diff options
735 files changed, 7271 insertions, 3653 deletions
diff --git a/.clang-format b/.clang-format index 1247d54f9e49..8d01225bfcb7 100644 --- a/.clang-format +++ b/.clang-format @@ -535,6 +535,7 @@ ForEachMacros: - 'perf_hpp_list__for_each_sort_list_safe' - 'perf_pmu__for_each_hybrid_pmu' - 'ping_portaddr_for_each_entry' + - 'ping_portaddr_for_each_entry_rcu' - 'plist_for_each' - 'plist_for_each_continue' - 'plist_for_each_entry' @@ -29,6 +29,7 @@ Alexandre Belloni <[email protected]> <alexandre.belloni@free-electr Alexei Starovoitov <[email protected]> <[email protected]> Alexei Starovoitov <[email protected]> <[email protected]> Alexei Starovoitov <[email protected]> <[email protected]> +Alex Hung <[email protected]> <[email protected]> Alex Shi <[email protected]> <[email protected]> Alex Shi <[email protected]> <[email protected]> Alex Shi <[email protected]> <[email protected]> @@ -286,6 +287,7 @@ Matthew Wilcox <[email protected]> <[email protected]> Matthew Wilcox <[email protected]> <[email protected]> Matthias Fuchs <[email protected]> <[email protected]> Matthieu CASTET <[email protected]> +Matti Vaittinen <[email protected]> <[email protected]> Matt Ranostay <[email protected]> <[email protected]> Matt Ranostay <[email protected]> Matthew Ranostay <[email protected]> Matt Ranostay <[email protected]> <[email protected]> @@ -371,6 +373,8 @@ Ricardo Ribalda <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> +Muchun Song <[email protected]> <[email protected]> +Muchun Song <[email protected]> <[email protected]> Ross Zwisler <[email protected]> <[email protected]> Rudolf Marek <[email protected]> Rui Saraiva <[email protected]> @@ -382,6 +386,7 @@ Santosh Shilimkar <[email protected]> Santosh Shilimkar <[email protected]> Sarangdhar Joshi <[email protected]> Sascha Hauer <[email protected]> +Satya Priya <[email protected]> <[email protected]> S.Çağlar Onur <[email protected]> Sean Christopherson <[email protected]> <[email protected]> Sean Nyekjaer <[email protected]> <[email protected]> @@ -389,6 +394,7 @@ Sebastian Reichel <[email protected]> <[email protected]> Sebastian Reichel <[email protected]> <[email protected]> Sedat Dilek <[email protected]> <[email protected]> Seth Forshee <[email protected]> <[email protected]> +Shannon Nelson <[email protected]> <[email protected]> Shiraz Hashim <[email protected]> <[email protected]> Shuah Khan <[email protected]> <[email protected]> Shuah Khan <[email protected]> <[email protected]> @@ -2452,6 +2452,10 @@ S: 482 Shadowgraph Dr. S: San Jose, CA 95110 S: USA +N: Michal Marek +D: Kbuild Maintainer 2009-2017 + N: Martin Mares W: http://www.ucw.cz/~mj/ diff --git a/Documentation/RCU/arrayRCU.rst b/Documentation/RCU/arrayRCU.rst deleted file mode 100644 index a5f2ff8fc54c..000000000000 --- a/Documentation/RCU/arrayRCU.rst +++ /dev/null @@ -1,165 +0,0 @@ -.. _array_rcu_doc: - -Using RCU to Protect Read-Mostly Arrays -======================================= - -Although RCU is more commonly used to protect linked lists, it can -also be used to protect arrays. Three situations are as follows: - -1. :ref:`Hash Tables <hash_tables>` - -2. :ref:`Static Arrays <static_arrays>` - -3. :ref:`Resizable Arrays <resizable_arrays>` - -Each of these three situations involves an RCU-protected pointer to an -array that is separately indexed. It might be tempting to consider use -of RCU to instead protect the index into an array, however, this use -case is **not** supported. The problem with RCU-protected indexes into -arrays is that compilers can play way too many optimization games with -integers, which means that the rules governing handling of these indexes -are far more trouble than they are worth. If RCU-protected indexes into -arrays prove to be particularly valuable (which they have not thus far), -explicit cooperation from the compiler will be required to permit them -to be safely used. - -That aside, each of the three RCU-protected pointer situations are -described in the following sections. - -.. _hash_tables: - -Situation 1: Hash Tables ------------------------- - -Hash tables are often implemented as an array, where each array entry -has a linked-list hash chain. Each hash chain can be protected by RCU -as described in listRCU.rst. This approach also applies to other -array-of-list situations, such as radix trees. - -.. _static_arrays: - -Situation 2: Static Arrays --------------------------- - -Static arrays, where the data (rather than a pointer to the data) is -located in each array element, and where the array is never resized, -have not been used with RCU. Rik van Riel recommends using seqlock in -this situation, which would also have minimal read-side overhead as long -as updates are rare. - -Quick Quiz: - Why is it so important that updates be rare when using seqlock? - -:ref:`Answer to Quick Quiz <answer_quick_quiz_seqlock>` - -.. _resizable_arrays: - -Situation 3: Resizable Arrays ------------------------------- - -Use of RCU for resizable arrays is demonstrated by the grow_ary() -function formerly used by the System V IPC code. The array is used -to map from semaphore, message-queue, and shared-memory IDs to the data -structure that represents the corresponding IPC construct. The grow_ary() -function does not acquire any locks; instead its caller must hold the -ids->sem semaphore. - -The grow_ary() function, shown below, does some limit checks, allocates a -new ipc_id_ary, copies the old to the new portion of the new, initializes -the remainder of the new, updates the ids->entries pointer to point to -the new array, and invokes ipc_rcu_putref() to free up the old array. -Note that rcu_assign_pointer() is used to update the ids->entries pointer, -which includes any memory barriers required on whatever architecture -you are running on:: - - static int grow_ary(struct ipc_ids* ids, int newsize) - { - struct ipc_id_ary* new; - struct ipc_id_ary* old; - int i; - int size = ids->entries->size; - - if(newsize > IPCMNI) - newsize = IPCMNI; - if(newsize <= size) - return newsize; - - new = ipc_rcu_alloc(sizeof(struct kern_ipc_perm *)*newsize + - sizeof(struct ipc_id_ary)); - if(new == NULL) - return size; - new->size = newsize; - memcpy(new->p, ids->entries->p, - sizeof(struct kern_ipc_perm *)*size + - sizeof(struct ipc_id_ary)); - for(i=size;i<newsize;i++) { - new->p[i] = NULL; - } - old = ids->entries; - - /* - * Use rcu_assign_pointer() to make sure the memcpyed - * contents of the new array are visible before the new - * array becomes visible. - */ - rcu_assign_pointer(ids->entries, new); - - ipc_rcu_putref(old); - return newsize; - } - -The ipc_rcu_putref() function decrements the array's reference count -and then, if the reference count has dropped to zero, uses call_rcu() -to free the array after a grace period has elapsed. - -The array is traversed by the ipc_lock() function. This function -indexes into the array under the protection of rcu_read_lock(), -using rcu_dereference() to pick up the pointer to the array so -that it may later safely be dereferenced -- memory barriers are -required on the Alpha CPU. Since the size of the array is stored -with the array itself, there can be no array-size mismatches, so -a simple check suffices. The pointer to the structure corresponding -to the desired IPC object is placed in "out", with NULL indicating -a non-existent entry. After acquiring "out->lock", the "out->deleted" -flag indicates whether the IPC object is in the process of being -deleted, and, if not, the pointer is returned:: - - struct kern_ipc_perm* ipc_lock(struct ipc_ids* ids, int id) - { - struct kern_ipc_perm* out; - int lid = id % SEQ_MULTIPLIER; - struct ipc_id_ary* entries; - - rcu_read_lock(); - entries = rcu_dereference(ids->entries); - if(lid >= entries->size) { - rcu_read_unlock(); - return NULL; - } - out = entries->p[lid]; - if(out == NULL) { - rcu_read_unlock(); - return NULL; - } - spin_lock(&out->lock); - - /* ipc_rmid() may have already freed the ID while ipc_lock - * was spinning: here verify that the structure is still valid - */ - if (out->deleted) { - spin_unlock(&out->lock); - rcu_read_unlock(); - return NULL; - } - return out; - } - -.. _answer_quick_quiz_seqlock: - -Answer to Quick Quiz: - Why is it so important that updates be rare when using seqlock? - - The reason that it is important that updates be rare when - using seqlock is that frequent updates can livelock readers. - One way to avoid this problem is to assign a seqlock for - each array entry rather than to the entire array. diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index 048c5bc1f813..cc361fb01ed4 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -32,8 +32,8 @@ over a rather long period of time, but improvements are always welcome! for lockless updates. This does result in the mildly counter-intuitive situation where rcu_read_lock() and rcu_read_unlock() are used to protect updates, however, this - approach provides the same potential simplifications that garbage - collectors do. + approach can provide the same simplifications to certain types + of lockless algorithms that garbage collectors do. 1. Does the update code have proper mutual exclusion? @@ -49,12 +49,12 @@ over a rather long period of time, but improvements are always welcome! them -- even x86 allows later loads to be reordered to precede earlier stores), and be prepared to explain why this added complexity is worthwhile. If you choose #c, be prepared to - explain how this single task does not become a major bottleneck on - big multiprocessor machines (for example, if the task is updating - information relating to itself that other tasks can read, there - by definition can be no bottleneck). Note that the definition - of "large" has changed significantly: Eight CPUs was "large" - in the year 2000, but a hundred CPUs was unremarkable in 2017. + explain how this single task does not become a major bottleneck + on large systems (for example, if the task is updating information + relating to itself that other tasks can read, there by definition + can be no bottleneck). Note that the definition of "large" has + changed significantly: Eight CPUs was "large" in the year 2000, + but a hundred CPUs was unremarkable in 2017. 2. Do the RCU read-side critical sections make proper use of rcu_read_lock() and friends? These primitives are needed @@ -97,33 +97,38 @@ over a rather long period of time, but improvements are always welcome! b. Proceed as in (a) above, but also maintain per-element locks (that are acquired by both readers and writers) - that guard per-element state. Of course, fields that - the readers refrain from accessing can be guarded by - some other lock acquired only by updaters, if desired. + that guard per-element state. Fields that the readers + refrain from accessing can be guarded by some other lock + acquired only by updaters, if desired. - This works quite well, also. + This also works quite well. c. Make updates appear atomic to readers. For example, pointer updates to properly aligned fields will appear atomic, as will individual atomic primitives. Sequences of operations performed under a lock will *not* appear to be atomic to RCU readers, nor will sequences - of multiple atomic primitives. + of multiple atomic primitives. One alternative is to + move multiple individual fields to a separate structure, + thus solving the multiple-field problem by imposing an + additional level of indirection. This can work, but is starting to get a bit tricky. - d. Carefully order the updates and the reads so that - readers see valid data at all phases of the update. - This is often more difficult than it sounds, especially - given modern CPUs' tendency to reorder memory references. - One must usually liberally sprinkle memory barriers - (smp_wmb(), smp_rmb(), smp_mb()) through the code, - making it difficult to understand and to test. - - It is usually better to group the changing data into - a separate structure, so that the change may be made - to appear atomic by updating a pointer to reference - a new structure containing updated values. + d. Carefully order the updates and the reads so that readers + see valid data at all phases of the update. This is often + more difficult than it sounds, especially given modern + CPUs' tendency to reorder memory references. One must + usually liberally sprinkle memory-ordering operations + through the code, making it difficult to understand and + to test. Where it works, it is better to use things + like smp_store_release() and smp_load_acquire(), but in + some cases the smp_mb() full memory barrier is required. + + As noted earlier, it is usually better to group the + changing data into a separate structure, so that the + change may be made to appear atomic by updating a pointer + to reference a new structure containing updated values. 4. Weakly ordered CPUs pose special challenges. Almost all CPUs are weakly ordered -- even x86 CPUs allow later loads to be @@ -188,26 +193,29 @@ over a rather long period of time, but improvements are always welcome! when publicizing a pointer to a structure that can be traversed by an RCU read-side critical section. -5. If call_rcu() or call_srcu() is used, the callback function will - be called from softirq context. In particular, it cannot block. - If you need the callback to block, run that code in a workqueue - handler scheduled from the callback. The queue_rcu_work() - function does this for you in the case of call_rcu(). +5. If any of call_rcu(), call_srcu(), call_rcu_tasks(), + call_rcu_tasks_rude(), or call_rcu_tasks_trace() is used, + the callback function may be invoked from softirq context, + and in any case with bottom halves disabled. In particular, + this callback function cannot block. If you need the callback + to block, run that code in a workqueue handler scheduled from + the callback. The queue_rcu_work() function does this for you + in the case of call_rcu(). 6. Since synchronize_rcu() can block, it cannot be called from any sort of irq context. The same rule applies - for synchronize_srcu(), synchronize_rcu_expedited(), and - synchronize_srcu_expedited(). + for synchronize_srcu(), synchronize_rcu_expedited(), + synchronize_srcu_expedited(), synchronize_rcu_tasks(), + synchronize_rcu_tasks_rude(), and synchronize_rcu_tasks_trace(). The expedited forms of these primitives have the same semantics - as the non-expedited forms, but expediting is both expensive and - (with the exception of synchronize_srcu_expedited()) unfriendly - to real-time workloads. Use of the expedited primitives should - be restricted to rare configuration-change operations that would - not normally be undertaken while a real-time workload is running. - However, real-time workloads can use rcupdate.rcu_normal kernel - boot parameter to completely disable expedited grace periods, - though this might have performance implications. + as the non-expedited forms, but expediting is more CPU intensive. + Use of the expedited primitives should be restricted to rare + configuration-change operations that would not normally be + undertaken while a real-time workload is running. Note that + IPI-sensitive real-time workloads can use the rcupdate.rcu_normal + kernel boot parameter to completely disable expedited grace + periods, though this might have performance implications. In particular, if you find yourself invoking one of the expedited primitives repeatedly in a loop, please do everyone a favor: @@ -215,8 +223,9 @@ over a rather long period of time, but improvements are always welcome! a single non-expedited primitive to cover the entire batch. This will very likely be faster than the loop containing the expedited primitive, and will be much much easier on the rest - of the system, especially to real-time workloads running on - the rest of the system. + of the system, especially to real-time workloads running on the + rest of the system. Alternatively, instead use asynchronous + primitives such as call_rcu(). 7. As of v4.20, a given kernel implements only one RCU flavor, which is RCU-sched for PREEMPTION=n and RCU-preempt for PREEMPTION=y. @@ -239,7 +248,8 @@ over a rather long period of time, but improvements are always welcome! the corresponding readers must use rcu_read_lock_trace() and rcu_read_unlock_trace(). If an updater uses call_rcu_tasks_rude() or synchronize_rcu_tasks_rude(), then the corresponding readers - must use anything that disables interrupts. + must use anything that disables preemption, for example, + preempt_disable() and preempt_enable(). Mixing things up will result in confusion and broken kernels, and has even resulted in an exploitable security issue. Therefore, @@ -253,15 +263,16 @@ over a rather long period of time, but improvements are always welcome! that this usage is safe is that readers can use anything that disables BH when updaters use call_rcu() or synchronize_rcu(). -8. Although synchronize_rcu() is slower than is call_rcu(), it - usually results in simpler code. So, unless update performance is - critically important, the updaters cannot block, or the latency of - synchronize_rcu() is visible from userspace, synchronize_rcu() - should be used in preference to call_rcu(). Furthermore, - kfree_rcu() usually results in even simpler code than does - synchronize_rcu() without synchronize_rcu()'s multi-millisecond - latency. So please take advantage of kfree_rcu()'s "fire and - forget" memory-freeing capabilities where it applies. +8. Although synchronize_rcu() is slower than is call_rcu(), + it usually results in simpler code. So, unless update + performance is critically important, the updaters cannot block, + or the latency of synchronize_rcu() is visible from userspace, + synchronize_rcu() should be used in preference to call_rcu(). + Furthermore, kfree_rcu() and kvfree_rcu() usually result + in even simpler code than does synchronize_rcu() without + synchronize_rcu()'s multi-millisecond latency. So please take + advantage of kfree_rcu()'s and kvfree_rcu()'s "fire and forget" + memory-freeing capabilities where it applies. An especially important property of the synchronize_rcu() primitive is that it automatically self-limits: if grace periods @@ -271,8 +282,8 @@ over a rather long period of time, but improvements are always welcome! cases where grace periods are delayed, as failing to do so can result in excessive realtime latencies or even OOM conditions. - Ways of gaining this self-limiting property when using call_rcu() - include: + Ways of gaining this self-limiting property when using call_rcu(), + kfree_rcu(), or kvfree_rcu() include: a. Keeping a count of the number of data-structure elements used by the RCU-protected data structure, including @@ -304,18 +315,21 @@ over a rather long period of time, but improvements are always welcome! here is that superuser already has lots of ways to crash the machine. - d. Periodically invoke synchronize_rcu(), permitting a limited - number of updates per grace period. Better yet, periodically - invoke rcu_barrier() to wait for all outstanding callbacks. + d. Periodically invoke rcu_barrier(), permitting a limited + number of updates per grace period. - The same cautions apply to call_srcu() and kfree_rcu(). + The same cautions apply to call_srcu(), call_rcu_tasks(), + call_rcu_tasks_rude(), and call_rcu_tasks_trace(). This is + why there is an srcu_barrier(), rcu_barrier_tasks(), + rcu_barrier_tasks_rude(), and rcu_barrier_tasks_rude(), + respectively. - Note that although these primitives do take action to avoid memory - exhaustion when any given CPU has too many callbacks, a determined - user could still exhaust memory. This is especially the case - if a system with a large number of CPUs has been configured to - offload all of its RCU callbacks onto a single CPU, or if the - system has relatively little free memory. + Note that although these primitives do take action to avoid + memory exhaustion when any given CPU has too many callbacks, + a determined user or administrator can still exhaust memory. + This is especially the case if a system with a large number of + CPUs has been configured to offload all of its RCU callbacks onto + a single CPU, or if the system has relatively little free memory. 9. All RCU list-traversal primitives, which include rcu_dereference(), list_for_each_entry_rcu(), and @@ -344,14 +358,14 @@ over a rather long period of time, but improvements are always welcome! and you don't hold the appropriate update-side lock, you *must* use the "_rcu()" variants of the list macros. Failing to do so will break Alpha, cause aggressive compilers to generate bad code, - and confuse people trying to read your code. + and confuse people trying to understand your code. 11. Any lock acquired by an RCU callback must be acquired elsewhere - with softirq disabled, e.g., via spin_lock_irqsave(), - spin_lock_bh(), etc. Failing to disable softirq on a given - acquisition of that lock will result in deadlock as soon as - the RCU softirq handler happens to run your RCU callback while - interrupting that acquisition's critical section. + with softirq disabled, e.g., via spin_lock_bh(). Failing to + disable softirq on a given acquisition of that lock will result + in deadlock as soon as the RCU softirq handler happens to run + your RCU callback while interrupting that acquisition's critical + section. 12. RCU callbacks can be and are executed in parallel. In many cases, the callback code simply wrappers around kfree(), so that this @@ -372,7 +386,17 @@ over a rather long period of time, but improvements are always welcome! for some real-time workloads, this is the whole point of using the rcu_nocbs= kernel boot parameter. -13. Unlike other forms of RCU, it *is* permissible to block in an + In addition, do not assume that callbacks queued in a given order + will be invoked in that order, even if they all are queued on the + same CPU. Furthermore, do not assume that same-CPU callbacks will + be invoked serially. For example, in recent kernels, CPUs can be + switched between offloaded and de-offloaded callback invocation, + and while a given CPU is undergoing such a switch, its callbacks + might be concurrently invoked by that CPU's softirq handler and + that CPU's rcuo kthread. At such times, that CPU's callbacks + might be executed both concurrently and out of order. + +13. Unlike most flavors of RCU, it *is* permissible to block in an SRCU read-side critical section (demarked by srcu_read_lock() and srcu_read_unlock()), hence the "SRCU": "sleepable RCU". Please note that if you don't need to sleep in read-side critical @@ -412,6 +436,12 @@ over a rather long period of time, but improvements are always welcome! never sends IPIs to other CPUs, so it is easier on real-time workloads than is synchronize_rcu_expedited(). + It is also permissible to sleep in RCU Tasks Trace read-side + critical, which are delimited by rcu_read_lock_trace() and + rcu_read_unlock_trace(). However, this is a specialized flavor + of RCU, and you should not use it without first checking with + its current users. In most cases, you should instead use SRCU. + Note that rcu_assign_pointer() relates to SRCU just as it does to other forms of RCU, but instead of rcu_dereference() you should use srcu_dereference() in order to avoid lockdep splats. @@ -442,50 +472,62 @@ over a rather long period of time, but improvements are always welcome! find problems as follows: CONFIG_PROVE_LOCKING: - check that accesses to RCU-protected data - structures are carried out under the proper RCU - read-side critical section, while holding the right - combination of locks, or whatever other conditions - are appropriate. + check that accesses to RCU-protected data structures + are carried out under the proper RCU read-side critical + section, while holding the right combination of locks, + or whatever other conditions are appropriate. CONFIG_DEBUG_OBJECTS_RCU_HEAD: - check that you don't pass the - same object to call_rcu() (or friends) before an RCU - grace period has elapsed since the last time that you - passed that same object to call_rcu() (or friends). + check that you don't pass the same object to call_rcu() + (or friends) before an RCU grace period has elapsed + since the last time that you passed that same object to + call_rcu() (or friends). __rcu sparse checks: - tag the pointer to the RCU-protected data - structure with __rcu, and sparse will warn you if you - access that pointer without the services of one of the - variants of rcu_dereference(). + tag the pointer to the RCU-protected data structure + with __rcu, and sparse will warn you if you access that + pointer without the services of one of the variants + of rcu_dereference(). These debugging aids can help you find problems that are otherwise extremely difficult to spot. -17. If you register a callback using call_rcu() or call_srcu(), and - pass in a function defined within a loadable module, then it in - necessary to wait for all pending callbacks to be invoked after - the last invocation and before unloading that module. Note that - it is absolutely *not* sufficient to wait for a grace period! - The current (say) synchronize_rcu() implementation is *not* - guaranteed to wait for callbacks registered on other CPUs. - Or even on the current CPU if that CPU recently went offline - and came back online. +17. If you pass a callback function defined within a module to one of + call_rcu(), call_srcu(), call_rcu_tasks(), call_rcu_tasks_rude(), + or call_rcu_tasks_trace(), then it is necessary to wait for all + pending callbacks to be invoked before unloading that module. + Note that it is absolutely *not* sufficient to wait for a grace + period! For example, synchronize_rcu() implementation is *not* + guaranteed to wait for callbacks registered on other CPUs via + call_rcu(). Or even on the current CPU if that CPU recently + went offline and came back online. You instead need to use one of the barrier functions: - call_rcu() -> rcu_barrier() - call_srcu() -> srcu_barrier() + - call_rcu_tasks() -> rcu_barrier_tasks() + - call_rcu_tasks_rude() -> rcu_barrier_tasks_rude() + - call_rcu_tasks_trace() -> rcu_barrier_tasks_trace() However, these barrier functions are absolutely *not* guaranteed - to wait for a grace period. In fact, if there are no call_rcu() - callbacks waiting anywhere in the system, rcu_barrier() is within - its rights to return immediately. - - So if you need to wait for both an RCU grace period and for - all pre-existing call_rcu() callbacks, you will need to execute - both rcu_barrier() and synchronize_rcu(), if necessary, using - something like workqueues to execute them concurrently. + to wait for a grace period. For example, if there are no + call_rcu() callbacks queued anywhere in the system, rcu_barrier() + can and will return immediately. + + So if you need to wait for both a grace period and for all + pre-existing callbacks, you will need to invoke both functions, + with the pair depending on the flavor of RCU: + + - Either synchronize_rcu() or synchronize_rcu_expedited(), + together with rcu_barrier() + - Either synchronize_srcu() or synchronize_srcu_expedited(), + together with and srcu_barrier() + - synchronize_rcu_tasks() and rcu_barrier_tasks() + - synchronize_tasks_rude() and rcu_barrier_tasks_rude() + - synchronize_tasks_trace() and rcu_barrier_tasks_trace() + + If necessary, you can use something like workqueues to execute + the requisite pair of functions concurrently. See rcubarrier.rst for more information. diff --git a/Documentation/RCU/index.rst b/Documentation/RCU/index.rst index e703d3dbe60c..84a79903f6a8 100644 --- a/Documentation/RCU/index.rst +++ b/Documentation/RCU/index.rst @@ -9,7 +9,6 @@ RCU concepts .. toctree:: :maxdepth: 3 - arrayRCU checklist lockdep lockdep-splat diff --git a/Documentation/RCU/listRCU.rst b/Documentation/RCU/listRCU.rst index 2a643e293fb4..bdc4bcc5289f 100644 --- a/Documentation/RCU/listRCU.rst +++ b/Documentation/RCU/listRCU.rst @@ -3,11 +3,10 @@ Using RCU to Protect Read-Mostly Linked Lists ============================================= -One of the best applications of RCU is to protect read-mostly linked lists -(``struct list_head`` in list.h). One big advantage of this approach -is that all of the required memory barriers are included for you in -the list macros. This document describes several applications of RCU, -with the best fits first. +One of the most common uses of RCU is protecting read-mostly linked lists +(``struct list_head`` in list.h). One big advantage of this approach is +that all of the required memory ordering is provided by the list macros. +This document describes several list-based RCU use cases. Example 1: Read-mostly list: Deferred Destruction @@ -35,7 +34,8 @@ The code traversing the list of all processes typically looks like:: } rcu_read_unlock(); -The simplified code for removing a process from a task list is:: +The simplified and heavily inlined code for removing a process from a +task list is:: void release_task(struct task_struct *p) { @@ -45,39 +45,48 @@ The simplified code for removing a process from a task list is:: call_rcu(&p->rcu, delayed_put_task_struct); } -When a process exits, ``release_task()`` calls ``list_del_rcu(&p->tasks)`` under -``tasklist_lock`` writer lock protection, to remove the task from the list of -all tasks. The ``tasklist_lock`` prevents concurrent list additions/removals -from corrupting the list. Readers using ``for_each_process()`` are not protected -with the ``tasklist_lock``. To prevent readers from noticing changes in the list -pointers, the ``task_struct`` object is freed only after one or more grace -periods elapse (with the help of call_rcu()). This deferring of destruction -ensures that any readers traversing the list will see valid ``p->tasks.next`` -pointers and deletion/freeing can happen in parallel with traversal of the list. -This pattern is also called an **existence lock**, since RCU pins the object in -memory until all existing readers finish. +When a process exits, ``release_task()`` calls ``list_del_rcu(&p->tasks)`` +via __exit_signal() and __unhash_process() under ``tasklist_lock`` +writer lock protection. The list_del_rcu() invocation removes +the task from the list of all tasks. The ``tasklist_lock`` +prevents concurrent list additions/removals from corrupting the +list. Readers using ``for_each_process()`` are not protected with the +``tasklist_lock``. To prevent readers from noticing changes in the list +pointers, the ``task_struct`` object is freed only after one or more +grace periods elapse, with the help of call_rcu(), which is invoked via +put_task_struct_rcu_user(). This deferring of destruction ensures that +any readers traversing the list will see valid ``p->tasks.next`` pointers +and deletion/freeing can happen in parallel with traversal of the list. +This pattern is also called an **existence lock**, since RCU refrains +from invoking the delayed_put_task_struct() callback function until +all existing readers finish, which guarantees that the ``task_struct`` +object in question will remain in existence until after the completion +of all RCU readers that might possibly have a reference to that object. Example 2: Read-Side Action Taken Outside of Lock: No In-Place Updates ---------------------------------------------------------------------- -The best applications are cases where, if reader-writer locking were -used, the read-side lock would be dropped before taking any action -based on the results of the search. The most celebrated example is -the routing table. Because the routing table is tracking the state of -equipment outside of the computer, it will at times contain stale data. -Therefore, once the route has been computed, there is no need to hold -the routing table static during transmission of the packet. After all, -you can hold the routing table static all you want, but that won't keep -the external Internet from changing, and it is the state of the external -Internet that really matters. In addition, routing entries are typically -added or deleted, rather than being modified in place. - -A straightforward example of this use of RCU may be found in the -system-call auditing support. For example, a reader-writer locked +Some reader-writer locking use cases compute a value while holding +the read-side lock, but continue to use that value after that lock is +released. These use cases are often good candidates for conversion +to RCU. One prominent example involves network packet routing. +Because the packet-routing data tracks the state of equipment outside +of the computer, it will at times contain stale data. Therefore, once +the route has been computed, there is no need to hold the routing table +static during transmission of the packet. After all, you can hold the +routing table static all you want, but that won't keep the external +Internet from changing, and it is the state of the external Internet +that really matters. In addition, routing entries are typically added +or deleted, rather than being modified in place. This is a rare example +of the finite speed of light and the non-zero size of atoms actually +helping make synchronization be lighter weight. + +A straightforward example of this type of RCU use case may be found in +the system-call auditing support. For example, a reader-writer locked implementation of ``audit_filter_task()`` might be as follows:: - static enum audit_state audit_filter_task(struct task_struct *tsk) + static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) { struct audit_entry *e; enum audit_state state; @@ -86,6 +95,8 @@ implementation of ``audit_filter_task()`` might be as follows:: /* Note: audit_filter_mutex held by caller. */ list_for_each_entry(e, &audit_tsklist, list) { if (audit_filter_rules(tsk, &e->rule, NULL, &state)) { + if (state == AUDIT_STATE_RECORD) + *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); read_unlock(&auditsc_lock); return state; } @@ -101,7 +112,7 @@ you are turning auditing off, it is OK to audit a few extra system calls. This means that RCU can be easily applied to the read side, as follows:: - static enum audit_state audit_filter_task(struct task_struct *tsk) + static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) { struct audit_entry *e; enum audit_state state; @@ -110,6 +121,8 @@ This means that RCU can be easily applied to the read side, as follows:: /* Note: audit_filter_mutex held by caller. */ list_for_each_entry_rcu(e, &audit_tsklist, list) { if (audit_filter_rules(tsk, &e->rule, NULL, &state)) { + if (state == AUDIT_STATE_RECORD) + *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); rcu_read_unlock(); return state; } @@ -118,13 +131,15 @@ This means that RCU can be easily applied to the read side, as follows:: return AUDIT_BUILD_CONTEXT; } -The ``read_lock()`` and ``read_unlock()`` calls have become rcu_read_lock() -and rcu_read_unlock(), respectively, and the list_for_each_entry() has -become list_for_each_entry_rcu(). The **_rcu()** list-traversal primitives -insert the read-side memory barriers that are required on DEC Alpha CPUs. +The read_lock() and read_unlock() calls have become rcu_read_lock() +and rcu_read_unlock(), respectively, and the list_for_each_entry() +has become list_for_each_entry_rcu(). The **_rcu()** list-traversal +primitives add READ_ONCE() and diagnostic checks for incorrect use +outside of an RCU read-side critical section. The changes to the update side are also straightforward. A reader-writer lock -might be used as follows for deletion and insertion:: +might be used as follows for deletion and insertion in these simplified +versions of audit_del_rule() and audit_add_rule():: static inline int audit_del_rule(struct audit_rule *rule, struct list_head *list) @@ -188,16 +203,16 @@ Following are the RCU equivalents for these two functions:: return 0; } -Normally, the ``write_lock()`` and ``write_unlock()`` would be replaced by a +Normally, the write_lock() and write_unlock() would be replaced by a spin_lock() and a spin_unlock(). But in this case, all callers hold ``audit_filter_mutex``, so no additional locking is required. The -``auditsc_lock`` can therefore be eliminated, since use of RCU eliminates the +auditsc_lock can therefore be eliminated, since use of RCU eliminates the need for writers to exclude readers. The list_del(), list_add(), and list_add_tail() primitives have been replaced by list_del_rcu(), list_add_rcu(), and list_add_tail_rcu(). -The **_rcu()** list-manipulation primitives add memory barriers that are needed on -weakly ordered CPUs (most of them!). The list_del_rcu() primitive omits the +The **_rcu()** list-manipulation primitives add memory barriers that are +needed on weakly ordered CPUs. The list_del_rcu() primitive omits the pointer poisoning debug-assist code that would otherwise cause concurrent readers to fail spectacularly. @@ -238,7 +253,9 @@ need to be filled in):: The RCU version creates a copy, updates the copy, then replaces the old entry with the newly updated entry. This sequence of actions, allowing concurrent reads while making a copy to perform an update, is what gives -RCU (*read-copy update*) its name. The RCU code is as follows:: +RCU (*read-copy update*) its name. + +The RCU version of audit_upd_rule() is as follows:: static inline int audit_upd_rule(struct audit_rule *rule, struct list_head *list, @@ -267,6 +284,9 @@ RCU (*read-copy update*) its name. The RCU code is as follows:: Again, this assumes that the caller holds ``audit_filter_mutex``. Normally, the writer lock would become a spinlock in this sort of code. +The update_lsm_rule() does something very similar, for those who would +prefer to look at real Linux-kernel code. + Another use of this pattern can be found in the openswitch driver's *connection tracking table* code in ``ct_limit_set()``. The table holds connection tracking entries and has a limit on the maximum entries. There is one such table @@ -281,9 +301,10 @@ Example 4: Eliminating Stale Data --------------------------------- The auditing example above tolerates stale data, as do most algorithms -that are tracking external state. Because there is a delay from the -time the external state changes before Linux becomes aware of the change, -additional RCU-induced staleness is generally not a problem. +that are tracking external state. After all, given there is a delay +from the time the external state changes before Linux becomes aware +of the change, and so as noted earlier, a small quantity of additional +RCU-induced staleness is generally not a problem. However, there are many examples where stale data cannot be tolerated. One example in the Linux kernel is the System V IPC (see the shm_lock() @@ -302,7 +323,7 @@ Quick Quiz: If the system-call audit module were to ever need to reject stale data, one way to accomplish this would be to add a ``deleted`` flag and a ``lock`` spinlock to the -audit_entry structure, and modify ``audit_filter_task()`` as follows:: +``audit_entry`` structure, and modify audit_filter_task() as follows:: static enum audit_state audit_filter_task(struct task_struct *tsk) { @@ -319,6 +340,8 @@ audit_entry structure, and modify ``audit_filter_task()`` as follows:: return AUDIT_BUILD_CONTEXT; } rcu_read_unlock(); + if (state == AUDIT_STATE_RECORD) + *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); return state; } } @@ -326,12 +349,6 @@ audit_entry structure, and modify ``audit_filter_task()`` as follows:: return AUDIT_BUILD_CONTEXT; } -Note that this example assumes that entries are only added and deleted. -Additional mechanism is required to deal correctly with the update-in-place -performed by ``audit_upd_rule()``. For one thing, ``audit_upd_rule()`` would -need additional memory barriers to ensure that the list_add_rcu() was really -executed before the list_del_rcu(). - The ``audit_del_rule()`` function would need to set the ``deleted`` flag under the spinlock as follows:: @@ -357,24 +374,32 @@ spinlock as follows:: This too assumes that the caller holds ``audit_filter_mutex``. +Note that this example assumes that entries are only added and deleted. +Additional mechanism is required to deal correctly with the update-in-place +performed by audit_upd_rule(). For one thing, audit_upd_rule() would +need to hold the locks of both the old ``audit_entry`` and its replacement +while executing the list_replace_rcu(). + Example 5: Skipping Stale Objects --------------------------------- -For some usecases, reader performance can be improved by skipping stale objects -during read-side list traversal if the object in concern is pending destruction -after one or more grace periods. One such example can be found in the timerfd -subsystem. When a ``CLOCK_REALTIME`` clock is reprogrammed - for example due to -setting of the system time, then all programmed timerfds that depend on this -clock get triggered and processes waiting on them to expire are woken up in -advance of their scheduled expiry. To facilitate this, all such timers are added -to an RCU-managed ``cancel_list`` when they are setup in +For some use cases, reader performance can be improved by skipping +stale objects during read-side list traversal, where stale objects +are those that will be removed and destroyed after one or more grace +periods. One such example can be found in the timerfd subsystem. When a +``CLOCK_REALTIME`` clock is reprogrammed (for example due to setting +of the system time) then all programmed ``timerfds`` that depend on +this clock get triggered and processes waiting on them are awakened in +advance of their scheduled expiry. To facilitate this, all such timers +are added to an RCU-managed ``cancel_list`` when they are setup in ``timerfd_setup_cancel()``:: static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { spin_lock(&ctx->cancel_lock); - if ((ctx->clockid == CLOCK_REALTIME && + if ((ctx->clockid == CLOCK_REALTIME || + ctx->clockid == CLOCK_REALTIME_ALARM) && (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { if (!ctx->might_cancel) { ctx->might_cancel = true; @@ -382,13 +407,16 @@ to an RCU-managed ``cancel_list`` when they are setup in list_add_rcu(&ctx->clist, &cancel_list); spin_unlock(&cancel_lock); } + } else { + __timerfd_remove_cancel(ctx); } spin_unlock(&ctx->cancel_lock); } -When a timerfd is freed (fd is closed), then the ``might_cancel`` flag of the -timerfd object is cleared, the object removed from the ``cancel_list`` and -destroyed:: +When a timerfd is freed (fd is closed), then the ``might_cancel`` +flag of the timerfd object is cleared, the object removed from the +``cancel_list`` and destroyed, as shown in this simplified and inlined +version of timerfd_release():: int timerfd_release(struct inode *inode, struct file *file) { @@ -403,7 +431,10 @@ destroyed:: } spin_unlock(&ctx->cancel_lock); - hrtimer_cancel(&ctx->t.tmr); + if (isalarm(ctx)) + alarm_cancel(&ctx->t.alarm); + else + hrtimer_cancel(&ctx->t.tmr); kfree_rcu(ctx, rcu); return 0; } @@ -416,6 +447,7 @@ objects:: void timerfd_clock_was_set(void) { + ktime_t moffs = ktime_mono_to_real(0); struct timerfd_ctx *ctx; unsigned long flags; @@ -424,7 +456,7 @@ objects:: if (!ctx->might_cancel) continue; spin_lock_irqsave(&ctx->wqh.lock, flags); - if (ctx->moffs != ktime_mono_to_real(0)) { + if (ctx->moffs != moffs) { ctx->moffs = KTIME_MAX; ctx->ticks++; wake_up_locked_poll(&ctx->wqh, EPOLLIN); @@ -434,10 +466,10 @@ objects:: rcu_read_unlock(); } -The key point here is, because RCU-traversal of the ``cancel_list`` happens -while objects are being added and removed to the list, sometimes the traversal -can step on an object that has been removed from the list. In this example, it -is seen that it is better to skip such objects using a flag. +The key point is that because RCU-protected traversal of the +``cancel_list`` happens concurrently with object addition and removal, +sometimes the traversal can access an object that has been removed from +the list. In this example, a flag is used to skip such objects. Summary diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst index a94f55991a71..9308f1bdba05 100644 --- a/Documentation/RCU/lockdep.rst +++ b/Documentation/RCU/lockdep.rst @@ -17,7 +17,9 @@ state:: rcu_read_lock_held() for normal RCU. rcu_read_lock_bh_held() for RCU-bh. rcu_read_lock_sched_held() for RCU-sched. + rcu_read_lock_any_held() for any of normal RCU, RCU-bh, and RCU-sched. srcu_read_lock_held() for SRCU. + rcu_read_lock_trace_held() for RCU Tasks Trace. These functions are conservative, and will therefore return 1 if they aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set). @@ -53,6 +55,8 @@ checking of rcu_dereference() primitives: is invoked by both SRCU readers and updaters. rcu_dereference_raw(p): Don't check. (Use sparingly, if at all.) + rcu_dereference_raw_check(p): + Don't do lockdep at all. (Use sparingly, if at all.) rcu_dereference_protected(p, c): Use explicit check expression "c", and omit all barriers and compiler constraints. This is useful when the data diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a465d5242774..42af9ca0127e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6959,3 +6959,14 @@ memory, and other data can't be written using xmon commands. off xmon is disabled. + + amd_pstate= [X86] + disable + Do not enable amd_pstate as the default + scaling driver for the supported processors + passive + Use amd_pstate as a scaling driver, driver requests a + desired performance on this abstract scale and the power + management firmware translates the requests into actual + hardware states (core frequency, data fabric and memory + clocks etc.) diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 8f3d30c5a0d8..06e23538f79c 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -283,23 +283,19 @@ efficiency frequency management method on AMD processors. Kernel Module Options for ``amd-pstate`` ========================================= -.. _shared_mem: - -``shared_mem`` -Use a module param (shared_mem) to enable related processors manually with -**amd_pstate.shared_mem=1**. -Due to the performance issue on the processors with `Shared Memory Support -<perf_cap_>`_, we disable it presently and will re-enable this by default -once we address performance issue with this solution. - -To check whether the current processor is using `Full MSR Support <perf_cap_>`_ -or `Shared Memory Support <perf_cap_>`_ : :: - - ray@hr-test1:~$ lscpu | grep cppc - Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm - -If the CPU flags have ``cppc``, then this processor supports `Full MSR Support -<perf_cap_>`_. Otherwise, it supports `Shared Memory Support <perf_cap_>`_. +Passive Mode +------------ + +``amd_pstate=passive`` + +It will be enabled if the ``amd_pstate=passive`` is passed to the kernel in the command line. +In this mode, ``amd_pstate`` driver software specifies a desired QoS target in the CPPC +performance scale as a relative number. This can be expressed as percentage of nominal +performance (infrastructure max). Below the nominal sustained performance level, +desired performance expresses the average performance level of the processor subject +to the Performance Reduction Tolerance register. Above the nominal performance level, +processor must provide at least nominal performance requested and go higher if current +operating conditions allow. ``cpupower`` tool support for ``amd-pstate`` diff --git a/Documentation/devicetree/bindings/clock/samsung,exynosautov9-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynosautov9-clock.yaml index 2ab4642679c0..55c4f94a14d1 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynosautov9-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynosautov9-clock.yaml @@ -148,7 +148,7 @@ allOf: items: - const: oscclk - const: dout_clkcmu_fsys1_bus - - const: dout_clkcmu_fsys1_mmc_card + - const: gout_clkcmu_fsys1_mmc_card - const: dout_clkcmu_fsys1_usbdrd - if: diff --git a/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml b/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml index b283c8ca2bbf..5c08d8b6e995 100644 --- a/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml @@ -62,13 +62,6 @@ properties: description: Inform the driver that last channel will be used to sensor battery. - aspeed,trim-data-valid: - type: boolean - description: | - The ADC reference voltage can be calibrated to obtain the trimming - data which will be stored in otp. This property informs the driver that - the data store in the otp is valid. - required: - compatible - reg diff --git a/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml b/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml index fe1c5016f7f3..1c191bc5a178 100644 --- a/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml +++ b/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml @@ -16,8 +16,11 @@ description: properties: compatible: - items: + oneOf: - const: goodix,gt7375p + - items: + - const: goodix,gt7986u + - const: goodix,gt7375p reg: enum: diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml index 2684562df4d9..be29e0b80995 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml @@ -24,7 +24,7 @@ properties: oneOf: - items: - enum: - - qcom,sc7280-bwmon + - qcom,sc7280-cpu-bwmon - qcom,sdm845-bwmon - const: qcom,msm8998-bwmon - const: qcom,msm8998-bwmon # BWMON v4 diff --git a/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml b/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml index 24d7bf21499e..9d44236f2deb 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml @@ -36,6 +36,9 @@ properties: resets: maxItems: 1 + iommus: + maxItems: 1 + required: - compatible - reg @@ -43,6 +46,7 @@ required: - clocks - clock-names - resets + - iommus additionalProperties: false @@ -59,6 +63,7 @@ examples: clocks = <&ccu CLK_BUS_VP9>, <&ccu CLK_VP9>; clock-names = "bus", "mod"; resets = <&ccu RST_BUS_VP9>; + iommus = <&iommu 5>; }; ... diff --git a/Documentation/loongarch/booting.rst b/Documentation/loongarch/booting.rst new file mode 100644 index 000000000000..91eccd410478 --- /dev/null +++ b/Documentation/loongarch/booting.rst @@ -0,0 +1,42 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +Booting Linux/LoongArch +======================= + +:Author: Yanteng Si <[email protected]> +:Date: 18 Nov 2022 + +Information passed from BootLoader to kernel +============================================ + +LoongArch supports ACPI and FDT. The information that needs to be passed +to the kernel includes the memmap, the initrd, the command line, optionally +the ACPI/FDT tables, and so on. + +The kernel is passed the following arguments on `kernel_entry` : + + - a0 = efi_boot: `efi_boot` is a flag indicating whether + this boot environment is fully UEFI-compliant. + + - a1 = cmdline: `cmdline` is a pointer to the kernel command line. + + - a2 = systemtable: `systemtable` points to the EFI system table. + All pointers involved at this stage are in physical addresses. + +Header of Linux/LoongArch kernel images +======================================= + +Linux/LoongArch kernel images are EFI images. Being PE files, they have +a 64-byte header structured like:: + + u32 MZ_MAGIC /* "MZ", MS-DOS header */ + u32 res0 = 0 /* Reserved */ + u64 kernel_entry /* Kernel entry point */ + u64 _end - _text /* Kernel image effective size */ + u64 load_offset /* Kernel image load offset from start of RAM */ + u64 res1 = 0 /* Reserved */ + u64 res2 = 0 /* Reserved */ + u64 res3 = 0 /* Reserved */ + u32 LINUX_PE_MAGIC /* Magic number */ + u32 pe_header - _head /* Offset to the PE header */ diff --git a/Documentation/loongarch/index.rst b/Documentation/loongarch/index.rst index aaba648db907..c779bfa00c05 100644 --- a/Documentation/loongarch/index.rst +++ b/Documentation/loongarch/index.rst @@ -9,6 +9,7 @@ LoongArch Architecture :numbered: introduction + booting irq-chip-model features diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 06f80e3785c5..cc621decd943 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1966,7 +1966,7 @@ There are some more advanced barrier functions: (*) io_stop_wc(); For memory accesses with write-combining attributes (e.g. those returned - by ioremap_wc(), the CPU may wait for prior accesses to be merged with + by ioremap_wc()), the CPU may wait for prior accesses to be merged with subsequent ones. io_stop_wc() can be used to prevent the merging of write-combining memory accesses before this macro with those after it when such wait has performance implications. diff --git a/Documentation/networking/generic_netlink.rst b/Documentation/networking/generic_netlink.rst index 59e04ccf80c1..d960dbd7e80e 100644 --- a/Documentation/networking/generic_netlink.rst +++ b/Documentation/networking/generic_netlink.rst @@ -6,4 +6,4 @@ Generic Netlink A wiki document on how to use Generic Netlink can be found here: - * http://www.linuxfoundation.org/collaborate/workgroups/networking/generic_netlink_howto + * https://wiki.linuxfoundation.org/networking/generic_netlink_howto diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index 75aa5531cc7d..7165927a708e 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -80,7 +80,7 @@ Documentation/memory-barriers.txt - 메모리 배리어의 종류. - 메모리 배리어에 대해 가정해선 안될 것. - - 데이터 의존성 배리어 (역사적). + - 주소 데이터 의존성 배리어 (역사적). - 컨트롤 의존성. - SMP 배리어 짝맞추기. - 메모리 배리어 시퀀스의 예. @@ -217,7 +217,7 @@ Documentation/memory-barriers.txt P = &B D = *Q; D 로 읽혀지는 값은 CPU 2 에서 P 로부터 읽혀진 주소값에 의존적이기 때문에 여기엔 -분명한 데이터 의존성이 있습니다. 하지만 이 이벤트들의 실행 결과로는 아래의 +분명한 주소 의존성이 있습니다. 하지만 이 이벤트들의 실행 결과로는 아래의 결과들이 모두 나타날 수 있습니다: (Q == &A) and (D == 1) @@ -416,19 +416,19 @@ CPU 에게 기대할 수 있는 최소한의 보장사항 몇가지가 있습니 하나씩 요청해 집어넣습니다. 쓰기 배리어 앞의 모든 스토어 오퍼레이션들은 쓰기 배리어 뒤의 모든 스토어 오퍼레이션들보다 _앞서_ 수행될 겁니다. - [!] 쓰기 배리어들은 읽기 또는 데이터 의존성 배리어와 함께 짝을 맞춰 + [!] 쓰기 배리어들은 읽기 또는 주소 의존성 배리어와 함께 짝을 맞춰 사용되어야만 함을 알아두세요; "SMP 배리어 짝맞추기" 서브섹션을 참고하세요. - (2) 데이터 의존성 배리어. + (2) 주소 의존성 배리어 (역사적). - 데이터 의존성 배리어는 읽기 배리어의 보다 완화된 형태입니다. 두개의 로드 + 주소 의존성 배리어는 읽기 배리어의 보다 완화된 형태입니다. 두개의 로드 오퍼레이션이 있고 두번째 것이 첫번째 것의 결과에 의존하고 있을 때(예: 두번째 로드가 참조할 주소를 첫번째 로드가 읽는 경우), 두번째 로드가 읽어올 데이터는 첫번째 로드에 의해 그 주소가 얻어진 뒤에 업데이트 됨을 보장하기 - 위해서 데이터 의존성 배리어가 필요할 수 있습니다. + 위해서 주소 의존성 배리어가 필요할 수 있습니다. - 데이터 의존성 배리어는 상호 의존적인 로드 오퍼레이션들 사이의 부분적 순서 + 주소 의존성 배리어는 상호 의존적인 로드 오퍼레이션들 사이의 부분적 순서 세우기입니다; 스토어 오퍼레이션들이나 독립적인 로드들, 또는 중복되는 로드들에 대해서는 어떤 영향도 끼치지 않습니다. @@ -436,37 +436,41 @@ CPU 에게 기대할 수 있는 최소한의 보장사항 몇가지가 있습니 오퍼레이션들을 던져 넣고 있으며, 거기에 관심이 있는 다른 CPU 는 그 오퍼레이션들을 메모리 시스템이 실행한 결과를 인지할 수 있습니다. 이처럼 다른 CPU 의 스토어 오퍼레이션의 결과에 관심을 두고 있는 CPU 가 수행 요청한 - 데이터 의존성 배리어는, 배리어 앞의 어떤 로드 오퍼레이션이 다른 CPU 에서 + 주소 의존성 배리어는, 배리어 앞의 어떤 로드 오퍼레이션이 다른 CPU 에서 던져 넣은 스토어 오퍼레이션과 같은 영역을 향했다면, 그런 스토어 - 오퍼레이션들이 만들어내는 결과가 데이터 의존성 배리어 뒤의 로드 + 오퍼레이션들이 만들어내는 결과가 주소 의존성 배리어 뒤의 로드 오퍼레이션들에게는 보일 것을 보장합니다. 이 순서 세우기 제약에 대한 그림을 보기 위해선 "메모리 배리어 시퀀스의 예" 서브섹션을 참고하시기 바랍니다. - [!] 첫번째 로드는 반드시 _데이터_ 의존성을 가져야지 컨트롤 의존성을 가져야 + [!] 첫번째 로드는 반드시 _주소_ 의존성을 가져야지 컨트롤 의존성을 가져야 하는게 아님을 알아두십시오. 만약 두번째 로드를 위한 주소가 첫번째 로드에 의존적이지만 그 의존성은 조건적이지 그 주소 자체를 가져오는게 아니라면, 그것은 _컨트롤_ 의존성이고, 이 경우에는 읽기 배리어나 그보다 강력한 무언가가 필요합니다. 더 자세한 내용을 위해서는 "컨트롤 의존성" 서브섹션을 참고하시기 바랍니다. - [!] 데이터 의존성 배리어는 보통 쓰기 배리어들과 함께 짝을 맞춰 사용되어야 + [!] 주소 의존성 배리어는 보통 쓰기 배리어들과 함께 짝을 맞춰 사용되어야 합니다; "SMP 배리어 짝맞추기" 서브섹션을 참고하세요. + [!] 커널 v5.9 릴리즈에서 명시적 주소 의존성 배리어를 위한 커널 API 들이 + 삭제되었습니다. 오늘날에는 공유된 변수들의 로드를 표시하는 READ_ONCE() 나 + rcu_dereference() 와 같은 API 들은 묵시적으로 주소 의존성 배리어를 제공합니다. + (3) 읽기 (또는 로드) 메모리 배리어. - 읽기 배리어는 데이터 의존성 배리어 기능의 보장사항에 더해서 배리어보다 - 앞서 명시된 모든 LOAD 오퍼레이션들이 배리어 뒤에 명시되는 모든 LOAD + 읽기 배리어는 주소 의존성 배리어 기능의 보장사항에 더해서 배리어보다 앞서 + 명시된 모든 LOAD 오퍼레이션들이 배리어 뒤에 명시되는 모든 LOAD 오퍼레이션들보다 먼저 행해진 것으로 시스템의 다른 컴포넌트들에 보여질 것을 보장합니다. 읽기 배리어는 로드 오퍼레이션에 행해지는 부분적 순서 세우기입니다; 스토어 오퍼레이션에 대해서는 어떤 영향도 끼치지 않습니다. - 읽기 메모리 배리어는 데이터 의존성 배리어를 내장하므로 데이터 의존성 - 배리어를 대신할 수 있습니다. + 읽기 메모리 배리어는 주소 의존성 배리어를 내장하므로 주소 의존성 배리어를 + 대신할 수 있습니다. [!] 읽기 배리어는 일반적으로 쓰기 배리어들과 함께 짝을 맞춰 사용되어야 합니다; "SMP 배리어 짝맞추기" 서브섹션을 참고하세요. @@ -571,16 +575,20 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE � Documentation/core-api/dma-api.rst -데이터 의존성 배리어 (역사적) ------------------------------ +주소 의존성 배리어 (역사적) +--------------------------- 리눅스 커널 v4.15 기준으로, smp_mb() 가 DEC Alpha 용 READ_ONCE() 코드에 추가되었는데, 이는 이 섹션에 주의를 기울여야 하는 사람들은 DEC Alpha 아키텍쳐 전용 코드를 만드는 사람들과 READ_ONCE() 자체를 만드는 사람들 뿐임을 의미합니다. -그런 분들을 위해, 그리고 역사에 관심 있는 분들을 위해, 여기 데이터 의존성 +그런 분들을 위해, 그리고 역사에 관심 있는 분들을 위해, 여기 주소 의존성 배리어에 대한 이야기를 적습니다. -데이터 의존성 배리어의 사용에 있어 지켜야 하는 사항들은 약간 미묘하고, 데이터 +[!] 주소 의존성은 로드에서 로드로와 로드에서 스토어로의 관계들 모두에서 +나타나지만, 주소 의존성 배리어는 로드에서 스토어로의 상황에서는 필요하지 +않습니다. + +주소 의존성 배리어의 사용에 있어 지켜야 하는 사항들은 약간 미묘하고, 데이터 의존성 배리어가 사용되어야 하는 상황도 항상 명백하지는 않습니다. 설명을 위해 다음의 이벤트 시퀀스를 생각해 봅시다: @@ -590,10 +598,13 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE � B = 4; <쓰기 배리어> WRITE_ONCE(P, &B) - Q = READ_ONCE(P); + Q = READ_ONCE_OLD(P); D = *Q; -여기엔 분명한 데이터 의존성이 존재하므로, 이 시퀀스가 끝났을 때 Q 는 &A 또는 &B +[!] READ_ONCE_OLD() 는 4.15 커널 전의 버전에서의, 주소 의존성 배리어를 내포하지 +않는 READ_ONCE() 에 해당합니다. + +여기엔 분명한 주소 의존성이 존재하므로, 이 시퀀스가 끝났을 때 Q 는 &A 또는 &B 일 것이고, 따라서: (Q == &A) 는 (D == 1) 를, @@ -608,8 +619,8 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE � 그렇지 않습니다, 그리고 이 현상은 (DEC Alpha 와 같은) 여러 CPU 에서 실제로 발견될 수 있습니다. -이 문제 상황을 제대로 해결하기 위해, 데이터 의존성 배리어나 그보다 강화된 -무언가가 주소를 읽어올 때와 데이터를 읽어올 때 사이에 추가되어야만 합니다: +이 문제 상황을 제대로 해결하기 위해, READ_ONCE() 는 커널 v4.15 릴리즈 부터 +묵시적 주소 의존성 배리어를 제공합니다: CPU 1 CPU 2 =============== =============== @@ -618,7 +629,7 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE � <쓰기 배리어> WRITE_ONCE(P, &B); Q = READ_ONCE(P); - <데이터 의존성 배리어> + <묵시적 주소 의존성 배리어> D = *Q; 이 변경은 앞의 처음 두가지 결과 중 하나만이 발생할 수 있고, 세번째의 결과는 @@ -634,7 +645,7 @@ P 는 짝수 번호 캐시 라인에 저장되어 있고, 변수 B 는 홀수 � 중이라면 포인터 P (&B) 의 새로운 값과 변수 B 의 기존 값 (2) 를 볼 수 있습니다. -의존적 쓰기들의 순서를 맞추는데에는 데이터 의존성 배리어가 필요치 않은데, 이는 +의존적 쓰기들의 순서를 맞추는데에는 주소 의존성 배리어가 필요치 않은데, 이는 리눅스 커널이 지원하는 CPU 들은 (1) 쓰기가 정말로 일어날지, (2) 쓰기가 어디에 이루어질지, 그리고 (3) 쓰여질 값을 확실히 알기 전까지는 쓰기를 수행하지 않기 때문입니다. 하지만 "컨트롤 의존성" 섹션과 @@ -647,12 +658,12 @@ Documentation/RCU/rcu_dereference.rst 파일을 주의 깊게 읽어 주시기 � B = 4; <쓰기 배리어> WRITE_ONCE(P, &B); - Q = READ_ONCE(P); + Q = READ_ONCE_OLD(P); WRITE_ONCE(*Q, 5); -따라서, Q 로의 읽기와 *Q 로의 쓰기 사이에는 데이터 종속성 배리어가 필요치 -않습니다. 달리 말하면, 데이터 종속성 배리어가 없더라도 다음 결과는 생기지 -않습니다: +따라서, Q 로의 읽기와 *Q 로의 쓰기 사이에는 주소 의존성 배리어가 필요치 +않습니다. 달리 말하면, 오늘날의 READ_ONCE() 의 묵시적 주소 의존성 배리어가 +없더라도 다음 결과는 생기지 않습니다: (Q == &B) && (B == 4) @@ -663,16 +674,16 @@ Documentation/RCU/rcu_dereference.rst 파일을 주의 깊게 읽어 주시기 � 해줍니다. -데이터 의존성에 의해 제공되는 이 순서규칙은 이를 포함하고 있는 CPU 에 +주소 의존성에 의해 제공되는 이 순서규칙은 이를 포함하고 있는 CPU 에 지역적임을 알아두시기 바랍니다. 더 많은 정보를 위해선 "Multicopy 원자성" 섹션을 참고하세요. -데이터 의존성 배리어는 매우 중요한데, 예를 들어 RCU 시스템에서 그렇습니다. +주소 의존성 배리어는 매우 중요한데, 예를 들어 RCU 시스템에서 그렇습니다. include/linux/rcupdate.h 의 rcu_assign_pointer() 와 rcu_dereference() 를 -참고하세요. 여기서 데이터 의존성 배리어는 RCU 로 관리되는 포인터의 타겟을 현재 -타겟에서 수정된 새로운 타겟으로 바꾸는 작업에서 새로 수정된 타겟이 초기화가 -완료되지 않은 채로 보여지는 일이 일어나지 않게 해줍니다. +참고하세요. 이것들은 RCU 로 관리되는 포인터의 타겟을 현재 타겟에서 수정된 +새로운 타겟으로 바꾸는 작업에서 새로 수정된 타겟이 초기화가 완료되지 않은 채로 +보여지는 일이 일어나지 않게 해줍니다. 더 많은 예를 위해선 "캐시 일관성" 서브섹션을 참고하세요. @@ -684,16 +695,17 @@ include/linux/rcupdate.h 의 rcu_assign_pointer() 와 rcu_dereference() 를 약간 다루기 어려울 수 있습니다. 이 섹션의 목적은 여러분이 컴파일러의 무시로 인해 여러분의 코드가 망가지는 걸 막을 수 있도록 돕는겁니다. -로드-로드 컨트롤 의존성은 데이터 의존성 배리어만으로는 정확히 동작할 수가 -없어서 읽기 메모리 배리어를 필요로 합니다. 아래의 코드를 봅시다: +로드-로드 컨트롤 의존성은 (묵시적인) 주소 의존성 배리어만으로는 정확히 동작할 +수가 없어서 읽기 메모리 배리어를 필요로 합니다. 아래의 코드를 봅시다: q = READ_ONCE(a); + <묵시적 주소 의존성 배리어> if (q) { - <데이터 의존성 배리어> /* BUG: No data dependency!!! */ + /* BUG: No address dependency!!! */ p = READ_ONCE(b); } -이 코드는 원하는 대로의 효과를 내지 못할 수 있는데, 이 코드에는 데이터 의존성이 +이 코드는 원하는 대로의 효과를 내지 못할 수 있는데, 이 코드에는 주소 의존성이 아니라 컨트롤 의존성이 존재하기 때문으로, 이런 상황에서 CPU 는 실행 속도를 더 빠르게 하기 위해 분기 조건의 결과를 예측하고 코드를 재배치 할 수 있어서 다른 CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레이션보다 먼저 발생한 @@ -930,9 +942,9 @@ CPU 간 상호작용을 다룰 때에 일부 타입의 메모리 배리어는 � 범용 배리어들은 범용 배리어끼리도 짝을 맞추지만 multicopy 원자성이 없는 대부분의 다른 타입의 배리어들과도 짝을 맞춥니다. ACQUIRE 배리어는 RELEASE 배리어와 짝을 맞춥니다만, 둘 다 범용 배리어를 포함해 다른 배리어들과도 짝을 -맞출 수 있습니다. 쓰기 배리어는 데이터 의존성 배리어나 컨트롤 의존성, ACQUIRE +맞출 수 있습니다. 쓰기 배리어는 주소 의존성 배리어나 컨트롤 의존성, ACQUIRE 배리어, RELEASE 배리어, 읽기 배리어, 또는 범용 배리어와 짝을 맞춥니다. -비슷하게 읽기 배리어나 컨트롤 의존성, 또는 데이터 의존성 배리어는 쓰기 배리어나 +비슷하게 읽기 배리어나 컨트롤 의존성, 또는 주소 의존성 배리어는 쓰기 배리어나 ACQUIRE 배리어, RELEASE 배리어, 또는 범용 배리어와 짝을 맞추는데, 다음과 같습니다: @@ -951,7 +963,7 @@ ACQUIRE 배리어, RELEASE 배리어, 또는 범용 배리어와 짝을 맞추� a = 1; <쓰기 배리어> WRITE_ONCE(b, &a); x = READ_ONCE(b); - <데이터 의존성 배리어> + <묵시적 주소 의존성 배리어> y = *x; 또는: @@ -970,8 +982,8 @@ ACQUIRE 배리어, RELEASE 배리어, 또는 범용 배리어와 짝을 맞추� 기본적으로, 여기서의 읽기 배리어는 "더 완화된" 타입일 순 있어도 항상 존재해야 합니다. -[!] 쓰기 배리어 앞의 스토어 오퍼레이션은 일반적으로 읽기 배리어나 데이터 -의존성 배리어 뒤의 로드 오퍼레이션과 매치될 것이고, 반대도 마찬가지입니다: +[!] 쓰기 배리어 앞의 스토어 오퍼레이션은 일반적으로 읽기 배리어나 주소 의존성 +배리어 뒤의 로드 오퍼레이션과 매치될 것이고, 반대도 마찬가지입니다: CPU 1 CPU 2 =================== =================== @@ -1023,7 +1035,7 @@ ACQUIRE 배리어, RELEASE 배리어, 또는 범용 배리어와 짝을 맞추� V -둘째, 데이터 의존성 배리어는 데이터 의존적 로드 오퍼레이션들의 부분적 순서 +둘째, 주소 의존성 배리어는 데이터 의존적 로드 오퍼레이션들의 부분적 순서 세우기로 동작합니다. 다음 일련의 이벤트들을 보세요: CPU 1 CPU 2 @@ -1069,7 +1081,7 @@ ACQUIRE 배리어, RELEASE 배리어, 또는 범용 배리어와 짝을 맞추� 앞의 예에서, CPU 2 는 (B 의 값이 될) *C 의 값 읽기가 C 의 LOAD 뒤에 이어짐에도 B 가 7 이라는 결과를 얻습니다. -하지만, 만약 데이터 의존성 배리어가 C 의 로드와 *C (즉, B) 의 로드 사이에 +하지만, 만약 주소 의존성 배리어가 C 의 로드와 *C (즉, B) 의 로드 사이에 있었다면: CPU 1 CPU 2 @@ -1080,7 +1092,7 @@ B 가 7 이라는 결과를 얻습니다. <쓰기 배리어> STORE C = &B LOAD X STORE D = 4 LOAD C (gets &B) - <데이터 의존성 배리어> + <주소 의존성 배리어> LOAD *C (reads B) 다음과 같이 됩니다: @@ -1103,7 +1115,7 @@ B 가 7 이라는 결과를 얻습니다. | +-------+ | | | | X->9 |------>| | | +-------+ | | - C 로의 스토어 앞의 ---> \ ddddddddddddddddd | | + C 로의 스토어 앞의 ---> \ aaaaaaaaaaaaaaaaa | | 모든 이벤트 결과가 \ +-------+ | | 뒤의 로드에게 ----->| B->2 |------>| | 보이게 강제한다 +-------+ | | @@ -1291,7 +1303,7 @@ A 의 로드 두개가 모두 B 의 로드 뒤에 있지만, 서로 다른 값� 즉각 완료한다 : : +-------+ -읽기 배리어나 데이터 의존성 배리어를 두번째 로드 직전에 놓는다면: +읽기 배리어나 주소 의존성 배리어를 두번째 로드 직전에 놓는다면: CPU 1 CPU 2 ======================= ======================= @@ -1785,21 +1797,20 @@ READ_ONCE(jiffies) 라고 할 필요가 없습니다. READ_ONCE() 와 WRITE_ONC CPU 메모리 배리어 ----------------- -리눅스 커널은 다음의 여덟개 기본 CPU 메모리 배리어를 가지고 있습니다: +리눅스 커널은 다음의 일곱개 기본 CPU 메모리 배리어를 가지고 있습니다: TYPE MANDATORY SMP CONDITIONAL - =============== ======================= =========================== + =============== ======================= =============== 범용 mb() smp_mb() 쓰기 wmb() smp_wmb() 읽기 rmb() smp_rmb() - 데이터 의존성 READ_ONCE() + 주소 의존성 READ_ONCE() -데이터 의존성 배리어를 제외한 모든 메모리 배리어는 컴파일러 배리어를 -포함합니다. 데이터 의존성은 컴파일러에의 추가적인 순서 보장을 포함하지 -않습니다. +주소 의존성 배리어를 제외한 모든 메모리 배리어는 컴파일러 배리어를 포함합니다. +주소 의존성은 컴파일러에의 추가적인 순서 보장을 포함하지 않습니다. -방백: 데이터 의존성이 있는 경우, 컴파일러는 해당 로드를 올바른 순서로 일으킬 +방백: 주소 의존성이 있는 경우, 컴파일러는 해당 로드를 올바른 순서로 일으킬 것으로 (예: `a[b]` 는 a[b] 를 로드 하기 전에 b 의 값을 먼저 로드한다) 기대되지만, C 언어 사양에는 컴파일러가 b 의 값을 추측 (예: 1 과 같음) 해서 b 로드 전에 a 로드를 하는 코드 (예: tmp = a[1]; if (b != 1) tmp = a[b]; ) 를 @@ -1863,6 +1874,7 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효� (*) dma_wmb(); (*) dma_rmb(); + (*) dma_mb(); 이것들은 CPU 와 DMA 가능한 디바이스에서 모두 액세스 가능한 공유 메모리의 읽기, 쓰기 작업들의 순서를 보장하기 위해 consistent memory 에서 사용하기 @@ -1893,12 +1905,13 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효� dma_rmb() 는 디스크립터로부터 데이터를 읽어오기 전에 디바이스가 소유권을 내려놓았을 것을 보장하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시 - 가졌음을 보기 전에 디스크립터에 데이터가 쓰였을 것을 보장합니다. 참고로, - writel() 을 사용하면 캐시 일관성이 있는 메모리 (cache coherent memory) - 쓰기가 MMIO 영역에의 쓰기 전에 완료되었을 것을 보장하므로 writel() 앞에 - wmb() 를 실행할 필요가 없음을 알아두시기 바랍니다. writel() 보다 비용이 - 저렴한 writel_relaxed() 는 이런 보장을 제공하지 않으므로 여기선 사용되지 - 않아야 합니다. + 가졌음을 보기 전에 디스크립터에 데이터가 쓰였을 것을 보장합니다. dma_mb() + 는 dma_rmb() 와 dma_wmb() 를 모두 내포합니다. 참고로, writel() 을 + 사용하면 캐시 일관성이 있는 메모리 (cache coherent memory) 쓰기가 MMIO + 영역에의 쓰기 전에 완료되었을 것을 보장하므로 writel() 앞에 wmb() 를 + 실행할 필요가 없음을 알아두시기 바랍니다. writel() 보다 비용이 저렴한 + writel_relaxed() 는 이런 보장을 제공하지 않으므로 여기선 사용되지 않아야 + 합니다. writel_relaxed() 와 같은 완화된 I/O 접근자들에 대한 자세한 내용을 위해서는 "커널 I/O 배리어의 효과" 섹션을, consistent memory 에 대한 자세한 내용을 @@ -1918,6 +1931,14 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효� Persistent memory 에서의 로드를 위해선 현재의 읽기 메모리 배리어로도 읽기 순서를 보장하는데 충분합니다. + (*) io_stop_wc(); + + 쓰기와 결합된 특성을 갖는 메모리 액세스의 경우 (예: ioremap_wc() 에 의해 + 리턴되는 것들), CPU 는 앞의 액세스들이 뒤따르는 것들과 병합되게끔 기다릴 + 수 있습니다. io_stop_wc() 는 그런 기다림이 성능에 영향을 끼칠 수 있을 때, + 이 매크로 앞의 쓰기-결합된 메모리 액세스들이 매크로 뒤의 것들과 병합되는 + 것을 방지하기 위해 사용될 수 있습니다. + ========================= 암묵적 커널 메모리 배리어 ========================= @@ -2827,9 +2848,9 @@ ld.acq 와 stl.rel 인스트럭션을 각각 만들어 내도록 합니다. DEC Alpha CPU 는 가장 완화된 메모리 순서의 CPU 중 하나입니다. 뿐만 아니라, Alpha CPU 의 일부 버전은 분할된 데이터 캐시를 가지고 있어서, 의미적으로 관계되어 있는 두개의 캐시 라인이 서로 다른 시간에 업데이트 되는게 가능합니다. -이게 데이터 의존성 배리어가 정말 필요해지는 부분인데, 데이터 의존성 배리어는 -메모리 일관성 시스템과 함께 두개의 캐시를 동기화 시켜서, 포인터 변경과 새로운 -데이터의 발견을 올바른 순서로 일어나게 하기 때문입니다. +이게 주소 의존성 배리어가 정말 필요해지는 부분인데, 주소 의존성 배리어는 메모리 +일관성 시스템과 함께 두개의 캐시를 동기화 시켜서, 포인터 변경과 새로운 데이터의 +발견을 올바른 순서로 일어나게 하기 때문입니다. 리눅스 커널의 메모리 배리어 모델은 Alpha 에 기초해서 정의되었습니다만, v4.15 부터는 Alpha 용 READ_ONCE() 코드 내에 smp_mb() 가 추가되어서 메모리 모델로의 diff --git a/Documentation/translations/zh_CN/loongarch/booting.rst b/Documentation/translations/zh_CN/loongarch/booting.rst new file mode 100644 index 000000000000..fb6440c438f0 --- /dev/null +++ b/Documentation/translations/zh_CN/loongarch/booting.rst @@ -0,0 +1,48 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/loongarch/booting.rst + +:翻译: + + 司延腾 Yanteng Si <[email protected]> + +==================== +启动 Linux/LoongArch +==================== + +:作者: 司延腾 <[email protected]> +:日期: 2022年11月18日 + +BootLoader传递给内核的信息 +========================== + +LoongArch支持ACPI和FDT启动，需要传递给内核的信息包括memmap、initrd、cmdline、可 +选的ACPI/FDT表等。 + +内核在 `kernel_entry` 入口处被传递以下参数: + + - a0 = efi_boot: `efi_boot` 是一个标志，表示这个启动环境是否完全符合UEFI + 的要求。 + + - a1 = cmdline: `cmdline` 是一个指向内核命令行的指针。 + + - a2 = systemtable: `systemtable` 指向EFI的系统表，在这个阶段涉及的所有 + 指针都是物理地址。 + +Linux/LoongArch内核镜像文件头 +============================= + +内核镜像是EFI镜像。作为PE文件，它们有一个64字节的头部结构体，如下所示:: + + u32 MZ_MAGIC /* "MZ", MS-DOS 头 */ + u32 res0 = 0 /* 保留 */ + u64 kernel_entry /* 内核入口点 */ + u64 _end - _text /* 内核镜像有效大小 */ + u64 load_offset /* 加载内核镜像相对内存起始地址的偏移量 */ + u64 res1 = 0 /* 保留 */ + u64 res2 = 0 /* 保留 */ + u64 res3 = 0 /* 保留 */ + u32 LINUX_PE_MAGIC /* 魔术数 */ + u32 pe_header - _head /* 到PE头的偏移量 */ diff --git a/Documentation/translations/zh_CN/loongarch/index.rst b/Documentation/translations/zh_CN/loongarch/index.rst index 7d23eb78379d..0273a08342f7 100644 --- a/Documentation/translations/zh_CN/loongarch/index.rst +++ b/Documentation/translations/zh_CN/loongarch/index.rst @@ -14,6 +14,7 @@ LoongArch体系结构 :numbered: introduction + booting irq-chip-model features diff --git a/Documentation/translations/zh_CN/loongarch/introduction.rst b/Documentation/translations/zh_CN/loongarch/introduction.rst index 128878f5bb70..f3ec25b163d7 100644 --- a/Documentation/translations/zh_CN/loongarch/introduction.rst +++ b/Documentation/translations/zh_CN/loongarch/introduction.rst @@ -70,8 +70,8 @@ LA64中每个寄存器为64位宽。 ``$r0`` 的内容总是固定为0，而其� ================= ================== =================== ========== .. note:: - 注意：在一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 - ``$a0`` 和 ``$a1`` 的别名，属于已经废弃的用法。 + 注意：在一些遗留代码中有时可能见到 ``$fv0`` 和 ``$fv1`` ，它们是 + ``$fa0`` 和 ``$fa1`` 的别名，属于已经废弃的用法。 向量寄存器 diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index eee9f857a986..896914e3a847 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -7213,14 +7213,13 @@ veto the transition. :Parameters: args[0] is the maximum poll time in nanoseconds :Returns: 0 on success; -1 on error -This capability overrides the kvm module parameter halt_poll_ns for the -target VM. - -VCPU polling allows a VCPU to poll for wakeup events instead of immediately -scheduling during guest halts. The maximum time a VCPU can spend polling is -controlled by the kvm module parameter halt_poll_ns. This capability allows -the maximum halt time to specified on a per-VM basis, effectively overriding -the module parameter for the target VM. +KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the +maximum halt-polling time for all vCPUs in the target VM. This capability can +be invoked at any time and any number of times to dynamically change the +maximum halt-polling time. + +See Documentation/virt/kvm/halt-polling.rst for more information on halt +polling. 7.21 KVM_CAP_X86_USER_SPACE_MSR ------------------------------- diff --git a/Documentation/virt/kvm/x86/halt-polling.rst b/Documentation/virt/kvm/halt-polling.rst index 4922e4a15f18..3fae39b1a5ba 100644 --- a/Documentation/virt/kvm/x86/halt-polling.rst +++ b/Documentation/virt/kvm/halt-polling.rst @@ -119,6 +119,19 @@ These module parameters can be set from the debugfs files in: Note: that these module parameters are system wide values and are not able to be tuned on a per vm basis. +Any changes to these parameters will be picked up by new and existing vCPUs the +next time they halt, with the notable exception of VMs using KVM_CAP_HALT_POLL +(see next section). + +KVM_CAP_HALT_POLL +================= + +KVM_CAP_HALT_POLL is a VM capability that allows userspace to override halt_poll_ns +on a per-VM basis. VMs using KVM_CAP_HALT_POLL ignore halt_poll_ns completely (but +still obey halt_poll_ns_grow, halt_poll_ns_grow_start, and halt_poll_ns_shrink). + +See Documentation/virt/kvm/api.rst for more information on this capability. + Further Notes ============= diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index e0a2c74e1043..ad13ec55ddfe 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -17,4 +17,5 @@ KVM locking vcpu-requests + halt-polling review-checklist diff --git a/Documentation/virt/kvm/x86/index.rst b/Documentation/virt/kvm/x86/index.rst index 7ff588826b9f..9ece6b8dc817 100644 --- a/Documentation/virt/kvm/x86/index.rst +++ b/Documentation/virt/kvm/x86/index.rst @@ -10,7 +10,6 @@ KVM for x86 systems amd-memory-encryption cpuid errata - halt-polling hypercalls mmu msr diff --git a/MAINTAINERS b/MAINTAINERS index 00ff4a2949b8..886d3f69ee64 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5299,7 +5299,7 @@ M: Johannes Weiner <[email protected]> M: Michal Hocko <[email protected]> M: Roman Gushchin <[email protected]> M: Shakeel Butt <[email protected]> -R: Muchun Song <[email protected]> +R: Muchun Song <[email protected]> S: Maintained @@ -5585,8 +5585,6 @@ F: drivers/scsi/cxgbi/cxgb3i CXGB4 CRYPTO DRIVER (chcr) M: Ayush Sawal <[email protected]> -M: Vinay Kumar Yadav <[email protected]> -M: Rohit Maheshwari <[email protected]> S: Supported W: http://www.chelsio.com @@ -5594,8 +5592,6 @@ F: drivers/crypto/chelsio CXGB4 INLINE CRYPTO DRIVER M: Ayush Sawal <[email protected]> -M: Vinay Kumar Yadav <[email protected]> -M: Rohit Maheshwari <[email protected]> S: Supported W: http://www.chelsio.com @@ -9443,7 +9439,7 @@ F: drivers/net/ethernet/huawei/hinic/ HUGETLB SUBSYSTEM M: Mike Kravetz <[email protected]> -M: Muchun Song <[email protected]> +M: Muchun Song <[email protected]> S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -10287,7 +10283,7 @@ T: git https://github.com/intel/gvt-linux.git F: drivers/gpu/drm/i915/gvt/ INTEL HID EVENT DRIVER -M: Alex Hung <[email protected]> +M: Alex Hung <[email protected]> S: Maintained F: drivers/platform/x86/intel/hid.c @@ -11035,6 +11031,7 @@ KCONFIG M: Masahiro Yamada <[email protected]> S: Maintained +Q: https://patchwork.kernel.org/project/linux-kbuild/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git kconfig F: Documentation/kbuild/kconfig* F: scripts/Kconfig.include @@ -11092,10 +11089,12 @@ F: fs/autofs/ KERNEL BUILD + files below scripts/ (unless maintained elsewhere) M: Masahiro Yamada <[email protected]> -M: Michal Marek <[email protected]> +R: Nathan Chancellor <[email protected]> R: Nick Desaulniers <[email protected]> +R: Nicolas Schier <[email protected]> S: Maintained +Q: https://patchwork.kernel.org/project/linux-kbuild/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git F: Documentation/kbuild/ F: Makefile @@ -15949,6 +15948,7 @@ Q: https://patchwork.kernel.org/project/linux-pci/list/ B: https://bugzilla.kernel.org C: irc://irc.oftc.net/linux-pci T: git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git +F: Documentation/devicetree/bindings/pci/ F: drivers/pci/controller/ F: drivers/pci/pci-bridge-emul.c F: drivers/pci/pci-bridge-emul.h @@ -16055,7 +16055,7 @@ F: Documentation/devicetree/bindings/pci/microchip* F: drivers/pci/controller/*microchip* PCIE DRIVER FOR QUALCOMM MSM -M: Stanimir Varbanov <[email protected]> +M: Manivannan Sadhasivam <[email protected]> S: Maintained @@ -16145,7 +16145,8 @@ F: include/linux/peci-cpu.h F: include/linux/peci.h PENSANDO ETHERNET DRIVERS -M: Shannon Nelson <[email protected]> +M: Shannon Nelson <[email protected]> +M: Brett Creeley <[email protected]> S: Supported @@ -17481,10 +17482,8 @@ S: Maintained F: drivers/net/wireless/realtek/rtw89/ REDPINE WIRELESS DRIVER -M: Amitkumar Karwar <[email protected]> -M: Siva Rebbagondla <[email protected]> -S: Maintained +S: Orphan F: drivers/net/wireless/rsi/ REGISTER MAP ABSTRACTION @@ -18007,7 +18006,7 @@ L: [email protected] S: Maintained F: drivers/video/fbdev/savage/ -S390 +S390 ARCHITECTURE M: Heiko Carstens <[email protected]> M: Vasily Gorbik <[email protected]> M: Alexander Gordeev <[email protected]> @@ -18062,6 +18061,15 @@ L: [email protected] S: Supported F: drivers/s390/net/ +S390 MM +M: Alexander Gordeev <[email protected]> +M: Gerald Schaefer <[email protected]> +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git +F: arch/s390/include/asm/pgtable.h +F: arch/s390/mm + S390 PCI SUBSYSTEM M: Niklas Schnelle <[email protected]> M: Gerald Schaefer <[email protected]> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 8f138e580d1a..6b95244c3057 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -468,6 +468,9 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM config ARCH_HAVE_NMI_SAFE_CMPXCHG bool +config ARCH_HAS_NMI_SAFE_THIS_CPU_OPS + bool + config HAVE_ALIGNED_STRUCT_PAGE bool help diff --git a/arch/arm/boot/dts/am335x-pcm-953.dtsi b/arch/arm/boot/dts/am335x-pcm-953.dtsi index dae448040a97..947497413977 100644 --- a/arch/arm/boot/dts/am335x-pcm-953.dtsi +++ b/arch/arm/boot/dts/am335x-pcm-953.dtsi @@ -12,22 +12,20 @@ compatible = "phytec,am335x-pcm-953", "phytec,am335x-phycore-som", "ti,am33xx"; /* Power */ - regulators { - vcc3v3: fixedregulator@1 { - compatible = "regulator-fixed"; - regulator-name = "vcc3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - }; + vcc3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + }; - vcc1v8: fixedregulator@2 { - compatible = "regulator-fixed"; - regulator-name = "vcc1v8"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - }; + vcc1v8: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; }; /* User IO */ diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi index 7a113325abb9..6f9004ebf424 100644 --- a/arch/arm/boot/dts/at91rm9200.dtsi +++ b/arch/arm/boot/dts/at91rm9200.dtsi @@ -666,7 +666,7 @@ compatible = "atmel,at91rm9200-udc"; reg = <0xfffb0000 0x4000>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&pmc PMC_TYPE_PERIPHERAL 11>, <&pmc PMC_TYPE_SYSTEM 2>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 11>, <&pmc PMC_TYPE_SYSTEM 1>; clock-names = "pclk", "hclk"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 60d61291f344..024af2db638e 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -39,6 +39,13 @@ }; + usb1 { + pinctrl_usb1_vbus_gpio: usb1_vbus_gpio { + atmel,pins = + <AT91_PIOC 5 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>; /* PC5 GPIO */ + }; + }; + mmc0_slot1 { pinctrl_board_mmc0_slot1: mmc0_slot1-board { atmel,pins = @@ -84,6 +91,8 @@ }; usb1: gadget@fffa4000 { + pinctrl-0 = <&pinctrl_usb1_vbus_gpio>; + pinctrl-names = "default"; atmel,vbus-gpio = <&pioC 5 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index b4605edfd2ab..d8fa83effd63 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -364,8 +364,8 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wifi>; interrupts-extended = <&gpio1 30 IRQ_TYPE_LEVEL_HIGH>; - ref-clock-frequency = "38400000"; - tcxo-clock-frequency = "19200000"; + ref-clock-frequency = <38400000>; + tcxo-clock-frequency = <19200000>; }; }; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 03d2e8544a4e..0fc9e6b8b05d 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1270,10 +1270,10 @@ clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>; }; - gpmi: nand-controller@33002000 { + gpmi: nand-controller@33002000{ compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <0>; + #size-cells = <1>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/rk3036-evb.dts b/arch/arm/boot/dts/rk3036-evb.dts index 9fd4d9db9f8f..becdc0b664bf 100644 --- a/arch/arm/boot/dts/rk3036-evb.dts +++ b/arch/arm/boot/dts/rk3036-evb.dts @@ -35,11 +35,10 @@ &i2c1 { status = "okay"; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; }; }; diff --git a/arch/arm/boot/dts/rk3066a-mk808.dts b/arch/arm/boot/dts/rk3066a-mk808.dts index cfa318a506eb..2db5ba706208 100644 --- a/arch/arm/boot/dts/rk3066a-mk808.dts +++ b/arch/arm/boot/dts/rk3066a-mk808.dts @@ -32,7 +32,7 @@ keyup-threshold-microvolt = <2500000>; poll-interval = <100>; - recovery { + button-recovery { label = "recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <0>; diff --git a/arch/arm/boot/dts/rk3188-radxarock.dts b/arch/arm/boot/dts/rk3188-radxarock.dts index e7cf18823558..118deacd38c4 100644 --- a/arch/arm/boot/dts/rk3188-radxarock.dts +++ b/arch/arm/boot/dts/rk3188-radxarock.dts @@ -71,7 +71,7 @@ #sound-dai-cells = <0>; }; - ir_recv: gpio-ir-receiver { + ir_recv: ir-receiver { compatible = "gpio-ir-receiver"; gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi index cdd4a0bd5133..44b54af0bbf9 100644 --- a/arch/arm/boot/dts/rk3188.dtsi +++ b/arch/arm/boot/dts/rk3188.dtsi @@ -379,7 +379,7 @@ rockchip,pins = <2 RK_PD3 1 &pcfg_pull_none>; }; - lcdc1_rgb24: ldcd1-rgb24 { + lcdc1_rgb24: lcdc1-rgb24 { rockchip,pins = <2 RK_PA0 1 &pcfg_pull_none>, <2 RK_PA1 1 &pcfg_pull_none>, <2 RK_PA2 1 &pcfg_pull_none>, @@ -607,7 +607,6 @@ &global_timer { interrupts = <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; - status = "disabled"; }; &local_timer { diff --git a/arch/arm/boot/dts/rk3288-evb-act8846.dts b/arch/arm/boot/dts/rk3288-evb-act8846.dts index be695b8c1f67..8a635c243127 100644 --- a/arch/arm/boot/dts/rk3288-evb-act8846.dts +++ b/arch/arm/boot/dts/rk3288-evb-act8846.dts @@ -54,7 +54,7 @@ vin-supply = <&vcc_sys>; }; - hym8563@51 { + rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; diff --git a/arch/arm/boot/dts/rk3288-evb.dtsi b/arch/arm/boot/dts/rk3288-evb.dtsi index 399d6b9c5fd4..382d2839cf47 100644 --- a/arch/arm/boot/dts/rk3288-evb.dtsi +++ b/arch/arm/boot/dts/rk3288-evb.dtsi @@ -28,19 +28,19 @@ press-threshold-microvolt = <300000>; }; - menu { + button-menu { label = "Menu"; linux,code = <KEY_MENU>; press-threshold-microvolt = <640000>; }; - esc { + button-esc { label = "Esc"; linux,code = <KEY_ESC>; press-threshold-microvolt = <1000000>; }; - home { + button-home { label = "Home"; linux,code = <KEY_HOME>; press-threshold-microvolt = <1300000>; diff --git a/arch/arm/boot/dts/rk3288-firefly.dtsi b/arch/arm/boot/dts/rk3288-firefly.dtsi index 052afe5543e2..3836c61cfb76 100644 --- a/arch/arm/boot/dts/rk3288-firefly.dtsi +++ b/arch/arm/boot/dts/rk3288-firefly.dtsi @@ -233,11 +233,10 @@ vin-supply = <&vcc_sys>; }; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; interrupt-parent = <&gpio7>; interrupts = <RK_PA4 IRQ_TYPE_EDGE_FALLING>; diff --git a/arch/arm/boot/dts/rk3288-miqi.dts b/arch/arm/boot/dts/rk3288-miqi.dts index 713f55e143c6..db1eb648e0e1 100644 --- a/arch/arm/boot/dts/rk3288-miqi.dts +++ b/arch/arm/boot/dts/rk3288-miqi.dts @@ -162,11 +162,10 @@ vin-supply = <&vcc_sys>; }; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; }; diff --git a/arch/arm/boot/dts/rk3288-rock2-square.dts b/arch/arm/boot/dts/rk3288-rock2-square.dts index 80e0f07c8e87..13cfdaa95cc7 100644 --- a/arch/arm/boot/dts/rk3288-rock2-square.dts +++ b/arch/arm/boot/dts/rk3288-rock2-square.dts @@ -165,11 +165,10 @@ }; &i2c0 { - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; interrupt-parent = <&gpio0>; interrupts = <RK_PA4 IRQ_TYPE_EDGE_FALLING>; diff --git a/arch/arm/boot/dts/rk3288-vmarc-som.dtsi b/arch/arm/boot/dts/rk3288-vmarc-som.dtsi index 0ae2bd150e37..793951655b73 100644 --- a/arch/arm/boot/dts/rk3288-vmarc-som.dtsi +++ b/arch/arm/boot/dts/rk3288-vmarc-som.dtsi @@ -241,7 +241,6 @@ interrupt-parent = <&gpio5>; interrupts = <RK_PC3 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "hym8563"; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi index bf285091a9eb..cb4e42ede56a 100644 --- a/arch/arm/boot/dts/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rk3xxx.dtsi @@ -76,6 +76,13 @@ reg = <0x1013c200 0x20>; interrupts = <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>; clocks = <&cru CORE_PERI>; + status = "disabled"; + /* The clock source and the sched_clock provided by the arm_global_timer + * on Rockchip rk3066a/rk3188 are quite unstable because their rates + * depend on the CPU frequency. + * Keep the arm_global_timer disabled in order to have the + * DW_APB_TIMER (rk3066a) or ROCKCHIP_TIMER (rk3188) selected by default. + */ }; local_timer: local-timer@1013c600 { diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index fe87397c3d8c..bdbc1e590891 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -17,7 +17,7 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ARM_pc = (__ip); \ - (regs)->ARM_fp = (unsigned long) __builtin_frame_address(0); \ + frame_pointer((regs)) = (unsigned long) __builtin_frame_address(0); \ (regs)->ARM_sp = current_stack_pointer; \ (regs)->ARM_cpsr = SVC_MODE; \ } diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h index d16aba48fa0a..090011394477 100644 --- a/arch/arm/include/asm/pgtable-nommu.h +++ b/arch/arm/include/asm/pgtable-nommu.h @@ -45,12 +45,6 @@ typedef pte_t *pte_addr_t; /* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) (virt_to_page(0)) - -/* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) (prot) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 78a532068fec..ef48a55e9af8 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -10,6 +10,15 @@ #include <linux/const.h> #include <asm/proc-fns.h> +#ifndef __ASSEMBLY__ +/* + * ZERO_PAGE is a global shared page that is always zero: used + * for zero-mapped memory areas etc.. + */ +extern struct page *empty_zero_page; +#define ZERO_PAGE(vaddr) (empty_zero_page) +#endif + #ifndef CONFIG_MMU #include <asm-generic/pgtable-nopud.h> @@ -139,13 +148,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, */ #ifndef __ASSEMBLY__ -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern struct page *empty_zero_page; -#define ZERO_PAGE(vaddr) (empty_zero_page) - extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c index 67ed68fbe3a5..bf2b5c6a18c6 100644 --- a/arch/arm/mach-at91/sama5.c +++ b/arch/arm/mach-at91/sama5.c @@ -26,7 +26,7 @@ static void sama5_l2c310_write_sec(unsigned long val, unsigned reg) static void __init sama5_secure_cache_init(void) { sam_secure_init(); - if (sam_linux_is_optee_available()) + if (IS_ENABLED(CONFIG_OUTER_CACHE) && sam_linux_is_optee_available()) outer_cache.write_sec = sama5_l2c310_write_sec; } diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 25c9d184fa4c..1c57ac401649 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -393,8 +393,10 @@ static void __init mxs_machine_init(void) root = of_find_node_by_path("/"); ret = of_property_read_string(root, "model", &soc_dev_attr->machine); - if (ret) + if (ret) { + kfree(soc_dev_attr); return; + } soc_dev_attr->family = "Freescale MXS Family"; soc_dev_attr->soc_id = mxs_get_soc_id(); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 46cccd6bf705..de988cba9a4b 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -105,6 +105,19 @@ static inline bool is_write_fault(unsigned int fsr) return (fsr & FSR_WRITE) && !