCKETS; i++) + WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a0a93d987a3b..47ec1046ad11 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -214,6 +214,8 @@ static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 }, [NFTA_EXTHDR_LEN] = { .type = NLA_U32 }, [NFTA_EXTHDR_FLAGS] = { .type = NLA_U32 }, + [NFTA_EXTHDR_OP] = { .type = NLA_U32 }, + [NFTA_EXTHDR_SREG] = { .type = NLA_U32 }, }; static int nft_exthdr_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a77dd514297c..55802e97f906 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1729,8 +1729,17 @@ static int __net_init xt_net_init(struct net *net) return 0; } +static void __net_exit xt_net_exit(struct net *net) +{ + int i; + + for (i = 0; i < NFPROTO_NUMPROTO; i++) + WARN_ON_ONCE(!list_empty(&net->xt.tables[i])); +} + static struct pernet_operations xt_net_ops = { .init = xt_net_init, + .exit = xt_net_exit, }; static int __init xt_init(void) diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 041da0d9c06f..1f7fbd3c7e5a 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -27,6 +27,9 @@ static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, { struct sock_fprog_kern program; + if (len > XT_BPF_MAX_NUM_INSTR) + return -EINVAL; + program.len = len; program.filter = insns; @@ -55,6 +58,9 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) mm_segment_t oldfs = get_fs(); int retval, fd; + if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX) + return -EINVAL; + set_fs(KERNEL_DS); fd = bpf_obj_get_user(path, 0); set_fs(oldfs); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 36e14b1f061d..a34f314a8c23 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/capability.h> #include <linux/if.h> #include <linux/inetdevice.h> #include <linux/ip.h> @@ -70,6 +71,9 @@ static int xt_osf_add_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *kf = NULL, *sf; int err = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; @@ -115,6 +119,9 @@ static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *sf; int err = -ENOENT; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b9e0ee4e22f5..79cc1bf36e4a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -253,6 +253,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct sock *sk = skb->sk; int ret = -ENOMEM; + if (!net_eq(dev_net(dev), sock_net(sk))) + return 0; + dev_hold(dev); if (is_vmalloc_addr(skb->head)) diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 1e3f10e5da99..6445184b2759 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -22,7 +22,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbmark_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 2ea1f26c9e96..7221437ca3a6 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -22,7 +22,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbtcindex_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ddcf04b4ab43..b91ea03e3afa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -23,7 +23,6 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/kmod.h> -#include <linux/err.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -352,6 +351,8 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { struct tcf_chain *chain; + if (!block) + return; /* Hold a refcnt for all chains, except 0, so that they don't disappear * while we are iterating. */ @@ -378,8 +379,6 @@ void tcf_block_put(struct tcf_block *block) { struct tcf_block_ext_info ei = {0, }; - if (!block) - return; tcf_block_put_ext(block, block->q, &ei); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac152b4f4247..507859cdd1cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -45,7 +45,6 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> -#include <linux/netdevice.h> #include <linux/idr.h> struct tc_u_knode { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b6c4f536876b..0f1eab99ff4e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -795,6 +795,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; + if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) + goto nla_put_failure; if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; qlen = q->q.qlen; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 5ecc38f35d47..fc1286f499c1 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -68,6 +68,8 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + net_inc_ingress_queue(); + mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; @@ -78,7 +80,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) if (err) return err; - net_inc_ingress_queue(); sch->flags |= TCQ_F_CPUSTATS; return 0; @@ -172,6 +173,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + net_inc_ingress_queue(); + net_inc_egress_queue(); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; @@ -190,18 +194,11 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); if (err) - goto err_egress_block_get; - - net_inc_ingress_queue(); - net_inc_egress_queue(); + return err; sch->flags |= TCQ_F_CPUSTATS; return 0; - -err_egress_block_get: - tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); - return err; } static void clsact_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 9d874e60e032..f0747eb87dc4 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -157,6 +157,7 @@ static int red_offload(struct Qdisc *sch, bool enable) .handle = sch->handle, .parent = sch->parent, }; + int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -171,7 +172,14 @@ static int red_offload(struct Qdisc *sch, bool enable) opt.command = TC_RED_DESTROY; } - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); + + if (!err && enable) + sch->flags |= TCQ_F_OFFLOADED; + else + sch->flags &= ~TCQ_F_OFFLOADED; + + return err; } static void red_destroy(struct Qdisc *sch) @@ -274,7 +282,7 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) return red_change(sch, opt); } -static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) +static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) { struct net_device *dev = qdisc_dev(sch); struct tc_red_qopt_offload hw_stats = { @@ -286,21 +294,12 @@ static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) .stats.qstats = &sch->qstats, }, }; - int err; - opt->flags &= ~TC_RED_OFFLOADED; - if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) - return 0; - - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, - &hw_stats); - if (err == -EOPNOTSUPP) + if (!