diff options
970 files changed, 15852 insertions, 7773 deletions
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index 273e654d7d08..2f0fcb2112d2 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -31,6 +31,14 @@ has lapsed, so this approach may be used in non-GPL software, if desired. (In contrast, implementation of RCU is permitted only in software licensed under either GPL or LGPL. Sorry!!!) +In 1987, Rashid et al. described lazy TLB-flush [RichardRashid87a]. +At first glance, this has nothing to do with RCU, but nevertheless +this paper helped inspire the update-side batching used in the later +RCU implementation in DYNIX/ptx. In 1988, Barbara Liskov published +a description of Argus that noted that use of out-of-date values can +be tolerated in some situations. Thus, this paper provides some early +theoretical justification for use of stale data. + In 1990, Pugh [Pugh90] noted that explicitly tracking which threads were reading a given data structure permitted deferred free to operate in the presence of non-terminating threads. However, this explicit @@ -41,11 +49,11 @@ providing a fine-grained locking design, however, it would be interesting to see how much of the performance advantage reported in 1990 remains today. -At about this same time, Adams [Adams91] described ``chaotic relaxation'', -where the normal barriers between successive iterations of convergent -numerical algorithms are relaxed, so that iteration $n$ might use -data from iteration $n-1$ or even $n-2$. This introduces error, -which typically slows convergence and thus increases the number of +At about this same time, Andrews [Andrews91textbook] described ``chaotic +relaxation'', where the normal barriers between successive iterations +of convergent numerical algorithms are relaxed, so that iteration $n$ +might use data from iteration $n-1$ or even $n-2$. This introduces +error, which typically slows convergence and thus increases the number of iterations required. However, this increase is sometimes more than made up for by a reduction in the number of expensive barrier operations, which are otherwise required to synchronize the threads at the end @@ -55,7 +63,8 @@ is thus inapplicable to most data structures in operating-system kernels. In 1992, Henry (now Alexia) Massalin completed a dissertation advising parallel programmers to defer processing when feasible to simplify -synchronization. RCU makes extremely heavy use of this advice. +synchronization [HMassalinPhD]. RCU makes extremely heavy use of +this advice. In 1993, Jacobson [Jacobson93] verbally described what is perhaps the simplest deferred-free technique: simply waiting a fixed amount of time @@ -90,27 +99,29 @@ mechanism, which is quite similar to RCU [Gamsa99]. These operating systems made pervasive use of RCU in place of "existence locks", which greatly simplifies locking hierarchies and helps avoid deadlocks. -2001 saw the first RCU presentation involving Linux [McKenney01a] -at OLS. The resulting abundance of RCU patches was presented the -following year [McKenney02a], and use of RCU in dcache was first -described that same year [Linder02a]. +The year 2000 saw an email exchange that would likely have +led to yet another independent invention of something like RCU +[RustyRussell2000a,RustyRussell2000b]. Instead, 2001 saw the first +RCU presentation involving Linux [McKenney01a] at OLS. The resulting +abundance of RCU patches was presented the following year [McKenney02a], +and use of RCU in dcache was first described that same year [Linder02a]. Also in 2002, Michael [Michael02b,Michael02a] presented "hazard-pointer" techniques that defer the destruction of data structures to simplify non-blocking synchronization (wait-free synchronization, lock-free synchronization, and obstruction-free synchronization are all examples of -non-blocking synchronization). In particular, this technique eliminates -locking, reduces contention, reduces memory latency for readers, and -parallelizes pipeline stalls and memory latency for writers. However, -these techniques still impose significant read-side overhead in the -form of memory barriers. Researchers at Sun worked along similar lines -in the same timeframe [HerlihyLM02]. These techniques can be thought -of as inside-out reference counts, where the count is represented by the -number of hazard pointers referencing a given data structure rather than -the more conventional counter field within the data structure itself. -The key advantage of inside-out reference counts is that they can be -stored in immortal variables, thus allowing races between access and -deletion to be avoided. +non-blocking synchronization). The corresponding journal article appeared +in 2004 [MagedMichael04a]. This technique eliminates locking, reduces +contention, reduces memory latency for readers, and parallelizes pipeline +stalls and memory latency for writers. However, these techniques still +impose significant read-side overhead in the form of memory barriers. +Researchers at Sun worked along similar lines in the same timeframe +[HerlihyLM02]. These techniques can be thought of as inside-out reference +counts, where the count is represented by the number of hazard pointers +referencing a given data structure rather than the more conventional +counter field within the data structure itself. The key advantage +of inside-out reference counts is that they can be stored in immortal +variables, thus allowing races between access and deletion to be avoided. By the same token, RCU can be thought of as a "bulk reference count", where some form of reference counter covers all reference by a given CPU @@ -123,8 +134,10 @@ can be thought of in other terms as well. In 2003, the K42 group described how RCU could be used to create hot-pluggable implementations of operating-system functions [Appavoo03a]. -Later that year saw a paper describing an RCU implementation of System -V IPC [Arcangeli03], and an introduction to RCU in Linux Journal +Later that year saw a paper describing an RCU implementation +of System V IPC [Arcangeli03] (following up on a suggestion by +Hugh Dickins [Dickins02a] and an implementation by Mingming Cao +[MingmingCao2002IPCRCU]), and an introduction to RCU in Linux Journal [McKenney03a]. 2004 has seen a Linux-Journal article on use of RCU in dcache @@ -383,6 +396,21 @@ for Programming Languages and Operating Systems}" } } +@phdthesis{HMassalinPhD +,author="H. Massalin" +,title="Synthesis: An Efficient Implementation of Fundamental Operating +System Services" +,school="Columbia University" +,address="New York, NY" +,year="1992" +,annotation={ + Mondo optimizing compiler. + Wait-free stuff. + Good advice: defer work to avoid synchronization. See page 90 + (PDF page 106), Section 5.4, fourth bullet point. +} +} + @unpublished{Jacobson93 ,author="Van Jacobson" ,title="Avoid Read-Side Locking Via Delayed Free" @@ -671,6 +699,20 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni" [Viewed October 18, 2004]" } +@conference{Michael02b +,author="Maged M. Michael" +,title="High Performance Dynamic Lock-Free Hash Tables and List-Based Sets" +,Year="2002" +,Month="August" +,booktitle="{Proceedings of the 14\textsuperscript{th} Annual ACM +Symposium on Parallel +Algorithms and Architecture}" +,pages="73-82" +,annotation={ +Like the title says... +} +} + @Conference{Linder02a ,Author="Hanna Linder and Dipankar Sarma and Maneesh Soni" ,Title="Scalability of the Directory Entry Cache" @@ -727,6 +769,24 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell" } } +@conference{Michael02a +,author="Maged M. Michael" +,title="Safe Memory Reclamation for Dynamic Lock-Free Objects Using Atomic +Reads and Writes" +,Year="2002" +,Month="August" +,booktitle="{Proceedings of the 21\textsuperscript{st} Annual ACM +Symposium on Principles of Distributed Computing}" +,pages="21-30" +,annotation={ + Each thread keeps an array of pointers to items that it is + currently referencing. Sort of an inside-out garbage collection + mechanism, but one that requires the accessing code to explicitly + state its needs. Also requires read-side memory barriers on + most architectures. +} +} + @unpublished{Dickins02a ,author="Hugh Dickins" ,title="Use RCU for System-V IPC" @@ -735,6 +795,17 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell" ,note="private communication" } +@InProceedings{HerlihyLM02 +,author={Maurice Herlihy and Victor Luchangco and Mark Moir} +,title="The Repeat Offender Problem: A Mechanism for Supporting Dynamic-Sized, +Lock-Free Data Structures" +,booktitle={Proceedings of 16\textsuperscript{th} International +Symposium on Distributed Computing} +,year=2002 +,month="October" +,pages="339-353" +} + @unpublished{Sarma02b ,Author="Dipankar Sarma" ,Title="Some dcache\_rcu benchmark numbers" @@ -749,6 +820,19 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell" } } +@unpublished{MingmingCao2002IPCRCU +,Author="Mingming Cao" +,Title="[PATCH]updated ipc lock patch" +,month="October" +,year="2002" +,note="Available: +\url{https://lkml.org/lkml/2002/10/24/262} +[Viewed February 15, 2014]" +,annotation={ + Mingming Cao's patch to introduce RCU to SysV IPC. +} +} + @unpublished{LinusTorvalds2003a ,Author="Linus Torvalds" ,Title="Re: {[PATCH]} small fixes in brlock.h" @@ -982,6 +1066,23 @@ Realtime Applications" } } +@article{MagedMichael04a +,author="Maged M. Michael" +,title="Hazard Pointers: Safe Memory Reclamation for Lock-Free Objects" +,Year="2004" +,Month="June" +,journal="IEEE Transactions on Parallel and Distributed Systems" +,volume="15" +,number="6" +,pages="491-504" +,url="Available: +\url{http://www.research.ibm.com/people/m/michael/ieeetpds-2004.pdf} +[Viewed March 1, 2005]" +,annotation={ + New canonical hazard-pointer citation. +} +} + @phdthesis{PaulEdwardMcKenneyPhD ,author="Paul E. McKenney" ,title="Exploiting Deferred Destruction: diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 91266193b8f4..9d10d1db16a5 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -256,10 +256,10 @@ over a rather long period of time, but improvements are always welcome! variations on this theme. b. Limiting update rate. For example, if updates occur only - once per hour, then no explicit rate limiting is required, - unless your system is already badly broken. The dcache - subsystem takes this approach -- updates are guarded - by a global lock, limiting their rate. + once per hour, then no explicit rate limiting is + required, unless your system is already badly broken. + Older versions of the dcache subsystem take this approach, + guarding updates with a global lock, limiting their rate. c. Trusted update -- if updates can only be done manually by superuser or some other trusted user, then it might not @@ -268,7 +268,8 @@ over a rather long period of time, but improvements are always welcome! the machine. d. Use call_rcu_bh() rather than call_rcu(), in order to take - advantage of call_rcu_bh()'s faster grace periods. + advantage of call_rcu_bh()'s faster grace periods. (This + is only a partial solution, though.) e. Periodically invoke synchronize_rcu(), permitting a limited number of updates per grace period. @@ -276,6 +277,13 @@ over a rather long period of time, but improvements are always welcome! The same cautions apply to call_rcu_bh(), call_rcu_sched(), call_srcu(), and kfree_rcu(). + 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. + 9. All RCU list-traversal primitives, which include rcu_dereference(), list_for_each_entry_rcu(), and list_for_each_safe_rcu(), must be either within an RCU read-side diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt index e6b72d355151..68c0f517c60e 100644 --- a/Documentation/device-mapper/cache.txt +++ b/Documentation/device-mapper/cache.txt @@ -124,12 +124,11 @@ the default being 204800 sectors (or 100MB). Updating on-disk metadata ------------------------- -On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is -written. If no such requests are made then commits will occur every -second. This means the cache behaves like a physical disk that has a -write cache (the same is true of the thin-provisioning target). If -power is lost you may lose some recent writes. The metadata should -always be consistent in spite of any crash. +On-disk metadata is committed every time a FLUSH or FUA bio is written. +If no such requests are made then commits will occur every second. This +means the cache behaves like a physical disk that has a volatile write +cache. If power is lost you may lose some recent writes. The metadata +should always be consistent in spite of any crash. The 'dirty' state for a cache block changes far too frequently for us to keep updating it on the fly. So we treat it as a hint. In normal diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt index 8a7a3d46e0da..05a27e9442bd 100644 --- a/Documentation/device-mapper/thin-provisioning.txt +++ b/Documentation/device-mapper/thin-provisioning.txt @@ -116,6 +116,35 @@ Resuming a device with a new table itself triggers an event so the userspace daemon can use this to detect a situation where a new table already exceeds the threshold. +A low water mark for the metadata device is maintained in the kernel and +will trigger a dm event if free space on the metadata device drops below +it. + +Updating on-disk metadata +------------------------- + +On-disk metadata is committed every time a FLUSH or FUA bio is written. +If no such requests are made then commits will occur every second. This +means the thin-provisioning target behaves like a physical disk that has +a volatile write cache. If power is lost you may lose some recent +writes. The metadata should always be consistent in spite of any crash. + +If data space is exhausted the pool will either error or queue IO +according to the configuration (see: error_if_no_space). If metadata +space is exhausted or a metadata operation fails: the pool will error IO +until the pool is taken offline and repair is performed to 1) fix any +potential inconsistencies and 2) clear the flag that imposes repair. +Once the pool's metadata device is repaired it may be resized, which +will allow the pool to return to normal operation. Note that if a pool +is flagged as needing repair, the pool's data and metadata devices +cannot be resized until repair is performed. It should also be noted +that when the pool's metadata space is exhausted the current metadata +transaction is aborted. Given that the pool will cache IO whose +completion may have already been acknowledged to upper IO layers +(e.g. filesystem) it is strongly suggested that consistency checks +(e.g. fsck) be performed on those layers when repair of the pool is +required. + Thin provisioning ----------------- @@ -258,10 +287,9 @@ ii) Status should register for the event and then check the target's status. held metadata root: - The location, in sectors, of the metadata root that has been + The location, in blocks, of the metadata root that has been 'held' for userspace read access. '-' indicates there is no - held root. This feature is not yet implemented so '-' is - always returned. + held root. discard_passdown|no_discard_passdown Whether or not discards are actually being passed down to the diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt index a6a352c2771e..5992dceec7af 100644 --- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt +++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt @@ -21,9 +21,9 @@ Required Properties: must appear in the same order as the output clocks. - #clock-cells: Must be 1 - clock-output-names: The name of the clocks as free-form strings - - renesas,indices: Indices of the gate clocks into the group (0 to 31) + - renesas,clock-indices: Indices of the gate clocks into the group (0 to 31) -The clocks, clock-output-names and renesas,indices properties contain one +The clocks, clock-output-names and renesas,clock-indices properties contain one entry per gate clock. The MSTP groups are sparsely populated. Unimplemented gate clocks must not be declared. diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt index 11ace3c3d805..4fc392763611 100644 --- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt +++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt @@ -7,3 +7,4 @@ Required properties: Optional properties: - local-mac-address : Ethernet mac address to use +- vdd-supply: supply for Ethernet mac diff --git a/Documentation/devicetree/bindings/net/opencores-ethoc.txt b/Documentation/devicetree/bindings/net/opencores-ethoc.txt new file mode 100644 index 000000000000..2dc127c30d9b --- /dev/null +++ b/Documentation/devicetree/bindings/net/opencores-ethoc.txt @@ -0,0 +1,22 @@ +* OpenCores MAC 10/100 Mbps + +Required properties: +- compatible: Should be "opencores,ethoc". +- reg: two memory regions (address and length), + first region is for the device registers and descriptor rings, + second is for the device packet memory. +- interrupts: interrupt for the device. + +Optional properties: +- clocks: phandle to refer to the clk used as per + Documentation/devicetree/bindings/clock/clock-bindings.txt + +Examples: + + enet0: ethoc@fd030000 { + compatible = "opencores,ethoc"; + reg = <0xfd030000 0x4000 0xfd800000 0x4000>; + interrupts = <1>; + local-mac-address = [00 50 c2 13 6f 00]; + clocks = <&osc>; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt index 9e9e9ef9f852..c119debe6bab 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt @@ -1,4 +1,4 @@ -Broadcom Capri Pin Controller +Broadcom BCM281xx Pin Controller This is a pin controller for the Broadcom BCM281xx SoC family, which includes BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs. @@ -7,14 +7,14 @@ BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs. Required Properties: -- compatible: Must be "brcm,capri-pinctrl". +- compatible: Must be "brcm,bcm11351-pinctrl" - reg: Base address of the PAD Controller register block and the size of the block. For example, the following is the bare minimum node: pinctrl@35004800 { - compatible = "brcm,capri-pinctrl"; + compatible = "brcm,bcm11351-pinctrl"; reg = <0x35004800 0x430>; }; @@ -119,7 +119,7 @@ Optional Properties (for HDMI pins): Example: // pin controller node pinctrl@35004800 { - compatible = "brcm,capri-pinctrl"; + compatible = "brcmbcm11351-pinctrl"; reg = <0x35004800 0x430>; // pin configuration node diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 7116fda7077f..67755ea834a7 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1011,6 +1011,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. parameter will force ia64_sal_cache_flush to call ia64_pal_cache_flush instead of SAL_CACHE_FLUSH. + forcepae [X86-32] + Forcefully enable Physical Address Extension (PAE). + Many Pentium M systems disable PAE but may have a + functionally usable PAE implementation. + Warning: use of this parameter will taint the kernel + and may cause unknown problems. + ftrace=[tracer] [FTRACE] will set and start the specified tracer as early as possible in order to facilitate early @@ -2053,8 +2060,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. IOAPICs that may be present in the system. nokaslr [X86] - Disable kernel base offset ASLR (Address Space - Layout Randomization) if built into the kernel. + Disable kernel and module base offset ASLR (Address + Space Layout Randomization) if built into the kernel. noautogroup Disable scheduler automatic task group creation. diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt index 827104fb9364..f3cd299fcc41 100644 --- a/Documentation/kernel-per-CPU-kthreads.txt +++ b/Documentation/kernel-per-CPU-kthreads.txt @@ -162,7 +162,18 @@ Purpose: Execute workqueue requests To reduce its OS jitter, do any of the following: 1. Run your workload at a real-time priority, which will allow preempting the kworker daemons. -2. Do any of the following needed to avoid jitter that your +2. A given workqueue can be made visible in the sysfs filesystem + by passing the WQ_SYSFS to that workqueue's alloc_workqueue(). + Such a workqueue can be confined to a given subset of the + CPUs using the /sys/devices/virtual/workqueue/*/cpumask sysfs + files. The set of WQ_SYSFS workqueues can be displayed using + "ls sys/devices/virtual/workqueue". That said, the workqueues + maintainer would like to caution people against indiscriminately + sprinkling WQ_SYSFS across all the workqueues. The reason for + caution is that it is easy to add WQ_SYSFS, but because sysfs is + part of the formal user/kernel API, it can be nearly impossible + to remove it, even if its addition was a mistake. +3. Do any of the following needed to avoid jitter that your application cannot tolerate: a. Build your kernel with CONFIG_SLUB=y rather than CONFIG_SLAB=y, thus avoiding the slab allocator's periodic diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 102dc19c4119..11c1d2049662 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -608,26 +608,30 @@ as follows: b = p; /* BUG: Compiler can reorder!!! */ do_something(); -The solution is again ACCESS_ONCE(), which preserves the ordering between -the load from variable 'a' and the store to variable 'b': +The solution is again ACCESS_ONCE() and barrier(), which preserves the +ordering between the load from variable 'a' and the store to variable 'b': q = ACCESS_ONCE(a); if (q) { + barrier(); ACCESS_ONCE(b) = p; do_something(); } else { + barrier(); ACCESS_ONCE(b) = p; do_something_else(); } -You could also use barrier() to prevent the compiler from moving -the stores to variable 'b', but barrier() would not prevent the -compiler from proving to itself that a==1 always, so ACCESS_ONCE() -is also needed. +The initial ACCESS_ONCE() is required to prevent the compiler from +proving the value of 'a', and the pair of barrier() invocations are +required to prevent the compiler from pulling the two identical stores +to 'b' out from the legs of the "if" statement. It is important to note that control dependencies absolutely require a a conditional. For example, the following "optimized" version of -the above example breaks ordering: +the above example breaks ordering, which is why the barrier() invocations +are absolutely required if you have identical stores in both legs of +the "if" statement: q = ACCESS_ONCE(a); ACCESS_ONCE(b) = p; /* BUG: No ordering vs. load from a!!! */ @@ -643,9 +647,11 @@ It is of course legal for the prior load to be part of the conditional, for example, as follows: if (ACCESS_ONCE(a) > 0) { + barrier(); ACCESS_ONCE(b) = q / 2; do_something(); } else { + barrier(); ACCESS_ONCE(b) = q / 3; do_something_else(); } @@ -659,9 +665,11 @@ the needed conditional. For example: q = ACCESS_ONCE(a); if (q % MAX) { + barrier(); ACCESS_ONCE(b) = p; do_something(); } else { + barrier(); ACCESS_ONCE(b) = p; do_something_else(); } @@ -723,8 +731,13 @@ In summary: use smb_rmb(), smp_wmb(), or, in the case of prior stores and later loads, smp_mb(). + (*) If both legs of the "if" statement begin with identical stores + to the same variable, a barrier() statement is required at the + beginning of each leg of the "if" statement. + (*) Control dependencies require at least one run-time conditional - between the prior load and the subsequent store. If the compiler + between the prior load and the subsequent store, and this + conditional must involve the prior load. If the compiler is able to optimize the conditional away, it will have also optimized away the ordering. Careful use of ACCESS_ONCE() can help to preserve the needed conditional. @@ -1249,6 +1262,23 @@ The ACCESS_ONCE() function can prevent any number of optimizations that, while perfectly safe in single-threaded code, can be fatal in concurrent code. Here are some examples of these sorts of optimizations: + (*) The compiler is within its rights to reorder loads and stores + to the same variable, and in some cases, the CPU is within its + rights to reorder loads to the same variable. This means that + the following code: + + a[0] = x; + a[1] = x; + + Might result in an older value of x stored in a[1] than in a[0]. + Prevent both the compiler and the CPU from doing this as follows: + + a[0] = ACCESS_ONCE(x); + a[1] = ACCESS_ONCE(x); + + In short, ACCESS_ONCE() provides cache coherence for accesses from + multiple CPUs to a single variable. + (*) The compiler is within its rights to merge successive loads from the same variable. Such merging can cause the compiler to "optimize" the following code: @@ -1644,12 +1674,12 @@ for each construct. These operations all imply certain barriers: Memory operations issued after the ACQUIRE will be completed after the ACQUIRE operation has completed. - Memory operations issued before the ACQUIRE may be completed after the - ACQUIRE operation has completed. An smp_mb__before_spinlock(), combined - with a following ACQUIRE, orders prior loads against subsequent stores and - stores and prior stores against subsequent stores. Note that this is - weaker than smp_mb()! The smp_mb__before_spinlock() primitive is free on - many architectures. + Memory operations issued before the ACQUIRE may be completed after + the ACQUIRE operation has completed. An smp_mb__before_spinlock(), + combined with a following ACQUIRE, orders prior loads against + subsequent loads and stores and also orders prior stores against + subsequent stores. Note that this is weaker than smp_mb()! The + smp_mb__before_spinlock() primitive is free on many architectures. (2) RELEASE operation implication: @@ -1694,24 +1724,21 @@ may occur as: ACQUIRE M, STORE *B, STORE *A, RELEASE M -This same reordering can of course occur if the lock's ACQUIRE and RELEASE are -to the same lock variable, but only from the perspective of another CPU not -holding that lock. - -In short, a RELEASE followed by an ACQUIRE may -not- be assumed to be a full -memory barrier because it is possible for a preceding RELEASE to pass a -later ACQUIRE from the viewpoint of the CPU, but not from the viewpoint -of the compiler. Note that deadlocks cannot be introduced by this -interchange because if such a deadlock threatened, the RELEASE would -simply complete. - -If it is necessary for a RELEASE-ACQUIRE pair to produce a full barrier, the -ACQUIRE can be followed by an smp_mb__after_unlock_lock() invocation. This -will produce a full barrier if either (a) the RELEASE and the ACQUIRE are -executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on the -same variable. The smp_mb__after_unlock_lock() primitive is free on many -architectures. Without smp_mb__after_unlock_lock(), the critical sections -corresponding to the RELEASE and the ACQUIRE can cross: +When the ACQUIRE and RELEASE are a lock acquisition and release, +respectively, this same reordering can occur if the lock's ACQUIRE and +RELEASE are to the same lock variable, but only from the perspective of +another CPU not holding that lock. In short, a ACQUIRE followed by an +RELEASE may -not- be assumed to be a full memory barrier. + +Similarly, the reverse case of a RELEASE followed by an ACQUIRE does not +imply a full memory barrier. If it is necessary for a RELEASE-ACQUIRE +pair to produce a full barrier, the ACQUIRE can be followed by an +smp_mb__after_unlock_lock() invocation. This will produce a full barrier +if either (a) the RELEASE and the ACQUIRE are executed by the same +CPU or task, or (b) the RELEASE and ACQUIRE act on the same variable. +The smp_mb__after_unlock_lock() primitive is free on many architectures. +Without smp_mb__after_unlock_lock(), the CPU's execution of the critical +sections corresponding to the RELEASE and the ACQUIRE can cross, so that: *A = a; RELEASE M @@ -1722,7 +1749,36 @@ could occur as: ACQUIRE N, STORE *B, STORE *A, RELEASE M -With smp_mb__after_unlock_lock(), they cannot, so that: +It might appear that this reordering could introduce a deadlock. +However, this cannot happen because if such a deadlock threatened, +the RELEASE would simply complete, thereby avoiding the deadlock. + + Why does this work? + + One key point is that we are only talking about the CPU doing + the reordering, not the compiler. If the compiler (or, for + that matter, the developer) switched the operations, deadlock + -could- occur. + + But suppose the CPU reordered the operations. In this case, + the unlock precedes the lock in the assembly code. The CPU + simply elected to try executing the later lock operation first. + If there is a deadlock, this lock operation will simply spin (or + try to sleep, but more on that later). The CPU will eventually + execute the unlock operation (which preceded the lock operation + in the assembly code), which will unravel the potential deadlock, + allowing the lock operation to succeed. + + But what if the lock is a sleeplock? In that case, the code will + try to enter the scheduler, where it will eventually encounter + a memory barrier, which will force the earlier unlock operation + to complete, again unraveling the deadlock. There might be + a sleep-unlock race, but the locking primitive needs to resolve + such races properly in any case. + +With smp_mb__after_unlock_lock(), the two critical sections cannot overlap. +For example, with the following code, the store to *A will always be +seen by other CPUs before the store to *B: *A = a; RELEASE M @@ -1730,13 +1786,18 @@ With smp_mb__after_unlock_lock(), they cannot, so that: smp_mb__after_unlock_lock(); *B = b; -will always occur as either of the following: +The operations will always occur in one of the following orders: - STORE *A, RELEASE, ACQUIRE, STORE *B - STORE *A, ACQUIRE, RELEASE, STORE *B + STORE *A, RELEASE, ACQUIRE, smp_mb__after_unlock_lock(), STORE *B + STORE *A, ACQUIRE, RELEASE, smp_mb__after_unlock_lock(), STORE *B + ACQUIRE, STORE *A, RELEASE, smp_mb__after_unlock_lock(), STORE *B If the RELEASE and ACQUIRE were instead both operating on the same lock -variable, only the first of these two alternatives can occur. +variable, only the first of these alternatives can occur. In addition, +the more strongly ordered systems may rule out some of the above orders. +But in any case, as noted earlier, the smp_mb__after_unlock_lock() +ensures that the store to *A will always be seen as happening before +the store to *B. Locks and semaphores may not provide any guarantee of ordering on UP compiled systems, and so cannot be counted on in such a situation to actually achieve @@ -2757,7 +2818,7 @@ in that order, but, without intervention, the sequence may have almost any combination of elements combined or discarded, provided the program's view of the world remains consistent. Note that ACCESS_ONCE() is -not- optional in the above example, as there are architectures where a given CPU might -interchange successive loads to the same location. On such architectures, +reorder successive loads to the same location. On such architectures, ACCESS_ONCE() does whatever is necessary to prevent this, for example, on Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the special ld.acq and st.rel instructions that prevent such reordering. diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index f3089d423515..0cbe6ec22d6f 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -554,12 +554,6 @@ solution for a couple of reasons: not specified in the struct can_frame and therefore it is only valid in CANFD_MTU sized CAN FD frames. - As long as the payload length is <=8 the received CAN frames from CAN FD - capable CAN devices can be received and read by legacy sockets too. When - user-generated CAN FD frames have a payload length <=8 these can be send - by legacy CAN network interfaces too. Sending CAN FD frames with payload - length > 8 to a legacy CAN network interface returns an -EMSGSIZE error. - Implementation hint for new CAN applications: To build a CAN FD aware application use struct canfd_frame as basic CAN diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt index b26122973525..c6af4bac5aa8 100644 --- a/Documentation/networking/netlink_mmap.txt +++ b/Documentation/networking/netlink_mmap.txt @@ -226,9 +226,9 @@ Ring setup: void *rx_ring, *tx_ring; /* Configure ring parameters */ - if (setsockopt(fd, NETLINK_RX_RING, &req, sizeof(req)) < 0) + if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0) exit(1); - if (setsockopt(fd, NETLINK_TX_RING, &req, sizeof(req)) < 0) + if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0) exit(1) /* Calculate size of each individual ring */ diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 1404674c0a02..6fea79efb4cb 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -453,7 +453,7 @@ TP_STATUS_COPY : This flag indicates that the frame (and associated enabled previously with setsockopt() and the PACKET_COPY_THRESH option. - The number of frames than can be buffered to + The number of frames that can be buffered to be read with recvfrom is limited like a normal socket. See the SO_RCVBUF option in the socket (7) man page. diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 661d3c316a17..048c92b487f6 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -21,26 +21,38 @@ has such a feature). SO_TIMESTAMPING: -Instructs the socket layer which kind of information is wanted. The -parameter is an integer with some of the following bits set. Setting -other bits is an error and doesn't change the current state. - -SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamp in hardware -SOF_TIMESTAMPING_TX_SOFTWARE: if SOF_TIMESTAMPING_TX_HARDWARE is off or - fails, then do it in software -SOF_TIMESTAMPING_RX_HARDWARE: return the original, unmodified time stamp - as generated by the hardware -SOF_TIMESTAMPING_RX_SOFTWARE: if SOF_TIMESTAMPING_RX_HARDWARE is off or - fails, then do it in software -SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp -SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to - the system time base -SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in - software - -SOF_TIMESTAMPING_TX/RX determine how time stamps are generated. -SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the -following control message: +Instructs the socket layer which kind of information should be collected +and/or reported. The parameter is an integer with some of the following +bits set. Setting other bits is an error and doesn't change the current +state. + +Four of the bits are requests to the stack to try to generate +timestamps. Any combination of them is valid. + +SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamps in hardware +SOF_TIMESTAMPING_TX_SOFTWARE: try to obtain send time stamps in software +SOF_TIMESTAMPING_RX_HARDWARE: try to obtain receive time stamps in hardware +SOF_TIMESTAMPING_RX_SOFTWARE: try to obtain receive time stamps in software + +The other three bits control which timestamps will be reported in a +generated control message. If none of these bits are set or if none of +the set bits correspond to data that is available, then the control +message will not be generated: + +SOF_TIMESTAMPING_SOFTWARE: report systime if available +SOF_TIMESTAMPING_SYS_HARDWARE: report hwtimetrans if available +SOF_TIMESTAMPING_RAW_HARDWARE: report hwtimeraw if available + +It is worth noting that timestamps may be collected for reasons other +than being requested by a particular socket with +SOF_TIMESTAMPING_[TR]X_(HARD|SOFT)WARE. For example, most drivers that +can generate hardware receive timestamps ignore +SOF_TIMESTAMPING_RX_HARDWARE. It is still a good idea to set that flag +in case future drivers pay attention. + +If timestamps are reported, they will appear in a control message with +cmsg_level==SOL_SOCKET, cmsg_type==SO_TIMESTAMPING, and a payload like +this: struct scm_timestamping { struct timespec systime; diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index e55124e7c40c..ec8be46bf48d 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -320,10 +320,11 @@ This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. ============================================================== -hung_task_warning: +hung_task_warnings: The maximum number of warnings to report. During a check interval -When this value is reached, no more the warnings will be reported. +if a hung task is detected, this value is decreased by 1. +When this value reaches 0, no more warnings will be reported. This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. -1: report an infinite number of warnings. @@ -441,8 +442,7 @@ feature should be disabled. Otherwise, if the system overhead from the feature is too high then the rate the kernel samples for NUMA hinting faults may be controlled by the numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, -numa_balancing_scan_size_mb, numa_balancing_settle_count sysctls and -numa_balancing_migrate_deferred. +numa_balancing_scan_size_mb, and numa_balancing_settle_count sysctls. ============================================================== @@ -483,13 +483,6 @@ rate for each task. numa_balancing_scan_size_mb is how many megabytes worth of pages are scanned for a given scan. -numa_balancing_migrate_deferred is how many page migrations get skipped -unconditionally, after a page migration is skipped because a page is shared -with other tasks. This reduces page migration overhead, and determines -how much stronger the "move task near its memory" policy scheduler becomes, -versus the "move memory near its task" memory management policy, for workloads -with shared memory. - ============================================================== osrelease, ostype & version: diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index cb81741d3b0b..a75e3adaa39d 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -182,7 +182,7 @@ Offset Proto Name Meaning 0226/1 2.02+(3 ext_loader_ver Extended boot loader version 0227/1 2.02+(3 ext_loader_type Extended boot loader ID 0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line -022C/4 2.03+ ramdisk_max Highest legal initrd address +022C/4 2.03+ initrd_addr_max Highest legal initrd address 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not 0235/1 2.10+ min_alignment Minimum alignment, as a power of two @@ -534,7 +534,7 @@ Protocol: 2.02+ zero, the kernel will assume that your boot loader does not support the 2.02+ protocol. -Field name: ramdisk_max +Field name: initrd_addr_max Type: read Offset/size: 0x22c/4 Protocol: 2.03+ diff --git a/MAINTAINERS b/MAINTAINERS index c6d0e93eff62..900d98eec2fc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -73,7 +73,8 @@ Descriptions of section entries: L: Mailing list that is relevant to this area W: Web-page with status/info Q: Patchwork web based patch tracking system site - T: SCM tree type and location. Type is one of: git, hg, quilt, stgit, topgit. + T: SCM tree type and location. + Type is one of: git, hg, quilt, stgit, topgit S: Status, one of the following: Supported: Someone is actually paid to look after this. Maintained: Someone actually looks after it. @@ -473,7 +474,7 @@ F: net/rxrpc/af_rxrpc.c AGPGART DRIVER M: David Airlie <airlied@linux.ie> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git +T: git git://people.freedesktop.org/~airlied/linux (part of drm maint) S: Maintained F: drivers/char/agp/ F: include/linux/agp* @@ -910,11 +911,11 @@ F: arch/arm/include/asm/hardware/dec21285.h F: arch/arm/mach-footbridge/ ARM/FREESCALE IMX / MXC ARM ARCHITECTURE -M: Shawn Guo <shawn.guo@linaro.org> +M: Shawn Guo <shawn.guo@freescale.com> M: Sascha Hauer <kernel@pengutronix.de> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.linaro.org/people/shawnguo/linux-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git F: arch/arm/mach-imx/ F: arch/arm/boot/dts/imx* F: arch/arm/configs/imx*_defconfig @@ -1612,11 +1613,11 @@ S: Maintained F: drivers/net/wireless/atmel* ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER -M: Bradley Grove <linuxdrivers@attotech.com> -L: linux-scsi@vger.kernel.org -W: http://www.attotech.com -S: Supported -F: drivers/scsi/esas2r +M: Bradley Grove <linuxdrivers@attotech.com> +L: linux-scsi@vger.kernel.org +W: http://www.attotech.com +S: Supported +F: drivers/scsi/esas2r AUDIT SUBSYSTEM M: Eric Paris <eparis@redhat.com> @@ -1737,6 +1738,7 @@ F: include/uapi/linux/bfs_fs.h BLACKFIN ARCHITECTURE M: Steven Miao <realmz6@gmail.com> L: adi-buildroot-devel@lists.sourceforge.net +T: git git://git.code.sf.net/p/adi-linux/code W: http://blackfin.uclinux.org S: Supported F: arch/blackfin/ @@ -1830,8 +1832,8 @@ F: net/bluetooth/ F: include/net/bluetooth/ BONDING DRIVER -M: Jay Vosburgh <fubar@us.ibm.com> -M: Veaceslav Falico <vfalico@redhat.com> +M: Jay Vosburgh <j.vosburgh@gmail.com> +M: Veaceslav Falico <vfalico@gmail.com> M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org W: http://sourceforge.net/projects/bonding/ @@ -2159,7 +2161,7 @@ F: Documentation/zh_CN/ CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER M: Peter Chen <Peter.Chen@freescale.com> -T: git://github.com/hzpeterchen/linux-usb.git +T: git git://github.com/hzpeterchen/linux-usb.git L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/chipidea/ @@ -2179,9 +2181,9 @@ S: Supported F: drivers/net/ethernet/cisco/enic/ CISCO VIC LOW LATENCY NIC DRIVER -M: Upinder Malhi <umalhi@cisco.com> -S: Supported -F: drivers/infiniband/hw/usnic +M: Upinder Malhi <umalhi@cisco.com> +S: Supported +F: drivers/infiniband/hw/usnic CIRRUS LOGIC EP93XX ETHERNET DRIVER M: Hartley Sweeten <hsweeten@visionengravers.com> @@ -2378,20 +2380,20 @@ F: drivers/cpufreq/arm_big_little.c F: drivers/cpufreq/arm_big_little_dt.c CPUIDLE DRIVER - ARM BIG LITTLE -M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> -M: Daniel Lezcano <daniel.lezcano@linaro.org> -L: linux-pm@vger.kernel.org -L: linux-arm-kernel@lists.infradead.org -T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git -S: Maintained -F: drivers/cpuidle/cpuidle-big_little.c +M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> +M: Daniel Lezcano <daniel.lezcano@linaro.org> +L: linux-pm@vger.kernel.org +L: linux-arm-kernel@lists.infradead.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git +S: Maintained +F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVERS M: Rafael J. Wysocki <rjw@rjwysocki.net> M: Daniel Lezcano <daniel.lezcano@linaro.org> L: linux-pm@vger.kernel.org S: Maintained -T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git F: drivers/cpuidle/* F: include/linux/cpuidle.h @@ -2458,9 +2460,9 @@ S: Maintained F: sound/pci/cs5535audio/ CW1200 WLAN driver -M: Solomon Peachy <pizza@shaftnet.org> -S: Maintained -F: drivers/net/wireless/cw1200/ +M: Solomon Peachy <pizza@shaftnet.org> +S: Maintained +F: drivers/net/wireless/cw1200/ CX18 VIDEO4LINUX DRIVER M: Andy Walls <awalls@md.metrocast.net> @@ -2799,9 +2801,9 @@ S: Supported F: drivers/acpi/dock.c DOCUMENTATION -M: Rob Landley <rob@landley.net> +M: Randy Dunlap <rdunlap@infradead.org> L: linux-doc@vger.kernel.org -T: TBD +T: quilt http://www.infradead.org/~rdunlap/Doc/patches/ S: Maintained F: Documentation/ @@ -3095,6 +3097,8 @@ F: fs/ecryptfs/ EDAC-CORE M: Doug Thompson <dougthompson@xmission.com> +M: Borislav Petkov <bp@alien8.de> +M: Mauro Carvalho Chehab <m.chehab@samsung.com> L: linux-edac@vger.kernel.org W: bluesmoke.sourceforge.net S: Supported @@ -4541,6 +4545,7 @@ M: Greg Rose <gregory.v.rose@intel.com> M: Alex Duyck <alexander.h.duyck@intel.com> M: John Ronciak <john.ronciak@intel.com> M: Mitch Williams <mitch.a.williams@intel.com> +M: Linux NICS <linux.nics@intel.com> L: e1000-devel@lists.sourceforge.net W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ @@ -4558,6 +4563,7 @@ F: Documentation/networking/ixgbevf.txt F: Documentation/networking/i40e.txt F: Documentation/networking/i40evf.txt F: drivers/net/ethernet/intel/ +F: drivers/net/ethernet/intel/*/ INTEL-MID GPIO DRIVER M: David Cohen <david.a.cohen@linux.intel.com> @@ -4914,7 +4920,7 @@ F: drivers/staging/ktap/ KCONFIG M: "Yann E. MORIN" <yann.morin.1998@free.fr> L: linux-kbuild@vger.kernel.org -T: git://gitorious.org/linux-kconfig/linux-kconfig +T: git git://gitorious.org/linux-kconfig/linux-kconfig S: Maintained F: Documentation/kbuild/kconfig-language.txt F: scripts/kconfig/ @@ -5471,11 +5477,11 @@ S: Maintained F: drivers/media/tuners/m88ts2022* MA901 MASTERKIT USB FM RADIO DRIVER -M: Alexey Klimov <klimov.linux@gmail.com> -L: linux-media@vger.kernel.org -T: git git://linuxtv.org/media_tree.git -S: Maintained -F: drivers/media/radio/radio-ma901.c +M: Alexey Klimov <klimov.linux@gmail.com> +L: linux-media@vger.kernel.org +T: git git://linuxtv.org/media_tree.git +S: Maintained +F: drivers/media/radio/radio-ma901.c MAC80211 M: Johannes Berg <johannes@sipsolutions.net> @@ -5636,7 +5642,7 @@ F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) M: Amir Vadai <amirv@mellanox.com> -L: netdev@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ @@ -5677,7 +5683,7 @@ F: include/linux/mtd/ F: include/uapi/mtd/ MEN A21 WATCHDOG DRIVER -M: Johannes Thumshirn <johannes.thumshirn@men.de> +M: Johannes Thumshirn <johannes.thumshirn@men.de> L: linux-watchdog@vger.kernel.org S: Supported F: drivers/watchdog/mena21_wdt.c @@ -5733,20 +5739,20 @@ L: linux-rdma@vger.kernel.org W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ -T: git://openfabrics.org/~eli/connect-ib.git +T: git git://openfabrics.org/~eli/connect-ib.git S: Supported F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ Mellanox MLX5 IB driver -M: Eli Cohen <eli@mellanox.com> -L: linux-rdma@vger.kernel.org -W: http://www.mellanox.com -Q: http://patchwork.kernel.org/project/linux-rdma/list/ -T: git://openfabrics.org/~eli/connect-ib.git -S: Supported -F: include/linux/mlx5/ -F: drivers/infiniband/hw/mlx5/ +M: Eli Cohen <eli@mellanox.com> +L: linux-rdma@vger.kernel.org +W: http://www.mellanox.com +Q: http://patchwork.kernel.org/project/linux-rdma/list/ +T: git git://openfabrics.org/~eli/connect-ib.git +S: Supported +F: include/linux/mlx5/ +F: drivers/infiniband/hw/mlx5/ MODULE SUPPORT M: Rusty Russell <rusty@rustcorp.com.au> @@ -5998,6 +6004,9 @@ F: include/linux/netdevice.h F: include/uapi/linux/in.h F: include/uapi/linux/net.h F: include/uapi/linux/netdevice.h +F: tools/net/ +F: tools/testing/selftests/net/ +F: lib/random32.c NETWORKING [IPv4/IPv6] M: "David S. Miller" <davem@davemloft.net> @@ -6171,6 +6180,12 @@ S: Supported F: drivers/block/nvme* F: include/linux/nvme.h +NXP TDA998X DRM DRIVER +M: Russell King <rmk+kernel@arm.linux.org.uk> +S: Supported +F: drivers/gpu/drm/i2c/tda998x_drv.c +F: include/drm/i2c/tda998x.h + OMAP SUPPORT M: Tony Lindgren <tony@atomide.com> L: linux-omap@vger.kernel.org @@ -8700,17 +8715,17 @@ S: Maintained F: drivers/media/radio/radio-raremono.c THERMAL -M: Zhang Rui <rui.zhang@intel.com> -M: Eduardo Valentin <eduardo.valentin@ti.com> -L: linux-pm@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git -Q: https://patchwork.kernel.org/project/linux-pm/list/ -S: Supported -F: drivers/thermal/ -F: include/linux/thermal.h -F: include/linux/cpu_cooling.h -F: Documentation/devicetree/bindings/thermal/ +M: Zhang Rui <rui.zhang@intel.com> +M: Eduardo Valentin <eduardo.valentin@ti.com> +L: linux-pm@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git +Q: https://patchwork.kernel.org/project/linux-pm/list/ +S: Supported +F: drivers/thermal/ +F: include/linux/thermal.h +F: include/linux/cpu_cooling.h +F: Documentation/devicetree/bindings/thermal/ THINGM BLINK(1) USB RGB LED DRIVER M: Vivien Didelot <vivien.didelot@savoirfairelinux.com> @@ -9812,7 +9827,7 @@ ZR36067 VIDEO FOR LINUX DRIVER L: mjpeg-users@lists.sourceforge.net L: linux-media@vger.kernel.org W: http://mjpeg.sourceforge.net/driver-zoran/ -T: Mercurial http://linuxtv.org/hg/v4l-dvb +T: hg http://linuxtv.org/hg/v4l-dvb S: Odd Fixes F: drivers/media/pci/zoran/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Shuffling Zombie Juror # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index a73a8e208a4a..7736f426ff3b 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -1,7 +1,8 @@ -generic-y += clkdev.h +generic-y += clkdev.h generic-y += exec.h -generic-y += trace_clock.h -generic-y += preempt.h generic-y += hash.h +generic-y += mcs_spinlock.h +generic-y += preempt.h +generic-y += trace_clock.h diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 0d3362991c31..e76fd79f32b0 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,15 +1,15 @@ generic-y += auxvec.h generic-y += barrier.h -generic-y += bugs.h generic-y += bitsperlong.h +generic-y += bugs.h generic-y += clkdev.h generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h generic-y += errno.h -generic-y += fcntl.h generic-y += fb.h +generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h generic-y += hash.h @@ -22,6 +22,7 @@ generic-y += kmap_types.h generic-y += kvm_para.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h @@ -30,6 +31,7 @@ generic-y += pci.h generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sembuf.h @@ -48,4 +50,3 @@ generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 6b58c1de7577..400c663b21c2 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -282,7 +282,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, #else /* if V-P const for loop, PTAG can be written once outside loop */ if (full_page_op) - write_aux_reg(ARC_REG_DC_PTAG, paddr); + write_aux_reg(aux_tag, paddr); #endif while (num_lines-- > 0) { @@ -296,7 +296,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, write_aux_reg(aux_cmd, vaddr); vaddr += L1_CACHE_BYTES; #else - write_aux_reg(aux, paddr); + write_aux_reg(aux_cmd, paddr); paddr += L1_CACHE_BYTES; #endif } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e25419817791..15949459611f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1578,6 +1578,7 @@ config BL_SWITCHER_DUMMY_IF choice prompt "Memory split" + depends on MMU default VMSPLIT_3G help Select the desired split between kernel and user memory. @@ -1595,6 +1596,7 @@ endchoice config PAGE_OFFSET hex + default PHYS_OFFSET if !MMU default 0x40000000 if VMSPLIT_1G default 0x80000000 if VMSPLIT_2G default 0xC0000000 @@ -1903,6 +1905,7 @@ config XEN depends on ARM && AEABI && OF depends on CPU_V7 && !CPU_V6 depends on !GENERIC_ATOMIC64 + depends on MMU select ARM_PSCI select SWIOTLB_XEN select ARCH_DMA_ADDR_T_64BIT diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore index 47279aa96a6a..0714e0334e33 100644 --- a/arch/arm/boot/compressed/.gitignore +++ b/arch/arm/boot/compressed/.gitignore @@ -1,4 +1,5 @@ ashldi3.S +bswapsdi2.S font.c lib1funcs.S hyp-stub.S diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi index e491b82f8d67..792fde1b7f75 100644 --- a/arch/arm/boot/dts/bcm11351.dtsi +++ b/arch/arm/boot/dts/bcm11351.dtsi @@ -147,7 +147,7 @@ }; pinctrl@35004800 { - compatible = "brcm,capri-pinctrl"; + compatible = "brcm,bcm11351-pinctrl"; reg = <0x35004800 0x430>; }; diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi index 2363593e1050..ef58d1c24313 100644 --- a/arch/arm/boot/dts/keystone-clocks.dtsi +++ b/arch/arm/boot/dts/keystone-clocks.dtsi @@ -612,7 +612,7 @@ clocks { compatible = "ti,keystone,psc-clock"; clocks = <&chipclk13>; clock-output-names = "vcp-3"; - reg = <0x0235000a8 0xb00>, <0x02350060 0x400>; + reg = <0x023500a8 0xb00>, <0x02350060 0x400>; reg-names = "control", "domain"; domain-id = <24>; }; diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index c551e4af4d83..d3b253bbc885 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -13,7 +13,7 @@ / { model = "OMAP3 GTA04"; - compatible = "ti,omap3-gta04", "ti,omap3"; + compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3"; cpus { cpu@0 { diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts index 25a2b5f652fd..f2779ac75872 100644 --- a/arch/arm/boot/dts/omap3-igep0020.dts +++ b/arch/arm/boot/dts/omap3-igep0020.dts @@ -14,7 +14,7 @@ / { model = "IGEPv2 (TI OMAP AM/DM37x)"; - compatible = "isee,omap3-igep0020", "ti,omap3"; + compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3"; leds { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts index 145c58cfc8ac..2793749eb1ba 100644 --- a/arch/arm/boot/dts/omap3-igep0030.dts +++ b/arch/arm/boot/dts/omap3-igep0030.dts @@ -13,7 +13,7 @@ / { model = "IGEP COM MODULE (TI OMAP AM/DM37x)"; - compatible = "isee,omap3-igep0030", "ti,omap3"; + compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3"; leds { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi index 6c31c26e6cc0..db58cad6acd3 100644 --- a/arch/arm/boot/dts/sama5d36.dtsi +++ b/arch/arm/boot/dts/sama5d36.dtsi @@ -8,8 +8,8 @@ */ #include "sama5d3.dtsi" #include "sama5d3_can.dtsi" -#include "sama5d3_emac.dtsi" #include "sama5d3_gmac.dtsi" +#include "sama5d3_emac.dtsi" #include "sama5d3_lcd.dtsi" #include "sama5d3_mci2.dtsi" #include "sama5d3_tcb1.dtsi" diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 10666ca8aee1..d4d2763f4794 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -426,7 +426,7 @@ }; rtp: rtp@01c25000 { - compatible = "allwinner,sun4i-ts"; + compatible = "allwinner,sun4i-a10-ts"; reg = <0x01c25000 0x100>; interrupts = <29>; }; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index 64961595e8d6..79fd412005b0 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -383,7 +383,7 @@ }; rtp: rtp@01c25000 { - compatible = "allwinner,sun4i-ts"; + compatible = "allwinner,sun4i-a10-ts"; reg = <0x01c25000 0x100>; interrupts = <29>; }; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index 320335abfccd..c463fd730c91 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -346,7 +346,7 @@ }; rtp: rtp@01c25000 { - compatible = "allwinner,sun4i-ts"; + compatible = "allwinner,sun4i-a10-ts"; reg = <0x01c25000 0x100>; interrupts = <29>; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 9ff09484847b..6f25cf559ad0 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -454,7 +454,7 @@ rtc: rtc@01c20d00 { compatible = "allwinner,sun7i-a20-rtc"; reg = <0x01c20d00 0x20>; - interrupts = <0 24 1>; + interrupts = <0 24 4>; }; sid: eeprom@01c23800 { @@ -463,7 +463,7 @@ }; rtp: rtp@01c25000 { - compatible = "allwinner,sun4i-ts"; + compatible = "allwinner,sun4i-a10-ts"; reg = <0x01c25000 0x100>; interrupts = <0 29 4>; }; @@ -596,10 +596,10 @@ hstimer@01c60000 { compatible = "allwinner,sun7i-a20-hstimer"; reg = <0x01c60000 0x1000>; - interrupts = <0 81 1>, - <0 82 1>, - <0 83 1>, - <0 84 1>; + interrupts = <0 81 4>, + <0 82 4>, + <0 83 4>, + <0 84 4>; clocks = <&ahb_gates 28>; }; diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 00fe9e9710fd..27d69b558c5d 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -204,7 +204,10 @@ CONFIG_MMC_BLOCK_MINORS=16 CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_TEGRA=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y CONFIG_LEDS_GPIO=y +CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y CONFIG_LEDS_TRIGGER_ONESHOT=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 3278afe2c3ab..23e728ecf8ab 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -7,16 +7,19 @@ generic-y += current.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h +generic-y += hash.h generic-y += ioctl.h generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kdebug.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += msgbuf.h generic-y += param.h generic-y += parport.h generic-y += poll.h +generic-y += preempt.h generic-y += resource.h generic-y += sections.h generic-y += segment.h @@ -33,5 +36,3 @@ generic-y += termios.h generic-y += timex.h generic-y += trace_clock.h generic-y += unaligned.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 8756e4bcdba0..4afb376d9c7c 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -30,14 +30,15 @@ */ #define UL(x) _AC(x, UL) +/* PAGE_OFFSET - the virtual address of the start of the kernel image */ +#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) + #ifdef CONFIG_MMU /* - * PAGE_OFFSET - the virtual address of the start of the kernel image * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area */ -#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) #define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M)) #define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M) @@ -104,10 +105,6 @@ #define END_MEM (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE) #endif -#ifndef PAGE_OFFSET -#define PAGE_OFFSET PLAT_PHYS_OFFSET -#endif - /* * The module can be at any place in ram in nommu mode. */ diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 58b8b84adcd2..2fe85fff5cca 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -20,9 +20,6 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define mc_capable() (cpu_topology[0].socket_id != -1) -#define smt_capable() (cpu_topology[0].thread_id != -1) - void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 47cd974e57ea..c96ecacb2021 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -177,6 +177,18 @@ __lookup_processor_type_data: .long __proc_info_end .size __lookup_processor_type_data, . - __lookup_processor_type_data +__error_lpae: +#ifdef CONFIG_DEBUG_LL + adr r0, str_lpae + bl printascii + b __error +str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n" +#else + b __error +#endif + .align +ENDPROC(__error_lpae) + __error_p: #ifdef CONFIG_DEBUG_LL adr r0, str_p1 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 914616e0bdcd..f5f381d91556 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -102,7 +102,7 @@ ENTRY(stext) and r3, r3, #0xf @ extract VMSA support cmp r3, #5 @ long-descriptor translation table format? THUMB( it lo ) @ force fixup-able long branch encoding - blo __error_p @ only classic page table format + blo __error_lpae @ only classic page table format #endif #ifndef CONFIG_XIP_KERNEL diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 92f7b15dd221..adabeababeb0 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -30,7 +30,6 @@ #include <linux/uaccess.h> #include <linux/random.h> #include <linux/hw_breakpoint.h> -#include <linux/cpuidle.h> #include <linux/leds.h> #include <linux/reboot.h> @@ -133,7 +132,11 @@ EXPORT_SYMBOL_GPL(arm_pm_restart); void (*arm_pm_idle)(void); -static void default_idle(void) +/* + * Called from the core idle loop. + */ + +void arch_cpu_idle(void) { if (arm_pm_idle) arm_pm_idle(); @@ -168,15 +171,6 @@ void arch_cpu_idle_dead(void) #endif /* - * Called from the core idle loop. - */ -void arch_cpu_idle(void) -{ - if (cpuidle_idle_call()) - default_idle(); -} - -/* * Called by kexec, immediately prior to machine_kexec(). * * This must completely disable all secondary CPUs; simply causing those CPUs diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c index 3b05aea56d1f..11ed9152e665 100644 --- a/arch/arm/mach-omap2/cclock3xxx_data.c +++ b/arch/arm/mach-omap2/cclock3xxx_data.c @@ -433,7 +433,9 @@ static const struct clk_ops dpll4_m5x2_ck_ops = { .enable = &omap2_dflt_clk_enable, .disable = &omap2_dflt_clk_disable, .is_enabled = &omap2_dflt_clk_is_enabled, + .set_rate = &omap3_clkoutx2_set_rate, .recalc_rate = &omap3_clkoutx2_recalc, + .round_rate = &omap3_clkoutx2_round_rate, }; static const struct clk_ops dpll4_m5x2_ck_3630_ops = { diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index 4c158c838d40..01fc710c8181 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -23,6 +23,8 @@ #include "prm.h" #include "clockdomain.h" +#define MAX_CPUS 2 + /* Machine specific information */ struct idle_statedata { u32 cpu_state; @@ -48,11 +50,11 @@ static struct idle_statedata omap4_idle_data[] = { }, }; -static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS]; -static struct clockdomain *cpu_clkdm[NR_CPUS]; +static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS]; +static struct clockdomain *cpu_clkdm[MAX_CPUS]; static atomic_t abort_barrier; -static bool cpu_done[NR_CPUS]; +static bool cpu_done[MAX_CPUS]; static struct idle_statedata *state_ptr = &omap4_idle_data[0]; /* Private functions */ diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c index 3185ced807c9..3c418ea54bbe 100644 --- a/arch/arm/mach-omap2/dpll3xxx.c +++ b/arch/arm/mach-omap2/dpll3xxx.c @@ -623,6 +623,32 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk) /* Clock control for DPLL outputs */ +/* Find the parent DPLL for the given clkoutx2 clock */ +static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw) +{ + struct clk_hw_omap *pclk = NULL; + struct clk *parent; + + /* Walk up the parents of clk, looking for a DPLL */ + do { + do { + parent = __clk_get_parent(hw->clk); + hw = __clk_get_hw(parent); + } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC)); + if (!hw) + break; + pclk = to_clk_hw_omap(hw); + } while (pclk && !pclk->dpll_data); + + /* clk does not have a DPLL as a parent? error in the clock data */ + if (!pclk) { + WARN_ON(1); + return NULL; + } + + return pclk; +} + /** * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate * @clk: DPLL output struct clk @@ -637,27 +663,14 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long rate; u32 v; struct clk_hw_omap *pclk = NULL; - struct clk *parent; if (!parent_rate) return 0; - /* Walk up the parents of clk, looking for a DPLL */ - do { - do { - parent = __clk_get_parent(hw->clk); - hw = __clk_get_hw(parent); - } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC)); - if (!hw) - break; - pclk = to_clk_hw_omap(hw); - } while (pclk && !pclk->dpll_data); + pclk = omap3_find_clkoutx2_dpll(hw); - /* clk does not have a DPLL as a parent? error in the clock data */ - if (!pclk) { - WARN_ON(1); + if (!pclk) return 0; - } dd = pclk->dpll_data; @@ -672,6 +685,55 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, return rate; } +int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + return 0; +} + +long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + const struct dpll_data *dd; + u32 v; + struct clk_hw_omap *pclk = NULL; + + if (!*prate) + return 0; + + pclk = omap3_find_clkoutx2_dpll(hw); + + if (!pclk) + return 0; + + dd = pclk->dpll_data; + + /* TYPE J does not have a clkoutx2 */ + if (dd->flags & DPLL_J_TYPE) { + *prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate); + return *prate; + } + + WARN_ON(!dd->enable_mask); + + v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask; + v >>= __ffs(dd->enable_mask); + + /* If in bypass, the rate is fixed to the bypass rate*/ + if (v != OMAP3XXX_EN_DPLL_LOCKED) + return *prate; + + if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) { + unsigned long best_parent; + + best_parent = (rate / 2); + *prate = __clk_round_rate(__clk_get_parent(hw->clk), + best_parent); + } + + return *prate * 2; +} + /* OMAP3/4 non-CORE DPLL clkops */ const struct clk_hw_omap_ops clkhwops_omap3_dpll = { .allow_idle = omap3_dpll_allow_idle, diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 42d81885c700..1f33f5db10d5 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1947,29 +1947,31 @@ static int _ocp_softreset(struct omap_hwmod *oh) goto dis_opt_clks; _write_sysconfig(v, oh); - ret = _clear_softreset(oh, &v); - if (ret) - goto dis_opt_clks; - - _write_sysconfig(v, oh); if (oh->class->sysc->srst_udelay) udelay(oh->class->sysc->srst_udelay); c = _wait_softreset_complete(oh); - if (c == MAX_MODULE_SOFTRESET_WAIT) + if (c == MAX_MODULE_SOFTRESET_WAIT) { pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n", oh->name, MAX_MODULE_SOFTRESET_WAIT); - else + ret = -ETIMEDOUT; + goto dis_opt_clks; + } else { pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c); + } + + ret = _clear_softreset(oh, &v); + if (ret) + goto dis_opt_clks; + + _write_sysconfig(v, oh); /* * XXX add _HWMOD_STATE_WEDGED for modules that don't come back from * _wait_target_ready() or _reset() */ - ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0; - dis_opt_clks: if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET) _disable_optional_clocks(oh); diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 18f333c440db..810c205d668b 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -1365,11 +1365,10 @@ static struct omap_hwmod_class_sysconfig dra7xx_spinlock_sysc = { .rev_offs = 0x0000, .sysc_offs = 0x0010, .syss_offs = 0x0014, - .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY | - SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE | - SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS), - .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | - SIDLE_SMART_WKUP), + .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP | + SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | + SYSS_HAS_RESET_STATUS), + .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), .sysc_fields = &omap_hwmod_sysc_type1, }; diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 3d5b24dcd9a4..c33e07e2f0d4 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -22,6 +22,8 @@ #include "common-board-devices.h" #include "dss-common.h" #include "control.h" +#include "omap-secure.h" +#include "soc.h" struct pdata_init { const char *compatible; @@ -169,6 +171,22 @@ static void __init am3517_evm_legacy_init(void) omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET); omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */ } + +static void __init nokia_n900_legacy_init(void) +{ + hsmmc2_internal_input_clk(); + + if (omap_type() == OMAP2_DEVICE_TYPE_SEC) { + if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) { + pr_info("RX-51: Enabling ARM errata 430973 workaround\n"); + /* set IBE to 1 */ + rx51_secure_update_aux_cr(BIT(6), 0); + } else { + pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n"); + pr_warning("Thumb binaries may crash randomly without this workaround\n"); + } + } +} #endif /* CONFIG_ARCH_OMAP3 */ #ifdef CONFIG_ARCH_OMAP4 @@ -239,6 +257,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = { #endif #ifdef CONFIG_ARCH_OMAP3 OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata), + OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata), OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata), /* Only on am3517 */ OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL), @@ -259,7 +278,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = { static struct pdata_init pdata_quirks[] __initdata = { #ifdef CONFIG_ARCH_OMAP3 { "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, }, - { "nokia,omap3-n900", hsmmc2_internal_input_clk, }, + { "nokia,omap3-n900", nokia_n900_legacy_init, }, { "nokia,omap3-n9", hsmmc2_internal_input_clk, }, { "nokia,omap3-n950", hsmmc2_internal_input_clk, }, { "isee,omap3-igep0020", omap3_igep0020_legacy_init, }, diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c index 6334b96b4097..280f3c58abe5 100644 --- a/arch/arm/mach-omap2/prminst44xx.c +++ b/arch/arm/mach-omap2/prminst44xx.c @@ -183,11 +183,11 @@ void omap4_prminst_global_warm_sw_reset(void) OMAP4_PRM_RSTCTRL_OFFSET); v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK; omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION, - OMAP4430_PRM_DEVICE_INST, + dev_inst, OMAP4_PRM_RSTCTRL_OFFSET); /* OCP barrier */ v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION, - OMAP4430_PRM_DEVICE_INST, + dev_inst, OMAP4_PRM_RSTCTRL_OFFSET); } diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h index f33679d2d3ee..50e1d850ee2e 100644 --- a/arch/arm/mach-sa1100/include/mach/collie.h +++ b/arch/arm/mach-sa1100/include/mach/collie.h @@ -13,6 +13,8 @@ #ifndef __ASM_ARCH_COLLIE_H #define __ASM_ARCH_COLLIE_H +#include "hardware.h" /* Gives GPIO_MAX */ + extern void locomolcd_power(int on); #define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1) diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c index 2b3a56414271..ef69152f9b52 100644 --- a/arch/arm/mm/dump.c +++ b/arch/arm/mm/dump.c @@ -264,6 +264,9 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) note_page(st, addr, 3, pmd_val(*pmd)); else walk_pte(st, pmd, addr); + + if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1])) + note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1])); } } diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 71c53ecfcc3a..3bdfdda70567 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -12,6 +12,7 @@ generic-y += dma.h generic-y += emergency-restart.h generic-y += errno.h generic-y += ftrace.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -22,12 +23,14 @@ generic-y += kmap_types.h generic-y += kvm_para.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h generic-y += mutex.h generic-y += pci.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -38,8 +41,8 @@ generic-y += shmbuf.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h -generic-y += switch_to.h generic-y += swab.h +generic-y += switch_to.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h @@ -49,5 +52,3 @@ generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 1c0a9be2ffa8..9cce0098f4cd 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -33,7 +33,6 @@ #include <linux/kallsyms.h> #include <linux/init.h> #include <linux/cpu.h> -#include <linux/cpuidle.h> #include <linux/elfcore.h> #include <linux/pm.h> #include <linux/tick.h> @@ -94,10 +93,8 @@ void arch_cpu_idle(void) * This should do all the clock switching and wait for interrupt * tricks */ - if (cpuidle_idle_call()) { - cpu_do_idle(); - local_irq_enable(); - } + cpu_do_idle(); + local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index c7c64a63c29f..00a0f3ccd6eb 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -1,22 +1,23 @@ -generic-y += clkdev.h -generic-y += cputime.h -generic-y += delay.h -generic-y += device.h -generic-y += div64.h -generic-y += emergency-restart.h -generic-y += exec.h -generic-y += futex.h -generic-y += preempt.h -generic-y += irq_regs.h -generic-y += param.h -generic-y += local.h -generic-y += local64.h -generic-y += percpu.h -generic-y += scatterlist.h -generic-y += sections.h -generic-y += topology.h -generic-y += trace_clock.h +generic-y += clkdev.h +generic-y += cputime.h +generic-y += delay.h +generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h +generic-y += exec.h +generic-y += futex.h +generic-y += hash.h +generic-y += irq_regs.h +generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h +generic-y += param.h +generic-y += percpu.h +generic-y += preempt.h +generic-y += scatterlist.h +generic-y += sections.h +generic-y += topology.h +generic-y += trace_clock.h generic-y += vga.h -generic-y += xor.h -generic-y += hash.h +generic-y += xor.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 359d36fdc247..0d93b9a79ca9 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -10,6 +10,7 @@ generic-y += emergency-restart.h generic-y += errno.h generic-y += fb.h generic-y += futex.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ipcbuf.h @@ -17,14 +18,16 @@ generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kvm_para.h -generic-y += local64.h generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h generic-y += mutex.h generic-y += param.h generic-y += percpu.h generic-y += pgalloc.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sembuf.h @@ -44,5 +47,3 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index d73bb85ccdd3..8dbdce8421b0 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -15,6 +15,7 @@ generic-y += exec.h generic-y += fb.h generic-y += fcntl.h generic-y += futex.h +generic-y += hash.h generic-y += hw_irq.h generic-y += io.h generic-y += ioctl.h @@ -24,6 +25,7 @@ generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += local.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += mmu.h generic-y += mmu_context.h @@ -34,6 +36,7 @@ generic-y += percpu.h generic-y += pgalloc.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += segment.h @@ -56,5 +59,3 @@ generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h index 09c5a0f5f4d1..86648c083bb4 100644 --- a/arch/c6x/include/asm/cache.h +++ b/arch/c6x/include/asm/cache.h @@ -12,6 +12,7 @@ #define _ASM_C6X_CACHE_H #include <linux/irqflags.h> +#include <linux/init.h> /* * Cache line size diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index f3fd8768f095..056027f38351 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -9,8 +9,9 @@ generic-y += exec.h generic-y += hash.h generic-y += kvm_para.h generic-y += linkage.h +generic-y += mcs_spinlock.h generic-y += module.h +generic-y += preempt.h generic-y += trace_clock.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h index 184066ceb1f6..053c17b36559 100644 --- a/arch/cris/include/asm/bitops.h +++ b/arch/cris/include/asm/bitops.h @@ -144,7 +144,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) * definition, which doesn't have the same semantics. We don't want to * use -fno-builtin, so just hide the name ffs. */ -#define ffs kernel_ffs +#define ffs(x) kernel_ffs(x) #include <asm-generic/bitops/fls.h> #include <asm-generic/bitops/__fls.h> diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index bc42f14c9c2e..babb9338ebf8 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -1,6 +1,7 @@ generic-y += clkdev.h generic-y += exec.h -generic-y += trace_clock.h -generic-y += preempt.h generic-y += hash.h +generic-y += mcs_spinlock.h +generic-y += preempt.h +generic-y += trace_clock.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 38ca45d3df1e..eadcc118f950 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -25,14 +25,16 @@ generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += local64.h generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h generic-y += pci.h generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += rwsem.h generic-y += scatterlist.h @@ -45,8 +47,8 @@ generic-y += siginfo.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h -generic-y += statfs.h generic-y += stat.h +generic-y += statfs.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h @@ -55,4 +57,3 @@ generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h generic-y += xor.h -generic-y += preempt.h diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 283a83154b5e..0da4aa2602ae 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -1,8 +1,9 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += hash.h generic-y += kvm_para.h -generic-y += trace_clock.h +generic-y += mcs_spinlock.h generic-y += preempt.h +generic-y += trace_clock.h generic-y += vtime.h -generic-y += hash.h diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index a2496e449b75..5cb55a1e606b 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -77,7 +77,6 @@ void build_cpu_to_node_map(void); #define topology_core_id(cpu) (cpu_data(cpu)->core_id) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) #define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) -#define smt_capable() (smp_num_siblings > 1) #endif extern void arch_fix_phys_package_id(int num, u32 slot); diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index da5b462e6de6..741b99c1a0b1 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -477,6 +477,9 @@ efi_init (void) char *cp, vendor[100] = "unknown"; int i; + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); + /* * It's too early to be able to use the standard kernel command line * support... @@ -529,6 +532,8 @@ efi_init (void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + palo_phys = EFI_INVALID_TABLE_ADDR; if (efi_config_init(arch_tables) != 0) @@ -657,6 +662,8 @@ efi_enter_virtual_mode (void) return; } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + /* * Now that EFI is in virtual mode, we call the EFI functions more * efficiently: diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index a96bcf83a735..20e8a9b21d75 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -98,7 +98,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) /* attempt to allocate a granule's worth of cached memory pages */ page = alloc_pages_exact_node(nid, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, IA64_GRANULE_SHIFT-PAGE_SHIFT); if (!page) { mutex_unlock(&uc_pool->add_chunk_mutex); diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index 932435ac4e5c..5825a35b2c56 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -1,7 +1,8 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += hash.h +generic-y += mcs_spinlock.h generic-y += module.h -generic-y += trace_clock.h generic-y += preempt.h -generic-y += hash.h +generic-y += trace_clock.h diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index dbdd2231c75d..b2e322939256 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -17,6 +17,7 @@ config M68K select FPU if MMU select ARCH_WANT_IPC_PARSE_VERSION select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE + select HAVE_FUTEX_CMPXCHG if MMU && FUTEX select HAVE_MOD_ARCH_SPECIFIC select MODULES_USE_ELF_REL select MODULES_USE_ELF_RELA diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 6fb9e813a910..c67c94a2d672 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -14,8 +14,9 @@ generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kvm_para.h -generic-y += local64.h generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += mutex.h generic-y += percpu.h diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index b716d807c2ec..c29ead89a317 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += fb.h generic-y += fcntl.h generic-y += futex.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -23,6 +24,7 @@ generic-y += kmap_types.h generic-y += kvm_para.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += msgbuf.h generic-y += mutex.h generic-y += param.h @@ -30,6 +32,7 @@ generic-y += pci.h generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += sembuf.h @@ -52,5 +55,3 @@ generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 2b98bc73642a..1f590ab8f323 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += barrier.h generic-y += clkdev.h generic-y += exec.h generic-y += hash.h -generic-y += trace_clock.h -generic-y += syscalls.h +generic-y += mcs_spinlock.h generic-y += preempt.h +generic-y += syscalls.h +generic-y += trace_clock.h diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index dcae3a7035db..95fa1f1d5c8b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1776,12 +1776,12 @@ endchoice config FORCE_MAX_ZONEORDER int "Maximum zone order" - range 14 64 if HUGETLB_PAGE && PAGE_SIZE_64KB - default "14" if HUGETLB_PAGE && PAGE_SIZE_64KB - range 13 64 if HUGETLB_PAGE && PAGE_SIZE_32KB - default "13" if HUGETLB_PAGE && PAGE_SIZE_32KB - range 12 64 if HUGETLB_PAGE && PAGE_SIZE_16KB - default "12" if HUGETLB_PAGE && PAGE_SIZE_16KB + range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB + default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB + range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB + default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB + range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB + default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB range 11 64 default "11" help @@ -2353,9 +2353,8 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. config MIPS_O32_FP64_SUPPORT - bool "Support for O32 binaries using 64-bit FP" + bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)" depends on 32BIT || MIPS32_O32 - default y help When this is enabled, the kernel will support use of 64-bit floating point registers with binaries using the O32 ABI along with the @@ -2367,7 +2366,14 @@ config MIPS_O32_FP64_SUPPORT of your kernel & potentially improve FP emulation performance by saying N here. - If unsure, say Y. + Although binutils currently supports use of this flag the details + concerning its effect upon the O32 ABI in userland are still being + worked on. In order to avoid userland becoming dependant upon current + behaviour before the details have been finalised, this option should + be considered experimental and only enabled by those working upon + said details. + + If unsure, say N. config USE_OF bool diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c index 9edc35ff8cf1..acf9a2a37f5a 100644 --- a/arch/mips/alchemy/board-gpr.c +++ b/arch/mips/alchemy/board-gpr.c @@ -53,10 +53,8 @@ void __init prom_init(void) prom_init_cmdline(); memsize_str = prom_getenv("memsize"); - if (!memsize_str) + if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) memsize = 0x04000000; - else - strict_strtoul(memsize_str, 0, &memsize); add_memory_region(0, memsize, BOOT_MEM_RAM); } diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c index 9969dbab19e3..25a59a23547e 100644 --- a/arch/mips/alchemy/board-mtx1.c +++ b/arch/mips/alchemy/board-mtx1.c @@ -52,10 +52,8 @@ void __init prom_init(void) prom_init_cmdline(); memsize_str = prom_getenv("memsize"); - if (!memsize_str) + if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) memsize = 0x04000000; - else - strict_strtoul(memsize_str, 0, &memsize); add_memory_region(0, memsize, BOOT_MEM_RAM); } diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c index 6d612e2b949b..cdd8246f92b3 100644 --- a/arch/mips/bcm47xx/board.c +++ b/arch/mips/bcm47xx/board.c @@ -1,3 +1,4 @@ +#include <linux/errno.h> #include <linux/export.h> #include <linux/string.h> #include <bcm47xx_board.h> diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c index 6decb27cf48b..2bed73a684ae 100644 --- a/arch/mips/bcm47xx/nvram.c +++ b/arch/mips/bcm47xx/nvram.c @@ -196,7 +196,7 @@ int bcm47xx_nvram_gpio_pin(const char *name) char nvram_var[10]; char buf[30]; - for (i = 0; i < 16; i++) { + for (i = 0; i < 32; i++) { err = snprintf(nvram_var, sizeof(nvram_var), "gpio%i", i); if (err <= 0) continue; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 25fbfae06c1f..c2bb4f896ce7 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -975,10 +975,6 @@ static int octeon_irq_ciu_xlat(struct irq_domain *d, if (ciu > 1 || bit > 63) return -EINVAL; - /* These are the GPIO lines */ - if (ciu == 0 && bit >= 16 && bit < 32) - return -EINVAL; - *out_hwirq = (ciu << 6) | bit; *out_type = 0; @@ -1007,6 +1003,10 @@ static int octeon_irq_ciu_map(struct irq_domain *d, if (!octeon_irq_virq_in_range(virq)) return -EINVAL; + /* Don't map irq if it is reserved for GPIO. */ + if (line == 0 && bit >= 16 && bit <32) + return 0; + if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0) return -EINVAL; @@ -1525,10 +1525,6 @@ static int octeon_irq_ciu2_xlat(struct irq_domain *d, ciu = intspec[0]; bit = intspec[1]; - /* Line 7 are the GPIO lines */ - if (ciu > 6 || bit > 63) - return -EINVAL; - *out_hwirq = (ciu << 6) | bit; *out_type = 0; @@ -1570,8 +1566,14 @@ static int octeon_irq_ciu2_map(struct irq_domain *d, if (!octeon_irq_virq_in_range(virq)) return -EINVAL; - /* Line 7 are the GPIO lines */ - if (line > 6 || octeon_irq_ciu_to_irq[line][bit] != 0) + /* + * Don't map irq if it is reserved for GPIO. + * (Line 7 are the GPIO lines.) + */ + if (line == 7) + return 0; + + if (line > 7 || octeon_irq_ciu_to_irq[line][bit] != 0) return -EINVAL; if (octeon_irq_ciu2_is_edge(line, bit)) diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 2d7f65052c1f..05439187891d 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -2,16 +2,17 @@ generic-y += cputime.h generic-y += current.h generic-y += emergency-restart.h +generic-y += hash.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += mutex.h generic-y += parport.h generic-y += percpu.h +generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += segment.h generic-y += serial.h generic-y += trace_clock.h -generic-y += preempt.h generic-y += ucontext.h generic-y += xor.h -generic-y += hash.h diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 3220c93ea981..4225e99bd7bf 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -9,6 +9,7 @@ #define _ASM_ASMMACRO_H #include <asm/hazards.h> +#include <asm/asm-offsets.h> #ifdef CONFIG_32BIT #include <asm/asmmacro-32.h> @@ -54,11 +55,21 @@ .endm .macro local_irq_disable reg=t0 +#ifdef CONFIG_PREEMPT + lw \reg, TI_PRE_COUNT($28) + addi \reg, \reg, 1 + sw \reg, TI_PRE_COUNT($28) +#endif mfc0 \reg, CP0_STATUS ori \reg, \reg, 1 xori \reg, \reg, 1 mtc0 \reg, CP0_STATUS irq_disable_hazard +#ifdef CONFIG_PREEMPT + lw \reg, TI_PRE_COUNT($28) + addi \reg, \reg, -1 + sw \reg, TI_PRE_COUNT($28) +#endif .endm #endif /* CONFIG_MIPS_MT_SMTC */ @@ -106,7 +117,7 @@ .endm .macro fpu_save_double thread status tmp -#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) sll \tmp, \status, 5 bgez \tmp, 10f fpu_save_16odd \thread @@ -159,7 +170,7 @@ .endm .macro fpu_restore_double thread status tmp -#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) sll \tmp, \status, 5 bgez \tmp, 10f # 16 register mode? diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 6b9749540edf..58e50cbdb1a6 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -57,7 +57,7 @@ static inline int __enable_fpu(enum fpu_mode mode) return 0; case FPU_64BIT: -#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_MIPS64)) +#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT)) /* we only have a 32-bit FPU */ return SIGFPE; #endif diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index ce35c9af0c28..992aaba603b5 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -22,12 +22,12 @@ extern void _mcount(void); #define safe_load(load, src, dst, error) \ do { \ asm volatile ( \ - "1: " load " %[" STR(dst) "], 0(%[" STR(src) "])\n"\ - " li %[" STR(error) "], 0\n" \ + "1: " load " %[tmp_dst], 0(%[tmp_src])\n" \ + " li %[tmp_err], 0\n" \ "2:\n" \ \ ".section .fixup, \"ax\"\n" \ - "3: li %[" STR(error) "], 1\n" \ + "3: li %[tmp_err], 1\n" \ " j 2b\n" \ ".previous\n" \ \ @@ -35,8 +35,8 @@ do { \ STR(PTR) "\t1b, 3b\n\t" \ ".previous\n" \ \ - : [dst] "=&r" (dst), [error] "=r" (error)\ - : [src] "r" (src) \ + : [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\ + : [tmp_src] "r" (src) \ : "memory" \ ); \ } while (0) @@ -44,12 +44,12 @@ do { \ #define safe_store(store, src, dst, error) \ do { \ asm volatile ( \ - "1: " store " %[" STR(src) "], 0(%[" STR(dst) "])\n"\ - " li %[" STR(error) "], 0\n" \ + "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\ + " li %[tmp_err], 0\n" \ "2:\n" \ \ ".section .fixup, \"ax\"\n" \ - "3: li %[" STR(error) "], 1\n" \ + "3: li %[tmp_err], 1\n" \ " j 2b\n" \ ".previous\n" \ \ @@ -57,8 +57,8 @@ do { \ STR(PTR) "\t1b, 3b\n\t" \ ".previous\n" \ \ - : [error] "=r" (error) \ - : [dst] "r" (dst), [src] "r" (src)\ + : [tmp_err] "=r" (error) \ + : [tmp_dst] "r" (dst), [tmp_src] "r" (src)\ : "memory" \ ); \ } while (0) diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 33e8dbfc1b63..f35b131977e6 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -13,6 +13,7 @@ #ifndef __ASM_MIPS_SYSCALL_H #define __ASM_MIPS_SYSCALL_H +#include <linux/compiler.h> #include <linux/audit.h> #include <linux/elf-em.h> #include <linux/kernel.h> @@ -39,14 +40,14 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg, #ifdef CONFIG_32BIT case 4: case 5: case 6: case 7: - return get_user(*arg, (int *)usp + 4 * n); + return get_user(*arg, (int *)usp + n); #endif #ifdef CONFIG_64BIT case 4: case 5: case 6: case 7: #ifdef CONFIG_MIPS32_O32 if (test_thread_flag(TIF_32BIT_REGS)) - return get_user(*arg, (int *)usp + 4 * n); + return get_user(*arg, (int *)usp + n); else #endif *arg = regs->regs[4 + n]; @@ -57,6 +58,8 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg, default: BUG(); } + + unreachable(); } static inline long syscall_get_return_value(struct task_struct *task, @@ -83,11 +86,10 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { - unsigned long arg; int ret; while (n--) - ret |= mips_get_syscall_arg(&arg, task, regs, i++); + ret |= mips_get_syscall_arg(args++, task, regs, i++); /* * No way to communicate an error because this is a void function. diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h index 12609a17dc8b..20ea4859c822 100644 --- a/arch/mips/include/asm/topology.h +++ b/arch/mips/include/asm/topology.h @@ -10,8 +10,4 @@ #include <topology.h> -#ifdef CONFIG_SMP -#define smt_capable() (smp_num_siblings > 1) -#endif - #endif /* __ASM_TOPOLOGY_H */ diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index b39ba25b41cc..f25181b19941 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -163,8 +163,8 @@ enum cop1_sdw_func { */ enum cop1x_func { lwxc1_op = 0x00, ldxc1_op = 0x01, - pfetch_op = 0x07, swxc1_op = 0x08, - sdxc1_op = 0x09, madd_s_op = 0x20, + swxc1_op = 0x08, sdxc1_op = 0x09, + pfetch_op = 0x0f, madd_s_op = 0x20, madd_d_op = 0x21, madd_e_op = 0x22, msub_s_op = 0x28, msub_d_op = 0x29, msub_e_op = 0x2a, nmadd_s_op = 0x30, diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 185ba258361b..374ed74cd516 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -111,11 +111,10 @@ static int ftrace_modify_code_2(unsigned long ip, unsigned int new_code1, safe_store_code(new_code1, ip, faulted); if (unlikely(faulted)) return -EFAULT; - ip += 4; - safe_store_code(new_code2, ip, faulted); + safe_store_code(new_code2, ip + 4, faulted); if (unlikely(faulted)) return -EFAULT; - flush_icache_range(ip, ip + 8); /* original ip + 12 */ + flush_icache_range(ip, ip + 8); return 0; } #endif diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index 253b2fb52026..73b0ddf910d4 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -35,9 +35,9 @@ LEAF(_save_fp_context) cfc1 t1, fcr31 -#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) .set push -#ifdef CONFIG_MIPS32_R2 +#ifdef CONFIG_CPU_MIPS32_R2 .set mips64r2 mfc0 t0, CP0_STATUS sll t0, t0, 5 @@ -146,11 +146,11 @@ LEAF(_save_fp_context32) * - cp1 status/control register */ LEAF(_restore_fp_context) - EX lw t0, SC_FPC_CSR(a0) + EX lw t1, SC_FPC_CSR(a0) -#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) .set push -#ifdef CONFIG_MIPS32_R2 +#ifdef CONFIG_CPU_MIPS32_R2 .set mips64r2 mfc0 t0, CP0_STATUS sll t0, t0, 5 @@ -191,7 +191,7 @@ LEAF(_restore_fp_context) EX ldc1 $f26, SC_FPREGS+208(a0) EX ldc1 $f28, SC_FPREGS+224(a0) EX ldc1 $f30, SC_FPREGS+240(a0) - ctc1 t0, fcr31 + ctc1 t1, fcr31 jr ra li v0, 0 # success END(_restore_fp_context) @@ -199,7 +199,7 @@ LEAF(_restore_fp_context) #ifdef CONFIG_MIPS32_COMPAT LEAF(_restore_fp_context32) /* Restore an o32 sigcontext. */ - EX lw t0, SC32_FPC_CSR(a0) + EX lw t1, SC32_FPC_CSR(a0) mfc0 t0, CP0_STATUS sll t0, t0, 5 @@ -239,7 +239,7 @@ LEAF(_restore_fp_context32) EX ldc1 $f26, SC32_FPREGS+208(a0) EX ldc1 $f28, SC32_FPREGS+224(a0) EX ldc1 $f30, SC32_FPREGS+240(a0) - ctc1 t0, fcr31 + ctc1 t1, fcr31 jr ra li v0, 0 # success END(_restore_fp_context32) diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c index 56dc69635153..758fb3cd2326 100644 --- a/arch/mips/kernel/rtlx-cmp.c +++ b/arch/mips/kernel/rtlx-cmp.c @@ -112,5 +112,8 @@ void __exit rtlx_module_exit(void) for (i = 0; i < RTLX_CHANNELS; i++) device_destroy(mt_class, MKDEV(major, i)); + unregister_chrdev(major, RTLX_MODULE_NAME); + + aprp_hook = NULL; } diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c index 91d61ba422b4..9c1aca00fd54 100644 --- a/arch/mips/kernel/rtlx-mt.c +++ b/arch/mips/kernel/rtlx-mt.c @@ -144,5 +144,8 @@ void __exit rtlx_module_exit(void) for (i = 0; i < RTLX_CHANNELS; i++) device_destroy(mt_class, MKDEV(major, i)); + unregister_chrdev(major, RTLX_MODULE_NAME); + + aprp_hook = NULL; } diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 506925b2c3f3..0b4e2e38294b 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -1538,10 +1538,10 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; } - case 0x7: /* 7 */ - if (MIPSInst_FUNC(ir) != pfetch_op) { + case 0x3: + if (MIPSInst_FUNC(ir) != pfetch_op) return SIGILL; - } + /* ignore prefx operation */ break; diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c index 592ac0427426..84ac523b0ce0 100644 --- a/arch/mips/mti-malta/malta-amon.c +++ b/arch/mips/mti-malta/malta-amon.c @@ -72,7 +72,7 @@ int amon_cpu_start(int cpu, return 0; } -#ifdef CONFIG_MIPS_VPE_LOADER +#ifdef CONFIG_MIPS_VPE_LOADER_CMP int vpe_run(struct vpe *v) { struct vpe_notifications *n; diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index ca3e3a46a42f..2242181a6284 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -119,7 +119,7 @@ static void malta_hw0_irqdispatch(void) do_IRQ(MALTA_INT_BASE + irq); -#ifdef MIPS_VPE_APSP_API +#ifdef CONFIG_MIPS_VPE_APSP_API_MT if (aprp_hook) aprp_hook(); #endif @@ -310,7 +310,7 @@ static void ipi_call_dispatch(void) static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) { -#ifdef MIPS_VPE_APSP_API +#ifdef CONFIG_MIPS_VPE_APSP_API_CMP if (aprp_hook) aprp_hook(); #endif diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c index d37be36dc659..2b91b0e61566 100644 --- a/arch/mips/pci/msi-octeon.c +++ b/arch/mips/pci/msi-octeon.c @@ -150,6 +150,7 @@ msi_irq_allocated: msg.address_lo = ((128ul << 20) + CVMX_PCI_MSI_RCV) & 0xffffffff; msg.address_hi = ((128ul << 20) + CVMX_PCI_MSI_RCV) >> 32; + break; case OCTEON_DMA_BAR_TYPE_BIG: /* When using big bar, Bar 0 is based at 0 */ msg.address_lo = (0 + CVMX_PCI_MSI_RCV) & 0xffffffff; diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index 992e989ab785..cbc6b9bf45da 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -3,5 +3,6 @@ generic-y += barrier.h generic-y += clkdev.h generic-y += exec.h generic-y += hash.h -generic-y += trace_clock.h +generic-y += mcs_spinlock.h generic-y += preempt.h +generic-y += trace_clock.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 2e40f1ca8667..480af0d9c2f5 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -10,8 +10,8 @@ generic-y += bugs.h generic-y += cacheflush.h generic-y += checksum.h generic-y += clkdev.h -generic-y += cmpxchg.h generic-y += cmpxchg-local.h +generic-y += cmpxchg.h generic-y += cputime.h generic-y += current.h generic-y += device.h @@ -25,6 +25,7 @@ generic-y += fcntl.h generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -34,6 +35,7 @@ generic-y += kdebug.h generic-y += kmap_types.h generic-y += kvm_para.h generic-y += local.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += module.h generic-y += msgbuf.h @@ -41,6 +43,7 @@ generic-y += pci.h generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -53,11 +56,11 @@ generic-y += siginfo.h generic-y += signal.h generic-y += socket.h generic-y += sockios.h -generic-y += statfs.h generic-y += stat.h +generic-y += statfs.h generic-y += string.h -generic-y += switch_to.h generic-y += swab.h +generic-y += switch_to.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h @@ -68,5 +71,3 @@ generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 752c981bc3c7..ecf25e6678ad 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -1,9 +1,29 @@ +generic-y += auxvec.h generic-y += barrier.h -generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \ - segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \ - div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \ - poll.h xor.h clkdev.h exec.h -generic-y += trace_clock.h -generic-y += preempt.h +generic-y += clkdev.h +generic-y += cputime.h +generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h +generic-y += exec.h generic-y += hash.h +generic-y += hw_irq.h +generic-y += irq_regs.h +generic-y += kdebug.h +generic-y += kvm_para.h +generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h +generic-y += mutex.h +generic-y += param.h +generic-y += percpu.h +generic-y += poll.h +generic-y += preempt.h +generic-y += segment.h +generic-y += topology.h +generic-y += trace_clock.h +generic-y += user.h +generic-y += vga.h +generic-y += word-at-a-time.h +generic-y += xor.h diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 637fe031aa84..60d5d174dfe4 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -32,17 +32,6 @@ void copy_page_asm(void *to, void *from); void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, struct page *pg); -/* #define CONFIG_PARISC_TMPALIAS */ - -#ifdef CONFIG_PARISC_TMPALIAS -void clear_user_highpage(struct page *page, unsigned long vaddr); -#define clear_user_highpage clear_user_highpage -struct vm_area_struct; -void copy_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma); -#define __HAVE_ARCH_COPY_USER_HIGHPAGE -#endif - /* * These are used to make use of C type-checking.. */ diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 3516e0b27044..64f2992e439f 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -191,8 +191,4 @@ static __inline__ int arch_write_can_lock(arch_rwlock_t *rw) #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) -#define arch_spin_relax(lock) cpu_relax() -#define arch_read_relax(lock) cpu_relax() -#define arch_write_relax(lock) cpu_relax() - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 42706794a36f..265ae5190b0a 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -828,13 +828,13 @@ #define __NR_finit_module (__NR_Linux + 333) #define __NR_sched_setattr (__NR_Linux + 334) #define __NR_sched_getattr (__NR_Linux + 335) +#define __NR_utimes (__NR_Linux + 336) -#define __NR_Linux_syscalls (__NR_sched_getattr + 1) +#define __NR_Linux_syscalls (__NR_utimes + 1) #define __IGNORE_select /* newselect */ #define __IGNORE_fadvise64 /* fadvise64_64 */ -#define __IGNORE_utimes /* utime */ #define HPUX_GATEWAY_ADDR 0xC0000004 diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index ac87a40502e6..a6ffc775a9f8 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -581,67 +581,3 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } } - -#ifdef CONFIG_PARISC_TMPALIAS - -void clear_user_highpage(struct page *page, unsigned long vaddr) -{ - void *vto; - unsigned long flags; - - /* Clear using TMPALIAS region. The page doesn't need to - be flushed but the kernel mapping needs to be purged. */ - - vto = kmap_atomic(page); - - /* The PA-RISC 2.0 Architecture book states on page F-6: - "Before a write-capable translation is enabled, *all* - non-equivalently-aliased translations must be removed - from the page table and purged from the TLB. (Note - that the caches are not required to be flushed at this - time.) Before any non-equivalent aliased translation - is re-enabled, the virtual address range for the writeable - page (the entire page) must be flushed from the cache, - and the write-capable translation removed from the page - table and purged from the TLB." */ - - purge_kernel_dcache_page_asm((unsigned long)vto); - purge_tlb_start(flags); - pdtlb_kernel(vto); - purge_tlb_end(flags); - preempt_disable(); - clear_user_page_asm(vto, vaddr); - preempt_enable(); - - pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */ -} - -void copy_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - void *vfrom, *vto; - unsigned long flags; - - /* Copy using TMPALIAS region. This has the advantage - that the `from' page doesn't need to be flushed. However, - the `to' page must be flushed in copy_user_page_asm since - it can be used to bring in executable code. */ - - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); - - purge_kernel_dcache_page_asm((unsigned long)vto); - purge_tlb_start(flags); - pdtlb_kernel(vto); - pdtlb_kernel(vfrom); - purge_tlb_end(flags); - preempt_disable(); - copy_user_page_asm(vto, vfrom, vaddr); - flush_dcache_page_asm(__pa(vto), vaddr); - preempt_enable(); - - pagefault_enable(); /* kunmap_atomic(addr, KM_USER1); */ - pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */ -} - -#endif /* CONFIG_PARISC_TMPALIAS */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 8fa3fbb3e4d3..80e5dd248934 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -431,6 +431,7 @@ ENTRY_SAME(finit_module) ENTRY_SAME(sched_setattr) ENTRY_SAME(sched_getattr) /* 335 */ + ENTRY_COMP(utimes) /* Nothing yet */ diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 6c0a955a1b06..3fb1bc432f4f 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -1,7 +1,8 @@ generic-y += clkdev.h +generic-y += hash.h +generic-y += mcs_spinlock.h +generic-y += preempt.h generic-y += rwsem.h generic-y += trace_clock.h -generic-y += preempt.h generic-y += vtime.h -generic-y += hash.h diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index d0b5fca6b077..c9202151079f 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -99,7 +99,6 @@ static inline int prrn_is_enabled(void) #ifdef CONFIG_SMP #include <asm/cputable.h> -#define smt_capable() (cpu_has_feature(CPU_FTR_SMT)) #ifdef CONFIG_PPC64 #include <asm/smp.