(fsr & FSR_CM); } +static inline bool is_translation_fault(unsigned int fsr) +{ + int fs = fsr_fs(fsr); +#ifdef CONFIG_ARM_LPAE + if ((fs & FS_MMU_NOLL_MASK) == FS_TRANS_NOLL) + return true; +#else + if (fs == FS_L1_TRANS || fs == FS_L2_TRANS) + return true; +#endif + return false; +} + static void die_kernel_fault(const char *msg, struct mm_struct *mm, unsigned long addr, unsigned int fsr, struct pt_regs *regs) @@ -140,7 +153,8 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) + if (is_translation_fault(fsr) && + kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) return; msg = "paging request"; @@ -208,7 +222,7 @@ static inline bool is_permission_fault(unsigned int fsr) { int fs = fsr_fs(fsr); #ifdef CONFIG_ARM_LPAE - if ((fs & FS_PERM_NOLL_MASK) == FS_PERM_NOLL) + if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL) return true; #else if (fs == FS_L1_PERM || fs == FS_L2_PERM) diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 83b5ab32d7a4..54927ba1fa6e 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -14,8 +14,9 @@ #ifdef CONFIG_ARM_LPAE #define FSR_FS_AEA 17 +#define FS_TRANS_NOLL 0x4 #define FS_PERM_NOLL 0xC -#define FS_PERM_NOLL_MASK 0x3C +#define FS_MMU_NOLL_MASK 0x3C static inline int fsr_fs(unsigned int fsr) { @@ -23,8 +24,10 @@ static inline int fsr_fs(unsigned int fsr) } #else #define FSR_FS_AEA 22 -#define FS_L1_PERM 0xD -#define FS_L2_PERM 0xF +#define FS_L1_TRANS 0x5 +#define FS_L2_TRANS 0x7 +#define FS_L1_PERM 0xD +#define FS_L2_PERM 0xF static inline int fsr_fs(unsigned int fsr) { diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c42debaded95..c1494a4dee25 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -26,6 +26,13 @@ unsigned long vectors_base; +/* + * empty_zero_page is a special page that is used for + * zero-initialized data and COW. + */ +struct page *empty_zero_page; +EXPORT_SYMBOL(empty_zero_page); + #ifdef CONFIG_ARM_MPU struct mpu_rgn_info mpu_rgn_info; #endif @@ -148,9 +155,21 @@ void __init adjust_lowmem_bounds(void) */ void __init paging_init(const struct machine_desc *mdesc) { + void *zero_page; + early_trap_init((void *)vectors_base); mpu_setup(); + + /* allocate the zero page. */ + zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!zero_page) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); + bootmem_init(); + + empty_zero_page = virt_to_page(zero_page); + flush_dcache_page(empty_zero_page); } /* diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 505c8a1ccbe0..099ee812f3f1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -31,6 +31,7 @@ config ARM64 select ARCH_HAS_KCOV select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index 53f6660656ac..ca1d287a0a01 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -161,6 +161,7 @@ clocks = <&ccu CLK_BUS_VP9>, <&ccu CLK_VP9>; clock-names = "bus", "mod"; resets = <&ccu RST_BUS_VP9>; + iommus = <&iommu 5>; }; video-codec@1c0e000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index 9f1469db554d..b4c1ef2559f2 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -544,14 +544,14 @@ pinctrl_pcie0: pcie0grp { fsl,pins = < - MX8MP_IOMUXC_I2C4_SCL__PCIE_CLKREQ_B 0x61 /* open drain, pull up */ - MX8MP_IOMUXC_SD1_DATA5__GPIO2_IO07 0x41 + MX8MP_IOMUXC_I2C4_SCL__PCIE_CLKREQ_B 0x60 /* open drain, pull up */ + MX8MP_IOMUXC_SD1_DATA5__GPIO2_IO07 0x40 >; }; pinctrl_pcie0_reg: pcie0reggrp { fsl,pins = < - MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 0x41 + MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 0x40 >; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-evb.dts b/arch/arm64/boot/dts/rockchip/px30-evb.dts index 07008d84434c..c1bbd555f5f5 100644 --- a/arch/arm64/boot/dts/rockchip/px30-evb.dts +++ b/arch/arm64/boot/dts/rockchip/px30-evb.dts @@ -30,31 +30,31 @@ keyup-threshold-microvolt = <1800000>; poll-interval = <100>; - esc-key { + button-esc { label = "esc"; linux,code = <KEY_ESC>; press-threshold-microvolt = <1310000>; }; - home-key { + button-home { label = "home"; linux,code = <KEY_HOME>; press-threshold-microvolt = <624000>; }; - menu-key { + button-menu { label = "menu"; linux,code = <KEY_MENU>; press-threshold-microvolt = <987000>; }; - vol-down-key { + button-down { label = "volume down"; linux,code = <KEY_VOLUMEDOWN>; press-threshold-microvolt = <300000>; }; - vol-up-key { + button-up { label = "volume up"; linux,code = <KEY_VOLUMEUP>; press-threshold-microvolt = <17000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-evb.dts b/arch/arm64/boot/dts/rockchip/rk3308-evb.dts index 9fe9b0d11003..184b84fdde07 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-evb.dts @@ -23,7 +23,7 @@ poll-interval = <100>; keyup-threshold-microvolt = <1800000>; - func-key { + button-func { linux,code = <KEY_FN>; label = "function"; press-threshold-microvolt = <18000>; @@ -37,31 +37,31 @@ poll-interval = <100>; keyup-threshold-microvolt = <1800000>; - esc-key { + button-esc { linux,code = <KEY_MICMUTE>; label = "micmute"; press-threshold-microvolt = <1130000>; }; - home-key { + button-home { linux,code = <KEY_MODE>; label = "mode"; press-threshold-microvolt = <901000>; }; - menu-key { + button-menu { linux,code = <KEY_PLAY>; label = "play"; press-threshold-microvolt = <624000>; }; - vol-down-key { + button-down { linux,code = <KEY_VOLUMEDOWN>; label = "volume down"; press-threshold-microvolt = <300000>; }; - vol-up-key { + button-up { linux,code = <KEY_VOLUMEUP>; label = "volume up"; press-threshold-microvolt = <18000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts index ea6820902ede..7ea48167747c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts @@ -19,7 +19,7 @@ stdout-path = "serial2:1500000n8"; }; - ir_rx { + ir-receiver { compatible = "gpio-ir-receiver"; gpios = <&gpio0 RK_PC0 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts index 43c928ac98f0..1deef53a4c94 100644 --- a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts @@ -25,7 +25,7 @@ keyup-threshold-microvolt = <1800000>; poll-interval = <100>; - recovery { + button-recovery { label = "recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <17000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts index 7f5bba0c6001..81d1064fdb21 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts +++ b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts @@ -208,11 +208,10 @@ vin-supply = <&vcc_sys>; }; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; /* rtc_int is not connected */ }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts index 38d757c00548..5589f3db6b36 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts +++ b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts @@ -192,11 +192,10 @@ vin-supply = <&vcc_sys>; }; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; /* rtc_int is not connected */ }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index ed3348b558f8..a47d9f758611 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -734,10 +734,6 @@ camera: &i2c7 { }; /* PINCTRL OVERRIDES */ -&ec_ap_int_l { - rockchip,pins = <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>; -}; - &ap_fw_wp { rockchip,pins = <0 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi index 2a332763c35c..9d9297bc5f04 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi @@ -123,7 +123,7 @@ keyup-threshold-microvolt = <1800000>; poll-interval = <100>; - recovery { + button-recovery { label = "Recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <18000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts b/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts index 452728b82e42..3bf8f959e42c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts @@ -39,7 +39,7 @@ keyup-threshold-microvolt = <1800000>; poll-interval = <100>; - recovery { + button-recovery { label = "Recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <18000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-m4b.dts b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-m4b.dts index 72182c58cc46..65cb21837b0c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-m4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-m4b.dts @@ -19,7 +19,7 @@ keyup-threshold-microvolt = <1500000>; poll-interval = <100>; - recovery { + button-recovery { label = "Recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <18000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi index 278123b4f911..b6e082f1f6d9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi @@ -167,6 +167,7 @@ }; &emmc_phy { + rockchip,enable-strobe-pulldown; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts index 9e2e246e0bab..dba4d03bfc2b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts @@ -52,13 +52,13 @@ press-threshold-microvolt = <300000>; }; - back { + button-back { label = "Back"; linux,code = <KEY_BACK>; press-threshold-microvolt = <985000>; }; - menu { + button-menu { label = "Menu"; linux,code = <KEY_MENU>; press-threshold-microvolt = <1314000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index 04c752f49be9..115c14c0a3c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -207,7 +207,7 @@ cap-sd-highspeed; cd-gpios = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; disable-wp; - max-frequency = <150000000>; + max-frequency = <40000000>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>; vmmc-supply = <&vcc3v3_baseboard>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts index 5a2661ae0131..7ba1c28f70a9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts @@ -98,13 +98,12 @@ }; &i2c0 { - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; interrupt-parent = <&gpio0>; interrupts = <RK_PA5 IRQ_TYPE_EDGE_FALLING>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "xin32k"; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi index 2f4b1b2e3ac7..bbf1e3f24585 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi @@ -41,7 +41,7 @@ keyup-threshold-microvolt = <1500000>; poll-interval = <100>; - recovery { + button-recovery { label = "Recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <18000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 645ced6617a6..1f76d3501bda 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -509,7 +509,6 @@ &i2s1 { rockchip,playback-channels = <2>; rockchip,capture-channels = <2>; - status = "okay"; }; &i2s2 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts index 13927e7d0724..dbec2b7173a0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts @@ -33,13 +33,13 @@ press-threshold-microvolt = <300000>; }; - back { + button-back { label = "Back"; linux,code = <KEY_BACK>; press-threshold-microvolt = <985000>; }; - menu { + button-menu { label = "Menu"; linux,code = <KEY_MENU>; press-threshold-microvolt = <1314000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi b/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi index 935b8c68a71d..bf9eb0405b62 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399pro-vmarc-som.dtsi @@ -297,11 +297,10 @@ clock-frequency = <400000>; status = "okay"; - hym8563: hym8563@51 { + hym8563: rtc@51 { compatible = "haoyu,hym8563"; reg = <0x51>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "hym8563"; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi index 0d45868132b9..8d61f824c12d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi @@ -23,7 +23,7 @@ io-channel-names = "buttons"; keyup-threshold-microvolt = <1750000>; - recovery { + button-recovery { label = "recovery"; linux,code = <KEY_VENDOR>; press-threshold-microvolt = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index a05460b92415..25a8c781f4e7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -740,7 +740,7 @@ &uart1 { pinctrl-names = "default"; - pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn>; + pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn &uart1m0_rtsn>; status = "okay"; uart-has-rtscts; @@ -748,13 +748,14 @@ compatible = "brcm,bcm43438-bt"; clocks = <&rk817 1>; clock-names = "lpo"; - device-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; - host-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; + device-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&bt_host_wake_l &bt_wake_l &bt_enable_h>; vbat-supply = <&vcc_sys>; vddio-supply = <&vcca1v8_pmu>; + max-speed = <3000000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts index 77b179cd20e7..b276eb0810c7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts @@ -246,7 +246,7 @@ compatible = "rockchip,rk809"; reg = <0x20>; interrupt-parent = <&gpio0>; - interrupts = <RK_PA7 IRQ_TYPE_LEVEL_LOW>; + interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>; assigned-clocks = <&cru I2S1_MCLKOUT_TX>; assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts index dba648c2f57e..9fd262334d77 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts @@ -142,7 +142,7 @@ assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>; assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>, <&gmac1_clkin>; clock_in_out = "input"; - phy-mode = "rgmii-id"; + phy-mode = "rgmii"; phy-supply = <&vcc_3v3>; pinctrl-names = "default"; pinctrl-0 = <&gmac1m0_miim @@ -432,11 +432,7 @@ &i2c3 { pinctrl-names = "default"; - pinctrl-0 = <&i2c3m1_xfer>; - status = "okay"; -}; - -&i2c5 { + pinctrl-0 = <&i2c3m0_xfer>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index c282f6e79960..26d7fda275ed 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -500,7 +500,6 @@ interrupt-parent = <&gpio0>; interrupts = <RK_PD3 IRQ_TYPE_EDGE_FALLING>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "rtcic_32kout"; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts index fb87a168fe96..539ef8cc7792 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts @@ -509,7 +509,6 @@ interrupt-parent = <&gpio0>; interrupts = <RK_PD3 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <0>; - clock-frequency = <32768>; clock-output-names = "rtcic_32kout"; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index d6cf535d8352..439e2bc5d5d8 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,16 +14,8 @@ #ifdef CONFIG_EFI extern void efi_init(void); - -bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg); #else #define efi_init() - -static inline -bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) -{ - return false; -} #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 67babd5f04c2..75691a2641c1 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> SYM_FUNC_START(__efi_rt_asm_wrapper) - stp x29, x30, [sp, #-112]! + stp x29, x30, [sp, #-32]! mov x29, sp /* @@ -17,20 +17,6 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) stp x1, x18, [sp, #16] /* - * Preserve all callee saved registers and record the stack pointer - * value in a per-CPU variable so we can recover from synchronous - * exceptions occurring while running the firmware routines. - */ - stp x19, x20, [sp, #32] - stp x21, x22, [sp, #48] - stp x23, x24, [sp, #64] - stp x25, x26, [sp, #80] - stp x27, x28, [sp, #96] - - adr_this_cpu x8, __efi_rt_asm_recover_sp, x9 - str x29, [x8] - - /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the * stack. @@ -45,7 +31,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) ldp x1, x2, [sp, #16] cmp x2, x18 - ldp x29, x30, [sp], #112 + ldp x29, x30, [sp], #32 b.ne 0f ret 0: @@ -59,18 +45,3 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x18, x2 b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) - -SYM_FUNC_START(__efi_rt_asm_recover) - ldr_this_cpu x8, __efi_rt_asm_recover_sp, x9 - mov sp, x8 - - ldp x0, x18, [sp, #16] - ldp x19, x20, [sp, #32] - ldp x21, x22, [sp, #48] - ldp x23, x24, [sp, #64] - ldp x25, x26, [sp, #80] - ldp x27, x28, [sp, #96] - ldp x29, x30, [sp], #112 - - b efi_handle_runtime_exception -SYM_FUNC_END(__efi_rt_asm_recover) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index ee53f2a0aa03..a908a37f0367 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,7 +9,6 @@ #include <linux/efi.h> #include <linux/init.h> -#include <linux/percpu.h> #include <asm/efi.h> @@ -145,28 +144,3 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } - -asmlinkage DEFINE_PER_CPU(u64, __efi_rt_asm_recover_sp); - -asmlinkage efi_status_t __efi_rt_asm_recover(void); - -asmlinkage efi_status_t efi_handle_runtime_exception(const char *f) -{ - pr_err(FW_BUG "Synchronous exception occurred in EFI runtime service %s()\n", f); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return EFI_ABORTED; -} - -bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) -{ - /* Check whether the exception occurred while running the firmware */ - if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64) - return false; - - pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); - add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - dump_stack(); - - regs->pc = (u64)__efi_rt_asm_recover; - return true; -} diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..5240f6acad64 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -36,7 +36,22 @@ void arch_dma_prep_coherent(struct page *page, size_t size) { unsigned long start = (unsigned long)page_address(page); - dcache_clean_poc(start, start + size); + /* + * The architecture only requires a clean to the PoC here in order to + * meet the requirements of the DMA API. However, some vendors (i.e. + * Qualcomm) abuse the DMA API for transferring buffers from the + * non-secure to the secure world, resetting the system if a non-secure + * access shows up after the buffer has been transferred: + * + * https://lore.kernel.org/r/[email protected] + * + * Using clean+invalidate appears to make this issue less likely, but + * the drivers themselves still need fixing as the CPU could issue a + * speculative read from the buffer via the linear mapping irrespective + * of the cache maintenance we use. Once the drivers are fixed, we can + * relax this to a clean operation. + */ + dcache_clean_inval_poc(start, start + size); } #ifdef CONFIG_IOMMU_DMA diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3e9cf9826417..5b391490e045 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -30,7 +30,6 @@ #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> -#include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -392,9 +391,6 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, msg = "paging request"; } - if (efi_runtime_fixup_exception(regs, msg)) - return; - die_kernel_fault(msg, addr, esr, regs); } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 903096bd87f8..386adde2feff 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -10,6 +10,7 @@ config LOONGARCH select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_INLINE_READ_LOCK if !PREEMPTION diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index f4cb54d5afd6..01b57b726322 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -97,7 +97,7 @@ KBUILD_LDFLAGS += -m $(ld-emul) ifdef CONFIG_LOONGARCH CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ - egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ + grep -E -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g') endif diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index d06d4542b634..5332b1433f38 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -117,7 +117,7 @@ extern struct fwnode_handle *liointc_handle; extern struct fwnode_handle *pch_lpc_handle; extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; -extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev); +extern irqreturn_t loongson_ipi_interrupt(int irq, void *dev); #include <asm-generic/irq.h> diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 946704bee599..79d5bfd913e0 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -349,13 +349,17 @@ static inline pte_t pte_mkclean(pte_t pte) static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= (_PAGE_DIRTY | _PAGE_MODIFIED); + pte_val(pte) |= _PAGE_MODIFIED; + if (pte_val(pte) & _PAGE_WRITE) + pte_val(pte) |= _PAGE_DIRTY; return pte; } static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) |= (_PAGE_WRITE | _PAGE_DIRTY); + pte_val(pte) |= _PAGE_WRITE; + if (pte_val(pte) & _PAGE_MODIFIED) + pte_val(pte) |= _PAGE_DIRTY; return pte; } @@ -455,7 +459,9 @@ static inline int pmd_write(pmd_t pmd) static inline pmd_t pmd_mkwrite(pmd_t pmd) { - pmd_val(pmd) |= (_PAGE_WRITE | _PAGE_DIRTY); + pmd_val(pmd) |= _PAGE_WRITE; + if (pmd_val(pmd) & _PAGE_MODIFIED) + pmd_val(pmd) |= _PAGE_DIRTY; return pmd; } @@ -478,10 +484,13 @@ static inline pmd_t pmd_mkclean(pmd_t pmd) static inline pmd_t pmd_mkdirty(pmd_t pmd) { - pmd_val(pmd) |= (_PAGE_DIRTY | _PAGE_MODIFIED); + pmd_val(pmd) |= _PAGE_MODIFIED; + if (pmd_val(pmd) & _PAGE_WRITE) + pmd_val(pmd) |= _PAGE_DIRTY; return pmd; } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_ACCESSED); diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 71189b28bfb2..d82687390b4a 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -19,21 +19,21 @@ extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; extern cpumask_t cpu_foreign_map[]; -void loongson3_smp_setup(void); -void loongson3_prepare_cpus(unsigned int max_cpus); -void loongson3_boot_secondary(int cpu, struct task_struct *idle); -void loongson3_init_secondary(void); -void loongson3_smp_finish(void); -void loongson3_send_ipi_single(int cpu, unsigned int action); -void loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action); +void loongson_smp_setup(void); +void loongson_prepare_cpus(unsigned int max_cpus); +void loongson_boot_secondary(int cpu, struct task_struct *idle); +void loongson_init_secondary(void); +void loongson_smp_finish(void); +void loongson_send_ipi_single(int cpu, unsigned int action); +void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action); #ifdef CONFIG_HOTPLUG_CPU -int loongson3_cpu_disable(void); -void loongson3_cpu_die(unsigned int cpu); +int loongson_cpu_disable(void); +void loongson_cpu_die(unsigned int cpu); #endif static inline void plat_smp_setup(void) { - loongson3_smp_setup(); + loongson_smp_setup(); } static inline int raw_smp_processor_id(void) @@ -78,35 +78,25 @@ extern void calculate_cpu_foreign_map(void); */ extern void show_ipi_list(struct seq_file *p, int prec); -/* - * This function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ -static inline void smp_send_reschedule(int cpu) -{ - loongson3_send_ipi_single(cpu, SMP_RESCHEDULE); -} - static inline void arch_send_call_function_single_ipi(int cpu) { - loongson3_send_ipi_single(cpu, SMP_CALL_FUNCTION); + loongson_send_ipi_single(cpu, SMP_CALL_FUNCTION); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - loongson3_send_ipi_mask(mask, SMP_CALL_FUNCTION); + loongson_send_ipi_mask(mask, SMP_CALL_FUNCTION); } #ifdef CONFIG_HOTPLUG_CPU static inline int __cpu_disable(void) { - return loongson3_cpu_disable(); + return loongson_cpu_disable(); } static inline void __cpu_die(unsigned int cpu) { - loongson3_cpu_die(cpu); + loongson_cpu_die(cpu); } extern void play_dead(void); diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 335398482038..8319cc409009 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -56,23 +56,6 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) return ioremap_cache(phys, size); } -void __init acpi_boot_table_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return; - - /* - * Initialize the ACPI boot-time table parser. - */ - if (acpi_table_init()) { - disable_acpi(); - return; - } -} - #ifdef CONFIG_SMP static int set_processor_mask(u32 id, u32 flags) { @@ -156,13 +139,21 @@ static void __init acpi_process_madt(void) loongson_sysconf.nr_cpus = num_processors; } -int __init acpi_boot_init(void) +void __init acpi_boot_table_init(void) { /* * If acpi_disabled, bail out */ if (acpi_disabled) - return -1; + return; + + /* + * Initialize the ACPI boot-time table parser. + */ + if (acpi_table_init()) { + disable_acpi(); + return; + } loongson_sysconf.boot_cpu_id = read_csr_cpuid(); @@ -173,8 +164,6 @@ int __init acpi_boot_init(void) /* Do not enable ACPI SPCR console by default */ acpi_parse_spcr(earlycon_acpi_spcr_enable, false); - - return 0; } #ifdef CONFIG_ACPI_NUMA diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 1ba19c76563e..0524bf1169b7 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -117,7 +117,7 @@ void __init init_IRQ(void) if (ipi_irq < 0) panic("IPI IRQ mapping failed\n"); irq_set_percpu_devid(ipi_irq); - r = request_percpu_irq(ipi_irq, loongson3_ipi_interrupt, "IPI", &ipi_dummy_dev); + r = request_percpu_irq(ipi_irq, loongson_ipi_interrupt, "IPI", &ipi_dummy_dev); if (r < 0) panic("IPI IRQ request failed\n"); #endif diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 2526b68f1c0f..ddb8ba4eb399 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -152,7 +152,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->csr_crmd = p->thread.csr_crmd; childregs->csr_prmd = p->thread.csr_prmd; childregs->csr_ecfg = p->thread.csr_ecfg; - return 0; + goto out; } /* user thread */ @@ -171,14 +171,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) */ childregs->csr_euen = 0; + if (clone_flags & CLONE_SETTLS) + childregs->regs[2] = tls; + +out: clear_tsk_thread_flag(p, TIF_USEDFPU); clear_tsk_thread_flag(p, TIF_USEDSIMD); clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE); clear_tsk_thread_flag(p, TIF_LASX_CTX_LIVE); - if (clone_flags & CLONE_SETTLS) - childregs->regs[2] = tls; - return 0; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 1eb63fa9bc81..ae436def7ee9 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -257,7 +257,6 @@ void __init platform_init(void) #ifdef CONFIG_ACPI acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); - acpi_boot_init(); #endif #ifdef CONFIG_NUMA diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 781a4d4bdddc..14508d429ffa 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -136,12 +136,12 @@ static void ipi_write_action(int cpu, u32 action) } } -void loongson3_send_ipi_single(int cpu, unsigned int action) +void loongson_send_ipi_single(int cpu, unsigned int action) { ipi_write_action(cpu_logical_map(cpu), (u32)action); } -void loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) +void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) { unsigned int i; @@ -149,7 +149,18 @@ void loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) ipi_write_action(cpu_logical_map(i), (u32)action); } -irqreturn_t loongson3_ipi_interrupt(int irq, void *dev) +/* + * This function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ +void smp_send_reschedule(int cpu) +{ + loongson_send_ipi_single(cpu, SMP_RESCHEDULE); +} +EXPORT_SYMBOL_GPL(smp_send_reschedule); + +irqreturn_t loongson_ipi_interrupt(int irq, void *dev) { unsigned int action; unsigned int cpu = smp_processor_id(); @@ -169,7 +180,7 @@ irqreturn_t loongson3_ipi_interrupt(int irq, void *dev) return IRQ_HANDLED; } -void __init loongson3_smp_setup(void) +void __init loongson_smp_setup(void) { cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package; cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package; @@ -178,7 +189,7 @@ void __init loongson3_smp_setup(void) pr_info("Detected %i available CPU(s)\n", loongson_sysconf.nr_cpus); } -void __init loongson3_prepare_cpus(unsigned int max_cpus) +void __init loongson_prepare_cpus(unsigned int max_cpus) { int i = 0; @@ -193,7 +204,7 @@ void __init loongson3_prepare_cpus(unsigned int max_cpus) /* * Setup the PC, SP, and TP of a secondary processor and start it running! */ -void loongson3_boot_secondary(int cpu, struct task_struct *idle) +void loongson_boot_secondary(int cpu, struct task_struct *idle) { unsigned long entry; @@ -205,13 +216,13 @@ void loongson3_boot_secondary(int cpu, struct task_struct *idle) csr_mail_send(entry, cpu_logical_map(cpu), 0); - loongson3_send_ipi_single(cpu, SMP_BOOT_CPU); + loongson_send_ipi_single(cpu, SMP_BOOT_CPU); } /* * SMP init and finish on secondary CPUs */ -void loongson3_init_secondary(void) +void loongson_init_secondary(void) { unsigned int cpu = smp_processor_id(); unsigned int imask = ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | @@ -231,7 +242,7 @@ void loongson3_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; } -void loongson3_smp_finish(void) +void loongson_smp_finish(void) { local_irq_enable(); iocsr_write64(0, LOONGARCH_IOCSR_MBUF0); @@ -240,7 +251,7 @@ void loongson3_smp_finish(void) #ifdef CONFIG_HOTPLUG_CPU -int loongson3_cpu_disable(void) +int loongson_cpu_disable(void) { unsigned long flags; unsigned int cpu = smp_processor_id(); @@ -262,7 +273,7 @@ int loongson3_cpu_disable(void) return 0; } -void loongson3_cpu_die(unsigned int cpu) +void loongson_cpu_die(unsigned int cpu) { while (per_cpu(cpu_state, cpu) != CPU_DEAD) cpu_relax(); @@ -300,19 +311,19 @@ void play_dead(void) */ #ifdef CONFIG_PM -static int loongson3_ipi_suspend(void) +static int loongson_ipi_suspend(void) { return 0; } -static void loongson3_ipi_resume(void) +static void loongson_ipi_resume(void) { iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN); } -static struct syscore_ops loongson3_ipi_syscore_ops = { - .resume = loongson3_ipi_resume, - .suspend = loongson3_ipi_suspend, +static struct syscore_ops loongson_ipi_syscore_ops = { + .resume = loongson_ipi_resume, + .suspend = loongson_ipi_suspend, }; /* @@ -321,7 +332,7 @@ static struct syscore_ops loongson3_ipi_syscore_ops = { */ static int __init ipi_pm_init(void) { - register_syscore_ops(&loongson3_ipi_syscore_ops); + register_syscore_ops(&loongson_ipi_syscore_ops); return 0; } @@ -425,7 +436,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { init_new_context(current, &init_mm); current_thread_info()->cpu = 0; - loongson3_prepare_cpus(max_cpus); + loongson_prepare_cpus(max_cpus); set_cpu_sibling_map(0); set_cpu_core_map(0); calculate_cpu_foreign_map(); @@ -436,7 +447,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - loongson3_boot_secondary(cpu, tidle); + loongson_boot_secondary(cpu, tidle); /* Wait for CPU to start and be ready to sync counters */ if (!wait_for_completion_timeout(&cpu_starting, @@ -465,7 +476,7 @@ asmlinkage void start_secondary(void) cpu_probe(); constant_clockevent_init(); - loongson3_init_secondary(); + loongson_init_secondary(); set_cpu_sibling_map(cpu); set_cpu_core_map(cpu); @@ -487,11 +498,11 @@ asmlinkage void start_secondary(void) complete(&cpu_running); /* - * irq will be enabled in loongson3_smp_finish(), enabling it too + * irq will be enabled in loongson_smp_finish(), enabling it too * early is dangerous. */ WARN_ON_ONCE(!irqs_disabled()); - loongson3_smp_finish(); + loongson_smp_finish(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index b206d9159205..4571c3c87cd4 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -43,7 +43,8 @@ static bool unwind_by_prologue(struct unwind_state *state) { struct stack_info *info = &state->stack_info; union loongarch_instruction *ip, *ip_end; - unsigned long frame_size = 0, frame_ra = -1; + long frame_ra = -1; + unsigned long frame_size = 0; unsigned long size, offset, pc = state->pc; if (state->sp >= info->end || state->sp < info->begin) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index d8ee8fbc8c67..58781c6e4191 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -10,6 +10,8 @@ #include <asm/regdef.h> #include <asm/stackframe.h> +#define INVTLB_ADDR_GFALSE_AND_ASID 5 + #define PTRS_PER_PGD_BITS (PAGE_SHIFT - 3) #define PTRS_PER_PUD_BITS (PAGE_SHIFT - 3) #define PTRS_PER_PMD_BITS (PAGE_SHIFT - 3) @@ -136,13 +138,10 @@ tlb_huge_update_load: ori t0, ra, _PAGE_VALID st.d t0, t1, 0 #endif - tlbsrch - addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX - tlbwr - - csrxchg zero, t1, LOONGARCH_CSR_TLBIDX + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 /* * A huge PTE describes an area the size of the @@ -287,13 +286,11 @@ tlb_huge_update_store: ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif - tlbsrch - addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX - tlbwr + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 - csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -436,6 +433,11 @@ tlb_huge_update_modify: ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 + /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -466,7 +468,7 @@ tlb_huge_update_modify: addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX - tlbwr + tlbfill /* Reset default page size */ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile index 3f8a86c4336a..02e6be9c5b0d 100644 --- a/arch/microblaze/Makefile +++ b/arch/microblaze/Makefile @@ -67,12 +67,12 @@ linux.bin.ub linux.bin.gz: linux.bin linux.bin: vmlinux linux.bin linux.bin.gz linux.bin.ub: $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ - @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' + @echo 'Kernel: $(boot)/$@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' PHONY += simpleImage.$(DTB) simpleImage.$(DTB): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(addprefix $(boot)/$@., ub unstrip strip) - @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' + @echo 'Kernel: $(boot)/$@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' define archhelp echo '* linux.bin - Create raw binary' diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 6caec386ad2f..4678627673df 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -622,6 +622,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd; } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_ACCESSED); diff --git a/arch/nios2/boot/Makefile b/arch/nios2/boot/Makefile index 8c3ad76602f3..29c11a06b750 100644 --- a/arch/nios2/boot/Makefile +++ b/arch/nios2/boot/Makefile @@ -20,7 +20,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE $(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) -$(obj)/vmImage: $(obj)/vmlinux.gz +$(obj)/vmImage: $(obj)/vmlinux.gz FORCE $(call if_changed,uimage) @$(kecho) 'Kernel: $@ is ready' diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 4745bb9998bd..6d8492b6e2b8 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -602,6 +602,7 @@ ____##func(struct pt_regs *regs) /* kernel/traps.c */ DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception); #ifdef CONFIG_PPC_BOOK3S_64 +DECLARE_INTERRUPT_HANDLER_RAW(machine_check_early_boot); DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async); #endif DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 7786e3ac7611..8c3862b4c259 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -142,7 +142,7 @@ SECTIONS #endif .data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) { - *(.data.rel.ro*) + *(.data.rel.ro .data.rel.ro.*) } .branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) { diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 43f1c76d48ce..a379b0ce19ff 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -113,23 +113,19 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) { int i; - /* First arg comes in as a 32 bits pointer. */ - EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3)); - EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0)); + /* Initialize tail_call_cnt, to be skipped if we do tail calls. */ + EMIT(PPC_RAW_LI(_R4, 0)); + +#define BPF_TAILCALL_PROLOGUE_SIZE 4 + EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx))); - /* - * Initialize tail_call_cnt in stack frame if we do tail calls. - * Otherwise, put in NOPs so that it can be skipped when we are - * invoked through a tail call. - */ if (ctx->seen & SEEN_TAILCALL) - EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1, - bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); - else - EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); -#define BPF_TAILCALL_PROLOGUE_SIZE 16 + /* First arg comes in as a 32 bits pointer. */ + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3)); + EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0)); /* * We need a stack frame, but we don't necessarily need to @@ -170,24 +166,24 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx for (i = BPF_PPC_NVR_MIN; i <= 31; i++) if (bpf_is_seen_register(ctx, i)) EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i))); -} - -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) -{ - EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); - - bpf_jit_emit_common_epilogue(image, ctx); - - /* Tear down our stack frame */ if (ctx->seen & SEEN_FUNC) EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF)); + /* Tear down our stack frame */ EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx))); if (ctx->seen & SEEN_FUNC) EMIT(PPC_RAW_MTLR(_R0)); +} + +void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); + + bpf_jit_emit_common_epilogue(image, ctx); + EMIT(PPC_RAW_BLR()); } @@ -244,7 +240,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array)); EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs))); - EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); /* * if (prog == NULL) @@ -255,19 +250,14 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o /* goto *(prog->bpf_func + prologue_size); */ EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func))); - - if (ctx->seen & SEEN_FUNC) - EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF)); - EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE)); - - if (ctx->seen & SEEN_FUNC) - EMIT(PPC_RAW_MTLR(_R0)); - EMIT(PPC_RAW_MTCTR(_R3)); EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1))); + /* Put tail_call_cnt in r4 */ + EMIT(PPC_RAW_MR(_R4, _R0)); + /* tear restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index fa78595a6089..593cf09264d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -317,9 +317,9 @@ config SMP config NR_CPUS int "Maximum number of CPUs (2-512)" depends on SMP - range 2 512 if !SBI_V01 - range 2 32 if SBI_V01 && 32BIT - range 2 64 if SBI_V01 && 64BIT + range 2 512 if !RISCV_SBI_V01 + range 2 32 if RISCV_SBI_V01 && 32BIT + range 2 64 if RISCV_SBI_V01 && 64BIT default "32" if 32BIT default "64" if 64BIT diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 1b471ff73178..816e753de636 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -23,6 +23,7 @@ #define REG_L __REG_SEL(ld, lw) #define REG_S __REG_SEL(sd, sw) #define REG_SC __REG_SEL(sc.d, sc.w) +#define REG_AMOSWAP_AQ __REG_SEL(amoswap.d.aq, amoswap.w.aq) #define REG_ASM __REG_SEL(.dword, .word) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index f74879a8f1ea..e229d7be4b66 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -10,6 +10,7 @@ #include <asm/mmu_context.h> #include <asm/ptrace.h> #include <asm/tlbflush.h> +#include <asm/pgalloc.h> #ifdef CONFIG_EFI extern void efi_init(void); @@ -20,7 +21,10 @@ extern void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); -#define arch_efi_call_virt_setup() efi_virtmap_load() +#define arch_efi_call_virt_setup() ({ \ + sync_kernel_mappings(efi_mm.pgd); \ + efi_virtmap_load(); \ + }) #define arch_efi_call_virt_teardown() efi_virtmap_unload() #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 947f23d7b6af..59dc12b5b7e8 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -127,6 +127,13 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) #define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) #endif /* __PAGETABLE_PMD_FOLDED */ +static inline void sync_kernel_mappings(pgd_t *pgd) +{ + memcpy(pgd + USER_PTRS_PER_PGD, + init_mm.pgd + USER_PTRS_PER_PGD, + (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); +} + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; @@ -135,9 +142,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) if (likely(pgd != NULL)) { memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); /* Copy kernel mappings */ - memcpy(pgd + USER_PTRS_PER_PGD, - init_mm.pgd + USER_PTRS_PER_PGD, - (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); + sync_kernel_mappings(pgd); } return pgd; } diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7ec936910a96..92ec2d9d7273 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -600,6 +600,7 @@ static inline int pmd_dirty(pmd_t pmd) return pte_dirty(pmd_pte(pmd)); } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pte_young(pmd_pte(pmd)); diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index d3443be7eedc..3831b638ecab 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -50,6 +50,9 @@ void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops); /* Clear IPI for current CPU */ void riscv_clear_ipi(void); +/* Check other CPUs stop or not */ +bool smp_crash_stop_failed(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index b9eda3fcbd6d..186abd146eaf 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -404,6 +404,19 @@ handle_syscall_trace_exit: #ifdef CONFIG_VMAP_STACK handle_kernel_stack_overflow: + /* + * Takes the psuedo-spinlock for the shadow stack, in case multiple + * harts are concurrently overflowing their kernel stacks. We could + * store any value here, but since we're overflowing the kernel stack + * already we only have SP to use as a scratch register. So we just + * swap in the address of the spinlock, as that's definately non-zero. + * + * Pairs with a store_release in handle_bad_stack(). + */ +1: la sp, spin_shadow_stack + REG_AMOSWAP_AQ sp, sp, (sp) + bnez sp, 1b + la sp, shadow_stack addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index ee79e6839b86..2d139b724bc8 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -15,6 +15,8 @@ #include <linux/compiler.h> /* For unreachable() */ #include <linux/cpu.h> /* For cpu_down() */ #include <linux/reboot.h> +#include <linux/interrupt.h> +#include <linux/irq.h> /* * kexec_image_info - Print received image details @@ -138,20 +140,35 @@ void machine_shutdown(void) #endif } -/* Override the weak function in kernel/panic.c */ -void crash_smp_send_stop(void) +static void machine_kexec_mask_interrupts(void) { - static int cpus_stopped; + unsigned int i; + struct irq_desc *desc; - /* - * This function can be called twice in panic path, but obviously - * we execute this only once. - */ - if (cpus_stopped) - return; + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int ret; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + /* + * First try to remove the active state. If this + * fails, try to EOI the interrupt. + */ + ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + + if (ret && irqd_irq_inprogress(&desc->irq_data) && + chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); - smp_send_stop(); - cpus_stopped = 1; + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } } /* @@ -169,6 +186,8 @@ machine_crash_shutdown(struct pt_regs *regs) crash_smp_send_stop(); crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + pr_info("Starting crashdump kernel...\n"); } @@ -195,6 +214,11 @@ machine_kexec(struct kimage *image) void *control_code_buffer = page_address(image->control_code_page); riscv_kexec_method kexec_method = NULL; +#ifdef CONFIG_SMP + WARN(smp_crash_stop_failed(), + "Some CPUs may be stale, kdump will be unreliable.\n"); +#endif + if (image->type != KEXEC_TYPE_CRASH) kexec_method = control_code_buffer; else diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 67ec1fadcfe2..86acd690d529 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -322,10 +322,11 @@ subsys_initcall(topology_init); void free_initmem(void) { - if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) - set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), - IS_ENABLED(CONFIG_64BIT) ? - set_memory_rw : set_memory_rw_nx); + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) { + set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx); + if (IS_ENABLED(CONFIG_64BIT)) + set_kernel_memory(__init_begin, __init_end, set_memory_nx); + } free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 760a64518c58..8c3b59f1f9b8 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -12,6 +12,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/kexec.h> #include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> @@ -22,11 +23,13 @@ #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> +#include <asm/cpu_ops.h> enum ipi_message_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, IPI_IRQ_WORK, IPI_TIMER, IPI_MAX @@ -71,6 +74,32 @@ static void ipi_stop(void) wait_for_interrupt(); } +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); + +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_has_hotplug(cpu)) + cpu_ops[cpu]->cpu_stop(); +#endif + + for(;;) + wait_for_interrupt(); +} +#else +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + unreachable(); +} +#endif + static const struct riscv_ipi_ops *ipi_ops __ro_after_init; void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops) @@ -124,8 +153,9 @@ void arch_irq_work_raise(void) void handle_IPI(struct pt_regs *regs) { - unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits; - unsigned long *stats = ipi_data[smp_processor_id()].stats; + unsigned int cpu = smp_processor_id(); + unsigned long *pending_ipis = &ipi_data[cpu].bits; + unsigned long *stats = ipi_data[cpu].stats; riscv_clear_ipi(); @@ -154,6 +184,10 @@ void handle_IPI(struct pt_regs *regs) ipi_stop(); } + if (ops & (1 << IPI_CPU_CRASH_STOP)) { + ipi_cpu_crash_stop(cpu, get_irq_regs()); + } + if (ops & (1 << IPI_IRQ_WORK)) { stats[IPI_IRQ_WORK]++; irq_work_run(); @@ -176,6 +210,7 @@ static const char * const ipi_names[] = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNC] = "Function call interrupts", [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", [IPI_TIMER] = "Timer broadcast interrupts", }; @@ -235,6 +270,64 @@ void smp_send_stop(void) cpumask_pr_args(cpu_online_mask)); } +#ifdef CONFIG_KEXEC_CORE +/* + * The number of CPUs online, not counting this CPU (which may not be + * fully online and so not counted in num_online_cpus()). + */ +static inline unsigned int num_other_online_cpus(void) +{ + unsigned int this_cpu_online = cpu_online(smp_processor_id()); + + return num_online_cpus() - this_cpu_online; +} + +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + cpumask_t mask; + unsigned long timeout; + + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + */ + if (cpus_stopped) + return; + + cpus_stopped = 1; + + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); + + pr_crit("SMP: stopping secondary CPUs\n"); + send_ipi_mask(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); +} + +bool smp_crash_stop_failed(void) +{ + return (atomic_read(&waiting_for_crash_ipi) > 0); +} +#endif + void smp_send_reschedule(int cpu) { send_ipi_single(cpu, IPI_RESCHEDULE); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f3e96d60a2ff..7abd8e4c4df6 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -221,11 +221,29 @@ asmlinkage unsigned long get_overflow_stack(void) OVERFLOW_STACK_SIZE; } +/* + * A pseudo spinlock to protect the shadow stack from being used by multiple + * harts concurrently. This isn't a real spinlock because the lock side must + * be taken without a valid stack and only a single register, it's only taken + * while in the process of panicing anyway so the performance and error + * checking a proper spinlock gives us doesn't matter. + */ +unsigned long spin_shadow_stack; + asmlinkage void handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); + /* + * We're done with the shadow stack by this point, as we're on the + * overflow stack. Tell any other concurrent overflowing harts that + * they can proceed with panicing by releasing the pseudo-spinlock. + * + * This pairs with an amoswap.aq in handle_kernel_stack_overflow. + */ + smp_store_release(&spin_shadow_stack, 0); + console_verbose(); pr_emerg("Insufficient stack space to handle exception!\n"); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index db6548509bb3..06e6b27f3bcc 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -17,6 +17,7 @@ vdso-syms += flush_icache obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ccflags-y := -fno-stack-protector +ccflags-y += -DDISABLE_BRANCH_PROFILING ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index de575af02ffe..48a11deb502c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -73,6 +73,7 @@ config S390 select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_MEM_ENCRYPT + select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME select ARCH_HAS_SET_MEMORY diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index f1cb9391190d..11e901286414 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -763,6 +763,7 @@ static inline int pmd_dirty(pmd_t pmd) return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index dd74fe664ed1..e4ef67e4da0a 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -46,7 +46,7 @@ struct save_area { u64 fprs[16]; u32 fpc; u32 prefix; - u64 todpreg; + u32 todpreg; u64 timer; u64 todcmp; u64 vxrs_low[16]; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 94138f8f0c1c..ace2541ababd 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -546,8 +546,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI)) scb_s->eca |= scb_o->eca & ECA_CEI; /* Epoch Extension */ - if (test_kvm_facility(vcpu->kvm, 139)) + if (test_kvm_facility(vcpu->kvm, 139)) { scb_s->ecd |= scb_o->ecd & ECD_MEF; + scb_s->epdx = scb_o->epdx; + } /* etoken */ if (test_kvm_facility(vcpu->kvm, 156)) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index a779418ceba9..3bc9736bddb1 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -693,6 +693,7 @@ static inline unsigned long pmd_dirty(pmd_t pmd) return pte_dirty(pte); } +#define pmd_young pmd_young static inline unsigned long pmd_young(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67745ceab0db..7d11f718ff0c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -81,6 +81,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9860ca5979f8..9e38ffaadb5d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -83,7 +83,7 @@ cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 8b70237c33f7..d6f3703e4119 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -861,8 +861,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) pmu_enabled = cpuc->enabled; cpuc->enabled = 0; - /* stop everything (includes BRS) */ - amd_pmu_disable_all(); + amd_brs_disable_all(); /* Drain BRS is in use (could be inactive) */ if (cpuc->lbr_users) @@ -873,7 +872,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) cpuc->enabled = pmu_enabled; if (pmu_enabled) - amd_pmu_enable_all(0); + amd_brs_enable_all(); return amd_pmu_adjust_nmi_window(handled); } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index d568afc705d2..83f15fe411b3 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -553,6 +553,7 @@ static void uncore_clean_online(void) hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) { hlist_del(&uncore->node); + kfree(uncore->events); kfree(uncore); } } diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 82ef87e9a897..42a55794004a 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1263,6 +1263,15 @@ static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages) if (1 << order != nr_pages) goto out; + /* + * Some processors cannot always support single range for more than + * 4KB - refer errata TGL052, ADL037 and RPL017. Future processors might + * also be affected, so for now rather than trying to keep track of + * which ones, just disable it for all. + */ + if (nr_pages > 1) + goto out; + buf->single = true; buf->nr_pages = nr_pages; ret = 0; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index f49bc3ec76e6..a269049a43ce 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void) static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; - struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu]; int ret; ret = hv_common_cpu_init(cpu); @@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu) if (!hv_vp_assist_page) return 0; - if (!*hvp) { - if (hv_root_partition) { - /* - * For root partition we get the hypervisor provided VP assist - * page, instead of allocating a new page. - */ - rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - *hvp = memremap(msr.pfn << - HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, - PAGE_SIZE, MEMREMAP_WB); - } else { - /* - * The VP assist page is an "overlay" page (see Hyper-V TLFS's - * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed - * out to make sure we always write the EOI MSR in - * hv_apic_eoi_write() *after* the EOI optimization is disabled - * in hv_cpu_die(), otherwise a CPU may not be stopped in the - * case of CPU offlining and the VM will hang. - */ + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + if (!*hvp) *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - if (*hvp) - msr.pfn = vmalloc_to_pfn(*hvp); - } - WARN_ON(!(*hvp)); - if (*hvp) { - msr.enable = 1; - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - } + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + + } + if (!WARN_ON(!(*hvp))) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } return hyperv_init_ghcb(); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..b2da7cb64b31 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -305,6 +305,9 @@ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ + +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c936ce9f0c47..dfdb103ae4f6 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -321,7 +321,7 @@ static inline void indirect_branch_prediction_barrier(void) /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); -extern void write_spec_ctrl_current(u64 val, bool force); +extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5059799bebe3..286a71810f9e 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -139,6 +139,7 @@ static inline int pmd_dirty(pmd_t pmd) return pmd_flags(pmd) & _PAGE_DIRTY; } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; @@ -1438,6 +1439,14 @@ static inline bool arch_has_hw_pte_young(void) return true; } +#ifdef CONFIG_XEN_PV +#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return !cpu_feature_enabled(X86_FEATURE_XENPV); +} +#endif + #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 60ece592b220..dbb38a6b4dfb 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -37,7 +37,7 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); * rsi = lockval (second argument) * rdx = internal variable (set to 0) */ -asm (".pushsection .spinlock.text;" +asm (".pushsection .spinlock.text, \"ax\";" ".globl " PV_UNLOCK ";" ".type " PV_UNLOCK ", @function;" ".align 4,0x90;" diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3e3230cccaa7..6daf84229548 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -60,11 +60,18 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); static DEFINE_MUTEX(spec_ctrl_mutex); +/* Update SPEC_CTRL MSR and its cached copy unconditionally */ +static void update_spec_ctrl(u64 val) +{ + this_cpu_write(x86_spec_ctrl_current, val); + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + /* * Keep track of the SPEC_CTRL MSR value for the current task, which may differ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ -void write_spec_ctrl_current(u64 val, bool force) +void update_spec_ctrl_cond(u64 val) { if (this_cpu_read(x86_spec_ctrl_current) == val) return; @@ -75,7 +82,7 @@ void write_spec_ctrl_current(u64 val, bool force) * When KERNEL_IBRS this MSR is written on return-to-user, unless * forced the update can be delayed until that time. */ - if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) wrmsrl(MSR_IA32_SPEC_CTRL, val); } @@ -1328,7 +1335,7 @@ static void __init spec_ctrl_disable_kernel_rrsba(void) if (ia32_cap & ARCH_CAP_RRSBA) { x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } } @@ -1450,7 +1457,7 @@ static void __init spectre_v2_select_mitigation(void) if (spectre_v2_in_ibrs_mode(mode)) { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } switch (mode) { @@ -1564,7 +1571,7 @@ static void __init spectre_v2_select_mitigation(void) static void update_stibp_msr(void * __unused) { u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); - write_spec_ctrl_current(val, true); + update_spec_ctrl(val); } /* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1797,7 +1804,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } } @@ -2048,7 +2055,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index ebe79d60619f..da8b8ea6b063 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -356,6 +356,9 @@ static int sgx_validate_offset_length(struct sgx_encl *encl, if (!length || !IS_ALIGNED(length, PAGE_SIZE)) return -EINVAL; + if (offset + length < offset) + return -EINVAL; + if (offset + length - PAGE_SIZE >= encl->size) return -EINVAL; diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index ec7bbac3a9f2..8009c8346d8f 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -58,24 +58,6 @@ static void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool tsx_ctrl_is_supported(void) -{ - u64 ia32_cap = x86_read_arch_cap_msr(); - - /* - * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this - * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. - * - * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a - * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES - * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get - * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, - * tsx= cmdline requests will do nothing on CPUs without - * MSR_IA32_TSX_CTRL support. - */ - return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); -} - static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) { if (boot_cpu_has_bug(X86_BUG_TAA)) @@ -135,7 +117,7 @@ static void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); - } else if (tsx_ctrl_is_supported()) { + } else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) { rdmsrl(MSR_IA32_TSX_CTRL, msr); msr |= TSX_CTRL_CPUID_CLEAR; wrmsrl(MSR_IA32_TSX_CTRL, msr); @@ -158,7 +140,8 @@ static void tsx_dev_mode_disable(void) u64 mcu_opt_ctrl; /* Check if RTM_ALLOW exists */ - if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + if (!boot_cpu_has_bug(X86_BUG_TAA) || + !cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL) || !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) return; @@ -191,7 +174,20 @@ void __init tsx_init(void) return; } - if (!tsx_ctrl_is_supported()) { + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + if (x86_read_arch_cap_msr() & ARCH_CAP_TSX_CTRL_MSR) { + setup_force_cpu_cap(X86_FEATURE_MSR_TSX_CTRL); + } else { tsx_ctrl_state = TSX_CTRL_NOT_SUPPORTED; return; } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3b28c5b25e12..d00db56a8868 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -605,9 +605,9 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); save_fpregs_to_fpstate(dst_fpu); + fpregs_unlock(); if (!(clone_flags & CLONE_THREAD)) fpu_inherit_perms(dst_fpu); - fpregs_unlock(); /* * Children never inherit PASID state. diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c21b7347a26d..e436c9c1ef3b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -600,7 +600,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, } if (updmsr) - write_spec_ctrl_current(msr, false); + update_spec_ctrl_cond(msr); } static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1ccb769f62af..b6f96d47e596 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2443,6 +2443,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, { bool list_unstable, zapped_root = false; + lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); @@ -4262,14 +4263,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - - if (is_tdp_mmu_fault) + if (is_tdp_mmu_fault) { r = kvm_tdp_mmu_map(vcpu, fault); - else + } else { + r = make_mmu_pages_available(vcpu); + if (r) + goto out_unlock; r = __direct_map(vcpu, fault); + } out_unlock: if (is_tdp_mmu_fault) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 4c620999d230..995bc0f90759 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1091,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); } @@ -1125,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm) if (!svm->nested.initialized) return; + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; @@ -1143,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm) svm->nested.initialized = false; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void svm_leave_nested(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4b6d2b050e57..ce362e88a567 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1438,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); @@ -3425,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0c62352dda6a..5b0d4859e4b7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4854,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -6440,9 +6441,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 490ec23c8450..69227f77b201 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -5195,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_SMM) { if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - kvm_x86_ops.nested_ops->leave_nested(vcpu); + kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } @@ -9805,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } @@ -10560,10 +10566,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - if (is_guest_mode(vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); - } else { + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; @@ -11997,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 2dae413bd62a..f3098c0e386a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -954,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); } +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, evtchn_port_t *ports) { @@ -1042,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, *r = -EFAULT; goto out; } + if (ports[i] >= max_evtchn_port(vcpu->kvm)) { + *r = -EINVAL; + goto out; + } } if (sched_poll.nr_ports == 1) @@ -1215,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) bool longmode; u64 input, params[6], r = -ENOSYS; bool handled = false; + u8 cpl; input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -1242,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) params[5] = (u64)kvm_r9_read(vcpu); } #endif + cpl = static_call(kvm_x86_get_cpl)(vcpu); trace_kvm_xen_hypercall(input, params[0], params[1], params[2], params[3], params[4], params[5]); + /* + * Only allow hypercall acceleration for CPL0. The rare hypercalls that + * are permitted in guest userspace can be handled by the VMM. + */ + if (unlikely(cpl > 0)) + goto handle_in_userspace; + switch (input) { case __HYPERVISOR_xen_version: if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) { @@ -1279,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) if (handled) return kvm_xen_hypercall_set_result(vcpu, r); +handle_in_userspace: vcpu->run->exit_reason = KVM_EXIT_XEN; vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; vcpu->run->xen.u.hcall.longmode = longmode; - vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu); + vcpu->run->xen.u.hcall.cpl = cpl; vcpu->run->xen.u.hcall.input = input; vcpu->run->xen.u.hcall.params[0] = params[0]; vcpu->run->xen.u.hcall.params[1] = params[1]; @@ -1297,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } -static inline int max_evtchn_port(struct kvm *kvm) -{ - if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) - return EVTCHN_2L_NR_CHANNELS; - else - return COMPAT_EVTCHN_2L_NR_CHANNELS; -} - static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port) { int poll_evtchn = vcpu->arch.xen.poll_evtchn; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 78c5bc654cff..6453fbaedb08 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -217,9 +217,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PHYSICAL_PAGE_MASK; + phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; + /* + * Mask out any bits not part of the actual physical + * address, like memory encryption bits. + */ + phys_addr &= PHYSICAL_PAGE_MASK; + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 4cd39f304e20..93ae33248f42 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -513,16 +513,23 @@ static int pm_cpu_check(const struct x86_cpu_id *c) static void pm_save_spec_msr(void) { - u32 spec_msr_id[] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_TSX_CTRL, - MSR_TSX_FORCE_ABORT, - MSR_IA32_MCU_OPT_CTRL, - MSR_AMD64_LS_CFG, - MSR_AMD64_DE_CFG, + struct msr_enumeration { + u32 msr_no; + u32 feature; + } msr_enum[] = { + { MSR_IA32_SPEC_CTRL, X86_FEATURE_MSR_SPEC_CTRL }, + { MSR_IA32_TSX_CTRL, X86_FEATURE_MSR_TSX_CTRL }, + { MSR_TSX_FORCE_ABORT, X86_FEATURE_TSX_FORCE_ABORT }, + { MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL }, + { MSR_AMD64_LS_CFG, X86_FEATURE_LS_CFG_SSBD }, + { MSR_AMD64_DE_CFG, X86_FEATURE_LFENCE_RDTSC }, }; + int i; - msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); + for (i = 0; i < ARRAY_SIZE(msr_enum); i++) { + if (boot_cpu_has(msr_enum[i].feature)) + msr_build_context(&msr_enum[i].msr_no, 1); + } } static int pm_check_save_msr(void) diff --git a/block/blk-mq.c b/block/blk-mq.c index 6a789cda68a5..228a6696d835 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4045,9 +4045,14 @@ EXPORT_SYMBOL(__blk_mq_alloc_disk); struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass) { + struct gendisk *disk; + if (!blk_get_queue(q)) return NULL; - return __alloc_disk_node(q, NUMA_NO_NODE, lkclass); + disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass); + if (!disk) + blk_put_queue(q); + return disk; } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 23f49a2f4d14..6cceca64a6bc 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -562,17 +562,26 @@ static int initiator_cmp(void *priv, const struct list_head *a, { struct memory_initiator *ia; struct memory_initiator *ib; - unsigned long *p_nodes = priv; ia = list_entry(a, struct memory_initiator, node); ib = list_entry(b, struct memory_initiator, node); - set_bit(ia->processor_pxm, p_nodes); - set_bit(ib->processor_pxm, p_nodes); - return ia->processor_pxm - ib->processor_pxm; } +static int initiators_to_nodemask(unsigned long *p_nodes) +{ + struct memory_initiator *initiator; + + if (list_empty(&initiators)) + return -ENXIO; + + list_for_each_entry(initiator, &initiators, node) + set_bit(initiator->processor_pxm, p_nodes); + + return 0; +} + static void hmat_register_target_initiators(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); @@ -609,7 +618,10 @@ static void hmat_register_target_initiators(struct memory_target *target) * initiators. */ bitmap_zero(p_nodes, MAX_NUMNODES); - list_sort(p_nodes, &initiators, initiator_cmp); + list_sort(NULL, &initiators, initiator_cmp); + if (initiators_to_nodemask(p_nodes) < 0) + return; + if (!access0done) { for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { loc = localities_types[i]; @@ -643,8 +655,9 @@ static void hmat_register_target_initiators(struct memory_target *target) /* Access 1 ignores Generic Initiators */ bitmap_zero(p_nodes, MAX_NUMNODES); - list_sort(p_nodes, &initiators, initiator_cmp); - best = 0; + if (initiators_to_nodemask(p_nodes) < 0) + return; + for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { loc = localities_types[i]; if (!loc) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index ddf17e2d266c..b9e336bacf17 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -109,7 +109,7 @@ struct clk *ahci_platform_find_clk(struct ahci_host_priv *hpriv, const char *con int i; for (i = 0; i < hpriv->n_clks; i++) { - if (!strcmp(hpriv->clks[i].id, con_id)) + if (hpriv->clks[i].id && !strcmp(hpriv->clks[i].id, con_id)) return hpriv->clks[i].clk; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index f96cb01e9604..e9de9d846b73 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -57,10 +57,8 @@ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) struct ublk_rq_data { - union { - struct callback_head work; - struct llist_node node; - }; + struct llist_node node; + struct callback_head work; }; struct ublk_uring_cmd_pdu { @@ -766,15 +764,31 @@ static inline void __ublk_rq_task_work(struct request *req) ubq_complete_io_cmd(io, UBLK_IO_RES_OK); } +static inline void ublk_forward_io_cmds(struct ublk_queue *ubq) +{ + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data, *tmp; + + io_cmds = llist_reverse_order(io_cmds); + llist_for_each_entry_safe(data, tmp, io_cmds, node) + __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); +} + +static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) +{ + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data, *tmp; + + llist_for_each_entry_safe(data, tmp, io_cmds, node) + __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); +} + static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; - struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); - struct ublk_rq_data *data; - llist_for_each_entry(data, io_cmds, node) - __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); + ublk_forward_io_cmds(ubq); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -782,14 +796,20 @@ static void ublk_rq_task_work_fn(struct callback_head *work) struct ublk_rq_data *data = container_of(work, struct ublk_rq_data, work); struct request *req = blk_mq_rq_from_pdu(data); + struct ublk_queue *ubq = req->mq_hctx->driver_data; - __ublk_rq_task_work(req); + ublk_forward_io_cmds(ubq); } -static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) +static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) { - struct ublk_io *io = &ubq->ios[rq->tag]; + struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); + struct ublk_io *io; + if (!llist_add(&data->node, &ubq->io_cmds)) + return; + + io = &ubq->ios[rq->tag]; /* * If the check pass, we know that this is a re-issued request aborted * previously in monitor_work because the ubq_daemon(cmd's task) is @@ -803,11 +823,11 @@ static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) * guarantees that here is a re-issued request aborted previously. */ if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { - struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); - struct ublk_rq_data *data; - - llist_for_each_entry(data, io_cmds, node) - __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); + ublk_abort_io_cmds(ubq); + } else if (ublk_can_use_task_work(ubq)) { + if (task_work_add(ubq->ubq_daemon, &data->work, + TWA_SIGNAL_NO_IPI)) + ublk_abort_io_cmds(ubq); } else { struct io_uring_cmd *cmd = io->cmd; struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); @@ -817,23 +837,6 @@ static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) } } -static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq, - bool last) -{ - struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); - - if (ublk_can_use_task_work(ubq)) { - enum task_work_notify_mode notify_mode = last ? - TWA_SIGNAL_NO_IPI : TWA_NONE; - - if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) - __ublk_abort_rq(ubq, rq); - } else { - if (llist_add(&data->node, &ubq->io_cmds)) - ublk_submit_cmd(ubq, rq); - } -} - static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -865,19 +868,11 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } - ublk_queue_cmd(ubq, rq, bd->last); + ublk_queue_cmd(ubq, rq); return BLK_STS_OK; } -static void ublk_commit_rqs(struct blk_mq_hw_ctx *hctx) -{ - struct ublk_queue *ubq = hctx->driver_data; - - if (ublk_can_use_task_work(ubq)) - __set_notify_signal(ubq->ubq_daemon); -} - static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, unsigned int hctx_idx) { @@ -899,7 +894,6 @@ static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req, static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, - .commit_rqs = ublk_commit_rqs, .init_hctx = ublk_init_hctx, .init_request = ublk_init_rq, }; @@ -1197,7 +1191,7 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, struct ublk_queue *ubq = ublk_get_queue(ub, q_id); struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag); - ublk_queue_cmd(ubq, req, true); + ublk_queue_cmd(ubq, req); } static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 271963805a38..f05018988a17 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2056,6 +2056,11 @@ static int btusb_setup_csr(struct hci_dev *hdev) rp = (struct hci_rp_read_local_version *)skb->data; + bt_dev_info(hdev, "CSR: Setting up dongle with HCI ver=%u rev=%04x; LMP ver=%u subver=%04x; manufacturer=%u", + le16_to_cpu(rp->hci_ver), le16_to_cpu(rp->hci_rev), + le16_to_cpu(rp->lmp_ver), le16_to_cpu(rp->lmp_subver), + le16_to_cpu(rp->manufacturer)); + /* Detect a wide host of Chinese controllers that aren't CSR. * * Known fake bcdDevices: 0x0100, 0x0134, 0x1915, 0x2520, 0x7558, 0x8891 @@ -2118,6 +2123,7 @@ static int btusb_setup_csr(struct hci_dev *hdev) * without these the controller will lock up. */ set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks); set_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks); diff --git a/drivers/bus/intel-ixp4xx-eb.c b/drivers/bus/intel-ixp4xx-eb.c index a4388440aca7..91db001eb69a 100644 --- a/drivers/bus/intel-ixp4xx-eb.c +++ b/drivers/bus/intel-ixp4xx-eb.c @@ -49,7 +49,7 @@ #define IXP4XX_EXP_SIZE_SHIFT 10 #define IXP4XX_EXP_CNFG_0 BIT(9) /* Always zero */ #define IXP43X_EXP_SYNC_INTEL BIT(8) /* Only on IXP43x */ -#define IXP43X_EXP_EXP_CHIP BIT(7) /* Only on IXP43x */ +#define IXP43X_EXP_EXP_CHIP BIT(7) /* Only on IXP43x, dangerous to touch on IXP42x */ #define IXP4XX_EXP_BYTE_RD16 BIT(6) #define IXP4XX_EXP_HRDY_POL BIT(5) /* Only on IXP42x */ #define IXP4XX_EXP_MUX_EN BIT(4) @@ -57,8 +57,6 @@ #define IXP4XX_EXP_WORD BIT(2) /* Always zero */ #define IXP4XX_EXP_WR_EN BIT(1) #define IXP4XX_EXP_BYTE_EN BIT(0) -#define IXP42X_RESERVED (BIT(30)|IXP4XX_EXP_CNFG_0|BIT(8)|BIT(7)|IXP4XX_EXP_WORD) -#define IXP43X_RESERVED (BIT(30)|IXP4XX_EXP_CNFG_0|BIT(5)|IXP4XX_EXP_WORD) #define IXP4XX_EXP_CNFG0 0x20 #define IXP4XX_EXP_CNFG0_MEM_MAP BIT(31) @@ -252,10 +250,9 @@ static void ixp4xx_exp_setup_chipselect(struct ixp4xx_eb *eb, cs_cfg |= val << IXP4XX_EXP_CYC_TYPE_SHIFT; } - if (eb->is_42x) - cs_cfg &= ~IXP42X_RESERVED; if (eb->is_43x) { - cs_cfg &= ~IXP43X_RESERVED; + /* Should always be zero */ + cs_cfg &= ~IXP4XX_EXP_WORD; /* * This bit for Intel strata flash is currently unused, but let's * report it if we find one. diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 4cd2e127946e..3aa91aed3bf7 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -267,6 +267,9 @@ EXPORT_SYMBOL_GPL(sunxi_rsb_driver_register); /* common code that starts a transfer */ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) { + u32 int_mask, status; + bool timeout; + if (readl(rsb->regs + RSB_CTRL) & RSB_CTRL_START_TRANS) { dev_dbg(rsb->dev, "RSB transfer still in progress\n"); return -EBUSY; @@ -274,13 +277,23 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) reinit_completion(&rsb->complete); - writel(RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER, - rsb->regs + RSB_INTE); + int_mask = RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER; + writel(int_mask, rsb->regs + RSB_INTE); writel(RSB_CTRL_START_TRANS | RSB_CTRL_GLOBAL_INT_ENB, rsb->regs + RSB_CTRL); - if (!wait_for_completion_io_timeout(&rsb->complete, - msecs_to_jiffies(100))) { + if (irqs_disabled()) { + timeout = readl_poll_timeout_atomic(rsb->regs + RSB_INTS, + status, (status & int_mask), + 10, 100000); + writel(status, rsb->regs + RSB_INTS); + } else { + timeout = !wait_for_completion_io_timeout(&rsb->complete, + msecs_to_jiffies(100)); + status = rsb->status; + } + + if (timeout) { dev_dbg(rsb->dev, "RSB timeout\n"); /* abort the transfer */ @@ -292,18 +305,18 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) return -ETIMEDOUT; } - if (rsb->status & RSB_INTS_LOAD_BSY) { + if (status & RSB_INTS_LOAD_BSY) { dev_dbg(rsb->dev, "RSB busy\n"); return -EBUSY; } - if (rsb->status & RSB_INTS_TRANS_ERR) { - if (rsb->status & RSB_INTS_TRANS_ERR_ACK) { + if (status & RSB_INTS_TRANS_ERR) { + if (status & RSB_INTS_TRANS_ERR_ACK) { dev_dbg(rsb->dev, "RSB slave nack\n"); return -EINVAL; } - if (rsb->status & RSB_INTS_TRANS_ERR_DATA) { + if (status & RSB_INTS_TRANS_ERR_DATA) { dev_dbg(rsb->dev, "RSB transfer data error\n"); return -EIO; } @@ -812,14 +825,6 @@ static int sunxi_rsb_remove(struct platform_device *pdev) return 0; } -static void sunxi_rsb_shutdown(struct platform_device *pdev) -{ - struct sunxi_rsb *rsb = platform_get_drvdata(pdev); - - pm_runtime_disable(&pdev->dev); - sunxi_rsb_hw_exit(rsb); -} - static const struct dev_pm_ops sunxi_rsb_dev_pm_ops = { SET_RUNTIME_PM_OPS(sunxi_rsb_runtime_suspend, sunxi_rsb_runtime_resume, NULL) @@ -835,7 +840,6 @@ MODULE_DEVICE_TABLE(of, sunxi_rsb_of_match_table); static struct platform_driver sunxi_rsb_driver = { .probe = sunxi_rsb_probe, .remove = sunxi_rsb_remove, - .shutdown = sunxi_rsb_shutdown, .driver = { .name = RSB_CTRL_NAME, .of_match_table = sunxi_rsb_of_match_table, diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 1621ce818705..d69905233aff 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -401,13 +401,14 @@ int tpm_pm_suspend(struct device *dev) !pm_suspend_via_firmware()) goto suspended; - if (!tpm_chip_start(chip)) { + rc = tpm_try_get_ops(chip); + if (!rc) { if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_STATE); else rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); - tpm_chip_stop(chip); + tpm_put_ops(chip); } suspended: diff --git a/drivers/clk/at91/at91rm9200.c b/drivers/clk/at91/at91rm9200.c index b174f727a8ef..16870943a13e 100644 --- a/drivers/clk/at91/at91rm9200.c +++ b/drivers/clk/at91/at91rm9200.c @@ -40,7 +40,7 @@ static const struct clk_pll_characteristics rm9200_pll_characteristics = { }; static const struct sck at91rm9200_systemck[] = { - { .n = "udpck", .p = "usbck", .id = 2 }, + { .n = "udpck", .p = "usbck", .id = 1 }, { .n = "uhpck", .p = "usbck", .id = 4 }, { .n = "pck0", .p = "prog0", .id = 8 }, { .n = "pck1", .p = "prog1", .id = 9 }, diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index a18ed88f3b82..b3198784e1c3 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -5364,6 +5364,8 @@ static struct clk_branch gcc_ufs_1_card_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_1_card_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -5432,6 +5434,8 @@ static struct clk_branch gcc_ufs_card_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_card_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -5848,6 +5852,8 @@ static struct clk_branch gcc_ufs_ref_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_ref_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, }, diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c index 7cf5e130e92f..0f21a8a767ac 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -11,7 +11,6 @@ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/pm_domain.h> -#include <linux/pm_runtime.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/reset-controller.h> @@ -56,22 +55,6 @@ enum gdsc_status { GDSC_ON }; -static int gdsc_pm_runtime_get(struct gdsc *sc) -{ - if (!sc->dev) - return 0; - - return pm_runtime_resume_and_get(sc->dev); -} - -static int gdsc_pm_runtime_put(struct gdsc *sc) -{ - if (!sc->dev) - return 0; - - return pm_runtime_put_sync(sc->dev); -} - /* Returns 1 if GDSC status is status, 0 if not, and < 0 on error */ static int gdsc_check_status(struct gdsc *sc, enum gdsc_status status) { @@ -271,8 +254,9 @@ static void gdsc_retain_ff_on(struct gdsc *sc) regmap_update_bits(sc->regmap, sc->gdscr, mask, mask); } -static int _gdsc_enable(struct gdsc *sc) +static int gdsc_enable(struct generic_pm_domain *domain) { + struct gdsc *sc = domain_to_gdsc(domain); int ret; if (sc->pwrsts == PWRSTS_ON) @@ -328,22 +312,11 @@ static int _gdsc_enable(struct gdsc *sc) return 0; } -static int gdsc_enable(struct generic_pm_domain *domain) +static int gdsc_disable(struct generic_pm_domain *domain) { struct gdsc *sc = domain_to_gdsc(domain); int ret; - ret = gdsc_pm_runtime_get(sc); - if (ret) - return ret; - - return _gdsc_enable(sc); -} - -static int _gdsc_disable(struct gdsc *sc) -{ - int ret; - if (sc->pwrsts == PWRSTS_ON) return gdsc_assert_reset(sc); @@ -388,18 +361,6 @@ static int _gdsc_disable(struct gdsc *sc) return 0; } -static int gdsc_disable(struct generic_pm_domain *domain) -{ - struct gdsc *sc = domain_to_gdsc(domain); - int ret; - - ret = _gdsc_disable(sc); - - gdsc_pm_runtime_put(sc); - - return ret; -} - static int gdsc_init(struct gdsc *sc) { u32 mask, val; @@ -447,11 +408,6 @@ static int gdsc_init(struct gdsc *sc) return ret; } - /* ...and the power-domain */ - ret = gdsc_pm_runtime_get(sc); - if (ret) - goto err_disable_supply; - /* * Votable GDSCs can be ON due to Vote from other masters. * If a Votable GDSC is ON, make sure we have a Vote. @@ -459,14 +415,14 @@ static int gdsc_init(struct gdsc *sc) if (sc->flags & VOTABLE) { ret = gdsc_update_collapse_bit(sc, false); if (ret) - goto err_put_rpm; + goto err_disable_supply; } /* Turn on HW trigger mode if supported */ if (sc->flags & HW_CTRL) { ret = gdsc_hwctrl(sc, true); if (ret < 0) - goto err_put_rpm; + goto err_disable_supply; } /* @@ -496,13 +452,10 @@ static int gdsc_init(struct gdsc *sc) ret = pm_genpd_init(&sc->pd, NULL, !on); if (ret) - goto err_put_rpm; + goto err_disable_supply; return 0; -err_put_rpm: - if (on) - gdsc_pm_runtime_put(sc); err_disable_supply: if (on && sc->rsupply) regulator_disable(sc->rsupply); @@ -541,8 +494,6 @@ int gdsc_register(struct gdsc_desc *desc, for (i = 0; i < num; i++) { if (!scs[i]) continue; - if (pm_runtime_enabled(dev)) - scs[i]->dev = dev; scs[i]->regmap = regmap; scs[i]->rcdev = rcdev; ret = gdsc_init(scs[i]); diff --git a/drivers/clk/qcom/gdsc.h b/drivers/clk/qcom/gdsc.h index 981a12c8502d..803512688336 100644 --- a/drivers/clk/qcom/gdsc.h +++ b/drivers/clk/qcom/gdsc.h @@ -30,7 +30,6 @@ struct reset_controller_dev; * @resets: ids of resets associated with this gdsc * @reset_count: number of @resets * @rcdev: reset controller - * @dev: the device holding the GDSC, used for pm_runtime calls */ struct gdsc { struct generic_pm_domain pd; @@ -74,7 +73,6 @@ struct gdsc { const char *supply; struct regulator *rsupply; - struct device *dev; }; struct gdsc_desc { diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c index 273f77d54dab..e6d6cbf8c4e6 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -81,17 +81,19 @@ MODULE_DEVICE_TABLE(of, exynos_clkout_ids); static int exynos_clkout_match_parent_dev(struct device *dev, u32 *mux_mask) { const struct exynos_clkout_variant *variant; + const struct of_device_id *match; if (!dev->parent) { dev_err(dev, "not instantiated from MFD\n"); return -EINVAL; } - variant = of_device_get_match_data(dev->parent); - if (!variant) { + match = of_match_device(exynos_clkout_ids, dev->parent); + if (!match) { dev_err(dev, "cannot match parent device\n"); return -EINVAL; } + variant = match->data; *mux_mask = variant->mux_mask; diff --git a/drivers/clk/samsung/clk-exynos7885.c b/drivers/clk/samsung/clk-exynos7885.c index 62ce6814f141..0d2a950ed184 100644 --- a/drivers/clk/samsung/clk-exynos7885.c +++ b/drivers/clk/samsung/clk-exynos7885.c @@ -231,7 +231,7 @@ static const struct samsung_div_clock top_div_clks[] __initconst = { CLK_CON_DIV_PLL_SHARED0_DIV2, 0, 1), DIV(CLK_DOUT_SHARED0_DIV3, "dout_shared0_div3", "fout_shared0_pll", CLK_CON_DIV_PLL_SHARED0_DIV3, 0, 2), - DIV(CLK_DOUT_SHARED0_DIV4, "dout_shared0_div4", "fout_shared0_pll", + DIV(CLK_DOUT_SHARED0_DIV4, "dout_shared0_div4", "dout_shared0_div2", CLK_CON_DIV_PLL_SHARED0_DIV4, 0, 1), DIV(CLK_DOUT_SHARED0_DIV5, "dout_shared0_div5", "fout_shared0_pll", CLK_CON_DIV_PLL_SHARED0_DIV5, 0, 3), @@ -239,7 +239,7 @@ static const struct samsung_div_clock top_div_clks[] __initconst = { CLK_CON_DIV_PLL_SHARED1_DIV2, 0, 1), DIV(CLK_DOUT_SHARED1_DIV3, "dout_shared1_div3", "fout_shared1_pll", CLK_CON_DIV_PLL_SHARED1_DIV3, 0, 2), - DIV(CLK_DOUT_SHARED1_DIV4, "dout_shared1_div4", "fout_shared1_pll", + DIV(CLK_DOUT_SHARED1_DIV4, "dout_shared1_div4", "dout_shared1_div2", CLK_CON_DIV_PLL_SHARED1_DIV4, 0, 1), /* CORE */ diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index a7ff77550e17..933bb960490d 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -806,6 +806,9 @@ static u64 __arch_timer_check_delta(void) /* * XGene-1 implements CVAL in terms of TVAL, meaning * that the maximum timer range is 32bit. Shame on them. + * + * Note that TVAL is signed, thus has only 31 of its + * 32 bits to express magnitude. */ MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, APM_CPU_PART_POTENZA)), @@ -813,8 +816,8 @@ static u64 __arch_timer_check_delta(void) }; if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) { - pr_warn_once("Broken CNTx_CVAL_EL1, limiting width to 32bits"); - return CLOCKSOURCE_MASK(32); + pr_warn_once("Broken CNTx_CVAL_EL1, using 31 bit TVAL instead.\n"); + return CLOCKSOURCE_MASK(31); } #endif return CLOCKSOURCE_MASK(arch_counter_get_width()); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 969a552da8d2..a0d66fabf073 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -51,7 +51,7 @@ static int riscv_clock_next_event(unsigned long delta, static unsigned int riscv_clock_event_irq; static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = { .name = "riscv_timer_clockevent", - .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP, + .features = CLOCK_EVT_FEAT_ONESHOT, .rating = 100, .set_next_event = riscv_clock_next_event, }; diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 310779b07daf..00476e94db90 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -35,7 +35,7 @@ config X86_PCC_CPUFREQ If in doubt, say N. config X86_AMD_PSTATE - tristate "AMD Processor P-State driver" + bool "AMD Processor P-State driver" depends on X86 && ACPI select ACPI_PROCESSOR select ACPI_CPPC_LIB if X86_64 diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index ace7d50cf2ac..204e39006dda 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -59,12 +59,8 @@ * we disable it by default to go acpi-cpufreq on these processors and add a * module parameter to be able to enable it manually for debugging. */ -static bool shared_mem = false; -module_param(shared_mem, bool, 0444); -MODULE_PARM_DESC(shared_mem, - "enable amd-pstate on processors with shared memory solution (false = disabled (default), true = enabled)"); - static struct cpufreq_driver amd_pstate_driver; +static int cppc_load __initdata; static inline int pstate_enable(bool enable) { @@ -424,12 +420,22 @@ static void amd_pstate_boost_init(struct amd_cpudata *cpudata) amd_pstate_driver.boost_enabled = true; } +static void amd_perf_ctl_reset(unsigned int cpu) +{ + wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; struct device *dev; struct amd_cpudata *cpudata; + /* + * Resetting PERF_CTL_MSR will put the CPU in P0 frequency, + * which is ideal for initialization process. + */ + amd_perf_ctl_reset(policy->cpu); dev = get_cpu_device(policy->cpu); if (!dev) return -ENODEV; @@ -616,6 +622,15 @@ static int __init amd_pstate_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return -ENODEV; + /* + * by default the pstate driver is disabled to load + * enable the amd_pstate passive mode driver explicitly + * with amd_pstate=passive in kernel command line + */ + if (!cppc_load) { + pr_debug("driver load is disabled, boot with amd_pstate=passive to enable this\n"); + return -ENODEV; + } if (!acpi_cpc_valid()) { pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n"); @@ -630,13 +645,11 @@ static int __init amd_pstate_init(void) if (boot_cpu_has(X86_FEATURE_CPPC)) { pr_debug("AMD CPPC MSR based functionality is supported\n"); amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf; - } else if (shared_mem) { + } else { + pr_debug("AMD CPPC shared memory based functionality is supported\n"); static_call_update(amd_pstate_enable, cppc_enable); static_call_update(amd_pstate_init_perf, cppc_init_perf); static_call_update(amd_pstate_update_perf, cppc_update_perf); - } else { - pr_info("This processor supports shared memory solution, you can enable it with amd_pstate.shared_mem=1\n"); - return -ENODEV; } /* enable amd pstate feature */ @@ -653,16 +666,22 @@ static int __init amd_pstate_init(void) return ret; } +device_initcall(amd_pstate_init); -static void __exit amd_pstate_exit(void) +static int __init amd_pstate_param(char *str) { - cpufreq_unregister_driver(&amd_pstate_driver); + if (!str) + return -EINVAL; - amd_pstate_enable(false); -} + if (!strcmp(str, "disable")) { + cppc_load = 0; + pr_info("driver is explicitly disabled\n"); + } else if (!strcmp(str, "passive")) + cppc_load = 1; -module_init(amd_pstate_init); -module_exit(amd_pstate_exit); + return 0; +} +early_param("amd_pstate", amd_pstate_param); MODULE_AUTHOR("Huang Rui <[email protected]>"); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index 97086fab698e..903325aac991 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -8,6 +8,13 @@ static bool nohmem; module_param_named(disable, nohmem, bool, 0444); +static struct resource hmem_active = { + .name = "HMEM devices", + .start = 0, + .end = -1, + .flags = IORESOURCE_MEM, +}; + void hmem_register_device(int target_nid, struct resource *r) { /* define a clean / non-busy resource for the platform device */ @@ -41,6 +48,12 @@ void hmem_register_device(int target_nid, struct resource *r) goto out_pdev; } + if (!__request_region(&hmem_active, res.start, resource_size(&res), + dev_name(&pdev->dev), 0)) { + dev_dbg(&pdev->dev, "hmem range %pr already active\n", &res); + goto out_active; + } + pdev->dev.numa_node = numa_map_to_online_node(target_nid); info = (struct memregion_info) { .target_node = target_nid, @@ -66,6 +79,8 @@ void hmem_register_device(int target_nid, struct resource *r) return; out_resource: + __release_region(&hmem_active, res.start, resource_size(&res)); +out_active: platform_device_put(pdev); out_pdev: memregion_free(id); @@ -73,15 +88,6 @@ out_pdev: static __init int hmem_register_one(struct resource *res, void *data) { - /* - * If the resource is not a top-level resource it was already - * assigned to a device by the HMAT parsing. - */ - if (res->parent != &iomem_resource) { - pr_info("HMEM: skip %pr, already claimed\n", res); - return 0; - } - hmem_register_device(phys_to_target_node(res->start), res); return 0; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index dd0f83ee505b..e6f36c014c4c 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/dma-buf.h> #include <linux/dma-fence.h> +#include <linux/dma-fence-unwrap.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> @@ -391,8 +392,10 @@ static long dma_buf_import_sync_file(struct dma_buf *dmabuf, const void __user *user_data) { struct dma_buf_import_sync_file arg; - struct dma_fence *fence; + struct dma_fence *fence, *f; enum dma_resv_usage usage; + struct dma_fence_unwrap iter; + unsigned int num_fences; int ret = 0; if (copy_from_user(&arg, user_data, sizeof(arg))) @@ -411,13 +414,21 @@ static long dma_buf_import_sync_file(struct dma_buf *dmabuf, usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ; - dma_resv_lock(dmabuf->resv, NULL); + num_fences = 0; + dma_fence_unwrap_for_each(f, &iter, fence) + ++num_fences; - ret = dma_resv_reserve_fences(dmabuf->resv, 1); - if (!ret) - dma_resv_add_fence(dmabuf->resv, fence, usage); + if (num_fences > 0) { + dma_resv_lock(dmabuf->resv, NULL); - dma_resv_unlock(dmabuf->resv); + ret = dma_resv_reserve_fences(dmabuf->resv, num_fences); + if (!ret) { + dma_fence_unwrap_for_each(f, &iter, fence) + dma_resv_add_fence(dmabuf->resv, f, usage); + } + + dma_resv_unlock(dmabuf->resv); + } dma_fence_put(fence); diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 8f5848aa144f..59d158873f4c 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -233,18 +233,6 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) return ERR_PTR(-EINVAL); } - /* check the name is unique */ - mutex_lock(&heap_list_lock); - list_for_each_entry(h, &heap_list, list) { - if (!strcmp(h->name, exp_info->name)) { - mutex_unlock(&heap_list_lock); - pr_err("dma_heap: Already registered heap named %s\n", - exp_info->name); - return ERR_PTR(-EINVAL); - } - } - mutex_unlock(&heap_list_lock); - heap = kzalloc(sizeof(*heap), GFP_KERNEL); if (!heap) return ERR_PTR(-ENOMEM); @@ -283,13 +271,27 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) err_ret = ERR_CAST(dev_ret); goto err2; } - /* Add heap to the list */ + mutex_lock(&heap_list_lock); + /* check the name is unique */ + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + err_ret = ERR_PTR(-EINVAL); + goto err3; + } + } + + /* Add heap to the list */ list_add(&heap->list, &heap_list); mutex_unlock(&heap_list_lock); return heap; +err3: + device_destroy(dma_heap_class, heap->heap_devt); err2: cdev_del(&heap->heap_cdev); err1: diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 6c416955da53..bbe0a7cabb75 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -246,7 +246,9 @@ config FPGA_MGR_VERSAL_FPGA config FPGA_M10_BMC_SEC_UPDATE tristate "Intel MAX10 BMC Secure Update driver" - depends on MFD_INTEL_M10_BMC && FW_UPLOAD + depends on MFD_INTEL_M10_BMC + select FW_LOADER + select FW_UPLOAD help Secure update support for the Intel MAX10 board management controller. diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c index 14e6b3e64add..6f3ded619c8b 100644 --- a/drivers/gpio/gpio-amd8111.c +++ b/drivers/gpio/gpio-amd8111.c @@ -226,7 +226,10 @@ found: ioport_unmap(gp.pm); goto out; } + return 0; + out: + pci_dev_put(pdev); return err; } @@ -234,6 +237,7 @@ static void __exit amd_gpio_exit(void) { gpiochip_remove(&gp.chip); ioport_unmap(gp.pm); + pci_dev_put(gp.pdev); } module_init(amd_gpio_init); diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 870910bb9dd3..200e43a6f4b4 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -610,6 +610,7 @@ static int rockchip_gpiolib_register(struct rockchip_pin_bank *bank) return -ENODATA; pctldev = of_pinctrl_get(pctlnp); + of_node_put(pctlnp); if (!pctldev) return -ENODEV; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4756ea08894f..a70522aef355 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -526,12 +526,13 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) if (ret) return ret; + /* From this point, the .release() function cleans up gpio_device */ + gdev->dev.release = gpiodevice_release; + ret = gpiochip_sysfs_register(gdev); if (ret) goto err_remove_device; - /* From this point, the .release() function cleans up gpio_device */ - gdev->dev.release = gpiodevice_release; dev_dbg(&gdev->dev, "registered GPIOs %d to %d on %s\n", gdev->base, gdev->base + gdev->ngpio - 1, gdev->chip->label ? : "generic"); @@ -597,10 +598,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct fwnode_handle *fwnode = NULL; struct gpio_device *gdev; unsigned long flags; - int base = gc->base; unsigned int i; + u32 ngpios = 0; + int base = 0; int ret = 0; - u32 ngpios; if (gc->fwnode) fwnode = gc->fwnode; @@ -647,17 +648,12 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, else gdev->owner = THIS_MODULE; - gdev->descs = kcalloc(gc->ngpio, sizeof(gdev->descs[0]), GFP_KERNEL); - if (!gdev->descs) { - ret = -ENOMEM; - goto err_free_dev_name; - } - /* * Try the device properties if the driver didn't supply the number * of GPIO lines. */ - if (gc->ngpio == 0) { + ngpios = gc->ngpio; + if (ngpios == 0) { ret = device_property_read_u32(&gdev->dev, "ngpios", &ngpios); if (ret == -ENODATA) /* @@ -668,7 +664,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, */ ngpios = 0; else if (ret) - goto err_free_descs; + goto err_free_dev_name; gc->ngpio = ngpios; } @@ -676,13 +672,19 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, if (gc->ngpio == 0) { chip_err(gc, "tried to insert a GPIO chip with zero lines\n"); ret = -EINVAL; - goto err_free_descs; + goto err_free_dev_name; } if (gc->ngpio > FASTPATH_NGPIO) chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n", gc->ngpio, FASTPATH_NGPIO); + gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL); + if (!gdev->descs) { + ret = -ENOMEM; + goto err_free_dev_name; + } + gdev->label = kstrdup_const(gc->label ?: "unknown", GFP_KERNEL); if (!gdev->label) { ret = -ENOMEM; @@ -701,11 +703,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, * it may be a pipe dream. It will not happen before we get rid * of the sysfs interface anyways. */ + base = gc->base; if (base < 0) { base = gpiochip_find_base(gc->ngpio); if (base < 0) { - ret = base; spin_unlock_irqrestore(&gpio_lock, flags); + ret = base; + base = 0; goto err_free_label; } /* @@ -816,6 +820,11 @@ err_remove_of_chip: err_free_gpiochip_mask: gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); + if (gdev->dev.release) { + /* release() has been registered by gpiochip_setup_dev() */ + put_device(&gdev->dev); + goto err_print_message; + } err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); list_del(&gdev->list); @@ -829,13 +838,14 @@ err_free_dev_name: err_free_ida: ida_free(&gpio_ida, gdev->id); err_free_gdev: + kfree(gdev); +err_print_message: /* failures here can mean systems won't boot... */ if (ret != -EPROBE_DEFER) { pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__, - gdev->base, gdev->base + gdev->ngpio - 1, + base, base + (int)ngpios - 1, gc->label ? : "generic", ret); } - kfree(gdev); return ret; } EXPORT_SYMBOL_GPL(gpiochip_add_data_with_key); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c index c8935d718207..4485bb29bec9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c @@ -41,5 +41,6 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = { .get_atc_vmid_pasid_mapping_info = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info, .set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base, + .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 6d1ff7b9258d..1f76e27f1a35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -986,6 +986,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, struct amdkfd_process_info *process_info = mem->process_info; struct amdgpu_bo *bo = mem->bo; struct ttm_operation_ctx ctx = { true, false }; + struct hmm_range *range; int ret = 0; mutex_lock(&process_info->lock); @@ -1015,7 +1016,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, return 0; } - ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range); if (ret) { pr_err("%s: Failed to get user pages: %d\n", __func__, ret); goto unregister_out; @@ -1033,7 +1034,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, amdgpu_bo_unreserve(bo); release_out: - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); unregister_out: if (ret) amdgpu_mn_unregister(bo); @@ -2370,6 +2371,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, /* Go through userptr_inval_list and update any invalid user_pages */ list_for_each_entry(mem, &process_info->userptr_inval_list, validate_list.head) { + struct hmm_range *range; + invalid = atomic_read(&mem->invalid); if (!invalid) /* BO hasn't been invalidated since the last @@ -2380,7 +2383,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, bo = mem->bo; /* Get updated user pages */ - ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &range); if (ret) { pr_debug("Failed %d to get user pages\n", ret); @@ -2399,7 +2403,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, * FIXME: Cannot ignore the return code, must hold * notifier_lock */ - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); } /* Mark the BO as valid unless it was invalidated diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 2168163aad2d..252a876b0725 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -209,6 +209,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, list_add_tail(&e->tv.head, &bucket[priority]); e->user_pages = NULL; + e->range = NULL; } /* Connect the sorted buckets in the output list. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 9caea1688fc3..e4d78491bcc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -26,6 +26,8 @@ #include <drm/ttm/ttm_execbuf_util.h> #include <drm/amdgpu_drm.h> +struct hmm_range; + struct amdgpu_device; struct amdgpu_bo; struct amdgpu_bo_va; @@ -36,6 +38,7 @@ struct amdgpu_bo_list_entry { struct amdgpu_bo_va *bo_va; uint32_t priority; struct page **user_pages; + struct hmm_range *range; bool user_invalidated; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 491d4846fc02..cfb262911bfc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -328,7 +328,6 @@ static void amdgpu_connector_free_edid(struct drm_connector *connector) kfree(amdgpu_connector->edid); amdgpu_connector->edid = NULL; - drm_connector_update_edid_property(connector, NULL); } static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d038b258cc92..365e3fb6a9e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -913,7 +913,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, goto out_free_user_pages; } - r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages); + r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages, &e->range); if (r) { kvfree(e->user_pages); e->user_pages = NULL; @@ -991,9 +991,10 @@ out_free_user_pages: if (!e->user_pages) continue; - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); kvfree(e->user_pages); e->user_pages = NULL; + e->range = NULL; } mutex_unlock(&p->bo_list->bo_list_mutex); return r; @@ -1273,7 +1274,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); + e->range = NULL; } if (r) { r = -EAGAIN; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 8ef31d687ef3..91571b1324f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -378,6 +378,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, struct amdgpu_device *adev = drm_to_adev(dev); struct drm_amdgpu_gem_userptr *args = data; struct drm_gem_object *gobj; + struct hmm_range *range; struct amdgpu_bo *bo; uint32_t handle; int r; @@ -413,14 +414,13 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, if (r) goto release_object; - if (args->flags & AMDGPU_GEM_USERPTR_REGISTER) { - r = amdgpu_mn_register(bo, args->addr); - if (r) - goto release_object; - } + r = amdgpu_mn_register(bo, args->addr); + if (r) + goto release_object; if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) { - r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &range); if (r) goto release_object; @@ -443,7 +443,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, user_pages_done: if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); release_object: drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index b06cb0bb166c..28612e56d0d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -479,6 +479,12 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev) unsigned i; unsigned vmhub, inv_eng; + if (adev->enable_mes) { + /* reserve engine 5 for firmware */ + for (vmhub = 0; vmhub < AMDGPU_MAX_VMHUBS; vmhub++) + vm_inv_engs[vmhub] &= ~(1 << 5); + } + for (i = 0; i < adev->num_rings; ++i) { ring = adev->rings[i]; vmhub = ring->funcs->vmhub; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index cd968e781077..adac650cf544 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -169,7 +169,11 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job) amdgpu_sync_free(&job->sync); amdgpu_sync_free(&job->sched_sync); - dma_fence_put(&job->hw_fence); + /* only put the hw fence if has embedded fence */ + if (!job->hw_fence.ops) + kfree(job); + else + dma_fence_put(&job->hw_fence); } void amdgpu_job_set_gang_leader(struct amdgpu_job *job, @@ -254,6 +258,9 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job, DRM_ERROR("Error adding fence (%d)\n", r); } + if (!fence && job->gang_submit) + fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); + while (fence == NULL && vm && !job->vmid) { r = amdgpu_vmid_grab(vm, ring, &job->sync, &job->base.s_fence->finished, @@ -264,9 +271,6 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job, fence = amdgpu_sync_get_fence(&job->sync); } - if (!fence && job->gang_submit) - fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); - return fence; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index effa7df3ddbf..7978307e1d6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -172,6 +172,7 @@ void psp_ta_free_shared_buf(struct ta_mem_context *mem_ctx) { amdgpu_bo_free_kernel(&mem_ctx->shared_bo, &mem_ctx->shared_mc_addr, &mem_ctx->shared_buf); + mem_ctx->shared_bo = NULL; } static void psp_free_shared_bufs(struct psp_context *psp) @@ -182,6 +183,7 @@ static void psp_free_shared_bufs(struct psp_context *psp) /* free TMR memory buffer */ pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr); + psp->tmr_bo = NULL; /* free xgmi shared memory */ psp_ta_free_shared_buf(&psp->xgmi_context.context.mem_context); @@ -743,7 +745,7 @@ static int psp_load_toc(struct psp_context *psp, /* Set up Trusted Memory Region */ static int psp_tmr_init(struct psp_context *psp) { - int ret; + int ret = 0; int tmr_size; void *tmr_buf; void **pptr; @@ -770,10 +772,12 @@ static int psp_tmr_init(struct psp_context *psp) } } - pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, - AMDGPU_GEM_DOMAIN_VRAM, - &psp->tmr_bo, &psp->tmr_mc_addr, pptr); + if (!psp->tmr_bo) { + pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, + AMDGPU_GEM_DOMAIN_VRAM, + &psp->tmr_bo, &psp->tmr_mc_addr, pptr); + } return ret; } @@ -2732,8 +2736,6 @@ static int psp_suspend(void *handle) } out: - psp_free_shared_bufs(psp); - return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 57277b1cf183..b64938ed8cb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -643,9 +643,6 @@ struct amdgpu_ttm_tt { struct task_struct *usertask; uint32_t userflags; bool bound; -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - struct hmm_range *range; -#endif }; #define ttm_to_amdgpu_ttm_tt(ptr) container_of(ptr, struct amdgpu_ttm_tt, ttm) @@ -658,7 +655,8 @@ struct amdgpu_ttm_tt { * Calling function must call amdgpu_ttm_tt_userptr_range_done() once and only * once afterwards to stop HMM tracking */ -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range) { struct ttm_tt *ttm = bo->tbo.ttm; struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); @@ -668,16 +666,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) bool readonly; int r = 0; + /* Make sure get_user_pages_done() can cleanup gracefully */ + *range = NULL; + mm = bo->notifier.mm; if (unlikely(!mm)) { DRM_DEBUG_DRIVER("BO is not registered?