(sch->flags & TCQ_F_OFFLOADED)) return 0; - if (!err) - opt->flags |= TC_RED_OFFLOADED; - - return err; + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats); } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -319,7 +318,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) int err; sch->qstats.backlog = q->qdisc->qstats.backlog; - err = red_dump_offload(sch, &opt); + err = red_dump_offload_stats(sch, &opt); if (err) goto nla_put_failure; @@ -347,7 +346,7 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .marked = q->stats.prob_mark + q->stats.forced_mark, }; - if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) { + if (sch->flags & TCQ_F_OFFLOADED) { struct red_stats hw_stats = {0}; struct tc_red_qopt_offload hw_stats_request = { .command = TC_RED_XSTATS, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index eb17a911aa29..3253f724a995 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3891,13 +3891,17 @@ static int sctp_setsockopt_reset_streams(struct sock *sk, struct sctp_association *asoc; int retval = -EINVAL; - if (optlen < sizeof(struct sctp_reset_streams)) + if (optlen < sizeof(*params)) return -EINVAL; params = memdup_user(optval, optlen); if (IS_ERR(params)) return PTR_ERR(params); + if (params->srs_number_streams * sizeof(__u16) > + optlen - sizeof(*params)) + goto out; + asoc = sctp_id2assoc(sk, params->srs_assoc_id); if (!asoc) goto out; 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/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 333b9d697ae5..33b74fd84051 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1001,6 +1001,7 @@ void xprt_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + unsigned int connect_cookie; int status, numreqs; dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); @@ -1024,6 +1025,7 @@ void xprt_transmit(struct rpc_task *task) } else if (!req->rq_bytes_sent) return; + connect_cookie = xprt->connect_cookie; req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); trace_xprt_transmit(xprt, req->rq_xid, status); @@ -1047,20 +1049,28 @@ void xprt_transmit(struct rpc_task *task) xprt->stat.bklog_u += xprt->backlog.qlen; xprt->stat.sending_u += xprt->sending.qlen; xprt->stat.pending_u += xprt->pending.qlen; + spin_unlock_bh(&xprt->transport_lock); - /* Don't race with disconnect */ - if (!xprt_connected(xprt)) - task->tk_status = -ENOTCONN; - else { + req->rq_connect_cookie = connect_cookie; + if (rpc_reply_expected(task) && !READ_ONCE(req->rq_reply_bytes_recvd)) { /* - * Sleep on the pending queue since - * we're expecting a reply. + * Sleep on the pending queue if we're expecting a reply. + * The spinlock ensures atomicity between the test of + * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). */ - if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) + spin_lock(&xprt->recv_lock); + if (!req->rq_reply_bytes_recvd) { rpc_sleep_on(&xprt->pending, task, xprt_timer); - req->rq_connect_cookie = xprt->connect_cookie; + /* + * Send an extra queue wakeup call if the + * connection was dropped in case the call to + * rpc_sleep_on() raced. + */ + if (!xprt_connected(xprt)) + xprt_wake_pending_tasks(xprt, -ENOTCONN); + } + spin_unlock(&xprt->recv_lock); } - spin_unlock_bh(&xprt->transport_lock); } static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index ed34dc0f144c..a3f2ab283aeb 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1408,11 +1408,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", __func__, rep, req, be32_to_cpu(rep->rr_xid)); - if (list_empty(&req->rl_registered) && - !test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) - rpcrdma_complete_rqst(rep); - else - queue_work(rpcrdma_receive_wq, &rep->rr_work); + queue_work_on(req->rl_cpu, rpcrdma_receive_wq, &rep->rr_work); return; out_badstatus: diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 646c24494ea7..6ee1ad8978f3 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -52,6 +52,7 @@ #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/sunrpc/addr.h> +#include <linux/smp.h> #include "xprt_rdma.h" @@ -656,6 +657,7 @@ xprt_rdma_allocate(struct rpc_task *task) task->tk_pid, __func__, rqst->rq_callsize, rqst->rq_rcvsize, req); + req->rl_cpu = smp_processor_id(); req->rl_connect_cookie = 0; /* our reserved value */ rpcrdma_set_xprtdata(rqst, req); rqst->rq_buffer = req->rl_sendbuf->rg_base; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 710b3f77db82..8607c029c0dd 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -83,7 +83,7 @@ rpcrdma_alloc_wq(void) struct workqueue_struct *recv_wq; recv_wq = alloc_workqueue("xprtrdma_receive", - WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_HIGHPRI, + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!recv_wq) return -ENOMEM; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 51686d9eac5f..1342f743f1c4 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -342,6 +342,7 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_list; + int rl_cpu; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 5d18c0caa92b..41127d0b925e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1140,7 +1140,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, __skb_dequeue(arrvq); __skb_queue_tail(inputq, skb); } - refcount_dec(&skb->users); + kfree_skb(skb); spin_unlock_bh(&inputq->lock); continue; } diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 278d979c211a..d7d6cb00c47b 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -25,17 +25,45 @@ endif $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) @$(kecho) " GEN $@" - @echo '#include "reg.h"' > $@ - @echo 'const u8 shipped_regdb_certs[] = {' >> $@ - @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done - @echo '};' >> $@ - @echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@ + @(set -e; \ + allf=""; \ + for f in $^ ; do \ + # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ + thisf=$$(od -An -v -tx1 < $$f | \ + sed -e 's/ /\n/g' | \ + sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ + sed -e 's/^/0x/;s/$$/,/'); \ + # file should not be empty - maybe command substitution failed? \ + test ! -z "$$thisf";\ + allf=$$allf$$thisf;\ + done; \ + ( \ + echo '#include "reg.h"'; \ + echo 'const u8 shipped_regdb_certs[] = {'; \ + echo "$$allf"; \ + echo '};'; \ + echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ + ) >> $@) $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @$(kecho) " GEN $@" - @echo '#include "reg.h"' > $@ - @echo 'const u8 extra_regdb_certs[] = {' >> $@ - @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done - @echo '};' >> $@ - @echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@ + @(set -e; \ + allf=""; \ + for f in $^ ; do \ + # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ + thisf=$$(od -An -v -tx1 < $$f | \ + sed -e 's/ /\n/g' | \ + sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ + sed -e 's/^/0x/;s/$$/,/'); \ + # file should not be empty - maybe command substitution failed? \ + test ! -z "$$thisf";\ + allf=$$allf$$thisf;\ + done; \ + ( \ + echo '#include "reg.h"'; \ + echo 'const u8 extra_regdb_certs[] = {'; \ + echo "$$allf"; \ + echo '};'; \ + echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);'; \ + ) >> $@) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 040aa79e1d9d..31031f10fe56 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6233,28 +6233,6 @@ sub process { } } -# whine about ACCESS_ONCE - if ($^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/sound/core/rawmidi.c b/sound/core/rawmidi.c index b3b353d72527..f055ca10bbc1 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -579,15 +579,14 @@ static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream, return 0; } -int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +static int __snd_rawmidi_info_select(struct snd_card *card, + struct snd_rawmidi_info *info) { struct snd_rawmidi *rmidi; struct snd_rawmidi_str *pstr; struct snd_rawmidi_substream *substream; - mutex_lock(®ister_mutex); rmidi = snd_rawmidi_search(card, info->device); - mutex_unlock(®ister_mutex); if (!rmidi) return -ENXIO; if (info->stream < 0 || info->stream > 1) @@ -603,6 +602,16 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info } return -ENXIO; } + +int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +{ + int ret; + + mutex_lock(®ister_mutex); + ret = __snd_rawmidi_info_select(card, info); + mutex_unlock(®ister_mutex); + return ret; +} EXPORT_SYMBOL(snd_rawmidi_info_select); static int snd_rawmidi_info_select_user(struct snd_card *card, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index c19c81d230bd..b4f1b6e88305 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -55,10 +55,11 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); #define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b) #define is_geminilake(codec) (((codec)->core.vendor_id == 0x8086280d) || \ ((codec)->core.vendor_id == 0x80862800)) +#define is_cannonlake(codec) ((codec)->core.vendor_id == 0x8086280c) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ - || is_kabylake(codec)) || is_geminilake(codec) - + || is_kabylake(codec)) || is_geminilake(codec) \ + || is_cannonlake(codec) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) #define is_valleyview_plus(codec) (is_valleyview(codec) || is_cherryview(codec)) @@ -3841,6 +3842,7 @@ HDA_CODEC_ENTRY(0x80862808, "Broadwell HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), +HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4b21f71d685c..6a4db00511ab 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5185,6 +5185,22 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } } +/* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ +static void alc274_fixup_bind_dacs(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + static hda_nid_t preferred_pairs[] = { + 0x21, 0x03, 0x1b, 0x03, 0x16, 0x02, + 0 + }; + + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + spec->gen.preferred_dacs = preferred_pairs; +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -5302,6 +5318,8 @@ enum { ALC233_FIXUP_LENOVO_MULTI_CODECS, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC700_FIXUP_INTEL_REFERENCE, + ALC274_FIXUP_DELL_BIND_DACS, + ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, }; static const struct hda_fixup