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8d4c247f1738..af064d28b365 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1048,6 +1048,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); + /* + * Flush TM state out so we can copy it. __switch_to_tm() does this + * flush but it removes the checkpointed state from the current CPU and + * transitions the CPU out of TM mode. Hence we need to call + * tm_recheckpoint_new_task() (on the same task) to restore the + * checkpointed state back and the TM mode. + */ + __switch_to_tm(src); + tm_recheckpoint_new_task(src); *dst = *src; diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index 1482327cfeba..d88736fbece6 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index e66d4ec04d95..818dce344e82 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1504,73 +1504,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 1: addi r8,r8,16 .endr - /* Save DEC */ - mfspr r5,SPRN_DEC - mftb r6 - extsw r5,r5 - add r5,r5,r6 - std r5,VCPU_DEC_EXPIRES(r9) - -BEGIN_FTR_SECTION - b 8f -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) - /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - - /* Save POWER8-specific registers */ - mfspr r5, SPRN_IAMR - mfspr r6, SPRN_PSPB - mfspr r7, SPRN_FSCR - std r5, VCPU_IAMR(r9) - stw r6, VCPU_PSPB(r9) - std r7, VCPU_FSCR(r9) - mfspr r5, SPRN_IC - mfspr r6, SPRN_VTB - mfspr r7, SPRN_TAR - std r5, VCPU_IC(r9) - std r6, VCPU_VTB(r9) - std r7, VCPU_TAR(r9) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - mfspr r5, SPRN_TFHAR - mfspr r6, SPRN_TFIAR - mfspr r7, SPRN_TEXASR - std r5, VCPU_TFHAR(r9) - std r6, VCPU_TFIAR(r9) - std r7, VCPU_TEXASR(r9) -#endif - mfspr r8, SPRN_EBBHR - std r8, VCPU_EBBHR(r9) - mfspr r5, SPRN_EBBRR - mfspr r6, SPRN_BESCR - mfspr r7, SPRN_CSIGR - mfspr r8, SPRN_TACR - std r5, VCPU_EBBRR(r9) - std r6, VCPU_BESCR(r9) - std r7, VCPU_CSIGR(r9) - std r8, VCPU_TACR(r9) - mfspr r5, SPRN_TCSCR - mfspr r6, SPRN_ACOP - mfspr r7, SPRN_PID - mfspr r8, SPRN_WORT - std r5, VCPU_TCSCR(r9) - std r6, VCPU_ACOP(r9) - stw r7, VCPU_GUEST_PID(r9) - std r8, VCPU_WORT(r9) -8: - - /* Save and reset AMR and UAMOR before turning on the MMU */ -BEGIN_FTR_SECTION - mfspr r5,SPRN_AMR - mfspr r6,SPRN_UAMOR - std r5,VCPU_AMR(r9) - std r6,VCPU_UAMOR(r9) - li r6,0 - mtspr SPRN_AMR,r6 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - /* Unset guest mode */ li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) @@ -2203,7 +2136,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif mfspr r6,SPRN_VRSAVE - stw r6,VCPU_VRSAVE(r3) + stw r6,VCPU_VRSAVE(r31) mtlr r30 mtmsrd r5 isync @@ -2240,7 +2173,7 @@ BEGIN_FTR_SECTION bl .load_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif - lwz r7,VCPU_VRSAVE(r4) + lwz r7,VCPU_VRSAVE(r31) mtspr SPRN_VRSAVE,r7 mtlr r30 mr r4,r31 diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 5ec1e47a0d77..e865d748179b 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -123,7 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order) area->nid = nid; area->order = order; - area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE, + area->pages = alloc_pages_exact_node(area->nid, + GFP_KERNEL|__GFP_THISNODE, area->order); if (!area->pages) { diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 49318385d4fa..4a0a64fe25df 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -83,7 +83,6 @@ static struct timer_list spuloadavg_timer; #define MIN_SPU_TIMESLICE max(5 * HZ / (1000 * SPUSCHED_TICK), 1) #define DEF_SPU_TIMESLICE (100 * HZ / (1000 * SPUSCHED_TICK)) -#define MAX_USER_PRIO (MAX_PRIO - MAX_RT_PRIO) #define SCALE_PRIO(x, prio) \ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_SPU_TIMESLICE) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 110f4fbd319f..81a7a0a79be7 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -26,7 +26,6 @@ #include <linux/of_fdt.h> #include <linux/interrupt.h> #include <linux/bug.h> -#include <linux/cpuidle.h> #include <linux/pci.h> #include <asm/machdep.h> @@ -225,16 +224,6 @@ static int __init pnv_probe(void) return 1; } -void powernv_idle(void) -{ - /* Hook to cpuidle framework if available, else - * call on default platform idle code - */ - if (cpuidle_idle_call()) { - power7_idle(); - } -} - define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -244,7 +233,7 @@ define_machine(powernv) { .show_cpuinfo = pnv_show_cpuinfo, .progress = pnv_progress, .machine_shutdown = pnv_shutdown, - .power_save = powernv_idle, + .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 972df0ffd4dc..2db8cc691bf4 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -39,7 +39,6 @@ #include <linux/irq.h> #include <linux/seq_file.h> #include <linux/root_dev.h> -#include <linux/cpuidle.h> #include <linux/of.h> #include <linux/kexec.h> @@ -356,29 +355,24 @@ early_initcall(alloc_dispatch_log_kmem_cache); static void pseries_lpar_idle(void) { - /* This would call on the cpuidle framework, and the back-end pseries - * driver to go to idle states + /* + * Default handler to go into low thread priority and possibly + * low power mode by cedeing processor to hypervisor */ - if (cpuidle_idle_call()) { - /* On error, execute default handler - * to go into low thread priority and possibly - * low power mode by cedeing processor to hypervisor - */ - /* Indicate to hypervisor that we are idle. */ - get_lppaca()->idle = 1; + /* Indicate to hypervisor that we are idle. */ + get_lppaca()->idle = 1; - /* - * Yield the processor to the hypervisor. We return if - * an external interrupt occurs (which are driven prior - * to returning here) or if a prod occurs from another - * processor. When returning here, external interrupts - * are enabled. - */ - cede_processor(); + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + cede_processor(); - get_lppaca()->idle = 0; - } + get_lppaca()->idle = 0; } /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 65a07750f4f9..bb74b21f007a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -117,6 +117,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 8386a4a1f19a..57892a8a9055 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,6 +1,7 @@ generic-y += clkdev.h -generic-y += trace_clock.h -generic-y += preempt.h generic-y += hash.h +generic-y += mcs_spinlock.h +generic-y += preempt.h +generic-y += trace_clock.h diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index 146b9d5e89f8..4630cf217b5b 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -1,10 +1,11 @@ header-y += + generic-y += barrier.h generic-y += clkdev.h generic-y += hash.h +generic-y += mcs_spinlock.h +generic-y += preempt.h generic-y += trace_clock.h generic-y += xor.h -generic-y += preempt.h - diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 0cd7198a4524..c19e47dacb31 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -8,18 +8,21 @@ generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h generic-y += fcntl.h +generic-y += hash.h generic-y += ioctl.h generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kvm_para.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h +generic-y += mman.h +generic-y += msgbuf.h generic-y += param.h generic-y += parport.h generic-y += percpu.h generic-y += poll.h -generic-y += mman.h -generic-y += msgbuf.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sembuf.h @@ -34,5 +37,3 @@ generic-y += termios.h generic-y += trace_clock.h generic-y += ucontext.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h index 673515bc4135..aa1b2b9088a7 100644 --- a/arch/sh/include/cpu-sh2/cpu/cache.h +++ b/arch/sh/include/cpu-sh2/cpu/cache.h @@ -18,7 +18,7 @@ #define SH_CACHE_ASSOC 8 #if defined(CONFIG_CPU_SUBTYPE_SH7619) -#define CCR 0xffffffec +#define SH_CCR 0xffffffec #define CCR_CACHE_CE 0x01 /* Cache enable */ #define CCR_CACHE_WT 0x02 /* CCR[bit1=1,bit2=1] */ diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h index defb0baa5a06..b27ce92cb600 100644 --- a/arch/sh/include/cpu-sh2a/cpu/cache.h +++ b/arch/sh/include/cpu-sh2a/cpu/cache.h @@ -17,8 +17,8 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xfffc1000 /* CCR1 */ -#define CCR2 0xfffc1004 +#define SH_CCR 0xfffc1000 /* CCR1 */ +#define SH_CCR2 0xfffc1004 /* * Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h index bee2d81c56bf..29700fd88c75 100644 --- a/arch/sh/include/cpu-sh3/cpu/cache.h +++ b/arch/sh/include/cpu-sh3/cpu/cache.h @@ -17,7 +17,7 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xffffffec /* Address of Cache Control Register */ +#define SH_CCR 0xffffffec /* Address of Cache Control Register */ #define CCR_CACHE_CE 0x01 /* Cache Enable */ #define CCR_CACHE_WT 0x02 /* Write-Through (for P0,U0,P3) (else writeback) */ diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h index 7bfb9e8b069c..92c4cd119b66 100644 --- a/arch/sh/include/cpu-sh4/cpu/cache.h +++ b/arch/sh/include/cpu-sh4/cpu/cache.h @@ -17,7 +17,7 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xff00001c /* Address of Cache Control Register */ +#define SH_CCR 0xff00001c /* Address of Cache Control Register */ #define CCR_CACHE_OCE 0x0001 /* Operand Cache Enable */ #define CCR_CACHE_WT 0x0002 /* Write-Through (for P0,U0,P3) (else writeback)*/ #define CCR_CACHE_CB 0x0004 /* Copy-Back (for P1) (else writethrough) */ diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c index ecf83cd158dc..0d7360d549c1 100644 --- a/arch/sh/kernel/cpu/init.c +++ b/arch/sh/kernel/cpu/init.c @@ -112,7 +112,7 @@ static void cache_init(void) unsigned long ccr, flags; jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); /* * At this point we don't know whether the cache is enabled or not - a @@ -189,7 +189,7 @@ static void cache_init(void) l2_cache_init(); - __raw_writel(flags, CCR); + __raw_writel(flags, SH_CCR); back_to_cached(); } #else diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 2ea4483fd722..be616ee0cf87 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -16,7 +16,6 @@ #include <linux/thread_info.h> #include <linux/irqflags.h> #include <linux/smp.h> -#include <linux/cpuidle.h> #include <linux/atomic.h> #include <asm/pgalloc.h> #include <asm/smp.h> @@ -40,8 +39,7 @@ void arch_cpu_idle_dead(void) void arch_cpu_idle(void) { - if (cpuidle_idle_call()) - sh_idle(); + sh_idle(); } void __init select_idle_routine(void) diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 115725198038..777e50f33c00 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -36,7 +36,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) */ jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); if ((ccr & CCR_CACHE_ENABLE) == 0) { back_to_cached(); diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c index defcf719f2e8..a74259f2f981 100644 --- a/arch/sh/mm/cache-sh2.c +++ b/arch/sh/mm/cache-sh2.c @@ -63,9 +63,9 @@ static void sh2__flush_invalidate_region(void *start, int size) local_irq_save(flags); jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); ccr |= CCR_CACHE_INVALIDATE; - __raw_writel(ccr, CCR); + __raw_writel(ccr, SH_CCR); back_to_cached(); local_irq_restore(flags); diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c index 949e2d3138a0..ee87d081259b 100644 --- a/arch/sh/mm/cache-sh2a.c +++ b/arch/sh/mm/cache-sh2a.c @@ -134,7 +134,8 @@ static void sh2a__flush_invalidate_region(void *start, int size) /* If there are too many pages then just blow the cache */ if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) { - __raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR); + __raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE, + SH_CCR); } else { for (v = begin; v < end; v += L1_CACHE_BYTES) sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v); @@ -167,7 +168,8 @@ static void sh2a_flush_icache_range(void *args) /* I-Cache invalidate */ /* If there are too many pages then just blow the cache */ if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) { - __raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR); + __raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE, + SH_CCR); } else { for (v = start; v < end; v += L1_CACHE_BYTES) sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v); diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 0e529285b28d..51d8f7f31d1d 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -133,9 +133,9 @@ static void flush_icache_all(void) jump_to_uncached(); /* Flush I-cache */ - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); ccr |= CCR_CACHE_ICI; - __raw_writel(ccr, CCR); + __raw_writel(ccr, SH_CCR); /* * back_to_cached() will take care of the barrier for us, don't add diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c index c0adbee97b5f..24c58b7dc022 100644 --- a/arch/sh/mm/cache-shx3.c +++ b/arch/sh/mm/cache-shx3.c @@ -19,7 +19,7 @@ void __init shx3_cache_init(void) { unsigned int ccr; - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); /* * If we've got cache aliases, resolve them in hardware. @@ -40,5 +40,5 @@ void __init shx3_cache_init(void) ccr |= CCR_CACHE_IBE; #endif - writel_uncached(ccr, CCR); + writel_uncached(ccr, SH_CCR); } diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 616966a96cba..097c2cdd117f 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -285,8 +285,8 @@ void __init cpu_cache_init(void) { unsigned int cache_disabled = 0; -#ifdef CCR - cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE); +#ifdef SH_CCR + cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE); #endif compute_alias(&boot_cpu_data.icache); diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 4b60a0c325ec..a45821818003 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -6,15 +6,16 @@ generic-y += cputime.h generic-y += div64.h generic-y += emergency-restart.h generic-y += exec.h -generic-y += linkage.h -generic-y += local64.h -generic-y += mutex.h +generic-y += hash.h generic-y += irq_regs.h +generic-y += linkage.h generic-y += local.h +generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += module.h +generic-y += mutex.h +generic-y += preempt.h generic-y += serial.h generic-y += trace_clock.h generic-y += types.h generic-y += word-at-a-time.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index dd3bef4b9896..05710393959f 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -32,7 +32,6 @@ DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); extern cpumask_t cpu_core_map[NR_CPUS]; -extern int sparc64_multi_core; extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index 1754390a426f..a2d10fc64faf 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -42,8 +42,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus) #define topology_core_id(cpu) (cpu_data(cpu).core_id) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) #define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) -#define mc_capable() (sparc64_multi_core) -#define smt_capable() (sparc64_multi_core) #endif /* CONFIG_SMP */ extern cpumask_t cpu_core_map[NR_CPUS]; diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index b90bf23e3aab..a1a4400d4025 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -896,10 +896,6 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask) mdesc_iterate_over_cpus(fill_in_one_cpu, NULL, mask); -#ifdef CONFIG_SMP - sparc64_multi_core = 1; -#endif - hp = mdesc_grab(); set_core_ids(hp); diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 32a280ec38c1..d7b4967f8fa6 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -58,9 +58,12 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); + local_irq_enable(); } else { unsigned long pstate; + local_irq_enable(); + /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. */ @@ -82,7 +85,6 @@ void arch_cpu_idle(void) : "=&r" (pstate) : "i" (PSTATE_IE)); } - local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 6b39125eb927..9a690d39c01b 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -555,9 +555,6 @@ static void *fill_in_one_cpu(struct device_node *dp, int cpuid, int arg) cpu_data(cpuid).core_id = portid + 1; cpu_data(cpuid).proc_id = portid; -#ifdef CONFIG_SMP - sparc64_multi_core = 1; -#endif } else { cpu_data(cpuid).dcache_size = of_getintprop_default(dp, "dcache-size", 16 * 1024); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b085311dcd0e..9781048161ab 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -53,8 +53,6 @@ #include "cpumap.h" -int sparc64_multi_core __read_mostly; - DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE; cpumask_t cpu_core_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = CPU_MASK_NONE }; diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index 87729fff13b9..33a17e7b3ccd 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -189,7 +189,8 @@ linux_sparc_syscall32: mov %i0, %l5 ! IEU1 5: call %l7 ! CTI Group brk forced srl %i5, 0, %o5 ! IEU1 - ba,a,pt %xcc, 3f + ba,pt %xcc, 3f + sra %o0, 0, %o0 /* Linux native system calls enter here... */ .align 32 @@ -217,7 +218,6 @@ linux_sparc_syscall: 3: stx %o0, [%sp + PTREGS_OFF + PT_V9_I0] ret_sys_call: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %g3 - sra %o0, 0, %o0 mov %ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2 sllx %g2, 32, %g2 diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 3b3a360b429a..f5d506fdddad 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -273,7 +273,7 @@ void __init pgtable_cache_init(void) prom_halt(); } - for (i = 0; i < 8; i++) { + for (i = 0; i < ARRAY_SIZE(tsb_cache_names); i++) { unsigned long size = 8192 << i; const char *name = tsb_cache_names[i]; diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 3793c75e45d9..0aa5675e7025 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -11,6 +11,7 @@ generic-y += errno.h generic-y += exec.h generic-y += fb.h generic-y += fcntl.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -18,12 +19,14 @@ generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += msgbuf.h generic-y += mutex.h generic-y += param.h generic-y += parport.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sembuf.h @@ -38,5 +41,3 @@ generic-y += termios.h generic-y += trace_clock.h generic-y += types.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 88a330dcdede..a5e4b6068213 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,8 +1,28 @@ -generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h -generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h -generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h -generic-y += switch_to.h clkdev.h -generic-y += trace_clock.h -generic-y += preempt.h -generic-y += hash.h generic-y += barrier.h +generic-y += bug.h +generic-y += clkdev.h +generic-y += cputime.h +generic-y += current.h +generic-y += delay.h +generic-y += device.h +generic-y += emergency-restart.h +generic-y += exec.h +generic-y += ftrace.h +generic-y += futex.h +generic-y += hardirq.h +generic-y += hash.h +generic-y += hw_irq.h +generic-y += io.h +generic-y += irq_regs.h +generic-y += kdebug.h +generic-y += mcs_spinlock.h +generic-y += mutex.h +generic-y += param.h +generic-y += pci.h +generic-y += percpu.h +generic-y += preempt.h +generic-y += sections.h +generic-y += switch_to.h +generic-y += topology.h +generic-y += trace_clock.h +generic-y += xor.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 3ef4f9d9bf5d..1e5fb872a4aa 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += fcntl.h generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -24,6 +25,7 @@ generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += local.h +generic-y += mcs_spinlock.h generic-y += mman.h generic-y += module.h generic-y += msgbuf.h @@ -32,6 +34,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -60,5 +63,3 @@ generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0af5250d914f..8453fe1342ea 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1585,6 +1585,20 @@ config EFI_STUB See Documentation/efi-stub.txt for more information. +config EFI_MIXED + bool "EFI mixed-mode support" + depends on EFI_STUB && X86_64 + ---help--- + Enabling this feature allows a 64-bit kernel to be booted + on a 32-bit firmware, provided that your CPU supports 64-bit + mode. + + Note that it is not possible to boot a mixed-mode enabled + kernel via the EFI boot stub - a bootloader that supports + the EFI handover protocol must be used. + + If unsure, say N. + config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index c026cca5602c..f3aaf231b4e5 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -341,10 +341,6 @@ config X86_USE_3DNOW def_bool y depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML -config X86_OOSTORE - def_bool y - depends on (MWINCHIP3D || MWINCHIPC6) && MTRR - # # P6_NOPs are a relatively minor optimization that require a family >= # 6 processor, except that it is broken on certain VIA chips. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 321a52ccf63a..61bd2ad94281 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -81,6 +81,15 @@ config X86_PTDUMP kernel. If in doubt, say "N" +config EFI_PGT_DUMP + bool "Dump the EFI pagetable" + depends on EFI && X86_PTDUMP + ---help--- + Enable this if you want to dump the EFI page table before + enabling virtual mode. This can be used to debug miscellaneous + issues with the mapping of the EFI runtime regions into that + table. + config DEBUG_RODATA bool "Write protect kernel read-only data structures" default y diff --git a/arch/x86/Makefile b/arch/x86/Makefile index eeda43abed6e..3b9348a0c1a4 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -82,8 +82,8 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 - # Don't autogenerate MMX or SSE instructions - KBUILD_CFLAGS += -mno-mmx -mno-sse + # Don't autogenerate traditional x87, MMX or SSE instructions + KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387 # Use -mpreferred-stack-boundary=3 if supported. KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) @@ -152,6 +152,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI # does binutils support specific instructions? asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1) +asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 878df7e88cd4..abb9eba61b50 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -80,7 +80,7 @@ targets += voffset.h $(obj)/voffset.h: vmlinux FORCE $(call if_changed,voffset) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index a7677babf946..1e6146137f8e 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -19,10 +19,272 @@ static efi_system_table_t *sys_table; +static struct efi_config *efi_early; + +#define efi_call_early(f, ...) \ + efi_early->call(efi_early->f, __VA_ARGS__); + +#define BOOT_SERVICES(bits) \ +static void setup_boot_services##bits(struct efi_config *c) \ +{ \ + efi_system_table_##bits##_t *table; \ + efi_boot_services_##bits##_t *bt; \ + \ + table = (typeof(table))sys_table; \ + \ + c->text_output = table->con_out; \ + \ + bt = (typeof(bt))(unsigned long)(table->boottime); \ + \ + c->allocate_pool = bt->allocate_pool; \ + c->allocate_pages = bt->allocate_pages; \ + c->get_memory_map = bt->get_memory_map; \ + c->free_pool = bt->free_pool; \ + c->free_pages = bt->free_pages; \ + c->locate_handle = bt->locate_handle; \ + c->handle_protocol = bt->handle_protocol; \ + c->exit_boot_services = bt->exit_boot_services; \ +} +BOOT_SERVICES(32); +BOOT_SERVICES(64); -#include "../../../../drivers/firmware/efi/efi-stub-helper.c" +static void efi_printk(efi_system_table_t *, char *); +static void efi_char16_printk(efi_system_table_t *, efi_char16_t *); + +static efi_status_t +__file_size32(void *__fh, efi_char16_t *filename_16, + void **handle, u64 *file_sz) +{ + efi_file_handle_32_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + u32 info_sz; + + status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to open file: "); + efi_char16_printk(sys_table, filename_16); + efi_printk(sys_table, "\n"); + return status; + } + + *handle = h; + + info_sz = 0; + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table, "Failed to get file info size\n"); + return status; + } + +grow: + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for file info\n"); + return status; + } + + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_early(free_pool, info); + goto grow; + } + + *file_sz = info->file_size; + efi_call_early(free_pool, info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to get initrd info\n"); + + return status; +} + +static efi_status_t +__file_size64(void *__fh, efi_char16_t *filename_16, + void **handle, u64 *file_sz) +{ + efi_file_handle_64_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + u32 info_sz; + status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to open file: "); + efi_char16_printk(sys_table, filename_16); + efi_printk(sys_table, "\n"); + return status; + } + *handle = h; + + info_sz = 0; + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table, "Failed to get file info size\n"); + return status; + } + +grow: + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for file info\n"); + return status; + } + + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_early(free_pool, info); + goto grow; + } + + *file_sz = info->file_size; + efi_call_early(free_pool, info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to get initrd info\n"); + + return status; +} +static efi_status_t +efi_file_size(efi_system_table_t *sys_table, void *__fh, + efi_char16_t *filename_16, void **handle, u64 *file_sz) +{ + if (efi_early->is64) + return __file_size64(__fh, filename_16, handle, file_sz); + + return __file_size32(__fh, filename_16, handle, file_sz); +} + +static inline efi_status_t +efi_file_read(void *__fh, void *handle, unsigned long *size, void *addr) +{ + unsigned long func; + + if (efi_early->is64) { + efi_file_handle_64_t *fh = __fh; + + func = (unsigned long)fh->read; + return efi_early->call(func, handle, size, addr); + } else { + efi_file_handle_32_t *fh = __fh; + + func = (unsigned long)fh->read; + return efi_early->call(func, handle, size, addr); + } +} + +static inline efi_status_t efi_file_close(void *__fh, void *handle) +{ + if (efi_early->is64) { + efi_file_handle_64_t *fh = __fh; + + return efi_early->call((unsigned long)fh->close, handle); + } else { + efi_file_handle_32_t *fh = __fh; + + return efi_early->call((unsigned long)fh->close, handle); + } +} + +static inline efi_status_t __open_volume32(void *__image, void **__fh) +{ + efi_file_io_interface_t *io; + efi_loaded_image_32_t *image = __image; + efi_file_handle_32_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)image->device_handle; + unsigned long func; + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to handle fs_proto\n"); + return status; + } + + func = (unsigned long)io->open_volume; + status = efi_early->call(func, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to open volume\n"); + + *__fh = fh; + return status; +} + +static inline efi_status_t __open_volume64(void *__image, void **__fh) +{ + efi_file_io_interface_t *io; + efi_loaded_image_64_t *image = __image; + efi_file_handle_64_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)image->device_handle; + unsigned long func; + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to handle fs_proto\n"); + return status; + } + + func = (unsigned long)io->open_volume; + status = efi_early->call(func, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to open volume\n"); + + *__fh = fh; + return status; +} + +static inline efi_status_t +efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) +{ + if (efi_early->is64) + return __open_volume64(__image, __fh); + + return __open_volume32(__image, __fh); +} + +static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) +{ + unsigned long output_string; + size_t offset; + + if (efi_early->is64) { + struct efi_simple_text_output_protocol_64 *out; + u64 *func; + + offset = offsetof(typeof(*out), output_string); + output_string = efi_early->text_output + offset; + func = (u64 *)output_string; + + efi_early->call(*func, efi_early->text_output, str); + } else { + struct efi_simple_text_output_protocol_32 *out; + u32 *func; + + offset = offsetof(typeof(*out), output_string); + output_string = efi_early->text_output + offset; + func = (u32 *)output_string; + + efi_early->call(*func, efi_early->text_output, str); + } +} + +#include "../../../../drivers/firmware/efi/efi-stub-helper.c" static void find_bits(unsigned long mask, u8 *pos, u8 *size) { @@ -47,105 +309,97 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } -static efi_status_t setup_efi_pci(struct boot_params *params) +static efi_status_t +__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) { - efi_pci_io_protocol *pci; + struct pci_setup_rom *rom = NULL; efi_status_t status; - void **pci_handle; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - unsigned long nr_pci, size = 0; - int i; - struct setup_data *data; + unsigned long size; + uint64_t attributes; - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + status = efi_early->call(pci->attributes, pci, + EfiPciIoAttributeOperationGet, 0, 0, + &attributes); + if (status != EFI_SUCCESS) + return status; - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; + if (!pci->romimage || !pci->romsize) + return EFI_INVALID_PARAMETER; - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &size, pci_handle); + size = pci->romsize + sizeof(*rom); - if (status == EFI_BUFFER_TOO_SMALL) { - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, size, &pci_handle); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); + if (status != EFI_SUCCESS) + return status; - if (status != EFI_SUCCESS) - return status; + memset(rom, 0, sizeof(*rom)); - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &size, pci_handle); - } + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; + *__rom = rom; - if (status != EFI_SUCCESS) - goto free_handle; - - nr_pci = size / sizeof(void *); - for (i = 0; i < nr_pci; i++) { - void *h = pci_handle[i]; - uint64_t attributes; - struct pci_setup_rom *rom; + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &(rom->vendor)); - status = efi_call_phys3(sys_table->boottime->handle_protocol, - h, &pci_proto, &pci); + if (status != EFI_SUCCESS) + goto free_struct; - if (status != EFI_SUCCESS) - continue; + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &(rom->devid)); - if (!pci) - continue; + if (status != EFI_SUCCESS) + goto free_struct; -#ifdef CONFIG_X86_64 - status = efi_call_phys4(pci->attributes, pci, - EfiPciIoAttributeOperationGet, 0, - &attributes); -#else - status = efi_call_phys5(pci->attributes, pci, - EfiPciIoAttributeOperationGet, 0, 0, - &attributes); -#endif - if (status != EFI_SUCCESS) - continue; + status = efi_early->call(pci->get_location, pci, &(rom->segment), + &(rom->bus), &(rom->device), &(rom->function)); - if (!pci->romimage || !pci->romsize) - continue; + if (status != EFI_SUCCESS) + goto free_struct; - size = pci->romsize + sizeof(*rom); + memcpy(rom->romdata, pci->romimage, pci->romsize); + return status; - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, size, &rom); +free_struct: + efi_call_early(free_pool, rom); + return status; +} - if (status != EFI_SUCCESS) - continue; +static efi_status_t +setup_efi_pci32(struct boot_params *params, void **pci_handle, + unsigned long size) +{ + efi_pci_io_protocol_32 *pci = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + u32 *handles = (u32 *)(unsigned long)pci_handle; + efi_status_t status; + unsigned long nr_pci; + struct setup_data *data; + int i; - rom->data.type = SETUP_PCI; - rom->data.len = size - sizeof(struct setup_data); - rom->data.next = 0; - rom->pcilen = pci->romsize; + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - status = efi_call_phys5(pci->pci.read, pci, - EfiPciIoWidthUint16, PCI_VENDOR_ID, - 1, &(rom->vendor)); + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; - if (status != EFI_SUCCESS) - goto free_struct; + nr_pci = size / sizeof(u32); + for (i = 0; i < nr_pci; i++) { + struct pci_setup_rom *rom = NULL; + u32 h = handles[i]; - status = efi_call_phys5(pci->pci.read, pci, - EfiPciIoWidthUint16, PCI_DEVICE_ID, - 1, &(rom->devid)); + status = efi_call_early(handle_protocol, h, + &pci_proto, (void **)&pci); if (status != EFI_SUCCESS) - goto free_struct; + continue; - status = efi_call_phys5(pci->get_location, pci, - &(rom->segment), &(rom->bus), - &(rom->device), &(rom->function)); + if (!pci) + continue; + status = __setup_efi_pci32(pci, &rom); if (status != EFI_SUCCESS) - goto free_struct; - - memcpy(rom->romdata, pci->romimage, pci->romsize); + continue; if (data) data->next = (unsigned long)rom; @@ -154,105 +408,155 @@ static efi_status_t setup_efi_pci(struct boot_params *params) data = (struct setup_data *)rom; - continue; - free_struct: - efi_call_phys1(sys_table->boottime->free_pool, rom); } -free_handle: - efi_call_phys1(sys_table->boottime->free_pool, pci_handle); return status; } -/* - * See if we have Graphics Output Protocol - */ -static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size) +static efi_status_t +__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom) { - struct efi_graphics_output_protocol *gop, *first_gop; - struct efi_pixel_bitmask pixel_info; - unsigned long nr_gops; + struct pci_setup_rom *rom; efi_status_t status; - void **gop_handle; - u16 width, height; - u32 fb_base, fb_size; - u32 pixels_per_scan_line; - int pixel_format; - int i; + unsigned long size; + uint64_t attributes; - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, size, &gop_handle); + status = efi_early->call(pci->attributes, pci, + EfiPciIoAttributeOperationGet, 0, + &attributes); if (status != EFI_SUCCESS) return status; - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, proto, - NULL, &size, gop_handle); + if (!pci->romimage || !pci->romsize) + return EFI_INVALID_PARAMETER; + + size = pci->romsize + sizeof(*rom); + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); if (status != EFI_SUCCESS) - goto free_handle; + return status; - first_gop = NULL; + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; + *__rom = rom; - nr_gops = size / sizeof(void *); - for (i = 0; i < nr_gops; i++) { - struct efi_graphics_output_mode_info *info; - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; - bool conout_found = false; - void *dummy; - void *h = gop_handle[i]; + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &(rom->vendor)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &(rom->devid)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->get_location, pci, &(rom->segment), + &(rom->bus), &(rom->device), &(rom->function)); + + if (status != EFI_SUCCESS) + goto free_struct; + + memcpy(rom->romdata, pci->romimage, pci->romsize); + return status; + +free_struct: + efi_call_early(free_pool, rom); + return status; + +} + +static efi_status_t +setup_efi_pci64(struct boot_params *params, void **pci_handle, + unsigned long size) +{ + efi_pci_io_protocol_64 *pci = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + u64 *handles = (u64 *)(unsigned long)pci_handle; + efi_status_t status; + unsigned long nr_pci; + struct setup_data *data; + int i; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / sizeof(u64); + for (i = 0; i < nr_pci; i++) { + struct pci_setup_rom *rom = NULL; + u64 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + &pci_proto, (void **)&pci); - status = efi_call_phys3(sys_table->boottime->handle_protocol, - h, proto, &gop); if (status != EFI_SUCCESS) continue; - status = efi_call_phys3(sys_table->boottime->handle_protocol, - h, &conout_proto, &dummy); + if (!pci) + continue; - if (status == EFI_SUCCESS) - conout_found = true; + status = __setup_efi_pci64(pci, &rom); + if (status != EFI_SUCCESS) + continue; - status = efi_call_phys4(gop->query_mode, gop, - gop->mode->mode, &size, &info); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { - /* - * Systems that use the UEFI Console Splitter may - * provide multiple GOP devices, not all of which are - * backed by real hardware. The workaround is to search - * for a GOP implementing the ConOut protocol, and if - * one isn't found, to just fall back to the first GOP. - */ - width = info->horizontal_resolution; - height = info->vertical_resolution; - fb_base = gop->mode->frame_buffer_base; - fb_size = gop->mode->frame_buffer_size; - pixel_format = info->pixel_format; - pixel_info = info->pixel_information; - pixels_per_scan_line = info->pixels_per_scan_line; + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; - /* - * Once we've found a GOP supporting ConOut, - * don't bother looking any further. - */ - first_gop = gop; - if (conout_found) - break; - } } - /* Did we find any GOPs? */ - if (!first_gop) + return status; +} + +static efi_status_t setup_efi_pci(struct boot_params *params) +{ + efi_status_t status; + void **pci_handle = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + unsigned long size = 0; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); + + if (status == EFI_BUFFER_TOO_SMALL) { + status = efi_call_early(allocate_pool, + EFI_LOADER_DATA, + size, (void **)&pci_handle); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, &pci_proto, + NULL, &size, pci_handle); + } + + if (status != EFI_SUCCESS) goto free_handle; - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; + if (efi_early->is64) + status = setup_efi_pci64(params, pci_handle, size); + else + status = setup_efi_pci32(params, pci_handle, size); - si->lfb_width = width; - si->lfb_height = height; - si->lfb_base = fb_base; - si->pages = 1; +free_handle: + efi_call_early(free_pool, pci_handle); + return status; +} +static void +setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, + struct efi_pixel_bitmask pixel_info, int pixel_format) +{ if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { si->lfb_depth = 32; si->lfb_linelength = pixels_per_scan_line * 4; @@ -297,62 +601,319 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, si->rsvd_size = 0; si->rsvd_pos = 0; } +} + +static efi_status_t +__gop_query32(struct efi_graphics_output_protocol_32 *gop32, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u32 *fb_base) +{ + struct efi_graphics_output_protocol_mode_32 *mode; + efi_status_t status; + unsigned long m; + + m = gop32->mode; + mode = (struct efi_graphics_output_protocol_mode_32 *)m; + + status = efi_early->call(gop32->query_mode, gop32, + mode->mode, size, info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop32(struct screen_info *si, efi_guid_t *proto, + unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_32 *gop32, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status; + u32 *handles = (u32 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop32 = NULL; + + nr_gops = size / sizeof(u32); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + u32 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop32); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query32(gop32, &info, &size, &fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + pixel_format = info->pixel_format; + pixel_info = info->pixel_information; + pixels_per_scan_line = info->pixels_per_scan_line; + + /* + * Once we've found a GOP supporting ConOut, + * don't bother looking any further. + */ + first_gop = gop32; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); si->lfb_size = si->lfb_linelength * si->lfb_height; si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: + return status; +} -free_handle: - efi_call_phys1(sys_table->boottime->free_pool, gop_handle); +static efi_status_t +__gop_query64(struct efi_graphics_output_protocol_64 *gop64, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u32 *fb_base) +{ + struct efi_graphics_output_protocol_mode_64 *mode; + efi_status_t status; + unsigned long m; + + m = gop64->mode; + mode = (struct efi_graphics_output_protocol_mode_64 *)m; + + status = efi_early->call(gop64->query_mode, gop64, + mode->mode, size, info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop64(struct screen_info *si, efi_guid_t *proto, + unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_64 *gop64, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status; + u64 *handles = (u64 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop64 = NULL; + + nr_gops = size / sizeof(u64); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + u64 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop64); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query64(gop64, &info, &size, &fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + pixel_format = info->pixel_format; + pixel_info = info->pixel_information; + pixels_per_scan_line = info->pixels_per_scan_line; + + /* + * Once we've found a GOP supporting ConOut, + * don't bother looking any further. + */ + first_gop = gop64; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); + + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: return status; } /* - * See if we have Universal Graphics Adapter (UGA) protocol + * See if we have Graphics Output Protocol */ -static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, +static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, unsigned long size) { - struct efi_uga_draw_protocol *uga, *first_uga; - unsigned long nr_ugas; efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - int i; + void **gop_handle = NULL; - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, size, &uga_handle); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&gop_handle); if (status != EFI_SUCCESS) return status; - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, uga_proto, - NULL, &size, uga_handle); + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + proto, NULL, &size, gop_handle); if (status != EFI_SUCCESS) goto free_handle; + if (efi_early->is64) + status = setup_gop64(si, proto, size, gop_handle); + else + status = setup_gop32(si, proto, size, gop_handle); + +free_handle: + efi_call_early(free_pool, gop_handle); + return status; +} + +static efi_status_t +setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) +{ + struct efi_uga_draw_protocol *uga = NULL, *first_uga; + efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + unsigned long nr_ugas; + u32 *handles = (u32 *)uga_handle;; + efi_status_t status; + int i; + first_uga = NULL; + nr_ugas = size / sizeof(u32); + for (i = 0; i < nr_ugas; i++) { + efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; + u32 w, h, depth, refresh; + void *pciio; + u32 handle = handles[i]; + + status = efi_call_early(handle_protocol, handle, + &uga_proto, (void **)&uga); + if (status != EFI_SUCCESS) + continue; + + efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); + + status = efi_early->call((unsigned long)uga->get_mode, uga, + &w, &h, &depth, &refresh); + if (status == EFI_SUCCESS && (!first_uga || pciio)) { + *width = w; + *height = h; + + /* + * Once we've found a UGA supporting PCIIO, + * don't bother looking any further. + */ + if (pciio) + break; - nr_ugas = size / sizeof(void *); + first_uga = uga; + } + } + + return status; +} + +static efi_status_t +setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) +{ + struct efi_uga_draw_protocol *uga = NULL, *first_uga; + efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + unsigned long nr_ugas; + u64 *handles = (u64 *)uga_handle;; + efi_status_t status; + int i; + + first_uga = NULL; + nr_ugas = size / sizeof(u64); for (i = 0; i < nr_ugas; i++) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - void *handle = uga_handle[i]; u32 w, h, depth, refresh; void *pciio; + u64 handle = handles[i]; - status = efi_call_phys3(sys_table->boottime->handle_protocol, - handle, uga_proto, &uga); + status = efi_call_early(handle_protocol, handle, + &uga_proto, (void **)&uga); if (status != EFI_SUCCESS) continue; - efi_call_phys3(sys_table->boottime->handle_protocol, - handle, &pciio_proto, &pciio); + efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_call_phys5(uga->get_mode, uga, &w, &h, - &depth, &refresh); + status = efi_early->call((unsigned long)uga->get_mode, uga, + &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { - width = w; - height = h; + *width = w; + *height = h; /* * Once we've found a UGA supporting PCIIO, @@ -365,7 +926,39 @@ static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, } } - if (!first_uga) + return status; +} + +/* + * See if we have Universal Graphics Adapter (UGA) protocol + */ +static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, + unsigned long size) +{ + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&uga_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + height = 0; + width = 0; + + if (efi_early->is64) + status = setup_uga64(uga_handle, size, &width, &height); + else + status = setup_uga32(uga_handle, size, &width, &height); + + if (!width && !height) goto free_handle; /* EFI framebuffer */ @@ -384,9 +977,8 @@ static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, si->rsvd_size = 8; si->rsvd_pos = 24; - free_handle: - efi_call_phys1(sys_table->boottime->free_pool, uga_handle); + efi_call_early(free_pool, uga_handle); return status; } @@ -404,29 +996,28 @@ void setup_graphics(struct boot_params *boot_params) memset(si, 0, sizeof(*si)); size = 0; - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, &graphics_proto, - NULL, &size, gop_handle); + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + &graphics_proto, NULL, &size, gop_handle); if (status == EFI_BUFFER_TOO_SMALL) status = setup_gop(si, &graphics_proto, size); if (status != EFI_SUCCESS) { size = 0; - status = efi_call_phys5(sys_table->boottime->locate_handle, - EFI_LOCATE_BY_PROTOCOL, &uga_proto, - NULL, &size, uga_handle); + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + &uga_proto, NULL, &size, uga_handle); if (status == EFI_BUFFER_TOO_SMALL) setup_uga(si, &uga_proto, size); } } - /* * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create * one for us). */ -struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) +struct boot_params *make_boot_params(struct efi_config *c) { struct boot_params *boot_params; struct sys_desc_table *sdt; @@ -434,7 +1025,7 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) struct setup_header *hdr; struct efi_info *efi; efi_loaded_image_t *image; - void *options; + void *options, *handle; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; @@ -445,14 +1036,21 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) unsigned long ramdisk_addr; unsigned long ramdisk_size; - sys_table = _table; + efi_early = c; + sys_table = (efi_system_table_t *)(unsigned long)efi_early->table; + handle = (void *)(unsigned long)efi_early->image_handle; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) return NULL; - status = efi_call_phys3(sys_table->boottime->handle_protocol, - handle, &proto, (void *)&image); + if (efi_early->is64) + setup_boot_services64(efi_early); + else + setup_boot_services32(efi_early); + + status = efi_call_early(handle_protocol, handle, + &proto, (void *)&image); if (status != EFI_SUCCESS) { efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); return NULL; @@ -641,14 +1239,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, sizeof(struct e820entry) * nr_desc; if (*e820ext) { - efi_call_phys1(sys_table->boottime->free_pool, *e820ext); + efi_call_early(free_pool, *e820ext); *e820ext = NULL; *e820ext_size = 0; } - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, size, e820ext); - + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)e820ext); if (status == EFI_SUCCESS) *e820ext_size = size; @@ -656,12 +1253,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, } static efi_status_t exit_boot(struct boot_params *boot_params, - void *handle) + void *handle, bool is64) { struct efi_info *efi = &boot_params->efi_info; unsigned long map_sz, key, desc_size; efi_memory_desc_t *mem_map; struct setup_data *e820ext; + const char *signature; __u32 e820ext_size; __u32 nr_desc, prev_nr_desc; efi_status_t status; @@ -691,11 +1289,13 @@ get_map: if (status != EFI_SUCCESS) goto free_mem_map; - efi_call_phys1(sys_table->boottime->free_pool, mem_map); + efi_call_early(free_pool, mem_map); goto get_map; /* Allocated memory, get map again */ } - memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32)); + signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + memcpy(&efi->efi_loader_signature, signature, sizeof(__u32)); + efi->efi_systab = (unsigned long)sys_table; efi->efi_memdesc_size = desc_size; efi->efi_memdesc_version = desc_version; @@ -708,8 +1308,7 @@ get_map: #endif /* Might as well exit boot services now */ - status = efi_call_phys2(sys_table->boottime->exit_boot_services, - handle, key); + status = efi_call_early(exit_boot_services, handle, key); if (status != EFI_SUCCESS) { /* * ExitBootServices() will fail if any of the event @@ -722,7 +1321,7 @@ get_map: goto free_mem_map; called_exit = true; - efi_call_phys1(sys_table->boottime->free_pool, mem_map); + efi_call_early(free_pool, mem_map); goto get_map; } @@ -736,23 +1335,31 @@ get_map: return EFI_SUCCESS; free_mem_map: - efi_call_phys1(sys_table->boottime->free_pool, mem_map); + efi_call_early(free_pool, mem_map); return status; } - /* * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params *efi_main(void *handle, efi_system_table_t *_table, +struct boot_params *efi_main(struct efi_config *c, struct boot_params *boot_params) { - struct desc_ptr *gdt; + struct desc_ptr *gdt = NULL; efi_loaded_image_t *image; struct setup_header *hdr = &boot_params->hdr; efi_status_t status; struct desc_struct *desc; + void *handle; + efi_system_table_t *_table; + bool is64; + + efi_early = c; + + _table = (efi_system_table_t *)(unsigned long)efi_early->table; + handle = (void *)(unsigned long)efi_early->image_handle; + is64 = efi_early->is64; sys_table = _table; @@ -760,13 +1367,17 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; + if (is64) + setup_boot_services64(efi_early); + else + setup_boot_services32(efi_early); + setup_graphics(boot_params); setup_efi_pci(boot_params); - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, sizeof(*gdt), - (void **)&gdt); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + sizeof(*gdt), (void **)&gdt); if (status != EFI_SUCCESS) { efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); goto fail; @@ -797,7 +1408,7 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, hdr->code32_start = bzimage_addr; } - status = exit_boot(boot_params, handle); + status = exit_boot(boot_params, handle, is64); if (status != EFI_SUCCESS) goto fail; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 81b6b652b46a..c88c31ecad12 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -37,6 +37,24 @@ struct efi_graphics_output_mode_info { u32 pixels_per_scan_line; } __packed; +struct efi_graphics_output_protocol_mode_32 { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode_64 { + u32 max_mode; + u32 mode; + u64 info; + u64 size_of_info; + u64 frame_buffer_base; + u64 frame_buffer_size; +} __packed; + struct efi_graphics_output_protocol_mode { u32 max_mode; u32 mode; @@ -46,6 +64,20 @@ struct efi_graphics_output_protocol_mode { unsigned long frame_buffer_size; } __packed; +struct efi_graphics_output_protocol_32 { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; +}; + +struct efi_graphics_output_protocol_64 { + u64 query_mode; + u64 set_mode; + u64 blt; + u64 mode; +}; + struct efi_graphics_output_protocol { void *query_mode; unsigned long set_mode; @@ -53,10 +85,38 @@ struct efi_graphics_output_protocol { struct efi_graphics_output_protocol_mode *mode; }; +struct efi_uga_draw_protocol_32 { + u32 get_mode; + u32 set_mode; + u32 blt; +}; + +struct efi_uga_draw_protocol_64 { + u64 get_mode; + u64 set_mode; + u64 blt; +}; + struct efi_uga_draw_protocol { void *get_mode; void *set_mode; void *blt; }; +struct efi_config { + u64 image_handle; + u64 table; + u64 allocate_pool; + u64 allocate_pages; + u64 get_memory_map; + u64 free_pool; + u64 free_pages; + u64 locate_handle; + u64 handle_protocol; + u64 exit_boot_services; + u64 text_output; + efi_status_t (*call)(unsigned long, ...); + bool is64; +} __packed; + #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S index cedc60de86eb..7ff3632806b1 100644 --- a/arch/x86/boot/compressed/efi_stub_64.S +++ b/arch/x86/boot/compressed/efi_stub_64.S @@ -1 +1,30 @@ +#include <asm/segment.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> + #include "../../platform/efi/efi_stub_64.S" + +#ifdef CONFIG_EFI_MIXED + .code64 + .text +ENTRY(efi64_thunk) + push %rbp + push %rbx + + subq $16, %rsp + leaq efi_exit32(%rip), %rax + movl %eax, 8(%rsp) + leaq efi_gdt64(%rip), %rax + movl %eax, 4(%rsp) + movl %eax, 2(%rax) /* Fixup the gdt base address */ + leaq efi32_boot_gdt(%rip), %rax + movl %eax, (%rsp) + + call __efi64_thunk + + addq $16, %rsp + pop %rbx + pop %rbp + ret +ENDPROC(efi64_thunk) +#endif /* CONFIG_EFI_MIXED */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 9116aac232c7..de9d4200d305 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -42,26 +42,53 @@ ENTRY(startup_32) ENTRY(efi_pe_entry) add $0x4, %esp + call 1f +1: popl %esi + subl $1b, %esi + + popl %ecx + movl %ecx, efi32_config(%esi) /* Handle */ + popl %ecx + movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 88(%eax) + pushl %eax + call make_boot_params cmpl $0, %eax - je 1f - movl 0x4(%esp), %esi - movl (%esp), %ecx + je fail + popl %ecx pushl %eax - pushl %esi pushl %ecx - sub $0x4, %esp + jmp 2f /* Skip efi_config initialization */ -ENTRY(efi_stub_entry) +ENTRY(efi32_stub_entry) add $0x4, %esp + popl %ecx + popl %edx + + call 1f +1: popl %esi + subl $1b, %esi + + movl %ecx, efi32_config(%esi) /* Handle */ + movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 88(%eax) + pushl %eax +2: call efi_main cmpl $0, %eax movl %eax, %esi jne 2f -1: +fail: /* EFI init failed, so hang. */ hlt - jmp 1b + jmp fail 2: call 3f 3: @@ -202,6 +229,15 @@ relocated: xorl %ebx, %ebx jmp *%eax +#ifdef CONFIG_EFI_STUB + .data +efi32_config: + .fill 11,8,0 + .long efi_call_phys + .long 0 + .byte 0 +#endif + /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c5c1ae0997e7..57e58a5fa210 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -113,7 +113,8 @@ ENTRY(startup_32) lgdt gdt(%ebp) /* Enable PAE mode */ - movl $(X86_CR4_PAE), %eax + movl %cr4, %eax + orl $X86_CR4_PAE, %eax movl %eax, %cr4 /* @@ -178,6 +179,13 @@ ENTRY(startup_32) */ pushl $__KERNEL_CS leal startup_64(%ebp), %eax +#ifdef CONFIG_EFI_MIXED + movl efi32_config(%ebp), %ebx + cmp $0, %ebx + jz 1f + leal handover_entry(%ebp), %eax +1: +#endif pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -188,6 +196,30 @@ ENTRY(startup_32) lret ENDPROC(startup_32) +#ifdef CONFIG_EFI_MIXED + .org 0x190 +ENTRY(efi32_stub_entry) + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi + + leal (BP_scratch+4)(%esi), %esp + call 1f +1: pop %ebp + subl $1b, %ebp + + movl %ecx, efi32_config(%ebp) + movl %edx, efi32_config+8(%ebp) + sgdtl efi32_boot_gdt(%ebp) + + leal efi32_config(%ebp), %eax + movl %eax, efi_config(%ebp) + + jmp startup_32 +ENDPROC(efi32_stub_entry) +#endif + .code64 .org 0x200 ENTRY(startup_64) @@ -209,26 +241,48 @@ ENTRY(startup_64) jmp preferred_addr ENTRY(efi_pe_entry) - mov %rcx, %rdi - mov %rdx, %rsi - pushq %rdi - pushq %rsi + movq %rcx, efi64_config(%rip) /* Handle */ + movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ + + leaq efi64_config(%rip), %rax + movq %rax, efi_config(%rip) + + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). + */ + addq %rbp, efi64_config+88(%rip) + + movq %rax, %rdi call make_boot_params cmpq $0,%rax - je 1f - mov %rax, %rdx - popq %rsi - popq %rdi + je fail + mov %rax, %rsi + jmp 2f /* Skip the relocation */ -ENTRY(efi_stub_entry) +handover_entry: + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). + */ + movq efi_config(%rip), %rax + addq %rbp, 88(%rax) +2: + movq efi_config(%rip), %rdi call efi_main movq %rax,%rsi cmpq $0,%rax jne 2f -1: +fail: /* EFI init failed, so hang. */ hlt - jmp 1b + jmp fail 2: call 3f 3: @@ -307,6 +361,20 @@ preferred_addr: leaq relocated(%rbx), %rax jmp *%rax +#ifdef CONFIG_EFI_STUB + .org 0x390 +ENTRY(efi64_stub_entry) + movq %rdi, efi64_config(%rip) /* Handle */ + movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */ + + leaq efi64_config(%rip), %rax + movq %rax, efi_config(%rip) + + movq %rdx, %rsi + jmp handover_entry +ENDPROC(efi64_stub_entry) +#endif + .text relocated: @@ -372,6 +440,25 @@ gdt: .quad 0x0000000000000000 /* TS continued */ gdt_end: +#ifdef CONFIG_EFI_STUB +efi_config: + .quad 0 + +#ifdef CONFIG_EFI_MIXED + .global efi32_config +efi32_config: + .fill 11,8,0 + .quad efi64_thunk + .byte 0 +#endif + + .global efi64_config +efi64_config: + .fill 11,8,0 + .quad efi_call6 + .byte 1 +#endif /* CONFIG_EFI_STUB */ + /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index 100a9a10076a..f0d0b20fe149 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -67,6 +67,13 @@ static int is_transmeta(void) cpu_vendor[2] == A32('M', 'x', '8', '6'); } +static int is_intel(void) +{ + return cpu_vendor[0] == A32('G', 'e', 'n', 'u') && + cpu_vendor[1] == A32('i', 'n', 'e', 'I') && + cpu_vendor[2] == A32('n', 't', 'e', 'l'); +} + /* Returns a bitmask of which words we have error bits in */ static int check_cpuflags(void) { @@ -153,6 +160,19 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); err = check_cpuflags(); + } else if (err == 0x01 && + !(err_flags[0] & ~(1 << X86_FEATURE_PAE)) && + is_intel() && cpu.level == 6 && + (cpu.model == 9 || cpu.model == 13)) { + /* PAE is disabled on this Pentium M but can be forced */ + if (cmdline_find_option_bool("forcepae")) { + puts("WARNING: Forcing PAE in CPU flags\n"); + set_bit(X86_FEATURE_PAE, cpu.flags); + err = check_cpuflags(); + } + else { + puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n"); + } } if (err_flags_ptr) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index ec3b8ba68096..0ca9a5c362bc 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -283,7 +283,7 @@ _start: # Part 2 of the header, from the old setup.S .ascii "HdrS" # header signature - .word 0x020c # header version number (>= 0x0105) + .word 0x020d # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG @@ -350,7 +350,7 @@ cmd_line_ptr: .long 0 # (Header version 0x0202 or later) # can be located anywhere in # low memory 0x10000 or higher. -ramdisk_max: .long 0x7fffffff +initrd_addr_max: .long 0x7fffffff # (Header version 0x0203 or later) # The highest safe address for # the contents of an initrd @@ -375,7 +375,8 @@ xloadflags: # define XLF0 0 #endif -#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) +#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) && \ + !defined(CONFIG_EFI_MIXED) /* kernel/boot_param/ramdisk could be loaded above 4g */ # define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G #else @@ -383,10 +384,14 @@ xloadflags: #endif #ifdef CONFIG_EFI_STUB -# ifdef CONFIG_X86_64 -# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */ +# ifdef CONFIG_EFI_MIXED +# define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64) # else -# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */ +# ifdef CONFIG_X86_64 +# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */ +# else +# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */ +# endif # endif #else # define XLF23 0 @@ -426,13 +431,7 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr #define INIT_SIZE VO_INIT_SIZE #endif init_size: .long INIT_SIZE # kernel initialization size -handover_offset: -#ifdef CONFIG_EFI_STUB - .long 0x30 # offset to the handover - # protocol entry point -#else - .long 0 -#endif +handover_offset: .long 0 # Filled in by build.c # End of setup header ##################################################### diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 8e15b22391fc..1a2f2121cada 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -53,7 +53,8 @@ int is_big_kernel; #define PECOFF_RELOC_RESERVE 0x20 -unsigned long efi_stub_entry; +unsigned long efi32_stub_entry; +unsigned long efi64_stub_entry; unsigned long efi_pe_entry; unsigned long startup_64; @@ -219,6 +220,52 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) update_pecoff_section_header(".text", text_start, text_sz); } +static int reserve_pecoff_reloc_section(int c) +{ + /* Reserve 0x20 bytes for .reloc section */ + memset(buf+c, 0, PECOFF_RELOC_RESERVE); + return PECOFF_RELOC_RESERVE; +} + +static void efi_stub_defaults(void) +{ + /* Defaults for old kernel */ +#ifdef CONFIG_X86_32 + efi_pe_entry = 0x10; +#else + efi_pe_entry = 0x210; + startup_64 = 0x200; +#endif +} + +static void efi_stub_entry_update(void) +{ + unsigned long addr = efi32_stub_entry; + +#ifdef CONFIG_X86_64 + /* Yes, this is really how we defined it :( */ + addr = efi64_stub_entry - 0x200; +#endif + +#ifdef CONFIG_EFI_MIXED + if (efi32_stub_entry != addr) + die("32-bit and 64-bit EFI entry points do not match\n"); +#endif + put_unaligned_le32(addr, &buf[0x264]); +} + +#else + +static inline void update_pecoff_setup_and_reloc(unsigned int size) {} +static inline void update_pecoff_text(unsigned int text_start, + unsigned int file_sz) {} +static inline void efi_stub_defaults(void) {} +static inline void efi_stub_entry_update(void) {} + +static inline int reserve_pecoff_reloc_section(int c) +{ + return 0; +} #endif /* CONFIG_EFI_STUB */ @@ -250,7 +297,8 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi_stub_entry); + PARSE_ZOFS(p, efi32_stub_entry); + PARSE_ZOFS(p, efi64_stub_entry); PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, startup_64); @@ -271,15 +319,7 @@ int main(int argc, char ** argv) void *kernel; u32 crc = 0xffffffffUL; - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; - efi_stub_entry = 0x30; -#else - efi_pe_entry = 0x210; - efi_stub_entry = 0x230; - startup_64 = 0x200; -#endif + efi_stub_defaults(); if (argc != 5) usage(); @@ -302,11 +342,7 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); -#ifdef CONFIG_EFI_STUB - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - c += PECOFF_RELOC_RESERVE; -#endif + c += reserve_pecoff_reloc_section(c); /* Pad unused space with zeros */ setup_sectors = (c + 511) / 512; @@ -315,9 +351,7 @@ int main(int argc, char ** argv) i = setup_sectors*512; memset(buf+c, 0, i-c); -#ifdef CONFIG_EFI_STUB update_pecoff_setup_and_reloc(i); -#endif /* Set the default root device */ put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); @@ -342,14 +376,9 @@ int main(int argc, char ** argv) buf[0x1f1] = setup_sectors-1; put_unaligned_le32(sys_size, &buf[0x1f4]); -#ifdef CONFIG_EFI_STUB update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); -#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ - efi_stub_entry -= 0x200; -#endif - put_unaligned_le32(efi_stub_entry, &buf[0x264]); -#endif + efi_stub_entry_update(); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 7f669853317a..a8fee078b92f 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -5,3 +5,4 @@ genhdr-y += unistd_64.h genhdr-y += unistd_x32.h generic-y += clkdev.h +generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 1d2091a226bc..19b0ebafcd3e 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -93,9 +93,6 @@ static inline int is_vsmp_box(void) return 0; } #endif -extern void xapic_wait_icr_idle(void); -extern u32 safe_xapic_wait_icr_idle(void); -extern void xapic_icr_write(u32, u32); extern int setup_profiling_timer(unsigned int); static inline void native_apic_mem_write(u32 reg, u32 v) @@ -184,7 +181,6 @@ extern int x2apic_phys; extern int x2apic_preenabled; extern void check_x2apic(void); extern void enable_x2apic(void); -extern void x2apic_icr_write(u32 low, u32 id); static inline int x2apic_enabled(void) { u64 msr; @@ -221,7 +217,6 @@ static inline void x2apic_force_phys(void) { } -#define nox2apic 0 #define x2apic_preenabled 0 #define x2apic_supported() 0 #endif @@ -351,7 +346,7 @@ struct apic { int trampoline_phys_low; int trampoline_phys_high; - void (*wait_for_init_deassert)(atomic_t *deassert); + bool wait_for_init_deassert; void (*smp_callin_clear_local_apic)(void); void (*inquire_remote_apic)(int apicid); @@ -517,13 +512,6 @@ extern int default_cpu_present_to_apicid(int mps_cpu); extern int default_check_phys_apicid_present(int phys_apicid); #endif -static inline void default_wait_for_init_deassert(atomic_t *deassert) -{ - while (!atomic_read(deassert)) - cpu_relax(); - return; -} - extern void generic_bigsmp_probe(void); diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 04a48903b2eb..69bbb4845020 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -85,11 +85,7 @@ #else # define smp_rmb() barrier() #endif -#ifdef CONFIG_X86_OOSTORE -# define smp_wmb() wmb() -#else -# define smp_wmb() barrier() -#endif +#define smp_wmb() barrier() #define smp_read_barrier_depends() read_barrier_depends() #define set_mb(var, value) do { (void)xchg(&var, value); } while (0) #else /* !SMP */ @@ -100,7 +96,7 @@ #define set_mb(var, value) do { var = value; barrier(); } while (0) #endif /* SMP */ -#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) +#if defined(CONFIG_X86_PPRO_FENCE) /* * For either of these options x86 doesn't have a strong TSO memory diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e099f9502ace..bc507d7640f8 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -217,9 +217,14 @@ #define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_CLFLUSHOPT (9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_AVX512PF (9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER (9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD (9*32+28) /* AVX-512 Conflict Detection */ /* * BUG word(s) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 3d6b9f81cc68..0869434eaf72 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -19,9 +19,11 @@ */ #define EFI_OLD_MEMMAP EFI_ARCH_1 +#define EFI32_LOADER_SIGNATURE "EL32" +#define EFI64_LOADER_SIGNATURE "EL64" + #ifdef CONFIG_X86_32 -#define EFI_LOADER_SIGNATURE "EL32" extern unsigned long asmlinkage efi_call_phys(void *, ...); @@ -57,8 +59,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ -#define EFI_LOADER_SIGNATURE "EL64" - extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); @@ -119,7 +119,6 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; -extern unsigned long x86_efi_facility; extern struct efi_scratch efi_scratch; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); extern int efi_memblock_x86_reserve_range(void); @@ -130,10 +129,13 @@ extern void efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); -extern void efi_setup_page_tables(void); +extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); +extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages); extern void __init old_map_region(efi_memory_desc_t *md); extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_mkexec(void); +extern void __init efi_dump_pagetable(void); +extern void __init efi_apply_memmap_quirks(void); struct efi_setup_data { u64 fw_vendor; @@ -152,8 +154,40 @@ static inline bool efi_is_native(void) return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT); } +static inline bool efi_runtime_supported(void) +{ + if (efi_is_native()) + return true; + + if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP)) + return true; + + return false; +} + extern struct console early_efi_console; extern void parse_efi_setup(u64 phys_addr, u32 data_len); + +#ifdef CONFIG_EFI_MIXED +extern void efi_thunk_runtime_setup(void); +extern efi_status_t efi_thunk_set_virtual_address_map( + void *phys_set_virtual_address_map, + unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map); +#else +static inline void efi_thunk_runtime_setup(void) {} +static inline efi_status_t efi_thunk_set_virtual_address_map( + void *phys_set_virtual_address_map, + unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) +{ + return EFI_SUCCESS; +} +#endif /* CONFIG_EFI_MIXED */ #else /* * IF EFI is not configured, have the EFI calls return -ENOSYS. diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 34f69cb9350a..91d9c69a629e 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -237,7 +237,7 @@ memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) static inline void flush_write_buffers(void) { -#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) +#if defined(CONFIG_X86_PPRO_FENCE) asm volatile("lock; addl $0,0(%%esp)": : :"memory"); #endif } diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index e139b13f2a33..de36f22eb0b9 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -214,6 +214,8 @@ do { \ struct msr *msrs_alloc(void); void msrs_free(struct msr *msrs); +int msr_set_bit(u32 msr, u8 bit); +int msr_clear_bit(u32 msr, u8 bit); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 86f9301903c8..5f2fc4441b11 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_NMI_H #define _ASM_X86_NMI_H +#include <linux/irq_work.h> #include <linux/pm.h> #include <asm/irq.h> #include <asm/io.h> @@ -38,6 +39,8 @@ typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *); struct nmiaction { struct list_head list; nmi_handler_t handler; + u64 max_duration; + struct irq_work irq_work; unsigned long flags; const char *name; }; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5ad38ad07890..b459ddf27d64 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -15,9 +15,10 @@ : (prot)) #ifndef __ASSEMBLY__ - #include <asm/x86_init.h> +void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -445,20 +446,10 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } -static inline int pteval_present(pteval_t pteval) -{ - /* - * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this - * way clearly states that the intent is that protnone and numa - * hinting ptes are considered present for the purposes of - * pagetable operations like zapping, protection changes, gup etc. - */ - return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA); -} - static inline int pte_present(pte_t a) { - return pteval_present(pte_flags(a)); + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE | + _PAGE_NUMA); } #define pte_accessible pte_accessible diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 1aa9ccd43223..708f19fb4fc7 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -382,9 +382,13 @@ static inline void update_page_count(int level, unsigned long pages) { } * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); +extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level); extern phys_addr_t slow_virt_to_phys(void *__address); extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, unsigned numpages, unsigned long page_flags); +void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, + unsigned numpages); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 645cad2c95ff..e820c080a4e9 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -191,6 +191,14 @@ static inline void clflush(volatile void *__p) asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } +static inline void clflushopt(volatile void *__p) +{ + alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0", + ".byte 0x66; clflush %P0", + X86_FEATURE_CLFLUSHOPT, + "+m" (*(volatile char __force *)__p)); +} + #define nop() asm volatile ("nop") diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index bf156ded74b5..0f62f5482d91 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -26,10 +26,9 @@ # define LOCK_PTR_REG "D" #endif -#if defined(CONFIG_X86_32) && \ - (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)) +#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE)) /* - * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock + * On PPro SMP, we use a locked operation to unlock * (PPro errata 66, 92) */ # define UNLOCK_LOCK_PREFIX LOCK_PREFIX diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index d35f24e231cd..b28097e4c8c3 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { } extern const struct cpumask *cpu_coregroup_mask(int cpu); -#ifdef ENABLE_TOPO_DEFINES #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) + +#ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #endif @@ -133,12 +134,6 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) struct pci_bus; void x86_pci_root_bus_resources(int bus, struct list_head *resources); -#ifdef CONFIG_SMP -#define mc_capable() ((boot_cpu_data.x86_max_cores > 1) && \ - (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)) -#define smt_capable() (smp_num_siblings > 1) -#endif - #ifdef CONFIG_NUMA extern int get_mp_bus_to_node(int busnum); extern void set_mp_bus_to_node(int busnum, int node); diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 554738963b28..6c1d7411eb00 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -6,11 +6,14 @@ #define XSTATE_CPUID 0x0000000d -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 +#define XSTATE_FP 0x1 +#define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 +#define XSTATE_BNDREGS 0x8 +#define XSTATE_BNDCSR 0x10 +#define XSTATE_OPMASK 0x20 +#define XSTATE_ZMM_Hi256 0x40 +#define XSTATE_Hi16_ZMM 0x80 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -23,7 +26,8 @@ #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) /* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ + | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) /* Supported features which require eager state saving */ #define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index c19fc60ff062..4924f4be2b99 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -368,33 +368,58 @@ #define THERM_LOG_THRESHOLD1 (1 << 9) /* MISC_ENABLE bits: architectural */ -#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) -#define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) -#define MSR_IA32_MISC_ENABLE_EMON (1ULL << 7) -#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << 11) -#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << 12) -#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << 16) -#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << 18) -#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << 22) -#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << 23) -#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << 34) +#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0 +#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) +#define MSR_IA32_MISC_ENABLE_TCC_BIT 1 +#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT) +#define MSR_IA32_MISC_ENABLE_EMON_BIT 7 +#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT) +#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11 +#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT) +#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12 +#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT) +#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16 +#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT) +#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18 +#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT) +#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22 +#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT); +#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23 +#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34 +#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT) /* MISC_ENABLE bits: model-specific, meaning may vary from core to core */ -#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << 2) -#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << 3) -#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << 4) -#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << 6) -#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << 8) -#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << 9) -#define MSR_IA32_MISC_ENABLE_FERR (1ULL << 10) -#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << 10) -#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << 13) -#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << 19) -#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << 20) -#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << 24) -#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << 37) -#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << 38) -#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << 39) +#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2 +#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT) +#define MSR_IA32_MISC_ENABLE_TM1_BIT 3 +#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT) +#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4 +#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6 +#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8 +#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT) +#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9 +#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_FERR_BIT 10 +#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT) +#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10 +#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT) +#define MSR_IA32_MISC_ENABLE_TM2_BIT 13 +#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT) +#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19 +#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20 +#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT) +#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24 +#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT) +#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37 +#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38 +#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 +#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) #define MSR_IA32_TSC_DEADLINE 0x000006E0 diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1dac94265b59..9f46f2b1cfc2 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -613,10 +613,10 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) int nid; nid = acpi_get_node(handle); - if (nid == -1 || !node_online(nid)) - return; - set_apicid_to_node(physid, nid); - numa_set_node(cpu, nid); + if (nid != -1) { + set_apicid_to_node(physid, nid); + numa_set_node(cpu, nid); + } #endif } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index fd972a3e4cbb..9fa8aa051f54 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -18,7 +18,6 @@ #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/bitops.h> -#include <linux/ioport.h> #include <linux/suspend.h> #include <asm/e820.h> #include <asm/io.h> @@ -54,18 +53,6 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -static struct resource gart_resource = { - .name = "GART", - .flags = IORESOURCE_MEM, -}; - -static void __init insert_aperture_resource(u32 aper_base, u32 aper_size) -{ - gart_resource.start = aper_base; - gart_resource.end = aper_base + aper_size - 1; - insert_resource(&iomem_resource, &gart_resource); -} - /* This code runs before the PCI subsystem is initialized, so just access the northbridge directly. */ @@ -96,7 +83,6 @@ static u32 __init allocate_aperture(void) memblock_reserve(addr, aper_size); printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", aper_size >> 10, addr); - insert_aperture_resource((u32)addr, aper_size); register_nosave_region(addr >> PAGE_SHIFT, (addr+aper_size) >> PAGE_SHIFT); @@ -444,12 +430,8 @@ int __init gart_iommu_hole_init(void) out: if (!fix && !fallback_aper_force) { - if (last_aper_base) { - unsigned long n = (32 * 1024 * 1024) << last_aper_order; - - insert_aperture_resource((u32)last_aper_base, n); + if (last_aper_base) return 1; - } return 0; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a70a9e..53e20531470e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -133,6 +133,10 @@ static inline void imcr_apic_to_pic(void) * +1=force-enable */ static int force_enable_local_apic __initdata; + +/* Control whether x2APIC mode is enabled or not */ +static bool nox2apic __initdata; + /* * APIC command line parameters */ @@ -162,8 +166,7 @@ int x2apic_mode; /* x2apic enabled before OS handover */ int x2apic_preenabled; static int x2apic_disabled; -static int nox2apic; -static __init int setup_nox2apic(char *str) +static int __init setup_nox2apic(char *str) { if (x2apic_enabled()) { int apicid = native_apic_msr_read(APIC_ID); @@ -178,7 +181,7 @@ static __init int setup_nox2apic(char *str) } else setup_clear_cpu_cap(X86_FEATURE_X2APIC); - nox2apic = 1; + nox2apic = true; return 0; } @@ -283,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void) void native_apic_icr_write(u32 low, u32 id) { + unsigned long flags; + + local_irq_save(flags); apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id)); apic_write(APIC_ICR, low); + local_irq_restore(flags); } u64 native_apic_icr_read(void) diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 2c621a6b901a..7c1b29479513 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -198,7 +198,7 @@ static struct apic apic_flat = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, @@ -314,7 +314,7 @@ static struct apic apic_physflat = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 191ce75c0e54..8c7c98249c20 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -172,8 +172,7 @@ struct apic apic_noop = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 3e67f9e3d7ef..a5b45df8bc88 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -248,7 +248,7 @@ static const struct apic apic_numachip __refconst = { .wakeup_secondary_cpu = numachip_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, /* REMRD not supported */ diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index d50e3640d5ae..e4840aa7a255 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -199,8 +199,7 @@ static struct apic apic_bigsmp = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index c55224731b2d..6f8f8b348a39 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -394,12 +394,6 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_wait_for_init_deassert(atomic_t *deassert) -{ - while (!atomic_read(deassert)) - cpu_relax(); -} - static unsigned int es7000_get_apic_id(unsigned long x) { return (x >> 24) & 0xFF; @@ -658,8 +652,7 @@ static struct apic __refdata apic_es7000_cluster = { .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, /* Nothing to do for most platforms, since cleared by the INIT cycle: */ .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, @@ -722,8 +715,7 @@ static struct apic __refdata apic_es7000 = { .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, - .wait_for_init_deassert = es7000_wait_for_init_deassert, - + .wait_for_init_deassert = true, /* Nothing to do for most platforms, since cleared by the INIT cycle: */ .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 1e42e8f305ee..030ea1c04f72 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -505,8 +505,7 @@ static struct apic __refdata apic_numaq = { .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH, /* We don't do anything here because we use NMI's to boot instead */ - .wait_for_init_deassert = NULL, - + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = numaq_smp_callin_clear_local_apic, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index eb35ef9ee63f..cceb352c968c 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -119,8 +119,7 @@ static struct apic apic_default = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 00146f9b0254..b656128611cd 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -532,8 +532,7 @@ static struct apic apic_summit = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = default_wait_for_init_deassert, - + .wait_for_init_deassert = true, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cac85ee6913f..e66766bf1641 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -279,7 +279,7 @@ static struct apic apic_x2apic_cluster = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index de231e328cae..6d600ebf6c12 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -133,7 +133,7 @@ static struct apic apic_x2apic_phys = { .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d263b1307de1..7834389ba5be 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -396,7 +396,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .wakeup_secondary_cpu = uv_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, - .wait_for_init_deassert = NULL, + .wait_for_init_deassert = false, .smp_callin_clear_local_apic = NULL, .inquire_remote_apic = NULL, diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c67ffa686064..ce8b8ff0e0ef 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -218,7 +218,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) */ WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); - add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); } static void init_amd_k7(struct cpuinfo_x86 *c) @@ -233,9 +233,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) if (c->x86_model >= 6 && c->x86_model <= 10) { if (!cpu_has(c, X86_FEATURE_XMM)) { printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); - rdmsr(MSR_K7_HWCR, l, h); - l &= ~0x00008000; - wrmsr(MSR_K7_HWCR, l, h); + msr_clear_bit(MSR_K7_HWCR, 15); set_cpu_cap(c, X86_FEATURE_XMM); } } @@ -509,14 +507,8 @@ static void early_init_amd(struct cpuinfo_x86 *c) #endif /* F16h erratum 793, CVE-2013-6885 */ - if (c->x86 == 0x16 && c->x86_model <= 0xf) { - u64 val; - - rdmsrl(MSR_AMD64_LS_CFG, val); - if (!(val & BIT(15))) - wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15)); - } - + if (c->x86 == 0x16 && c->x86_model <= 0xf) + msr_set_bit(MSR_AMD64_LS_CFG, 15); } static const int amd_erratum_383[]; @@ -536,11 +528,8 @@ static void init_amd(struct cpuinfo_x86 *c) * Errata 63 for SH-B3 steppings * Errata 122 for all steppings (F+ have it disabled by default) */ - if (c->x86 == 0xf) { - rdmsrl(MSR_K7_HWCR, value); - value |= 1 << 6; - wrmsrl(MSR_K7_HWCR, value); - } + if (c->x86 == 0xf) + msr_set_bit(MSR_K7_HWCR, 6); #endif early_init_amd(c); @@ -623,14 +612,11 @@ static void init_amd(struct cpuinfo_x86 *c) (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { - if (!rdmsrl_safe(0xc0011005, &value)) { - value |= 1ULL << 54; - wrmsrl_safe(0xc0011005, value); + if (msr_set_bit(0xc0011005, 54) > 0) { rdmsrl(0xc0011005, value); - if (value & (1ULL << 54)) { + if (value & BIT_64(54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); - printk(KERN_INFO FW_INFO "CPU: Re-enabling " - "disabled Topology Extensions Support\n"); + pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); } } } @@ -709,19 +695,12 @@ static void init_amd(struct cpuinfo_x86 *c) * Disable GART TLB Walk Errors on Fam10h. We do this here * because this is always needed when GART is enabled, even in a * kernel which has no MCE support built in. - * BIOS should disable GartTlbWlk Errors themself. If - * it doesn't do it here as suggested by the BKDG. + * BIOS should disable GartTlbWlk Errors already. If + * it doesn't, do it here as suggested by the BKDG. * * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 */ - u64 mask; - int err; - - err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask); - if (err == 0) { - mask |= (1 << 10); - wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask); - } + msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); /* * On family 10h BIOS may not have properly enabled WC+ support, @@ -733,10 +712,7 @@ static void init_amd(struct cpuinfo_x86 *c) * NOTE: we want to use the _safe accessors so as not to #GP kvm * guests on older kvm hosts. */ - - rdmsrl_safe(MSR_AMD64_BU_CFG2, &value); - value &= ~(1ULL << 24); - wrmsrl_safe(MSR_AMD64_BU_CFG2, value); + msr_clear_bit(MSR_AMD64_BU_CFG2, 24); if (cpu_has_amd_erratum(c, amd_erratum_383)) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 8779edab684e..d8fba5c15fbd 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -8,236 +8,6 @@ #include "cpu.h" -#ifdef CONFIG_X86_OOSTORE - -static u32 power2(u32 x) -{ - u32 s = 1; - - while (s <= x) - s <<= 1; - - return s >>= 1; -} - - -/* - * Set up an actual MCR - */ -static void centaur_mcr_insert(int reg, u32 base, u32 size, int key) -{ - u32 lo, hi; - - hi = base & ~0xFFF; - lo = ~(size-1); /* Size is a power of 2 so this makes a mask */ - lo &= ~0xFFF; /* Remove the ctrl value bits */ - lo |= key; /* Attribute we wish to set */ - wrmsr(reg+MSR_IDT_MCR0, lo, hi); - mtrr_centaur_report_mcr(reg, lo, hi); /* Tell the mtrr driver */ -} - -/* - * Figure what we can cover with MCR's - * - * Shortcut: We know you can't put 4Gig of RAM on a winchip - */ -static u32 ramtop(void) -{ - u32 clip = 0xFFFFFFFFUL; - u32 top = 0; - int i; - - for (i = 0; i < e820.nr_map; i++) { - unsigned long start, end; - - if (e820.map[i].addr > 0xFFFFFFFFUL) - continue; - /* - * Don't MCR over reserved space. Ignore the ISA hole - * we frob around that catastrophe already - */ - if (e820.map[i].type == E820_RESERVED) { - if (e820.map[i].addr >= 0x100000UL && - e820.map[i].addr < clip) - clip = e820.map[i].addr; - continue; - } - start = e820.map[i].addr; - end = e820.map[i].addr + e820.map[i].size; - if (start >= end) - continue; - if (end > top) - top = end; - } - /* - * Everything below 'top' should be RAM except for the ISA hole. - * Because of the limited MCR's we want to map NV/ACPI into our - * MCR range for gunk in RAM - * - * Clip might cause us to MCR insufficient RAM but that is an - * acceptable failure mode and should only bite obscure boxes with - * a VESA hole at 15Mb - * - * The second case Clip sometimes kicks in is when the EBDA is marked - * as reserved. Again we fail safe with reasonable results - */ - if (top > clip) - top = clip; - - return top; -} - -/* - * Compute a set of MCR's to give maximum coverage - */ -static int centaur_mcr_compute(int nr, int key) -{ - u32 mem = ramtop(); - u32 root = power2(mem); - u32 base = root; - u32 top = root; - u32 floor = 0; - int ct = 0; - - while (ct < nr) { - u32 fspace = 0; - u32 high; - u32 low; - - /* - * Find the largest block we will fill going upwards - */ - high = power2(mem-top); - - /* - * Find the largest block we will fill going downwards - */ - low = base/2; - - /* - * Don't fill below 1Mb going downwards as there - * is an ISA hole in the way. - */ - if (base <= 1024*1024) - low = 0; - - /* - * See how much space we could cover by filling below - * the ISA hole - */ - - if (floor == 0) - fspace = 512*1024; - else if (floor == 512*1024) - fspace = 128*1024; - - /* And forget ROM space */ - - /* - * Now install the largest coverage we get - */ - if (fspace > high && fspace > low) { - centaur_mcr_insert(ct, floor, fspace, key); - floor += fspace; - } else if (high > low) { - centaur_mcr_insert(ct, top, high, key); - top += high; - } else if (low > 0) { - base -= low; - centaur_mcr_insert(ct, base, low, key); - } else - break; - ct++; - } - /* - * We loaded ct values. We now need to set the mask. The caller - * must do this bit. - */ - return ct; -} - -static void centaur_create_optimal_mcr(void) -{ - int used; - int i; - - /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining and weak write ordered. - * - * To experiment with: Linux never uses stack operations for - * mmio spaces so we could globally enable stack operation wc - * - * Load the registers with type 31 - full write combining, all - * writes weakly ordered. - */ - used = centaur_mcr_compute(6, 31); - - /* - * Wipe unused MCRs - */ - for (i = used; i < 8; i++) - wrmsr(MSR_IDT_MCR0+i, 0, 0); -} - -static void winchip2_create_optimal_mcr(void) -{ - u32 lo, hi; - int used; - int i; - - /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining, weak store ordered. - * - * Load the registers with type 25 - * 8 - weak write ordering - * 16 - weak read ordering - * 1 - write combining - */ - used = centaur_mcr_compute(6, 25); - - /* - * Mark the registers we are using. - */ - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - for (i = 0; i < used; i++) - lo |= 1<<(9+i); - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - - /* - * Wipe unused MCRs - */ - - for (i = used; i < 8; i++) - wrmsr(MSR_IDT_MCR0+i, 0, 0); -} - -/* - * Handle the MCR key on the Winchip 2. - */ -static void winchip2_unprotect_mcr(void) -{ - u32 lo, hi; - u32 key; - - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo &= ~0x1C0; /* blank bits 8-6 */ - key = (lo>>17) & 7; - lo |= key<<6; /* replace with unlock key */ - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); -} - -static void winchip2_protect_mcr(void) -{ - u32 lo, hi; - - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo &= ~0x1C0; /* blank bits 8-6 */ - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); -} -#endif /* CONFIG_X86_OOSTORE */ - #define ACE_PRESENT (1 << 6) #define ACE_ENABLED (1 << 7) #define ACE_FCR (1 << 28) /* MSR_VIA_FCR */ @@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c) fcr_clr = DPDC; printk(KERN_NOTICE "Disabling bugged TSC.\n"); clear_cpu_cap(c, X86_FEATURE_TSC); -#ifdef CONFIG_X86_OOSTORE - centaur_create_optimal_mcr(); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - * - * The C6 original lacks weak read order - * - * Note 0x120 is write only on Winchip 1 - */ - wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0); -#endif break; case 8: switch (c->x86_mask) { @@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c) fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| E2MMX|EAMD3D; fcr_clr = DPDC; -#ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - */ - lo |= 31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); -#endif break; case 9: name = "3"; fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| E2MMX|EAMD3D; fcr_clr = DPDC; -#ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* - * Enable: - * write combining on non-stack, non-string - * write combining on string, all types - * weak write ordering - */ - lo |= 31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); -#endif break; default: name = "??"; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 5cd9bfabd645..897d6201ef10 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -31,11 +31,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* Unmask CPUID levels if masked: */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - - if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) { - misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID; - wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) { c->cpuid_level = cpuid_eax(0); get_cpu_cap(c); } @@ -129,16 +126,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) * Ingo Molnar reported a Pentium D (model 6) and a Xeon * (model 2) with the same problem. */ - if (c->x86 == 15) { - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - - if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) { - printk(KERN_INFO "kmemcheck: Disabling fast string operations\n"); - - misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING; - wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); - } - } + if (c->x86 == 15) + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) + pr_info("kmemcheck: Disabling fast string operations\n"); #endif /* @@ -195,10 +186,16 @@ static void intel_smp_check(struct cpuinfo_x86 *c) } } -static void intel_workarounds(struct cpuinfo_x86 *c) +static int forcepae; +static int __init forcepae_setup(char *__unused) { - unsigned long lo, hi; + forcepae = 1; + return 1; +} +__setup("forcepae", forcepae_setup); +static void intel_workarounds(struct cpuinfo_x86 *c) +{ #ifdef CONFIG_X86_F00F_BUG /* * All current models of Pentium and Pentium with MMX technology CPUs @@ -225,16 +222,26 @@ static void intel_workarounds(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_SEP); /* + * PAE CPUID issue: many Pentium M report no PAE but may have a + * functionally usable PAE implementation. + * Forcefully enable PAE if kernel parameter "forcepae" is present. + */ + if (forcepae) { + printk(KERN_WARNING "PAE forced!\n"); + set_cpu_cap(c, X86_FEATURE_PAE); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); + } + + /* * P4 Xeon errata 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { - rdmsr(MSR_IA32_MISC_ENABLE, lo, hi); - if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) { - printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n"); - printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n"); - lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE; - wrmsr(MSR_IA32_MISC_ENABLE, lo, hi); + if (msr_set_bit(MSR_IA32_MISC_ENABLE, + MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) + > 0) { + pr_info("CPU: C0 stepping P4 Xeon detected.\n"); + pr_info("CPU: Disabling hardware prefetching (Errata 037)\n"); } } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9f7ca266864a..832d05a914ba 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -26,6 +26,7 @@ #include <asm/irq_regs.h> #include <asm/i8259.h> #include <asm/apic.h> +#include <asm/timer.