\n"); return -EFAULT; } - /* Another get_user_pages is running at the same time?? */ - if (WARN_ON(gtt->range)) - return -EFAULT; - if (!mmget_not_zero(mm)) /* Happens during process shutdown */ return -ESRCH; @@ -695,7 +692,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) readonly = amdgpu_ttm_tt_is_readonly(ttm); r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start, - ttm->num_pages, >t->range, readonly, + ttm->num_pages, range, readonly, true, NULL); out_unlock: mmap_read_unlock(mm); @@ -713,30 +710,24 @@ out_unlock: * * Returns: true if pages are still valid */ -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); - bool r = false; - if (!gtt || !gtt->userptr) + if (!gtt || !gtt->userptr || !range) return false; DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%x\n", gtt->userptr, ttm->num_pages); - WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns, - "No user pages to check\n"); + WARN_ONCE(!range->hmm_pfns, "No user pages to check\n"); - if (gtt->range) { - /* - * FIXME: Must always hold notifier_lock for this, and must - * not ignore the return code. - */ - r = amdgpu_hmm_range_get_pages_done(gtt->range); - gtt->range = NULL; - } - - return !r; + /* + * FIXME: Must always hold notifier_lock for this, and must + * not ignore the return code. + */ + return !amdgpu_hmm_range_get_pages_done(range); } #endif @@ -813,20 +804,6 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev, /* unmap the pages mapped to the device */ dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0); sg_free_table(ttm->sg); - -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - if (gtt->range) { - unsigned long i; - - for (i = 0; i < ttm->num_pages; i++) { - if (ttm->pages[i] != - hmm_pfn_to_page(gtt->range->hmm_pfns[i])) - break; - } - - WARN((i == ttm->num_pages), "Missing get_user_page_done\n"); - } -#endif } static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 6a70818039dd..a37207011a69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -39,6 +39,8 @@ #define AMDGPU_POISON 0xd0bed0be +struct hmm_range; + struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; @@ -149,15 +151,19 @@ void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type); #if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages); -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm); +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range); +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range); #else static inline int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, - struct page **pages) + struct page **pages, + struct hmm_range **range) { return -EPERM; } -static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 0b52af415b28..ce64ca1c6e66 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -156,6 +156,9 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) break; case IP_VERSION(3, 0, 2): fw_name = FIRMWARE_VANGOGH; + if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && + (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) + adev->vcn.indirect_sram = true; break; case IP_VERSION(3, 0, 16): fw_name = FIRMWARE_DIMGREY_CAVEFISH; diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h index f772bb499f3e..0312c71c3af9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h +++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h @@ -32,7 +32,6 @@ #define RB_ENABLED (1 << 0) #define RB4_ENABLED (1 << 1) -#define MMSCH_DOORBELL_OFFSET 0x8 #define MMSCH_VF_ENGINE_STATUS__PASS 0x1 diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 1122bd4eae98..4d780e4430e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -907,13 +907,13 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /** - * sdma_v4_0_gfx_stop - stop the gfx async dma engines + * sdma_v4_0_gfx_enable - enable the gfx async dma engines * * @adev: amdgpu_device pointer - * - * Stop the gfx async dma ring buffers (VEGA10). + * @enable: enable SDMA RB/IB + * control the gfx async dma ring buffers (VEGA10). */ -static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) +static void sdma_v4_0_gfx_enable(struct amdgpu_device *adev, bool enable) { u32 rb_cntl, ib_cntl; int i; @@ -922,10 +922,10 @@ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL); - rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); + rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl); ib_cntl = RREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL); - ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0); + ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL, ib_cntl); } } @@ -1044,7 +1044,7 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable) int i; if (!enable) { - sdma_v4_0_gfx_stop(adev); + sdma_v4_0_gfx_enable(adev, enable); sdma_v4_0_rlc_stop(adev); if (adev->sdma.has_page_queue) sdma_v4_0_page_stop(adev); @@ -1960,8 +1960,10 @@ static int sdma_v4_0_suspend(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU saves SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_gfx_enable(adev, false); return 0; + } return sdma_v4_0_hw_fini(adev); } @@ -1971,8 +1973,12 @@ static int sdma_v4_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU restores SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_enable(adev, true); + sdma_v4_0_gfx_enable(adev, true); + amdgpu_ttm_set_buffer_funcs_status(adev, true); return 0; + } return sdma_v4_0_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 897a5ce9c9da..dcc49b01bd59 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -100,7 +100,6 @@ static int vcn_v4_0_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i, r; - int vcn_doorbell_index = 0; r = amdgpu_vcn_sw_init(adev); if (r) @@ -112,12 +111,6 @@ static int vcn_v4_0_sw_init(void *handle) if (r) return r; - if (amdgpu_sriov_vf(adev)) { - vcn_doorbell_index = adev->doorbell_index.vcn.vcn_ring0_1 - MMSCH_DOORBELL_OFFSET; - /* get DWORD offset */ - vcn_doorbell_index = vcn_doorbell_index << 1; - } - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn4_fw_shared *fw_shared; @@ -135,7 +128,7 @@ static int vcn_v4_0_sw_init(void *handle) ring = &adev->vcn.inst[i].ring_enc[0]; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1; + ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * (adev->vcn.num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 6925e0280dbe..f4f3d2665a6b 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -5,6 +5,7 @@ menu "Display Engine Configuration" config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y + depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64 select SND_HDA_COMPONENT if SND_HDA_CORE select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128) help @@ -12,6 +13,12 @@ config DRM_AMD_DC support for AMDGPU. This adds required support for Vega and Raven ASICs. + calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64) + architectures built with Clang (all released versions), whereby the stack + frame gets blown up to well over 5k. This would cause an immediate kernel + panic on most architectures. We'll revert this when the following bug report + has been resolved: https://github.com/llvm/llvm-project/issues/41896. + config DRM_AMD_DC_DCN def_bool n help diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 3e1ecca72430..512c32327eb1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1372,7 +1372,44 @@ static const struct dmi_system_id hpd_disconnect_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"), + }, + }, {} + /* TODO: refactor this from a fixed table to a dynamic option */ }; static void retrieve_dmi_info(struct amdgpu_display_manager *dm) @@ -6475,7 +6512,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, struct drm_connector_state *new_con_state; struct amdgpu_dm_connector *aconnector; struct dm_connector_state *dm_conn_state; - int i, j; + int i, j, ret; int vcpi, pbn_div, pbn, slot_num = 0; for_each_new_connector_in_state(state, connector, new_con_state, i) { @@ -6522,8 +6559,11 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, dm_conn_state->pbn = pbn; dm_conn_state->vcpi_slots = slot_num; - drm_dp_mst_atomic_enable_dsc(state, aconnector->port, dm_conn_state->pbn, - false); + ret = drm_dp_mst_atomic_enable_dsc(state, aconnector->port, + dm_conn_state->pbn, false); + if (ret < 0) + return ret; + continue; } @@ -9537,10 +9577,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, #if defined(CONFIG_DRM_AMD_DC_DCN) if (dc_resource_is_dsc_encoding_supported(dc)) { - if (!pre_validate_dsc(state, &dm_state, vars)) { - ret = -EINVAL; + ret = pre_validate_dsc(state, &dm_state, vars); + if (ret != 0) goto fail; - } } #endif @@ -9635,9 +9674,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } #if defined(CONFIG_DRM_AMD_DC_DCN) - if (!compute_mst_dsc_configs_for_state(state, dm_state->context, vars)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 6ff96b4bdda5..6483ba266893 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -703,13 +703,13 @@ static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) return dsc_config.bits_per_pixel; } -static bool increase_dsc_bpp(struct drm_atomic_state *state, - struct drm_dp_mst_topology_state *mst_state, - struct dc_link *dc_link, - struct dsc_mst_fairness_params *params, - struct dsc_mst_fairness_vars *vars, - int count, - int k) +static int increase_dsc_bpp(struct drm_atomic_state *state, + struct drm_dp_mst_topology_state *mst_state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count, + int k) { int i; bool bpp_increased[MAX_PIPES]; @@ -719,6 +719,7 @@ static bool increase_dsc_bpp(struct drm_atomic_state *state, int remaining_to_increase = 0; int link_timeslots_used; int fair_pbn_alloc; + int ret = 0; for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { @@ -757,52 +758,60 @@ static bool increase_dsc_bpp(struct drm_atomic_state *state, if (initial_slack[next_index] > fair_pbn_alloc) { vars[next_index].pbn += fair_pbn_alloc; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; + + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].bpp_x16 = bpp_x16_from_pbn(params[next_index], vars[next_index].pbn); } else { vars[next_index].pbn -= fair_pbn_alloc; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } } else { vars[next_index].pbn += initial_slack[next_index]; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; + + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].bpp_x16 = params[next_index].bw_range.max_target_bpp_x16; } else { vars[next_index].pbn -= initial_slack[next_index]; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } } bpp_increased[next_index] = true; remaining_to_increase--; } - return true; + return 0; } -static bool try_disable_dsc(struct drm_atomic_state *state, - struct dc_link *dc_link, - struct dsc_mst_fairness_params *params, - struct dsc_mst_fairness_vars *vars, - int count, - int k) +static int try_disable_dsc(struct drm_atomic_state *state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count, + int k) { int i; bool tried[MAX_PIPES]; @@ -810,6 +819,7 @@ static bool try_disable_dsc(struct drm_atomic_state *state, int max_kbps_increase; int next_index; int remaining_to_try = 0; + int ret; for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled @@ -840,49 +850,52 @@ static bool try_disable_dsc(struct drm_atomic_state *state, break; vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps); - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].dsc_enabled = false; vars[next_index].bpp_x16 = 0; } else { vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps); - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } tried[next_index] = true; remaining_to_try--; } - return true; + return 0; } -static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dc_link *dc_link, - struct dsc_mst_fairness_vars *vars, - struct drm_dp_mst_topology_mgr *mgr, - int *link_vars_start_index) +static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dc_link *dc_link, + struct dsc_mst_fairness_vars *vars, + struct drm_dp_mst_topology_mgr *mgr, + int *link_vars_start_index) { struct dc_stream_state *stream; struct dsc_mst_fairness_params params[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_state *mst_state = drm_atomic_get_mst_topology_state(state, mgr); int count = 0; - int i, k; + int i, k, ret; bool debugfs_overwrite = false; memset(params, 0, sizeof(params)); if (IS_ERR(mst_state)) - return false; + return PTR_ERR(mst_state); mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link); #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -933,7 +946,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (count == 0) { ASSERT(0); - return true; + return 0; } /* k is start index of vars for current phy link used by mst hub */ @@ -947,13 +960,17 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, - vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, + vars[i + k].pbn); + if (ret < 0) + return ret; } - if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) { + ret = drm_dp_mst_atomic_check(state); + if (ret == 0 && !debugfs_overwrite) { set_dsc_configs_from_fairness_vars(params, vars, count, k); - return true; + return 0; + } else if (ret != -ENOSPC) { + return ret; } /* Try max compression */ @@ -962,31 +979,36 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, - params[i].port, vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, + params[i].port, vars[i + k].pbn); + if (ret < 0) + return ret; } else { vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, - params[i].port, vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, + params[i].port, vars[i + k].pbn); + if (ret < 0) + return ret; } } - if (drm_dp_mst_atomic_check(state)) - return false; + ret = drm_dp_mst_atomic_check(state); + if (ret != 0) + return ret; /* Optimize degree of compression */ - if (!increase_dsc_bpp(state, mst_state, dc_link, params, vars, count, k)) - return false; + ret = increase_dsc_bpp(state, mst_state, dc_link, params, vars, count, k); + if (ret < 0) + return ret; - if (!try_disable_dsc(state, dc_link, params, vars, count, k)) - return false; + ret = try_disable_dsc(state, dc_link, params, vars, count, k); + if (ret < 0) + return ret; set_dsc_configs_from_fairness_vars(params, vars, count, k); - return true; + return 0; } static bool is_dsc_need_re_compute( @@ -1087,15 +1109,17 @@ static bool is_dsc_need_re_compute( return is_dsc_need_re_compute; } -bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars) +int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { int i, j; struct dc_stream_state *stream; bool computed_streams[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; + struct drm_dp_mst_topology_mgr *mst_mgr; int link_vars_start_index = 0; + int ret = 0; for (i = 0; i < dc_state->stream_count; i++) computed_streams[i] = false; @@ -1108,7 +1132,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; - if (!aconnector || !aconnector->dc_sink) + if (!aconnector || !aconnector->dc_sink || !aconnector->port) continue; if (!aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported) @@ -1118,19 +1142,16 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, continue; if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) - return false; + return -EINVAL; if (!is_dsc_need_re_compute(state, dc_state, stream->link)) continue; - mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, - &aconnector->mst_mgr, - &link_vars_start_index)) { - mutex_unlock(&aconnector->mst_mgr.lock); - return false; - } - mutex_unlock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + ret = compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, mst_mgr, + &link_vars_start_index); + if (ret != 0) + return ret; for (j = 0; j < dc_state->stream_count; j++) { if (dc_state->streams[j]->link == stream->link) @@ -1143,22 +1164,23 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (stream->timing.flags.DSC == 1) if (dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream) != DC_OK) - return false; + return -EINVAL; } - return true; + return ret; } -static bool - pre_compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars) +static int pre_compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { int i, j; struct dc_stream_state *stream; bool computed_streams[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; + struct drm_dp_mst_topology_mgr *mst_mgr; int link_vars_start_index = 0; + int ret = 0; for (i = 0; i < dc_state->stream_count; i++) computed_streams[i] = false; @@ -1171,7 +1193,7 @@ static bool aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; - if (!aconnector || !aconnector->dc_sink) + if (!aconnector || !aconnector->dc_sink || !aconnector->port) continue; if (!aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported) @@ -1183,14 +1205,11 @@ static bool if (!is_dsc_need_re_compute(state, dc_state, stream->link)) continue; - mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, - &aconnector->mst_mgr, - &link_vars_start_index)) { - mutex_unlock(&aconnector->mst_mgr.lock); - return false; - } - mutex_unlock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + ret = compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, mst_mgr, + &link_vars_start_index); + if (ret != 0) + return ret; for (j = 0; j < dc_state->stream_count; j++) { if (dc_state->streams[j]->link == stream->link) @@ -1198,7 +1217,7 @@ static bool } } - return true; + return ret; } static int find_crtc_index_in_state_by_stream(struct drm_atomic_state *state, @@ -1253,9 +1272,9 @@ static bool is_dsc_precompute_needed(struct drm_atomic_state *state) return ret; } -bool pre_validate_dsc(struct drm_atomic_state *state, - struct dm_atomic_state **dm_state_ptr, - struct dsc_mst_fairness_vars *vars) +int pre_validate_dsc(struct drm_atomic_state *state, + struct dm_atomic_state **dm_state_ptr, + struct dsc_mst_fairness_vars *vars) { int i; struct dm_atomic_state *dm_state; @@ -1264,11 +1283,12 @@ bool pre_validate_dsc(struct drm_atomic_state *state, if (!is_dsc_precompute_needed(state)) { DRM_INFO_ONCE("DSC precompute is not needed.\n"); - return true; + return 0; } - if (dm_atomic_get_state(state, dm_state_ptr)) { + ret = dm_atomic_get_state(state, dm_state_ptr); + if (ret != 0) { DRM_INFO_ONCE("dm_atomic_get_state() failed\n"); - return false; + return ret; } dm_state = *dm_state_ptr; @@ -1280,7 +1300,7 @@ bool pre_validate_dsc(struct drm_atomic_state *state, local_dc_state = kmemdup(dm_state->context, sizeof(struct dc_state), GFP_KERNEL); if (!local_dc_state) - return false; + return -ENOMEM; for (i = 0; i < local_dc_state->stream_count; i++) { struct dc_stream_state *stream = dm_state->context->streams[i]; @@ -1316,9 +1336,9 @@ bool pre_validate_dsc(struct drm_atomic_state *state, if (ret != 0) goto clean_exit; - if (!pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars)) { + ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars); + if (ret != 0) { DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; goto clean_exit; } @@ -1349,7 +1369,7 @@ clean_exit: kfree(local_dc_state); - return (ret == 0); + return ret; } static unsigned int kbps_from_pbn(unsigned int pbn) @@ -1392,6 +1412,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0; unsigned int max_compressed_bw_in_kbps = 0; struct dc_dsc_bw_range bw_range = {0}; + struct drm_dp_mst_topology_mgr *mst_mgr; /* * check if the mode could be supported if DSC pass-through is supported @@ -1400,7 +1421,8 @@ enum dc_status dm_dp_mst_is_port_support_mode( */ if (is_dsc_common_config_possible(stream, &bw_range) && aconnector->port->passthrough_aux) { - mutex_lock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + mutex_lock(&mst_mgr->lock); cur_link_settings = stream->link->verified_link_cap; @@ -1413,7 +1435,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps); - mutex_unlock(&aconnector->mst_mgr.lock); + mutex_unlock(&mst_mgr->lock); /* * use the maximum dsc compression bandwidth as the required diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index b92a7c5671aa..97fd70df531b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -53,15 +53,15 @@ struct dsc_mst_fairness_vars { struct amdgpu_dm_connector *aconnector; }; -bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars); +int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars); bool needs_dsc_aux_workaround(struct dc_link *link); -bool pre_validate_dsc(struct drm_atomic_state *state, - struct dm_atomic_state **dm_state_ptr, - struct dsc_mst_fairness_vars *vars); +int pre_validate_dsc(struct drm_atomic_state *state, + struct dm_atomic_state **dm_state_ptr, + struct dsc_mst_fairness_vars *vars); enum dc_status dm_dp_mst_is_port_support_mode( struct amdgpu_dm_connector *aconnector, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c index ef0795b14a1f..2db595672a46 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c @@ -123,9 +123,10 @@ static int dcn314_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uint32_t result; result = dcn314_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK); - smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", + result); if (result == VBIOSSMC_Status_BUSY) return -1; @@ -216,6 +217,12 @@ int dcn314_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int request VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz)); +#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", + actual_dcfclk_set_mhz, + actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; } diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 1b70b78e2fa1..af631085e88c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -359,7 +359,8 @@ static const struct dce_audio_registers audio_regs[] = { audio_regs(2), audio_regs(3), audio_regs(4), - audio_regs(5) + audio_regs(5), + audio_regs(6), }; #define DCE120_AUD_COMMON_MASK_SH_LIST(mask_sh)\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c index b9765b3899e1..ef52e6b6eccf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c @@ -436,34 +436,48 @@ void dpp1_set_cursor_position( uint32_t height) { struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; + int x_hotspot = pos->x_hotspot; + int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; + int cursor_height = (int)height; + int cursor_width = (int)width; uint32_t cur_en = pos->enable ? 1 : 0; - // Cursor width/height and hotspots need to be rotated for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { - swap(width, height); + swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } if (src_x_offset >= (int)param->viewport.width) cur_en = 0; /* not visible beyond right edge*/ - if (src_x_offset + (int)width <= 0) + if (src_x_offset + cursor_width <= 0) cur_en = 0; /* not visible beyond left edge*/ if (src_y_offset >= (int)param->viewport.height) cur_en = 0; /* not visible beyond bottom edge*/ - if (src_y_offset + (int)height <= 0) + if (src_y_offset + cursor_height <= 0) cur_en = 0; /* not visible beyond top edge*/ REG_UPDATE(CURSOR0_CONTROL, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index 52e201e9b091..a142a00bc432 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1179,10 +1179,12 @@ void hubp1_cursor_set_position( const struct dc_cursor_mi_param *param) { struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; int x_hotspot = pos->x_hotspot; int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; int cursor_height = (int)hubp->curs_attr.height; int cursor_width = (int)hubp->curs_attr.width; uint32_t dst_x_offset; @@ -1200,18 +1202,26 @@ void hubp1_cursor_set_position( if (hubp->curs_attr.address.quad_part == 0) return; - // Rotated cursor width/height and hotspots tweaks for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0; @@ -1248,8 +1258,8 @@ void hubp1_cursor_set_position( CURSOR_Y_POSITION, pos->y); REG_SET_2(CURSOR_HOT_SPOT, 0, - CURSOR_HOT_SPOT_X, x_hotspot, - CURSOR_HOT_SPOT_Y, y_hotspot); + CURSOR_HOT_SPOT_X, pos->x_hotspot, + CURSOR_HOT_SPOT_Y, pos->y_hotspot); REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 938dba5249d4..4566bc7abf17 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -973,10 +973,12 @@ void hubp2_cursor_set_position( const struct dc_cursor_mi_param *param) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; int x_hotspot = pos->x_hotspot; int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; int cursor_height = (int)hubp->curs_attr.height; int cursor_width = (int)hubp->curs_attr.width; uint32_t dst_x_offset; @@ -994,18 +996,26 @@ void hubp2_cursor_set_position( if (hubp->curs_attr.address.quad_part == 0) return; - // Rotated cursor width/height and hotspots tweaks for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0; @@ -1042,8 +1052,8 @@ void hubp2_cursor_set_position( CURSOR_Y_POSITION, pos->y); REG_SET_2(CURSOR_HOT_SPOT, 0, - CURSOR_HOT_SPOT_X, x_hotspot, - CURSOR_HOT_SPOT_Y, y_hotspot); + CURSOR_HOT_SPOT_X, pos->x_hotspot, + CURSOR_HOT_SPOT_Y, pos->y_hotspot); REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); @@ -1052,8 +1062,8 @@ void hubp2_cursor_set_position( hubp->pos.cur_ctl.bits.cur_enable = cur_en; hubp->pos.position.bits.x_pos = pos->x; hubp->pos.position.bits.y_pos = pos->y; - hubp->pos.hot_spot.bits.x_hot = x_hotspot; - hubp->pos.hot_spot.bits.y_hot = y_hotspot; + hubp->pos.hot_spot.bits.x_hot = pos->x_hotspot; + hubp->pos.hot_spot.bits.y_hot = pos->y_hotspot; hubp->pos.dst_offset.bits.dst_x_offset = dst_x_offset; /* Cursor Rectangle Cache * Cursor bitmaps have different hotspot values diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 1bd7e0f327d8..389a8938ee45 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -96,6 +96,13 @@ static void dccg314_set_pixel_rate_div( struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + // Don't program 0xF into the register field. Not valid since + // K1 / K2 field is only 1 / 2 bits wide + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) { + BREAK_TO_DEBUGGER(); + return; + } + dccg314_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA || (k1 == cur_k1 && k2 == cur_k2)) return; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 588c1c71241f..a0741794db62 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -348,10 +348,8 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) - return odm_combine_factor; - if (is_dp_128b_132b_signal(pipe_ctx)) { + *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { *k1_div = PIXEL_RATE_DIV_BY_1; @@ -359,7 +357,7 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig *k2_div = PIXEL_RATE_DIV_BY_2; else *k2_div = PIXEL_RATE_DIV_BY_4; - } else if (dc_is_dp_signal(pipe_ctx->stream->signal)) { + } else if (dc_is_dp_signal(pipe_ctx->stream->signal) || dc_is_virtual_signal(pipe_ctx->stream->signal)) { if (two_pix_per_container) { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index e4daed44ef5f..df4f25119142 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -96,8 +96,10 @@ static void dccg32_set_pixel_rate_div( // Don't program 0xF into the register field. Not valid since // K1 / K2 field is only 1 / 2 bits wide - if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) { + BREAK_TO_DEBUGGER(); return; + } dccg32_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); if (k1 == cur_k1 && k2 == cur_k2) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index ac41a763bb1d..d0b46a3e0155 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1171,10 +1171,8 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) - return odm_combine_factor; - if (is_dp_128b_132b_signal(pipe_ctx)) { + *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { *k1_div = PIXEL_RATE_DIV_BY_1; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index b03a7814e96d..fa3778849db1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -111,7 +111,7 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat mall_alloc_width_blk_aligned = full_vp_width_blk_aligned; /* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */ - mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) / + mall_alloc_height_blk_aligned = (pipe->plane_res.scl_data.viewport.height - 1 + mblk_height - 1) / mblk_height * mblk_height + mblk_height; /* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 12e17bcfca3f..2abe3967f7fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -157,7 +157,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { .dispclk_dppclk_vco_speed_mhz = 4300.0, .do_urgent_latency_adjustment = true, .urgent_latency_adjustment_fabric_clock_component_us = 1.0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, }; void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) @@ -211,7 +211,7 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) /* 'DalDummyClockChangeLatencyNs' registry key option set to 0x7FFFFFFF can be used to disable Set C for dummy p-state */ if (clk_mgr->base.ctx->dc->bb_overrides.dummy_clock_change_latency_ns != 0x7FFFFFFF) { clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].valid = true; - clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us = 38; + clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us = 50; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.fclk_change_latency_us = fclk_change_latency_us; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us = sr_exit_time_us; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us = sr_enter_plus_exit_time_us; @@ -221,7 +221,7 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].pmfw_breakdown.min_uclk = min_uclk_mhz; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].pmfw_breakdown.max_uclk = 0xFFFF; clk_mgr->base.bw_params->dummy_pstate_table[0].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[0].memclk_mhz * 16; - clk_mgr->base.bw_params->dummy_pstate_table[0].dummy_pstate_latency_us = 38; + clk_mgr->base.bw_params->dummy_pstate_table[0].dummy_pstate_latency_us = 50; clk_mgr->base.bw_params->dummy_pstate_table[1].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[1].memclk_mhz * 16; clk_mgr->base.bw_params->dummy_pstate_table[1].dummy_pstate_latency_us = 9; clk_mgr->base.bw_params->dummy_pstate_table[2].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[2].memclk_mhz * 16; @@ -1910,7 +1910,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] == dm_dram_clock_change_unsupported) { - int min_dram_speed_mts_offset = dc->clk_mgr->bw_params->clk_table.num_entries - 1; + int min_dram_speed_mts_offset = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1; min_dram_speed_mts = dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index 432b4ecd01a7..f4b176599be7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -126,9 +126,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, .round_trip_ping_latency_dcfclk_cycles = 263, - .urgent_latency_pixel_data_only_us = 9.35, - .urgent_latency_pixel_mixed_with_vm_data_us = 9.35, - .urgent_latency_vm_data_only_us = 9.35, + .urgent_latency_pixel_data_only_us = 4, + .urgent_latency_pixel_mixed_with_vm_data_us = 4, + .urgent_latency_vm_data_only_us = 4, .fclk_change_latency_us = 20, .usr_retraining_latency_us = 2, .smn_latency_us = 2, @@ -156,7 +156,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .dispclk_dppclk_vco_speed_mhz = 4300.0, .do_urgent_latency_adjustment = true, .urgent_latency_adjustment_fabric_clock_component_us = 1.0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, }; static void get_optimal_ntuple(struct _vcs_dpi_voltage_scaling_st *entry) diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 630f3395e90a..a0207a8f8756 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -1153,7 +1153,7 @@ struct vba_vars_st { double UrgBurstFactorLumaPre[DC__NUM_DPP__MAX]; double UrgBurstFactorChromaPre[DC__NUM_DPP__MAX]; bool NotUrgentLatencyHidingPre[DC__NUM_DPP__MAX]; - bool LinkCapacitySupport[DC__NUM_DPP__MAX]; + bool LinkCapacitySupport[DC__VOLTAGE_STATES]; bool VREADY_AT_OR_AFTER_VSYNC[DC__NUM_DPP__MAX]; unsigned int MIN_DST_Y_NEXT_START[DC__NUM_DPP__MAX]; unsigned int VFrontPorch[DC__NUM_DPP__MAX]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h index 25c08f963f49..d6b13933a98f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h @@ -25,10 +25,10 @@ // *** IMPORTANT *** // PMFW TEAM: Always increment the interface version on any change to this file -#define SMU13_DRIVER_IF_VERSION 0x2C +#define SMU13_DRIVER_IF_VERSION 0x35 //Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x20 +#define PPTABLE_VERSION 0x27 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 @@ -96,7 +96,7 @@ #define FEATURE_MEM_TEMP_READ_BIT 47 #define FEATURE_ATHUB_MMHUB_PG_BIT 48 #define FEATURE_SOC_PCC_BIT 49 -#define FEATURE_SPARE_50_BIT 50 +#define FEATURE_EDC_PWRBRK_BIT 50 #define FEATURE_SPARE_51_BIT 51 #define FEATURE_SPARE_52_BIT 52 #define FEATURE_SPARE_53_BIT 53 @@ -282,15 +282,15 @@ typedef enum { } I2cControllerPort_e; typedef enum { - I2C_CONTROLLER_NAME_VR_GFX = 0, - I2C_CONTROLLER_NAME_VR_SOC, - I2C_CONTROLLER_NAME_VR_VMEMP, - I2C_CONTROLLER_NAME_VR_VDDIO, - I2C_CONTROLLER_NAME_LIQUID0, - I2C_CONTROLLER_NAME_LIQUID1, - I2C_CONTROLLER_NAME_PLX, - I2C_CONTROLLER_NAME_OTHER, - I2C_CONTROLLER_NAME_COUNT, + I2C_CONTROLLER_NAME_VR_GFX = 0, + I2C_CONTROLLER_NAME_VR_SOC, + I2C_CONTROLLER_NAME_VR_VMEMP, + I2C_CONTROLLER_NAME_VR_VDDIO, + I2C_CONTROLLER_NAME_LIQUID0, + I2C_CONTROLLER_NAME_LIQUID1, + I2C_CONTROLLER_NAME_PLX, + I2C_CONTROLLER_NAME_FAN_INTAKE, + I2C_CONTROLLER_NAME_COUNT, } I2cControllerName_e; typedef enum { @@ -302,6 +302,7 @@ typedef enum { I2C_CONTROLLER_THROTTLER_LIQUID0, I2C_CONTROLLER_THROTTLER_LIQUID1, I2C_CONTROLLER_THROTTLER_PLX, + I2C_CONTROLLER_THROTTLER_FAN_INTAKE, I2C_CONTROLLER_THROTTLER_INA3221, I2C_CONTROLLER_THROTTLER_COUNT, } I2cControllerThrottler_e; @@ -309,8 +310,9 @@ typedef enum { typedef enum { I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5, I2C_CONTROLLER_PROTOCOL_VR_IR35217, - I2C_CONTROLLER_PROTOCOL_TMP_TMP102A, + I2C_CONTROLLER_PROTOCOL_TMP_MAX31875, I2C_CONTROLLER_PROTOCOL_INA3221, + I2C_CONTROLLER_PROTOCOL_TMP_MAX6604, I2C_CONTROLLER_PROTOCOL_COUNT, } I2cControllerProtocol_e; @@ -690,6 +692,9 @@ typedef struct { #define PP_OD_FEATURE_UCLK_BIT 8 #define PP_OD_FEATURE_ZERO_FAN_BIT 9 #define PP_OD_FEATURE_TEMPERATURE_BIT 10 +#define PP_OD_FEATURE_POWER_FEATURE_CTRL_BIT 11 +#define PP_OD_FEATURE_ASIC_TDC_BIT 12 +#define PP_OD_FEATURE_COUNT 13 typedef enum { PP_OD_POWER_FEATURE_ALWAYS_ENABLED, @@ -697,6 +702,11 @@ typedef enum { PP_OD_POWER_FEATURE_ALWAYS_DISABLED, } PP_OD_POWER_FEATURE_e; +typedef enum { + FAN_MODE_AUTO = 0, + FAN_MODE_MANUAL_LINEAR, +} FanMode_e; + typedef struct { uint32_t FeatureCtrlMask; @@ -708,8 +718,8 @@ typedef struct { uint8_t RuntimePwrSavingFeaturesCtrl; //Frequency changes - int16_t GfxclkFmin; // MHz - int16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz @@ -730,7 +740,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4]; - uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10]; uint32_t MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround } OverDriveTable_t; @@ -748,8 +763,8 @@ typedef struct { uint8_t IdlePwrSavingFeaturesCtrl; uint8_t RuntimePwrSavingFeaturesCtrl; - uint16_t GfxclkFmin; // MHz - uint16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz @@ -769,7 +784,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4]; - uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10]; } OverDriveLimits_t; @@ -903,7 +923,8 @@ typedef struct { uint16_t FanStartTempMin; uint16_t FanStartTempMax; - uint32_t Spare[12]; + uint16_t PowerMinPpt0[POWER_SOURCE_COUNT]; + uint32_t Spare[11]; } MsgLimits_t; @@ -1086,11 +1107,13 @@ typedef struct { uint32_t GfxoffSpare[15]; // GFX GPO - float DfllBtcMasterScalerM; + uint32_t DfllBtcMasterScalerM; int32_t DfllBtcMasterScalerB; - float DfllBtcSlaveScalerM; + uint32_t DfllBtcSlaveScalerM; int32_t DfllBtcSlaveScalerB; - uint32_t GfxGpoSpare[12]; + uint32_t DfllPccAsWaitCtrl; //GDFLL_AS_WAIT_CTRL_PCC register value to be passed to RLC msg + uint32_t DfllPccAsStepCtrl; //GDFLL_AS_STEP_CTRL_PCC register value to be passed to RLC msg + uint32_t GfxGpoSpare[10]; // GFX DCS @@ -1106,7 +1129,10 @@ typedef struct { uint16_t DcsTimeout; //This is the amount of time SMU FW waits for RLC to put GFX into GFXOFF before reverting to the fallback mechanism of throttling GFXCLK to Fmin. - uint32_t DcsSpare[16]; + uint32_t DcsSpare[14]; + + // UCLK section + uint16_t ShadowFreqTableUclk[NUM_UCLK_DPM_LEVELS]; // In MHz // UCLK section uint8_t UseStrobeModeOptimizations; //Set to indicate that FW should use strobe mode optimizations @@ -1163,13 +1189,14 @@ typedef struct { uint16_t IntakeTempHighIntakeAcousticLimit; uint16_t IntakeTempAcouticLimitReleaseRate; - uint16_t FanStalledTempLimitOffset; + int16_t FanAbnormalTempLimitOffset; uint16_t FanStalledTriggerRpm; - uint16_t FanAbnormalTriggerRpm; - uint16_t FanPadding; - - uint32_t FanSpare[14]; + uint16_t FanAbnormalTriggerRpmCoeff; + uint16_t FanAbnormalDetectionEnable; + uint8_t FanIntakeSensorSupport; + uint8_t FanIntakePadding[3]; + uint32_t FanSpare[13]; // SECTION: VDD_GFX AVFS uint8_t OverrideGfxAvfsFuses; @@ -1193,7 +1220,6 @@ typedef struct { uint32_t dGbV_dT_vmin; uint32_t dGbV_dT_vmax; - //Unused: PMFW-9370 uint32_t V2F_vmin_range_low; uint32_t V2F_vmin_range_high; uint32_t V2F_vmax_range_low; @@ -1238,8 +1264,21 @@ typedef struct { // SECTION: Advanced Options uint32_t DebugOverrides; + // Section: Total Board Power idle vs active coefficients + uint8_t TotalBoardPowerSupport; + uint8_t TotalBoardPowerPadding[3]; + + int16_t TotalIdleBoardPowerM; + int16_t TotalIdleBoardPowerB; + int16_t TotalBoardPowerM; + int16_t TotalBoardPowerB; + + QuadraticInt_t qFeffCoeffGameClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBaseClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBoostClock[POWER_SOURCE_COUNT]; + // SECTION: Sku Reserved - uint32_t Spare[64]; + uint32_t Spare[43]; // Padding for MMHUB - do not modify this uint32_t MmHubPadding[8]; @@ -1304,7 +1343,8 @@ typedef struct { // SECTION: Clock Spread Spectrum // UCLK Spread Spectrum - uint16_t UclkSpreadPadding; + uint8_t UclkTrainingModeSpreadPercent; // Q4.4 + uint8_t UclkSpreadPadding; uint16_t UclkSpreadFreq; // kHz // UCLK Spread Spectrum @@ -1317,11 +1357,7 @@ typedef struct { // Section: Memory Config uint8_t DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e - uint8_t PaddingMem1[3]; - - // Section: Total Board Power - uint16_t TotalBoardPower; //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power - uint16_t BoardPowerPadding; + uint8_t PaddingMem1[7]; // SECTION: UMC feature flags uint8_t HsrEnabled; @@ -1423,8 +1459,11 @@ typedef struct { uint16_t Vcn1ActivityPercentage ; uint32_t EnergyAccumulator; - uint16_t AverageSocketPower ; + uint16_t AverageSocketPower; + uint16_t AverageTotalBoardPower; + uint16_t AvgTemperature[TEMP_COUNT]; + uint16_t AvgTemperatureFanIntake; uint8_t PcieRate ; uint8_t PcieWidth ; @@ -1592,5 +1631,7 @@ typedef struct { #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D0 0x5 #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D3 0x6 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7 +#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 +#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9 #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index b7f4569aff2a..865d6358918d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -31,7 +31,7 @@ #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 40d8ca37f5bc..aa51c61a78c7 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2720,6 +2720,9 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, * if supported. In any case the default RGB888 format is added */ + /* Default 8bit RGB fallback */ + output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; + if (max_bpc >= 16 && info->bpc == 16) { if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV16_1X48; @@ -2753,9 +2756,6 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV8_1X24; - /* Default 8bit RGB fallback */ - output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; - *num_output_fmts = i; return output_fmts; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 3c3561942eb6..eb24322df721 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -931,9 +931,9 @@ static void ti_sn_bridge_set_video_timings(struct ti_sn65dsi86 *pdata) &pdata->bridge.encoder->crtc->state->adjusted_mode; u8 hsync_polarity = 0, vsync_polarity = 0; - if (mode->flags & DRM_MODE_FLAG_PHSYNC) + if (mode->flags & DRM_MODE_FLAG_NHSYNC) hsync_polarity = CHA_HSYNC_POLARITY; - if (mode->flags & DRM_MODE_FLAG_PVSYNC) + if (mode->flags & DRM_MODE_FLAG_NVSYNC) vsync_polarity = CHA_VSYNC_POLARITY; ti_sn65dsi86_write_u16(pdata, SN_CHA_ACTIVE_LINE_LENGTH_LOW_REG, diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index ecd22c038c8c..51a46689cda7 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -5186,7 +5186,7 @@ int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm mst_state = drm_atomic_get_mst_topology_state(state, mgr); if (IS_ERR(mst_state)) - return -EINVAL; + return PTR_ERR(mst_state); list_for_each_entry(pos, &mst_state->payloads, next) { diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 35138f8a375c..b602cd72a120 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -571,12 +571,20 @@ static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - int ret; WARN_ON(shmem->base.import_attach); - ret = drm_gem_shmem_get_pages(shmem); - WARN_ON_ONCE(ret != 0); + mutex_lock(&shmem->pages_lock); + + /* + * We should have already pinned the pages when the buffer was first + * mmap'd, vm_open() just grabs an additional reference for the new + * mm the vma is getting copied into (ie. on fork()). + */ + if (!WARN_ON_ONCE(!shmem->pages_use_count)) + shmem->pages_use_count++; + + mutex_unlock(&shmem->pages_lock); drm_gem_vm_open(vma); } @@ -622,10 +630,8 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct } ret = drm_gem_shmem_get_pages(shmem); - if (ret) { - drm_gem_vm_close(vma); + if (ret) return ret; - } vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 461c62c88413..de77054195c6 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -3723,12 +3723,16 @@ out: static u8 bigjoiner_pipes(struct drm_i915_private *i915) { + u8 pipes; + if (DISPLAY_VER(i915) >= 12) - return BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D); + pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D); else if (DISPLAY_VER(i915) >= 11) - return BIT(PIPE_B) | BIT(PIPE_C); + pipes = BIT(PIPE_B) | BIT(PIPE_C); else - return 0; + pipes = 0; + + return pipes & RUNTIME_INFO(i915)->pipe_mask; } static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 1e608b9e5055..1a63da28f330 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -2434,7 +2434,7 @@ intel_display_power_ddi_io_domain(struct drm_i915_private *i915, enum port port) { const struct intel_ddi_port_domains *domains = intel_port_domains_for_port(i915, port); - if (drm_WARN_ON(&i915->drm, !domains) || domains->ddi_io == POWER_DOMAIN_INVALID) + if (drm_WARN_ON(&i915->drm, !domains || domains->ddi_io == POWER_DOMAIN_INVALID)) return POWER_DOMAIN_PORT_DDI_IO_A; return domains->ddi_io + (int)(port - domains->port_start); @@ -2445,7 +2445,7 @@ intel_display_power_ddi_lanes_domain(struct drm_i915_private *i915, enum port po { const struct intel_ddi_port_domains *domains = intel_port_domains_for_port(i915, port); - if (drm_WARN_ON(&i915->drm, !domains) || domains->ddi_lanes == POWER_DOMAIN_INVALID) + if (drm_WARN_ON(&i915->drm, !domains || domains->ddi_lanes == POWER_DOMAIN_INVALID)) return POWER_DOMAIN_PORT_DDI_LANES_A; return domains->ddi_lanes + (int)(port - domains->port_start); @@ -2471,7 +2471,7 @@ intel_display_power_legacy_aux_domain(struct drm_i915_private *i915, enum aux_ch { const struct intel_ddi_port_domains *domains = intel_port_domains_for_aux_ch(i915, aux_ch); - if (drm_WARN_ON(&i915->drm, !domains) || domains->aux_legacy_usbc == POWER_DOMAIN_INVALID) + if (drm_WARN_ON(&i915->drm, !domains || domains->aux_legacy_usbc == POWER_DOMAIN_INVALID)) return POWER_DOMAIN_AUX_A; return domains->aux_legacy_usbc + (int)(aux_ch - domains->aux_ch_start); @@ -2482,7 +2482,7 @@ intel_display_power_tbt_aux_domain(struct drm_i915_private *i915, enum aux_ch au { const struct intel_ddi_port_domains *domains = intel_port_domains_for_aux_ch(i915, aux_ch); - if (drm_WARN_ON(&i915->drm, !domains) || domains->aux_tbt == POWER_DOMAIN_INVALID) + if (drm_WARN_ON(&i915->drm, !domains || domains->aux_tbt == POWER_DOMAIN_INVALID)) return POWER_DOMAIN_AUX_TBT1; return domains->aux_tbt + (int)(aux_ch - domains->aux_ch_start); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 3d4305eea1aa..0d6d640225fc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -612,6 +612,10 @@ static int i915_ttm_truncate(struct drm_i915_gem_object *obj) WARN_ON_ONCE(obj->mm.madv == I915_MADV_WILLNEED); + err = ttm_bo_wait(bo, true, false); + if (err) + return err; + err = i915_ttm_move_notify(bo); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index d0b03a928b9a..7caa3412a244 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -625,8 +625,13 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) return -EINTR; } - return timeout ? timeout : intel_uc_wait_for_idle(>->uc, - remaining_timeout); + if (timeout) + return timeout; + + if (remaining_timeout < 0) + remaining_timeout = 0; + + return intel_uc_wait_for_idle(>->uc, remaining_timeout); } int intel_gt_init(struct intel_gt *gt) @@ -1017,6 +1022,11 @@ static void mmio_invalidate_full(struct intel_gt *gt) if (!i915_mmio_reg_offset(rb.reg)) continue; + if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS)) + rb.bit = _MASKED_BIT_ENABLE(rb.bit); + intel_uncore_write_fw(uncore, rb.reg, rb.bit); awake |= engine->mask; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index edb881d75630..1dfd01668c79 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -199,7 +199,7 @@ out_active: spin_lock(&timelines->lock); if (remaining_timeout) *remaining_timeout = timeout; - return active_count ? timeout : 0; + return active_count ? timeout ?: -ETIME : 0; } static void retire_work_handler(struct work_struct *work) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 7a45e5360caf..714221f9a131 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -664,8 +664,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) return -ESRCH; } - kvm_get_kvm(vgpu->vfio_device.kvm); - if (__kvmgt_vgpu_exist(vgpu)) return -EEXIST; @@ -676,6 +674,7 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; + kvm_get_kvm(vgpu->vfio_device.kvm); kvm_page_track_register_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); @@ -715,15 +714,14 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); + kvm_put_kvm(vgpu->vfio_device.kvm); + kvmgt_protect_table_destroy(vgpu); gvt_cache_destroy(vgpu); intel_vgpu_release_msi_eventfd_ctx(vgpu); vgpu->attached = false; - - if (vgpu->vfio_device.kvm) - kvm_put_kvm(vgpu->vfio_device.kvm); } static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar) diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 2403ccd52c74..bba8cb6e8ae4 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -471,8 +471,7 @@ static int xelpdp_get_dram_info(struct drm_i915_private *i915) u32 val = intel_uncore_read(&i915->uncore, MTL_MEM_SS_INFO_GLOBAL); struct dram_info *dram_info = &i915->dram_info; - val = REG_FIELD_GET(MTL_DDR_TYPE_MASK, val); - switch (val) { + switch (REG_FIELD_GET(MTL_DDR_TYPE_MASK, val)) { case 0: dram_info->type = INTEL_DRAM_DDR4; break; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 089046fa21be..50fa3df0bc0c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -1085,21 +1085,21 @@ int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data, reset_ppn_array(pdesc->strsPPNs, ARRAY_SIZE(pdesc->strsPPNs)); /* Pin mksGuestStat user pages and store those in the instance descriptor */ - nr_pinned_stat = pin_user_pages(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat, NULL); + nr_pinned_stat = pin_user_pages_fast(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat); if (num_pages_stat != nr_pinned_stat) goto err_pin_stat; for (i = 0; i < num_pages_stat; ++i) pdesc->statPPNs[i] = page_to_pfn(pages_stat[i]); - nr_pinned_info = pin_user_pages(arg->info, num_pages_info, FOLL_LONGTERM, pages_info, NULL); + nr_pinned_info = pin_user_pages_fast(arg->info, num_pages_info, FOLL_LONGTERM, pages_info); if (num_pages_info != nr_pinned_info) goto err_pin_info; for (i = 0; i < num_pages_info; ++i) pdesc->infoPPNs[i] = page_to_pfn(pages_info[i]); - nr_pinned_strs = pin_user_pages(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs, NULL); + nr_pinned_strs = pin_user_pages_fast(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs); if (num_pages_strs != nr_pinned_strs) goto err_pin_strs; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index ecd3c2fc978b..9c79873f62f0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -949,6 +949,10 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv) struct drm_device *dev = &dev_priv->drm; int i, ret; + /* Screen objects won't work if GMR's aren't available */ + if (!dev_priv->has_gmr) + return -ENOSYS; + if (!(dev_priv->capabilities & SVGA_CAP_SCREEN_OBJECT_2)) { return -ENOSYS; } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 9c1d31f63f85..bd47628da6be 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1315,6 +1315,9 @@ static s32 snto32(__u32 value, unsigned n) if (!value || !n) return 0; + if (n > 32) + n = 32; + switch (n) { case 8: return ((__s8)value); case 16: return ((__s16)value); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index dad953f66996..8f58c3c1bec3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -274,6 +274,7 @@ #define USB_DEVICE_ID_CH_AXIS_295 0x001c #define USB_VENDOR_ID_CHERRY 0x046a +#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c #define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023 #define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027 @@ -917,6 +918,7 @@ #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd #define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb #define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0 +#define USB_DEVICE_ID_MS_MOUSE_0783 0x0783 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -1215,6 +1217,7 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K15A 0x6e21 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 +#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017 0x73f6 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 @@ -1381,6 +1384,7 @@ #define USB_VENDOR_ID_PRIMAX 0x0461 #define USB_DEVICE_ID_PRIMAX_MOUSE_4D22 0x4d22 +#define USB_DEVICE_ID_PRIMAX_MOUSE_4E2A 0x4e2a #define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05 #define USB_DEVICE_ID_PRIMAX_REZEL 0x4e72 #define USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D0F 0x4d0f diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 430fa4f52ed3..75ebfcf31889 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -121,6 +121,11 @@ static const struct hid_device_id ite_devices[] = { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003), .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index 5e6a0cef2a06..e3fcf1353fb3 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -872,6 +872,12 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att return -ENOMEM; i = strlen(lbuf); + + if (i == 0) { + kfree(lbuf); + return -EINVAL; + } + if (lbuf[i-1] == '\n') { if (i == 1) { kfree(lbuf); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 71a9c258a20b..8a2aac18dcc5 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4269,21 +4269,6 @@ static void hidpp_remove(struct hid_device *hdev) mutex_destroy(&hidpp->send_mutex); } -static const struct hid_device_id unhandled_hidpp_devices[] = { - /* Logitech Harmony Adapter for PS3, handled in hid-sony */ - { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_HARMONY_PS3) }, - /* Handled in hid-generic */ - { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD) }, - {} -}; - -static bool hidpp_match(struct hid_device *hdev, - bool ignore_special_driver) -{ - /* Refuse to handle devices handled by other HID drivers */ - return !hid_match_id(hdev, unhandled_hidpp_devices); -} - #define LDJ_DEVICE(product) \ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, \ USB_VENDOR_ID_LOGITECH, (product)) @@ -4367,9 +4352,15 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, - - { /* And try to enable HID++ for all the Logitech Bluetooth devices */ - HID_DEVICE(BUS_BLUETOOTH, HID_GROUP_ANY, USB_VENDOR_ID_LOGITECH, HID_ANY_ID) }, + { /* M-RCQ142 V470 Cordless Laser Mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb008) }, + { /* MX Master mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb012) }, + { /* MX Ergo trackball over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01d) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01e) }, + { /* MX Master 3 mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb023) }, {} }; @@ -4383,7 +4374,6 @@ static const struct hid_usage_id hidpp_usages[] = { static struct hid_driver hidpp_driver = { .name = "logitech-hidpp-device", .id_table = hidpp_devices, - .match = hidpp_match, .report_fixup = hidpp_report_fixup, .probe = hidpp_probe, .remove = hidpp_remove, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 50e1c717fc0a..0e9702c7f7d6 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -54,6 +54,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS }, @@ -122,6 +123,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_MOUSE_0783), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PIXART_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE3_COVER), HID_QUIRK_NO_INIT_REPORTS }, @@ -146,6 +148,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_MOUSE_4D22), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_MOUSE_4E2A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D0F), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D65), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4E22), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 0fbc408c2607..7fa6fe04f1b2 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -192,6 +192,7 @@ static int uclogic_probe(struct hid_device *hdev, * than the pen, so use QUIRK_MULTI_INPUT for all tablets. */ hdev->quirks |= HID_QUIRK_MULTI_INPUT; + hdev->quirks |= HID_QUIRK_HIDINPUT_FORCE; /* Allocate and assign driver data */ drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL); diff --git a/drivers/hid/hid-uclogic-rdesc.c b/drivers/hid/hid-uclogic-rdesc.c index 4bd54c4fb5b0..6b73eb0df6bd 100644 --- a/drivers/hid/hid-uclogic-rdesc.c +++ b/drivers/hid/hid-uclogic-rdesc.c @@ -1193,7 +1193,7 @@ __u8 *uclogic_rdesc_template_apply(const __u8 *template_ptr, p[sizeof(btn_head)] < param_num) { v = param_list[p[sizeof(btn_head)]]; put_unaligned((__u8)0x2A, p); /* Usage Maximum */ - put_unaligned_le16((__force u16)cpu_to_le16(v), p + 1); + put_unaligned((__force u16)cpu_to_le16(v), (s16 *)(p + 1)); p += sizeof(btn_head) + 1; } else { p++; diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig index 5273ee2bb134..d65abe65ce73 100644 --- a/drivers/hid/i2c-hid/Kconfig +++ b/drivers/hid/i2c-hid/Kconfig @@ -66,6 +66,6 @@ endmenu config I2C_HID_CORE tristate - default y if I2C_HID_ACPI=y || I2C_HID_OF=y || I2C_HID_OF_GOODIX=y - default m if I2C_HID_ACPI=m || I2C_HID_OF=m || I2C_HID_OF_GOODIX=m + default y if I2C_HID_ACPI=y || I2C_HID_OF=y || I2C_HID_OF_ELAN=y || I2C_HID_OF_GOODIX=y + default m if I2C_HID_ACPI=m || I2C_HID_OF=m || I2C_HID_OF_ELAN=m || I2C_HID_OF_GOODIX=m select HID diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 5b120402d405..cc23b90cae02 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -533,13 +533,17 @@ static void vmbus_add_channel_work(struct work_struct *work) * Add the new device to the bus. This will kick off device-driver * binding which eventually invokes the device driver's AddDevice() * method. + * + * If vmbus_device_register() fails, the 'device_obj' is freed in + * vmbus_device_release() as called by device_unregister() in the + * error path of vmbus_device_register(). In the outside error + * path, there's no need to free it. */ ret = vmbus_device_register(newchannel->device_obj); if (ret != 0) { pr_err("unable to add child device object (relid %d)\n", newchannel->offermsg.child_relid); - kfree(newchannel->device_obj); goto err_deq_chan; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8b2e413bf19c..e592c481f7ae 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2082,6 +2082,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) ret = device_register(&child_device_obj->device); if (ret) { pr_err("Unable to register child device\n"); + put_device(&child_device_obj->device); return ret; } diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 81e688975c6a..a901e4e33d81 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -938,6 +938,8 @@ static int asus_ec_probe(struct platform_device *pdev) ec_data->nr_sensors = hweight_long(ec_data->board_info->sensors); ec_data->sensors = devm_kcalloc(dev, ec_data->nr_sensors, sizeof(struct ec_sensor), GFP_KERNEL); + if (!ec_data->sensors) + return -ENOMEM; status = setup_lock_data(dev); if (status) { diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 8bf32c6c85d9..9bee4d33fbdf 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -242,10 +242,13 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) */ if (host_bridge && host_bridge->vendor == PCI_VENDOR_ID_INTEL) { for (i = 0; i < ARRAY_SIZE(tjmax_pci_table); i++) { - if (host_bridge->device == tjmax_pci_table[i].device) + if (host_bridge->device == tjmax_pci_table[i].device) { + pci_dev_put(host_bridge); return tjmax_pci_table[i].tjmax; + } } } + pci_dev_put(host_bridge); for (i = 0; i < ARRAY_SIZE(tjmax_table); i++) { if (strstr(c->x86_model_id, tjmax_table[i].id)) @@ -533,6 +536,10 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) { struct temp_data *tdata = pdata->core_data[indx]; + /* if we errored on add then this is already gone */ + if (!tdata) + return; + /* Remove the sysfs attributes */ sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group); diff --git a/drivers/hwmon/i5500_temp.c b/drivers/hwmon/i5500_temp.c index 05f68e9c9477..23b9f94fe0a9 100644 --- a/drivers/hwmon/i5500_temp.c +++ b/drivers/hwmon/i5500_temp.c @@ -117,7 +117,7 @@ static int i5500_temp_probe(struct pci_dev *pdev, u32 tstimer; s8 tsfsc; - err = pci_enable_device(pdev); + err = pcim_enable_device(pdev); if (err) { dev_err(&pdev->dev, "Failed to enable device\n"); return err; diff --git a/drivers/hwmon/ibmpex.c b/drivers/hwmon/ibmpex.c index f6ec165c0fa8..1837cccd993c 100644 --- a/drivers/hwmon/ibmpex.c +++ b/drivers/hwmon/ibmpex.c @@ -502,6 +502,7 @@ static void ibmpex_register_bmc(int iface, struct device *dev) return; out_register: + list_del(&data->list); hwmon_device_unregister(data->hwmon_dev); out_user: ipmi_destroy_user(data->user); diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c index 2a57f4b60c29..e06186986444 100644 --- a/drivers/hwmon/ina3221.c +++ b/drivers/hwmon/ina3221.c @@ -228,7 +228,7 @@ static int ina3221_read_value(struct ina3221_data *ina, unsigned int reg, * Shunt Voltage Sum register has 14-bit value with 1-bit shift * Other Shunt Voltage registers have 12 bits with 3-bit shift */ - if (reg == INA3221_SHUNT_SUM) + if (reg == INA3221_SHUNT_SUM || reg == INA3221_CRIT_SUM) *val = sign_extend32(regval >> 1, 14); else *val = sign_extend32(regval >> 3, 12); @@ -465,7 +465,7 @@ static int ina3221_write_curr(struct device *dev, u32 attr, * SHUNT_SUM: (1 / 40uV) << 1 = 1 / 20uV * SHUNT[1-3]: (1 / 40uV) << 3 = 1 / 5uV */ - if (reg == INA3221_SHUNT_SUM) + if (reg == INA3221_SHUNT_SUM || reg == INA3221_CRIT_SUM) regval = DIV_ROUND_CLOSEST(voltage_uv, 20) & 0xfffe; else regval = DIV_ROUND_CLOSEST(voltage_uv, 5) & 0xfff8; diff --git a/drivers/hwmon/ltc2947-core.c b/drivers/hwmon/ltc2947-core.c index 7404e974762f..2dbbbac9de09 100644 --- a/drivers/hwmon/ltc2947-core.c +++ b/drivers/hwmon/ltc2947-core.c @@ -396,7 +396,7 @@ static int ltc2947_read_temp(struct device *dev, const u32 attr, long *val, return ret; /* in milidegrees celcius, temp is given by: */ - *val = (__val * 204) + 550; + *val = (__val * 204) + 5500; return 0; } diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index fe0cd205502d..f58943cb1341 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -852,7 +852,8 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, CDNS_I2C_POLL_US, CDNS_I2C_TIMEOUT_US); if (ret) { ret = -EAGAIN; - i2c_recover_bus(adap); + if (id->adap.bus_recovery_info) + i2c_recover_bus(adap); goto out; } @@ -1263,8 +1264,13 @@ static int cdns_i2c_probe(struct platform_device *pdev) id->rinfo.pinctrl = devm_pinctrl_get(&pdev->dev); if (IS_ERR(id->rinfo.pinctrl)) { + int err = PTR_ERR(id->rinfo.pinctrl); + dev_info(&pdev->dev, "can't get pinctrl, bus recovery not supported\n"); - return PTR_ERR(id->rinfo.pinctrl); + if (err != -ENODEV) + return err; + } else { + id->adap.bus_recovery_info = &id->rinfo; } id->membase = devm_platform_get_and_ioremap_resource(pdev, 0, &r_mem); @@ -1283,7 +1289,6 @@ static int cdns_i2c_probe(struct platform_device *pdev) id->adap.retries = 3; /* Default retry value. */ id->adap.algo_data = id; id->adap.dev.parent = &pdev->dev; - id->adap.bus_recovery_info = &id->rinfo; init_completion(&id->xfer_done); snprintf(id->adap.name, sizeof(id->adap.name), "Cadence I2C at %08lx", (unsigned long)r_mem->start); diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 3082183bd66a..fc70920c4dda 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1132,7 +1132,8 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, int i, result; unsigned int temp; int block_data = msgs->flags & I2C_M_RECV_LEN; - int use_dma = i2c_imx->dma && msgs->len >= DMA_THRESHOLD && !block_data; + int use_dma = i2c_imx->dma && msgs->flags & I2C_M_DMA_SAFE && + msgs->len >= DMA_THRESHOLD && !block_data; dev_dbg(&i2c_imx->adapter.dev, "<%s> write slave address: addr=0x%x\n", @@ -1298,7 +1299,8 @@ static int i2c_imx_xfer_common(struct i2c_adapter *adapter, result = i2c_imx_read(i2c_imx, &msgs[i], is_lastmsg, atomic); } else { if (!atomic && - i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD) + i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD && + msgs[i].flags & I2C_M_DMA_SAFE) result = i2c_imx_dma_write(i2c_imx, &msgs[i]); else result = i2c_imx_write(i2c_imx, &msgs[i], atomic); diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 0c365b57d957..83457359ec45 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -2393,8 +2393,17 @@ static struct platform_driver npcm_i2c_bus_driver = { static int __init npcm_i2c_init(void) { + int ret; + npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL); - return platform_driver_register(&npcm_i2c_bus_driver); + + ret = platform_driver_register(&npcm_i2c_bus_driver); + if (ret) { + debugfs_remove_recursive(npcm_i2c_debugfs_dir); + return ret; + } + + return 0; } module_init(npcm_i2c_init); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 84a77512614d..8fce98bb77ff 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -626,7 +626,6 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i dev_err(gi2c->se.dev, "I2C timeout gpi flags:%d addr:0x%x\n", gi2c->cur->flags, gi2c->cur->addr); gi2c->err = -ETIMEDOUT; - goto err; } if (gi2c->err) { diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index b4edf10e8fd0..7539b0740351 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -467,6 +467,7 @@ static int i2c_device_probe(struct device *dev) { struct i2c_client *client = i2c_verify_client(dev); struct i2c_driver *driver; + bool do_power_on; int status; if (!client) @@ -545,8 +546,8 @@ static int i2c_device_probe(struct device *dev) if (status < 0) goto err_clear_wakeup_irq; - status = dev_pm_domain_attach(&client->dev, - !i2c_acpi_waive_d0_probe(dev)); + do_power_on = !i2c_acpi_waive_d0_probe(dev); + status = dev_pm_domain_attach(&client->dev, do_power_on); if (status) goto err_clear_wakeup_irq; @@ -585,7 +586,7 @@ static int i2c_device_probe(struct device *dev) err_release_driver_resources: devres_release_group(&client->dev, client->devres_group_id); err_detach_pm_domain: - dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); + dev_pm_domain_detach(&client->dev, do_power_on); err_clear_wakeup_irq: dev_pm_clear_wake_irq(&client->dev); device_init_wakeup(&client->dev, false); @@ -610,7 +611,7 @@ static void i2c_device_remove(struct device *dev) devres_release_group(&client->dev, client->devres_group_id); - dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); + dev_pm_domain_detach(&client->dev, true); dev_pm_clear_wake_irq(&client->dev); device_init_wakeup(&client->dev, false); diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c index 490c342ef72a..6e4d10a7cd32 100644 --- a/drivers/iio/accel/bma400_core.c +++ b/drivers/iio/accel/bma400_core.c @@ -805,8 +805,10 @@ static int bma400_get_steps_reg(struct bma400_data *data, int *val) ret = regmap_bulk_read(data->regmap, BMA400_STEP_CNT0_REG, steps_raw, BMA400_STEP_RAW_LEN); - if (ret) + if (ret) { + kfree(steps_raw); return ret; + } *val = get_unaligned_le24(steps_raw); kfree(steps_raw); return IIO_VAL_INT; diff --git a/drivers/iio/adc/aspeed_adc.c b/drivers/iio/adc/aspeed_adc.c index 9341e0e0eb55..998e8bcc06e1 100644 --- a/drivers/iio/adc/aspeed_adc.c +++ b/drivers/iio/adc/aspeed_adc.c @@ -202,6 +202,8 @@ static int aspeed_adc_set_trim_data(struct iio_dev *indio_dev) ((scu_otp) & (data->model_data->trim_locate->field)) >> __ffs(data->model_data->trim_locate->field); + if (!trimming_val) + trimming_val = 0x8; } dev_dbg(data->dev, "trimming val = %d, offset = %08x, fields = %08x\n", @@ -563,12 +565,9 @@ static int aspeed_adc_probe(struct platform_device *pdev) if (ret) return ret; - if (of_find_property(data->dev->of_node, "aspeed,trim-data-valid", - NULL)) { - ret = aspeed_adc_set_trim_data(indio_dev); - if (ret) - return ret; - } + ret = aspeed_adc_set_trim_data(indio_dev); + if (ret) + return ret; if (of_find_property(data->dev->of_node, "aspeed,battery-sensing", NULL)) { diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index 3bb4028c5d74..df3bc5c3d378 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -245,14 +245,14 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct afe4403_data *afe = iio_priv(indio_dev); - unsigned int reg = afe4403_channel_values[chan->address]; - unsigned int field = afe4403_channel_leds[chan->address]; + unsigned int reg, field; int ret; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_RAW: + reg = afe4403_channel_values[chan->address]; ret = afe4403_read(afe, reg, val); if (ret) return ret; @@ -262,6 +262,7 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + field = afe4403_channel_leds[chan->address]; ret = regmap_field_read(afe->fields[field], val); if (ret) return ret; diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c index 8fca787b2524..836da31b7e30 100644 --- a/drivers/iio/health/afe4404.c +++ b/drivers/iio/health/afe4404.c @@ -250,20 +250,20 @@ static int afe4404_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct afe4404_data *afe = iio_priv(indio_dev); - unsigned int value_reg = afe4404_channel_values[chan->address]; - unsigned int led_field = afe4404_channel_leds[chan->address]; - unsigned int offdac_field = afe4404_channel_offdacs[chan->address]; + unsigned int value_reg, led_field, offdac_field; int ret; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_RAW: + value_reg = afe4404_channel_values[chan->address]; ret = regmap_read(afe->regmap, value_reg, val); if (ret) return ret; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: + offdac_field = afe4404_channel_offdacs[chan->address]; ret = regmap_field_read(afe->fields[offdac_field], val); if (ret) return ret; @@ -273,6 +273,7 @@ static int afe4404_read_raw(struct iio_dev *indio_dev, case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + led_field = afe4404_channel_leds[chan->address]; ret = regmap_field_read(afe->fields[led_field], val); if (ret) return ret; @@ -295,19 +296,20 @@ static int afe4404_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct afe4404_data *afe = iio_priv(indio_dev); - unsigned int led_field = afe4404_channel_leds[chan->address]; - unsigned int offdac_field = afe4404_channel_offdacs[chan->address]; + unsigned int led_field, offdac_field; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_OFFSET: + offdac_field = afe4404_channel_offdacs[chan->address]; return regmap_field_write(afe->fields[offdac_field], val); } break; case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + led_field = afe4404_channel_leds[chan->address]; return regmap_field_write(afe->fields[led_field], val); } break; diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c index 994f03a71520..d86a3305d9e8 100644 --- a/drivers/iio/industrialio-sw-trigger.c +++ b/drivers/iio/industrialio-sw-trigger.c @@ -58,8 +58,12 @@ int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t) t->group = configfs_register_default_group(iio_triggers_group, t->name, &iio_trigger_type_group_type); - if (IS_ERR(t->group)) + if (IS_ERR(t->group)) { + mutex_lock(&iio_trigger_types_lock); + list_del(&t->list); + mutex_unlock(&iio_trigger_types_lock); ret = PTR_ERR(t->group); + } return ret; } diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 7cf6e8490123..0d4447df7200 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -293,6 +293,8 @@ config RPR0521 tristate "ROHM RPR0521 ALS and proximity sensor driver" depends on I2C select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say Y here if you want to build support for ROHM's RPR0521 ambient light and proximity sensor device. diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index b62c139baf41..38d4c7644bef 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -54,9 +54,6 @@ #define APDS9960_REG_CONTROL_PGAIN_MASK_SHIFT 2 #define APDS9960_REG_CONFIG_2 0x90 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK 0x60 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT 5 - #define APDS9960_REG_ID 0x92 #define APDS9960_REG_STATUS 0x93 @@ -77,6 +74,9 @@ #define APDS9960_REG_GCONF_1_GFIFO_THRES_MASK_SHIFT 6 #define APDS9960_REG_GCONF_2 0xa3 +#define APDS9960_REG_GCONF_2_GGAIN_MASK 0x60 +#define APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT 5 + #define APDS9960_REG_GOFFSET_U 0xa4 #define APDS9960_REG_GOFFSET_D 0xa5 #define APDS9960_REG_GPULSE 0xa6 @@ -396,9 +396,9 @@ static int apds9960_set_pxs_gain(struct apds9960_data *data, int val) } ret = regmap_update_bits(data->regmap, - APDS9960_REG_CONFIG_2, - APDS9960_REG_CONFIG_2_GGAIN_MASK, - idx << APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT); + APDS9960_REG_GCONF_2, + APDS9960_REG_GCONF_2_GGAIN_MASK, + idx << APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT); if (!ret) data->pxs_gain = idx; mutex_unlock(&data->lock); diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c index b86de1312512..84b87526b7ba 100644 --- a/drivers/input/joystick/iforce/iforce-main.c +++ b/drivers/input/joystick/iforce/iforce-main.c @@ -273,22 +273,22 @@ int iforce_init_device(struct device *parent, u16 bustype, * Get device info. */ - if (!iforce_get_id_packet(iforce, 'M', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'M', buf, &len) && len >= 3) input_dev->id.vendor = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet M\n"); - if (!iforce_get_id_packet(iforce, 'P', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'P', buf, &len) && len >= 3) input_dev->id.product = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet P\n"); - if (!iforce_get_id_packet(iforce, 'B', buf, &len) || len < 3) + if (!iforce_get_id_packet(iforce, 'B', buf, &len) && len >= 3) iforce->device_memory.end = get_unaligned_le16(buf + 1); else dev_warn(&iforce->dev->dev, "Device does not respond to id packet B\n"); - if (!iforce_get_id_packet(iforce, 'N', buf, &len) || len < 2) + if (!iforce_get_id_packet(iforce, 'N', buf, &len) && len >= 2) ff_effects = buf[1]; else dev_warn(&iforce->dev->dev, "Device does not respond to id packet N\n"); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 480476121c01..09489380afda 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -18,6 +18,10 @@ #include <linux/gpio.h> #include <linux/platform_device.h> +static bool use_low_level_irq; +module_param(use_low_level_irq, bool, 0444); +MODULE_PARM_DESC(use_low_level_irq, "Use low-level triggered IRQ instead of edge triggered"); + struct soc_button_info { const char *name; int acpi_index; @@ -74,6 +78,13 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { }, }, { + /* Acer Switch V 10 SW5-017, same issue as Acer Switch 10 SW5-012. */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + }, + { /* * Acer One S1003. _LID method messes with power-button GPIO * IRQ settings, leading to a non working power-button. @@ -164,7 +175,8 @@ soc_button_device_create(struct platform_device *pdev, } /* See dmi_use_low_level_irq[] comment */ - if (!autorepeat && dmi_check_system(dmi_use_low_level_irq)) { + if (!autorepeat && (use_low_level_irq || + dmi_check_system(dmi_use_low_level_irq))) { irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW); gpio_keys[n_buttons].irq = irq; gpio_keys[n_buttons].gpio = -ENOENT; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index fa021af8506e..b0f776448a1c 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -192,6 +192,7 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ + "SYN3286", /* HP Laptop 15-da3001TU */ NULL }; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 0778dc03cd9e..46f8a694291e 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -115,18 +115,18 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER) }, { - /* ASUS ZenBook UX425UA */ + /* ASUS ZenBook UX425UA/QA */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425"), }, .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) }, { - /* ASUS ZenBook UM325UA */ + /* ASUS ZenBook UM325UA/QA */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325"), }, .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) }, diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index f9486495baef..6dac7c1853a5 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1543,8 +1543,6 @@ static int i8042_probe(struct platform_device *dev) { int error; - i8042_platform_device = dev; - if (i8042_reset == I8042_RESET_ALWAYS) { error = i8042_controller_selftest(); if (error) @@ -1582,7 +1580,6 @@ static int i8042_probe(struct platform_device *dev) i8042_free_aux_ports(); /* in case KBD failed but AUX not */ i8042_free_irqs(); i8042_controller_reset(false); - i8042_platform_device = NULL; return error; } @@ -1592,7 +1589,6 @@ static int i8042_remove(struct platform_device *dev) i8042_unregister_ports(); i8042_free_irqs(); i8042_controller_reset(false); - i8042_platform_device = NULL; return 0; } diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index a33cc7950cf5..c281e49826c2 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -1158,6 +1158,7 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) input_set_abs_params(ts->input_dev, ABS_MT_WIDTH_MAJOR, 0, 255, 0, 0); input_set_abs_params(ts->input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); +retry_read_config: /* Read configuration and apply touchscreen parameters */ goodix_read_config(ts); @@ -1165,6 +1166,16 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) touchscreen_parse_properties(ts->input_dev, true, &ts->prop); if (!ts->prop.max_x || !ts->prop.max_y || !ts->max_touch_num) { + if (!ts->reset_controller_at_probe && + ts->irq_pin_access_method != IRQ_PIN_ACCESS_NONE) { + dev_info(&ts->client->dev, "Config not set, resetting controller\n"); + /* Retry after a controller reset */ + ts->reset_controller_at_probe = true; + error = goodix_reset(ts); + if (error) + return error; + goto retry_read_config; + } dev_err(&ts->client->dev, "Invalid config (%d, %d, %d), using defaults\n", ts->prop.max_x, ts->prop.max_y, ts->max_touch_num); diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index 3a4952935366..3d9c5758d8a4 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -211,12 +211,14 @@ static int raydium_i2c_send(struct i2c_client *client, error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer)); if (likely(!error)) - return 0; + goto out; msleep(RM_RETRY_DELAY_MS); } while (++tries < RM_MAX_RETRIES); dev_err(&client->dev, "%s failed: %d\n", __func__, error); +out: + kfree(tx_buf); return error; } diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 5a8f780e7ffd..bc94059a5b87 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -820,6 +820,7 @@ int __init dmar_dev_scope_init(void) info = dmar_alloc_pci_notify_info(dev, BUS_NOTIFY_ADD_DEVICE); if (!info) { + pci_dev_put(dev); return dmar_dev_scope_status; } else { dmar_pci_bus_add_dev(info); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 48cdcd0a5cf3..644ca49e8cf8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -959,11 +959,9 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; - if (domain_use_first_level(domain)) { - pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; - if (iommu_is_dma_domain(&domain->domain)) - pteval |= DMA_FL_PTE_ACCESS; - } + if (domain_use_first_level(domain)) + pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS; + if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -1398,6 +1396,24 @@ static void domain_update_iotlb(struct dmar_domain *domain) spin_unlock_irqrestore(&domain->lock, flags); } +/* + * The extra devTLB flush quirk impacts those QAT devices with PCI device + * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device() + * check because it applies only to the built-in QAT devices and it doesn't + * grant additional privileges. + */ +#define BUGGY_QAT_DEVID_MASK 0x4940 +static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev) +{ + if (pdev->vendor != PCI_VENDOR_ID_INTEL) + return false; + + if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK) + return false; + + return true; +} + static void iommu_enable_pci_caps(struct device_domain_info *info) { struct pci_dev *pdev; @@ -1480,6 +1496,7 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info, qdep = info->ats_qdep; qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, qdep, addr, mask); + quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep); } static void iommu_flush_dev_iotlb(struct dmar_domain *domain, @@ -3856,8 +3873,10 @@ static inline bool has_external_pci(void) struct pci_dev *pdev = NULL; for_each_pci_dev(pdev) - if (pdev->external_facing) + if (pdev->external_facing) { + pci_dev_put(pdev); return true; + } return false; } @@ -4492,9 +4511,10 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) if (dev_is_pci(dev)) { if (ecap_dev_iotlb_support(iommu->ecap) && pci_ats_supported(pdev) && - dmar_ats_supported(pdev, iommu)) + dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; - + info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { int features = pci_pasid_features(pdev); @@ -4933,3 +4953,48 @@ static void __init check_tylersburg_isoch(void) pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n", vtisochctrl); } + +/* + * Here we deal with a device TLB defect where device may inadvertently issue ATS + * invalidation completion before posted writes initiated with translated address + * that utilized translations matching the invalidation address range, violating + * the invalidation completion ordering. + * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is + * vulnerable to this defect. In other words, any dTLB invalidation initiated not + * under the control of the trusted/privileged host device driver must use this + * quirk. + * Device TLBs are invalidated under the following six conditions: + * 1. Device driver does DMA API unmap IOVA + * 2. Device driver unbind a PASID from a process, sva_unbind_device() + * 3. PASID is torn down, after PASID cache is flushed. e.g. process + * exit_mmap() due to crash + * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where + * VM has to free pages that were unmapped + * 5. Userspace driver unmaps a DMA buffer + * 6. Cache invalidation in vSVA usage (upcoming) + * + * For #1 and #2, device drivers are responsible for stopping DMA traffic + * before unmap/unbind. For #3, iommu driver gets mmu_notifier to + * invalidate TLB the same way as normal user unmap which will use this quirk. + * The dTLB invalidation after PASID cache flush does not need this quirk. + * + * As a reminder, #6 will *NEED* this quirk as we enable nested translation. + */ +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long mask, + u32 pasid, u16 qdep) +{ + u16 sid; + + if (likely(!info->dtlb_extra_inval)) + return; + + sid = PCI_DEVID(info->bus, info->devfn); + if (pasid == PASID_RID2PASID) { + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, address, mask); + } else { + qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid, + pasid, qdep, address, mask); + } +} diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 92023dff9513..db9df7c3790c 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -623,6 +623,7 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; + u8 dtlb_extra_inval:1; /* Quirk for devices need extra flush */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ @@ -728,6 +729,9 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, unsigned int size_order); +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long pages, + u32 pasid, u16 qdep); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, u32 pasid); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index c30ddac40ee5..e13d7e5273e1 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -642,7 +642,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). */ - if (pasid != PASID_RID2PASID) + if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -685,7 +685,8 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, * We should set SRE bit as well since the addresses are expected * to be GPAs. */ - pasid_set_sre(pte); + if (ecap_srs(iommu->ecap)) + pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7d08eb034f2d..03b25358946c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -184,10 +184,13 @@ static void __flush_svm_range_dev(struct intel_svm *svm, return; qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih); - if (info->ats_enabled) + if (info->ats_enabled) { qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid, svm->pasid, sdev->qdep, address, order_base_2(pages)); + quirk_extra_dev_tlb_flush(info, address, order_base_2(pages), + svm->pasid, sdev->qdep); + } } static void intel_flush_svm_range_dev(struct intel_svm *svm, @@ -745,12 +748,16 @@ bad_req: * If prq is to be handled outside iommu driver via receiver of * the fault notifiers, we skip the page response here. */ - if (!pdev || intel_svm_prq_report(iommu, &pdev->dev, req)) - handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + if (!pdev) + goto bad_req; - trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, - req->priv_data[0], req->priv_data[1], - iommu->prq_seq_number++); + if (intel_svm_prq_report(iommu, &pdev->dev, req)) + handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + else + trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, + req->priv_data[0], req->priv_data[1], + iommu->prq_seq_number++); + pci_dev_put(pdev); prq_advance: head = (head + sizeof(*req)) & PRQ_RING_MASK; } diff --git a/drivers/media/common/videobuf2/frame_vector.c b/drivers/media/common/videobuf2/frame_vector.c index 542dde9d2609..144027035892 100644 --- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -35,11 +35,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, struct frame_vector *vec) { - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - int ret_pin_user_pages_fast = 0; - int ret = 0; - int err; + int ret; if (nr_frames == 0) return 0; @@ -52,57 +48,17 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, ret = pin_user_pages_fast(start, nr_frames, FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, (struct page **)(vec->ptrs)); - if (ret > 0) { - vec->got_ref = true; - vec->is_pfns = false; - goto out_unlocked; - } - ret_pin_user_pages_fast = ret; - - mmap_read_lock(mm); - vec->got_ref = false; - vec->is_pfns = true; - ret = 0; - do { - unsigned long *nums = frame_vector_pfns(vec); - - vma = vma_lookup(mm, start); - if (!vma) - break; - - while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { - err = follow_pfn(vma, start, &nums[ret]); - if (err) { - if (ret) - goto out; - // If follow_pfn() returns -EINVAL, then this - // is not an IO mapping or a raw PFN mapping. - // In that case, return the original error from - // pin_user_pages_fast(). Otherwise this - // function would return -EINVAL when - // pin_user_pages_fast() returned -ENOMEM, - // which makes debugging hard. - if (err == -EINVAL && ret_pin_user_pages_fast) - ret = ret_pin_user_pages_fast; - else - ret = err; - goto out; - } - start += PAGE_SIZE; - ret++; - } - /* Bail out if VMA doesn't completely cover the tail page. */ - if (start < vma->vm_end) - break; - } while (ret < nr_frames); -out: - mmap_read_unlock(mm); -out_unlocked: - if (!ret) - ret = -EFAULT; - if (ret > 0) - vec->nr_frames = ret; - return ret; + vec->got_ref = true; + vec->is_pfns = false; + vec->nr_frames = ret; + + if (likely(ret > 0)) + return ret; + + /* This used to (racily) return non-refcounted pfns. Let people know */ + WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); + vec->nr_frames = 0; + return ret ? ret : -EFAULT; } EXPORT_SYMBOL(get_vaddr_frames); diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index ab9697f3b5f1..92efc4676df6 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -813,7 +813,13 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, num_buffers = max_t(unsigned int, *count, q->min_buffers_needed); num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory value + * in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); set_queue_coherency(q, non_coherent_mem); /* @@ -823,22 +829,27 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Check that driver has set sane values */ - if (WARN_ON(!num_planes)) - return -EINVAL; + if (WARN_ON(!num_planes)) { + ret = -EINVAL; + goto error; + } for (i = 0; i < num_planes; i++) - if (WARN_ON(!plane_sizes[i])) - return -EINVAL; + if (WARN_ON(!plane_sizes[i])) { + ret = -EINVAL; + goto error; + } /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -879,7 +890,8 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -895,6 +907,12 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, q->waiting_for_buffers = !q->is_output; return 0; + +error: + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_core_reqbufs); @@ -906,6 +924,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; + bool no_previous_buffers = !q->num_buffers; int ret; if (q->num_buffers == VB2_MAX_FRAME) { @@ -913,13 +932,19 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, return -ENOBUFS; } - if (!q->num_buffers) { + if (no_previous_buffers) { if (q->waiting_in_dqbuf && *count) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory + * value in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); q->waiting_for_buffers = !q->is_output; set_queue_coherency(q, non_coherent_mem); } else { @@ -945,14 +970,15 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -983,7 +1009,8 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -998,6 +1025,14 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, *count = allocated_buffers; return 0; + +error: + if (no_previous_buffers) { + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + } + return ret; } EXPORT_SYMBOL_GPL(vb2_core_create_bufs); @@ -2165,6 +2200,22 @@ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long off, unsigned int buffer, plane; /* + * Sanity checks to ensure the lock is held, MEMORY_MMAP is + * used and fileio isn't active. + */ + lockdep_assert_held(&q->mmap_lock); + + if (q->memory != VB2_MEMORY_MMAP) { + dprintk(q, 1, "queue is not currently set up for mmap\n"); + return -EINVAL; + } + + if (vb2_fileio_is_active(q)) { + dprintk(q, 1, "file io in progress\n"); + return -EBUSY; + } + + /* * Go over all buffers and their planes, comparing the given offset * with an offset assigned to each plane. If a match is found, * return its buffer and plane numbers. @@ -2265,11 +2316,6 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) int ret; unsigned long length; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } - /* * Check memory area access mode. */ @@ -2291,14 +2337,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) mutex_lock(&q->mmap_lock); - if (vb2_fileio_is_active(q)) { - dprintk(q, 1, "mmap: file io in progress\n"); - ret = -EBUSY; - goto unlock; - } - /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) @@ -2351,22 +2392,25 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q, void *vaddr; int ret; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } + mutex_lock(&q->mmap_lock); /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock; vb = q->bufs[buffer]; vaddr = vb2_plane_vaddr(vb, plane); + mutex_unlock(&q->mmap_lock); return vaddr ? (unsigned long)vaddr : -EINVAL; + +unlock: + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_get_unmapped_area); #endif diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index 003c32fed3f7..942d0005c55e 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -145,6 +145,8 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, const struct v4l2_bt_timings *bt = &t->bt; const struct v4l2_bt_timings_cap *cap = &dvcap->bt; u32 caps = cap->capabilities; + const u32 max_vert = 10240; + u32 max_hor = 3 * bt->width; if (t->type != V4L2_DV_BT_656_1120) return false; @@ -166,14 +168,20 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, if (!bt->interlaced && (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch)) return false; - if (bt->hfrontporch > 2 * bt->width || - bt->hsync > 1024 || bt->hbackporch > 1024) + /* + * Some video receivers cannot properly separate the frontporch, + * backporch and sync values, and instead they only have the total + * blanking. That can be assigned to any of these three fields. + * So just check that none of these are way out of range. + */ + if (bt->hfrontporch > max_hor || + bt->hsync > max_hor || bt->hbackporch > max_hor) return false; - if (bt->vfrontporch > 4096 || - bt->vsync > 128 || bt->vbackporch > 4096) + if (bt->vfrontporch > max_vert || + bt->vsync > max_vert || bt->vbackporch > max_vert) return false; - if (bt->interlaced && (bt->il_vfrontporch > 4096 || - bt->il_vsync > 128 || bt->il_vbackporch > 4096)) + if (bt->interlaced && (bt->il_vfrontporch > max_vert || + bt->il_vsync > max_vert || bt->il_vbackporch > max_vert)) return false; return fnc == NULL || fnc(t, fnc_handle); } diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index c5de202f530a..de1cc9e1ae57 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1484,6 +1484,11 @@ void mmc_init_erase(struct mmc_card *card) card->pref_erase = 0; } +static bool is_trim_arg(unsigned int arg) +{ + return (arg & MMC_TRIM_OR_DISCARD_ARGS) && arg != MMC_DISCARD_ARG; +} + static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card, unsigned int arg, unsigned int qty) { @@ -1766,7 +1771,7 @@ int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr, !