alc269_fixups[] = { @@ -6112,6 +6130,21 @@ static const struct hda_fixup alc269_fixups[] = { {} } }, + [ALC274_FIXUP_DELL_BIND_DACS] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_bind_dacs, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC274_FIXUP_DELL_AIO_LINEOUT_VERB] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1b, 0x0401102f }, + { } + }, + .chained = true, + .chain_id = ALC274_FIXUP_DELL_BIND_DACS + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6578,7 +6611,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x1b, 0x90a70130}, {0x21, 0x03211020}), - SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, {0x12, 0xb7a60130}, {0x13, 0xb8a61140}, {0x16, 0x90170110}, diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 7c9e361b2200..2b4ceda36291 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2173,20 +2173,25 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid, kctl->private_value = (unsigned long)namelist; kctl->private_free = usb_mixer_selector_elem_free; - nameid = uac_selector_unit_iSelector(desc); + /* check the static mapping table at first */ len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name)); - if (len) - ; - else if (nameid) - len = snd_usb_copy_string_desc(state, nameid, kctl->id.name, - sizeof(kctl->id.name)); - else - len = get_term_name(state, &state->oterm, - kctl->id.name, sizeof(kctl->id.name), 0); - if (!len) { - strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* no mapping ? */ + /* if iSelector is given, use it */ + nameid = uac_selector_unit_iSelector(desc); + if (nameid) + len = snd_usb_copy_string_desc(state, nameid, + kctl->id.name, + sizeof(kctl->id.name)); + /* ... or pick up the terminal name at next */ + if (!len) + len = get_term_name(state, &state->oterm, + kctl->id.name, sizeof(kctl->id.name), 0); + /* ... or use the fixed string "USB" as the last resort */ + if (!len) + strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* and add the proper suffix */ if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR) append_ctl_name(kctl, " Clock Source"); else if ((state->oterm.type & 0xff00) == 0x0100) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 77eecaa4db1f..a66ef5777887 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1166,10 +1166,11 @@ static bool is_marantz_denon_dac(unsigned int id) /* TEAC UD-501/UD-503/NT-503 USB DACs need a vendor cmd to switch * between PCM/DOP and native DSD mode */ -static bool is_teac_50X_dac(unsigned int id) +static bool is_teac_dsd_dac(unsigned int id) { switch (id) { case USB_ID(0x0644, 0x8043): /* TEAC UD-501/UD-503/NT-503 */ + case USB_ID(0x0644, 0x8044): /* Esoteric D-05X */ return true; } return false; @@ -1202,7 +1203,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs, break; } mdelay(20); - } else if (is_teac_50X_dac(subs->stream->chip->usb_id)) { + } else if (is_teac_dsd_dac(subs->stream->chip->usb_id)) { /* Vendor mode switch cmd is required. */ switch (fmt->altsetting) { case 3: /* DSD mode (DSD_U32) requested */ @@ -1392,7 +1393,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, } /* TEAC devices with USB DAC functionality */ - if (is_teac_50X_dac(chip->usb_id)) { + if (is_teac_dsd_dac(chip->usb_id)) { if (fp->altsetting == 3) return SNDRV_PCM_FMTBIT_DSD_U32_BE; } 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/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..13a58531e6fa --- /dev/null +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,7 @@ +#if defined(__aarch64__) +#include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" +#elif defined(__s390__) +#include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#else +#include <uapi/asm-generic/bpf_perf_event.h> +#endif 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/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 21a2d76b67dc..792af7c3b74f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,19 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(CURDIR))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -endif -include $(srctree)/tools/scripts/Makefile.arch - -$(call detected_var,SRCARCH) - LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf APIDIR := ../../../include/uapi -ASMDIR:= ../../../arch/$(ARCH)/include/uapi GENDIR := ../../../../include/generated GENHDR := $(GENDIR)/autoconf.h @@ -21,7 +10,7 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(ASMDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index 8a1cd1616de4..c9c81614a66a 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -50,14 +50,14 @@ static int parse_status(const char *value) while (*c != '\0') { int port, status, speed, devid; - unsigned long socket; + int sockfd; char lbusid[SYSFS_BUS_ID_SIZE]; struct usbip_imported_device *idev; char hub[3]; - ret = sscanf(c, "%2s %d %d %d %x %lx %31s\n", + ret = sscanf(c, "%2s %d %d %d %x %u %31s\n", hub, &port, &status, &speed, - &devid, &socket, lbusid); + &devid, &sockfd, lbusid); if (ret < 5) { dbg("sscanf failed: %d", ret); @@ -66,7 +66,7 @@ static int parse_status(const char *value) dbg("hub %s port %d status %d speed %d devid %x", hub, port, status, speed, devid); - dbg("socket %lx lbusid %s", socket, lbusid); + dbg("sockfd %u lbusid %s", sockfd, lbusid); /* if a device is connected, look at it */ idev = &vhci_driver->idev[port]; @@ -106,7 +106,7 @@ static int parse_status(const char *value) return 0; } -#define MAX_STATUS_NAME 16 +#define MAX_STATUS_NAME 18 static int refresh_imported_device_list(void) { 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 |