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -105,6 +106,11 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); + +#ifdef CONFIG_X86_IO_APIC + no_timer_check = 1; +#endif + } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 79f9f848bee4..ae407f7226c8 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -892,7 +892,6 @@ static void x86_pmu_enable(struct pmu *pmu) * hw_perf_group_sched_in() or x86_pmu_enable() * * step1: save events moving to new counters - * step2: reprogram moved events into new counters */ for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; @@ -918,6 +917,9 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu_stop(event, PERF_EF_UPDATE); } + /* + * step2: reprogram moved events into new counters + */ for (i = 0; i < cpuc->n_events; i++) { event = cpuc->event_list[i]; hwc = &event->hw; @@ -1043,7 +1045,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed - * at commit time (->commit_txn) as a whole + * at commit time (->commit_txn) as a whole. */ if (cpuc->group_flag & PERF_EVENT_TXN) goto done_collect; @@ -1058,6 +1060,10 @@ static int x86_pmu_add(struct perf_event *event, int flags) memcpy(cpuc->assign, assign, n*sizeof(int)); done_collect: + /* + * Commit the collect_events() state. See x86_pmu_del() and + * x86_pmu_*_txn(). + */ cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; @@ -1183,28 +1189,38 @@ static void x86_pmu_del(struct perf_event *event, int flags) * If we're called during a txn, we don't need to do anything. * The events never got scheduled and ->cancel_txn will truncate * the event_list. + * + * XXX assumes any ->del() called during a TXN will only be on + * an event added during that same TXN. */ if (cpuc->group_flag & PERF_EVENT_TXN) return; + /* + * Not a TXN, therefore cleanup properly. + */ x86_pmu_stop(event, PERF_EF_UPDATE); for (i = 0; i < cpuc->n_events; i++) { - if (event == cpuc->event_list[i]) { + if (event == cpuc->event_list[i]) + break; + } - if (i >= cpuc->n_events - cpuc->n_added) - --cpuc->n_added; + if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */ + return; - if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, event); + /* If we have a newly added event; make sure to decrease n_added. */ + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; - while (++i < cpuc->n_events) - cpuc->event_list[i-1] = cpuc->event_list[i]; + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(cpuc, event); + + /* Delete the array entry. */ + while (++i < cpuc->n_events) + cpuc->event_list[i-1] = cpuc->event_list[i]; + --cpuc->n_events; - --cpuc->n_events; - break; - } - } perf_event_update_userpage(event); } @@ -1598,7 +1614,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) { __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); /* - * Truncate the collected events. + * Truncate collected array by the number of events added in this + * transaction. See x86_pmu_add() and x86_pmu_*_txn(). */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); @@ -1609,6 +1626,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) * Commit group events scheduling transaction * Perform the group schedulability test as a whole * Return 0 if success + * + * Does not cancel the transaction on failure; expects the caller to do this. */ static int x86_pmu_commit_txn(struct pmu *pmu) { diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 4972c244d0bc..3b2f9bdd974b 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -130,9 +130,11 @@ struct cpu_hw_events { unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; int enabled; - int n_events; - int n_added; - int n_txn; + int n_events; /* the # of events in the below arrays */ + int n_added; /* the # last events in the below arrays; + they've never been enabled yet */ + int n_txn; /* the # last events in the below arrays; + added in the current transaction */ int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index c88f7f4b03ee..bd2253d40cff 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -66,6 +66,47 @@ DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); +static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); +static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); +static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); +static void uncore_pmu_event_read(struct perf_event *event); + +static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct intel_uncore_pmu, pmu); +} + +static struct intel_uncore_box * +uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +{ + struct intel_uncore_box *box; + + box = *per_cpu_ptr(pmu->box, cpu); + if (box) + return box; + + raw_spin_lock(&uncore_box_lock); + list_for_each_entry(box, &pmu->box_list, list) { + if (box->phys_id == topology_physical_package_id(cpu)) { + atomic_inc(&box->refcnt); + *per_cpu_ptr(pmu->box, cpu) = box; + break; + } + } + raw_spin_unlock(&uncore_box_lock); + + return *per_cpu_ptr(pmu->box, cpu); +} + +static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + /* + * perf core schedules event on the basis of cpu, uncore events are + * collected by one of the cpus inside a physical package. + */ + return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); +} + static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { u64 count; @@ -1639,6 +1680,349 @@ static struct intel_uncore_type *snb_msr_uncores[] = { &snb_uncore_cbox, NULL, }; + +enum { + SNB_PCI_UNCORE_IMC, +}; + +static struct uncore_event_desc snb_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), + INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), + INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + + { /* end: all zeroes */ }, +}; + +#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff +#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 + +/* page size multiple covering all config regs */ +#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 + +#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 +#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 +#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE + +static struct attribute *snb_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group snb_uncore_imc_format_group = { + .name = "format", + .attrs = snb_uncore_imc_formats_attr, +}; + +static void snb_uncore_imc_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; + resource_size_t addr; + u32 pci_dword; + + pci_read_config_dword(pdev, where, &pci_dword); + addr = pci_dword; + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + pci_read_config_dword(pdev, where + 4, &pci_dword); + addr |= ((resource_size_t)pci_dword << 32); +#endif + + addr &= ~(PAGE_SIZE - 1); + + box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); + box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; +} + +static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); +} + +/* + * custom event_init() function because we define our own fixed, free + * running counters, so we do not want to conflict with generic uncore + * logic. Also simplifies processing + */ +static int snb_uncore_imc_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; + int idx, base; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + + /* check only supported bits are set */ + if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) + return -EINVAL; + + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + /* + * check event is known (whitelist, determines counter) + */ + switch (cfg) { + case SNB_UNCORE_PCI_IMC_DATA_READS: + base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; + idx = UNCORE_PMC_IDX_FIXED; + break; + case SNB_UNCORE_PCI_IMC_DATA_WRITES: + base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; + idx = UNCORE_PMC_IDX_FIXED + 1; + break; + default: + return -EINVAL; + } + + /* must be done before validate_group */ + event->hw.event_base = base; + event->hw.config = cfg; + event->hw.idx = idx; + + /* no group validation needed, we have free running counters */ + + return 0; +} + +static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + return 0; +} + +static void snb_uncore_imc_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + u64 count; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->n_active++; + + list_add_tail(&event->active_entry, &box->active_list); + + count = snb_uncore_imc_read_counter(box, event); + local64_set(&event->hw.prev_count, count); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + box->n_active--; + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + list_del(&event->active_entry); + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int snb_uncore_imc_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!box) + return -ENODEV; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + snb_uncore_imc_event_start(event, 0); + + box->n_events++; + + return 0; +} + +static void snb_uncore_imc_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + --box->n_events; + break; + } + } +} + +static int snb_pci2phy_map_init(int devid) +{ + struct pci_dev *dev = NULL; + int bus; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); + if (!dev) + return -ENOTTY; + + bus = dev->bus->number; + + pcibus_to_physid[bus] = 0; + + pci_dev_put(dev); + + return 0; +} + +static struct pmu snb_uncore_imc_pmu = { + .task_ctx_nr = perf_invalid_context, + .event_init = snb_uncore_imc_event_init, + .add = snb_uncore_imc_event_add, + .del = snb_uncore_imc_event_del, + .start = snb_uncore_imc_event_start, + .stop = snb_uncore_imc_event_stop, + .read = uncore_pmu_event_read, +}; + +static struct intel_uncore_ops snb_uncore_imc_ops = { + .init_box = snb_uncore_imc_init_box, + .enable_box = snb_uncore_imc_enable_box, + .disable_box = snb_uncore_imc_disable_box, + .disable_event = snb_uncore_imc_disable_event, + .enable_event = snb_uncore_imc_enable_event, + .hw_config = snb_uncore_imc_hw_config, + .read_counter = snb_uncore_imc_read_counter, +}; + +static struct intel_uncore_type snb_uncore_imc = { + .name = "imc", + .num_counters = 2, + .num_boxes = 1, + .fixed_ctr_bits = 32, + .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, + .event_descs = snb_uncore_imc_events, + .format_group = &snb_uncore_imc_format_group, + .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, + .ops = &snb_uncore_imc_ops, + .pmu = &snb_uncore_imc_pmu, +}; + +static struct intel_uncore_type *snb_pci_uncores[] = { + [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(snb_uncore_pci_ids) = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static DEFINE_PCI_DEVICE_TABLE(ivb_uncore_pci_ids) = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static DEFINE_PCI_DEVICE_TABLE(hsw_uncore_pci_ids) = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static struct pci_driver snb_uncore_pci_driver = { + .name = "snb_uncore", + .id_table = snb_uncore_pci_ids, +}; + +static struct pci_driver ivb_uncore_pci_driver = { + .name = "ivb_uncore", + .id_table = ivb_uncore_pci_ids, +}; + +static struct pci_driver hsw_uncore_pci_driver = { + .name = "hsw_uncore", + .id_table = hsw_uncore_pci_ids, +}; + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ @@ -2789,6 +3173,7 @@ again: static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) { struct intel_uncore_box *box; + struct perf_event *event; unsigned long flags; int bit; @@ -2801,19 +3186,27 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) */ local_irq_save(flags); + /* + * handle boxes with an active event list as opposed to active + * counters + */ + list_for_each_entry(event, &box->active_list, active_entry) { + uncore_perf_event_update(box, event); + } + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) uncore_perf_event_update(box, box->events[bit]); local_irq_restore(flags); - hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL)); + hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration)); return HRTIMER_RESTART; } static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { __hrtimer_start_range_ns(&box->hrtimer, - ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0, + ns_to_ktime(box->hrtimer_duration), 0, HRTIMER_MODE_REL_PINNED, 0); } @@ -2847,43 +3240,12 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, box->cpu = -1; box->phys_id = -1; - return box; -} - -static struct intel_uncore_box * -uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) -{ - struct intel_uncore_box *box; - - box = *per_cpu_ptr(pmu->box, cpu); - if (box) - return box; - - raw_spin_lock(&uncore_box_lock); - list_for_each_entry(box, &pmu->box_list, list) { - if (box->phys_id == topology_physical_package_id(cpu)) { - atomic_inc(&box->refcnt); - *per_cpu_ptr(pmu->box, cpu) = box; - break; - } - } - raw_spin_unlock(&uncore_box_lock); - - return *per_cpu_ptr(pmu->box, cpu); -} + /* set default hrtimer timeout */ + box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; -static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) -{ - return container_of(event->pmu, struct intel_uncore_pmu, pmu); -} + INIT_LIST_HEAD(&box->active_list); -static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) -{ - /* - * perf core schedules event on the basis of cpu, uncore events are - * collected by one of the cpus inside a physical package. - */ - return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); + return box; } static int @@ -3279,16 +3641,21 @@ static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; - pmu->pmu = (struct pmu) { - .attr_groups = pmu->type->attr_groups, - .task_ctx_nr = perf_invalid_context, - .event_init = uncore_pmu_event_init, - .add = uncore_pmu_event_add, - .del = uncore_pmu_event_del, - .start = uncore_pmu_event_start, - .stop = uncore_pmu_event_stop, - .read = uncore_pmu_event_read, - }; + if (!pmu->type->pmu) { + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + }; + } else { + pmu->pmu = *pmu->type->pmu; + pmu->pmu.attr_groups = pmu->type->attr_groups; + } if (pmu->type->num_boxes == 1) { if (strlen(pmu->type->name) > 0) @@ -3334,6 +3701,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type) if (!pmus) return -ENOMEM; + type->pmus = pmus; + type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, 0, type->num_counters, 0, 0); @@ -3369,7 +3738,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type) } type->pmu_group = &uncore_pmu_attr_group; - type->pmus = pmus; return 0; fail: uncore_type_exit(type); @@ -3501,6 +3869,28 @@ static int __init uncore_pci_init(void) pci_uncores = ivt_pci_uncores; uncore_pci_driver = &ivt_uncore_pci_driver; break; + case 42: /* Sandy Bridge */ + ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC); + if (ret) + return ret; + pci_uncores = snb_pci_uncores; + uncore_pci_driver = &snb_uncore_pci_driver; + break; + case 58: /* Ivy Bridge */ + ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC); + if (ret) + return ret; + pci_uncores = snb_pci_uncores; + uncore_pci_driver = &ivb_uncore_pci_driver; + break; + case 60: /* Haswell */ + case 69: /* Haswell Celeron */ + ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC); + if (ret) + return ret; + pci_uncores = snb_pci_uncores; + uncore_pci_driver = &hsw_uncore_pci_driver; + break; default: return 0; } @@ -3772,7 +4162,7 @@ static void __init uncore_cpu_setup(void *dummy) static int __init uncore_cpu_init(void) { - int ret, cpu, max_cores; + int ret, max_cores; max_cores = boot_cpu_data.x86_max_cores; switch (boot_cpu_data.x86_model) { @@ -3816,29 +4206,6 @@ static int __init uncore_cpu_init(void) if (ret) return ret; - get_online_cpus(); - - for_each_online_cpu(cpu) { - int i, phys_id = topology_physical_package_id(cpu); - - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) { - phys_id = -1; - break; - } - } - if (phys_id < 0) - continue; - - uncore_cpu_prepare(cpu, phys_id); - uncore_event_init_cpu(cpu); - } - on_each_cpu(uncore_cpu_setup, NULL, 1); - - register_cpu_notifier(&uncore_cpu_nb); - - put_online_cpus(); - return 0; } @@ -3867,6 +4234,41 @@ static int __init uncore_pmus_register(void) return 0; } +static void __init uncore_cpumask_init(void) +{ + int cpu; + + /* + * ony invoke once from msr or pci init code + */ + if (!cpumask_empty(&uncore_cpu_mask)) + return; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + int i, phys_id = topology_physical_package_id(cpu); + + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) { + phys_id = -1; + break; + } + } + if (phys_id < 0) + continue; + + uncore_cpu_prepare(cpu, phys_id); + uncore_event_init_cpu(cpu); + } + on_each_cpu(uncore_cpu_setup, NULL, 1); + + register_cpu_notifier(&uncore_cpu_nb); + + put_online_cpus(); +} + + static int __init intel_uncore_init(void) { int ret; @@ -3885,6 +4287,7 @@ static int __init intel_uncore_init(void) uncore_pci_exit(); goto fail; } + uncore_cpumask_init(); uncore_pmus_register(); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index a80ab71a883d..90236f0c94a9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -6,6 +6,7 @@ #define UNCORE_PMU_NAME_LEN 32 #define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) +#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff #define UNCORE_PMC_IDX_MAX_GENERIC 8 @@ -440,6 +441,7 @@ struct intel_uncore_type { struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; const struct attribute_group *attr_groups[4]; + struct pmu *pmu; /* for custom pmu ops */ }; #define pmu_group attr_groups[0] @@ -488,8 +490,11 @@ struct intel_uncore_box { u64 tags[UNCORE_PMC_IDX_MAX]; struct pci_dev *pci_dev; struct intel_uncore_pmu *pmu; + u64 hrtimer_duration; /* hrtimer timeout for this box */ struct hrtimer hrtimer; struct list_head list; + struct list_head active_list; + void *io_addr; struct intel_uncore_extra_reg shared_regs[0]; }; diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 3486e6660357..5d466b7d8609 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -1257,7 +1257,24 @@ again: pass++; goto again; } - + /* + * Perf does test runs to see if a whole group can be assigned + * together succesfully. There can be multiple rounds of this. + * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config + * bits, such that the next round of group assignments will + * cause the above p4_should_swap_ts to pass instead of fail. + * This leads to counters exclusive to thread0 being used by + * thread1. + * + * Solve this with a cheap hack, reset the idx back to -1 to + * force a new lookup (p4_next_cntr) to get the right counter + * for the right thread. + * + * This probably doesn't comply with the general spirit of how + * perf wants to work, but P4 is special. :-( + */ + if (p4_should_swap_ts(hwc->config, cpu)) + hwc->idx = -1; p4_pmu_swap_config_ts(hwc, cpu); if (assign) assign[i] = cntr_idx; @@ -1322,6 +1339,7 @@ static __initconst const struct x86_pmu p4_pmu = { __init int p4_pmu_init(void) { unsigned int low, high; + int i, reg; /* If we get stripped -- indexing fails */ BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC); @@ -1340,5 +1358,19 @@ __init int p4_pmu_init(void) x86_pmu = p4_pmu; + /* + * Even though the counters are configured to interrupt a particular + * logical processor when an overflow happens, testing has shown that + * on kdump kernels (which uses a single cpu), thread1's counter + * continues to run and will report an NMI on thread0. Due to the + * overflow bug, this leads to a stream of unknown NMIs. + * + * Solve this by zero'ing out the registers to mimic a reset. + */ + for (i = 0; i < x86_pmu.num_counters; i++) { + reg = x86_pmu_config_addr(i); + wrmsrl_safe(reg, 0ULL); + } + return 0; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a57902efe2d5..507de8066594 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -57,9 +57,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { #ifdef CONFIG_X86_32 struct pt_regs fixed_regs; -#endif -#ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); regs = &fixed_regs; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index f2a1770ca176..a21d49c071db 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -30,7 +30,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long dummy; stack = &dummy; - if (task && task != current) + if (task != current) stack = (unsigned long *)task->thread.sp; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 81ba27679f18..f36bd42d6f0c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers) /* This is global to keep gas from relaxing the jumps */ ENTRY(early_idt_handler) cld + + cmpl $2,(%esp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,%ss:early_recursion_flag je hlt_loop incl %ss:early_recursion_flag @@ -594,8 +598,9 @@ ex_entry: pop %edx pop %ecx pop %eax - addl $8,%esp /* drop vector number and error code */ decl %ss:early_recursion_flag +is_nmi: + addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e1aabdb314c8..a468c0a65c42 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,6 +343,9 @@ early_idt_handlers: ENTRY(early_idt_handler) cld + cmpl $2,(%rsp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,early_recursion_flag(%rip) jz 1f incl early_recursion_flag(%rip) @@ -405,8 +408,9 @@ ENTRY(early_idt_handler) popq %rdx popq %rcx popq %rax - addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) +is_nmi: + addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e8368c6dd2a2..d5dd80814419 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin); void __kernel_fpu_end(void) { - if (use_eager_fpu()) - math_state_restore(); - else + if (use_eager_fpu()) { + /* + * For eager fpu, most the time, tsk_used_math() is true. + * Restore the user math as we are done with the kernel usage. + * At few instances during thread exit, signal handling etc, + * tsk_used_math() is false. Those few places will take proper + * actions, so we don't need to restore the math here. + */ + if (likely(tsk_used_math(current))) + math_state_restore(); + } else { stts(); + } } EXPORT_SYMBOL(__kernel_fpu_end); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 18be189368bb..e69f9882bf95 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/jump_label.h> +#include <linux/random.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -43,13 +44,52 @@ do { \ } while (0) #endif +#ifdef CONFIG_RANDOMIZE_BASE +static unsigned long module_load_offset; +static int randomize_modules = 1; + +/* Mutex protects the module_load_offset. */ +static DEFINE_MUTEX(module_kaslr_mutex); + +static int __init parse_nokaslr(char *p) +{ + randomize_modules = 0; + return 0; +} +early_param("nokaslr", parse_nokaslr); + +static unsigned long int get_module_load_offset(void) +{ + if (randomize_modules) { + mutex_lock(&module_kaslr_mutex); + /* + * Calculate the module_load_offset the first time this + * code is called. Once calculated it stays the same until + * reboot. + */ + if (module_load_offset == 0) + module_load_offset = + (get_random_int() % 1024 + 1) * PAGE_SIZE; + mutex_unlock(&module_kaslr_mutex); + } + return module_load_offset; +} +#else +static unsigned long int get_module_load_offset(void) +{ + return 0; +} +#endif + void *module_alloc(unsigned long size) { if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - NUMA_NO_NODE, __builtin_return_address(0)); + return __vmalloc_node_range(size, 1, + MODULES_VADDR + get_module_load_offset(), + MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, + PAGE_KERNEL_EXEC, NUMA_NO_NODE, + __builtin_return_address(0)); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 6fcb49ce50a1..b4872b999a71 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -87,6 +87,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; + static int __init nmi_warning_debugfs(void) { debugfs_create_u64("nmi_longest_ns", 0644, @@ -95,6 +96,20 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); +static void nmi_max_handler(struct irq_work *w) +{ + struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + int remainder_ns, decimal_msecs; + u64 whole_msecs = ACCESS_ONCE(a->max_duration); + + remainder_ns = do_div(whole_msecs, (1000 * 1000)); + decimal_msecs = remainder_ns / 1000; + + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", + a->handler, whole_msecs, decimal_msecs); +} + static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); @@ -110,26 +125,20 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * to handle those situations. */ list_for_each_entry_rcu(a, &desc->head, list) { - u64 before, delta, whole_msecs; - int remainder_ns, decimal_msecs, thishandled; + int thishandled; + u64 delta; - before = sched_clock(); + delta = sched_clock(); thishandled = a->handler(type, regs); handled += thishandled; - delta = sched_clock() - before; + delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns) + if (delta < nmi_longest_ns || delta < a->max_duration) continue; - nmi_longest_ns = delta; - whole_msecs = delta; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); - decimal_msecs = remainder_ns / 1000; - printk_ratelimited(KERN_INFO - "INFO: NMI handler (%ps) took too long to run: " - "%lld.%03d msecs\n", a->handler, whole_msecs, - decimal_msecs); + a->max_duration = delta; + irq_work_queue(&a->irq_work); } rcu_read_unlock(); @@ -146,6 +155,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; + init_irq_work(&action->irq_work, nmi_max_handler); + spin_lock_irqsave(&desc->lock, flags); /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3fb8d95ab8b5..4505e2a950d8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -298,10 +298,7 @@ void arch_cpu_idle_dead(void) */ void arch_cpu_idle(void) { - if (cpuidle_idle_call()) - x86_idle(); - else - local_irq_enable(); + x86_idle(); } /* diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 7c6acd4b8995..ff898bbf579d 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - node = val & 7; + node = pcibus_to_node(dev->bus) | (val & 7); /* * Some hardware may return an invalid node ID, * so check it first: diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 06853e670354..fa511acff7e6 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -926,11 +926,11 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); - set_bit(EFI_64BIT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } if (efi_enabled(EFI_BOOT)) @@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p) register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI - /* Once setup is done above, unmap the EFI memory map on - * mismatched firmware/kernel archtectures since there is no - * support for runtime services. - */ - if (efi_enabled(EFI_BOOT) && !efi_is_native()) { - pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); - efi_unmap_memmap(); - } + if (efi_enabled(EFI_BOOT)) + efi_apply_memmap_quirks(); #endif } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a32da804252e..60179ec39d4c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -122,8 +122,9 @@ static void smp_callin(void) * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. */ cpuid = smp_processor_id(); - if (apic->wait_for_init_deassert && cpuid != 0) - apic->wait_for_init_deassert(&init_deasserted); + if (apic->wait_for_init_deassert && cpuid) + while (!atomic_read(&init_deasserted)) + cpu_relax(); /* * (This works even if the APIC is not enabled.) @@ -701,11 +702,15 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, int id; int boot_error; + preempt_disable(); + /* * Wake up AP by INIT, INIT, STARTUP sequence. */ - if (cpu) - return wakeup_secondary_cpu_via_init(apicid, start_ip); + if (cpu) { + boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); + goto out; + } /* * Wake up BSP by nmi. @@ -725,6 +730,9 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); } +out: + preempt_enable(); + return boot_error; } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 24d3c91e9812..6ec91c00d84d 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -23,7 +23,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; +__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e81df8fce027..2de1bc09a8d4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3002,10 +3002,8 @@ static int cr8_write_interception(struct vcpu_svm *svm) u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(svm); - if (irqchip_in_kernel(svm->vcpu.kvm)) { - clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); + if (irqchip_in_kernel(svm->vcpu.kvm)) return r; - } if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) return r; kvm_run->exit_reason = KVM_EXIT_SET_TPR; @@ -3567,6 +3565,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK)) return; + clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); + if (irr == -1) return; diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c index 3056702e81fb..ff4fa51a5b1f 100644 --- a/arch/x86/lib/hash.c +++ b/arch/x86/lib/hash.c @@ -32,6 +32,7 @@ */ #include <linux/hash.h> +#include <linux/init.h> #include <asm/processor.h> #include <asm/cpufeature.h> @@ -39,7 +40,11 @@ static inline u32 crc32_u32(u32 crc, u32 val) { +#ifdef CONFIG_AS_CRC32 asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val)); +#else + asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val)); +#endif return crc; } @@ -49,19 +54,18 @@ static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed) u32 i, tmp = 0; for (i = 0; i < len / 4; i++) - seed = crc32_u32(*p32++, seed); + seed = crc32_u32(seed, *p32++); - switch (3 - (len & 0x03)) { - case 0: + switch (len & 3) { + case 3: tmp |= *((const u8 *) p32 + 2) << 16; /* fallthrough */ - case 1: + case 2: tmp |= *((const u8 *) p32 + 1) << 8; /* fallthrough */ - case 2: + case 1: tmp |= *((const u8 *) p32); - seed = crc32_u32(tmp, seed); - default: + seed = crc32_u32(seed, tmp); break; } @@ -74,12 +78,12 @@ static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed) u32 i; for (i = 0; i < len; i++) - seed = crc32_u32(*p32++, seed); + seed = crc32_u32(seed, *p32++); return seed; } -void setup_arch_fast_hash(struct fast_hash_ops *ops) +void __init setup_arch_fast_hash(struct fast_hash_ops *ops) { if (cpu_has_xmm4_2) { ops->hash = intel_crc4_2_hash; diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index e78761d6b7f8..a404b4b75533 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -4,7 +4,7 @@ #undef memcpy #undef memset -void *memcpy(void *to, const void *from, size_t n) +__visible void *memcpy(void *to, const void *from, size_t n) { #ifdef CONFIG_X86_USE_3DNOW return __memcpy3d(to, from, n); @@ -14,13 +14,13 @@ void *memcpy(void *to, const void *from, size_t n) } EXPORT_SYMBOL(memcpy); -void *memset(void *s, int c, size_t count) +__visible void *memset(void *s, int c, size_t count) { return __memset(s, c, count); } EXPORT_SYMBOL(memset); -void *memmove(void *dest, const void *src, size_t n) +__visible void *memmove(void *dest, const void *src, size_t n) { int d0,d1,d2,d3,d4,d5; char *ret = dest; diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 8f8eebdca7d4..db9db446b71a 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -8,7 +8,7 @@ struct msr *msrs_alloc(void) msrs = alloc_percpu(struct msr); if (!msrs) { - pr_warning("%s: error allocating msrs\n", __func__); + pr_warn("%s: error allocating msrs\n", __func__); return NULL; } @@ -21,3 +21,90 @@ void msrs_free(struct msr *msrs) free_percpu(msrs); } EXPORT_SYMBOL(msrs_free); + +/** + * Read an MSR with error handling + * + * @msr: MSR to read + * @m: value to read into + * + * It returns read data only on success, otherwise it doesn't change the output + * argument @m. + * + */ +int msr_read(u32 msr, struct msr *m) +{ + int err; + u64 val; + + err = rdmsrl_safe(msr, &val); + if (!err) + m->q = val; + + return err; +} + +/** + * Write an MSR with error handling + * + * @msr: MSR to write + * @m: value to write + */ +int msr_write(u32 msr, struct msr *m) +{ + return wrmsrl_safe(msr, m->q); +} + +static inline int __flip_bit(u32 msr, u8 bit, bool set) +{ + struct msr m, m1; + int err = -EINVAL; + + if (bit > 63) + return err; + + err = msr_read(msr, &m); + if (err) + return err; + + m1 = m; + if (set) + m1.q |= BIT_64(bit); + else + m1.q &= ~BIT_64(bit); + + if (m1.q == m.q) + return 0; + + err = msr_write(msr, &m); + if (err) + return err; + + return 1; +} + +/** + * Set @bit in a MSR @msr. + * + * Retval: + * < 0: An error was encountered. + * = 0: Bit was already set. + * > 0: Hardware accepted the MSR write. + */ +int msr_set_bit(u32 msr, u8 bit) +{ + return __flip_bit(msr, bit, true); +} + +/** + * Clear @bit in a MSR @msr. + * + * Retval: + * < 0: An error was encountered. + * = 0: Bit was already cleared. + * > 0: Hardware accepted the MSR write. + */ +int msr_clear_bit(u32 msr, u8 bit) +{ + return __flip_bit(msr, bit, false); +} diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0002a3a33081..20621d753d5f 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,6 +30,7 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + bool to_dmesg; }; struct addr_marker { @@ -88,10 +89,28 @@ static struct addr_marker address_markers[] = { #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT) #define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) +#define pt_dump_seq_printf(m, to_dmesg, fmt, args...) \ +({ \ + if (to_dmesg) \ + printk(KERN_INFO fmt, ##args); \ + else \ + if (m) \ + seq_printf(m, fmt, ##args); \ +}) + +#define pt_dump_cont_printf(m, to_dmesg, fmt, args...) \ +({ \ + if (to_dmesg) \ + printk(KERN_CONT fmt, ##args); \ + else \ + if (m) \ + seq_printf(m, fmt, ##args); \ +}) + /* * Print a readable form of a pgprot_t to the seq_file */ -static void printk_prot(struct seq_file *m, pgprot_t prot, int level) +static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) { pgprotval_t pr = pgprot_val(prot); static const char * const level_name[] = @@ -99,47 +118,47 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level) if (!pgprot_val(prot)) { /* Not present */ - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); } else { if (pr & _PAGE_USER) - seq_printf(m, "USR "); + pt_dump_cont_printf(m, dmsg, "USR "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_RW) - seq_printf(m, "RW "); + pt_dump_cont_printf(m, dmsg, "RW "); else - seq_printf(m, "ro "); + pt_dump_cont_printf(m, dmsg, "ro "); if (pr & _PAGE_PWT) - seq_printf(m, "PWT "); + pt_dump_cont_printf(m, dmsg, "PWT "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_PCD) - seq_printf(m, "PCD "); + pt_dump_cont_printf(m, dmsg, "PCD "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); /* Bit 9 has a different meaning on level 3 vs 4 */ if (level <= 3) { if (pr & _PAGE_PSE) - seq_printf(m, "PSE "); + pt_dump_cont_printf(m, dmsg, "PSE "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); } else { if (pr & _PAGE_PAT) - seq_printf(m, "pat "); + pt_dump_cont_printf(m, dmsg, "pat "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); } if (pr & _PAGE_GLOBAL) - seq_printf(m, "GLB "); + pt_dump_cont_printf(m, dmsg, "GLB "); else - seq_printf(m, " "); + pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_NX) - seq_printf(m, "NX "); + pt_dump_cont_printf(m, dmsg, "NX "); else - seq_printf(m, "x "); + pt_dump_cont_printf(m, dmsg, "x "); } - seq_printf(m, "%s\n", level_name[level]); + pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]); } /* @@ -178,7 +197,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; - seq_printf(m, "---[ %s ]---\n", st->marker->name); + pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", + st->marker->name); } else if (prot != cur || level != st->level || st->current_address >= st->marker[1].start_address) { const char *unit = units; @@ -188,17 +208,17 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); + pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); delta = (st->current_address - st->start_address) >> 10; while (!(delta & 1023) && unit[1]) { delta >>= 10; unit++; } - seq_printf(m, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level); + pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level, st->to_dmesg); /* * We print markers for special areas of address space, @@ -207,7 +227,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, */ if (st->current_address >= st->marker[1].start_address) { st->marker++; - seq_printf(m, "---[ %s ]---\n", st->marker->name); + pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", + st->marker->name); } st->start_address = st->current_address; @@ -296,7 +317,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, #define pgd_none(a) pud_none(__pud(pgd_val(a))) #endif -static void walk_pgd_level(struct seq_file *m) +void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_level4_pgt; @@ -304,9 +325,12 @@ static void walk_pgd_level(struct seq_file *m) pgd_t *start = swapper_pg_dir; #endif int i; - struct pg_state st; + struct pg_state st = {}; - memset(&st, 0, sizeof(st)); + if (pgd) { + start = pgd; + st.to_dmesg = true; + } for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); @@ -331,7 +355,7 @@ static void walk_pgd_level(struct seq_file *m) static int ptdump_show(struct seq_file *m, void *v) { - walk_pgd_level(m); + ptdump_walk_pgd_level(m, NULL); return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 6dea040cc3a1..8e5722992677 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -584,8 +584,13 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (error_code & PF_INSTR) { unsigned int level; + pgd_t *pgd; + pte_t *pte; - pte_t *pte = lookup_address(address, &level); + pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd += pgd_index(address); + + pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) printk(nx_warning, from_kuid(&init_user_ns, current_uid())); @@ -1020,13 +1025,17 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. + * + * This function must have noinline because both callers + * {,trace_}do_page_fault() have notrace on. Having this an actual function + * guarantees there's a function trace entry. */ -static void __kprobes -__do_page_fault(struct pt_regs *regs, unsigned long error_code) +static void __kprobes noinline +__do_page_fault(struct pt_regs *regs, unsigned long error_code, + unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; - unsigned long address; struct mm_struct *mm; int fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -1034,9 +1043,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) tsk = current; mm = tsk->mm; - /* Get the faulting address: */ - address = read_cr2(); - /* * Detect and handle instructions that would cause a page fault for * both a tracked kernel page and a userspace page. @@ -1248,32 +1254,50 @@ good_area: up_read(&mm->mmap_sem); } -dotraplinkage void __kprobes +dotraplinkage void __kprobes notrace do_page_fault(struct pt_regs *regs, unsigned long error_code) { + unsigned long address = read_cr2(); /* Get the faulting address */ enum ctx_state prev_state; + /* + * We must have this function tagged with __kprobes, notrace and call + * read_cr2() before calling anything else. To avoid calling any kind + * of tracing machinery before we've observed the CR2 value. + * + * exception_{enter,exit}() contain all sorts of tracepoints. + */ + prev_state = exception_enter(); - __do_page_fault(regs, error_code); + __do_page_fault(regs, error_code, address); exception_exit(prev_state); } -static void trace_page_fault_entries(struct pt_regs *regs, +#ifdef CONFIG_TRACING +static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, unsigned long error_code) { if (user_mode(regs)) - trace_page_fault_user(read_cr2(), regs, error_code); + trace_page_fault_user(address, regs, error_code); else - trace_page_fault_kernel(read_cr2(), regs, error_code); + trace_page_fault_kernel(address, regs, error_code); } -dotraplinkage void __kprobes +dotraplinkage void __kprobes notrace trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) { + /* + * The exception_enter and tracepoint processing could + * trigger another page faults (user space callchain + * reading) and destroy the original cr2 value, so read + * the faulting address now. + */ + unsigned long address = read_cr2(); enum ctx_state prev_state; prev_state = exception_enter(); - trace_page_fault_entries(regs, error_code); - __do_page_fault(regs, error_code); + trace_page_fault_entries(address, regs, error_code); + __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +#endif /* CONFIG_TRACING */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index b3b19f46c016..ae242a7c11c7 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -126,8 +126,8 @@ within(unsigned long addr, unsigned long start, unsigned long end) * @vaddr: virtual start address * @size: number of bytes to flush * - * clflush is an unordered instruction which needs fencing with mfence - * to avoid ordering issues. + * clflushopt is an unordered instruction which needs fencing with mfence or + * sfence to avoid ordering issues. */ void clflush_cache_range(void *vaddr, unsigned int size) { @@ -136,11 +136,11 @@ void clflush_cache_range(void *vaddr, unsigned int size) mb(); for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size) - clflush(vaddr); + clflushopt(vaddr); /* * Flush any possible final partial cacheline: */ - clflush(vend); + clflushopt(vend); mb(); } @@ -323,8 +323,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, return prot; } -static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address, - unsigned int *level) +/* + * Lookup the page table entry for a virtual address in a specific pgd. + * Return a pointer to the entry and the level of the mapping. + */ +pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level) { pud_t *pud; pmd_t *pmd; @@ -365,7 +369,7 @@ static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address, */ pte_t *lookup_address(unsigned long address, unsigned int *level) { - return __lookup_address_in_pgd(pgd_offset_k(address), address, level); + return lookup_address_in_pgd(pgd_offset_k(address), address, level); } EXPORT_SYMBOL_GPL(lookup_address); @@ -373,7 +377,7 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { if (cpa->pgd) - return __lookup_address_in_pgd(cpa->pgd + pgd_index(address), + return lookup_address_in_pgd(cpa->pgd + pgd_index(address), address, level); return lookup_address(address, level); @@ -692,6 +696,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd) return true; } +static bool try_to_free_pud_page(pud_t *pud) +{ + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) + if (!pud_none(pud[i])) + return false; + + free_page((unsigned long)pud); + return true; +} + static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); @@ -805,6 +821,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) */ } +static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) +{ + pgd_t *pgd_entry = root + pgd_index(addr); + + unmap_pud_range(pgd_entry, addr, end); + + if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry))) + pgd_clear(pgd_entry); +} + static int alloc_pte_page(pmd_t *pmd) { pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); @@ -999,9 +1025,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, static int populate_pgd(struct cpa_data *cpa, unsigned long addr) { pgprot_t pgprot = __pgprot(_KERNPG_TABLE); - bool allocd_pgd = false; - pgd_t *pgd_entry; pud_t *pud = NULL; /* shut up gcc */ + pgd_t *pgd_entry; int ret; pgd_entry = cpa->pgd + pgd_index(addr); @@ -1015,7 +1040,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) return -1; set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); - allocd_pgd = true; } pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); @@ -1023,19 +1047,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) ret = populate_pud(cpa, addr, pgd_entry, pgprot); if (ret < 0) { - unmap_pud_range(pgd_entry, addr, + unmap_pgd_range(cpa->pgd, addr, addr + (cpa->numpages << PAGE_SHIFT)); - - if (allocd_pgd) { - /* - * If I allocated this PUD page, I can just as well - * free it in this error path. - */ - pgd_clear(pgd_entry); - free_page((unsigned long)pud); - } return ret; } + cpa->numpages = ret; return 0; } @@ -1377,10 +1393,10 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cache = cache_attr(mask_set); /* - * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it and in the + * On success we use CLFLUSH, when the CPU supports it to + * avoid the WBINVD. If the CPU does not support it and in the * error case we fall back to cpa_flush_all (which uses - * wbindv): + * WBINVD): */ if (!ret && cpu_has_clflush) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { @@ -1861,6 +1877,12 @@ out: return retval; } +void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, + unsigned numpages) +{ + unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT)); +} + /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 877b9a1b2152..01495755701b 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -140,7 +140,7 @@ bpf_slow_path_byte_msh: push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ - mov $SIZE,%ecx; /* size */ \ + mov $SIZE,%edx; /* size */ \ call bpf_internal_load_pointer_neg_helper; \ test %rax,%rax; \ pop SKBDATA; \ diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index b7b0b35c1981..d51045afcaaf 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o +obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 1a201ac7cef8..3781dd39e8bd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -52,6 +52,7 @@ #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/rtc.h> +#include <asm/uv/uv.h> #define EFI_DEBUG @@ -67,9 +68,7 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -unsigned long x86_efi_facility; - -static __initdata efi_config_table_type_t arch_tables[] = { +static efi_config_table_type_t arch_tables[] __initdata = { #ifdef CONFIG_X86_UV {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab}, #endif @@ -78,16 +77,7 @@ static __initdata efi_config_table_type_t arch_tables[] = { u64 efi_setup; /* efi setup_data physical address */ -/* - * Returns 1 if 'facility' is enabled, 0 otherwise. - */ -int efi_enabled(int facility) -{ - return test_bit(facility, &x86_efi_facility) != 0; -} -EXPORT_SYMBOL(efi_enabled); - -static bool __initdata disable_runtime = false; +static bool disable_runtime __initdata = false; static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -256,27 +246,12 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -static efi_status_t __init phys_efi_get_time(efi_time_t *tm, - efi_time_cap_t *tc) -{ - unsigned long flags; - efi_status_t status; - - spin_lock_irqsave(&rtc_lock, flags); - efi_call_phys_prelog(); - status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm), - virt_to_phys(tc)); - efi_call_phys_epilog(); - spin_unlock_irqrestore(&rtc_lock, flags); - return status; -} - int efi_set_rtc_mmss(const struct timespec *now) { unsigned long nowtime = now->tv_sec; - efi_status_t status; - efi_time_t eft; - efi_time_cap_t cap; + efi_status_t status; + efi_time_t eft; + efi_time_cap_t cap; struct rtc_time tm; status = efi.get_time(&eft, &cap); @@ -294,9 +269,8 @@ int efi_set_rtc_mmss(const struct timespec *now) eft.second = tm.tm_sec; eft.nanosecond = 0; } else { - printk(KERN_ERR - "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", - __FUNCTION__, nowtime); + pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", + __func__, nowtime); return -1; } @@ -412,8 +386,7 @@ static void __init print_efi_memmap(void) p < memmap.map_end; p += memmap.desc_size, i++) { md = p; - pr_info("mem%02u: type=%u, attr=0x%llx, " - "range=[0x%016llx-0x%016llx) (%lluMB)\n", + pr_info("mem%02u: type=%u, attr=0x%llx, range=[0x%016llx-0x%016llx) (%lluMB)\n", i, md->type, md->attribute, md->phys_addr, md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT), (md->num_pages >> (20 - EFI_PAGE_SHIFT))); @@ -445,9 +418,8 @@ void __init efi_reserve_boot_services(void) memblock_is_region_reserved(start, size)) { /* Could not reserve, skip it */ md->num_pages = 0; - memblock_dbg("Could not reserve boot range " - "[0x%010llx-0x%010llx]\n", - start, start+size-1); + memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", + start, start+size-1); } else memblock_reserve(start, size); } @@ -455,7 +427,7 @@ void __init efi_reserve_boot_services(void) void __init efi_unmap_memmap(void) { - clear_bit(EFI_MEMMAP, &x86_efi_facility); + clear_bit(EFI_MEMMAP, &efi.flags); if (memmap.map) { early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; @@ -466,9 +438,6 @@ void __init efi_free_boot_services(void) { void *p; - if (!efi_is_native()) - return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; unsigned long long start = md->phys_addr; @@ -583,45 +552,82 @@ static int __init efi_systab_init(void *phys) return -EINVAL; } if ((efi.systab->hdr.revision >> 16) == 0) - pr_err("Warning: System table version " - "%d.%02d, expected 1.00 or greater!\n", + pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + return 0; } -static int __init efi_runtime_init(void) +static int __init efi_runtime_init32(void) { - efi_runtime_services_t *runtime; + efi_runtime_services_32_t *runtime; + + runtime = early_ioremap((unsigned long)efi.systab->runtime, + sizeof(efi_runtime_services_32_t)); + if (!runtime) { + pr_err("Could not map the runtime service table!\n"); + return -ENOMEM; + } /* - * Check out the runtime services table. We need to map - * the runtime services table so that we can grab the physical - * address of several of the EFI runtime functions, needed to - * set the firmware into virtual mode. + * We will only need *early* access to the following two + * EFI runtime services before set_virtual_address_map + * is invoked. */ + efi_phys.set_virtual_address_map = + (efi_set_virtual_address_map_t *) + (unsigned long)runtime->set_virtual_address_map; + early_iounmap(runtime, sizeof(efi_runtime_services_32_t)); + + return 0; +} + +static int __init efi_runtime_init64(void) +{ + efi_runtime_services_64_t *runtime; + runtime = early_ioremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_t)); + sizeof(efi_runtime_services_64_t)); if (!runtime) { pr_err("Could not map the runtime service table!\n"); return -ENOMEM; } + /* - * We will only need *early* access to the following - * two EFI runtime services before set_virtual_address_map + * We will only need *early* access to the following two + * EFI runtime services before set_virtual_address_map * is invoked. */ - efi_phys.get_time = (efi_get_time_t *)runtime->get_time; efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - runtime->set_virtual_address_map; + (efi_set_virtual_address_map_t *) + (unsigned long)runtime->set_virtual_address_map; + early_iounmap(runtime, sizeof(efi_runtime_services_64_t)); + + return 0; +} + +static int __init efi_runtime_init(void) +{ + int rv; + /* - * Make efi_get_time can be called before entering - * virtual mode. + * Check out the runtime services table. We need to map + * the runtime services table so that we can grab the physical + * address of several of the EFI runtime functions, needed to + * set the firmware into virtual mode. */ - efi.get_time = phys_efi_get_time; - early_iounmap(runtime, sizeof(efi_runtime_services_t)); + if (efi_enabled(EFI_64BIT)) + rv = efi_runtime_init64(); + else + rv = efi_runtime_init32(); + + if (rv) + return rv; + + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); return 0; } @@ -640,6 +646,8 @@ static int __init efi_memmap_init(void) if (add_efi_memmap) do_add_efi_memmap(); + set_bit(EFI_MEMMAP, &efi.flags); + return 0; } @@ -722,7 +730,7 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); efi.config_table = (unsigned long)efi.systab->tables; efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; @@ -750,24 +758,21 @@ void __init efi_init(void) if (efi_config_init(arch_tables)) return; - set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); - /* * Note: We currently don't support runtime services on an EFI * that doesn't match the kernel 32/64-bit mode. */ - if (!efi_is_native()) + if (!efi_runtime_supported()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); else { if (disable_runtime || efi_runtime_init()) return; - set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &x86_efi_facility); + set_bit(EFI_MEMMAP, &efi.flags); print_efi_memmap(); } @@ -844,6 +849,22 @@ void __init old_map_region(efi_memory_desc_t *md) (unsigned long long)md->phys_addr); } +static void native_runtime_setup(void) +{ + efi.get_time = virt_efi_get_time; + efi.set_time = virt_efi_set_time; + efi.get_wakeup_time = virt_efi_get_wakeup_time; + efi.set_wakeup_time = virt_efi_set_wakeup_time; + efi.get_variable = virt_efi_get_variable; + efi.get_next_variable = virt_efi_get_next_variable; + efi.set_variable = virt_efi_set_variable; + efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count; + efi.reset_system = virt_efi_reset_system; + efi.query_variable_info = virt_efi_query_variable_info; + efi.update_capsule = virt_efi_update_capsule; + efi.query_capsule_caps = virt_efi_query_capsule_caps; +} + /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { @@ -891,8 +912,9 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) } } -static int __init save_runtime_map(void) +static void __init save_runtime_map(void) { +#ifdef CONFIG_KEXEC efi_memory_desc_t *md; void *tmp, *p, *q = NULL; int count = 0; @@ -914,38 +936,44 @@ static int __init save_runtime_map(void) } efi_runtime_map_setup(q, count, memmap.desc_size); + return; - return 0; out: kfree(q); - return -ENOMEM; + pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); +#endif } -/* - * Map efi regions which were passed via setup_data. The virt_addr is a fixed - * addr which was used in first kernel of a kexec boot. - */ -static void __init efi_map_regions_fixed(void) +static void *realloc_pages(void *old_memmap, int old_shift) { - void *p; - efi_memory_desc_t *md; + void *ret; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - efi_map_region_fixed(md); /* FIXME: add error handling */ - get_systab_virt_addr(md); - } + ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1); + if (!ret) + goto out; + /* + * A first-time allocation doesn't have anything to copy. + */ + if (!old_memmap) + return ret; + + memcpy(ret, old_memmap, PAGE_SIZE << old_shift); + +out: + free_pages((unsigned long)old_memmap, old_shift); + return ret; } /* - * Map efi memory ranges for runtime serivce and update new_memmap with virtual - * addresses. + * Map the efi memory ranges of the runtime services and update new_mmap with + * virtual addresses. */ -static void * __init efi_map_regions(int *count) +static void * __init efi_map_regions(int *count, int *pg_shift) { + void *p, *new_memmap = NULL; + unsigned long left = 0; efi_memory_desc_t *md; - void *p, *tmp, *new_memmap = NULL; for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; @@ -960,20 +988,80 @@ static void * __init efi_map_regions(int *count) efi_map_region(md); get_systab_virt_addr(md); - tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size, - GFP_KERNEL); - if (!tmp) - goto out; - new_memmap = tmp; + if (left < memmap.desc_size) { + new_memmap = realloc_pages(new_memmap, *pg_shift); + if (!new_memmap) + return NULL; + + left += PAGE_SIZE << *pg_shift; + (*pg_shift)++; + } + memcpy(new_memmap + (*count * memmap.desc_size), md, memmap.desc_size); + + left -= memmap.desc_size; (*count)++; } return new_memmap; -out: - kfree(new_memmap); - return NULL; +} + +static void __init kexec_enter_virtual_mode(void) +{ +#ifdef CONFIG_KEXEC + efi_memory_desc_t *md; + void *p; + + efi.systab = NULL; + + /* + * We don't do virtual mode, since we don't do runtime services, on + * non-native EFI + */ + if (!efi_is_native()) { + efi_unmap_memmap(); + return; + } + + /* + * Map efi regions which were passed via setup_data. The virt_addr is a + * fixed addr which was used in first kernel of a kexec boot. + */ + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + md = p; + efi_map_region_fixed(md); /* FIXME: add error handling */ + get_systab_virt_addr(md); + } + + save_runtime_map(); + + BUG_ON(!efi.systab); + + efi_sync_low_kernel_mappings(); + + /* + * Now that EFI is in virtual mode, update the function + * pointers in the runtime service table to the new virtual addresses. + * + * Call EFI services through wrapper functions. + */ + efi.runtime_version = efi_systab.hdr.revision; + + native_runtime_setup(); + + efi.set_virtual_address_map = NULL; + + if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) + runtime_code_page_mkexec(); + + /* clean DUMMY object */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); +#endif } /* @@ -995,57 +1083,53 @@ out: * * Specially for kexec boot, efi runtime maps in previous kernel should * be passed in via setup_data. In that case runtime ranges will be mapped - * to the same virtual addresses as the first kernel. + * to the same virtual addresses as the first kernel, see + * kexec_enter_virtual_mode(). */ -void __init efi_enter_virtual_mode(void) +static void __init __efi_enter_virtual_mode(void) { - efi_status_t status; + int count = 0, pg_shift = 0; void *new_memmap = NULL; - int err, count = 0; + efi_status_t status; efi.systab = NULL; - /* - * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI - */ - if (!efi_is_native()) { - efi_unmap_memmap(); + efi_merge_regions(); + new_memmap = efi_map_regions(&count, &pg_shift); + if (!new_memmap) { + pr_err("Error reallocating memory, EFI runtime non-functional!\n"); return; } - if (efi_setup) { - efi_map_regions_fixed(); - } else { - efi_merge_regions(); - new_memmap = efi_map_regions(&count); - if (!new_memmap) { - pr_err("Error reallocating memory, EFI runtime non-functional!\n"); - return; - } - } - - err = save_runtime_map(); - if (err) - pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); + save_runtime_map(); BUG_ON(!efi.systab); - efi_setup_page_tables(); + if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) + return; + efi_sync_low_kernel_mappings(); + efi_dump_pagetable(); - if (!efi_setup) { + if (efi_is_native()) { status = phys_efi_set_virtual_address_map( - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, - (efi_memory_desc_t *)__pa(new_memmap)); - - if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", - status); - panic("EFI call to SetVirtualAddressMap() failed!"); - } + memmap.desc_size * count, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)__pa(new_memmap)); + } else { + status = efi_thunk_set_virtual_address_map( + efi_phys.set_virtual_address_map, + memmap.desc_size * count, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)__pa(new_memmap)); + } + + if (status != EFI_SUCCESS) { + pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + panic("EFI call to SetVirtualAddressMap() failed!"); } /* @@ -1055,23 +1139,43 @@ void __init efi_enter_virtual_mode(void) * Call EFI services through wrapper functions. */ efi.runtime_version = efi_systab.hdr.revision; - efi.get_time = virt_efi_get_time; - efi.set_time = virt_efi_set_time; - efi.get_wakeup_time = virt_efi_get_wakeup_time; - efi.set_wakeup_time = virt_efi_set_wakeup_time; - efi.get_variable = virt_efi_get_variable; - efi.get_next_variable = virt_efi_get_next_variable; - efi.set_variable = virt_efi_set_variable; - efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count; - efi.reset_system = virt_efi_reset_system; + + if (efi_is_native()) + native_runtime_setup(); + else + efi_thunk_runtime_setup(); + efi.set_virtual_address_map = NULL; - efi.query_variable_info = virt_efi_query_variable_info; - efi.update_capsule = virt_efi_update_capsule; - efi.query_capsule_caps = virt_efi_query_capsule_caps; efi_runtime_mkexec(); - kfree(new_memmap); + /* + * We mapped the descriptor array into the EFI pagetable above but we're + * not unmapping it here. Here's why: + * + * We're copying select PGDs from the kernel page table to the EFI page + * table and when we do so and make changes to those PGDs like unmapping + * stuff from them, those changes appear in the kernel page table and we + * go boom. + * + * From setup_real_mode(): + * + * ... + * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd; + * + * In this particular case, our allocation is in PGD 0 of the EFI page + * table but we've copied that PGD from PGD[272] of the EFI page table: + * + * pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272 + * + * where the direct memory mapping in kernel space is. + * + * new_memmap's VA comes from that direct mapping and thus clearing it, + * it would get cleared in the kernel page table too. + * + * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift); + */ + free_pages((unsigned long)new_memmap, pg_shift); /* clean DUMMY object */ efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, @@ -1081,6 +1185,14 @@ void __init efi_enter_virtual_mode(void) 0, NULL); } +void __init efi_enter_virtual_mode(void) +{ + if (efi_setup) + kexec_enter_virtual_mode(); + else + __efi_enter_virtual_mode(); +} + /* * Convenience functions to obtain memory types and attributes */ @@ -1118,9 +1230,8 @@ u64 efi_mem_attributes(unsigned long phys_addr) } /* - * Some firmware has serious problems when using more than 50% of the EFI - * variable store, i.e. it triggers bugs that can brick machines. Ensure that - * we never use more than this safe limit. + * Some firmware implementations refuse to boot if there's insufficient space + * in the variable store. Ensure that we never use more than a safe limit. * * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable * store. @@ -1139,10 +1250,9 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) return status; /* - * Some firmware implementations refuse to boot if there's insufficient - * space in the variable store. We account for that by refusing the - * write if permitting it would reduce the available space to under - * 5KB. This figure was provided by Samsung, so should be safe. + * We account for that by refusing the write if permitting it would + * reduce the available space to under 5KB. This figure was provided by + * Samsung, so should be safe. */ if ((remaining_size - size < EFI_MIN_RESERVE) && !efi_no_storage_paranoia) { @@ -1205,8 +1315,27 @@ static int __init parse_efi_cmdline(char *str) str++; if (!strncmp(str, "old_map", 7)) - set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + set_bit(EFI_OLD_MEMMAP, &efi.flags); return 0; } early_param("efi", parse_efi_cmdline); + +void __init efi_apply_memmap_quirks(void) +{ + /* + * Once setup is done earlier, unmap the EFI memory map on mismatched + * firmware/kernel architectures since there is no support for runtime + * services. + */ + if (!efi_runtime_supported()) { + pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); + efi_unmap_memmap(); + } + + /* + * UV doesn't support the new EFI pagetable mapping yet. + */ + if (is_uv_system()) + set_bit(EFI_OLD_MEMMAP, &efi.flags); +} diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 0b74cdf7f816..9ee3491e31fb 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -40,7 +40,12 @@ static unsigned long efi_rt_eflags; void efi_sync_low_kernel_mappings(void) {} -void efi_setup_page_tables(void) {} +void __init efi_dump_pagetable(void) {} +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + return 0; +} +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {} void __init efi_map_region(efi_memory_desc_t *md) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 0c2a234fef1e..290d397e1dd9 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -39,6 +39,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/realmode.h> +#include <asm/time.h> static pgd_t *save_pgd __initdata; static unsigned long efi_flags __initdata; @@ -58,7 +59,8 @@ struct efi_scratch { u64 prev_cr3; pgd_t *efi_pgt; bool use_pgd; -}; + u64 phys_stack; +} __packed; static void __init early_code_mapping_set_exec(int executable) { @@ -137,12 +139,64 @@ void efi_sync_low_kernel_mappings(void) sizeof(pgd_t) * num_pgds); } -void efi_setup_page_tables(void) +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { + unsigned long text; + struct page *page; + unsigned npages; + pgd_t *pgd; + + if (efi_enabled(EFI_OLD_MEMMAP)) + return 0; + efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; + pgd = __va(efi_scratch.efi_pgt); - if (!efi_enabled(EFI_OLD_MEMMAP)) - efi_scratch.use_pgd = true; + /* + * It can happen that the physical address of new_memmap lands in memory + * which is not mapped in the EFI page table. Therefore we need to go + * and ident-map those pages containing the map before calling + * phys_efi_set_virtual_address_map(). + */ + if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) { + pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); + return 1; + } + + efi_scratch.use_pgd = true; + + /* + * When making calls to the firmware everything needs to be 1:1 + * mapped and addressable with 32-bit pointers. Map the kernel + * text and allocate a new stack because we can't rely on the + * stack pointer being < 4GB. + */ + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return 0; + + page = alloc_page(GFP_KERNEL|__GFP_DMA32); + if (!page) + panic("Unable to allocate EFI runtime stack < 4GB\n"); + + efi_scratch.phys_stack = virt_to_phys(page_address(page)); + efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ + + npages = (_end - _text) >> PAGE_SHIFT; + text = __pa(_text); + + if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) { + pr_err("Failed to map kernel text 1:1\n"); + return 1; + } + + return 0; +} + +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages); } static void __init __map_region(efi_memory_desc_t *md, u64 va) @@ -173,6 +227,16 @@ void __init efi_map_region(efi_memory_desc_t *md) */ __map_region(md, md->phys_addr); + /* + * Enforce the 1:1 mapping as the default virtual address when + * booting in EFI mixed mode, because even though we may be + * running a 64-bit kernel, the firmware may only be 32-bit. + */ + if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) { + md->virt_addr = md->phys_addr; + return; + } + efi_va -= size; /* Is PA 2M-aligned? */ @@ -242,3 +306,299 @@ void __init efi_runtime_mkexec(void) if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); } + +void __init efi_dump_pagetable(void) +{ +#ifdef CONFIG_EFI_PGT_DUMP + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + ptdump_walk_pgd_level(NULL, pgd); +#endif +} + +#ifdef CONFIG_EFI_MIXED +extern efi_status_t efi64_thunk(u32, ...); + +#define runtime_service32(func) \ +({ \ + u32 table = (u32)(unsigned long)efi.systab; \ + u32 *rt, *___f; \ + \ + rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime)); \ + ___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \ + *___f; \ +}) + +/* + * Switch to the EFI page tables early so that we can access the 1:1 + * runtime services mappings which are not mapped in any other page + * tables. This function must be called before runtime_service32(). + * + * Also, disable interrupts because the IDT points to 64-bit handlers, + * which aren't going to function correctly when we switch to 32-bit. + */ +#define efi_thunk(f, ...) \ +({ \ + efi_status_t __s; \ + unsigned long flags; \ + u32 func; \ + \ + efi_sync_low_kernel_mappings(); \ + local_irq_save(flags); \ + \ + efi_scratch.prev_cr3 = read_cr3(); \ + write_cr3((unsigned long)efi_scratch.efi_pgt); \ + __flush_tlb_all(); \ + \ + func = runtime_service32(f); \ + __s = efi64_thunk(func, __VA_ARGS__); \ + \ + write_cr3(efi_scratch.prev_cr3); \ + __flush_tlb_all(); \ + local_irq_restore(flags); \ + \ + __s; \ +}) + +efi_status_t efi_thunk_set_virtual_address_map( + void *phys_set_virtual_address_map, + unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) +{ + efi_status_t status; + unsigned long flags; + u32 func; + + efi_sync_low_kernel_mappings(); + local_irq_save(flags); + + efi_scratch.prev_cr3 = read_cr3(); + write_cr3((unsigned long)efi_scratch.efi_pgt); + __flush_tlb_all(); + + func = (u32)(unsigned long)phys_set_virtual_address_map; + status = efi64_thunk(func, memory_map_size, descriptor_size, + descriptor_version, virtual_map); + + write_cr3(efi_scratch.prev_cr3); + __flush_tlb_all(); + local_irq_restore(flags); + + return status; +} + +static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) +{ + efi_status_t status; + u32 phys_tm, phys_tc; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + phys_tc = virt_to_phys(tc); + + status = efi_thunk(get_time, phys_tm, phys_tc); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t efi_thunk_set_time(efi_time_t *tm) +{ + efi_status_t status; + u32 phys_tm; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + + status = efi_thunk(set_time, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t +efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, + efi_time_t *tm) +{ + efi_status_t status; + u32 phys_enabled, phys_pending, phys_tm; + + spin_lock(&rtc_lock); + + phys_enabled = virt_to_phys(enabled); + phys_pending = virt_to_phys(pending); + phys_tm = virt_to_phys(tm); + + status = efi_thunk(get_wakeup_time, phys_enabled, + phys_pending, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t +efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +{ + efi_status_t status; + u32 phys_tm; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + + status = efi_thunk(set_wakeup_time, enabled, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + + +static efi_status_t +efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, void *data) +{ + efi_status_t status; + u32 phys_name, phys_vendor, phys_attr; + u32 phys_data_size, phys_data; + + phys_data_size = virt_to_phys(data_size); + phys_vendor = virt_to_phys(vendor); + phys_name = virt_to_phys(name); + phys_attr = virt_to_phys(attr); + phys_data = virt_to_phys(data); + + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); + + return status; +} + +static efi_status_t +efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, void *data) +{ + u32 phys_name, phys_vendor, phys_data; + efi_status_t status; + + phys_name = virt_to_phys(name); + phys_vendor = virt_to_phys(vendor); + phys_data = virt_to_phys(data); + + /* If data_size is > sizeof(u32) we've got problems */ + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); + + return status; +} + +static efi_status_t +efi_thunk_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) +{ + efi_status_t status; + u32 phys_name_size, phys_name, phys_vendor; + + phys_name_size = virt_to_phys(name_size); + phys_vendor = virt_to_phys(vendor); + phys_name = virt_to_phys(name); + + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); + + return status; +} + +static efi_status_t +efi_thunk_get_next_high_mono_count(u32 *count) +{ + efi_status_t status; + u32 phys_count; + + phys_count = virt_to_phys(count); + status = efi_thunk(get_next_high_mono_count, phys_count); + + return status; +} + +static void +efi_thunk_reset_system(int reset_type, efi_status_t status, + unsigned long data_size, efi_char16_t *data) +{ + u32 phys_data; + + phys_data = virt_to_phys(data); + + efi_thunk(reset_system, reset_type, status, data_size, phys_data); +} + +static efi_status_t +efi_thunk_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list) +{ + /* + * To properly support this function we would need to repackage + * 'capsules' because the firmware doesn't understand 64-bit + * pointers. + */ + return EFI_UNSUPPORTED; +} + +static efi_status_t +efi_thunk_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + efi_status_t status; + u32 phys_storage, phys_remaining, phys_max; + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + phys_storage = virt_to_phys(storage_space); + phys_remaining = virt_to_phys(remaining_space); + phys_max = virt_to_phys(max_variable_size); + + status = efi_thunk(query_variable_info, attr, phys_storage, + phys_remaining, phys_max); + + return status; +} + +static efi_status_t +efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, + int *reset_type) +{ + /* + * To properly support this function we would need to repackage + * 'capsules' because the firmware doesn't understand 64-bit + * pointers. + */ + return EFI_UNSUPPORTED; +} + +void efi_thunk_runtime_setup(void) +{ + efi.get_time = efi_thunk_get_time; + efi.set_time = efi_thunk_set_time; + efi.get_wakeup_time = efi_thunk_get_wakeup_time; + efi.set_wakeup_time = efi_thunk_set_wakeup_time; + efi.get_variable = efi_thunk_get_variable; + efi.get_next_variable = efi_thunk_get_next_variable; + efi.set_variable = efi_thunk_set_variable; + efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count; + efi.reset_system = efi_thunk_reset_system; + efi.query_variable_info = efi_thunk_query_variable_info; + efi.update_capsule = efi_thunk_update_capsule; + efi.query_capsule_caps = efi_thunk_query_capsule_caps; +} +#endif /* CONFIG_EFI_MIXED */ diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 88073b140298..e0984ef0374b 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -7,6 +7,10 @@ */ #include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> +#include <asm/page_types.h> #define SAVE_XMM \ mov %rsp, %rax; \ @@ -164,7 +168,169 @@ ENTRY(efi_call6) ret ENDPROC(efi_call6) +#ifdef CONFIG_EFI_MIXED + +/* + * We run this function from the 1:1 mapping. + * + * This function must be invoked with a 1:1 mapped stack. + */ +ENTRY(__efi64_thunk) + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + subq $32, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movq %r8, %rsi + movl %esi, 0xc(%rsp) + movq %r9, %rsi + movl %esi, 0x10(%rsp) + + sgdt save_gdt(%rip) + + leaq 1f(%rip), %rbx + movq %rbx, func_rt_ptr(%rip) + + /* Switch to gdt with 32-bit segments */ + movl 64(%rsp), %eax + lgdt (%rax) + + leaq efi_enter32(%rip), %rax + pushq $__KERNEL_CS + pushq %rax + lretq + +1: addq $32, %rsp + + lgdt save_gdt(%rip) + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + + /* + * Convert 32-bit status code into 64-bit. + */ + test %rax, %rax + jz 1f + movl %eax, %ecx + andl $0x0fffffff, %ecx + andl $0xf0000000, %eax + shl $32, %rax + or %rcx, %rax +1: + ret +ENDPROC(__efi64_thunk) + +ENTRY(efi_exit32) + movq func_rt_ptr(%rip), %rax + push %rax + mov %rdi, %rax + ret +ENDPROC(efi_exit32) + + .code32 +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +ENTRY(efi_enter32) + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + + /* Reload pgtables */ + movl %cr3, %eax + movl %eax, %cr3 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Disable long mode via EFER */ + movl $MSR_EFER, %ecx + rdmsr + btrl $_EFER_LME, %eax + wrmsr + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + /* + * Some firmware will return with interrupts enabled. Be sure to + * disable them before we switch GDTs. + */ + cli + + movl 68(%esp), %eax + movl %eax, 2(%eax) + lgdtl (%eax) + + movl %cr4, %eax + btsl $(X86_CR4_PAE_BIT), %eax + movl %eax, %cr4 + + movl %cr3, %eax + movl %eax, %cr3 + + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + xorl %eax, %eax + lldt %ax + + movl 72(%esp), %eax + pushl $__KERNEL_CS + pushl %eax + + /* Enable paging */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + lret +ENDPROC(efi_enter32) + + .data + .balign 8 + .global efi32_boot_gdt +efi32_boot_gdt: .word 0 + .quad 0 + +save_gdt: .word 0 + .quad 0 +func_rt_ptr: .quad 0 + + .global efi_gdt64 +efi_gdt64: + .word efi_gdt64_end - efi_gdt64 + .long 0 /* Filled out by user */ + .word 0 + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00af9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf92000000ffff /* __KERNEL_DS */ + .quad 0x0080890000000000 /* TS descriptor */ + .quad 0x0000000000000000 /* TS continued */ +efi_gdt64_end: +#endif /* CONFIG_EFI_MIXED */ + .data ENTRY(efi_scratch) .fill 3,8,0 .byte 0 + .quad 0 diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S new file mode 100644 index 000000000000..8806fa73e6e6 --- /dev/null +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -0,0 +1,65 @@ +/* + * Copyright (C) 2014 Intel Corporation; author Matt Fleming + */ + +#include <linux/linkage.h> +#include <asm/page_types.h> + + .text + .code64 +ENTRY(efi64_thunk) + push %rbp + push %rbx + + /* + * Switch to 1:1 mapped 32-bit stack pointer. + */ + movq %rsp, efi_saved_sp(%rip) + movq efi_scratch+25(%rip), %rsp + + /* + * Calculate the physical address of the kernel text. + */ + movq $__START_KERNEL_map, %rax + subq phys_base(%rip), %rax + + /* + * Push some physical addresses onto the stack. This is easier + * to do now in a code64 section while the assembler can address + * 64-bit values. Note that all the addresses on the stack are + * 32-bit. + */ + subq $16, %rsp + leaq efi_exit32(%rip), %rbx + subq %rax, %rbx + movl %ebx, 8(%rsp) + leaq efi_gdt64(%rip), %rbx + subq %rax, %rbx + movl %ebx, 2(%ebx) + movl %ebx, 4(%rsp) + leaq efi_gdt32(%rip), %rbx + subq %rax, %rbx + movl %ebx, 2(%ebx) + movl %ebx, (%rsp) + + leaq __efi64_thunk(%rip), %rbx + subq %rax, %rbx + call *%rbx + + movq efi_saved_sp(%rip), %rsp + pop %rbx + pop %rbp + retq +ENDPROC(efi64_thunk) + + .data +efi_gdt32: + .word efi_gdt32_end - efi_gdt32 + .long 0 /* Filled out above */ + .word 0 + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00cf9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf93000000ffff /* __KERNEL_DS */ +efi_gdt32_end: + +efi_saved_sp: .quad 0 diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c index 39febb214e8c..9471b9456f25 100644 --- a/arch/x86/platform/ts5500/ts5500.c +++ b/arch/x86/platform/ts5500/ts5500.c @@ -88,7 +88,7 @@ struct ts5500_sbc { static const struct { const char * const string; const ssize_t offset; -} ts5500_signatures[] __initdata = { +} ts5500_signatures[] __initconst = { { "TS-5x00 AMD Elan", 0xb14 }, }; diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 7d01b8c56c00..cc04e67bfd05 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -40,11 +40,7 @@ #define smp_rmb() barrier() #endif /* CONFIG_X86_PPRO_FENCE */ -#ifdef CONFIG_X86_OOSTORE -#define smp_wmb() wmb() -#else /* CONFIG_X86_OOSTORE */ #define smp_wmb() barrier() -#endif /* CONFIG_X86_OOSTORE */ #define smp_read_barrier_depends() read_barrier_depends() #define set_mb(var, value) do { (void)xchg(&var, value); } while (0) diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index fd14be1d1472..9206ac7961a5 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -2,6 +2,8 @@ # Building vDSO images for x86. # +KBUILD_CFLAGS += $(DISABLE_LTO) + VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y @@ -35,7 +37,8 @@ export CPPFLAGS_vdso.lds += -P -C VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,--no-undefined \ - -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 + -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \ + $(DISABLE_LTO) $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so @@ -127,7 +130,7 @@ vdso32.so-$(VDSO32-y) += sysenter vdso32-images = $(vdso32.so-y:%=vdso32-%.so) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 # This makes sure the $(obj) subdirectory exists even though vdso32/ # is not a kbuild sub-make subdirectory. @@ -181,7 +184,8 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ + $(LTO_CFLAGS) GCOV_PROFILE := n # diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 256282e7888b..2423ef04ffea 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, /* Assume pteval_t is equivalent to all the other *val_t types. */ static pteval_t pte_mfn_to_pfn(pteval_t val) { - if (pteval_present(val)) { + if (val & _PAGE_PRESENT) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; unsigned long pfn = mfn_to_pfn(mfn); @@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) static pteval_t pte_pfn_to_mfn(pteval_t val) { - if (pteval_present(val)) { + if (val & _PAGE_PRESENT) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; pteval_t flags = val & PTE_FLAGS_MASK; unsigned long mfn; diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 0a337e4a8370..c3d20ba6eb86 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += errno.h generic-y += exec.h generic-y += fcntl.h generic-y += hardirq.h +generic-y += hash.h generic-y += ioctl.h generic-y += irq_regs.h generic-y += kdebug.h @@ -17,7 +18,9 @@ generic-y += kvm_para.h generic-y += linkage.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += percpu.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -27,5 +30,3 @@ generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/block/blk-core.c b/block/blk-core.c index 853f92749202..bfe16d5af9f9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -693,20 +693,11 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) if (!uninit_q) return NULL; - uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL); - if (!uninit_q->flush_rq) - goto out_cleanup_queue; - q = blk_init_allocated_queue(uninit_q, rfn, lock); if (!q) - goto out_free_flush_rq; - return q; + blk_cleanup_queue(uninit_q); -out_free_flush_rq: - kfree(uninit_q->flush_rq); -out_cleanup_queue: - blk_cleanup_queue(uninit_q); - return NULL; + return q; } EXPORT_SYMBOL(blk_init_queue_node); @@ -717,9 +708,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, if (!q) return NULL; - if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) + q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL); + if (!q->flush_rq) return NULL; + if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) + goto fail; + q->request_fn = rfn; q->prep_rq_fn = NULL; q->unprep_rq_fn = NULL; @@ -742,12 +737,16 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, /* init elevator */ if (elevator_init(q, NULL)) { mutex_unlock(&q->sysfs_lock); - return NULL; + goto fail; } mutex_unlock(&q->sysfs_lock); return q; + +fail: + kfree(q->flush_rq); + return NULL; } EXPORT_SYMBOL(blk_init_allocated_queue); diff --git a/block/blk-exec.c b/block/blk-exec.c index c68613bb4c79..dbf4502b1d67 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, * be resued after dying flag is set */ if (q->mq_ops) { - blk_mq_insert_request(q, rq, at_head, true); + blk_mq_insert_request(rq, at_head, true, false); return; } diff --git a/block/blk-flush.c b/block/blk-flush.c index 66e2b697f5db..43e6b4755e9a 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -137,17 +137,20 @@ static void mq_flush_run(struct work_struct *work) rq = container_of(work, struct request, mq_flush_work); memset(&rq->csd, 0, sizeof(rq->csd)); - blk_mq_run_request(rq, true, false); + blk_mq_insert_request(rq, false, true, false); } -static bool blk_flush_queue_rq(struct request *rq) +static bool blk_flush_queue_rq(struct request *rq, bool add_front) { if (rq->q->mq_ops) { INIT_WORK(&rq->mq_flush_work, mq_flush_run); kblockd_schedule_work(rq->q, &rq->mq_flush_work); return false; } else { - list_add_tail(&rq->queuelist, &rq->q->queue_head); + if (add_front) + list_add(&rq->queuelist, &rq->q->queue_head); + else + list_add_tail(&rq->queuelist, &rq->q->queue_head); return true; } } @@ -193,7 +196,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq, case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &q->flush_data_in_flight); - queued = blk_flush_queue_rq(rq); + queued = blk_flush_queue_rq(rq, true); break; case REQ_FSEQ_DONE: @@ -326,7 +329,7 @@ static bool blk_kick_flush(struct request_queue *q) q->flush_rq->rq_disk = first_rq->rq_disk; q->flush_rq->end_io = flush_end_io; - return blk_flush_queue_rq(q->flush_rq); + return blk_flush_queue_rq(q->flush_rq, false); } static void flush_data_end_io(struct request *rq, int error) @@ -411,7 +414,7 @@ void blk_insert_flush(struct request *rq) if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { if (q->mq_ops) { - blk_mq_run_request(rq, false, true); + blk_mq_insert_request(rq, false, false, true); } else list_add_tail(&rq->queuelist, &q->queue_head); return; diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c index 3146befb56aa..136ef8643bba 100644 --- a/block/blk-mq-cpu.c +++ b/block/blk-mq-cpu.c @@ -11,7 +11,7 @@ #include "blk-mq.h" static LIST_HEAD(blk_mq_cpu_notify_list); -static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock); +static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock); static int blk_mq_main_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) @@ -19,12 +19,12 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self, unsigned int cpu = (unsigned long) hcpu; struct blk_mq_cpu_notifier *notify; - spin_lock(&blk_mq_cpu_notify_lock); + raw_spin_lock(&blk_mq_cpu_notify_lock); list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) notify->notify(notify->data, action, cpu); - spin_unlock(&blk_mq_cpu_notify_lock); + raw_spin_unlock(&blk_mq_cpu_notify_lock); return NOTIFY_OK; } @@ -32,16 +32,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier) { BUG_ON(!notifier->notify); - spin_lock(&blk_mq_cpu_notify_lock); + raw_spin_lock(&blk_mq_cpu_notify_lock); list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list); - spin_unlock(&blk_mq_cpu_notify_lock); + raw_spin_unlock(&blk_mq_cpu_notify_lock); } void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier) { - spin_lock(&blk_mq_cpu_notify_lock); + raw_spin_lock(&blk_mq_cpu_notify_lock); list_del(¬ifier->list); - spin_unlock(&blk_mq_cpu_notify_lock); + raw_spin_unlock(&blk_mq_cpu_notify_lock); } void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, diff --git a/block/blk-mq.c b/block/blk-mq.c index 1fa9dd153fde..883f72089015 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -73,8 +73,8 @@ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, set_bit(ctx->index_hw, hctx->ctx_map); } -static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp, - bool reserved) +static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx, + gfp_t gfp, bool reserved) { struct request *rq; unsigned int tag; @@ -193,12 +193,6 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, ctx->rq_dispatched[rw_is_sync(rw_flags)]++; } -static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx, - gfp_t gfp, bool reserved) -{ - return blk_mq_alloc_rq(hctx, gfp, reserved); -} - static struct request *blk_mq_alloc_request_pinned(struct request_queue *q, int rw, gfp_t gfp, bool reserved) @@ -289,38 +283,10 @@ void blk_mq_free_request(struct request *rq) __blk_mq_free_request(hctx, ctx, rq); } -static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error) -{ - if (error) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; - - if (unlikely(rq->cmd_flags & REQ_QUIET)) - set_bit(BIO_QUIET, &bio->bi_flags); - - /* don't actually finish bio if it's part of flush sequence */ - if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) - bio_endio(bio, error); -} - -void blk_mq_end_io(struct request *rq, int error) +bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes) { - struct bio *bio = rq->bio; - unsigned int bytes = 0; - - trace_block_rq_complete(rq->q, rq); - - while (bio) { - struct bio *next = bio->bi_next; - - bio->bi_next = NULL; - bytes += bio->bi_iter.bi_size; - blk_mq_bio_endio(rq, bio, error); - bio = next; - } - - blk_account_io_completion(rq, bytes); + if (blk_update_request(rq, error, blk_rq_bytes(rq))) + return true; blk_account_io_done(rq); @@ -328,8 +294,9 @@ void blk_mq_end_io(struct request *rq, int error) rq->end_io(rq, error); else blk_mq_free_request(rq); + return false; } -EXPORT_SYMBOL(blk_mq_end_io); +EXPORT_SYMBOL(blk_mq_end_io_partial); static void __blk_mq_complete_request_remote(void *data) { @@ -730,60 +697,27 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, blk_mq_add_timer(rq); } -void blk_mq_insert_request(struct request_queue *q, struct request *rq, - bool at_head, bool run_queue) +void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, + bool async) { + struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx, *current_ctx; + struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; + + current_ctx = blk_mq_get_ctx(q); + if (!cpu_online(ctx->cpu)) + rq->mq_ctx = ctx = current_ctx; - ctx = rq->mq_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); - if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) { + if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) && + !(rq->cmd_flags & (REQ_FLUSH_SEQ))) { blk_insert_flush(rq); } else { - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) { - ctx = current_ctx; - hctx = q->mq_ops->map_queue(q, ctx->cpu); - rq->mq_ctx = ctx; - } spin_lock(&ctx->lock); __blk_mq_insert_request(hctx, rq, at_head); spin_unlock(&ctx->lock); - - blk_mq_put_ctx(current_ctx); - } - - if (run_queue) - __blk_mq_run_hw_queue(hctx); -} -EXPORT_SYMBOL(blk_mq_insert_request); - -/* - * This is a special version of blk_mq_insert_request to bypass FLUSH request - * check. Should only be used internally. - */ -void blk_mq_run_request(struct request *rq, bool run_queue, bool async) -{ - struct request_queue *q = rq->q; - struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - - ctx = rq->mq_ctx; - if (!cpu_online(ctx->cpu)) { - ctx = current_ctx; - rq->mq_ctx = ctx; } - hctx = q->mq_ops->map_queue(q, ctx->cpu); - - /* ctx->cpu might be offline */ - spin_lock(&ctx->lock); - __blk_mq_insert_request(hctx, rq, false); - spin_unlock(&ctx->lock); blk_mq_put_ctx(current_ctx); @@ -926,6 +860,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio) ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); + if (is_sync) + rw |= REQ_SYNC; trace_block_getrq(q, bio, rw); rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false); if (likely(rq)) diff --git a/block/blk-mq.h b/block/blk-mq.h index ed0035cd458e..72beba1f9d55 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -23,7 +23,6 @@ struct blk_mq_ctx { }; void __blk_mq_complete_request(struct request *rq); -void blk_mq_run_request(struct request *rq, bool run_queue, bool async); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_init_flush(struct request_queue *q); void blk_mq_drain_queue(struct request_queue *q); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 959d41acc108..d7d32c28829b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -67,6 +67,8 @@ enum ec_command { #define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */ #define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */ #define ACPI_EC_MSI_UDELAY 550 /* Wait 550us for MSI EC */ +#define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query + * when trying to clear the EC */ enum { EC_FLAGS_QUERY_PENDING, /* Query is pending */ @@ -116,6 +118,7 @@ EXPORT_SYMBOL(first_ec); static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */ static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */ static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */ +static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */ /* -------------------------------------------------------------------------- Transaction Management @@ -440,6 +443,29 @@ acpi_handle ec_get_handle(void) EXPORT_SYMBOL(ec_get_handle); +static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data); + +/* + * Clears stale _Q events that might have accumulated in the EC. + * Run with locked ec mutex. + */ +static void acpi_ec_clear(struct acpi_ec *ec) +{ + int i, status; + u8 value = 0; + + for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { + status = acpi_ec_query_unlocked(ec, &value); + if (status || !value) + break; + } + + if (unlikely(i == ACPI_EC_CLEAR_MAX)) + pr_warn("Warning: Maximum of %d stale EC events cleared\n", i); + else + pr_info("%d stale EC events cleared\n", i); +} + void acpi_ec_block_transactions(void) { struct acpi_ec *ec = first_ec; @@ -463,6 +489,10 @@ void acpi_ec_unblock_transactions(void) mutex_lock(&ec->mutex); /* Allow transactions to be carried out again */ clear_bit(EC_FLAGS_BLOCKED, &ec->flags); + + if (EC_FLAGS_CLEAR_ON_RESUME) + acpi_ec_clear(ec); + mutex_unlock(&ec->mutex); } @@ -821,6 +851,13 @@ static int acpi_ec_add(struct acpi_device *device) /* EC is fully operational, allow queries */ clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags); + + /* Clear stale _Q events if hardware might require that */ + if (EC_FLAGS_CLEAR_ON_RESUME) { + mutex_lock(&ec->mutex); + acpi_ec_clear(ec); + mutex_unlock(&ec->mutex); + } return ret; } @@ -922,6 +959,30 @@ static int ec_enlarge_storm_threshold(const struct dmi_system_id *id) return 0; } +/* + * On some hardware it is necessary to clear events accumulated by the EC during + * sleep. These ECs stop reporting GPEs until they are manually polled, if too + * many events are accumulated. (e.g. Samsung Series 5/9 notebooks) + * + * https://bugzilla.kernel.org/show_bug.cgi?id=44161 + * + * Ideally, the EC should also be instructed NOT to accumulate events during + * sleep (which Windows seems to do somehow), but the interface to control this + * behaviour is not known at this time. + * + * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx, + * however it is very likely that other Samsung models are affected. + * + * On systems which don't accumulate _Q events during sleep, this extra check + * should be harmless. + */ +static int ec_clear_on_resume(const struct dmi_system_id *id) +{ + pr_debug("Detected system needing EC poll on resume.\n"); + EC_FLAGS_CLEAR_ON_RESUME = 1; + return 0; +} + static struct dmi_system_id ec_dmi_table[] __initdata = { { ec_skip_dsdt_scan, "Compal JFL92", { @@ -965,6 +1026,9 @@ static struct dmi_system_id ec_dmi_table[] __initdata = { ec_validate_ecdt, "ASUS hardware", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL}, + { + ec_clear_on_resume, "Samsung hardware", { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL}, {}, }; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index b7201fc6f1e1..0bdacc5e26a3 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -77,18 +77,24 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_MEMORY24: memory24 = &ares->data.memory24; + if (!memory24->address_length) + return false; acpi_dev_get_memresource(res, memory24->minimum, memory24->address_length, memory24->write_protect); break; case ACPI_RESOURCE_TYPE_MEMORY32: memory32 = &ares->data.memory32; + if (!memory32->address_length) + return false; acpi_dev_get_memresource(res, memory32->minimum, memory32->address_length, memory32->write_protect); break; case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: fixed_memory32 = &ares->data.fixed_memory32; + if (!fixed_memory32->address_length) + return false; acpi_dev_get_memresource(res, fixed_memory32->address, fixed_memory32->address_length, fixed_memory32->write_protect); @@ -144,12 +150,16 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_IO: io = &ares->data.io; + if (!io->address_length) + return false; acpi_dev_get_ioresource(res, io->minimum, io->address_length, io->io_decode); break; case ACPI_RESOURCE_TYPE_FIXED_IO: fixed_io = &ares->data.fixed_io; + if (!fixed_io->address_length) + return false; acpi_dev_get_ioresource(res, fixed_io->address, fixed_io->address_length, ACPI_DECODE_10); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index b718806657cd..c40fb2e81bbc 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -71,6 +71,17 @@ static int acpi_sleep_prepare(u32 acpi_state) return 0; } +static bool acpi_sleep_state_supported(u8 sleep_state) +{ + acpi_status status; + u8 type_a, type_b; + + status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b); + return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware + || (acpi_gbl_FADT.sleep_control.address + && acpi_gbl_FADT.sleep_status.address)); +} + #ifdef CONFIG_ACPI_SLEEP static u32 acpi_target_sleep_state = ACPI_STATE_S0; @@ -604,15 +615,9 @@ static void acpi_sleep_suspend_setup(void) { int i; - for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) { - acpi_status status; - u8 type_a, type_b; - - status = acpi_get_sleep_type_data(i, &type_a, &type_b); - if (ACPI_SUCCESS(status)) { + for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) + if (acpi_sleep_state_supported(i)) sleep_states[i] = 1; - } - } suspend_set_ops(old_suspend_ordering ? &acpi_suspend_ops_old : &acpi_suspend_ops); @@ -740,11 +745,7 @@ static const struct platform_hibernation_ops acpi_hibernation_ops_old = { static void acpi_sleep_hibernate_setup(void) { - acpi_status status; - u8 type_a, type_b; - - status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b); - if (ACPI_FAILURE(status)) + if (!acpi_sleep_state_supported(ACPI_STATE_S4)) return; hibernation_set_ops(old_suspend_ordering ? @@ -793,8 +794,6 @@ static void acpi_power_off(void) int __init acpi_sleep_init(void) { - acpi_status status; - u8 type_a, type_b; char supported[ACPI_S_STATE_COUNT * 3 + 1]; char *pos = supported; int i; @@ -806,8 +805,7 @@ int __init acpi_sleep_init(void) acpi_sleep_suspend_setup(); acpi_sleep_hibernate_setup(); - status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b); - if (ACPI_SUCCESS(status)) { + if (acpi_sleep_state_supported(ACPI_STATE_S5)) { sleep_states[ACPI_STATE_S5] = 1; pm_power_off_prepare = acpi_power_off_prepare; pm_power_off = acpi_power_off; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 1a3dbd1b196e..8cb2522d592a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4175,6 +4175,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */ { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA }, + { "ST1000LM024 HN-M101MBB", "2BA30001", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ @@ -4224,7 +4225,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* devices that don't properly handle queued TRIM commands */ { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT???M500SSD1", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 8184451b57c0..422b7d84f686 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -874,7 +874,7 @@ bio_pageinc(struct bio *bio) /* Non-zero page count for non-head members of * compound pages is no longer allowed by the kernel. */ - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_inc(&page->_count); } } @@ -887,7 +887,7 @@ bio_pagedec(struct bio *bio) struct bvec_iter iter; bio_for_each_segment(bv, bio, iter) { - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_dec(&page->_count); } } diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 516026954be6..d777bb7cea93 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -4498,7 +4498,7 @@ static int mtip_pci_probe(struct pci_dev *pdev, } dev_info(&pdev->dev, "NUMA node %d (closest: %d,%d, probe on %d:%d)\n", my_node, pcibus_to_node(pdev->bus), dev_to_node(&pdev->dev), - cpu_to_node(smp_processor_id()), smp_processor_id()); + cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id()); dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node); if (dd == NULL) { diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index b52e9a6d6aad..54174cb32feb 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -53,7 +53,7 @@ #define MTIP_FTL_REBUILD_TIMEOUT_MS 2400000 /* unaligned IO handling */ -#define MTIP_MAX_UNALIGNED_SLOTS 8 +#define MTIP_MAX_UNALIGNED_SLOTS 2 /* Macro to extract the tag bit number from a tag value. */ #define MTIP_TAG_BIT(tag) (tag & 0x1F) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b365e0dfccb6..34898d53395b 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2109,7 +2109,6 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request) rbd_assert(img_request->obj_request_count > 0); rbd_assert(which != BAD_WHICH); rbd_assert(which < img_request->obj_request_count); - rbd_assert(which >= img_request->next_completion); spin_lock_irq(&img_request->completion_lock); if (which != img_request->next_completion) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 011e55d820b1..51c557cfd92b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -612,6 +612,8 @@ static ssize_t disksize_store(struct device *dev, disksize = PAGE_ALIGN(disksize); meta = zram_meta_alloc(disksize); + if (!meta) + return -ENOMEM; down_write(&zram->init_lock); if (zram->init_done) { up_write(&zram->init_lock); diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c index bd313f7816a8..c1af80bcdf20 100644 --- a/drivers/clk/at91/clk-master.c +++ b/drivers/clk/at91/clk-master.c @@ -242,7 +242,7 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc, irq = irq_of_parse_and_map(np, 0); if (!irq) - return; + goto out_free_characteristics; clk = at91_clk_register_master(pmc, irq, name, num_parents, parent_names, layout, diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c index 6a934a5296bd..05e04ce0f148 100644 --- a/drivers/clk/clk-nomadik.c +++ b/drivers/clk/clk-nomadik.c @@ -494,6 +494,9 @@ static const struct file_operations nomadik_src_clk_debugfs_ops = { static int __init nomadik_src_clk_init_debugfs(void) { + /* Vital for multiplatform */ + if (!src_base) + return -ENODEV; src_pcksr0_boot = readl(src_base + SRC_PCKSR0); src_pcksr1_boot = readl(src_base + SRC_PCKSR1); debugfs_create_file("nomadik-src-clk", S_IFREG | S_IRUGO, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 5517944495d8..c42e608af6bb 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2226,24 +2226,25 @@ EXPORT_SYMBOL_GPL(devm_clk_unregister); */ int __clk_get(struct clk *clk) { - if (clk && !try_module_get(clk->owner)) - return 0; + if (clk) { + if (!try_module_get(clk->owner)) + return 0; - kref_get(&clk->ref); + kref_get(&clk->ref); + } return 1; } void __clk_put(struct clk *clk) { - if (WARN_ON_ONCE(IS_ERR(clk))) + if (!clk || WARN_ON_ONCE(IS_ERR(clk))) return; clk_prepare_lock(); kref_put(&clk->ref, __clk_release); clk_prepare_unlock(); - if (clk) - module_put(clk->owner); + module_put(clk->owner); } /*** clk rate change notifiers ***/ diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c index 17a598398a53..86f1e362eafb 100644 --- a/drivers/clk/keystone/gate.c +++ b/drivers/clk/keystone/gate.c @@ -179,6 +179,7 @@ static struct clk *clk_register_psc(struct device *dev, init.name = name; init.ops = &clk_psc_ops; + init.flags = 0; init.parent_names = (parent_name ? &parent_name : NULL); init.num_parents = (parent_name ? 