(card->ext_csd.sec_feature_support & EXT_CSD_SEC_ER_EN)) return -EOPNOTSUPP; - if (mmc_card_mmc(card) && (arg & MMC_TRIM_ARGS) && + if (mmc_card_mmc(card) && is_trim_arg(arg) && !(card->ext_csd.sec_feature_support & EXT_CSD_SEC_GB_CL_EN)) return -EOPNOTSUPP; @@ -1796,7 +1801,7 @@ int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr, * identified by the card->eg_boundary flag. */ rem = card->erase_size - (from % card->erase_size); - if ((arg & MMC_TRIM_ARGS) && (card->eg_boundary) && (nr > rem)) { + if ((arg & MMC_TRIM_OR_DISCARD_ARGS) && card->eg_boundary && nr > rem) { err = mmc_do_erase(card, from, from + rem - 1, arg); from += rem; if ((err) || (to <= from)) diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index 8d9bceeff986..155ce2bdfe62 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -3179,7 +3179,8 @@ static int __mmc_test_register_dbgfs_file(struct mmc_card *card, struct mmc_test_dbgfs_file *df; if (card->debugfs_root) - debugfs_create_file(name, mode, card->debugfs_root, card, fops); + file = debugfs_create_file(name, mode, card->debugfs_root, + card, fops); df = kmalloc(sizeof(*df), GFP_KERNEL); if (!df) { diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index df941438aef5..26bc59b5a7cc 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2588,13 +2588,11 @@ static int msdc_of_clock_parse(struct platform_device *pdev, return PTR_ERR(host->src_clk_cg); } - host->sys_clk_cg = devm_clk_get_optional(&pdev->dev, "sys_cg"); + /* If present, always enable for this clock gate */ + host->sys_clk_cg = devm_clk_get_optional_enabled(&pdev->dev, "sys_cg"); if (IS_ERR(host->sys_clk_cg)) host->sys_clk_cg = NULL; - /* If present, always enable for this clock gate */ - clk_prepare_enable(host->sys_clk_cg); - host->bulk_clks[0].id = "pclk_cg"; host->bulk_clks[1].id = "axi_cg"; host->bulk_clks[2].id = "ahb_cg"; diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 31ea0a2fce35..ffeb5759830f 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1512,7 +1512,7 @@ static void esdhc_cqe_enable(struct mmc_host *mmc) * system resume back. */ cqhci_writel(cq_host, 0, CQHCI_CTL); - if (cqhci_readl(cq_host, CQHCI_CTL) && CQHCI_HALT) + if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT) dev_err(mmc_dev(host->mmc), "failed to exit halt state when enable CQE\n"); diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index b92a408f138d..bec3f9e3cd3f 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -470,7 +470,7 @@ static int sdhci_sprd_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) } if (IS_ERR(sprd_host->pinctrl)) - return 0; + goto reset; switch (ios->signal_voltage) { case MMC_SIGNAL_VOLTAGE_180: @@ -498,6 +498,8 @@ static int sdhci_sprd_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) /* Wait for 300 ~ 500 us for pin state stable */ usleep_range(300, 500); + +reset: sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); return 0; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index fef03de85b99..c7ad32a75b57 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -373,6 +373,7 @@ static void sdhci_init(struct sdhci_host *host, int soft) if (soft) { /* force clock reconfiguration */ host->clock = 0; + host->reinit_uhs = true; mmc->ops->set_ios(mmc, &mmc->ios); } } @@ -2293,11 +2294,46 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing) } EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling); +static bool sdhci_timing_has_preset(unsigned char timing) +{ + switch (timing) { + case MMC_TIMING_UHS_SDR12: + case MMC_TIMING_UHS_SDR25: + case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_SDR104: + case MMC_TIMING_UHS_DDR50: + case MMC_TIMING_MMC_DDR52: + return true; + }; + return false; +} + +static bool sdhci_preset_needed(struct sdhci_host *host, unsigned char timing) +{ + return !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN) && + sdhci_timing_has_preset(timing); +} + +static bool sdhci_presetable_values_change(struct sdhci_host *host, struct mmc_ios *ios) +{ + /* + * Preset Values are: Driver Strength, Clock Generator and SDCLK/RCLK + * Frequency. Check if preset values need to be enabled, or the Driver + * Strength needs updating. Note, clock changes are handled separately. + */ + return !host->preset_enabled && + (sdhci_preset_needed(host, ios->timing) || host->drv_type != ios->drv_type); +} + void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); + bool reinit_uhs = host->reinit_uhs; + bool turning_on_clk = false; u8 ctrl; + host->reinit_uhs = false; + if (ios->power_mode == MMC_POWER_UNDEFINED) return; @@ -2323,6 +2359,8 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) sdhci_enable_preset_value(host, false); if (!ios->clock || ios->clock != host->clock) { + turning_on_clk = ios->clock && !host->clock; + host->ops->set_clock(host, ios->clock); host->clock = ios->clock; @@ -2349,6 +2387,17 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->ops->set_bus_width(host, ios->bus_width); + /* + * Special case to avoid multiple clock changes during voltage + * switching. + */ + if (!reinit_uhs && + turning_on_clk && + host->timing == ios->timing && + host->version >= SDHCI_SPEC_300 && + !sdhci_presetable_values_change(host, ios)) + return; + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); if (!(host->quirks & SDHCI_QUIRK_NO_HISPD_BIT)) { @@ -2392,6 +2441,7 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) } sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2); + host->drv_type = ios->drv_type; } else { /* * According to SDHC Spec v3.00, if the Preset Value @@ -2419,19 +2469,14 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->ops->set_uhs_signaling(host, ios->timing); host->timing = ios->timing; - if (!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN) && - ((ios->timing == MMC_TIMING_UHS_SDR12) || - (ios->timing == MMC_TIMING_UHS_SDR25) || - (ios->timing == MMC_TIMING_UHS_SDR50) || - (ios->timing == MMC_TIMING_UHS_SDR104) || - (ios->timing == MMC_TIMING_UHS_DDR50) || - (ios->timing == MMC_TIMING_MMC_DDR52))) { + if (sdhci_preset_needed(host, ios->timing)) { u16 preset; sdhci_enable_preset_value(host, true); preset = sdhci_get_preset_value(host); ios->drv_type = FIELD_GET(SDHCI_PRESET_DRV_MASK, preset); + host->drv_type = ios->drv_type; } /* Re-enable SD Clock */ @@ -3768,6 +3813,7 @@ int sdhci_resume_host(struct sdhci_host *host) sdhci_init(host, 0); host->pwr = 0; host->clock = 0; + host->reinit_uhs = true; mmc->ops->set_ios(mmc, &mmc->ios); } else { sdhci_init(host, (mmc->pm_flags & MMC_PM_KEEP_POWER)); @@ -3830,6 +3876,7 @@ int sdhci_runtime_resume_host(struct sdhci_host *host, int soft_reset) /* Force clock and power re-program */ host->pwr = 0; host->clock = 0; + host->reinit_uhs = true; mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios); mmc->ops->set_ios(mmc, &mmc->ios); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index d750c464bd1e..87a3aaa07438 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -524,6 +524,8 @@ struct sdhci_host { unsigned int clock; /* Current clock (MHz) */ u8 pwr; /* Current voltage */ + u8 drv_type; /* Current UHS-I driver type */ + bool reinit_uhs; /* Force UHS-related re-initialization */ bool runtime_suspended; /* Host is runtime suspended */ bool bus_on; /* Bus power prevents runtime suspend */ diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 24150c933fcb..dc3253b318da 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -113,6 +113,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) struct com20020_dev *info; struct net_device *dev; struct arcnet_local *lp; + int ret = -ENOMEM; dev_dbg(&p_dev->dev, "com20020_attach()\n"); @@ -142,12 +143,18 @@ static int com20020_probe(struct pcmcia_device *p_dev) info->dev = dev; p_dev->priv = info; - return com20020_config(p_dev); + ret = com20020_config(p_dev); + if (ret) + goto fail_config; + + return 0; +fail_config: + free_arcdev(dev); fail_alloc_dev: kfree(info); fail_alloc_info: - return -ENOMEM; + return ret; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e84c49bf4d0c..b9a882f182d2 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3231,16 +3231,23 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct slave *curr_active_slave, *curr_arp_slave; - struct icmp6hdr *hdr = icmp6_hdr(skb); struct in6_addr *saddr, *daddr; + struct { + struct ipv6hdr ip6; + struct icmp6hdr icmp6; + } *combined, _combined; if (skb->pkt_type == PACKET_OTHERHOST || - skb->pkt_type == PACKET_LOOPBACK || - hdr->icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) + skb->pkt_type == PACKET_LOOPBACK) + goto out; + + combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); + if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || + combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) goto out; - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; + saddr = &combined->ip6.saddr; + daddr = &combined->ip6.daddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index 094197780776..dc7192ecb001 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -263,8 +263,10 @@ static void can327_feed_frame_to_netdev(struct can327 *elm, struct sk_buff *skb) { lockdep_assert_held(&elm->lock); - if (!netif_running(elm->dev)) + if (!netif_running(elm->dev)) { + kfree_skb(skb); return; + } /* Queue for NAPI pickup. * rx-offload will update stats and LEDs for us. @@ -794,9 +796,9 @@ static int can327_netdev_close(struct net_device *dev) netif_stop_queue(dev); - /* Give UART one final chance to flush. */ - clear_bit(TTY_DO_WRITE_WAKEUP, &elm->tty->flags); - flush_work(&elm->tx_work); + /* We don't flush the UART TX queue here, as we want final stop + * commands (like the above dummy char) to be flushed out. + */ can_rx_offload_disable(&elm->offload); elm->can.state = CAN_STATE_STOPPED; @@ -1067,12 +1069,15 @@ static void can327_ldisc_close(struct tty_struct *tty) { struct can327 *elm = (struct can327 *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set elm->tty = NULL after this. - */ + /* unregister_netdev() calls .ndo_stop() so we don't have to. */ unregister_candev(elm->dev); + /* Give UART one final chance to flush. + * No need to clear TTY_DO_WRITE_WAKEUP since .write_wakeup() is + * serialised against .close() and will not be called once we return. + */ + flush_work(&elm->tx_work); + /* Mark channel as dead */ spin_lock_bh(&elm->lock); tty->disc_data = NULL; diff --git a/drivers/net/can/cc770/cc770_isa.c b/drivers/net/can/cc770/cc770_isa.c index 194c86e0f340..8f6dccd5a587 100644 --- a/drivers/net/can/cc770/cc770_isa.c +++ b/drivers/net/can/cc770/cc770_isa.c @@ -264,22 +264,24 @@ static int cc770_isa_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "couldn't register device (err=%d)\n", err); - goto exit_unmap; + goto exit_free; } dev_info(&pdev->dev, "device registered (reg_base=0x%p, irq=%d)\n", priv->reg_base, dev->irq); return 0; - exit_unmap: +exit_free: + free_cc770dev(dev); +exit_unmap: if (mem[idx]) iounmap(base); - exit_release: +exit_release: if (mem[idx]) release_mem_region(mem[idx], iosize); else release_region(port[idx], iosize); - exit: +exit: return err; } diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 00d11e95fd98..e5575d2755e4 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1909,7 +1909,7 @@ int m_can_class_get_clocks(struct m_can_classdev *cdev) cdev->hclk = devm_clk_get(cdev->dev, "hclk"); cdev->cclk = devm_clk_get(cdev->dev, "cclk"); - if (IS_ERR(cdev->cclk)) { + if (IS_ERR(cdev->hclk) || IS_ERR(cdev->cclk)) { dev_err(cdev->dev, "no clock found\n"); ret = -ENODEV; } diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index 8f184a852a0a..f2219aa2824b 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -120,7 +120,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) ret = pci_alloc_irq_vectors(pci, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) - return ret; + goto err_free_dev; mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); @@ -132,7 +132,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) ret = m_can_class_register(mcan_class); if (ret) - goto err; + goto err_free_irq; /* Enable interrupt control at CAN wrapper IP */ writel(0x1, base + CTL_CSR_INT_CTL_OFFSET); @@ -144,8 +144,10 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) return 0; -err: +err_free_irq: pci_free_irq_vectors(pci); +err_free_dev: + m_can_class_free_dev(mcan_class->net); return ret; } @@ -161,6 +163,7 @@ static void m_can_pci_remove(struct pci_dev *pci) writel(0x0, priv->base + CTL_CSR_INT_CTL_OFFSET); m_can_class_unregister(mcan_class); + m_can_class_free_dev(mcan_class->net); pci_free_irq_vectors(pci); } diff --git a/drivers/net/can/sja1000/sja1000_isa.c b/drivers/net/can/sja1000/sja1000_isa.c index d513fac50718..db3e767d5320 100644 --- a/drivers/net/can/sja1000/sja1000_isa.c +++ b/drivers/net/can/sja1000/sja1000_isa.c @@ -202,22 +202,24 @@ static int sja1000_isa_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "registering %s failed (err=%d)\n", DRV_NAME, err); - goto exit_unmap; + goto exit_free; } dev_info(&pdev->dev, "%s device registered (reg_base=0x%p, irq=%d)\n", DRV_NAME, priv->reg_base, dev->irq); return 0; - exit_unmap: +exit_free: + free_sja1000dev(dev); +exit_unmap: if (mem[idx]) iounmap(base); - exit_release: +exit_release: if (mem[idx]) release_mem_region(mem[idx], iosize); else release_region(port[idx], iosize); - exit: +exit: return err; } diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index fbb34139daa1..f4db77007c13 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -864,12 +864,14 @@ static void slcan_close(struct tty_struct *tty) { struct slcan *sl = (struct slcan *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set sl->tty = NULL after this. - */ unregister_candev(sl->dev); + /* + * The netdev needn't be UP (so .ndo_stop() is not called). Hence make + * sure this is not running before freeing it up. + */ + flush_work(&sl->tx_work); + /* Mark channel as dead */ spin_lock_bh(&sl->lock); tty->disc_data = NULL; diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 81b88e9e5bdc..42323f5e6f3a 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -234,6 +234,10 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, u8 rxerr = msg->msg.rx.data[2]; u8 txerr = msg->msg.rx.data[3]; + netdev_dbg(priv->netdev, + "CAN_ERR_EV_EXT: dlc=%#02x state=%02x ecc=%02x rec=%02x tec=%02x\n", + msg->msg.rx.dlc, state, ecc, rxerr, txerr); + skb = alloc_can_err_skb(priv->netdev, &cf); if (skb == NULL) { stats->rx_dropped++; @@ -260,6 +264,8 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, break; default: priv->can.state = CAN_STATE_ERROR_ACTIVE; + txerr = 0; + rxerr = 0; break; } } else { diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 25f863b4f5f0..ddb7c5735c9a 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -2091,8 +2091,11 @@ static int es58x_init_netdev(struct es58x_device *es58x_dev, int channel_idx) netdev->dev_port = channel_idx; ret = register_candev(netdev); - if (ret) + if (ret) { + es58x_dev->netdev[channel_idx] = NULL; + free_candev(netdev); return ret; + } netdev_queue_set_dql_min_limit(netdev_get_tx_queue(netdev, 0), es58x_dev->param->dql_min_limit); diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 218b098b261d..47619e9cb005 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -47,6 +47,10 @@ #define MCBA_VER_REQ_USB 1 #define MCBA_VER_REQ_CAN 2 +/* Drive the CAN_RES signal LOW "0" to activate R24 and R25 */ +#define MCBA_VER_TERMINATION_ON 0 +#define MCBA_VER_TERMINATION_OFF 1 + #define MCBA_SIDL_EXID_MASK 0x8 #define MCBA_DLC_MASK 0xf #define MCBA_DLC_RTR_MASK 0x40 @@ -463,7 +467,7 @@ static void mcba_usb_process_ka_usb(struct mcba_priv *priv, priv->usb_ka_first_pass = false; } - if (msg->termination_state) + if (msg->termination_state == MCBA_VER_TERMINATION_ON) priv->can.termination = MCBA_TERMINATION_ENABLED; else priv->can.termination = MCBA_TERMINATION_DISABLED; @@ -785,9 +789,9 @@ static int mcba_set_termination(struct net_device *netdev, u16 term) }; if (term == MCBA_TERMINATION_ENABLED) - usb_msg.termination = 1; + usb_msg.termination = MCBA_VER_TERMINATION_ON; else - usb_msg.termination = 0; + usb_msg.termination = MCBA_VER_TERMINATION_OFF; mcba_usb_xmit_cmd(priv, (struct mcba_usb_msg *)&usb_msg); diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 438e46af03e9..80f07bd20593 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -961,7 +961,7 @@ static const struct lan9303_mib_desc lan9303_mib[] = { { .offset = LAN9303_MAC_TX_BRDCST_CNT_0, .name = "TxBroad", }, { .offset = LAN9303_MAC_TX_PAUSE_CNT_0, .name = "TxPause", }, { .offset = LAN9303_MAC_TX_MULCST_CNT_0, .name = "TxMulti", }, - { .offset = LAN9303_MAC_RX_UNDSZE_CNT_0, .name = "TxUnderRun", }, + { .offset = LAN9303_MAC_RX_UNDSZE_CNT_0, .name = "RxShort", }, { .offset = LAN9303_MAC_TX_64_CNT_0, .name = "Tx64Byte", }, { .offset = LAN9303_MAC_TX_127_CNT_0, .name = "Tx128Byte", }, { .offset = LAN9303_MAC_TX_255_CNT_0, .name = "Tx256Byte", }, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 2479be3a1e35..937cb22cb3d4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -833,10 +833,13 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, chip->info->ops->phylink_get_caps(chip, port, config); - /* Internal ports need GMII for PHYLIB */ - if (mv88e6xxx_phy_is_internal(ds, port)) + if (mv88e6xxx_phy_is_internal(ds, port)) { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + /* Internal ports with no phy-mode need GMII for PHYLIB */ __set_bit(PHY_INTERFACE_MODE_GMII, config->supported_interfaces); + } } static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 10c6fea1227f..bdbbff2a7909 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -95,6 +95,8 @@ static int sja1105_setup_devlink_regions(struct dsa_switch *ds) if (IS_ERR(region)) { while (--i >= 0) dsa_devlink_region_destroy(priv->regions[i]); + + kfree(priv->regions); return PTR_ERR(region); } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 412666111b0c..b70dcf32a26d 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1038,7 +1038,7 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv) policing[bcast].sharindx = port; /* Only SJA1110 has multicast policers */ - if (mcast <= table->ops->max_entry_count) + if (mcast < table->ops->max_entry_count) policing[mcast].sharindx = port; } diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 215dd17ca790..4059fcc8c832 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -256,6 +256,9 @@ static int sja1105_base_tx_mdio_read(struct mii_bus *bus, int phy, int reg) u32 tmp; int rc; + if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + rc = sja1105_xfer_u32(priv, SPI_READ, regs->mdio_100base_tx + reg, &tmp, NULL); if (rc < 0) @@ -272,6 +275,9 @@ static int sja1105_base_tx_mdio_write(struct mii_bus *bus, int phy, int reg, const struct sja1105_regs *regs = priv->info->regs; u32 tmp = val; + if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + return sja1105_xfer_u32(priv, SPI_WRITE, regs->mdio_100base_tx + reg, &tmp, NULL); } diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index e104fb02817d..aa0d2f3aaeaa 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -258,6 +258,7 @@ static int greth_init_rings(struct greth_private *greth) if (dma_mapping_error(greth->dev, dma_addr)) { if (netif_msg_ifup(greth)) dev_err(greth->dev, "Could not create initial DMA mapping\n"); + dev_kfree_skb(skb); goto cleanup; } greth->rx_skbuff[i] = skb; diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7633b227b2ca..711d5b5a4c49 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -990,6 +990,7 @@ static int tse_shutdown(struct net_device *dev) int ret; phylink_stop(priv->phylink); + phylink_disconnect_phy(priv->phylink); netif_stop_queue(dev); napi_disable(&priv->napi); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a08f221e30d4..ac4ea93bd8dd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -13,6 +13,7 @@ #include "aq_ptp.h" #include "aq_filters.h" #include "aq_macsec.h" +#include "aq_main.h" #include <linux/ptp_clock_kernel.h> @@ -858,7 +859,7 @@ static int aq_set_ringparam(struct net_device *ndev, if (netif_running(ndev)) { ndev_running = true; - dev_close(ndev); + aq_ndev_close(ndev); } cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min); @@ -874,7 +875,7 @@ static int aq_set_ringparam(struct net_device *ndev, goto err_exit; if (ndev_running) - err = dev_open(ndev, NULL); + err = aq_ndev_open(ndev); err_exit: return err; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 8a0af371e7dc..77609dc0a08d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -58,7 +58,7 @@ struct net_device *aq_ndev_alloc(void) return ndev; } -static int aq_ndev_open(struct net_device *ndev) +int aq_ndev_open(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); int err = 0; @@ -88,7 +88,7 @@ err_exit: return err; } -static int aq_ndev_close(struct net_device *ndev) +int aq_ndev_close(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.h b/drivers/net/ethernet/aquantia/atlantic/aq_main.h index 99870865f66d..a78c1a168d8e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.h @@ -16,5 +16,7 @@ DECLARE_STATIC_KEY_FALSE(aq_xdp_locking_key); void aq_ndev_schedule_work(struct work_struct *work); struct net_device *aq_ndev_alloc(void); +int aq_ndev_open(struct net_device *ndev); +int aq_ndev_close(struct net_device *ndev); #endif /* AQ_MAIN_H */ diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 55dfdb34e37b..f4ca0c6c0f51 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -71,13 +71,14 @@ config BCM63XX_ENET config BCMGENET tristate "Broadcom GENET internal MAC support" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL || !ARCH_BCM2835 select MII select PHYLIB select FIXED_PHY select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB - select BROADCOM_PHY if (ARCH_BCM2835 && PTP_1588_CLOCK_OPTIONAL) + select BROADCOM_PHY if ARCH_BCM2835 help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 11d15cd03600..77d4cb4ad782 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -795,16 +795,20 @@ static void bnx2x_vf_enable_traffic(struct bnx2x *bp, struct bnx2x_virtf *vf) static u8 bnx2x_vf_is_pcie_pending(struct bnx2x *bp, u8 abs_vfid) { - struct pci_dev *dev; struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid); + struct pci_dev *dev; + bool pending; if (!vf) return false; dev = pci_get_domain_bus_and_slot(vf->domain, vf->bus, vf->devfn); - if (dev) - return bnx2x_is_pcie_pending(dev); - return false; + if (!dev) + return false; + pending = bnx2x_is_pcie_pending(dev); + pci_dev_put(dev); + + return pending; } int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 75771825c3f9..98793b2ac2c7 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1794,7 +1794,7 @@ static int liquidio_open(struct net_device *netdev) ifstate_set(lio, LIO_IFSTATE_RUNNING); - if (!OCTEON_CN23XX_PF(oct) || (OCTEON_CN23XX_PF(oct) && !oct->msix_on)) { + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) { ret = setup_tx_poll_fn(netdev); if (ret) goto err_poll; @@ -1824,7 +1824,7 @@ static int liquidio_open(struct net_device *netdev) return 0; err_rx_ctrl: - if (!OCTEON_CN23XX_PF(oct) || (OCTEON_CN23XX_PF(oct) && !oct->msix_on)) + if (!OCTEON_CN23XX_PF(oct) || !oct->msix_on) cleanup_tx_poll_fn(netdev); err_poll: if (lio->ptp_clock) { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 98f3dc460ca7..f2f95493ec89 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2239,7 +2239,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_unregister_interrupts; + goto err_destroy_workqueue; } nic->msg_enable = debug; @@ -2248,6 +2248,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; +err_destroy_workqueue: + destroy_workqueue(nic->nicvf_rx_mode_wq); err_unregister_interrupts: nicvf_unregister_interrupts(nic); err_free_netdev: diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 2f6484dc186a..7eb2ddbe9bad 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1436,8 +1436,10 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl, return AE_OK; } - if (strncmp(string.pointer, bgx_sel, 4)) + if (strncmp(string.pointer, bgx_sel, 4)) { + kfree(string.pointer); return AE_OK; + } acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, bgx_acpi_register_phy, NULL, bgx, NULL); diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c index a523ddda7609..de7105a84747 100644 --- a/drivers/net/ethernet/davicom/dm9051.c +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -798,8 +798,10 @@ static int dm9051_loop_rx(struct board_info *db) } ret = dm9051_stop_mrcmd(db); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } skb->protocol = eth_type_trans(skb, db->ndev); if (db->ndev->features & NETIF_F_RXCSUM) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 48fb391951dd..13d5ff4e0e02 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -542,6 +542,27 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) return (budget != 0); } +static bool tsnep_tx_pending(struct tsnep_tx *tx) +{ + unsigned long flags; + struct tsnep_tx_entry *entry; + bool pending = false; + + spin_lock_irqsave(&tx->lock, flags); + + if (tx->read != tx->write) { + entry = &tx->entry[tx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_TX_DESC_OWNER_MASK) == + (entry->properties & TSNEP_TX_DESC_OWNER_MASK)) + pending = true; + } + + spin_unlock_irqrestore(&tx->lock, flags); + + return pending; +} + static int tsnep_tx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_tx *tx) { @@ -821,6 +842,19 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, return done; } +static bool tsnep_rx_pending(struct tsnep_rx *rx) +{ + struct tsnep_rx_entry *entry; + + entry = &rx->entry[rx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_DESC_OWNER_COUNTER_MASK) == + (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) + return true; + + return false; +} + static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_rx *rx) { @@ -866,6 +900,17 @@ static void tsnep_rx_close(struct tsnep_rx *rx) tsnep_rx_ring_cleanup(rx); } +static bool tsnep_pending(struct tsnep_queue *queue) +{ + if (queue->tx && tsnep_tx_pending(queue->tx)) + return true; + + if (queue->rx && tsnep_rx_pending(queue->rx)) + return true; + + return false; +} + static int tsnep_poll(struct napi_struct *napi, int budget) { struct tsnep_queue *queue = container_of(napi, struct tsnep_queue, @@ -886,9 +931,19 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (!complete) return budget; - if (likely(napi_complete_done(napi, done))) + if (likely(napi_complete_done(napi, done))) { tsnep_enable_irq(queue->adapter, queue->irq_mask); + /* reschedule if work is already pending, prevent rotten packets + * which are transmitted or received after polling but before + * interrupt enable + */ + if (tsnep_pending(queue)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + napi_schedule(napi); + } + } + return min(done, budget - 1); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index cacd454ac696..c39b866e2582 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -132,6 +132,7 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, acl_entry_cfg->key_iova))) { dev_err(dev, "DMA mapping failed\n"); + kfree(cmd_buff); return -EFAULT; } @@ -142,6 +143,7 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err); + kfree(cmd_buff); return err; } @@ -172,6 +174,7 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, acl_entry_cfg->key_iova))) { dev_err(dev, "DMA mapping failed\n"); + kfree(cmd_buff); return -EFAULT; } @@ -182,6 +185,7 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err); + kfree(cmd_buff); return err; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index f8c06c3f9464..8671591cb750 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2058,7 +2058,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); - tbmr = ENETC_TBMR_EN; + tbmr = ENETC_TBMR_EN | ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH; @@ -2461,7 +2461,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) /* Reset all ring priorities to 0 */ for (i = 0; i < priv->num_tx_rings; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, 0); + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } return 0; @@ -2480,7 +2481,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) */ for (i = 0; i < num_tc; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, i); + tx_ring->prio = i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); } /* Reset the number of netdev queues based on the TC count */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 161930a65f61..c6d8cc15c270 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -95,6 +95,7 @@ struct enetc_bdr { void __iomem *rcir; }; u16 index; + u16 prio; int bd_count; /* # of BDs */ int next_to_use; int next_to_clean; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index a842e1999122..fcebb54224c0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -137,6 +137,7 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_bdr *tx_ring; int err; int i; @@ -145,16 +146,20 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) if (priv->tx_ring[i]->tsd_enable) return -EBUSY; - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? i : 0); + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? i : 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } err = enetc_setup_taprio(ndev, taprio); - - if (err) - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? 0 : i); + if (err) { + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? 0 : i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + } return err; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f623c12eaf95..23e1a94b9ce4 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -74,7 +74,7 @@ #include "fec.h" static void set_multicast_list(struct net_device *ndev); -static void fec_enet_itr_coal_init(struct net_device *ndev); +static void fec_enet_itr_coal_set(struct net_device *ndev); #define DRIVER_NAME "fec" @@ -1220,8 +1220,8 @@ fec_restart(struct net_device *ndev) writel(0, fep->hwp + FEC_IMASK); /* Init the interrupt coalescing */ - fec_enet_itr_coal_init(ndev); - + if (fep->quirks & FEC_QUIRK_HAS_COALESCE) + fec_enet_itr_coal_set(ndev); } static int fec_enet_ipc_handle_init(struct fec_enet_private *fep) @@ -2856,19 +2856,6 @@ static int fec_enet_set_coalesce(struct net_device *ndev, return 0; } -static void fec_enet_itr_coal_init(struct net_device *ndev) -{ - struct ethtool_coalesce ec; - - ec.rx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT; - ec.rx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT; - - ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT; - ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT; - - fec_enet_set_coalesce(ndev, &ec, NULL, NULL); -} - static int fec_enet_get_tunable(struct net_device *netdev, const struct ethtool_tunable *tuna, void *data) @@ -3623,6 +3610,10 @@ static int fec_enet_init(struct net_device *ndev) fep->rx_align = 0x3; fep->tx_align = 0x3; #endif + fep->rx_pkts_itr = FEC_ITR_ICFT_DEFAULT; + fep->tx_pkts_itr = FEC_ITR_ICFT_DEFAULT; + fep->rx_time_itr = FEC_ITR_ICTT_DEFAULT; + fep->tx_time_itr = FEC_ITR_ICTT_DEFAULT; /* Check mask of the streaming and coherent API */ ret = dma_set_mask_and_coherent(&fep->pdev->dev, DMA_BIT_MASK(32)); diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 93846bace028..ce2571c16e43 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -283,7 +283,7 @@ static int hisi_femac_rx(struct net_device *dev, int limit) skb->protocol = eth_type_trans(skb, dev); napi_gro_receive(&priv->napi, skb); dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += len; next: pos = (pos + 1) % rxq->num; if (rx_pkts_num >= limit) diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index ffcf797dfa90..f867e9531117 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -550,7 +550,7 @@ static int hix5hd2_rx(struct net_device *dev, int limit) skb->protocol = eth_type_trans(skb, dev); napi_gro_receive(&priv->napi, skb); dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += len; next: pos = dma_ring_incr(pos, RX_DESC_NUM); } diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 560d1d442232..d3fdc290937f 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1741,11 +1741,8 @@ static int e100_xmit_prepare(struct nic *nic, struct cb *cb, dma_addr = dma_map_single(&nic->pdev->dev, skb->data, skb->len, DMA_TO_DEVICE); /* If we can't map the skb, have the upper layer try later */ - if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { - dev_kfree_skb_any(skb); - skb = NULL; + if (dma_mapping_error(&nic->pdev->dev, dma_addr)) return -ENOMEM; - } /* * Use the last 4 bytes of the SKB payload packet as the CRC, used for diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 49e926959ad3..55cf2f62bb30 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5936,9 +5936,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, e1000_tx_queue(tx_ring, tx_flags, count); /* Make sure there is space in the ring for the next send. */ e1000_maybe_stop_tx(tx_ring, - (MAX_SKB_FRAGS * + ((MAX_SKB_FRAGS + 1) * DIV_ROUND_UP(PAGE_SIZE, - adapter->tx_fifo_limit) + 2)); + adapter->tx_fifo_limit) + 4)); if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 4a6630586ec9..fc373472e4e1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -32,6 +32,8 @@ struct workqueue_struct *fm10k_workqueue; **/ static int __init fm10k_init_module(void) { + int ret; + pr_info("%s\n", fm10k_driver_string); pr_info("%s\n", fm10k_copyright); @@ -43,7 +45,13 @@ static int __init fm10k_init_module(void) fm10k_dbg_init(); - return fm10k_register_pci_driver(); + ret = fm10k_register_pci_driver(); + if (ret) { + fm10k_dbg_exit(); + destroy_workqueue(fm10k_workqueue); + } + + return ret; } module_init(fm10k_init_module); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4a6a6e48c615..f6fa63e4253c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4464,11 +4464,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, return -EOPNOTSUPP; /* First 4 bytes of L4 header */ - if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF)) - new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK; - else if (!usr_ip4_spec->l4_4_bytes) - new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK); - else + if (usr_ip4_spec->l4_4_bytes) return -EOPNOTSUPP; /* Filtering on Type of Service is not supported. */ @@ -4507,11 +4503,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, else return -EOPNOTSUPP; - if (usr_ip6_spec->l4_4_bytes == htonl(0xFFFFFFFF)) - new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK; - else if (!usr_ip6_spec->l4_4_bytes) - new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK); - else + if (usr_ip6_spec->l4_4_bytes) return -EOPNOTSUPP; /* Filtering on Traffic class is not supported. */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b5dcd15ced36..6416322d7c18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10655,6 +10655,21 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) } /** + * i40e_clean_xps_state - clean xps state for every tx_ring + * @vsi: ptr to the VSI + **/ +static void i40e_clean_xps_state(struct i40e_vsi *vsi) +{ + int i; + + if (vsi->tx_rings) + for (i = 0; i < vsi->num_queue_pairs; i++) + if (vsi->tx_rings[i]) + clear_bit(__I40E_TX_XPS_INIT_DONE, + vsi->tx_rings[i]->state); +} + +/** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure * @@ -10678,8 +10693,10 @@ static void i40e_prep_for_reset(struct i40e_pf *pf) i40e_pf_quiesce_all_vsi(pf); for (v = 0; v < pf->num_alloc_vsi; v++) { - if (pf->vsi[v]) + if (pf->vsi[v]) { + i40e_clean_xps_state(pf->vsi[v]); pf->vsi[v]->seid = 0; + } } i40e_shutdown_adminq(&pf->hw); @@ -16644,6 +16661,8 @@ static struct pci_driver i40e_driver = { **/ static int __init i40e_init_module(void) { + int err; + pr_info("%s: %s\n", i40e_driver_name, i40e_driver_string); pr_info("%s: %s\n", i40e_driver_name, i40e_copyright); @@ -16661,7 +16680,14 @@ static int __init i40e_init_module(void) } i40e_dbg_init(); - return pci_register_driver(&i40e_driver); + err = pci_register_driver(&i40e_driver); + if (err) { + destroy_workqueue(i40e_wq); + i40e_dbg_exit(); + return err; + } + + return 0; } module_init(i40e_init_module); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 72ddcefc45b1..635f93d60318 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1578,6 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_cleanup_reset_vf(vf); i40e_flush(hw); + usleep_range(20000, 40000); clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states); return true; @@ -1701,6 +1702,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) } i40e_flush(hw); + usleep_range(20000, 40000); clear_bit(__I40E_VF_DISABLE, pf->state); return true; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 3f6187c16424..0d1bab4ac1b0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -298,7 +298,6 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) -#define IAVF_FLAG_INITIAL_MAC_SET BIT(23) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3fc572341781..f71e132ede09 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1087,12 +1087,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (ret) return ret; - /* If this is an initial set MAC during VF spawn do not wait */ - if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) { - adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET; - return 0; - } - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, iavf_is_mac_set_handled(netdev, addr->sa_data), msecs_to_jiffies(2500)); @@ -2605,8 +2599,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET; - adapter->tx_desc_count = IAVF_DEFAULT_TXD; adapter->rx_desc_count = IAVF_DEFAULT_RXD; err = iavf_init_interrupt_scheme(adapter); @@ -2921,7 +2913,6 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); - adapter->netdev->flags &= ~IFF_UP; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); @@ -3021,6 +3012,11 @@ static void iavf_reset_task(struct work_struct *work) iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + if (netif_running(netdev)) { + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3033,6 +3029,7 @@ continue_reset: if (running) { netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); adapter->link_up = false; iavf_napi_disable_all(adapter); } @@ -3172,6 +3169,16 @@ reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + + if (netif_running(netdev)) { + /* Close device to ensure that Tx queues will not be started + * during netif_device_attach() at the end of the reset task. + */ + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } + dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); reset_finish: rtnl_lock(); @@ -5035,23 +5042,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; - struct iavf_cloud_filter *cf, *cftmp; - struct iavf_hw *hw = &adapter->hw; + struct net_device *netdev; + struct iavf_hw *hw; int err; - /* When reboot/shutdown is in progress no need to do anything - * as the adapter is already REMOVE state that was set during - * iavf_shutdown() callback. - */ - if (adapter->state == __IAVF_REMOVE) + netdev = adapter->netdev; + hw = &adapter->hw; + + if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return; - set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); /* Wait until port initialization is complete. * There are flows where register/unregister netdev may race. */ @@ -5191,6 +5196,8 @@ static struct pci_driver iavf_driver = { **/ static int __init iavf_init_module(void) { + int ret; + pr_info("iavf: %s\n", iavf_driver_string); pr_info("%s\n", iavf_copyright); @@ -5201,7 +5208,12 @@ static int __init iavf_init_module(void) pr_err("%s: Failed to create workqueue\n", iavf_driver_name); return -ENOMEM; } - return pci_register_driver(&iavf_driver); + + ret = pci_register_driver(&iavf_driver); + if (ret) + destroy_workqueue(iavf_wq); + + return ret; } module_init(iavf_init_module); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0f6718719453..ca2898467dcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3145,15 +3145,15 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) */ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) { - irqreturn_t ret = IRQ_HANDLED; struct ice_pf *pf = data; - bool irq_handled; - irq_handled = ice_ptp_process_ts(pf); - if (!irq_handled) - ret = IRQ_WAKE_THREAD; + if (ice_is_reset_in_progress(pf->state)) + return IRQ_HANDLED; - return ret; + while (!ice_ptp_process_ts(pf)) + usleep_range(50, 100); + + return IRQ_HANDLED; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 011b727ab190..0f668468d141 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -614,11 +614,14 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) * 2) extend the 40b timestamp value to get a 64bit timestamp * 3) send that timestamp to the stack * - * After looping, if we still have waiting SKBs, return true. This may cause us - * effectively poll even when not strictly necessary. We do this because it's - * possible a new timestamp was requested around the same time as the interrupt. - * In some cases hardware might not interrupt us again when the timestamp is - * captured. + * Returns true if all timestamps were handled, and false if any slots remain + * without a timestamp. + * + * After looping, if we still have waiting SKBs, return false. This may cause + * us effectively poll even when not strictly necessary. We do this because + * it's possible a new timestamp was requested around the same time as the + * interrupt. In some cases hardware might not interrupt us again when the + * timestamp is captured. * * Note that we only take the tracking lock when clearing the bit and when * checking if we need to re-queue this task. The only place where bits can be @@ -641,7 +644,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) u8 idx; if (!tx->init) - return false; + return true; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); @@ -2381,10 +2384,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) */ bool ice_ptp_process_ts(struct ice_pf *pf) { - if (pf->ptp.port.tx.init) - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); - - return false; + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); } static void ice_ptp_periodic_work(struct kthread_work *work) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index e5f3e7680dc6..ff911af16a4b 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1413,6 +1413,8 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data) *data = 1; return -1; } + wr32(E1000_IVAR_MISC, E1000_IVAR_VALID << 8); + wr32(E1000_EIMS, BIT(0)); } else if (adapter->flags & IGB_FLAG_HAS_MSI) { shared_int = false; if (request_irq(irq, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 99933e89717a..e338fa572793 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4869,6 +4869,8 @@ static struct pci_driver ixgbevf_driver = { **/ static int __init ixgbevf_init_module(void) { + int err; + pr_info("%s\n", ixgbevf_driver_string); pr_info("%s\n", ixgbevf_copyright); ixgbevf_wq = create_singlethread_workqueue(ixgbevf_driver_name); @@ -4877,7 +4879,13 @@ static int __init ixgbevf_init_module(void) return -ENOMEM; } - return pci_register_driver(&ixgbevf_driver); + err = pci_register_driver(&ixgbevf_driver); + if (err) { + destroy_workqueue(ixgbevf_wq); + return err; + } + + return 0; } module_init(ixgbevf_init_module); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ff3e361e06e7..5aefaaff0871 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4271,7 +4271,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) /* Use the cpu associated to the rxq when it is online, in all * the other cases, use the cpu 0 which can't be offline. */ - if (cpu_online(pp->rxq_def)) + if (pp->rxq_def < nr_cpu_ids && cpu_online(pp->rxq_def)) elected_cpu = pp->rxq_def; max_cpu = num_present_cpus(); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index eb0fb8128096..b399bdb1ca36 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7350,6 +7350,7 @@ static int mvpp2_get_sram(struct platform_device *pdev, struct mvpp2 *priv) { struct resource *res; + void __iomem *base; res = platform_get_resource(pdev, IORESOURCE_MEM, 2); if (!res) { @@ -7360,9 +7361,12 @@ static int mvpp2_get_sram(struct platform_device *pdev, return 0; } - priv->cm3_base = devm_ioremap_resource(&pdev->dev, res); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); - return PTR_ERR_OR_ZERO(priv->cm3_base); + priv->cm3_base = base; + return 0; } static int mvpp2_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 6b4f640163f7..993ac180a5db 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,7 +32,6 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK - depends on MACSEC || !MACSEC depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index 4a343f853b28..c0bedf402da9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -951,7 +951,7 @@ static void mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction d else event.intr_mask = (dir == MCS_RX) ? MCS_BBE_RX_PLFIFO_OVERFLOW_INT : - MCS_BBE_RX_PLFIFO_OVERFLOW_INT; + MCS_BBE_TX_PLFIFO_OVERFLOW_INT; /* Notify the lmac_id info which ran into BBE fatal error */ event.lmac_id = i & 0x3ULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index a1970ebedf95..f66dde2b0f92 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -880,6 +880,8 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) sprintf(lmac, "LMAC%d", lmac_id); seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\n", dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac); + + pci_dev_put(pdev); } return 0; } @@ -2566,6 +2568,7 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id) } } + pci_dev_put(pdev); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 7646bb2ec89b..a62c1b322012 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4985,6 +4985,8 @@ static int nix_setup_ipolicers(struct rvu *rvu, ipolicer->ref_count = devm_kcalloc(rvu->dev, ipolicer->band_prof.max, sizeof(u16), GFP_KERNEL); + if (!ipolicer->ref_count) + return -ENOMEM; } /* Set policer timeunit to 2us ie (19 + 1) * 100 nsec = 2us */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index b04fb226f708..ae50d56258ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -62,15 +62,18 @@ int rvu_sdp_init(struct rvu *rvu) pfvf->sdp_info = devm_kzalloc(rvu->dev, sizeof(struct sdp_node_info), GFP_KERNEL); - if (!pfvf->sdp_info) + if (!pfvf->sdp_info) { + pci_dev_put(pdev); return -ENOMEM; + } dev_info(rvu->dev, "SDP PF number:%d\n", sdp_pf_num[i]); - put_device(&pdev->dev); i++; } + pci_dev_put(pdev); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 282db6fe3b08..67aa02bb2b85 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -884,7 +884,7 @@ static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, static inline u16 otx2_get_smq_idx(struct otx2_nic *pfvf, u16 qidx) { #ifdef CONFIG_DCB - if (pfvf->pfc_alloc_status[qidx]) + if (qidx < NIX_PF_PFC_PRIO_MAX && pfvf->pfc_alloc_status[qidx]) return pfvf->pfc_schq_list[NIX_TXSCH_LVL_SMQ][qidx]; #endif diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index e64318c110fd..6a01ab1a6e6f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -1134,7 +1134,12 @@ int otx2_init_tc(struct otx2_nic *nic) return err; tc->flow_ht_params = tc_flow_ht_params; - return rhashtable_init(&tc->flow_table, &tc->flow_ht_params); + err = rhashtable_init(&tc->flow_table, &tc->flow_ht_params); + if (err) { + kfree(tc->tc_entries_bitmap); + tc->tc_entries_bitmap = NULL; + } + return err; } EXPORT_SYMBOL(otx2_init_tc); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 24f9d6024745..47796e4d900c 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -746,6 +746,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) return 0; err_sfp_bind: + unregister_netdev(dev); err_register_netdev: prestera_port_list_del(port); err_port_init: diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index 4046be0e86ff..a9a1028cb17b 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -457,7 +457,7 @@ prestera_kern_neigh_cache_find(struct prestera_switch *sw, n_cache = rhashtable_lookup_fast(&sw->router->kern_neigh_cache_ht, key, __prestera_kern_neigh_cache_ht_params); - return IS_ERR(n_cache) ? NULL : n_cache; + return n_cache; } static void diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c index aa080dc57ff0..02faaea2aefa 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router_hw.c @@ -330,7 +330,7 @@ prestera_nh_neigh_find(struct prestera_switch *sw, nh_neigh = rhashtable_lookup_fast(&sw->router->nh_neigh_ht, key, __prestera_nh_neigh_ht_params); - return IS_ERR(nh_neigh) ? NULL : nh_neigh; + return nh_neigh; } struct prestera_nh_neigh * @@ -484,7 +484,7 @@ __prestera_nexthop_group_find(struct prestera_switch *sw, nh_grp = rhashtable_lookup_fast(&sw->router->nexthop_group_ht, key, __prestera_nexthop_group_ht_params); - return IS_ERR(nh_grp) ? NULL : nh_grp; + return nh_grp; } static struct prestera_nexthop_group * diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 7cd381530aa4..1d36619c5ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2378,8 +2378,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) data + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dma_dev, - dma_addr))) + dma_addr))) { + skb_free_frag(data); return -ENOMEM; + } } rxd->rxd1 = (unsigned int)dma_addr; ring->data[i] = data; @@ -2996,8 +2998,10 @@ static int mtk_open(struct net_device *dev) int i; err = mtk_start_dma(eth); - if (err) + if (err) { + phylink_disconnect_phy(mac->phylink); return err; + } for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) mtk_ppe_start(eth->ppe[i]); @@ -4143,13 +4147,13 @@ static int mtk_probe(struct platform_device *pdev) eth->soc->offload_version, i); if (!eth->ppe[i]) { err = -ENOMEM; - goto err_free_dev; + goto err_deinit_ppe; } } err = mtk_eth_offload_init(eth); if (err) - goto err_free_dev; + goto err_deinit_ppe; } for (i = 0; i < MTK_MAX_DEVS; i++) { @@ -4159,7 +4163,7 @@ static int mtk_probe(struct platform_device *pdev) err = register_netdev(eth->netdev[i]); if (err) { dev_err(eth->dev, "error bringing up device\n"); - goto err_deinit_mdio; + goto err_deinit_ppe; } else netif_info(eth, probe, eth->netdev[i], "mediatek frame engine at 0x%08lx, irq %d\n", @@ -4177,7 +4181,8 @@ static int mtk_probe(struct platform_device *pdev) return 0; -err_deinit_mdio: +err_deinit_ppe: + mtk_ppe_deinit(eth); mtk_mdio_cleanup(eth); err_free_dev: mtk_free_dev(eth); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 2d8ca99f2467..784ecb2dc9fb 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -737,7 +737,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, MTK_PPE_ENTRIES * soc->foe_entry_size, &ppe->foe_phys, GFP_KERNEL); if (!foe) - return NULL; + goto err_free_l2_flows; ppe->foe_table = foe; @@ -745,11 +745,26 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, sizeof(*ppe->foe_flow); ppe->foe_flow = devm_kzalloc(dev, foe_flow_size, GFP_KERNEL); if (!ppe->foe_flow) - return NULL; + goto err_free_l2_flows; mtk_ppe_debugfs_init(ppe, index); return ppe; + +err_free_l2_flows: + rhashtable_destroy(&ppe->l2_flows); + return NULL; +} + +void mtk_ppe_deinit(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) { + if (!eth->ppe[i]) + return; + rhashtable_destroy(ð->ppe[i]->l2_flows); + } } static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index 0b7a67a958e4..a09c32539bcc 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -304,6 +304,7 @@ struct mtk_ppe { struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int version, int index); +void mtk_ppe_deinit(struct mtk_eth *eth); void mtk_ppe_start(struct mtk_ppe *ppe); int mtk_ppe_stop(struct mtk_ppe *ppe); diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index b149e601f673..48cfaa7eaf50 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -697,7 +697,8 @@ static int mlx4_create_zones(struct mlx4_dev *dev, err = mlx4_bitmap_init(*bitmap + k, 1, MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0, 0); - mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); + if (!err) + mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); } if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 2e0d59ca62b5..e7a894ba5c3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,8 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/tout.h" +#define CREATE_TRACE_POINTS +#include "diag/cmd_tracepoint.h" enum { CMD_IF_REV = 5, @@ -785,27 +787,14 @@ EXPORT_SYMBOL(mlx5_cmd_out_err); static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) { u16 opcode, op_mod; - u32 syndrome; - u8 status; u16 uid; - int err; - - syndrome = MLX5_GET(mbox_out, out, syndrome); - status = MLX5_GET(mbox_out, out, status); opcode = MLX5_GET(mbox_in, in, opcode); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); - err = cmd_status_to_err(status); - if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY) mlx5_cmd_out_err(dev, opcode, op_mod, out); - else - mlx5_core_dbg(dev, - "%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n", - mlx5_command_str(opcode), opcode, op_mod, uid, - cmd_status_str(status), status, syndrome, err); } int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) @@ -1016,6 +1005,7 @@ static void cmd_work_handler(struct work_struct *work) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* Skip sending command to fw if internal error */ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { ent->ret = -ENXIO; @@ -1023,7 +1013,6 @@ static void cmd_work_handler(struct work_struct *work) return; } - cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -1508,8 +1497,8 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, return -EFAULT; err = sscanf(outlen_str, "%d", &outlen); - if (err < 0) - return err; + if (err != 1) + return -EINVAL; ptr = kzalloc(outlen, GFP_KERNEL); if (!ptr) @@ -1672,8 +1661,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force cmd_ent_put(ent); /* timeout work was canceled */ if (!forced || /* Real FW completion */ - pci_channel_offline(dev->pdev) || /* FW is inaccessible */ - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + mlx5_cmd_is_down(dev) || /* No real FW completion is expected */ + !opcode_allowed(cmd, ent->op)) cmd_ent_put(ent); ent->ts2 = ktime_get_ns(); @@ -1892,6 +1881,16 @@ out_in: return err; } +static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) +{ + u32 syndrome = MLX5_GET(mbox_out, out, syndrome); + u8 status = MLX5_GET(mbox_out, out, status); + + trace_mlx5_cmd(mlx5_command_str(opcode), opcode, op_mod, + cmd_status_str(status), status, syndrome, + cmd_status_to_err(status)); +} + static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { @@ -1914,7 +1913,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, } /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ -static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out) +static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); u8 status = MLX5_GET(mbox_out, out, status); @@ -1922,8 +1921,10 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void * if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */ err = -EIO; - if (!err && status != MLX5_CMD_STAT_OK) + if (!err && status != MLX5_CMD_STAT_OK) { err = -EREMOTEIO; + mlx5_cmd_err_trace(dev, opcode, op_mod, out); + } cmd_status_log(dev, opcode, status, syndrome, err); return err; @@ -1951,9 +1952,9 @@ int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); - return err; + return cmd_status_err(dev, err, opcode, op_mod, out); } EXPORT_SYMBOL(mlx5_cmd_do); @@ -1997,8 +1998,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); + err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); } EXPORT_SYMBOL(mlx5_cmd_exec_polling); @@ -2034,7 +2036,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) struct mlx5_async_ctx *ctx; ctx = work->ctx; - status = cmd_status_err(ctx->dev, status, work->opcode, work->out); + status = cmd_status_err(ctx->dev, status, work->opcode, work->op_mod, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) complete(&ctx->inflight_done); @@ -2049,6 +2051,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; work->opcode = MLX5_GET(mbox_in, in, opcode); + work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h new file mode 100644 index 000000000000..406ebe17405f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_CMD_TP_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_CMD_TP_H_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +TRACE_EVENT(mlx5_cmd, + TP_PROTO(const char *command_str, u16 opcode, u16 op_mod, + const char *status_str, u8 status, u32 syndrome, int err), + TP_ARGS(command_str, opcode, op_mod, status_str, status, syndrome, err), + TP_STRUCT__entry(__string(command_str, command_str) + __field(u16, opcode) + __field(u16, op_mod) + __string(status_str, status_str) + __field(u8, status) + __field(u32, syndrome) + __field(int, err) + ), + TP_fast_assign(__assign_str(command_str, command_str); + __entry->opcode = opcode; + __entry->op_mod = op_mod; + __assign_str(status_str, status_str); + __entry->status = status; + __entry->syndrome = syndrome; + __entry->err = err; + ), + TP_printk("%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)", + __get_str(command_str), __entry->opcode, __entry->op_mod, + __get_str(status_str), __entry->status, __entry->syndrome, + __entry->err) +); + +#endif /* _MLX5_CMD_TP_H_ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE cmd_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 978a2bb8e122..21831386b26e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -638,7 +638,7 @@ static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer, trace_timestamp = (timestamp_event.timestamp & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); else - trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) | + trace_timestamp = ((timestamp_event.timestamp - 1) & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 5aff97914367..ff73d25bc6eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -224,15 +224,16 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW)) continue; - spec = &flow->attr->parse_attr->spec; - - /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; /* mark the flow's encap dest as non-valid */ esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; + esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL; + + /* update from encap rule to slow path rule */ + spec = &flow->attr->parse_attr->spec; + rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -251,6 +252,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); + e->pkt_reformat = NULL; } static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, @@ -762,8 +764,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid) + struct net_device **encap_dev) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -878,9 +879,8 @@ attach_flow: if (e->flags & MLX5_ENCAP_ENTRY_VALID) { attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - *encap_valid = true; } else { - *encap_valid = false; + flow_flag_set(flow, SLOW); } mutex_unlock(&esw->offloads.encap_tbl_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index d542b8476491..8ad273dde40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -17,8 +17,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid); + struct net_device **encap_dev); int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index 285d32d2fd08..d7c020f72401 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -365,7 +365,7 @@ void mlx5e_accel_fs_tcp_destroy(struct mlx5e_flow_steering *fs) for (i = 0; i < ACCEL_FS_TCP_NUM_TYPES; i++) accel_fs_tcp_destroy_table(fs, i); - kfree(accel_tcp); + kvfree(accel_tcp); mlx5e_fs_set_accel_tcp(fs, NULL); } @@ -397,7 +397,7 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs) err_destroy_tables: while (--i >= 0) accel_fs_tcp_destroy_table(fs, i); - kfree(accel_tcp); + kvfree(accel_tcp); mlx5e_fs_set_accel_tcp(fs, NULL); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 2ef36cb9555a..f900709639f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -368,15 +368,15 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, obj_attrs.aso_pdn = macsec->aso.pdn; obj_attrs.epn_state = sa->epn_state; - if (is_tx) { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci); - key = &ctx->sa.tx_sa->key; - } else { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); - key = &ctx->sa.rx_sa->key; + key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key; + + if (sa->epn_state.epn_enabled) { + obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) : + cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); + + memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); } - memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); obj_attrs.replay_window = ctx->secy->replay_window; obj_attrs.replay_protect = ctx->secy->replay_protect; @@ -427,15 +427,15 @@ mlx5e_macsec_get_rx_sc_from_sc_list(const struct list_head *list, sci_t sci) return NULL; } -static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec, - struct mlx5e_macsec_sa *rx_sa, - bool active) +static int macsec_rx_sa_active_update(struct macsec_context *ctx, + struct mlx5e_macsec_sa *rx_sa, + bool active) { - struct mlx5_core_dev *mdev = macsec->mdev; - struct mlx5_macsec_obj_attrs attrs = {}; + struct mlx5e_priv *priv = netdev_priv(ctx->netdev); + struct mlx5e_macsec *macsec = priv->macsec; int err = 0; - if (rx_sa->active != active) + if (rx_sa->active == active) return 0; rx_sa->active = active; @@ -444,13 +444,11 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec, return 0; } - attrs.sci = cpu_to_be64((__force u64)rx_sa->sci); - attrs.enc_key_id = rx_sa->enc_key_id; - err = mlx5e_macsec_create_object(mdev, &attrs, false, &rx_sa->macsec_obj_id); + err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false); if (err) - return err; + rx_sa->active = false; - return 0; + return err; } static bool mlx5e_macsec_secy_features_validate(struct macsec_context *ctx) @@ -476,6 +474,11 @@ static bool mlx5e_macsec_secy_features_validate(struct macsec_context *ctx) return false; } + if (!ctx->secy->tx_sc.encrypt) { + netdev_err(netdev, "MACsec offload: encrypt off isn't supported\n"); + return false; + } + return true; } @@ -620,6 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) if (tx_sa->active == ctx_tx_sa->active) goto out; + tx_sa->active = ctx_tx_sa->active; if (tx_sa->assoc_num != tx_sc->encoding_sa) goto out; @@ -635,8 +639,6 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) mlx5e_macsec_cleanup_sa(macsec, tx_sa, true); } - - tx_sa->active = ctx_tx_sa->active; out: mutex_unlock(&macsec->lock); @@ -736,9 +738,14 @@ static int mlx5e_macsec_add_rxsc(struct macsec_context *ctx) sc_xarray_element->rx_sc = rx_sc; err = xa_alloc(&macsec->sc_xarray, &sc_xarray_element->fs_id, sc_xarray_element, - XA_LIMIT(1, USHRT_MAX), GFP_KERNEL); - if (err) + XA_LIMIT(1, MLX5_MACEC_RX_FS_ID_MAX), GFP_KERNEL); + if (err) { + if (err == -EBUSY) + netdev_err(ctx->netdev, + "MACsec offload: unable to create entry for RX SC (%d Rx SCs already allocated)\n", + MLX5_MACEC_RX_FS_ID_MAX); goto destroy_sc_xarray_elemenet; + } rx_sc->md_dst = metadata_dst_alloc(0, METADATA_MACSEC, GFP_KERNEL); if (!rx_sc->md_dst) { @@ -798,16 +805,16 @@ static int mlx5e_macsec_upd_rxsc(struct macsec_context *ctx) goto out; } - rx_sc->active = ctx_rx_sc->active; if (rx_sc->active == ctx_rx_sc->active) goto out; + rx_sc->active = ctx_rx_sc->active; for (i = 0; i < MACSEC_NUM_AN; ++i) { rx_sa = rx_sc->rx_sa[i]; if (!rx_sa) continue; - err = mlx5e_macsec_update_rx_sa(macsec, rx_sa, rx_sa->active && ctx_rx_sc->active); + err = macsec_rx_sa_active_update(ctx, rx_sa, rx_sa->active && ctx_rx_sc->active); if (err) goto out; } @@ -818,16 +825,43 @@ out: return err; } +static void macsec_del_rxsc_ctx(struct mlx5e_macsec *macsec, struct mlx5e_macsec_rx_sc *rx_sc) +{ + struct mlx5e_macsec_sa *rx_sa; + int i; + + for (i = 0; i < MACSEC_NUM_AN; ++i) { + rx_sa = rx_sc->rx_sa[i]; + if (!rx_sa) + continue; + + mlx5e_macsec_cleanup_sa(macsec, rx_sa, false); + mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); + + kfree(rx_sa); + rx_sc->rx_sa[i] = NULL; + } + + /* At this point the relevant MACsec offload Rx rule already removed at + * mlx5e_macsec_cleanup_sa need to wait for datapath to finish current + * Rx related data propagating using xa_erase which uses rcu to sync, + * once fs_id is erased then this rx_sc is hidden from datapath. + */ + list_del_rcu(&rx_sc->rx_sc_list_element); + xa_erase(&macsec->sc_xarray, rx_sc->sc_xarray_element->fs_id); + metadata_dst_free(rx_sc->md_dst); + kfree(rx_sc->sc_xarray_element); + kfree_rcu(rx_sc); +} + static int mlx5e_macsec_del_rxsc(struct macsec_context *ctx) { struct mlx5e_priv *priv = netdev_priv(ctx->netdev); struct mlx5e_macsec_device *macsec_device; struct mlx5e_macsec_rx_sc *rx_sc; - struct mlx5e_macsec_sa *rx_sa; struct mlx5e_macsec *macsec; struct list_head *list; int err = 0; - int i; mutex_lock(&priv->macsec->lock); @@ -849,31 +883,7 @@ static int mlx5e_macsec_del_rxsc(struct macsec_context *ctx) goto out; } - for (i = 0; i < MACSEC_NUM_AN; ++i) { - rx_sa = rx_sc->rx_sa[i]; - if (!rx_sa) - continue; - - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false); - mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); - - kfree(rx_sa); - rx_sc->rx_sa[i] = NULL; - } - -/* - * At this point the relevant MACsec offload Rx rule already removed at - * mlx5e_macsec_cleanup_sa need to wait for datapath to finish current - * Rx related data propagating using xa_erase which uses rcu to sync, - * once fs_id is erased then this rx_sc is hidden from datapath. - */ - list_del_rcu(&rx_sc->rx_sc_list_element); - xa_erase(&macsec->sc_xarray, rx_sc->sc_xarray_element->fs_id); - metadata_dst_free(rx_sc->md_dst); - kfree(rx_sc->sc_xarray_element); - - kfree_rcu(rx_sc); - + macsec_del_rxsc_ctx(macsec, rx_sc); out: mutex_unlock(&macsec->lock); @@ -1015,7 +1025,7 @@ static int mlx5e_macsec_upd_rxsa(struct macsec_context *ctx) goto out; } - err = mlx5e_macsec_update_rx_sa(macsec, rx_sa, ctx_rx_sa->active); + err = macsec_rx_sa_active_update(ctx, rx_sa, ctx_rx_sa->active); out: mutex_unlock(&macsec->lock); @@ -1155,7 +1165,7 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, false, false); + err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false); if (err) goto out; } @@ -1234,7 +1244,6 @@ static int mlx5e_macsec_del_secy(struct macsec_context *ctx) struct mlx5e_priv *priv = netdev_priv(ctx->netdev); struct mlx5e_macsec_device *macsec_device; struct mlx5e_macsec_rx_sc *rx_sc, *tmp; - struct mlx5e_macsec_sa *rx_sa; struct mlx5e_macsec_sa *tx_sa; struct mlx5e_macsec *macsec; struct list_head *list; @@ -1263,28 +1272,15 @@ static int mlx5e_macsec_del_secy(struct macsec_context *ctx) } list = &macsec_device->macsec_rx_sc_list_head; - list_for_each_entry_safe(rx_sc, tmp, list, rx_sc_list_element) { - for (i = 0; i < MACSEC_NUM_AN; ++i) { - rx_sa = rx_sc->rx_sa[i]; - if (!rx_sa) - continue; - - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false); - mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); - kfree(rx_sa); - rx_sc->rx_sa[i] = NULL; - } - - list_del_rcu(&rx_sc->rx_sc_list_element); - - kfree_rcu(rx_sc); - } + list_for_each_entry_safe(rx_sc, tmp, list, rx_sc_list_element) + macsec_del_rxsc_ctx(macsec, rx_sc); kfree(macsec_device->dev_addr); macsec_device->dev_addr = NULL; list_del_rcu(&macsec_device->macsec_device_list_element); --macsec->num_of_devices; + kfree(macsec_device); out: mutex_unlock(&macsec->lock); @@ -1536,6 +1532,8 @@ static void macsec_async_event(struct work_struct *work) async_work = container_of(work, struct mlx5e_macsec_async_work, work); macsec = async_work->macsec; + mutex_lock(&macsec->lock); + mdev = async_work->mdev; obj_id = async_work->obj_id; macsec_sa = get_macsec_tx_sa_from_obj_id(macsec, obj_id); @@ -1557,6 +1555,7 @@ static void macsec_async_event(struct work_struct *work) out_async_work: kfree(async_work); + mutex_unlock(&macsec->lock); } static int macsec_obj_change_event(struct notifier_block *nb, unsigned long event, void *data) @@ -1745,7 +1744,7 @@ void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, if (!macsec) return; - fs_id = MLX5_MACSEC_METADATA_HANDLE(macsec_meta_data); + fs_id = MLX5_MACSEC_RX_METADAT_HANDLE(macsec_meta_data); rcu_read_lock(); sc_xarray_element = xa_load(&macsec->sc_xarray, fs_id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h index d580b4a91253..347380a2cd9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h @@ -10,9 +10,11 @@ #include <net/macsec.h> #include <net/dst_metadata.h> -/* Bit31 - 30: MACsec marker, Bit3-0: MACsec id */ +/* Bit31 - 30: MACsec marker, Bit15-0: MACsec id */ +#define MLX5_MACEC_RX_FS_ID_MAX USHRT_MAX /* Must be power of two */ +#define MLX5_MACSEC_RX_FS_ID_MASK MLX5_MACEC_RX_FS_ID_MAX #define MLX5_MACSEC_METADATA_MARKER(metadata) ((((metadata) >> 30) & 0x3) == 0x1) -#define MLX5_MACSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(3, 0)) +#define MLX5_MACSEC_RX_METADAT_HANDLE(metadata) ((metadata) & MLX5_MACSEC_RX_FS_ID_MASK) struct mlx5e_priv; struct mlx5e_macsec; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 1ac0cf04e811..5b658a5588c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -250,7 +250,7 @@ static int macsec_fs_tx_create(struct mlx5e_macsec_fs *macsec_fs) struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; u32 *flow_group_in; - int err = 0; + int err; ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_EGRESS_MACSEC); if (!ns) @@ -261,8 +261,10 @@ static int macsec_fs_tx_create(struct mlx5e_macsec_fs *macsec_fs) return -ENOMEM; flow_group_in = kvzalloc(inlen, GFP_KERNEL); - if (!flow_group_in) + if (!flow_group_in) { + err = -ENOMEM; goto out_spec; + } tx_tables = &tx_fs->tables; ft_crypto = &tx_tables->ft_crypto; @@ -898,7 +900,7 @@ static int macsec_fs_rx_create(struct mlx5e_macsec_fs *macsec_fs) struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; u32 *flow_group_in; - int err = 0; + int err; ns = mlx5_get_flow_namespace(macsec_fs->mdev, MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC); if (!ns) @@ -909,8 +911,10 @@ static int macsec_fs_rx_create(struct mlx5e_macsec_fs *macsec_fs) return -ENOMEM; flow_group_in = kvzalloc(inlen, GFP_KERNEL); - if (!flow_group_in) + if (!flow_group_in) { + err = -ENOMEM; goto free_spec; + } rx_tables = &rx_fs->tables; ft_crypto = &rx_tables->ft_crypto; @@ -1142,10 +1146,10 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs, ft_crypto = &rx_tables->ft_crypto; /* Set bit[31 - 30] macsec marker - 0x01 */ - /* Set bit[3-0] fs id */ + /* Set bit[15-0] fs id */ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, fs_id | BIT(30)); + MLX5_SET(set_action_in, action, data, MLX5_MACSEC_RX_METADAT_HANDLE(fs_id) | BIT(30)); MLX5_SET(set_action_in, action, offset, 0); MLX5_SET(set_action_in, action, length, 32); @@ -1205,6 +1209,7 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs, rx_rule->rule[1] = rule; } + kvfree(spec); return macsec_rule; err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 24aa25da482b..1728e197558d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -35,7 +35,6 @@ #include "en.h" #include "en/port.h" #include "en/params.h" -#include "en/xsk/pool.h" #include "en/ptp.h" #include "lib/clock.h" #include "en/fs_ethtool.h" @@ -412,15 +411,8 @@ void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch) { mutex_lock(&priv->state_lock); - ch->max_combined = priv->max_nch; ch->combined_count = priv->channels.params.num_channels; - if (priv->xsk.refcnt) { - /* The upper half are XSK queues. */ - ch->max_combined *= 2; - ch->combined_count *= 2; - } - mutex_unlock(&priv->state_lock); } @@ -454,16 +446,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); - /* Don't allow changing the number of channels if there is an active - * XSK, because the numeration of the XSK and regular RQs will change. - */ - if (priv->xsk.refcnt) { - err = -EINVAL; - netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n", - __func__); - goto out; - } - /* Don't allow changing the number of channels if HTB offload is active, * because the numeration of the QoS SQs will change, while per-queue * qdiscs are attached. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e3a4f01bcceb..5e41dfdf79c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -206,10 +206,11 @@ static void mlx5e_disable_blocking_events(struct mlx5e_priv *priv) static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_mode) { u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode); + u32 sz; - WARN_ON_ONCE(entries * umr_entry_size % MLX5_OCTWORD); + sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); - return entries * umr_entry_size / MLX5_OCTWORD; + return sz / MLX5_OCTWORD; } static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 5a6aa61ec82a..bd9936af4582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1634,7 +1634,6 @@ set_encap_dests(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack, - bool *encap_valid, bool *vf_tun) { struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -1651,7 +1650,6 @@ set_encap_dests(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; - *encap_valid = true; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { struct net_device *out_dev; @@ -1668,7 +1666,7 @@ set_encap_dests(struct mlx5e_priv *priv, goto out; } err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev, encap_valid); + extack, &encap_dev); dev_put(out_dev); if (err) goto out; @@ -1732,8 +1730,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun, encap_valid; u32 max_prio, max_chain; + bool vf_tun; int err = 0; parse_attr = attr->parse_attr; @@ -1823,7 +1821,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -1853,7 +1851,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid || flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); @@ -3759,7 +3757,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *next_attr = NULL; struct mlx5e_post_act_handle *handle; - bool vf_tun, encap_valid = true; + bool vf_tun; int err; /* This is going in reverse order as needed. @@ -3781,13 +3779,10 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (list_is_last(&attr->list, &flow->attrs)) break; - err = set_encap_dests(flow->priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); if (err) goto out_free; - if (!encap_valid) - flow_flag_set(flow, SLOW); - err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); if (err) goto out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2169486c4bfb..374e3fbdc2cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1362,6 +1362,9 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) devl_rate_nodes_destroy(devlink); } + /* Destroy legacy fdb when disabling sriov in legacy mode. */ + if (esw->mode == MLX5_ESWITCH_LEGACY) + mlx5_eswitch_disable_locked(esw); esw->esw_funcs.num_vfs = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index f68dc2d0dbe6..3029bc1c0dd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -736,6 +736,14 @@ void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw); +static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw) +{ + if (mlx5_esw_allowed(esw)) + return esw->esw_funcs.num_vfs; + + return 0; +} + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 728ca9f2bb9d..8c6c9bcb3dc3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -433,7 +433,7 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f mlx5_lag_mpesw_is_activated(esw->dev)) dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; } - if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { + if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; flow_act->pkt_reformat = esw_attr->dests[attr_idx].pkt_reformat; @@ -3387,6 +3387,13 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, int err; esw->mode = MLX5_ESWITCH_LEGACY; + + /* If changing from switchdev to legacy mode without sriov enabled, + * no need to create legacy fdb. + */ + if (!mlx5_sriov_is_enabled(esw->dev)) + return 0; + err = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); if (err) NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 108a3503f413..edd910258314 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -312,6 +312,8 @@ revert_changes: for (curr_dest = 0; curr_dest < num_vport_dests; curr_dest++) { struct mlx5_termtbl_handle *tt = attr->dests[curr_dest].termtbl; + attr->dests[curr_dest].termtbl = NULL; + /* search for the destination associated with the * current term table */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 9d908a0ccfef..1e46f9afa40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -9,7 +9,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, MLX5_FW_RESET_FLAGS_PENDING_COMP, - MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, + MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED }; struct mlx5_fw_reset { @@ -406,7 +407,7 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) err = mlx5_pci_link_toggle(dev); if (err) { mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, no reset done, err %d\n", err); - goto done; + set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags); } mlx5_enter_error_state(dev, true); @@ -482,6 +483,10 @@ int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) goto out; } err = fw_reset->ret; + if (test_and_clear_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags)) { + mlx5_unload_one_devl_locked(dev); + mlx5_load_one_devl_locked(dev, false); + } out: clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index a9f4ede4a9bf..32c3e0a649a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -228,9 +228,8 @@ static void mlx5_ldev_free(struct kref *ref) if (ldev->nb.notifier_call) unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); - mlx5_lag_mpesw_cleanup(ldev); - cancel_work_sync(&ldev->mpesw_work); destroy_workqueue(ldev->wq); + mlx5_lag_mpesw_cleanup(ldev); mutex_destroy(&ldev->lock); kfree(ldev); } @@ -701,10 +700,13 @@ static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) return false; #ifdef CONFIG_MLX5_ESWITCH - dev = ldev->pf[MLX5_LAG_P1].dev; - if ((mlx5_sriov_is_enabled(dev)) && !is_mdev_switchdev_mode(dev)) - return false; + for (i = 0; i < ldev->ports; i++) { + dev = ldev->pf[i].dev; + if (mlx5_eswitch_num_vfs(dev->priv.eswitch) && !is_mdev_switchdev_mode(dev)) + return false; + } + dev = ldev->pf[MLX5_LAG_P1].dev; mode = mlx5_eswitch_mode(dev); for (i = 0; i < ldev->ports; i++) if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index ce2ce8ccbd70..f30ac2de639f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -50,6 +50,19 @@ struct lag_tracker { enum netdev_lag_hash hash_type; }; +enum mpesw_op { + MLX5_MPESW_OP_ENABLE, + MLX5_MPESW_OP_DISABLE, +}; + +struct mlx5_mpesw_work_st { + struct work_struct work; + struct mlx5_lag *lag; + enum mpesw_op op; + struct completion comp; + int result; +}; + /* LAG data of a ConnectX card. * It serves both its phys functions. */ @@ -66,7 +79,6 @@ struct mlx5_lag { struct lag_tracker tracker; struct workqueue_struct *wq; struct delayed_work bond_work; - struct work_struct mpesw_work; struct notifier_block nb; struct lag_mp lag_mp; struct mlx5_lag_port_sel port_sel; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index f643202b29c6..c17e8f1ec914 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -7,63 +7,95 @@ #include "eswitch.h" #include "lib/mlx5.h" -void mlx5_mpesw_work(struct work_struct *work) +static int add_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = container_of(work, struct mlx5_lag, mpesw_work); + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int err; - mutex_lock(&ldev->lock); - mlx5_disable_lag(ldev); - mutex_unlock(&ldev->lock); -} + if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) + return 0; -static void mlx5_lag_disable_mpesw(struct mlx5_core_dev *dev) -{ - struct mlx5_lag *ldev = dev->priv.lag; + if (ldev->mode != MLX5_LAG_MODE_NONE) { + err = -EINVAL; + goto out_err; + } - if (!queue_work(ldev->wq, &ldev->mpesw_work)) - mlx5_core_warn(dev, "failed to queue work\n"); + err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); + if (err) { + mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); + goto out_err; + } + + return 0; + +out_err: + atomic_dec(&ldev->lag_mpesw.mpesw_rule_count); + return err; } -void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +static void del_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = dev->priv.lag; + if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && + ldev->mode == MLX5_LAG_MODE_MPESW) + mlx5_disable_lag(ldev); +} - if (!ldev) - return; +static void mlx5_mpesw_work(struct work_struct *work) +{ + struct mlx5_mpesw_work_st *mpesww = container_of(work, struct mlx5_mpesw_work_st, work); + struct mlx5_lag *ldev = mpesww->lag; mutex_lock(&ldev->lock); - if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && - ldev->mode == MLX5_LAG_MODE_MPESW) - mlx5_lag_disable_mpesw(dev); + if (mpesww->op == MLX5_MPESW_OP_ENABLE) + mpesww->result = add_mpesw_rule(ldev); + else if (mpesww->op == MLX5_MPESW_OP_DISABLE) + del_mpesw_rule(ldev); mutex_unlock(&ldev->lock); + + complete(&mpesww->comp); } -int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +static int mlx5_lag_mpesw_queue_work(struct mlx5_core_dev *dev, + enum mpesw_op op) { struct mlx5_lag *ldev = dev->priv.lag; + struct mlx5_mpesw_work_st *work; int err = 0; if (!ldev) return 0; - mutex_lock(&ldev->lock); - if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) - goto out; + work = kzalloc(sizeof(*work), GFP_KERNEL); + if (!work) + return -ENOMEM; - if (ldev->mode != MLX5_LAG_MODE_NONE) { + INIT_WORK(&work->work, mlx5_mpesw_work); + init_completion(&work->comp); + work->op = op; + work->lag = ldev; + + if (!queue_work(ldev->wq, &work->work)) { + mlx5_core_warn(dev, "failed to queue mpesw work\n"); err = -EINVAL; goto out; } - - err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); - if (err) - mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); - + wait_for_completion(&work->comp); + err = work->result; out: - mutex_unlock(&ldev->lock); + kfree(work); return err; } +void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +{ + mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_DISABLE); +} + +int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +{ + return mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_ENABLE); +} + int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) { struct mlx5_lag *ldev = mdev->priv.lag; @@ -71,12 +103,9 @@ int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) if (!netif_is_bond_master(out_dev) || !ldev) return 0; - mutex_lock(&ldev->lock); - if (ldev->mode == MLX5_LAG_MODE_MPESW) { - mutex_unlock(&ldev->lock); + if (ldev->mode == MLX5_LAG_MODE_MPESW) return -EOPNOTSUPP; - } - mutex_unlock(&ldev->lock); + return 0; } @@ -90,11 +119,10 @@ bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev) void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) { - INIT_WORK(&ldev->mpesw_work, mlx5_mpesw_work); atomic_set(&ldev->lag_mpesw.mpesw_rule_count, 0); } void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev) { - cancel_delayed_work_sync(&ldev->bond_work); + WARN_ON(atomic_read(&ldev->lag_mpesw.mpesw_rule_count)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index be4abcb8fcd5..88e8daffcf92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -12,7 +12,6 @@ struct lag_mpesw { atomic_t mpesw_rule_count; }; -void mlx5_mpesw_work(struct work_struct *work); int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev); bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 283c4cc28944..e58775a7d955 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1798,7 +1798,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, res = state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; - mlx5_pci_trace(dev, "Exit, result = %d, %s\n", res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, result = %d, %s\n", + __func__, dev->state, dev->pci_status, res, result2str(res)); return res; } @@ -1837,7 +1838,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); int err; - mlx5_pci_trace(dev, "Enter\n"); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Enter\n", + __func__, dev->state, dev->pci_status); err = mlx5_pci_enable_device(dev); if (err) { @@ -1859,7 +1861,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) res = PCI_ERS_RESULT_RECOVERED; out: - mlx5_pci_trace(dev, "Exit, err = %d, result = %d, %s\n", err, res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, err = %d, result = %d, %s\n", + __func__, dev->state, dev->pci_status, err, res, result2str(res)); return res; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 7da012ff0d41..8e2abbab05f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -18,6 +18,10 @@ struct mlx5_sf_dev_table { phys_addr_t base_address; u64 sf_bar_length; struct notifier_block nb; + struct mutex table_lock; /* Serializes sf life cycle and vhca state change handler */ + struct workqueue_struct *active_wq; + struct work_struct work; + u8 stop_active_wq:1; struct mlx5_core_dev *dev; }; @@ -168,6 +172,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ return 0; sf_index = event->function_id - base_id; + mutex_lock(&table->table_lock); sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { case MLX5_VHCA_STATE_INVALID: @@ -191,6 +196,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ default: break; } + mutex_unlock(&table->table_lock); return 0; } @@ -215,6 +221,78 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) return 0; } +static void mlx5_sf_dev_add_active_work(struct work_struct *work) +{ + struct mlx5_sf_dev_table *table = container_of(work, struct mlx5_sf_dev_table, work); + u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; + struct mlx5_core_dev *dev = table->dev; + u16 max_functions; + u16 function_id; + u16 sw_func_id; + int err = 0; + u8 state; + int i; + + max_functions = mlx5_sf_max_functions(dev); + function_id = MLX5_CAP_GEN(dev, sf_base_id); + for (i = 0; i < max_functions; i++, function_id++) { + if (table->stop_active_wq) + return; + err = mlx5_cmd_query_vhca_state(dev, function_id, out, sizeof(out)); + if (err) + /* A failure of specific vhca doesn't mean others will + * fail as well. + */ + continue; + state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); + if (state != MLX5_VHCA_STATE_ACTIVE) + continue; + + sw_func_id = MLX5_GET(query_vhca_state_out, out, vhca_state_context.sw_function_id); + mutex_lock(&table->table_lock); + /* Don't probe device which is already probe */ + if (!xa_load(&table->devices, i)) + mlx5_sf_dev_add(dev, i, function_id, sw_func_id); + /* There is a race where SF got inactive after the query + * above. e.g.: the query returns that the state of the + * SF is active, and after that the eswitch manager set it to + * inactive. + * This case cannot be managed in SW, since the probing of the + * SF is on one system, and the inactivation is on a different + * system. + * If the inactive is done after the SF perform init_hca(), + * the SF will fully probe and then removed. If it was + * done before init_hca(), the SF probe will fail. + */ + mutex_unlock(&table->table_lock); + } +} + +/* In case SFs are generated externally, probe active SFs */ +static int mlx5_sf_dev_queue_active_work(struct mlx5_sf_dev_table *table) +{ + if (MLX5_CAP_GEN(table->dev, eswitch_manager)) + return 0; /* the table is local */ + + /* Use a workqueue to probe active SFs, which are in large + * quantity and may take up to minutes to probe. + */ + table->active_wq = create_singlethread_workqueue("mlx5_active_sf"); + if (!table->active_wq) + return -ENOMEM; + INIT_WORK(&table->work, &mlx5_sf_dev_add_active_work); + queue_work(table->active_wq, &table->work); + return 0; +} + +static void mlx5_sf_dev_destroy_active_work(struct mlx5_sf_dev_table *table) +{ + if (table->active_wq) { + table->stop_active_wq = true; + destroy_workqueue(table->active_wq); + } +} + void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) { struct mlx5_sf_dev_table *table; @@ -240,11 +318,17 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) table->base_address = pci_resource_start(dev->pdev, 2); table->max_sfs = max_sfs; xa_init(&table->devices); + mutex_init(&table->table_lock); dev->priv.sf_dev_table = table; err = mlx5_vhca_event_notifier_register(dev, &table->nb); if (err) goto vhca_err; + + err = mlx5_sf_dev_queue_active_work(table); + if (err) + goto add_active_err; + err = mlx5_sf_dev_vhca_arm_all(table); if (err) goto arm_err; @@ -252,6 +336,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) return; arm_err: + mlx5_sf_dev_destroy_active_work(table); +add_active_err: mlx5_vhca_event_notifier_unregister(dev, &table->nb); vhca_err: table->max_sfs = 0; @@ -279,7 +365,9 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) if (!table) return; + mlx5_sf_dev_destroy_active_work(table); mlx5_vhca_event_notifier_unregister(dev, &table->nb); + mutex_destroy(&table->table_lock); /* Now that event handler is not running, it is safe to destroy * the sf device without race. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c index 31d443dd8386..f68461b13391 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -46,7 +46,7 @@ static int dr_table_set_miss_action_nic(struct mlx5dr_domain *dmn, int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, struct mlx5dr_action *action) { - int ret; + int ret = -EOPNOTSUPP; if (action && action->action_type != DR_ACTION_TYP_FT) return -EOPNOTSUPP; @@ -67,6 +67,9 @@ int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, goto out; } + if (ret) + goto out; + /* Release old action */ if (tbl->miss_action) refcount_dec(&tbl->miss_action->refcount); diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c index 81a8ccca7e5e..5693784eec5b 100644 --- a/drivers/net/ethernet/microchip/encx24j600-regmap.c +++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c @@ -359,7 +359,7 @@ static int regmap_encx24j600_phy_reg_read(void *context, unsigned int reg, goto err_out; usleep_range(26, 100); - while ((ret = regmap_read(ctx->regmap, MISTAT, &mistat) != 0) && + while (((ret = regmap_read(ctx->regmap, MISTAT, &mistat)) == 0) && (mistat & BUSY)) cpu_relax(); @@ -397,7 +397,7 @@ static int regmap_encx24j600_phy_reg_write(void *context, unsigned int reg, goto err_out; usleep_range(26, 100); - while ((ret = regmap_read(ctx->regmap, MISTAT, &mistat) != 0) && + while (((ret = regmap_read(ctx->regmap, MISTAT, &mistat)) == 0) && (mistat & BUSY)) cpu_relax(); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c index 66360c8c5a38..141897dfe388 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c @@ -317,7 +317,7 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) next_dcb_hw = sparx5_fdma_next_dcb(tx, tx->curr_entry); db_hw = &next_dcb_hw->db[0]; if (!(db_hw->status & FDMA_DCB_STATUS_DONE)) - tx->dropped++; + return -EINVAL; db = list_first_entry(&tx->db_list, struct sparx5_db, list); list_move_tail(&db->list, &tx->db_list); next_dcb_hw->nextptr = FDMA_DCB_INVALID_DATA; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index eeac04b84638..b6bbb3c9bd7a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -887,6 +887,8 @@ static int mchp_sparx5_probe(struct platform_device *pdev) cleanup_ports: sparx5_cleanup_ports(sparx5); + if (sparx5->mact_queue) + destroy_workqueue(sparx5->mact_queue); cleanup_config: kfree(configs); cleanup_pnode: @@ -911,6 +913,7 @@ static int mchp_sparx5_remove(struct platform_device *pdev) sparx5_cleanup_ports(sparx5); /* Unregister netdevs */ sparx5_unregister_notifier_blocks(sparx5); + destroy_workqueue(sparx5->mact_queue); return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index 19516ccad533..d078156581d5 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -104,7 +104,7 @@ static int sparx5_port_open(struct net_device *ndev) err = phylink_of_phy_connect(port->phylink, port->of_node, 0); if (err) { netdev_err(ndev, "Could not attach to PHY\n"); - return err; + goto err_connect; } phylink_start(port->phylink); @@ -116,10 +116,20 @@ static int sparx5_port_open(struct net_device *ndev) err = sparx5_serdes_set(port->sparx5, port, &port->conf); else err = phy_power_on(port->serdes); - if (err) + if (err) { netdev_err(ndev, "%s failed\n", __func__); + goto out_power; + } } + return 0; + +out_power: + phylink_stop(port->phylink); + phylink_disconnect_phy(port->phylink); +err_connect: + sparx5_port_enable(port, false); + return err; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 83c16ca5b30f..6db6ac6a3bbc 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -234,9 +234,8 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) sparx5_set_port_ifh(ifh, port->portno); if (sparx5->ptp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - ret = sparx5_ptp_txtstamp_request(port, skb); - if (ret) - return ret; + if (sparx5_ptp_txtstamp_request(port, skb) < 0) + return NETDEV_TX_BUSY; sparx5_set_port_ifh_rew_op(ifh, SPARX5_SKB_CB(skb)->rew_op); sparx5_set_port_ifh_pdu_type(ifh, SPARX5_SKB_CB(skb)->pdu_type); @@ -250,23 +249,31 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) else ret = sparx5_inject(sparx5, ifh, skb, dev); - if (ret == NETDEV_TX_OK) { - stats->tx_bytes += skb->len; - stats->tx_packets++; + if (ret == -EBUSY) + goto busy; + if (ret < 0) + goto drop; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && - SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) - return ret; + stats->tx_bytes += skb->len; + stats->tx_packets++; + sparx5->tx.packets++; - dev_kfree_skb_any(skb); - } else { - stats->tx_dropped++; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + return NETDEV_TX_OK; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && - SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) - sparx5_ptp_txtstamp_release(port, skb); - } - return ret; + dev_consume_skb_any(skb); + return NETDEV_TX_OK; +drop: + stats->tx_dropped++; + sparx5->tx.dropped++; + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; +busy: + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + sparx5_ptp_txtstamp_release(port, skb); + return NETDEV_TX_BUSY; } static enum hrtimer_restart sparx5_injection_timeout(struct hrtimer *tmr) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index e05429c751ee..dc2c3756e3a2 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -90,13 +90,10 @@ static int sparx5_tc_setup_qdisc_ets(struct net_device *ndev, } } - sparx5_tc_ets_add(port, params); - break; + return sparx5_tc_ets_add(port, params); case TC_ETS_DESTROY: - sparx5_tc_ets_del(port); - - break; + return sparx5_tc_ets_del(port); case TC_ETS_GRAFT: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h index 4a6efe6ada08..65c24ee49efd 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ b/drivers/net/ethernet/microsoft/mana/gdma.h @@ -498,7 +498,14 @@ enum { #define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) -#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT +/* Advertise to the NIC firmware: the NAPI work_done variable race is fixed, + * so the driver is able to reliably support features like busy_poll. + */ +#define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) + +#define GDMA_DRV_CAP_FLAGS1 \ + (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ + GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9259a74eca40..27a0f3af8aab 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1303,10 +1303,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) xdp_do_flush(); } -static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) +static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; u8 arm_bit; + int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1315,26 +1316,31 @@ static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) else mana_poll_tx_cq(cq); - if (cq->work_done < cq->budget && - napi_complete_done(&cq->napi, cq->work_done)) { + w = cq->work_done; + + if (w < cq->budget && + napi_complete_done(&cq->napi, w)) { arm_bit = SET_ARM_BIT; } else { arm_bit = 0; } mana_gd_ring_cq(gdma_queue, arm_bit); + + return w; } static int mana_poll(struct napi_struct *napi, int budget) { struct mana_cq *cq = container_of(napi, struct mana_cq, napi); + int w; cq->work_done = 0; cq->budget = budget; - mana_cq_handler(cq, cq->gdma_cq); + w = mana_cq_handler(cq, cq->gdma_cq); - return min(cq->work_done, budget); + return min(w, budget); } static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue) diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index 2b427d8ccb2f..ccacb6ab6c39 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -282,7 +282,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) dma_len = skb_headlen(skb); if (skb_is_gso(skb)) type = NFDK_DESC_TX_TYPE_TSO; - else if (!nr_frags && dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + else if (!nr_frags && dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; @@ -927,7 +927,7 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, dma_len = pkt_len; dma_addr = rxbuf->dma_addr + dma_off; - if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; @@ -1325,7 +1325,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txbuf = &tx_ring->ktxbufs[wr_idx]; dma_len = skb_headlen(skb); - if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 405786c00334..cb08d7bf9524 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -341,7 +341,7 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) return ret; attrs.split = eth_port.is_split; - attrs.splittable = !attrs.split; + attrs.splittable = eth_port.port_lanes > 1 && !attrs.split; attrs.lanes = eth_port.port_lanes; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = eth_port.label_port; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1775997f9c69..991059d6cb32 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1432,6 +1432,9 @@ nfp_port_get_module_info(struct net_device *netdev, u8 data; port = nfp_port_from_netdev(netdev); + if (!port) + return -EOPNOTSUPP; + /* update port state to get latest interface */ set_bit(NFP_PORT_CHANGED, &port->flags); eth_port = nfp_port_get_eth_port(port); diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 19d043b593cc..62320be4de5a 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -249,25 +249,26 @@ static void nixge_hw_dma_bd_release(struct net_device *ndev) struct sk_buff *skb; int i; - for (i = 0; i < RX_BD_NUM; i++) { - phys_addr = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], - phys); - - dma_unmap_single(ndev->dev.parent, phys_addr, - NIXGE_MAX_JUMBO_FRAME_SIZE, - DMA_FROM_DEVICE); - - skb = (struct sk_buff *)(uintptr_t) - nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], - sw_id_offset); - dev_kfree_skb(skb); - } + if (priv->rx_bd_v) { + for (i = 0; i < RX_BD_NUM; i++) { + phys_addr = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + phys); + + dma_unmap_single(ndev->dev.parent, phys_addr, + NIXGE_MAX_JUMBO_FRAME_SIZE, + DMA_FROM_DEVICE); + + skb = (struct sk_buff *)(uintptr_t) + nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + sw_id_offset); + dev_kfree_skb(skb); + } - if (priv->rx_bd_v) dma_free_coherent(ndev->dev.parent, sizeof(*priv->rx_bd_v) * RX_BD_NUM, priv->rx_bd_v, priv->rx_bd_p); + } if (priv->tx_skb) devm_kfree(ndev->dev.parent, priv->tx_skb); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 3f2c30184752..28b7cec485ef 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -1143,6 +1143,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter, buffer_info->dma = 0; buffer_info->time_stamp = 0; tx_ring->next_to_use = ring_num; + dev_kfree_skb_any(skb); return; } buffer_info->mapped = true; @@ -2459,6 +2460,7 @@ static void pch_gbe_remove(struct pci_dev *pdev) unregister_netdev(netdev); pch_gbe_phy_hw_reset(&adapter->hw); + pci_dev_put(adapter->ptp_pdev); free_netdev(netdev); } @@ -2533,7 +2535,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, /* setup the private structure */ ret = pch_gbe_sw_init(adapter); if (ret) - goto err_free_netdev; + goto err_put_dev; /* Initialize PHY */ ret = pch_gbe_init_phy(adapter); @@ -2591,6 +2593,8 @@ static int pch_gbe_probe(struct pci_dev *pdev, err_free_adapter: pch_gbe_phy_hw_reset(&adapter->hw); +err_put_dev: + pci_dev_put(adapter->ptp_pdev); err_free_netdev: free_netdev(netdev); return ret; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 9fb1fa479d4b..16e6bd466143 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -767,34 +767,34 @@ static int qed_mcp_cancel_load_req(struct qed_hwfn *p_hwfn, return rc; } -#define CONFIG_QEDE_BITMAP_IDX BIT(0) -#define CONFIG_QED_SRIOV_BITMAP_IDX BIT(1) -#define CONFIG_QEDR_BITMAP_IDX BIT(2) -#define CONFIG_QEDF_BITMAP_IDX BIT(4) -#define CONFIG_QEDI_BITMAP_IDX BIT(5) -#define CONFIG_QED_LL2_BITMAP_IDX BIT(6) +#define BITMAP_IDX_FOR_CONFIG_QEDE BIT(0) +#define BITMAP_IDX_FOR_CONFIG_QED_SRIOV BIT(1) +#define BITMAP_IDX_FOR_CONFIG_QEDR BIT(2) +#define BITMAP_IDX_FOR_CONFIG_QEDF BIT(4) +#define BITMAP_IDX_FOR_CONFIG_QEDI BIT(5) +#define BITMAP_IDX_FOR_CONFIG_QED_LL2 BIT(6) static u32 qed_get_config_bitmap(void) { u32 config_bitmap = 0x0; if (IS_ENABLED(CONFIG_QEDE)) - config_bitmap |= CONFIG_QEDE_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QEDE; if (IS_ENABLED(CONFIG_QED_SRIOV)) - config_bitmap |= CONFIG_QED_SRIOV_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QED_SRIOV; if (IS_ENABLED(CONFIG_QED_RDMA)) - config_bitmap |= CONFIG_QEDR_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QEDR; if (IS_ENABLED(CONFIG_QED_FCOE)) - config_bitmap |= CONFIG_QEDF_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QEDF; if (IS_ENABLED(CONFIG_QED_ISCSI)) - config_bitmap |= CONFIG_QEDI_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QEDI; if (IS_ENABLED(CONFIG_QED_LL2)) - config_bitmap |= CONFIG_QED_LL2_BITMAP_IDX; + config_bitmap |= BITMAP_IDX_FOR_CONFIG_QED_LL2; return config_bitmap; } diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 76072f8c3d2f..0d57ffcedf0c 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2471,6 +2471,7 @@ static netdev_tx_t ql3xxx_send(struct sk_buff *skb, skb_shinfo(skb)->nr_frags); if (tx_cb->seg_count == -1) { netdev_err(ndev, "%s: invalid segment count!\n", __func__); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index bd0607680329..2fd5c6fdb500 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -2991,7 +2991,7 @@ static void qlcnic_83xx_recover_driver_lock(struct qlcnic_adapter *adapter) QLCWRX(adapter->ahw, QLC_83XX_RECOVER_DRV_LOCK, val); dev_info(&adapter->pdev->dev, "%s: lock recovery initiated\n", __func__); - msleep(QLC_83XX_DRV_LOCK_RECOVERY_DELAY); + mdelay(QLC_83XX_DRV_LOCK_RECOVERY_DELAY); val = QLCRDX(adapter->ahw, QLC_83XX_RECOVER_DRV_LOCK); id = ((val >> 2) & 0xF); if (id == adapter->portnum) { @@ -3027,7 +3027,7 @@ int qlcnic_83xx_lock_driver(struct qlcnic_adapter *adapter) if (status) break; - msleep(QLC_83XX_DRV_LOCK_WAIT_DELAY); + mdelay(QLC_83XX_DRV_LOCK_WAIT_DELAY); i++; if (i == 1) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 36324126db6d..33f723a9f471 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -841,7 +841,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); stats->rx_packets++; - stats->rx_bytes += priv->rx_1st_skb->len; + stats->rx_bytes += pkt_len; break; } } @@ -3020,6 +3020,7 @@ static int __maybe_unused ravb_resume(struct device *dev) ret = ravb_open(ndev); if (ret < 0) return ret; + ravb_set_rx_mode(ndev); netif_device_attach(ndev); } diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 88fa29572e23..ddcc325ed570 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -218,6 +218,7 @@ netdev_tx_t __ef100_hard_start_xmit(struct sk_buff *skb, skb->len, skb->data_len, channel->channel); if (!efx->n_channels || !efx->n_tx_channels || !channel) { netif_stop_queue(net_dev); + dev_kfree_skb_any(skb); goto err; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c25bfecb4a2d..e5cfde1cbd5c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -748,6 +748,8 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, if (fc & FLOW_RX) { pr_debug("\tReceive Flow-Control ON\n"); flow |= GMAC_RX_FLOW_CTRL_RFE; + } else { + pr_debug("\tReceive Flow-Control OFF\n"); } writel(flow, ioaddr + GMAC_RX_FLOW_CTRL); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6b43da78cdf0..23ec0a9e396c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1061,8 +1061,16 @@ static void stmmac_mac_link_up(struct phylink_config *config, ctrl |= priv->hw->link.duplex; /* Flow Control operation */ - if (tx_pause && rx_pause) - stmmac_mac_flow_ctrl(priv, duplex); + if (rx_pause && tx_pause) + priv->flow_ctrl = FLOW_AUTO; + else if (rx_pause && !tx_pause) + priv->flow_ctrl = FLOW_RX; + else if (!rx_pause && tx_pause) + priv->flow_ctrl = FLOW_TX; + else + priv->flow_ctrl = FLOW_OFF; + + stmmac_mac_flow_ctrl(priv, duplex); if (ctrl != old_ctrl) writel(ctrl, priv->ioaddr + MAC_CTRL_REG); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 50f6b4a14be4..eb6d9cd8e93f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -108,10 +108,10 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) axi->axi_lpi_en = of_property_read_bool(np, "snps,lpi_en"); axi->axi_xit_frm = of_property_read_bool(np, "snps,xit_frm"); - axi->axi_kbbe = of_property_read_bool(np, "snps,axi_kbbe"); - axi->axi_fb = of_property_read_bool(np, "snps,axi_fb"); - axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); - axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); + axi->axi_kbbe = of_property_read_bool(np, "snps,kbbe"); + axi->axi_fb = of_property_read_bool(np, "snps,fb"); + axi->axi_mb = of_property_read_bool(np, "snps,mb"); + axi->axi_rb = of_property_read_bool(np, "snps,rb"); if (of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt)) axi->axi_wr_osr_lmt = 1; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index c50b137f92d7..b3b0ba842541 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1454,7 +1454,7 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy if (speed == SPEED_1000) mac_control |= CPSW_SL_CTL_GIG; - if (speed == SPEED_10 && interface == PHY_INTERFACE_MODE_RGMII) + if (speed == SPEED_10 && phy_interface_mode_is_rgmii(interface)) /* Can be used with in band mode only */ mac_control |= CPSW_SL_CTL_EXT_EN; if (speed == SPEED_100 && interface == PHY_INTERFACE_MODE_RMII) @@ -2082,7 +2082,7 @@ static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common) for (i = 0; i < common->port_num; i++) { port = &common->ports[i]; - if (port->ndev) + if (port->ndev && port->ndev->reg_state == NETREG_REGISTERED) unregister_netdev(port->ndev); } } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 450b16ad40a4..e1a569b99e4a 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -885,7 +885,7 @@ static int ca8210_spi_transfer( dev_dbg(&spi->dev, "%s called\n", __func__); - cas_ctl = kmalloc(sizeof(*cas_ctl), GFP_ATOMIC); + cas_ctl = kzalloc(sizeof(*cas_ctl), GFP_ATOMIC); if (!cas_ctl) return -ENOMEM; diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index c69b87d3837d..edc769daad07 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -970,7 +970,7 @@ static int cc2520_hw_init(struct cc2520_private *priv) if (timeout-- <= 0) { dev_err(&priv->spi->dev, "oscillator start failed!\n"); - return ret; + return -ETIMEDOUT; } udelay(1); } while (!(status & CC2520_STATUS_XOSC32M_STABLE)); diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index de94921cbef9..025e0c19ec25 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -98,6 +98,7 @@ struct ipvl_port { struct sk_buff_head backlog; int count; struct ida ida; + netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 54c94a69c2bb..796a38f9d7b2 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -83,6 +83,7 @@ static int ipvlan_port_create(struct net_device *dev) if (err) goto err; + netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: @@ -95,6 +96,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; + netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 14e8d04cb434..2e9742952c4e 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -211,7 +211,7 @@ static __net_init int loopback_net_init(struct net *net) int err; err = -ENOMEM; - dev = alloc_netdev(0, "lo", NET_NAME_UNKNOWN, loopback_setup); + dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup); if (!dev) goto out; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 85376d2f24ca..2fbac51b9b19 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3698,6 +3698,7 @@ static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCB] = { .type = NLA_U8 }, [IFLA_MACSEC_REPLAY_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_VALIDATION] = { .type = NLA_U8 }, + [IFLA_MACSEC_OFFLOAD] = { .type = NLA_U8 }, }; static void macsec_free_netdev(struct net_device *dev) @@ -3835,7 +3836,6 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; - int ret; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 689e728345ce..b782c35c4ac1 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -98,6 +98,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, */ rc = phy_device_register(phy); if (rc) { + device_set_node(&phy->mdio.dev, NULL); fwnode_handle_put(child); return rc; } @@ -148,12 +149,13 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, /* Associate the fwnode with the device structure so it * can be looked up later. */ - phy->mdio.dev.fwnode = child; + phy->mdio.dev.fwnode = fwnode_handle_get(child); /* All data is now stored in the phy struct, so register it */ rc = phy_device_register(phy); if (rc) { - fwnode_handle_put(phy->mdio.dev.fwnode); + phy->mdio.dev.fwnode = NULL; + fwnode_handle_put(child); goto clean_phy; } } else if (is_of_node(child)) { diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 796e9c7857d0..510822d6d0d9 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -68,8 +68,9 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, /* All data is now stored in the mdiodev struct; register it. */ rc = mdio_device_register(mdiodev); if (rc) { + device_set_node(&mdiodev->dev, NULL); + fwnode_handle_put(fwnode); mdio_device_free(mdiodev); - of_node_put(child); return rc; } diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 464d88ca8ab0..a4abea921046 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -484,7 +484,14 @@ static int __init ntb_netdev_init_module(void) rc = ntb_transport_register_client_dev(KBUILD_MODNAME); if (rc) return rc; - return ntb_transport_register_client(&ntb_netdev_client); + + rc = ntb_transport_register_client(&ntb_netdev_client); + if (rc) { + ntb_transport_unregister_client_dev(KBUILD_MODNAME); + return rc; + } + + return 0; } module_init(ntb_netdev_init_module); diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 349b7b1dbbf2..d49965907561 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -870,8 +870,10 @@ static int at803x_probe(struct phy_device *phydev) .wolopts = 0, }; - if (ccr < 0) + if (ccr < 0) { + ret = ccr; goto err; + } mode_cfg = ccr & AT803X_MODE_CFG_MASK; switch (mode_cfg) { diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 250742ffdfd9..044828d081d2 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/unistd.h> +#include <linux/property.h> void mdio_device_free(struct mdio_device *mdiodev) { @@ -30,6 +31,7 @@ EXPORT_SYMBOL(mdio_device_free); static void mdio_device_release(struct device *dev) { + fwnode_handle_put(dev->fwnode); kfree(to_mdio_device(dev)); } diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 24bae27eedef..cae24091fb6f 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/bitfield.h> #include <linux/hwmon.h> +#include <linux/mutex.h> #include <linux/phy.h> #include <linux/polynomial.h> #include <linux/netdevice.h> @@ -70,6 +71,14 @@ #define VPSPEC1_TEMP_STA 0x0E #define VPSPEC1_TEMP_STA_DATA GENMASK(9, 0) +/* Mailbox */ +#define VSPEC1_MBOX_DATA 0x5 +#define VSPEC1_MBOX_ADDRLO 0x6 +#define VSPEC1_MBOX_CMD 0x7 +#define VSPEC1_MBOX_CMD_ADDRHI GENMASK(7, 0) +#define VSPEC1_MBOX_CMD_RD (0 << 8) +#define VSPEC1_MBOX_CMD_READY BIT(15) + /* WoL */ #define VPSPEC2_WOL_CTL 0x0E06 #define VPSPEC2_WOL_AD01 0x0E08 @@ -77,7 +86,13 @@ #define VPSPEC2_WOL_AD45 0x0E0A #define WOL_EN BIT(0) +/* Internal registers, access via mbox */ +#define REG_GPIO0_OUT 0xd3ce00 + struct gpy_priv { + /* serialize mailbox acesses */ + struct mutex mbox_lock; + u8 fw_major; u8 fw_minor; }; @@ -187,6 +202,45 @@ static int gpy_hwmon_register(struct phy_device *phydev) } #endif +static int gpy_mbox_read(struct phy_device *phydev, u32 addr) +{ + struct gpy_priv *priv = phydev->priv; + int val, ret; + u16 cmd; + + mutex_lock(&priv->mbox_lock); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_ADDRLO, + addr); + if (ret) + goto out; + + cmd = VSPEC1_MBOX_CMD_RD; + cmd |= FIELD_PREP(VSPEC1_MBOX_CMD_ADDRHI, addr >> 16); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_CMD, cmd); + if (ret) + goto out; + + /* The mbox read is used in the interrupt workaround. It was observed + * that a read might take up to 2.5ms. This is also the time for which + * the interrupt line is stuck low. To be on the safe side, poll the + * ready bit for 10ms. + */ + ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + VSPEC1_MBOX_CMD, val, + (val & VSPEC1_MBOX_CMD_READY), + 500, 10000, false); + if (ret) + goto out; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_DATA); + +out: + mutex_unlock(&priv->mbox_lock); + return ret; +} + static int gpy_config_init(struct phy_device *phydev) { int ret; @@ -201,6 +255,13 @@ static int gpy_config_init(struct phy_device *phydev) return ret < 0 ? ret : 0; } +static bool gpy_has_broken_mdint(struct phy_device *phydev) +{ + /* At least these PHYs are known to have broken interrupt handling */ + return phydev->drv->phy_id == PHY_ID_GPY215B || + phydev->drv->phy_id == PHY_ID_GPY215C; +} + static int gpy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -218,6 +279,7 @@ static int gpy_probe(struct phy_device *phydev) if (!priv) return -ENOMEM; phydev->priv = priv; + mutex_init(&priv->mbox_lock); fw_version = phy_read(phydev, PHY_FWV); if (fw_version < 0) @@ -492,6 +554,29 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev) if (!(reg & PHY_IMASK_MASK)) return IRQ_NONE; + /* The PHY might leave the interrupt line asserted even after PHY_ISTAT + * is read. To avoid interrupt storms, delay the interrupt handling as + * long as the PHY drives the interrupt line. An internal bus read will + * stall as long as the interrupt line is asserted, thus just read a + * random register here. + * Because we cannot access the internal bus at all while the interrupt + * is driven by the PHY, there is no way to make the interrupt line + * unstuck (e.g. by changing the pinmux to GPIO input) during that time + * frame. Therefore, polling is the best we can do and won't do any more + * harm. + * It was observed that this bug happens on link state and link speed + * changes on a GPY215B and GYP215C independent of the firmware version + * (which doesn't mean that this list is exhaustive). + */ + if (gpy_has_broken_mdint(phydev) && + (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) { + reg = gpy_mbox_read(phydev, REG_GPIO0_OUT); + if (reg < 0) { + phy_error(phydev); + return IRQ_NONE; + } + } + phy_trigger_machine(phydev); return IRQ_HANDLED; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 57849ac0384e..8cff61dbc4b5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -217,6 +217,7 @@ static void phy_mdio_device_free(struct mdio_device *mdiodev) static void phy_device_release(struct device *dev) { + fwnode_handle_put(dev->fwnode); kfree(to_phy_device(dev)); } @@ -1520,6 +1521,7 @@ error: error_module_put: module_put(d->driver->owner); + d->driver = NULL; error_put_device: put_device(d); if (ndev_owner != bus->owner) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 6547b6cc6cbe..2805b04d6402 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1603,19 +1603,29 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, linkmode_copy(supported, phy->supported); linkmode_copy(config.advertising, phy->advertising); - /* Clause 45 PHYs switch their Serdes lane between several different - * modes, normally 10GBASE-R, SGMII. Some use 2500BASE-X for 2.5G - * speeds. We really need to know which interface modes the PHY and - * MAC supports to properly work out which linkmodes can be supported. + /* Check whether we would use rate matching for the proposed interface + * mode. */ - if (phy->is_c45 && + config.rate_matching = phy_get_rate_matching(phy, interface); + + /* Clause 45 PHYs may switch their Serdes lane between, e.g. 10GBASE-R, + * 5GBASE-R, 2500BASE-X and SGMII if they are not using rate matching. + * For some interface modes (e.g. RXAUI, XAUI and USXGMII) switching + * their Serdes is either unnecessary or not reasonable. + * + * For these which switch interface modes, we really need to know which + * interface modes the PHY supports to properly work out which ethtool + * linkmodes can be supported. For now, as a work-around, we validate + * against all interface modes, which may lead to more ethtool link + * modes being advertised than are actually supported. + */ + if (phy->is_c45 && config.rate_matching == RATE_MATCH_NONE && interface != PHY_INTERFACE_MODE_RXAUI && interface != PHY_INTERFACE_MODE_XAUI && interface != PHY_INTERFACE_MODE_USXGMII) config.interface = PHY_INTERFACE_MODE_NA; else config.interface = interface; - config.rate_matching = phy_get_rate_matching(phy, config.interface); ret = phylink_validate(pl, supported, &config); if (ret) { diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index c8791e9b451d..40ce8abe6999 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -450,12 +450,12 @@ plip_bh_timeout_error(struct net_device *dev, struct net_local *nl, } rcv->state = PLIP_PK_DONE; if (rcv->skb) { - kfree_skb(rcv->skb); + dev_kfree_skb_irq(rcv->skb); rcv->skb = NULL; } snd->state = PLIP_PK_DONE; if (snd->skb) { - dev_kfree_skb(snd->skb); + dev_consume_skb_irq(snd->skb); snd->skb = NULL; } spin_unlock_irq(&nl->lock); diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index a52ee2bf5575..6312f67f260e 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -914,6 +914,7 @@ static int tbnet_open(struct net_device *dev) eof_mask, tbnet_start_poll, net); if (!ring) { netdev_err(dev, "failed to allocate Rx ring\n"); + tb_xdomain_release_out_hopid(xd, hopid); tb_ring_free(net->tx_ring.ring); net->tx_ring.ring = NULL; return -ENOMEM; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7a3ab3427369..24001112c323 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -686,7 +686,6 @@ static void __tun_detach(struct tun_file *tfile, bool clean) if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); - sock_put(&tfile->sk); } } @@ -702,6 +701,9 @@ static void tun_detach(struct tun_file *tfile, bool clean) if (dev) netdev_state_change(dev); rtnl_unlock(); + + if (clean) + sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8d5cbda33f66..0897fdb6254b 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1915,6 +1915,7 @@ static const struct driver_info cdc_ncm_zlp_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, + .set_rx_mode = usbnet_cdc_update_filter, }; /* Same as cdc_ncm_info, but with FLAG_WWAN */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index afd6faa4c2ec..554d4e2a84a4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1423,6 +1423,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ + {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7106932c6f88..86e52454b5b5 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3949,12 +3949,11 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; free_unregister_netdev: - virtio_reset_device(vdev); - unregister_netdev(dev); free_failover: net_failover_destroy(vi->failover); free_vqs: + virtio_reset_device(vdev); cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d3e7b27eb933..6f1e560fb15c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -75,8 +75,14 @@ vmxnet3_enable_all_intrs(struct vmxnet3_adapter *adapter) for (i = 0; i < adapter->intr.num_intrs; i++) vmxnet3_enable_intr(adapter, i); - adapter->shared->devRead.intrConf.intrCtrl &= + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl &= + cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl &= cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } } @@ -85,8 +91,14 @@ vmxnet3_disable_all_intrs(struct vmxnet3_adapter *adapter) { int i; - adapter->shared->devRead.intrConf.intrCtrl |= + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl |= + cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } for (i = 0; i < adapter->intr.num_intrs; i++) vmxnet3_disable_intr(adapter, i); } @@ -1396,6 +1408,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, }; u32 num_pkts = 0; bool skip_page_frags = false; + bool encap_lro = false; struct Vmxnet3_RxCompDesc *rcd; struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; u16 segCnt = 0, mss = 0; @@ -1556,13 +1569,18 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, if (VMXNET3_VERSION_GE_2(adapter) && rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) { struct Vmxnet3_RxCompDescExt *rcdlro; + union Vmxnet3_GenericDesc *gdesc; + rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd; + gdesc = (union Vmxnet3_GenericDesc *)rcd; segCnt = rcdlro->segCnt; WARN_ON_ONCE(segCnt == 0); mss = rcdlro->mss; if (unlikely(segCnt <= 1)) segCnt = 0; + encap_lro = (le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)); } else { segCnt = 0; } @@ -1630,7 +1648,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, vmxnet3_rx_csum(adapter, skb, (union Vmxnet3_GenericDesc *)rcd); skb->protocol = eth_type_trans(skb, adapter->netdev); - if (!rcd->tcp || + if ((!rcd->tcp && !encap_lro) || !(adapter->netdev->features & NETIF_F_LRO)) goto not_lro; @@ -1639,7 +1657,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, SKB_GSO_TCPV4 : SKB_GSO_TCPV6; skb_shinfo(skb)->gso_size = mss; skb_shinfo(skb)->gso_segs = segCnt; - } else if (segCnt != 0 || skb->len > mtu) { + } else if ((segCnt != 0 || skb->len > mtu) && !encap_lro) { u32 hlen; hlen = vmxnet3_get_hdr_len(adapter, skb, @@ -1668,6 +1686,7 @@ not_lro: napi_gro_receive(&rq->napi, skb); ctx->skb = NULL; + encap_lro = false; num_pkts++; } diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index 9bbfff803357..b545d93c6e37 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -959,30 +959,51 @@ static inline void wilc_wfi_cfg_parse_ch_attr(u8 *buf, u32 len, u8 sta_ch) return; while (index + sizeof(*e) <= len) { + u16 attr_size; + e = (struct wilc_attr_entry *)&buf[index]; - if (e->attr_type == IEEE80211_P2P_ATTR_CHANNEL_LIST) + attr_size = le16_to_cpu(e->attr_len); + + if (index + sizeof(*e) + attr_size > len) + return; + + if (e->attr_type == IEEE80211_P2P_ATTR_CHANNEL_LIST && + attr_size >= (sizeof(struct wilc_attr_ch_list) - sizeof(*e))) ch_list_idx = index; - else if (e->attr_type == IEEE80211_P2P_ATTR_OPER_CHANNEL) + else if (e->attr_type == IEEE80211_P2P_ATTR_OPER_CHANNEL && + attr_size == (sizeof(struct wilc_attr_oper_ch) - sizeof(*e))) op_ch_idx = index; + if (ch_list_idx && op_ch_idx) break; - index += le16_to_cpu(e->attr_len) + sizeof(*e); + + index += sizeof(*e) + attr_size; } if (ch_list_idx) { - u16 attr_size; - struct wilc_ch_list_elem *e; - int i; + u16 elem_size; ch_list = (struct wilc_attr_ch_list *)&buf[ch_list_idx]; - attr_size = le16_to_cpu(ch_list->attr_len); - for (i = 0; i < attr_size;) { + /* the number of bytes following the final 'elem' member */ + elem_size = le16_to_cpu(ch_list->attr_len) - + (sizeof(*ch_list) - sizeof(struct wilc_attr_entry)); + for (unsigned int i = 0; i < elem_size;) { + struct wilc_ch_list_elem *e; + e = (struct wilc_ch_list_elem *)(ch_list->elem + i); + + i += sizeof(*e); + if (i > elem_size) + break; + + i += e->no_of_channels; + if (i > elem_size) + break; + if (e->op_class == WILC_WLAN_OPERATING_CLASS_2_4GHZ) { memset(e->ch_list, sta_ch, e->no_of_channels); break; } - i += e->no_of_channels; } } diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index eb1d1ba3a443..67df8221b5ae 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -482,14 +482,25 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies->data, ies->len); if (rsn_ie) { + int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; - param->mode_802_11i = 2; - param->rsn_found = true; /* extract RSN capabilities */ - offset += (rsn_ie[offset] * 4) + 2; - offset += (rsn_ie[offset] * 4) + 2; - memcpy(param->rsn_cap, &rsn_ie[offset], 2); + if (offset < rsn_ie_len) { + /* skip over pairwise suites */ + offset += (rsn_ie[offset] * 4) + 2; + + if (offset < rsn_ie_len) { + /* skip over authentication suites */ + offset += (rsn_ie[offset] * 4) + 2; + + if (offset + 1 < rsn_ie_len) { + param->mode_802_11i = 2; + param->rsn_found = true; + memcpy(param->rsn_cap, &rsn_ie[offset], 2); + } + } + } } if (param->rsn_found) { diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index 9c7a9a2a1f25..fc928b298a98 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -332,6 +332,7 @@ struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, if (!ipc_mux->ul_adb.pp_qlt[i]) { for (j = i - 1; j >= 0; j--) kfree(ipc_mux->ul_adb.pp_qlt[j]); + kfree(ipc_mux); return NULL; } } diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index d41e373f9c0a..d6b166fc5c0e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -365,7 +365,8 @@ static void ipc_mux_dl_cmd_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) /* Pass the DL packet to the netif layer. */ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, struct iosm_wwan *wwan, u32 offset, - u8 service_class, struct sk_buff *skb) + u8 service_class, struct sk_buff *skb, + u32 pkt_len) { struct sk_buff *dest_skb = skb_clone(skb, GFP_ATOMIC); @@ -373,7 +374,7 @@ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, return -ENOMEM; skb_pull(dest_skb, offset); - skb_set_tail_pointer(dest_skb, dest_skb->len); + skb_trim(dest_skb, pkt_len); /* Pass the packet to the netif layer. */ dest_skb->priority = service_class; @@ -429,7 +430,7 @@ static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux, static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) { - u32 pad_len, packet_offset; + u32 pad_len, packet_offset, adgh_len; struct iosm_wwan *wwan; struct mux_adgh *adgh; u8 *block = skb->data; @@ -470,10 +471,12 @@ static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, packet_offset = sizeof(*adgh) + pad_len; if_id += ipc_mux->wwan_q_offset; + adgh_len = le16_to_cpu(adgh->length); /* Pass the packet to the netif layer */ rc = ipc_mux_net_receive(ipc_mux, if_id, wwan, packet_offset, - adgh->service_class, skb); + adgh->service_class, skb, + adgh_len - packet_offset); if (rc) { dev_err(ipc_mux->dev, "mux adgh decoding error"); return; @@ -547,7 +550,7 @@ static int mux_dl_process_dg(struct iosm_mux *ipc_mux, struct mux_adbh *adbh, int if_id, int nr_of_dg) { u32 dl_head_pad_len = ipc_mux->session[if_id].dl_head_pad_len; - u32 packet_offset, i, rc; + u32 packet_offset, i, rc, dg_len; for (i = 0; i < nr_of_dg; i++, dg++) { if (le32_to_cpu(dg->datagram_index) @@ -562,11 +565,12 @@ static int mux_dl_process_dg(struct iosm_mux *ipc_mux, struct mux_adbh *adbh, packet_offset = le32_to_cpu(dg->datagram_index) + dl_head_pad_len; + dg_len = le16_to_cpu(dg->datagram_length); /* Pass the packet to the netif layer. */ rc = ipc_mux_net_receive(ipc_mux, if_id, ipc_mux->wwan, packet_offset, - dg->service_class, - skb); + dg->service_class, skb, + dg_len - dl_head_pad_len); if (rc) goto dg_error; } @@ -1207,10 +1211,9 @@ static int mux_ul_dg_update_tbl_index(struct iosm_mux *ipc_mux, qlth_n_ql_size, ul_list); ipc_mux_ul_adb_finish(ipc_mux); if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed, - IOSM_AGGR_MUX_SIG_ADBH)) { - dev_kfree_skb(src_skb); + IOSM_AGGR_MUX_SIG_ADBH)) return -ENOMEM; - } + ipc_mux->size_needed = le32_to_cpu(adb->adbh->block_length); ipc_mux->size_needed += offsetof(struct mux_adth, dg); @@ -1471,8 +1474,7 @@ void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb) ipc_mux->ul_data_pend_bytes); /* Reset the skb settings. */ - skb->tail = 0; - skb->len = 0; + skb_trim(skb, 0); /* Add the consumed ADB to the free list. */ skb_queue_tail((&ipc_mux->ul_adb.free_list), skb); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index d3d34d1c4704..5bf5a93937c9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -249,7 +249,7 @@ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) if (object->integer.value == 3) sleep_state = IPC_PCIE_D3L2; - kfree(object); + ACPI_FREE(object); default_ret: return sleep_state; diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.h b/drivers/net/wwan/iosm/iosm_ipc_protocol.h index 9b3a6d86ece7..289397c4ea6c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_protocol.h +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.h @@ -122,7 +122,7 @@ struct iosm_protocol { struct iosm_imem *imem; struct ipc_rsp *rsp_ring[IPC_MEM_MSG_ENTRIES]; struct device *dev; - phys_addr_t phy_ap_shm; + dma_addr_t phy_ap_shm; u32 old_msg_tail; }; diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 3458af31e864..7d0f5e4f0a78 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -165,6 +165,8 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name) return -EFAULT; } + kfree(buffer.pointer); + #endif return 0; } diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 1545cbee77a4..3dbfc8a6924e 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -386,7 +386,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 650fa180220f..f3f2c07423a6 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -254,14 +254,16 @@ xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) skb_clear_hash(skb); - xenvif_rx_queue_tail(queue, skb); + if (!xenvif_rx_queue_tail(queue, skb)) + goto drop; + xenvif_kick_thread(queue); return NETDEV_TX_OK; drop: vif->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3d2081bbbc86..bf627af723bf 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -332,10 +332,13 @@ static int xenvif_count_requests(struct xenvif_queue *queue, struct xenvif_tx_cb { - u16 pending_idx; + u16 copy_pending_idx[XEN_NETBK_LEGACY_SLOTS_MAX + 1]; + u8 copy_count; }; #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) +#define copy_pending_idx(skb, i) (XENVIF_TX_CB(skb)->copy_pending_idx[i]) +#define copy_count(skb) (XENVIF_TX_CB(skb)->copy_count) static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, u16 pending_idx, @@ -370,31 +373,93 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) return skb; } -static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_map_grant_ref *gop, - unsigned int frag_overflow, - struct sk_buff *nskb) +static void xenvif_get_requests(struct xenvif_queue *queue, + struct sk_buff *skb, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txfrags, + unsigned *copy_ops, + unsigned *map_ops, + unsigned int frag_overflow, + struct sk_buff *nskb, + unsigned int extra_count, + unsigned int data_len) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; - int start; + u16 pending_idx; pending_ring_idx_t index; unsigned int nr_slots; + struct gnttab_copy *cop = queue->tx_copy_ops + *copy_ops; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; + struct xen_netif_tx_request *txp = first; + + nr_slots = shinfo->nr_frags + 1; + + copy_count(skb) = 0; + + /* Create copy ops for exactly data_len bytes into the skb head. */ + __skb_put(skb, data_len); + while (data_len > 0) { + int amount = data_len > txp->size ? txp->size : data_len; + + cop->source.u.ref = txp->gref; + cop->source.domid = queue->vif->domid; + cop->source.offset = txp->offset; + + cop->dest.domid = DOMID_SELF; + cop->dest.offset = (offset_in_page(skb->data + + skb_headlen(skb) - + data_len)) & ~XEN_PAGE_MASK; + cop->dest.u.gmfn = virt_to_gfn(skb->data + skb_headlen(skb) + - data_len); + + cop->len = amount; + cop->flags = GNTCOPY_source_gref; - nr_slots = shinfo->nr_frags; + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; + callback_param(queue, pending_idx).ctx = NULL; + copy_pending_idx(skb, copy_count(skb)) = pending_idx; + copy_count(skb)++; + + cop++; + data_len -= amount; - /* Skip first skb fragment if it is on same page as header fragment. */ - start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + if (amount == txp->size) { + /* The copy op covered the full tx_request */ + + memcpy(&queue->pending_tx_info[pending_idx].req, + txp, sizeof(*txp)); + queue->pending_tx_info[pending_idx].extra_count = + (txp == first) ? extra_count : 0; + + if (txp == first) + txp = txfrags; + else + txp++; + queue->pending_cons++; + nr_slots--; + } else { + /* The copy op partially covered the tx_request. + * The remainder will be mapped. + */ + txp->offset += amount; + txp->size -= amount; + } + } - for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, txp++, gop++) { + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; - xenvif_tx_create_map_op(queue, pending_idx, txp, 0, gop); + xenvif_tx_create_map_op(queue, pending_idx, txp, + txp == first ? extra_count : 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + + if (txp == first) + txp = txfrags; + else + txp++; } if (frag_overflow) { @@ -415,7 +480,8 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que skb_shinfo(skb)->frag_list = nskb; } - return gop; + (*copy_ops) = cop - queue->tx_copy_ops; + (*map_ops) = gop - queue->tx_map_ops; } static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, @@ -451,7 +517,7 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct gnttab_copy **gopp_copy) { struct gnttab_map_grant_ref *gop_map = *gopp_map; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + u16 pending_idx; /* This always points to the shinfo of the skb being checked, which * could be either the first or the one on the frag_list */ @@ -462,24 +528,37 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct skb_shared_info *first_shinfo = NULL; int nr_frags = shinfo->nr_frags; const bool sharedslot = nr_frags && - frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; - int i, err; + frag_get_pending_idx(&shinfo->frags[0]) == + copy_pending_idx(skb, copy_count(skb) - 1); + int i, err = 0; - /* Check status of header. */ - err = (*gopp_copy)->status; - if (unlikely(err)) { - if (net_ratelimit()) - netdev_dbg(queue->vif->dev, - "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", - (*gopp_copy)->status, - pending_idx, - (*gopp_copy)->source.u.ref); - /* The first frag might still have this slot mapped */ - if (!sharedslot) - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_ERROR); + for (i = 0; i < copy_count(skb); i++) { + int newerr; + + /* Check status of header. */ + pending_idx = copy_pending_idx(skb, i); + + newerr = (*gopp_copy)->status; + if (likely(!newerr)) { + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } else { + err = newerr; + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", + (*gopp_copy)->status, + pending_idx, + (*gopp_copy)->source.u.ref); + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + } + (*gopp_copy)++; } - (*gopp_copy)++; check_frags: for (i = 0; i < nr_frags; i++, gop_map++) { @@ -526,14 +605,6 @@ check_frags: if (err) continue; - /* First error: if the header haven't shared a slot with the - * first frag, release it as well. - */ - if (!sharedslot) - xenvif_idx_release(queue, - XENVIF_TX_CB(skb)->pending_idx, - XEN_NETIF_RSP_OKAY); - /* Invalidate preceding fragments of this skb. */ for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); @@ -803,7 +874,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, unsigned *copy_ops, unsigned *map_ops) { - struct gnttab_map_grant_ref *gop = queue->tx_map_ops; struct sk_buff *skb, *nskb; int ret; unsigned int frag_overflow; @@ -885,8 +955,12 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, continue; } + data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN) ? + XEN_NETBACK_TX_COPY_LEN : txreq.size; + ret = xenvif_count_requests(queue, &txreq, extra_count, txfrags, work_to_do); + if (unlikely(ret < 0)) break; @@ -912,9 +986,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, index = pending_index(queue->pending_cons); pending_idx = queue->pending_ring[index]; - data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN && - ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? - XEN_NETBACK_TX_COPY_LEN : txreq.size; + if (ret >= XEN_NETBK_LEGACY_SLOTS_MAX - 1 && data_len < txreq.size) + data_len = txreq.size; skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { @@ -925,8 +998,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, } skb_shinfo(skb)->nr_frags = ret; - if (data_len < txreq.size) - skb_shinfo(skb)->nr_frags++; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ @@ -988,54 +1059,19 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, type); } - XENVIF_TX_CB(skb)->pending_idx = pending_idx; - - __skb_put(skb, data_len); - queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; - queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; - queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; - - queue->tx_copy_ops[*copy_ops].dest.u.gmfn = - virt_to_gfn(skb->data); - queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; - queue->tx_copy_ops[*copy_ops].dest.offset = - offset_in_page(skb->data) & ~XEN_PAGE_MASK; - - queue->tx_copy_ops[*copy_ops].len = data_len; - queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; - - (*copy_ops)++; - - if (data_len < txreq.size) { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - pending_idx); - xenvif_tx_create_map_op(queue, pending_idx, &txreq, - extra_count, gop); - gop++; - } else { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - INVALID_PENDING_IDX); - memcpy(&queue->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - queue->pending_tx_info[pending_idx].extra_count = - extra_count; - } - - queue->pending_cons++; - - gop = xenvif_get_requests(queue, skb, txfrags, gop, - frag_overflow, nskb); + xenvif_get_requests(queue, skb, &txreq, txfrags, copy_ops, + map_ops, frag_overflow, nskb, extra_count, + data_len); __skb_queue_tail(&queue->tx_queue, skb); queue->tx.req_cons = idx; - if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + if ((*map_ops >= ARRAY_SIZE(queue->tx_map_ops)) || (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) break; } - (*map_ops) = gop - queue->tx_map_ops; return; } @@ -1114,9 +1150,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; - unsigned data_len; - pending_idx = XENVIF_TX_CB(skb)->pending_idx; + pending_idx = copy_pending_idx(skb, 0); txp = &queue->pending_tx_info[pending_idx].req; /* Check the remap error code. */ @@ -1135,18 +1170,6 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) continue; } - data_len = skb->len; - callback_param(queue, pending_idx).ctx = NULL; - if (data_len < txp->size) { - /* Append the packet payload as a fragment. */ - txp->offset += data_len; - txp->size -= data_len; - } else { - /* Schedule a response immediately. */ - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_OKAY); - } - if (txp->flags & XEN_NETTXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; else if (txp->flags & XEN_NETTXF_data_validated) @@ -1332,7 +1355,7 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) /* Called after netfront has transmitted */ int xenvif_tx_action(struct xenvif_queue *queue, int budget) { - unsigned nr_mops, nr_cops = 0; + unsigned nr_mops = 0, nr_cops = 0; int work_done, ret; if (unlikely(!tx_work_todo(queue))) diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index 932762177110..0ba754ebc5ba 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -82,9 +82,10 @@ static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) return false; } -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) { unsigned long flags; + bool ret = true; spin_lock_irqsave(&queue->rx_queue.lock, flags); @@ -92,8 +93,7 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) struct net_device *dev = queue->vif->dev; netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); - kfree_skb(skb); - queue->vif->dev->stats.rx_dropped++; + ret = false; } else { if (skb_queue_empty(&queue->rx_queue)) xenvif_update_needed_slots(queue, skb); @@ -104,6 +104,8 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) } spin_unlock_irqrestore(&queue->rx_queue.lock, flags); + + return ret; } static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9af2b027c19c..dc404e05970c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1862,6 +1862,12 @@ static int netfront_resume(struct xenbus_device *dev) netif_tx_unlock_bh(info->netdev); xennet_disconnect_backend(info); + + rtnl_lock(); + if (info->queues) + xennet_destroy_queues(info); + rtnl_unlock(); + return 0; } diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 24436c9e54c9..97600826af69 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -112,8 +112,10 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, struct nfcmrvl_i2c_drv_data *drv_data = priv->drv_data; int ret; - if (test_bit(NFCMRVL_PHY_ERROR, &priv->flags)) + if (test_bit(NFCMRVL_PHY_ERROR, &priv->flags)) { + kfree_skb(skb); return -EREMOTEIO; + } ret = i2c_master_send(drv_data->i2c, skb->data, skb->len); diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 580cb6ecffee..66b198663387 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -73,11 +73,15 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct nxp_nci_info *info = nci_get_drvdata(ndev); int r; - if (!info->phy_ops->write) + if (!info->phy_ops->write) { + kfree_skb(skb); return -EOPNOTSUPP; + } - if (info->mode != NXP_NCI_MODE_NCI) + if (info->mode != NXP_NCI_MODE_NCI) { + kfree_skb(skb); return -EINVAL; + } r = info->phy_ops->write(info->phy_id, skb); if (r < 0) { diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 0270e05b68df..aec356880adf 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -105,6 +105,7 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) mutex_lock(&info->mutex); if (s3fwrn5_get_mode(info) != S3FWRN5_MODE_NCI) { + kfree_skb(skb); mutex_unlock(&info->mutex); return -EINVAL; } diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 7764b1a4c3cf..ec87dd21e054 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -312,6 +312,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, int r = 0; struct device *dev = &ndev->nfc_dev->dev; struct nfc_evt_transaction *transaction; + u32 aid_len; + u8 params_len; pr_debug("connectivity gate event: %x\n", event); @@ -325,26 +327,47 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, * Description Tag Length * AID 81 5 to 16 * PARAMETERS 82 0 to 255 + * + * The key differences are aid storage length is variably sized + * in the packet, but fixed in nfc_evt_transaction, and that + * the aid_len is u8 in the packet, but u32 in the structure, + * and the tags in the packet are not included in + * nfc_evt_transaction. + * + * size(b): 1 1 5-16 1 1 0-255 + * offset: 0 1 2 aid_len + 2 aid_len + 3 aid_len + 4 + * mem name: aid_tag(M) aid_len aid params_tag(M) params_len params + * example: 0x81 5-16 X 0x82 0-255 X */ - if (skb->len < NFC_MIN_AID_LENGTH + 2 && - skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) + if (skb->len < 2 || skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); - if (!transaction) - return -ENOMEM; + aid_len = skb->data[1]; - transaction->aid_len = skb->data[1]; - memcpy(transaction->aid, &skb->data[2], transaction->aid_len); + if (skb->len < aid_len + 4 || + aid_len > sizeof(transaction->aid)) + return -EPROTO; - /* Check next byte is PARAMETERS tag (82) */ - if (skb->data[transaction->aid_len + 2] != - NFC_EVT_TRANSACTION_PARAMS_TAG) + params_len = skb->data[aid_len + 3]; + + /* Verify PARAMETERS tag is (82), and final check that there is + * enough space in the packet to read everything. + */ + if (skb->data[aid_len + 2] != NFC_EVT_TRANSACTION_PARAMS_TAG || + skb->len < aid_len + 4 + params_len) return -EPROTO; - transaction->params_len = skb->data[transaction->aid_len + 3]; - memcpy(transaction->params, skb->data + - transaction->aid_len + 4, transaction->params_len); + transaction = devm_kzalloc(dev, sizeof(*transaction) + + params_len, GFP_KERNEL); + if (!transaction) + return -ENOMEM; + + transaction->aid_len = aid_len; + transaction->params_len = params_len; + + memcpy(transaction->aid, &skb->data[2], aid_len); + memcpy(transaction->params, &skb->data[aid_len + 4], + params_len); r = nfc_se_transaction(ndev->nfc_dev, host, transaction); break; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index da55ce45ac70..7e3893d06bab 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3095,10 +3095,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (!ctrl->identified) { unsigned int i; - ret = nvme_init_subsystem(ctrl, id); - if (ret) - goto out_free; - /* * Check for quirks. Quirk can depend on firmware version, * so, in principle, the set of quirks present can change @@ -3111,6 +3107,10 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (quirk_matches(id, &core_quirks[i])) ctrl->quirks |= core_quirks[i].quirks; } + + ret = nvme_init_subsystem(ctrl, id); + if (ret) + goto out_free; } memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -4304,7 +4304,7 @@ static void nvme_ns_remove(struct nvme_ns *ns) mutex_unlock(&ns->ctrl->subsys->lock); /* guarantee not available in head->list */ - synchronize_rcu(); + synchronize_srcu(&ns->head->srcu); if (!nvme_ns_head_multipath(ns->head)) nvme_cdev_del(&ns->cdev, &ns->cdev_device); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 93e2138a8b42..7e025b8948cb 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -174,11 +174,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns) struct nvme_ns_head *head = ns->head; sector_t capacity = get_capacity(head->disk); int node; + int srcu_idx; + srcu_idx = srcu_read_lock(&head->srcu); list_for_each_entry_rcu(ns, &head->list, siblings) { if (capacity != get_capacity(ns->disk)) clear_bit(NVME_NS_READY, &ns->flags); } + srcu_read_unlock(&head->srcu, srcu_idx); for_each_node(node) rcu_assign_pointer(head->current_path[node], NULL); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f4335519399d..488ad7dabeb8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -797,6 +797,8 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma); if (bv->bv_len > first_prp_len) cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len); + else + cmnd->dptr.prp2 = 0; return BLK_STS_OK; } diff --git a/drivers/nvmem/lan9662-otpc.c b/drivers/nvmem/lan9662-otpc.c index 377bf34c2946..56fc19f092a7 100644 --- a/drivers/nvmem/lan9662-otpc.c +++ b/drivers/nvmem/lan9662-otpc.c @@ -36,7 +36,7 @@ struct lan9662_otp { void __iomem *base; }; -static bool lan9662_otp_wait_flag_clear(void __iomem *reg, u32 flag) +static int lan9662_otp_wait_flag_clear(void __iomem *reg, u32 flag) { u32 val; diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c index b11c3c974b3d..80cb187f1481 100644 --- a/drivers/nvmem/rmem.c +++ b/drivers/nvmem/rmem.c @@ -37,9 +37,9 @@ static int rmem_read(void *context, unsigned int offset, * but as of Dec 2020 this isn't possible on arm64. */ addr = memremap(priv->mem->base, available, MEMREMAP_WB); - if (IS_ERR(addr)) { + if (!addr) { dev_err(priv->dev, "Failed to remap memory region\n"); - return PTR_ERR(addr); + return -ENOMEM; } count = memory_read_from_buffer(val, bytes, &off, addr, available); diff --git a/drivers/of/property.c b/drivers/of/property.c index 967f79b59016..134cfc980b70 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -993,8 +993,10 @@ of_fwnode_get_reference_args(const struct fwnode_handle *fwnode, nargs, index, &of_args); if (ret < 0) return ret; - if (!args) + if (!args) { + of_node_put(of_args.np); return 0; + } args->nargs = of_args.args_count; args->fwnode = of_fwnode_handle(of_args.np); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ba64284eaf9f..f1ec8931dfbc 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1613,7 +1613,7 @@ out: } static u32 hv_compose_msi_req_v1( - struct pci_create_interrupt *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt *int_pkt, u32 slot, u8 vector, u16 vector_count) { int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; @@ -1632,6 +1632,35 @@ static u32 hv_compose_msi_req_v1( } /* + * The vCPU selected by hv_compose_multi_msi_req_get_cpu() and + * hv_compose_msi_req_get_cpu() is a "dummy" vCPU because the final vCPU to be + * interrupted is specified later in hv_irq_unmask() and communicated to Hyper-V + * via the HVCALL_RETARGET_INTERRUPT hypercall. But the choice of dummy vCPU is + * not irrelevant because Hyper-V chooses the physical CPU to handle the + * interrupts based on the vCPU specified in message sent to the vPCI VSP in + * hv_compose_msi_msg(). Hyper-V's choice of pCPU is not visible to the guest, + * but assigning too many vPCI device interrupts to the same pCPU can cause a + * performance bottleneck. So we spread out the dummy vCPUs to influence Hyper-V + * to spread out the pCPUs that it selects. + * + * For the single-MSI and MSI-X cases, it's OK for hv_compose_msi_req_get_cpu() + * to always return the same dummy vCPU, because a second call to + * hv_compose_msi_msg() contains the "real" vCPU, causing Hyper-V to choose a + * new pCPU for the interrupt. But for the multi-MSI case, the second call to + * hv_compose_msi_msg() exits without sending a message to the vPCI VSP, so the + * original dummy vCPU is used. This dummy vCPU must be round-robin'ed so that + * the pCPUs are spread out. All interrupts for a multi-MSI device end up using + * the same pCPU, even though the vCPUs will be spread out by later calls + * to hv_irq_unmask(), but that is the best we can do now. + * + * With Hyper-V in Nov 2022, the HVCALL_RETARGET_INTERRUPT hypercall does *not* + * cause Hyper-V to reselect the pCPU based on the specified vCPU. Such an + * enhancement is planned for a future version. With that enhancement, the + * dummy vCPU selection won't matter, and interrupts for the same multi-MSI + * device will be spread across multiple pCPUs. + */ + +/* * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten * by subsequent retarget in hv_irq_unmask(). */ @@ -1640,18 +1669,39 @@ static int hv_compose_msi_req_get_cpu(const struct cpumask *affinity) return cpumask_first_and(affinity, cpu_online_mask); } -static u32 hv_compose_msi_req_v2( - struct pci_create_interrupt2 *int_pkt, const struct cpumask *affinity, - u32 slot, u8 vector, u16 vector_count) +/* + * Make sure the dummy vCPU values for multi-MSI don't all point to vCPU0. + */ +static int hv_compose_multi_msi_req_get_cpu(void) { + static DEFINE_SPINLOCK(multi_msi_cpu_lock); + + /* -1 means starting with CPU 0 */ + static int cpu_next = -1; + + unsigned long flags; int cpu; + spin_lock_irqsave(&multi_msi_cpu_lock, flags); + + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids, + false); + cpu = cpu_next; + + spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); + + return cpu; +} + +static u32 hv_compose_msi_req_v2( + struct pci_create_interrupt2 *int_pkt, int cpu, + u32 slot, u8 vector, u16 vector_count) +{ int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1660,18 +1710,15 @@ static u32 hv_compose_msi_req_v2( } static u32 hv_compose_msi_req_v3( - struct pci_create_interrupt3 *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt3 *int_pkt, int cpu, u32 slot, u32 vector, u16 vector_count) { - int cpu; - int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.reserved = 0; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1715,12 +1762,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_create_interrupt3 v3; } int_pkts; } __packed ctxt; + bool multi_msi; u64 trans_id; u32 size; int ret; + int cpu; + + msi_desc = irq_data_get_msi_desc(data); + multi_msi = !msi_desc->pci.msi_attrib.is_msix && + msi_desc->nvec_used > 1; /* Reuse the previous allocation */ - if (data->chip_data) { + if (data->chip_data && multi_msi) { int_desc = data->chip_data; msg->address_hi = int_desc->address >> 32; msg->address_lo = int_desc->address & 0xffffffff; @@ -1728,7 +1781,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - msi_desc = irq_data_get_msi_desc(data); pdev = msi_desc_to_pci_dev(msi_desc); dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; @@ -1738,11 +1790,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (!hpdev) goto return_null_message; + /* Free any previous message that might have already been composed. */ + if (data->chip_data && !multi_msi) { + int_desc = data->chip_data; + data->chip_data = NULL; + hv_int_desc_free(hpdev, int_desc); + } + int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); if (!int_desc) goto drop_reference; - if (!msi_desc->pci.msi_attrib.is_msix && msi_desc->nvec_used > 1) { + if (multi_msi) { /* * If this is not the first MSI of Multi MSI, we already have * a mapping. Can exit early. @@ -1767,9 +1826,11 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ vector = 32; vector_count = msi_desc->nvec_used; + cpu = hv_compose_multi_msi_req_get_cpu(); } else { vector = hv_msi_get_int_vector(data); vector_count = 1; + cpu = hv_compose_msi_req_get_cpu(dest); } /* @@ -1785,7 +1846,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) switch (hbus->protocol_version) { case PCI_PROTOCOL_VERSION_1_1: size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, - dest, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1794,7 +1854,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) case PCI_PROTOCOL_VERSION_1_2: case PCI_PROTOCOL_VERSION_1_3: size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, - dest, + cpu, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1802,7 +1862,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) case PCI_PROTOCOL_VERSION_1_4: size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3, - dest, + cpu, hpdev->desc.win_slot.slot, vector, vector_count); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 52ecd66ce357..047a8374b4fd 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -436,9 +436,14 @@ static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input) writel(value, padcfg0); } +static int __intel_gpio_get_gpio_mode(u32 value) +{ + return (value & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; +} + static int intel_gpio_get_gpio_mode(void __iomem *padcfg0) { - return (readl(padcfg0) & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; + return __intel_gpio_get_gpio_mode(readl(padcfg0)); } static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) @@ -1674,6 +1679,7 @@ EXPORT_SYMBOL_GPL(intel_pinctrl_get_soc_data); static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int pin) { const struct pin_desc *pd = pin_desc_get(pctrl->pctldev, pin); + u32 value; if (!pd || !intel_pad_usable(pctrl, pin)) return false; @@ -1688,6 +1694,25 @@ static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int gpiochip_line_is_irq(&pctrl->chip, intel_pin_to_gpio(pctrl, pin))) return true; + /* + * The firmware on some systems may configure GPIO pins to be + * an interrupt source in so called "direct IRQ" mode. In such + * cases the GPIO controller driver has no idea if those pins + * are being used or not. At the same time, there is a known bug + * in the firmwares that don't restore the pin settings correctly + * after suspend, i.e. by an unknown reason the Rx value becomes + * inverted. + * + * Hence, let's save and restore the pins that are configured + * as GPIOs in the input mode with GPIROUTIOXAPIC bit set. + * + * See https://bugzilla.kernel.org/show_bug.cgi?id=214749. + */ + value = readl(intel_get_padcfg(pctrl, pin, PADCFG0)); + if ((value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) && + (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO)) + return true; + return false; } diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c index 65d312967619..27f0a54e12bf 100644 --- a/drivers/pinctrl/mediatek/mtk-eint.c +++ b/drivers/pinctrl/mediatek/mtk-eint.c @@ -303,12 +303,15 @@ static struct irq_chip mtk_eint_irq_chip = { static unsigned int mtk_eint_hw_init(struct mtk_eint *eint) { - void __iomem *reg = eint->base + eint->regs->dom_en; + void __iomem *dom_en = eint->base + eint->regs->dom_en; + void __iomem *mask_set = eint->base + eint->regs->mask_set; unsigned int i; for (i = 0; i < eint->hw->ap_num; i += 32) { - writel(0xffffffff, reg); - reg += 4; + writel(0xffffffff, dom_en); + writel(0xffffffff, mask_set); + dom_en += 4; + mask_set += 4; } return 0; diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 67bec7ea0f8b..414ee6bb8ac9 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -727,7 +727,7 @@ static int pcs_allocate_pin_table(struct pcs_device *pcs) mux_bytes = pcs->width / BITS_PER_BYTE; - if (pcs->bits_per_mux) { + if (pcs->bits_per_mux && pcs->fmask) { pcs->bits_per_pin = fls(pcs->fmask); nr_pins = (pcs->size * BITS_PER_BYTE) / pcs->bits_per_pin; } else { diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index ef4ae977b8e0..439d282aafd1 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -739,8 +739,14 @@ static void amd_pmc_s2idle_prepare(void) static void amd_pmc_s2idle_check(void) { struct amd_pmc_dev *pdev = &pmc; + struct smu_metrics table; int rc; + /* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */ + if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) && + table.s0i3_last_entry_status) + usleep_range(10000, 20000); + /* Dump the IdleMask before we add to the STB */ amd_pmc_idlemask_read(pdev, pdev->dev, NULL); diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 863fabe05bdc..307ee6f71042 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -725,7 +725,14 @@ static int ab8500_btemp_probe(struct platform_device *pdev) /* Get thermal zone and ADC */ di->tz = thermal_zone_get_zone_by_name("battery-thermal"); if (IS_ERR(di->tz)) { - return dev_err_probe(dev, PTR_ERR(di->tz), + ret = PTR_ERR(di->tz); + /* + * This usually just means we are probing before the thermal + * zone, so just defer. + */ + if (ret == -ENODEV) + ret = -EPROBE_DEFER; + return dev_err_probe(dev, ret, "failed to get battery thermal zone\n"); } di->bat_ctrl = devm_iio_channel_get(dev, "bat_ctrl"); diff --git a/drivers/power/supply/ip5xxx_power.c b/drivers/power/supply/ip5xxx_power.c index 218e8e689a3f..00221e9c0bfc 100644 --- a/drivers/power/supply/ip5xxx_power.c +++ b/drivers/power/supply/ip5xxx_power.c @@ -352,7 +352,7 @@ static int ip5xxx_battery_get_property(struct power_supply *psy, ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATIADC_DAT0, IP5XXX_BATIADC_DAT1, &raw); - val->intval = DIV_ROUND_CLOSEST(raw * 745985, 1000); + val->intval = DIV_ROUND_CLOSEST(raw * 149197, 200); return 0; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index 635f051b0821..f20a6ac584cc 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -121,7 +121,7 @@ struct rk817_charger { #define ADC_TO_CHARGE_UAH(adc_value, res_div) \ (adc_value / 3600 * 172 / res_div) -static u8 rk817_chg_cur_to_reg(u32 chg_cur_ma) +static int rk817_chg_cur_to_reg(u32 chg_cur_ma) { if (chg_cur_ma >= 3500) return CHG_3_5A; @@ -864,8 +864,8 @@ static int rk817_battery_init(struct rk817_charger *charger, { struct rk808 *rk808 = charger->rk808; u32 tmp, max_chg_vol_mv, max_chg_cur_ma; - u8 max_chg_vol_reg, chg_term_i_reg, max_chg_cur_reg; - int ret, chg_term_ma; + u8 max_chg_vol_reg, chg_term_i_reg; + int ret, chg_term_ma, max_chg_cur_reg; u8 bulk_reg[2]; /* Get initial plug state */ @@ -1116,14 +1116,12 @@ static int rk817_charger_probe(struct platform_device *pdev) charger->bat_ps = devm_power_supply_register(&pdev->dev, &rk817_bat_desc, &pscfg); - - charger->chg_ps = devm_power_supply_register(&pdev->dev, - &rk817_chg_desc, &pscfg); - - if (IS_ERR(charger->chg_ps)) + if (IS_ERR(charger->bat_ps)) return dev_err_probe(dev, -EINVAL, "Battery failed to probe\n"); + charger->chg_ps = devm_power_supply_register(&pdev->dev, + &rk817_chg_desc, &pscfg); if (IS_ERR(charger->chg_ps)) return dev_err_probe(dev, -EINVAL, "Charger failed to probe\n"); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index bcccad8f7516..e8c00a884f1f 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5154,6 +5154,7 @@ static void regulator_dev_release(struct device *dev) { struct regulator_dev *rdev = dev_get_drvdata(dev); + debugfs_remove_recursive(rdev->debugfs); kfree(rdev->constraints); of_node_put(rdev->dev.of_node); kfree(rdev); @@ -5644,11 +5645,15 @@ wash: mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); + put_device(&rdev->dev); + rdev = NULL; clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); + if (rdev && rdev->dev.of_node) + of_node_put(rdev->dev.of_node); + kfree(rdev); kfree(config); - put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); @@ -5677,7 +5682,6 @@ void regulator_unregister(struct regulator_dev *rdev) mutex_lock(®ulator_list_mutex); - debugfs_remove_recursive(rdev->debugfs); WARN_ON(rdev->open_count); regulator_remove_coupling(rdev); unset_regulator_supplies(rdev); diff --git a/drivers/regulator/rt5759-regulator.c b/drivers/regulator/rt5759-regulator.c index 6b96899eb27e..8488417f4b2c 100644 --- a/drivers/regulator/rt5759-regulator.c +++ b/drivers/regulator/rt5759-regulator.c @@ -243,6 +243,7 @@ static int rt5759_regulator_register(struct rt5759_priv *priv) if (priv->chip_type == CHIP_TYPE_RT5759A) reg_desc->uV_step = RT5759A_STEP_UV; + memset(®_cfg, 0, sizeof(reg_cfg)); reg_cfg.dev = priv->dev; reg_cfg.of_node = np; reg_cfg.init_data = of_get_regulator_init_data(priv->dev, np, reg_desc); diff --git a/drivers/regulator/slg51000-regulator.c b/drivers/regulator/slg51000-regulator.c index 75a941fb3c2b..1b2eee95ad3f 100644 --- a/drivers/regulator/slg51000-regulator.c +++ b/drivers/regulator/slg51000-regulator.c @@ -457,6 +457,8 @@ static int slg51000_i2c_probe(struct i2c_client *client) chip->cs_gpiod = cs_gpiod; } + usleep_range(10000, 11000); + i2c_set_clientdata(client, chip); chip->chip_irq = client->irq; chip->dev = dev; diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c index 430265c404d6..f3856750944f 100644 --- a/drivers/regulator/twl6030-regulator.c +++ b/drivers/regulator/twl6030-regulator.c @@ -67,6 +67,7 @@ struct twlreg_info { #define TWL6030_CFG_STATE_SLEEP 0x03 #define TWL6030_CFG_STATE_GRP_SHIFT 5 #define TWL6030_CFG_STATE_APP_SHIFT 2 +#define TWL6030_CFG_STATE_MASK 0x03 #define TWL6030_CFG_STATE_APP_MASK (0x03 << TWL6030_CFG_STATE_APP_SHIFT) #define TWL6030_CFG_STATE_APP(v) (((v) & TWL6030_CFG_STATE_APP_MASK) >>\ TWL6030_CFG_STATE_APP_SHIFT) @@ -128,13 +129,14 @@ static int twl6030reg_is_enabled(struct regulator_dev *rdev) if (grp < 0) return grp; grp &= P1_GRP_6030; + val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); + val = TWL6030_CFG_STATE_APP(val); } else { + val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); + val &= TWL6030_CFG_STATE_MASK; grp = 1; } - val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); - val = TWL6030_CFG_STATE_APP(val); - return grp && (val == TWL6030_CFG_STATE_ON); } @@ -187,7 +189,12 @@ static int twl6030reg_get_status(struct regulator_dev *rdev) val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); - switch (TWL6030_CFG_STATE_APP(val)) { + if (info->features & TWL6032_SUBCLASS) + val &= TWL6030_CFG_STATE_MASK; + else + val = TWL6030_CFG_STATE_APP(val); + + switch (val) { case TWL6030_CFG_STATE_ON: return REGULATOR_STATUS_NORMAL; @@ -530,6 +537,7 @@ static const struct twlreg_info TWL6030_INFO_##label = { \ #define TWL6032_ADJUSTABLE_LDO(label, offset) \ static const struct twlreg_info TWL6032_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ @@ -562,6 +570,7 @@ static const struct twlreg_info TWLFIXED_INFO_##label = { \ #define TWL6032_ADJUSTABLE_SMPS(label, offset) \ static const struct twlreg_info TWLSMPS_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index cb83f81da416..df17f0f9cb0f 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -1954,7 +1954,7 @@ dasd_copy_pair_show(struct device *dev, break; } } - if (!copy->entry[i].primary) + if (i == DASD_CP_ENTRIES) goto out; /* print all secondary */ diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 662730f3b027..5d0b9991e91a 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4722,7 +4722,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, struct dasd_device *basedev; struct req_iterator iter; struct dasd_ccw_req *cqr; - unsigned int first_offs; unsigned int trkcount; unsigned long *idaws; unsigned int size; @@ -4756,7 +4755,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, last_trk = (blk_rq_pos(req) + blk_rq_sectors(req) - 1) / DASD_RAW_SECTORS_PER_TRACK; trkcount = last_trk - first_trk + 1; - first_offs = 0; if (rq_data_dir(req) == READ) cmd = DASD_ECKD_CCW_READ_TRACK; @@ -4800,13 +4798,13 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, if (use_prefix) { prefix_LRE(ccw++, data, first_trk, last_trk, cmd, basedev, - startdev, 1, first_offs + 1, trkcount, 0, 0); + startdev, 1, 0, trkcount, 0, 0); } else { define_extent(ccw++, data, first_trk, last_trk, cmd, basedev, 0); ccw[-1].flags |= CCW_FLAG_CC; data += sizeof(struct DE_eckd_data); - locate_record_ext(ccw++, data, first_trk, first_offs + 1, + locate_record_ext(ccw++, data, first_trk, 0, trkcount, cmd, basedev, 0, 0); } @@ -5500,7 +5498,7 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp) * Dump the range of CCWs into 'page' buffer * and return number of printed chars. */ -static int +static void dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) { int len, count; @@ -5518,16 +5516,21 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) else datap = (char *) ((addr_t) from->cda); - /* dump data (max 32 bytes) */ - for (count = 0; count < from->count && count < 32; count++) { - if (count % 8 == 0) len += sprintf(page + len, " "); - if (count % 4 == 0) len += sprintf(page + len, " "); + /* dump data (max 128 bytes) */ + for (count = 0; count < from->count && count < 128; count++) { + if (count % 32 == 0) + len += sprintf(page + len, "\n"); + if (count % 8 == 0) + len += sprintf(page + len, " "); + if (count % 4 == 0) + len += sprintf(page + len, " "); len += sprintf(page + len, "%02x", datap[count]); } len += sprintf(page + len, "\n"); from++; } - return len; + if (len > 0) + printk(KERN_ERR "%s", page); } static void @@ -5619,37 +5622,33 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, if (req) { /* req == NULL for unsolicited interrupts */ /* dump the Channel Program (max 140 Bytes per line) */ - /* Count CCW and print first CCWs (maximum 1024 % 140 = 7) */ + /* Count CCW and print first CCWs (maximum 7) */ first = req->cpaddr; for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++); to = min(first + 6, last); - len = sprintf(page, PRINTK_HEADER - " Related CP in req: %p\n", req); - dasd_eckd_dump_ccw_range(first, to, page + len); - printk(KERN_ERR "%s", page); + printk(KERN_ERR PRINTK_HEADER " Related CP in req: %p\n", req); + dasd_eckd_dump_ccw_range(first, to, page); /* print failing CCW area (maximum 4) */ /* scsw->cda is either valid or zero */ - len = 0; from = ++to; fail = (struct ccw1 *)(addr_t) irb->scsw.cmd.cpa; /* failing CCW */ if (from < fail - 2) { from = fail - 2; /* there is a gap - print header */ - len += sprintf(page, PRINTK_HEADER "......\n"); + printk(KERN_ERR PRINTK_HEADER "......\n"); } to = min(fail + 1, last); - len += dasd_eckd_dump_ccw_range(from, to, page + len); + dasd_eckd_dump_ccw_range(from, to, page + len); /* print last CCWs (maximum 2) */ + len = 0; from = max(from, ++to); if (from < last - 1) { from = last - 1; /* there is a gap - print header */ - len += sprintf(page + len, PRINTK_HEADER "......\n"); + printk(KERN_ERR PRINTK_HEADER "......\n"); } - len += dasd_eckd_dump_ccw_range(from, last, page + len); - if (len > 0) - printk(KERN_ERR "%s", page); + dasd_eckd_dump_ccw_range(from, last, page + len); } free_page((unsigned long) page); } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index d0ddf2cc9786..9327dcdd6e5e 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -401,7 +401,7 @@ dasd_ioctl_copy_pair_swap(struct block_device *bdev, void __user *argp) return -EFAULT; } if (memchr_inv(data.reserved, 0, sizeof(data.reserved))) { - pr_warn("%s: Ivalid swap data specified.\n", + pr_warn("%s: Invalid swap data specified\n", dev_name(&device->cdev->dev)); dasd_put_device(device); return DASD_COPYPAIRSWAP_INVALID; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 59ac98f2bd27..b02c631f3b71 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -233,8 +233,11 @@ static void __init ap_init_qci_info(void) if (!ap_qci_info) return; ap_qci_info_old = kzalloc(sizeof(*ap_qci_info_old), GFP_KERNEL); - if (!ap_qci_info_old) + if (!ap_qci_info_old) { + kfree(ap_qci_info); + ap_qci_info = NULL; return; + } if (ap_fetch_qci_info(ap_qci_info) != 0) { kfree(ap_qci_info); kfree(ap_qci_info_old); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9dc935886e9f..c6ded3fdd715 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -758,7 +758,6 @@ static void qeth_l2_br2dev_worker(struct work_struct *work) struct list_head *iter; int err = 0; - kfree(br2dev_event_work); QETH_CARD_TEXT_(card, 4, "b2dw%04lx", event); QETH_CARD_TEXT_(card, 4, "ma%012llx", ether_addr_to_u64(addr)); @@ -815,6 +814,7 @@ unlock: dev_put(brdev); dev_put(lsyncdev); dev_put(dstdev); + kfree(br2dev_event_work); } static int qeth_l2_br2dev_queue_work(struct net_device *brdev, diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 19223b075568..ab3ea529cca7 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -884,7 +884,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req) const bool is_srb = zfcp_fsf_req_is_status_read_buffer(req); struct zfcp_adapter *adapter = req->adapter; struct zfcp_qdio *qdio = adapter->qdio; - int req_id = req->req_id; + unsigned long req_id = req->req_id; zfcp_reqlist_add(adapter->req_list, req); diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index f77ee4051b00..3306de7170f6 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -3265,7 +3265,8 @@ void mpi3mr_process_op_reply_desc(struct mpi3mr_ioc *mrioc, } if (scmd->result != (DID_OK << 16) && (scmd->cmnd[0] != ATA_12) && - (scmd->cmnd[0] != ATA_16)) { + (scmd->cmnd[0] != ATA_16) && + mrioc->logging_level & MPI3_DEBUG_SCSI_ERROR) { ioc_info(mrioc, "%s :scmd->result 0x%x\n", __func__, scmd->result); scsi_print_command(scmd); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 629853662b82..bebda917b138 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7323,8 +7323,12 @@ static int sdebug_add_host_helper(int per_host_idx) dev_set_name(&sdbg_host->dev, "adapter%d", sdebug_num_hosts); error = device_register(&sdbg_host->dev); - if (error) + if (error) { + spin_lock(&sdebug_host_list_lock); + list_del(&sdbg_host->host_list); + spin_unlock(&sdebug_host_list_lock); goto clean; + } ++sdebug_num_hosts; return 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 6995c8979230..ac5ff0783b4f 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -312,7 +312,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd) * Ensure that all tasks observe the host state change before the * host_failed change. */ - call_rcu(&scmd->rcu, scsi_eh_inc_host_failed); + call_rcu_hurry(&scmd->rcu, scsi_eh_inc_host_failed); } /** diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index cd3db9684e52..f473c002fa4d 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -231,7 +231,7 @@ iscsi_create_endpoint(int dd_size) dev_set_name(&ep->dev, "ep-%d", id); err = device_register(&ep->dev); if (err) - goto free_id; + goto put_dev; err = sysfs_create_group(&ep->dev.kobj, &iscsi_endpoint_group); if (err) @@ -245,10 +245,12 @@ unregister_dev: device_unregister(&ep->dev); return NULL; -free_id: +put_dev: mutex_lock(&iscsi_ep_idr_mutex); idr_remove(&iscsi_ep_idr, id); mutex_unlock(&iscsi_ep_idr_mutex); + put_device(&ep->dev); + return NULL; free_ep: kfree(ep); return NULL; @@ -766,7 +768,7 @@ iscsi_create_iface(struct Scsi_Host *shost, struct iscsi_transport *transport, err = device_register(&iface->dev); if (err) - goto free_iface; + goto put_dev; err = sysfs_create_group(&iface->dev.kobj, &iscsi_iface_group); if (err) @@ -780,9 +782,8 @@ unreg_iface: device_unregister(&iface->dev); return NULL; -free_iface: - put_device(iface->dev.parent); - kfree(iface); +put_dev: + put_device(&iface->dev); return NULL; } EXPORT_SYMBOL_GPL(iscsi_create_iface); @@ -1251,15 +1252,15 @@ iscsi_create_flashnode_sess(struct Scsi_Host *shost, int index, err = device_register(&fnode_sess->dev); if (err) - goto free_fnode_sess; + goto put_dev; if (dd_size) fnode_sess->dd_data = &fnode_sess[1]; return fnode_sess; -free_fnode_sess: - kfree(fnode_sess); +put_dev: + put_device(&fnode_sess->dev); return NULL; } EXPORT_SYMBOL_GPL(iscsi_create_flashnode_sess); @@ -1299,15 +1300,15 @@ iscsi_create_flashnode_conn(struct Scsi_Host *shost, err = device_register(&fnode_conn->dev); if (err) - goto free_fnode_conn; + goto put_dev; if (dd_size) fnode_conn->dd_data = &fnode_conn[1]; return fnode_conn; -free_fnode_conn: - kfree(fnode_conn); +put_dev: + put_device(&fnode_conn->dev); return NULL; } EXPORT_SYMBOL_GPL(iscsi_create_flashnode_conn); @@ -4815,7 +4816,7 @@ iscsi_register_transport(struct iscsi_transport *tt) dev_set_name(&priv->dev, "%s", tt->name); err = device_register(&priv->dev); if (err) - goto free_priv; + goto put_dev; err = sysfs_create_group(&priv->dev.kobj, &iscsi_transport_group); if (err) @@ -4850,8 +4851,8 @@ iscsi_register_transport(struct iscsi_transport *tt) unregister_dev: device_unregister(&priv->dev); return NULL; -free_priv: - kfree(priv); +put_dev: + put_device(&priv->dev); return NULL; } EXPORT_SYMBOL_GPL(iscsi_register_transport); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index bc46721aa01c..3c5b7e4227b2 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -303,16 +303,21 @@ enum storvsc_request_type { }; /* - * SRB status codes and masks; a subset of the codes used here. + * SRB status codes and masks. In the 8-bit field, the two high order bits + * are flags, while the remaining 6 bits are an integer status code. The + * definitions here include only the subset of the integer status codes that + * are tested for in this driver. */ - #define SRB_STATUS_AUTOSENSE_VALID 0x80 #define SRB_STATUS_QUEUE_FROZEN 0x40 -#define SRB_STATUS_INVALID_LUN 0x20 -#define SRB_STATUS_SUCCESS 0x01 -#define SRB_STATUS_ABORTED 0x02 -#define SRB_STATUS_ERROR 0x04 -#define SRB_STATUS_DATA_OVERRUN 0x12 + +/* SRB status integer codes */ +#define SRB_STATUS_SUCCESS 0x01 +#define SRB_STATUS_ABORTED 0x02 +#define SRB_STATUS_ERROR 0x04 +#define SRB_STATUS_INVALID_REQUEST 0x06 +#define SRB_STATUS_DATA_OVERRUN 0x12 +#define SRB_STATUS_INVALID_LUN 0x20 #define SRB_STATUS(status) \ (status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN)) @@ -969,38 +974,25 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, void (*process_err_fn)(struct work_struct *work); struct hv_host_device *host_dev = shost_priv(host); - /* - * In some situations, Hyper-V sets multiple bits in the - * srb_status, such as ABORTED and ERROR. So process them - * individually, with the most specific bits first. - */ - - if (vm_srb->srb_status & SRB_STATUS_INVALID_LUN) { - set_host_byte(scmnd, DID_NO_CONNECT); - process_err_fn = storvsc_remove_lun; - goto do_work; - } + switch (SRB_STATUS(vm_srb->srb_status)) { + case SRB_STATUS_ERROR: + case SRB_STATUS_ABORTED: + case SRB_STATUS_INVALID_REQUEST: + if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) { + /* Check for capacity change */ + if ((asc == 0x2a) && (ascq == 0x9)) { + process_err_fn = storvsc_device_scan; + /* Retry the I/O that triggered this. */ + set_host_byte(scmnd, DID_REQUEUE); + goto do_work; + } - if (vm_srb->srb_status & SRB_STATUS_ABORTED) { - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID && - /* Capacity data has changed */ - (asc == 0x2a) && (ascq == 0x9)) { - process_err_fn = storvsc_device_scan; /* - * Retry the I/O that triggered this. + * Otherwise, let upper layer deal with the + * error when sense message is present */ - set_host_byte(scmnd, DID_REQUEUE); - goto do_work; - } - } - - if (vm_srb->srb_status & SRB_STATUS_ERROR) { - /* - * Let upper layer deal with error when - * sense message is present. - */ - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) return; + } /* * If there is an error; offline the device since all @@ -1023,6 +1015,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, default: set_host_byte(scmnd, DID_ERROR); } + return; + + case SRB_STATUS_INVALID_LUN: + set_host_byte(scmnd, DID_NO_CONNECT); + process_err_fn = storvsc_remove_lun; + goto do_work; + } return; diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index 1322b8cce5b7..ababb910b391 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -128,12 +128,15 @@ static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws) dw_spi_dma_sg_burst_init(dws); + pci_dev_put(dma_dev); + return 0; free_rxchan: dma_release_channel(dws->rxchan); dws->rxchan = NULL; err_exit: + pci_dev_put(dma_dev); return -EBUSY; } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 30d82cc7300b..d209930069cf 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -444,8 +444,7 @@ static unsigned int mx51_ecspi_clkdiv(struct spi_imx_data *spi_imx, unsigned int pre, post; unsigned int fin = spi_imx->spi_clk; - if (unlikely(fspi > fin)) - return 0; + fspi = min(fspi, fin); post = fls(fin) - fls(fspi); if (fin > fspi << post) @@ -1608,6 +1607,13 @@ static int spi_imx_transfer_one(struct spi_controller *controller, return spi_imx_pio_transfer_slave(spi, transfer); /* + * If we decided in spi_imx_can_dma() that we want to do a DMA + * transfer, the SPI transfer has already been mapped, so we + * have to do the DMA transfer here. + */ + if (spi_imx->usedma) + return spi_imx_dma_transfer(spi_imx, transfer); + /* * Calculate the estimated time in us the transfer runs. Find * the number of Hz per byte per polling limit. */ @@ -1618,9 +1624,6 @@ static int spi_imx_transfer_one(struct spi_controller *controller, if (transfer->len < byte_limit) return spi_imx_poll_transfer(spi, transfer); - if (spi_imx->usedma) - return spi_imx_dma_transfer(spi_imx, transfer); - return spi_imx_pio_transfer(spi, transfer); } diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index a33c9a3de395..d6aff909fc36 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1273,8 +1273,11 @@ static int mtk_spi_remove(struct platform_device *pdev) { struct spi_master *master = platform_get_drvdata(pdev); struct mtk_spi *mdata = spi_master_get_devdata(master); + int ret; - pm_runtime_disable(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) + return ret; mtk_spi_reset(mdata); @@ -1283,6 +1286,9 @@ static int mtk_spi_remove(struct platform_device *pdev) clk_unprepare(mdata->spi_hclk); } + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c index 10f0c5a6e0dc..9f356612ba7e 100644 --- a/drivers/spi/spi-tegra210-quad.c +++ b/drivers/spi/spi-tegra210-quad.c @@ -924,8 +924,9 @@ static int tegra_qspi_start_transfer_one(struct spi_device *spi, static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_device *spi) { struct tegra_qspi_client_data *cdata; + struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master); - cdata = devm_kzalloc(&spi->dev, sizeof(*cdata), GFP_KERNEL); + cdata = devm_kzalloc(tqspi->dev, sizeof(*cdata), GFP_KERNEL); if (!cdata) return NULL; diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 4407b56aa6d1..139031ccb700 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -397,6 +397,7 @@ static int tcm_loop_setup_hba_bus(struct tcm_loop_hba *tl_hba, int tcm_loop_host ret = device_register(&tl_hba->dev); if (ret) { pr_err("device_register() failed for tl_hba->dev: %d\n", ret); + put_device(&tl_hba->dev); return -ENODEV; } @@ -1073,7 +1074,7 @@ check_len: */ ret = tcm_loop_setup_hba_bus(tl_hba, tcm_loop_hba_no_cnt); if (ret) - goto out; + return ERR_PTR(ret); sh = tl_hba->sh; tcm_loop_hba_no_cnt++; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index f3947be13e2e..64f0e047c23d 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -80,7 +80,7 @@ static int optee_register_device(const uuid_t *device_uuid) rc = device_register(&optee_device->dev); if (rc) { pr_err("device registration failed, err: %d\n", rc); - kfree(optee_device); + put_device(&optee_device->dev); } return rc; diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index c67715f6f756..f9aa50ff14d4 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -600,11 +600,11 @@ int cdnsp_halt_endpoint(struct cdnsp_device *pdev, trace_cdnsp_ep_halt(value ? "Set" : "Clear"); - if (value) { - ret = cdnsp_cmd_stop_ep(pdev, pep); - if (ret) - return ret; + ret = cdnsp_cmd_stop_ep(pdev, pep); + if (ret) + return ret; + if (value) { if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_STOPPED) { cdnsp_queue_halt_endpoint(pdev, pep->idx); cdnsp_ring_cmd_db(pdev); @@ -613,10 +613,6 @@ int cdnsp_halt_endpoint(struct cdnsp_device *pdev, pep->ep_state |= EP_HALTED; } else { - /* - * In device mode driver can call reset endpoint command - * from any endpoint state. - */ cdnsp_queue_reset_ep(pdev, pep->idx); cdnsp_ring_cmd_db(pdev); ret = cdnsp_wait_for_cmd_compl(pdev); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 794e413800ae..2f29431f612e 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1763,10 +1763,15 @@ static u32 cdnsp_td_remainder(struct cdnsp_device *pdev, int trb_buff_len, unsigned int td_total_len, struct cdnsp_request *preq, - bool more_trbs_coming) + bool more_trbs_coming, + bool zlp) { u32 maxp, total_packet_count; + /* Before ZLP driver needs set TD_SIZE = 1. */ + if (zlp) + return 1; + /* One TRB with a zero-length data packet. */ if (!more_trbs_coming || (transferred == 0 && trb_buff_len == 0) || trb_buff_len == td_total_len) @@ -1960,7 +1965,8 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) /* Set the TRB length, TD size, and interrupter fields. */ remainder = cdnsp_td_remainder(pdev, enqd_len, trb_buff_len, full_len, preq, - more_trbs_coming); + more_trbs_coming, + zero_len_trb); length_field = TRB_LEN(trb_buff_len) | TRB_TD_SIZE(remainder) | TRB_INTR_TARGET(0); @@ -2025,7 +2031,7 @@ int cdnsp_queue_ctrl_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) if (preq->request.length > 0) { remainder = cdnsp_td_remainder(pdev, 0, preq->request.length, - preq->request.length, preq, 1); + preq->request.length, preq, 1, 0); length_field = TRB_LEN(preq->request.length) | TRB_TD_SIZE(remainder) | TRB_INTR_TARGET(0); @@ -2076,7 +2082,8 @@ int cdnsp_cmd_stop_ep(struct cdnsp_device *pdev, struct cdnsp_ep *pep) u32 ep_state = GET_EP_CTX_STATE(pep->out_ctx); int ret = 0; - if (ep_state == EP_STATE_STOPPED || ep_state == EP_STATE_DISABLED) { + if (ep_state == EP_STATE_STOPPED || ep_state == EP_STATE_DISABLED || + ep_state == EP_STATE_HALTED) { trace_cdnsp_ep_stopped_or_disabled(pep->out_ctx); goto ep_stopped; } @@ -2225,7 +2232,7 @@ static int cdnsp_queue_isoc_tx(struct cdnsp_device *pdev, /* Set the TRB length, TD size, & interrupter fields. */ remainder = cdnsp_td_remainder(pdev, running_total, trb_buff_len, td_len, preq, - more_trbs_coming); + more_trbs_coming, 0); length_field = TRB_LEN(trb_buff_len) | TRB_INTR_TARGET(0); diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 0ecf20eeceee..4be6a873bd07 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -37,15 +37,6 @@ struct dwc3_exynos { struct regulator *vdd10; }; -static int dwc3_exynos_remove_child(struct device *dev, void *unused) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int dwc3_exynos_probe(struct platform_device *pdev) { struct dwc3_exynos *exynos; @@ -142,7 +133,7 @@ static int dwc3_exynos_remove(struct platform_device *pdev) struct dwc3_exynos *exynos = platform_get_drvdata(pdev); int i; - device_for_each_child(&pdev->dev, NULL, dwc3_exynos_remove_child); + of_platform_depopulate(&pdev->dev); for (i = exynos->num_clks - 1; i >= 0; i--) clk_disable_unprepare(exynos->clks[i]); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 026d4029bda6..6d524fa76443 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -291,7 +291,8 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, * * DWC_usb3 3.30a and DWC_usb31 1.90a programming guide section 3.2.2 */ - if (dwc->gadget->speed <= USB_SPEED_HIGH) { + if (dwc->gadget->speed <= USB_SPEED_HIGH || + DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_ENDTRANSFER) { reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); if (unlikely(reg & DWC3_GUSB2PHYCFG_SUSPHY)) { saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; @@ -1023,12 +1024,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); - /* Clear out the ep descriptors for non-ep0 */ - if (dep->number > 1) { - dep->endpoint.comp_desc = NULL; - dep->endpoint.desc = NULL; - } - dwc3_remove_requests(dwc, dep, -ESHUTDOWN); dep->stream_capable = false; @@ -1043,6 +1038,12 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) mask |= (DWC3_EP_DELAY_STOP | DWC3_EP_TRANSFER_STARTED); dep->flags &= mask; + /* Clear out the ep descriptors for non-ep0 */ + if (dep->number > 1) { + dep->endpoint.comp_desc = NULL; + dep->endpoint.desc = NULL; + } + return 0; } diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index c4ed48d6b8a4..a189b08bba80 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -199,16 +199,6 @@ uvc_send_response(struct uvc_device *uvc, struct uvc_request_data *data) * V4L2 ioctls */ -struct uvc_format { - u8 bpp; - u32 fcc; -}; - -static struct uvc_format uvc_formats[] = { - { 16, V4L2_PIX_FMT_YUYV }, - { 0, V4L2_PIX_FMT_MJPEG }, -}; - static int uvc_v4l2_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { @@ -243,47 +233,6 @@ uvc_v4l2_get_format(struct file *file, void *fh, struct v4l2_format *fmt) } static int -uvc_v4l2_set_format(struct file *file, void *fh, struct v4l2_format *fmt) -{ - struct video_device *vdev = video_devdata(file); - struct uvc_device *uvc = video_get_drvdata(vdev); - struct uvc_video *video = &uvc->video; - struct uvc_format *format; - unsigned int imagesize; - unsigned int bpl; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(uvc_formats); ++i) { - format = &uvc_formats[i]; - if (format->fcc == fmt->fmt.pix.pixelformat) - break; - } - - if (i == ARRAY_SIZE(uvc_formats)) { - uvcg_info(&uvc->func, "Unsupported format 0x%08x.