1 : 0); diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c index 81a202d12a7a..bef198a83863 100644 --- a/drivers/clk/mvebu/armada-370.c +++ b/drivers/clk/mvebu/armada-370.c @@ -141,13 +141,6 @@ static const struct coreclk_soc_desc a370_coreclks = { .num_ratios = ARRAY_SIZE(a370_coreclk_ratios), }; -static void __init a370_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &a370_coreclks); -} -CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock", - a370_coreclk_init); - /* * Clock Gating Control */ @@ -168,9 +161,15 @@ static const struct clk_gating_soc_desc a370_gating_desc[] __initconst = { { } }; -static void __init a370_clk_gating_init(struct device_node *np) +static void __init a370_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, a370_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,armada-370-gating-clock"); + + mvebu_coreclk_setup(np, &a370_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, a370_gating_desc); } -CLK_OF_DECLARE(a370_clk_gating, "marvell,armada-370-gating-clock", - a370_clk_gating_init); +CLK_OF_DECLARE(a370_clk, "marvell,armada-370-core-clock", a370_clk_init); + diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c index 9922c4475aa8..b3094315a3c0 100644 --- a/drivers/clk/mvebu/armada-xp.c +++ b/drivers/clk/mvebu/armada-xp.c @@ -158,13 +158,6 @@ static const struct coreclk_soc_desc axp_coreclks = { .num_ratios = ARRAY_SIZE(axp_coreclk_ratios), }; -static void __init axp_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &axp_coreclks); -} -CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock", - axp_coreclk_init); - /* * Clock Gating Control */ @@ -202,9 +195,14 @@ static const struct clk_gating_soc_desc axp_gating_desc[] __initconst = { { } }; -static void __init axp_clk_gating_init(struct device_node *np) +static void __init axp_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, axp_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,armada-xp-gating-clock"); + + mvebu_coreclk_setup(np, &axp_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, axp_gating_desc); } -CLK_OF_DECLARE(axp_clk_gating, "marvell,armada-xp-gating-clock", - axp_clk_gating_init); +CLK_OF_DECLARE(axp_clk, "marvell,armada-xp-core-clock", axp_clk_init); diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c index 38aee1e3f242..b8c2424ac926 100644 --- a/drivers/clk/mvebu/dove.c +++ b/drivers/clk/mvebu/dove.c @@ -154,12 +154,6 @@ static const struct coreclk_soc_desc dove_coreclks = { .num_ratios = ARRAY_SIZE(dove_coreclk_ratios), }; -static void __init dove_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &dove_coreclks); -} -CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init); - /* * Clock Gating Control */ @@ -186,9 +180,14 @@ static const struct clk_gating_soc_desc dove_gating_desc[] __initconst = { { } }; -static void __init dove_clk_gating_init(struct device_node *np) +static void __init dove_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, dove_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,dove-gating-clock"); + + mvebu_coreclk_setup(np, &dove_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, dove_gating_desc); } -CLK_OF_DECLARE(dove_clk_gating, "marvell,dove-gating-clock", - dove_clk_gating_init); +CLK_OF_DECLARE(dove_clk, "marvell,dove-core-clock", dove_clk_init); diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c index 2636a55f29f9..ddb666a86500 100644 --- a/drivers/clk/mvebu/kirkwood.c +++ b/drivers/clk/mvebu/kirkwood.c @@ -193,13 +193,6 @@ static const struct coreclk_soc_desc kirkwood_coreclks = { .num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios), }; -static void __init kirkwood_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &kirkwood_coreclks); -} -CLK_OF_DECLARE(kirkwood_core_clk, "marvell,kirkwood-core-clock", - kirkwood_coreclk_init); - static const struct coreclk_soc_desc mv88f6180_coreclks = { .get_tclk_freq = kirkwood_get_tclk_freq, .get_cpu_freq = mv88f6180_get_cpu_freq, @@ -208,13 +201,6 @@ static const struct coreclk_soc_desc mv88f6180_coreclks = { .num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios), }; -static void __init mv88f6180_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &mv88f6180_coreclks); -} -CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock", - mv88f6180_coreclk_init); - /* * Clock Gating Control */ @@ -239,9 +225,21 @@ static const struct clk_gating_soc_desc kirkwood_gating_desc[] __initconst = { { } }; -static void __init kirkwood_clk_gating_init(struct device_node *np) +static void __init kirkwood_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, kirkwood_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,kirkwood-gating-clock"); + + + if (of_device_is_compatible(np, "marvell,mv88f6180-core-clock")) + mvebu_coreclk_setup(np, &mv88f6180_coreclks); + else + mvebu_coreclk_setup(np, &kirkwood_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc); } -CLK_OF_DECLARE(kirkwood_clk_gating, "marvell,kirkwood-gating-clock", - kirkwood_clk_gating_init); +CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock", + kirkwood_clk_init); +CLK_OF_DECLARE(mv88f6180_clk, "marvell,mv88f6180-core-clock", + kirkwood_clk_init); diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c index a59ec217a124..99c27b1c625b 100644 --- a/drivers/clk/shmobile/clk-rcar-gen2.c +++ b/drivers/clk/shmobile/clk-rcar-gen2.c @@ -26,6 +26,8 @@ struct rcar_gen2_cpg { void __iomem *reg; }; +#define CPG_FRQCRB 0x00000004 +#define CPG_FRQCRB_KICK BIT(31) #define CPG_SDCKCR 0x00000074 #define CPG_PLL0CR 0x000000d8 #define CPG_FRQCRC 0x000000e0 @@ -45,6 +47,7 @@ struct rcar_gen2_cpg { struct cpg_z_clk { struct clk_hw hw; void __iomem *reg; + void __iomem *kick_reg; }; #define to_z_clk(_hw) container_of(_hw, struct cpg_z_clk, hw) @@ -83,17 +86,45 @@ static int cpg_z_clk_set_rate(struct clk_hw *hw, unsigned long rate, { struct cpg_z_clk *zclk = to_z_clk(hw); unsigned int mult; - u32 val; + u32 val, kick; + unsigned int i; mult = div_u64((u64)rate * 32, parent_rate); mult = clamp(mult, 1U, 32U); + if (clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK) + return -EBUSY; + val = clk_readl(zclk->reg); val &= ~CPG_FRQCRC_ZFC_MASK; val |= (32 - mult) << CPG_FRQCRC_ZFC_SHIFT; clk_writel(val, zclk->reg); - return 0; + /* + * Set KICK bit in FRQCRB to update hardware setting and wait for + * clock change completion. + */ + kick = clk_readl(zclk->kick_reg); + kick |= CPG_FRQCRB_KICK; + clk_writel(kick, zclk->kick_reg); + + /* + * Note: There is no HW information about the worst case latency. + * + * Using experimental measurements, it seems that no more than + * ~10 iterations are needed, independently of the CPU rate. + * Since this value might be dependant of external xtal rate, pll1 + * rate or even the other emulation clocks rate, use 1000 as a + * "super" safe value. + */ + for (i = 1000; i; i--) { + if (!(clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK)) + return 0; + + cpu_relax(); + } + + return -ETIMEDOUT; } static const struct clk_ops cpg_z_clk_ops = { @@ -120,6 +151,7 @@ static struct clk * __init cpg_z_clk_register(struct rcar_gen2_cpg *cpg) init.num_parents = 1; zclk->reg = cpg->reg + CPG_FRQCRC; + zclk->kick_reg = cpg->reg + CPG_FRQCRB; zclk->hw.init = &init; clk = clk_register(NULL, &zclk->hw); @@ -186,7 +218,7 @@ rcar_gen2_cpg_register_clock(struct device_node *np, struct rcar_gen2_cpg *cpg, const char *name) { const struct clk_div_table *table = NULL; - const char *parent_name = "main"; + const char *parent_name; unsigned int shift; unsigned int mult = 1; unsigned int div = 1; @@ -201,23 +233,31 @@ rcar_gen2_cpg_register_clock(struct device_node *np, struct rcar_gen2_cpg *cpg, * the multiplier value. */ u32 value = clk_readl(cpg->reg + CPG_PLL0CR); + parent_name = "main"; mult = ((value >> 24) & ((1 << 7) - 1)) + 1; } else if (!strcmp(name, "pll1")) { + parent_name = "main"; mult = config->pll1_mult / 2; } else if (!strcmp(name, "pll3")) { + parent_name = "main"; mult = config->pll3_mult; } else if (!strcmp(name, "lb")) { + parent_name = "pll1_div2"; div = cpg_mode & BIT(18) ? 36 : 24; } else if (!strcmp(name, "qspi")) { + parent_name = "pll1_div2"; div = (cpg_mode & (BIT(3) | BIT(2) | BIT(1))) == BIT(2) - ? 16 : 20; + ? 8 : 10; } else if (!strcmp(name, "sdh")) { + parent_name = "pll1_div2"; table = cpg_sdh_div_table; shift = 8; } else if (!strcmp(name, "sd0")) { + parent_name = "pll1_div2"; table = cpg_sd01_div_table; shift = 4; } else if (!strcmp(name, "sd1")) { + parent_name = "pll1_div2"; table = cpg_sd01_div_table; shift = 0; } else if (!strcmp(name, "z")) { diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c index 4d75b1f37e3a..290f9c1a3749 100644 --- a/drivers/clk/tegra/clk-divider.c +++ b/drivers/clk/tegra/clk-divider.c @@ -59,7 +59,7 @@ static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate, return 0; if (divider_ux1 > get_max_div(divider)) - return -EINVAL; + return get_max_div(divider); return divider_ux1; } diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h index cf0c323f2c36..c39613c519af 100644 --- a/drivers/clk/tegra/clk-id.h +++ b/drivers/clk/tegra/clk-id.h @@ -180,9 +180,13 @@ enum clk_id { tegra_clk_sbc6_8, tegra_clk_sclk, tegra_clk_sdmmc1, + tegra_clk_sdmmc1_8, tegra_clk_sdmmc2, + tegra_clk_sdmmc2_8, tegra_clk_sdmmc3, + tegra_clk_sdmmc3_8, tegra_clk_sdmmc4, + tegra_clk_sdmmc4_8, tegra_clk_se, tegra_clk_soc_therm, tegra_clk_sor0, diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c index 5c35885f4a7c..1fa5c3f33b20 100644 --- a/drivers/clk/tegra/clk-tegra-periph.c +++ b/drivers/clk/tegra/clk-tegra-periph.c @@ -371,9 +371,7 @@ static const char *mux_pllp3_pllc_clkm[] = { static const char *mux_pllm_pllc_pllp_plla_pllc2_c3_clkm[] = { "pll_m", "pll_c", "pll_p", "pll_a", "pll_c2", "pll_c3", "clk_m" }; -static u32 mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx[] = { - [0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6, -}; +#define mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx NULL static const char *mux_pllm_pllc2_c_c3_pllp_plla_pllc4[] = { "pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0", "pll_c4", @@ -465,6 +463,10 @@ static struct tegra_periph_init_data periph_clks[] = { MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1), MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1), MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2), + MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8), + MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8), + MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8), + MUX8("sdmmc4", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC4, 15, 0, tegra_clk_sdmmc4_8), MUX8("sbc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC1, 41, TEGRA_PERIPH_ON_APB, tegra_clk_sbc1_8), MUX8("sbc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC2, 44, TEGRA_PERIPH_ON_APB, tegra_clk_sbc2_8), MUX8("sbc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC3, 46, TEGRA_PERIPH_ON_APB, tegra_clk_sbc3_8), @@ -492,7 +494,7 @@ static struct tegra_periph_init_data periph_clks[] = { UART("uartb", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTB, 7, tegra_clk_uartb), UART("uartc", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTC, 55, tegra_clk_uartc), UART("uartd", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTD, 65, tegra_clk_uartd), - UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 65, tegra_clk_uarte), + UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 66, tegra_clk_uarte), XUSB("xusb_host_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_HOST_SRC, 143, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_host_src), XUSB("xusb_falcon_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_FALCON_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_falcon_src), XUSB("xusb_fs_src", mux_clkm_48M_pllp_480M, CLK_SOURCE_XUSB_FS_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_fs_src), diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c index 05dce4aa2c11..feb3201c85ce 100644 --- a/drivers/clk/tegra/clk-tegra-super-gen4.c +++ b/drivers/clk/tegra/clk-tegra-super-gen4.c @@ -120,7 +120,7 @@ void __init tegra_super_clk_gen4_init(void __iomem *clk_base, ARRAY_SIZE(cclk_lp_parents), CLK_SET_RATE_PARENT, clk_base + CCLKLP_BURST_POLICY, - 0, 4, 8, 9, NULL); + TEGRA_DIVIDER_2, 4, 8, 9, NULL); *dt_clk = clk; } diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index 90d9d25f2228..80431f0fb268 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -682,12 +682,12 @@ static struct tegra_clk tegra114_clks[tegra_clk_max] __initdata = { [tegra_clk_timer] = { .dt_id = TEGRA114_CLK_TIMER, .present = true }, [tegra_clk_uarta] = { .dt_id = TEGRA114_CLK_UARTA, .present = true }, [tegra_clk_uartd] = { .dt_id = TEGRA114_CLK_UARTD, .present = true }, - [tegra_clk_sdmmc2] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true }, + [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true }, [tegra_clk_i2s1] = { .dt_id = TEGRA114_CLK_I2S1, .present = true }, [tegra_clk_i2c1] = { .dt_id = TEGRA114_CLK_I2C1, .present = true }, [tegra_clk_ndflash] = { .dt_id = TEGRA114_CLK_NDFLASH, .present = true }, - [tegra_clk_sdmmc1] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true }, - [tegra_clk_sdmmc4] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true }, + [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true }, + [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA114_CLK_PWM, .present = true }, [tegra_clk_i2s0] = { .dt_id = TEGRA114_CLK_I2S0, .present = true }, [tegra_clk_i2s2] = { .dt_id = TEGRA114_CLK_I2S2, .present = true }, @@ -723,7 +723,7 @@ static struct tegra_clk tegra114_clks[tegra_clk_max] __initdata = { [tegra_clk_bsev] = { .dt_id = TEGRA114_CLK_BSEV, .present = true }, [tegra_clk_i2c3] = { .dt_id = TEGRA114_CLK_I2C3, .present = true }, [tegra_clk_sbc4_8] = { .dt_id = TEGRA114_CLK_SBC4, .present = true }, - [tegra_clk_sdmmc3] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true }, + [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true }, [tegra_clk_owr] = { .dt_id = TEGRA114_CLK_OWR, .present = true }, [tegra_clk_csite] = { .dt_id = TEGRA114_CLK_CSITE, .present = true }, [tegra_clk_la] = { .dt_id = TEGRA114_CLK_LA, .present = true }, diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index aff86b5bc745..166e02f16c8a 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -516,11 +516,11 @@ static struct div_nmp pllp_nmp = { }; static struct tegra_clk_pll_freq_table pll_p_freq_table[] = { - {12000000, 216000000, 432, 12, 1, 8}, - {13000000, 216000000, 432, 13, 1, 8}, - {16800000, 216000000, 360, 14, 1, 8}, - {19200000, 216000000, 360, 16, 1, 8}, - {26000000, 216000000, 432, 26, 1, 8}, + {12000000, 408000000, 408, 12, 0, 8}, + {13000000, 408000000, 408, 13, 0, 8}, + {16800000, 408000000, 340, 14, 0, 8}, + {19200000, 408000000, 340, 16, 0, 8}, + {26000000, 408000000, 408, 26, 0, 8}, {0, 0, 0, 0, 0, 0}, }; @@ -570,6 +570,15 @@ static struct tegra_clk_pll_params pll_a_params = { .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_USE_LOCK, }; +static struct div_nmp plld_nmp = { + .divm_shift = 0, + .divm_width = 5, + .divn_shift = 8, + .divn_width = 11, + .divp_shift = 20, + .divp_width = 3, +}; + static struct tegra_clk_pll_freq_table pll_d_freq_table[] = { {12000000, 216000000, 864, 12, 4, 12}, {13000000, 216000000, 864, 13, 4, 12}, @@ -603,19 +612,18 @@ static struct tegra_clk_pll_params pll_d_params = { .lock_mask = PLL_BASE_LOCK, .lock_enable_bit_idx = PLLDU_MISC_LOCK_ENABLE, .lock_delay = 1000, - .div_nmp = &pllp_nmp, + .div_nmp = &plld_nmp, .freq_table = pll_d_freq_table, .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON | TEGRA_PLL_USE_LOCK, }; static struct tegra_clk_pll_freq_table tegra124_pll_d2_freq_table[] = { - { 12000000, 148500000, 99, 1, 8}, - { 12000000, 594000000, 99, 1, 1}, - { 13000000, 594000000, 91, 1, 1}, /* actual: 591.5 MHz */ - { 16800000, 594000000, 71, 1, 1}, /* actual: 596.4 MHz */ - { 19200000, 594000000, 62, 1, 1}, /* actual: 595.2 MHz */ - { 26000000, 594000000, 91, 2, 1}, /* actual: 591.5 MHz */ + { 12000000, 594000000, 99, 1, 2}, + { 13000000, 594000000, 91, 1, 2}, /* actual: 591.5 MHz */ + { 16800000, 594000000, 71, 1, 2}, /* actual: 596.4 MHz */ + { 19200000, 594000000, 62, 1, 2}, /* actual: 595.2 MHz */ + { 26000000, 594000000, 91, 2, 2}, /* actual: 591.5 MHz */ { 0, 0, 0, 0, 0, 0 }, }; @@ -753,21 +761,19 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true }, [tegra_clk_timer] = { .dt_id = TEGRA124_CLK_TIMER, .present = true }, [tegra_clk_uarta] = { .dt_id = TEGRA124_CLK_UARTA, .present = true }, - [tegra_clk_sdmmc2] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true }, + [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true }, [tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true }, [tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true }, [tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true }, - [tegra_clk_sdmmc1] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true }, - [tegra_clk_sdmmc4] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, + [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true }, + [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true }, [tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true }, - [tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true }, [tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true }, [tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true }, - [tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true }, [tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true }, [tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true }, - [tegra_clk_host1x] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true }, + [tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true }, [tegra_clk_vcp] = { .dt_id = TEGRA124_CLK_VCP, .present = true }, [tegra_clk_i2s0] = { .dt_id = TEGRA124_CLK_I2S0, .present = true }, [tegra_clk_apbdma] = { .dt_id = TEGRA124_CLK_APBDMA, .present = true }, @@ -794,7 +800,7 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_uartd] = { .dt_id = TEGRA124_CLK_UARTD, .present = true }, [tegra_clk_i2c3] = { .dt_id = TEGRA124_CLK_I2C3, .present = true }, [tegra_clk_sbc4] = { .dt_id = TEGRA124_CLK_SBC4, .present = true }, - [tegra_clk_sdmmc3] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true }, + [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true }, [tegra_clk_pcie] = { .dt_id = TEGRA124_CLK_PCIE, .present = true }, [tegra_clk_owr] = { .dt_id = TEGRA124_CLK_OWR, .present = true }, [tegra_clk_afi] = { .dt_id = TEGRA124_CLK_AFI, .present = true }, @@ -1286,9 +1292,9 @@ static void __init tegra124_pll_init(void __iomem *clk_base, clk_register_clkdev(clk, "pll_d2", NULL); clks[TEGRA124_CLK_PLL_D2] = clk; - /* PLLD2_OUT0 ?? */ + /* PLLD2_OUT0 */ clk = clk_register_fixed_factor(NULL, "pll_d2_out0", "pll_d2", - CLK_SET_RATE_PARENT, 1, 2); + CLK_SET_RATE_PARENT, 1, 1); clk_register_clkdev(clk, "pll_d2_out0", NULL); clks[TEGRA124_CLK_PLL_D2_OUT0] = clk; diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index dbace152b2fa..dace2b1b5ae6 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -574,6 +574,8 @@ static struct tegra_clk tegra20_clks[tegra_clk_max] __initdata = { [tegra_clk_tvdac] = { .dt_id = TEGRA20_CLK_TVDAC, .present = true }, [tegra_clk_vi_sensor] = { .dt_id = TEGRA20_CLK_VI_SENSOR, .present = true }, [tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true }, + [tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true }, + [tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true }, }; static unsigned long tegra20_clk_measure_input_freq(void) diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c index 02821b06a39e..a918bc481c52 100644 --- a/drivers/clocksource/vf_pit_timer.c +++ b/drivers/clocksource/vf_pit_timer.c @@ -54,7 +54,7 @@ static inline void pit_irq_acknowledge(void) static u64 pit_read_sched_clock(void) { - return __raw_readl(clksrc_base + PITCVAL); + return ~__raw_readl(clksrc_base + PITCVAL); } static int __init pit_clocksource_init(unsigned long rate) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index cb003a6b72c8..199b52b7c3e1 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1109,12 +1109,27 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, goto err_set_policy_cpu; } + /* related cpus should atleast have policy->cpus */ + cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus); + + /* + * affected cpus must always be the one, which are online. We aren't + * managing offline cpus here. + */ + cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); + + if (!frozen) { + policy->user_policy.min = policy->min; + policy->user_policy.max = policy->max; + } + + down_write(&policy->rwsem); write_lock_irqsave(&cpufreq_driver_lock, flags); for_each_cpu(j, policy->cpus) per_cpu(cpufreq_cpu_data, j) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - if (cpufreq_driver->get) { + if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { policy->cur = cpufreq_driver->get(policy->cpu); if (!policy->cur) { pr_err("%s: ->get() failed\n", __func__); @@ -1162,20 +1177,6 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, } } - /* related cpus should atleast have policy->cpus */ - cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus); - - /* - * affected cpus must always be the one, which are online. We aren't - * managing offline cpus here. - */ - cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); - - if (!frozen) { - policy->user_policy.min = policy->min; - policy->user_policy.max = policy->max; - } - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_START, policy); @@ -1206,6 +1207,7 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, policy->user_policy.policy = policy->policy; policy->user_policy.governor = policy->governor; } + up_write(&policy->rwsem); kobject_uevent(&policy->kobj, KOBJ_ADD); up_read(&cpufreq_rwsem); @@ -1546,23 +1548,16 @@ static unsigned int __cpufreq_get(unsigned int cpu) */ unsigned int cpufreq_get(unsigned int cpu) { - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); unsigned int ret_freq = 0; - if (cpufreq_disabled() || !cpufreq_driver) - return -ENOENT; - - BUG_ON(!policy); - - if (!down_read_trylock(&cpufreq_rwsem)) - return 0; - - down_read(&policy->rwsem); - - ret_freq = __cpufreq_get(cpu); + if (policy) { + down_read(&policy->rwsem); + ret_freq = __cpufreq_get(cpu); + up_read(&policy->rwsem); - up_read(&policy->rwsem); - up_read(&cpufreq_rwsem); + cpufreq_cpu_put(policy); + } return ret_freq; } @@ -2148,7 +2143,7 @@ int cpufreq_update_policy(unsigned int cpu) * BIOS might change freq behind our back * -> ask driver for current freq and notify governors about a change */ - if (cpufreq_driver->get) { + if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { new_policy.cur = cpufreq_driver->get(cpu); if (!policy->cur) { pr_debug("Driver did not initialize current freq"); diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 78fd174c57e8..f48607cd2540 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -14,6 +14,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> +#include <asm/runlatch.h> struct cpuidle_driver powernv_idle_driver = { .name = "powernv_idle", @@ -30,12 +31,14 @@ static int snooze_loop(struct cpuidle_device *dev, local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); + ppc64_runlatch_off(); while (!need_resched()) { HMT_low(); HMT_very_low(); } HMT_medium(); + ppc64_runlatch_on(); clear_thread_flag(TIF_POLLING_NRFLAG); smp_mb(); return index; @@ -45,7 +48,9 @@ static int nap_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { + ppc64_runlatch_off(); power7_idle(); + ppc64_runlatch_on(); return index; } diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index 7ab564aa0b1c..6f7b01956885 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -17,6 +17,7 @@ #include <asm/reg.h> #include <asm/machdep.h> #include <asm/firmware.h> +#include <asm/runlatch.h> #include <asm/plpar_wrappers.h> struct cpuidle_driver pseries_idle_driver = { @@ -29,6 +30,7 @@ static struct cpuidle_state *cpuidle_state_table; static inline void idle_loop_prolog(unsigned long *in_purr) { + ppc64_runlatch_off(); *in_purr = mfspr(SPRN_PURR); /* * Indicate to the HV that we are idle. Now would be @@ -45,6 +47,10 @@ static inline void idle_loop_epilog(unsigned long in_purr) wait_cycles += mfspr(SPRN_PURR) - in_purr; get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); get_lppaca()->idle = 0; + + if (irqs_disabled()) + local_irq_enable(); + ppc64_runlatch_on(); } static int snooze_loop(struct cpuidle_device *dev, diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index de4aa409abe2..2c6d5e118ac1 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -916,7 +916,7 @@ static int lookup_existing_device(struct device *dev, void *data) old->config_rom_retries = 0; fw_notice(card, "rediscovered device %s\n", dev_name(dev)); - PREPARE_DELAYED_WORK(&old->work, fw_device_update); + old->workfn = fw_device_update; fw_schedule_device_work(old, 0); if (current_node == card->root_node) @@ -1075,7 +1075,7 @@ static void fw_device_init(struct work_struct *work) if (atomic_cmpxchg(&device->state, FW_DEVICE_INITIALIZING, FW_DEVICE_RUNNING) == FW_DEVICE_GONE) { - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, SHUTDOWN_DELAY); } else { fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n", @@ -1196,13 +1196,20 @@ static void fw_device_refresh(struct work_struct *work) dev_name(&device->device), fw_rcode_string(ret)); gone: atomic_set(&device->state, FW_DEVICE_GONE); - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, SHUTDOWN_DELAY); out: if (node_id == card->root_node->node_id) fw_schedule_bm_work(card, 0); } +static void fw_device_workfn(struct work_struct *work) +{ + struct fw_device *device = container_of(to_delayed_work(work), + struct fw_device, work); + device->workfn(work); +} + void fw_node_event(struct fw_card *card, struct fw_node *node, int event) { struct fw_device *device; @@ -1252,7 +1259,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) * power-up after getting plugged in. We schedule the * first config rom scan half a second after bus reset. */ - INIT_DELAYED_WORK(&device->work, fw_device_init); + device->workfn = fw_device_init; + INIT_DELAYED_WORK(&device->work, fw_device_workfn); fw_schedule_device_work(device, INITIAL_DELAY); break; @@ -1268,7 +1276,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) if (atomic_cmpxchg(&device->state, FW_DEVICE_RUNNING, FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_refresh); + device->workfn = fw_device_refresh; fw_schedule_device_work(device, device->is_local ? 0 : INITIAL_DELAY); } @@ -1283,7 +1291,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) smp_wmb(); /* update node_id before generation */ device->generation = card->generation; if (atomic_read(&device->state) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_update); + device->workfn = fw_device_update; fw_schedule_device_work(device, 0); } break; @@ -1308,7 +1316,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) device = node->data; if (atomic_xchg(&device->state, FW_DEVICE_GONE) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, list_empty(&card->link) ? 0 : SHUTDOWN_DELAY); } diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index 6b895986dc22..4af0a7bad7f2 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -929,8 +929,6 @@ static void fwnet_write_complete(struct fw_card *card, int rcode, if (rcode == RCODE_COMPLETE) { fwnet_transmit_packet_done(ptask); } else { - fwnet_transmit_packet_failed(ptask); - if (printk_timed_ratelimit(&j, 1000) || rcode != last_rcode) { dev_err(&ptask->dev->netdev->dev, "fwnet_write_complete failed: %x (skipped %d)\n", @@ -938,8 +936,10 @@ static void fwnet_write_complete(struct fw_card *card, int rcode, errors_skipped = 0; last_rcode = rcode; - } else + } else { errors_skipped++; + } + fwnet_transmit_packet_failed(ptask); } } diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 6f74d8d3f700..8db663219560 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -290,7 +290,6 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_NO_MSI 0x10 #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 -#define QUIRK_PHY_LCTRL_TIMEOUT 0x80 /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { @@ -303,10 +302,7 @@ static const struct { QUIRK_BE_HEADERS}, {PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6, - QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI}, - - {PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID, - QUIRK_PHY_LCTRL_TIMEOUT}, + QUIRK_NO_MSI}, {PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID, QUIRK_RESET_PACKET}, @@ -353,7 +349,6 @@ MODULE_PARM_DESC(quirks, "Chip quirks (default = 0" ", disable MSI = " __stringify(QUIRK_NO_MSI) ", TI SLLZ059 erratum = " __stringify(QUIRK_TI_SLLZ059) ", IR wake unreliable = " __stringify(QUIRK_IR_WAKE) - ", phy LCtrl timeout = " __stringify(QUIRK_PHY_LCTRL_TIMEOUT) ")"); #define OHCI_PARAM_DEBUG_AT_AR 1 @@ -2299,9 +2294,6 @@ static int ohci_enable(struct fw_card *card, * TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but * cannot actually use the phy at that time. These need tens of * millisecods pause between LPS write and first phy access too. - * - * But do not wait for 50msec on Agere/LSI cards. Their phy - * arbitration state machine may time out during such a long wait. */ reg_write(ohci, OHCI1394_HCControlSet, @@ -2309,11 +2301,8 @@ static int ohci_enable(struct fw_card *card, OHCI1394_HCControl_postedWriteEnable); flush_writes(ohci); - if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT)) + for (lps = 0, i = 0; !lps && i < 3; i++) { msleep(50); - - for (lps = 0, i = 0; !lps && i < 150; i++) { - msleep(1); lps = reg_read(ohci, OHCI1394_HCControlSet) & OHCI1394_HCControl_LPS; } diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 281029daf98c..7aef911fdc71 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -146,6 +146,7 @@ struct sbp2_logical_unit { */ int generation; int retries; + work_func_t workfn; struct delayed_work work; bool has_sdev; bool blocked; @@ -864,7 +865,7 @@ static void sbp2_login(struct work_struct *work) /* set appropriate retry limit(s) in BUSY_TIMEOUT register */ sbp2_set_busy_timeout(lu); - PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect); + lu->workfn = sbp2_reconnect; sbp2_agent_reset(lu); /* This was a re-login. */ @@ -918,7 +919,7 @@ static void sbp2_login(struct work_struct *work) * If a bus reset happened, sbp2_update will have requeued * lu->work already. Reset the work from reconnect to login. */ - PREPARE_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; } static void sbp2_reconnect(struct work_struct *work) @@ -952,7 +953,7 @@ static void sbp2_reconnect(struct work_struct *work) lu->retries++ >= 5) { dev_err(tgt_dev(tgt), "failed to reconnect\n"); lu->retries = 0; - PREPARE_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; } sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5)); @@ -972,6 +973,13 @@ static void sbp2_reconnect(struct work_struct *work) sbp2_conditionally_unblock(lu); } +static void sbp2_lu_workfn(struct work_struct *work) +{ + struct sbp2_logical_unit *lu = container_of(to_delayed_work(work), + struct sbp2_logical_unit, work); + lu->workfn(work); +} + static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry) { struct sbp2_logical_unit *lu; @@ -998,7 +1006,8 @@ static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry) lu->blocked = false; ++tgt->dont_block; INIT_LIST_HEAD(&lu->orb_list); - INIT_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; + INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn); list_add_tail(&lu->link, &tgt->lu_list); return 0; diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c index 1b5e8e46226d..7160c43c59fc 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/firmware/dcdbas.c @@ -584,7 +584,7 @@ static struct platform_driver dcdbas_driver = { .remove = dcdbas_remove, }; -static const struct platform_device_info dcdbas_dev_info __initdata = { +static const struct platform_device_info dcdbas_dev_info __initconst = { .name = DRIVER_NAME, .id = -1, .dma_mask = DMA_BIT_MASK(32), diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c index b6bffbfd3be7..ff50aeebf0d9 100644 --- a/drivers/firmware/efi/efi-stub-helper.c +++ b/drivers/firmware/efi/efi-stub-helper.c @@ -16,18 +16,6 @@ struct file_info { u64 size; }; - - - -static void efi_char16_printk(efi_system_table_t *sys_table_arg, - efi_char16_t *str) -{ - struct efi_simple_text_output_protocol *out; - - out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out; - efi_call_phys2(out->output_string, out, str); -} - static void efi_printk(efi_system_table_t *sys_table_arg, char *str) { char *s8; @@ -65,20 +53,23 @@ again: * allocation which may be in a new descriptor region. */ *map_size += sizeof(*m); - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, *map_size, (void **)&m); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + *map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; - status = efi_call_phys5(sys_table_arg->boottime->get_memory_map, - map_size, m, &key, desc_size, &desc_version); + *desc_size = 0; + key = 0; + status = efi_call_early(get_memory_map, map_size, m, + &key, desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_phys1(sys_table_arg->boottime->free_pool, m); + efi_call_early(free_pool, m); goto again; } if (status != EFI_SUCCESS) - efi_call_phys1(sys_table_arg->boottime->free_pool, m); + efi_call_early(free_pool, m); + if (key_ptr && status == EFI_SUCCESS) *key_ptr = key; if (desc_ver && status == EFI_SUCCESS) @@ -158,7 +149,7 @@ again: if (!max_addr) status = EFI_NOT_FOUND; else { - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &max_addr); if (status != EFI_SUCCESS) { @@ -170,8 +161,7 @@ again: *addr = max_addr; } - efi_call_phys1(sys_table_arg->boottime->free_pool, map); - + efi_call_early(free_pool, map); fail: return status; } @@ -231,7 +221,7 @@ static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, if ((start + size) > end) continue; - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &start); if (status == EFI_SUCCESS) { @@ -243,7 +233,7 @@ static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, if (i == map_size / desc_size) status = EFI_NOT_FOUND; - efi_call_phys1(sys_table_arg->boottime->free_pool, map); + efi_call_early(free_pool, map); fail: return status; } @@ -257,7 +247,7 @@ static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, return; nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; - efi_call_phys2(sys_table_arg->boottime->free_pages, addr, nr_pages); + efi_call_early(free_pages, addr, nr_pages); } @@ -276,9 +266,7 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, { struct file_info *files; unsigned long file_addr; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; u64 file_size_total; - efi_file_io_interface_t *io; efi_file_handle_t *fh; efi_status_t status; int nr_files; @@ -319,10 +307,8 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, if (!nr_files) return EFI_SUCCESS; - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, - nr_files * sizeof(*files), - (void **)&files); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + nr_files * sizeof(*files), (void **)&files); if (status != EFI_SUCCESS) { efi_printk(sys_table_arg, "Failed to alloc mem for file handle list\n"); goto fail; @@ -331,13 +317,8 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, str = cmd_line; for (i = 0; i < nr_files; i++) { struct file_info *file; - efi_file_handle_t *h; - efi_file_info_t *info; efi_char16_t filename_16[256]; - unsigned long info_sz; - efi_guid_t info_guid = EFI_FILE_INFO_ID; efi_char16_t *p; - u64 file_sz; str = strstr(str, option_string); if (!str) @@ -368,71 +349,18 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, /* Only open the volume once. */ if (!i) { - efi_boot_services_t *boottime; - - boottime = sys_table_arg->boottime; - - status = efi_call_phys3(boottime->handle_protocol, - image->device_handle, &fs_proto, - (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); - goto free_files; - } - - status = efi_call_phys2(io->open_volume, io, &fh); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to open volume\n"); + status = efi_open_volume(sys_table_arg, image, + (void **)&fh); + if (status != EFI_SUCCESS) goto free_files; - } } - status = efi_call_phys5(fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to open file: "); - efi_char16_printk(sys_table_arg, filename_16); - efi_printk(sys_table_arg, "\n"); + status = efi_file_size(sys_table_arg, fh, filename_16, + (void **)&file->handle, &file->size); + if (status != EFI_SUCCESS) goto close_handles; - } - file->handle = h; - - info_sz = 0; - status = efi_call_phys4(h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table_arg, "Failed to get file info size\n"); - goto close_handles; - } - -grow: - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, info_sz, - (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to alloc mem for file info\n"); - goto close_handles; - } - - status = efi_call_phys4(h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_phys1(sys_table_arg->boottime->free_pool, - info); - goto grow; - } - - file_sz = info->file_size; - efi_call_phys1(sys_table_arg->boottime->free_pool, info); - - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to get file info\n"); - goto close_handles; - } - - file->size = file_sz; - file_size_total += file_sz; + file_size_total += file->size; } if (file_size_total) { @@ -468,10 +396,10 @@ grow: chunksize = EFI_READ_CHUNK_SIZE; else chunksize = size; - status = efi_call_phys3(fh->read, - files[j].handle, - &chunksize, - (void *)addr); + + status = efi_file_read(fh, files[j].handle, + &chunksize, + (void *)addr); if (status != EFI_SUCCESS) { efi_printk(sys_table_arg, "Failed to read file\n"); goto free_file_total; @@ -480,12 +408,12 @@ grow: size -= chunksize; } - efi_call_phys1(fh->close, files[j].handle); + efi_file_close(fh, files[j].handle); } } - efi_call_phys1(sys_table_arg->boottime->free_pool, files); + efi_call_early(free_pool, files); *load_addr = file_addr; *load_size = file_size_total; @@ -497,9 +425,9 @@ free_file_total: close_handles: for (k = j; k < i; k++) - efi_call_phys1(fh->close, files[k].handle); + efi_file_close(fh, files[k].handle); free_files: - efi_call_phys1(sys_table_arg->boottime->free_pool, files); + efi_call_early(free_pool, files); fail: *load_addr = 0; *load_size = 0; @@ -545,7 +473,7 @@ static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, * as possible while respecting the required alignment. */ nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &efi_addr); new_addr = efi_addr; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4753bac65279..af20f1712337 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -233,7 +233,7 @@ static __initdata efi_config_table_type_t common_tables[] = { {SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab}, {SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios}, {UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga}, - {NULL_GUID, NULL, 0}, + {NULL_GUID, NULL, NULL}, }; static __init int match_config_table(efi_guid_t *guid, @@ -313,5 +313,8 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) } pr_cont("\n"); early_iounmap(config_tables, efi.systab->nr_tables * sz); + + set_bit(EFI_CONFIG_TABLES, &efi.flags); + return 0; } diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 3dc248239197..50ea412a25e6 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -227,7 +227,7 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) memcpy(&entry->var, new_var, count); err = efivar_entry_set(entry, new_var->Attributes, - new_var->DataSize, new_var->Data, false); + new_var->DataSize, new_var->Data, NULL); if (err) { printk(KERN_WARNING "efivars: set_variable() failed: status=%d\n", err); return -EIO; diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index acf3a36c9ebc..32982da82694 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -68,15 +68,7 @@ void __armada_drm_queue_unref_work(struct drm_device *dev, { struct armada_private *priv = dev->dev_private; - /* - * Yes, we really must jump through these hoops just to store a - * _pointer_ to something into the kfifo. This is utterly insane - * and idiotic, because it kfifo requires the _data_ pointed to by - * the pointer const, not the pointer itself. Not only that, but - * you have to pass a pointer _to_ the pointer you want stored. - */ - const struct drm_framebuffer *silly_api_alert = fb; - WARN_ON(!kfifo_put(&priv->fb_unref, &silly_api_alert)); + WARN_ON(!kfifo_put(&priv->fb_unref, fb)); schedule_work(&priv->fb_unref_work); } diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig index c8fcf12019f0..5f8b0c2b9a44 100644 --- a/drivers/gpu/drm/bochs/Kconfig +++ b/drivers/gpu/drm/bochs/Kconfig @@ -2,6 +2,7 @@ config DRM_BOCHS tristate "DRM Support for bochs dispi vga interface (qemu stdvga)" depends on DRM && PCI select DRM_KMS_HELPER + select DRM_KMS_FB_HELPER select FB_SYS_FILLRECT select FB_SYS_COPYAREA select FB_SYS_IMAGEBLIT diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index bb8f58012189..534cb89b160d 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -32,6 +32,12 @@ #include <drm/drmP.h> #if defined(CONFIG_X86) + +/* + * clflushopt is an unordered instruction which needs fencing with mfence or + * sfence to avoid ordering issues. For drm_clflush_page this fencing happens + * in the caller. + */ static void drm_clflush_page(struct page *page) { @@ -44,7 +50,7 @@ drm_clflush_page(struct page *page) page_virtual = kmap_atomic(page); for (i = 0; i < PAGE_SIZE; i += size) - clflush(page_virtual + i); + clflushopt(page_virtual + i); kunmap_atomic(page_virtual); } @@ -133,7 +139,7 @@ drm_clflush_virt_range(char *addr, unsigned long length) mb(); for (; addr < end; addr += boot_cpu_data.x86_clflush_size) clflush(addr); - clflush(end - 1); + clflushopt(end - 1); mb(); return; } diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 5736aaa7e86c..f7af69bcf3f4 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -468,8 +468,8 @@ void drm_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver) } else { list_for_each_entry_safe(dev, tmp, &driver->legacy_dev_list, legacy_dev_list) { - drm_put_dev(dev); list_del(&dev->legacy_dev_list); + drm_put_dev(dev); } } DRM_INFO("Module unloaded\n"); diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 215131ab1dd2..c204b4e3356e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -172,20 +172,24 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file) ret = exynos_drm_subdrv_open(dev, file); if (ret) - goto out; + goto err_file_priv_free; anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops, NULL, 0); if (IS_ERR(anon_filp)) { ret = PTR_ERR(anon_filp); - goto out; + goto err_subdrv_close; } anon_filp->f_mode = FMODE_READ | FMODE_WRITE; file_priv->anon_filp = anon_filp; return ret; -out: + +err_subdrv_close: + exynos_drm_subdrv_close(dev, file); + +err_file_priv_free: kfree(file_priv); file->driver_priv = NULL; return ret; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 04f1f02c4019..ec7bb0fc71bc 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -403,7 +403,7 @@ MODULE_DEVICE_TABLE(pci, pciidlist); void intel_detect_pch(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct pci_dev *pch; + struct pci_dev *pch = NULL; /* In all current cases, num_pipes is equivalent to the PCH_NOP setting * (which really amounts to a PCH but no South Display). @@ -424,12 +424,9 @@ void intel_detect_pch(struct drm_device *dev) * all the ISA bridge devices and check for the first match, instead * of only checking the first one. */ - pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); - while (pch) { - struct pci_dev *curr = pch; + while ((pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, pch))) { if (pch->vendor == PCI_VENDOR_ID_INTEL) { - unsigned short id; - id = pch->device & INTEL_PCH_DEVICE_ID_MASK; + unsigned short id = pch->device & INTEL_PCH_DEVICE_ID_MASK; dev_priv->pch_id = id; if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) { @@ -461,18 +458,16 @@ void intel_detect_pch(struct drm_device *dev) DRM_DEBUG_KMS("Found LynxPoint LP PCH\n"); WARN_ON(!IS_HASWELL(dev)); WARN_ON(!IS_ULT(dev)); - } else { - goto check_next; - } - pci_dev_put(pch); + } else + continue; + break; } -check_next: - pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, curr); - pci_dev_put(curr); } if (!pch) - DRM_DEBUG_KMS("No PCH found?\n"); + DRM_DEBUG_KMS("No PCH found.\n"); + + pci_dev_put(pch); } bool i915_semaphore_is_enabled(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 40a2b36b276b..d278be110805 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -842,7 +842,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev) dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, dev_priv->gtt.base.start / PAGE_SIZE, dev_priv->gtt.base.total / PAGE_SIZE, - false); + true); } void i915_gem_restore_gtt_mappings(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 1a24e84f2315..28d24caa49f3 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -82,9 +82,22 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size, "Graphics Stolen Memory"); if (r == NULL) { - DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n", - base, base + (uint32_t)dev_priv->gtt.stolen_size); - base = 0; + /* + * One more attempt but this time requesting region from + * base + 1, as we have seen that this resolves the region + * conflict with the PCI Bus. + * This is a BIOS w/a: Some BIOS wrap stolen in the root + * PCI bus, but have an off-by-one error. Hence retry the + * reservation starting from 1 instead of 0. + */ + r = devm_request_mem_region(dev->dev, base + 1, + dev_priv->gtt.stolen_size - 1, + "Graphics Stolen Memory"); + if (r == NULL) { + DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n", + base, base + (uint32_t)dev_priv->gtt.stolen_size); + base = 0; + } } return base; @@ -201,6 +214,13 @@ int i915_gem_init_stolen(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; int bios_reserved = 0; +#ifdef CONFIG_INTEL_IOMMU + if (intel_iommu_gfx_mapped) { + DRM_INFO("DMAR active, disabling use of stolen memory\n"); + return 0; + } +#endif + if (dev_priv->gtt.stolen_size == 0) return 0; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9fec71175571..d554169ac592 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -618,33 +618,25 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) /* raw reads, only for fast reads of display block, no need for forcewake etc. */ #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__)) -#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__)) static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t status; - - if (INTEL_INFO(dev)->gen < 7) { - status = pipe == PIPE_A ? - DE_PIPEA_VBLANK : - DE_PIPEB_VBLANK; + int reg; + + if (INTEL_INFO(dev)->gen >= 8) { + status = GEN8_PIPE_VBLANK; + reg = GEN8_DE_PIPE_ISR(pipe); + } else if (INTEL_INFO(dev)->gen >= 7) { + status = DE_PIPE_VBLANK_IVB(pipe); + reg = DEISR; } else { - switch (pipe) { - default: - case PIPE_A: - status = DE_PIPEA_VBLANK_IVB; - break; - case PIPE_B: - status = DE_PIPEB_VBLANK_IVB; - break; - case PIPE_C: - status = DE_PIPEC_VBLANK_IVB; - break; - } + status = DE_PIPE_VBLANK(pipe); + reg = DEISR; } - return __raw_i915_read32(dev_priv, DEISR) & status; + return __raw_i915_read32(dev_priv, reg) & status; } static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, @@ -702,7 +694,28 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, else position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3; - if (HAS_PCH_SPLIT(dev)) { + if (HAS_DDI(dev)) { + /* + * On HSW HDMI outputs there seems to be a 2 line + * difference, whereas eDP has the normal 1 line + * difference that earlier platforms have. External + * DP is unknown. For now just check for the 2 line + * difference case on all output types on HSW+. + * + * This might misinterpret the scanline counter being + * one line too far along on eDP, but that's less + * dangerous than the alternative since that would lead + * the vblank timestamp code astray when it sees a + * scanline count before vblank_start during a vblank + * interrupt. + */ + in_vbl = ilk_pipe_in_vblank_locked(dev, pipe); + if ((in_vbl && (position == vbl_start - 2 || + position == vbl_start - 1)) || + (!in_vbl && (position == vbl_end - 2 || + position == vbl_end - 1))) + position = (position + 2) % vtotal; + } else if (HAS_PCH_SPLIT(dev)) { /* * The scanline counter increments at the leading edge * of hsync, ie. it completely misses the active portion @@ -2769,10 +2782,9 @@ static void ibx_irq_postinstall(struct drm_device *dev) return; if (HAS_PCH_IBX(dev)) { - mask = SDE_GMBUS | SDE_AUX_MASK | SDE_TRANSB_FIFO_UNDER | - SDE_TRANSA_FIFO_UNDER | SDE_POISON; + mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON; } else { - mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT | SDE_ERROR_CPT; + mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT; I915_WRITE(SERR_INT, I915_READ(SERR_INT)); } @@ -2832,20 +2844,19 @@ static int ironlake_irq_postinstall(struct drm_device *dev) display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB | DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB | DE_PLANEB_FLIP_DONE_IVB | - DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB | - DE_ERR_INT_IVB); + DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB); extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB | - DE_PIPEA_VBLANK_IVB); + DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB); I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT)); } else { display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT | DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE | DE_AUX_CHANNEL_A | - DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN | DE_PIPEB_CRC_DONE | DE_PIPEA_CRC_DONE | DE_POISON); - extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT; + extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT | + DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN; } dev_priv->irq_mask = ~display_mask; @@ -2961,9 +2972,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE | GEN8_PIPE_CDCLK_CRC_DONE | - GEN8_PIPE_FIFO_UNDERRUN | GEN8_DE_PIPE_IRQ_FAULT_ERRORS; - uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK; + uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | + GEN8_PIPE_FIFO_UNDERRUN; int pipe; dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked; dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index e06b9e017d6b..234ac5f7bc5a 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1244,6 +1244,7 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder) if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + ironlake_edp_panel_vdd_on(intel_dp); ironlake_edp_panel_off(intel_dp); } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 4c1672809493..9b8a7c7ea7fc 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1092,12 +1092,12 @@ static void assert_cursor(struct drm_i915_private *dev_priv, struct drm_device *dev = dev_priv->dev; bool cur_state; - if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) - cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; - else if (IS_845G(dev) || IS_I865G(dev)) + if (IS_845G(dev) || IS_I865G(dev)) cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE; - else + else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; + else + cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; WARN(cur_state != state, "cursor on pipe %c assertion failure (expected %s, current %s)\n", diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 57552eb386b0..2688f6d64bb9 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1249,17 +1249,24 @@ void ironlake_edp_panel_off(struct intel_dp *intel_dp) DRM_DEBUG_KMS("Turn eDP power off\n"); + WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n"); + pp = ironlake_get_pp_control(intel_dp); /* We need to switch off panel power _and_ force vdd, for otherwise some * panels get very unhappy and cease to work. */ - pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE); + pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE); pp_ctrl_reg = _pp_ctrl_reg(intel_dp); I915_WRITE(pp_ctrl_reg, pp); POSTING_READ(pp_ctrl_reg); + intel_dp->want_panel_vdd = false; + ironlake_wait_panel_off(intel_dp); + + /* We got a reference when we enabled the VDD. */ + intel_runtime_pm_put(dev_priv); } void ironlake_edp_backlight_on(struct intel_dp *intel_dp) @@ -1639,7 +1646,7 @@ static void intel_edp_psr_enable_source(struct intel_dp *intel_dp) val |= EDP_PSR_LINK_DISABLE; I915_WRITE(EDP_PSR_CTL(dev), val | - IS_BROADWELL(dev) ? 0 : link_entry_time | + (IS_BROADWELL(dev) ? 0 : link_entry_time) | max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT | idle_frames << EDP_PSR_IDLE_FRAME_SHIFT | EDP_PSR_ENABLE); @@ -1784,6 +1791,7 @@ static void intel_disable_dp(struct intel_encoder *encoder) /* Make sure the panel is off before trying to change the mode. But also * ensure that we have vdd while we switch off the panel. */ + ironlake_edp_panel_vdd_on(intel_dp); ironlake_edp_backlight_off(intel_dp); intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); ironlake_edp_panel_off(intel_dp); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 6db0d9d17f47..ee3181ebcc92 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -845,7 +845,7 @@ static int hdmi_portclock_limit(struct intel_hdmi *hdmi) { struct drm_device *dev = intel_hdmi_to_dev(hdmi); - if (IS_G4X(dev)) + if (!hdmi->has_hdmi_sink || IS_G4X(dev)) return 165000; else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8) return 300000; @@ -899,8 +899,8 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, * outputs. We also need to check that the higher clock still fits * within limits. */ - if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= portclock_limit - && HAS_PCH_SPLIT(dev)) { + if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink && + clock_12bpc <= portclock_limit && HAS_PCH_SPLIT(dev)) { DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n"); desired_bpp = 12*3; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 350de359123a..079ea38f14d9 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -698,7 +698,7 @@ static void i9xx_enable_backlight(struct intel_connector *connector) freq /= 0xff; ctl = freq << 17; - if (IS_GEN2(dev) && panel->backlight.combination_mode) + if (panel->backlight.combination_mode) ctl |= BLM_LEGACY_MODE; if (IS_PINEVIEW(dev) && panel->backlight.active_low_pwm) ctl |= BLM_POLARITY_PNV; @@ -979,7 +979,7 @@ static int i9xx_setup_backlight(struct intel_connector *connector) ctl = I915_READ(BLC_PWM_CTL); - if (IS_GEN2(dev)) + if (IS_GEN2(dev) || IS_I915GM(dev) || IS_I945GM(dev)) panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE; if (IS_PINEVIEW(dev)) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d77cc81900f9..e1fc35a72656 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3493,6 +3493,8 @@ static void valleyview_setup_pctx(struct drm_device *dev) u32 pcbr; int pctx_size = 24*1024; + WARN_ON(!mutex_is_locked(&dev->struct_mutex)); + pcbr = I915_READ(VLV_PCBR); if (pcbr) { /* BIOS set it up already, grab the pre-alloc'd space */ @@ -3542,8 +3544,6 @@ static void valleyview_enable_rps(struct drm_device *dev) I915_WRITE(GTFIFODBG, gtfifodbg); } - valleyview_setup_pctx(dev); - /* If VLV, Forcewake all wells, else re-direct to regular path */ gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); @@ -4395,6 +4395,8 @@ void intel_enable_gt_powersave(struct drm_device *dev) ironlake_enable_rc6(dev); intel_init_emon(dev); } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + if (IS_VALLEYVIEW(dev)) + valleyview_setup_pctx(dev); /* * PCU communication is slow and this doesn't need to be * done at any specific time, so do this out of our fast path diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 89c484d8ac26..4ee702ac8907 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -866,13 +866,16 @@ static int nouveau_pmops_runtime_suspend(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); int ret; - if (nouveau_runtime_pm == 0) - return -EINVAL; + if (nouveau_runtime_pm == 0) { + pm_runtime_forbid(dev); + return -EBUSY; + } /* are we optimus enabled? */ if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) { DRM_DEBUG_DRIVER("failing to power off - not optimus\n"); - return -EINVAL; + pm_runtime_forbid(dev); + return -EBUSY; } nv_debug_level(SILENT); @@ -923,12 +926,15 @@ static int nouveau_pmops_runtime_idle(struct device *dev) struct nouveau_drm *drm = nouveau_drm(drm_dev); struct drm_crtc *crtc; - if (nouveau_runtime_pm == 0) + if (nouveau_runtime_pm == 0) { + pm_runtime_forbid(dev); return -EBUSY; + } /* are we optimus enabled? */ if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) { DRM_DEBUG_DRIVER("failing to power off - not optimus\n"); + pm_runtime_forbid(dev); return -EBUSY; } diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 2cec2ab02f80..607dc14d195e 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1314,7 +1314,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t } if (is_dp) args.v5.ucLaneNum = dp_lane_count; - else if (radeon_encoder->pixel_clock > 165000) + else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock)) args.v5.ucLaneNum = 8; else args.v5.ucLaneNum = 4; diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index e6419ca7cd37..bbb17841a9e5 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3046,7 +3046,7 @@ static u32 cik_create_bitmask(u32 bit_width) } /** - * cik_select_se_sh - select which SE, SH to address + * cik_get_rb_disabled - computes the mask of disabled RBs * * @rdev: radeon_device pointer * @max_rb_num: max RBs (render backends) for the asic @@ -4134,8 +4134,11 @@ static void cik_cp_compute_enable(struct radeon_device *rdev, bool enable) { if (enable) WREG32(CP_MEC_CNTL, 0); - else + else { WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT)); + rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false; + rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false; + } udelay(50); } @@ -7902,7 +7905,8 @@ int cik_resume(struct radeon_device *rdev) /* init golden registers */ cik_init_golden_registers(rdev); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = cik_startup(rdev); diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index 1ecb3f1070e3..94626ea90fa5 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -264,6 +264,8 @@ static void cik_sdma_gfx_stop(struct radeon_device *rdev) WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl); WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0); } + rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false; + rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false; } /** @@ -291,6 +293,11 @@ void cik_sdma_enable(struct radeon_device *rdev, bool enable) u32 me_cntl, reg_offset; int i; + if (enable == false) { + cik_sdma_gfx_stop(rdev); + cik_sdma_rlc_stop(rdev); + } + for (i = 0; i < 2; i++) { if (i == 0) reg_offset = SDMA0_REGISTER_OFFSET; @@ -420,10 +427,6 @@ static int cik_sdma_load_microcode(struct radeon_device *rdev) if (!rdev->sdma_fw) return -EINVAL; - /* stop the gfx rings and rlc compute queues */ - cik_sdma_gfx_stop(rdev); - cik_sdma_rlc_stop(rdev); - /* halt the MEs */ cik_sdma_enable(rdev, false); @@ -492,9 +495,6 @@ int cik_sdma_resume(struct radeon_device *rdev) */ void cik_sdma_fini(struct radeon_device *rdev) { - /* stop the gfx rings and rlc compute queues */ - cik_sdma_gfx_stop(rdev); - cik_sdma_rlc_stop(rdev); /* halt the MEs */ cik_sdma_enable(rdev, false); radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 8a2c010b7dc5..27b0ff16082e 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -5299,7 +5299,8 @@ int evergreen_resume(struct radeon_device *rdev) /* init golden registers */ evergreen_init_golden_registers(rdev); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = evergreen_startup(rdev); diff --git a/drivers/gpu/drm/radeon/evergreen_smc.h b/drivers/gpu/drm/radeon/evergreen_smc.h index 76ada8cfe902..3a03ba37d043 100644 --- a/drivers/gpu/drm/radeon/evergreen_smc.h +++ b/drivers/gpu/drm/radeon/evergreen_smc.h @@ -57,7 +57,7 @@ typedef struct SMC_Evergreen_MCRegisters SMC_Evergreen_MCRegisters; #define EVERGREEN_SMC_FIRMWARE_HEADER_LOCATION 0x100 -#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters 0x0 +#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters 0x8 #define EVERGREEN_SMC_FIRMWARE_HEADER_stateTable 0xC #define EVERGREEN_SMC_FIRMWARE_HEADER_mcRegisterTable 0x20 diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index ea932ac66fc6..bf6300cfd62d 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -2105,7 +2105,8 @@ int cayman_resume(struct radeon_device *rdev) /* init golden registers */ ni_init_golden_registers(rdev); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = cayman_startup(rdev); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index ef024ce3f7cc..3cc78bb66042 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -3942,8 +3942,6 @@ int r100_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = r100_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 7c63ef840e86..0b658b34b33a 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -1430,8 +1430,6 @@ int r300_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = r300_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c index 3768aab2710b..802b19220a21 100644 --- a/drivers/gpu/drm/radeon/r420.c +++ b/drivers/gpu/drm/radeon/r420.c @@ -325,8 +325,6 @@ int r420_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = r420_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c index e209eb75024f..98d6053c36c6 100644 --- a/drivers/gpu/drm/radeon/r520.c +++ b/drivers/gpu/drm/radeon/r520.c @@ -240,8 +240,6 @@ int r520_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = r520_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index cdbc4171fe73..647ef4079217 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2968,7 +2968,8 @@ int r600_resume(struct radeon_device *rdev) /* post card */ atom_asic_init(rdev->mode_info.atom_context); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = r600_startup(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index b012cbbc3ed5..044bc98fb459 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1521,13 +1521,16 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) if (r) DRM_ERROR("ib ring test failed (%d).\n", r); - if (rdev->pm.dpm_enabled) { + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) { /* do dpm late init */ r = radeon_pm_late_init(rdev); if (r) { rdev->pm.dpm_enabled = false; DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); } + } else { + /* resume old pm late */ + radeon_pm_resume(rdev); } radeon_restore_bios_scratch_regs(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 84a1bbb75f91..f633c2782170 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -403,11 +403,15 @@ static int radeon_pmops_runtime_suspend(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); int ret; - if (radeon_runtime_pm == 0) - return -EINVAL; + if (radeon_runtime_pm == 0) { + pm_runtime_forbid(dev); + return -EBUSY; + } - if (radeon_runtime_pm == -1 && !radeon_is_px()) - return -EINVAL; + if (radeon_runtime_pm == -1 && !radeon_is_px()) { + pm_runtime_forbid(dev); + return -EBUSY; + } drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; drm_kms_helper_poll_disable(drm_dev); @@ -456,12 +460,15 @@ static int radeon_pmops_runtime_idle(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); struct drm_crtc *crtc; - if (radeon_runtime_pm == 0) + if (radeon_runtime_pm == 0) { + pm_runtime_forbid(dev); return -EBUSY; + } /* are we PX enabled? */ if (radeon_runtime_pm == -1 && !radeon_is_px()) { DRM_DEBUG_DRIVER("failing to power off - not px\n"); + pm_runtime_forbid(dev); return -EBUSY; } diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 2aecd6dc2610..66ed3ea71440 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -33,6 +33,13 @@ #include <linux/vga_switcheroo.h> #include <linux/slab.h> #include <linux/pm_runtime.h> + +#if defined(CONFIG_VGA_SWITCHEROO) +bool radeon_is_px(void); +#else +static inline bool radeon_is_px(void) { return false; } +#endif + /** * radeon_driver_unload_kms - Main unload function for KMS. * @@ -130,7 +137,8 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) "Error during ACPI methods call\n"); } - if (radeon_runtime_pm != 0) { + if ((radeon_runtime_pm == 1) || + ((radeon_runtime_pm == -1) && radeon_is_px())) { pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); pm_runtime_set_active(dev->dev); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 77f5b0c3edb8..040a2a10ea17 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -714,6 +714,9 @@ int radeon_ttm_init(struct radeon_device *rdev) DRM_ERROR("Failed initializing VRAM heap.\n"); return r; } + /* Change the size here instead of the init above so only lpfn is affected */ + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); + r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->stollen_vga_memory); @@ -935,7 +938,7 @@ static ssize_t radeon_ttm_gtt_read(struct file *f, char __user *buf, while (size) { loff_t p = *pos / PAGE_SIZE; unsigned off = *pos & ~PAGE_MASK; - ssize_t cur_size = min(size, PAGE_SIZE - off); + size_t cur_size = min_t(size_t, size, PAGE_SIZE - off); struct page *page; void *ptr; diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index b5c2369cda2f..130d5cc50d43 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -474,8 +474,6 @@ int rs400_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = rs400_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index fdcde7693032..72d3616de08e 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -1048,8 +1048,6 @@ int rs600_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = rs600_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 35950738bd5e..3462b64369bf 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -756,8 +756,6 @@ int rs690_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = rs690_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 98e8138ff779..237dd29d9f1c 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -586,8 +586,6 @@ int rv515_resume(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); - radeon_pm_resume(rdev); - rdev->accel_working = true; r = rv515_startup(rdev); if (r) { diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index 4e37a42305d8..fef310773aad 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -1811,7 +1811,8 @@ int rv770_resume(struct radeon_device *rdev) /* init golden registers */ rv770_init_golden_registers(rdev); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = rv770_startup(rdev); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 83578324e5d1..9a124d0608b3 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -6618,7 +6618,8 @@ int si_resume(struct radeon_device *rdev) /* init golden registers */ si_init_golden_registers(rdev); - radeon_pm_resume(rdev); + if (rdev->pm.pm_method == PM_METHOD_DPM) + radeon_pm_resume(rdev); rdev->accel_working = true; r = si_startup(rdev); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index a06651309388..214b7992a3aa 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -351,9 +351,11 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, moved: if (bo->evicted) { - ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement); - if (ret) - pr_err("Can not flush read caches\n"); + if (bdev->driver->invalidate_caches) { + ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement); + if (ret) + pr_err("Can not flush read caches\n"); + } bo->evicted = false; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 801231c9ae48..0ce48e5a9cb4 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -339,11 +339,13 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma, vma->vm_private_data = bo; /* - * PFNMAP is faster than MIXEDMAP due to reduced page - * administration. So use MIXEDMAP only if private VMA, where - * we need to support COW. + * We'd like to use VM_PFNMAP on shared mappings, where + * (vma->vm_flags & VM_SHARED) != 0, for performance reasons, + * but for some reason VM_PFNMAP + x86 PAT + write-combine is very + * bad for performance. Until that has been sorted out, use + * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719 */ - vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP; + vma->vm_flags |= VM_MIXEDMAP; vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; return 0; out_unref: @@ -359,7 +361,7 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo) vma->vm_ops = &ttm_bo_vm_ops; vma->vm_private_data = ttm_bo_reference(bo); - vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP; + vma->vm_flags |= VM_MIXEDMAP; vma->vm_flags |= VM_IO | VM_DONTEXPAND; return 0; } diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index 8d67b943ac05..0394811251bd 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -177,8 +177,10 @@ void udl_gem_free_object(struct drm_gem_object *gem_obj) if (obj->vmapping) udl_gem_vunmap(obj); - if (gem_obj->import_attach) + if (gem_obj->import_attach) { drm_prime_gem_destroy(gem_obj, obj->sg); + put_device(gem_obj->dev->dev); + } if (obj->pages) udl_gem_put_pages(obj); @@ -256,9 +258,12 @@ struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev, int ret; /* need to attach */ + get_device(dev->dev); attach = dma_buf_attach(dma_buf, dev->dev); - if (IS_ERR(attach)) + if (IS_ERR(attach)) { + put_device(dev->dev); return ERR_CAST(attach); + } get_dma_buf(dma_buf); @@ -282,6 +287,6 @@ fail_unmap: fail_detach: dma_buf_detach(dma_buf, attach); dma_buf_put(dma_buf); - + put_device(dev->dev); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 82468d902915..e7af580ab977 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -830,6 +830,24 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, if (unlikely(ret != 0)) goto out_unlock; + /* + * A gb-aware client referencing a shared surface will + * expect a backup buffer to be present. + */ + if (dev_priv->has_mob && req->shareable) { + uint32_t backup_handle; + + ret = vmw_user_dmabuf_alloc(dev_priv, tfile, + res->backup_size, + true, + &backup_handle, + &res->backup); + if (unlikely(ret != 0)) { + vmw_resource_unreference(&res); + goto out_unlock; + } + } + tmp = vmw_resource_reference(&srf->res); ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime, req->shareable, VMW_RES_SURFACE, diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index befe0e336471..24883b4d1a49 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -43,6 +43,7 @@ #define G25_REV_MIN 0x22 #define G27_REV_MAJ 0x12 #define G27_REV_MIN 0x38 +#define G27_2_REV_MIN 0x39 #define to_hid_device(pdev) container_of(pdev, struct hid_device, dev) @@ -130,6 +131,7 @@ static const struct lg4ff_usb_revision lg4ff_revs[] = { {DFP_REV_MAJ, DFP_REV_MIN, &native_dfp}, /* Driving Force Pro */ {G25_REV_MAJ, G25_REV_MIN, &native_g25}, /* G25 */ {G27_REV_MAJ, G27_REV_MIN, &native_g27}, /* G27 */ + {G27_REV_MAJ, G27_2_REV_MIN, &native_g27}, /* G27 v2 */ }; /* Recalculates X axis value accordingly to currently selected range */ diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 12354055d474..2f19b15f47f2 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -42,6 +42,7 @@ #define DUALSHOCK4_CONTROLLER_BT BIT(6) #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER_USB | BUZZ_CONTROLLER | DUALSHOCK4_CONTROLLER_USB) +#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER_USB | DUALSHOCK4_CONTROLLER_USB) #define MAX_LEDS 4 @@ -499,6 +500,7 @@ struct sony_sc { __u8 right; #endif + __u8 worker_initialized; __u8 led_state[MAX_LEDS]; __u8 led_count; }; @@ -993,22 +995,11 @@ static int sony_init_ff(struct hid_device *hdev) return input_ff_create_memless(input_dev, NULL, sony_play_effect); } -static void sony_destroy_ff(struct hid_device *hdev) -{ - struct sony_sc *sc = hid_get_drvdata(hdev); - - cancel_work_sync(&sc->state_worker); -} - #else static int sony_init_ff(struct hid_device *hdev) { return 0; } - -static void sony_destroy_ff(struct hid_device *hdev) -{ -} #endif static int sony_set_output_report(struct sony_sc *sc, int req_id, int req_size) @@ -1077,6 +1068,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) if (sc->quirks & SIXAXIS_CONTROLLER_USB) { hdev->hid_output_raw_report = sixaxis_usb_output_raw_report; ret = sixaxis_set_operational_usb(hdev); + + sc->worker_initialized = 1; INIT_WORK(&sc->state_worker, sixaxis_state_worker); } else if (sc->quirks & SIXAXIS_CONTROLLER_BT) @@ -1087,6 +1080,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret < 0) goto err_stop; + sc->worker_initialized = 1; INIT_WORK(&sc->state_worker, dualshock4_state_worker); } else { ret = 0; @@ -1101,9 +1095,11 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) goto err_stop; } - ret = sony_init_ff(hdev); - if (ret < 0) - goto err_stop; + if (sc->quirks & SONY_FF_SUPPORT) { + ret = sony_init_ff(hdev); + if (ret < 0) + goto err_stop; + } return 0; err_stop: @@ -1120,7 +1116,8 @@ static void sony_remove(struct hid_device *hdev) if (sc->quirks & SONY_LED_SUPPORT) sony_leds_remove(hdev); - sony_destroy_ff(hdev); + if (sc->worker_initialized) + cancel_work_sync(&sc->state_worker); hid_hw_stop(hdev); } diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index cb0137b3718d..ab24ce2eb28f 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -320,13 +320,13 @@ static void drop_ref(struct hidraw *hidraw, int exists_bit) hid_hw_close(hidraw->hid); wake_up_interruptible(&hidraw->wait); } + device_destroy(hidraw_class, + MKDEV(hidraw_major, hidraw->minor)); } else { --hidraw->open; } if (!hidraw->open) { if (!hidraw->exist) { - device_destroy(hidraw_class, - MKDEV(hidraw_major, hidraw->minor)); hidraw_table[hidraw->minor] = NULL; kfree(hidraw); } else { diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index f5ed03164d86..de17c5593d97 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -387,7 +387,7 @@ config I2C_CBUS_GPIO config I2C_CPM tristate "Freescale CPM1 or CPM2 (MPC8xx/826x)" - depends on (CPM1 || CPM2) && OF_I2C + depends on CPM1 || CPM2 help This supports the use of the I2C interface on Freescale processors with CPM1 or CPM2. diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index be7f0a20d634..f3b89a4698b6 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -39,7 +39,9 @@ #include <linux/i2c.h> #include <linux/io.h> #include <linux/dma-mapping.h> +#include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <sysdev/fsl_soc.h> #include <asm/cpm.h> diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index e81c5547e647..f9c12e92fdd6 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -53,8 +53,8 @@ #include "user.h" #define DRV_NAME MLX4_IB_DRV_NAME -#define DRV_VERSION "1.0" -#define DRV_RELDATE "April 4, 2008" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb 2014" #define MLX4_IB_FLOW_MAX_PRIO 0xFFF #define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index aa03e732b6a8..bf900579ac08 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -46,8 +46,8 @@ #include "mlx5_ib.h" #define DRIVER_NAME "mlx5_ib" -#define DRIVER_VERSION "1.0" -#define DRIVER_RELDATE "June 2013" +#define DRIVER_VERSION "2.2-1" +#define DRIVER_RELDATE "Feb 2014" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver"); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index d18d08a076e8..8ee228e9ab5a 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -492,12 +492,11 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->state = ISER_CONN_INIT; INIT_LIST_HEAD(&isert_conn->conn_accept_node); init_completion(&isert_conn->conn_login_comp); - init_waitqueue_head(&isert_conn->conn_wait); - init_waitqueue_head(&isert_conn->conn_wait_comp_err); + init_completion(&isert_conn->conn_wait); + init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); - mutex_init(&isert_conn->conn_comp_mutex); spin_lock_init(&isert_conn->conn_lock); cma_id->context = isert_conn; @@ -688,11 +687,11 @@ isert_disconnect_work(struct work_struct *work) pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); mutex_lock(&isert_conn->conn_mutex); - isert_conn->state = ISER_CONN_DOWN; + if (isert_conn->state == ISER_CONN_UP) + isert_conn->state = ISER_CONN_TERMINATING; if (isert_conn->post_recv_buf_count == 0 && atomic_read(&isert_conn->post_send_buf_count) == 0) { - pr_debug("Calling wake_up(&isert_conn->conn_wait);\n"); mutex_unlock(&isert_conn->conn_mutex); goto wake_up; } @@ -712,7 +711,7 @@ isert_disconnect_work(struct work_struct *work) mutex_unlock(&isert_conn->conn_mutex); wake_up: - wake_up(&isert_conn->conn_wait); + complete(&isert_conn->conn_wait); isert_put_conn(isert_conn); } @@ -888,16 +887,17 @@ isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, * Coalesce send completion interrupts by only setting IB_SEND_SIGNALED * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls. */ - mutex_lock(&isert_conn->conn_comp_mutex); - if (coalesce && + mutex_lock(&isert_conn->conn_mutex); + if (coalesce && isert_conn->state == ISER_CONN_UP && ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) { + tx_desc->llnode_active = true; llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist); - mutex_unlock(&isert_conn->conn_comp_mutex); + mutex_unlock(&isert_conn->conn_mutex); return; } isert_conn->conn_comp_batch = 0; tx_desc->comp_llnode_batch = llist_del_all(&isert_conn->conn_comp_llist); - mutex_unlock(&isert_conn->conn_comp_mutex); + mutex_unlock(&isert_conn->conn_mutex); send_wr->send_flags = IB_SEND_SIGNALED; } @@ -1464,7 +1464,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd) case ISCSI_OP_SCSI_CMD: spin_lock_bh(&conn->cmd_lock); if (!list_empty(&cmd->i_conn_node)) - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); if (cmd->data_direction == DMA_TO_DEVICE) @@ -1476,7 +1476,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd) case ISCSI_OP_SCSI_TMFUNC: spin_lock_bh(&conn->cmd_lock); if (!list_empty(&cmd->i_conn_node)) - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); transport_generic_free_cmd(&cmd->se_cmd, 0); @@ -1486,7 +1486,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd) case ISCSI_OP_TEXT: spin_lock_bh(&conn->cmd_lock); if (!list_empty(&cmd->i_conn_node)) - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); /* @@ -1549,6 +1549,7 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc, iscsit_stop_dataout_timer(cmd); device->unreg_rdma_mem(isert_cmd, isert_conn); cmd->write_data_done = wr->cur_rdma_length; + wr->send_wr_num = 0; pr_debug("Cmd: %p RDMA_READ comp calling execute_cmd\n", isert_cmd); spin_lock_bh(&cmd->istate_lock); @@ -1589,7 +1590,7 @@ isert_do_control_comp(struct work_struct *work) pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n"); /* * Call atomic_dec(&isert_conn->post_send_buf_count) - * from isert_free_conn() + * from isert_wait_conn() */ isert_conn->logout_posted = true; iscsit_logout_post_handler(cmd, cmd->conn); @@ -1613,6 +1614,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc, struct ib_device *ib_dev) { struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; + struct isert_rdma_wr *wr = &isert_cmd->rdma_wr; if (cmd->i_state == ISTATE_SEND_TASKMGTRSP || cmd->i_state == ISTATE_SEND_LOGOUTRSP || @@ -1624,7 +1626,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc, queue_work(isert_comp_wq, &isert_cmd->comp_work); return; } - atomic_dec(&isert_conn->post_send_buf_count); + atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; isert_completion_put(tx_desc, isert_cmd, ib_dev); @@ -1662,7 +1664,7 @@ __isert_send_completion(struct iser_tx_desc *tx_desc, case ISER_IB_RDMA_READ: pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n"); - atomic_dec(&isert_conn->post_send_buf_count); + atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count); isert_completion_rdma_read(tx_desc, isert_cmd); break; default: @@ -1691,31 +1693,76 @@ isert_send_completion(struct iser_tx_desc *tx_desc, } static void -isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn) +isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_dev) +{ + struct llist_node *llnode; + struct isert_rdma_wr *wr; + struct iser_tx_desc *t; + + mutex_lock(&isert_conn->conn_mutex); + llnode = llist_del_all(&isert_conn->conn_comp_llist); + isert_conn->conn_comp_batch = 0; + mutex_unlock(&isert_conn->conn_mutex); + + while (llnode) { + t = llist_entry(llnode, struct iser_tx_desc, comp_llnode); + llnode = llist_next(llnode); + wr = &t->isert_cmd->rdma_wr; + + atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); + isert_completion_put(t, t->isert_cmd, ib_dev); + } +} + +static void +isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn) { struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_cmd *isert_cmd = tx_desc->isert_cmd; + struct llist_node *llnode = tx_desc->comp_llnode_batch; + struct isert_rdma_wr *wr; + struct iser_tx_desc *t; - if (tx_desc) { - struct isert_cmd *isert_cmd = tx_desc->isert_cmd; + while (llnode) { + t = llist_entry(llnode, struct iser_tx_desc, comp_llnode); + llnode = llist_next(llnode); + wr = &t->isert_cmd->rdma_wr; - if (!isert_cmd) - isert_unmap_tx_desc(tx_desc, ib_dev); - else - isert_completion_put(tx_desc, isert_cmd, ib_dev); + atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); + isert_completion_put(t, t->isert_cmd, ib_dev); } + tx_desc->comp_llnode_batch = NULL; - if (isert_conn->post_recv_buf_count == 0 && - atomic_read(&isert_conn->post_send_buf_count) == 0) { - pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - pr_debug("Calling wake_up from isert_cq_comp_err\n"); + if (!isert_cmd) + isert_unmap_tx_desc(tx_desc, ib_dev); + else + isert_completion_put(tx_desc, isert_cmd, ib_dev); +} - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->state != ISER_CONN_DOWN) - isert_conn->state = ISER_CONN_TERMINATING; - mutex_unlock(&isert_conn->conn_mutex); +static void +isert_cq_rx_comp_err(struct isert_conn *isert_conn) +{ + struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct iscsi_conn *conn = isert_conn->conn; - wake_up(&isert_conn->conn_wait_comp_err); + if (isert_conn->post_recv_buf_count) + return; + + isert_cq_drain_comp_llist(isert_conn, ib_dev); + + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); } + + while (atomic_read(&isert_conn->post_send_buf_count)) + msleep(3000); + + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_DOWN; + mutex_unlock(&isert_conn->conn_mutex); + + complete(&isert_conn->conn_wait_comp_err); } static void @@ -1740,8 +1787,14 @@ isert_cq_tx_work(struct work_struct *work) pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n"); pr_debug("TX wc.status: 0x%08x\n", wc.status); pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err); - atomic_dec(&isert_conn->post_send_buf_count); - isert_cq_comp_err(tx_desc, isert_conn); + + if (wc.wr_id != ISER_FASTREG_LI_WRID) { + if (tx_desc->llnode_active) + continue; + + atomic_dec(&isert_conn->post_send_buf_count); + isert_cq_tx_comp_err(tx_desc, isert_conn); + } } } @@ -1784,7 +1837,7 @@ isert_cq_rx_work(struct work_struct *work) wc.vendor_err); } isert_conn->post_recv_buf_count--; - isert_cq_comp_err(NULL, isert_conn); + isert_cq_rx_comp_err(isert_conn); } } @@ -2202,6 +2255,7 @@ isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc, if (!fr_desc->valid) { memset(&inv_wr, 0, sizeof(inv_wr)); + inv_wr.wr_id = ISER_FASTREG_LI_WRID; inv_wr.opcode = IB_WR_LOCAL_INV; inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey; wr = &inv_wr; @@ -2212,6 +2266,7 @@ isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc, /* Prepare FASTREG WR */ memset(&fr_wr, 0, sizeof(fr_wr)); + fr_wr.wr_id = ISER_FASTREG_LI_WRID; fr_wr.opcode = IB_WR_FAST_REG_MR; fr_wr.wr.fast_reg.iova_start = fr_desc->data_frpl->page_list[0] + page_off; @@ -2377,12 +2432,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) isert_init_send_wr(isert_conn, isert_cmd, &isert_cmd->tx_desc.send_wr, true); - atomic_inc(&isert_conn->post_send_buf_count); + atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed); if (rc) { pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n"); - atomic_dec(&isert_conn->post_send_buf_count); + atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); } pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data READ\n", isert_cmd); @@ -2410,12 +2465,12 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery) return rc; } - atomic_inc(&isert_conn->post_send_buf_count); + atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count); rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed); if (rc) { pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n"); - atomic_dec(&isert_conn->post_send_buf_count); + atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count); } pr_debug("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n", isert_cmd); @@ -2702,22 +2757,11 @@ isert_free_np(struct iscsi_np *np) kfree(isert_np); } -static int isert_check_state(struct isert_conn *isert_conn, int state) -{ - int ret; - - mutex_lock(&isert_conn->conn_mutex); - ret = (isert_conn->state == state); - mutex_unlock(&isert_conn->conn_mutex); - - return ret; -} - -static void isert_free_conn(struct iscsi_conn *conn) +static void isert_wait_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; - pr_debug("isert_free_conn: Starting \n"); + pr_debug("isert_wait_conn: Starting \n"); /* * Decrement post_send_buf_count for special case when called * from isert_do_control_comp() -> iscsit_logout_post_handler() @@ -2727,38 +2771,29 @@ static void isert_free_conn(struct iscsi_conn *conn) atomic_dec(&isert_conn->post_send_buf_count); if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) { - pr_debug("Calling rdma_disconnect from isert_free_conn\n"); + pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); rdma_disconnect(isert_conn->conn_cm_id); } /* * Only wait for conn_wait_comp_err if the isert_conn made it * into full feature phase.. */ - if (isert_conn->state == ISER_CONN_UP) { - pr_debug("isert_free_conn: Before wait_event comp_err %d\n", - isert_conn->state); - mutex_unlock(&isert_conn->conn_mutex); - - wait_event(isert_conn->conn_wait_comp_err, - (isert_check_state(isert_conn, ISER_CONN_TERMINATING))); - - wait_event(isert_conn->conn_wait, - (isert_check_state(isert_conn, ISER_CONN_DOWN))); - - isert_put_conn(isert_conn); - return; - } if (isert_conn->state == ISER_CONN_INIT) { mutex_unlock(&isert_conn->conn_mutex); - isert_put_conn(isert_conn); return; } - pr_debug("isert_free_conn: wait_event conn_wait %d\n", - isert_conn->state); + if (isert_conn->state == ISER_CONN_UP) + isert_conn->state = ISER_CONN_TERMINATING; mutex_unlock(&isert_conn->conn_mutex); - wait_event(isert_conn->conn_wait, - (isert_check_state(isert_conn, ISER_CONN_DOWN))); + wait_for_completion(&isert_conn->conn_wait_comp_err); + + wait_for_completion(&isert_conn->conn_wait); +} + +static void isert_free_conn(struct iscsi_conn *conn) +{ + struct isert_conn *isert_conn = conn->context; isert_put_conn(isert_conn); } @@ -2771,6 +2806,7 @@ static struct iscsit_transport iser_target_transport = { .iscsit_setup_np = isert_setup_np, .iscsit_accept_np = isert_accept_np, .iscsit_free_np = isert_free_np, + .iscsit_wait_conn = isert_wait_conn, .iscsit_free_conn = isert_free_conn, .iscsit_get_login_rx = isert_get_login_rx, .iscsit_put_login_tx = isert_put_login_tx, diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 708a069002f3..f6ae7f5dd408 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -6,6 +6,7 @@ #define ISERT_RDMA_LISTEN_BACKLOG 10 #define ISCSI_ISER_SG_TABLESIZE 256 +#define ISER_FASTREG_LI_WRID 0xffffffffffffffffULL enum isert_desc_type { ISCSI_TX_CONTROL, @@ -45,6 +46,7 @@ struct iser_tx_desc { struct isert_cmd *isert_cmd; struct llist_node *comp_llnode_batch; struct llist_node comp_llnode; + bool llnode_active; struct ib_send_wr send_wr; } __packed; @@ -116,8 +118,8 @@ struct isert_conn { struct isert_device *conn_device; struct work_struct conn_logout_work; struct mutex conn_mutex; - wait_queue_head_t conn_wait; - wait_queue_head_t conn_wait_comp_err; + struct completion conn_wait; + struct completion conn_wait_comp_err; struct kref conn_kref; struct list_head conn_fr_pool; int conn_fr_pool_size; @@ -126,7 +128,6 @@ struct isert_conn { #define ISERT_COMP_BATCH_COUNT 8 int conn_comp_batch; struct llist_head conn_comp_llist; - struct mutex conn_comp_mutex; }; #define ISERT_MAX_CQ 64 diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index a06e12552886..ce953d895f5b 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -954,11 +954,13 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd, return -EFAULT; error = input_ff_upload(dev, &effect, file); + if (error) + return error; if (put_user(effect.id, &(((struct ff_effect __user *)p)->id))) return -EFAULT; - return error; + return 0; } /* Multi-number variable-length handlers */ diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c index bb3b57bea8ba..5ef7fcf0e250 100644 --- a/drivers/input/keyboard/adp5588-keys.c +++ b/drivers/input/keyboard/adp5588-keys.c @@ -76,8 +76,18 @@ static int adp5588_gpio_get_value(struct gpio_chip *chip, unsigned off) struct adp5588_kpad *kpad = container_of(chip, struct adp5588_kpad, gc); unsigned int bank = ADP5588_BANK(kpad->gpiomap[off]); unsigned int bit = ADP5588_BIT(kpad->gpiomap[off]); + int val; - return !!(adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank) & bit); + mutex_lock(&kpad->gpio_lock); + + if (kpad->dir[bank] & bit) + val = kpad->dat_out[bank]; + else + val = adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank); + + mutex_unlock(&kpad->gpio_lock); + + return !!(val & bit); } static void adp5588_gpio_set_value(struct gpio_chip *chip, diff --git a/drivers/input/misc/da9052_onkey.c b/drivers/input/misc/da9052_onkey.c index 1f695f229ea8..184c8f21ab59 100644 --- a/drivers/input/misc/da9052_onkey.c +++ b/drivers/input/misc/da9052_onkey.c @@ -27,29 +27,32 @@ struct da9052_onkey { static void da9052_onkey_query(struct da9052_onkey *onkey) { - int key_stat; + int ret; - key_stat = da9052_reg_read(onkey->da9052, DA9052_EVENT_B_REG); - if (key_stat < 0) { + ret = da9052_reg_read(onkey->da9052, DA9052_STATUS_A_REG); + if (ret < 0) { dev_err(onkey->da9052->dev, - "Failed to read onkey event %d\n", key_stat); + "Failed to read onkey event err=%d\n", ret); } else { /* * Since interrupt for deassertion of ONKEY pin is not * generated, onkey event state determines the onkey * button state. */ - key_stat &= DA9052_EVENTB_ENONKEY; - input_report_key(onkey->input, KEY_POWER, key_stat); + bool pressed = !(ret & DA9052_STATUSA_NONKEY); + + input_report_key(onkey->input, KEY_POWER, pressed); input_sync(onkey->input); - } - /* - * Interrupt is generated only when the ONKEY pin is asserted. - * Hence the deassertion of the pin is simulated through work queue. - */ - if (key_stat) - schedule_delayed_work(&onkey->work, msecs_to_jiffies(50)); + /* + * Interrupt is generated only when the ONKEY pin + * is asserted. Hence the deassertion of the pin + * is simulated through work queue. + */ + if (pressed) + schedule_delayed_work(&onkey->work, + msecs_to_jiffies(50)); + } } static void da9052_onkey_work(struct work_struct *work) diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c index 87095e2f5153..8af34ffe208b 100644 --- a/drivers/input/mouse/cypress_ps2.c +++ b/drivers/input/mouse/cypress_ps2.c @@ -409,7 +409,6 @@ static int cypress_set_input_params(struct input_dev *input, __clear_bit(REL_X, input->relbit); __clear_bit(REL_Y, input->relbit); - __set_bit(INPUT_PROP_BUTTONPAD, input->propbit); __set_bit(EV_KEY, input->evbit); __set_bit(BTN_LEFT, input->keybit); __set_bit(BTN_RIGHT, input->keybit); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 26386f9d2569..d8d49d10f9bb 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -265,11 +265,22 @@ static int synaptics_identify(struct psmouse *psmouse) * Read touchpad resolution and maximum reported coordinates * Resolution is left zero if touchpad does not support the query */ + +static const int *quirk_min_max; + static int synaptics_resolution(struct psmouse *psmouse) { struct synaptics_data *priv = psmouse->private; unsigned char resp[3]; + if (quirk_min_max) { + priv->x_min = quirk_min_max[0]; + priv->x_max = quirk_min_max[1]; + priv->y_min = quirk_min_max[2]; + priv->y_max = quirk_min_max[3]; + return 0; + } + if (SYN_ID_MAJOR(priv->identity) < 4) return 0; @@ -1485,10 +1496,54 @@ static const struct dmi_system_id olpc_dmi_table[] __initconst = { { } }; +static const struct dmi_system_id min_max_dmi_table[] __initconst = { +#if defined(CONFIG_DMI) + { + /* Lenovo ThinkPad Helix */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"), + }, + .driver_data = (int []){1024, 5052, 2258, 4832}, + }, + { + /* Lenovo ThinkPad X240 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"), + }, + .driver_data = (int []){1232, 5710, 1156, 4696}, + }, + { + /* Lenovo ThinkPad T440s */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"), + }, + .driver_data = (int []){1024, 5112, 2024, 4832}, + }, + { + /* Lenovo ThinkPad T540p */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"), + }, + .driver_data = (int []){1024, 5056, 2058, 4832}, + }, +#endif + { } +}; + void __init synaptics_module_init(void) { + const struct dmi_system_id *min_max_dmi; + impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table); broken_olpc_ec = dmi_check_system(olpc_dmi_table); + + min_max_dmi = dmi_first_match(min_max_dmi_table); + if (min_max_dmi) + quirk_min_max = min_max_dmi->driver_data; } static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode) diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 4c842c320c2e..b604564dec5c 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -67,7 +67,6 @@ struct mousedev { struct device dev; struct cdev cdev; bool exist; - bool is_mixdev; struct list_head mixdev_node; bool opened_by_mixdev; @@ -77,6 +76,9 @@ struct mousedev { int old_x[4], old_y[4]; int frac_dx, frac_dy; unsigned long touch; + + int (*open_device)(struct mousedev *mousedev); + void (*close_device)(struct mousedev *mousedev); }; enum mousedev_emul { @@ -116,9 +118,6 @@ static unsigned char mousedev_imex_seq[] = { 0xf3, 200, 0xf3, 200, 0xf3, 80 }; static struct mousedev *mousedev_mix; static LIST_HEAD(mousedev_mix_list); -static void mixdev_open_devices(void); -static void mixdev_close_devices(void); - #define fx(i) (mousedev->old_x[(mousedev->pkt_count - (i)) & 03]) #define fy(i) (mousedev->old_y[(mousedev->pkt_count - (i)) & 03]) @@ -428,9 +427,7 @@ static int mousedev_open_device(struct mousedev *mousedev) if (retval) return retval; - if (mousedev->is_mixdev) - mixdev_open_devices(); - else if (!mousedev->exist) + if (!mousedev->exist) retval = -ENODEV; else if (!mousedev->open++) { retval = input_open_device(&mousedev->handle); @@ -446,9 +443,7 @@ static void mousedev_close_device(struct mousedev *mousedev) { mutex_lock(&mousedev->mutex); - if (mousedev->is_mixdev) - mixdev_close_devices(); - else if (mousedev->exist && !--mousedev->open) + if (mousedev->exist && !--mousedev->open) input_close_device(&mousedev->handle); mutex_unlock(&mousedev->mutex); @@ -459,21 +454,29 @@ static void mousedev_close_device(struct mousedev *mousedev) * stream. Note that this function is called with mousedev_mix->mutex * held. */ -static void mixdev_open_devices(void) +static int mixdev_open_devices(struct mousedev *mixdev) { - struct mousedev *mousedev; + int error; + + error = mutex_lock_interruptible(&mixdev->mutex); + if (error) + return error; - if (mousedev_mix->open++) - return; + if (!mixdev->open++) { + struct mousedev *mousedev; - list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) { - if (!mousedev->opened_by_mixdev) { - if (mousedev_open_device(mousedev)) - continue; + list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) { + if (!mousedev->opened_by_mixdev) { + if (mousedev_open_device(mousedev)) + continue; - mousedev->opened_by_mixdev = true; + mousedev->opened_by_mixdev = true; + } } } + + mutex_unlock(&mixdev->mutex); + return 0; } /* @@ -481,19 +484,22 @@ static void mixdev_open_devices(void) * device. Note that this function is called with mousedev_mix->mutex * held. */ -static void mixdev_close_devices(void) +static void mixdev_close_devices(struct mousedev *mixdev) { - struct mousedev *mousedev; + mutex_lock(&mixdev->mutex); - if (--mousedev_mix->open) - return; + if (!--mixdev->open) { + struct mousedev *mousedev; - list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) { - if (mousedev->opened_by_mixdev) { - mousedev->opened_by_mixdev = false; - mousedev_close_device(mousedev); + list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) { + if (mousedev->opened_by_mixdev) { + mousedev->opened_by_mixdev = false; + mousedev_close_device(mousedev); + } } } + + mutex_unlock(&mixdev->mutex); } @@ -522,7 +528,7 @@ static int mousedev_release(struct inode *inode, struct file *file) mousedev_detach_client(mousedev, client); kfree(client); - mousedev_close_device(mousedev); + mousedev->close_device(mousedev); return 0; } @@ -550,7 +556,7 @@ static int mousedev_open(struct inode *inode, struct file *file) client->mousedev = mousedev; mousedev_attach_client(mousedev, client); - error = mousedev_open_device(mousedev); + error = mousedev->open_device(mousedev); if (error) goto err_free_client; @@ -861,16 +867,21 @@ static struct mousedev *mousedev_create(struct input_dev *dev, if (mixdev) { dev_set_name(&mousedev->dev, "mice"); + + mousedev->open_device = mixdev_open_devices; + mousedev->close_device = mixdev_close_devices; } else { int dev_no = minor; /* Normalize device number if it falls into legacy range */ if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS) dev_no -= MOUSEDEV_MINOR_BASE; dev_set_name(&mousedev->dev, "mouse%d", dev_no); + + mousedev->open_device = mousedev_open_device; + mousedev->close_device = mousedev_close_device; } mousedev->exist = true; - mousedev->is_mixdev = mixdev; mousedev->handle.dev = input_get_device(dev); mousedev->handle.name = dev_name(&mousedev->dev); mousedev->handle.handler = handler; @@ -919,7 +930,7 @@ static void mousedev_destroy(struct mousedev *mousedev) device_del(&mousedev->dev); mousedev_cleanup(mousedev); input_free_minor(MINOR(mousedev->dev.devt)); - if (!mousedev->is_mixdev) + if (mousedev != mousedev_mix) input_unregister_handle(&mousedev->handle); put_device(&mousedev->dev); } diff --git a/drivers/isdn/capi/Kconfig b/drivers/isdn/capi/Kconfig index f04686580040..9816c51eb5c2 100644 --- a/drivers/isdn/capi/Kconfig +++ b/drivers/isdn/capi/Kconfig @@ -16,9 +16,17 @@ config CAPI_TRACE This will increase the size of the kernelcapi module by 20 KB. If unsure, say Y. +config ISDN_CAPI_CAPI20 + tristate "CAPI2.0 /dev/capi support" + help + This option will provide the CAPI 2.0 interface to userspace + applications via /dev/capi20. Applications should use the + standardized libcapi20 to access this functionality. You should say + Y/M here. + config ISDN_CAPI_MIDDLEWARE bool "CAPI2.0 Middleware support" - depends on TTY + depends on ISDN_CAPI_CAPI20 && TTY help This option will enhance the capabilities of the /dev/capi20 interface. It will provide a means of moving a data connection, @@ -26,14 +34,6 @@ config ISDN_CAPI_MIDDLEWARE device. If you want to use pppd with pppdcapiplugin to dial up to your ISP, say Y here. -config ISDN_CAPI_CAPI20 - tristate "CAPI2.0 /dev/capi support" - help - This option will provide the CAPI 2.0 interface to userspace - applications via /dev/capi20. Applications should use the - standardized libcapi20 to access this functionality. You should say - Y/M here. - config ISDN_CAPI_CAPIDRV tristate "CAPI2.0 capidrv interface support" depends on ISDN_I4L diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 9a06fe883766..95ad936e6048 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -254,16 +254,6 @@ config DM_THIN_PROVISIONING ---help--- Provides thin provisioning and snapshots that share a data store. -config DM_DEBUG_BLOCK_STACK_TRACING - boolean "Keep stack trace of persistent data block lock holders" - depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA - select STACKTRACE - ---help--- - Enable this for messages that may help debug problems with the - block manager locking used by thin provisioning and caching. - - If unsure, say N. - config DM_CACHE tristate "Cache target (EXPERIMENTAL)" depends on BLK_DEV_DM diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c index 1e018e986610..0e385e40909e 100644 --- a/drivers/md/dm-cache-policy-mq.c +++ b/drivers/md/dm-cache-policy-mq.c @@ -872,7 +872,7 @@ static void mq_destroy(struct dm_cache_policy *p) { struct mq_policy *mq = to_mq_policy(p); - kfree(mq->table); + vfree(mq->table); epool_exit(&mq->cache_pool); epool_exit(&mq->pre_cache_pool); kfree(mq); @@ -1245,7 +1245,7 @@ static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16); mq->hash_bits = ffs(mq->nr_buckets) - 1; - mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL); + mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets); if (!mq->table) goto bad_alloc_table; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 1af70145fab9..074b9c8e4cf0 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -979,12 +979,13 @@ static void issue_copy_real(struct dm_cache_migration *mg) int r; struct dm_io_region o_region, c_region; struct cache *cache = mg->cache; + sector_t cblock = from_cblock(mg->cblock); o_region.bdev = cache->origin_dev->bdev; o_region.count = cache->sectors_per_block; c_region.bdev = cache->cache_dev->bdev; - c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block; + c_region.sector = cblock * cache->sectors_per_block; c_region.count = cache->sectors_per_block; if (mg->writeback || mg->demote) { @@ -2464,20 +2465,18 @@ static int cache_map(struct dm_target *ti, struct bio *bio) bool discarded_block; struct dm_bio_prison_cell *cell; struct policy_result lookup_result; - struct per_bio_data *pb; + struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size); - if (from_oblock(block) > from_oblock(cache->origin_blocks)) { + if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) { /* * This can only occur if the io goes to a partial block at * the end of the origin device. We don't cache these. * Just remap to the origin and carry on. */ - remap_to_origin_clear_discard(cache, bio, block); + remap_to_origin(cache, bio); return DM_MAPIO_REMAPPED; } - pb = init_per_bio_data(bio, pb_data_size); - if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) { defer_bio(cache, bio); return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index afc3d017de4c..d6e88178d22c 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -546,6 +546,9 @@ static int read_exceptions(struct pstore *ps, r = insert_exceptions(ps, area, callback, callback_context, &full); + if (!full) + memcpy(ps->area, area, ps->store->chunk_size << SECTOR_SHIFT); + dm_bufio_release(bp); dm_bufio_forget(client, chunk); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index baa87ff12816..fb9efc829182 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -76,7 +76,7 @@ #define THIN_SUPERBLOCK_MAGIC 27022010 #define THIN_SUPERBLOCK_LOCATION 0 -#define THIN_VERSION 1 +#define THIN_VERSION 2 #define THIN_METADATA_CACHE_SIZE 64 #define SECTOR_TO_BLOCK_SHIFT 3 @@ -1755,3 +1755,38 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd, return r; } + +int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd) +{ + int r; + struct dm_block *sblock; + struct thin_disk_superblock *disk_super; + + down_write(&pmd->root_lock); + pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG; + + r = superblock_lock(pmd, &sblock); + if (r) { + DMERR("couldn't read superblock"); + goto out; + } + + disk_super = dm_block_data(sblock); + disk_super->flags = cpu_to_le32(pmd->flags); + + dm_bm_unlock(sblock); +out: + up_write(&pmd->root_lock); + return r; +} + +bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd) +{ + bool needs_check; + + down_read(&pmd->root_lock); + needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG; + up_read(&pmd->root_lock); + + return needs_check; +} diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index 82ea384d36ff..e3c857db195a 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -25,6 +25,11 @@ /*----------------------------------------------------------------*/ +/* + * Thin metadata superblock flags. + */ +#define THIN_METADATA_NEEDS_CHECK_FLAG (1 << 0) + struct dm_pool_metadata; struct dm_thin_device; @@ -202,6 +207,12 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd, dm_sm_threshold_fn fn, void *context); +/* + * Updates the superblock immediately. + */ +int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd); +bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd); + /*----------------------------------------------------------------*/ #endif diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 7e84baccf0ad..be70d38745f7 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -130,10 +130,11 @@ static void build_virtual_key(struct dm_thin_device *td, dm_block_t b, struct dm_thin_new_mapping; /* - * The pool runs in 3 modes. Ordered in degraded order for comparisons. + * The pool runs in 4 modes. Ordered in degraded order for comparisons. */ enum pool_mode { PM_WRITE, /* metadata may be changed */ + PM_OUT_OF_DATA_SPACE, /* metadata may be changed, though data may not be allocated */ PM_READ_ONLY, /* metadata may not be changed */ PM_FAIL, /* all I/O fails */ }; @@ -198,7 +199,6 @@ struct pool { }; static enum pool_mode get_pool_mode(struct pool *pool); -static void out_of_data_space(struct pool *pool); static void metadata_operation_failed(struct pool *pool, const char *op, int r); /* @@ -226,6 +226,7 @@ struct thin_c { struct pool *pool; struct dm_thin_device *td; + bool requeue_mode:1; }; /*----------------------------------------------------------------*/ @@ -369,14 +370,18 @@ struct dm_thin_endio_hook { struct dm_thin_new_mapping *overwrite_mapping; }; -static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master) +static void requeue_bio_list(struct thin_c *tc, struct bio_list *master) { struct bio *bio; struct bio_list bios; + unsigned long flags; bio_list_init(&bios); + + spin_lock_irqsave(&tc->pool->lock, flags); bio_list_merge(&bios, master); bio_list_init(master); + spin_unlock_irqrestore(&tc->pool->lock, flags); while ((bio = bio_list_pop(&bios))) { struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook)); @@ -391,12 +396,26 @@ static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master) static void requeue_io(struct thin_c *tc) { struct pool *pool = tc->pool; + + requeue_bio_list(tc, &pool->deferred_bios); + requeue_bio_list(tc, &pool->retry_on_resume_list); +} + +static void error_retry_list(struct pool *pool) +{ + struct bio *bio; unsigned long flags; + struct bio_list bios; + + bio_list_init(&bios); spin_lock_irqsave(&pool->lock, flags); - __requeue_bio_list(tc, &pool->deferred_bios); - __requeue_bio_list(tc, &pool->retry_on_resume_list); + bio_list_merge(&bios, &pool->retry_on_resume_list); + bio_list_init(&pool->retry_on_resume_list); spin_unlock_irqrestore(&pool->lock, flags); + + while ((bio = bio_list_pop(&bios))) + bio_io_error(bio); } /* @@ -925,13 +944,15 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks) } } +static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); + static int alloc_data_block(struct thin_c *tc, dm_block_t *result) { int r; dm_block_t free_blocks; struct pool *pool = tc->pool; - if (get_pool_mode(pool) != PM_WRITE) + if (WARN_ON(get_pool_mode(pool) != PM_WRITE)) return -EINVAL; r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); @@ -958,7 +979,7 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) } if (!free_blocks) { - out_of_data_space(pool); + set_pool_mode(pool, PM_OUT_OF_DATA_SPACE); return -ENOSPC; } } @@ -988,15 +1009,32 @@ static void retry_on_resume(struct bio *bio) spin_unlock_irqrestore(&pool->lock, flags); } -static void handle_unserviceable_bio(struct pool *pool, struct bio *bio) +static bool should_error_unserviceable_bio(struct pool *pool) { - /* - * When pool is read-only, no cell locking is needed because - * nothing is changing. - */ - WARN_ON_ONCE(get_pool_mode(pool) != PM_READ_ONLY); + enum pool_mode m = get_pool_mode(pool); + + switch (m) { + case PM_WRITE: + /* Shouldn't get here */ + DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode"); + return true; + + case PM_OUT_OF_DATA_SPACE: + return pool->pf.error_if_no_space; - if (pool->pf.error_if_no_space) + case PM_READ_ONLY: + case PM_FAIL: + return true; + default: + /* Shouldn't get here */ + DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode"); + return true; + } +} + +static void handle_unserviceable_bio(struct pool *pool, struct bio *bio) +{ + if (should_error_unserviceable_bio(pool)) bio_io_error(bio); else retry_on_resume(bio); @@ -1007,11 +1045,20 @@ static void retry_bios_on_resume(struct pool *pool, struct dm_bio_prison_cell *c struct bio *bio; struct bio_list bios; + if (should_error_unserviceable_bio(pool)) { + cell_error(pool, cell); + return; + } + bio_list_init(&bios); cell_release(pool, cell, &bios); - while ((bio = bio_list_pop(&bios))) - handle_unserviceable_bio(pool, bio); + if (should_error_unserviceable_bio(pool)) + while ((bio = bio_list_pop(&bios))) + bio_io_error(bio); + else + while ((bio = bio_list_pop(&bios))) + retry_on_resume(bio); } static void process_discard(struct thin_c *tc, struct bio *bio) @@ -1296,6 +1343,11 @@ static void process_bio_read_only(struct thin_c *tc, struct bio *bio) } } +static void process_bio_success(struct thin_c *tc, struct bio *bio) +{ + bio_endio(bio, 0); +} + static void process_bio_fail(struct thin_c *tc, struct bio *bio) { bio_io_error(bio); @@ -1328,6 +1380,11 @@ static void process_deferred_bios(struct pool *pool) struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook)); struct thin_c *tc = h->tc; + if (tc->requeue_mode) { + bio_endio(bio, DM_ENDIO_REQUEUE); + continue; + } + /* * If we've got no free new_mapping structs, and processing * this bio might require one, we pause until there are some @@ -1394,51 +1451,134 @@ static void do_waker(struct work_struct *ws) /*----------------------------------------------------------------*/ +struct noflush_work { + struct work_struct worker; + struct thin_c *tc; + + atomic_t complete; + wait_queue_head_t wait; +}; + +static void complete_noflush_work(struct noflush_work *w) +{ + atomic_set(&w->complete, 1); + wake_up(&w->wait); +} + +static void do_noflush_start(struct work_struct *ws) +{ + struct noflush_work *w = container_of(ws, struct noflush_work, worker); + w->tc->requeue_mode = true; + requeue_io(w->tc); + complete_noflush_work(w); +} + +static void do_noflush_stop(struct work_struct *ws) +{ + struct noflush_work *w = container_of(ws, struct noflush_work, worker); + w->tc->requeue_mode = false; + complete_noflush_work(w); +} + +static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *)) +{ + struct noflush_work w; + + INIT_WORK(&w.worker, fn); + w.tc = tc; + atomic_set(&w.complete, 0); + init_waitqueue_head(&w.wait); + + queue_work(tc->pool->wq, &w.worker); + + wait_event(w.wait, atomic_read(&w.complete)); +} + +/*----------------------------------------------------------------*/ + static enum pool_mode get_pool_mode(struct pool *pool) { return pool->pf.mode; } +static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode) +{ + dm_table_event(pool->ti->table); + DMINFO("%s: switching pool to %s mode", + dm_device_name(pool->pool_md), new_mode); +} + static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) { - int r; - enum pool_mode old_mode = pool->pf.mode; + struct pool_c *pt = pool->ti->private; + bool needs_check = dm_pool_metadata_needs_check(pool->pmd); + enum pool_mode old_mode = get_pool_mode(pool); + + /* + * Never allow the pool to transition to PM_WRITE mode if user + * intervention is required to verify metadata and data consistency. + */ + if (new_mode == PM_WRITE && needs_check) { + DMERR("%s: unable to switch pool to write mode until repaired.", + dm_device_name(pool->pool_md)); + if (old_mode != new_mode) + new_mode = old_mode; + else + new_mode = PM_READ_ONLY; + } + /* + * If we were in PM_FAIL mode, rollback of metadata failed. We're + * not going to recover without a thin_repair. So we never let the + * pool move out of the old mode. + */ + if (old_mode == PM_FAIL) + new_mode = old_mode; switch (new_mode) { case PM_FAIL: if (old_mode != new_mode) - DMERR("%s: switching pool to failure mode", - dm_device_name(pool->pool_md)); + notify_of_pool_mode_change(pool, "failure"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_fail; pool->process_discard = process_bio_fail; pool->process_prepared_mapping = process_prepared_mapping_fail; pool->process_prepared_discard = process_prepared_discard_fail; + + error_retry_list(pool); break; case PM_READ_ONLY: if (old_mode != new_mode) - DMERR("%s: switching pool to read-only mode", - dm_device_name(pool->pool_md)); - r = dm_pool_abort_metadata(pool->pmd); - if (r) { - DMERR("%s: aborting transaction failed", - dm_device_name(pool->pool_md)); - new_mode = PM_FAIL; - set_pool_mode(pool, new_mode); - } else { - dm_pool_metadata_read_only(pool->pmd); - pool->process_bio = process_bio_read_only; - pool->process_discard = process_discard; - pool->process_prepared_mapping = process_prepared_mapping_fail; - pool->process_prepared_discard = process_prepared_discard_passdown; - } + notify_of_pool_mode_change(pool, "read-only"); + dm_pool_metadata_read_only(pool->pmd); + pool->process_bio = process_bio_read_only; + pool->process_discard = process_bio_success; + pool->process_prepared_mapping = process_prepared_mapping_fail; + pool->process_prepared_discard = process_prepared_discard_passdown; + + error_retry_list(pool); + break; + + case PM_OUT_OF_DATA_SPACE: + /* + * Ideally we'd never hit this state; the low water mark + * would trigger userland to extend the pool before we + * completely run out of data space. However, many small + * IOs to unprovisioned space can consume data space at an + * alarming rate. Adjust your low water mark if you're + * frequently seeing this mode. + */ + if (old_mode != new_mode) + notify_of_pool_mode_change(pool, "out-of-data-space"); + pool->process_bio = process_bio_read_only; + pool->process_discard = process_discard; + pool->process_prepared_mapping = process_prepared_mapping; + pool->process_prepared_discard = process_prepared_discard_passdown; break; case PM_WRITE: if (old_mode != new_mode) - DMINFO("%s: switching pool to write mode", - dm_device_name(pool->pool_md)); + notify_of_pool_mode_change(pool, "write"); dm_pool_metadata_read_write(pool->pmd); pool->process_bio = process_bio; pool->process_discard = process_discard; @@ -1448,32 +1588,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) } pool->pf.mode = new_mode; + /* + * The pool mode may have changed, sync it so bind_control_target() + * doesn't cause an unexpected mode transition on resume. + */ + pt->adjusted_pf.mode = new_mode; } -/* - * Rather than calling set_pool_mode directly, use these which describe the - * reason for mode degradation. - */ -static void out_of_data_space(struct pool *pool) +static void abort_transaction(struct pool *pool) { - DMERR_LIMIT("%s: no free data space available.", - dm_device_name(pool->pool_md)); - set_pool_mode(pool, PM_READ_ONLY); + const char *dev_name = dm_device_name(pool->pool_md); + + DMERR_LIMIT("%s: aborting current metadata transaction", dev_name); + if (dm_pool_abort_metadata(pool->pmd)) { + DMERR("%s: failed to abort metadata transaction", dev_name); + set_pool_mode(pool, PM_FAIL); + } + + if (dm_pool_metadata_set_needs_check(pool->pmd)) { + DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name); + set_pool_mode(pool, PM_FAIL); + } } static void metadata_operation_failed(struct pool *pool, const char *op, int r) { - dm_block_t free_blocks; - DMERR_LIMIT("%s: metadata operation '%s' failed: error = %d", dm_device_name(pool->pool_md), op, r); - if (r == -ENOSPC && - !dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks) && - !free_blocks) - DMERR_LIMIT("%s: no free metadata space available.", - dm_device_name(pool->pool_md)); - + abort_transaction(pool); set_pool_mode(pool, PM_READ_ONLY); } @@ -1524,6 +1667,11 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) thin_hook_bio(tc, bio); + if (tc->requeue_mode) { + bio_endio(bio, DM_ENDIO_REQUEUE); + return DM_MAPIO_SUBMITTED; + } + if (get_pool_mode(tc->pool) == PM_FAIL) { bio_io_error(bio); return DM_MAPIO_SUBMITTED; @@ -1687,7 +1835,7 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti) /* * We want to make sure that a pool in PM_FAIL mode is never upgraded. */ - enum pool_mode old_mode = pool->pf.mode; + enum pool_mode old_mode = get_pool_mode(pool); enum pool_mode new_mode = pt->adjusted_pf.mode; /* @@ -1701,16 +1849,6 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti) pool->pf = pt->adjusted_pf; pool->low_water_blocks = pt->low_water_blocks; - /* - * If we were in PM_FAIL mode, rollback of metadata failed. We're - * not going to recover without a thin_repair. So we never let the - * pool move out of the old mode. On the other hand a PM_READ_ONLY - * may have been due to a lack of metadata or data space, and may - * now work (ie. if the underlying devices have been resized). - */ - if (old_mode == PM_FAIL) - new_mode = old_mode; - set_pool_mode(pool, new_mode); return 0; @@ -2253,6 +2391,12 @@ static int maybe_resize_data_dev(struct dm_target *ti, bool *need_commit) return -EINVAL; } else if (data_size > sb_data_size) { + if (dm_pool_metadata_needs_check(pool->pmd)) { + DMERR("%s: unable to grow the data device until repaired.", + dm_device_name(pool->pool_md)); + return 0; + } + if (sb_data_size) DMINFO("%s: growing the data device from %llu to %llu blocks", dm_device_name(pool->pool_md), @@ -2294,6 +2438,12 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) return -EINVAL; } else if (metadata_dev_size > sb_metadata_dev_size) { + if (dm_pool_metadata_needs_check(pool->pmd)) { + DMERR("%s: unable to grow the metadata device until repaired.", + dm_device_name(pool->pool_md)); + return 0; + } + warn_if_metadata_device_too_big(pool->md_dev); DMINFO("%s: growing the metadata device from %llu to %llu blocks", dm_device_name(pool->pool_md), @@ -2681,7 +2831,9 @@ static void pool_status(struct dm_target *ti, status_type_t type, else DMEMIT("- "); - if (pool->pf.mode == PM_READ_ONLY) + if (pool->pf.mode == PM_OUT_OF_DATA_SPACE) + DMEMIT("out_of_data_space "); + else if (pool->pf.mode == PM_READ_ONLY) DMEMIT("ro "); else DMEMIT("rw "); @@ -2795,7 +2947,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 10, 0}, + .version = {1, 11, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -2997,10 +3149,23 @@ static int thin_endio(struct dm_target *ti, struct bio *bio, int err) return 0; } -static void thin_postsuspend(struct dm_target *ti) +static void thin_presuspend(struct dm_target *ti) { + struct thin_c *tc = ti->private; + if (dm_noflush_suspending(ti)) - requeue_io((struct thin_c *)ti->private); + noflush_work(tc, do_noflush_start); +} + +static void thin_postsuspend(struct dm_target *ti) +{ + struct thin_c *tc = ti->private; + + /* + * The dm_noflush_suspending flag has been cleared by now, so + * unfortunately we must always run this. + */ + noflush_work(tc, do_noflush_stop); } /* @@ -3085,12 +3250,13 @@ static int thin_iterate_devices(struct dm_target *ti, static struct target_type thin_target = { .name = "thin", - .version = {1, 10, 0}, + .version = {1, 11, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, .map = thin_map, .end_io = thin_endio, + .presuspend = thin_presuspend, .postsuspend = thin_postsuspend, .status = thin_status, .iterate_devices = thin_iterate_devices, diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig index 19b268795415..0c2dec7aec20 100644 --- a/drivers/md/persistent-data/Kconfig +++ b/drivers/md/persistent-data/Kconfig @@ -6,3 +6,13 @@ config DM_PERSISTENT_DATA ---help--- Library providing immutable on-disk data structure support for device-mapper targets such as the thin provisioning target. + +config DM_DEBUG_BLOCK_STACK_TRACING + boolean "Keep stack trace of persistent data block lock holders" + depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA + select STACKTRACE + ---help--- + Enable this for messages that may help debug problems with the + block manager locking used by thin provisioning and caching. + + If unsure, say N. diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index e9bdd462f4f5..786b689bdfc7 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -91,6 +91,69 @@ struct block_op { dm_block_t block; }; +struct bop_ring_buffer { + unsigned begin; + unsigned end; + struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1]; +}; + +static void brb_init(struct bop_ring_buffer *brb) +{ + brb->begin = 0; + brb->end = 0; +} + +static bool brb_empty(struct bop_ring_buffer *brb) +{ + return brb->begin == brb->end; +} + +static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old) +{ + unsigned r = old + 1; + return (r >= (sizeof(brb->bops) / sizeof(*brb->bops))) ? 0 : r; +} + +static int brb_push(struct bop_ring_buffer *brb, + enum block_op_type type, dm_block_t b) +{ + struct block_op *bop; + unsigned next = brb_next(brb, brb->end); + + /* + * We don't allow the last bop to be filled, this way we can + * differentiate between full and empty. + */ + if (next == brb->begin) + return -ENOMEM; + + bop = brb->bops + brb->end; + bop->type = type; + bop->block = b; + + brb->end = next; + + return 0; +} + +static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result) +{ + struct block_op *bop; + + if (brb_empty(brb)) + return -ENODATA; + + bop = brb->bops + brb->begin; + result->type = bop->type; + result->block = bop->block; + + brb->begin = brb_next(brb, brb->begin); + + return 0; +} + +/*----------------------------------------------------------------*/ + struct sm_metadata { struct dm_space_map sm; @@ -101,25 +164,20 @@ struct sm_metadata { unsigned recursion_count; unsigned allocated_this_transaction; - unsigned nr_uncommitted; - struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS]; + struct bop_ring_buffer uncommitted; struct threshold threshold; }; static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b) { - struct block_op *op; + int r = brb_push(&smm->uncommitted, type, b); - if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) { + if (r) { DMERR("too many recursive allocations"); return -ENOMEM; } - op = smm->uncommitted + smm->nr_uncommitted++; - op->type = type; - op->block = b; - return 0; } @@ -158,11 +216,17 @@ static int out(struct sm_metadata *smm) return -ENOMEM; } - if (smm->recursion_count == 1 && smm->nr_uncommitted) { - while (smm->nr_uncommitted && !r) { - smm->nr_uncommitted--; - r = commit_bop(smm, smm->uncommitted + - smm->nr_uncommitted); + if (smm->recursion_count == 1) { + while (!brb_empty(&smm->uncommitted)) { + struct block_op bop; + + r = brb_pop(&smm->uncommitted, &bop); + if (r) { + DMERR("bug in bop ring buffer"); + break; + } + + r = commit_bop(smm, &bop); if (r) break; } @@ -217,7 +281,8 @@ static int sm_metadata_get_nr_free(struct dm_space_map *sm, dm_block_t *count) static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, uint32_t *result) { - int r, i; + int r; + unsigned i; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); unsigned adjustment = 0; @@ -225,8 +290,10 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, * We may have some uncommitted adjustments to add. This list * should always be really short. */ - for (i = 0; i < smm->nr_uncommitted; i++) { - struct block_op *op = smm->uncommitted + i; + for (i = smm->uncommitted.begin; + i != smm->uncommitted.end; + i = brb_next(&smm->uncommitted, i)) { + struct block_op *op = smm->uncommitted.bops + i; if (op->block != b) continue; @@ -254,7 +321,8 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm, dm_block_t b, int *result) { - int r, i, adjustment = 0; + int r, adjustment = 0; + unsigned i; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); uint32_t rc; @@ -262,8 +330,11 @@ static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm, * We may have some uncommitted adjustments to add. This list * should always be really short. */ - for (i = 0; i < smm->nr_uncommitted; i++) { - struct block_op *op = smm->uncommitted + i; + for (i = smm->uncommitted.begin; + i != smm->uncommitted.end; + i = brb_next(&smm->uncommitted, i)) { + + struct block_op *op = smm->uncommitted.bops + i; if (op->block != b) continue; @@ -671,7 +742,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm, smm->begin = superblock + 1; smm->recursion_count = 0; smm->allocated_this_transaction = 0; - smm->nr_uncommitted = 0; + brb_init(&smm->uncommitted); threshold_init(&smm->threshold); memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm)); @@ -715,7 +786,7 @@ int dm_sm_metadata_open(struct dm_space_map *sm, smm->begin = 0; smm->recursion_count = 0; smm->allocated_this_transaction = 0; - smm->nr_uncommitted = 0; + brb_init(&smm->uncommitted); threshold_init(&smm->threshold); memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index b9e2000969f0..95c894482fdd 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -240,7 +240,7 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name, nid = cpu_to_node(cpu); page = alloc_pages_exact_node(nid, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, pg_order); if (page == NULL) { dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d " diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 6d20fbde8d43..dcde56057fe1 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -181,7 +181,7 @@ static inline int __agg_has_partner(struct aggregator *agg) */ static inline void __disable_port(struct port *port) { - bond_set_slave_inactive_flags(port->slave); + bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); } /** @@ -193,7 +193,7 @@ static inline void __enable_port(struct port *port) struct slave *slave = port->slave; if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev)) - bond_set_slave_active_flags(slave); + bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER); } /** @@ -2062,6 +2062,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) struct list_head *iter; struct slave *slave; struct port *port; + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; read_lock(&bond->lock); rcu_read_lock(); @@ -2119,8 +2120,19 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } re_arm: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } rcu_read_unlock(); read_unlock(&bond->lock); + + if (should_notify_rtnl && rtnl_trylock()) { + bond_slave_state_notify(bond); + rtnl_unlock(); + } queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index a2c47476804d..e8f133e926aa 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -730,7 +730,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon client_info->ntt = 0; } - if (!vlan_get_tag(skb, &client_info->vlan_id)) + if (vlan_get_tag(skb, &client_info->vlan_id)) client_info->vlan_id = 0; if (!client_info->assigned) { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1c6104d3501d..e5628fc725c3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -829,21 +829,25 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); } else { rcu_assign_pointer(bond->curr_active_slave, new_active); } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, @@ -1193,6 +1197,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) return -EBUSY; } + if (bond_dev == slave_dev) { + pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name); + return -EPERM; + } + /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { @@ -1463,14 +1472,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) switch (bond->params.mode) { case BOND_MODE_ACTIVEBACKUP: - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, + BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ if (!prev_slave) { SLAVE_AD_INFO(new_slave).id = 1; @@ -1488,7 +1498,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: pr_debug("This slave is always active in trunk mode\n"); @@ -1654,9 +1664,6 @@ static int __bond_release_one(struct net_device *bond_dev, return -EINVAL; } - /* release the slave from its bond */ - bond->slave_cnt--; - bond_sysfs_slave_del(slave); bond_upper_dev_unlink(bond_dev, slave_dev); @@ -1738,6 +1745,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); + bond->slave_cnt--; if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -2015,7 +2023,8 @@ static void bond_miimon_commit(struct bonding *bond) if (bond->params.mode == BOND_MODE_ACTIVEBACKUP || bond->params.mode == BOND_MODE_8023AD) - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); @@ -2562,7 +2571,8 @@ static void bond_ab_arp_commit(struct bonding *bond) slave->link = BOND_LINK_UP; if (bond->current_arp_slave) { bond_set_slave_inactive_flags( - bond->current_arp_slave); + bond->current_arp_slave, + BOND_SLAVE_NOTIFY_NOW); bond->current_arp_slave = NULL; } @@ -2582,7 +2592,8 @@ static void bond_ab_arp_commit(struct bonding *bond) slave->link_failure_count++; slave->link = BOND_LINK_DOWN; - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); @@ -2615,17 +2626,17 @@ do_failover: /* * Send ARP probes for active-backup mode ARP monitor. + * + * Called with rcu_read_lock hold. */ static bool bond_ab_arp_probe(struct bonding *bond) { struct slave *slave, *before = NULL, *new_slave = NULL, - *curr_arp_slave, *curr_active_slave; + *curr_arp_slave = rcu_dereference(bond->current_arp_slave), + *curr_active_slave = rcu_dereference(bond->curr_active_slave); struct list_head *iter; bool found = false; - - rcu_read_lock(); - curr_arp_slave = rcu_dereference(bond->current_arp_slave); - curr_active_slave = rcu_dereference(bond->curr_active_slave); + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; if (curr_arp_slave && curr_active_slave) pr_info("PROBE: c_arp %s && cas %s BAD\n", @@ -2634,32 +2645,23 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (curr_active_slave) { bond_arp_send_all(bond, curr_active_slave); - rcu_read_unlock(); - return true; + return should_notify_rtnl; } - rcu_read_unlock(); /* if we don't have a curr_active_slave, search for the next available * backup slave from the current_arp_slave and make it the candidate * for becoming the curr_active_slave */ - if (!rtnl_trylock()) - return false; - /* curr_arp_slave might have gone away */ - curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave); - if (!curr_arp_slave) { - curr_arp_slave = bond_first_slave(bond); - if (!curr_arp_slave) { - rtnl_unlock(); - return true; - } + curr_arp_slave = bond_first_slave_rcu(bond); + if (!curr_arp_slave) + return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave); + bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave(bond, slave, iter) { + bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && IS_UP(slave->dev)) before = slave; @@ -2677,7 +2679,8 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_LATER); pr_info("%s: backup interface %s is now down.\n", bond->dev->name, slave->dev->name); @@ -2689,26 +2692,31 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (!new_slave && before) new_slave = before; - if (!new_slave) { - rtnl_unlock(); - return true; - } + if (!new_slave) + goto check_state; new_slave->link = BOND_LINK_BACK; - bond_set_slave_active_flags(new_slave); + bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_arp_send_all(bond, new_slave); new_slave->jiffies = jiffies; rcu_assign_pointer(bond->current_arp_slave, new_slave); - rtnl_unlock(); - return true; +check_state: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } + return should_notify_rtnl; } static void bond_activebackup_arp_mon(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); - bool should_notify_peers = false, should_commit = false; + bool should_notify_peers = false; + bool should_notify_rtnl = false; int delta_in_ticks; delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); @@ -2717,11 +2725,12 @@ static void bond_activebackup_arp_mon(struct work_struct *work) goto re_arm; rcu_read_lock(); + should_notify_peers = bond_should_notify_peers(bond); - should_commit = bond_ab_arp_inspect(bond); - rcu_read_unlock(); - if (should_commit) { + if (bond_ab_arp_inspect(bond)) { + rcu_read_unlock(); + /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { delta_in_ticks = 1; @@ -2730,23 +2739,28 @@ static void bond_activebackup_arp_mon(struct work_struct *work) } bond_ab_arp_commit(bond); + rtnl_unlock(); + rcu_read_lock(); } - if (!bond_ab_arp_probe(bond)) { - /* rtnl locking failed, re-arm */ - delta_in_ticks = 1; - should_notify_peers = false; - } + should_notify_rtnl = bond_ab_arp_probe(bond); + rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - if (should_notify_peers) { + if (should_notify_peers || should_notify_rtnl) { if (!rtnl_trylock()) return; - call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); + + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); + if (should_notify_rtnl) + bond_slave_state_notify(bond); + rtnl_unlock(); } } @@ -3046,9 +3060,11 @@ static int bond_open(struct net_device *bond_dev) bond_for_each_slave(bond, slave, iter) { if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) && (slave != bond->curr_active_slave)) { - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } else { - bond_set_slave_active_flags(slave); + bond_set_slave_active_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } } read_unlock(&bond->curr_slave_lock); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index c37878432717..298c26509095 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -121,6 +121,7 @@ static struct bond_opt_value bond_resend_igmp_tbl[] = { static struct bond_opt_value bond_lp_interval_tbl[] = { { "minval", 1, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT}, { "maxval", INT_MAX, BOND_VALFLAG_MAX}, + { NULL, -1, 0}, }; static struct bond_option bond_opts[] = { diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 86ccfb9f71cc..2b0fdec695f7 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -195,7 +195,8 @@ struct slave { s8 new_link; u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ - inactive:1; /* indicates inactive slave */ + inactive:1, /* indicates inactive slave */ + should_notify:1; /* indicateds whether the state changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; @@ -303,6 +304,24 @@ static inline void bond_set_backup_slave(struct slave *slave) } } +static inline void bond_set_slave_state(struct slave *slave, + int slave_state, bool notify) +{ + if (slave->backup == slave_state) + return; + + slave->backup = slave_state; + if (notify) { + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL); + slave->should_notify = 0; + } else { + if (slave->should_notify) + slave->should_notify = 0; + else + slave->should_notify = 1; + } +} + static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; @@ -316,6 +335,19 @@ static inline void bond_slave_state_change(struct bonding *bond) } } +static inline void bond_slave_state_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify) { + rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_KERNEL); + tmp->should_notify = 0; + } + } +} + static inline int bond_slave_state(struct slave *slave) { return slave->backup; @@ -343,6 +375,9 @@ static inline bool bond_is_active_slave(struct slave *slave) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) +#define BOND_SLAVE_NOTIFY_NOW true +#define BOND_SLAVE_NOTIFY_LATER false + static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { @@ -394,17 +429,19 @@ static inline void bond_netpoll_send_skb(const struct slave *slave, } #endif -static inline void bond_set_slave_inactive_flags(struct slave *slave) +static inline void bond_set_slave_inactive_flags(struct slave *slave, + bool notify) { if (!bond_is_lb(slave->bond)) - bond_set_backup_slave(slave); + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; } -static inline void bond_set_slave_active_flags(struct slave *slave) +static inline void bond_set_slave_active_flags(struct slave *slave, + bool notify) { - bond_set_active_slave(slave); + bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 320bef2dba42..61376abdab39 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -144,6 +144,8 @@ #define FLEXCAN_MB_CODE_MASK (0xf0ffffff) +#define FLEXCAN_TIMEOUT_US (50) + /* * FLEXCAN hardware feature flags * @@ -262,6 +264,22 @@ static inline void flexcan_write(u32 val, void __iomem *addr) } #endif +static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv) +{ + if (!priv->reg_xceiver) + return 0; + + return regulator_enable(priv->reg_xceiver); +} + +static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv) +{ + if (!priv->reg_xceiver) + return 0; + + return regulator_disable(priv->reg_xceiver); +} + static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, u32 reg_esr) { @@ -269,26 +287,95 @@ static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, (reg_esr & FLEXCAN_ESR_ERR_BUS); } -static inline void flexcan_chip_enable(struct flexcan_priv *priv) +static int flexcan_chip_enable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = flexcan_read(®s->mcr); reg &= ~FLEXCAN_MCR_MDIS; flexcan_write(reg, ®s->mcr); - udelay(10); + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) + return -ETIMEDOUT; + + return 0; } -static inline void flexcan_chip_disable(struct flexcan_priv *priv) +static int flexcan_chip_disable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = flexcan_read(®s->mcr); reg |= FLEXCAN_MCR_MDIS; flexcan_write(reg, ®s->mcr); + + while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + usleep_range(10, 20); + + if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_freeze(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; + u32 reg; + + reg = flexcan_read(®s->mcr); + reg |= FLEXCAN_MCR_HALT; + flexcan_write(reg, ®s->mcr); + + while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + usleep_range(100, 200); + + if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_unfreeze(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + u32 reg; + + reg = flexcan_read(®s->mcr); + reg &= ~FLEXCAN_MCR_HALT; + flexcan_write(reg, ®s->mcr); + + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_softreset(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr); + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST) + return -ETIMEDOUT; + + return 0; } static int flexcan_get_berr_counter(const struct net_device *dev, @@ -709,19 +796,14 @@ static int flexcan_chip_start(struct net_device *dev) u32 reg_mcr, reg_ctrl; /* enable module */ - flexcan_chip_enable(priv); + err = flexcan_chip_enable(priv); + if (err) + return err; /* soft reset */ - flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr); - udelay(10); - - reg_mcr = flexcan_read(®s->mcr); - if (reg_mcr & FLEXCAN_MCR_SOFTRST) { - netdev_err(dev, "Failed to softreset can module (mcr=0x%08x)\n", - reg_mcr); - err = -ENODEV; - goto out; - } + err = flexcan_chip_softreset(priv); + if (err) + goto out_chip_disable; flexcan_set_bittiming(dev); @@ -788,16 +870,14 @@ static int flexcan_chip_start(struct net_device *dev) if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES) flexcan_write(0x0, ®s->rxfgmask); - if (priv->reg_xceiver) { - err = regulator_enable(priv->reg_xceiver); - if (err) - goto out; - } + err = flexcan_transceiver_enable(priv); + if (err) + goto out_chip_disable; /* synchronize with the can bus */ - reg_mcr = flexcan_read(®s->mcr); - reg_mcr &= ~FLEXCAN_MCR_HALT; - flexcan_write(reg_mcr, ®s->mcr); + err = flexcan_chip_unfreeze(priv); + if (err) + goto out_transceiver_disable; priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -810,7 +890,9 @@ static int flexcan_chip_start(struct net_device *dev) return 0; - out: + out_transceiver_disable: + flexcan_transceiver_disable(priv); + out_chip_disable: flexcan_chip_disable(priv); return err; } @@ -825,18 +907,17 @@ static void flexcan_chip_stop(struct net_device *dev) { struct flexcan_priv *priv = netdev_priv(dev); struct flexcan_regs __iomem *regs = priv->base; - u32 reg; + + /* freeze + disable module */ + flexcan_chip_freeze(priv); + flexcan_chip_disable(priv); /* Disable all interrupts */ flexcan_write(0, ®s->imask1); + flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, + ®s->ctrl); - /* Disable + halt module */ - reg = flexcan_read(®s->mcr); - reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT; - flexcan_write(reg, ®s->mcr); - - if (priv->reg_xceiver) - regulator_disable(priv->reg_xceiver); + flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; return; @@ -866,7 +947,7 @@ static int flexcan_open(struct net_device *dev) /* start chip and queuing */ err = flexcan_chip_start(dev); if (err) - goto out_close; + goto out_free_irq; can_led_event(dev, CAN_LED_EVENT_OPEN); @@ -875,6 +956,8 @@ static int flexcan_open(struct net_device *dev) return 0; + out_free_irq: + free_irq(dev->irq, dev); out_close: close_candev(dev); out_disable_per: @@ -945,12 +1028,16 @@ static int register_flexcandev(struct net_device *dev) goto out_disable_ipg; /* select "bus clock", chip must be disabled */ - flexcan_chip_disable(priv); + err = flexcan_chip_disable(priv); + if (err) + goto out_disable_per; reg = flexcan_read(®s->ctrl); reg |= FLEXCAN_CTRL_CLK_SRC; flexcan_write(reg, ®s->ctrl); - flexcan_chip_enable(priv); + err = flexcan_chip_enable(priv); + if (err) + goto out_chip_disable; /* set freeze, halt and activate FIFO, restrict register access */ reg = flexcan_read(®s->mcr); @@ -967,14 +1054,15 @@ static int register_flexcandev(struct net_device *dev) if (!(reg & FLEXCAN_MCR_FEN)) { netdev_err(dev, "Could not enable RX FIFO, unsupported core\n"); err = -ENODEV; - goto out_disable_per; + goto out_chip_disable; } err = register_candev(dev); - out_disable_per: /* disable core and turn off clocks */ + out_chip_disable: flexcan_chip_disable(priv); + out_disable_per: clk_disable_unprepare(priv->clk_per); out_disable_ipg: clk_disable_unprepare(priv->clk_ipg); @@ -1104,9 +1192,10 @@ static int flexcan_probe(struct platform_device *pdev) static int flexcan_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct flexcan_priv *priv = netdev_priv(dev); unregister_flexcandev(dev); - + netif_napi_del(&priv->napi); free_candev(dev); return 0; @@ -1117,8 +1206,11 @@ static int flexcan_suspend(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); + int err; - flexcan_chip_disable(priv); + err = flexcan_chip_disable(priv); + if (err) + return err; if (netif_running(dev)) { netif_stop_queue(dev); @@ -1139,9 +1231,7 @@ static int flexcan_resume(struct device *device) netif_device_attach(dev); netif_start_queue(dev); } - flexcan_chip_enable(priv); - - return 0; + return flexcan_chip_enable(priv); } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 2e45f6ec1bf0..380d24922049 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1248,19 +1248,13 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * shared register for the high 32 bits, so only a single, aligned, * 4 GB physical address range can be used for descriptors. */ - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { dev_dbg(&pdev->dev, "DMA to 64-BIT addresses\n"); } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA config, aborting\n"); - goto out_pci_disable; - } + dev_err(&pdev->dev, "No usable DMA config, aborting\n"); + goto out_pci_disable; } } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index d5c2d3e912e5..422aab27ea1b 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2436,7 +2436,7 @@ err_reset: err_register: err_sw_init: err_eeprom: - iounmap(adapter->hw.hw_addr); + pci_iounmap(pdev, adapter->hw.hw_addr); err_init_netdev: err_ioremap: free_netdev(netdev); @@ -2474,7 +2474,7 @@ static void atl1e_remove(struct pci_dev *pdev) unregister_netdev(netdev); atl1e_free_ring_resources(adapter); atl1e_force_ps(&adapter->hw); - iounmap(adapter->hw.hw_addr); + pci_iounmap(pdev, adapter->hw.hw_addr); pci_release_regions(pdev); free_netdev(netdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 1f7b5aa114fa..8a7bf7dad898 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1484,6 +1484,10 @@ static int b44_open(struct net_device *dev) add_timer(&bp->timer); b44_enable_ints(bp); + + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + phy_start(bp->phydev); + netif_start_queue(dev); out: return err; @@ -1646,6 +1650,9 @@ static int b44_close(struct net_device *dev) netif_stop_queue(dev); + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + phy_stop(bp->phydev); + napi_disable(&bp->napi); del_timer_sync(&bp->timer); @@ -2222,7 +2229,12 @@ static void b44_adjust_link(struct net_device *dev) } if (status_changed) { - b44_check_phy(bp); + u32 val = br32(bp, B44_TX_CTRL); + if (bp->flags & B44_FLAG_FULL_DUPLEX) + val |= TX_CTRL_DUPLEX; + else + val &= ~TX_CTRL_DUPLEX; + bw32(bp, B44_TX_CTRL, val); phy_print_status(phydev); } } diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index cda25ac45b47..6c9e1c9bdeb8 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2507,6 +2507,7 @@ bnx2_fw_sync(struct bnx2 *bp, u32 msg_data, int ack, int silent) bp->fw_wr_seq++; msg_data |= bp->fw_wr_seq; + bp->fw_last_msg = msg_data; bnx2_shmem_wr(bp, BNX2_DRV_MB, msg_data); @@ -4000,8 +4001,23 @@ bnx2_setup_wol(struct bnx2 *bp) wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL; } - if (!(bp->flags & BNX2_FLAG_NO_WOL)) - bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg, 1, 0); + if (!(bp->flags & BNX2_FLAG_NO_WOL)) { + u32 val; + + wol_msg |= BNX2_DRV_MSG_DATA_WAIT3; + if (bp->fw_last_msg || BNX2_CHIP(bp) != BNX2_CHIP_5709) { + bnx2_fw_sync(bp, wol_msg, 1, 0); + return; + } + /* Tell firmware not to power down the PHY yet, otherwise + * the chip will take a long time to respond to MMIO reads. + */ + val = bnx2_shmem_rd(bp, BNX2_PORT_FEATURE); + bnx2_shmem_wr(bp, BNX2_PORT_FEATURE, + val | BNX2_PORT_FEATURE_ASF_ENABLED); + bnx2_fw_sync(bp, wol_msg, 1, 0); + bnx2_shmem_wr(bp, BNX2_PORT_FEATURE, val); + } } @@ -4033,9 +4049,22 @@ bnx2_set_power_state(struct bnx2 *bp, pci_power_t state) if (bp->wol) pci_set_power_state(bp->pdev, PCI_D3hot); - } else { - pci_set_power_state(bp->pdev, PCI_D3hot); + break; + + } + if (!bp->fw_last_msg && BNX2_CHIP(bp) == BNX2_CHIP_5709) { + u32 val; + + /* Tell firmware not to power down the PHY yet, + * otherwise the other port may not respond to + * MMIO reads. + */ + val = bnx2_shmem_rd(bp, BNX2_BC_STATE_CONDITION); + val &= ~BNX2_CONDITION_PM_STATE_MASK; + val |= BNX2_CONDITION_PM_STATE_UNPREP; + bnx2_shmem_wr(bp, BNX2_BC_STATE_CONDITION, val); } + pci_set_power_state(bp->pdev, PCI_D3hot); /* No more memory access after this point until * device is brought back to D0. diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/ethernet/broadcom/bnx2.h index f1cf2c44e7ed..e341bc366fa5 100644 --- a/drivers/net/ethernet/broadcom/bnx2.h +++ b/drivers/net/ethernet/broadcom/bnx2.h @@ -6900,6 +6900,7 @@ struct bnx2 { u16 fw_wr_seq; u16 fw_drv_pulse_wr_seq; + u32 fw_last_msg; int rx_max_ring; int rx_ring_size; @@ -7406,6 +7407,10 @@ struct bnx2_rv2p_fw_file { #define BNX2_CONDITION_MFW_RUN_NCSI 0x00006000 #define BNX2_CONDITION_MFW_RUN_NONE 0x0000e000 #define BNX2_CONDITION_MFW_RUN_MASK 0x0000e000 +#define BNX2_CONDITION_PM_STATE_MASK 0x00030000 +#define BNX2_CONDITION_PM_STATE_FULL 0x00030000 +#define BNX2_CONDITION_PM_STATE_PREP 0x00020000 +#define BNX2_CONDITION_PM_STATE_UNPREP 0x00010000 #define BNX2_BC_STATE_DEBUG_CMD 0x1dc #define BNX2_BC_STATE_BC_DBG_CMD_SIGNATURE 0x42440000 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 66c0df78c3ff..dbcff509dc3f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3875,7 +3875,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) xmit_type); } - /* Add the macs to the parsing BD this is a vf */ + /* Add the macs to the parsing BD if this is a vf or if + * Tx Switching is enabled. + */ if (IS_VF(bp)) { /* override GRE parameters in BD */ bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi, @@ -3887,6 +3889,11 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) &pbd_e2->data.mac_addr.dst_mid, &pbd_e2->data.mac_addr.dst_lo, eth->h_dest); + } else if (bp->flags & TX_SWITCHING) { + bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi, + &pbd_e2->data.mac_addr.dst_mid, + &pbd_e2->data.mac_addr.dst_lo, + eth->h_dest); } SET_FLAG(pbd_e2_parsing_data, diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index fcf9105a5476..09f3fefcbf9c 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1,6 +1,6 @@ /* cnic.c: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2013 Broadcom Corporation + * Copyright (c) 2006-2014 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -342,7 +342,7 @@ static int cnic_send_nlmsg(struct cnic_local *cp, u32 type, while (retry < 3) { rc = 0; rcu_read_lock(); - ulp_ops = rcu_dereference(cnic_ulp_tbl[CNIC_ULP_ISCSI]); + ulp_ops = rcu_dereference(cp->ulp_ops[CNIC_ULP_ISCSI]); if (ulp_ops) rc = ulp_ops->iscsi_nl_send_msg( cp->ulp_handle[CNIC_ULP_ISCSI], @@ -726,7 +726,7 @@ static void cnic_free_dma(struct cnic_dev *dev, struct cnic_dma *dma) for (i = 0; i < dma->num_pages; i++) { if (dma->pg_arr[i]) { - dma_free_coherent(&dev->pcidev->dev, BNX2_PAGE_SIZE, + dma_free_coherent(&dev->pcidev->dev, CNIC_PAGE_SIZE, dma->pg_arr[i], dma->pg_map_arr[i]); dma->pg_arr[i] = NULL; } @@ -785,7 +785,7 @@ static int cnic_alloc_dma(struct cnic_dev *dev, struct cnic_dma *dma, for (i = 0; i < pages; i++) { dma->pg_arr[i] = dma_alloc_coherent(&dev->pcidev->dev, - BNX2_PAGE_SIZE, + CNIC_PAGE_SIZE, &dma->pg_map_arr[i], GFP_ATOMIC); if (dma->pg_arr[i] == NULL) @@ -794,8 +794,8 @@ static int cnic_alloc_dma(struct cnic_dev *dev, struct cnic_dma *dma, if (!use_pg_tbl) return 0; - dma->pgtbl_size = ((pages * 8) + BNX2_PAGE_SIZE - 1) & - ~(BNX2_PAGE_SIZE - 1); + dma->pgtbl_size = ((pages * 8) + CNIC_PAGE_SIZE - 1) & + ~(CNIC_PAGE_SIZE - 1); dma->pgtbl = dma_alloc_coherent(&dev->pcidev->dev, dma->pgtbl_size, &dma->pgtbl_map, GFP_ATOMIC); if (dma->pgtbl == NULL) @@ -900,8 +900,8 @@ static int cnic_alloc_context(struct cnic_dev *dev) if (BNX2_CHIP(cp) == BNX2_CHIP_5709) { int i, k, arr_size; - cp->ctx_blk_size = BNX2_PAGE_SIZE; - cp->cids_per_blk = BNX2_PAGE_SIZE / 128; + cp->ctx_blk_size = CNIC_PAGE_SIZE; + cp->cids_per_blk = CNIC_PAGE_SIZE / 128; arr_size = BNX2_MAX_CID / cp->cids_per_blk * sizeof(struct cnic_ctx); cp->ctx_arr = kzalloc(arr_size, GFP_KERNEL); @@ -933,7 +933,7 @@ static int cnic_alloc_context(struct cnic_dev *dev) for (i = 0; i < cp->ctx_blks; i++) { cp->ctx_arr[i].ctx = dma_alloc_coherent(&dev->pcidev->dev, - BNX2_PAGE_SIZE, + CNIC_PAGE_SIZE, &cp->ctx_arr[i].mapping, GFP_KERNEL); if (cp->ctx_arr[i].ctx == NULL) @@ -1013,7 +1013,7 @@ static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages) if (udev->l2_ring) return 0; - udev->l2_ring_size = pages * BNX2_PAGE_SIZE; + udev->l2_ring_size = pages * CNIC_PAGE_SIZE; udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size, &udev->l2_ring_map, GFP_KERNEL | __GFP_COMP); @@ -1021,7 +1021,7 @@ static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages) return -ENOMEM; udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size; - udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size); + udev->l2_buf_size = CNIC_PAGE_ALIGN(udev->l2_buf_size); udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size, &udev->l2_buf_map, GFP_KERNEL | __GFP_COMP); @@ -1102,7 +1102,7 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo->mem[0].size = MB_GET_CID_ADDR(TX_TSS_CID + TX_MAX_TSS_RINGS + 1); uinfo->mem[1].addr = (unsigned long) cp->status_blk.gen & - PAGE_MASK; + CNIC_PAGE_MASK; if (cp->ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) uinfo->mem[1].size = BNX2_SBLK_MSIX_ALIGN_SIZE * 9; else @@ -1113,7 +1113,7 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo->mem[0].size = pci_resource_len(dev->pcidev, 0); uinfo->mem[1].addr = (unsigned long) cp->bnx2x_def_status_blk & - PAGE_MASK; + CNIC_PAGE_MASK; uinfo->mem[1].size = sizeof(*cp->bnx2x_def_status_blk); uinfo->name = "bnx2x_cnic"; @@ -1267,14 +1267,14 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) for (i = MAX_ISCSI_TBL_SZ; i < cp->max_cid_space; i++) cp->ctx_tbl[i].ulp_proto_id = CNIC_ULP_FCOE; - pages = PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) / - PAGE_SIZE; + pages = CNIC_PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) / + CNIC_PAGE_SIZE; ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0); if (ret) return -ENOMEM; - n = PAGE_SIZE / CNIC_KWQ16_DATA_SIZE; + n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE; for (i = 0, j = 0; i < cp->max_cid_space; i++) { long off = CNIC_KWQ16_DATA_SIZE * (i % n); @@ -1296,7 +1296,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) goto error; } - pages = PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / PAGE_SIZE; + pages = CNIC_PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / CNIC_PAGE_SIZE; ret = cnic_alloc_dma(dev, &cp->gbl_buf_info, pages, 0); if (ret) goto error; @@ -1466,8 +1466,8 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) cp->r2tq_size = cp->num_iscsi_tasks * BNX2X_ISCSI_MAX_PENDING_R2TS * BNX2X_ISCSI_R2TQE_SIZE; cp->hq_size = cp->num_ccells * BNX2X_ISCSI_HQ_BD_SIZE; - pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE; - hq_bds = pages * (PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE); + pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE; + hq_bds = pages * (CNIC_PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE); cp->num_cqs = req1->num_cqs; if (!dev->max_iscsi_conn) @@ -1477,9 +1477,9 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_RQ_SIZE_OFFSET(pfid), req1->rq_num_wqes); CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid), - PAGE_SIZE); + CNIC_PAGE_SIZE); CNIC_WR8(dev, BAR_TSTRORM_INTMEM + - TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT); + TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS); CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid), req1->num_tasks_per_conn); @@ -1489,9 +1489,9 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) USTORM_ISCSI_RQ_BUFFER_SIZE_OFFSET(pfid), req1->rq_buffer_size); CNIC_WR16(dev, BAR_USTRORM_INTMEM + USTORM_ISCSI_PAGE_SIZE_OFFSET(pfid), - PAGE_SIZE); + CNIC_PAGE_SIZE); CNIC_WR8(dev, BAR_USTRORM_INTMEM + - USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT); + USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS); CNIC_WR16(dev, BAR_USTRORM_INTMEM + USTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid), req1->num_tasks_per_conn); @@ -1504,9 +1504,9 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) /* init Xstorm RAM */ CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid), - PAGE_SIZE); + CNIC_PAGE_SIZE); CNIC_WR8(dev, BAR_XSTRORM_INTMEM + - XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT); + XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS); CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid), req1->num_tasks_per_conn); @@ -1519,9 +1519,9 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) /* init Cstorm RAM */ CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid), - PAGE_SIZE); + CNIC_PAGE_SIZE); CNIC_WR8(dev, BAR_CSTRORM_INTMEM + - CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT); + CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS); CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid), req1->num_tasks_per_conn); @@ -1623,18 +1623,18 @@ static int cnic_alloc_bnx2x_conn_resc(struct cnic_dev *dev, u32 l5_cid) } ctx->cid = cid; - pages = PAGE_ALIGN(cp->task_array_size) / PAGE_SIZE; + pages = CNIC_PAGE_ALIGN(cp->task_array_size) / CNIC_PAGE_SIZE; ret = cnic_alloc_dma(dev, &iscsi->task_array_info, pages, 1); if (ret) goto error; - pages = PAGE_ALIGN(cp->r2tq_size) / PAGE_SIZE; + pages = CNIC_PAGE_ALIGN(cp->r2tq_size) / CNIC_PAGE_SIZE; ret = cnic_alloc_dma(dev, &iscsi->r2tq_info, pages, 1); if (ret) goto error; - pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE; + pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE; ret = cnic_alloc_dma(dev, &iscsi->hq_info, pages, 1); if (ret) goto error; @@ -1760,7 +1760,7 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[], ictx->tstorm_st_context.iscsi.hdr_bytes_2_fetch = ISCSI_HEADER_SIZE; /* TSTORM requires the base address of RQ DB & not PTE */ ictx->tstorm_st_context.iscsi.rq_db_phy_addr.lo = - req2->rq_page_table_addr_lo & PAGE_MASK; + req2->rq_page_table_addr_lo & CNIC_PAGE_MASK; ictx->tstorm_st_context.iscsi.rq_db_phy_addr.hi = req2->rq_page_table_addr_hi; ictx->tstorm_st_context.iscsi.iscsi_conn_id = req1->iscsi_conn_id; @@ -1842,7 +1842,7 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[], /* CSTORM and USTORM initialization is different, CSTORM requires * CQ DB base & not PTE addr */ ictx->cstorm_st_context.cq_db_base.lo = - req1->cq_page_table_addr_lo & PAGE_MASK; + req1->cq_page_table_addr_lo & CNIC_PAGE_MASK; ictx->cstorm_st_context.cq_db_base.hi = req1->cq_page_table_addr_hi; ictx->cstorm_st_context.iscsi_conn_id = req1->iscsi_conn_id; ictx->cstorm_st_context.cq_proc_en_bit_map = (1 << cp->num_cqs) - 1; @@ -2911,7 +2911,7 @@ static int cnic_l2_completion(struct cnic_local *cp) u16 hw_cons, sw_cons; struct cnic_uio_dev *udev = cp->udev; union eth_rx_cqe *cqe, *cqe_ring = (union eth_rx_cqe *) - (udev->l2_ring + (2 * BNX2_PAGE_SIZE)); + (udev->l2_ring + (2 * CNIC_PAGE_SIZE)); u32 cmd; int comp = 0; @@ -3244,7 +3244,8 @@ static int cnic_copy_ulp_stats(struct cnic_dev *dev, int ulp_type) int rc; mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl_prot(ulp_type); + ulp_ops = rcu_dereference_protected(cp->ulp_ops[ulp_type], + lockdep_is_held(&cnic_lock)); if (ulp_ops && ulp_ops->cnic_get_stats) rc = ulp_ops->cnic_get_stats(cp->ulp_handle[ulp_type]); else @@ -4384,7 +4385,7 @@ static int cnic_setup_5709_context(struct cnic_dev *dev, int valid) u32 idx = cp->ctx_arr[i].cid / cp->cids_per_blk; u32 val; - memset(cp->ctx_arr[i].ctx, 0, BNX2_PAGE_SIZE); + memset(cp->ctx_arr[i].ctx, 0, CNIC_PAGE_SIZE); CNIC_WR(dev, BNX2_CTX_HOST_PAGE_TBL_DATA0, (cp->ctx_arr[i].mapping & 0xffffffff) | valid_bit); @@ -4628,7 +4629,7 @@ static void cnic_init_bnx2_rx_ring(struct cnic_dev *dev) val = BNX2_L2CTX_L2_STATUSB_NUM(sb_id); cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_HOST_BDIDX, val); - rxbd = udev->l2_ring + BNX2_PAGE_SIZE; + rxbd = udev->l2_ring + CNIC_PAGE_SIZE; for (i = 0; i < BNX2_MAX_RX_DESC_CNT; i++, rxbd++) { dma_addr_t buf_map; int n = (i % cp->l2_rx_ring_size) + 1; @@ -4639,11 +4640,11 @@ static void cnic_init_bnx2_rx_ring(struct cnic_dev *dev) rxbd->rx_bd_haddr_hi = (u64) buf_map >> 32; rxbd->rx_bd_haddr_lo = (u64) buf_map & 0xffffffff; } - val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32; + val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32; cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_HI, val); rxbd->rx_bd_haddr_hi = val; - val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff; + val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff; cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_LO, val); rxbd->rx_bd_haddr_lo = val; @@ -4709,10 +4710,10 @@ static int cnic_start_bnx2_hw(struct cnic_dev *dev) val = CNIC_RD(dev, BNX2_MQ_CONFIG); val &= ~BNX2_MQ_CONFIG_KNL_BYP_BLK_SIZE; - if (BNX2_PAGE_BITS > 12) + if (CNIC_PAGE_BITS > 12) val |= (12 - 8) << 4; else - val |= (BNX2_PAGE_BITS - 8) << 4; + val |= (CNIC_PAGE_BITS - 8) << 4; CNIC_WR(dev, BNX2_MQ_CONFIG, val); @@ -4742,13 +4743,13 @@ static int cnic_start_bnx2_hw(struct cnic_dev *dev) /* Initialize the kernel work queue context. */ val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE | - (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ; + (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ; cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_TYPE, val); - val = (BNX2_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16; + val = (CNIC_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16; cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val); - val = ((BNX2_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT; + val = ((CNIC_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT; cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val); val = (u32) ((u64) cp->kwq_info.pgtbl_map >> 32); @@ -4768,13 +4769,13 @@ static int cnic_start_bnx2_hw(struct cnic_dev *dev) /* Initialize the kernel complete queue context. */ val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE | - (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ; + (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ; cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_TYPE, val); - val = (BNX2_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16; + val = (CNIC_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16; cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val); - val = ((BNX2_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT; + val = ((CNIC_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT; cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val); val = (u32) ((u64) cp->kcq1.dma.pgtbl_map >> 32); @@ -4918,7 +4919,7 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev, u32 cli = cp->ethdev->iscsi_l2_client_id; u32 val; - memset(txbd, 0, BNX2_PAGE_SIZE); + memset(txbd, 0, CNIC_PAGE_SIZE); buf_map = udev->l2_buf_map; for (i = 0; i < BNX2_MAX_TX_DESC_CNT; i += 3, txbd += 3) { @@ -4978,9 +4979,9 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev, struct bnx2x *bp = netdev_priv(dev->netdev); struct cnic_uio_dev *udev = cp->udev; struct eth_rx_bd *rxbd = (struct eth_rx_bd *) (udev->l2_ring + - BNX2_PAGE_SIZE); + CNIC_PAGE_SIZE); struct eth_rx_cqe_next_page *rxcqe = (struct eth_rx_cqe_next_page *) - (udev->l2_ring + (2 * BNX2_PAGE_SIZE)); + (udev->l2_ring + (2 * CNIC_PAGE_SIZE)); struct host_sp_status_block *sb = cp->bnx2x_def_status_blk; int i; u32 cli = cp->ethdev->iscsi_l2_client_id; @@ -5004,20 +5005,20 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev, rxbd->addr_lo = cpu_to_le32(buf_map & 0xffffffff); } - val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32; + val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32; rxbd->addr_hi = cpu_to_le32(val); data->rx.bd_page_base.hi = cpu_to_le32(val); - val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff; + val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff; rxbd->addr_lo = cpu_to_le32(val); data->rx.bd_page_base.lo = cpu_to_le32(val); rxcqe += BNX2X_MAX_RCQ_DESC_CNT; - val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) >> 32; + val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) >> 32; rxcqe->addr_hi = cpu_to_le32(val); data->rx.cqe_page_base.hi = cpu_to_le32(val); - val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) & 0xffffffff; + val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) & 0xffffffff; rxcqe->addr_lo = cpu_to_le32(val); data->rx.cqe_page_base.lo = cpu_to_le32(val); @@ -5265,8 +5266,8 @@ static void cnic_shutdown_rings(struct cnic_dev *dev) msleep(10); } clear_bit(CNIC_LCL_FL_RINGS_INITED, &cp->cnic_local_flags); - rx_ring = udev->l2_ring + BNX2_PAGE_SIZE; - memset(rx_ring, 0, BNX2_PAGE_SIZE); + rx_ring = udev->l2_ring + CNIC_PAGE_SIZE; + memset(rx_ring, 0, CNIC_PAGE_SIZE); } static int cnic_register_netdev(struct cnic_dev *dev) diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index 0d6b13f854d9..d535ae4228b4 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -1,6 +1,6 @@ /* cnic.h: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2013 Broadcom Corporation + * Copyright (c) 2006-2014 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index 95a8e4b11c9f..dcbca6997e8f 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -1,7 +1,7 @@ /* cnic.c: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2013 Broadcom Corporation + * Copyright (c) 2006-2014 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h index 8cf6b1926069..5f4d5573a73d 100644 --- a/drivers/net/ethernet/broadcom/cnic_if.h +++ b/drivers/net/ethernet/broadcom/cnic_if.h @@ -1,6 +1,6 @@ /* cnic_if.h: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2013 Broadcom Corporation + * Copyright (c) 2006-2014 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -14,8 +14,8 @@ #include "bnx2x/bnx2x_mfw_req.h" -#define CNIC_MODULE_VERSION "2.5.19" -#define CNIC_MODULE_RELDATE "December 19, 2013" +#define CNIC_MODULE_VERSION "2.5.20" +#define CNIC_MODULE_RELDATE "March 14, 2014" #define CNIC_ULP_RDMA 0 #define CNIC_ULP_ISCSI 1 @@ -24,6 +24,16 @@ #define MAX_CNIC_ULP_TYPE_EXT 3 #define MAX_CNIC_ULP_TYPE 4 +/* Use CPU native page size up to 16K for cnic ring sizes. */ +#if (PAGE_SHIFT > 14) +#define CNIC_PAGE_BITS 14 +#else +#define CNIC_PAGE_BITS PAGE_SHIFT +#endif +#define CNIC_PAGE_SIZE (1 << (CNIC_PAGE_BITS)) +#define CNIC_PAGE_ALIGN(addr) ALIGN(addr, CNIC_PAGE_SIZE) +#define CNIC_PAGE_MASK (~((CNIC_PAGE_SIZE) - 1)) + struct kwqe { u32 kwqe_op_flag; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3167ed6593b0..70a225c8df5c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6843,8 +6843,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) work_mask |= opaque_key; - if ((desc->err_vlan & RXD_ERR_MASK) != 0 && - (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) { + if (desc->err_vlan & RXD_ERR_MASK) { drop_it: tg3_recycle_rx(tnapi, tpr, opaque_key, desc_idx, *post_ptr); @@ -17650,8 +17649,6 @@ static int tg3_init_one(struct pci_dev *pdev, tg3_init_bufmgr_config(tp); - features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - /* 5700 B0 chips do not support checksumming correctly due * to hardware bugs. */ @@ -17683,7 +17680,8 @@ static int tg3_init_one(struct pci_dev *pdev, features |= NETIF_F_TSO_ECN; } - dev->features |= features; + dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; dev->vlan_features |= features; /* diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index ef472385bce4..04321e5a356e 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2608,7 +2608,11 @@ struct tg3_rx_buffer_desc { #define RXD_ERR_TOO_SMALL 0x00400000 #define RXD_ERR_NO_RESOURCES 0x00800000 #define RXD_ERR_HUGE_FRAME 0x01000000 -#define RXD_ERR_MASK 0xffff0000 + +#define RXD_ERR_MASK (RXD_ERR_BAD_CRC | RXD_ERR_COLLISION | \ + RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE | \ + RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL | \ + RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME) u32 reserved; u32 opaque; diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index 1803c3959044..354ae9792bad 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -1704,7 +1704,7 @@ bfa_flash_sem_get(void __iomem *bar) while (!bfa_raw_sem_get(bar)) { if (--n <= 0) return BFA_STATUS_BADFLASH; - udelay(10000); + mdelay(10); } return BFA_STATUS_OK; } diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index cf64f3d0b60d..4ad1187e82fb 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -707,7 +707,8 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) else skb_checksum_none_assert(skb); - if (flags & BNA_CQ_EF_VLAN) + if ((flags & BNA_CQ_EF_VLAN) && + (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cmpl->vlan_tag)); if (BNAD_RXBUF_IS_SK_BUFF(unmap_q->type)) @@ -2094,7 +2095,9 @@ bnad_init_rx_config(struct bnad *bnad, struct bna_rx_config *rx_config) rx_config->q1_buf_size = BFI_SMALL_RXBUF_SIZE; } - rx_config->vlan_strip_status = BNA_STATUS_T_ENABLED; + rx_config->vlan_strip_status = + (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ? + BNA_STATUS_T_ENABLED : BNA_STATUS_T_DISABLED; } static void @@ -3245,11 +3248,6 @@ bnad_set_rx_mode(struct net_device *netdev) BNA_RXMODE_ALLMULTI; bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL); - if (bnad->cfg_flags & BNAD_CF_PROMISC) - bna_rx_vlan_strip_disable(bnad->rx_info[0].rx); - else - bna_rx_vlan_strip_enable(bnad->rx_info[0].rx); - spin_unlock_irqrestore(&bnad->bna_lock, flags); } @@ -3374,6 +3372,27 @@ bnad_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) return 0; } +static int bnad_set_features(struct net_device *dev, netdev_features_t features) +{ + struct bnad *bnad = netdev_priv(dev); + netdev_features_t changed = features ^ dev->features; + + if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(dev)) { + unsigned long flags; + + spin_lock_irqsave(&bnad->bna_lock, flags); + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + bna_rx_vlan_strip_enable(bnad->rx_info[0].rx); + else + bna_rx_vlan_strip_disable(bnad->rx_info[0].rx); + + spin_unlock_irqrestore(&bnad->bna_lock, flags); + } + + return 0; +} + #ifdef CONFIG_NET_POLL_CONTROLLER static void bnad_netpoll(struct net_device *netdev) @@ -3421,6 +3440,7 @@ static const struct net_device_ops bnad_netdev_ops = { .ndo_change_mtu = bnad_change_mtu, .ndo_vlan_rx_add_vid = bnad_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bnad_vlan_rx_kill_vid, + .ndo_set_features = bnad_set_features, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bnad_netpoll #endif @@ -3433,14 +3453,14 @@ bnad_netdev_init(struct bnad *bnad, bool using_dac) netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX; + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; netdev->vlan_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6; - netdev->features |= netdev->hw_features | - NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; + netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; if (using_dac) netdev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 3190d38e16fb..d0c38e01e99f 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -632,11 +632,16 @@ static void gem_rx_refill(struct macb *bp) "Unable to allocate sk_buff\n"); break; } - bp->rx_skbuff[entry] = skb; /* now fill corresponding descriptor entry */ paddr = dma_map_single(&bp->pdev->dev, skb->data, bp->rx_buffer_size, DMA_FROM_DEVICE); + if (dma_mapping_error(&bp->pdev->dev, paddr)) { + dev_kfree_skb(skb); + break; + } + + bp->rx_skbuff[entry] = skb; if (entry == RX_RING_SIZE - 1) paddr |= MACB_BIT(RX_WRAP); @@ -725,7 +730,7 @@ static int gem_rx(struct macb *bp, int budget) skb_put(skb, len); addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, addr)); dma_unmap_single(&bp->pdev->dev, addr, - len, DMA_FROM_DEVICE); + bp->rx_buffer_size, DMA_FROM_DEVICE); skb->protocol = eth_type_trans(skb, bp->dev); skb_checksum_none_assert(skb); @@ -1036,11 +1041,15 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev) } entry = macb_tx_ring_wrap(bp->tx_head); - bp->tx_head++; netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry); mapping = dma_map_single(&bp->pdev->dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(&bp->pdev->dev, mapping)) { + kfree_skb(skb); + goto unlock; + } + bp->tx_head++; tx_skb = &bp->tx_skb[entry]; tx_skb->skb = skb; tx_skb->mapping = mapping; @@ -1066,6 +1075,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev) if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1) netif_stop_queue(dev); +unlock: spin_unlock_irqrestore(&bp->lock, flags); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 43ab35fea48d..34e2488767d9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6179,6 +6179,7 @@ static struct pci_driver cxgb4_driver = { .id_table = cxgb4_pci_tbl, .probe = init_one, .remove = remove_one, + .shutdown = remove_one, .err_handler = &cxgb4_eeh, }; diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 8d09615da585..05529e273050 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -350,11 +350,13 @@ struct be_drv_stats { u32 roce_drops_crc; }; +/* A vlan-id of 0xFFFF must be used to clear transparent vlan-tagging */ +#define BE_RESET_VLAN_TAG_ID 0xFFFF + struct be_vf_cfg { unsigned char mac_addr[ETH_ALEN]; int if_handle; int pmac_id; - u16 def_vid; u16 vlan_tag; u32 tx_rate; }; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 04ac9c6a0d39..36c80612e21a 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -913,24 +913,14 @@ static int be_ipv6_tx_stall_chk(struct be_adapter *adapter, return BE3_chip(adapter) && be_ipv6_exthdr_check(skb); } -static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, - struct sk_buff *skb, - bool *skip_hw_vlan) +static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter, + struct sk_buff *skb, + bool *skip_hw_vlan) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; unsigned int eth_hdr_len; struct iphdr *ip; - /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or less - * may cause a transmit stall on that port. So the work-around is to - * pad short packets (<= 32 bytes) to a 36-byte length. - */ - if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { - if (skb_padto(skb, 36)) - goto tx_drop; - skb->len = 36; - } - /* For padded packets, BE HW modifies tot_len field in IP header * incorrecly when VLAN tag is inserted by HW. * For padded packets, Lancer computes incorrect checksum. @@ -959,7 +949,7 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, vlan_tx_tag_present(skb)) { skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan); if (unlikely(!skb)) - goto tx_drop; + goto err; } /* HW may lockup when VLAN HW tagging is requested on @@ -981,15 +971,39 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, be_vlan_tag_tx_chk(adapter, skb)) { skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan); if (unlikely(!skb)) - goto tx_drop; + goto err; } return skb; tx_drop: dev_kfree_skb_any(skb); +err: return NULL; } +static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, + struct sk_buff *skb, + bool *skip_hw_vlan) +{ + /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or + * less may cause a transmit stall on that port. So the work-around is + * to pad short packets (<= 32 bytes) to a 36-byte length. + */ + if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { + if (skb_padto(skb, 36)) + return NULL; + skb->len = 36; + } + + if (BEx_chip(adapter) || lancer_chip(adapter)) { + skb = be_lancer_xmit_workarounds(adapter, skb, skip_hw_vlan); + if (!skb) + return NULL; + } + + return skb; +} + static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -1157,6 +1171,14 @@ ret: return status; } +static void be_clear_promisc(struct be_adapter *adapter) +{ + adapter->promiscuous = false; + adapter->flags &= ~BE_FLAGS_VLAN_PROMISC; + + be_cmd_rx_filter(adapter, IFF_PROMISC, OFF); +} + static void be_set_rx_mode(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -1170,9 +1192,7 @@ static void be_set_rx_mode(struct net_device *netdev) /* BE was previously in promiscuous mode; disable it */ if (adapter->promiscuous) { - adapter->promiscuous = false; - be_cmd_rx_filter(adapter, IFF_PROMISC, OFF); - + be_clear_promisc(adapter); if (adapter->vlans_added) be_vid_config(adapter); } @@ -1287,24 +1307,20 @@ static int be_set_vf_vlan(struct net_device *netdev, if (vlan || qos) { vlan |= qos << VLAN_PRIO_SHIFT; - if (vf_cfg->vlan_tag != vlan) { - /* If this is new value, program it. Else skip. */ - vf_cfg->vlan_tag = vlan; + if (vf_cfg->vlan_tag != vlan) status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_cfg->if_handle, 0); - } } else { /* Reset Transparent Vlan Tagging. */ - vf_cfg->vlan_tag = 0; - vlan = vf_cfg->def_vid; - status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, - vf_cfg->if_handle, 0); + status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, + vf + 1, vf_cfg->if_handle, 0); } - - if (status) + if (!status) + vf_cfg->vlan_tag = vlan; + else dev_info(&adapter->pdev->dev, - "VLAN %d config on VF %d failed\n", vlan, vf); + "VLAN %d config on VF %d failed\n", vlan, vf); return status; } @@ -3013,11 +3029,11 @@ static int be_vf_setup_init(struct be_adapter *adapter) static int be_vf_setup(struct be_adapter *adapter) { + struct device *dev = &adapter->pdev->dev; struct be_vf_cfg *vf_cfg; - u16 def_vlan, lnk_speed; int status, old_vfs, vf; - struct device *dev = &adapter->pdev->dev; u32 privileges; + u16 lnk_speed; old_vfs = pci_num_vf(adapter->pdev); if (old_vfs) { @@ -3084,12 +3100,6 @@ static int be_vf_setup(struct be_adapter *adapter) if (!status) vf_cfg->tx_rate = lnk_speed; - status = be_cmd_get_hsw_config(adapter, &def_vlan, - vf + 1, vf_cfg->if_handle, NULL); - if (status) - goto err; - vf_cfg->def_vid = def_vlan; - if (!old_vfs) be_cmd_enable_vf(adapter, vf + 1); } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 903362a7b584..03a351300013 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -389,12 +389,6 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev) netdev_err(ndev, "Tx DMA memory map failed\n"); return NETDEV_TX_OK; } - /* Send it on its way. Tell FEC it's ready, interrupt when done, - * it's the last BD of the frame, and to put the CRC on the end. - */ - status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR - | BD_ENET_TX_LAST | BD_ENET_TX_TC); - bdp->cbd_sc = status; if (fep->bufdesc_ex) { @@ -416,6 +410,13 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev) } } + /* Send it on its way. Tell FEC it's ready, interrupt when done, + * it's the last BD of the frame, and to put the CRC on the end. + */ + status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR + | BD_ENET_TX_LAST | BD_ENET_TX_TC); + bdp->cbd_sc = status; + bdp_pre = fec_enet_get_prevdesc(bdp, fep); if ((id_entry->driver_data & FEC_QUIRK_ERR006358) && !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) { @@ -527,13 +528,6 @@ fec_restart(struct net_device *ndev, int duplex) /* Clear any outstanding interrupt. */ writel(0xffc00000, fep->hwp + FEC_IEVENT); - /* Setup multicast filter. */ - set_multicast_list(ndev); -#ifndef CONFIG_M5272 - writel(0, fep->hwp + FEC_HASH_TABLE_HIGH); - writel(0, fep->hwp + FEC_HASH_TABLE_LOW); -#endif - /* Set maximum receive buffer size. */ writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE); @@ -654,6 +648,13 @@ fec_restart(struct net_device *ndev, int duplex) writel(rcntl, fep->hwp + FEC_R_CNTRL); + /* Setup multicast filter. */ + set_multicast_list(ndev); +#ifndef CONFIG_M5272 + writel(0, fep->hwp + FEC_HASH_TABLE_HIGH); + writel(0, fep->hwp + FEC_HASH_TABLE_LOW); +#endif + if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) { /* enable ENET endian swap */ ecntl |= (1 << 8); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 4be971590461..1fc8334fc181 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -522,10 +522,21 @@ retry: return rc; } +static u64 ibmveth_encode_mac_addr(u8 *mac) +{ + int i; + u64 encoded = 0; + + for (i = 0; i < ETH_ALEN; i++) + encoded = (encoded << 8) | mac[i]; + + return encoded; +} + static int ibmveth_open(struct net_device *netdev) { struct ibmveth_adapter *adapter = netdev_priv(netdev); - u64 mac_address = 0; + u64 mac_address; int rxq_entries = 1; unsigned long lpar_rc; int rc; @@ -579,8 +590,7 @@ static int ibmveth_open(struct net_device *netdev) adapter->rx_queue.num_slots = rxq_entries; adapter->rx_queue.toggle = 1; - memcpy(&mac_address, netdev->dev_addr, netdev->addr_len); - mac_address = mac_address >> 16; + mac_address = ibmveth_encode_mac_addr(netdev->dev_addr); rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len; @@ -1183,8 +1193,8 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) /* add the addresses to the filter table */ netdev_for_each_mc_addr(ha, netdev) { /* add the multicast address to the filter table */ - unsigned long mcast_addr = 0; - memcpy(((char *)&mcast_addr)+2, ha->addr, ETH_ALEN); + u64 mcast_addr; + mcast_addr = ibmveth_encode_mac_addr(ha->addr); lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastAddFilter, mcast_addr); @@ -1372,9 +1382,6 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16); - adapter->mac_addr = 0; - memcpy(&adapter->mac_addr, mac_addr_p, ETH_ALEN); - netdev->irq = dev->irq; netdev->netdev_ops = &ibmveth_netdev_ops; netdev->ethtool_ops = &netdev_ethtool_ops; @@ -1383,7 +1390,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; netdev->features |= netdev->hw_features; - memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len); + memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN); for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { struct kobject *kobj = &adapter->rx_buff_pool[i].kobj; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 451ba7949e15..1f37499d4398 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -138,7 +138,6 @@ struct ibmveth_adapter { struct napi_struct napi; struct net_device_stats stats; unsigned int mcastFilterSize; - unsigned long mac_addr; void * buffer_list_addr; void * filter_list_addr; dma_addr_t buffer_list_dma; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f418f4f20f94..8d76fca7fde7 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -22,6 +22,7 @@ #include <linux/interrupt.h> #include <net/ip.h> #include <net/ipv6.h> +#include <linux/io.h> #include <linux/of.h> #include <linux/of_irq.h> #include <linux/of_mdio.h> @@ -88,8 +89,9 @@ #define MVNETA_TX_IN_PRGRS BIT(1) #define MVNETA_TX_FIFO_EMPTY BIT(8) #define MVNETA_RX_MIN_FRAME_SIZE 0x247c -#define MVNETA_SGMII_SERDES_CFG 0x24A0 +#define MVNETA_SERDES_CFG 0x24A0 #define MVNETA_SGMII_SERDES_PROTO 0x0cc7 +#define MVNETA_RGMII_SERDES_PROTO 0x0667 #define MVNETA_TYPE_PRIO 0x24bc #define MVNETA_FORCE_UNI BIT(21) #define MVNETA_TXQ_CMD_1 0x24e4 @@ -161,7 +163,7 @@ #define MVNETA_GMAC_MAX_RX_SIZE_MASK 0x7ffc #define MVNETA_GMAC0_PORT_ENABLE BIT(0) #define MVNETA_GMAC_CTRL_2 0x2c08 -#define MVNETA_GMAC2_PSC_ENABLE BIT(3) +#define MVNETA_GMAC2_PCS_ENABLE BIT(3) #define MVNETA_GMAC2_PORT_RGMII BIT(4) #define MVNETA_GMAC2_PORT_RESET BIT(6) #define MVNETA_GMAC_STATUS 0x2c10 @@ -710,35 +712,6 @@ static void mvneta_rxq_bm_disable(struct mvneta_port *pp, mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val); } - - -/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */ -static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable) -{ - u32 val; - - val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); - - if (enable) - val |= MVNETA_GMAC2_PORT_RGMII; - else - val &= ~MVNETA_GMAC2_PORT_RGMII; - - mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); -} - -/* Config SGMII port */ -static void mvneta_port_sgmii_config(struct mvneta_port *pp) -{ - u32 val; - - val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); - val |= MVNETA_GMAC2_PSC_ENABLE; - mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); - - mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); -} - /* Start the Ethernet port RX and TX activity */ static void mvneta_port_up(struct mvneta_port *pp) { @@ -2756,12 +2729,15 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0); if (phy_mode == PHY_INTERFACE_MODE_SGMII) - mvneta_port_sgmii_config(pp); + mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); + else + mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO); + + val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); - mvneta_gmac_rgmii_set(pp, 1); + val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII; /* Cancel Port Reset */ - val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); val &= ~MVNETA_GMAC2_PORT_RESET; mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); @@ -2774,6 +2750,7 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) static int mvneta_probe(struct platform_device *pdev) { const struct mbus_dram_target_info *dram_target_info; + struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *phy_node; u32 phy_addr; @@ -2838,9 +2815,15 @@ static int mvneta_probe(struct platform_device *pdev) clk_prepare_enable(pp->clk); - pp->base = of_iomap(dn, 0); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + err = -ENODEV; + goto err_clk; + } + + pp->base = devm_ioremap_resource(&pdev->dev, res); if (pp->base == NULL) { - err = -ENOMEM; + err = PTR_ERR(pp->base); goto err_clk; } @@ -2848,7 +2831,7 @@ static int mvneta_probe(struct platform_device *pdev) pp->stats = alloc_percpu(struct mvneta_pcpu_stats); if (!pp->stats) { err = -ENOMEM; - goto err_unmap; + goto err_clk; } for_each_possible_cpu(cpu) { @@ -2913,8 +2896,6 @@ err_deinit: mvneta_deinit(pp); err_free_stats: free_percpu(pp->stats); -err_unmap: - iounmap(pp->base); err_clk: clk_disable_unprepare(pp->clk); err_free_irq: @@ -2934,7 +2915,6 @@ static int mvneta_remove(struct platform_device *pdev) mvneta_deinit(pp); clk_disable_unprepare(pp->clk); free_percpu(pp->stats); - iounmap(pp->base); irq_dispose_mapping(dev->irq); free_netdev(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index fad45316200a..84a96f70dfb5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -742,6 +742,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, err = mlx4_en_uc_steer_add(priv, new_mac, &qpn, &entry->reg_id); + if (err) + return err; + if (priv->tunnel_reg_id) { + mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id); + priv->tunnel_reg_id = 0; + } + err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn, + &priv->tunnel_reg_id); return err; } } @@ -1792,6 +1800,8 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) mc_list[5] = priv->port; mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, MLX4_PROT_ETH, mclist->reg_id); + if (mclist->tunnel_reg_id) + mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id); } mlx4_en_clear_list(dev); list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 91b69ff4b4a2..7e2995ecea6f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -129,13 +129,14 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [0] = "RSS support", [1] = "RSS Toeplitz Hash Function support", [2] = "RSS XOR Hash Function support", - [3] = "Device manage flow steering support", + [3] = "Device managed flow steering support", [4] = "Automatic MAC reassignment support", [5] = "Time stamping support", [6] = "VST (control vlan insertion/stripping) support", [7] = "FSM (MAC anti-spoofing) support", [8] = "Dynamic QP updates support", - [9] = "TCP/IP offloads/flow-steering for VXLAN support" + [9] = "Device managed flow steering IPoIB support", + [10] = "TCP/IP offloads/flow-steering for VXLAN support" }; int i; @@ -859,7 +860,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET); /* For guests, disable vxlan tunneling */ - MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN); + MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VXLAN); field &= 0xf7; MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN); @@ -869,7 +870,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET); /* For guests, disable mw type 2 */ - MLX4_GET(bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); + MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN; MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET); @@ -883,7 +884,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, } /* turn off ipoib managed steering for guests */ - MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); + MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); field &= ~0x80; MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d711158b0d4b..d413e60071d4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -150,6 +150,8 @@ struct mlx4_port_config { struct pci_dev *pdev; }; +static atomic_t pf_loading = ATOMIC_INIT(0); + int mlx4_check_port_params(struct mlx4_dev *dev, enum mlx4_port_type *port_type) { @@ -749,7 +751,7 @@ static void mlx4_request_modules(struct mlx4_dev *dev) has_eth_port = true; } - if (has_ib_port) + if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)) request_module_nowait(IB_DRV_NAME); if (has_eth_port) request_module_nowait(EN_DRV_NAME); @@ -1407,6 +1409,11 @@ static int mlx4_init_slave(struct mlx4_dev *dev) u32 slave_read; u32 cmd_channel_ver; + if (atomic_read(&pf_loading)) { + mlx4_warn(dev, "PF is not ready. Deferring probe\n"); + return -EPROBE_DEFER; + } + mutex_lock(&priv->cmd.slave_cmd_mutex); priv->cmd.max_cmds = 1; mlx4_warn(dev, "Sending reset\n"); @@ -2319,7 +2326,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) if (num_vfs) { mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs); + + atomic_inc(&pf_loading); err = pci_enable_sriov(pdev, num_vfs); + atomic_dec(&pf_loading); + if (err) { mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n", err); @@ -2670,7 +2681,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) { - int ret = __mlx4_init_one(pdev, 0); + const struct pci_device_id *id; + int ret; + + id = pci_match_id(mlx4_pci_table, pdev); + ret = __mlx4_init_one(pdev, id->driver_data); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } @@ -2684,6 +2699,7 @@ static struct pci_driver mlx4_driver = { .name = DRV_NAME, .id_table = mlx4_pci_table, .probe = mlx4_init_one, + .shutdown = mlx4_remove_one, .remove = mlx4_remove_one, .err_handler = &mlx4_err_handler, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 6b65f7795215..7aec6c833973 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -51,8 +51,8 @@ #define DRV_NAME "mlx4_core" #define PFX DRV_NAME ": " -#define DRV_VERSION "1.1" -#define DRV_RELDATE "Dec, 2011" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb, 2014" #define MLX4_FS_UDP_UC_EN (1 << 1) #define MLX4_FS_TCP_UC_EN (1 << 2) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 9ca223bc90fc..b57e8c87a34e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -57,8 +57,8 @@ #include "en_port.h" #define DRV_NAME "mlx4_en" -#define DRV_VERSION "2.0" -#define DRV_RELDATE "Dec 2011" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb 2014" #define MLX4_EN_MSG_LEVEL (NETIF_MSG_LINK | NETIF_MSG_IFDOWN) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a064f06e0cb8..23b7e2d35a93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -46,8 +46,8 @@ #include "mlx5_core.h" #define DRIVER_NAME "mlx5_core" -#define DRIVER_VERSION "1.0" -#define DRIVER_RELDATE "June 2013" +#define DRIVER_VERSION "2.2-1" +#define DRIVER_RELDATE "Feb 2014" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox ConnectX-IB HCA core library"); diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index 727b546a9eb8..e0c92e0e5e1d 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -23,6 +23,7 @@ #include <linux/crc32.h> #include <linux/mii.h> #include <linux/eeprom_93cx6.h> +#include <linux/regulator/consumer.h> #include <linux/spi/spi.h> @@ -83,6 +84,7 @@ union ks8851_tx_hdr { * @rc_rxqcr: Cached copy of KS_RXQCR. * @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM. + * @vdd_reg: Optional regulator supplying the chip * * The @lock ensures that the chip is protected when certain operations are * in progress. When the read or write packet transfer is in progress, most @@ -130,6 +132,7 @@ struct ks8851_net { struct spi_transfer spi_xfer2[2]; struct eeprom_93cx6 eeprom; + struct regulator *vdd_reg; }; static int msg_enable; @@ -1414,6 +1417,21 @@ static int ks8851_probe(struct spi_device *spi) ks->spidev = spi; ks->tx_space = 6144; + ks->vdd_reg = regulator_get_optional(&spi->dev, "vdd"); + if (IS_ERR(ks->vdd_reg)) { + ret = PTR_ERR(ks->vdd_reg); + if (ret == -EPROBE_DEFER) + goto err_reg; + } else { + ret = regulator_enable(ks->vdd_reg); + if (ret) { + dev_err(&spi->dev, "regulator enable fail: %d\n", + ret); + goto err_reg_en; + } + } + + mutex_init(&ks->lock); spin_lock_init(&ks->statelock); @@ -1508,8 +1526,14 @@ static int ks8851_probe(struct spi_device *spi) err_netdev: free_irq(ndev->irq, ks); -err_id: err_irq: +err_id: + if (!IS_ERR(ks->vdd_reg)) + regulator_disable(ks->vdd_reg); +err_reg_en: + if (!IS_ERR(ks->vdd_reg)) + regulator_put(ks->vdd_reg); +err_reg: free_netdev(ndev); return ret; } @@ -1523,6 +1547,10 @@ static int ks8851_remove(struct spi_device *spi) unregister_netdev(priv->netdev); free_irq(spi->irq, priv); + if (!IS_ERR(priv->vdd_reg)) { + regulator_disable(priv->vdd_reg); + regulator_put(priv->vdd_reg); + } free_netdev(priv->netdev); return 0; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 4146664d4d6a..27c4f131863b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -340,6 +340,7 @@ int qlcnic_83xx_setup_intr(struct qlcnic_adapter *adapter) if (qlcnic_sriov_vf_check(adapter)) return -EINVAL; num_msix = 1; + adapter->drv_sds_rings = QLCNIC_SINGLE_RING; adapter->drv_tx_rings = QLCNIC_SINGLE_RING; } } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c index 77f1bce432d2..7d4f54912bad 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c @@ -807,7 +807,7 @@ qlcnic_dcb_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, u8 *prio, !type->tc_param_valid) return; - if (tc < 0 || (tc > QLC_DCB_MAX_TC)) + if (tc < 0 || (tc >= QLC_DCB_MAX_TC)) return; tc_cfg = &type->tc_cfg[tc]; @@ -843,7 +843,7 @@ static void qlcnic_dcb_get_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, !type->tc_param_valid) return; - if (pgid < 0 || pgid > QLC_DCB_MAX_PG) + if (pgid < 0 || pgid >= QLC_DCB_MAX_PG) return; pgcfg = &type->pg_cfg[pgid]; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index ba78c7481fa3..1222865cfb73 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -816,9 +816,10 @@ static int qlcnic_82xx_setup_intr(struct qlcnic_adapter *adapter) if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { qlcnic_disable_multi_tx(adapter); + adapter->drv_sds_rings = QLCNIC_SINGLE_RING; err = qlcnic_enable_msi_legacy(adapter); - if (!err) + if (err) return err; } } @@ -3863,7 +3864,7 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt, strcpy(buf, "Tx"); } - if (!qlcnic_use_msi_x && !qlcnic_use_msi) { + if (!QLCNIC_IS_MSI_FAMILY(adapter)) { netdev_err(netdev, "No RSS/TSS support in INT-x mode\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index 09acf15c3a56..e5277a632671 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -13,8 +13,6 @@ #define QLC_VF_MIN_TX_RATE 100 #define QLC_VF_MAX_TX_RATE 9999 #define QLC_MAC_OPCODE_MASK 0x7 -#define QLC_MAC_STAR_ADD 6 -#define QLC_MAC_STAR_DEL 7 #define QLC_VF_FLOOD_BIT BIT_16 #define QLC_FLOOD_MODE 0x5 @@ -1206,13 +1204,6 @@ static int qlcnic_sriov_validate_cfg_macvlan(struct qlcnic_adapter *adapter, struct qlcnic_vport *vp = vf->vp; u8 op, new_op; - if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) || - ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) { - netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n", - vf->pci_func); - return -EINVAL; - } - if (!