\n", - fmt->fmt.pix.pixelformat); - return -EINVAL; - } - - bpl = format->bpp * fmt->fmt.pix.width / 8; - imagesize = bpl ? bpl * fmt->fmt.pix.height : fmt->fmt.pix.sizeimage; - - video->fcc = format->fcc; - video->bpp = format->bpp; - video->width = fmt->fmt.pix.width; - video->height = fmt->fmt.pix.height; - video->imagesize = imagesize; - - fmt->fmt.pix.field = V4L2_FIELD_NONE; - fmt->fmt.pix.bytesperline = bpl; - fmt->fmt.pix.sizeimage = imagesize; - fmt->fmt.pix.colorspace = V4L2_COLORSPACE_SRGB; - fmt->fmt.pix.priv = 0; - - return 0; -} - -static int uvc_v4l2_try_format(struct file *file, void *fh, struct v4l2_format *fmt) { struct video_device *vdev = video_devdata(file); @@ -324,6 +273,27 @@ uvc_v4l2_try_format(struct file *file, void *fh, struct v4l2_format *fmt) } static int +uvc_v4l2_set_format(struct file *file, void *fh, struct v4l2_format *fmt) +{ + struct video_device *vdev = video_devdata(file); + struct uvc_device *uvc = video_get_drvdata(vdev); + struct uvc_video *video = &uvc->video; + int ret; + + ret = uvc_v4l2_try_format(file, fh, fmt); + if (ret) + return ret; + + video->fcc = fmt->fmt.pix.pixelformat; + video->bpp = fmt->fmt.pix.bytesperline * 8 / video->width; + video->width = fmt->fmt.pix.width; + video->height = fmt->fmt.pix.height; + video->imagesize = fmt->fmt.pix.sizeimage; + + return ret; +} + +static int uvc_v4l2_enum_frameintervals(struct file *file, void *fh, struct v4l2_frmivalenum *fival) { diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 098b62f7b701..c0143d38df83 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -577,7 +577,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, if (scr_readw(r) != vc->vc_video_erase_char) break; if (r != q && new_rows >= rows + logo_lines) { - save = kmalloc(array3_size(logo_lines, new_cols, 2), + save = kzalloc(array3_size(logo_lines, new_cols, 2), GFP_KERNEL); if (save) { int i = min(cols, new_cols); diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index f422f9c58ba7..1ea6d2e5b218 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -67,8 +67,27 @@ static bool is_vmpck_empty(struct snp_guest_dev *snp_dev) return true; } +/* + * If an error is received from the host or AMD Secure Processor (ASP) there + * are two options. Either retry the exact same encrypted request or discontinue + * using the VMPCK. + * + * This is because in the current encryption scheme GHCB v2 uses AES-GCM to + * encrypt the requests. The IV for this scheme is the sequence number. GCM + * cannot tolerate IV reuse. + * + * The ASP FW v1.51 only increments the sequence numbers on a successful + * guest<->ASP back and forth and only accepts messages at its exact sequence + * number. + * + * So if the sequence number were to be reused the encryption scheme is + * vulnerable. If the sequence number were incremented for a fresh IV the ASP + * will reject the request. + */ static void snp_disable_vmpck(struct snp_guest_dev *snp_dev) { + dev_alert(snp_dev->dev, "Disabling vmpck_id %d to prevent IV reuse.\n", + vmpck_id); memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN); snp_dev->vmpck = NULL; } @@ -321,34 +340,71 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in if (rc) return rc; - /* Call firmware to process the request */ + /* + * Call firmware to process the request. In this function the encrypted + * message enters shared memory with the host. So after this call the + * sequence number must be incremented or the VMPCK must be deleted to + * prevent reuse of the IV. + */ rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + + /* + * If the extended guest request fails due to having too small of a + * certificate data buffer, retry the same guest request without the + * extended data request in order to increment the sequence number + * and thus avoid IV reuse. + */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && + err == SNP_GUEST_REQ_INVALID_LEN) { + const unsigned int certs_npages = snp_dev->input.data_npages; + + exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + /* + * If this call to the firmware succeeds, the sequence number can + * be incremented allowing for continued use of the VMPCK. If + * there is an error reflected in the return value, this value + * is checked further down and the result will be the deletion + * of the VMPCK and the error code being propagated back to the + * user as an ioctl() return code. + */ + rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + + /* + * Override the error to inform callers the given extended + * request buffer size was too small and give the caller the + * required buffer size. + */ + err = SNP_GUEST_REQ_INVALID_LEN; + snp_dev->input.data_npages = certs_npages; + } + if (fw_err) *fw_err = err; - if (rc) - return rc; + if (rc) { + dev_alert(snp_dev->dev, + "Detected error from ASP request. rc: %d, fw_err: %llu\n", + rc, *fw_err); + goto disable_vmpck; + } - /* - * The verify_and_dec_payload() will fail only if the hypervisor is - * actively modifying the message header or corrupting the encrypted payload. - * This hints that hypervisor is acting in a bad faith. Disable the VMPCK so that - * the key cannot be used for any communication. The key is disabled to ensure - * that AES-GCM does not use the same IV while encrypting the request payload. - */ rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz); if (rc) { dev_alert(snp_dev->dev, - "Detected unexpected decode failure, disabling the vmpck_id %d\n", - vmpck_id); - snp_disable_vmpck(snp_dev); - return rc; + "Detected unexpected decode failure from ASP. rc: %d\n", + rc); + goto disable_vmpck; } /* Increment to new message sequence after payload decryption was successful. */ snp_inc_msg_seqno(snp_dev); return 0; + +disable_vmpck: + snp_disable_vmpck(snp_dev); + return rc; } static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index c0031a3ab42f..3ac5fcf98d0d 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -167,8 +167,8 @@ responded: clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags); } - if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && - rtt_us < server->probe.rtt) { + rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us); + if (rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; diff --git a/fs/afs/server.c b/fs/afs/server.c index 4981baf97835..b5237206eac3 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -406,7 +406,7 @@ void afs_put_server(struct afs_net *net, struct afs_server *server, if (!server) return; - a = atomic_inc_return(&server->active); + a = atomic_read(&server->active); zero = __refcount_dec_and_test(&server->ref, &r); trace_afs_server(debug_id, r - 1, a, reason); if (unlikely(zero)) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a9543f01184c..dcb510f38dda 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -4663,7 +4663,12 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, int ret; int i; - ASSERT(!path->nowait); + /* + * The nowait semantics are used only for write paths, where we don't + * use the tree mod log and sequence numbers. + */ + if (time_seq) + ASSERT(!path->nowait); nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) @@ -4683,7 +4688,14 @@ again: if (path->need_commit_sem) { path->need_commit_sem = 0; need_commit_sem = true; - down_read(&fs_info->commit_root_sem); + if (path->nowait) { + if (!down_read_trylock(&fs_info->commit_root_sem)) { + ret = -EAGAIN; + goto done; + } + } else { + down_read(&fs_info->commit_root_sem); + } } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); } @@ -4759,7 +4771,7 @@ again: next = c; ret = read_block_for_search(root, path, &next, level, slot, &key); - if (ret == -EAGAIN) + if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { @@ -4769,6 +4781,10 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && path->nowait) { + ret = -EAGAIN; + goto done; + } if (!ret && time_seq) { /* * If we don't get the lock, we may be racing @@ -4799,7 +4815,7 @@ again: ret = read_block_for_search(root, path, &next, level, 0, &key); - if (ret == -EAGAIN) + if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { @@ -4807,8 +4823,16 @@ again: goto done; } - if (!path->skip_locking) - btrfs_tree_read_lock(next); + if (!path->skip_locking) { + if (path->nowait) { + if (!btrfs_try_tree_read_lock(next)) { + ret = -EAGAIN; + goto done; + } + } else { + btrfs_tree_read_lock(next); + } + } } ret = 0; done: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d5dd8bed1488..5ba2e810dc6e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3105,6 +3105,8 @@ static int btrfs_ioctl_get_subvol_info(struct inode *inode, void __user *argp) } } + btrfs_free_path(path); + path = NULL; if (copy_to_user(argp, subvol_info, sizeof(*subvol_info))) ret = -EFAULT; @@ -3194,6 +3196,8 @@ static int btrfs_ioctl_get_subvol_rootref(struct btrfs_root *root, } out: + btrfs_free_path(path); + if (!ret || ret == -EOVERFLOW) { rootrefs->num_items = found; /* update min_treeid for next search */ @@ -3205,7 +3209,6 @@ out: } kfree(rootrefs); - btrfs_free_path(path); return ret; } @@ -4231,6 +4234,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) ipath->fspath->val[i] = rel_ptr; } + btrfs_free_path(path); + path = NULL; ret = copy_to_user((void __user *)(unsigned long)ipa->fspath, ipath->fspath, size); if (ret) { @@ -4281,21 +4286,20 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, size = min_t(u32, loi->size, SZ_16M); } - path = btrfs_alloc_path(); - if (!path) { - ret = -ENOMEM; - goto out; - } - inodes = init_data_container(size); if (IS_ERR(inodes)) { ret = PTR_ERR(inodes); - inodes = NULL; - goto out; + goto out_loi; } + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } ret = iterate_inodes_from_logical(loi->logical, fs_info, path, inodes, ignore_offset); + btrfs_free_path(path); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -4307,7 +4311,6 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, ret = -EFAULT; out: - btrfs_free_path(path); kvfree(inodes); out_loi: kfree(loi); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9334c3157c22..b74105a10f16 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2951,14 +2951,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, dstgroup->rsv_rfer = inherit->lim.rsv_rfer; dstgroup->rsv_excl = inherit->lim.rsv_excl; - ret = update_qgroup_limit_item(trans, dstgroup); - if (ret) { - qgroup_mark_inconsistent(fs_info); - btrfs_info(fs_info, - "unable to update quota limit for %llu", - dstgroup->qgroupid); - goto unlock; - } + qgroup_dirty(fs_info, dstgroup); } if (srcid) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 145c84b44fd0..1c4b693ee4a3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5702,6 +5702,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, u64 ext_len; u64 clone_len; u64 clone_data_offset; + bool crossed_src_i_size = false; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(clone_root->root, path); @@ -5759,8 +5760,10 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, if (key.offset >= clone_src_i_size) break; - if (key.offset + ext_len > clone_src_i_size) + if (key.offset + ext_len > clone_src_i_size) { ext_len = clone_src_i_size - key.offset; + crossed_src_i_size = true; + } clone_data_offset = btrfs_file_extent_offset(leaf, ei); if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte) { @@ -5821,6 +5824,25 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, ret = send_clone(sctx, offset, clone_len, clone_root); } + } else if (crossed_src_i_size && clone_len < len) { + /* + * If we are at i_size of the clone source inode and we + * can not clone from it, terminate the loop. This is + * to avoid sending two write operations, one with a + * length matching clone_len and the final one after + * this loop with a length of len - clone_len. + * + * When using encoded writes (BTRFS_SEND_FLAG_COMPRESSED + * was passed to the send ioctl), this helps avoid + * sending an encoded write for an offset that is not + * sector size aligned, in case the i_size of the source + * inode is not sector size aligned. That will make the + * receiver fallback to decompression of the data and + * writing it using regular buffered IO, therefore while + * not incorrect, it's not optimal due decompression and + * possible re-compression at the receiver. + */ + break; } else { ret = send_extent_data(sctx, dst_path, offset, clone_len); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 699b54b3acaa..74fef1f49c35 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -2321,8 +2321,11 @@ int __init btrfs_init_sysfs(void) #ifdef CONFIG_BTRFS_DEBUG ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group); - if (ret) - goto out2; + if (ret) { + sysfs_unmerge_group(&btrfs_kset->kobj, + &btrfs_static_feature_attr_group); + goto out_remove_group; + } #endif return 0; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 813986e38258..c3cf3dabe0b1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3694,15 +3694,29 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans, u64 *last_old_dentry_offset) { struct btrfs_root *log = inode->root->log_root; - struct extent_buffer *src = path->nodes[0]; - const int nritems = btrfs_header_nritems(src); + struct extent_buffer *src; + const int nritems = btrfs_header_nritems(path->nodes[0]); const u64 ino = btrfs_ino(inode); bool last_found = false; int batch_start = 0; int batch_size = 0; int i; - for (i = path->slots[0]; i < nritems; i++) { + /* + * We need to clone the leaf, release the read lock on it, and use the + * clone before modifying the log tree. See the comment at copy_items() + * about why we need to do this. + */ + src = btrfs_clone_extent_buffer(path->nodes[0]); + if (!src) + return -ENOMEM; + + i = path->slots[0]; + btrfs_release_path(path); + path->nodes[0] = src; + path->slots[0] = i; + + for (; i < nritems; i++) { struct btrfs_dir_item *di; struct btrfs_key key; int ret; @@ -4303,7 +4317,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, { struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; - struct extent_buffer *src = src_path->nodes[0]; + struct extent_buffer *src; int ret = 0; struct btrfs_key *ins_keys; u32 *ins_sizes; @@ -4314,6 +4328,43 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM); const u64 i_size = i_size_read(&inode->vfs_inode); + /* + * To keep lockdep happy and avoid deadlocks, clone the source leaf and + * use the clone. This is because otherwise we would be changing the log + * tree, to insert items from the subvolume tree or insert csum items, + * while holding a read lock on a leaf from the subvolume tree, which + * creates a nasty lock dependency when COWing log tree nodes/leaves: + * + * 1) Modifying the log tree triggers an extent buffer allocation while + * holding a write lock on a parent extent buffer from the log tree. + * Allocating the pages for an extent buffer, or the extent buffer + * struct, can trigger inode eviction and finally the inode eviction + * will trigger a release/remove of a delayed node, which requires + * taking the delayed node's mutex; + * + * 2) Allocating a metadata extent for a log tree can trigger the async + * reclaim thread and make us wait for it to release enough space and + * unblock our reservation ticket. The reclaim thread can start + * flushing delayed items, and that in turn results in the need to + * lock delayed node mutexes and in the need to write lock extent + * buffers of a subvolume tree - all this while holding a write lock + * on the parent extent buffer in the log tree. + * + * So one task in scenario 1) running in parallel with another task in + * scenario 2) could lead to a deadlock, one wanting to lock a delayed + * node mutex while having a read lock on a leaf from the subvolume, + * while the other is holding the delayed node's mutex and wants to + * write lock the same subvolume leaf for flushing delayed items. + */ + src = btrfs_clone_extent_buffer(src_path->nodes[0]); + if (!src) + return -ENOMEM; + + i = src_path->slots[0]; + btrfs_release_path(src_path); + src_path->nodes[0] = src; + src_path->slots[0] = i; + ins_data = kmalloc(nr * sizeof(struct btrfs_key) + nr * sizeof(u32), GFP_NOFS); if (!ins_data) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1912abf6d020..c9e2b0c85309 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -134,7 +134,8 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, super[i] = page_address(page[i]); } - if (super[0]->generation > super[1]->generation) + if (btrfs_super_generation(super[0]) > + btrfs_super_generation(super[1])) sector = zones[1].start; else sector = zones[0].start; @@ -466,7 +467,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) goto out; } - zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL); + zones = kvcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL); if (!zones) { ret = -ENOMEM; goto out; @@ -585,7 +586,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } - kfree(zones); + kvfree(zones); switch (bdev_zoned_model(bdev)) { case BLK_ZONED_HM: @@ -617,7 +618,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) return 0; out: - kfree(zones); + kvfree(zones); out_free_zone_info: btrfs_destroy_dev_zone_info(device); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index fe220686bba4..712a43161448 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1281,7 +1281,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, rc = filemap_write_and_wait_range(src_inode->i_mapping, off, off + len - 1); if (rc) - goto out; + goto unlock; /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); @@ -1297,6 +1297,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, * that target is updated on the server */ CIFS_I(target_inode)->time = 0; + +unlock: /* although unlocking in the reverse order from locking is not * strictly necessary here it is a little cleaner to be consistent */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1cc47dd3b4d6..9db9527c61cf 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3855,9 +3855,13 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id); out: - free_xid(mnt_ctx.xid); cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); - return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); + rc = mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); + if (rc) + goto error; + + free_xid(mnt_ctx.xid); + return rc; error: dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id); @@ -3884,8 +3888,12 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; } + rc = mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); + if (rc) + goto error; + free_xid(mnt_ctx.xid); - return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); + return rc; error: mount_put_conns(&mnt_ctx); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 89d5fa887364..6419ec47c2a8 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -343,7 +343,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = put_user(ExtAttrBits & FS_FL_USER_VISIBLE, (int __user *)arg); - if (rc != EOPNOTSUPP) + if (rc != -EOPNOTSUPP) break; } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ @@ -373,7 +373,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) * pSMBFile->fid.netfid, * extAttrBits, * &ExtAttrMask); - * if (rc != EOPNOTSUPP) + * if (rc != -EOPNOTSUPP) * break; */ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 92e4278ec35d..9e7d9f0baa18 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -302,14 +302,14 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) /* now drop the ref to the current iface */ if (old_iface && iface) { - kref_put(&old_iface->refcount, release_iface); cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n", &old_iface->sockaddr, &iface->sockaddr); - } else if (old_iface) { kref_put(&old_iface->refcount, release_iface); + } else if (old_iface) { cifs_dbg(FYI, "releasing ref to iface: %pIS\n", &old_iface->sockaddr); + kref_put(&old_iface->refcount, release_iface); } else { WARN_ON(!iface); cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 880cd494afea..bfaafd02fb1f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1116,6 +1116,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); + if (rc) + goto sea_exit; smb2_set_next_command(tcon, &rqst[1]); smb2_set_related(&rqst[1]); @@ -1126,6 +1128,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rqst[2].rq_nvec = 1; rc = SMB2_close_init(tcon, server, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); + if (rc) + goto sea_exit; smb2_set_related(&rqst[2]); rc = compound_send_recv(xid, ses, server, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index f1956288307f..6c399a8b22b3 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5184,6 +5184,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, * and it is decreased till we reach start. */ again: + ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else @@ -5227,14 +5228,21 @@ again: ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); - if (le32_to_cpu(extent->ee_block) > 0) + if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; - else - /* Beginning is reached, end of the loop */ + else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; - /* Update path extent in case we need to stop */ - while (le32_to_cpu(extent->ee_block) < start) + else { + extent = EXT_LAST_EXTENT(path[depth].p_hdr); + while (le32_to_cpu(extent->ee_block) >= start) + extent--; + + if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) + break; + extent++; + iterator = NULL; + } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, diff --git a/fs/file.c b/fs/file.c index 5f9c802a5d8d..c942c89ca4cd 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1003,7 +1003,16 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask) struct files_struct *files = current->files; struct file *file; - if (atomic_read(&files->count) == 1) { + /* + * If another thread is concurrently calling close_fd() followed + * by put_files_struct(), we must not observe the old table + * entry combined with the new refcount - otherwise we could + * return a file that is concurrently being freed. + * + * atomic_read_acquire() pairs with atomic_dec_and_test() in + * put_files_struct(). + */ + if (atomic_read_acquire(&files->count) == 1) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 443f83382b9b..9958d4020771 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1712,18 +1712,26 @@ static int writeback_single_inode(struct inode *inode, wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* - * If the inode is now fully clean, then it can be safely removed from - * its writeback list (if any). Otherwise the flusher threads are - * responsible for the writeback lists. + * If the inode is freeing, its i_io_list shoudn't be updated + * as it can be finally deleted at this moment. */ - if (!(inode->i_state & I_DIRTY_ALL)) - inode_cgwb_move_to_attached(inode, wb); - else if (!(inode->i_state & I_SYNC_QUEUED)) { - if ((inode->i_state & I_DIRTY)) - redirty_tail_locked(inode, wb); - else if (inode->i_state & I_DIRTY_TIME) { - inode->dirtied_when = jiffies; - inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + if (!(inode->i_state & I_FREEING)) { + /* + * If the inode is now fully clean, then it can be safely + * removed from its writeback list (if any). Otherwise the + * flusher threads are responsible for the writeback lists. + */ + if (!(inode->i_state & I_DIRTY_ALL)) + inode_cgwb_move_to_attached(inode, wb); + else if (!(inode->i_state & I_SYNC_QUEUED)) { + if ((inode->i_state & I_DIRTY)) + redirty_tail_locked(inode, wb); + else if (inode->i_state & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; + inode_io_list_move_locked(inode, + wb, + &wb->b_dirty_time); + } } } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 451d8a077e12..bce2492186d0 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -605,6 +605,14 @@ again: set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); queue = true; } + /* + * We could race with cookie_lru which may set LRU_DISCARD bit + * but has yet to run the cookie state machine. If this happens + * and another thread tries to use the cookie, clear LRU_DISCARD + * so we don't end up withdrawing the cookie while in use. + */ + if (test_and_clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard_clear); break; case FSCACHE_COOKIE_STATE_FAILED: diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index a058e0136bfe..ab8ceddf9efa 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -203,7 +203,11 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, struct fscache_volume *volume; struct fscache_cache *cache; size_t klen, hlen; - char *key; + u8 *key; + + klen = strlen(volume_key); + if (klen > NAME_MAX) + return NULL; if (!coherency_data) coherency_len = 0; @@ -229,7 +233,6 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, /* Stick the length on the front of the key and pad it out to make * hashing easier. */ - klen = strlen(volume_key); hlen = round_up(1 + klen + 1, sizeof(__le32)); key = kzalloc(hlen, GFP_KERNEL); if (!key) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 71bfb663aac5..89f4741728ba 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2963,11 +2963,9 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, .mode = mode }; int err; - bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) || - (mode & (FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_ZERO_RANGE)); - - bool block_faults = FUSE_IS_DAX(inode) && lock_inode; + bool block_faults = FUSE_IS_DAX(inode) && + (!(mode & FALLOC_FL_KEEP_SIZE) || + (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))); if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) @@ -2976,22 +2974,20 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, if (fm->fc->no_fallocate) return -EOPNOTSUPP; - if (lock_inode) { - inode_lock(inode); - if (block_faults) { - filemap_invalidate_lock(inode->i_mapping); - err = fuse_dax_break_layouts(inode, 0, 0); - if (err) - goto out; - } + inode_lock(inode); + if (block_faults) { + filemap_invalidate_lock(inode->i_mapping); + err = fuse_dax_break_layouts(inode, 0, 0); + if (err) + goto out; + } - if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) { - loff_t endbyte = offset + length - 1; + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) { + loff_t endbyte = offset + length - 1; - err = fuse_writeback_range(inode, offset, endbyte); - if (err) - goto out; - } + err = fuse_writeback_range(inode, offset, endbyte); + if (err) + goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && @@ -3039,8 +3035,7 @@ out: if (block_faults) filemap_invalidate_unlock(inode->i_mapping); - if (lock_inode) - inode_unlock(inode); + inode_unlock(inode); fuse_flush_time_update(inode); diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 8de970d6146f..94b8ed4ef870 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1794,9 +1794,9 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, ret = vfs_copy_file_range(src_fp->filp, src_off, dst_fp->filp, dst_off, len, 0); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_fp->filp, src_off, - dst_fp->filp, dst_off, - len, 0); + ret = vfs_copy_file_range(src_fp->filp, src_off, + dst_fp->filp, dst_off, len, + COPY_FILE_SPLICE); if (ret < 0) return ret; diff --git a/fs/namei.c b/fs/namei.c index 578c2110df02..9155ecb547ce 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3591,6 +3591,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; + int open_flag = file->f_flags; /* we want directory to be writable */ error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); @@ -3613,7 +3614,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, if (error) return error; inode = file_inode(file); - if (!(file->f_flags & O_EXCL)) { + if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f650afedd67f..849a720ab43f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -596,8 +596,8 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src, src_pos, dst, dst_pos, - count, 0); + ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, + COPY_FILE_SPLICE); return ret; } @@ -871,10 +871,11 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct svc_rqst *rqstp = sd->u.data; struct page *page = buf->page; // may be a compound one unsigned offset = buf->offset; + struct page *last_page; - page += offset / PAGE_SIZE; - for (int i = sd->len; i > 0; i -= PAGE_SIZE) - svc_rqst_replace_page(rqstp, page++); + last_page = page + (offset + sd->len - 1) / PAGE_SIZE; + for (page += offset / PAGE_SIZE; page <= last_page; page++) + svc_rqst_replace_page(rqstp, page); if (rqstp->rq_res.page_len == 0) // first call rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 3b55e239705f..9930fa901039 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -111,6 +111,13 @@ static void nilfs_dat_commit_free(struct inode *dat, kunmap_atomic(kaddr); nilfs_dat_commit_entry(dat, req); + + if (unlikely(req->pr_desc_bh == NULL || req->pr_bitmap_bh == NULL)) { + nilfs_error(dat->i_sb, + "state inconsistency probably due to duplicate use of vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + return; + } nilfs_palloc_commit_free_entry(dat, req); } diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 77ff8e95421f..dc359b56fdfa 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -495,14 +495,22 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { struct buffer_head *bh; + void *kaddr; + struct nilfs_segment_usage *su; int ret; + down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); if (!ret) { mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(sufile); + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + nilfs_segment_usage_set_dirty(su); + kunmap_atomic(kaddr); brelse(bh); } + up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 5101131e6047..440960110a42 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -115,7 +115,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); - show_val_kb(m, "SecPageTables: ", + show_val_kb(m, "SecPageTables: ", global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); diff --git a/fs/read_write.c b/fs/read_write.c index 328ce8cf9a85..24b9668d6377 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1388,6 +1388,8 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { + lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); + return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } @@ -1424,7 +1426,9 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ - if (file_out->f_op->copy_file_range) { + if (flags & COPY_FILE_SPLICE) { + /* cross sb splice is allowed */ + } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; @@ -1474,8 +1478,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, size_t len, unsigned int flags) { ssize_t ret; + bool splice = flags & COPY_FILE_SPLICE; - if (flags != 0) + if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, @@ -1501,14 +1506,14 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ - if (file_out->f_op->copy_file_range) { + if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; } - if (file_in->f_op->remap_file_range && + if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, @@ -1528,6 +1533,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). + * + * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); @@ -1582,6 +1589,10 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, pos_out = f_out.file->f_pos; } + ret = -EINVAL; + if (flags != 0) + goto out; + ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 860f0b1032c6..2c53fbb8d918 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -41,6 +41,13 @@ static void zonefs_account_active(struct inode *inode) return; /* + * For zones that transitioned to the offline or readonly condition, + * we only need to clear the active state. + */ + if (zi->i_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY)) + goto out; + + /* * If the zone is active, that is, if it is explicitly open or * partially written, check if it was already accounted as active. */ @@ -53,6 +60,7 @@ static void zonefs_account_active(struct inode *inode) return; } +out: /* The zone is not active. If it was, update the active count */ if (zi->i_flags & ZONEFS_ZONE_ACTIVE) { zi->i_flags &= ~ZONEFS_ZONE_ACTIVE; @@ -324,6 +332,7 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, inode->i_flags |= S_IMMUTABLE; inode->i_mode &= ~0777; zone->wp = zone->start; + zi->i_flags |= ZONEFS_ZONE_OFFLINE; return 0; case BLK_ZONE_COND_READONLY: /* @@ -342,8 +351,10 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, zone->cond = BLK_ZONE_COND_OFFLINE; inode->i_mode &= ~0777; zone->wp = zone->start; + zi->i_flags |= ZONEFS_ZONE_OFFLINE; return 0; } + zi->i_flags |= ZONEFS_ZONE_READONLY; inode->i_mode &= ~0222; return i_size_read(inode); case BLK_ZONE_COND_FULL: @@ -478,8 +489,7 @@ static void __zonefs_io_error(struct inode *inode, bool write) struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = - zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + unsigned int nr_zones = 1; struct zonefs_ioerr_data err = { .inode = inode, .write = write, @@ -487,6 +497,15 @@ static void __zonefs_io_error(struct inode *inode, bool write) int ret; /* + * The only files that have more than one zone are conventional zone + * files with aggregated conventional zones, for which the inode zone + * size is always larger than the device zone size. + */ + if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev)) + nr_zones = zi->i_zone_size >> + (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + + /* * Memory allocations in blkdev_report_zones() can trigger a memory * reclaim which may in turn cause a recursion into zonefs as well as * struct request allocations for the same device. The former case may @@ -1407,6 +1426,14 @@ static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, zi->i_ztype = type; zi->i_zsector = zone->start; zi->i_zone_size = zone->len << SECTOR_SHIFT; + if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT && + !(sbi->s_features & ZONEFS_F_AGGRCNV)) { + zonefs_err(sb, + "zone size %llu doesn't match device's zone sectors %llu\n", + zi->i_zone_size, + bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT); + return -EINVAL; + } zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE, zone->capacity << SECTOR_SHIFT); @@ -1456,11 +1483,11 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; - int ret; + int ret = -ENOMEM; dentry = d_alloc_name(parent, name); if (!dentry) - return NULL; + return ERR_PTR(ret); inode = new_inode(parent->d_sb); if (!inode) @@ -1485,7 +1512,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, dput: dput(dentry); - return NULL; + return ERR_PTR(ret); } struct zonefs_zone_data { @@ -1505,7 +1532,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, struct blk_zone *zone, *next, *end; const char *zgroup_name; char *file_name; - struct dentry *dir; + struct dentry *dir, *dent; unsigned int n = 0; int ret; @@ -1523,8 +1550,8 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, zgroup_name = "seq"; dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type); - if (!dir) { - ret = -ENOMEM; + if (IS_ERR(dir)) { + ret = PTR_ERR(dir); goto free; } @@ -1570,8 +1597,9 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, * Use the file number within its group as file name. */ snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n); - if (!zonefs_create_inode(dir, file_name, zone, type)) { - ret = -ENOMEM; + dent = zonefs_create_inode(dir, file_name, zone, type); + if (IS_ERR(dent)) { + ret = PTR_ERR(dent); goto free; } @@ -1905,18 +1933,18 @@ static int __init zonefs_init(void) if (ret) return ret; - ret = register_filesystem(&zonefs_type); + ret = zonefs_sysfs_init(); if (ret) goto destroy_inodecache; - ret = zonefs_sysfs_init(); + ret = register_filesystem(&zonefs_type); if (ret) - goto unregister_fs; + goto sysfs_exit; return 0; -unregister_fs: - unregister_filesystem(&zonefs_type); +sysfs_exit: + zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); @@ -1925,9 +1953,9 @@ destroy_inodecache: static void __exit zonefs_exit(void) { + unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); - unregister_filesystem(&zonefs_type); } MODULE_AUTHOR("Damien Le Moal"); diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c index 9cb6755ce39a..9920689dc098 100644 --- a/fs/zonefs/sysfs.c +++ b/fs/zonefs/sysfs.c @@ -15,11 +15,6 @@ struct zonefs_sysfs_attr { ssize_t (*show)(struct zonefs_sb_info *sbi, char *buf); }; -static inline struct zonefs_sysfs_attr *to_attr(struct attribute *attr) -{ - return container_of(attr, struct zonefs_sysfs_attr, attr); -} - #define ZONEFS_SYSFS_ATTR_RO(name) \ static struct zonefs_sysfs_attr zonefs_sysfs_attr_##name = __ATTR_RO(name) diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index 4b3de66c3233..1dbe78119ff1 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -39,8 +39,10 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone) return ZONEFS_ZTYPE_SEQ; } -#define ZONEFS_ZONE_OPEN (1 << 0) -#define ZONEFS_ZONE_ACTIVE (1 << 1) +#define ZONEFS_ZONE_OPEN (1U << 0) +#define ZONEFS_ZONE_ACTIVE (1U << 1) +#define ZONEFS_ZONE_OFFLINE (1U << 2) +#define ZONEFS_ZONE_READONLY (1U << 3) /* * In-memory inode data. diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 492dce43236e..cab7cfebf40b 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -222,12 +222,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #define tlb_needs_table_invalidate() (true) #endif +void tlb_remove_table_sync_one(void); + #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif +static inline void tlb_remove_table_sync_one(void) { } + #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h index 5755ae5a4712..6a869682c120 100644 --- a/include/linux/can/platform/sja1000.h +++ b/include/linux/can/platform/sja1000.h @@ -14,7 +14,7 @@ #define OCR_MODE_TEST 0x01 #define OCR_MODE_NORMAL 0x02 #define OCR_MODE_CLOCK 0x03 -#define OCR_MODE_MASK 0x07 +#define OCR_MODE_MASK 0x03 #define OCR_TX0_INVERT 0x04 #define OCR_TX0_PULLDOWN 0x08 #define OCR_TX0_PULLUP 0x10 diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 528bd44b59e2..2b7d077de7ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -68,6 +68,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 9f6e25467844..444236dadcf0 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,7 +20,6 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; - bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -32,6 +31,10 @@ struct fault_attr { struct dentry *dname; }; +enum fault_flags { + FAULT_NOWARN = 1 << 0, +}; + #define FAULT_ATTR_INITIALIZER { \ .interval = 1, \ .times = ATOMIC_INIT(1), \ @@ -40,11 +43,11 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ - .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER int setup_fault_attr(struct fault_attr *attr, char *str); +bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags); bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/include/linux/fs.h b/include/linux/fs.h index e654435f1651..59ae95ddb679 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2089,6 +2089,14 @@ struct dir_context { */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) +/* + * These flags control the behavior of vfs_copy_file_range(). + * They are not available to the user via syscall. + * + * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops + */ +#define COPY_FILE_SPLICE (1 << 0) + struct iov_iter; struct io_uring_cmd; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 36e5dd84cf59..8e312c8323a8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -75,7 +75,7 @@ struct fscache_volume { atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; unsigned int key_hash; /* Hash of key string */ - char *key; /* Volume ID, eg. "[email protected]@1234" */ + u8 *key; /* Volume ID, eg. "[email protected]@1234" */ struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ struct hlist_bl_node hash_link; /* Link in hash table */ struct work_struct work; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ef4aea3b356e..65a78773dcca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -210,6 +210,20 @@ alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct p return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); } +static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) +{ + gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); + + if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) + return; + + if (node_online(this_node)) + return; + + pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); + dump_stack(); +} + /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). @@ -218,7 +232,7 @@ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); + warn_if_node_offline(nid, gfp_mask); return __alloc_pages(gfp_mask, order, nid, NULL); } @@ -227,7 +241,7 @@ static inline struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid)); + warn_if_node_offline(nid, gfp); return __folio_alloc(gfp, order, nid, NULL); } diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 43bc8a2edccf..0ded9e271523 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -16,6 +16,9 @@ enum io_uring_cmd_flags { IO_URING_F_SQE128 = 4, IO_URING_F_CQE32 = 8, IO_URING_F_IOPOLL = 16, + + /* the request is executed from poll, it should not be freed */ + IO_URING_F_MULTISHOT = 32, }; struct io_uring_cmd { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 18592bdf4c1b..915142abdf76 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -416,7 +416,7 @@ static __always_inline void guest_context_enter_irqoff(void) */ if (!context_tracking_guest_enter()) { instrumentation_begin(); - rcu_virt_note_context_switch(smp_processor_id()); + rcu_virt_note_context_switch(); instrumentation_end(); } } @@ -776,6 +776,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af2ceb4160bc..06cbad166225 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -981,6 +981,7 @@ struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ + u16 op_mod; /* cmd op_mod */ void *out; /* pointer to the cmd output buffer */ }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 8bbcccbc5565..974ccca609d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1852,6 +1852,25 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct folio *single_folio; /* Locked folio to be unmapped */ + bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ +}; + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) +/* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ +#define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) + #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -1869,6 +1888,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details); void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); @@ -3467,12 +3488,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -/* - * Whether to drop the pte markers, for example, the uffd-wp information for - * file-backed memory. This should only be specified when we will completely - * drop the page in the mm, either by truncation or unmapping of the vma. By - * default, the flag is not set. - */ -#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) - #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 9c50bc40f8ff..6f7993803ee7 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -451,7 +451,7 @@ static inline bool mmc_ready_for_data(u32 status) #define MMC_SECURE_TRIM1_ARG 0x80000001 #define MMC_SECURE_TRIM2_ARG 0x80008000 #define MMC_SECURE_ARGS 0x80000000 -#define MMC_TRIM_ARGS 0x00008001 +#define MMC_TRIM_OR_DISCARD_ARGS 0x00008003 #define mmc_driver_type_mask(n) (1 << (n)) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a108b60a6962..5f0d7d0b9471 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -165,6 +165,13 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr) return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } +#ifndef pmd_young +static inline int pmd_young(pmd_t pmd) +{ + return 0; +} +#endif + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, @@ -260,6 +267,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_nonleaf_pmd_young +/* + * Return whether the accessed bit in non-leaf PMD entries is supported on the + * local CPU. + */ +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); +} +#endif + #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 08605ce7379d..4da98ca6273e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -108,6 +108,15 @@ static inline int rcu_preempt_depth(void) #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_RCU_LAZY +void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); +#else +static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} +#endif + /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; @@ -340,6 +349,11 @@ static inline int rcu_read_lock_any_held(void) return !preemptible(); } +static inline int debug_lockdep_rcu_enabled(void) +{ + return 0; +} + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 768196a5f39d..5c271bf3a1e7 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -142,12 +142,10 @@ static inline int rcu_needs_cpu(void) * Take advantage of the fact that there is only one CPU, which * allows us to ignore virtualization-based context switches. */ -static inline void rcu_virt_note_context_switch(int cpu) { } +static inline void rcu_virt_note_context_switch(void) { } static inline void rcu_cpu_stall_reset(void) { } static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; } static inline void rcu_irq_exit_check_preempt(void) { } -#define rcu_is_idle_cpu(cpu) \ - (is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq()) static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 5efb51486e8a..4003bf6cfa1c 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -27,7 +27,7 @@ void rcu_cpu_stall_reset(void); * wrapper around rcu_note_context_switch(), which allows TINY_RCU * to save a few bytes. The caller must have disabled interrupts. */ -static inline void rcu_virt_note_context_switch(int cpu) +static inline void rcu_virt_note_context_switch(void) { rcu_note_context_switch(false); } @@ -87,8 +87,6 @@ bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); void cond_synchronize_rcu(unsigned long oldstate); void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); -bool rcu_is_idle_cpu(int cpu); - #ifdef CONFIG_PROVE_RCU void rcu_irq_exit_check_preempt(void); #else diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 2504df9a0453..3c7d295746f6 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -100,7 +100,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, - struct file *filp, poll_table *poll_table); + struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/slab.h b/include/linux/slab.h index 45efc6c553b8..e7534a7b2daf 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -76,6 +76,17 @@ * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * + * Note that it is not possible to acquire a lock within a structure + * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference + * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages + * are not zeroed before being given to the slab, which means that any + * locks must be initialized after each and every kmem_struct_alloc(). + * Alternatively, make the ctor passed to kmem_cache_create() initialize + * the locks at page-allocation time, as is done in __i915_request_ctor(), + * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers + * to safely acquire those ctor-initialized locks under rcu_read_lock() + * protection. + * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 01226e4d960a..f0814ffca34b 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -64,6 +64,20 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +#ifdef CONFIG_NEED_SRCU_NMI_SAFE +int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); +#else +static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) +{ + return __srcu_read_lock(ssp); +} +static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) +{ + __srcu_read_unlock(ssp, idx); +} +#endif /* CONFIG_NEED_SRCU_NMI_SAFE */ + #ifdef CONFIG_SRCU void srcu_init(void); #else /* #ifdef CONFIG_SRCU */ @@ -104,6 +118,18 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +#define SRCU_NMI_UNKNOWN 0x0 +#define SRCU_NMI_UNSAFE 0x1 +#define SRCU_NMI_SAFE 0x2 + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_TREE_SRCU) +void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe); +#else +static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, + bool nmi_safe) { } +#endif + + /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing @@ -161,17 +187,36 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; + srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; } +/** + * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section, but in an NMI-safe manner. + * See srcu_read_lock() for more information. + */ +static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) +{ + int retval; + + srcu_check_nmi_safety(ssp, true); + retval = __srcu_read_lock_nmisafe(ssp); + rcu_lock_acquire(&(ssp)->dep_map); + return retval; +} + /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; + srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); return retval; } @@ -187,14 +232,32 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); + srcu_check_nmi_safety(ssp, false); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } +/** + * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit an SRCU read-side critical section, but in an NMI-safe manner. + */ +static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) + __releases(ssp) +{ + WARN_ON_ONCE(idx & ~0x1); + srcu_check_nmi_safety(ssp, true); + rcu_lock_release(&(ssp)->dep_map); + __srcu_read_unlock_nmisafe(ssp, idx); +} + /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { + srcu_check_nmi_safety(ssp, false); __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index e3014319d1ad..c689a81752c9 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -23,8 +23,9 @@ struct srcu_struct; */ struct srcu_data { /* Read-side state. */ - unsigned long srcu_lock_count[2]; /* Locks per CPU. */ - unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */ + atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ + atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ + int srcu_nmi_safety; /* NMI-safe srcu_struct structure? */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 86b95ccb81bb..b07b277d6a16 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -33,11 +33,13 @@ * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS -#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#define SWP_PFN_BITS min_t(int, \ + sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ + SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: diff --git a/include/linux/trace.h b/include/linux/trace.h index b5e16e438448..80ffda871749 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -26,13 +26,13 @@ struct trace_export { int flags; }; +struct trace_array; + #ifdef CONFIG_TRACING int register_ftrace_export(struct trace_export *export); int unregister_ftrace_export(struct trace_export *export); -struct trace_array; - void trace_printk_init_buffers(void); __printf(3, 4) int trace_array_printk(struct trace_array *tr, unsigned long ip, diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e004ba04a9ae..684f1cd28730 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -228,6 +228,17 @@ enum { */ HCI_QUIRK_VALID_LE_STATES, + /* When this quirk is set, then erroneous data reporting + * is ignored. This is mainly due to the fact that the HCI + * Read Default Erroneous Data Reporting command is advertised, + * but not supported; these controllers often reply with unknown + * command and tend to lock up randomly. Needing a hard reset. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, + /* * When this quirk is set, then the hci_suspend_notifier is not * registered. This is intended for devices which drop completely @@ -1424,7 +1435,6 @@ struct hci_std_codecs_v2 { } __packed; struct hci_vnd_codec_v2 { - __u8 id; __le16 cid; __le16 vid; __u8 transport; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3af1e927247d..69174093078f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -281,7 +281,8 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's * rcv_saddr field should already have been updated when this is called. */ -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk); +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); +void inet_bhash2_reset_saddr(struct sock *sk); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 20745cf7ae1a..2f2a6023fb0e 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -83,7 +83,7 @@ struct neigh_parms { struct rcu_head rcu_head; int reachable_time; - int qlen; + u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; diff --git a/include/net/ping.h b/include/net/ping.h index e4ff3911cbf5..9233ad3de0ad 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,9 +16,6 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -#define ping_portaddr_for_each_entry(__sk, node, list) \ - hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) - /* * gid_t is either uint or ushort. We want to pass it to * proc_dointvec_minmax(), so it must not be larger than MAX_INT diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h index 01a70b27e026..65058faea4db 100644 --- a/include/net/sctp/stream_sched.h +++ b/include/net/sctp/stream_sched.h @@ -26,6 +26,8 @@ struct sctp_sched_ops { int (*init)(struct sctp_stream *stream); /* Init a stream */ int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp); + /* free a stream */ + void (*free_sid)(struct sctp_stream *stream, __u16 sid); /* Frees the entire thing */ void (*free)(struct sctp_stream *stream); diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 83fd81c82e4c..9fbd3832bcdc 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -84,8 +84,8 @@ enum sof_ipc_dai_type { SOF_DAI_AMD_BT, /**< AMD ACP BT*/ SOF_DAI_AMD_SP, /**< AMD ACP SP */ SOF_DAI_AMD_DMIC, /**< AMD ACP DMIC */ - SOF_DAI_AMD_HS, /**< Amd HS */ SOF_DAI_MEDIATEK_AFE, /**< Mediatek AFE */ + SOF_DAI_AMD_HS, /**< Amd HS */ }; /* general purpose DAI configuration */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index c078c48a8e6d..a6190aa1b406 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -66,6 +66,7 @@ enum fscache_cookie_trace { fscache_cookie_put_work, fscache_cookie_see_active, fscache_cookie_see_lru_discard, + fscache_cookie_see_lru_discard_clear, fscache_cookie_see_lru_do_one, fscache_cookie_see_relinquish, fscache_cookie_see_withdraw, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_cookie_put_work, "PQ work ") \ EM(fscache_cookie_see_active, "- activ") \ EM(fscache_cookie_see_lru_discard, "- x-lru") \ + EM(fscache_cookie_see_lru_discard_clear,"- lrudc") \ EM(fscache_cookie_see_lru_do_one, "- lrudo") \ EM(fscache_cookie_see_relinquish, "- x-rlq") \ EM(fscache_cookie_see_withdraw, "- x-wth") \ diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 935af4947917..760455dfa860 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -171,15 +171,15 @@ TRACE_EVENT(mm_collapse_huge_page_swapin, TRACE_EVENT(mm_khugepaged_scan_file, - TP_PROTO(struct mm_struct *mm, struct page *page, const char *filename, + TP_PROTO(struct mm_struct *mm, struct page *page, struct file *file, int present, int swap, int result), - TP_ARGS(mm, page, filename, present, swap, result), + TP_ARGS(mm, page, file, present, swap, result), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(unsigned long, pfn) - __string(filename, filename) + __string(filename, file->f_path.dentry->d_iname) __field(int, present) __field(int, swap) __field(int, result) @@ -188,7 +188,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TP_fast_assign( __entry->mm = mm; __entry->pfn = page ? page_to_pfn(page) : -1; - __assign_str(filename, filename); + __assign_str(filename, file->f_path.dentry->d_iname); __entry->present = present; __entry->swap = swap; __entry->result = result; diff --git a/init/Kconfig b/init/Kconfig index abf65098f1b6..94125d3b6893 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -87,7 +87,7 @@ config CC_HAS_ASM_GOTO_OUTPUT config CC_HAS_ASM_GOTO_TIED_OUTPUT depends on CC_HAS_ASM_GOTO_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. - def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .\n": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) + def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) diff --git a/io_uring/filetable.c b/io_uring/filetable.c index 7b473259f3f4..68dfc6936aa7 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -101,8 +101,6 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); - if (ret) - fput(file); return ret; } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4a1e482747cc..61cd7ffd0f6a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1768,7 +1768,7 @@ int io_poll_issue(struct io_kiocb *req, bool *locked) io_tw_lock(req->ctx, locked); if (unlikely(req->task->flags & PF_EXITING)) return -EFAULT; - return io_issue_sqe(req, IO_URING_F_NONBLOCK); + return io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_MULTISHOT); } struct io_wq_work *io_wq_free_work(struct io_wq_work *work) @@ -2707,8 +2707,10 @@ static __cold void io_tctx_exit_cb(struct callback_head *cb) /* * When @in_idle, we're in cancellation and it's racy to remove the * node. It'll be removed by the end of cancellation, just ignore it. + * tctx can be NULL if the queueing of this task_work raced with + * work cancelation off the exec path. */ - if (!atomic_read(&tctx->in_idle)) + if (tctx && !atomic_read(&tctx->in_idle)) io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index e99a79f2df9b..50bc3af44953 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -17,8 +17,8 @@ enum { IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED, /* - * Intended only when both REQ_F_POLLED and REQ_F_APOLL_MULTISHOT - * are set to indicate to the poll runner that multishot should be + * Intended only when both IO_URING_F_MULTISHOT is passed + * to indicate to the poll runner that multishot should be * removed and the result is set on req->cqe.res. */ IOU_STOP_MULTISHOT = -ECANCELED, @@ -238,9 +238,14 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) static inline int io_run_task_work(void) { + /* + * Always check-and-clear the task_work notification signal. With how + * signaling works for task_work, we can find it set with nothing to + * run. We need to clear it for that case, like get_signal() does. + */ + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + clear_notify_signal(); if (task_work_pending(current)) { - if (test_thread_flag(TIF_NOTIFY_SIGNAL)) - clear_notify_signal(); __set_current_state(TASK_RUNNING); task_work_run(); return 1; diff --git a/io_uring/net.c b/io_uring/net.c index 15dea91625e2..ab83da7e80f0 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -67,8 +67,6 @@ struct io_sr_msg { struct io_kiocb *notif; }; -#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) - int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown); @@ -591,7 +589,8 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) * again (for multishot). */ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, - unsigned int cflags, bool mshot_finished) + unsigned int cflags, bool mshot_finished, + unsigned issue_flags) { if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { io_req_set_res(req, *ret, cflags); @@ -614,7 +613,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, io_req_set_res(req, *ret, cflags); - if (req->flags & REQ_F_POLLED) + if (issue_flags & IO_URING_F_MULTISHOT) *ret = IOU_STOP_MULTISHOT; else *ret = IOU_OK; @@ -773,8 +772,7 @@ retry_multishot: if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) { ret = io_setup_async_msg(req, kmsg, issue_flags); - if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == - IO_APOLL_MULTI_POLLED) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_MULTISHOT)) { io_kbuf_recycle(req, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } @@ -803,7 +801,7 @@ retry_multishot: if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags, mshot_finished)) + if (!io_recv_finish(req, &ret, cflags, mshot_finished, issue_flags)) goto retry_multishot; if (mshot_finished) { @@ -869,7 +867,7 @@ retry_multishot: ret = sock_recvmsg(sock, &msg, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) { - if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) { + if (issue_flags & IO_URING_F_MULTISHOT) { io_kbuf_recycle(req, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } @@ -902,7 +900,7 @@ out_free: if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags, ret <= 0)) + if (!io_recv_finish(req, &ret, cflags, ret <= 0, issue_flags)) goto retry_multishot; return ret; @@ -1289,8 +1287,7 @@ retry: * return EAGAIN to arm the poll infra since it * has already been done */ - if ((req->flags & IO_APOLL_MULTI_POLLED) == - IO_APOLL_MULTI_POLLED) + if (issue_flags & IO_URING_F_MULTISHOT) ret = IOU_ISSUE_SKIP_COMPLETE; return ret; } @@ -1315,9 +1312,7 @@ retry: goto retry; io_req_set_res(req, ret, 0); - if (req->flags & REQ_F_POLLED) - return IOU_STOP_MULTISHOT; - return IOU_OK; + return (issue_flags & IO_URING_F_MULTISHOT) ? IOU_STOP_MULTISHOT : IOU_OK; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/io_uring/poll.c b/io_uring/poll.c index f500506984ec..d9bf1767867e 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -40,7 +40,14 @@ struct io_poll_table { }; #define IO_POLL_CANCEL_FLAG BIT(31) -#define IO_POLL_REF_MASK GENMASK(30, 0) +#define IO_POLL_RETRY_FLAG BIT(30) +#define IO_POLL_REF_MASK GENMASK(29, 0) + +/* + * We usually have 1-2 refs taken, 128 is more than enough and we want to + * maximise the margin between this amount and the moment when it overflows. + */ +#define IO_POLL_REF_BIAS 128 #define IO_WQE_F_DOUBLE 1 @@ -58,6 +65,21 @@ static inline bool wqe_is_double(struct wait_queue_entry *wqe) return priv & IO_WQE_F_DOUBLE; } +static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) +{ + int v; + + /* + * poll_refs are already elevated and we don't have much hope for + * grabbing the ownership. Instead of incrementing set a retry flag + * to notify the loop that there might have been some change. + */ + v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); + if (v & IO_POLL_REF_MASK) + return false; + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} + /* * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can * bump it and acquire ownership. It's disallowed to modify requests while not @@ -66,6 +88,8 @@ static inline bool wqe_is_double(struct wait_queue_entry *wqe) */ static inline bool io_poll_get_ownership(struct io_kiocb *req) { + if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) + return io_poll_get_ownership_slowpath(req); return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } @@ -228,6 +252,23 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return IOU_POLL_DONE; if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->cqe.res = 0; + if (v & IO_POLL_RETRY_FLAG) { + req->cqe.res = 0; + /* + * We won't find new events that came in between + * vfs_poll and the ref put unless we clear the flag + * in advance. + */ + atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); + v &= ~IO_POLL_RETRY_FLAG; + } /* the mask was stashed in __io_poll_execute */ if (!req->cqe.res) { @@ -239,6 +280,8 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) continue; if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; + if (io_is_uring_fops(req->file)) + return IOU_POLL_DONE; /* multishot, just fill a CQE and proceed */ if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { @@ -258,11 +301,15 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return ret; } + /* force the next iteration to vfs_poll() */ + req->cqe.res = 0; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it. */ - } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs)); + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & + IO_POLL_REF_MASK); return IOU_POLL_NO_ACTION; } @@ -506,7 +553,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; - int v; INIT_HLIST_NODE(&req->hash_node); req->work.cancel_seq = atomic_read(&ctx->cancel_seq); @@ -574,11 +620,10 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (ipt->owning) { /* - * Release ownership. If someone tried to queue a tw while it was - * locked, kick it off for them. + * Try to release ownership. If we see a change of state, e.g. + * poll was waken up, queue up a tw, it'll deal with it. */ - v = atomic_dec_return(&req->poll_refs); - if (unlikely(v & IO_POLL_REF_MASK)) + if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) __io_poll_execute(req, 0); } return 0; diff --git a/ipc/sem.c b/ipc/sem.c index c8496f98b139..00f88aa01ac5 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2179,14 +2179,15 @@ long __do_semtimedop(int semid, struct sembuf *sops, * scenarios where we were awakened externally, during the * window between wake_q_add() and wake_up_q(). */ + rcu_read_lock(); error = READ_ONCE(queue.status); if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); + rcu_read_unlock(); goto out; } - rcu_read_lock(); locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) diff --git a/ipc/shm.c b/ipc/shm.c index 7d86f058fb86..bd2fcc4d454e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -275,10 +275,8 @@ static inline void shm_rmid(struct shmid_kernel *s) } -static int __shm_open(struct vm_area_struct *vma) +static int __shm_open(struct shm_file_data *sfd) { - struct file *file = vma->vm_file; - struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); @@ -302,7 +300,15 @@ static int __shm_open(struct vm_area_struct *vma) /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { - int err = __shm_open(vma); + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + int err; + + /* Always call underlying open if present */ + if (sfd->vm_ops->open) + sfd->vm_ops->open(vma); + + err = __shm_open(sfd); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. @@ -359,10 +365,8 @@ static bool shm_may_destroy(struct shmid_kernel *shp) * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ -static void shm_close(struct vm_area_struct *vma) +static void __shm_close(struct shm_file_data *sfd) { - struct file *file = vma->vm_file; - struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; @@ -388,6 +392,18 @@ done: up_write(&shm_ids(ns).rwsem); } +static void shm_close(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + /* Always call underlying close if present */ + if (sfd->vm_ops->close) + sfd->vm_ops->close(vma); + + __shm_close(sfd); +} + /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { @@ -583,13 +599,13 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ - ret = __shm_open(vma); + ret = __shm_open(sfd); if (ret) return ret; ret = call_mmap(sfd->file, vma); if (ret) { - shm_close(vma); + __shm_close(sfd); return ret; } sfd->vm_ops = vma->vm_ops; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 802fc15b0d73..f27fa5ba7d72 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -74,7 +74,7 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, gfp_flags | __GFP_NOWARN); if (selem) { if (value) - memcpy(SDATA(selem)->data, value, smap->map.value_size); + copy_map_value(&smap->map, SDATA(selem)->data, value); return selem; } diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index fd4020835ec6..367b0a42ada9 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -167,7 +167,6 @@ struct cgroup_mgctx { extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ec3717003d5..7f04f995c975 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2291,6 +2291,7 @@ event_sched_out(struct perf_event *event, !event->pending_work) { event->pending_work = 1; dec = false; + WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount)); task_work_add(current, &event->pending_task, TWA_RESUME); } if (dec) @@ -2336,6 +2337,7 @@ group_sched_out(struct perf_event *group_event, #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL +#define DETACH_DEAD 0x04UL /* * Cross CPU call to remove a performance event @@ -2356,12 +2358,20 @@ __perf_remove_from_context(struct perf_event *event, update_cgrp_time_from_cpuctx(cpuctx, false); } + /* + * Ensure event_sched_out() switches to OFF, at the very least + * this avoids raising perf_pending_task() at this time. + */ + if (flags & DETACH_DEAD) + event->pending_disable = 1; event_sched_out(event, cpuctx, ctx); if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) perf_child_detach(event); list_del_event(event, ctx); + if (flags & DETACH_DEAD) + event->state = PERF_EVENT_STATE_DEAD; if (!ctx->nr_events && ctx->is_active) { if (ctx == &cpuctx->ctx) @@ -5121,9 +5131,7 @@ int perf_event_release_kernel(struct perf_event *event) ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, DETACH_GROUP); - raw_spin_lock_irq(&ctx->lock); /* * Mark this event as STATE_DEAD, there is no external reference to it * anymore. @@ -5135,8 +5143,7 @@ int perf_event_release_kernel(struct perf_event *event) * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - event->state = PERF_EVENT_STATE_DEAD; - raw_spin_unlock_irq(&ctx->lock); + perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD); perf_event_ctx_unlock(event, ctx); @@ -6577,6 +6584,8 @@ static void perf_pending_task(struct callback_head *head) if (rctx >= 0) perf_swevent_put_recursion_context(rctx); preempt_enable_notrace(); + + put_event(event); } #ifdef CONFIG_GUEST_PERF_EVENTS @@ -9030,7 +9039,7 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)subprog->bpf_func, subprog->jited_len, unregister, - prog->aux->ksym.name); + subprog->aux->ksym.name); } } } @@ -9273,6 +9282,19 @@ int perf_event_account_interrupt(struct perf_event *event) return __perf_event_account_interrupt(event, 1); } +static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) +{ + /* + * Due to interrupt latency (AKA "skid"), we may enter the + * kernel before taking an overflow, even if the PMU is only + * counting user events. + */ + if (event->attr.exclude_kernel && !user_mode(regs)) + return false; + + return true; +} + /* * Generic event overflow handling, sampling. */ @@ -9307,15 +9329,38 @@ static int __perf_event_overflow(struct perf_event *event, if (event->attr.sigtrap) { /* - * Should not be able to return to user space without processing - * pending_sigtrap (kernel events can overflow multiple times). + * The desired behaviour of sigtrap vs invalid samples is a bit + * tricky; on the one hand, one should not loose the SIGTRAP if + * it is the first event, on the other hand, we should also not + * trigger the WARN or override the data address. */ - WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel); + bool valid_sample = sample_is_allowed(event, regs); + unsigned int pending_id = 1; + + if (regs) + pending_id = hash32_ptr((void *)instruction_pointer(regs)) ?: 1; if (!event->pending_sigtrap) { - event->pending_sigtrap = 1; + event->pending_sigtrap = pending_id; local_inc(&event->ctx->nr_pending); + } else if (event->attr.exclude_kernel && valid_sample) { + /* + * Should not be able to return to user space without + * consuming pending_sigtrap; with exceptions: + * + * 1. Where !exclude_kernel, events can overflow again + * in the kernel without returning to user space. + * + * 2. Events that can overflow again before the IRQ- + * work without user space progress (e.g. hrtimer). + * To approximate progress (with false negatives), + * check 32-bit hash of the current IP. + */ + WARN_ON_ONCE(event->pending_sigtrap != pending_id); } - event->pending_addr = data->addr; + + event->pending_addr = 0; + if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) + event->pending_addr = data->addr; irq_work_queue(&event->pending_irq); } diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index cbb0bed958ab..7670a811a565 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -280,6 +280,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) for (i = 0; i < sfn_ptr->num_counters; i++) dfn_ptr->counters[i] += sfn_ptr->counters[i]; + + sfn_ptr = list_next_entry(sfn_ptr, head); } } diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index fe12dfe254ec..54d077e1a2dc 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -14,10 +14,12 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/minmax.h> #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/sched.h> +#include <linux/string.h> #include <linux/uaccess.h> #include "encoding.h" @@ -1308,3 +1310,51 @@ noinline void __tsan_atomic_signal_fence(int memorder) } } EXPORT_SYMBOL(__tsan_atomic_signal_fence); + +#ifdef __HAVE_ARCH_MEMSET +void *__tsan_memset(void *s, int c, size_t count); +noinline void *__tsan_memset(void *s, int c, size_t count) +{ + /* + * Instead of not setting up watchpoints where accessed size is greater + * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. + */ + size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); + + check_access(s, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + return memset(s, c, count); +} +#else +void *__tsan_memset(void *s, int c, size_t count) __alias(memset); +#endif +EXPORT_SYMBOL(__tsan_memset); + +#ifdef __HAVE_ARCH_MEMMOVE +void *__tsan_memmove(void *dst, const void *src, size_t len); +noinline void *__tsan_memmove(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memmove(dst, src, len); +} +#else +void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); +#endif +EXPORT_SYMBOL(__tsan_memmove); + +#ifdef __HAVE_ARCH_MEMCPY +void *__tsan_memcpy(void *dst, const void *src, size_t len); +noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memcpy(dst, src, len); +} +#else +void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); +#endif +EXPORT_SYMBOL(__tsan_memcpy); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index cd9f5a66a690..3050631e528d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1766,7 +1766,13 @@ static int __unregister_kprobe_top(struct kprobe *p) if ((list_p != p) && (list_p->post_handler)) goto noclean; } - ap->post_handler = NULL; + /* + * For the kprobe-on-ftrace case, we keep the + * post_handler setting to identify this aggrprobe + * armed with kprobe_ipmodify_ops. + */ + if (!kprobe_ftrace(ap)) + ap->post_handler = NULL; } noclean: /* diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index d471d22a5e21..05106e6fbd0e 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -72,6 +72,9 @@ config TREE_SRCU help This option selects the full-fledged version of SRCU. +config NEED_SRCU_NMI_SAFE + def_bool HAVE_NMI && !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !TINY_SRCU + config TASKS_RCU_GENERIC def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU select SRCU @@ -311,4 +314,12 @@ config TASKS_TRACE_RCU_READ_MB Say N here if you hate read-side memory barriers. Take the default if you are unsure. +config RCU_LAZY + bool "RCU callback lazy invocation functionality" + depends on RCU_NOCB_CPU + default n + help + To save power, batch RCU callbacks and flush after delay, memory + pressure, or callback list growing too big. + endmenu # "RCU Subsystem" diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index be5979da07f5..65704cbc9df7 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -474,6 +474,14 @@ enum rcutorture_type { INVALID_RCU_FLAVOR }; +#if defined(CONFIG_RCU_LAZY) +unsigned long rcu_lazy_get_jiffies_till_flush(void); +void rcu_lazy_set_jiffies_till_flush(unsigned long j); +#else +static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; } +static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { } +#endif + #if defined(CONFIG_TREE_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, unsigned long *gp_seq); diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 3ef02d4a8108..91fb5905a008 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -95,6 +95,7 @@ torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?"); torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate."); +torture_param(int, kfree_by_call_rcu, 0, "Use call_rcu() to emulate kfree_rcu()?"); static char *scale_type = "rcu"; module_param(scale_type, charp, 0444); @@ -175,7 +176,7 @@ static struct rcu_scale_ops rcu_ops = { .get_gp_seq = rcu_get_gp_seq, .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed, - .async = call_rcu, + .async = call_rcu_hurry, .gp_barrier = rcu_barrier, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, @@ -659,6 +660,14 @@ struct kfree_obj { struct rcu_head rh; }; +/* Used if doing RCU-kfree'ing via call_rcu(). */ +static void kfree_call_rcu(struct rcu_head *rh) +{ + struct kfree_obj *obj = container_of(rh, struct kfree_obj, rh); + + kfree(obj); +} + static int kfree_scale_thread(void *arg) { @@ -696,6 +705,11 @@ kfree_scale_thread(void *arg) if (!alloc_ptr) return -ENOMEM; + if (kfree_by_call_rcu) { + call_rcu(&(alloc_ptr->rh), kfree_call_rcu); + continue; + } + // By default kfree_rcu_test_single and kfree_rcu_test_double are // initialized to false. If both have the same value (false or true) // both are randomly tested, otherwise only the one with value true @@ -767,11 +781,58 @@ kfree_scale_shutdown(void *arg) return -EINVAL; } +// Used if doing RCU-kfree'ing via call_rcu(). +static unsigned long jiffies_at_lazy_cb; +static struct rcu_head lazy_test1_rh; +static int rcu_lazy_test1_cb_called; +static void call_rcu_lazy_test1(struct rcu_head *rh) +{ + jiffies_at_lazy_cb = jiffies; + WRITE_ONCE(rcu_lazy_test1_cb_called, 1); +} + static int __init kfree_scale_init(void) { - long i; int firsterr = 0; + long i; + unsigned long jif_start; + unsigned long orig_jif; + + // Also, do a quick self-test to ensure laziness is as much as + // expected. + if (kfree_by_call_rcu && !IS_ENABLED(CONFIG_RCU_LAZY)) { + pr_alert("CONFIG_RCU_LAZY is disabled, falling back to kfree_rcu() for delayed RCU kfree'ing\n"); + kfree_by_call_rcu = 0; + } + + if (kfree_by_call_rcu) { + /* do a test to check the timeout. */ + orig_jif = rcu_lazy_get_jiffies_till_flush(); + + rcu_lazy_set_jiffies_till_flush(2 * HZ); + rcu_barrier(); + + jif_start = jiffies; + jiffies_at_lazy_cb = 0; + call_rcu(&lazy_test1_rh, call_rcu_lazy_test1); + + smp_cond_load_relaxed(&rcu_lazy_test1_cb_called, VAL == 1); + + rcu_lazy_set_jiffies_till_flush(orig_jif); + + if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) { + pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n"); + WARN_ON_ONCE(1); + return -1; + } + + if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start > 3 * HZ)) { + pr_alert("ERROR: call_rcu() CBs are being too lazy!\n"); + WARN_ON_ONCE(1); + return -1; + } + } kfree_nrealthreads = compute_real(kfree_nthreads); /* Start up the kthreads. */ @@ -784,7 +845,9 @@ kfree_scale_init(void) schedule_timeout_uninterruptible(1); } - pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj)); + pr_alert("kfree object size=%zu, kfree_by_call_rcu=%d\n", + kfree_mult * sizeof(struct kfree_obj), + kfree_by_call_rcu); kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]), GFP_KERNEL); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 503c2aa845a4..634df26a2c27 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -357,6 +357,10 @@ struct rcu_torture_ops { bool (*poll_gp_state_exp)(unsigned long oldstate); void (*cond_sync_exp)(unsigned long oldstate); void (*cond_sync_exp_full)(struct rcu_gp_oldstate *rgosp); + unsigned long (*get_comp_state)(void); + void (*get_comp_state_full)(struct rcu_gp_oldstate *rgosp); + bool (*same_gp_state)(unsigned long oldstate1, unsigned long oldstate2); + bool (*same_gp_state_full)(struct rcu_gp_oldstate *rgosp1, struct rcu_gp_oldstate *rgosp2); unsigned long (*get_gp_state)(void); void (*get_gp_state_full)(struct rcu_gp_oldstate *rgosp); unsigned long (*get_gp_completed)(void); @@ -510,7 +514,7 @@ static unsigned long rcu_no_completed(void) static void rcu_torture_deferred_free(struct rcu_torture *p) { - call_rcu(&p->rtort_rcu, rcu_torture_cb); + call_rcu_hurry(&p->rtort_rcu, rcu_torture_cb); } static void rcu_sync_torture_init(void) @@ -535,6 +539,10 @@ static struct rcu_torture_ops rcu_ops = { .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, + .same_gp_state = same_state_synchronize_rcu, + .same_gp_state_full = same_state_synchronize_rcu_full, + .get_comp_state = get_completed_synchronize_rcu, + .get_comp_state_full = get_completed_synchronize_rcu_full, .get_gp_state = get_state_synchronize_rcu, .get_gp_state_full = get_state_synchronize_rcu_full, .get_gp_completed = get_completed_synchronize_rcu, @@ -551,7 +559,7 @@ static struct rcu_torture_ops rcu_ops = { .start_gp_poll_exp_full = start_poll_synchronize_rcu_expedited_full, .poll_gp_state_exp = poll_state_synchronize_rcu, .cond_sync_exp = cond_synchronize_rcu_expedited, - .call = call_rcu, + .call = call_rcu_hurry, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, .stats = NULL, @@ -615,10 +623,14 @@ static struct rcu_torture_ops rcu_busted_ops = { DEFINE_STATIC_SRCU(srcu_ctl); static struct srcu_struct srcu_ctld; static struct srcu_struct *srcu_ctlp = &srcu_ctl; +static struct rcu_torture_ops srcud_ops; static int srcu_torture_read_lock(void) __acquires(srcu_ctlp) { - return srcu_read_lock(srcu_ctlp); + if (cur_ops == &srcud_ops) + return srcu_read_lock_nmisafe(srcu_ctlp); + else + return srcu_read_lock(srcu_ctlp); } static void @@ -642,7 +654,10 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp) { - srcu_read_unlock(srcu_ctlp, idx); + if (cur_ops == &srcud_ops) + srcu_read_unlock_nmisafe(srcu_ctlp, idx); + else + srcu_read_unlock(srcu_ctlp, idx); } static int torture_srcu_read_lock_held(void) @@ -848,7 +863,7 @@ static void rcu_tasks_torture_deferred_free(struct rcu_torture *p) static void synchronize_rcu_mult_test(void) { - synchronize_rcu_mult(call_rcu_tasks, call_rcu); + synchronize_rcu_mult(call_rcu_tasks, call_rcu_hurry); } static struct rcu_torture_ops tasks_ops = { @@ -1258,13 +1273,15 @@ static void rcu_torture_write_types(void) } else if (gp_normal && !cur_ops->deferred_free) { pr_alert("%s: gp_normal without primitives.\n", __func__); } - if (gp_poll1 && cur_ops->start_gp_poll && cur_ops->poll_gp_state) { + if (gp_poll1 && cur_ops->get_comp_state && cur_ops->same_gp_state && + cur_ops->start_gp_poll && cur_ops->poll_gp_state) { synctype[nsynctypes++] = RTWS_POLL_GET; pr_info("%s: Testing polling GPs.\n", __func__); } else if (gp_poll && (!cur_ops->start_gp_poll || !cur_ops->poll_gp_state)) { pr_alert("%s: gp_poll without primitives.\n", __func__); } - if (gp_poll_full1 && cur_ops->start_gp_poll_full && cur_ops->poll_gp_state_full) { + if (gp_poll_full1 && cur_ops->get_comp_state_full && cur_ops->same_gp_state_full + && cur_ops->start_gp_poll_full && cur_ops->poll_gp_state_full) { synctype[nsynctypes++] = RTWS_POLL_GET_FULL; pr_info("%s: Testing polling full-state GPs.\n", __func__); } else if (gp_poll_full && (!cur_ops->start_gp_poll_full || !cur_ops->poll_gp_state_full)) { @@ -1339,14 +1356,18 @@ rcu_torture_writer(void *arg) struct rcu_gp_oldstate cookie_full; int expediting = 0; unsigned long gp_snap; + unsigned long gp_snap1; struct rcu_gp_oldstate gp_snap_full; + struct rcu_gp_oldstate gp_snap1_full; int i; int idx; int oldnice = task_nice(current); + struct rcu_gp_oldstate rgo[NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE]; struct rcu_torture *rp; struct rcu_torture *old_rp; static DEFINE_TORTURE_RANDOM(rand); bool stutter_waited; + unsigned long ulo[NUM_ACTIVE_RCU_POLL_OLDSTATE]; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); if (!can_expedite) @@ -1463,20 +1484,43 @@ rcu_torture_writer(void *arg) break; case RTWS_POLL_GET: rcu_torture_writer_state = RTWS_POLL_GET; + for (i = 0; i < ARRAY_SIZE(ulo); i++) + ulo[i] = cur_ops->get_comp_state(); gp_snap = cur_ops->start_gp_poll(); rcu_torture_writer_state = RTWS_POLL_WAIT; - while (!cur_ops->poll_gp_state(gp_snap)) + while (!cur_ops->poll_gp_state(gp_snap)) { + gp_snap1 = cur_ops->get_gp_state(); + for (i = 0; i < ARRAY_SIZE(ulo); i++) + if (cur_ops->poll_gp_state(ulo[i]) || + cur_ops->same_gp_state(ulo[i], gp_snap1)) { + ulo[i] = gp_snap1; + break; + } + WARN_ON_ONCE(i >= ARRAY_SIZE(ulo)); torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + } rcu_torture_pipe_update(old_rp); break; case RTWS_POLL_GET_FULL: rcu_torture_writer_state = RTWS_POLL_GET_FULL; + for (i = 0; i < ARRAY_SIZE(rgo); i++) + cur_ops->get_comp_state_full(&rgo[i]); cur_ops->start_gp_poll_full(&gp_snap_full); rcu_torture_writer_state = RTWS_POLL_WAIT_FULL; - while (!cur_ops->poll_gp_state_full(&gp_snap_full)) + while (!cur_ops->poll_gp_state_full(&gp_snap_full)) { + cur_ops->get_gp_state_full(&gp_snap1_full); + for (i = 0; i < ARRAY_SIZE(rgo); i++) + if (cur_ops->poll_gp_state_full(&rgo[i]) || + cur_ops->same_gp_state_full(&rgo[i], + &gp_snap1_full)) { + rgo[i] = gp_snap1_full; + break; + } + WARN_ON_ONCE(i >= ARRAY_SIZE(rgo)); torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + } rcu_torture_pipe_update(old_rp); break; case RTWS_POLL_GET_EXP: @@ -3388,13 +3432,13 @@ static void rcu_test_debug_objects(void) /* Try to queue the rh2 pair of callbacks for the same grace period. */ preempt_disable(); /* Prevent preemption from interrupting test. */ rcu_read_lock(); /* Make it impossible to finish a grace period. */ - call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */ + call_rcu_hurry(&rh1, rcu_torture_leak_cb); /* Start grace period. */ local_irq_disable(); /* Make it harder to start a new grace period. */ - call_rcu(&rh2, rcu_torture_leak_cb); - call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */ + call_rcu_hurry(&rh2, rcu_torture_leak_cb); + call_rcu_hurry(&rh2, rcu_torture_err_cb); /* Duplicate callback. */ if (rhp) { - call_rcu(rhp, rcu_torture_leak_cb); - call_rcu(rhp, rcu_torture_err_cb); /* Another duplicate callback. */ + call_rcu_hurry(rhp, rcu_torture_leak_cb); + call_rcu_hurry(rhp, rcu_torture_err_cb); /* Another duplicate callback. */ } local_irq_enable(); rcu_read_unlock(); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 1c304fec89c0..ca4b5dcec675 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -417,7 +417,7 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx) for_each_possible_cpu(cpu) { struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu); - sum += READ_ONCE(cpuc->srcu_lock_count[idx]); + sum += atomic_long_read(&cpuc->srcu_lock_count[idx]); } return sum; } @@ -429,13 +429,18 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx) static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx) { int cpu; + unsigned long mask = 0; unsigned long sum = 0; for_each_possible_cpu(cpu) { struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu); - sum += READ_ONCE(cpuc->srcu_unlock_count[idx]); + sum += atomic_long_read(&cpuc->srcu_unlock_count[idx]); + if (IS_ENABLED(CONFIG_PROVE_RCU)) + mask = mask | READ_ONCE(cpuc->srcu_nmi_safety); } + WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask >> 1)), + "Mixed NMI-safe readers for srcu_struct at %ps.\n", ssp); return sum; } @@ -503,10 +508,10 @@ static bool srcu_readers_active(struct srcu_struct *ssp) for_each_possible_cpu(cpu) { struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu); - sum += READ_ONCE(cpuc->srcu_lock_count[0]); - sum += READ_ONCE(cpuc->srcu_lock_count[1]); - sum -= READ_ONCE(cpuc->srcu_unlock_count[0]); - sum -= READ_ONCE(cpuc->srcu_unlock_count[1]); + sum += atomic_long_read(&cpuc->srcu_lock_count[0]); + sum += atomic_long_read(&cpuc->srcu_lock_count[1]); + sum -= atomic_long_read(&cpuc->srcu_unlock_count[0]); + sum -= atomic_long_read(&cpuc->srcu_unlock_count[1]); } return sum; } @@ -626,6 +631,29 @@ void cleanup_srcu_struct(struct srcu_struct *ssp) } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); +#ifdef CONFIG_PROVE_RCU +/* + * Check for consistent NMI safety. + */ +void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe) +{ + int nmi_safe_mask = 1 << nmi_safe; + int old_nmi_safe_mask; + struct srcu_data *sdp; + + /* NMI-unsafe use in NMI is a bad sign */ + WARN_ON_ONCE(!nmi_safe && in_nmi()); + sdp = raw_cpu_ptr(ssp->sda); + old_nmi_safe_mask = READ_ONCE(sdp->srcu_nmi_safety); + if (!old_nmi_safe_mask) { + WRITE_ONCE(sdp->srcu_nmi_safety, nmi_safe_mask); + return; + } + WARN_ONCE(old_nmi_safe_mask != nmi_safe_mask, "CPU %d old state %d new state %d\n", sdp->cpu, old_nmi_safe_mask, nmi_safe_mask); +} +EXPORT_SYMBOL_GPL(srcu_check_nmi_safety); +#endif /* CONFIG_PROVE_RCU */ + /* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. @@ -636,7 +664,7 @@ int __srcu_read_lock(struct srcu_struct *ssp) int idx; idx = READ_ONCE(ssp->srcu_idx) & 0x1; - this_cpu_inc(ssp->sda->srcu_lock_count[idx]); + this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); smp_mb(); /* B */ /* Avoid leaking the critical section. */ return idx; } @@ -650,10 +678,45 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) { smp_mb(); /* C */ /* Avoid leaking the critical section. */ - this_cpu_inc(ssp->sda->srcu_unlock_count[idx]); + this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); +#ifdef CONFIG_NEED_SRCU_NMI_SAFE + +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct, but in an NMI-safe manner using RMW atomics. + * Returns an index that must be passed to the matching srcu_read_unlock(). + */ +int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) +{ + int idx; + struct srcu_data *sdp = raw_cpu_ptr(ssp->sda); + + idx = READ_ONCE(ssp->srcu_idx) & 0x1; + atomic_long_inc(&sdp->srcu_lock_count[idx]); + smp_mb__after_atomic(); /* B */ /* Avoid leaking the critical section. */ + return idx; +} +EXPORT_SYMBOL_GPL(__srcu_read_lock_nmisafe); + +/* + * Removes the count for the old reader from the appropriate per-CPU + * element of the srcu_struct. Note that this may well be a different + * CPU than that which was incremented by the corresponding srcu_read_lock(). + */ +void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) +{ + struct srcu_data *sdp = raw_cpu_ptr(ssp->sda); + + smp_mb__before_atomic(); /* C */ /* Avoid leaking the critical section. */ + atomic_long_inc(&sdp->srcu_unlock_count[idx]); +} +EXPORT_SYMBOL_GPL(__srcu_read_unlock_nmisafe); + +#endif // CONFIG_NEED_SRCU_NMI_SAFE + /* * Start an SRCU grace period. */ @@ -1090,7 +1153,12 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, int ss_state; check_init_srcu_struct(ssp); - idx = srcu_read_lock(ssp); + /* + * While starting a new grace period, make sure we are in an + * SRCU read-side critical section so that the grace-period + * sequence number cannot wrap around in the meantime. + */ + idx = __srcu_read_lock_nmisafe(ssp); ss_state = smp_load_acquire(&ssp->srcu_size_state); if (ss_state < SRCU_SIZE_WAIT_CALL) sdp = per_cpu_ptr(ssp->sda, 0); @@ -1123,7 +1191,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, srcu_funnel_gp_start(ssp, sdp, s, do_norm); else if (needexp) srcu_funnel_exp_start(ssp, sdp_mynode, s); - srcu_read_unlock(ssp, idx); + __srcu_read_unlock_nmisafe(ssp, idx); return s; } @@ -1427,13 +1495,13 @@ void srcu_barrier(struct srcu_struct *ssp) /* Initial count prevents reaching zero until all CBs are posted. */ atomic_set(&ssp->srcu_barrier_cpu_cnt, 1); - idx = srcu_read_lock(ssp); + idx = __srcu_read_lock_nmisafe(ssp); if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, 0)); else for_each_possible_cpu(cpu) srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu)); - srcu_read_unlock(ssp, idx); + __srcu_read_unlock_nmisafe(ssp, idx); /* Remove the initial count, at which point reaching zero can happen. */ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt)) @@ -1687,8 +1755,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) struct srcu_data *sdp; sdp = per_cpu_ptr(ssp->sda, cpu); - u0 = data_race(sdp->srcu_unlock_count[!idx]); - u1 = data_race(sdp->srcu_unlock_count[idx]); + u0 = data_race(atomic_long_read(&sdp->srcu_unlock_count[!idx])); + u1 = data_race(atomic_long_read(&sdp->srcu_unlock_count[idx])); /* * Make sure that a lock is always counted if the corresponding @@ -1696,8 +1764,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) */ smp_rmb(); - l0 = data_race(sdp->srcu_lock_count[!idx]); - l1 = data_race(sdp->srcu_lock_count[idx]); + l0 = data_race(atomic_long_read(&sdp->srcu_lock_count[!idx])); + l1 = data_race(atomic_long_read(&sdp->srcu_lock_count[idx])); c0 = l0 - u0; c1 = l1 - u1; diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 5cefc702158f..e550f97779b8 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -44,7 +44,7 @@ static void rcu_sync_func(struct rcu_head *rhp); static void rcu_sync_call(struct rcu_sync *rsp) { - call_rcu(&rsp->cb_head, rcu_sync_func); + call_rcu_hurry(&rsp->cb_head, rcu_sync_func); } /** diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index f5bf6fb430da..b0b885e071fa 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -728,7 +728,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) if (rtsi > 0 && !reported && time_after(j, lastinfo + rtsi)) { lastinfo = j; rtsi = rtsi * rcu_task_stall_info_mult; - pr_info("%s: %s grace period %lu is %lu jiffies old.\n", + pr_info("%s: %s grace period number %lu (since boot) is %lu jiffies old.\n", __func__, rtp->kname, rtp->tasks_gp_seq, j - rtp->gp_start); } } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index a33a8d4942c3..72913ce21258 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -44,7 +44,7 @@ static struct rcu_ctrlblk rcu_ctrlblk = { void rcu_barrier(void) { - wait_rcu_gp(call_rcu); + wait_rcu_gp(call_rcu_hurry); } EXPORT_SYMBOL(rcu_barrier); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 93416afebd59..d04f2192f02c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -301,12 +301,6 @@ static bool rcu_dynticks_in_eqs(int snap) return !(snap & RCU_DYNTICKS_IDX); } -/* Return true if the specified CPU is currently idle from an RCU viewpoint. */ -bool rcu_is_idle_cpu(int cpu) -{ - return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); -} - /* * Return true if the CPU corresponding to the specified rcu_data * structure has spent some time in an extended quiescent state since @@ -2108,7 +2102,7 @@ int rcutree_dying_cpu(unsigned int cpu) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return 0; - blkd = !!(rnp->qsmask & rdp->grpmask); + blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask); trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), blkd ? TPS("cpuofl-bgp") : TPS("cpuofl")); return 0; @@ -2418,7 +2412,7 @@ void rcu_force_quiescent_state(void) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = __this_cpu_read(rcu_data.mynode); + rnp = raw_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); @@ -2730,47 +2724,8 @@ static void check_cb_ovld(struct rcu_data *rdp) raw_spin_unlock_rcu_node(rnp); } -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. - * - * RCU read-side critical sections are delimited by rcu_read_lock() - * and rcu_read_unlock(), and may be nested. In addition, but only in - * v5.0 and later, regions of code across which interrupts, preemption, - * or softirqs have been disabled also serve as RCU read-side critical - * sections. This includes hardware interrupt handlers, softirq handlers, - * and NMI handlers. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - * - * Implementation of these memory-ordering guarantees is described here: - * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. - */ -void call_rcu(struct rcu_head *head, rcu_callback_t func) +static void +__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy) { static atomic_t doublefrees; unsigned long flags; @@ -2811,7 +2766,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func) } check_cb_ovld(rdp); - if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags)) + if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy)) return; // Enqueued onto ->nocb_bypass, so just leave. // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock. rcu_segcblist_enqueue(&rdp->cblist, head); @@ -2833,8 +2788,84 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func) local_irq_restore(flags); } } -EXPORT_SYMBOL_GPL(call_rcu); +#ifdef CONFIG_RCU_LAZY +/** + * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and + * flush all lazy callbacks (including the new one) to the main ->cblist while + * doing so. + * + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. + * + * Use this API instead of call_rcu() if you don't want the callback to be + * invoked after very long periods of time, which can happen on systems without + * memory pressure and on systems which are lightly loaded or mostly idle. + * This function will cause callbacks to be invoked sooner than later at the + * expense of extra power. Other than that, this function is identical to, and + * reuses call_rcu()'s logic. Refer to call_rcu() for more details about memory + * ordering and other functionality. + */ +void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) +{ + return __call_rcu_common(head, func, false); +} +EXPORT_SYMBOL_GPL(call_rcu_hurry); +#endif + +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * By default the callbacks are 'lazy' and are kept hidden from the main + * ->cblist to prevent starting of grace periods too soon. + * If you desire grace periods to start very soon, use call_rcu_hurry(). + * + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. + * + * RCU read-side critical sections are delimited by rcu_read_lock() + * and rcu_read_unlock(), and may be nested. In addition, but only in + * v5.0 and later, regions of code across which interrupts, preemption, + * or softirqs have been disabled also serve as RCU read-side critical + * sections. This includes hardware interrupt handlers, softirq handlers, + * and NMI handlers. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). + * + * Implementation of these memory-ordering guarantees is described here: + * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. + */ +void call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY)); +} +EXPORT_SYMBOL_GPL(call_rcu); /* Maximum number of jiffies to wait before draining a batch. */ #define KFREE_DRAIN_JIFFIES (5 * HZ) @@ -3509,7 +3540,7 @@ void synchronize_rcu(void) if (rcu_gp_is_expedited()) synchronize_rcu_expedited(); else - wait_rcu_gp(call_rcu); + wait_rcu_gp(call_rcu_hurry); return; } @@ -3896,6 +3927,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp) { unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence); unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap); + bool wake_nocb = false; + bool was_alldone = false; lockdep_assert_held(&rcu_state.barrier_lock); if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq)) @@ -3904,7 +3937,14 @@ static void rcu_barrier_entrain(struct rcu_data *rdp) rdp->barrier_head.func = rcu_barrier_callback; debug_rcu_head_queue(&rdp->barrier_head); rcu_nocb_lock(rdp); - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); + /* + * Flush bypass and wakeup rcuog if we add callbacks to an empty regular + * queue. This way we don't wait for bypass timer that can reach seconds + * if it's fully lazy. + */ + was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); + wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist); if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) { atomic_inc(&rcu_state.barrier_cpu_count); } else { @@ -3912,6 +3952,8 @@ static void rcu_barrier_entrain(struct rcu_data *rdp) rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence); } rcu_nocb_unlock(rdp); + if (wake_nocb) + wake_nocb_gp(rdp, false); smp_store_release(&rdp->barrier_seq_snap, gseq); } @@ -4278,8 +4320,6 @@ void rcu_report_dead(unsigned int cpu) // Do any dangling deferred wakeups. do_nocb_deferred_wakeup(rdp); - /* QS for any half-done expedited grace period. */ - rcu_report_exp_rdp(rdp); rcu_preempt_deferred_qs(current); /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ @@ -4327,7 +4367,7 @@ void rcutree_migrate_callbacks(int cpu) my_rdp = this_cpu_ptr(&rcu_data); my_rnp = my_rdp->mynode; rcu_nocb_lock(my_rdp); /* irqs already disabled. */ - WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies)); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies, false)); raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */ /* Leverage recent GPs and set GP for new callbacks. */ needwake = rcu_advance_cbs(my_rnp, rdp) || diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index d4a97e40ea9c..fcb5d696eb17 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -263,14 +263,16 @@ struct rcu_data { unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */ + long lazy_len; /* Length of buffered lazy callbacks. */ int cpu; }; /* Values for nocb_defer_wakeup field in struct rcu_data. */ #define RCU_NOCB_WAKE_NOT 0 #define RCU_NOCB_WAKE_BYPASS 1 -#define RCU_NOCB_WAKE 2 -#define RCU_NOCB_WAKE_FORCE 3 +#define RCU_NOCB_WAKE_LAZY 2 +#define RCU_NOCB_WAKE 3 +#define RCU_NOCB_WAKE_FORCE 4 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ @@ -439,10 +441,12 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); +static bool wake_nocb_gp(struct rcu_data *rdp, bool force); static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j); + unsigned long j, bool lazy); static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags); + bool *was_alldone, unsigned long flags, + bool lazy); static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, unsigned long flags); static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 18e9b4cd78ef..ed6c3cce28f2 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -937,7 +937,7 @@ void synchronize_rcu_expedited(void) /* If expedited grace periods are prohibited, fall back to normal. */ if (rcu_gp_is_normal()) { - wait_rcu_gp(call_rcu); + wait_rcu_gp(call_rcu_hurry); return; } diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 0a5f0ef41484..9e1c8caec5ce 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -257,6 +257,31 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force) } /* + * LAZY_FLUSH_JIFFIES decides the maximum amount of time that + * can elapse before lazy callbacks are flushed. Lazy callbacks + * could be flushed much earlier for a number of other reasons + * however, LAZY_FLUSH_JIFFIES will ensure no lazy callbacks are + * left unsubmitted to RCU after those many jiffies. + */ +#define LAZY_FLUSH_JIFFIES (10 * HZ) +static unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES; + +#ifdef CONFIG_RCU_LAZY +// To be called only from test code. +void rcu_lazy_set_jiffies_till_flush(unsigned long jif) +{ + jiffies_till_flush = jif; +} +EXPORT_SYMBOL(rcu_lazy_set_jiffies_till_flush); + +unsigned long rcu_lazy_get_jiffies_till_flush(void) +{ + return jiffies_till_flush; +} +EXPORT_SYMBOL(rcu_lazy_get_jiffies_till_flush); +#endif + +/* * Arrange to wake the GP kthread for this NOCB group at some future * time when it is safe to do so. */ @@ -269,10 +294,14 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); /* - * Bypass wakeup overrides previous deferments. In case - * of callback storm, no need to wake up too early. + * Bypass wakeup overrides previous deferments. In case of + * callback storms, no need to wake up too early. */ - if (waketype == RCU_NOCB_WAKE_BYPASS) { + if (waketype == RCU_NOCB_WAKE_LAZY && + rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) { + mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush); + WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); + } else if (waketype == RCU_NOCB_WAKE_BYPASS) { mod_timer(&rdp_gp->nocb_timer, jiffies + 2); WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); } else { @@ -293,12 +322,16 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, * proves to be initially empty, just return false because the no-CB GP * kthread may need to be awakened in this case. * + * Return true if there was something to be flushed and it succeeded, otherwise + * false. + * * Note that this function always returns true if rhp is NULL. */ -static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) +static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp_in, + unsigned long j, bool lazy) { struct rcu_cblist rcl; + struct rcu_head *rhp = rhp_in; WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp)); rcu_lockdep_assert_cblist_protected(rdp); @@ -310,7 +343,20 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, /* Note: ->cblist.len already accounts for ->nocb_bypass contents. */ if (rhp) rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ + + /* + * If the new CB requested was a lazy one, queue it onto the main + * ->cblist so that we can take advantage of the grace-period that will + * happen regardless. But queue it onto the bypass list first so that + * the lazy CB is ordered with the existing CBs in the bypass list. + */ + if (lazy && rhp) { + rcu_cblist_enqueue(&rdp->nocb_bypass, rhp); + rhp = NULL; + } rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp); + WRITE_ONCE(rdp->lazy_len, 0); + rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl); WRITE_ONCE(rdp->nocb_bypass_first, j); rcu_nocb_bypass_unlock(rdp); @@ -326,13 +372,13 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, * Note that this function always returns true if rhp is NULL. */ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) + unsigned long j, bool lazy) { if (!rcu_rdp_is_offloaded(rdp)) return true; rcu_lockdep_assert_cblist_protected(rdp); rcu_nocb_bypass_lock(rdp); - return rcu_nocb_do_flush_bypass(rdp, rhp, j); + return rcu_nocb_do_flush_bypass(rdp, rhp, j, lazy); } /* @@ -345,7 +391,7 @@ static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j) if (!rcu_rdp_is_offloaded(rdp) || !rcu_nocb_bypass_trylock(rdp)) return; - WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j)); + WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j, false)); } /* @@ -367,12 +413,14 @@ static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j) * there is only one CPU in operation. */ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags) + bool *was_alldone, unsigned long flags, + bool lazy) { unsigned long c; unsigned long cur_gp_seq; unsigned long j = jiffies; long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + bool bypass_is_lazy = (ncbs == READ_ONCE(rdp->lazy_len)); lockdep_assert_irqs_disabled(); @@ -417,24 +465,29 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, // If there hasn't yet been all that many ->cblist enqueues // this jiffy, tell the caller to enqueue onto ->cblist. But flush // ->nocb_bypass first. - if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy) { + // Lazy CBs throttle this back and do immediate bypass queuing. + if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy && !lazy) { rcu_nocb_lock(rdp); *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); if (*was_alldone) trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstQ")); - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j)); + + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j, false)); WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); return false; // Caller must enqueue the callback. } // If ->nocb_bypass has been used too long or is too full, // flush ->nocb_bypass to ->cblist. - if ((ncbs && j != READ_ONCE(rdp->nocb_bypass_first)) || + if ((ncbs && !bypass_is_lazy && j != READ_ONCE(rdp->nocb_bypass_first)) || + (ncbs && bypass_is_lazy && + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush))) || ncbs >= qhimark) { rcu_nocb_lock(rdp); - if (!rcu_nocb_flush_bypass(rdp, rhp, j)) { - *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); + + if (!rcu_nocb_flush_bypass(rdp, rhp, j, lazy)) { if (*was_alldone) trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstQ")); @@ -447,7 +500,12 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, rcu_advance_cbs_nowake(rdp->mynode, rdp); rdp->nocb_gp_adv_time = j; } - rcu_nocb_unlock_irqrestore(rdp, flags); + + // The flush succeeded and we moved CBs into the regular list. + // Don't wait for the wake up timer as it may be too far ahead. + // Wake up the GP thread now instead, if the cblist was empty. + __call_rcu_nocb_wake(rdp, *was_alldone, flags); + return true; // Callback already enqueued. } @@ -457,13 +515,24 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ rcu_cblist_enqueue(&rdp->nocb_bypass, rhp); + + if (lazy) + WRITE_ONCE(rdp->lazy_len, rdp->lazy_len + 1); + if (!ncbs) { WRITE_ONCE(rdp->nocb_bypass_first, j); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQ")); } rcu_nocb_bypass_unlock(rdp); smp_mb(); /* Order enqueue before wake. */ - if (ncbs) { + // A wake up of the grace period kthread or timer adjustment + // needs to be done only if: + // 1. Bypass list was fully empty before (this is the first + // bypass list entry), or: + // 2. Both of these conditions are met: + // a. The bypass list previously had only lazy CBs, and: + // b. The new CB is non-lazy. + if (ncbs && (!bypass_is_lazy || lazy)) { local_irq_restore(flags); } else { // No-CBs GP kthread might be indefinitely asleep, if so, wake. @@ -491,8 +560,10 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, unsigned long flags) __releases(rdp->nocb_lock) { + long bypass_len; unsigned long cur_gp_seq; unsigned long j; + long lazy_len; long len; struct task_struct *t; @@ -506,9 +577,16 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, } // Need to actually to a wakeup. len = rcu_segcblist_n_cbs(&rdp->cblist); + bypass_len = rcu_cblist_n_cbs(&rdp->nocb_bypass); + lazy_len = READ_ONCE(rdp->lazy_len); if (was_alldone) { rdp->qlen_last_fqs_check = len; - if (!irqs_disabled_flags(flags)) { + // Only lazy CBs in bypass list + if (lazy_len && bypass_len == lazy_len) { + rcu_nocb_unlock_irqrestore(rdp, flags); + wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY, + TPS("WakeLazy")); + } else if (!irqs_disabled_flags(flags)) { /* ... if queue was empty ... */ rcu_nocb_unlock_irqrestore(rdp, flags); wake_nocb_gp(rdp, false); @@ -599,12 +677,12 @@ static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu) static void nocb_gp_wait(struct rcu_data *my_rdp) { bool bypass = false; - long bypass_ncbs; int __maybe_unused cpu = my_rdp->cpu; unsigned long cur_gp_seq; unsigned long flags; bool gotcbs = false; unsigned long j = jiffies; + bool lazy = false; bool needwait_gp = false; // This prevents actual uninitialized use. bool needwake; bool needwake_gp; @@ -634,24 +712,43 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) * won't be ignored for long. */ list_for_each_entry(rdp, &my_rdp->nocb_head_rdp, nocb_entry_rdp) { + long bypass_ncbs; + bool flush_bypass = false; + long lazy_ncbs; + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check")); rcu_nocb_lock_irqsave(rdp, flags); lockdep_assert_held(&rdp->nocb_lock); bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - if (bypass_ncbs && + lazy_ncbs = READ_ONCE(rdp->lazy_len); + + if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) && + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) || + bypass_ncbs > 2 * qhimark)) { + flush_bypass = true; + } else if (bypass_ncbs && (lazy_ncbs != bypass_ncbs) && (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) || bypass_ncbs > 2 * qhimark)) { - // Bypass full or old, so flush it. - (void)rcu_nocb_try_flush_bypass(rdp, j); - bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + flush_bypass = true; } else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) { rcu_nocb_unlock_irqrestore(rdp, flags); continue; /* No callbacks here, try next. */ } + + if (flush_bypass) { + // Bypass full or old, so flush it. + (void)rcu_nocb_try_flush_bypass(rdp, j); + bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); + lazy_ncbs = READ_ONCE(rdp->lazy_len); + } + if (bypass_ncbs) { trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("Bypass")); - bypass = true; + bypass_ncbs == lazy_ncbs ? TPS("Lazy") : TPS("Bypass")); + if (bypass_ncbs == lazy_ncbs) + lazy = true; + else + bypass = true; } rnp = rdp->mynode; @@ -699,12 +796,20 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) my_rdp->nocb_gp_gp = needwait_gp; my_rdp->nocb_gp_seq = needwait_gp ? wait_gp_seq : 0; - if (bypass && !rcu_nocb_poll) { - // At least one child with non-empty ->nocb_bypass, so set - // timer in order to avoid stranding its callbacks. - wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_BYPASS, - TPS("WakeBypassIsDeferred")); + // At least one child with non-empty ->nocb_bypass, so set + // timer in order to avoid stranding its callbacks. + if (!rcu_nocb_poll) { + // If bypass list only has lazy CBs. Add a deferred lazy wake up. + if (lazy && !bypass) { + wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_LAZY, + TPS("WakeLazyIsDeferred")); + // Otherwise add a deferred bypass wake up. + } else if (bypass) { + wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_BYPASS, + TPS("WakeBypassIsDeferred")); + } } + if (rcu_nocb_poll) { /* Polling, so trace if first poll in the series. */ if (gotcbs) @@ -1030,7 +1135,7 @@ static long rcu_nocb_rdp_deoffload(void *arg) * return false, which means that future calls to rcu_nocb_try_bypass() * will refuse to put anything into the bypass. */ - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); /* * Start with invoking rcu_core() early. This way if the current thread * happens to preempt an ongoing call to rcu_core() in the middle, @@ -1207,47 +1312,87 @@ int rcu_nocb_cpu_offload(int cpu) } EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload); -void __init rcu_init_nohz(void) +static unsigned long +lazy_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { int cpu; - bool need_rcu_nocb_mask = false; - bool offload_all = false; - struct rcu_data *rdp; + unsigned long count = 0; -#if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) - if (!rcu_state.nocb_is_setup) { - need_rcu_nocb_mask = true; - offload_all = true; + /* Snapshot count of all CPUs */ + for_each_possible_cpu(cpu) { + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + + count += READ_ONCE(rdp->lazy_len); } -#endif /* #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) */ -#if defined(CONFIG_NO_HZ_FULL) - if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) { - need_rcu_nocb_mask = true; - offload_all = false; /* NO_HZ_FULL has its own mask. */ + return count ? count : SHRINK_EMPTY; +} + +static unsigned long +lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + int cpu; + unsigned long flags; + unsigned long count = 0; + + /* Snapshot count of all CPUs */ + for_each_possible_cpu(cpu) { + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + int _count = READ_ONCE(rdp->lazy_len); + + if (_count == 0) + continue; + rcu_nocb_lock_irqsave(rdp, flags); + WRITE_ONCE(rdp->lazy_len, 0); + rcu_nocb_unlock_irqrestore(rdp, flags); + wake_nocb_gp(rdp, false); + sc->nr_to_scan -= _count; + count += _count; + if (sc->nr_to_scan <= 0) + break; } -#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + return count ? count : SHRINK_STOP; +} + +static struct shrinker lazy_rcu_shrinker = { + .count_objects = lazy_rcu_shrink_count, + .scan_objects = lazy_rcu_shrink_scan, + .batch = 0, + .seeks = DEFAULT_SEEKS, +}; + +void __init rcu_init_nohz(void) +{ + int cpu; + struct rcu_data *rdp; + const struct cpumask *cpumask = NULL; + +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) + cpumask = tick_nohz_full_mask; +#endif - if (need_rcu_nocb_mask) { + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) && + !rcu_state.nocb_is_setup && !cpumask) + cpumask = cpu_possible_mask; + + if (cpumask) { if (!cpumask_available(rcu_nocb_mask)) { if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); return; } } + + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, cpumask); rcu_state.nocb_is_setup = true; } if (!rcu_state.nocb_is_setup) return; -#if defined(CONFIG_NO_HZ_FULL) - if (tick_nohz_full_running) - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); -#endif /* #if defined(CONFIG_NO_HZ_FULL) */ - - if (offload_all) - cpumask_setall(rcu_nocb_mask); + if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy")) + pr_err("Failed to register lazy_rcu shrinker!\n"); if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n"); @@ -1284,6 +1429,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) raw_spin_lock_init(&rdp->nocb_gp_lock); timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0); rcu_cblist_init(&rdp->nocb_bypass); + WRITE_ONCE(rdp->lazy_len, 0); mutex_init(&rdp->nocb_gp_kthread_mutex); } @@ -1564,14 +1710,19 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) { } +static bool wake_nocb_gp(struct rcu_data *rdp, bool force) +{ + return false; +} + static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) + unsigned long j, bool lazy) { return true; } static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags) + bool *was_alldone, unsigned long flags, bool lazy) { return false; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e3142ee35fc6..7b0fe741a088 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1221,11 +1221,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) * We don't include outgoingcpu in the affinity set, use -1 if there is * no outgoing CPU. If there are no CPUs left in the affinity set, * this function allows the kthread to execute on any CPU. + * + * Any future concurrent calls are serialized via ->boost_kthread_mutex. */ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { struct task_struct *t = rnp->boost_kthread_task; - unsigned long mask = rcu_rnp_online_cpus(rnp); + unsigned long mask; cpumask_var_t cm; int cpu; @@ -1234,6 +1236,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) return; mutex_lock(&rnp->boost_kthread_mutex); + mask = rcu_rnp_online_cpus(rnp); for_each_leaf_node_possible_cpu(rnp, cpu) if ((mask & leaf_node_cpu_bit(rnp, cpu)) && cpu != outgoingcpu) diff --git a/kernel/rseq.c b/kernel/rseq.c index bda8175f8f99..d38ab944105d 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -171,12 +171,27 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) return 0; } +static bool rseq_warn_flags(const char *str, u32 flags) +{ + u32 test_flags; + + if (!flags) + return false; + test_flags = flags & RSEQ_CS_NO_RESTART_FLAGS; + if (test_flags) + pr_warn_once("Deprecated flags (%u) in %s ABI structure", test_flags, str); + test_flags = flags & ~RSEQ_CS_NO_RESTART_FLAGS; + if (test_flags) + pr_warn_once("Unknown flags (%u) in %s ABI structure", test_flags, str); + return true; +} + static int rseq_need_restart(struct task_struct *t, u32 cs_flags) { u32 flags, event_mask; int ret; - if (WARN_ON_ONCE(cs_flags & RSEQ_CS_NO_RESTART_FLAGS) || cs_flags) + if (rseq_warn_flags("rseq_cs", cs_flags)) return -EINVAL; /* Get thread flags. */ @@ -184,7 +199,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags) if (ret) return ret; - if (WARN_ON_ONCE(flags & RSEQ_CS_NO_RESTART_FLAGS) || flags) + if (rseq_warn_flags("rseq", flags)) return -EINVAL; /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cb2aa2b54c7a..daff72f00385 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4200,6 +4200,40 @@ out: return success; } +static bool __task_needs_rq_lock(struct task_struct *p) +{ + unsigned int state = READ_ONCE(p->__state); + + /* + * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when + * the task is blocked. Make sure to check @state since ttwu() can drop + * locks at the end, see ttwu_queue_wakelist(). + */ + if (state == TASK_RUNNING || state == TASK_WAKING) + return true; + + /* + * Ensure we load p->on_rq after p->__state, otherwise it would be + * possible to, falsely, observe p->on_rq == 0. + * + * See try_to_wake_up() for a longer comment. + */ + smp_rmb(); + if (p->on_rq) + return true; + +#ifdef CONFIG_SMP + /* + * Ensure the task has finished __schedule() and will not be referenced + * anymore. Again, see try_to_wake_up() for a longer comment. + */ + smp_rmb(); + smp_cond_load_acquire(&p->on_cpu, !VAL); +#endif + + return false; +} + /** * task_call_func - Invoke a function on task in fixed state * @p: Process for which the function is to be invoked, can be @current. @@ -4217,28 +4251,12 @@ out: int task_call_func(struct task_struct *p, task_call_f func, void *arg) { struct rq *rq = NULL; - unsigned int state; struct rq_flags rf; int ret; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); - state = READ_ONCE(p->__state); - - /* - * Ensure we load p->on_rq after p->__state, otherwise it would be - * possible to, falsely, observe p->on_rq == 0. - * - * See try_to_wake_up() for a longer comment. - */ - smp_rmb(); - - /* - * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when - * the task is blocked. Make sure to check @state since ttwu() can drop - * locks at the end, see ttwu_queue_wakelist(). - */ - if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq) + if (__task_needs_rq_lock(p)) rq = __task_rq_lock(p, &rf); /* diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 9161d1136d01..1207c78f85c1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -25,9 +25,6 @@ struct sugov_policy { unsigned int next_freq; unsigned int cached_raw_freq; - /* max CPU capacity, which is equal for all CPUs in freq. domain */ - unsigned long max; - /* The next fields are only needed if fast switch cannot be used: */ struct irq_work irq_work; struct kthread_work work; @@ -51,6 +48,7 @@ struct sugov_cpu { unsigned long util; unsigned long bw_dl; + unsigned long max; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -160,6 +158,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); + sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->bw_dl = cpu_bw_dl(rq); sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), FREQUENCY_UTIL, NULL); @@ -254,7 +253,6 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, */ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long boost; /* No boost currently required */ @@ -282,8 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = sg_cpu->iowait_boost * sg_policy->max; - boost >>= SCHED_CAPACITY_SHIFT; + boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; @@ -340,7 +337,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, if (!sugov_update_single_common(sg_cpu, time, flags)) return; - next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max); + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. @@ -376,7 +373,6 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, unsigned int flags) { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); - struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long prev_util = sg_cpu->util; /* @@ -403,8 +399,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, sg_cpu->util = prev_util; cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), - map_util_perf(sg_cpu->util), - sg_policy->max); + map_util_perf(sg_cpu->util), sg_cpu->max); sg_cpu->sg_policy->last_freq_update_time = time; } @@ -413,19 +408,25 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned long util = 0; + unsigned long util = 0, max = 1; unsigned int j; for_each_cpu(j, policy->cpus) { struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); + unsigned long j_util, j_max; sugov_get_util(j_sg_cpu); sugov_iowait_apply(j_sg_cpu, time); + j_util = j_sg_cpu->util; + j_max = j_sg_cpu->max; - util = max(j_sg_cpu->util, util); + if (j_util * max > j_max * util) { + util = j_util; + max = j_max; + } } - return get_next_freq(sg_policy, util, sg_policy->max); + return get_next_freq(sg_policy, util, max); } static void @@ -751,7 +752,7 @@ static int sugov_start(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; void (*uu)(struct update_util_data *data, u64 time, unsigned int flags); - unsigned int cpu = cpumask_first(policy->cpus); + unsigned int cpu; sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; sg_policy->last_freq_update_time = 0; @@ -759,7 +760,6 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->work_in_progress = false; sg_policy->limits_changed = false; sg_policy->cached_raw_freq = 0; - sg_policy->max = arch_scale_cpu_capacity(cpu); sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 188c305aeb8b..c6d9dec11b74 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -267,13 +267,14 @@ int proc_dostring(struct ctl_table *table, int write, ppos); } -static size_t proc_skip_spaces(char **buf) +static void proc_skip_spaces(char **buf, size_t *size) { - size_t ret; - char *tmp = skip_spaces(*buf); - ret = tmp - *buf; - *buf = tmp; - return ret; + while (*size) { + if (!isspace(**buf)) + break; + (*size)--; + (*buf)++; + } } static void proc_skip_char(char **buf, size_t *size, const char v) @@ -342,13 +343,12 @@ static int proc_get_long(char **buf, size_t *size, unsigned long *val, bool *neg, const char *perm_tr, unsigned perm_tr_len, char *tr) { - int len; char *p, tmp[TMPBUFLEN]; + ssize_t len = *size; - if (!*size) + if (len <= 0) return -EINVAL; - len = *size; if (len > TMPBUFLEN - 1) len = TMPBUFLEN - 1; @@ -521,7 +521,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, bool neg; if (write) { - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -548,7 +548,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; @@ -590,7 +590,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) { err = -EINVAL; goto out_free; @@ -610,7 +610,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, } if (!err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); out_free: if (err) @@ -1075,7 +1075,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (write) { bool neg; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -1104,7 +1104,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7dc023641bf1..33236241f236 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1289,6 +1289,7 @@ static int ftrace_add_mod(struct trace_array *tr, if (!ftrace_mod) return -ENOMEM; + INIT_LIST_HEAD(&ftrace_mod->list); ftrace_mod->func = kstrdup(func, GFP_KERNEL); ftrace_mod->module = kstrdup(module, GFP_KERNEL); ftrace_mod->enable = enable; @@ -3190,7 +3191,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) /* if we can't allocate this size, try something smaller */ if (!order) return -ENOMEM; - order >>= 1; + order--; goto again; } @@ -7391,7 +7392,7 @@ void __init ftrace_init(void) } pr_info("ftrace: allocating %ld entries in %ld pages\n", - count, count / ENTRIES_PER_PAGE + 1); + count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); ret = ftrace_process_locs(NULL, __start_mcount_loc, diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index d81f7c51025c..c736487fc0e4 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -73,6 +73,10 @@ static struct trace_event_file *gen_kretprobe_test; #define KPROBE_GEN_TEST_ARG3 NULL #endif +static bool trace_event_file_is_valid(struct trace_event_file *input) +{ + return input && !IS_ERR(input); +} /* * Test to make sure we can create a kprobe event, then add more @@ -139,6 +143,8 @@ static int __init test_gen_kprobe_cmd(void) kfree(buf); return ret; delete: + if (trace_event_file_is_valid(gen_kprobe_test)) + gen_kprobe_test = NULL; /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); goto out; @@ -202,6 +208,8 @@ static int __init test_gen_kretprobe_cmd(void) kfree(buf); return ret; delete: + if (trace_event_file_is_valid(gen_kretprobe_test)) + gen_kretprobe_test = NULL; /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); goto out; @@ -217,10 +225,12 @@ static int __init kprobe_event_gen_test_init(void) ret = test_gen_kretprobe_cmd(); if (ret) { - WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, - "kprobes", - "gen_kretprobe_test", false)); - trace_put_event_file(gen_kretprobe_test); + if (trace_event_file_is_valid(gen_kretprobe_test)) { + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + trace_put_event_file(gen_kretprobe_test); + } WARN_ON(kprobe_event_delete("gen_kretprobe_test")); } @@ -229,24 +239,30 @@ static int __init kprobe_event_gen_test_init(void) static void __exit kprobe_event_gen_test_exit(void) { - /* Disable the event or you can't remove it */ - WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, - "kprobes", - "gen_kprobe_test", false)); + if (trace_event_file_is_valid(gen_kprobe_test)) { + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, + "kprobes", + "gen_kprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kprobe_test); + } - /* Now give the file and instance back */ - trace_put_event_file(gen_kprobe_test); /* Now unregister and free the event */ WARN_ON(kprobe_event_delete("gen_kprobe_test")); - /* Disable the event or you can't remove it */ - WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, - "kprobes", - "gen_kretprobe_test", false)); + if (trace_event_file_is_valid(gen_kretprobe_test)) { + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kretprobe_test); + } - /* Now give the file and instance back */ - trace_put_event_file(gen_kretprobe_test); /* Now unregister and free the event */ WARN_ON(kprobe_event_delete("gen_kretprobe_test")); diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index c69d82273ce7..32c3dfdb4d6a 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -83,8 +83,10 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler) { struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL); - if (!rh || !handler) + if (!rh || !handler) { + kfree(rh); return NULL; + } rh->data = data; rh->handler = handler; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9712083832f4..b21bf14bae9b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -519,6 +519,7 @@ struct ring_buffer_per_cpu { local_t committing; local_t commits; local_t pages_touched; + local_t pages_lost; local_t pages_read; long last_pages_touch; size_t shortest_full; @@ -894,10 +895,18 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) { size_t read; + size_t lost; size_t cnt; read = local_read(&buffer->buffers[cpu]->pages_read); + lost = local_read(&buffer->buffers[cpu]->pages_lost); cnt = local_read(&buffer->buffers[cpu]->pages_touched); + + if (WARN_ON_ONCE(cnt < lost)) + return 0; + + cnt -= lost; + /* The reader can read an empty page, but not more than that */ if (cnt < read) { WARN_ON_ONCE(read > cnt + 1); @@ -907,6 +916,21 @@ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) return cnt - read; } +static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + size_t nr_pages; + size_t dirty; + + nr_pages = cpu_buffer->nr_pages; + if (!nr_pages || !full) + return true; + + dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + + return (dirty * 100) > (full * nr_pages); +} + /* * rb_wake_up_waiters - wake up tasks waiting for ring buffer input * @@ -1046,22 +1070,20 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) !ring_buffer_empty_cpu(buffer, cpu)) { unsigned long flags; bool pagebusy; - size_t nr_pages; - size_t dirty; + bool done; if (!full) break; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - nr_pages = cpu_buffer->nr_pages; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + done = !pagebusy && full_hit(buffer, cpu, full); + if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (!pagebusy && - (!nr_pages || (dirty * 100) > full * nr_pages)) + if (done) break; } @@ -1087,6 +1109,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * @cpu: the cpu buffer to wait on * @filp: the file descriptor * @poll_table: The poll descriptor + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise @@ -1096,14 +1119,15 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * zero otherwise. */ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, - struct file *filp, poll_table *poll_table) + struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *work; - if (cpu == RING_BUFFER_ALL_CPUS) + if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; - else { + full = 0; + } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -EINVAL; @@ -1111,8 +1135,14 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, work = &cpu_buffer->irq_work; } - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + if (full) { + poll_wait(filp, &work->full_waiters, poll_table); + work->full_waiters_pending = true; + } else { + poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + } + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -1128,6 +1158,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); + if (full) + return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -1769,9 +1802,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(cpu_buffer->reader_page); - rb_head_page_deactivate(cpu_buffer); - if (head) { + rb_head_page_deactivate(cpu_buffer); + list_for_each_entry_safe(bpage, tmp, head, list) { list_del_init(&bpage->list); free_buffer_page(bpage); @@ -2007,6 +2040,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) */ local_add(page_entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_inc(&cpu_buffer->pages_lost); } /* @@ -2491,6 +2525,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, */ local_add(entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_inc(&cpu_buffer->pages_lost); /* * The entries will be zeroed out when we move the @@ -3155,10 +3190,6 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, static __always_inline void rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { - size_t nr_pages; - size_t dirty; - size_t full; - if (buffer->irq_work.waiters_pending) { buffer->irq_work.waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ @@ -3182,10 +3213,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched); - full = cpu_buffer->shortest_full; - nr_pages = cpu_buffer->nr_pages; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu); - if (full && nr_pages && (dirty * 100) <= full * nr_pages) + if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full)) return; cpu_buffer->irq_work.wakeup_full = true; @@ -5248,6 +5276,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); local_set(&cpu_buffer->pages_touched, 0); + local_set(&cpu_buffer->pages_lost, 0); local_set(&cpu_buffer->pages_read, 0); cpu_buffer->last_pages_touch = 0; cpu_buffer->shortest_full = 0; diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 0b15e975d2c2..8d77526892f4 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -120,15 +120,13 @@ static int __init test_gen_synth_cmd(void) /* Now generate a gen_synth_test event */ ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals)); - out: + free: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ synth_event_delete("gen_synth_test"); - free: - kfree(buf); - - goto out; + goto free; } /* @@ -227,15 +225,13 @@ static int __init test_empty_synth_event(void) /* Now trace an empty_synth_test event */ ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals)); - out: + free: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ synth_event_delete("empty_synth_test"); - free: - kfree(buf); - - goto out; + goto free; } static struct synth_field_desc create_synth_test_fields[] = { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 47a44b055a1d..5cfc95a52bc3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2180,10 +2180,12 @@ void tracing_reset_online_cpus(struct array_buffer *buf) } /* Must have trace_types_lock held */ -void tracing_reset_all_online_cpus(void) +void tracing_reset_all_online_cpus_unlocked(void) { struct trace_array *tr; + lockdep_assert_held(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->clear_trace) continue; @@ -2195,6 +2197,13 @@ void tracing_reset_all_online_cpus(void) } } +void tracing_reset_all_online_cpus(void) +{ + mutex_lock(&trace_types_lock); + tracing_reset_all_online_cpus_unlocked(); + mutex_unlock(&trace_types_lock); +} + /* * The tgid_map array maps from pid to tgid; i.e. the value stored at index i * is the tgid last observed corresponding to pid=i. @@ -6657,6 +6666,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) mutex_unlock(&trace_types_lock); free_cpumask_var(iter->started); + kfree(iter->fmt); mutex_destroy(&iter->mutex); kfree(iter); @@ -6681,7 +6691,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, - filp, poll_table); + filp, poll_table, iter->tr->buffer_percent); } static __poll_t @@ -7802,6 +7812,7 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, int len) { struct tracing_log_err *err; + char *cmd; if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { err = alloc_tracing_log_err(len); @@ -7810,12 +7821,12 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, return err; } - + cmd = kzalloc(len, GFP_KERNEL); + if (!cmd) + return ERR_PTR(-ENOMEM); err = list_first_entry(&tr->err_log, struct tracing_log_err, list); kfree(err->cmd); - err->cmd = kzalloc(len, GFP_KERNEL); - if (!err->cmd) - return ERR_PTR(-ENOMEM); + err->cmd = cmd; list_del(&err->list); return err; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 54ee5711c729..d42e24507152 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -580,6 +580,7 @@ int tracing_is_enabled(void); void tracing_reset_online_cpus(struct array_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); +void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index 154996684fb5..4376887e0d8a 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -118,6 +118,7 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type if (ret) break; } + tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex); out: argv_free(argv); @@ -214,6 +215,7 @@ int dyn_events_release_all(struct dyn_event_operations *type) break; } out: + tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex); return ret; diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 5dd0617e5df6..352b65e2b910 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -52,6 +52,7 @@ static void trace_event_probe_cleanup(struct trace_eprobe *ep) kfree(ep->event_system); if (ep->event) trace_event_put_ref(ep->event); + kfree(ep->filter_str); kfree(ep); } @@ -563,6 +564,9 @@ static void eprobe_trigger_func(struct event_trigger_data *data, { struct eprobe_data *edata = data->private_data; + if (unlikely(!rec)) + return; + __eprobe_trace_func(edata, rec); } @@ -642,7 +646,7 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file) INIT_LIST_HEAD(&trigger->list); if (ep->filter_str) { - ret = create_event_filter(file->tr, file->event_call, + ret = create_event_filter(file->tr, ep->event, ep->filter_str, false, &filter); if (ret) goto error; @@ -900,7 +904,7 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[ static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[]) { - struct event_filter *dummy; + struct event_filter *dummy = NULL; int i, ret, len = 0; char *p; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0356cae0cf74..f71ea6e79b3c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2880,7 +2880,10 @@ static int probe_remove_event_call(struct trace_event_call *call) * TRACE_REG_UNREGISTER. */ if (file->flags & EVENT_FILE_FL_ENABLED) - return -EBUSY; + goto busy; + + if (file->flags & EVENT_FILE_FL_WAS_ENABLED) + tr->clear_trace = true; /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this @@ -2893,6 +2896,12 @@ static int probe_remove_event_call(struct trace_event_call *call) __trace_remove_event_call(call); return 0; + busy: + /* No need to clear the trace now */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + tr->clear_trace = false; + } + return -EBUSY; } /* Remove an event_call */ @@ -2972,7 +2981,7 @@ static void trace_module_remove_events(struct module *mod) * over from this module may be passed to the new module events and * unexpected results may occur. */ - tracing_reset_all_online_cpus(); + tracing_reset_all_online_cpus_unlocked(); } static int trace_module_notify(struct notifier_block *self, diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 48465f7e97b4..1c82478e8dff 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -983,7 +983,7 @@ static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data, * A trigger can define one or more variables. If any one of them is * currently referenced by any other trigger, this function will * determine that. - + * * Typically used to determine whether or not a trigger can be removed * - if there are any references to a trigger's variables, it cannot. * @@ -3226,7 +3226,7 @@ static struct field_var *create_field_var(struct hist_trigger_data *hist_data, * events. However, for convenience, users are allowed to directly * specify an event field in an action, which will be automatically * converted into a variable on their behalf. - + * * This function creates a field variable with the name var_name on * the hist trigger currently being defined on the target event. If * subsys_name and event_name are specified, this function simply @@ -5143,6 +5143,9 @@ static void event_hist_trigger(struct event_trigger_data *data, void *key = NULL; unsigned int i; + if (unlikely(!rbe)) + return; + memset(compound_key, 0, hist_data->key_size); for_each_hist_key_field(i, hist_data) { diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index e310052dc83c..c3b582d19b62 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -828,10 +828,9 @@ static int register_synth_event(struct synth_event *event) } ret = set_synth_event_print_fmt(call); - if (ret < 0) { + /* unregister_trace_event() will be called inside */ + if (ret < 0) trace_remove_event_call(call); - goto err; - } out: return ret; err: @@ -1426,7 +1425,6 @@ int synth_event_delete(const char *event_name) mutex_unlock(&event_mutex); if (mod) { - mutex_lock(&trace_types_lock); /* * It is safest to reset the ring buffer if the module * being unloaded registered any events that were @@ -1438,7 +1436,6 @@ int synth_event_delete(const char *event_name) * occur. */ tracing_reset_all_online_cpus(); - mutex_unlock(&trace_types_lock); } return ret; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index ae78c2d53c8a..539b08ae7020 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1100,8 +1100,10 @@ static int user_event_create(const char *raw_command) group = current_user_event_group(); - if (!group) + if (!group) { + kfree(name); return -ENOENT; + } mutex_lock(&group->reg_mutex); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 78d536d3ff3d..4300c5dc4e5d 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id) void osnoise_trace_irq_exit(int id, const char *desc) { struct osnoise_variables *osn_var = this_cpu_osn_var(); - int duration; + s64 duration; if (!osn_var->sampling) return; @@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback(void *data, unsigned int vec_nr) static void trace_softirq_exit_callback(void *data, unsigned int vec_nr) { struct osnoise_variables *osn_var = this_cpu_osn_var(); - int duration; + s64 duration; if (!osn_var->sampling) return; @@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *osn_var, struct task_struct *t) static void thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) { - int duration; + s64 duration; if (!osn_var->sampling) return; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index b69e207012c9..942ddbdace4a 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -201,8 +201,6 @@ print_syscall_exit(struct trace_iterator *iter, int flags, return trace_handle_return(s); } -extern char *__bad_type_size(void); - #define SYSCALL_FIELD(_type, _name) { \ .type = #_type, .name = #_name, \ .size = sizeof(_type), .align = __alignof__(_type), \ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7cd5f5e7e0a1..07895deca271 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1771,7 +1771,7 @@ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { rwork->wq = wq; - call_rcu(&rwork->rcu, rcu_work_rcufn); + call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c3c0b077ade3..3638b3424be5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -399,6 +399,7 @@ config FRAME_WARN default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 2048 if PARISC default 1536 if (!64BIT && XTENSA) + default 1280 if KASAN && !64BIT default 1024 if !64BIT default 2048 if 64BIT help @@ -1874,8 +1875,14 @@ config NETDEV_NOTIFIER_ERROR_INJECT If unsure, say N. config FUNCTION_ERROR_INJECTION - def_bool y + bool "Fault-injections of functions" depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES + help + Add fault injections into various functions that are annotated with + ALLOW_ERROR_INJECTION() in the kernel. BPF may also modify the return + value of theses functions. This is useful to test error paths of code. + + If unsure, say N config FAULT_INJECTION bool "Fault-injection framework" @@ -2107,6 +2114,7 @@ config KPROBES_SANITY_TEST depends on DEBUG_KERNEL depends on KPROBES depends on KUNIT + select STACKTRACE if ARCH_CORRECT_STACKTRACE_ON_KRETPROBE default KUNIT_ALL_TESTS help This option provides for testing basic kprobes functionality on diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index 47a693c45864..375575a5a0e3 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -125,7 +125,7 @@ config KCSAN_SKIP_WATCH default 4000 help The number of per-CPU memory operations to skip, before another - watchpoint is set up, i.e. one in KCSAN_WATCH_SKIP per-CPU + watchpoint is set up, i.e. one in KCSAN_SKIP_WATCH per-CPU memory operations are used to set up a watchpoint. A smaller value results in more aggressive race detection, whereas a larger value improves system performance at the cost of missing some races. @@ -135,8 +135,8 @@ config KCSAN_SKIP_WATCH_RANDOMIZE default y help If instruction skip count should be randomized, where the maximum is - KCSAN_WATCH_SKIP. If false, the chosen value is always - KCSAN_WATCH_SKIP. + KCSAN_SKIP_WATCH. If false, the chosen value is always + KCSAN_SKIP_WATCH. config KCSAN_INTERRUPT_WATCHER bool "Interruptible watchers" if !KCSAN_STRICT diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 96e092de5b72..adb2f9355ee6 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -41,9 +41,6 @@ EXPORT_SYMBOL_GPL(setup_fault_attr); static void fail_dump(struct fault_attr *attr) { - if (attr->no_warn) - return; - if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) { printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n" "name %pd, interval %lu, probability %lu, " @@ -103,7 +100,7 @@ static inline bool fail_stacktrace(struct fault_attr *attr) * http://www.nongnu.org/failmalloc/ */ -bool should_fail(struct fault_attr *attr, ssize_t size) +bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) { if (in_task()) { unsigned int fail_nth = READ_ONCE(current->fail_nth); @@ -146,13 +143,19 @@ bool should_fail(struct fault_attr *attr, ssize_t size) return false; fail: - fail_dump(attr); + if (!(flags & FAULT_NOWARN)) + fail_dump(attr); if (atomic_read(&attr->times) != -1) atomic_dec_not_zero(&attr->times); return true; } + +bool should_fail(struct fault_attr *attr, ssize_t size) +{ + return should_fail_ex(attr, size, 0); +} EXPORT_SYMBOL_GPL(should_fail); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index e5c5315da274..668f6aa6a75d 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -230,7 +230,8 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ - call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); + call_rcu_hurry(&ref->data->rcu, + percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile index c415a685d61b..e814061d6aa0 100644 --- a/lib/vdso/Makefile +++ b/lib/vdso/Makefile @@ -17,6 +17,6 @@ $(error ARCH_REL_TYPE_ABS is not set) endif quiet_cmd_vdso_check = VDSOCHK $@ - cmd_vdso_check = if $(OBJDUMP) -R $@ | egrep -h "$(ARCH_REL_TYPE_ABS)"; \ + cmd_vdso_check = if $(OBJDUMP) -R $@ | grep -E -h "$(ARCH_REL_TYPE_ABS)"; \ then (echo >&2 "$@: dynamic relocations are not supported"; \ rm -f $@; /bin/false); fi diff --git a/mm/compaction.c b/mm/compaction.c index c51f7f545afe..1f6da31dd9a5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -985,28 +985,28 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } /* + * Be careful not to clear PageLRU until after we're + * sure the page is not being freed elsewhere -- the + * page release code relies on it. + */ + if (unlikely(!get_page_unless_zero(page))) + goto isolate_fail; + + /* * Migration will fail if an anonymous page is pinned in memory, * so avoid taking lru_lock and isolating it unnecessarily in an * admittedly racy check. */ mapping = page_mapping(page); - if (!mapping && page_count(page) > page_mapcount(page)) - goto isolate_fail; + if (!mapping && (page_count(page) - 1) > total_mapcount(page)) + goto isolate_fail_put; /* * Only allow to migrate anonymous pages in GFP_NOFS context * because those do not depend on fs locks. */ if (!(cc->gfp_mask & __GFP_FS) && mapping) - goto isolate_fail; - - /* - * Be careful not to clear PageLRU until after we're - * sure the page is not being freed elsewhere -- the - * page release code relies on it. - */ - if (unlikely(!get_page_unless_zero(page))) - goto isolate_fail; + goto isolate_fail_put; /* Only take pages on LRU: a check now makes later tests safe */ if (!PageLRU(page)) diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 9f1219a67e3f..07e5f1bdf025 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -2283,12 +2283,54 @@ static struct damos *damon_sysfs_mk_scheme( &wmarks); } +static void damon_sysfs_update_scheme(struct damos *scheme, + struct damon_sysfs_scheme *sysfs_scheme) +{ + struct damon_sysfs_access_pattern *access_pattern = + sysfs_scheme->access_pattern; + struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas; + struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights; + struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks; + + scheme->pattern.min_sz_region = access_pattern->sz->min; + scheme->pattern.max_sz_region = access_pattern->sz->max; + scheme->pattern.min_nr_accesses = access_pattern->nr_accesses->min; + scheme->pattern.max_nr_accesses = access_pattern->nr_accesses->max; + scheme->pattern.min_age_region = access_pattern->age->min; + scheme->pattern.max_age_region = access_pattern->age->max; + + scheme->action = sysfs_scheme->action; + + scheme->quota.ms = sysfs_quotas->ms; + scheme->quota.sz = sysfs_quotas->sz; + scheme->quota.reset_interval = sysfs_quotas->reset_interval_ms; + scheme->quota.weight_sz = sysfs_weights->sz; + scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses; + scheme->quota.weight_age = sysfs_weights->age; + + scheme->wmarks.metric = sysfs_wmarks->metric; + scheme->wmarks.interval = sysfs_wmarks->interval_us; + scheme->wmarks.high = sysfs_wmarks->high; + scheme->wmarks.mid = sysfs_wmarks->mid; + scheme->wmarks.low = sysfs_wmarks->low; +} + static int damon_sysfs_set_schemes(struct damon_ctx *ctx, struct damon_sysfs_schemes *sysfs_schemes) { - int i; + struct damos *scheme, *next; + int i = 0; - for (i = 0; i < sysfs_schemes->nr; i++) { + damon_for_each_scheme_safe(scheme, next, ctx) { + if (i < sysfs_schemes->nr) + damon_sysfs_update_scheme(scheme, + sysfs_schemes->schemes_arr[i]); + else + damon_destroy_scheme(scheme); + i++; + } + + for (; i < sysfs_schemes->nr; i++) { struct damos *scheme, *next; scheme = damon_sysfs_mk_scheme(sysfs_schemes->schemes_arr[i]); @@ -2339,6 +2381,10 @@ static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond) damon_for_each_scheme(scheme, ctx) { struct damon_sysfs_stats *sysfs_stats; + /* user could have removed the scheme sysfs dir */ + if (schemes_idx >= sysfs_schemes->nr) + break; + sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats; sysfs_stats->nr_tried = scheme->stat.nr_tried; sysfs_stats->sz_tried = scheme->stat.sz_tried; diff --git a/mm/failslab.c b/mm/failslab.c index 58df9789f1d2..ffc420c0e767 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -16,6 +16,8 @@ static struct { bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) { + int flags = 0; + /* No fault-injection for bootstrap cache */ if (unlikely(s == kmem_cache)) return false; @@ -30,10 +32,16 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) return false; + /* + * In some cases, it expects to specify __GFP_NOWARN + * to avoid printing any information(not just a warning), + * thus avoiding deadlocks. See commit 6b9dbedbe349 for + * details. + */ if (gfpflags & __GFP_NOWARN) - failslab.attr.no_warn = true; + flags |= FAULT_NOWARN; - return should_fail(&failslab.attr, s->object_size); + return should_fail_ex(&failslab.attr, s->object_size, flags); } static int __init setup_failslab(char *str) @@ -2852,7 +2852,7 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; - if (unlikely(pud_huge(pud))) { + if (unlikely(pud_huge(pud) || pud_devmap(pud))) { if (!gup_huge_pud(pud, pudp, addr, next, flags, pages, nr)) return 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e48f8ef45b17..e36ca75311a5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1800,6 +1800,7 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); + __ClearPageReserved(page); __SetPageHead(page); for (i = 0; i < nr_pages; i++) { p = nth_page(page, i); @@ -1816,7 +1817,8 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, * on the head page when they need know if put_page() is needed * after get_user_pages(). */ - __ClearPageReserved(p); + if (i != 0) /* head page cleared above */ + __ClearPageReserved(p); /* * Subtle and very unlikely * @@ -5204,17 +5206,22 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); - /* - * Unlock and free the vma lock before releasing i_mmap_rwsem. When - * the vma_lock is freed, this makes the vma ineligible for pmd - * sharing. And, i_mmap_rwsem is required to set up pmd sharing. - * This is important as page tables for this unmapped range will - * be asynchrously deleted. If the page tables are shared, there - * will be issues when accessed by someone else. - */ - __hugetlb_vma_unlock_write_free(vma); - - i_mmap_unlock_write(vma->vm_file->f_mapping); + if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ + /* + * Unlock and free the vma lock before releasing i_mmap_rwsem. + * When the vma_lock is freed, this makes the vma ineligible + * for pmd sharing. And, i_mmap_rwsem is required to set up + * pmd sharing. This is important as page tables for this + * unmapped range will be asynchrously deleted. If the page + * tables are shared, there will be issues when accessed by + * someone else. + */ + __hugetlb_vma_unlock_write_free(vma); + i_mmap_unlock_write(vma->vm_file->f_mapping); + } else { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 7e496856c2eb..46ecea18c4ca 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -75,18 +75,23 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") || str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") || + str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") || !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) { /* - * In case of tail calls from any of the below - * to any of the above. + * In case of tail calls from any of the below to any of + * the above, optimized by the compiler such that the + * stack trace would omit the initial entry point below. */ fallback = skipnr + 1; } - /* Also the *_bulk() variants by only checking prefixes. */ + /* + * The below list should only include the initial entry points + * into the slab allocators. Includes the *_bulk() variants by + * checking prefixes. + */ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") || str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") || - str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") || str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") || str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc")) goto found; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 4734315f7940..3703a56571c1 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -97,8 +97,8 @@ struct collapse_control { /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; - /* Last target selected in hpage_collapse_find_target_node() */ - int last_target_node; + /* nodemask for allocation fallback */ + nodemask_t alloc_nmask; }; /** @@ -734,7 +734,6 @@ static void khugepaged_alloc_sleep(void) struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, - .last_target_node = NUMA_NO_NODE, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) @@ -783,16 +782,11 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) target_node = nid; } - /* do some balance if several nodes have the same hit record */ - if (target_node <= cc->last_target_node) - for (nid = cc->last_target_node + 1; nid < MAX_NUMNODES; - nid++) - if (max_value == cc->node_load[nid]) { - target_node = nid; - break; - } + for_each_online_node(nid) { + if (max_value == cc->node_load[nid]) + node_set(nid, cc->alloc_nmask); + } - cc->last_target_node = target_node; return target_node; } #else @@ -802,9 +796,10 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node) +static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node, + nodemask_t *nmask) { - *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); + *hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return false; @@ -955,12 +950,11 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, struct collapse_control *cc) { - /* Only allocate from the target node */ gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : - GFP_TRANSHUGE) | __GFP_THISNODE; + GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); - if (!hpage_collapse_alloc_page(hpage, gfp, node)) + if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) return SCAN_ALLOC_HUGE_PAGE_FAIL; if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp))) return SCAN_CGROUP_CHARGE_FAIL; @@ -1057,6 +1051,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); + tlb_remove_table_sync_one(); spin_lock(pte_ptl); result = __collapse_huge_page_isolate(vma, address, pte, cc, @@ -1144,6 +1139,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { @@ -1384,16 +1380,43 @@ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, return SCAN_SUCCEED; } +/* + * A note about locking: + * Trying to take the page table spinlocks would be useless here because those + * are only used to synchronize: + * + * - modifying terminal entries (ones that point to a data page, not to another + * page table) + * - installing *new* non-terminal entries + * + * Instead, we need roughly the same kind of protection as free_pgtables() or + * mm_take_all_locks() (but only for a single VMA): + * The mmap lock together with this VMA's rmap locks covers all paths towards + * the page table entries we're messing with here, except for hardware page + * table walks and lockless_pages_from_mm(). + */ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - spinlock_t *ptl; pmd_t pmd; + struct mmu_notifier_range range; mmap_assert_write_locked(mm); - ptl = pmd_lock(vma->vm_mm, pmdp); + if (vma->vm_file) + lockdep_assert_held_write(&vma->vm_file->f_mapping->i_mmap_rwsem); + /* + * All anon_vmas attached to the VMA have the same root and are + * therefore locked by the same lock. + */ + if (vma->anon_vma) + lockdep_assert_held_write(&vma->anon_vma->root->rwsem); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr, + addr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); pmd = pmdp_collapse_flush(vma, addr, pmdp); - spin_unlock(ptl); + tlb_remove_table_sync_one(); + mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pmd); pte_free(mm, pmd_pgtable(pmd)); @@ -1444,6 +1467,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) return SCAN_VMA_CHECK; + /* + * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings + * that got written to. Without this, we'd have to also lock the + * anon_vma if one exists. + */ + if (vma->anon_vma) + return SCAN_VMA_CHECK; + /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; @@ -1477,6 +1508,20 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto drop_hpage; } + /* + * We need to lock the mapping so that from here on, only GUP-fast and + * hardware page walks can access the parts of the page tables that + * we're operating on. + * See collapse_and_free_pmd(). + */ + i_mmap_lock_write(vma->vm_file->f_mapping); + + /* + * This spinlock should be unnecessary: Nobody else should be accessing + * the page tables under spinlock protection here, only + * lockless_pages_from_mm() and the hardware page walker can access page + * tables while all the high-level locks are held in write mode. + */ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); result = SCAN_FAIL; @@ -1531,6 +1576,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, /* step 4: remove pte entries */ collapse_and_free_pmd(mm, vma, haddr, pmd); + i_mmap_unlock_write(vma->vm_file->f_mapping); + maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd @@ -1544,6 +1591,7 @@ drop_hpage: abort: pte_unmap_unlock(start_pte, ptl); + i_mmap_unlock_write(vma->vm_file->f_mapping); goto drop_hpage; } @@ -1600,7 +1648,8 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * An alternative would be drop the check, but check that page * table is clear before calling pmdp_collapse_flush() under * ptl. It has higher chance to recover THP for the VMA, but - * has higher cost too. + * has higher cost too. It would also probably require locking + * the anon_vma. */ if (vma->anon_vma) { result = SCAN_PAGE_ANON; @@ -2077,6 +2126,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, page)) @@ -2157,8 +2207,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, } } - trace_mm_khugepaged_scan_file(mm, page, file->f_path.dentry->d_iname, - present, swap, result); + trace_mm_khugepaged_scan_file(mm, page, file, present, swap, result); return result; } #else @@ -2576,7 +2625,6 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, if (!cc) return -ENOMEM; cc->is_khugepaged = false; - cc->last_target_node = NUMA_NO_NODE; mmgrab(mm); lru_add_drain_all(); @@ -2602,6 +2650,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); diff --git a/mm/madvise.c b/mm/madvise.c index c7105ec6d08c..b913ba6efc10 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -772,8 +772,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The - * zap_page_range call sets things up for shrink_active_list to actually free - * these pages later if no one else has touched them in the meantime, + * zap_page_range_single call sets things up for shrink_active_list to actually + * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * @@ -790,7 +790,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - zap_page_range(vma, start, end - start); + zap_page_range_single(vma, start, end - start, NULL); return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2d8549ae1b30..266a1ab05434 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3026,7 +3026,7 @@ struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) { struct obj_cgroup *objcg; - if (!memcg_kmem_enabled() || memcg_kmem_bypass()) + if (!memcg_kmem_enabled()) return NULL; if (PageMemcgKmem(page)) { @@ -4832,6 +4832,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4886,6 +4887,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, goto out_put_cfile; /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows * about these events. The following is crude but the whole thing @@ -4893,7 +4904,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4917,7 +4928,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) diff --git a/mm/memory.c b/mm/memory.c index f88c351aecd4..8c8420934d60 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1341,15 +1341,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) return ret; } -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct folio *single_folio; /* Locked folio to be unmapped */ - bool even_cows; /* Zap COWed private pages too? */ - zap_flags_t zap_flags; /* Extra flags for zapping */ -}; - /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { @@ -1720,7 +1711,7 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, { struct mmu_notifier_range range; struct zap_details details = { - .zap_flags = ZAP_FLAG_DROP_MARKER, + .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, /* Careful - we need to zap private pages too! */ .even_cows = true, }; @@ -1774,19 +1765,27 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * * The range must fit into one VMA. */ -static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { + const unsigned long end = address + size; struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, address + size); + address, end); + if (is_vm_hugetlb_page(vma)) + adjust_range_if_pmd_sharing_possible(vma, &range.start, + &range.end); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); - unmap_single_vma(&tlb, vma, address, range.end, details); + /* + * unmap 'address-end' not 'range.start-range.end' as range + * could have been expanded for hugetlb pmd sharing. + */ + unmap_single_vma(&tlb, vma, address, end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } @@ -3763,7 +3762,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); - vmf->page->pgmap->ops->migrate_to_ram(vmf); + ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 6fa682eef7a0..721b2365dbca 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -357,7 +357,8 @@ static bool migrate_vma_check_page(struct page *page, struct page *fault_page) } /* - * Unmaps pages for migration. Returns number of unmapped pages. + * Unmaps pages for migration. Returns number of source pfns marked as + * migrating. */ static unsigned long migrate_device_unmap(unsigned long *src_pfns, unsigned long npages, @@ -373,8 +374,11 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns, struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; - if (!page) + if (!page) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) + unmapped++; continue; + } /* ZONE_DEVICE pages are not on LRU */ if (!is_zone_device_page(page)) { diff --git a/mm/mmap.c b/mm/mmap.c index c3c5c1d6103d..54abd46e6007 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -226,8 +226,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Search one past newbrk */ mas_set(&mas, newbrk); brkvma = mas_find(&mas, oldbrk); - BUG_ON(brkvma == NULL); - if (brkvma->vm_start >= oldbrk) + if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. @@ -456,7 +455,7 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) * vma_mas_szero() - Set a given range to zero. Used when modifying a * vm_area_struct start or end. * - * @mm: The struct_mm + * @mas: The maple tree ma_state * @start: The start address to zero * @end: The end address to zero. */ @@ -1779,9 +1778,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, */ pgoff = 0; get_area = shmem_get_unmapped_area; - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - /* Ensures that larger anonymous mappings are THP aligned. */ - get_area = thp_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); @@ -2949,9 +2945,9 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ - if (vma && - (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) && - ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) { + if (vma && vma->vm_end == addr && !vma_policy(vma) && + can_vma_merge_after(vma, flags, NULL, NULL, + addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { mas_set_range(mas, vma->vm_start, addr + len - 1); if (mas_preallocate(mas, vma, GFP_KERNEL)) return -ENOMEM; @@ -3038,11 +3034,6 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) goto munmap_failed; vma = mas_prev(&mas, 0); - if (!vma || vma->vm_end != addr || vma_policy(vma) || - !can_vma_merge_after(vma, flags, NULL, NULL, - addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) - vma = NULL; - ret = do_brk_flags(&mas, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index add4244e5790..3a2c3f8cad2f 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -153,7 +153,7 @@ static void tlb_remove_table_smp_sync(void *arg) /* Simply deliver the interrupt */ } -static void tlb_remove_table_sync_one(void) +void tlb_remove_table_sync_one(void) { /* * This isn't an RCU grace period and hence the page-tables cannot be @@ -177,8 +177,6 @@ static void tlb_remove_table_free(struct mmu_table_batch *batch) #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ -static void tlb_remove_table_sync_one(void) { } - static void tlb_remove_table_free(struct mmu_table_batch *batch) { __tlb_remove_table_free(batch); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 218b28ee49ed..6e60657875d3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3887,6 +3887,8 @@ __setup("fail_page_alloc=", setup_fail_page_alloc); static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { + int flags = 0; + if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) @@ -3897,10 +3899,11 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; + /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) - fail_page_alloc.attr.no_warn = true; + flags |= FAULT_NOWARN; - return should_fail(&fail_page_alloc.attr, 1 << order); + return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/mm/page_ext.c b/mm/page_ext.c index affe80243b6d..ddf1968560f0 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -166,7 +166,7 @@ struct page_ext *page_ext_get(struct page *page) /** * page_ext_put() - Working with page extended information is done. - * @page_ext - Page extended information received from page_ext_get(). + * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. diff --git a/mm/shmem.c b/mm/shmem.c index c1d8b8a1aa3b..82911fefc2d5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -948,6 +948,15 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index++; } + /* + * When undoing a failed fallocate, we want none of the partial folio + * zeroing and splitting below, but shall want to truncate the whole + * folio when !uptodate indicates that it was added by this fallocate, + * even when [lstart, lend] covers only a part of the folio. + */ + if (unfalloc) + goto whole_folios; + same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT); if (folio) { @@ -973,6 +982,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, folio_put(folio); } +whole_folios: + index = start; while (index < end) { cond_resched(); diff --git a/mm/swapfile.c b/mm/swapfile.c index 5fc1237a9f21..72e481aacd5d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -973,23 +973,23 @@ done: scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { - if (swap_offset_available_and_locked(si, offset)) - goto checks; if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } + if (swap_offset_available_and_locked(si, offset)) + goto checks; } offset = si->lowest_bit; while (offset < scan_base) { - if (swap_offset_available_and_locked(si, offset)) - goto checks; if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } + if (swap_offset_available_and_locked(si, offset)) + goto checks; offset++; } spin_lock(&si->lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index 04d8b88e5216..8fcc5fa768c0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2514,8 +2514,20 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ - if (stat.nr_unqueued_dirty == nr_taken) + if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); + /* + * For cgroupv1 dirty throttling is achieved by waking up + * the kernel flusher here and later waiting on folios + * which are in writeback to finish (see shrink_folio_list()). + * + * Flusher may not be able to issue writeback quickly + * enough for cgroupv1 writeback throttling to work + * on a large system. + */ + if (!writeback_throttling_sane(sc)) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); + } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; @@ -3975,7 +3987,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area goto next; if (!pmd_trans_huge(pmd[i])) { - if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && + if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; @@ -4073,14 +4085,14 @@ restart: #endif walk->mm_stats[MM_NONLEAF_TOTAL]++; -#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG - if (get_cap(LRU_GEN_NONLEAF_YOUNG)) { + if (arch_has_hw_nonleaf_pmd_young() && + get_cap(LRU_GEN_NONLEAF_YOUNG)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); } -#endif + if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i)) continue; @@ -4971,10 +4983,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap int scanned; int reclaimed; LIST_HEAD(list); + LIST_HEAD(clean); struct folio *folio; + struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; + bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -4991,20 +5006,37 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap if (list_empty(&list)) return scanned; - +retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); + sc->nr_reclaimed += reclaimed; - list_for_each_entry(folio, &list, lru) { - /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ - if (folio_test_workingset(folio)) - folio_set_referenced(folio); + list_for_each_entry_safe_reverse(folio, next, &list, lru) { + if (!folio_evictable(folio)) { + list_del(&folio->lru); + folio_putback_lru(folio); + continue; + } - /* don't add rejected pages to the oldest generation */ if (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio))) - folio_clear_active(folio); - else - folio_set_active(folio); + (folio_test_dirty(folio) || folio_test_writeback(folio))) { + /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ + if (folio_test_workingset(folio)) + folio_set_referenced(folio); + continue; + } + + if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || + folio_mapped(folio) || folio_test_locked(folio) || + folio_test_dirty(folio) || folio_test_writeback(folio)) { + /* don't add rejected folios to the oldest generation */ + set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, + BIT(PG_active)); + continue; + } + + /* retry folios that may have missed folio_rotate_reclaimable() */ + list_move(&folio->lru, &clean); + sc->nr_scanned -= folio_nr_pages(folio); } spin_lock_irq(&lruvec->lru_lock); @@ -5026,7 +5058,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap mem_cgroup_uncharge_list(&list); free_unref_page_list(&list); - sc->nr_reclaimed += reclaimed; + INIT_LIST_HEAD(&list); + list_splice_init(&clean, &list); + + if (!list_empty(&list)) { + skip_retry = true; + goto retry; + } if (need_swapping && type == LRU_GEN_ANON) *need_swapping = true; @@ -5354,7 +5392,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK)) caps |= BIT(LRU_GEN_MM_WALK); - if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG)) + if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps); @@ -5844,8 +5882,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + bool proportional_reclaim; struct blk_plug plug; - bool scan_adjusted; if (lru_gen_enabled()) { lru_gen_shrink_lruvec(lruvec, sc); @@ -5868,8 +5906,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ - scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() && - sc->priority == DEF_PRIORITY); + proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || @@ -5889,7 +5927,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); - if (nr_reclaimed < nr_to_reclaim || scan_adjusted) + if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* @@ -5940,8 +5978,6 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); - - scan_adjusted = true; } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 56a186768750..07db2f436d44 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -120,7 +120,7 @@ struct p9_conn { struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; - char tmp_buf[7]; + char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; @@ -202,9 +202,11 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } spin_unlock(&m->req_lock); @@ -291,7 +293,7 @@ static void p9_read_work(struct work_struct *work) if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; - m->rc.capacity = 7; /* start by reading header */ + m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); @@ -314,7 +316,7 @@ static void p9_read_work(struct work_struct *work) p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ - m->rc.size = 7; + m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, @@ -322,14 +324,6 @@ static void p9_read_work(struct work_struct *work) goto error; } - if (m->rc.size >= m->client->msize) { - p9_debug(P9_DEBUG_ERROR, - "requested packet size too big: %d\n", - m->rc.size); - err = -EIO; - goto error; - } - p9_debug(P9_DEBUG_TRANS, "mux %p pkt: size: %d bytes tag: %d\n", m, m->rc.size, m->rc.tag); @@ -342,6 +336,14 @@ static void p9_read_work(struct work_struct *work) goto error; } + if (m->rc.size > m->rreq->rc.capacity) { + p9_debug(P9_DEBUG_ERROR, + "requested packet size too big: %d for tag %d with capacity %zd\n", + m->rc.size, m->rc.tag, m->rreq->rc.capacity); + err = -EIO; + goto error; + } + if (!m->rreq->rc.sdata) { p9_debug(P9_DEBUG_ERROR, "No recv fcall for tag %d (req %p), disconnecting!\n", @@ -860,8 +862,10 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); - if (!p) + if (!p) { + sock_release(csocket); return -ENOMEM; + } csocket->sk->sk_allocation = GFP_NOIO; file = sock_alloc_file(csocket, 0, NULL); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index b15c64128c3e..aaa5fd364691 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -208,6 +208,14 @@ static void p9_xen_response(struct work_struct *work) continue; } + if (h.size > req->rc.capacity) { + dev_warn(&priv->dev->dev, + "requested packet size too big: %d for tag %d with capacity %zd\n", + h.size, h.tag, req->rc.capacity); + req->status = REQ_STATUS_ERROR; + goto recv_error; + } + memcpy(&req->rc, &h, sizeof(h)); req->rc.offset = 0; @@ -217,6 +225,7 @@ static void p9_xen_response(struct work_struct *work) masked_prod, &masked_cons, XEN_9PFS_RING_SIZE(ring)); +recv_error: virt_mb(); cons += h.size; ring->intf->in_cons = cons; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 215af9b3b589..c57d643afb10 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -972,6 +972,7 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); hci_dev_unlock(hdev); + hci_dev_put(hdev); if (!hcon) return -ENOENT; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index dc65974f5adb..1c3c7ff5c3c6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -737,7 +737,7 @@ static int __init bt_init(void) err = bt_sysfs_init(); if (err < 0) - return err; + goto cleanup_led; err = sock_register(&bt_sock_family_ops); if (err) @@ -773,6 +773,8 @@ unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); +cleanup_led: + bt_leds_cleanup(); return err; } diff --git a/net/bluetooth/hci_codec.c b/net/bluetooth/hci_codec.c index 38201532f58e..3cc135bb1d30 100644 --- a/net/bluetooth/hci_codec.c +++ b/net/bluetooth/hci_codec.c @@ -72,9 +72,8 @@ static void hci_read_codec_capabilities(struct hci_dev *hdev, __u8 transport, continue; } - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODEC_CAPS, - sizeof(*cmd), cmd, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODEC_CAPS, + sizeof(*cmd), cmd, 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read codec capabilities (%ld)", PTR_ERR(skb)); @@ -127,8 +126,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) struct hci_op_read_local_codec_caps caps; __u8 i; - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, + 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", @@ -158,7 +157,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) for (i = 0; i < std_codecs->num; i++) { caps.id = std_codecs->codec[i]; caps.direction = 0x00; - hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK, &caps); + hci_read_codec_capabilities(hdev, + LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } skb_pull(skb, flex_array_size(std_codecs, codec, std_codecs->num) @@ -178,7 +178,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) caps.cid = vnd_codecs->codec[i].cid; caps.vid = vnd_codecs->codec[i].vid; caps.direction = 0x00; - hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK, &caps); + hci_read_codec_capabilities(hdev, + LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } error: @@ -194,8 +195,8 @@ void hci_read_supported_codecs_v2(struct hci_dev *hdev) struct hci_op_read_local_codec_caps caps; __u8 i; - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODECS_V2, 0, NULL, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS_V2, 0, NULL, + 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 0540555b3704..d97fac4f7130 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2764,7 +2764,8 @@ int hci_register_suspend_notifier(struct hci_dev *hdev) { int ret = 0; - if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { + if (!hdev->suspend_notifier.notifier_call && + !test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } @@ -2776,8 +2777,11 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) { int ret = 0; - if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) + if (hdev->suspend_notifier.notifier_call) { ret = unregister_pm_notifier(&hdev->suspend_notifier); + if (!ret) + hdev->suspend_notifier.notifier_call = NULL; + } return ret; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 5a0296a4352e..f7e006a36382 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -269,7 +269,7 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, const void *param) { - bt_dev_err(req->hdev, "HCI_REQ-0x%4.4x", opcode); + bt_dev_dbg(req->hdev, "HCI_REQ-0x%4.4x", opcode); hci_req_add_ev(req, opcode, plen, param, 0); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 76c3107c9f91..1fc693122a47 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -12,6 +12,7 @@ #include <net/bluetooth/mgmt.h> #include "hci_request.h" +#include "hci_codec.h" #include "hci_debugfs.h" #include "smp.h" #include "eir.h" @@ -3780,7 +3781,8 @@ static int hci_read_page_scan_activity_sync(struct hci_dev *hdev) static int hci_read_def_err_data_reporting_sync(struct hci_dev *hdev) { if (!(hdev->commands[18] & 0x04) || - !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING)) + !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || + test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_READ_DEF_ERR_DATA_REPORTING, @@ -4238,11 +4240,12 @@ static int hci_set_event_mask_page_2_sync(struct hci_dev *hdev) /* Read local codec list if the HCI command is supported */ static int hci_read_local_codecs_sync(struct hci_dev *hdev) { - if (!(hdev->commands[29] & 0x20)) - return 0; + if (hdev->commands[45] & 0x04) + hci_read_supported_codecs_v2(hdev); + else if (hdev->commands[29] & 0x20) + hci_read_supported_codecs(hdev); - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, - HCI_CMD_TIMEOUT); + return 0; } /* Read local pairing options if the HCI command is supported */ @@ -4298,7 +4301,8 @@ static int hci_set_err_data_report_sync(struct hci_dev *hdev) bool enabled = hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED); if (!(hdev->commands[18] & 0x08) || - !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING)) + !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || + test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) return 0; if (enabled == hdev->err_data_reporting) @@ -4457,6 +4461,9 @@ static const struct { HCI_QUIRK_BROKEN(STORED_LINK_KEY, "HCI Delete Stored Link Key command is advertised, " "but not supported."), + HCI_QUIRK_BROKEN(ERR_DATA_REPORTING, + "HCI Read Default Erroneous Data Reporting command is " + "advertised, but not supported."), HCI_QUIRK_BROKEN(READ_TRANSMIT_POWER, "HCI Read Transmit Power Level command is advertised, " "but not supported."), diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index f825857db6d0..26db929b97c4 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -879,6 +879,7 @@ static int iso_listen_bis(struct sock *sk) iso_pi(sk)->bc_sid); hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 9c24947aa41e..9fdede5fe71c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4453,7 +4453,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); - chan->num_conf_rsp++; + if (chan->num_conf_rsp < L2CAP_CONF_MAX_CONF_RSP) + chan->num_conf_rsp++; /* Reset config buffer. */ chan->conf_len = 0; diff --git a/net/can/af_can.c b/net/can/af_can.c index 27dcdcc0b808..c69168f11e44 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -677,7 +677,7 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_can_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_can_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -692,7 +692,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_canfd_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_canfd_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -707,7 +707,7 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, static int canxl_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_canxl_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_canxl_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN XL skbuff: dev type %d, len %d\n", dev->type, skb->len); diff --git a/net/core/dst.c b/net/core/dst.c index bc9c9be4e080..a4e738d321ba 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -174,7 +174,7 @@ void dst_release(struct dst_entry *dst) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); if (!newrefcnt) - call_rcu(&dst->rcu_head, dst_destroy_rcu); + call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 25cd35f5922e..007730412947 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -296,7 +296,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6fac2f0ef074..711cd3b4347a 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -48,9 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; + case LWTUNNEL_ENCAP_XFRM: + /* module autoload not supported for encap type */ + return NULL; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: - case LWTUNNEL_ENCAP_XFRM: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a77a85e357e0..952a54763358 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -307,7 +307,31 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_parms_qlen_dec(struct net_device *dev, int family) +{ + struct neigh_parms *p; + + rcu_read_lock(); + p = neigh_get_dev_parms_rcu(dev, family); + if (p) + p->qlen--; + rcu_read_unlock(); +} + +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net, + int family) { struct sk_buff_head tmp; unsigned long flags; @@ -321,13 +345,7 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) struct net_device *dev = skb->dev; if (net == NULL || net_eq(dev_net(dev), net)) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, family); __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } @@ -409,7 +427,8 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, + tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; @@ -1621,13 +1640,8 @@ static void neigh_proxy_process(struct timer_list *t) if (tdif <= 0) { struct net_device *dev = skb->dev; - struct in_device *in_dev; - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, tbl->family); __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) { @@ -1821,7 +1835,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue, NULL); + pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); @@ -3539,18 +3553,6 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } -static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, - int family) -{ - switch (family) { - case AF_INET: - return __in_dev_arp_parms_get_rcu(dev); - case AF_INET6: - return __in6_dev_nd_parms_get_rcu(dev); - } - return NULL; -} - static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 713b7b8dad7e..b780827f5e0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = fl4->daddr; if (inet->inet_saddr == 0) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = - inet_bhashfn_portaddr(&dccp_hashinfo, sk, - sock_net(sk), - inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; @@ -157,6 +143,7 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e57b43006074..602f3432d80b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, - sk, sock_net(sk), - inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } - saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -985,6 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index c548ca3e9b0e..85e35c5e8890 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -279,8 +279,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 846588c0070a..53a206d11685 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -49,7 +49,8 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, return NULL; } - pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN); + if (pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN)) + return NULL; dsa_default_offload_fwd_mark(skb); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 38fa19c1e2d5..429250298ac4 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -21,7 +21,8 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, if (!skb->dev) return NULL; - pskb_trim_rcsum(skb, skb->len - len); + if (pskb_trim_rcsum(skb, skb->len - len)) + return NULL; dsa_default_offload_fwd_mark(skb); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 83e4136516b0..1a85125bda6d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -665,7 +665,8 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, * padding and trailer we need to account for the fact that * skb->data points to skb_mac_header(skb) + ETH_HLEN. */ - pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + if (pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN)) + return NULL; /* Trap-to-host frame, no timestamp trailer */ } else { *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index a50429a62f74..56bb27d67a2e 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -351,17 +351,18 @@ static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev, struct hsr_node *node_src) { bool was_multicast_frame; - int res; + int res, recv_len; was_multicast_frame = (skb->pkt_type == PACKET_MULTICAST); hsr_addr_subst_source(node_src, skb); skb_pull(skb, ETH_HLEN); + recv_len = skb->len; res = netif_rx(skb); if (res == NET_RX_DROP) { dev->stats.rx_dropped++; } else { dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += recv_len; if (was_multicast_frame) dev->stats.multicast++; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4728087c42a5..0da679411330 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e8b9a9202fec..b0acf6e19aed 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -234,13 +234,20 @@ static void inet_free_ifa(struct in_ifaddr *ifa) call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); } +static void in_dev_free_rcu(struct rcu_head *head) +{ + struct in_device *idev = container_of(head, struct in_device, rcu_head); + + kfree(rcu_dereference_protected(idev->mc_hash, 1)); + kfree(idev); +} + void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); - kfree(rcu_dereference_protected(idev->mc_hash, 1)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif @@ -248,7 +255,7 @@ void in_dev_finish_destroy(struct in_device *idev) if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else - kfree(idev); + call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); @@ -298,12 +305,6 @@ out_kfree: goto out; } -static void in_dev_rcu_put(struct rcu_head *head) -{ - struct in_device *idev = container_of(head, struct in_device, rcu_head); - in_dev_put(idev); -} - static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; @@ -328,7 +329,7 @@ static void inetdev_destroy(struct in_device *in_dev) neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); - call_rcu(&in_dev->rcu_head, in_dev_rcu_put); + in_dev_put(in_dev); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 170152772d33..3969fa805679 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f361d3d56be2..b5736ef16ed2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -841,6 +841,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, return -EINVAL; } + if (!cfg->fc_table) + cfg->fc_table = RT_TABLE_MAIN; + return 0; errout: return err; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f721c308248b..ce9ff3c62e84 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -423,6 +423,7 @@ static struct fib_info *fib_find_info(struct fib_info *nfi) nfi->fib_prefsrc == fi->fib_prefsrc && nfi->fib_priority == fi->fib_priority && nfi->fib_type == fi->fib_type && + nfi->fib_tb_id == fi->fib_tb_id && memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(u32) * RTAX_MAX) == 0 && !