(cmd->req.arg[1] & BIT_8)) return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index ce2cfddbed50..656c65ddadb4 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4765,7 +4765,9 @@ static int qlge_probe(struct pci_dev *pdev, ndev->features = ndev->hw_features; ndev->vlan_features = ndev->hw_features; /* vlan gets same features (except vlan filter) */ - ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); if (test_bit(QL_DMA64, &qdev->flags)) ndev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 91a67ae8f17b..3ff7bc3e7a23 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -209,7 +209,7 @@ static const struct { [RTL_GIGA_MAC_VER_16] = _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true), [RTL_GIGA_MAC_VER_17] = - _R("RTL8168b/8111b", RTL_TD_1, NULL, JUMBO_4K, false), + _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false), [RTL_GIGA_MAC_VER_18] = _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false), [RTL_GIGA_MAC_VER_19] = @@ -7118,6 +7118,8 @@ rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } mutex_init(&tp->wk.mutex); + u64_stats_init(&tp->rx_stats.syncp); + u64_stats_init(&tp->tx_stats.syncp); /* Get MAC address */ for (i = 0; i < ETH_ALEN; i++) diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index eb75fbd11a01..d7a36829649a 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1668,6 +1668,13 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) struct efx_ptp_data *ptp = efx->ptp_data; int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE); + if (!ptp) { + if (net_ratelimit()) + netif_warn(efx, drv, efx->net_dev, + "Received PTP event but PTP not set up\n"); + return; + } + if (!ptp->enabled) return; diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index 72d282bf33a5..c553f6b5a913 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -151,7 +151,7 @@ static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) sizeof(struct dma_desc))); } -const struct stmmac_chain_mode_ops chain_mode_ops = { +const struct stmmac_mode_ops chain_mode_ops = { .init = stmmac_init_dma_chain, .is_jumbo_frm = stmmac_is_jumbo_frm, .jumbo_frm = stmmac_jumbo_frm, diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 7834a3993946..74610f3aca9e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -419,20 +419,13 @@ struct mii_regs { unsigned int data; /* MII Data */ }; -struct stmmac_ring_mode_ops { - unsigned int (*is_jumbo_frm) (int len, int ehn_desc); - unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum); - void (*refill_desc3) (void *priv, struct dma_desc *p); - void (*init_desc3) (struct dma_desc *p); - void (*clean_desc3) (void *priv, struct dma_desc *p); - int (*set_16kib_bfsize) (int mtu); -}; - -struct stmmac_chain_mode_ops { +struct stmmac_mode_ops { void (*init) (void *des, dma_addr_t phy_addr, unsigned int size, unsigned int extend_desc); unsigned int (*is_jumbo_frm) (int len, int ehn_desc); unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum); + int (*set_16kib_bfsize)(int mtu); + void (*init_desc3)(struct dma_desc *p); void (*refill_desc3) (void *priv, struct dma_desc *p); void (*clean_desc3) (void *priv, struct dma_desc *p); }; @@ -441,8 +434,7 @@ struct mac_device_info { const struct stmmac_ops *mac; const struct stmmac_desc_ops *desc; const struct stmmac_dma_ops *dma; - const struct stmmac_ring_mode_ops *ring; - const struct stmmac_chain_mode_ops *chain; + const struct stmmac_mode_ops *mode; const struct stmmac_hwtimestamp *ptp; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; @@ -460,7 +452,7 @@ void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, void stmmac_set_mac(void __iomem *ioaddr, bool enable); void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr); -extern const struct stmmac_ring_mode_ops ring_mode_ops; -extern const struct stmmac_chain_mode_ops chain_mode_ops; +extern const struct stmmac_mode_ops ring_mode_ops; +extern const struct stmmac_mode_ops chain_mode_ops; #endif /* __COMMON_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index a96c7c2f5f3f..650a4be6bce5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -100,10 +100,9 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) { struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; - if (unlikely(priv->plat->has_gmac)) - /* Fill DES3 in case of RING mode */ - if (priv->dma_buf_sz >= BUF_SIZE_8KiB) - p->des3 = p->des2 + BUF_SIZE_8KiB; + /* Fill DES3 in case of RING mode */ + if (priv->dma_buf_sz >= BUF_SIZE_8KiB) + p->des3 = p->des2 + BUF_SIZE_8KiB; } /* In ring mode we need to fill the desc3 because it is used as buffer */ @@ -126,7 +125,7 @@ static int stmmac_set_16kib_bfsize(int mtu) return ret; } -const struct stmmac_ring_mode_ops ring_mode_ops = { +const struct stmmac_mode_ops ring_mode_ops = { .is_jumbo_frm = stmmac_is_jumbo_frm, .jumbo_frm = stmmac_jumbo_frm, .refill_desc3 = stmmac_refill_desc3, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a2e7d2c96e36..8543e1cfd55e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -92,8 +92,8 @@ static int tc = TC_DEFAULT; module_param(tc, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(tc, "DMA threshold control value"); -#define DMA_BUFFER_SIZE BUF_SIZE_4KiB -static int buf_sz = DMA_BUFFER_SIZE; +#define DEFAULT_BUFSIZE 1536 +static int buf_sz = DEFAULT_BUFSIZE; module_param(buf_sz, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(buf_sz, "DMA buffer size"); @@ -136,8 +136,8 @@ static void stmmac_verify_args(void) dma_rxsize = DMA_RX_SIZE; if (unlikely(dma_txsize < 0)) dma_txsize = DMA_TX_SIZE; - if (unlikely((buf_sz < DMA_BUFFER_SIZE) || (buf_sz > BUF_SIZE_16KiB))) - buf_sz = DMA_BUFFER_SIZE; + if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB))) + buf_sz = DEFAULT_BUFSIZE; if (unlikely(flow_ctrl > 1)) flow_ctrl = FLOW_AUTO; else if (likely(flow_ctrl < 0)) @@ -286,10 +286,25 @@ bool stmmac_eee_init(struct stmmac_priv *priv) /* MAC core supports the EEE feature. */ if (priv->dma_cap.eee) { + int tx_lpi_timer = priv->tx_lpi_timer; + /* Check if the PHY supports EEE */ - if (phy_init_eee(priv->phydev, 1)) + if (phy_init_eee(priv->phydev, 1)) { + /* To manage at run-time if the EEE cannot be supported + * anymore (for example because the lp caps have been + * changed). + * In that case the driver disable own timers. + */ + if (priv->eee_active) { + pr_debug("stmmac: disable EEE\n"); + del_timer_sync(&priv->eee_ctrl_timer); + priv->hw->mac->set_eee_timer(priv->ioaddr, 0, + tx_lpi_timer); + } + priv->eee_active = 0; goto out; - + } + /* Activate the EEE and start timers */ if (!priv->eee_active) { priv->eee_active = 1; init_timer(&priv->eee_ctrl_timer); @@ -300,13 +315,13 @@ bool stmmac_eee_init(struct stmmac_priv *priv) priv->hw->mac->set_eee_timer(priv->ioaddr, STMMAC_DEFAULT_LIT_LS, - priv->tx_lpi_timer); + tx_lpi_timer); } else /* Set HW EEE according to the speed */ priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link); - pr_info("stmmac: Energy-Efficient Ethernet initialized\n"); + pr_debug("stmmac: Energy-Efficient Ethernet initialized\n"); ret = true; } @@ -886,10 +901,10 @@ static int stmmac_set_bfsize(int mtu, int bufsize) ret = BUF_SIZE_8KiB; else if (mtu >= BUF_SIZE_2KiB) ret = BUF_SIZE_4KiB; - else if (mtu >= DMA_BUFFER_SIZE) + else if (mtu > DEFAULT_BUFSIZE) ret = BUF_SIZE_2KiB; else - ret = DMA_BUFFER_SIZE; + ret = DEFAULT_BUFSIZE; return ret; } @@ -951,9 +966,9 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, p->des2 = priv->rx_skbuff_dma[i]; - if ((priv->mode == STMMAC_RING_MODE) && + if ((priv->hw->mode->init_desc3) && (priv->dma_buf_sz == BUF_SIZE_16KiB)) - priv->hw->ring->init_desc3(p); + priv->hw->mode->init_desc3(p); return 0; } @@ -984,11 +999,8 @@ static int init_dma_desc_rings(struct net_device *dev) unsigned int bfsize = 0; int ret = -ENOMEM; - /* Set the max buffer size according to the DESC mode - * and the MTU. Note that RING mode allows 16KiB bsize. - */ - if (priv->mode == STMMAC_RING_MODE) - bfsize = priv->hw->ring->set_16kib_bfsize(dev->mtu); + if (priv->hw->mode->set_16kib_bfsize) + bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu); if (bfsize < BUF_SIZE_16KiB) bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); @@ -1029,15 +1041,15 @@ static int init_dma_desc_rings(struct net_device *dev) /* Setup the chained descriptor addresses */ if (priv->mode == STMMAC_CHAIN_MODE) { if (priv->extend_desc) { - priv->hw->chain->init(priv->dma_erx, priv->dma_rx_phy, - rxsize, 1); - priv->hw->chain->init(priv->dma_etx, priv->dma_tx_phy, - txsize, 1); + priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy, + rxsize, 1); + priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy, + txsize, 1); } else { - priv->hw->chain->init(priv->dma_rx, priv->dma_rx_phy, - rxsize, 0); - priv->hw->chain->init(priv->dma_tx, priv->dma_tx_phy, - txsize, 0); + priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy, + rxsize, 0); + priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy, + txsize, 0); } } @@ -1288,7 +1300,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) DMA_TO_DEVICE); priv->tx_skbuff_dma[entry] = 0; } - priv->hw->ring->clean_desc3(priv, p); + priv->hw->mode->clean_desc3(priv, p); if (likely(skb != NULL)) { dev_kfree_skb(skb); @@ -1705,7 +1717,7 @@ static int stmmac_open(struct net_device *dev) priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize); priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); - alloc_dma_desc_resources(priv); + ret = alloc_dma_desc_resources(priv); if (ret < 0) { pr_err("%s: DMA descriptors allocation failed\n", __func__); goto dma_desc_error; @@ -1844,6 +1856,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) int nfrags = skb_shinfo(skb)->nr_frags; struct dma_desc *desc, *first; unsigned int nopaged_len = skb_headlen(skb); + unsigned int enh_desc = priv->plat->enh_desc; if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) { if (!netif_queue_stopped(dev)) { @@ -1871,27 +1884,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first = desc; /* To program the descriptors according to the size of the frame */ - if (priv->mode == STMMAC_RING_MODE) { - is_jumbo = priv->hw->ring->is_jumbo_frm(skb->len, - priv->plat->enh_desc); - if (unlikely(is_jumbo)) - entry = priv->hw->ring->jumbo_frm(priv, skb, - csum_insertion); - } else { - is_jumbo = priv->hw->chain->is_jumbo_frm(skb->len, - priv->plat->enh_desc); - if (unlikely(is_jumbo)) - entry = priv->hw->chain->jumbo_frm(priv, skb, - csum_insertion); - } + if (enh_desc) + is_jumbo = priv->hw->mode->is_jumbo_frm(skb->len, enh_desc); + if (likely(!is_jumbo)) { desc->des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); priv->tx_skbuff_dma[entry] = desc->des2; priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum_insertion, priv->mode); - } else + } else { desc = first; + entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion); + } for (i = 0; i < nfrags; i++) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -2029,7 +2034,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) p->des2 = priv->rx_skbuff_dma[entry]; - priv->hw->ring->refill_desc3(priv, p); + priv->hw->mode->refill_desc3(priv, p); if (netif_msg_rx_status(priv)) pr_debug("\trefill entry #%d\n", entry); @@ -2633,11 +2638,11 @@ static int stmmac_hw_init(struct stmmac_priv *priv) /* To use the chained or ring mode */ if (chain_mode) { - priv->hw->chain = &chain_mode_ops; + priv->hw->mode = &chain_mode_ops; pr_info(" Chain mode enabled\n"); priv->mode = STMMAC_CHAIN_MODE; } else { - priv->hw->ring = &ring_mode_ops; + priv->hw->mode = &ring_mode_ops; pr_info(" Ring mode enabled\n"); priv->mode = STMMAC_RING_MODE; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index c61bc72b8e90..8fb32a80f1c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -36,7 +36,7 @@ static const struct of_device_id stmmac_dt_ids[] = { #ifdef CONFIG_DWMAC_STI { .compatible = "st,stih415-dwmac", .data = &sti_gmac_data}, { .compatible = "st,stih416-dwmac", .data = &sti_gmac_data}, - { .compatible = "st,stih127-dwmac", .data = &sti_gmac_data}, + { .compatible = "st,stid127-dwmac", .data = &sti_gmac_data}, #endif /* SoC specific glue layers should come before generic bindings */ { .compatible = "st,spear600-gmac"}, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 651087b5c8da..7d6d8ec676c8 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1164,11 +1164,17 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv) { + u32 slave_port; + + slave_port = cpsw_get_slave_port(priv, slave->slave_num); + if (!slave->phy) return; phy_stop(slave->phy); phy_disconnect(slave->phy); slave->phy = NULL; + cpsw_ale_control_set(priv->ale, slave_port, + ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); } static int cpsw_ndo_open(struct net_device *ndev) @@ -2223,10 +2229,6 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_ale_ret; } - if (cpts_register(&pdev->dev, priv->cpts, - data->cpts_clock_mult, data->cpts_clock_shift)) - dev_err(priv->dev, "error registering cpts device\n"); - cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d)\n", &ss_res->start, ndev->irq); diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 364d0c7952c0..88ef27067bf2 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -355,7 +355,7 @@ int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr) int i; spin_lock_irqsave(&ctlr->lock, flags); - if (ctlr->state != CPDMA_STATE_ACTIVE) { + if (ctlr->state == CPDMA_STATE_TEARDOWN) { spin_unlock_irqrestore(&ctlr->lock, flags); return -EINVAL; } @@ -891,7 +891,7 @@ int cpdma_chan_stop(struct cpdma_chan *chan) unsigned timeout; spin_lock_irqsave(&chan->lock, flags); - if (chan->state != CPDMA_STATE_ACTIVE) { + if (chan->state == CPDMA_STATE_TEARDOWN) { spin_unlock_irqrestore(&chan->lock, flags); return -EINVAL; } diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index cd9b164a0434..8f0e69ce07ca 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1532,9 +1532,9 @@ static int emac_dev_open(struct net_device *ndev) struct device *emac_dev = &ndev->dev; u32 cnt; struct resource *res; - int ret; + int q, m, ret; + int res_num = 0, irq_num = 0; int i = 0; - int k = 0; struct emac_priv *priv = netdev_priv(ndev); pm_runtime_get(&priv->pdev->dev); @@ -1564,15 +1564,24 @@ static int emac_dev_open(struct net_device *ndev) } /* Request IRQ */ + while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, + res_num))) { + for (irq_num = res->start; irq_num <= res->end; irq_num++) { + dev_err(emac_dev, "Request IRQ %d\n", irq_num); + if (request_irq(irq_num, emac_irq, 0, ndev->name, + ndev)) { + dev_err(emac_dev, + "DaVinci EMAC: request_irq() failed\n"); + ret = -EBUSY; - while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) { - for (i = res->start; i <= res->end; i++) { - if (devm_request_irq(&priv->pdev->dev, i, emac_irq, - 0, ndev->name, ndev)) goto rollback; + } } - k++; + res_num++; } + /* prepare counters for rollback in case of an error */ + res_num--; + irq_num--; /* Start/Enable EMAC hardware */ emac_hw_enable(priv); @@ -1639,11 +1648,23 @@ static int emac_dev_open(struct net_device *ndev) return 0; -rollback: - - dev_err(emac_dev, "DaVinci EMAC: devm_request_irq() failed"); - ret = -EBUSY; err: + emac_int_disable(priv); + napi_disable(&priv->napi); + +rollback: + for (q = res_num; q >= 0; q--) { + res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, q); + /* at the first iteration, irq_num is already set to the + * right value + */ + if (q != res_num) + irq_num = res->end; + + for (m = irq_num; m >= res->start; m--) + free_irq(m, ndev); + } + cpdma_ctlr_stop(priv->dma); pm_runtime_put(&priv->pdev->dev); return ret; } @@ -1659,6 +1680,9 @@ err: */ static int emac_dev_stop(struct net_device *ndev) { + struct resource *res; + int i = 0; + int irq_num; struct emac_priv *priv = netdev_priv(ndev); struct device *emac_dev = &ndev->dev; @@ -1674,6 +1698,13 @@ static int emac_dev_stop(struct net_device *ndev) if (priv->phydev) phy_disconnect(priv->phydev); + /* Free IRQ */ + while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, i))) { + for (irq_num = res->start; irq_num <= res->end; irq_num++) + free_irq(irq_num, priv->ndev); + i++; + } + if (netif_msg_drv(priv)) dev_notice(emac_dev, "DaVinci EMAC: %s stopped\n", ndev->name); diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index ef312bc6b865..6ac20a6738f4 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -923,7 +923,7 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) { dev_err(&pdev->dev, "32-bit PCI DMA addresses not supported by the card!?\n"); - goto err_out; + goto err_out_pci_disable; } /* sanity check */ @@ -931,7 +931,7 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) (pci_resource_len(pdev, 1) < io_size)) { rc = -EIO; dev_err(&pdev->dev, "Insufficient PCI resources, aborting\n"); - goto err_out; + goto err_out_pci_disable; } pioaddr = pci_resource_start(pdev, 0); @@ -942,7 +942,7 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev = alloc_etherdev(sizeof(struct rhine_private)); if (!dev) { rc = -ENOMEM; - goto err_out; + goto err_out_pci_disable; } SET_NETDEV_DEV(dev, &pdev->dev); @@ -1084,6 +1084,8 @@ err_out_free_res: pci_release_regions(pdev); err_out_free_netdev: free_netdev(dev); +err_out_pci_disable: + pci_disable_device(pdev); err_out: return rc; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7141a1937360..d6fce9750b95 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -442,6 +442,8 @@ static int netvsc_probe(struct hv_device *dev, if (!net) return -ENOMEM; + netif_carrier_off(net); + net_device_ctx = netdev_priv(net); net_device_ctx->device_ctx = dev; hv_set_drvdata(dev, net); @@ -473,6 +475,8 @@ static int netvsc_probe(struct hv_device *dev, pr_err("Unable to register netdev.\n"); rndis_filter_device_remove(dev); free_netdev(net); + } else { + schedule_delayed_work(&net_device_ctx->dwork, 0); } return ret; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 1084e5de3ceb..b54fd257652b 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -243,6 +243,22 @@ static int rndis_filter_send_request(struct rndis_device *dev, return ret; } +static void rndis_set_link_state(struct rndis_device *rdev, + struct rndis_request *request) +{ + u32 link_status; + struct rndis_query_complete *query_complete; + + query_complete = &request->response_msg.msg.query_complete; + + if (query_complete->status == RNDIS_STATUS_SUCCESS && + query_complete->info_buflen == sizeof(u32)) { + memcpy(&link_status, (void *)((unsigned long)query_complete + + query_complete->info_buf_offset), sizeof(u32)); + rdev->link_state = link_status != 0; + } +} + static void rndis_filter_receive_response(struct rndis_device *dev, struct rndis_message *resp) { @@ -272,6 +288,10 @@ static void rndis_filter_receive_response(struct rndis_device *dev, sizeof(struct rndis_message) + RNDIS_EXT_LEN) { memcpy(&request->response_msg, resp, resp->msg_len); + if (request->request_msg.ndis_msg_type == + RNDIS_MSG_QUERY && request->request_msg.msg. + query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS) + rndis_set_link_state(dev, request); } else { netdev_err(ndev, "rndis response buffer overflow " @@ -620,7 +640,6 @@ static int rndis_filter_query_device_link_status(struct rndis_device *dev) ret = rndis_filter_query_device(dev, RNDIS_OID_GEN_MEDIA_CONNECT_STATUS, &link_status, &size); - dev->link_state = (link_status != 0) ? true : false; return ret; } diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index ab31544bc254..a30258aad139 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -546,12 +546,12 @@ at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb) int rc; unsigned long flags; - spin_lock(&lp->lock); + spin_lock_irqsave(&lp->lock, flags); if (lp->irq_busy) { - spin_unlock(&lp->lock); + spin_unlock_irqrestore(&lp->lock, flags); return -EBUSY; } - spin_unlock(&lp->lock); + spin_unlock_irqrestore(&lp->lock, flags); might_sleep(); @@ -725,10 +725,11 @@ static void at86rf230_irqwork_level(struct work_struct *work) static irqreturn_t at86rf230_isr(int irq, void *data) { struct at86rf230_local *lp = data; + unsigned long flags; - spin_lock(&lp->lock); + spin_lock_irqsave(&lp->lock, flags); lp->irq_busy = 1; - spin_unlock(&lp->lock); + spin_unlock_irqrestore(&lp->lock, flags); schedule_work(&lp->irqwork); diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index c14d39bf32d0..d7b2e947184b 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -180,7 +180,8 @@ static void ifb_setup(struct net_device *dev) dev->tx_queue_len = TX_Q_LIMIT; dev->features |= IFB_FEATURES; - dev->vlan_features |= IFB_FEATURES; + dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index a5d21893670d..1831fb7cd017 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -506,6 +506,9 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) static struct lock_class_key macvlan_netdev_xmit_lock_key; static struct lock_class_key macvlan_netdev_addr_lock_key; +#define ALWAYS_ON_FEATURES \ + (NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \ @@ -539,7 +542,7 @@ static int macvlan_init(struct net_device *dev) dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; - dev->features |= NETIF_F_LLTX; + dev->features |= ALWAYS_ON_FEATURES; dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; @@ -699,7 +702,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features = netdev_increment_features(vlan->lowerdev->features, features, mask); - features |= NETIF_F_LLTX; + features |= ALWAYS_ON_FEATURES; return features; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 19c9eca0ef26..76d96b9ebcdb 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -164,9 +164,9 @@ static const struct phy_setting settings[] = { * of that setting. Returns the index of the last setting if * none of the others match. */ -static inline int phy_find_setting(int speed, int duplex) +static inline unsigned int phy_find_setting(int speed, int duplex) { - int idx = 0; + unsigned int idx = 0; while (idx < ARRAY_SIZE(settings) && (settings[idx].speed != speed || settings[idx].duplex != duplex)) @@ -185,7 +185,7 @@ static inline int phy_find_setting(int speed, int duplex) * the mask in features. Returns the index of the last setting * if nothing else matches. */ -static inline int phy_find_valid(int idx, u32 features) +static inline unsigned int phy_find_valid(unsigned int idx, u32 features) { while (idx < MAX_NUM_SETTINGS && !(settings[idx].setting & features)) idx++; @@ -204,7 +204,7 @@ static inline int phy_find_valid(int idx, u32 features) static void phy_sanitize_settings(struct phy_device *phydev) { u32 features = phydev->supported; - int idx; + unsigned int idx; /* Sanitize settings based on PHY capabilities */ if ((features & SUPPORTED_Autoneg) == 0) @@ -954,7 +954,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) (phydev->interface == PHY_INTERFACE_MODE_RGMII))) { int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv; - int idx, status; + int status; + unsigned int idx; /* Read phy status to properly get the right settings */ status = phy_read_status(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 82514e72b3d8..2f6989b1e0dc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -683,10 +683,9 @@ EXPORT_SYMBOL(phy_detach); int phy_suspend(struct phy_device *phydev) { struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver); - struct ethtool_wolinfo wol; + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; /* If the device has WOL enabled, we cannot suspend the PHY */ - wol.cmd = ETHTOOL_GWOL; phy_ethtool_get_wol(phydev, &wol); if (wol.wolopts) return -EBUSY; @@ -916,6 +915,8 @@ int genphy_read_status(struct phy_device *phydev) int err; int lpa; int lpagb = 0; + int common_adv; + int common_adv_gb = 0; /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); @@ -937,7 +938,7 @@ int genphy_read_status(struct phy_device *phydev) phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb); - lpagb &= adv << 2; + common_adv_gb = lpagb & adv << 2; } lpa = phy_read(phydev, MII_LPA); @@ -950,25 +951,25 @@ int genphy_read_status(struct phy_device *phydev) if (adv < 0) return adv; - lpa &= adv; + common_adv = lpa & adv; phydev->speed = SPEED_10; phydev->duplex = DUPLEX_HALF; phydev->pause = 0; phydev->asym_pause = 0; - if (lpagb & (LPA_1000FULL | LPA_1000HALF)) { + if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) { phydev->speed = SPEED_1000; - if (lpagb & LPA_1000FULL) + if (common_adv_gb & LPA_1000FULL) phydev->duplex = DUPLEX_FULL; - } else if (lpa & (LPA_100FULL | LPA_100HALF)) { + } else if (common_adv & (LPA_100FULL | LPA_100HALF)) { phydev->speed = SPEED_100; - if (lpa & LPA_100FULL) + if (common_adv & LPA_100FULL) phydev->duplex = DUPLEX_FULL; } else - if (lpa & LPA_10FULL) + if (common_adv & LPA_10FULL) phydev->duplex = DUPLEX_FULL; if (phydev->duplex == DUPLEX_FULL) { diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8fe9cb7d0f72..26f8635b027d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1686,7 +1686,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->features = dev->hw_features; - dev->vlan_features = dev->features; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, file, false); diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index 433f0a00c683..e2797f1e1b31 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_USB_HSO) += hso.o obj-$(CONFIG_USB_NET_AX8817X) += asix.o asix-y := asix_devices.o asix_common.o ax88172a.o obj-$(CONFIG_USB_NET_AX88179_178A) += ax88179_178a.o -obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o r815x.o +obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o obj-$(CONFIG_USB_NET_CDC_EEM) += cdc_eem.o obj-$(CONFIG_USB_NET_DM9601) += dm9601.o obj-$(CONFIG_USB_NET_SR9700) += sr9700.o diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 955df81a4358..054e59ca6946 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1029,20 +1029,12 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) dev->mii.phy_id = 0x03; dev->mii.supports_gmii = 1; - if (usb_device_no_sg_constraint(dev->udev)) - dev->can_dma_sg = 1; - dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; - if (dev->can_dma_sg) { - dev->net->features |= NETIF_F_SG | NETIF_F_TSO; - dev->net->hw_features |= NETIF_F_SG | NETIF_F_TSO; - } - /* Enable checksum offload */ *tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP | AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6; @@ -1395,6 +1387,19 @@ static const struct driver_info ax88178a_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info dlink_dub1312_info = { + .description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct driver_info sitecom_info = { .description = "Sitecom USB 3.0 to Gigabit Adapter", .bind = ax88179_bind, @@ -1421,6 +1426,19 @@ static const struct driver_info samsung_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info lenovo_info = { + .description = "Lenovo OneLinkDock Gigabit LAN", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct usb_device_id products[] = { { /* ASIX AX88179 10/100/1000 */ @@ -1431,6 +1449,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0b95, 0x178a), .driver_info = (unsigned long)&ax88178a_info, }, { + /* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */ + USB_DEVICE(0x2001, 0x4a00), + .driver_info = (unsigned long)&dlink_dub1312_info, +}, { /* Sitecom USB 3.0 to Gigabit Adapter */ USB_DEVICE(0x0df6, 0x0072), .driver_info = (unsigned long)&sitecom_info, @@ -1438,6 +1460,10 @@ static const struct usb_device_id products[] = { /* Samsung USB Ethernet Adapter */ USB_DEVICE(0x04e8, 0xa100), .driver_info = (unsigned long)&samsung_info, +}, { + /* Lenovo OneLinkDock Gigabit LAN */ + USB_DEVICE(0x17ef, 0x304b), + .driver_info = (unsigned long)&lenovo_info, }, { }, }; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 42e176912c8e..bd363b27e854 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -652,6 +652,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* Samsung USB Ethernet Adapters */ +{ + USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, 0xa101, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* WHITELIST!!! * * CDC Ether uses two interfaces, not necessarily consecutive. diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index dbff290ed0e4..d350d2795e10 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -68,7 +68,6 @@ static struct usb_driver cdc_ncm_driver; static int cdc_ncm_setup(struct usbnet *dev) { struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; - struct usb_cdc_ncm_ntb_parameters ncm_parm; u32 val; u8 flags; u8 iface_no; @@ -82,22 +81,22 @@ static int cdc_ncm_setup(struct usbnet *dev) err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_PARAMETERS, USB_TYPE_CLASS | USB_DIR_IN |USB_RECIP_INTERFACE, - 0, iface_no, &ncm_parm, - sizeof(ncm_parm)); + 0, iface_no, &ctx->ncm_parm, + sizeof(ctx->ncm_parm)); if (err < 0) { dev_err(&dev->intf->dev, "failed GET_NTB_PARAMETERS\n"); return err; /* GET_NTB_PARAMETERS is required */ } /* read correct set of parameters according to device mode */ - ctx->rx_max = le32_to_cpu(ncm_parm.dwNtbInMaxSize); - ctx->tx_max = le32_to_cpu(ncm_parm.dwNtbOutMaxSize); - ctx->tx_remainder = le16_to_cpu(ncm_parm.wNdpOutPayloadRemainder); - ctx->tx_modulus = le16_to_cpu(ncm_parm.wNdpOutDivisor); - ctx->tx_ndp_modulus = le16_to_cpu(ncm_parm.wNdpOutAlignment); + ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize); + ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize); + ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder); + ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor); + ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment); /* devices prior to NCM Errata shall set this field to zero */ - ctx->tx_max_datagrams = le16_to_cpu(ncm_parm.wNtbOutMaxDatagrams); - ntb_fmt_supported = le16_to_cpu(ncm_parm.bmNtbFormatsSupported); + ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams); + ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported); /* there are some minor differences in NCM and MBIM defaults */ if (cdc_ncm_comm_intf_is_mbim(ctx->control->cur_altsetting)) { @@ -146,7 +145,7 @@ static int cdc_ncm_setup(struct usbnet *dev) } /* inform device about NTB input size changes */ - if (ctx->rx_max != le32_to_cpu(ncm_parm.dwNtbInMaxSize)) { + if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) { __le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max); err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE, @@ -162,14 +161,6 @@ static int cdc_ncm_setup(struct usbnet *dev) dev_dbg(&dev->intf->dev, "Using default maximum transmit length=%d\n", CDC_NCM_NTB_MAX_SIZE_TX); ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX; - - /* Adding a pad byte here simplifies the handling in - * cdc_ncm_fill_tx_frame, by making tx_max always - * represent the real skb max size. - */ - if (ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0) - ctx->tx_max++; - } /* @@ -439,6 +430,10 @@ advance: goto error2; } + /* initialize data interface */ + if (cdc_ncm_setup(dev)) + goto error2; + /* configure data interface */ temp = usb_set_interface(dev->udev, iface_no, data_altsetting); if (temp) { @@ -453,12 +448,6 @@ advance: goto error2; } - /* initialize data interface */ - if (cdc_ncm_setup(dev)) { - dev_dbg(&intf->dev, "cdc_ncm_setup() failed\n"); - goto error2; - } - usb_set_intfdata(ctx->data, dev); usb_set_intfdata(ctx->control, dev); @@ -475,6 +464,15 @@ advance: dev->hard_mtu = ctx->tx_max; dev->rx_urb_size = ctx->rx_max; + /* cdc_ncm_setup will override dwNtbOutMaxSize if it is + * outside the sane range. Adding a pad byte here if necessary + * simplifies the handling in cdc_ncm_fill_tx_frame, making + * tx_max always represent the real skb max size. + */ + if (ctx->tx_max != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) && + ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0) + ctx->tx_max++; + return 0; error2: diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d89dbe395ad2..adb12f349a61 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -449,9 +449,6 @@ enum rtl8152_flags { #define MCU_TYPE_PLA 0x0100 #define MCU_TYPE_USB 0x0000 -#define REALTEK_USB_DEVICE(vend, prod) \ - USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC) - struct rx_desc { __le32 opts1; #define RX_LEN_MASK 0x7fff @@ -2739,6 +2736,12 @@ static int rtl8152_probe(struct usb_interface *intf, struct net_device *netdev; int ret; + if (udev->actconfig->desc.bConfigurationValue != 1) { + usb_driver_set_configuration(udev, 1); + return -ENODEV; + } + + usb_reset_device(udev); netdev = alloc_etherdev(sizeof(struct r8152)); if (!netdev) { dev_err(&intf->dev, "Out of memory\n"); @@ -2819,9 +2822,9 @@ static void rtl8152_disconnect(struct usb_interface *intf) /* table of devices that work with this driver */ static struct usb_device_id rtl8152_table[] = { - {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)}, - {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)}, - {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)}, + {USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)}, + {USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)}, + {USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)}, {} }; diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c deleted file mode 100644 index f0a8791b7636..000000000000 --- a/drivers/net/usb/r815x.c +++ /dev/null @@ -1,248 +0,0 @@ -#include <linux/module.h> -#include <linux/netdevice.h> -#include <linux/mii.h> -#include <linux/usb.h> -#include <linux/usb/cdc.h> -#include <linux/usb/usbnet.h> - -#define RTL815x_REQT_READ 0xc0 -#define RTL815x_REQT_WRITE 0x40 -#define RTL815x_REQ_GET_REGS 0x05 -#define RTL815x_REQ_SET_REGS 0x05 - -#define MCU_TYPE_PLA 0x0100 -#define OCP_BASE 0xe86c -#define BASE_MII 0xa400 - -#define BYTE_EN_DWORD 0xff -#define BYTE_EN_WORD 0x33 -#define BYTE_EN_BYTE 0x11 - -#define R815x_PHY_ID 32 -#define REALTEK_VENDOR_ID 0x0bda - - -static int pla_read_word(struct usb_device *udev, u16 index) -{ - int ret; - u8 shift = index & 2; - __le32 *tmp; - - tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - index &= ~3; - - ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), - RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, - index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500); - if (ret < 0) - goto out2; - - ret = __le32_to_cpu(*tmp); - ret >>= (shift * 8); - ret &= 0xffff; - -out2: - kfree(tmp); - return ret; -} - -static int pla_write_word(struct usb_device *udev, u16 index, u32 data) -{ - __le32 *tmp; - u32 mask = 0xffff; - u16 byen = BYTE_EN_WORD; - u8 shift = index & 2; - int ret; - - tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - data &= mask; - - if (shift) { - byen <<= shift; - mask <<= (shift * 8); - data <<= (shift * 8); - index &= ~3; - } - - ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), - RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, - index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500); - if (ret < 0) - goto out3; - - data |= __le32_to_cpu(*tmp) & ~mask; - *tmp = __cpu_to_le32(data); - - ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), - RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE, - index, MCU_TYPE_PLA | byen, tmp, sizeof(*tmp), - 500); - -out3: - kfree(tmp); - return ret; -} - -static int ocp_reg_read(struct usbnet *dev, u16 addr) -{ - u16 ocp_base, ocp_index; - int ret; - - ocp_base = addr & 0xf000; - ret = pla_write_word(dev->udev, OCP_BASE, ocp_base); - if (ret < 0) - goto out; - - ocp_index = (addr & 0x0fff) | 0xb000; - ret = pla_read_word(dev->udev, ocp_index); - -out: - return ret; -} - -static int ocp_reg_write(struct usbnet *dev, u16 addr, u16 data) -{ - u16 ocp_base, ocp_index; - int ret; - - ocp_base = addr & 0xf000; - ret = pla_write_word(dev->udev, OCP_BASE, ocp_base); - if (ret < 0) - goto out1; - - ocp_index = (addr & 0x0fff) | 0xb000; - ret = pla_write_word(dev->udev, ocp_index, data); - -out1: - return ret; -} - -static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg) -{ - struct usbnet *dev = netdev_priv(netdev); - int ret; - - if (phy_id != R815x_PHY_ID) - return -EINVAL; - - if (usb_autopm_get_interface(dev->intf) < 0) - return -ENODEV; - - ret = ocp_reg_read(dev, BASE_MII + reg * 2); - - usb_autopm_put_interface(dev->intf); - return ret; -} - -static -void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val) -{ - struct usbnet *dev = netdev_priv(netdev); - - if (phy_id != R815x_PHY_ID) - return; - - if (usb_autopm_get_interface(dev->intf) < 0) - return; - - ocp_reg_write(dev, BASE_MII + reg * 2, val); - - usb_autopm_put_interface(dev->intf); -} - -static int r8153_bind(struct usbnet *dev, struct usb_interface *intf) -{ - int status; - - status = usbnet_cdc_bind(dev, intf); - if (status < 0) - return status; - - dev->mii.dev = dev->net; - dev->mii.mdio_read = r815x_mdio_read; - dev->mii.mdio_write = r815x_mdio_write; - dev->mii.phy_id_mask = 0x3f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = R815x_PHY_ID; - dev->mii.supports_gmii = 1; - - return status; -} - -static int r8152_bind(struct usbnet *dev, struct usb_interface *intf) -{ - int status; - - status = usbnet_cdc_bind(dev, intf); - if (status < 0) - return status; - - dev->mii.dev = dev->net; - dev->mii.mdio_read = r815x_mdio_read; - dev->mii.mdio_write = r815x_mdio_write; - dev->mii.phy_id_mask = 0x3f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = R815x_PHY_ID; - dev->mii.supports_gmii = 0; - - return status; -} - -static const struct driver_info r8152_info = { - .description = "RTL8152 ECM Device", - .flags = FLAG_ETHER | FLAG_POINTTOPOINT, - .bind = r8152_bind, - .unbind = usbnet_cdc_unbind, - .status = usbnet_cdc_status, - .manage_power = usbnet_manage_power, -}; - -static const struct driver_info r8153_info = { - .description = "RTL8153 ECM Device", - .flags = FLAG_ETHER | FLAG_POINTTOPOINT, - .bind = r8153_bind, - .unbind = usbnet_cdc_unbind, - .status = usbnet_cdc_status, - .manage_power = usbnet_manage_power, -}; - -static const struct usb_device_id products[] = { -{ - USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = (unsigned long) &r8152_info, -}, - -{ - USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = (unsigned long) &r8153_info, -}, - - { }, /* END */ -}; -MODULE_DEVICE_TABLE(usb, products); - -static struct usb_driver r815x_driver = { - .name = "r815x", - .id_table = products, - .probe = usbnet_probe, - .disconnect = usbnet_disconnect, - .suspend = usbnet_suspend, - .resume = usbnet_resume, - .reset_resume = usbnet_resume, - .supports_autosuspend = 1, - .disable_hub_initiated_lpm = 1, -}; - -module_usb_driver(r815x_driver); - -MODULE_AUTHOR("Hayes Wang"); -MODULE_DESCRIPTION("Realtek USB ECM device"); -MODULE_LICENSE("GPL"); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index dd10d5817d2a..f9e96c427558 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -752,14 +752,12 @@ EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs); // precondition: never called in_interrupt static void usbnet_terminate_urbs(struct usbnet *dev) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup); DECLARE_WAITQUEUE(wait, current); int temp; /* ensure there are no more active urbs */ - add_wait_queue(&unlink_wakeup, &wait); + add_wait_queue(&dev->wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); - dev->wait = &unlink_wakeup; temp = unlink_urbs(dev, &dev->txq) + unlink_urbs(dev, &dev->rxq); @@ -773,15 +771,14 @@ static void usbnet_terminate_urbs(struct usbnet *dev) "waited for %d urb completions\n", temp); } set_current_state(TASK_RUNNING); - dev->wait = NULL; - remove_wait_queue(&unlink_wakeup, &wait); + remove_wait_queue(&dev->wait, &wait); } int usbnet_stop (struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct driver_info *info = dev->driver_info; - int retval; + int retval, pm; clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue (net); @@ -791,6 +788,8 @@ int usbnet_stop (struct net_device *net) net->stats.rx_packets, net->stats.tx_packets, net->stats.rx_errors, net->stats.tx_errors); + /* to not race resume */ + pm = usb_autopm_get_interface(dev->intf); /* allow minidriver to stop correctly (wireless devices to turn off * radio etc) */ if (info->stop) { @@ -817,6 +816,9 @@ int usbnet_stop (struct net_device *net) dev->flags = 0; del_timer_sync (&dev->delay); tasklet_kill (&dev->bh); + if (!pm) + usb_autopm_put_interface(dev->intf); + if (info->manage_power && !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags)) info->manage_power(dev, 0); @@ -1437,11 +1439,12 @@ static void usbnet_bh (unsigned long param) /* restart RX again after disabling due to high error rate */ clear_bit(EVENT_RX_KILL, &dev->flags); - // waiting for all pending urbs to complete? - if (dev->wait) { - if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) { - wake_up (dev->wait); - } + /* waiting for all pending urbs to complete? + * only then can we forgo submitting anew + */ + if (waitqueue_active(&dev->wait)) { + if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0) + wake_up_all(&dev->wait); // or are we maybe short a few urbs? } else if (netif_running (dev->net) && @@ -1580,6 +1583,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->driver_name = name; dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK); + init_waitqueue_head(&dev->wait); skb_queue_head_init (&dev->rxq); skb_queue_head_init (&dev->txq); skb_queue_head_init (&dev->done); @@ -1791,9 +1795,10 @@ int usbnet_resume (struct usb_interface *intf) spin_unlock_irq(&dev->txq.lock); if (test_bit(EVENT_DEV_OPEN, &dev->flags)) { - /* handle remote wakeup ASAP */ - if (!dev->wait && - netif_device_present(dev->net) && + /* handle remote wakeup ASAP + * we cannot race against stop + */ + if (netif_device_present(dev->net) && !timer_pending(&dev->delay) && !test_bit(EVENT_RX_HALT, &dev->flags)) rx_alloc_submit(dev, GFP_NOIO); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 2ec2041b62d4..c0e7c64765ab 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -285,7 +285,11 @@ static void veth_setup(struct net_device *dev) dev->ethtool_ops = &veth_ethtool_ops; dev->features |= NETIF_F_LLTX; dev->features |= VETH_FEATURES; - dev->vlan_features = dev->features; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); dev->destructor = veth_dev_free; dev->hw_features = VETH_FEATURES; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d75f8edf4fb3..841b60831df1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -671,8 +671,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp) if (err) break; } while (rq->vq->num_free); - if (unlikely(!virtqueue_kick(rq->vq))) - return false; + virtqueue_kick(rq->vq); return !oom; } @@ -877,7 +876,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) err = xmit_skb(sq, skb); /* This should not happen! */ - if (unlikely(err) || unlikely(!virtqueue_kick(sq->vq))) { + if (unlikely(err)) { dev->stats.tx_fifo_errors++; if (net_ratelimit()) dev_warn(&dev->dev, @@ -886,6 +885,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) kfree_skb(skb); return NETDEV_TX_OK; } + virtqueue_kick(sq->vq); /* Don't wait up for transmitted skbs to be freed. */ skb_orphan(skb); @@ -1711,7 +1711,8 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3be786faaaec..0fa3b44f7342 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1762,11 +1762,20 @@ vmxnet3_netpoll(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) - vmxnet3_disable_all_intrs(adapter); - - vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size); - vmxnet3_enable_all_intrs(adapter); + switch (adapter->intr.type) { +#ifdef CONFIG_PCI_MSI + case VMXNET3_IT_MSIX: { + int i; + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_msix_rx(0, &adapter->rx_queue[i]); + break; + } +#endif + case VMXNET3_IT_MSI: + default: + vmxnet3_intr(0, adapter->netdev); + break; + } } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index b0f705c2378f..1236812c7be6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1318,6 +1318,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) neigh_release(n); + if (reply == NULL) + goto out; + skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; @@ -1339,15 +1342,103 @@ out: } #if IS_ENABLED(CONFIG_IPV6) + +static struct sk_buff *vxlan_na_create(struct sk_buff *request, + struct neighbour *n, bool isrouter) +{ + struct net_device *dev = request->dev; + struct sk_buff *reply; + struct nd_msg *ns, *na; + struct ipv6hdr *pip6; + u8 *daddr; + int na_olen = 8; /* opt hdr + ETH_ALEN for target */ + int ns_olen; + int i, len; + + if (dev == NULL) + return NULL; + + len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + + sizeof(*na) + na_olen + dev->needed_tailroom; + reply = alloc_skb(len, GFP_ATOMIC); + if (reply == NULL) + return NULL; + + reply->protocol = htons(ETH_P_IPV6); + reply->dev = dev; + skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); + skb_push(reply, sizeof(struct ethhdr)); + skb_set_mac_header(reply, 0); + + ns = (struct nd_msg *)skb_transport_header(request); + + daddr = eth_hdr(request)->h_source; + ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns); + for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { + if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + break; + } + } + + /* Ethernet header */ + ether_addr_copy(eth_hdr(reply)->h_dest, daddr); + ether_addr_copy(eth_hdr(reply)->h_source, n->ha); + eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); + reply->protocol = htons(ETH_P_IPV6); + + skb_pull(reply, sizeof(struct ethhdr)); + skb_set_network_header(reply, 0); + skb_put(reply, sizeof(struct ipv6hdr)); + + /* IPv6 header */ + + pip6 = ipv6_hdr(reply); + memset(pip6, 0, sizeof(struct ipv6hdr)); + pip6->version = 6; + pip6->priority = ipv6_hdr(request)->priority; + pip6->nexthdr = IPPROTO_ICMPV6; + pip6->hop_limit = 255; + pip6->daddr = ipv6_hdr(request)->saddr; + pip6->saddr = *(struct in6_addr *)n->primary_key; + + skb_pull(reply, sizeof(struct ipv6hdr)); + skb_set_transport_header(reply, 0); + + na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); + + /* Neighbor Advertisement */ + memset(na, 0, sizeof(*na)+na_olen); + na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + na->icmph.icmp6_router = isrouter; + na->icmph.icmp6_override = 1; + na->icmph.icmp6_solicited = 1; + na->target = ns->target; + ether_addr_copy(&na->opt[2], n->ha); + na->opt[0] = ND_OPT_TARGET_LL_ADDR; + na->opt[1] = na_olen >> 3; + + na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, + &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, + csum_partial(na, sizeof(*na)+na_olen, 0)); + + pip6->payload_len = htons(sizeof(*na)+na_olen); + + skb_push(reply, sizeof(struct ipv6hdr)); + + reply->ip_summed = CHECKSUM_UNNECESSARY; + + return reply; +} + static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct neighbour *n; - union vxlan_addr ipa; + struct nd_msg *msg; const struct ipv6hdr *iphdr; const struct in6_addr *saddr, *daddr; - struct nd_msg *msg; - struct inet6_dev *in6_dev = NULL; + struct neighbour *n; + struct inet6_dev *in6_dev; in6_dev = __in6_dev_get(dev); if (!in6_dev) @@ -1360,19 +1451,20 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) saddr = &iphdr->saddr; daddr = &iphdr->daddr; - if (ipv6_addr_loopback(daddr) || - ipv6_addr_is_multicast(daddr)) - goto out; - msg = (struct nd_msg *)skb_transport_header(skb); if (msg->icmph.icmp6_code != 0 || msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) goto out; - n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev); + if (ipv6_addr_loopback(daddr) || + ipv6_addr_is_multicast(&msg->target)) + goto out; + + n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_fdb *f; + struct sk_buff *reply; if (!(n->nud_state & NUD_CONNECTED)) { neigh_release(n); @@ -1386,13 +1478,23 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) goto out; } - ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target, - !!in6_dev->cnf.forwarding, - true, false, false); + reply = vxlan_na_create(skb, n, + !!(f ? f->flags & NTF_ROUTER : 0)); + neigh_release(n); + + if (reply == NULL) + goto out; + + if (netif_rx_ni(reply) == NET_RX_DROP) + dev->stats.rx_dropped++; + } else if (vxlan->flags & VXLAN_F_L3MISS) { - ipa.sin6.sin6_addr = *daddr; - ipa.sa.sa_family = AF_INET6; + union vxlan_addr ipa = { + .sin6.sin6_addr = msg->target, + .sa.sa_family = AF_INET6, + }; + vxlan_ip_miss(dev, &ipa); } diff --git a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h index 1cc13569b17b..1b6b4d0cfa97 100644 --- a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h +++ b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h @@ -57,7 +57,7 @@ static const u32 ar9462_2p0_baseband_postamble[][5] = { {0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e}, {0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, {0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c}, - {0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce}, + {0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5}, {0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021}, {0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282}, {0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27}, @@ -96,7 +96,7 @@ static const u32 ar9462_2p0_baseband_postamble[][5] = { {0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000}, {0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, {0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c}, - {0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce}, + {0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa}, {0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550}, }; diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 11eab9f01fd8..9078a6c5a74e 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -1534,7 +1534,7 @@ EXPORT_SYMBOL(ath9k_hw_check_nav); bool ath9k_hw_check_alive(struct ath_hw *ah) { int count = 50; - u32 reg; + u32 reg, last_val; if (AR_SREV_9300(ah)) return !ath9k_hw_detect_mac_hang(ah); @@ -1542,9 +1542,14 @@ bool ath9k_hw_check_alive(struct ath_hw *ah) if (AR_SREV_9285_12_OR_LATER(ah)) return true; + last_val = REG_READ(ah, AR_OBS_BUS_1); do { reg = REG_READ(ah, AR_OBS_BUS_1); + if (reg != last_val) + return true; + udelay(1); + last_val = reg; if ((reg & 0x7E7FFFEF) == 0x00702400) continue; diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index a0ebdd000fc2..82e340d3ec60 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -732,11 +732,18 @@ static struct ath_rxbuf *ath_get_next_rx_buf(struct ath_softc *sc, return NULL; /* - * mark descriptor as zero-length and set the 'more' - * flag to ensure that both buffers get discarded + * Re-check previous descriptor, in case it has been filled + * in the mean time. */ - rs->rs_datalen = 0; - rs->rs_more = true; + ret = ath9k_hw_rxprocdesc(ah, ds, rs); + if (ret == -EINPROGRESS) { + /* + * mark descriptor as zero-length and set the 'more' + * flag to ensure that both buffers get discarded + */ + rs->rs_datalen = 0; + rs->rs_more = true; + } } list_del(&bf->list); @@ -985,32 +992,32 @@ static int ath9k_rx_skb_preprocess(struct ath_softc *sc, struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_hdr *hdr; bool discard_current = sc->rx.discard_next; - int ret = 0; /* * Discard corrupt descriptors which are marked in * ath_get_next_rx_buf(). */ - sc->rx.discard_next = rx_stats->rs_more; if (discard_current) - return -EINVAL; + goto corrupt; + + sc->rx.discard_next = false; /* * Discard zero-length packets. */ if (!rx_stats->rs_datalen) { RX_STAT_INC(rx_len_err); - return -EINVAL; + goto corrupt; } - /* - * rs_status follows rs_datalen so if rs_datalen is too large - * we can take a hint that hardware corrupted it, so ignore - * those frames. - */ + /* + * rs_status follows rs_datalen so if rs_datalen is too large + * we can take a hint that hardware corrupted it, so ignore + * those frames. + */ if (rx_stats->rs_datalen > (common->rx_bufsize - ah->caps.rx_status_len)) { RX_STAT_INC(rx_len_err); - return -EINVAL; + goto corrupt; } /* Only use status info from the last fragment */ @@ -1024,10 +1031,8 @@ static int ath9k_rx_skb_preprocess(struct ath_softc *sc, * This is different from the other corrupt descriptor * condition handled above. */ - if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC) { - ret = -EINVAL; - goto exit; - } + if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC) + goto corrupt; hdr = (struct ieee80211_hdr *) (skb->data + ah->caps.rx_status_len); @@ -1043,18 +1048,15 @@ static int ath9k_rx_skb_preprocess(struct ath_softc *sc, if (ath_process_fft(sc, hdr, rx_stats, rx_status->mactime)) RX_STAT_INC(rx_spectral); - ret = -EINVAL; - goto exit; + return -EINVAL; } /* * everything but the rate is checked here, the rate check is done * separately to avoid doing two lookups for a rate for each frame. */ - if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error)) { - ret = -EINVAL; - goto exit; - } + if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error)) + return -EINVAL; if (ath_is_mybeacon(common, hdr)) { RX_STAT_INC(rx_beacons); @@ -1064,15 +1066,11 @@ static int ath9k_rx_skb_preprocess(struct ath_softc *sc, /* * This shouldn't happen, but have a safety check anyway. */ - if (WARN_ON(!ah->curchan)) { - ret = -EINVAL; - goto exit; - } + if (WARN_ON(!ah->curchan)) + return -EINVAL; - if (ath9k_process_rate(common, hw, rx_stats, rx_status)) { - ret =-EINVAL; - goto exit; - } + if (ath9k_process_rate(common, hw, rx_stats, rx_status)) + return -EINVAL; ath9k_process_rssi(common, hw, rx_stats, rx_status); @@ -1087,9 +1085,11 @@ static int ath9k_rx_skb_preprocess(struct ath_softc *sc, sc->rx.num_pkts++; #endif -exit: - sc->rx.discard_next = false; - return ret; + return 0; + +corrupt: + sc->rx.discard_next = rx_stats->rs_more; + return -EINVAL; } static void ath9k_rx_skb_postprocess(struct ath_common *common, diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 0a75e2f68c9d..55897d508a76 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -1444,14 +1444,16 @@ void ath_tx_aggr_sleep(struct ieee80211_sta *sta, struct ath_softc *sc, for (tidno = 0, tid = &an->tid[tidno]; tidno < IEEE80211_NUM_TIDS; tidno++, tid++) { - if (!tid->sched) - continue; - ac = tid->ac; txq = ac->txq; ath_txq_lock(sc, txq); + if (!tid->sched) { + ath_txq_unlock(sc, txq); + continue; + } + buffered = ath_tid_has_buffered(tid); tid->sched = false; @@ -2061,7 +2063,7 @@ static struct ath_buf *ath_tx_setup_buffer(struct ath_softc *sc, ATH_TXBUF_RESET(bf); - if (tid) { + if (tid && ieee80211_is_data_present(hdr->frame_control)) { fragno = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG; seqno = tid->seq_next; hdr->seq_ctrl = cpu_to_le16(tid->seq_next << IEEE80211_SEQ_SEQ_SHIFT); @@ -2184,14 +2186,15 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, txq->stopped = true; } + if (txctl->an && ieee80211_is_data_present(hdr->frame_control)) + tid = ath_get_skb_tid(sc, txctl->an, skb); + if (info->flags & IEEE80211_TX_CTL_PS_RESPONSE) { ath_txq_unlock(sc, txq); txq = sc->tx.uapsdq; ath_txq_lock(sc, txq); } else if (txctl->an && ieee80211_is_data_present(hdr->frame_control)) { - tid = ath_get_skb_tid(sc, txctl->an, skb); - WARN_ON(tid->ac->txq != txctl->txq); if (info->flags & IEEE80211_TX_CTL_CLEAR_PS_FILT) diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c index 3e991897d7ca..ddaa9efd053d 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c @@ -457,7 +457,6 @@ struct brcmf_sdio { u8 tx_hdrlen; /* sdio bus header length for tx packet */ bool txglom; /* host tx glomming enable flag */ - struct sk_buff *txglom_sgpad; /* scatter-gather padding buffer */ u16 head_align; /* buffer pointer alignment */ u16 sgentry_align; /* scatter-gather buffer alignment */ }; @@ -1944,19 +1943,21 @@ static int brcmf_sdio_txpkt_prep_sg(struct brcmf_sdio *bus, if (lastfrm && chain_pad) tail_pad += blksize - chain_pad; if (skb_tailroom(pkt) < tail_pad && pkt->len > blksize) { - pkt_pad = bus->txglom_sgpad; - if (pkt_pad == NULL) - brcmu_pkt_buf_get_skb(tail_pad + tail_chop); + pkt_pad = brcmu_pkt_buf_get_skb(tail_pad + tail_chop + + bus->head_align); if (pkt_pad == NULL) return -ENOMEM; ret = brcmf_sdio_txpkt_hdalign(bus, pkt_pad); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + kfree_skb(pkt_pad); return ret; + } memcpy(pkt_pad->data, pkt->data + pkt->len - tail_chop, tail_chop); *(u32 *)(pkt_pad->cb) = ALIGN_SKB_FLAG + tail_chop; skb_trim(pkt, pkt->len - tail_chop); + skb_trim(pkt_pad, tail_pad + tail_chop); __skb_queue_after(pktq, pkt, pkt_pad); } else { ntail = pkt->data_len + tail_pad - @@ -2011,7 +2012,7 @@ brcmf_sdio_txpkt_prep(struct brcmf_sdio *bus, struct sk_buff_head *pktq, return ret; head_pad = (u16)ret; if (head_pad) - memset(pkt_next->data, 0, head_pad + bus->tx_hdrlen); + memset(pkt_next->data + bus->tx_hdrlen, 0, head_pad); total_len += pkt_next->len; @@ -3486,10 +3487,6 @@ static int brcmf_sdio_bus_preinit(struct device *dev) bus->txglom = false; value = 1; pad_size = bus->sdiodev->func[2]->cur_blksize << 1; - bus->txglom_sgpad = brcmu_pkt_buf_get_skb(pad_size); - if (!bus->txglom_sgpad) - brcmf_err("allocating txglom padding skb failed, reduced performance\n"); - err = brcmf_iovar_data_set(bus->sdiodev->dev, "bus:rxglom", &value, sizeof(u32)); if (err < 0) { @@ -4053,7 +4050,6 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus) brcmf_sdio_chip_detach(&bus->ci); } - brcmu_pkt_buf_free_skb(bus->txglom_sgpad); kfree(bus->rxbuf); kfree(bus->hdrbuf); kfree(bus); diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c index d36e252d2ccb..596525528f50 100644 --- a/drivers/net/wireless/hostap/hostap_ap.c +++ b/drivers/net/wireless/hostap/hostap_ap.c @@ -147,7 +147,7 @@ static void ap_free_sta(struct ap_data *ap, struct sta_info *sta) if (!sta->ap && sta->u.sta.challenge) kfree(sta->u.sta.challenge); - del_timer(&sta->timer); + del_timer_sync(&sta->timer); #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */ kfree(sta); diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c index c0d070c5df5e..9cdd91cdf661 100644 --- a/drivers/net/wireless/iwlwifi/dvm/sta.c +++ b/drivers/net/wireless/iwlwifi/dvm/sta.c @@ -590,6 +590,7 @@ void iwl_deactivate_station(struct iwl_priv *priv, const u8 sta_id, sizeof(priv->tid_data[sta_id][tid])); priv->stations[sta_id].used &= ~IWL_STA_DRIVER_ACTIVE; + priv->stations[sta_id].used &= ~IWL_STA_UCODE_INPROGRESS; priv->num_stations--; diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c index a6839dfcb82d..398dd096674c 100644 --- a/drivers/net/wireless/iwlwifi/dvm/tx.c +++ b/drivers/net/wireless/iwlwifi/dvm/tx.c @@ -1291,8 +1291,6 @@ int iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv, struct iwl_compressed_ba_resp *ba_resp = (void *)pkt->data; struct iwl_ht_agg *agg; struct sk_buff_head reclaimed_skbs; - struct ieee80211_tx_info *info; - struct ieee80211_hdr *hdr; struct sk_buff *skb; int sta_id; int tid; @@ -1379,22 +1377,28 @@ int iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv, freed = 0; skb_queue_walk(&reclaimed_skbs, skb) { - hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_hdr *hdr = (void *)skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (ieee80211_is_data_qos(hdr->frame_control)) freed++; else WARN_ON_ONCE(1); - info = IEEE80211_SKB_CB(skb); iwl_trans_free_tx_cmd(priv->trans, info->driver_data[1]); + memset(&info->status, 0, sizeof(info->status)); + /* Packet was transmitted successfully, failures come as single + * frames because before failing a frame the firmware transmits + * it without aggregation at least once. + */ + info->flags |= IEEE80211_TX_STAT_ACK; + if (freed == 1) { /* this is the first skb we deliver in this batch */ /* put the rate scaling data there */ info = IEEE80211_SKB_CB(skb); memset(&info->status, 0, sizeof(info->status)); - info->flags |= IEEE80211_TX_STAT_ACK; info->flags |= IEEE80211_TX_STAT_AMPDU; info->status.ampdu_ack_len = ba_resp->txed_2_done; info->status.ampdu_len = ba_resp->txed; diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c index 76cde6ce6551..18a895a949d4 100644 --- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c +++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c @@ -872,8 +872,11 @@ void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif, lockdep_assert_held(&mvm->mutex); - /* Rssi update while not associated ?! */ - if (WARN_ON_ONCE(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)) + /* + * Rssi update while not associated - can happen since the statistics + * are handled asynchronously + */ + if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT) return; /* No BT - reports should be disabled */ diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h index e4ead86f06d6..2b0ba1fc3c82 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h @@ -152,7 +152,7 @@ enum iwl_power_scheme { IWL_POWER_SCHEME_LP }; -#define IWL_CONN_MAX_LISTEN_INTERVAL 70 +#define IWL_CONN_MAX_LISTEN_INTERVAL 10 #define IWL_UAPSD_AC_INFO (IEEE80211_WMM_IE_STA_QOSINFO_AC_VO |\ IEEE80211_WMM_IE_STA_QOSINFO_AC_VI |\ IEEE80211_WMM_IE_STA_QOSINFO_AC_BK |\ diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c index 4df12fa9d336..76ee486039d7 100644 --- a/drivers/net/wireless/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/iwlwifi/mvm/tx.c @@ -822,16 +822,12 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, struct iwl_mvm_ba_notif *ba_notif = (void *)pkt->data; struct sk_buff_head reclaimed_skbs; struct iwl_mvm_tid_data *tid_data; - struct ieee80211_tx_info *info; struct ieee80211_sta *sta; struct iwl_mvm_sta *mvmsta; - struct ieee80211_hdr *hdr; struct sk_buff *skb; int sta_id, tid, freed; - /* "flow" corresponds to Tx queue */ u16 scd_flow = le16_to_cpu(ba_notif->scd_flow); - /* "ssn" is start of block-ack Tx window, corresponds to index * (in Tx queue's circular buffer) of first TFD/frame in window */ u16 ba_resp_scd_ssn = le16_to_cpu(ba_notif->scd_ssn); @@ -888,22 +884,26 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, freed = 0; skb_queue_walk(&reclaimed_skbs, skb) { - hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_hdr *hdr = (void *)skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (ieee80211_is_data_qos(hdr->frame_control)) freed++; else WARN_ON_ONCE(1); - info = IEEE80211_SKB_CB(skb); iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]); + memset(&info->status, 0, sizeof(info->status)); + /* Packet was transmitted successfully, failures come as single + * frames because before failing a frame the firmware transmits + * it without aggregation at least once. + */ + info->flags |= IEEE80211_TX_STAT_ACK; + if (freed == 1) { /* this is the first skb we deliver in this batch */ /* put the rate scaling data there */ - info = IEEE80211_SKB_CB(skb); - memset(&info->status, 0, sizeof(info->status)); - info->flags |= IEEE80211_TX_STAT_ACK; info->flags |= IEEE80211_TX_STAT_AMPDU; info->status.ampdu_ack_len = ba_notif->txed_2_done; info->status.ampdu_len = ba_notif->txed; diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index f47bcbe2945a..3872ead75488 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -359,13 +359,12 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { /* 7265 Series */ {IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5110, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095A, 0x5112, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5100, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095A, 0x510A, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)}, - {IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)}, diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index 32f75007a825..cb6d189bc3e6 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -621,7 +621,7 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy, id = *pos++; elen = *pos++; left -= 2; - if (elen > left || elen == 0) { + if (elen > left) { lbs_deb_scan("scan response: invalid IE fmt\n"); goto done; } diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c index 5e0eec4d71c7..5d9a8084665d 100644 --- a/drivers/net/wireless/mwifiex/11ac.c +++ b/drivers/net/wireless/mwifiex/11ac.c @@ -189,8 +189,7 @@ int mwifiex_cmd_append_11ac_tlv(struct mwifiex_private *priv, vht_cap->header.len = cpu_to_le16(sizeof(struct ieee80211_vht_cap)); memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header), - (u8 *)bss_desc->bcn_vht_cap + - sizeof(struct ieee_types_header), + (u8 *)bss_desc->bcn_vht_cap, le16_to_cpu(vht_cap->header.len)); mwifiex_fill_vht_cap_tlv(priv, vht_cap, bss_desc->bss_band); diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c index 6261f8c53d44..7db1a89fdd95 100644 --- a/drivers/net/wireless/mwifiex/11n.c +++ b/drivers/net/wireless/mwifiex/11n.c @@ -308,8 +308,7 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv, ht_cap->header.len = cpu_to_le16(sizeof(struct ieee80211_ht_cap)); memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header), - (u8 *) bss_desc->bcn_ht_cap + - sizeof(struct ieee_types_header), + (u8 *)bss_desc->bcn_ht_cap, le16_to_cpu(ht_cap->header.len)); mwifiex_fill_cap_info(priv, radio_type, ht_cap); diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c index 03688aa14e8a..7fe7b53fb17a 100644 --- a/drivers/net/wireless/mwifiex/pcie.c +++ b/drivers/net/wireless/mwifiex/pcie.c @@ -1211,6 +1211,12 @@ static int mwifiex_pcie_process_recv_data(struct mwifiex_adapter *adapter) rd_index = card->rxbd_rdptr & reg->rx_mask; skb_data = card->rx_buf_list[rd_index]; + /* If skb allocation was failed earlier for Rx packet, + * rx_buf_list[rd_index] would have been left with a NULL. + */ + if (!skb_data) + return -ENOMEM; + MWIFIEX_SKB_PACB(skb_data, &buf_pa); pci_unmap_single(card->dev, buf_pa, MWIFIEX_RX_DATA_BUF_SIZE, PCI_DMA_FROMDEVICE); @@ -1525,6 +1531,14 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter) if (adapter->ps_state == PS_STATE_SLEEP_CFM) { mwifiex_process_sleep_confirm_resp(adapter, skb->data, skb->len); + mwifiex_pcie_enable_host_int(adapter); + if (mwifiex_write_reg(adapter, + PCIE_CPU_INT_EVENT, + CPU_INTR_SLEEP_CFM_DONE)) { + dev_warn(adapter->dev, + "Write register failed\n"); + return -1; + } while (reg->sleep_cookie && (count++ < 10) && mwifiex_pcie_ok_to_access_hw(adapter)) usleep_range(50, 60); @@ -1993,23 +2007,9 @@ static void mwifiex_interrupt_status(struct mwifiex_adapter *adapter) adapter->int_status |= pcie_ireg; spin_unlock_irqrestore(&adapter->int_lock, flags); - if (pcie_ireg & HOST_INTR_CMD_DONE) { - if ((adapter->ps_state == PS_STATE_SLEEP_CFM) || - (adapter->ps_state == PS_STATE_SLEEP)) { - mwifiex_pcie_enable_host_int(adapter); - if (mwifiex_write_reg(adapter, - PCIE_CPU_INT_EVENT, - CPU_INTR_SLEEP_CFM_DONE) - ) { - dev_warn(adapter->dev, - "Write register failed\n"); - return; - - } - } - } else if (!adapter->pps_uapsd_mode && - adapter->ps_state == PS_STATE_SLEEP && - mwifiex_pcie_ok_to_access_hw(adapter)) { + if (!adapter->pps_uapsd_mode && + adapter->ps_state == PS_STATE_SLEEP && + mwifiex_pcie_ok_to_access_hw(adapter)) { /* Potentially for PCIe we could get other * interrupts like shared. Don't change power * state until cookie is set */ diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c index 0a8a26e10f01..668547c2de84 100644 --- a/drivers/net/wireless/mwifiex/scan.c +++ b/drivers/net/wireless/mwifiex/scan.c @@ -2101,12 +2101,12 @@ mwifiex_save_curr_bcn(struct mwifiex_private *priv) curr_bss->ht_info_offset); if (curr_bss->bcn_vht_cap) - curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf + - curr_bss->vht_cap_offset); + curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf + + curr_bss->vht_cap_offset); if (curr_bss->bcn_vht_oper) - curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf + - curr_bss->vht_info_offset); + curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf + + curr_bss->vht_info_offset); if (curr_bss->bcn_bss_co_2040) curr_bss->bcn_bss_co_2040 = diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c index e8ebbd4bc3cd..208748804a55 100644 --- a/drivers/net/wireless/mwifiex/usb.c +++ b/drivers/net/wireless/mwifiex/usb.c @@ -22,8 +22,6 @@ #define USB_VERSION "1.0" -static const char usbdriver_name[] = "usb8xxx"; - static struct mwifiex_if_ops usb_ops; static struct semaphore add_remove_card_sem; static struct usb_card_rec *usb_card; @@ -527,13 +525,6 @@ static int mwifiex_usb_resume(struct usb_interface *intf) MWIFIEX_BSS_ROLE_ANY), MWIFIEX_ASYNC_CMD); -#ifdef CONFIG_PM - /* Resume handler may be called due to remote wakeup, - * force to exit suspend anyway - */ - usb_disable_autosuspend(card->udev); -#endif /* CONFIG_PM */ - return 0; } @@ -567,13 +558,12 @@ static void mwifiex_usb_disconnect(struct usb_interface *intf) } static struct usb_driver mwifiex_usb_driver = { - .name = usbdriver_name, + .name = "mwifiex_usb", .probe = mwifiex_usb_probe, .disconnect = mwifiex_usb_disconnect, .id_table = mwifiex_usb_table, .suspend = mwifiex_usb_suspend, .resume = mwifiex_usb_resume, - .supports_autosuspend = 1, }; static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter) diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c index 13eaeed03898..981cf6e7c73b 100644 --- a/drivers/net/wireless/mwifiex/wmm.c +++ b/drivers/net/wireless/mwifiex/wmm.c @@ -559,7 +559,8 @@ mwifiex_clean_txrx(struct mwifiex_private *priv) mwifiex_wmm_delete_all_ralist(priv); memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid)); - if (priv->adapter->if_ops.clean_pcie_ring) + if (priv->adapter->if_ops.clean_pcie_ring && + !priv->adapter->surprise_removed) priv->adapter->if_ops.clean_pcie_ring(priv->adapter); spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); } diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 7f8b5d156c8c..41d4a8167dc3 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -5460,14 +5460,15 @@ static void rt2800_init_bbp_53xx(struct rt2x00_dev *rt2x00dev) rt2800_bbp_write(rt2x00dev, 68, 0x0b); - rt2800_bbp_write(rt2x00dev, 69, 0x0d); - rt2800_bbp_write(rt2x00dev, 70, 0x06); + rt2800_bbp_write(rt2x00dev, 69, 0x12); rt2800_bbp_write(rt2x00dev, 73, 0x13); rt2800_bbp_write(rt2x00dev, 75, 0x46); rt2800_bbp_write(rt2x00dev, 76, 0x28); rt2800_bbp_write(rt2x00dev, 77, 0x59); + rt2800_bbp_write(rt2x00dev, 70, 0x0a); + rt2800_bbp_write(rt2x00dev, 79, 0x13); rt2800_bbp_write(rt2x00dev, 80, 0x05); rt2800_bbp_write(rt2x00dev, 81, 0x33); @@ -5510,7 +5511,6 @@ static void rt2800_init_bbp_53xx(struct rt2x00_dev *rt2x00dev) if (rt2x00_rt(rt2x00dev, RT5392)) { rt2800_bbp_write(rt2x00dev, 134, 0xd0); rt2800_bbp_write(rt2x00dev, 135, 0xf6); - rt2800_bbp_write(rt2x00dev, 148, 0x84); } rt2800_disable_unused_dac_adc(rt2x00dev); diff --git a/drivers/net/wireless/ti/wl1251/rx.c b/drivers/net/wireless/ti/wl1251/rx.c index 123c4bb50e0a..cde0eaf99714 100644 --- a/drivers/net/wireless/ti/wl1251/rx.c +++ b/drivers/net/wireless/ti/wl1251/rx.c @@ -180,7 +180,7 @@ static void wl1251_rx_body(struct wl1251 *wl, wl1251_mem_read(wl, rx_packet_ring_addr, rx_buffer, length); /* The actual length doesn't include the target's alignment */ - skb->len = desc->length - PLCP_HEADER_LENGTH; + skb_trim(skb, desc->length - PLCP_HEADER_LENGTH); fc = (u16 *)skb->data; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 7669d49a67e2..301cc037fda8 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -132,8 +132,7 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) /* If the skb is GSO then we'll also need an extra slot for the * metadata. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || - skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + if (skb_is_gso(skb)) min_slots_needed++; /* If the skb can't possibly fit in the remaining slots diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index e5284bca2d90..438d0c09b7e6 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -240,7 +240,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; unsigned long bytes; - int gso_type; + int gso_type = XEN_NETIF_GSO_TYPE_NONE; /* Data must not cross a page boundary. */ BUG_ON(size + offset > PAGE_SIZE<<compound_order(page)); @@ -299,12 +299,12 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, } /* Leave a gap for the GSO descriptor. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) - gso_type = XEN_NETIF_GSO_TYPE_TCPV4; - else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) - gso_type = XEN_NETIF_GSO_TYPE_TCPV6; - else - gso_type = XEN_NETIF_GSO_TYPE_NONE; + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + } if (*head && ((1 << gso_type) & vif->gso_mask)) vif->rx.req_cons++; @@ -338,19 +338,15 @@ static int xenvif_gop_skb(struct sk_buff *skb, int head = 1; int old_meta_prod; int gso_type; - int gso_size; old_meta_prod = npo->meta_prod; - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - gso_type = XEN_NETIF_GSO_TYPE_TCPV4; - gso_size = skb_shinfo(skb)->gso_size; - } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - gso_type = XEN_NETIF_GSO_TYPE_TCPV6; - gso_size = skb_shinfo(skb)->gso_size; - } else { - gso_type = XEN_NETIF_GSO_TYPE_NONE; - gso_size = 0; + gso_type = XEN_NETIF_GSO_TYPE_NONE; + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; } /* Set up a GSO prefix descriptor, if necessary */ @@ -358,7 +354,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; meta->gso_type = gso_type; - meta->gso_size = gso_size; + meta->gso_size = skb_shinfo(skb)->gso_size; meta->size = 0; meta->id = req->id; } @@ -368,7 +364,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, if ((1 << gso_type) & vif->gso_mask) { meta->gso_type = gso_type; - meta->gso_size = gso_size; + meta->gso_size = skb_shinfo(skb)->gso_size; } else { meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; @@ -500,8 +496,9 @@ static void xenvif_rx_action(struct xenvif *vif) size = skb_frag_size(&skb_shinfo(skb)->frags[i]); max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE); } - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || - skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + if (skb_is_gso(skb) && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || + skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) max_slots_needed++; /* If the skb may not fit then bail out now */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f9daa9e183f2..e30d80033cbc 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -907,6 +907,7 @@ static int handle_incoming_queue(struct net_device *dev, /* Ethernet work: Delayed to here as it peeks the header. */ skb->protocol = eth_type_trans(skb, dev); + skb_reset_network_header(skb); if (checksum_setup(dev, skb)) { kfree_skb(skb); diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 00660cc502c5..38901665c770 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -162,8 +162,6 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, avail = *r; pci_clip_resource_to_region(bus, &avail, region); - if (!resource_size(&avail)) - continue; /* * "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6b05f6134b68..fdbc294821e6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1192,6 +1192,9 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) return err; pci_fixup_device(pci_fixup_enable, dev); + if (dev->msi_enabled || dev->msix_enabled) + return 0; + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (pin) { pci_read_config_word(dev, PCI_COMMAND, &cmd); diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index be361b7cd30f..1e4e69384baa 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -217,7 +217,7 @@ config PINCTRL_IMX28 select PINCTRL_MXS config PINCTRL_MSM - tristate + bool select PINMUX select PINCONF select GENERIC_PINCONF diff --git a/drivers/pinctrl/pinctrl-capri.c b/drivers/pinctrl/pinctrl-capri.c index 4669c53f99b0..eb2500212147 100644 --- a/drivers/pinctrl/pinctrl-capri.c +++ b/drivers/pinctrl/pinctrl-capri.c @@ -1435,7 +1435,7 @@ int __init capri_pinctrl_probe(struct platform_device *pdev) } static struct of_device_id capri_pinctrl_of_match[] = { - { .compatible = "brcm,capri-pinctrl", }, + { .compatible = "brcm,bcm11351-pinctrl", }, { }, }; diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c index 9ccf681dad2f..f9fabe9bf47d 100644 --- a/drivers/pinctrl/pinctrl-sunxi.c +++ b/drivers/pinctrl/pinctrl-sunxi.c @@ -14,6 +14,7 @@ #include <linux/clk.h> #include <linux/gpio.h> #include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> @@ -584,7 +585,7 @@ static int sunxi_pinctrl_irq_set_type(struct irq_data *d, spin_lock_irqsave(&pctl->lock, flags); regval = readl(pctl->membase + reg); - regval &= ~IRQ_CFG_IRQ_MASK; + regval &= ~(IRQ_CFG_IRQ_MASK << index); writel(regval | (mode << index), pctl->membase + reg); spin_unlock_irqrestore(&pctl->lock, flags); @@ -665,6 +666,7 @@ static struct irq_chip sunxi_pinctrl_irq_chip = { static void sunxi_pinctrl_irq_handler(unsigned irq, struct irq_desc *desc) { + struct irq_chip *chip = irq_get_chip(irq); struct sunxi_pinctrl *pctl = irq_get_handler_data(irq); const unsigned long reg = readl(pctl->membase + IRQ_STATUS_REG); @@ -674,10 +676,12 @@ static void sunxi_pinctrl_irq_handler(unsigned irq, struct irq_desc *desc) if (reg) { int irqoffset; + chained_irq_enter(chip, desc); for_each_set_bit(irqoffset, ®, SUNXI_IRQ_NUMBER) { int pin_irq = irq_find_mapping(pctl->domain, irqoffset); generic_handle_irq(pin_irq); } + chained_irq_exit(chip, desc); } } diff --git a/drivers/pinctrl/pinctrl-sunxi.h b/drivers/pinctrl/pinctrl-sunxi.h index 01c494f8a14f..552b0e97077a 100644 --- a/drivers/pinctrl/pinctrl-sunxi.h +++ b/drivers/pinctrl/pinctrl-sunxi.h @@ -511,7 +511,7 @@ static inline u32 sunxi_pull_offset(u16 pin) static inline u32 sunxi_irq_cfg_reg(u16 irq) { - u8 reg = irq / IRQ_CFG_IRQ_PER_REG; + u8 reg = irq / IRQ_CFG_IRQ_PER_REG * 0x04; return reg + IRQ_CFG_REG; } @@ -523,7 +523,7 @@ static inline u32 sunxi_irq_cfg_offset(u16 irq) static inline u32 sunxi_irq_ctrl_reg(u16 irq) { - u8 reg = irq / IRQ_CTRL_IRQ_PER_REG; + u8 reg = irq / IRQ_CTRL_IRQ_PER_REG * 0x04; return reg + IRQ_CTRL_REG; } @@ -535,7 +535,7 @@ static inline u32 sunxi_irq_ctrl_offset(u16 irq) static inline u32 sunxi_irq_status_reg(u16 irq) { - u8 reg = irq / IRQ_STATUS_IRQ_PER_REG; + u8 reg = irq / IRQ_STATUS_IRQ_PER_REG * 0x04; return reg + IRQ_STATUS_REG; } diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c index 77d103fe39d9..567d6918d50b 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c @@ -89,7 +89,8 @@ enum { /* GPSR6 */ FN_IP13_10, FN_IP13_11, FN_IP13_12, FN_IP13_13, FN_IP13_14, - FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19, FN_IP13_22, FN_IP13_24_23, + FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19, + FN_IP13_22, FN_IP13_24_23, FN_SD1_CLK, FN_IP13_25, FN_IP13_26, FN_IP13_27, FN_IP13_30_28, FN_IP14_1_0, FN_IP14_2, FN_IP14_3, FN_IP14_4, FN_IP14_5, FN_IP14_6, FN_IP14_7, FN_IP14_10_8, FN_IP14_13_11, FN_IP14_16_14, FN_IP14_19_17, @@ -788,6 +789,7 @@ static const u16 pinmux_data[] = { PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN), PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC), PINMUX_DATA(DU0_DOTCLKIN_MARK, FN_DU0_DOTCLKIN), + PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK), /* IPSR0 */ PINMUX_IPSR_DATA(IP0_0, D0), @@ -3825,7 +3827,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { GP_6_11_FN, FN_IP13_25, GP_6_10_FN, FN_IP13_24_23, GP_6_9_FN, FN_IP13_22, - 0, 0, + GP_6_8_FN, FN_SD1_CLK, GP_6_7_FN, FN_IP13_21_19, GP_6_6_FN, FN_IP13_18_16, GP_6_5_FN, FN_IP13_15, diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c index a0d6152701cd..617a4916b50f 100644 --- a/drivers/pinctrl/sirf/pinctrl-sirf.c +++ b/drivers/pinctrl/sirf/pinctrl-sirf.c @@ -598,7 +598,7 @@ static unsigned int sirfsoc_gpio_irq_startup(struct irq_data *d) { struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d); - if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq)) + if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE)) dev_err(bank->chip.gc.dev, "unable to lock HW IRQ %lu for IRQ\n", d->hwirq); @@ -611,7 +611,7 @@ static void sirfsoc_gpio_irq_shutdown(struct irq_data *d) struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d); sirfsoc_gpio_irq_mask(d); - gpio_unlock_as_irq(&bank->chip.gc, d->hwirq); + gpio_unlock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE); } static struct irq_chip sirfsoc_irq_chip = { diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 167f3d00c916..66977ebf13b3 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -183,9 +183,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, struct resource r = {0}; int i, flags; - if (acpi_dev_resource_memory(res, &r) - || acpi_dev_resource_io(res, &r) - || acpi_dev_resource_address_space(res, &r) + if (acpi_dev_resource_address_space(res, &r) || acpi_dev_resource_ext_address_space(res, &r)) { pnp_add_resource(dev, &r); return AE_OK; @@ -217,6 +215,17 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, } switch (res->type) { + case ACPI_RESOURCE_TYPE_MEMORY24: + case ACPI_RESOURCE_TYPE_MEMORY32: + case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: + if (acpi_dev_resource_memory(res, &r)) + pnp_add_resource(dev, &r); + break; + case ACPI_RESOURCE_TYPE_IO: + case ACPI_RESOURCE_TYPE_FIXED_IO: + if (acpi_dev_resource_io(res, &r)) + pnp_add_resource(dev, &r); + break; case ACPI_RESOURCE_TYPE_DMA: dma = &res->data.dma; if (dma->channel_count > 0 && dma->channels[0] != (u8) -1) diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c index 769d265b221b..deb7f4bcdb7b 100644 --- a/drivers/pnp/pnpbios/bioscalls.c +++ b/drivers/pnp/pnpbios/bioscalls.c @@ -21,7 +21,7 @@ #include "pnpbios.h" -static struct { +__visible struct { u16 offset; u16 segment; } pnp_bios_callpoint; @@ -41,6 +41,7 @@ asmlinkage void pnp_bios_callfunc(void); __asm__(".text \n" __ALIGN_STR "\n" + ".globl pnp_bios_callfunc\n" "pnp_bios_callfunc:\n" " pushl %edx \n" " pushl %ecx \n" @@ -66,9 +67,9 @@ static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(0x4092, * after PnP BIOS oopses. */ -u32 pnp_bios_fault_esp; -u32 pnp_bios_fault_eip; -u32 pnp_bios_is_utter_crap = 0; +__visible u32 pnp_bios_fault_esp; +__visible u32 pnp_bios_fault_eip; +__visible u32 pnp_bios_is_utter_crap = 0; static spinlock_t pnp_bios_lock; diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h index b4b0d83f9ef6..7061ac0ad428 100644 --- a/drivers/rapidio/devices/tsi721.h +++ b/drivers/rapidio/devices/tsi721.h @@ -678,6 +678,7 @@ struct tsi721_bdma_chan { struct list_head free_list; dma_cookie_t completed_cookie; struct tasklet_struct tasklet; + bool active; }; #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index 502663f5f7c6..91245f5dbe81 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -206,8 +206,8 @@ void tsi721_bdma_handler(struct tsi721_bdma_chan *bdma_chan) { /* Disable BDMA channel interrupts */ iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE); - - tasklet_schedule(&bdma_chan->tasklet); + if (bdma_chan->active) + tasklet_schedule(&bdma_chan->tasklet); } #ifdef CONFIG_PCI_MSI @@ -562,7 +562,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan) } #endif /* CONFIG_PCI_MSI */ - tasklet_enable(&bdma_chan->tasklet); + bdma_chan->active = true; tsi721_bdma_interrupt_enable(bdma_chan, 1); return bdma_chan->bd_num - 1; @@ -576,9 +576,7 @@ err_out: static void tsi721_free_chan_resources(struct dma_chan *dchan) { struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan); -#ifdef CONFIG_PCI_MSI struct tsi721_device *priv = to_tsi721(dchan->device); -#endif LIST_HEAD(list); dev_dbg(dchan->device->dev, "%s: Entry\n", __func__); @@ -589,14 +587,25 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan) BUG_ON(!list_empty(&bdma_chan->active_list)); BUG_ON(!list_empty(&bdma_chan->queue)); - tasklet_disable(&bdma_chan->tasklet); + tsi721_bdma_interrupt_enable(bdma_chan, 0); + bdma_chan->active = false; + +#ifdef CONFIG_PCI_MSI + if (priv->flags & TSI721_USING_MSIX) { + synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE + + bdma_chan->id].vector); + synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT + + bdma_chan->id].vector); + } else +#endif + synchronize_irq(priv->pdev->irq); + + tasklet_kill(&bdma_chan->tasklet); spin_lock_bh(&bdma_chan->lock); list_splice_init(&bdma_chan->free_list, &list); spin_unlock_bh(&bdma_chan->lock); - tsi721_bdma_interrupt_enable(bdma_chan, 0); - #ifdef CONFIG_PCI_MSI if (priv->flags & TSI721_USING_MSIX) { free_irq(priv->msix[TSI721_VECT_DMA0_DONE + @@ -790,6 +799,7 @@ int tsi721_register_dma(struct tsi721_device *priv) bdma_chan->dchan.cookie = 1; bdma_chan->dchan.chan_id = i; bdma_chan->id = i; + bdma_chan->active = false; spin_lock_init(&bdma_chan->lock); @@ -799,7 +809,6 @@ int tsi721_register_dma(struct tsi721_device *priv) tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet, (unsigned long)bdma_chan); - tasklet_disable(&bdma_chan->tasklet); list_add_tail(&bdma_chan->dchan.device_node, &mport->dma.channels); } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index d1ac4caaf1b0..afca1bc24f26 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -953,6 +953,8 @@ static int machine_constraints_current(struct regulator_dev *rdev, return 0; } +static int _regulator_do_enable(struct regulator_dev *rdev); + /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source @@ -1013,10 +1015,9 @@ static int set_machine_constraints(struct regulator_dev *rdev, /* If the constraints say the regulator should be on at this point * and we have control then make sure it is enabled. */ - if ((rdev->constraints->always_on || rdev->constraints->boot_on) && - ops->enable) { - ret = ops->enable(rdev); - if (ret < 0) { + if (rdev->constraints->always_on || rdev->constraints->boot_on) { + ret = _regulator_do_enable(rdev); + if (ret < 0 && ret != -EINVAL) { rdev_err(rdev, "failed to enable\n"); goto out; } @@ -1907,8 +1908,6 @@ static int _regulator_do_disable(struct regulator_dev *rdev) trace_regulator_disable_complete(rdev_get_name(rdev)); - _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, - NULL); return 0; } @@ -1932,6 +1931,8 @@ static int _regulator_disable(struct regulator_dev *rdev) rdev_err(rdev, "failed to disable\n"); return ret; } + _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, + NULL); } rdev->use_count = 0; @@ -1984,20 +1985,16 @@ static int _regulator_force_disable(struct regulator_dev *rdev) { int ret = 0; - /* force disable */ - if (rdev->desc->ops->disable) { - /* ah well, who wants to live forever... */ - ret = rdev->desc->ops->disable(rdev); - if (ret < 0) { - rdev_err(rdev, "failed to force disable\n"); - return ret; - } - /* notify other consumers that power has been forced off */ - _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | - REGULATOR_EVENT_DISABLE, NULL); + ret = _regulator_do_disable(rdev); + if (ret < 0) { + rdev_err(rdev, "failed to force disable\n"); + return ret; } - return ret; + _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | + REGULATOR_EVENT_DISABLE, NULL); + + return 0; } /** @@ -3630,23 +3627,18 @@ int regulator_suspend_finish(void) mutex_lock(®ulator_list_mutex); list_for_each_entry(rdev, ®ulator_list, list) { - struct regulator_ops *ops = rdev->desc->ops; - mutex_lock(&rdev->mutex); - if ((rdev->use_count > 0 || rdev->constraints->always_on) && - ops->enable) { - error = ops->enable(rdev); + if (rdev->use_count > 0 || rdev->constraints->always_on) { + error = _regulator_do_enable(rdev); if (error) ret = error; } else { if (!have_full_constraints()) goto unlock; - if (!ops->disable) - goto unlock; if (!_regulator_is_enabled(rdev)) goto unlock; - error = ops->disable(rdev); + error = _regulator_do_disable(rdev); if (error) ret = error; } @@ -3820,7 +3812,7 @@ static int __init regulator_init_complete(void) ops = rdev->desc->ops; c = rdev->constraints; - if (!ops->disable || (c && c->always_on)) + if (c && c->always_on) continue; mutex_lock(&rdev->mutex); @@ -3841,7 +3833,7 @@ static int __init regulator_init_complete(void) /* We log since this may kill the system if it * goes wrong. */ rdev_info(rdev, "disabling\n"); - ret = ops->disable(rdev); + ret = _regulator_do_disable(rdev); if (ret != 0) rdev_err(rdev, "couldn't disable: %d\n", ret); } else { diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 7afd373b9595..c4cde9c08f1f 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -580,10 +580,12 @@ static int s3c_rtc_suspend(struct device *dev) clk_enable(rtc_clk); /* save TICNT for anyone using periodic interrupts */ - ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT); if (s3c_rtc_cpu_type == TYPE_S3C64XX) { ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON); ticnt_en_save &= S3C64XX_RTCCON_TICEN; + ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT); + } else { + ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT); } s3c_rtc_enable(pdev, 0); @@ -605,10 +607,15 @@ static int s3c_rtc_resume(struct device *dev) clk_enable(rtc_clk); s3c_rtc_enable(pdev, 1); - writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT); - if (s3c_rtc_cpu_type == TYPE_S3C64XX && ticnt_en_save) { - tmp = readw(s3c_rtc_base + S3C2410_RTCCON); - writew(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON); + if (s3c_rtc_cpu_type == TYPE_S3C64XX) { + writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT); + if (ticnt_en_save) { + tmp = readw(s3c_rtc_base + S3C2410_RTCCON); + writew(tmp | ticnt_en_save, + s3c_rtc_base + S3C2410_RTCCON); + } + } else { + writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT); } if (device_may_wakeup(dev) && wake_en) { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index c3a83df07894..795ed61a5496 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1660,7 +1660,6 @@ int qeth_qdio_clear_card(struct qeth_card *card, int use_halt) QDIO_FLAG_CLEANUP_USING_CLEAR); if (rc) QETH_CARD_TEXT_(card, 3, "1err%d", rc); - qdio_free(CARD_DDEV(card)); atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED); break; case QETH_QDIO_CLEANING: @@ -2605,6 +2604,7 @@ static int qeth_mpc_initialize(struct qeth_card *card) return 0; out_qdio: qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); + qdio_free(CARD_DDEV(card)); return rc; } @@ -4906,9 +4906,11 @@ retry: if (retries < 3) QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", dev_name(&card->gdev->dev)); + rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); rc = ccw_device_set_online(CARD_RDEV(card)); if (rc) goto retriable; @@ -4918,7 +4920,6 @@ retry: rc = ccw_device_set_online(CARD_DDEV(card)); if (rc) goto retriable; - rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); retriable: if (rc == -ERESTARTSYS) { QETH_DBF_TEXT(SETUP, 2, "break1"); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 0710550093ce..908d82529ee9 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1091,6 +1091,7 @@ out_remove: ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_RECOVER) card->state = CARD_STATE_RECOVER; else @@ -1132,6 +1133,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev, rc = (rc2) ? rc2 : rc3; if (rc) QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_UP) card->state = CARD_STATE_RECOVER; /* let user_space know that device is offline */ @@ -1194,6 +1196,7 @@ static void qeth_l2_shutdown(struct ccwgroup_device *gdev) qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); qeth_qdio_clear_card(card, 0); qeth_clear_qdio_buffers(card); + qdio_free(CARD_DDEV(card)); } static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 0f430424c3b8..3524d34ff694 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3447,6 +3447,7 @@ out_remove: ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_RECOVER) card->state = CARD_STATE_RECOVER; else @@ -3493,6 +3494,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev, rc = (rc2) ? rc2 : rc3; if (rc) QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_UP) card->state = CARD_STATE_RECOVER; /* let user_space know that device is offline */ @@ -3545,6 +3547,7 @@ static void qeth_l3_shutdown(struct ccwgroup_device *gdev) qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); qeth_qdio_clear_card(card, 0); qeth_clear_qdio_buffers(card); + qdio_free(CARD_DDEV(card)); } static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev) diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 1f375051483a..5642a9b250c2 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -325,7 +325,7 @@ static int beiscsi_eh_device_reset(struct scsi_cmnd *sc) if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE) continue; - if (abrt_task->sc->device->lun != abrt_task->sc->device->lun) + if (sc->device->lun != abrt_task->sc->device->lun) continue; /* Invalidate WRB Posted for this Task */ diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index ed880891cb7c..e9279a8c1e1c 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -594,13 +594,13 @@ static void bnx2fc_free_mp_resc(struct bnx2fc_cmd *io_req) mp_req->mp_resp_bd = NULL; } if (mp_req->req_buf) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, mp_req->req_buf, mp_req->req_buf_dma); mp_req->req_buf = NULL; } if (mp_req->resp_buf) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, mp_req->resp_buf, mp_req->resp_buf_dma); mp_req->resp_buf = NULL; @@ -622,7 +622,7 @@ int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req) mp_req->req_len = sizeof(struct fcp_cmnd); io_req->data_xfer_len = mp_req->req_len; - mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, &mp_req->req_buf_dma, GFP_ATOMIC); if (!mp_req->req_buf) { @@ -631,7 +631,7 @@ int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req) return FAILED; } - mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, &mp_req->resp_buf_dma, GFP_ATOMIC); if (!mp_req->resp_buf) { @@ -639,8 +639,8 @@ int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req) bnx2fc_free_mp_resc(io_req); return FAILED; } - memset(mp_req->req_buf, 0, PAGE_SIZE); - memset(mp_req->resp_buf, 0, PAGE_SIZE); + memset(mp_req->req_buf, 0, CNIC_PAGE_SIZE); + memset(mp_req->resp_buf, 0, CNIC_PAGE_SIZE); /* Allocate and map mp_req_bd and mp_resp_bd */ sz = sizeof(struct fcoe_bd_ctx); @@ -665,7 +665,7 @@ int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req) mp_req_bd = mp_req->mp_req_bd; mp_req_bd->buf_addr_lo = (u32)addr & 0xffffffff; mp_req_bd->buf_addr_hi = (u32)((u64)addr >> 32); - mp_req_bd->buf_len = PAGE_SIZE; + mp_req_bd->buf_len = CNIC_PAGE_SIZE; mp_req_bd->flags = 0; /* @@ -677,7 +677,7 @@ int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req) addr = mp_req->resp_buf_dma; mp_resp_bd->buf_addr_lo = (u32)addr & 0xffffffff; mp_resp_bd->buf_addr_hi = (u32)((u64)addr >> 32); - mp_resp_bd->buf_len = PAGE_SIZE; + mp_resp_bd->buf_len = CNIC_PAGE_SIZE; mp_resp_bd->flags = 0; return SUCCESS; diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c index 4d93177dfb53..d9bae5672273 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c +++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c @@ -673,7 +673,8 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, /* Allocate and map SQ */ tgt->sq_mem_size = tgt->max_sqes * BNX2FC_SQ_WQE_SIZE; - tgt->sq_mem_size = (tgt->sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + tgt->sq_mem_size = (tgt->sq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->sq = dma_alloc_coherent(&hba->pcidev->dev, tgt->sq_mem_size, &tgt->sq_dma, GFP_KERNEL); @@ -686,7 +687,8 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, /* Allocate and map CQ */ tgt->cq_mem_size = tgt->max_cqes * BNX2FC_CQ_WQE_SIZE; - tgt->cq_mem_size = (tgt->cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + tgt->cq_mem_size = (tgt->cq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->cq = dma_alloc_coherent(&hba->pcidev->dev, tgt->cq_mem_size, &tgt->cq_dma, GFP_KERNEL); @@ -699,7 +701,8 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, /* Allocate and map RQ and RQ PBL */ tgt->rq_mem_size = tgt->max_rqes * BNX2FC_RQ_WQE_SIZE; - tgt->rq_mem_size = (tgt->rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + tgt->rq_mem_size = (tgt->rq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->rq = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_mem_size, &tgt->rq_dma, GFP_KERNEL); @@ -710,8 +713,9 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, } memset(tgt->rq, 0, tgt->rq_mem_size); - tgt->rq_pbl_size = (tgt->rq_mem_size / PAGE_SIZE) * sizeof(void *); - tgt->rq_pbl_size = (tgt->rq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK; + tgt->rq_pbl_size = (tgt->rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *); + tgt->rq_pbl_size = (tgt->rq_pbl_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->rq_pbl = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_pbl_size, &tgt->rq_pbl_dma, GFP_KERNEL); @@ -722,7 +726,7 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, } memset(tgt->rq_pbl, 0, tgt->rq_pbl_size); - num_pages = tgt->rq_mem_size / PAGE_SIZE; + num_pages = tgt->rq_mem_size / CNIC_PAGE_SIZE; page = tgt->rq_dma; pbl = (u32 *)tgt->rq_pbl; @@ -731,13 +735,13 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, pbl++; *pbl = (u32)((u64)page >> 32); pbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } /* Allocate and map XFERQ */ tgt->xferq_mem_size = tgt->max_sqes * BNX2FC_XFERQ_WQE_SIZE; - tgt->xferq_mem_size = (tgt->xferq_mem_size + (PAGE_SIZE - 1)) & - PAGE_MASK; + tgt->xferq_mem_size = (tgt->xferq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->xferq = dma_alloc_coherent(&hba->pcidev->dev, tgt->xferq_mem_size, &tgt->xferq_dma, GFP_KERNEL); @@ -750,8 +754,8 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, /* Allocate and map CONFQ & CONFQ PBL */ tgt->confq_mem_size = tgt->max_sqes * BNX2FC_CONFQ_WQE_SIZE; - tgt->confq_mem_size = (tgt->confq_mem_size + (PAGE_SIZE - 1)) & - PAGE_MASK; + tgt->confq_mem_size = (tgt->confq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->confq = dma_alloc_coherent(&hba->pcidev->dev, tgt->confq_mem_size, &tgt->confq_dma, GFP_KERNEL); @@ -763,9 +767,9 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, memset(tgt->confq, 0, tgt->confq_mem_size); tgt->confq_pbl_size = - (tgt->confq_mem_size / PAGE_SIZE) * sizeof(void *); + (tgt->confq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *); tgt->confq_pbl_size = - (tgt->confq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (tgt->confq_pbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; tgt->confq_pbl = dma_alloc_coherent(&hba->pcidev->dev, tgt->confq_pbl_size, @@ -777,7 +781,7 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, } memset(tgt->confq_pbl, 0, tgt->confq_pbl_size); - num_pages = tgt->confq_mem_size / PAGE_SIZE; + num_pages = tgt->confq_mem_size / CNIC_PAGE_SIZE; page = tgt->confq_dma; pbl = (u32 *)tgt->confq_pbl; @@ -786,7 +790,7 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, pbl++; *pbl = (u32)((u64)page >> 32); pbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } /* Allocate and map ConnDB */ @@ -805,8 +809,8 @@ static int bnx2fc_alloc_session_resc(struct bnx2fc_hba *hba, /* Allocate and map LCQ */ tgt->lcq_mem_size = (tgt->max_sqes + 8) * BNX2FC_SQ_WQE_SIZE; - tgt->lcq_mem_size = (tgt->lcq_mem_size + (PAGE_SIZE - 1)) & - PAGE_MASK; + tgt->lcq_mem_size = (tgt->lcq_mem_size + (CNIC_PAGE_SIZE - 1)) & + CNIC_PAGE_MASK; tgt->lcq = dma_alloc_coherent(&hba->pcidev->dev, tgt->lcq_mem_size, &tgt->lcq_dma, GFP_KERNEL); diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index e4cf23df4b4f..b87a1933f880 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -61,7 +61,7 @@ static void bnx2i_adjust_qp_size(struct bnx2i_hba *hba) * yield integral num of page buffers */ /* adjust SQ */ - num_elements_per_pg = PAGE_SIZE / BNX2I_SQ_WQE_SIZE; + num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE; if (hba->max_sqes < num_elements_per_pg) hba->max_sqes = num_elements_per_pg; else if (hba->max_sqes % num_elements_per_pg) @@ -69,7 +69,7 @@ static void bnx2i_adjust_qp_size(struct bnx2i_hba *hba) ~(num_elements_per_pg - 1); /* adjust CQ */ - num_elements_per_pg = PAGE_SIZE / BNX2I_CQE_SIZE; + num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_CQE_SIZE; if (hba->max_cqes < num_elements_per_pg) hba->max_cqes = num_elements_per_pg; else if (hba->max_cqes % num_elements_per_pg) @@ -77,7 +77,7 @@ static void bnx2i_adjust_qp_size(struct bnx2i_hba *hba) ~(num_elements_per_pg - 1); /* adjust RQ */ - num_elements_per_pg = PAGE_SIZE / BNX2I_RQ_WQE_SIZE; + num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_RQ_WQE_SIZE; if (hba->max_rqes < num_elements_per_pg) hba->max_rqes = num_elements_per_pg; else if (hba->max_rqes % num_elements_per_pg) @@ -959,7 +959,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) /* SQ page table */ memset(ep->qp.sq_pgtbl_virt, 0, ep->qp.sq_pgtbl_size); - num_pages = ep->qp.sq_mem_size / PAGE_SIZE; + num_pages = ep->qp.sq_mem_size / CNIC_PAGE_SIZE; page = ep->qp.sq_phys; if (cnic_dev_10g) @@ -973,7 +973,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) ((u64) page >> 32); ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } else { /* PTE is written in big endian format for * 5706/5708/5709 devices */ @@ -981,13 +981,13 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) page; ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } } /* RQ page table */ memset(ep->qp.rq_pgtbl_virt, 0, ep->qp.rq_pgtbl_size); - num_pages = ep->qp.rq_mem_size / PAGE_SIZE; + num_pages = ep->qp.rq_mem_size / CNIC_PAGE_SIZE; page = ep->qp.rq_phys; if (cnic_dev_10g) @@ -1001,7 +1001,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) ((u64) page >> 32); ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } else { /* PTE is written in big endian format for * 5706/5708/5709 devices */ @@ -1009,13 +1009,13 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) page; ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } } /* CQ page table */ memset(ep->qp.cq_pgtbl_virt, 0, ep->qp.cq_pgtbl_size); - num_pages = ep->qp.cq_mem_size / PAGE_SIZE; + num_pages = ep->qp.cq_mem_size / CNIC_PAGE_SIZE; page = ep->qp.cq_phys; if (cnic_dev_10g) @@ -1029,7 +1029,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) ((u64) page >> 32); ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } else { /* PTE is written in big endian format for * 5706/5708/5709 devices */ @@ -1037,7 +1037,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep) ptbl++; *ptbl = (u32) page; ptbl++; - page += PAGE_SIZE; + page += CNIC_PAGE_SIZE; } } } @@ -1064,11 +1064,11 @@ int bnx2i_alloc_qp_resc(struct bnx2i_hba *hba, struct bnx2i_endpoint *ep) /* Allocate page table memory for SQ which is page aligned */ ep->qp.sq_mem_size = hba->max_sqes * BNX2I_SQ_WQE_SIZE; ep->qp.sq_mem_size = - (ep->qp.sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.sq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.sq_pgtbl_size = - (ep->qp.sq_mem_size / PAGE_SIZE) * sizeof(void *); + (ep->qp.sq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *); ep->qp.sq_pgtbl_size = - (ep->qp.sq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.sq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.sq_pgtbl_virt = dma_alloc_coherent(&hba->pcidev->dev, ep->qp.sq_pgtbl_size, @@ -1101,11 +1101,11 @@ int bnx2i_alloc_qp_resc(struct bnx2i_hba *hba, struct bnx2i_endpoint *ep) /* Allocate page table memory for CQ which is page aligned */ ep->qp.cq_mem_size = hba->max_cqes * BNX2I_CQE_SIZE; ep->qp.cq_mem_size = - (ep->qp.cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.cq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.cq_pgtbl_size = - (ep->qp.cq_mem_size / PAGE_SIZE) * sizeof(void *); + (ep->qp.cq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *); ep->qp.cq_pgtbl_size = - (ep->qp.cq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.cq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.cq_pgtbl_virt = dma_alloc_coherent(&hba->pcidev->dev, ep->qp.cq_pgtbl_size, @@ -1144,11 +1144,11 @@ int bnx2i_alloc_qp_resc(struct bnx2i_hba *hba, struct bnx2i_endpoint *ep) /* Allocate page table memory for RQ which is page aligned */ ep->qp.rq_mem_size = hba->max_rqes * BNX2I_RQ_WQE_SIZE; ep->qp.rq_mem_size = - (ep->qp.rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.rq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.rq_pgtbl_size = - (ep->qp.rq_mem_size / PAGE_SIZE) * sizeof(void *); + (ep->qp.rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *); ep->qp.rq_pgtbl_size = - (ep->qp.rq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK; + (ep->qp.rq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK; ep->qp.rq_pgtbl_virt = dma_alloc_coherent(&hba->pcidev->dev, ep->qp.rq_pgtbl_size, @@ -1270,7 +1270,7 @@ int bnx2i_send_fw_iscsi_init_msg(struct bnx2i_hba *hba) bnx2i_adjust_qp_size(hba); iscsi_init.flags = - ISCSI_PAGE_SIZE_4K << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT; + (CNIC_PAGE_BITS - 8) << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT; if (en_tcp_dack) iscsi_init.flags |= ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE; iscsi_init.reserved0 = 0; @@ -1288,15 +1288,15 @@ int bnx2i_send_fw_iscsi_init_msg(struct bnx2i_hba *hba) ((hba->num_ccell & 0xFFFF) | (hba->max_sqes << 16)); iscsi_init.num_ccells_per_conn = hba->num_ccell; iscsi_init.num_tasks_per_conn = hba->max_sqes; - iscsi_init.sq_wqes_per_page = PAGE_SIZE / BNX2I_SQ_WQE_SIZE; + iscsi_init.sq_wqes_per_page = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE; iscsi_init.sq_num_wqes = hba->max_sqes; iscsi_init.cq_log_wqes_per_page = - (u8) bnx2i_power_of2(PAGE_SIZE / BNX2I_CQE_SIZE); + (u8) bnx2i_power_of2(CNIC_PAGE_SIZE / BNX2I_CQE_SIZE); iscsi_init.cq_num_wqes = hba->max_cqes; iscsi_init.cq_num_pages = (hba->max_cqes * BNX2I_CQE_SIZE + - (PAGE_SIZE - 1)) / PAGE_SIZE; + (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE; iscsi_init.sq_num_pages = (hba->max_sqes * BNX2I_SQ_WQE_SIZE + - (PAGE_SIZE - 1)) / PAGE_SIZE; + (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE; iscsi_init.rq_buffer_size = BNX2I_RQ_WQE_SIZE; iscsi_init.rq_num_wqes = hba->max_rqes; diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index 854dad7d5b03..c8b0aff5bbd4 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -525,7 +525,7 @@ static int bnx2i_setup_mp_bdt(struct bnx2i_hba *hba) struct iscsi_bd *mp_bdt; u64 addr; - hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, &hba->mp_bd_dma, GFP_KERNEL); if (!hba->mp_bd_tbl) { printk(KERN_ERR "unable to allocate Middle Path BDT\n"); @@ -533,11 +533,12 @@ static int bnx2i_setup_mp_bdt(struct bnx2i_hba *hba) goto out; } - hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev, + CNIC_PAGE_SIZE, &hba->dummy_buf_dma, GFP_KERNEL); if (!hba->dummy_buffer) { printk(KERN_ERR "unable to alloc Middle Path Dummy Buffer\n"); - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, hba->mp_bd_tbl, hba->mp_bd_dma); hba->mp_bd_tbl = NULL; rc = -1; @@ -548,7 +549,7 @@ static int bnx2i_setup_mp_bdt(struct bnx2i_hba *hba) addr = (unsigned long) hba->dummy_buf_dma; mp_bdt->buffer_addr_lo = addr & 0xffffffff; mp_bdt->buffer_addr_hi = addr >> 32; - mp_bdt->buffer_length = PAGE_SIZE; + mp_bdt->buffer_length = CNIC_PAGE_SIZE; mp_bdt->flags = ISCSI_BD_LAST_IN_BD_CHAIN | ISCSI_BD_FIRST_IN_BD_CHAIN; out: @@ -565,12 +566,12 @@ out: static void bnx2i_free_mp_bdt(struct bnx2i_hba *hba) { if (hba->mp_bd_tbl) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, hba->mp_bd_tbl, hba->mp_bd_dma); hba->mp_bd_tbl = NULL; } if (hba->dummy_buffer) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, hba->dummy_buffer, hba->dummy_buf_dma); hba->dummy_buffer = NULL; } @@ -934,14 +935,14 @@ static void bnx2i_conn_free_login_resources(struct bnx2i_hba *hba, struct bnx2i_conn *bnx2i_conn) { if (bnx2i_conn->gen_pdu.resp_bd_tbl) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, bnx2i_conn->gen_pdu.resp_bd_tbl, bnx2i_conn->gen_pdu.resp_bd_dma); bnx2i_conn->gen_pdu.resp_bd_tbl = NULL; } if (bnx2i_conn->gen_pdu.req_bd_tbl) { - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, bnx2i_conn->gen_pdu.req_bd_tbl, bnx2i_conn->gen_pdu.req_bd_dma); bnx2i_conn->gen_pdu.req_bd_tbl = NULL; @@ -998,13 +999,13 @@ static int bnx2i_conn_alloc_login_resources(struct bnx2i_hba *hba, bnx2i_conn->gen_pdu.resp_wr_ptr = bnx2i_conn->gen_pdu.resp_buf; bnx2i_conn->gen_pdu.req_bd_tbl = - dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, &bnx2i_conn->gen_pdu.req_bd_dma, GFP_KERNEL); if (bnx2i_conn->gen_pdu.req_bd_tbl == NULL) goto login_req_bd_tbl_failure; bnx2i_conn->gen_pdu.resp_bd_tbl = - dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, &bnx2i_conn->gen_pdu.resp_bd_dma, GFP_KERNEL); if (bnx2i_conn->gen_pdu.resp_bd_tbl == NULL) @@ -1013,7 +1014,7 @@ static int bnx2i_conn_alloc_login_resources(struct bnx2i_hba *hba, return 0; login_resp_bd_tbl_failure: - dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE, + dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE, bnx2i_conn->gen_pdu.req_bd_tbl, bnx2i_conn->gen_pdu.req_bd_dma); bnx2i_conn->gen_pdu.req_bd_tbl = NULL; diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h index 4911310a38f5..22a9bb1abae1 100644 --- a/drivers/scsi/isci/host.h +++ b/drivers/scsi/isci/host.h @@ -311,9 +311,8 @@ static inline struct Scsi_Host *to_shost(struct isci_host *ihost) } #define for_each_isci_host(id, ihost, pdev) \ - for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \ - id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \ - ihost = to_pci_info(pdev)->hosts[++id]) + for (id = 0; id < SCI_MAX_CONTROLLERS && \ + (ihost = to_pci_info(pdev)->hosts[id]); id++) static inline void wait_for_start(struct isci_host *ihost) { diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c index 85c77f6b802b..ac879745ef80 100644 --- a/drivers/scsi/isci/port_config.c +++ b/drivers/scsi/isci/port_config.c @@ -615,13 +615,6 @@ static void sci_apc_agent_link_up(struct isci_host *ihost, SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION); } else { /* the phy is already the part of the port */ - u32 port_state = iport->sm.current_state_id; - - /* if the PORT'S state is resetting then the link up is from - * port hard reset in this case, we need to tell the port - * that link up is recieved - */ - BUG_ON(port_state != SCI_PORT_RESETTING); port_agent->phy_ready_mask |= 1 << phy_index; sci_port_link_up(iport, iphy); } diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c index 0d30ca849e8f..5d6fda72d659 100644 --- a/drivers/scsi/isci/task.c +++ b/drivers/scsi/isci/task.c @@ -801,7 +801,7 @@ int isci_task_I_T_nexus_reset(struct domain_device *dev) /* XXX: need to cleanup any ireqs targeting this * domain_device */ - ret = TMF_RESP_FUNC_COMPLETE; + ret = -ENODEV; goto out; } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index e1fe95ef23e1..266724b6b899 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -2996,8 +2996,7 @@ struct qla_hw_data { IS_QLA82XX(ha) || IS_QLA83XX(ha) || \ IS_QLA8044(ha)) #define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha)) -#define IS_NOPOLLING_TYPE(ha) ((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \ - IS_QLA83XX(ha)) && (ha)->flags.msix_enabled) +#define IS_NOPOLLING_TYPE(ha) (IS_QLA81XX(ha) && (ha)->flags.msix_enabled) #define IS_FAC_REQUIRED(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha)) #define IS_NOCACHE_VPD_TYPE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha)) #define IS_ALOGIO_CAPABLE(ha) (IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha)) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 9bc86b9e86b1..0a1dcb43d18b 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2880,6 +2880,7 @@ static int qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp) { #define MIN_MSIX_COUNT 2 +#define ATIO_VECTOR 2 int i, ret; struct msix_entry *entries; struct qla_msix_entry *qentry; @@ -2936,34 +2937,47 @@ msix_failed: } /* Enable MSI-X vectors for the base queue */ - for (i = 0; i < ha->msix_count; i++) { + for (i = 0; i < 2; i++) { qentry = &ha->msix_entries[i]; - if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) { - ret = request_irq(qentry->vector, - qla83xx_msix_entries[i].handler, - 0, qla83xx_msix_entries[i].name, rsp); - } else if (IS_P3P_TYPE(ha)) { + if (IS_P3P_TYPE(ha)) ret = request_irq(qentry->vector, qla82xx_msix_entries[i].handler, 0, qla82xx_msix_entries[i].name, rsp); - } else { + else ret = request_irq(qentry->vector, msix_entries[i].handler, 0, msix_entries[i].name, rsp); - } - if (ret) { - ql_log(ql_log_fatal, vha, 0x00cb, - "MSI-X: unable to register handler -- %x/%d.\n", - qentry->vector, ret); - qla24xx_disable_msix(ha); - ha->mqenable = 0; - goto msix_out; - } + if (ret) + goto msix_register_fail; qentry->have_irq = 1; qentry->rsp = rsp; rsp->msix = qentry; } + /* + * If target mode is enable, also request the vector for the ATIO + * queue. + */ + if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) { + qentry = &ha->msix_entries[ATIO_VECTOR]; + ret = request_irq(qentry->vector, + qla83xx_msix_entries[ATIO_VECTOR].handler, + 0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp); + qentry->have_irq = 1; + qentry->rsp = rsp; + rsp->msix = qentry; + } + +msix_register_fail: + if (ret) { + ql_log(ql_log_fatal, vha, 0x00cb, + "MSI-X: unable to register handler -- %x/%d.\n", + qentry->vector, ret); + qla24xx_disable_msix(ha); + ha->mqenable = 0; + goto msix_out; + } + /* Enable MSI-X vector for response queue update for queue 0 */ if (IS_QLA83XX(ha)) { if (ha->msixbase && ha->mqiobase && diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 17d740427240..9969fa1ef7c4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1419,6 +1419,9 @@ static void storvsc_device_destroy(struct scsi_device *sdevice) { struct stor_mem_pools *memp = sdevice->hostdata; + if (!memp) + return; + mempool_destroy(memp->request_mempool); kmem_cache_destroy(memp->request_pool); kfree(memp); diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c index 31534b51715a..c3b2fb9b6713 100644 --- a/drivers/spi/spi-ath79.c +++ b/drivers/spi/spi-ath79.c @@ -132,9 +132,9 @@ static int ath79_spi_setup_cs(struct spi_device *spi) flags = GPIOF_DIR_OUT; if (spi->mode & SPI_CS_HIGH) - flags |= GPIOF_INIT_HIGH; - else flags |= GPIOF_INIT_LOW; + else + flags |= GPIOF_INIT_HIGH; status = gpio_request_one(cdata->gpio, flags, dev_name(&spi->dev)); diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index b0842f751016..5d7b07f08326 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1455,6 +1455,14 @@ static int atmel_spi_suspend(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct atmel_spi *as = spi_master_get_devdata(master); + int ret; + + /* Stop the queue running */ + ret = spi_master_suspend(master); + if (ret) { + dev_warn(dev, "cannot suspend master\n"); + return ret; + } clk_disable_unprepare(as->clk); return 0; @@ -1464,9 +1472,16 @@ static int atmel_spi_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct atmel_spi *as = spi_master_get_devdata(master); + int ret; clk_prepare_enable(as->clk); - return 0; + + /* Start the queue running */ + ret = spi_master_resume(master); + if (ret) + dev_err(dev, "problem starting queue (%d)\n", ret); + + return ret; } static SIMPLE_DEV_PM_OPS(atmel_spi_pm_ops, atmel_spi_suspend, atmel_spi_resume); diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c index cabed8f9119e..28ae470397a9 100644 --- a/drivers/spi/spi-coldfire-qspi.c +++ b/drivers/spi/spi-coldfire-qspi.c @@ -514,7 +514,8 @@ static int mcfqspi_resume(struct device *dev) #ifdef CONFIG_PM_RUNTIME static int mcfqspi_runtime_suspend(struct device *dev) { - struct mcfqspi *mcfqspi = dev_get_drvdata(dev); + struct spi_master *master = dev_get_drvdata(dev); + struct mcfqspi *mcfqspi = spi_master_get_devdata(master); clk_disable(mcfqspi->clk); @@ -523,7 +524,8 @@ static int mcfqspi_runtime_suspend(struct device *dev) static int mcfqspi_runtime_resume(struct device *dev) { - struct mcfqspi *mcfqspi = dev_get_drvdata(dev); + struct spi_master *master = dev_get_drvdata(dev); + struct mcfqspi *mcfqspi = spi_master_get_devdata(master); clk_enable(mcfqspi->clk); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index ec79f726672a..a25392065d9b 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -420,7 +420,6 @@ static int dspi_suspend(struct device *dev) static int dspi_resume(struct device *dev) { - struct spi_master *master = dev_get_drvdata(dev); struct fsl_dspi *dspi = spi_master_get_devdata(master); @@ -504,7 +503,7 @@ static int dspi_probe(struct platform_device *pdev) clk_prepare_enable(dspi->clk); init_waitqueue_head(&dspi->waitq); - platform_set_drvdata(pdev, dspi); + platform_set_drvdata(pdev, master); ret = spi_bitbang_start(&dspi->bitbang); if (ret != 0) { @@ -525,7 +524,8 @@ out_master_put: static int dspi_remove(struct platform_device *pdev) { - struct fsl_dspi *dspi = platform_get_drvdata(pdev); + struct spi_master *master = platform_get_drvdata(pdev); + struct fsl_dspi *dspi = spi_master_get_devdata(master); /* Disconnect from the SPI framework */ spi_bitbang_stop(&dspi->bitbang); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index a5474ef9d2a0..47f15d97e7fa 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -948,8 +948,8 @@ static int spi_imx_remove(struct platform_device *pdev) spi_bitbang_stop(&spi_imx->bitbang); writel(0, spi_imx->base + MXC_CSPICTRL); - clk_disable_unprepare(spi_imx->clk_ipg); - clk_disable_unprepare(spi_imx->clk_per); + clk_unprepare(spi_imx->clk_ipg); + clk_unprepare(spi_imx->clk_per); spi_master_put(master); return 0; diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c index 2e7f38c7a961..88eb57e858b3 100644 --- a/drivers/spi/spi-topcliff-pch.c +++ b/drivers/spi/spi-topcliff-pch.c @@ -915,7 +915,7 @@ static void pch_spi_request_dma(struct pch_spi_data *data, int bpw) /* Set Tx DMA */ param = &dma->param_tx; param->dma_dev = &dma_dev->dev; - param->chan_id = data->master->bus_num * 2; /* Tx = 0, 2 */ + param->chan_id = data->ch * 2; /* Tx = 0, 2 */; param->tx_reg = data->io_base_addr + PCH_SPDWR; param->width = width; chan = dma_request_channel(mask, pch_spi_filter, param); @@ -930,7 +930,7 @@ static void pch_spi_request_dma(struct pch_spi_data *data, int bpw) /* Set Rx DMA */ param = &dma->param_rx; param->dma_dev = &dma_dev->dev; - param->chan_id = data->master->bus_num * 2 + 1; /* Rx = Tx + 1 */ + param->chan_id = data->ch * 2 + 1; /* Rx = Tx + 1 */; param->rx_reg = data->io_base_addr + PCH_SPDRR; param->width = width; chan = dma_request_channel(mask, pch_spi_filter, param); @@ -1452,6 +1452,11 @@ static int pch_spi_pd_probe(struct platform_device *plat_dev) pch_spi_set_master_mode(master); + if (use_dma) { + dev_info(&plat_dev->dev, "Use DMA for data transfers\n"); + pch_alloc_dma_buf(board_dat, data); + } + ret = spi_register_master(master); if (ret != 0) { dev_err(&plat_dev->dev, @@ -1459,14 +1464,10 @@ static int pch_spi_pd_probe(struct platform_device *plat_dev) goto err_spi_register_master; } - if (use_dma) { - dev_info(&plat_dev->dev, "Use DMA for data transfers\n"); - pch_alloc_dma_buf(board_dat, data); - } - return 0; err_spi_register_master: + pch_free_dma_buf(board_dat, data); free_irq(board_dat->pdev->irq, data); err_request_irq: pch_spi_free_resources(board_dat, data); diff --git a/drivers/staging/cxt1e1/linux.c b/drivers/staging/cxt1e1/linux.c index 4a08e16e42f7..79206cb3fb94 100644 --- a/drivers/staging/cxt1e1/linux.c +++ b/drivers/staging/cxt1e1/linux.c @@ -866,6 +866,8 @@ c4_ioctl (struct net_device *ndev, struct ifreq *ifr, int cmd) _IOC_SIZE (iocmd)); #endif iolen = _IOC_SIZE (iocmd); + if (iolen > sizeof(arg)) + return -EFAULT; data = ifr->ifr_data + sizeof (iocmd); if (copy_from_user (&arg, data, iolen)) return -EFAULT; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 7f1a7ce4b771..b83ec378d04f 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -785,7 +785,7 @@ static void iscsit_ack_from_expstatsn(struct iscsi_conn *conn, u32 exp_statsn) spin_unlock_bh(&conn->cmd_lock); list_for_each_entry_safe(cmd, cmd_p, &ack_list, i_conn_node) { - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); iscsit_free_cmd(cmd, false); } } @@ -3708,7 +3708,7 @@ iscsit_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state break; case ISTATE_REMOVE: spin_lock_bh(&conn->cmd_lock); - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_free_cmd(cmd, false); @@ -4151,7 +4151,7 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) spin_lock_bh(&conn->cmd_lock); list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) { - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_increment_maxcmdsn(cmd, sess); @@ -4196,6 +4196,10 @@ int iscsit_close_connection( iscsit_stop_timers_for_cmds(conn); iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + iscsit_free_queue_reqs_for_conn(conn); /* diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c index 33be1fb1df32..4ca8fd2a70db 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.c +++ b/drivers/target/iscsi/iscsi_target_erl2.c @@ -138,7 +138,7 @@ void iscsit_free_connection_recovery_entires(struct iscsi_session *sess) list_for_each_entry_safe(cmd, cmd_tmp, &cr->conn_recovery_cmd_list, i_conn_node) { - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); cmd->conn = NULL; spin_unlock(&cr->conn_recovery_cmd_lock); iscsit_free_cmd(cmd, true); @@ -160,7 +160,7 @@ void iscsit_free_connection_recovery_entires(struct iscsi_session *sess) list_for_each_entry_safe(cmd, cmd_tmp, &cr->conn_recovery_cmd_list, i_conn_node) { - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); cmd->conn = NULL; spin_unlock(&cr->conn_recovery_cmd_lock); iscsit_free_cmd(cmd, true); @@ -216,7 +216,7 @@ int iscsit_remove_cmd_from_connection_recovery( } cr = cmd->cr; - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); return --cr->cmd_count; } @@ -297,7 +297,7 @@ int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *conn) if (!(cmd->cmd_flags & ICF_OOO_CMDSN)) continue; - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_free_cmd(cmd, true); @@ -335,7 +335,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) /* * Only perform connection recovery on ISCSI_OP_SCSI_CMD or * ISCSI_OP_NOOP_OUT opcodes. For all other opcodes call - * list_del(&cmd->i_conn_node); to release the command to the + * list_del_init(&cmd->i_conn_node); to release the command to the * session pool and remove it from the connection's list. * * Also stop the DataOUT timer, which will be restarted after @@ -351,7 +351,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) " CID: %hu\n", cmd->iscsi_opcode, cmd->init_task_tag, cmd->cmd_sn, conn->cid); - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_free_cmd(cmd, true); spin_lock_bh(&conn->cmd_lock); @@ -371,7 +371,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) */ if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd && iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) { - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_free_cmd(cmd, true); spin_lock_bh(&conn->cmd_lock); @@ -393,7 +393,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) cmd->sess = conn->sess; - list_del(&cmd->i_conn_node); + list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); iscsit_free_all_datain_reqs(cmd); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 39761837608d..44a5471de00f 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -137,7 +137,7 @@ struct iscsi_portal_group *iscsit_get_tpg_from_np( list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) { spin_lock(&tpg->tpg_state_lock); - if (tpg->tpg_state == TPG_STATE_FREE) { + if (tpg->tpg_state != TPG_STATE_ACTIVE) { spin_unlock(&tpg->tpg_state_lock); continue; } diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 42f18fc1067b..77e6531fb0a1 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1079,25 +1079,31 @@ sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read, left = sectors * dev->prot_length; for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) { - - len = min(psg->length, left); - if (offset >= sg->length) { - sg = sg_next(sg); - offset = 0; - } + unsigned int psg_len, copied = 0; paddr = kmap_atomic(sg_page(psg)) + psg->offset; - addr = kmap_atomic(sg_page(sg)) + sg->offset + offset; - - if (read) - memcpy(paddr, addr, len); - else - memcpy(addr, paddr, len); - - left -= len; - offset += len; + psg_len = min(left, psg->length); + while (psg_len) { + len = min(psg_len, sg->length - offset); + addr = kmap_atomic(sg_page(sg)) + sg->offset + offset; + + if (read) + memcpy(paddr + copied, addr, len); + else + memcpy(addr, paddr + copied, len); + + left -= len; + offset += len; + copied += len; + psg_len -= len; + + if (offset >= sg->length) { + sg = sg_next(sg); + offset = 0; + } + kunmap_atomic(addr); + } kunmap_atomic(paddr); - kunmap_atomic(addr); } } diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 35c066489a19..5f88d767671e 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -136,6 +136,7 @@ config SPEAR_THERMAL config RCAR_THERMAL tristate "Renesas R-Car thermal driver" depends on ARCH_SHMOBILE || COMPILE_TEST + depends on HAS_IOMEM help Enable this to plug the R-Car thermal sensor driver into the Linux thermal framework. @@ -210,8 +211,16 @@ config ACPI_INT3403_THERMAL tristate "ACPI INT3403 thermal driver" depends on X86 && ACPI help - This driver uses ACPI INT3403 device objects. If present, it will - register each INT3403 thermal sensor as a thermal zone. + Newer laptops and tablets that use ACPI may have thermal sensors + outside the core CPU/SOC for thermal safety reasons. These + temperature sensors are also exposed for the OS to use via the so + called INT3403 ACPI object. This driver will, on devices that have + such sensors, expose the temperature information from these sensors + to userspace via the normal thermal framework. This means that a wide + range of applications and GUI widgets can show this information to + the user or use this information for making decisions. For example, + the Intel Thermal Daemon can use this information to allow the user + to select his laptop to run without turning on the fans. menu "Texas Instruments thermal drivers" source "drivers/thermal/ti-soc-thermal/Kconfig" diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 338a88bf6662..71b0ec0c370d 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -56,10 +56,15 @@ static LIST_HEAD(thermal_governor_list); static DEFINE_MUTEX(thermal_list_lock); static DEFINE_MUTEX(thermal_governor_lock); +static struct thermal_governor *def_governor; + static struct thermal_governor *__find_governor(const char *name) { struct thermal_governor *pos; + if (!name || !name[0]) + return def_governor; + list_for_each_entry(pos, &thermal_governor_list, governor_list) if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH)) return pos; @@ -82,17 +87,23 @@ int thermal_register_governor(struct thermal_governor *governor) if (__find_governor(governor->name) == NULL) { err = 0; list_add(&governor->governor_list, &thermal_governor_list); + if (!def_governor && !strncmp(governor->name, + DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH)) + def_governor = governor; } mutex_lock(&thermal_list_lock); list_for_each_entry(pos, &thermal_tz_list, node) { + /* + * only thermal zones with specified tz->tzp->governor_name + * may run with tz->govenor unset + */ if (pos->governor) continue; - if (pos->tzp) - name = pos->tzp->governor_name; - else - name = DEFAULT_THERMAL_GOVERNOR; + + name = pos->tzp->governor_name; + if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH)) pos->governor = governor; } @@ -342,8 +353,8 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz) static void handle_non_critical_trips(struct thermal_zone_device *tz, int trip, enum thermal_trip_type trip_type) { - if (tz->governor) - tz->governor->throttle(tz, trip); + tz->governor ? tz->governor->throttle(tz, trip) : + def_governor->throttle(tz, trip); } static void handle_critical_trips(struct thermal_zone_device *tz, @@ -1107,7 +1118,7 @@ __thermal_cooling_device_register(struct device_node *np, INIT_LIST_HEAD(&cdev->thermal_instances); cdev->np = np; cdev->ops = ops; - cdev->updated = true; + cdev->updated = false; cdev->device.class = &thermal_class; cdev->devdata = devdata; dev_set_name(&cdev->device, "cooling_device%d", cdev->id); @@ -1533,7 +1544,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type, if (tz->tzp) tz->governor = __find_governor(tz->tzp->governor_name); else - tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR); + tz->governor = def_governor; mutex_unlock(&thermal_governor_lock); diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c index 972e1c73722a..081fd7e6a9f0 100644 --- a/drivers/thermal/x86_pkg_temp_thermal.c +++ b/drivers/thermal/x86_pkg_temp_thermal.c @@ -68,6 +68,10 @@ struct phy_dev_entry { struct thermal_zone_device *tzone; }; +static const struct thermal_zone_params pkg_temp_tz_params = { + .no_hwmon = true, +}; + /* List maintaining number of package instances */ static LIST_HEAD(phy_dev_list); static DEFINE_MUTEX(phy_dev_list_mutex); @@ -394,7 +398,6 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) int err; u32 tj_max; struct phy_dev_entry *phy_dev_entry; - char buffer[30]; int thres_count; u32 eax, ebx, ecx, edx; u8 *temp; @@ -440,13 +443,11 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) phy_dev_entry->first_cpu = cpu; phy_dev_entry->tj_max = tj_max; phy_dev_entry->ref_cnt = 1; - snprintf(buffer, sizeof(buffer), "pkg-temp-%d\n", - phy_dev_entry->phys_proc_id); - phy_dev_entry->tzone = thermal_zone_device_register(buffer, + phy_dev_entry->tzone = thermal_zone_device_register("x86_pkg_temp", thres_count, (thres_count == MAX_NUMBER_OF_TRIPS) ? 0x03 : 0x01, - phy_dev_entry, &tzone_ops, NULL, 0, 0); + phy_dev_entry, &tzone_ops, &pkg_temp_tz_params, 0, 0); if (IS_ERR(phy_dev_entry->tzone)) { err = PTR_ERR(phy_dev_entry->tzone); goto err_ret_free; diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c index cf86e729532b..dc697cee248a 100644 --- a/drivers/tty/serial/sunhv.c +++ b/drivers/tty/serial/sunhv.c @@ -433,13 +433,10 @@ static void sunhv_console_write_paged(struct console *con, const char *s, unsign unsigned long flags; int locked = 1; - local_irq_save(flags); - if (port->sysrq) { - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&port->lock); - } else - spin_lock(&port->lock); + if (port->sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); while (n > 0) { unsigned long ra = __pa(con_write_page); @@ -470,8 +467,7 @@ static void sunhv_console_write_paged(struct console *con, const char *s, unsign } if (locked) - spin_unlock(&port->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&port->lock, flags); } static inline void sunhv_console_putchar(struct uart_port *port, char c) @@ -492,7 +488,10 @@ static void sunhv_console_write_bychar(struct console *con, const char *s, unsig unsigned long flags; int i, locked = 1; - local_irq_save(flags); + if (port->sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); if (port->sysrq) { locked = 0; } else if (oops_in_progress) { @@ -507,8 +506,7 @@ static void sunhv_console_write_bychar(struct console *con, const char *s, unsig } if (locked) - spin_unlock(&port->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&port->lock, flags); } static struct console sunhv_console = { diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c index 380fb5355cb2..5faa8e905e98 100644 --- a/drivers/tty/serial/sunsab.c +++ b/drivers/tty/serial/sunsab.c @@ -844,20 +844,16 @@ static void sunsab_console_write(struct console *con, const char *s, unsigned n) unsigned long flags; int locked = 1; - local_irq_save(flags); - if (up->port.sysrq) { - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&up->port.lock); - } else - spin_lock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); + else + spin_lock_irqsave(&up->port.lock, flags); uart_console_write(&up->port, s, n, sunsab_console_putchar); sunsab_tec_wait(up); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int sunsab_console_setup(struct console *con, char *options) diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c index db79b76f5c8e..9a0f24f83720 100644 --- a/drivers/tty/serial/sunsu.c +++ b/drivers/tty/serial/sunsu.c @@ -1295,13 +1295,10 @@ static void sunsu_console_write(struct console *co, const char *s, unsigned int ier; int locked = 1; - local_irq_save(flags); - if (up->port.sysrq) { - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&up->port.lock); - } else - spin_lock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); + else + spin_lock_irqsave(&up->port.lock, flags); /* * First save the UER then disable the interrupts @@ -1319,8 +1316,7 @@ static void sunsu_console_write(struct console *co, const char *s, serial_out(up, UART_IER, ier); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } /* diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c index 45a8c6aa5837..a2c40ed287d2 100644 --- a/drivers/tty/serial/sunzilog.c +++ b/drivers/tty/serial/sunzilog.c @@ -1195,20 +1195,16 @@ sunzilog_console_write(struct console *con, const char *s, unsigned int count) unsigned long flags; int locked = 1; - local_irq_save(flags); - if (up->port.sysrq) { - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&up->port.lock); - } else - spin_lock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); + else + spin_lock_irqsave(&up->port.lock, flags); uart_console_write(&up->port, s, count, sunzilog_putchar); udelay(2); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init sunzilog_console_setup(struct console *con, char *options) diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index d8a55e87877f..0ffb0cbe2823 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -39,17 +39,10 @@ lock_acquire(&(l)->dep_map, s, t, r, c, n, i) # define __rel(l, n, i) \ lock_release(&(l)->dep_map, n, i) -# ifdef CONFIG_PROVE_LOCKING -# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 2, NULL, i) -# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 2, n, i) -# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 2, NULL, i) -# define lockdep_release(l, n, i) __rel(l, n, i) -# else -# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 1, NULL, i) -# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 1, n, i) -# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 1, NULL, i) -# define lockdep_release(l, n, i) __rel(l, n, i) -# endif +#define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 1, NULL, i) +#define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 1, n, i) +#define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 1, NULL, i) +#define lockdep_release(l, n, i) __rel(l, n, i) #else # define lockdep_acquire(l, s, t, i) do { } while (0) # define lockdep_acquire_nest(l, s, t, n, i) do { } while (0) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 8d72f0c65937..062967c90b2a 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -717,6 +717,10 @@ int usb_get_configuration(struct usb_device *dev) result = -ENOMEM; goto err; } + + if (dev->quirks & USB_QUIRK_DELAY_INIT) + msleep(100); + result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); if (result < 0) { diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 8f37063c0a49..739ee8e8bdfd 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -47,6 +47,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Logitech HD Pro Webcams C920 and C930e */ + { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Logitech Quickcam Fusion */ { USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6fe577d46fa2..924a6ccdb622 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4733,6 +4733,9 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) /* Accept arbitrarily long scatter-gather lists */ hcd->self.sg_tablesize = ~0; + /* support to build packet from discontinuous buffers */ + hcd->self.no_sg_constraint = 1; + /* XHCI controllers don't stop the ep queue on short packets :| */ hcd->self.no_stop_on_short = 1; @@ -4757,14 +4760,6 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) /* xHCI private pointer was set in xhci_pci_probe for the second * registered roothub. */ - xhci = hcd_to_xhci(hcd); - /* - * Support arbitrarily aligned sg-list entries on hosts without - * TD fragment rules (which are currently unsupported). - */ - if (xhci->hci_version < 0x100) - hcd->self.no_sg_constraint = 1; - return 0; } @@ -4793,9 +4788,6 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) if (xhci->hci_version > 0x96) xhci->quirks |= XHCI_SPURIOUS_SUCCESS; - if (xhci->hci_version < 0x100) - hcd->self.no_sg_constraint = 1; - /* Make sure the HC is halted. */ retval = xhci_halt(xhci); if (retval) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4fb7a8f83c8a..54af4e933695 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -186,12 +186,12 @@ static bool is_invalid_reserved_pfn(unsigned long pfn) if (pfn_valid(pfn)) { bool reserved; struct page *tail = pfn_to_page(pfn); - struct page *head = compound_trans_head(tail); + struct page *head = compound_head(tail); reserved = !!(PageReserved(head)); if (head != tail) { /* * "head" is not a dangling pointer - * (compound_trans_head takes care of that) + * (compound_head takes care of that) * but the hugepage may have been split * from under us (and we may not hold a * reference count on the head page so it can diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index a0fa5de210cf..e1e22e0f01e8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -505,9 +505,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, r = -ENOBUFS; goto err; } - d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg, + r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg, ARRAY_SIZE(vq->iov) - seg, &out, &in, log, log_num); + if (unlikely(r < 0)) + goto err; + + d = r; if (d == vq->num) { r = 0; goto err; @@ -532,6 +536,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, *iovcount = seg; if (unlikely(log)) *log_num = nlogs; + + /* Detect overrun */ + if (unlikely(datalen > 0)) { + r = UIO_MAXIOV + 1; + goto err; + } return headcount; err: vhost_discard_vq_desc(vq, headcount); @@ -587,6 +597,14 @@ static void handle_rx(struct vhost_net *net) /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) break; + /* On overrun, truncate and discard */ + if (unlikely(headcount > UIO_MAXIOV)) { + msg.msg_iovlen = 1; + err = sock->ops->recvmsg(NULL, sock, &msg, + 1, MSG_DONTWAIT | MSG_TRUNC); + pr_debug("Discarded rx packet: len %zd\n", sock_len); + continue; + } /* OK, now we need to know about added descriptors. */ if (!headcount) { if (unlikely(vhost_enable_notify(&net->dev, vq))) { diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 37d06ea624aa..61a6ac8fa8fc 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -399,11 +399,25 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } + scrub_page(page); - pfn = page_to_pfn(page); - frame_list[i] = pfn_to_mfn(pfn); + frame_list[i] = page_to_pfn(page); + } - scrub_page(page); + /* + * Ensure that ballooned highmem pages don't have kmaps. + * + * Do this before changing the p2m as kmap_flush_unused() + * reads PTEs to obtain pages (and hence needs the original + * p2m entry). + */ + kmap_flush_unused(); + + /* Update direct mapping, invalidate P2M, and add to balloon. */ + for (i = 0; i < nr_pages; i++) { + pfn = frame_list[i]; + frame_list[i] = pfn_to_mfn(pfn); + page = pfn_to_page(pfn); #ifdef CONFIG_XEN_HAVE_PVMMU /* @@ -429,11 +443,9 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) } #endif - balloon_append(pfn_to_page(pfn)); + balloon_append(page); } - /* Ensure that ballooned highmem pages don't have kmaps. */ - kmap_flush_unused(); flush_tlb_all(); set_xen_guest_handle(reservation.extent_start, frame_list); diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 24084732b1d0..80ef38c73e5a 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -41,19 +41,8 @@ static const struct dentry_operations anon_inodefs_dentry_operations = { static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - struct dentry *root; - root = mount_pseudo(fs_type, "anon_inode:", NULL, + return mount_pseudo(fs_type, "anon_inode:", NULL, &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC); - if (!IS_ERR(root)) { - struct super_block *s = root->d_sb; - anon_inode_inode = alloc_anon_inode(s); - if (IS_ERR(anon_inode_inode)) { - dput(root); - deactivate_locked_super(s); - root = ERR_CAST(anon_inode_inode); - } - } - return root; } static struct file_system_type anon_inode_fs_type = { @@ -175,22 +164,15 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd); static int __init anon_inode_init(void) { - int error; - - error = register_filesystem(&anon_inode_fs_type); - if (error) - goto err_exit; anon_inode_mnt = kern_mount(&anon_inode_fs_type); - if (IS_ERR(anon_inode_mnt)) { - error = PTR_ERR(anon_inode_mnt); - goto err_unregister_filesystem; - } - return 0; + if (IS_ERR(anon_inode_mnt)) + panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); -err_unregister_filesystem: - unregister_filesystem(&anon_inode_fs_type); -err_exit: - panic(KERN_ERR "anon_inode_init() failed (%d)\n", error); + anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); + if (IS_ERR(anon_inode_inode)) + panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); + + return 0; } fs_initcall(anon_inode_init); diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 0129b78a6908..4f70f383132c 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -458,11 +458,10 @@ static int bio_integrity_verify(struct bio *bio) struct blk_integrity_exchg bix; struct bio_vec *bv; sector_t sector = bio->bi_integrity->bip_iter.bi_sector; - unsigned int sectors, total, ret; + unsigned int sectors, ret = 0; void *prot_buf = bio->bi_integrity->bip_buf; int i; - ret = total = 0; bix.disk_name = bio->bi_bdev->bd_disk->disk_name; bix.sector_size = bi->sector_size; @@ -484,8 +483,6 @@ static int bio_integrity_verify(struct bio *bio) sectors = bv->bv_len / bi->sector_size; sector += sectors; prot_buf += sectors * bi->tuple_size; - total += sectors * bi->tuple_size; - BUG_ON(total > bio->bi_integrity->bip_iter.bi_size); kunmap_atomic(kaddr); } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index cf32f0393369..c0f3718b77a8 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -513,7 +513,7 @@ struct cifs_mnt_data { static inline unsigned int get_rfc1002_length(void *buf) { - return be32_to_cpu(*((__be32 *)buf)); + return be32_to_cpu(*((__be32 *)buf)) & 0xffffff; } static inline void diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 53c15074bb36..834fce759d80 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2579,31 +2579,19 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; ssize_t rc = -EACCES; + loff_t lock_pos = pos; - BUG_ON(iocb->ki_pos != pos); - + if (file->f_flags & O_APPEND) + lock_pos = i_size_read(inode); /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents writing. */ down_read(&cinode->lock_sem); - if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs), + if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs), server->vals->exclusive_lock_type, NULL, - CIFS_WRITE_OP)) { - mutex_lock(&inode->i_mutex); - rc = __generic_file_aio_write(iocb, iov, nr_segs, - &iocb->ki_pos); - mutex_unlock(&inode->i_mutex); - } - - if (rc > 0) { - ssize_t err; - - err = generic_write_sync(file, iocb->ki_pos - rc, rc); - if (err < 0) - rc = err; - } - + CIFS_WRITE_OP)) + rc = generic_file_aio_write(iocb, iov, nr_segs, pos); up_read(&cinode->lock_sem); return rc; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b37570952846..18cd5650a5fc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -270,6 +270,26 @@ cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx, iov->iov_len = rqst->rq_pagesz; } +static unsigned long +rqst_len(struct smb_rqst *rqst) +{ + unsigned int i; + struct kvec *iov = rqst->rq_iov; + unsigned long buflen = 0; + + /* total up iov array first */ + for (i = 0; i < rqst->rq_nvec; i++) + buflen += iov[i].iov_len; + + /* add in the page array if there is one */ + if (rqst->rq_npages) { + buflen += rqst->rq_pagesz * (rqst->rq_npages - 1); + buflen += rqst->rq_tailsz; + } + + return buflen; +} + static int smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) { @@ -277,6 +297,7 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base); + unsigned long send_length; unsigned int i; size_t total_len = 0, sent; struct socket *ssocket = server->ssocket; @@ -285,6 +306,14 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) if (ssocket == NULL) return -ENOTSOCK; + /* sanity check send length */ + send_length = rqst_len(rqst); + if (send_length != smb_buf_length + 4) { + WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n", + send_length, smb_buf_length); + return -EIO; + } + cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length); dump_smb(iov[0].iov_base, iov[0].iov_len); diff --git a/fs/dcache.c b/fs/dcache.c index 265e0ce9769c..ca02c13a84aa 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2833,9 +2833,9 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; - if (*buflen < dlen + 1) - return -ENAMETOOLONG; *buflen -= dlen + 1; + if (*buflen < 0) + return -ENAMETOOLONG; p = *buffer -= dlen + 1; *p++ = '/'; while (dlen--) { diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 8dd524f32284..cdb2971192a5 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -21,7 +21,7 @@ static ssize_t efivarfs_file_write(struct file *file, u32 attributes; struct inode *inode = file->f_mapping->host; unsigned long datasize = count - sizeof(attributes); - ssize_t bytes = 0; + ssize_t bytes; bool set = false; if (count < sizeof(attributes)) @@ -33,14 +33,9 @@ static ssize_t efivarfs_file_write(struct file *file, if (attributes & ~(EFI_VARIABLE_MASK)) return -EINVAL; - data = kmalloc(datasize, GFP_KERNEL); - if (!data) - return -ENOMEM; - - if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) { - bytes = -EFAULT; - goto out; - } + data = memdup_user(userbuf + sizeof(attributes), datasize); + if (IS_ERR(data)) + return PTR_ERR(data); bytes = efivar_entry_set_get_size(var, attributes, &datasize, data, &set); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6e39895a91b8..24bfd7ff3049 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -38,6 +38,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/aio.h> +#include <linux/bitops.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -3921,18 +3922,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) void ext4_set_inode_flags(struct inode *inode) { unsigned int flags = EXT4_I(inode)->i_flags; + unsigned int new_fl = 0; - inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); if (flags & EXT4_SYNC_FL) - inode->i_flags |= S_SYNC; + new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) - inode->i_flags |= S_APPEND; + new_fl |= S_APPEND; if (flags & EXT4_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (flags & EXT4_NOATIME_FL) - inode->i_flags |= S_NOATIME; + new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) - inode->i_flags |= S_DIRSYNC; + new_fl |= S_DIRSYNC; + set_mask_bits(&inode->i_flags, + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl); } /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */ diff --git a/fs/file.c b/fs/file.c index db25c2bdfe46..b61293badfb1 100644 --- a/fs/file.c +++ b/fs/file.c @@ -497,7 +497,7 @@ repeat: error = fd; #if 1 /* Sanity check */ - if (rcu_dereference_raw(fdt->fd[fd]) != NULL) { + if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } @@ -683,35 +683,54 @@ EXPORT_SYMBOL(fget_raw); * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ -struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed) +static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; - *fput_needed = 0; if (atomic_read(&files->count) == 1) { file = __fcheck_files(files, fd); - if (file && (file->f_mode & mask)) - file = NULL; + if (!file || unlikely(file->f_mode & mask)) + return 0; + return (unsigned long)file; } else { file = __fget(fd, mask); - if (file) - *fput_needed = 1; + if (!file) + return 0; + return FDPUT_FPUT | (unsigned long)file; } - - return file; } -struct file *fget_light(unsigned int fd, int *fput_needed) +unsigned long __fdget(unsigned int fd) { - return __fget_light(fd, FMODE_PATH, fput_needed); + return __fget_light(fd, FMODE_PATH); } -EXPORT_SYMBOL(fget_light); +EXPORT_SYMBOL(__fdget); -struct file *fget_raw_light(unsigned int fd, int *fput_needed) +unsigned long __fdget_raw(unsigned int fd) { - return __fget_light(fd, 0, fput_needed); + return __fget_light(fd, 0); } +unsigned long __fdget_pos(unsigned int fd) +{ + unsigned long v = __fdget(fd); + struct file *file = (struct file *)(v & ~3); + + if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file_count(file) > 1) { + v |= FDPUT_POS_UNLOCK; + mutex_lock(&file->f_pos_lock); + } + } + return v; +} + +/* + * We only lock f_pos if we have threads or if the file might be + * shared with another process. In both cases we'll have an elevated + * file count (done either by fdget() or by fork()). + */ + void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; diff --git a/fs/file_table.c b/fs/file_table.c index 5fff9030be34..5b24008ea4f6 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -135,6 +135,7 @@ struct file *get_empty_filp(void) atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); + mutex_init(&f->f_pos_lock); eventpoll_init_file(f); /* f->f_version: 0 */ return f; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 968ce411db53..32602c667b4a 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -103,6 +103,8 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, folder = &entry->folder; memset(folder, 0, sizeof(*folder)); folder->type = cpu_to_be16(HFSPLUS_FOLDER); + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) + folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT); folder->id = cpu_to_be32(inode->i_ino); HFSPLUS_I(inode)->create_date = folder->create_date = @@ -203,6 +205,36 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, return hfs_brec_find(fd, hfs_find_rec_by_key); } +static void hfsplus_subfolders_inc(struct inode *dir) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); + + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { + /* + * Increment subfolder count. Note, the value is only meaningful + * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. + */ + HFSPLUS_I(dir)->subfolders++; + } +} + +static void hfsplus_subfolders_dec(struct inode *dir) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); + + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { + /* + * Decrement subfolder count. Note, the value is only meaningful + * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. + * + * Check for zero. Some subfolders may have been created + * by an implementation ignorant of this counter. + */ + if (HFSPLUS_I(dir)->subfolders) + HFSPLUS_I(dir)->subfolders--; + } +} + int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode) { @@ -247,6 +279,8 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, goto err1; dir->i_size++; + if (S_ISDIR(inode->i_mode)) + hfsplus_subfolders_inc(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); @@ -336,6 +370,8 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) goto out; dir->i_size--; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_dec(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); @@ -380,6 +416,7 @@ int hfsplus_rename_cat(u32 cnid, hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset, src_fd.entrylength); + type = be16_to_cpu(entry.type); /* create new dir entry with the data from the old entry */ hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); @@ -394,6 +431,8 @@ int hfsplus_rename_cat(u32 cnid, if (err) goto out; dst_dir->i_size++; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_inc(dst_dir); dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC; /* finally remove the old entry */ @@ -405,6 +444,8 @@ int hfsplus_rename_cat(u32 cnid, if (err) goto out; src_dir->i_size--; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_dec(src_dir); src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC; /* remove old thread entry */ diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 08846425b67f..62d571eb69ba 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -242,6 +242,7 @@ struct hfsplus_inode_info { */ sector_t fs_blocks; u8 userflags; /* BSD user file flags */ + u32 subfolders; /* Subfolder count (HFSX only) */ struct list_head open_dir_list; loff_t phys_size; diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 8ffb3a8ffe75..5a126828d85e 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -261,7 +261,7 @@ struct hfsplus_cat_folder { struct DInfo user_info; struct DXInfo finder_info; __be32 text_encoding; - u32 reserved; + __be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */ } __packed; /* HFS file info (stolen from hfs.h) */ @@ -301,11 +301,13 @@ struct hfsplus_cat_file { struct hfsplus_fork_raw rsrc_fork; } __packed; -/* File attribute bits */ +/* File and folder flag bits */ #define HFSPLUS_FILE_LOCKED 0x0001 #define HFSPLUS_FILE_THREAD_EXISTS 0x0002 #define HFSPLUS_XATTR_EXISTS 0x0004 #define HFSPLUS_ACL_EXISTS 0x0008 +#define HFSPLUS_HAS_FOLDER_COUNT 0x0010 /* Folder has subfolder count + * (HFSX only) */ /* HFS+ catalog thread (part of a cat_entry) */ struct hfsplus_cat_thread { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index fa929f325f87..a4f45bd88a63 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -375,6 +375,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) hip->extent_state = 0; hip->flags = 0; hip->userflags = 0; + hip->subfolders = 0; memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec)); memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec)); hip->alloc_blocks = 0; @@ -494,6 +495,10 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date); HFSPLUS_I(inode)->create_date = folder->create_date; HFSPLUS_I(inode)->fs_blocks = 0; + if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { + HFSPLUS_I(inode)->subfolders = + be32_to_cpu(folder->subfolders); + } inode->i_op = &hfsplus_dir_inode_operations; inode->i_fop = &hfsplus_dir_operations; } else if (type == HFSPLUS_FILE) { @@ -566,6 +571,10 @@ int hfsplus_cat_write_inode(struct inode *inode) folder->content_mod_date = hfsp_ut2mt(inode->i_mtime); folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime); folder->valence = cpu_to_be32(inode->i_size - 2); + if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { + folder->subfolders = + cpu_to_be32(HFSPLUS_I(inode)->subfolders); + } hfs_bnode_write(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); } else if (HFSPLUS_IS_RSRC(inode)) { diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 968eab5bc1f5..68537e8b7a09 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force) int token; if (!input) - return 0; + return 1; while ((p = strsep(&input, ",")) != NULL) { if (!*p) diff --git a/fs/mount.h b/fs/mount.h index a17458ca6f29..b29e42f05f34 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -19,13 +19,13 @@ struct mnt_pcp { }; struct mountpoint { - struct list_head m_hash; + struct hlist_node m_hash; struct dentry *m_dentry; int m_count; }; struct mount { - struct list_head mnt_hash; + struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; diff --git a/fs/namei.c b/fs/namei.c index 385f7817bfcc..4b491b431990 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1109,7 +1109,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, return false; if (!d_mountpoint(path->dentry)) - break; + return true; mounted = __lookup_mnt(path->mnt, path->dentry); if (!mounted) @@ -1125,20 +1125,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, */ *inode = path->dentry->d_inode; } - return true; -} - -static void follow_mount_rcu(struct nameidata *nd) -{ - while (d_mountpoint(nd->path.dentry)) { - struct mount *mounted; - mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry); - if (!mounted) - break; - nd->path.mnt = &mounted->mnt; - nd->path.dentry = mounted->mnt.mnt_root; - nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); - } + return read_seqretry(&mount_lock, nd->m_seq); } static int follow_dotdot_rcu(struct nameidata *nd) @@ -1166,7 +1153,17 @@ static int follow_dotdot_rcu(struct nameidata *nd) break; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } - follow_mount_rcu(nd); + while (d_mountpoint(nd->path.dentry)) { + struct mount *mounted; + mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry); + if (!mounted) + break; + nd->path.mnt = &mounted->mnt; + nd->path.dentry = mounted->mnt.mnt_root; + nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); + if (!read_seqretry(&mount_lock, nd->m_seq)) + goto failed; + } nd->inode = nd->path.dentry->d_inode; return 0; @@ -1884,7 +1881,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { - if (f.need_put) + if (f.flags & FDPUT_FPUT) *fp = f.file; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); rcu_read_lock(); diff --git a/fs/namespace.c b/fs/namespace.c index 22e536705c45..2ffc5a2905d4 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -23,11 +23,34 @@ #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> +#include <linux/bootmem.h> #include "pnode.h" #include "internal.h" -#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head)) -#define HASH_SIZE (1UL << HASH_SHIFT) +static unsigned int m_hash_mask __read_mostly; +static unsigned int m_hash_shift __read_mostly; +static unsigned int mp_hash_mask __read_mostly; +static unsigned int mp_hash_shift __read_mostly; + +static __initdata unsigned long mhash_entries; +static int __init set_mhash_entries(char *str) +{ + if (!str) + return 0; + mhash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mhash_entries=", set_mhash_entries); + +static __initdata unsigned long mphash_entries; +static int __init set_mphash_entries(char *str) +{ + if (!str) + return 0; + mphash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mphash_entries=", set_mphash_entries); static int event; static DEFINE_IDA(mnt_id_ida); @@ -36,8 +59,8 @@ static DEFINE_SPINLOCK(mnt_id_lock); static int mnt_id_start = 0; static int mnt_group_start = 1; -static struct list_head *mount_hashtable __read_mostly; -static struct list_head *mountpoint_hashtable __read_mostly; +static struct hlist_head *mount_hashtable __read_mostly; +static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); @@ -55,12 +78,19 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) +static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> HASH_SHIFT); - return tmp & (HASH_SIZE - 1); + tmp = tmp + (tmp >> m_hash_shift); + return &mount_hashtable[tmp & m_hash_mask]; +} + +static inline struct hlist_head *mp_hash(struct dentry *dentry) +{ + unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); + tmp = tmp + (tmp >> mp_hash_shift); + return &mountpoint_hashtable[tmp & mp_hash_mask]; } /* @@ -187,7 +217,7 @@ static struct mount *alloc_vfsmnt(const char *name) mnt->mnt_writers = 0; #endif - INIT_LIST_HEAD(&mnt->mnt_hash); + INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); @@ -575,10 +605,10 @@ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); + struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; - list_for_each_entry_rcu(p, head, mnt_hash) + hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; @@ -590,13 +620,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) */ struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); - struct mount *p; - - list_for_each_entry_reverse(p, head, mnt_hash) - if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) - return p; - return NULL; + struct mount *p, *res; + res = p = __lookup_mnt(mnt, dentry); + if (!p) + goto out; + hlist_for_each_entry_continue(p, mnt_hash) { + if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) + break; + res = p; + } +out: + return res; } /* @@ -633,11 +667,11 @@ struct vfsmount *lookup_mnt(struct path *path) static struct mountpoint *new_mountpoint(struct dentry *dentry) { - struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry); + struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; int ret; - list_for_each_entry(mp, chain, m_hash) { + hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) @@ -659,7 +693,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry) mp->m_dentry = dentry; mp->m_count = 1; - list_add(&mp->m_hash, chain); + hlist_add_head(&mp->m_hash, chain); return mp; } @@ -670,7 +704,7 @@ static void put_mountpoint(struct mountpoint *mp) spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); - list_del(&mp->m_hash); + hlist_del(&mp->m_hash); kfree(mp); } } @@ -712,7 +746,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path) mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); - list_del_init(&mnt->mnt_hash); + hlist_del_init_rcu(&mnt->mnt_hash); put_mountpoint(mnt->mnt_mp); mnt->mnt_mp = NULL; } @@ -739,15 +773,14 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mp->m_dentry)); + hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt) +static void commit_tree(struct mount *mnt, struct mount *shadows) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -762,8 +795,11 @@ static void commit_tree(struct mount *mnt) list_splice(&head, n->list.prev); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mnt->mnt_mountpoint)); + if (shadows) + hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash); + else + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); touch_mnt_namespace(n); } @@ -1153,26 +1189,28 @@ int may_umount(struct vfsmount *mnt) EXPORT_SYMBOL(may_umount); -static LIST_HEAD(unmounted); /* protected by namespace_sem */ +static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static void namespace_unlock(void) { struct mount *mnt; - LIST_HEAD(head); + struct hlist_head head = unmounted; - if (likely(list_empty(&unmounted))) { + if (likely(hlist_empty(&head))) { up_write(&namespace_sem); return; } - list_splice_init(&unmounted, &head); + head.first->pprev = &head.first; + INIT_HLIST_HEAD(&unmounted); + up_write(&namespace_sem); synchronize_rcu(); - while (!list_empty(&head)) { - mnt = list_first_entry(&head, struct mount, mnt_hash); - list_del_init(&mnt->mnt_hash); + while (!hlist_empty(&head)) { + mnt = hlist_entry(head.first, struct mount, mnt_hash); + hlist_del_init(&mnt->mnt_hash); if (mnt->mnt_ex_mountpoint.mnt) path_put(&mnt->mnt_ex_mountpoint); mntput(&mnt->mnt); @@ -1193,16 +1231,19 @@ static inline void namespace_lock(void) */ void umount_tree(struct mount *mnt, int how) { - LIST_HEAD(tmp_list); + HLIST_HEAD(tmp_list); struct mount *p; + struct mount *last = NULL; - for (p = mnt; p; p = next_mnt(p, mnt)) - list_move(&p->mnt_hash, &tmp_list); + for (p = mnt; p; p = next_mnt(p, mnt)) { + hlist_del_init_rcu(&p->mnt_hash); + hlist_add_head(&p->mnt_hash, &tmp_list); + } if (how) propagate_umount(&tmp_list); - list_for_each_entry(p, &tmp_list, mnt_hash) { + hlist_for_each_entry(p, &tmp_list, mnt_hash) { list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); @@ -1220,8 +1261,13 @@ void umount_tree(struct mount *mnt, int how) p->mnt_mp = NULL; } change_mnt_propagation(p, MS_PRIVATE); + last = p; + } + if (last) { + last->mnt_hash.next = unmounted.first; + unmounted.first = tmp_list.first; + unmounted.first->pprev = &unmounted.first; } - list_splice(&tmp_list, &unmounted); } static void shrink_submounts(struct mount *mnt); @@ -1605,24 +1651,23 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct mountpoint *dest_mp, struct path *parent_path) { - LIST_HEAD(tree_list); + HLIST_HEAD(tree_list); struct mount *child, *p; + struct hlist_node *n; int err; if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; - } - err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); - if (err) - goto out_cleanup_ids; - - lock_mount_hash(); - - if (IS_MNT_SHARED(dest_mnt)) { + err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); + if (err) + goto out_cleanup_ids; + lock_mount_hash(); for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); + } else { + lock_mount_hash(); } if (parent_path) { detach_mnt(source_mnt, parent_path); @@ -1630,20 +1675,22 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt); + commit_tree(source_mnt, NULL); } - list_for_each_entry_safe(child, p, &tree_list, mnt_hash) { - list_del_init(&child->mnt_hash); - commit_tree(child); + hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { + struct mount *q; + hlist_del_init(&child->mnt_hash); + q = __lookup_mnt_last(&child->mnt_parent->mnt, + child->mnt_mountpoint); + commit_tree(child, q); } unlock_mount_hash(); return 0; out_cleanup_ids: - if (IS_MNT_SHARED(dest_mnt)) - cleanup_group_ids(source_mnt, NULL); + cleanup_group_ids(source_mnt, NULL); out: return err; } @@ -2777,18 +2824,24 @@ void __init mnt_init(void) mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); - mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); + mount_hashtable = alloc_large_system_hash("Mount-cache", + sizeof(struct hlist_head), + mhash_entries, 19, + 0, + &m_hash_shift, &m_hash_mask, 0, 0); + mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", + sizeof(struct hlist_head), + mphash_entries, 19, + 0, + &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); - printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE); - - for (u = 0; u < HASH_SIZE; u++) - INIT_LIST_HEAD(&mount_hashtable[u]); - for (u = 0; u < HASH_SIZE; u++) - INIT_LIST_HEAD(&mountpoint_hashtable[u]); + for (u = 0; u <= m_hash_mask; u++) + INIT_HLIST_HEAD(&mount_hashtable[u]); + for (u = 0; u <= mp_hash_mask; u++) + INIT_HLIST_HEAD(&mountpoint_hashtable[u]); kernfs_init(); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index ef792f29f831..5d8ccecf5f5c 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -659,16 +659,19 @@ int nfs_async_inode_return_delegation(struct inode *inode, rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation == NULL) + goto out_enoent; - if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) { - rcu_read_unlock(); - return -ENOENT; - } + if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) + goto out_enoent; nfs_mark_return_delegation(server, delegation); rcu_read_unlock(); nfs_delegation_run_state_manager(clp); return 0; +out_enoent: + rcu_read_unlock(); + return -ENOENT; } static struct inode * diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 12c8132ad408..b9a35c05b60f 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -324,8 +324,9 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) &rdata->res.seq_res, task)) return; - nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context, - rdata->args.lock_context, FMODE_READ); + if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context, + rdata->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ } static void filelayout_read_call_done(struct rpc_task *task, void *data) @@ -435,8 +436,9 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data) &wdata->res.seq_res, task)) return; - nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context, - wdata->args.lock_context, FMODE_WRITE); + if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context, + wdata->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ } static void filelayout_write_call_done(struct rpc_task *task, void *data) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2da6a698b8f7..450bfedbe2f4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2398,13 +2398,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) { /* Use that stateid */ - } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) { + } else if (truncate && state != NULL) { struct nfs_lockowner lockowner = { .l_owner = current->files, .l_pid = current->tgid, }; - nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, - &lockowner); + if (!nfs4_valid_open_stateid(state)) + return -EBADF; + if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, + &lockowner) == -EIO) + return -EBADF; } else nfs4_stateid_copy(&arg.stateid, &zero_stateid); @@ -4011,8 +4014,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid, { nfs4_stateid current_stateid; - if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode)) - return false; + /* If the current stateid represents a lost lock, then exit */ + if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode) == -EIO) + return true; return nfs4_stateid_match(stateid, ¤t_stateid); } @@ -5828,8 +5832,7 @@ struct nfs_release_lockowner_data { struct nfs4_lock_state *lsp; struct nfs_server *server; struct nfs_release_lockowner_args args; - struct nfs4_sequence_args seq_args; - struct nfs4_sequence_res seq_res; + struct nfs_release_lockowner_res res; unsigned long timestamp; }; @@ -5837,7 +5840,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata { struct nfs_release_lockowner_data *data = calldata; nfs40_setup_sequence(data->server, - &data->seq_args, &data->seq_res, task); + &data->args.seq_args, &data->res.seq_res, task); data->timestamp = jiffies; } @@ -5846,7 +5849,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) struct nfs_release_lockowner_data *data = calldata; struct nfs_server *server = data->server; - nfs40_sequence_done(task, &data->seq_res); + nfs40_sequence_done(task, &data->res.seq_res); switch (task->tk_status) { case 0: @@ -5887,7 +5890,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; - nfs4_init_sequence(&data->seq_args, &data->seq_res, 0); data->lsp = lsp; data->server = server; data->args.lock_owner.clientid = server->nfs_client->cl_clientid; @@ -5895,6 +5897,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data->args.lock_owner.s_dev = server->s_dev; msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data); return 0; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e1a47217c05e..0deb32105ccf 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -974,9 +974,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst, else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) { nfs4_stateid_copy(dst, &lsp->ls_stateid); ret = 0; - smp_rmb(); - if (!list_empty(&lsp->ls_seqid.list)) - ret = -EWOULDBLOCK; } spin_unlock(&state->state_lock); nfs4_put_lock_state(lsp); @@ -984,10 +981,9 @@ out: return ret; } -static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) +static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) { const nfs4_stateid *src; - int ret; int seq; do { @@ -996,12 +992,7 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) if (test_bit(NFS_OPEN_STATE, &state->flags)) src = &state->open_stateid; nfs4_stateid_copy(dst, src); - ret = 0; - smp_rmb(); - if (!list_empty(&state->owner->so_seqid.list)) - ret = -EWOULDBLOCK; } while (read_seqretry(&state->seqlock, seq)); - return ret; } /* @@ -1026,7 +1017,8 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state, * choose to use. */ goto out; - ret = nfs4_copy_open_stateid(dst, state); + nfs4_copy_open_stateid(dst, state); + ret = 0; out: if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41)) dst->seqid = 0; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 017d3cb5e99b..6d7be3f80356 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -449,6 +449,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, fh_lock(fhp); host_err = notify_change(dentry, iap, NULL); fh_unlock(fhp); + err = nfserrno(host_err); out_put_write_access: if (size_change) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8450262bcf2a..51632c40e896 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2393,8 +2393,8 @@ out_dio: if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, pos, - pos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, *ppos, + *ppos + count - 1); if (ret < 0) written = ret; @@ -2407,8 +2407,8 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, pos, - pos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, *ppos, + *ppos + count - 1); } /* diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index aaa50611ec66..d7b5108789e2 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot) */ if (status < 0) mlog_errno(status); + /* + * Clear dq_off so that we search for the structure in quota file next + * time we acquire it. The structure might be deleted and reallocated + * elsewhere by another node while our dquot structure is on freelist. + */ + dquot->dq_off = 0; clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_trans: ocfs2_commit_trans(osb, handle); @@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) status = ocfs2_lock_global_qf(info, 1); if (status < 0) goto out; - if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { - status = ocfs2_qinfo_lock(info, 0); - if (status < 0) - goto out_dq; - status = qtree_read_dquot(&info->dqi_gi, dquot); - ocfs2_qinfo_unlock(info, 0); - if (status < 0) - goto out_dq; - } - set_bit(DQ_READ_B, &dquot->dq_flags); + status = ocfs2_qinfo_lock(info, 0); + if (status < 0) + goto out_dq; + /* + * We always want to read dquot structure from disk because we don't + * know what happened with it while it was on freelist. + */ + status = qtree_read_dquot(&info->dqi_gi, dquot); + ocfs2_qinfo_unlock(info, 0); + if (status < 0) + goto out_dq; OCFS2_DQUOT(dquot)->dq_use_count++; OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 2e4344be3b96..2001862bf2b1 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot) ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh); out: - /* Clear the read bit so that next time someone uses this - * dquot he reads fresh info from disk and allocates local - * dquot structure */ - clear_bit(DQ_READ_B, &dquot->dq_flags); return status; } diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 1324e6600e57..ca5ce14cbddc 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -346,7 +346,9 @@ int ocfs2_cluster_connect(const char *stack_name, strlcpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1); new_conn->cc_namelen = grouplen; - strlcpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1); + if (cluster_name_len) + strlcpy(new_conn->cc_cluster_name, cluster_name, + CLUSTER_NAME_MAX + 1); new_conn->cc_cluster_name_len = cluster_name_len; new_conn->cc_recovery_handler = recovery_handler; new_conn->cc_recovery_data = recovery_data; diff --git a/fs/open.c b/fs/open.c index 4b3e1edf2fe4..b9ed8b25c108 100644 --- a/fs/open.c +++ b/fs/open.c @@ -705,6 +705,10 @@ static int do_dentry_open(struct file *f, return 0; } + /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ + if (S_ISREG(inode->i_mode)) + f->f_mode |= FMODE_ATOMIC_POS; + f->f_op = fops_get(inode->i_fop); if (unlikely(WARN_ON(!f->f_op))) { error = -ENODEV; diff --git a/fs/pnode.c b/fs/pnode.c index c7221bb19801..88396df725b4 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -220,14 +220,14 @@ static struct mount *get_source(struct mount *dest, * @tree_list : list of heads of trees to be attached. */ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, - struct mount *source_mnt, struct list_head *tree_list) + struct mount *source_mnt, struct hlist_head *tree_list) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mount *m, *child; int ret = 0; struct mount *prev_dest_mnt = dest_mnt; struct mount *prev_src_mnt = source_mnt; - LIST_HEAD(tmp_list); + HLIST_HEAD(tmp_list); for (m = propagation_next(dest_mnt, dest_mnt); m; m = propagation_next(m, dest_mnt)) { @@ -246,27 +246,29 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, child = copy_tree(source, source->mnt.mnt_root, type); if (IS_ERR(child)) { ret = PTR_ERR(child); - list_splice(tree_list, tmp_list.prev); + tmp_list = *tree_list; + tmp_list.first->pprev = &tmp_list.first; + INIT_HLIST_HEAD(tree_list); goto out; } if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) { mnt_set_mountpoint(m, dest_mp, child); - list_add_tail(&child->mnt_hash, tree_list); + hlist_add_head(&child->mnt_hash, tree_list); } else { /* * This can happen if the parent mount was bind mounted * on some subdirectory of a shared/slave mount. */ - list_add_tail(&child->mnt_hash, &tmp_list); + hlist_add_head(&child->mnt_hash, &tmp_list); } prev_dest_mnt = m; prev_src_mnt = child; } out: lock_mount_hash(); - while (!list_empty(&tmp_list)) { - child = list_first_entry(&tmp_list, struct mount, mnt_hash); + while (!hlist_empty(&tmp_list)) { + child = hlist_entry(tmp_list.first, struct mount, mnt_hash); umount_tree(child, 0); } unlock_mount_hash(); @@ -338,8 +340,10 @@ static void __propagate_umount(struct mount *mnt) * umount the child only if the child has no * other children */ - if (child && list_empty(&child->mnt_mounts)) - list_move_tail(&child->mnt_hash, &mnt->mnt_hash); + if (child && list_empty(&child->mnt_mounts)) { + hlist_del_init_rcu(&child->mnt_hash); + hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); + } } } @@ -350,11 +354,11 @@ static void __propagate_umount(struct mount *mnt) * * vfsmount lock must be held for write */ -int propagate_umount(struct list_head *list) +int propagate_umount(struct hlist_head *list) { struct mount *mnt; - list_for_each_entry(mnt, list, mnt_hash) + hlist_for_each_entry(mnt, list, mnt_hash) __propagate_umount(mnt); return 0; } diff --git a/fs/pnode.h b/fs/pnode.h index 59e7eda1851e..fc28a27fa892 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -36,8 +36,8 @@ static inline void set_mnt_shared(struct mount *mnt) void change_mnt_propagation(struct mount *, int); int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, - struct list_head *); -int propagate_umount(struct list_head *); + struct hlist_head *); +int propagate_umount(struct hlist_head *); int propagate_mount_busy(struct mount *, int); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); diff --git a/fs/proc/base.c b/fs/proc/base.c index 51507065263b..b9760628e1fd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1824,6 +1824,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; + rc = -ENOENT; down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { diff --git a/fs/proc/page.c b/fs/proc/page.c index 02174a610315..e647c55275d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && - (PageLRU(compound_trans_head(page)) || - PageAnon(compound_trans_head(page)))) + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) u |= 1 << KPF_THP; /* diff --git a/fs/read_write.c b/fs/read_write.c index 72c09b4a01a4..31c6efa43183 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -264,10 +264,22 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); +static inline struct fd fdget_pos(int fd) +{ + return __to_fd(__fdget_pos(fd)); +} + +static inline void fdput_pos(struct fd f) +{ + if (f.flags & FDPUT_POS_UNLOCK) + mutex_unlock(&f.file->f_pos_lock); + fdput(f); +} + SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { off_t retval; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -278,7 +290,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } - fdput(f); + fdput_pos(f); return retval; } @@ -295,7 +307,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned int, whence) { int retval; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) @@ -315,7 +327,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, retval = 0; } out_putf: - fdput(f); + fdput_pos(f); return retval; } #endif @@ -498,7 +510,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -506,7 +518,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) ret = vfs_read(f.file, buf, count, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } return ret; } @@ -514,7 +526,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -522,7 +534,7 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, ret = vfs_write(f.file, buf, count, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } return ret; @@ -797,7 +809,7 @@ EXPORT_SYMBOL(vfs_writev); SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -805,7 +817,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, ret = vfs_readv(f.file, vec, vlen, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } if (ret > 0) @@ -817,7 +829,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -825,7 +837,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, ret = vfs_writev(f.file, vec, vlen, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } if (ret > 0) @@ -968,7 +980,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret; loff_t pos; @@ -978,7 +990,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, ret = compat_readv(f.file, vec, vlen, &pos); if (ret >= 0) f.file->f_pos = pos; - fdput(f); + fdput_pos(f); return ret; } @@ -1045,7 +1057,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, const struct compat_iovec __user *, vec, compat_ulong_t, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret; loff_t pos; @@ -1055,7 +1067,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, ret = compat_writev(f.file, vec, vlen, &pos); if (ret >= 0) f.file->f_pos = pos; - fdput(f); + fdput_pos(f); return ret; } diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h index fa2a50b7ee66..0a7e06623470 100644 --- a/include/asm-generic/bitops/const_hweight.h +++ b/include/asm-generic/bitops/const_hweight.h @@ -5,14 +5,15 @@ * Compile time versions of __arch_hweightN() */ #define __const_hweight8(w) \ - ( (!!((w) & (1ULL << 0))) + \ - (!!((w) & (1ULL << 1))) + \ - (!!((w) & (1ULL << 2))) + \ - (!!((w) & (1ULL << 3))) + \ - (!!((w) & (1ULL << 4))) + \ - (!!((w) & (1ULL << 5))) + \ - (!!((w) & (1ULL << 6))) + \ - (!!((w) & (1ULL << 7))) ) + ((unsigned int) \ + ((!!((w) & (1ULL << 0))) + \ + (!!((w) & (1ULL << 1))) + \ + (!!((w) & (1ULL << 2))) + \ + (!!((w) & (1ULL << 3))) + \ + (!!((w) & (1ULL << 4))) + \ + (!!((w) & (1ULL << 5))) + \ + (!!((w) & (1ULL << 6))) + \ + (!!