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) && @@ -888,9 +889,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, return 1; } - /* cannot match on nexthop object attributes */ - if (fi->nh) - return 1; + if (fi->nh) { + if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) + return 1; + return 0; + } if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -126,7 +126,7 @@ struct key_vector { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ - struct key_vector __rcu *tnode[0]; + DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 033bf3c2538f..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); - spin_lock_bh(&head2->lock); + spin_lock(&head2->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock(&head2->lock); + + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f866d6282b2b..cae9f1a4e059 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1492,24 +1492,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if (t->erspan_ver <= 2) { - if (t->erspan_ver != 0 && !t->collect_md) - o_flags |= TUNNEL_KEY; - - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - } - if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || @@ -1550,6 +1532,34 @@ nla_put_failure: return -EMSGSIZE; } +static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + + if (t->erspan_ver <= 2) { + if (t->erspan_ver != 0 && !t->collect_md) + t->parms.o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else if (t->erspan_ver == 2) { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } + + return ipgre_fill_info(skb, dev); + +nla_put_failure: + return -EMSGSIZE; +} + static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); @@ -1628,7 +1638,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, - .fill_info = ipgre_fill_info, + .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1b512390b3cf..e880ce77322a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, iph->tos, dev); if (unlikely(err)) goto drop_error; + } else { + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) + IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index bde333b24837..04b4ec07bb06 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -49,6 +49,11 @@ #include <net/transp_v6.h> #endif +#define ping_portaddr_for_each_entry(__sk, node, list) \ + hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) +#define ping_portaddr_for_each_entry_rcu(__sk, node, list) \ + hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) + struct ping_table { struct hlist_nulls_head hash[PING_HTABLE_SIZE]; spinlock_t lock; @@ -192,7 +197,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) return NULL; } - ping_portaddr_for_each_entry(sk, hnode, hslot) { + ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) { isk = inet_sk(sk); pr_debug("iterate\n"); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 54836a6b81d6..4f2205756cfe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87d440f47a70..da46357f501b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -343,6 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 79d43548279c..242f4295940e 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -346,6 +346,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e19507614f64..60fd91bb5171 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -920,6 +920,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err < 0) goto fail; + /* We prevent @rt from being freed. */ + rcu_read_lock(); + for (;;) { /* Prepare header of the next frame, * before previous one went down. */ @@ -943,6 +946,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); + rcu_read_unlock(); return 0; } @@ -950,6 +954,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); + rcu_read_unlock(); return err; slow_path_clean: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..f0548dbcabd2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -359,6 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 4a4b0e49ec92..ea435eba3053 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -287,9 +287,13 @@ int __init xfrm6_init(void) if (ret) goto out_state; - register_pernet_subsys(&xfrm6_net_ops); + ret = register_pernet_subsys(&xfrm6_net_ops); + if (ret) + goto out_protocol; out: return ret; +out_protocol: + xfrm6_protocol_fini(); out_state: xfrm6_state_fini(); out_policy: diff --git a/net/key/af_key.c b/net/key/af_key.c index c85df5b958d2..95edcbedf6ef 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { @@ -3382,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; - hdr->sadb_msg_seq = x->km.seq = get_acqseq(); + hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 754fdda8a5f5..9a1415fe3fa7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1474,11 +1474,12 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; - write_lock(&sk->sk_callback_lock); - + write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) - goto err_sock; + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); tunnel->l2tp_net = net; pn = l2tp_pernet(net); @@ -1507,8 +1508,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - rcu_assign_sk_user_data(sk, tunnel); } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1522,16 +1521,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock); - write_unlock(&sk->sk_callback_lock); return 0; err_sock: + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_sk_user_data(sk, NULL); +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); - - write_unlock(&sk->sk_callback_lock); err: return ret; } diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 2e66598fac79..e8ebd343e2bf 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -452,6 +452,9 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, (status->encoding == RX_ENC_HE && streams > 8))) return 0; + if (idx >= MCS_GROUP_RATES) + return 0; + duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; *overhead = 36 + (streams << 2); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 500ed1b81250..7e2065e72915 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -662,6 +662,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; + INIT_LIST_HEAD(&sdata->wpan_dev.list); /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b6dc6e260334..1dbc62537259 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2354,12 +2354,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out; } - /* if we are invoked by the msk cleanup code, the subflow is - * already orphaned - */ - if (ssk->sk_socket) - sock_orphan(ssk); - + sock_orphan(ssk); subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2940,7 +2935,11 @@ cleanup: if (ssk == msk->first) subflow->fail_tout = 0; - sock_orphan(ssk); + /* detach from the parent socket, but allow data_ready to + * push incoming data into the mptcp stack, to properly ack it + */ + ssk->sk_socket = NULL; + ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 02a54d59697b..2159b5f9988f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1745,16 +1745,16 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk) for (msk = head; msk; msk = next) { struct sock *sk = (struct sock *)msk; - bool slow, do_cancel_work; + bool do_cancel_work; sock_hold(sk); - slow = lock_sock_fast_nested(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); next = msk->dl_next; msk->first = NULL; msk->dl_next = NULL; do_cancel_work = __mptcp_close(sk, 0); - unlock_sock_fast(sk, slow); + release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); sock_put(sk); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3adc291d9ce1..7499192af586 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -916,7 +916,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >= AHASH_MAX_TUNED) goto set_full; - else if (h->bucketsize < multi) + else if (h->bucketsize <= multi) h->bucketsize += AHASH_INIT_SIZE; #endif if (n->size >= AHASH_MAX(h)) { diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..75d556d71652 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -151,18 +151,16 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) return -ERANGE; - if (retried) { + if (retried) ip = ntohl(h->next.ip); - e.ip = htonl(ip); - } for (; ip <= ip_to;) { + e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ip += hosts; - e.ip = htonl(ip); - if (e.ip == 0) + if (ip == 0) return 0; ret = 0; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f97bda06d2a9..23b3fedd619a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -891,7 +891,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) zone = nf_ct_zone(ct); if (!nf_ct_ext_valid_pre(ct->ext)) { - NF_CT_STAT_INC(net, insert_failed); + NF_CT_STAT_INC_ATOMIC(net, insert_failed); return -ETIMEDOUT; } @@ -938,7 +938,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (!nf_ct_ext_valid_post(ct->ext)) { nf_ct_kill(ct); - NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC_ATOMIC(net, drop); return -ETIMEDOUT; } @@ -1275,7 +1275,7 @@ chaintoolong: */ if (!nf_ct_ext_valid_post(ct->ext)) { nf_ct_kill(ct); - NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC_ATOMIC(net, drop); return NF_DROP; } @@ -1781,7 +1781,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7562b215b932..1286ae7d4609 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -330,7 +330,12 @@ nla_put_failure: #ifdef CONFIG_NF_CONNTRACK_MARK static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + u32 mark = READ_ONCE(ct->mark); + + if (!mark) + return 0; + + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -826,8 +831,8 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + if (events & (1 << IPCT_MARK) && + ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1154,7 +1159,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); @@ -2002,9 +2007,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif @@ -2730,7 +2735,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + if (ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index b04645ced89b..0fdcdb2c9ae4 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -997,13 +997,13 @@ static void flow_offload_queue_work(struct flow_offload_work *offload) struct net *net = read_pnet(&offload->flowtable->net); if (offload->cmd == FLOW_CLS_REPLACE) { - NF_FLOW_TABLE_STAT_INC(net, count_wq_add); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_add); queue_work(nf_flow_offload_add_wq, &offload->work); } else if (offload->cmd == FLOW_CLS_DESTROY) { - NF_FLOW_TABLE_STAT_INC(net, count_wq_del); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_del); queue_work(nf_flow_offload_del_wq, &offload->work); } else { - NF_FLOW_TABLE_STAT_INC(net, count_wq_stats); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_stats); queue_work(nf_flow_offload_stats_wq, &offload->work); } } @@ -1098,6 +1098,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, struct flow_block_cb *block_cb, *next; int err = 0; + down_write(&flowtable->flow_block_lock); switch (cmd) { case FLOW_BLOCK_BIND: list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); @@ -1112,6 +1113,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, WARN_ON_ONCE(1); err = -EOPNOTSUPP; } + up_write(&flowtable->flow_block_lock); return err; } @@ -1168,7 +1170,9 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); + down_write(&flowtable->flow_block_lock); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + up_write(&flowtable->flow_block_lock); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e7152d599d73..7a09421f19e1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5958,7 +5958,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, &timeout); if (err) return err; - } else if (set->flags & NFT_SET_TIMEOUT) { + } else if (set->flags & NFT_SET_TIMEOUT && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { timeout = set->timeout; } @@ -6024,7 +6025,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EOPNOTSUPP; goto err_set_elem_expr; } - } else if (set->num_exprs > 0) { + } else if (set->num_exprs > 0 && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) goto err_set_elem_expr_clone; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..641dc21f92b4 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4f9299b9dcdd..06d46d182634 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1162,6 +1162,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); struct nft_pipapo_field *f; + const u8 *start_p, *end_p; int i, bsize_max, err = 0; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) @@ -1202,9 +1203,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, } /* Validate */ + start_p = start; + end_p = end; nft_pipapo_for_each_field(f, i, m) { - const u8 *start_p = start, *end_p = end; - if (f->rules >= (unsigned long)NFT_PIPAPO_RULE0_MAX) return -ENOSPC; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675..ad3c033db64e 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits; - newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6a193cce2a75..4ffdf2f45c44 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -542,7 +542,7 @@ static int nci_open_device(struct nci_dev *ndev) skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); - ndev->flags = 0; + ndev->flags &= BIT(NCI_UNREG); } done: diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index aa5e712adf07..3d36ea5701f0 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 282c51051dcc..994a0a1efb58 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -240,6 +240,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, target->sens_res = nfca_poll->sens_res; target->sel_res = nfca_poll->sel_res; target->nfcid1_len = nfca_poll->nfcid1_len; + if (target->nfcid1_len > ARRAY_SIZE(target->nfcid1)) + return -EPROTO; if (target->nfcid1_len > 0) { memcpy(target->nfcid1, nfca_poll->nfcid1, target->nfcid1_len); @@ -248,6 +250,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcb_poll = (struct rf_tech_specific_params_nfcb_poll *)params; target->sensb_res_len = nfcb_poll->sensb_res_len; + if (target->sensb_res_len > ARRAY_SIZE(target->sensb_res)) + return -EPROTO; if (target->sensb_res_len > 0) { memcpy(target->sensb_res, nfcb_poll->sensb_res, target->sensb_res_len); @@ -256,6 +260,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcf_poll = (struct rf_tech_specific_params_nfcf_poll *)params; target->sensf_res_len = nfcf_poll->sensf_res_len; + if (target->sensf_res_len > ARRAY_SIZE(target->sensf_res)) + return -EPROTO; if (target->sensf_res_len > 0) { memcpy(target->sensf_res, nfcf_poll->sensf_res, target->sensf_res_len); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..c8eaf4234b2e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; - new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6ce8dd19f33c..1ab65f7f2a0a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2293,8 +2293,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (snaplen > res) @@ -3520,8 +3519,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; aux.tp_len = origlen; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1ad0ec5afb50..8499ceb7719c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -399,6 +399,7 @@ enum rxrpc_conn_proto_state { struct rxrpc_bundle { struct rxrpc_conn_parameters params; refcount_t ref; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..bdb335cb2d05 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); refcount_set(&bundle->ref, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -149,7 +152,7 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle) dead = __refcount_dec_and_test(&bundle->ref, &r); - _debug("PUT B=%x %d", d, r); + _debug("PUT B=%x %d", d, r - 1); if (dead) rxrpc_free_bundle(bundle); } @@ -338,6 +341,7 @@ found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -435,6 +439,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -725,6 +730,7 @@ granted_channel: smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -900,9 +906,8 @@ out: static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -921,15 +926,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -939,10 +951,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1e8ab4749c6c..4662a6ce8a7e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 66b143bb04ac..d41002e4613f 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -61,7 +61,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -81,7 +81,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b38d91d6b249..4c7f7861ea96 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -178,7 +178,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -936,9 +936,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return; - new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index d4102f0a9abd..eaa02f098d1c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -32,7 +32,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp; - newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { @@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -130,7 +130,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, } if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index ef9fceadef8d..ee6514af830f 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -52,6 +52,19 @@ static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) } } +static void sctp_stream_free_ext(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_sched_ops *sched; + + if (!SCTP_SO(stream, sid)->ext) + return; + + sched = sctp_sched_ops_from_stream(stream); + sched->free_sid(stream, sid); + kfree(SCTP_SO(stream, sid)->ext); + SCTP_SO(stream, sid)->ext = NULL; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -70,16 +83,14 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, * sctp_stream_update will swap ->out pointers. */ for (i = 0; i < outcnt; i++) { - kfree(SCTP_SO(new, i)->ext); + sctp_stream_free_ext(new, i); SCTP_SO(new, i)->ext = SCTP_SO(stream, i)->ext; SCTP_SO(stream, i)->ext = NULL; } } - for (i = outcnt; i < stream->outcnt; i++) { - kfree(SCTP_SO(stream, i)->ext); - SCTP_SO(stream, i)->ext = NULL; - } + for (i = outcnt; i < stream->outcnt; i++) + sctp_stream_free_ext(stream, i); } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, @@ -174,9 +185,9 @@ void sctp_stream_free(struct sctp_stream *stream) struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; - sched->free(stream); + sched->unsched_all(stream); for (i = 0; i < stream->outcnt; i++) - kfree(SCTP_SO(stream, i)->ext); + sctp_stream_free_ext(stream, i); genradix_free(&stream->out); genradix_free(&stream->in); } diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 1ad565ed5627..7c8f9d89e16a 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -46,6 +46,10 @@ static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid, return 0; } +static void sctp_sched_fcfs_free_sid(struct sctp_stream *stream, __u16 sid) +{ +} + static void sctp_sched_fcfs_free(struct sctp_stream *stream) { } @@ -96,6 +100,7 @@ static struct sctp_sched_ops sctp_sched_fcfs = { .get = sctp_sched_fcfs_get, .init = sctp_sched_fcfs_init, .init_sid = sctp_sched_fcfs_init_sid, + .free_sid = sctp_sched_fcfs_free_sid, .free = sctp_sched_fcfs_free, .enqueue = sctp_sched_fcfs_enqueue, .dequeue = sctp_sched_fcfs_dequeue, diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 80b5a2c4cbc7..4fc9f2923ed1 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -204,6 +204,24 @@ static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, return sctp_sched_prio_set(stream, sid, 0, gfp); } +static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head; + int i; + + if (!prio) + return; + + SCTP_SO(stream, sid)->ext->prio_head = NULL; + for (i = 0; i < stream->outcnt; i++) { + if (SCTP_SO(stream, i)->ext && + SCTP_SO(stream, i)->ext->prio_head == prio) + return; + } + + kfree(prio); +} + static void sctp_sched_prio_free(struct sctp_stream *stream) { struct sctp_stream_priorities *prio, *n; @@ -323,6 +341,7 @@ static struct sctp_sched_ops sctp_sched_prio = { .get = sctp_sched_prio_get, .init = sctp_sched_prio_init, .init_sid = sctp_sched_prio_init_sid, + .free_sid = sctp_sched_prio_free_sid, .free = sctp_sched_prio_free, .enqueue = sctp_sched_prio_enqueue, .dequeue = sctp_sched_prio_dequeue, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index ff425aed62c7..cc444fe0d67c 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -90,6 +90,10 @@ static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, return 0; } +static void sctp_sched_rr_free_sid(struct sctp_stream *stream, __u16 sid) +{ +} + static void sctp_sched_rr_free(struct sctp_stream *stream) { sctp_sched_rr_unsched_all(stream); @@ -177,6 +181,7 @@ static struct sctp_sched_ops sctp_sched_rr = { .get = sctp_sched_rr_get, .init = sctp_sched_rr_init, .init_sid = sctp_sched_rr_init_sid, + .free_sid = sctp_sched_rr_free_sid, .free = sctp_sched_rr_free, .enqueue = sctp_sched_rr_enqueue, .dequeue = sctp_sched_rr_dequeue, diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f09316a9035f..d67440de011e 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1971,6 +1971,9 @@ rcv: /* Ok, everything's fine, try to synch own keys according to peers' */ tipc_crypto_key_synch(rx, *skb); + /* Re-fetch skb cb as skb might be changed in tipc_msg_validate */ + skb_cb = TIPC_SKB_CB(*skb); + /* Mark skb decrypted */ skb_cb->decrypted = 1; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8630707901e..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/link.c b/net/tipc/link.c index e260c0d557f5..b3ce24823f50 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2224,7 +2224,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - skb_linearize(skb); + if (skb_linearize(skb)) + goto exit; + hdr = buf_msg(skb); data = msg_data(hdr); diff --git a/net/tipc/node.c b/net/tipc/node.c index b48d97cbbe29..49ddc484c4fe 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1689,6 +1689,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, struct tipc_node *n; struct sk_buff_head xmitq; bool node_up = false; + struct net *peer_net; int bearer_id; int rc; @@ -1705,18 +1706,23 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, return -EHOSTUNREACH; } + rcu_read_lock(); tipc_node_read_lock(n); node_up = node_is_up(n); - if (node_up && n->peer_net && check_net(n->peer_net)) { + peer_net = n->peer_net; + tipc_node_read_unlock(n); + if (node_up && peer_net && check_net(peer_net)) { /* xmit inner linux container */ - tipc_lxc_xmit(n->peer_net, list); + tipc_lxc_xmit(peer_net, list); if (likely(skb_queue_empty(list))) { - tipc_node_read_unlock(n); + rcu_read_unlock(); tipc_node_put(n); return 0; } } + rcu_read_unlock(); + tipc_node_read_lock(n); bearer_id = n->active_links[selector & 1]; if (unlikely(bearer_id == INVALID_BEARER_ID)) { tipc_node_read_unlock(n); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..e3b427a70398 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -467,7 +469,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -577,17 +579,17 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) diff --git a/net/unix/diag.c b/net/unix/diag.c index 105f522a89fe..616b55c5b890 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -114,14 +114,16 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql); } -static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb) +static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb, + struct user_namespace *user_ns) { - uid_t uid = from_kuid_munged(sk_user_ns(nlskb->sk), sock_i_uid(sk)); + uid_t uid = from_kuid_munged(user_ns, sock_i_uid(sk)); return nla_put(nlskb, UNIX_DIAG_UID, sizeof(uid_t), &uid); } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 portid, u32 seq, u32 flags, int sk_ino) + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags, int sk_ino) { struct nlmsghdr *nlh; struct unix_diag_msg *rep; @@ -167,7 +169,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_UID) && - sk_diag_dump_uid(sk, skb)) + sk_diag_dump_uid(sk, skb, user_ns)) goto out_nlmsg_trim; nlmsg_end(skb, nlh); @@ -179,7 +181,8 @@ out_nlmsg_trim: } static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 portid, u32 seq, u32 flags) + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags) { int sk_ino; @@ -190,7 +193,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (!sk_ino) return 0; - return sk_diag_fill(sk, skb, req, portid, seq, flags, sk_ino); + return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino); } static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -214,7 +217,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (!(req->udiag_states & (1 << sk->sk_state))) goto next; - if (sk_diag_dump(sk, skb, req, + if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) { @@ -282,7 +285,8 @@ again: if (!rep) goto out; - err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).portid, + err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, req->udiag_ino); if (err < 0) { nlmsg_free(rep); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index da752b0cc752..3d86482e83f5 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -330,7 +330,8 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, * determine if they are the same ie. */ if (tmp_old[0] == WLAN_EID_VENDOR_SPECIFIC) { - if (!memcmp(tmp_old + 2, tmp + 2, 5)) { + if (tmp_old[1] >= 5 && tmp[1] >= 5 && + !memcmp(tmp_old + 2, tmp + 2, 5)) { /* same vendor ie, copy from * subelement */ @@ -2526,10 +2527,15 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, const struct cfg80211_bss_ies *ies1, *ies2; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - struct cfg80211_non_tx_bss non_tx_data; + struct cfg80211_non_tx_bss non_tx_data = {}; res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, len, gfp); + + /* don't do any further MBSSID handling for S1G */ + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) + return res; + if (!res || !wiphy->support_mbssid || !cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5f5aafd418af..21269e8f2db4 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) } } +static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + __u32 seq = xo->seq.low; + + seq += skb_shinfo(skb)->gso_segs; + if (unlikely(seq < xo->seq.low)) + return true; + + return false; +} + struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; @@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 9f4d42eb090f..ce56d659c55a 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(xo->seq.low < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 8bbcced67c22..2a90139ecbe1 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -30,8 +30,8 @@ KBUILD_PKG_ROOTCMD ?="fakeroot -u" export KDEB_SOURCENAME # Include only those top-level files that are needed by make, plus the GPL copy TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \ - include init io_uring ipc kernel lib mm net samples scripts \ - security sound tools usr virt \ + include init io_uring ipc kernel lib mm net rust \ + samples scripts security sound tools usr virt \ .config .scmversion Makefile \ Kbuild Kconfig COPYING $(wildcard localversion*) MKSPEC := $(srctree)/scripts/package/mkspec diff --git a/scripts/faddr2line b/scripts/faddr2line index 5514c23f45c2..0e73aca4f908 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -74,7 +74,8 @@ command -v ${ADDR2LINE} >/dev/null 2>&1 || die "${ADDR2LINE} isn't installed" find_dir_prefix() { local objfile=$1 - local start_kernel_addr=$(${READELF} --symbols --wide $objfile | ${AWK} '$8 == "start_kernel" {printf "0x%s", $2}') + local start_kernel_addr=$(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | + ${AWK} '$8 == "start_kernel" {printf "0x%s", $2}') [[ -z $start_kernel_addr ]] && return local file_line=$(${ADDR2LINE} -e $objfile $start_kernel_addr) @@ -178,7 +179,7 @@ __faddr2line() { found=2 break fi - done < <(${READELF} --symbols --wide $objfile | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2) + done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2) if [[ $found = 0 ]]; then warn "can't find symbol: sym_name: $sym_name sym_sec: $sym_sec sym_addr: $sym_addr sym_elf_size: $sym_elf_size" @@ -259,7 +260,7 @@ __faddr2line() { DONE=1 - done < <(${READELF} --symbols --wide $objfile | ${AWK} -v fn=$sym_name '$4 == "FUNC" && $8 == fn') + done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v fn=$sym_name '$4 == "FUNC" && $8 == fn') } [[ $# -lt 2 ]] && usage diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 60a2a63a5e90..a3ac5a716e9f 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -90,7 +90,7 @@ if [ -n "$KDEB_PKGVERSION" ]; then packageversion=$KDEB_PKGVERSION revision=${packageversion##*-} else - revision=$(cat .version 2>/dev/null||echo 1) + revision=$($srctree/init/build-version) packageversion=$version-$revision fi sourcename=$KDEB_SOURCENAME diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index b7aee23fc387..47ef6bc30c0e 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -113,15 +113,19 @@ EXPORT_SYMBOL(snd_seq_dump_var_event); * expand the variable length event to linear buffer space. */ -static int seq_copy_in_kernel(char **bufptr, const void *src, int size) +static int seq_copy_in_kernel(void *ptr, void *src, int size) { + char **bufptr = ptr; + memcpy(*bufptr, src, size); *bufptr += size; return 0; } -static int seq_copy_in_user(char __user **bufptr, const void *src, int size) +static int seq_copy_in_user(void *ptr, void *src, int size) { + char __user **bufptr = ptr; + if (copy_to_user(*bufptr, src, size)) return -EFAULT; *bufptr += size; @@ -151,8 +155,7 @@ int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char return newlen; } err = snd_seq_dump_var_event(event, - in_kernel ? (snd_seq_dump_func_t)seq_copy_in_kernel : - (snd_seq_dump_func_t)seq_copy_in_user, + in_kernel ? seq_copy_in_kernel : seq_copy_in_user, &buf); return err < 0 ? err : newlen; } diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c index f99e00083141..4c677c8546c7 100644 --- a/sound/firewire/dice/dice-stream.c +++ b/sound/firewire/dice/dice-stream.c @@ -59,7 +59,7 @@ int snd_dice_stream_get_rate_mode(struct snd_dice *dice, unsigned int rate, static int select_clock(struct snd_dice *dice, unsigned int rate) { - __be32 reg; + __be32 reg, new; u32 data; int i; int err; @@ -83,15 +83,17 @@ static int select_clock(struct snd_dice *dice, unsigned int rate) if (completion_done(&dice->clock_accepted)) reinit_completion(&dice->clock_accepted); - reg = cpu_to_be32(data); + new = cpu_to_be32(data); err = snd_dice_transaction_write_global(dice, GLOBAL_CLOCK_SELECT, - ®, sizeof(reg)); + &new, sizeof(new)); if (err < 0) return err; if (wait_for_completion_timeout(&dice->clock_accepted, - msecs_to_jiffies(NOTIFICATION_TIMEOUT_MS)) == 0) - return -ETIMEDOUT; + msecs_to_jiffies(NOTIFICATION_TIMEOUT_MS)) == 0) { + if (reg != new) + return -ETIMEDOUT; + } return 0; } diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index 51721edd8f53..e88d9ff95cdf 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -143,7 +143,7 @@ static const struct snd_kcontrol_new cs42l51_snd_controls[] = { 0, 0xA0, 96, adc_att_tlv), SOC_DOUBLE_R_SX_TLV("PGA Volume", CS42L51_ALC_PGA_CTL, CS42L51_ALC_PGB_CTL, - 0, 0x19, 30, pga_tlv), + 0, 0x1A, 30, pga_tlv), SOC_SINGLE("Playback Deemphasis Switch", CS42L51_DAC_CTL, 3, 1, 0), SOC_SINGLE("Auto-Mute Switch", CS42L51_DAC_CTL, 2, 1, 0), SOC_SINGLE("Soft Ramp Switch", CS42L51_DAC_CTL, 1, 1, 0), diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h index fc19c34ca00e..b65560981abb 100644 --- a/sound/soc/codecs/hdac_hda.h +++ b/sound/soc/codecs/hdac_hda.h @@ -14,7 +14,7 @@ enum { HDAC_HDMI_1_DAI_ID, HDAC_HDMI_2_DAI_ID, HDAC_HDMI_3_DAI_ID, - HDAC_LAST_DAI_ID = HDAC_HDMI_3_DAI_ID, + HDAC_DAI_ID_NUM }; struct hdac_hda_pcm { @@ -24,7 +24,7 @@ struct hdac_hda_pcm { struct hdac_hda_priv { struct hda_codec *codec; - struct hdac_hda_pcm pcm[HDAC_LAST_DAI_ID]; + struct hdac_hda_pcm pcm[HDAC_DAI_ID_NUM]; bool need_display_power; }; diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c index 3e04c7f0cce4..ec0905df65d1 100644 --- a/sound/soc/codecs/max98373-i2c.c +++ b/sound/soc/codecs/max98373-i2c.c @@ -549,6 +549,10 @@ static int max98373_i2c_probe(struct i2c_client *i2c) max98373->cache = devm_kcalloc(&i2c->dev, max98373->cache_num, sizeof(*max98373->cache), GFP_KERNEL); + if (!max98373->cache) { + ret = -ENOMEM; + return ret; + } for (i = 0; i < max98373->cache_num; i++) max98373->cache[i].reg = max98373_i2c_cache_reg[i]; diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 4120842fe699..88a8392a58ed 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -230,7 +230,7 @@ static int rt711_sdca_read_prop(struct sdw_slave *slave) } /* set the timeout values */ - prop->clk_stop_timeout = 20; + prop->clk_stop_timeout = 700; /* wake-up event */ prop->wake_capable = 1; diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 4b2135eba74d..a916f4619ea3 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1794,6 +1794,7 @@ static void sgtl5000_i2c_remove(struct i2c_client *client) { struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client); + regmap_write(sgtl5000->regmap, SGTL5000_CHIP_CLK_CTRL, SGTL5000_CHIP_CLK_CTRL_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT); diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c index a969547708d4..52bb55724724 100644 --- a/sound/soc/codecs/tlv320adc3xxx.c +++ b/sound/soc/codecs/tlv320adc3xxx.c @@ -14,6 +14,7 @@ #include <dt-bindings/sound/tlv320adc3xxx.h> #include <linux/clk.h> +#include <linux/gpio/consumer.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/io.h> @@ -1025,7 +1026,9 @@ static const struct gpio_chip adc3xxx_gpio_chip = { static void adc3xxx_free_gpio(struct adc3xxx *adc3xxx) { +#ifdef CONFIG_GPIOLIB gpiochip_remove(&adc3xxx->gpio_chip); +#endif } static void adc3xxx_init_gpio(struct adc3xxx *adc3xxx) diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index b4b4355c6728..b901e4c65e8a 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2503,6 +2503,14 @@ static void wm8962_configure_bclk(struct snd_soc_component *component) snd_soc_component_update_bits(component, WM8962_CLOCKING2, WM8962_SYSCLK_ENA_MASK, WM8962_SYSCLK_ENA); + /* DSPCLK_DIV field in WM8962_CLOCKING1 register is used to generate + * correct frequency of LRCLK and BCLK. Sometimes the read-only value + * can't be updated timely after enabling SYSCLK. This results in wrong + * calculation values. Delay is introduced here to wait for newest + * value from register. The time of the delay should be at least + * 500~1000us according to test. + */ + usleep_range(500, 1000); dspclk = snd_soc_component_read(component, WM8962_CLOCKING1); if (snd_soc_component_get_bias_level(component) != SND_SOC_BIAS_ON) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 79ef4e269bc9..4b86ef82fd93 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -194,6 +194,25 @@ static int fsl_micfil_reset(struct device *dev) if (ret) return ret; + /* + * SRES is self-cleared bit, but REG_MICFIL_CTRL1 is defined + * as non-volatile register, so SRES still remain in regmap + * cache after set, that every update of REG_MICFIL_CTRL1, + * software reset happens. so clear it explicitly. + */ + ret = regmap_clear_bits(micfil->regmap, REG_MICFIL_CTRL1, + MICFIL_CTRL1_SRES); + if (ret) + return ret; + + /* + * Set SRES should clear CHnF flags, But even add delay here + * the CHnF may not be cleared sometimes, so clear CHnF explicitly. + */ + ret = regmap_write_bits(micfil->regmap, REG_MICFIL_STAT, 0xFF, 0xFF); + if (ret) + return ret; + return 0; } diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index bd88de056358..55b009d3c681 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -452,7 +452,7 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, val = ucontrol->value.integer.value[0]; if (mc->platform_max && val > mc->platform_max) return -EINVAL; - if (val > max - min) + if (val > max) return -EINVAL; val_mask = mask << shift; val = (val + min) & mask; @@ -464,10 +464,15 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, ret = err; if (snd_soc_volsw_is_stereo(mc)) { - unsigned int val2; + unsigned int val2 = ucontrol->value.integer.value[1]; + + if (mc->platform_max && val2 > mc->platform_max) + return -EINVAL; + if (val2 > max) + return -EINVAL; val_mask = mask << rshift; - val2 = (ucontrol->value.integer.value[1] + min) & mask; + val2 = (val2 + min) & mask; val2 = val2 << rshift; err = snd_soc_component_update_bits(component, reg2, val_mask, diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index fb87d6d23408..35a16c3f9591 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -822,11 +822,6 @@ static int __soc_pcm_open(struct snd_soc_pcm_runtime *rtd, ret = snd_soc_dai_startup(dai, substream); if (ret < 0) goto err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dai->tx_mask = 0; - else - dai->rx_mask = 0; } /* Dynamic PCM DAI links compat checks use dynamic capabilities */ @@ -1252,6 +1247,8 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe, return; be_substream = snd_soc_dpcm_get_substream(be, stream); + if (!be_substream) + return; for_each_dpcm_fe(be, stream, dpcm) { if (dpcm->fe == fe) diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index ce7f6942308f..f3dd9f8e621c 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -1077,7 +1077,7 @@ static int stm32_i2s_parse_dt(struct platform_device *pdev, if (irq < 0) return irq; - ret = devm_request_irq(&pdev->dev, irq, stm32_i2s_isr, IRQF_ONESHOT, + ret = devm_request_irq(&pdev->dev, irq, stm32_i2s_isr, 0, dev_name(&pdev->dev), i2s); if (ret) { dev_err(&pdev->dev, "irq request returned %d\n", ret); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 184ce1684dcd..91b7106a4a73 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -11169,7 +11169,7 @@ static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf } *link = bpf_program__attach_raw_tracepoint(prog, tp_name); - return libbpf_get_error(link); + return libbpf_get_error(*link); } /* Common logic for all BPF program types that attach to a btf_id */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index f3a8e8e74eb8..d504d96adc83 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -234,7 +234,7 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_USER_RINGBUF: key_size = 0; value_size = 0; - max_entries = 4096; + max_entries = sysconf(_SC_PAGE_SIZE); break; case BPF_MAP_TYPE_STRUCT_OPS: /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index d285171d4b69..6af142953a94 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -77,6 +77,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, __u32 len = sizeof(info); struct epoll_event *e; struct ring *r; + __u64 mmap_sz; void *tmp; int err; @@ -115,8 +116,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, r->mask = info.max_entries - 1; /* Map writable consumer page */ - tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, - map_fd, 0); + tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); if (tmp == MAP_FAILED) { err = -errno; pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", @@ -129,8 +129,12 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, * data size to allow simple reading of samples that wrap around the * end of a ring buffer. See kernel implementation for details. * */ - tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ, - MAP_SHARED, map_fd, rb->page_size); + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries); + return libbpf_err(-E2BIG); + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; ringbuf_unmap_ring(rb, r); @@ -348,6 +352,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) { struct bpf_map_info info; __u32 len = sizeof(info); + __u64 mmap_sz; void *tmp; struct epoll_event *rb_epoll; int err; @@ -384,8 +389,13 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) * simple reading and writing of samples that wrap around the end of * the buffer. See the kernel implementation for details. */ - tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, - PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size); + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("user ringbuf: ring buf size (%u) is too big\n", info.max_entries); + return -E2BIG; + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED, + map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", @@ -476,6 +486,10 @@ void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size) __u64 cons_pos, prod_pos; struct ringbuf_hdr *hdr; + /* The top two bits are used as special flags */ + if (size & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT)) + return errno = E2BIG, NULL; + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in * the kernel. */ diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index ee819a402b69..11a1d2d4f681 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -464,9 +464,10 @@ to address dependencies, since the address of a location accessed through a pointer will depend on the value read earlier from that pointer. -Finally, a read event and another memory access event are linked by a -control dependency if the value obtained by the read affects whether -the second event is executed at all. Simple example: +Finally, a read event X and a write event Y are linked by a control +dependency if Y syntactically lies within an arm of an if statement and +X affects the evaluation of the if condition via a data or address +dependency (or similarly for a switch statement). Simple example: int x, y; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 43ec14c29a60..a7f1e6c8bb0a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -999,6 +999,16 @@ static const char *uaccess_safe_builtin[] = { "__tsan_read_write4", "__tsan_read_write8", "__tsan_read_write16", + "__tsan_volatile_read1", + "__tsan_volatile_read2", + "__tsan_volatile_read4", + "__tsan_volatile_read8", + "__tsan_volatile_read16", + "__tsan_volatile_write1", + "__tsan_volatile_write2", + "__tsan_volatile_write4", + "__tsan_volatile_write8", + "__tsan_volatile_write16", "__tsan_atomic8_load", "__tsan_atomic16_load", "__tsan_atomic32_load", diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c index 099eb4dfd4f7..18405c3b7cee 100644 --- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c +++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c @@ -458,7 +458,7 @@ static void test_sk_storage_map_basic(void) struct { int cnt; int lock; - } value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value; + } value = { .cnt = 0xeB9f, .lock = 1, }, lookup_value; struct bpf_map_create_opts bad_xattr; int btf_fd, map_fd, sk_fd, err; @@ -483,38 +483,41 @@ static void test_sk_storage_map_basic(void) "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, BPF_F_LOCK); - CHECK(err || lookup_value.cnt != value.cnt, + CHECK(err || lookup_value.lock || lookup_value.cnt != value.cnt, "bpf_map_lookup_elem_flags(BPF_F_LOCK)", - "err:%d errno:%d cnt:%x(%x)\n", - err, errno, lookup_value.cnt, value.cnt); + "err:%d errno:%d lock:%x cnt:%x(%x)\n", + err, errno, lookup_value.lock, lookup_value.cnt, value.cnt); /* Bump the cnt and update with BPF_EXIST | BPF_F_LOCK */ value.cnt += 1; + value.lock = 2; err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_EXIST | BPF_F_LOCK); CHECK(err, "bpf_map_update_elem(BPF_EXIST|BPF_F_LOCK)", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, BPF_F_LOCK); - CHECK(err || lookup_value.cnt != value.cnt, + CHECK(err || lookup_value.lock || lookup_value.cnt != value.cnt, "bpf_map_lookup_elem_flags(BPF_F_LOCK)", - "err:%d errno:%d cnt:%x(%x)\n", - err, errno, lookup_value.cnt, value.cnt); + "err:%d errno:%d lock:%x cnt:%x(%x)\n", + err, errno, lookup_value.lock, lookup_value.cnt, value.cnt); /* Bump the cnt and update with BPF_EXIST */ value.cnt += 1; + value.lock = 2; err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_EXIST); CHECK(err, "bpf_map_update_elem(BPF_EXIST)", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, BPF_F_LOCK); - CHECK(err || lookup_value.cnt != value.cnt, + CHECK(err || lookup_value.lock || lookup_value.cnt != value.cnt, "bpf_map_lookup_elem_flags(BPF_F_LOCK)", - "err:%d errno:%d cnt:%x(%x)\n", - err, errno, lookup_value.cnt, value.cnt); + "err:%d errno:%d lock:%x cnt:%x(%x)\n", + err, errno, lookup_value.lock, lookup_value.cnt, value.cnt); /* Update with BPF_NOEXIST */ value.cnt += 1; + value.lock = 2; err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_NOEXIST | BPF_F_LOCK); CHECK(!err || errno != EEXIST, @@ -526,22 +529,23 @@ static void test_sk_storage_map_basic(void) value.cnt -= 1; err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, BPF_F_LOCK); - CHECK(err || lookup_value.cnt != value.cnt, + CHECK(err || lookup_value.lock || lookup_value.cnt != value.cnt, "bpf_map_lookup_elem_flags(BPF_F_LOCK)", - "err:%d errno:%d cnt:%x(%x)\n", - err, errno, lookup_value.cnt, value.cnt); + "err:%d errno:%d lock:%x cnt:%x(%x)\n", + err, errno, lookup_value.lock, lookup_value.cnt, value.cnt); /* Bump the cnt again and update with map_flags == 0 */ value.cnt += 1; + value.lock = 2; err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); CHECK(err, "bpf_map_update_elem()", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, BPF_F_LOCK); - CHECK(err || lookup_value.cnt != value.cnt, + CHECK(err || lookup_value.lock || lookup_value.cnt != value.cnt, "bpf_map_lookup_elem_flags(BPF_F_LOCK)", - "err:%d errno:%d cnt:%x(%x)\n", - err, errno, lookup_value.cnt, value.cnt); + "err:%d errno:%d lock:%x cnt:%x(%x)\n", + err, errno, lookup_value.lock, lookup_value.cnt, value.cnt); /* Test delete elem */ err = bpf_map_delete_elem(map_fd, &sk_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index d457a55ff408..a4b4133d39e9 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -358,10 +358,12 @@ static int get_syms(char ***symsp, size_t *cntp) * We attach to almost all kernel functions and some of them * will cause 'suspicious RCU usage' when fprobe is attached * to them. Filter out the current culprits - arch_cpu_idle - * and rcu_* functions. + * default_idle and rcu_* functions. */ if (!strcmp(name, "arch_cpu_idle")) continue; + if (!strcmp(name, "default_idle")) + continue; if (!strncmp(name, "rcu_", 4)) continue; if (!strcmp(name, "bpf_dispatcher_xdp_func")) @@ -400,7 +402,7 @@ error: return err; } -static void test_bench_attach(void) +void serial_test_kprobe_multi_bench_attach(void) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); struct kprobe_multi_empty *skel = NULL; @@ -468,6 +470,4 @@ void test_kprobe_multi_test(void) test_attach_api_syms(); if (test__start_subtest("attach_api_fails")) test_attach_api_fails(); - if (test__start_subtest("bench_attach")) - test_bench_attach(); } diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 22b31ebb3513..258ddc565deb 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -19,12 +19,12 @@ /* - * Memory cgroup charging is performed using percpu batches 32 pages + * Memory cgroup charging is performed using percpu batches 64 pages * big (look at MEMCG_CHARGE_BATCH), whereas memory.stat is exact. So * the maximum discrepancy between charge and vmstat entries is number - * of cpus multiplied by 32 pages. + * of cpus multiplied by 64 pages. */ -#define MAX_VMSTAT_ERROR (4096 * 32 * get_nprocs()) +#define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs()) static int alloc_dcache(const char *cgroup, void *arg) diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 2f0d705db9db..05d980fb083d 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -41,6 +41,7 @@ /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test /x86_64/svm_nested_soft_inject_test +/x86_64/svm_nested_shutdown_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/tsc_scaling_sync diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0172eb6cb6ee..4a2caef2c939 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -101,6 +101,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e8ca0d8a6a7e..5da0c5e2a7af 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -748,6 +748,19 @@ struct ex_regs { uint64_t rflags; }; +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 39c4409ef56a..41c1c73c464d 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1074,19 +1074,6 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) } } -struct idt_entry { - uint16_t offset0; - uint16_t selector; - uint16_t ist : 3; - uint16_t : 5; - uint16_t type : 4; - uint16_t : 1; - uint16_t dpl : 2; - uint16_t p : 1; - uint16_t offset1; - uint32_t offset2; uint32_t reserved; -}; - static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, int dpl, unsigned short selector) { diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c new file mode 100644 index 000000000000..e73fcdef47bb --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_nested_shutdown_test + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("ud2"); +} + +static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + idt[6].p = 0; // #UD is intercepted but its injection will cause #NP + idt[11].p = 0; // #NP is not intercepted and will cause another + // #NP that will be converted to #DF + idt[8].p = 0; // #DF will cause #NP which will cause SHUTDOWN + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here */ + GUEST_ASSERT(0); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + vm_vaddr_t svm_gva; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vcpu_alloc_svm(vm, &svm_gva); + + vcpu_args_set(vcpu, 2, svm_gva, vm->idt); + run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c index 70b44f0b52fe..ead5d878a71c 100644 --- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -3,6 +3,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include <string.h> #include <sys/ioctl.h> @@ -20,10 +21,11 @@ static void l2_guest_code(void) : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); } -void l1_guest_code(struct vmx_pages *vmx) -{ #define L2_GUEST_STACK_SIZE 64 - unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; +unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + +void l1_guest_code_vmx(struct vmx_pages *vmx) +{ GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); @@ -38,24 +40,53 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } +void l1_guest_code_svm(struct svm_test_data *svm) +{ + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* don't intercept shutdown to test the case of SVM allowing to do so */ + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here, L1 should crash */ + GUEST_ASSERT(0); +} + int main(void) { struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vcpu_events events; - vm_vaddr_t vmx_pages_gva; struct ucall uc; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + bool has_vmx = kvm_cpu_has(X86_FEATURE_VMX); + bool has_svm = kvm_cpu_has(X86_FEATURE_SVM); + + TEST_REQUIRE(has_vmx || has_svm); TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT)); - vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); + if (has_vmx) { + vm_vaddr_t vmx_pages_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + } else { + vm_vaddr_t svm_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm); + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); + } + + vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); run = vcpu->run; - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -78,13 +109,21 @@ int main(void) "No triple fault pending"); vcpu_run(vcpu); - switch (get_ucall(vcpu, &uc)) { - case UCALL_DONE: - break; - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - default: - TEST_FAIL("Unexpected ucall: %lu", uc.cmd); - } + if (has_svm) { + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + } else { + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } + return 0; } diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 3d7adee7a3e6..ff8fe93f679c 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only bind_bhash cmsg_sender +diag_uid fin_ack_lat gro hwtstamp_config diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 969620ae9928..1e4b397cece6 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,3 @@ -TEST_GEN_PROGS := test_unix_oob unix_connect +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c new file mode 100644 index 000000000000..5b88f7129fea --- /dev/null +++ b/tools/testing/selftests/net/af_unix/diag_uid.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#define _GNU_SOURCE +#include <sched.h> + +#include <unistd.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/sock_diag.h> +#include <linux/unix_diag.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/un.h> + +#include "../../kselftest_harness.h" + +FIXTURE(diag_uid) +{ + int netlink_fd; + int unix_fd; + __u32 inode; + __u64 cookie; +}; + +FIXTURE_VARIANT(diag_uid) +{ + int unshare; + int udiag_show; +}; + +FIXTURE_VARIANT_ADD(diag_uid, uid) +{ + .unshare = 0, + .udiag_show = UDIAG_SHOW_UID +}; + +FIXTURE_VARIANT_ADD(diag_uid, uid_unshare) +{ + .unshare = CLONE_NEWUSER, + .udiag_show = UDIAG_SHOW_UID +}; + +FIXTURE_SETUP(diag_uid) +{ + struct stat file_stat; + socklen_t optlen; + int ret; + + if (variant->unshare) + ASSERT_EQ(unshare(variant->unshare), 0); + + self->netlink_fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + ASSERT_NE(self->netlink_fd, -1); + + self->unix_fd = socket(AF_UNIX, SOCK_STREAM, 0); + ASSERT_NE(self->unix_fd, -1); + + ret = fstat(self->unix_fd, &file_stat); + ASSERT_EQ(ret, 0); + + self->inode = file_stat.st_ino; + + optlen = sizeof(self->cookie); + ret = getsockopt(self->unix_fd, SOL_SOCKET, SO_COOKIE, &self->cookie, &optlen); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(diag_uid) +{ + close(self->netlink_fd); + close(self->unix_fd); +} + +int send_request(struct __test_metadata *_metadata, + FIXTURE_DATA(diag_uid) *self, + const FIXTURE_VARIANT(diag_uid) *variant) +{ + struct { + struct nlmsghdr nlh; + struct unix_diag_req udr; + } req = { + .nlh = { + .nlmsg_len = sizeof(req), + .nlmsg_type = SOCK_DIAG_BY_FAMILY, + .nlmsg_flags = NLM_F_REQUEST + }, + .udr = { + .sdiag_family = AF_UNIX, + .udiag_ino = self->inode, + .udiag_cookie = { + (__u32)self->cookie, + (__u32)(self->cookie >> 32) + }, + .udiag_show = variant->udiag_show + } + }; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK + }; + struct iovec iov = { + .iov_base = &req, + .iov_len = sizeof(req) + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1 + }; + + return sendmsg(self->netlink_fd, &msg, 0); +} + +void render_response(struct __test_metadata *_metadata, + struct unix_diag_req *udr, __u32 len) +{ + unsigned int rta_len = len - NLMSG_LENGTH(sizeof(*udr)); + struct rtattr *attr; + uid_t uid; + + ASSERT_GT(len, sizeof(*udr)); + ASSERT_EQ(udr->sdiag_family, AF_UNIX); + + attr = (struct rtattr *)(udr + 1); + ASSERT_NE(RTA_OK(attr, rta_len), 0); + ASSERT_EQ(attr->rta_type, UNIX_DIAG_UID); + + uid = *(uid_t *)RTA_DATA(attr); + ASSERT_EQ(uid, getuid()); +} + +void receive_response(struct __test_metadata *_metadata, + FIXTURE_DATA(diag_uid) *self) +{ + long buf[8192 / sizeof(long)]; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK + }; + struct iovec iov = { + .iov_base = buf, + .iov_len = sizeof(buf) + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1 + }; + struct unix_diag_req *udr; + struct nlmsghdr *nlh; + int ret; + + ret = recvmsg(self->netlink_fd, &msg, 0); + ASSERT_GT(ret, 0); + + nlh = (struct nlmsghdr *)buf; + ASSERT_NE(NLMSG_OK(nlh, ret), 0); + ASSERT_EQ(nlh->nlmsg_type, SOCK_DIAG_BY_FAMILY); + + render_response(_metadata, NLMSG_DATA(nlh), nlh->nlmsg_len); + + nlh = NLMSG_NEXT(nlh, ret); + ASSERT_EQ(NLMSG_OK(nlh, ret), 0); +} + +TEST_F(diag_uid, 1) +{ + int ret; + + ret = send_request(_metadata, self, variant); + ASSERT_GT(ret, 0); + + receive_response(_metadata, self); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index ead7963b9bf0..bd89198cd817 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,5 +43,5 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y -CONFIG_CRYPTO_SM4=y +CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 31c3b6ebd388..21ca91473c09 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4196,10 +4196,13 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -which nettest >/dev/null -if [ $? -ne 0 ]; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip +# nettest can be run from PATH or from same directory as this selftest +if ! which nettest >/dev/null; then + PATH=$PWD:$PATH + if ! which nettest >/dev/null; then + echo "'nettest' command not found; skipping tests" + exit $ksft_skip + fi fi declare -i nfail=0 diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ee5e98204d3d..a47b26ab48f2 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1228,6 +1228,17 @@ ipv4_fcnal() run_cmd "$IP ro add 172.16.101.0/24 nhid 21" run_cmd "$IP ro del 172.16.101.0/24 nexthop via 172.16.1.7 dev veth1 nexthop via 172.16.1.8 dev veth1" log_test $? 2 "Delete multipath route with only nh id based entry" + + run_cmd "$IP nexthop add id 22 via 172.16.1.6 dev veth1" + run_cmd "$IP ro add 172.16.102.0/24 nhid 22" + run_cmd "$IP ro del 172.16.102.0/24 dev veth1" + log_test $? 2 "Delete route when specifying only nexthop device" + + run_cmd "$IP ro del 172.16.102.0/24 via 172.16.1.6" + log_test $? 2 "Delete route when specifying only gateway" + + run_cmd "$IP ro del 172.16.102.0/24" + log_test $? 0 "Delete route when not specifying nexthop attributes" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 2271a8727f62..5637b5dadabd 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1711,13 +1711,21 @@ ipv4_del_addr_test() $IP addr add dev dummy1 172.16.104.1/24 $IP addr add dev dummy1 172.16.104.11/24 + $IP addr add dev dummy1 172.16.104.12/24 + $IP addr add dev dummy1 172.16.104.13/24 $IP addr add dev dummy2 172.16.104.1/24 $IP addr add dev dummy2 172.16.104.11/24 + $IP addr add dev dummy2 172.16.104.12/24 $IP route add 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11 + $IP route add 172.16.106.0/24 dev lo src 172.16.104.12 + $IP route add table 0 172.16.107.0/24 via 172.16.104.2 src 172.16.104.13 $IP route add vrf red 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11 + $IP route add vrf red 172.16.106.0/24 dev lo src 172.16.104.12 set +e # removing address from device in vrf should only remove route from vrf table + echo " Regular FIB info" + $IP addr del dev dummy2 172.16.104.11/24 $IP ro ls vrf red | grep -q 172.16.105.0/24 log_test $? 1 "Route removed from VRF when source address deleted" @@ -1735,6 +1743,35 @@ ipv4_del_addr_test() $IP ro ls vrf red | grep -q 172.16.105.0/24 log_test $? 0 "Route in VRF is not removed by address delete" + # removing address from device in vrf should only remove route from vrf + # table even when the associated fib info only differs in table ID + echo " Identical FIB info with different table ID" + + $IP addr del dev dummy2 172.16.104.12/24 + $IP ro ls vrf red | grep -q 172.16.106.0/24 + log_test $? 1 "Route removed from VRF when source address deleted" + + $IP ro ls | grep -q 172.16.106.0/24 + log_test $? 0 "Route in default VRF not removed" + + $IP addr add dev dummy2 172.16.104.12/24 + $IP route add vrf red 172.16.106.0/24 dev lo src 172.16.104.12 + + $IP addr del dev dummy1 172.16.104.12/24 + $IP ro ls | grep -q 172.16.106.0/24 + log_test $? 1 "Route removed in default VRF when source address deleted" + + $IP ro ls vrf red | grep -q 172.16.106.0/24 + log_test $? 0 "Route in VRF is not removed by address delete" + + # removing address from device in default vrf should remove route from + # the default vrf even when route was inserted with a table ID of 0. + echo " Table ID 0" + + $IP addr del dev dummy1 172.16.104.13/24 + $IP ro ls | grep -q 172.16.107.0/24 + log_test $? 1 "Route removed in default VRF when source address deleted" + $IP li del dummy1 $IP li del dummy2 cleanup diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f3dd5f2a0272..2eeaf4aca644 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2152,7 +2152,7 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2165,7 +2165,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2178,7 +2178,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 0879da915014..80d36f7cfee8 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -35,8 +35,9 @@ init() ns1="ns1-$rndh" ns2="ns2-$rndh" + ns_sbox="ns_sbox-$rndh" - for netns in "$ns1" "$ns2";do + for netns in "$ns1" "$ns2" "$ns_sbox";do ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 @@ -73,7 +74,7 @@ init() cleanup() { - for netns in "$ns1" "$ns2"; do + for netns in "$ns1" "$ns2" "$ns_sbox"; do ip netns del $netns done rm -f "$cin" "$cout" @@ -243,7 +244,7 @@ do_mptcp_sockopt_tests() { local lret=0 - ./mptcp_sockopt + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? if [ $lret -ne 0 ]; then @@ -252,7 +253,7 @@ do_mptcp_sockopt_tests() return fi - ./mptcp_sockopt -6 + ip netns exec "$ns_sbox" ./mptcp_sockopt -6 lret=$? if [ $lret -ne 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ffa13a957a36..40aeb5a71a2a 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -247,9 +247,10 @@ run_test() tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 - # time is measured in ms, account for transfer size, affegated link speed + # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) - local time=$((size * 8 * 1000 * 10 / (( $rate1 + $rate2) * 1024 *1024 * 9) )) + # ms byte -> bit 10% mbit -> kbit -> bit 10% + local time=$((1000 * size * 8 * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) )) # mptcp_connect will do some sleeps to allow the mp_join handshake # completion (see mptcp_connect): 200ms on each side, add some slack diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 736e358dc549..dfe3d287f01d 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -686,10 +686,12 @@ setup_xfrm() { } setup_nettest_xfrm() { - which nettest >/dev/null - if [ $? -ne 0 ]; then - echo "'nettest' command not found; skipping tests" - return 1 + if ! which nettest >/dev/null; then + PATH=$PWD:$PATH + if ! which nettest >/dev/null; then + echo "'nettest' command not found; skipping tests" + return 1 + fi fi [ ${1} -eq 6 ] && proto="-6" || proto="" diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 0900c5438fbb..275491be3da2 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -782,7 +782,7 @@ kci_test_ipsec_offload() tmpl proto esp src $srcip dst $dstip spi 9 \ mode transport reqid 42 check_err $? - ip x p add dir out src $dstip/24 dst $srcip/24 \ + ip x p add dir in src $dstip/24 dst $srcip/24 \ tmpl proto esp src $dstip dst $srcip spi 9 \ mode transport reqid 42 check_err $? diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh index 0a49907cd4fe..da5bfd834eff 100755 --- a/tools/testing/selftests/net/toeplitz.sh +++ b/tools/testing/selftests/net/toeplitz.sh @@ -32,7 +32,7 @@ DEV="eth0" # This is determined by reading the RSS indirection table using ethtool. get_rss_cfg_num_rxqs() { echo $(ethtool -x "${DEV}" | - egrep [[:space:]]+[0-9]+:[[:space:]]+ | + grep -E [[:space:]]+[0-9]+:[[:space:]]+ | cut -d: -f2- | awk '{$1=$1};1' | tr ' ' '\n' | diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 6a443ca3cd3a..0c743752669a 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + # set global exit status, but never reset nonzero one. check_err() { @@ -34,7 +36,7 @@ cfg_veth() { ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp } run_one() { @@ -195,8 +197,8 @@ run_all() { return $ret } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index 8a1109a545db..894972877e8b 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + cleanup() { local -r jobs="$(jobs -p)" local -r ns="$(ip netns list|grep $PEER_NS)" @@ -34,7 +36,7 @@ run_one() { ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & @@ -80,8 +82,8 @@ run_all() { run_udp "${ipv6_args}" } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 7fe85ba51075..c9c4b9d65839 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -5,6 +5,8 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +BPF_FILE="../bpf/xdp_dummy.bpf.o" + cleanup() { local -r jobs="$(jobs -p)" local -r ns="$(ip netns list|grep $PEER_NS)" @@ -36,7 +38,7 @@ run_one() { ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on - ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp + ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action @@ -81,8 +83,8 @@ run_all() { run_udp "${ipv6_args}" } -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 1bcd82e1f662..c079565add39 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +BPF_FILE="../bpf/xdp_dummy.bpf.o" readonly BASE="ns-$(mktemp -u XXXXXX)" readonly SRC=2 readonly DST=1 @@ -46,7 +47,7 @@ create_ns() { ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24 ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad done - ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null + ip -n $NS_DST link set veth$DST xdp object ${BPF_FILE} section xdp 2>/dev/null } create_vxlan_endpoint() { diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 430895d1a2b6..2d073595c620 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +BPF_FILE="../bpf/xdp_dummy.bpf.o" readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" readonly BASE=`basename $STATS` readonly SRC=2 @@ -216,8 +217,8 @@ while getopts "hs:" option; do esac done -if [ ! -f ../bpf/xdp_dummy.o ]; then - echo "Missing xdp_dummy helper. Build bpf selftest first" +if [ ! -f ${BPF_FILE} ]; then + echo "Missing ${BPF_FILE}. Build bpf selftest first" exit 1 fi @@ -288,14 +289,14 @@ if [ $CPUS -gt 1 ]; then ip netns exec $NS_DST ethtool -L veth$DST rx 1 tx 2 2>/dev/null ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null printf "%-60s" "bad setting: XDP with RX nr less than TX" - ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} \ section xdp 2>/dev/null &&\ echo "fail - set operation successful ?!?" || echo " ok " # the following tests will run with multiple channels active ip netns exec $NS_SRC ethtool -L veth$SRC rx 2 ip netns exec $NS_DST ethtool -L veth$DST rx 2 - ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \ + ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} \ section xdp 2>/dev/null printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set" ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\ @@ -311,7 +312,7 @@ if [ $CPUS -gt 2 ]; then chk_channels "setting invalid channels nr" $DST 2 2 fi -ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null +ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp 2>/dev/null chk_gro_flag "with xdp attached - gro flag" $DST on chk_gro_flag " - peer gro flag" $SRC off chk_tso_flag " - tso flag" $SRC off diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 69ea659caca9..22f1e1d73fa8 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -95,6 +95,7 @@ all: run sysroot: sysroot/$(ARCH)/include sysroot/$(ARCH)/include: + $(Q)rm -rf sysroot/$(ARCH) sysroot/sysroot $(QUIET_MKDIR)mkdir -p sysroot $(Q)$(MAKE) -C ../../../include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone $(Q)mv sysroot/sysroot sysroot/$(ARCH) @@ -133,3 +134,5 @@ clean: $(Q)rm -rf initramfs $(call QUIET_CLEAN, run.out) $(Q)rm -rf run.out + +.PHONY: sysroot/$(ARCH)/include diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 78bced95ac63..f14f5076fb6d 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -565,6 +565,13 @@ int run_stdlib(int min, int max) CASE_TEST(strchr_foobar_z); EXPECT_STRZR(1, strchr("foobar", 'z')); break; CASE_TEST(strrchr_foobar_o); EXPECT_STREQ(1, strrchr("foobar", 'o'), "obar"); break; CASE_TEST(strrchr_foobar_z); EXPECT_STRZR(1, strrchr("foobar", 'z')); break; + CASE_TEST(memcmp_20_20); EXPECT_EQ(1, memcmp("aaa\x20", "aaa\x20", 4), 0); break; + CASE_TEST(memcmp_20_60); EXPECT_LT(1, memcmp("aaa\x20", "aaa\x60", 4), 0); break; + CASE_TEST(memcmp_60_20); EXPECT_GT(1, memcmp("aaa\x60", "aaa\x20", 4), 0); break; + CASE_TEST(memcmp_20_e0); EXPECT_LT(1, memcmp("aaa\x20", "aaa\xe0", 4), 0); break; + CASE_TEST(memcmp_e0_20); EXPECT_GT(1, memcmp("aaa\xe0", "aaa\x20", 4), 0); break; + CASE_TEST(memcmp_80_e0); EXPECT_LT(1, memcmp("aaa\x80", "aaa\xe0", 4), 0); break; + CASE_TEST(memcmp_e0_80); EXPECT_GT(1, memcmp("aaa\xe0", "aaa\x80", 4), 0); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ diff --git a/tools/testing/selftests/rcutorture/bin/config2csv.sh b/tools/testing/selftests/rcutorture/bin/config2csv.sh index d5a16631b16e..0cf55f1bf654 100755 --- a/tools/testing/selftests/rcutorture/bin/config2csv.sh +++ b/tools/testing/selftests/rcutorture/bin/config2csv.sh @@ -30,9 +30,8 @@ else fi scenarios="`echo $scenariosarg | sed -e "s/\<CFLIST\>/$defaultconfigs/g"`" -T=/tmp/config2latex.sh.$$ +T=`mktemp -d /tmp/config2latex.sh.XXXXXX` trap 'rm -rf $T' 0 -mkdir $T cat << '---EOF---' >> $T/p.awk END { diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh index 90016c359e83..b3d2e7efa40c 100755 --- a/tools/testing/selftests/rcutorture/bin/config_override.sh +++ b/tools/testing/selftests/rcutorture/bin/config_override.sh @@ -29,9 +29,8 @@ else exit 1 fi -T=${TMPDIR-/tmp}/config_override.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/config_override.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T sed < $override -e 's/^/grep -v "/' -e 's/=.*$/="/' | awk ' diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index 31584cee84d7..83fac1852ab2 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -7,9 +7,8 @@ # # Authors: Paul E. McKenney <[email protected]> -T=${TMPDIR-/tmp}/abat-chk-config.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/configcheck.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T cat $1 > $T/.config diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index d6e5ce084b1c..28bdb3ac7ba6 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -15,9 +15,8 @@ # # Authors: Paul E. McKenney <[email protected]> -T=${TMPDIR-/tmp}/configinit.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/configinit.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T # Capture config spec file. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh index 0941f1ddab65..8a968fbda02c 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh @@ -12,9 +12,8 @@ scriptname=$0 args="$*" -T=${TMPDIR-/tmp}/kvm-again.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-again.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T if ! test -d tools/testing/selftests/rcutorture/bin then @@ -51,27 +50,56 @@ RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh +bootargs= dryrun= dur= default_link="cp -R" -rundir="`pwd`/tools/testing/selftests/rcutorture/res/`date +%Y.%m.%d-%H.%M.%S-again`" +resdir="`pwd`/tools/testing/selftests/rcutorture/res" +rundir="$resdir/`date +%Y.%m.%d-%H.%M.%S-again`" +got_datestamp= +got_rundir= startdate="`date`" starttime="`get_starttime`" usage () { echo "Usage: $scriptname $oldrun [ arguments ]:" + echo " --bootargs kernel-boot-arguments" + echo " --datestamp string" echo " --dryrun" echo " --duration minutes | <seconds>s | <hours>h | <days>d" echo " --link hard|soft|copy" echo " --remote" echo " --rundir /new/res/path" + echo "Command line: $scriptname $args" exit 1 } while test $# -gt 0 do case "$1" in + --bootargs|--bootarg) + checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' + bootargs="$bootargs $2" + shift + ;; + --datestamp) + checkarg --datestamp "(relative pathname)" "$#" "$2" '^[a-zA-Z0-9._/-]*$' '^--' + if test -n "$got_rundir" || test -n "$got_datestamp" + then + echo Only one of --datestamp or --rundir may be specified + usage + fi + got_datestamp=y + ds=$2 + rundir="$resdir/$ds" + if test -e "$rundir" + then + echo "--datestamp $2: Already exists." + usage + fi + shift + ;; --dryrun) dryrun=1 ;; @@ -113,6 +141,12 @@ do ;; --rundir) checkarg --rundir "(absolute pathname)" "$#" "$2" '^/' '^error' + if test -n "$got_rundir" || test -n "$got_datestamp" + then + echo Only one of --datestamp or --rundir may be specified + usage + fi + got_rundir=y rundir=$2 if test -e "$rundir" then @@ -122,8 +156,11 @@ do shift ;; *) - echo Unknown argument $1 - usage + if test -n "$1" + then + echo Unknown argument $1 + usage + fi ;; esac shift @@ -156,7 +193,7 @@ do qemu_cmd_dir="`dirname "$i"`" kernel_dir="`echo $qemu_cmd_dir | sed -e 's/\.[0-9]\+$//'`" jitter_dir="`dirname "$kernel_dir"`" - kvm-transform.sh "$kernel_dir/bzImage" "$qemu_cmd_dir/console.log" "$jitter_dir" $dur < $T/qemu-cmd > $i + kvm-transform.sh "$kernel_dir/bzImage" "$qemu_cmd_dir/console.log" "$jitter_dir" $dur "$bootargs" < $T/qemu-cmd > $i if test -n "$arg_remote" then echo "# TORTURE_KCONFIG_GDB_ARG=''" >> $i diff --git a/tools/testing/selftests/rcutorture/bin/kvm-assign-cpus.sh b/tools/testing/selftests/rcutorture/bin/kvm-assign-cpus.sh index f99b2c146f83..46b08cd16ba5 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-assign-cpus.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-assign-cpus.sh @@ -7,9 +7,8 @@ # # Usage: kvm-assign-cpus.sh /path/to/sysfs -T=/tmp/kvm-assign-cpus.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-assign-cpus.sh.XXXXXX`" trap 'rm -rf $T' 0 2 -mkdir $T sysfsdir=${1-/sys/devices/system/node} if ! cd "$sysfsdir" > $T/msg 2>&1 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 5ad973dca820..e28a82851f7c 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -23,9 +23,8 @@ then fi resdir=${2} -T=${TMPDIR-/tmp}/test-linux.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-build.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T cp ${config_template} $T/config cat << ___EOF___ >> $T/config diff --git a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh index ee886b40a5d2..2b56baceb05d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh @@ -18,9 +18,8 @@ then exit 1 fi -T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-end-run-stats.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE PATH=${RCUTORTURE}/bin:$PATH; export PATH diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 0789c5606d2a..1df7e695edf7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -30,7 +30,7 @@ do resdir=`echo $i | sed -e 's,/$,,' -e 's,/[^/]*$,,'` head -1 $resdir/log fi - TORTURE_SUITE="`cat $i/../torture_suite`" + TORTURE_SUITE="`cat $i/../torture_suite`" ; export TORTURE_SUITE configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags case "${TORTURE_SUITE}" in diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index 9f0a5d5ff2dd..a2328163eba1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -34,19 +34,18 @@ fi shift # Pathnames: -# T: /tmp/kvm-remote.sh.$$ -# resdir: /tmp/kvm-remote.sh.$$/res -# rundir: /tmp/kvm-remote.sh.$$/res/$ds ("-remote" suffix) +# T: /tmp/kvm-remote.sh.NNNNNN where "NNNNNN" is set by mktemp +# resdir: /tmp/kvm-remote.sh.NNNNNN/res +# rundir: /tmp/kvm-remote.sh.NNNNNN/res/$ds ("-remote" suffix) # oldrun: `pwd`/tools/testing/.../res/$otherds # # Pathname segments: -# TD: kvm-remote.sh.$$ +# TD: kvm-remote.sh.NNNNNN # ds: yyyy.mm.dd-hh.mm.ss-remote -TD=kvm-remote.sh.$$ -T=${TMPDIR-/tmp}/$TD +T="`mktemp -d ${TMPDIR-/tmp}/kvm-remote.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T +TD="`basename "$T"`" resdir="$T/res" ds=`date +%Y.%m.%d-%H.%M.%S`-remote diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh index 1e29d656501b..c3808c490d92 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh @@ -13,9 +13,8 @@ # # Authors: Paul E. McKenney <[email protected]> -T=${TMPDIR-/tmp}/kvm-test-1-run-batch.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-test-1-run-batch.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T echo ---- Running batch $* # Check arguments diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-qemu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-qemu.sh index 44280582c594..76f24cd5825b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-qemu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run-qemu.sh @@ -17,9 +17,8 @@ # # Authors: Paul E. McKenney <[email protected]> -T=${TMPDIR-/tmp}/kvm-test-1-run-qemu.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-test-1-run-qemu.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T resdir="$1" if ! test -d "$resdir" @@ -109,7 +108,7 @@ do if test $kruntime -lt $seconds then echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1 - grep "^(qemu) qemu:" $resdir/kvm-test-1-run.sh.out >> $resdir/Warnings 2>&1 + grep "^(qemu) qemu:" $resdir/kvm-test-1-run*.sh.out >> $resdir/Warnings 2>&1 killpid="`sed -n "s/^(qemu) qemu: terminating on signal [0-9]* from pid \([0-9]*\).*$/\1/p" $resdir/Warnings`" if test -n "$killpid" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index f4c8055dbf7a..d2a3710a5f2a 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -25,9 +25,8 @@ # # Authors: Paul E. McKenney <[email protected]> -T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm-test-1-run.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T . functions.sh . $CONFIGFRAG/ver_functions.sh diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh index d40b4e60a50c..75a2610a27f3 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -3,10 +3,14 @@ # # Transform a qemu-cmd file to allow reuse. # -# Usage: kvm-transform.sh bzImage console.log jitter_dir [ seconds ] < qemu-cmd-in > qemu-cmd-out +# Usage: kvm-transform.sh bzImage console.log jitter_dir seconds [ bootargs ] < qemu-cmd-in > qemu-cmd-out # # bzImage: Kernel and initrd from the same prior kvm.sh run. # console.log: File into which to place console output. +# jitter_dir: Jitter directory for TORTURE_JITTER_START and +# TORTURE_JITTER_STOP environment variables. +# seconds: Run duaration for *.shutdown_secs module parameter. +# bootargs: New kernel boot parameters. Beware of Robert Tables. # # The original qemu-cmd file is provided on standard input. # The transformed qemu-cmd file is on standard output. @@ -17,6 +21,9 @@ # # Authors: Paul E. McKenney <[email protected]> +T=`mktemp -d /tmp/kvm-transform.sh.XXXXXXXXXX` +trap 'rm -rf $T' 0 2 + image="$1" if test -z "$image" then @@ -41,9 +48,17 @@ then echo "Invalid duration, should be numeric in seconds: '$seconds'" exit 1 fi +bootargs="$5" + +# Build awk program. +echo "BEGIN {" > $T/bootarg.awk +echo $bootargs | tr -s ' ' '\012' | + awk -v dq='"' '/./ { print "\tbootarg[" NR "] = " dq $1 dq ";" }' >> $T/bootarg.awk +echo $bootargs | tr -s ' ' '\012' | sed -e 's/=.*$//' | + awk -v dq='"' '/./ { print "\tbootpar[" NR "] = " dq $1 dq ";" }' >> $T/bootarg.awk +cat >> $T/bootarg.awk << '___EOF___' +} -awk -v image="$image" -v consolelog="$consolelog" -v jitter_dir="$jitter_dir" \ - -v seconds="$seconds" ' /^# seconds=/ { if (seconds == "") print $0; @@ -70,13 +85,7 @@ awk -v image="$image" -v consolelog="$consolelog" -v jitter_dir="$jitter_dir" \ { line = ""; for (i = 1; i <= NF; i++) { - if ("" seconds != "" && $i ~ /\.shutdown_secs=[0-9]*$/) { - sub(/[0-9]*$/, seconds, $i); - if (line == "") - line = $i; - else - line = line " " $i; - } else if (line == "") { + if (line == "") { line = $i; } else { line = line " " $i; @@ -87,7 +96,44 @@ awk -v image="$image" -v consolelog="$consolelog" -v jitter_dir="$jitter_dir" \ } else if ($i == "-kernel") { i++; line = line " " image; + } else if ($i == "-append") { + for (i++; i <= NF; i++) { + arg = $i; + lq = ""; + rq = ""; + if ("" seconds != "" && $i ~ /\.shutdown_secs=[0-9]*$/) + sub(/[0-9]*$/, seconds, arg); + if (arg ~ /^"/) { + lq = substr(arg, 1, 1); + arg = substr(arg, 2); + } + if (arg ~ /"$/) { + rq = substr(arg, length($i), 1); + arg = substr(arg, 1, length($i) - 1); + } + par = arg; + gsub(/=.*$/, "", par); + j = 1; + while (bootpar[j] != "") { + if (bootpar[j] == par) { + arg = ""; + break; + } + j++; + } + if (line == "") + line = lq arg; + else + line = line " " lq arg; + } + for (j in bootarg) + line = line " " bootarg[j]; + line = line rq; } } print line; -}' +} +___EOF___ + +awk -v image="$image" -v consolelog="$consolelog" -v jitter_dir="$jitter_dir" \ + -v seconds="$seconds" -f $T/bootarg.awk diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 6c734818a875..7710b1e1cdda 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -14,9 +14,8 @@ scriptname=$0 args="$*" -T=${TMPDIR-/tmp}/kvm.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/kvm.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T cd `dirname $scriptname`/../../../../../ diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 2dbfca3589b1..5a0b7ffcf047 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -15,9 +15,8 @@ F=$1 title=$2 -T=${TMPDIR-/tmp}/parse-build.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/parse-build.sh.XXXXXX`" trap 'rm -rf $T' 0 -mkdir $T . functions.sh diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index d477618e7261..130d0de4c3bb 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -206,9 +206,8 @@ ds="`date +%Y.%m.%d-%H.%M.%S`-torture" startdate="`date`" starttime="`get_starttime`" -T=/tmp/torture.sh.$$ +T="`mktemp -d ${TMPDIR-/tmp}/torture.sh.XXXXXX`" trap 'rm -rf $T' 0 2 -mkdir $T echo " --- " $scriptname $args | tee -a $T/log echo " --- Results directory: " $ds | tee -a $T/log @@ -278,6 +277,8 @@ function torture_one { then cat $T/$curflavor.out | tee -a $T/log echo retcode=$retcode | tee -a $T/log + else + echo $resdir > $T/last-resdir fi if test "$retcode" == 0 then @@ -303,10 +304,12 @@ function torture_set { shift curflavor=$flavor torture_one "$@" + mv $T/last-resdir $T/last-resdir-nodebug || : if test "$do_kasan" = "yes" then curflavor=${flavor}-kasan torture_one "$@" --kasan + mv $T/last-resdir $T/last-resdir-kasan || : fi if test "$do_kcsan" = "yes" then @@ -317,6 +320,7 @@ function torture_set { cur_kcsan_kmake_args="$kcsan_kmake_args" fi torture_one "$@" --kconfig "CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y" $kcsan_kmake_tag $cur_kcsan_kmake_args --kcsan + mv $T/last-resdir $T/last-resdir-kcsan || : fi } @@ -326,20 +330,34 @@ then echo " --- allmodconfig:" Start `date` | tee -a $T/log amcdir="tools/testing/selftests/rcutorture/res/$ds/allmodconfig" mkdir -p "$amcdir" - echo " --- make clean" > "$amcdir/Make.out" 2>&1 + echo " --- make clean" | tee $amcdir/log > "$amcdir/Make.out" 2>&1 make -j$MAKE_ALLOTED_CPUS clean >> "$amcdir/Make.out" 2>&1 - echo " --- make allmodconfig" >> "$amcdir/Make.out" 2>&1 - cp .config $amcdir - make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1 - echo " --- make " >> "$amcdir/Make.out" 2>&1 - make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1 - retcode="$?" - echo $retcode > "$amcdir/Make.exitcode" - if test "$retcode" == 0 + retcode=$? + buildphase='"make clean"' + if test "$retcode" -eq 0 + then + echo " --- make allmodconfig" | tee -a $amcdir/log >> "$amcdir/Make.out" 2>&1 + cp .config $amcdir + make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1 + retcode=$? + buildphase='"make allmodconfig"' + fi + if test "$retcode" -eq 0 + then + echo " --- make " | tee -a $amcdir/log >> "$amcdir/Make.out" 2>&1 + make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1 + retcode="$?" + echo $retcode > "$amcdir/Make.exitcode" + buildphase='"make"' + fi + if test "$retcode" -eq 0 then echo "allmodconfig($retcode)" $amcdir >> $T/successes + echo Success >> $amcdir/log else echo "allmodconfig($retcode)" $amcdir >> $T/failures + echo " --- allmodconfig Test summary:" >> $amcdir/log + echo " --- Summary: Exit code $retcode from $buildphase, see Make.out" >> $amcdir/log fi fi @@ -379,11 +397,48 @@ then else primlist= fi +firsttime=1 +do_kasan_save="$do_kasan" +do_kcsan_save="$do_kcsan" for prim in $primlist do - torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + if test -n "$firsttime" + then + torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : + if test -f "$T/last-resdir-kasan" + then + mv $T/last-resdir-kasan $T/first-resdir-kasan || : + fi + if test -f "$T/last-resdir-kcsan" + then + mv $T/last-resdir-kcsan $T/first-resdir-kcsan || : + fi + firsttime= + do_kasan= + do_kcsan= + else + torture_bootargs= + for i in $T/first-resdir-* + do + case "$i" in + *-nodebug) + torture_suffix= + ;; + *-kasan) + torture_suffix="-kasan" + ;; + *-kcsan) + torture_suffix="-kcsan" + ;; + esac + torture_set "refscale-$prim$torture_suffix" tools/testing/selftests/rcutorture/bin/kvm-again.sh "`cat "$i"`" --duration 5 --bootargs "refscale.scale_type=$prim" + done + fi done +do_kasan="$do_kasan_save" +do_kcsan="$do_kcsan_save" if test "$do_rcuscale" = yes then @@ -391,11 +446,48 @@ then else primlist= fi +firsttime=1 +do_kasan_save="$do_kasan" +do_kcsan_save="$do_kcsan" for prim in $primlist do - torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + if test -n "$firsttime" + then + torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : + if test -f "$T/last-resdir-kasan" + then + mv $T/last-resdir-kasan $T/first-resdir-kasan || : + fi + if test -f "$T/last-resdir-kcsan" + then + mv $T/last-resdir-kcsan $T/first-resdir-kcsan || : + fi + firsttime= + do_kasan= + do_kcsan= + else + torture_bootargs= + for i in $T/first-resdir-* + do + case "$i" in + *-nodebug) + torture_suffix= + ;; + *-kasan) + torture_suffix="-kasan" + ;; + *-kcsan) + torture_suffix="-kcsan" + ;; + esac + torture_set "rcuscale-$prim$torture_suffix" tools/testing/selftests/rcutorture/bin/kvm-again.sh "`cat "$i"`" --duration 5 --bootargs "rcuscale.scale_type=$prim" + done + fi done +do_kasan="$do_kasan_save" +do_kcsan="$do_kcsan_save" if test "$do_kvfree" = "yes" then @@ -458,7 +550,10 @@ if test -n "$tdir" && test $compress_concurrency -gt 0 then # KASAN vmlinux files can approach 1GB in size, so compress them. echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1 - find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo + find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo-all + find "$tdir" -type f -name 're-run' -print | sed -e 's,/re-run,,' | + grep -e '-k[ac]san$' > $T/xz-todo-copy + sort $T/xz-todo-all $T/xz-todo-copy | uniq -u > $T/xz-todo ncompresses=0 batchno=1 if test -s $T/xz-todo @@ -490,6 +585,24 @@ then echo Waiting for final batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log fi wait + if test -s $T/xz-todo-copy + then + # The trick here is that we need corresponding + # vmlinux files from corresponding scenarios. + echo Linking vmlinux.xz files to re-use scenarios `date` | tee -a "$tdir/log-xz" | tee -a $T/log + dirstash="`pwd`" + for i in `cat $T/xz-todo-copy` + do + cd $i + find . -name vmlinux -print > $T/xz-todo-copy-vmlinux + for v in `cat $T/xz-todo-copy-vmlinux` + do + rm -f "$v" + cp -l `cat $i/re-run`/"$i/$v".xz "`dirname "$v"`" + done + cd "$dirstash" + done + fi echo Size after compressing $n2compress files: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log echo Total duration `get_starttime_duration $starttime`. | tee -a $T/log else diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh index 26e193ffd2a2..873a892147e5 100644 --- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/vm/slabinfo-gnuplot.sh @@ -150,7 +150,7 @@ do_preprocess() let lines=3 out=`basename "$in"`"-slabs-by-loss" `cat "$in" | grep -A "$lines" 'Slabs sorted by loss' |\ - egrep -iv '\-\-|Name|Slabs'\ + grep -E -iv '\-\-|Name|Slabs'\ | awk '{print $1" "$4+$2*$3" "$4}' > "$out"` if [ $? -eq 0 ]; then do_slabs_plotting "$out" @@ -159,7 +159,7 @@ do_preprocess() let lines=3 out=`basename "$in"`"-slabs-by-size" `cat "$in" | grep -A "$lines" 'Slabs sorted by size' |\ - egrep -iv '\-\-|Name|Slabs'\ + grep -E -iv '\-\-|Name|Slabs'\ | awk '{print $1" "$4" "$4-$2*$3}' > "$out"` if [ $? -eq 0 ]; then do_slabs_plotting "$out" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 25d7872b29c1..fab4d3790578 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1198,8 +1198,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) goto out_err_no_arch_destroy_vm; } - kvm->max_halt_poll_ns = halt_poll_ns; - r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; @@ -3377,9 +3375,6 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > vcpu->kvm->max_halt_poll_ns) - val = vcpu->kvm->max_halt_poll_ns; - vcpu->halt_poll_ns = val; out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); @@ -3483,6 +3478,24 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, } } +static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (kvm->override_halt_poll_ns) { + /* + * Ensure kvm->max_halt_poll_ns is not read before + * kvm->override_halt_poll_ns. + * + * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. + */ + smp_rmb(); + return READ_ONCE(kvm->max_halt_poll_ns); + } + + return READ_ONCE(halt_poll_ns); +} + /* * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt * polling is enabled, busy wait for a short time before blocking to avoid the @@ -3491,12 +3504,18 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { + unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); - bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; bool waited = false; + bool do_halt_poll; u64 halt_ns; + if (vcpu->halt_poll_ns > max_halt_poll_ns) + vcpu->halt_poll_ns = max_halt_poll_ns; + + do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; + start = cur = poll_end = ktime_get(); if (do_halt_poll) { ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); @@ -3535,18 +3554,21 @@ out: update_halt_poll_stats(vcpu, start, poll_end, !waited); if (halt_poll_allowed) { + /* Recompute the max halt poll time in case it changed. */ + max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); + if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - } else if (vcpu->kvm->max_halt_poll_ns) { + } else if (max_halt_poll_ns) { if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && - halt_ns > vcpu->kvm->max_halt_poll_ns) + halt_ns > max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && - halt_ns < vcpu->kvm->max_halt_poll_ns) + else if (vcpu->halt_poll_ns < max_halt_poll_ns && + halt_ns < max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; @@ -4581,6 +4603,16 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, return -EINVAL; kvm->max_halt_poll_ns = cap->args[0]; + + /* + * Ensure kvm->override_halt_poll_ns does not become visible + * before kvm->max_halt_poll_ns. + * + * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). + */ + smp_wmb(); + kvm->override_halt_poll_ns = true; + return 0; } case KVM_CAP_DIRTY_LOG_RING: diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 346e47f15572..7c248193ca26 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -297,7 +297,12 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, if (!gpc->valid || old_uhva != gpc->uhva) { ret = hva_to_pfn_retry(kvm, gpc); } else { - /* If the HVA→PFN mapping was already valid, don't unmap it. */ + /* + * If the HVA→PFN mapping was already valid, don't unmap it. + * But do update gpc->khva because the offset within the page + * may have changed. + */ + gpc->khva = old_khva + page_offset; old_pfn = KVM_PFN_ERR_FAULT; old_khva = NULL; ret = 0; |