((w) & (1ULL << 7))))) #define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) #define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) diff --git a/include/asm-generic/mcs_spinlock.h b/include/asm-generic/mcs_spinlock.h new file mode 100644 index 000000000000..10cd4ffc6ba2 --- /dev/null +++ b/include/asm-generic/mcs_spinlock.h @@ -0,0 +1,13 @@ +#ifndef __ASM_MCS_SPINLOCK_H +#define __ASM_MCS_SPINLOCK_H + +/* + * Architectures can define their own: + * + * arch_mcs_spin_lock_contended(l) + * arch_mcs_spin_unlock_contended(l) + * + * See kernel/locking/mcs_spinlock.c. + */ + +#endif /* __ASM_MCS_SPINLOCK_H */ diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h index a1116a3b54ef..8c1603b10665 100644 --- a/include/dt-bindings/clock/tegra124-car.h +++ b/include/dt-bindings/clock/tegra124-car.h @@ -36,10 +36,10 @@ #define TEGRA124_CLK_PWM 17 #define TEGRA124_CLK_I2S2 18 /* 20 (register bit affects vi and vi_sensor) */ -#define TEGRA124_CLK_GR_2D 21 +/* 21 */ #define TEGRA124_CLK_USBD 22 #define TEGRA124_CLK_ISP 23 -#define TEGRA124_CLK_GR_3D 24 +/* 26 */ /* 25 */ #define TEGRA124_CLK_DISP2 26 #define TEGRA124_CLK_DISP1 27 diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index be85127bfed3..f27000f55a83 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -171,6 +171,11 @@ static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 add return 0; } +static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) +{ + return -ENXIO; +} + static inline int kvm_vgic_init(struct kvm *kvm) { return 0; diff --git a/include/linux/audit.h b/include/linux/audit.h index aa865a9a4c4f..ec1464df4c60 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -43,6 +43,7 @@ struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; +struct sk_buff; struct audit_krule { int vers_ops; @@ -463,7 +464,7 @@ extern int audit_filter_user(int type); extern int audit_filter_type(int type); extern int audit_rule_change(int type, __u32 portid, int seq, void *data, size_t datasz); -extern int audit_list_rules_send(__u32 portid, int seq); +extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern u32 audit_enabled; #else /* CONFIG_AUDIT */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index abc9ca778456..be5fd38bd5a0 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -196,6 +196,21 @@ static inline unsigned long __ffs64(u64 word) #ifdef __KERNEL__ +#ifndef set_mask_bits +#define set_mask_bits(ptr, _mask, _bits) \ +({ \ + const typeof(*ptr) mask = (_mask), bits = (_bits); \ + typeof(*ptr) old, new; \ + \ + do { \ + old = ACCESS_ONCE(*ptr); \ + new = (old & ~mask) | bits; \ + } while (cmpxchg(ptr, old, new) != old); \ + \ + new; \ +}) +#endif + #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 18ba8a627f46..2ff2e8d982be 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -121,8 +121,7 @@ void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struc void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); -void blk_mq_insert_request(struct request_queue *, struct request *, - bool, bool); +void blk_mq_insert_request(struct request *, bool, bool, bool); void blk_mq_run_queues(struct request_queue *q, bool async); void blk_mq_free_request(struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); @@ -134,7 +133,13 @@ struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_ind struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int); void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int); -void blk_mq_end_io(struct request *rq, int error); +bool blk_mq_end_io_partial(struct request *rq, int error, + unsigned int nr_bytes); +static inline void blk_mq_end_io(struct request *rq, int error) +{ + bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq)); + BUG_ON(!done); +} void blk_mq_complete_request(struct request *rq); diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 092b64168d7f..4a21a872dbbd 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -245,6 +245,10 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate, void omap2_init_clk_clkdm(struct clk_hw *clk); unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long parent_rate); +int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate); +long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate); int omap2_clkops_enable_clkdm(struct clk_hw *hw); void omap2_clkops_disable_clkdm(struct clk_hw *hw); int omap2_clk_disable_autoidle_all(void); diff --git a/include/linux/efi.h b/include/linux/efi.h index 0a819e7a60c9..6c100ff0cae4 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -153,6 +153,102 @@ typedef struct { u8 sets_to_zero; } efi_time_cap_t; +typedef struct { + efi_table_hdr_t hdr; + u32 raise_tpl; + u32 restore_tpl; + u32 allocate_pages; + u32 free_pages; + u32 get_memory_map; + u32 allocate_pool; + u32 free_pool; + u32 create_event; + u32 set_timer; + u32 wait_for_event; + u32 signal_event; + u32 close_event; + u32 check_event; + u32 install_protocol_interface; + u32 reinstall_protocol_interface; + u32 uninstall_protocol_interface; + u32 handle_protocol; + u32 __reserved; + u32 register_protocol_notify; + u32 locate_handle; + u32 locate_device_path; + u32 install_configuration_table; + u32 load_image; + u32 start_image; + u32 exit; + u32 unload_image; + u32 exit_boot_services; + u32 get_next_monotonic_count; + u32 stall; + u32 set_watchdog_timer; + u32 connect_controller; + u32 disconnect_controller; + u32 open_protocol; + u32 close_protocol; + u32 open_protocol_information; + u32 protocols_per_handle; + u32 locate_handle_buffer; + u32 locate_protocol; + u32 install_multiple_protocol_interfaces; + u32 uninstall_multiple_protocol_interfaces; + u32 calculate_crc32; + u32 copy_mem; + u32 set_mem; + u32 create_event_ex; +} __packed efi_boot_services_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 raise_tpl; + u64 restore_tpl; + u64 allocate_pages; + u64 free_pages; + u64 get_memory_map; + u64 allocate_pool; + u64 free_pool; + u64 create_event; + u64 set_timer; + u64 wait_for_event; + u64 signal_event; + u64 close_event; + u64 check_event; + u64 install_protocol_interface; + u64 reinstall_protocol_interface; + u64 uninstall_protocol_interface; + u64 handle_protocol; + u64 __reserved; + u64 register_protocol_notify; + u64 locate_handle; + u64 locate_device_path; + u64 install_configuration_table; + u64 load_image; + u64 start_image; + u64 exit; + u64 unload_image; + u64 exit_boot_services; + u64 get_next_monotonic_count; + u64 stall; + u64 set_watchdog_timer; + u64 connect_controller; + u64 disconnect_controller; + u64 open_protocol; + u64 close_protocol; + u64 open_protocol_information; + u64 protocols_per_handle; + u64 locate_handle_buffer; + u64 locate_protocol; + u64 install_multiple_protocol_interfaces; + u64 uninstall_multiple_protocol_interfaces; + u64 calculate_crc32; + u64 copy_mem; + u64 set_mem; + u64 create_event_ex; +} __packed efi_boot_services_64_t; + /* * EFI Boot Services table */ @@ -231,6 +327,15 @@ typedef enum { EfiPciIoAttributeOperationMaximum } EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION; +typedef struct { + u32 read; + u32 write; +} efi_pci_io_protocol_access_32_t; + +typedef struct { + u64 read; + u64 write; +} efi_pci_io_protocol_access_64_t; typedef struct { void *read; @@ -238,6 +343,46 @@ typedef struct { } efi_pci_io_protocol_access_t; typedef struct { + u32 poll_mem; + u32 poll_io; + efi_pci_io_protocol_access_32_t mem; + efi_pci_io_protocol_access_32_t io; + efi_pci_io_protocol_access_32_t pci; + u32 copy_mem; + u32 map; + u32 unmap; + u32 allocate_buffer; + u32 free_buffer; + u32 flush; + u32 get_location; + u32 attributes; + u32 get_bar_attributes; + u32 set_bar_attributes; + uint64_t romsize; + void *romimage; +} efi_pci_io_protocol_32; + +typedef struct { + u64 poll_mem; + u64 poll_io; + efi_pci_io_protocol_access_64_t mem; + efi_pci_io_protocol_access_64_t io; + efi_pci_io_protocol_access_64_t pci; + u64 copy_mem; + u64 map; + u64 unmap; + u64 allocate_buffer; + u64 free_buffer; + u64 flush; + u64 get_location; + u64 attributes; + u64 get_bar_attributes; + u64 set_bar_attributes; + uint64_t romsize; + void *romimage; +} efi_pci_io_protocol_64; + +typedef struct { void *poll_mem; void *poll_io; efi_pci_io_protocol_access_t mem; @@ -292,6 +437,42 @@ typedef struct { typedef struct { efi_table_hdr_t hdr; + u32 get_time; + u32 set_time; + u32 get_wakeup_time; + u32 set_wakeup_time; + u32 set_virtual_address_map; + u32 convert_pointer; + u32 get_variable; + u32 get_next_variable; + u32 set_variable; + u32 get_next_high_mono_count; + u32 reset_system; + u32 update_capsule; + u32 query_capsule_caps; + u32 query_variable_info; +} efi_runtime_services_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 get_time; + u64 set_time; + u64 get_wakeup_time; + u64 set_wakeup_time; + u64 set_virtual_address_map; + u64 convert_pointer; + u64 get_variable; + u64 get_next_variable; + u64 set_variable; + u64 get_next_high_mono_count; + u64 reset_system; + u64 update_capsule; + u64 query_capsule_caps; + u64 query_variable_info; +} efi_runtime_services_64_t; + +typedef struct { + efi_table_hdr_t hdr; void *get_time; void *set_time; void *get_wakeup_time; @@ -485,6 +666,38 @@ struct efi_memory_map { typedef struct { u32 revision; + u32 parent_handle; + u32 system_table; + u32 device_handle; + u32 file_path; + u32 reserved; + u32 load_options_size; + u32 load_options; + u32 image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + unsigned long unload; +} efi_loaded_image_32_t; + +typedef struct { + u32 revision; + u64 parent_handle; + u64 system_table; + u64 device_handle; + u64 file_path; + u64 reserved; + u32 load_options_size; + u64 load_options; + u64 image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + unsigned long unload; +} efi_loaded_image_64_t; + +typedef struct { + u32 revision; void *parent_handle; efi_system_table_t *system_table; void *device_handle; @@ -511,6 +724,34 @@ typedef struct { efi_char16_t filename[1]; } efi_file_info_t; +typedef struct { + u64 revision; + u32 open; + u32 close; + u32 delete; + u32 read; + u32 write; + u32 get_position; + u32 set_position; + u32 get_info; + u32 set_info; + u32 flush; +} efi_file_handle_32_t; + +typedef struct { + u64 revision; + u64 open; + u64 close; + u64 delete; + u64 read; + u64 write; + u64 get_position; + u64 set_position; + u64 get_info; + u64 set_info; + u64 flush; +} efi_file_handle_64_t; + typedef struct _efi_file_handle { u64 revision; efi_status_t (*open)(struct _efi_file_handle *, @@ -573,6 +814,7 @@ extern struct efi { efi_reset_system_t *reset_system; efi_set_virtual_address_map_t *set_virtual_address_map; struct efi_memory_map *memmap; + unsigned long flags; } efi; static inline int @@ -659,18 +901,17 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_ARCH_1 6 /* First arch-specific bit */ #ifdef CONFIG_EFI -# ifdef CONFIG_X86 -extern int efi_enabled(int facility); -# else -static inline int efi_enabled(int facility) +/* + * Test whether the above EFI_* bits are enabled. + */ +static inline bool efi_enabled(int feature) { - return 1; + return test_bit(feature, &efi.flags) != 0; } -# endif #else -static inline int efi_enabled(int facility) +static inline bool efi_enabled(int feature) { - return 0; + return false; } #endif @@ -809,6 +1050,17 @@ struct efivar_entry { bool deleting; }; +struct efi_simple_text_output_protocol_32 { + u32 reset; + u32 output_string; + u32 test_string; +}; + +struct efi_simple_text_output_protocol_64 { + u64 reset; + u64 output_string; + u64 test_string; +}; struct efi_simple_text_output_protocol { void *reset; diff --git a/include/linux/file.h b/include/linux/file.h index cbacf4faf447..4d69123377a2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -28,33 +28,36 @@ static inline void fput_light(struct file *file, int fput_needed) struct fd { struct file *file; - int need_put; + unsigned int flags; }; +#define FDPUT_FPUT 1 +#define FDPUT_POS_UNLOCK 2 static inline void fdput(struct fd fd) { - if (fd.need_put) + if (fd.flags & FDPUT_FPUT) fput(fd.file); } extern struct file *fget(unsigned int fd); -extern struct file *fget_light(unsigned int fd, int *fput_needed); +extern struct file *fget_raw(unsigned int fd); +extern unsigned long __fdget(unsigned int fd); +extern unsigned long __fdget_raw(unsigned int fd); +extern unsigned long __fdget_pos(unsigned int fd); -static inline struct fd fdget(unsigned int fd) +static inline struct fd __to_fd(unsigned long v) { - int b; - struct file *f = fget_light(fd, &b); - return (struct fd){f,b}; + return (struct fd){(struct file *)(v & ~3),v & 3}; } -extern struct file *fget_raw(unsigned int fd); -extern struct file *fget_raw_light(unsigned int fd, int *fput_needed); +static inline struct fd fdget(unsigned int fd) +{ + return __to_fd(__fdget(fd)); +} static inline struct fd fdget_raw(unsigned int fd) { - int b; - struct file *f = fget_raw_light(fd, &b); - return (struct fd){f,b}; + return __to_fd(__fdget_raw(fd)); } extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 5d7782e42b8f..c3683bdf28fe 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -200,6 +200,7 @@ struct fw_device { unsigned irmc:1; unsigned bc_implemented:2; + work_func_t workfn; struct delayed_work work; struct fw_attribute_group attribute_group; }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 60829565e552..23b2a35d712e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -123,6 +123,9 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) +/* File needs atomic accesses to f_pos */ +#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x1000000) @@ -780,13 +783,14 @@ struct file { const struct file_operations *f_op; /* - * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR. + * Protects f_ep_links, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; + struct mutex f_pos_lock; loff_t f_pos; struct fown_struct f_owner; const struct cred *f_cred; @@ -808,7 +812,7 @@ struct file { #ifdef CONFIG_DEBUG_WRITECOUNT unsigned long f_mnt_write_state; #endif -}; +} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4e4cc28623ad..4cdb3a17bcb5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -495,10 +495,6 @@ enum { FILTER_TRACE_FN, }; -#define EVENT_STORAGE_SIZE 128 -extern struct mutex event_storage_mutex; -extern char event_storage[EVENT_STORAGE_SIZE]; - extern int trace_event_raw_init(struct ftrace_event_call *call); extern int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, diff --git a/include/linux/futex.h b/include/linux/futex.h index b0d95cac826e..6435f46d6e13 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -55,7 +55,11 @@ union futex_key { #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); extern void exit_pi_state_list(struct task_struct *curr); +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else extern int futex_cmpxchg_enabled; +#endif #else static inline void exit_robust_list(struct task_struct *curr) { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0437439bc047..39b81dc7d01a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -123,6 +123,10 @@ struct vm_area_struct; __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ __GFP_NO_KSWAPD) +/* + * GFP_THISNODE does not perform any reclaim, you most likely want to + * use __GFP_THISNODE to allocate from a given node without fallback! + */ #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) #else diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index db512014e061..b826239bdce0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,46 +157,6 @@ static inline int hpage_nr_pages(struct page *page) return HPAGE_PMD_NR; return 1; } -/* - * compound_trans_head() should be used instead of compound_head(), - * whenever the "page" passed as parameter could be the tail of a - * transparent hugepage that could be undergoing a - * __split_huge_page_refcount(). The page structure layout often - * changes across releases and it makes extensive use of unions. So if - * the page structure layout will change in a way that - * page->first_page gets clobbered by __split_huge_page_refcount, the - * implementation making use of smp_rmb() will be required. - * - * Currently we define compound_trans_head as compound_head, because - * page->private is in the same union with page->first_page, and - * page->private isn't clobbered. However this also means we're - * currently leaving dirt into the page->private field of anonymous - * pages resulting from a THP split, instead of setting page->private - * to zero like for every other page that has PG_private not set. But - * anonymous pages don't use page->private so this is not a problem. - */ -#if 0 -/* This will be needed if page->private will be clobbered in split_huge_page */ -static inline struct page *compound_trans_head(struct page *page) -{ - if (PageTail(page)) { - struct page *head; - head = page->first_page; - smp_rmb(); - /* - * head may be a dangling pointer. - * __split_huge_page_refcount clears PageTail before - * overwriting first_page, so if PageTail is still - * there it means the head pointer isn't dangling. - */ - if (PageTail(page)) - return head; - } - return page; -} -#else -#define compound_trans_head(page) compound_head(page) -#endif extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); @@ -226,7 +186,6 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define split_huge_page_pmd_mm(__mm, __address, __pmd) \ do { } while (0) -#define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { diff --git a/include/linux/init.h b/include/linux/init.h index e1688802964f..a3ba27076342 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -163,6 +163,23 @@ extern bool initcall_debug; #ifndef __ASSEMBLY__ +#ifdef CONFIG_LTO +/* Work around a LTO gcc problem: when there is no reference to a variable + * in a module it will be moved to the end of the program. This causes + * reordering of initcalls which the kernel does not like. + * Add a dummy reference function to avoid this. The function is + * deleted by the linker. + */ +#define LTO_REFERENCE_INITCALL(x) \ + ; /* yes this is needed */ \ + static __used __exit void *reference_##x(void) \ + { \ + return &x; \ + } +#else +#define LTO_REFERENCE_INITCALL(x) +#endif + /* initcalls are now grouped by functionality into separate * subsections. Ordering inside the subsections is determined * by link order. @@ -175,7 +192,8 @@ extern bool initcall_debug; #define __define_initcall(fn, id) \ static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(".initcall" #id ".init"))) = fn + __attribute__((__section__(".initcall" #id ".init"))) = fn; \ + LTO_REFERENCE_INITCALL(__initcall_##fn##id) /* * Early initcalls run before initializing SMP. diff --git a/include/linux/io.h b/include/linux/io.h index f4f42faec686..8a18e75600cc 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -24,7 +24,7 @@ struct device; -void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); #ifdef CONFIG_MMU diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 66017028dcb3..19ae05d4b8ec 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -30,7 +30,9 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) work->func = func; } -void irq_work_queue(struct irq_work *work); +#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } + +bool irq_work_queue(struct irq_work *work); void irq_work_run(void); void irq_work_sync(struct irq_work *work); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 196d1ea86df0..08fb02477641 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -458,7 +458,7 @@ extern enum system_states { #define TAINT_PROPRIETARY_MODULE 0 #define TAINT_FORCED_MODULE 1 -#define TAINT_UNSAFE_SMP 2 +#define TAINT_CPU_OUT_OF_SPEC 2 #define TAINT_FORCED_RMMOD 3 #define TAINT_MACHINE_CHECK 4 #define TAINT_BAD_PAGE 5 diff --git a/include/linux/linkage.h b/include/linux/linkage.h index a6a42dd02466..34a513a2727b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -12,9 +12,9 @@ #endif #ifdef __cplusplus -#define CPP_ASMLINKAGE extern "C" +#define CPP_ASMLINKAGE extern "C" __visible #else -#define CPP_ASMLINKAGE +#define CPP_ASMLINKAGE __visible #endif #ifndef asmlinkage diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 92b1bfc5da60..008388f920d7 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -252,9 +252,9 @@ struct held_lock { unsigned int trylock:1; /* 16 bits */ unsigned int read:2; /* see lock_acquire() comment */ - unsigned int check:2; /* see lock_acquire() comment */ + unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; - unsigned int references:11; /* 32 bits */ + unsigned int references:12; /* 32 bits */ }; /* @@ -265,7 +265,7 @@ extern void lockdep_info(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); -extern void lockdep_sys_exit(void); +extern asmlinkage void lockdep_sys_exit(void); extern void lockdep_off(void); extern void lockdep_on(void); @@ -303,7 +303,7 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, (lock)->dep_map.key, sub) #define lockdep_set_novalidate_class(lock) \ - lockdep_set_class(lock, &__lockdep_no_validate__) + lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) /* * Compare locking classes */ @@ -326,9 +326,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock, * * Values for check: * - * 0: disabled - * 1: simple checks (freeing, held-at-exit-time, etc.) - * 2: full validation + * 0: simple checks (freeing, held-at-exit-time, etc.) + * 1: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, @@ -479,15 +478,9 @@ static inline void print_irqtrace_events(struct task_struct *curr) * on the per lock-class debug mode: */ -#ifdef CONFIG_PROVE_LOCKING - #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) - #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 2, n, i) - #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 2, n, i) -#else - #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) - #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) - #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) -#endif +#define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) +#define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) +#define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) @@ -518,13 +511,13 @@ static inline void print_irqtrace_events(struct task_struct *curr) # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ - lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_); \ + lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ - lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_); \ + lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ } while (0) #else diff --git a/include/linux/mm.h b/include/linux/mm.h index f28f46eade6a..c1b7414c7bef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -175,7 +175,7 @@ extern unsigned int kobjsize(const void *objp); * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ -#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP) +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* * mapping from the currently active vm_flags protection bits (the @@ -399,8 +399,18 @@ static inline void compound_unlock_irqrestore(struct page *page, static inline struct page *compound_head(struct page *page) { - if (unlikely(PageTail(page))) - return page->first_page; + if (unlikely(PageTail(page))) { + struct page *head = page->first_page; + + /* + * page->first_page may be a dangling pointer to an old + * compound page, so recheck that it is still a tail + * page before returning. + */ + smp_rmb(); + if (likely(PageTail(page))) + return head; + } return page; } @@ -757,7 +767,7 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { - return xchg(&page->_last_cpupid, cpupid); + return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) @@ -766,7 +776,7 @@ static inline int page_cpupid_last(struct page *page) } static inline void page_cpupid_reset_last(struct page *page) { - page->_last_cpupid = -1; + page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5f2052c83154..9b61b9bf81ac 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -590,10 +590,10 @@ static inline bool zone_is_empty(struct zone *zone) /* * The NUMA zonelists are doubled because we need zonelists that restrict the - * allocations to a single node for GFP_THISNODE. + * allocations to a single node for __GFP_THISNODE. * * [0] : Zonelist with fallback - * [1] : No fallback (GFP_THISNODE) + * [1] : No fallback (__GFP_THISNODE) */ #define MAX_ZONELISTS 2 diff --git a/include/linux/mutex.h b/include/linux/mutex.h index d3181936c138..11692dea18aa 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -46,6 +46,7 @@ * - detects multi-task circular deadlocks and prints out all affected * locks and tasks (and only those tasks) */ +struct optimistic_spin_queue; struct mutex { /* 1: unlocked, 0: locked, negative: locked, possible waiters */ atomic_t count; @@ -55,7 +56,7 @@ struct mutex { struct task_struct *owner; #endif #ifdef CONFIG_MUTEX_SPIN_ON_OWNER - void *spin_mlock; /* Spinner MCS lock */ + struct optimistic_spin_queue *osq; /* Spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; @@ -179,4 +180,4 @@ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); # define arch_mutex_cpu_relax() cpu_relax() #endif -#endif +#endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 1005ebf17575..5a09a48f2658 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -163,4 +163,11 @@ enum { /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) +#define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ + NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_FILTER | \ + NETIF_F_HW_VLAN_STAG_RX | \ + NETIF_F_HW_VLAN_STAG_TX) + #endif /* _LINUX_NETDEV_FEATURES_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e8eeebd49a98..daafd9561cbc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3014,7 +3014,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } -__be16 skb_network_protocol(struct sk_buff *skb); +__be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b2fb167b2e6d..5624e4e2763c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -467,9 +467,14 @@ struct nfs_lockt_res { }; struct nfs_release_lockowner_args { + struct nfs4_sequence_args seq_args; struct nfs_lowner lock_owner; }; +struct nfs_release_lockowner_res { + struct nfs4_sequence_res seq_res; +}; + struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 97fbecdd7a40..7399e6a3e9a0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2531,6 +2531,9 @@ #define PCI_VENDOR_ID_INTEL 0x8086 #define PCI_DEVICE_ID_INTEL_EESSC 0x0008 +#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 +#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154 +#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_PXHD_0 0x0320 #define PCI_DEVICE_ID_INTEL_PXHD_1 0x0321 #define PCI_DEVICE_ID_INTEL_PXH_0 0x0329 diff --git a/include/linux/rculist.h b/include/linux/rculist.h index dbaf99084112..8183b46fbaa2 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -247,9 +247,10 @@ static inline void list_splice_init_rcu(struct list_head *list, * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ - ({typeof (*ptr) __rcu *__ptr = (typeof (*ptr) __rcu __force *)ptr; \ - container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \ - }) +({ \ + typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \ + container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \ +}) /** * Where are list_empty_rcu() and list_first_entry_rcu()? @@ -285,11 +286,11 @@ static inline void list_splice_init_rcu(struct list_head *list, * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ - ({struct list_head *__ptr = (ptr); \ - struct list_head *__next = ACCESS_ONCE(__ptr->next); \ - likely(__ptr != __next) ? \ - list_entry_rcu(__next, type, member) : NULL; \ - }) +({ \ + struct list_head *__ptr = (ptr); \ + struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ +}) /** * list_for_each_entry_rcu - iterate over rcu list of given type diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 72bf3a01a4ee..00a7fd61b3c6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2001 * @@ -44,7 +44,9 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <asm/barrier.h> +extern int rcu_expedited; /* for sysctl */ #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ @@ -314,7 +316,7 @@ static inline bool rcu_lockdep_current_cpu_online(void) static inline void rcu_lock_acquire(struct lockdep_map *map) { - lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); + lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) @@ -479,11 +481,9 @@ static inline void rcu_preempt_sleep_check(void) do { \ rcu_preempt_sleep_check(); \ rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ - "Illegal context switch in RCU-bh" \ - " read-side critical section"); \ + "Illegal context switch in RCU-bh read-side critical section"); \ rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \ - "Illegal context switch in RCU-sched"\ - " read-side critical section"); \ + "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ @@ -510,43 +510,40 @@ static inline void rcu_preempt_sleep_check(void) #endif /* #else #ifdef __CHECKER__ */ #define __rcu_access_pointer(p, space) \ - ({ \ - typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ - }) +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + rcu_dereference_sparse(p, space); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) #define __rcu_dereference_check(p, c, space) \ - ({ \ - typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \ - " usage"); \ - rcu_dereference_sparse(p, space); \ - smp_read_barrier_depends(); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ - }) +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ + rcu_dereference_sparse(p, space); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) #define __rcu_dereference_protected(p, c, space) \ - ({ \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \ - " usage"); \ - rcu_dereference_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(p)); \ - }) +({ \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \ + rcu_dereference_sparse(p, space); \ + ((typeof(*p) __force __kernel *)(p)); \ +}) #define __rcu_access_index(p, space) \ - ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - (_________p1); \ - }) +({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + rcu_dereference_sparse(p, space); \ + (_________p1); \ +}) #define __rcu_dereference_index_check(p, c) \ - ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_lockdep_assert(c, \ - "suspicious rcu_dereference_index_check()" \ - " usage"); \ - smp_read_barrier_depends(); \ - (_________p1); \ - }) +({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + rcu_lockdep_assert(c, \ + "suspicious rcu_dereference_index_check() usage"); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable @@ -585,12 +582,7 @@ static inline void rcu_preempt_sleep_check(void) * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ -#define rcu_assign_pointer(p, v) \ - do { \ - smp_wmb(); \ - ACCESS_ONCE(p) = RCU_INITIALIZER(v); \ - } while (0) - +#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v)) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing @@ -1015,11 +1007,21 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#ifdef CONFIG_RCU_NOCB_CPU +#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) +static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) +{ + *delta_jiffies = ULONG_MAX; + return 0; +} +#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */ + +#if defined(CONFIG_RCU_NOCB_CPU_ALL) +static inline bool rcu_is_nocb_cpu(int cpu) { return true; } +#elif defined(CONFIG_RCU_NOCB_CPU) bool rcu_is_nocb_cpu(int cpu); #else static inline bool rcu_is_nocb_cpu(int cpu) { return false; } -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +#endif /* Only for use by adaptive-ticks code. */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 6f01771b571c..425c659d54e5 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * @@ -27,6 +27,16 @@ #include <linux/cache.h> +static inline unsigned long get_state_synchronize_rcu(void) +{ + return 0; +} + +static inline void cond_synchronize_rcu(unsigned long oldstate) +{ + might_sleep(); +} + static inline void rcu_barrier_bh(void) { wait_rcu_gp(call_rcu_bh); @@ -68,12 +78,6 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } -static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) -{ - *delta_jiffies = ULONG_MAX; - return 0; -} - static inline void rcu_note_context_switch(int cpu) { rcu_sched_qs(cpu); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 72137ee8c603..a59ca05fd4e3 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * @@ -31,7 +31,9 @@ #define __LINUX_RCUTREE_H void rcu_note_context_switch(int cpu); +#ifndef CONFIG_RCU_NOCB_CPU_ALL int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies); +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ void rcu_cpu_stall_reset(void); /* @@ -74,6 +76,8 @@ static inline void synchronize_rcu_bh_expedited(void) void rcu_barrier(void); void rcu_barrier_bh(void); void rcu_barrier_sched(void); +unsigned long get_state_synchronize_rcu(void); +void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 1da693d51255..b66c2110cb1f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -250,8 +250,7 @@ struct rmap_walk_control { int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); - int (*file_nonlinear)(struct page *, struct address_space *, - struct vm_area_struct *vma); + int (*file_nonlinear)(struct page *, struct address_space *, void *arg); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; diff --git a/include/linux/sched.h b/include/linux/sched.h index a781dec1cd0b..825ed838d4b9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3,6 +3,8 @@ #include <uapi/linux/sched.h> +#include <linux/sched/prio.h> + struct sched_param { int sched_priority; @@ -1077,6 +1079,7 @@ struct sched_entity { #endif #ifdef CONFIG_FAIR_GROUP_SCHED + int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; @@ -1460,6 +1463,9 @@ struct task_struct { struct mutex perf_event_mutex; struct list_head perf_event_list; #endif +#ifdef CONFIG_DEBUG_PREEMPT + unsigned long preempt_disable_ip; +#endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ short il_next; @@ -1470,9 +1476,10 @@ struct task_struct { unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; - int numa_migrate_deferred; unsigned long numa_migrate_retry; u64 node_stamp; /* migration stamp */ + u64 last_task_numa_placement; + u64 last_sum_exec_runtime; struct callback_head numa_work; struct list_head numa_entry; @@ -1483,15 +1490,22 @@ struct task_struct { * Scheduling placement decisions are made based on the these counts. * The values remain static for the duration of a PTE scan */ - unsigned long *numa_faults; + unsigned long *numa_faults_memory; unsigned long total_numa_faults; /* * numa_faults_buffer records faults per node during the current - * scan window. When the scan completes, the counts in numa_faults - * decay and these values are copied. + * scan window. When the scan completes, the counts in + * numa_faults_memory decay and these values are copied. + */ + unsigned long *numa_faults_buffer_memory; + + /* + * Track the nodes the process was running on when a NUMA hinting + * fault was incurred. */ - unsigned long *numa_faults_buffer; + unsigned long *numa_faults_cpu; + unsigned long *numa_faults_buffer_cpu; /* * numa_faults_locality tracks if faults recorded during the last @@ -1596,8 +1610,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p); - -extern unsigned int sysctl_numa_balancing_migrate_deferred; +extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, + int src_nid, int dst_cpu); #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) @@ -1613,6 +1627,11 @@ static inline void set_numabalancing_state(bool enabled) static inline void task_numa_free(struct task_struct *p) { } +static inline bool should_numa_migrate_memory(struct task_struct *p, + struct page *page, int src_nid, int dst_cpu) +{ + return true; +} #endif static inline struct pid *task_pid(struct task_struct *task) @@ -2080,7 +2099,16 @@ static inline void sched_autogroup_exit(struct signal_struct *sig) { } extern bool yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); -extern int task_nice(const struct task_struct *p); +/** + * task_nice - return the nice value of a given task. + * @p: the task in question. + * + * Return: The nice value [ -20 ... 0 ... 19 ]. + */ +static inline int task_nice(const struct task_struct *p) +{ + return PRIO_TO_NICE((p)->static_prio); +} extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h new file mode 100644 index 000000000000..ac322583c820 --- /dev/null +++ b/include/linux/sched/prio.h @@ -0,0 +1,44 @@ +#ifndef _SCHED_PRIO_H +#define _SCHED_PRIO_H + +#define MAX_NICE 19 +#define MIN_NICE -20 +#define NICE_WIDTH (MAX_NICE - MIN_NICE + 1) + +/* + * Priority of a process goes from 0..MAX_PRIO-1, valid RT + * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH + * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority + * values are inverted: lower p->prio value means higher priority. + * + * The MAX_USER_RT_PRIO value allows the actual maximum + * RT priority to be separate from the value exported to + * user-space. This allows kernel threads to set their + * priority to a value higher than any user task. Note: + * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. + */ + +#define MAX_USER_RT_PRIO 100 +#define MAX_RT_PRIO MAX_USER_RT_PRIO + +#define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) +#define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) + +/* + * Convert user-nice values [ -20 ... 0 ... 19 ] + * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], + * and back. + */ +#define NICE_TO_PRIO(nice) ((nice) + DEFAULT_PRIO) +#define PRIO_TO_NICE(prio) ((prio) - DEFAULT_PRIO) + +/* + * 'User priority' is the nice value converted to something we + * can work with better when scaling various scheduler parameters, + * it's a [ 0 ... 39 ] range. + */ +#define USER_PRIO(p) ((p)-MAX_RT_PRIO) +#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) +#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) + +#endif /* _SCHED_PRIO_H */ diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 34e4ebea8fce..6341f5be6e24 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -1,24 +1,7 @@ #ifndef _SCHED_RT_H #define _SCHED_RT_H -/* - * Priority of a process goes from 0..MAX_PRIO-1, valid RT - * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH - * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority - * values are inverted: lower p->prio value means higher priority. - * - * The MAX_USER_RT_PRIO value allows the actual maximum - * RT priority to be separate from the value exported to - * user-space. This allows kernel threads to set their - * priority to a value higher than any user task. Note: - * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. - */ - -#define MAX_USER_RT_PRIO 100 -#define MAX_RT_PRIO MAX_USER_RT_PRIO - -#define MAX_PRIO (MAX_RT_PRIO + 40) -#define DEFAULT_PRIO (MAX_RT_PRIO + 20) +#include <linux/sched/prio.h> static inline int rt_prio(int prio) { @@ -35,6 +18,7 @@ static inline int rt_task(struct task_struct *p) #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); +extern int rt_mutex_check_prio(struct task_struct *task, int newprio); extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) @@ -46,6 +30,12 @@ static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } + +static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) +{ + return 0; +} + static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; diff --git a/include/linux/security.h b/include/linux/security.h index 5623a7f965b7..2fc42d191f79 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1040,6 +1040,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * Allocate a security structure to the xp->security field; the security * field is initialized to NULL when the xfrm_policy is allocated. * Return 0 if operation was successful (memory to allocate, legal context) + * @gfp is to specify the context for the allocation * @xfrm_policy_clone_security: * @old_ctx contains an existing xfrm_sec_ctx. * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. @@ -1683,7 +1684,7 @@ struct security_operations { #ifdef CONFIG_SECURITY_NETWORK_XFRM int (*xfrm_policy_alloc_security) (struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *sec_ctx); + struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp); int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx); void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx); int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx); @@ -2859,7 +2860,8 @@ static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) #ifdef CONFIG_SECURITY_NETWORK_XFRM -int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx); +int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp); int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp); void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx); int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx); @@ -2877,7 +2879,9 @@ void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl); #else /* CONFIG_SECURITY_NETWORK_XFRM */ -static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx) +static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, + gfp_t gfp) { return 0; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ebbbe7b6d05..15ede6a823a6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2451,8 +2451,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, unsigned int flags); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); -void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, - int len, int hlen); +int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, + int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); @@ -2725,7 +2725,7 @@ static inline void nf_reset(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -2742,6 +2742,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) + dst->nf_trace = src->nf_trace; +#endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) diff --git a/include/linux/slab.h b/include/linux/slab.h index 9260abdd67df..b5b2df60299e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -410,7 +410,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %GFP_NOWAIT - Allocation will not sleep. * - * %GFP_THISNODE - Allocate node-local memory only. + * %__GFP_THISNODE - Allocate node-local memory only. * * %GFP_DMA - Allocation suitable for DMA. * Should only be used for kmalloc() caches. Otherwise, use a diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 9b058eecd403..a2783cb5d275 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 diff --git a/include/linux/torture.h b/include/linux/torture.h new file mode 100644 index 000000000000..b2e2b468e511 --- /dev/null +++ b/include/linux/torture.h @@ -0,0 +1,100 @@ +/* + * Common functions for in-kernel torture tests. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2014 + * + * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + */ + +#ifndef __LINUX_TORTURE_H +#define __LINUX_TORTURE_H + +#include <linux/types.h> +#include <linux/cache.h> +#include <linux/spinlock.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/seqlock.h> +#include <linux/lockdep.h> +#include <linux/completion.h> +#include <linux/debugobjects.h> +#include <linux/bug.h> +#include <linux/compiler.h> + +/* Definitions for a non-string torture-test module parameter. */ +#define torture_param(type, name, init, msg) \ + static type name = init; \ + module_param(name, type, 0444); \ + MODULE_PARM_DESC(name, msg); + +#define TORTURE_FLAG "-torture:" +#define TOROUT_STRING(s) \ + pr_alert("%s" TORTURE_FLAG s "\n", torture_type) +#define VERBOSE_TOROUT_STRING(s) \ + do { if (verbose) pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); } while (0) +#define VERBOSE_TOROUT_ERRSTRING(s) \ + do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0) + +/* Definitions for a non-string torture-test module parameter. */ +#define torture_parm(type, name, init, msg) \ + static type name = init; \ + module_param(name, type, 0444); \ + MODULE_PARM_DESC(name, msg); + +/* Definitions for online/offline exerciser. */ +int torture_onoff_init(long ooholdoff, long oointerval); +char *torture_onoff_stats(char *page); +bool torture_onoff_failures(void); + +/* Low-rider random number generator. */ +struct torture_random_state { + unsigned long trs_state; + long trs_count; +}; +#define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 } +unsigned long torture_random(struct torture_random_state *trsp); + +/* Task shuffler, which causes CPUs to occasionally go idle. */ +void torture_shuffle_task_register(struct task_struct *tp); +int torture_shuffle_init(long shuffint); + +/* Test auto-shutdown handling. */ +void torture_shutdown_absorb(const char *title); +int torture_shutdown_init(int ssecs, void (*cleanup)(void)); + +/* Task stuttering, which forces load/no-load transitions. */ +void stutter_wait(const char *title); +int torture_stutter_init(int s); + +/* Initialization and cleanup. */ +void torture_init_begin(char *ttype, bool v, int *runnable); +void torture_init_end(void); +bool torture_cleanup(void); +bool torture_must_stop(void); +bool torture_must_stop_irq(void); +void torture_kthread_stopping(char *title); +int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, + char *f, struct task_struct **tp); +void _torture_stop_kthread(char *m, struct task_struct **tp); + +#define torture_create_kthread(n, arg, tp) \ + _torture_create_kthread(n, (arg), #n, "Creating " #n " task", \ + "Failed to create " #n, &(tp)) +#define torture_stop_kthread(n, tp) \ + _torture_stop_kthread("Stopping " #n " task", &(tp)) + +#endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index accc497f8d72..7159a0a933df 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -60,6 +60,12 @@ struct tp_module { unsigned int num_tracepoints; struct tracepoint * const *tracepoints_ptrs; }; +bool trace_module_has_bad_taint(struct module *mod); +#else +static inline bool trace_module_has_bad_taint(struct module *mod) +{ + return false; +} #endif /* CONFIG_MODULES */ struct tracepoint_iter { diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index c3fa80745996..2c14d9cdd57a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -88,6 +88,7 @@ #define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB) struct cdc_ncm_ctx { + struct usb_cdc_ncm_ntb_parameters ncm_parm; struct hrtimer tx_timer; struct tasklet_struct bh; diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index e303eef94dd5..0662e98fef72 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -30,7 +30,7 @@ struct usbnet { struct driver_info *driver_info; const char *driver_name; void *driver_priv; - wait_queue_head_t *wait; + wait_queue_head_t wait; struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 9650a3ffd2d2..b4956a5fcc3f 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -31,8 +31,10 @@ #define IF_PREFIX_AUTOCONF 0x02 enum { + INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, INET6_IFADDR_STATE_POSTDAD, + INET6_IFADDR_STATE_ERRDAD, INET6_IFADDR_STATE_UP, INET6_IFADDR_STATE_DEAD, }; @@ -58,7 +60,7 @@ struct inet6_ifaddr { unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ - struct timer_list dad_timer; + struct delayed_work dad_work; struct inet6_dev *idev; struct rt6_info *rt; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 48ed75c21260..e77c10405d51 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -129,6 +129,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); void ip_tunnel_setup(struct net_device *dev, int net_id); +void ip_tunnel_dst_reset_all(struct ip_tunnel *t); /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, diff --git a/include/net/sock.h b/include/net/sock.h index 5c3f7c3624aa..b9586a137cad 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1488,6 +1488,11 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) */ #define sock_owned_by_user(sk) ((sk)->sk_lock.owned) +static inline void sock_release_ownership(struct sock *sk) +{ + sk->sk_lock.owned = 0; +} + /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -2186,7 +2191,6 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, { #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ (1UL << SOCK_TIMESTAMPING_SOFTWARE) | \ (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \ (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE)) diff --git a/include/net/tcp.h b/include/net/tcp.h index 56fc366da6d5..743accec6c76 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,20 +480,21 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_SYN_COOKIES #include <linux/ktime.h> -/* Syncookies use a monotonic timer which increments every 64 seconds. +/* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, - * i.e. a sent cookie is valid only at most for 128 seconds (or less if + * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 static inline u32 tcp_cookie_time(void) { - struct timespec now; - getnstimeofday(&now); - return now.tv_sec >> 6; /* 64 seconds granularity */ + u64 val = get_jiffies_64(); + + do_div(val, 60 * HZ); + return val; } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, @@ -1303,7 +1304,8 @@ struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ - u16 copied; /* queued in tcp_connect() */ + size_t size; + int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index afa5730fb3bd..fb5654a8ca3c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1648,6 +1648,11 @@ static inline int xfrm_aevent_is_on(struct net *net) } #endif +static inline int aead_len(struct xfrm_algo_aead *alg) +{ + return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); +} + static inline int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); @@ -1686,6 +1691,12 @@ static inline int xfrm_replay_clone(struct xfrm_state *x, return 0; } +static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) +{ + return kmemdup(orig, aead_len(orig), GFP_KERNEL); +} + + static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index ae5a17111968..4483fadfa68d 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -12,6 +12,7 @@ struct iscsit_transport { int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *); int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *); void (*iscsit_free_np)(struct iscsi_np *); + void (*iscsit_wait_conn)(struct iscsi_conn *); void (*iscsit_free_conn)(struct iscsi_conn *); int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ddc179b7a105..1fef3e6e9436 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -83,7 +83,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, ), TP_fast_assign( - __entry->client_id = clnt->cl_clid; + __entry->client_id = clnt ? clnt->cl_clid : -1; __entry->task_id = task->tk_pid; __entry->action = action; __entry->runstate = task->tk_runstate; @@ -91,7 +91,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, __entry->flags = task->tk_flags; ), - TP_printk("task:%u@%u flags=%4.4x state=%4.4lx status=%d action=%pf", + TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf", __entry->task_id, __entry->client_id, __entry->flags, __entry->runstate, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 1a8b28db3775..1ee19a24cc5f 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -310,15 +310,12 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = { \ #undef __array #define __array(type, item, len) \ do { \ - mutex_lock(&event_storage_mutex); \ + char *type_str = #type"["__stringify(len)"]"; \ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - snprintf(event_storage, sizeof(event_storage), \ - "%s[%d]", #type, len); \ - ret = trace_define_field(event_call, event_storage, #item, \ + ret = trace_define_field(event_call, type_str, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), FILTER_OTHER); \ - mutex_unlock(&event_storage_mutex); \ if (ret) \ return ret; \ } while (0); diff --git a/init/Kconfig b/init/Kconfig index 009a797dd242..d56cb03c1b49 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1387,6 +1387,13 @@ config FUTEX support for "fast userspace mutexes". The resulting kernel may not run glibc-based applications correctly. +config HAVE_FUTEX_CMPXCHG + bool + help + Architectures should select this if futex_atomic_cmpxchg_inatomic() + is implemented and always working. This removes a couple of runtime + checks. + config EPOLL bool "Enable eventpoll support" if EXPERT default y diff --git a/init/main.c b/init/main.c index eb03090cdced..9c7fd4c9249f 100644 --- a/init/main.c +++ b/init/main.c @@ -561,7 +561,6 @@ asmlinkage void __init start_kernel(void) init_timers(); hrtimers_init(); softirq_init(); - acpi_early_init(); timekeeping_init(); time_init(); sched_clock_postinit(); @@ -613,6 +612,7 @@ asmlinkage void __init start_kernel(void) calibrate_delay(); pidmap_init(); anon_vma_init(); + acpi_early_init(); #ifdef CONFIG_X86 if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); diff --git a/ipc/msg.c b/ipc/msg.c index 245db1140ad6..649853105a5d 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -901,6 +901,8 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl return -EINVAL; if (msgflg & MSG_COPY) { + if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT)) + return -EINVAL; copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax)); if (IS_ERR(copy)) return PTR_ERR(copy); diff --git a/kernel/Makefile b/kernel/Makefile index bc010ee272b6..f2a8b6246ce9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -18,11 +18,13 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_irq_work.o = -pg endif +# cond_syscall is currently not LTO compatible +CFLAGS_sys_ni.o = $(DISABLE_LTO) + obj-y += sched/ obj-y += locking/ obj-y += power/ obj-y += printk/ -obj-y += cpu/ obj-y += irq/ obj-y += rcu/ @@ -93,6 +95,7 @@ obj-$(CONFIG_PADATA) += padata.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o +obj-$(CONFIG_TORTURE_TEST) += torture.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/audit.c b/kernel/audit.c index 34c5a2310fbf..95a20f3f52f1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -182,7 +182,7 @@ struct audit_buffer { struct audit_reply { __u32 portid; - pid_t pid; + struct net *net; struct sk_buff *skb; }; @@ -500,7 +500,7 @@ int audit_send_list(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; - struct net *net = get_net_ns_by_pid(dest->pid); + struct net *net = dest->net; struct audit_net *aunet = net_generic(net, audit_net_id); /* wait for parent to finish and send an ACK */ @@ -510,6 +510,7 @@ int audit_send_list(void *_dest) while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(aunet->nlsk, skb, dest->portid, 0); + put_net(net); kfree(dest); return 0; @@ -543,7 +544,7 @@ out_kfree_skb: static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; - struct net *net = get_net_ns_by_pid(reply->pid); + struct net *net = reply->net; struct audit_net *aunet = net_generic(net, audit_net_id); mutex_lock(&audit_cmd_mutex); @@ -552,12 +553,13 @@ static int audit_send_reply_thread(void *arg) /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0); + put_net(net); kfree(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink - * @portid: netlink port to which to send reply + * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag @@ -568,9 +570,11 @@ static int audit_send_reply_thread(void *arg) * Allocates an skb, builds the netlink message, and sends it to the port id. * No failure notifications. */ -static void audit_send_reply(__u32 portid, int seq, int type, int done, +static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct sk_buff *skb; struct task_struct *tsk; struct audit_reply *reply = kmalloc(sizeof(struct audit_reply), @@ -583,8 +587,8 @@ static void audit_send_reply(__u32 portid, int seq, int type, int done, if (!skb) goto out; + reply->net = get_net(net); reply->portid = portid; - reply->pid = task_pid_vnr(current); reply->skb = skb; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); @@ -604,9 +608,19 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) int err = 0; /* Only support the initial namespaces for now. */ + /* + * We return ECONNREFUSED because it tricks userspace into thinking + * that audit was not configured into the kernel. Lots of users + * configure their PAM stack (because that's what the distro does) + * to reject login if unable to send messages to audit. If we return + * ECONNREFUSED the PAM stack thinks the kernel does not have audit + * configured in and will let login proceed. If we return EPERM + * userspace will reject all logins. This should be removed when we + * support non init namespaces!! + */ if ((current_user_ns() != &init_user_ns) || (task_active_pid_ns(current) != &init_pid_ns)) - return -EPERM; + return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: @@ -673,8 +687,7 @@ static int audit_get_feature(struct sk_buff *skb) seq = nlmsg_hdr(skb)->nlmsg_seq; - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, - &af, sizeof(af)); + audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af)); return 0; } @@ -794,8 +807,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) s.backlog = skb_queue_len(&audit_skb_queue); s.version = AUDIT_VERSION_LATEST; s.backlog_wait_time = audit_backlog_wait_time; - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, - &s, sizeof(s)); + audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { @@ -905,7 +917,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq, data, nlmsg_len(nlh)); break; case AUDIT_LIST_RULES: - err = audit_list_rules_send(NETLINK_CB(skb).portid, seq); + err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); @@ -970,8 +982,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO, - 0, 0, sig_data, sizeof(*sig_data) + len); + audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, + sig_data, sizeof(*sig_data) + len); kfree(sig_data); break; case AUDIT_TTY_GET: { @@ -983,8 +995,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) s.log_passwd = tsk->signal->audit_tty_log_passwd; spin_unlock(&tsk->sighand->siglock); - audit_send_reply(NETLINK_CB(skb).portid, seq, - AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); + audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { diff --git a/kernel/audit.h b/kernel/audit.h index 57cc64d67718..8df132214606 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -247,7 +247,7 @@ extern void audit_panic(const char *message); struct audit_netlink_list { __u32 portid; - pid_t pid; + struct net *net; struct sk_buff_head q; }; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 14a78cca384e..92062fd6cc8c 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -29,6 +29,8 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> +#include <net/net_namespace.h> +#include <net/sock.h> #include "audit.h" /* @@ -1065,11 +1067,13 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data, /** * audit_list_rules_send - list the audit rules - * @portid: target portid for netlink audit messages + * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ -int audit_list_rules_send(__u32 portid, int seq) +int audit_list_rules_send(struct sk_buff *request_skb, int seq) { + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct task_struct *tsk; struct audit_netlink_list *dest; int err = 0; @@ -1083,8 +1087,8 @@ int audit_list_rules_send(__u32 portid, int seq) dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL); if (!dest) return -ENOMEM; + dest->net = get_net(net); dest->portid = portid; - dest->pid = task_pid_vnr(current); skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 105f273b6f86..0c753ddd223b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4112,17 +4112,17 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) err = percpu_ref_init(&css->refcnt, css_release); if (err) - goto err_free; + goto err_free_css; init_css(css, ss, cgrp); err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id); if (err) - goto err_free; + goto err_free_percpu_ref; err = online_css(css); if (err) - goto err_free; + goto err_clear_dir; dget(cgrp->dentry); css_get(css->parent); @@ -4138,8 +4138,11 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) return 0; -err_free: +err_clear_dir: + cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id); +err_free_percpu_ref: percpu_ref_cancel_init(&css->refcnt); +err_free_css: ss->css_free(css); return err; } diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile deleted file mode 100644 index 59ab052ef7a0..000000000000 --- a/kernel/cpu/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-y = idle.o diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4410ac6a55f1..e6b1b66afe52 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -974,12 +974,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Temporarilly set tasks mems_allowed to target nodes of migration, * so that the migration code can allocate pages on these nodes. * - * Call holding cpuset_mutex, so current's cpuset won't change - * during this call, as manage_mutex holds off any cpuset_attach() - * calls. Therefore we don't need to take task_lock around the - * call to guarantee_online_mems(), as we know no one is changing - * our task's cpuset. - * * While the mm_struct we are migrating is typically from some * other task, the task_struct mems_allowed that we are hacking * is for our current task, which must allocate new pages for that @@ -996,8 +990,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + rcu_read_lock(); mems_cs = effective_nodemask_cpuset(task_cs(tsk)); guarantee_online_mems(mems_cs, &tsk->mems_allowed); + rcu_read_unlock(); } /* @@ -2486,9 +2482,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) task_lock(current); cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); task_unlock(current); - allowed = node_isset(node, cs->mems_allowed); mutex_unlock(&callback_mutex); return allowed; } diff --git a/kernel/events/core.c b/kernel/events/core.c index fa0b2d4ad83c..661951ab8ae7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -231,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, #define NR_ACCUMULATED_SAMPLES 128 static DEFINE_PER_CPU(u64, running_sample_length); -void perf_sample_event_took(u64 sample_len_ns) +static void perf_duration_warn(struct irq_work *w) { + u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); u64 avg_local_sample_len; u64 local_samples_len; + + local_samples_len = __get_cpu_var(running_sample_length); + avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES; + + printk_ratelimited(KERN_WARNING + "perf interrupt took too long (%lld > %lld), lowering " + "kernel.perf_event_max_sample_rate to %d\n", + avg_local_sample_len, allowed_ns >> 1, + sysctl_perf_event_sample_rate); +} + +static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn); + +void perf_sample_event_took(u64 sample_len_ns) +{ u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); + u64 avg_local_sample_len; + u64 local_samples_len; if (allowed_ns == 0) return; @@ -263,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns) sysctl_perf_event_sample_rate = max_samples_per_tick * HZ; perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; - printk_ratelimited(KERN_WARNING - "perf samples too long (%lld > %lld), lowering " - "kernel.perf_event_max_sample_rate to %d\n", - avg_local_sample_len, allowed_ns, - sysctl_perf_event_sample_rate); - update_perf_cpu_limits(); + + if (!irq_work_queue(&perf_duration_work)) { + early_printk("perf interrupt took too long (%lld > %lld), lowering " + "kernel.perf_event_max_sample_rate to %d\n", + avg_local_sample_len, allowed_ns >> 1, + sysctl_perf_event_sample_rate); + } } static atomic64_t perf_event_id; @@ -1714,7 +1733,7 @@ group_sched_in(struct perf_event *group_event, struct perf_event_context *ctx) { struct perf_event *event, *partial_group = NULL; - struct pmu *pmu = group_event->pmu; + struct pmu *pmu = ctx->pmu; u64 now = ctx->time; bool simulate = false; @@ -2563,8 +2582,6 @@ static void perf_branch_stack_sched_in(struct task_struct *prev, if (cpuctx->ctx.nr_branch_stack > 0 && pmu->flush_branch_stack) { - pmu = cpuctx->ctx.pmu; - perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(pmu); @@ -6294,7 +6311,7 @@ static int perf_event_idx_default(struct perf_event *event) * Ensures all contexts with the same task_ctx_nr have the same * pmu_cpu_context too. */ -static void *find_pmu_context(int ctxn) +static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) { struct pmu *pmu; diff --git a/kernel/extable.c b/kernel/extable.c index 763faf037ec1..d8a6446adbcb 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -36,7 +36,7 @@ extern struct exception_table_entry __start___ex_table[]; extern struct exception_table_entry __stop___ex_table[]; /* Cleared by build time tools if the table is already sorted. */ -u32 __initdata main_extable_sort_needed = 1; +u32 __initdata __visible main_extable_sort_needed = 1; /* Sort the kernel's built-in exception table */ void __init sort_main_extable(void) diff --git a/kernel/fork.c b/kernel/fork.c index a17621c6cd42..332688e5e7b4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -237,6 +237,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); + task_numa_free(tsk); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); diff --git a/kernel/futex.c b/kernel/futex.c index 44a1261cb9ff..67dacaf93e56 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -157,7 +157,9 @@ * enqueue. */ +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG int __read_mostly futex_cmpxchg_enabled; +#endif /* * Futex flags used to encode options to functions and preserve them across @@ -234,6 +236,7 @@ static const struct futex_q futex_q_init = { * waiting on a futex. */ struct futex_hash_bucket { + atomic_t waiters; spinlock_t lock; struct plist_head chain; } ____cacheline_aligned_in_smp; @@ -253,22 +256,37 @@ static inline void futex_get_mm(union futex_key *key) smp_mb__after_atomic_inc(); } -static inline bool hb_waiters_pending(struct futex_hash_bucket *hb) +/* + * Reflects a new waiter being added to the waitqueue. + */ +static inline void hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP + atomic_inc(&hb->waiters); /* - * Tasks trying to enter the critical region are most likely - * potential waiters that will be added to the plist. Ensure - * that wakers won't miss to-be-slept tasks in the window between - * the wait call and the actual plist_add. + * Full barrier (A), see the ordering comment above. */ - if (spin_is_locked(&hb->lock)) - return true; - smp_rmb(); /* Make sure we check the lock state first */ + smp_mb__after_atomic_inc(); +#endif +} + +/* + * Reflects a waiter being removed from the waitqueue by wakeup + * paths. + */ +static inline void hb_waiters_dec(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + atomic_dec(&hb->waiters); +#endif +} - return !plist_head_empty(&hb->chain); +static inline int hb_waiters_pending(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + return atomic_read(&hb->waiters); #else - return true; + return 1; #endif } @@ -954,6 +972,7 @@ static void __unqueue_futex(struct futex_q *q) hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); } /* @@ -1257,7 +1276,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, */ if (likely(&hb1->chain != &hb2->chain)) { plist_del(&q->list, &hb1->chain); + hb_waiters_dec(hb1); plist_add(&q->list, &hb2->chain); + hb_waiters_inc(hb2); q->lock_ptr = &hb2->lock; } get_futex_key_refs(key2); @@ -1600,6 +1621,17 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) struct futex_hash_bucket *hb; hb = hash_futex(&q->key); + + /* + * Increment the counter before taking the lock so that + * a potential waker won't miss a to-be-slept task that is + * waiting for the spinlock. This is safe as all queue_lock() + * users end up calling queue_me(). Similarly, for housekeeping, + * decrement the counter at queue_unlock() when some error has + * occurred and we don't end up adding the task to the list. + */ + hb_waiters_inc(hb); + q->lock_ptr = &hb->lock; spin_lock(&hb->lock); /* implies MB (A) */ @@ -1611,6 +1643,7 @@ queue_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); + hb_waiters_dec(hb); } /** @@ -2342,6 +2375,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * Unqueue the futex_q and determine which it was. */ plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; @@ -2843,9 +2877,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); } -static int __init futex_init(void) +static void __init futex_detect_cmpxchg(void) { +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG u32 curval; + + /* + * This will fail and we want it. Some arch implementations do + * runtime detection of the futex_atomic_cmpxchg_inatomic() + * functionality. We want to know that before we call in any + * of the complex code paths. Also we want to prevent + * registration of robust lists in that case. NULL is + * guaranteed to fault and we get -EFAULT on functional + * implementation, the non-functional ones will return + * -ENOSYS. + */ + if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) + futex_cmpxchg_enabled = 1; +#endif +} + +static int __init futex_init(void) +{ unsigned int futex_shift; unsigned long i; @@ -2861,20 +2914,11 @@ static int __init futex_init(void) &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; - /* - * This will fail and we want it. Some arch implementations do - * runtime detection of the futex_atomic_cmpxchg_inatomic() - * functionality. We want to know that before we call in any - * of the complex code paths. Also we want to prevent - * registration of robust lists in that case. NULL is - * guaranteed to fault and we get -EFAULT on functional - * implementation, the non-functional ones will return - * -ENOSYS. - */ - if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) - futex_cmpxchg_enabled = 1; + + futex_detect_cmpxchg(); for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cf68bb36fe58..f14033700c25 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -10,6 +10,7 @@ #include <linux/mutex.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/topology.h> #include <linux/seq_file.h> #include <linux/slab.h> diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 481a13c43b17..d3bf660cb57f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -802,8 +802,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, static void wake_threads_waitq(struct irq_desc *desc) { - if (atomic_dec_and_test(&desc->threads_active) && - waitqueue_active(&desc->wait_for_threads)) + if (atomic_dec_and_test(&desc->threads_active)) wake_up(&desc->wait_for_threads); } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 55fcce6065cf..a82170e2fa78 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -61,11 +61,11 @@ void __weak arch_irq_work_raise(void) * * Can be re-enqueued while the callback is still in progress. */ -void irq_work_queue(struct irq_work *work) +bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) - return; + return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); @@ -83,6 +83,8 @@ void irq_work_queue(struct irq_work *work) } preempt_enable(); + + return true; } EXPORT_SYMBOL_GPL(irq_work_queue); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index d945a949760f..e660964086e2 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -19,6 +19,8 @@ #include <linux/sched.h> #include <linux/capability.h> +#include <linux/rcupdate.h> /* rcu_expedited */ + #define KERNEL_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index baab8e5e7f66..306a76b51e0f 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o lglock.o +obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -23,3 +23,4 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o +obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index eb8a54783fa0..b0e9467922e1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1936,12 +1936,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) for (;;) { int distance = curr->lockdep_depth - depth + 1; - hlock = curr->held_locks + depth-1; + hlock = curr->held_locks + depth - 1; /* * Only non-recursive-read entries get new dependencies * added: */ - if (hlock->read != 2) { + if (hlock->read != 2 && hlock->check) { if (!check_prev_add(curr, hlock, next, distance, trylock_loop)) return 0; @@ -2098,7 +2098,7 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock, * (If lookup_chain_cache() returns with 1 it acquires * graph_lock for us) */ - if (!hlock->trylock && (hlock->check == 2) && + if (!hlock->trylock && hlock->check && lookup_chain_cache(curr, hlock, chain_key)) { /* * Check whether last held lock: @@ -2517,7 +2517,7 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark) BUG_ON(usage_bit >= LOCK_USAGE_STATES); - if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys) + if (!hlock->check) continue; if (!mark_lock(curr, hlock, usage_bit)) @@ -2557,7 +2557,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip) debug_atomic_inc(hardirqs_on_events); } -void trace_hardirqs_on_caller(unsigned long ip) +__visible void trace_hardirqs_on_caller(unsigned long ip) { time_hardirqs_on(CALLER_ADDR0, ip); @@ -2610,7 +2610,7 @@ EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -void trace_hardirqs_off_caller(unsigned long ip) +__visible void trace_hardirqs_off_caller(unsigned long ip) { struct task_struct *curr = current; @@ -3055,9 +3055,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int class_idx; u64 chain_key; - if (!prove_locking) - check = 1; - if (unlikely(!debug_locks)) return 0; @@ -3069,8 +3066,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; - if (lock->key == &__lockdep_no_validate__) - check = 1; + if (!prove_locking || lock->key == &__lockdep_no_validate__) + check = 0; if (subclass < NR_LOCKDEP_CACHING_CLASSES) class = lock->class_cache[subclass]; @@ -3138,7 +3135,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->holdtime_stamp = lockstat_clock(); #endif - if (check == 2 && !mark_irqflags(curr, hlock)) + if (check && !mark_irqflags(curr, hlock)) return 0; /* mark it as used: */ @@ -4191,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task) } EXPORT_SYMBOL_GPL(debug_show_held_locks); -void lockdep_sys_exit(void) +asmlinkage void lockdep_sys_exit(void) { struct task_struct *curr = current; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c new file mode 100644 index 000000000000..f26b1a18e34e --- /dev/null +++ b/kernel/locking/locktorture.c @@ -0,0 +1,452 @@ +/* + * Module-based torture test facility for locking + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2014 + * + * Author: Paul E. McKenney <paulmck@us.ibm.com> + * Based on kernel/rcu/torture.c. + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kthread.h> +#include <linux/err.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/reboot.h> +#include <linux/freezer.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include <linux/trace_clock.h> +#include <asm/byteorder.h> +#include <linux/torture.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); + +torture_param(int, nwriters_stress, -1, + "Number of write-locking stress-test threads"); +torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); +torture_param(int, onoff_interval, 0, + "Time between CPU hotplugs (s), 0=disable"); +torture_param(int, shuffle_interval, 3, + "Number of jiffies between shuffles, 0=disable"); +torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); +torture_param(int, stat_interval, 60, + "Number of seconds between stats printk()s"); +torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); +torture_param(bool, verbose, true, + "Enable verbose debugging printk()s"); + +static char *torture_type = "spin_lock"; +module_param(torture_type, charp, 0444); +MODULE_PARM_DESC(torture_type, + "Type of lock to torture (spin_lock, spin_lock_irq, ...)"); + +static atomic_t n_lock_torture_errors; + +static struct task_struct *stats_task; +static struct task_struct **writer_tasks; + +static int nrealwriters_stress; +static bool lock_is_write_held; + +struct lock_writer_stress_stats { + long n_write_lock_fail; + long n_write_lock_acquired; +}; +static struct lock_writer_stress_stats *lwsa; + +#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE) +#define LOCKTORTURE_RUNNABLE_INIT 1 +#else +#define LOCKTORTURE_RUNNABLE_INIT 0 +#endif +int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT; +module_param(locktorture_runnable, int, 0444); +MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot"); + +/* Forward reference. */ +static void lock_torture_cleanup(void); + +/* + * Operations vector for selecting different types of tests. + */ +struct lock_torture_ops { + void (*init)(void); + int (*writelock)(void); + void (*write_delay)(struct torture_random_state *trsp); + void (*writeunlock)(void); + unsigned long flags; + const char *name; +}; + +static struct lock_torture_ops *cur_ops; + +/* + * Definitions for lock torture testing. + */ + +static int torture_lock_busted_write_lock(void) +{ + return 0; /* BUGGY, do not use in real life!!! */ +} + +static void torture_lock_busted_write_delay(struct torture_random_state *trsp) +{ + const unsigned long longdelay_us = 100; + + /* We want a long delay occasionally to force massive contention. */ + if (!(torture_random(trsp) % + (nrealwriters_stress * 2000 * longdelay_us))) + mdelay(longdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_lock_busted_write_unlock(void) +{ + /* BUGGY, do not use in real life!!! */ +} + +static struct lock_torture_ops lock_busted_ops = { + .writelock = torture_lock_busted_write_lock, + .write_delay = torture_lock_busted_write_delay, + .writeunlock = torture_lock_busted_write_unlock, + .name = "lock_busted" +}; + +static DEFINE_SPINLOCK(torture_spinlock); + +static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock) +{ + spin_lock(&torture_spinlock); + return 0; +} + +static void torture_spin_lock_write_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_us = 100; + + /* We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (nrealwriters_stress * 2000 * longdelay_us))) + mdelay(longdelay_us); + if (!(torture_random(trsp) % + (nrealwriters_stress * 2 * shortdelay_us))) + udelay(shortdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock) +{ + spin_unlock(&torture_spinlock); +} + +static struct lock_torture_ops spin_lock_ops = { + .writelock = torture_spin_lock_write_lock, + .write_delay = torture_spin_lock_write_delay, + .writeunlock = torture_spin_lock_write_unlock, + .name = "spin_lock" +}; + +static int torture_spin_lock_write_lock_irq(void) +__acquires(torture_spinlock_irq) +{ + unsigned long flags; + + spin_lock_irqsave(&torture_spinlock, flags); + cur_ops->flags = flags; + return 0; +} + +static void torture_lock_spin_write_unlock_irq(void) +__releases(torture_spinlock) +{ + spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags); +} + +static struct lock_torture_ops spin_lock_irq_ops = { + .writelock = torture_spin_lock_write_lock_irq, + .write_delay = torture_spin_lock_write_delay, + .writeunlock = torture_lock_spin_write_unlock_irq, + .name = "spin_lock_irq" +}; + +/* + * Lock torture writer kthread. Repeatedly acquires and releases + * the lock, checking for duplicate acquisitions. + */ +static int lock_torture_writer(void *arg) +{ + struct lock_writer_stress_stats *lwsp = arg; + static DEFINE_TORTURE_RANDOM(rand); + + VERBOSE_TOROUT_STRING("lock_torture_writer task started"); + set_user_nice(current, 19); + + do { + schedule_timeout_uninterruptible(1); + cur_ops->writelock(); + if (WARN_ON_ONCE(lock_is_write_held)) + lwsp->n_write_lock_fail++; + lock_is_write_held = 1; + lwsp->n_write_lock_acquired++; + cur_ops->write_delay(&rand); + lock_is_write_held = 0; + cur_ops->writeunlock(); + stutter_wait("lock_torture_writer"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_writer"); + return 0; +} + +/* + * Create an lock-torture-statistics message in the specified buffer. + */ +static void lock_torture_printk(char *page) +{ + bool fail = 0; + int i; + long max = 0; + long min = lwsa[0].n_write_lock_acquired; + long long sum = 0; + + for (i = 0; i < nrealwriters_stress; i++) { + if (lwsa[i].n_write_lock_fail) + fail = true; + sum += lwsa[i].n_write_lock_acquired; + if (max < lwsa[i].n_write_lock_fail) + max = lwsa[i].n_write_lock_fail; + if (min > lwsa[i].n_write_lock_fail) + min = lwsa[i].n_write_lock_fail; + } + page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG); + page += sprintf(page, + "Writes: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n", + sum, max, min, max / 2 > min ? "???" : "", + fail, fail ? "!!!" : ""); + if (fail) + atomic_inc(&n_lock_torture_errors); +} + +/* + * Print torture statistics. Caller must ensure that there is only one + * call to this function at a given time!!! This is normally accomplished + * by relying on the module system to only have one copy of the module + * loaded, and then by giving the lock_torture_stats kthread full control + * (or the init/cleanup functions when lock_torture_stats thread is not + * running). + */ +static void lock_torture_stats_print(void) +{ + int size = nrealwriters_stress * 200 + 8192; + char *buf; + + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + pr_err("lock_torture_stats_print: Out of memory, need: %d", + size); + return; + } + lock_torture_printk(buf); + pr_alert("%s", buf); + kfree(buf); +} + +/* + * Periodically prints torture statistics, if periodic statistics printing + * was specified via the stat_interval module parameter. + * + * No need to worry about fullstop here, since this one doesn't reference + * volatile state or register callbacks. + */ +static int lock_torture_stats(void *arg) +{ + VERBOSE_TOROUT_STRING("lock_torture_stats task started"); + do { + schedule_timeout_interruptible(stat_interval * HZ); + lock_torture_stats_print(); + torture_shutdown_absorb("lock_torture_stats"); + } while (!torture_must_stop()); + torture_kthread_stopping("lock_torture_stats"); + return 0; +} + +static inline void +lock_torture_print_module_parms(struct lock_torture_ops *cur_ops, + const char *tag) +{ + pr_alert("%s" TORTURE_FLAG + "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, nrealwriters_stress, stat_interval, verbose, + shuffle_interval, stutter, shutdown_secs, + onoff_interval, onoff_holdoff); +} + +static void lock_torture_cleanup(void) +{ + int i; + + if (torture_cleanup()) + return; + + if (writer_tasks) { + for (i = 0; i < nrealwriters_stress; i++) + torture_stop_kthread(lock_torture_writer, + writer_tasks[i]); + kfree(writer_tasks); + writer_tasks = NULL; + } + + torture_stop_kthread(lock_torture_stats, stats_task); + lock_torture_stats_print(); /* -After- the stats thread is stopped! */ + + if (atomic_read(&n_lock_torture_errors)) + lock_torture_print_module_parms(cur_ops, + "End of test: FAILURE"); + else if (torture_onoff_failures()) + lock_torture_print_module_parms(cur_ops, + "End of test: LOCK_HOTPLUG"); + else + lock_torture_print_module_parms(cur_ops, + "End of test: SUCCESS"); +} + +static int __init lock_torture_init(void) +{ + int i; + int firsterr = 0; + static struct lock_torture_ops *torture_ops[] = { + &lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops, + }; + + torture_init_begin(torture_type, verbose, &locktorture_runnable); + + /* Process args and tell the world that the torturer is on the job. */ + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { + cur_ops = torture_ops[i]; + if (strcmp(torture_type, cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(torture_ops)) { + pr_alert("lock-torture: invalid torture type: \"%s\"\n", + torture_type); + pr_alert("lock-torture types:"); + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) + pr_alert(" %s", torture_ops[i]->name); + pr_alert("\n"); + torture_init_end(); + return -EINVAL; + } + if (cur_ops->init) + cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + + if (nwriters_stress >= 0) + nrealwriters_stress = nwriters_stress; + else + nrealwriters_stress = 2 * num_online_cpus(); + lock_torture_print_module_parms(cur_ops, "Start of test"); + + /* Initialize the statistics so that each run gets its own numbers. */ + + lock_is_write_held = 0; + lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL); + if (lwsa == NULL) { + VERBOSE_TOROUT_STRING("lwsa: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nrealwriters_stress; i++) { + lwsa[i].n_write_lock_fail = 0; + lwsa[i].n_write_lock_acquired = 0; + } + + /* Start up the kthreads. */ + + if (onoff_interval > 0) { + firsterr = torture_onoff_init(onoff_holdoff * HZ, + onoff_interval * HZ); + if (firsterr) + goto unwind; + } + if (shuffle_interval > 0) { + firsterr = torture_shuffle_init(shuffle_interval); + if (firsterr) + goto unwind; + } + if (shutdown_secs > 0) { + firsterr = torture_shutdown_init(shutdown_secs, + lock_torture_cleanup); + if (firsterr) + goto unwind; + } + if (stutter > 0) { + firsterr = torture_stutter_init(stutter); + if (firsterr) + goto unwind; + } + + writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]), + GFP_KERNEL); + if (writer_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nrealwriters_stress; i++) { + firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i], + writer_tasks[i]); + if (firsterr) + goto unwind; + } + if (stat_interval > 0) { + firsterr = torture_create_kthread(lock_torture_stats, NULL, + stats_task); + if (firsterr) + goto unwind; + } + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + lock_torture_cleanup(); + return firsterr; +} + +module_init(lock_torture_init); +module_exit(lock_torture_cleanup); diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c new file mode 100644 index 000000000000..838dc9e00669 --- /dev/null +++ b/kernel/locking/mcs_spinlock.c @@ -0,0 +1,178 @@ + +#include <linux/percpu.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include "mcs_spinlock.h" + +#ifdef CONFIG_SMP + +/* + * An MCS like lock especially tailored for optimistic spinning for sleeping + * lock implementations (mutex, rwsem, etc). + * + * Using a single mcs node per CPU is safe because sleeping locks should not be + * called from interrupt context and we have preemption disabled while + * spinning. + */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node); + +/* + * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. + * Can return NULL in case we were the last queued and we updated @lock instead. + */ +static inline struct optimistic_spin_queue * +osq_wait_next(struct optimistic_spin_queue **lock, + struct optimistic_spin_queue *node, + struct optimistic_spin_queue *prev) +{ + struct optimistic_spin_queue *next = NULL; + + for (;;) { + if (*lock == node && cmpxchg(lock, node, prev) == node) { + /* + * We were the last queued, we moved @lock back. @prev + * will now observe @lock and will complete its + * unlock()/unqueue(). + */ + break; + } + + /* + * We must xchg() the @node->next value, because if we were to + * leave it in, a concurrent unlock()/unqueue() from + * @node->next might complete Step-A and think its @prev is + * still valid. + * + * If the concurrent unlock()/unqueue() wins the race, we'll + * wait for either @lock to point to us, through its Step-B, or + * wait for a new @node->next from its Step-C. + */ + if (node->next) { + next = xchg(&node->next, NULL); + if (next) + break; + } + + arch_mutex_cpu_relax(); + } + + return next; +} + +bool osq_lock(struct optimistic_spin_queue **lock) +{ + struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node); + struct optimistic_spin_queue *prev, *next; + + node->locked = 0; + node->next = NULL; + + node->prev = prev = xchg(lock, node); + if (likely(prev == NULL)) + return true; + + ACCESS_ONCE(prev->next) = node; + + /* + * Normally @prev is untouchable after the above store; because at that + * moment unlock can proceed and wipe the node element from stack. + * + * However, since our nodes are static per-cpu storage, we're + * guaranteed their existence -- this allows us to apply + * cmpxchg in an attempt to undo our queueing. + */ + + while (!smp_load_acquire(&node->locked)) { + /* + * If we need to reschedule bail... so we can block. + */ + if (need_resched()) + goto unqueue; + + arch_mutex_cpu_relax(); + } + return true; + +unqueue: + /* + * Step - A -- stabilize @prev + * + * Undo our @prev->next assignment; this will make @prev's + * unlock()/unqueue() wait for a next pointer since @lock points to us + * (or later). + */ + + for (;;) { + if (prev->next == node && + cmpxchg(&prev->next, node, NULL) == node) + break; + + /* + * We can only fail the cmpxchg() racing against an unlock(), + * in which case we should observe @node->locked becomming + * true. + */ + if (smp_load_acquire(&node->locked)) + return true; + + arch_mutex_cpu_relax(); + + /* + * Or we race against a concurrent unqueue()'s step-B, in which + * case its step-C will write us a new @node->prev pointer. + */ + prev = ACCESS_ONCE(node->prev); + } + + /* + * Step - B -- stabilize @next + * + * Similar to unlock(), wait for @node->next or move @lock from @node + * back to @prev. + */ + + next = osq_wait_next(lock, node, prev); + if (!next) + return false; + + /* + * Step - C -- unlink + * + * @prev is stable because its still waiting for a new @prev->next + * pointer, @next is stable because our @node->next pointer is NULL and + * it will wait in Step-A. + */ + + ACCESS_ONCE(next->prev) = prev; + ACCESS_ONCE(prev->next) = next; + + return false; +} + +void osq_unlock(struct optimistic_spin_queue **lock) +{ + struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node); + struct optimistic_spin_queue *next; + + /* + * Fast path for the uncontended case. + */ + if (likely(cmpxchg(lock, node, NULL) == node)) + return; + + /* + * Second most likely case. + */ + next = xchg(&node->next, NULL); + if (next) { + ACCESS_ONCE(next->locked) = 1; + return; + } + + next = osq_wait_next(lock, node, NULL); + if (next) + ACCESS_ONCE(next->locked) = 1; +} + +#endif + diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h new file mode 100644 index 000000000000..a2dbac4aca6b --- /dev/null +++ b/kernel/locking/mcs_spinlock.h @@ -0,0 +1,129 @@ +/* + * MCS lock defines + * + * This file contains the main data structure and API definitions of MCS lock. + * + * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock + * with the desirable properties of being fair, and with each cpu trying + * to acquire the lock spinning on a local variable. + * It avoids expensive cache bouncings that common test-and-set spin-lock + * implementations incur. + */ +#ifndef __LINUX_MCS_SPINLOCK_H +#define __LINUX_MCS_SPINLOCK_H + +#include <asm/mcs_spinlock.h> + +struct mcs_spinlock { + struct mcs_spinlock *next; + int locked; /* 1 if lock acquired */ +}; + +#ifndef arch_mcs_spin_lock_contended +/* + * Using smp_load_acquire() provides a memory barrier that ensures + * subsequent operations happen after the lock is acquired. + */ +#define arch_mcs_spin_lock_contended(l) \ +do { \ + while (!(smp_load_acquire(l))) \ + arch_mutex_cpu_relax(); \ +} while (0) +#endif + +#ifndef arch_mcs_spin_unlock_contended +/* + * smp_store_release() provides a memory barrier to ensure all + * operations in the critical section has been completed before + * unlocking. + */ +#define arch_mcs_spin_unlock_contended(l) \ + smp_store_release((l), 1) +#endif + +/* + * Note: the smp_load_acquire/smp_store_release pair is not + * sufficient to form a full memory barrier across + * cpus for many architectures (except x86) for mcs_unlock and mcs_lock. + * For applications that need a full barrier across multiple cpus + * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be + * used after mcs_lock. + */ + +/* + * In order to acquire the lock, the caller should declare a local node and + * pass a reference of the node to this function in addition to the lock. + * If the lock has already been acquired, then this will proceed to spin + * on this node->locked until the previous lock holder sets the node->locked + * in mcs_spin_unlock(). + * + * We don't inline mcs_spin_lock() so that perf can correctly account for the + * time spent in this lock function. + */ +static inline +void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *prev; + + /* Init node */ + node->locked = 0; + node->next = NULL; + + prev = xchg(lock, node); + if (likely(prev == NULL)) { + /* + * Lock acquired, don't need to set node->locked to 1. Threads + * only spin on its own node->locked value for lock acquisition. + * However, since this thread can immediately acquire the lock + * and does not proceed to spin on its own node->locked, this + * value won't be used. If a debug mode is needed to + * audit lock status, then set node->locked value here. + */ + return; + } + ACCESS_ONCE(prev->next) = node; + + /* Wait until the lock holder passes the lock down. */ + arch_mcs_spin_lock_contended(&node->locked); +} + +/* + * Releases the lock. The caller should pass in the corresponding node that + * was used to acquire the lock. + */ +static inline +void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *next = ACCESS_ONCE(node->next); + + if (likely(!next)) { + /* + * Release the lock by setting it to NULL + */ + if (likely(cmpxchg(lock, node, NULL) == node)) + return; + /* Wait until the next pointer is set */ + while (!(next = ACCESS_ONCE(node->next))) + arch_mutex_cpu_relax(); + } + + /* Pass lock to next waiter. */ + arch_mcs_spin_unlock_contended(&next->locked); +} + +/* + * Cancellable version of the MCS lock above. + * + * Intended for adaptive spinning of sleeping locks: + * mutex_lock()/rwsem_down_{read,write}() etc. + */ + +struct optimistic_spin_queue { + struct optimistic_spin_queue *next, *prev; + int locked; /* 1 if lock acquired */ +}; + +extern bool osq_lock(struct optimistic_spin_queue **lock); +extern void osq_unlock(struct optimistic_spin_queue **lock); + +#endif /* __LINUX_MCS_SPINLOCK_H */ diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index faf6f5b53e77..e1191c996c59 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -83,6 +83,12 @@ void debug_mutex_unlock(struct mutex *lock) DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); + + /* + * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug + * mutexes so that we can do it here after we've verified state. + */ + atomic_set(&lock->count, 1); } void debug_mutex_init(struct mutex *lock, const char *name, diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 4dd6e4c219de..bc73d33c6760 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -25,6 +25,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/debug_locks.h> +#include "mcs_spinlock.h" /* * In the DEBUG case we are using the "NULL fastpath" for mutexes, @@ -33,6 +34,13 @@ #ifdef CONFIG_DEBUG_MUTEXES # include "mutex-debug.h" # include <asm-generic/mutex-null.h> +/* + * Must be 0 for the debug case so we do not do the unlock outside of the + * wait_lock region. debug_mutex_unlock() will do the actual unlock in this + * case. + */ +# undef __mutex_slowpath_needs_to_unlock +# define __mutex_slowpath_needs_to_unlock() 0 #else # include "mutex.h" # include <asm/mutex.h> @@ -52,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) INIT_LIST_HEAD(&lock->wait_list); mutex_clear_owner(lock); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER - lock->spin_mlock = NULL; + lock->osq = NULL; #endif debug_mutex_init(lock, name, key); @@ -67,8 +75,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -static __used noinline void __sched -__mutex_lock_slowpath(atomic_t *lock_count); +__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); /** * mutex_lock - acquire the mutex @@ -111,54 +118,7 @@ EXPORT_SYMBOL(mutex_lock); * more or less simultaneously, the spinners need to acquire a MCS lock * first before spinning on the owner field. * - * We don't inline mspin_lock() so that perf can correctly account for the - * time spent in this lock function. */ -struct mspin_node { - struct mspin_node *next ; - int locked; /* 1 if lock acquired */ -}; -#define MLOCK(mutex) ((struct mspin_node **)&((mutex)->spin_mlock)) - -static noinline -void mspin_lock(struct mspin_node **lock, struct mspin_node *node) -{ - struct mspin_node *prev; - - /* Init node */ - node->locked = 0; - node->next = NULL; - - prev = xchg(lock, node); - if (likely(prev == NULL)) { - /* Lock acquired */ - node->locked = 1; - return; - } - ACCESS_ONCE(prev->next) = node; - smp_wmb(); - /* Wait until the lock holder passes the lock down */ - while (!ACCESS_ONCE(node->locked)) - arch_mutex_cpu_relax(); -} - -static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node) -{ - struct mspin_node *next = ACCESS_ONCE(node->next); - - if (likely(!next)) { - /* - * Release the lock by setting it to NULL - */ - if (cmpxchg(lock, node, NULL) == node) - return; - /* Wait until the next pointer is set */ - while (!(next = ACCESS_ONCE(node->next))) - arch_mutex_cpu_relax(); - } - ACCESS_ONCE(next->locked) = 1; - smp_wmb(); -} /* * Mutex spinning code migrated from kernel/sched/core.c @@ -212,6 +172,9 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) struct task_struct *owner; int retval = 1; + if (need_resched()) + return 0; + rcu_read_lock(); owner = ACCESS_ONCE(lock->owner); if (owner) @@ -225,7 +188,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) } #endif -static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +__visible __used noinline +void __sched __mutex_unlock_slowpath(atomic_t *lock_count); /** * mutex_unlock - release the mutex @@ -446,9 +410,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (!mutex_can_spin_on_owner(lock)) goto slowpath; + if (!osq_lock(&lock->osq)) + goto slowpath; + for (;;) { struct task_struct *owner; - struct mspin_node node; if (use_ww_ctx && ww_ctx->acquired > 0) { struct ww_mutex *ww; @@ -463,19 +429,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * performed the optimistic spinning cannot be done. */ if (ACCESS_ONCE(ww->ctx)) - goto slowpath; + break; } /* * If there's an owner, wait for it to either * release the lock or go to sleep. */ - mspin_lock(MLOCK(lock), &node); owner = ACCESS_ONCE(lock->owner); - if (owner && !mutex_spin_on_owner(lock, owner)) { - mspin_unlock(MLOCK(lock), &node); - goto slowpath; - } + if (owner && !mutex_spin_on_owner(lock, owner)) + break; if ((atomic_read(&lock->count) == 1) && (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { @@ -488,11 +451,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } mutex_set_owner(lock); - mspin_unlock(MLOCK(lock), &node); + osq_unlock(&lock->osq); preempt_enable(); return 0; } - mspin_unlock(MLOCK(lock), &node); /* * When there's no owner, we might have preempted between the @@ -501,7 +463,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * the owner complete. */ if (!owner && (need_resched() || rt_task(task))) - goto slowpath; + break; /* * The cpu_relax() call is a compiler barrier which forces @@ -511,7 +473,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ arch_mutex_cpu_relax(); } + osq_unlock(&lock->osq); slowpath: + /* + * If we fell out of the spin path because of need_resched(), + * reschedule now, before we try-lock the mutex. This avoids getting + * scheduled out right after we obtained the mutex. + */ + if (need_resched()) + schedule_preempt_disabled(); #endif spin_lock_mutex(&lock->wait_lock, flags); @@ -717,10 +687,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; - spin_lock_mutex(&lock->wait_lock, flags); - mutex_release(&lock->dep_map, nested, _RET_IP_); - debug_mutex_unlock(lock); - /* * some architectures leave the lock unlocked in the fastpath failure * case, others need to leave it locked. In the later case we have to @@ -729,6 +695,10 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) if (__mutex_slowpath_needs_to_unlock()) atomic_set(&lock->count, 1); + spin_lock_mutex(&lock->wait_lock, flags); + mutex_release(&lock->dep_map, nested, _RET_IP_); + debug_mutex_unlock(lock); + if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ struct mutex_waiter *waiter = @@ -746,7 +716,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) /* * Release the lock, slowpath: */ -static __used noinline void +__visible void __mutex_unlock_slowpath(atomic_t *lock_count) { __mutex_unlock_common_slowpath(lock_count, 1); @@ -803,7 +773,7 @@ int __sched mutex_lock_killable(struct mutex *lock) } EXPORT_SYMBOL(mutex_lock_killable); -static __used noinline void __sched +__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2e960a2bab81..aa4dff04b594 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -213,6 +213,18 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task) } /* + * Called by sched_setscheduler() to check whether the priority change + * is overruled by a possible priority boosting. + */ +int rt_mutex_check_prio(struct task_struct *task, int newprio) +{ + if (!task_has_pi_waiters(task)) + return 0; + + return task_top_pi_waiter(task)->task->prio <= newprio; +} + +/* * Adjust the priority of a task, after its pi_waiters got modified. * * This can be both boosting and unboosting. task->pi_lock must be held. diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 19c5fa95e0b4..1d66e08e897d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -143,6 +143,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) /* * wait for the read lock to be granted */ +__visible struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; @@ -190,6 +191,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) /* * wait until we successfully acquire the write lock */ +__visible struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) { long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS; @@ -252,6 +254,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) * handle waking up a waiter on the semaphore * - up_read/up_write has decremented the active part of count if we come here */ +__visible struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; @@ -272,6 +275,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) * - caller incremented waiting part of count and discovered it still negative * - just wake up any readers at the front of the queue */ +__visible struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) { unsigned long flags; diff --git a/kernel/module.c b/kernel/module.c index d24fcf29cb64..8dc7f5e80dd8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1015,7 +1015,7 @@ static size_t module_flags_taint(struct module *mod, char *buf) buf[l++] = 'C'; /* * TAINT_FORCED_RMMOD: could be added. - * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't + * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't * apply to modules. */ return l; @@ -1948,6 +1948,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) switch (sym[i].st_shndx) { case SHN_COMMON: + /* Ignore common symbols */ + if (!strncmp(name, "__gnu_lto", 9)) + break; + /* We compiled with -fno-common. These are not supposed to happen. */ pr_debug("Common symbol: %s\n", name); diff --git a/kernel/notifier.c b/kernel/notifier.c index 2d5cc4ccff7f..db4c8b08a50c 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -309,7 +309,7 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh, * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ - if (rcu_dereference_raw(nh->head)) { + if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls); diff --git a/kernel/panic.c b/kernel/panic.c index 6d6300375090..cca8a913ae7c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -199,7 +199,7 @@ struct tnt { static const struct tnt tnts[] = { { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, { TAINT_FORCED_MODULE, 'F', ' ' }, - { TAINT_UNSAFE_SMP, 'S', ' ' }, + { TAINT_CPU_OUT_OF_SPEC, 'S', ' ' }, { TAINT_FORCED_RMMOD, 'R', ' ' }, { TAINT_MACHINE_CHECK, 'M', ' ' }, { TAINT_BAD_PAGE, 'B', ' ' }, @@ -459,7 +459,7 @@ EXPORT_SYMBOL(warn_slowpath_null); * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ -void __stack_chk_fail(void) +__visible void __stack_chk_fail(void) { panic("stack-protector: Kernel stack is corrupted in: %p\n", __builtin_return_address(0)); diff --git a/kernel/profile.c b/kernel/profile.c index 6631e1ef55ab..ebdd9c1a86b4 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -549,14 +549,14 @@ static int create_hash_tables(void) struct page *page; page = alloc_pages_exact_node(node, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) goto out_cleanup; per_cpu(cpu_profile_hits, cpu)[1] = (struct profile_hit *)page_address(page); page = alloc_pages_exact_node(node, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) goto out_cleanup; diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 01e9ec37a3e3..807ccfbf69b3 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,5 +1,5 @@ obj-y += update.o srcu.o -obj-$(CONFIG_RCU_TORTURE_TEST) += torture.o +obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 79c3877e9c5b..bfda2726ca45 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2011 * @@ -23,6 +23,7 @@ #ifndef __LINUX_RCU_H #define __LINUX_RCU_H +#include <trace/events/rcu.h> #ifdef CONFIG_RCU_TRACE #define RCU_TRACE(stmt) stmt #else /* #ifdef CONFIG_RCU_TRACE */ @@ -116,8 +117,6 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) } } -extern int rcu_expedited; - #ifdef CONFIG_RCU_STALL_COMMON extern int rcu_cpu_stall_suppress; diff --git a/kernel/rcu/torture.c b/kernel/rcu/rcutorture.c index 732f8ae3086a..bd30bc61bc05 100644 --- a/kernel/rcu/torture.c +++ b/kernel/rcu/rcutorture.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright (C) IBM Corporation, 2005, 2006 * @@ -48,110 +48,58 @@ #include <linux/slab.h> #include <linux/trace_clock.h> #include <asm/byteorder.h> +#include <linux/torture.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>"); -MODULE_ALIAS("rcutorture"); -#ifdef MODULE_PARAM_PREFIX -#undef MODULE_PARAM_PREFIX -#endif -#define MODULE_PARAM_PREFIX "rcutorture." - -static int fqs_duration; -module_param(fqs_duration, int, 0444); -MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable"); -static int fqs_holdoff; -module_param(fqs_holdoff, int, 0444); -MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)"); -static int fqs_stutter = 3; -module_param(fqs_stutter, int, 0444); -MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)"); -static bool gp_exp; -module_param(gp_exp, bool, 0444); -MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives"); -static bool gp_normal; -module_param(gp_normal, bool, 0444); -MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives"); -static int irqreader = 1; -module_param(irqreader, int, 0444); -MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers"); -static int n_barrier_cbs; -module_param(n_barrier_cbs, int, 0444); -MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing"); -static int nfakewriters = 4; -module_param(nfakewriters, int, 0444); -MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads"); -static int nreaders = -1; -module_param(nreaders, int, 0444); -MODULE_PARM_DESC(nreaders, "Number of RCU reader threads"); -static int object_debug; -module_param(object_debug, int, 0444); -MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing"); -static int onoff_holdoff; -module_param(onoff_holdoff, int, 0444); -MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)"); -static int onoff_interval; -module_param(onoff_interval, int, 0444); -MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable"); -static int shuffle_interval = 3; -module_param(shuffle_interval, int, 0444); -MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles"); -static int shutdown_secs; -module_param(shutdown_secs, int, 0444); -MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable."); -static int stall_cpu; -module_param(stall_cpu, int, 0444); -MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable."); -static int stall_cpu_holdoff = 10; -module_param(stall_cpu_holdoff, int, 0444); -MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s)."); -static int stat_interval = 60; -module_param(stat_interval, int, 0644); -MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s"); -static int stutter = 5; -module_param(stutter, int, 0444); -MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test"); -static int test_boost = 1; -module_param(test_boost, int, 0444); -MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); -static int test_boost_duration = 4; -module_param(test_boost_duration, int, 0444); -MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds."); -static int test_boost_interval = 7; -module_param(test_boost_interval, int, 0444); -MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds."); -static bool test_no_idle_hz = true; -module_param(test_no_idle_hz, bool, 0444); -MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs"); + +torture_param(int, fqs_duration, 0, + "Duration of fqs bursts (us), 0 to disable"); +torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); +torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)"); +torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); +torture_param(bool, gp_normal, false, + "Use normal (non-expedited) GP wait primitives"); +torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers"); +torture_param(int, n_barrier_cbs, 0, + "# of callbacks/kthreads for barrier testing"); +torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads"); +torture_param(int, nreaders, -1, "Number of RCU reader threads"); +torture_param(int, object_debug, 0, + "Enable debug-object double call_rcu() testing"); +torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); +torture_param(int, onoff_interval, 0, + "Time between CPU hotplugs (s), 0=disable"); +torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); +torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); +torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); +torture_param(int, stall_cpu_holdoff, 10, + "Time to wait before starting stall (s)."); +torture_param(int, stat_interval, 60, + "Number of seconds between stats printk()s"); +torture_param(int, stutter, 5, "Number of seconds to run/halt test"); +torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); +torture_param(int, test_boost_duration, 4, + "Duration of each boost test, seconds."); +torture_param(int, test_boost_interval, 7, + "Interval between boost tests, seconds."); +torture_param(bool, test_no_idle_hz, true, + "Test support for tickless idle CPUs"); +torture_param(bool, verbose, true, + "Enable verbose debugging printk()s"); + static char *torture_type = "rcu"; module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); -static bool verbose; -module_param(verbose, bool, 0444); -MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s"); - -#define TORTURE_FLAG "-torture:" -#define PRINTK_STRING(s) \ - do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) -#define VERBOSE_PRINTK_STRING(s) \ - do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) -#define VERBOSE_PRINTK_ERRSTRING(s) \ - do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0) static int nrealreaders; static struct task_struct *writer_task; static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; -static struct task_struct *shuffler_task; -static struct task_struct *stutter_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; -static struct task_struct *shutdown_task; -#ifdef CONFIG_HOTPLUG_CPU -static struct task_struct *onoff_task; -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ static struct task_struct *stall_task; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; @@ -170,10 +118,10 @@ static struct rcu_torture __rcu *rcu_torture_current; static unsigned long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = - { 0 }; -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = - { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], + rcu_torture_count) = { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], + rcu_torture_batch) = { 0 }; static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1]; static atomic_t n_rcu_torture_alloc; static atomic_t n_rcu_torture_alloc_fail; @@ -186,22 +134,9 @@ static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; static long n_rcu_torture_timers; -static long n_offline_attempts; -static long n_offline_successes; -static unsigned long sum_offline; -static int min_offline = -1; -static int max_offline; -static long n_online_attempts; -static long n_online_successes; -static unsigned long sum_online; -static int min_online = -1; -static int max_online; static long n_barrier_attempts; static long n_barrier_successes; static struct list_head rcu_torture_removed; -static cpumask_var_t shuffle_tmp_mask; - -static int stutter_pause_test; #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) #define RCUTORTURE_RUNNABLE_INIT 1 @@ -232,7 +167,6 @@ static u64 notrace rcu_trace_clock_local(void) } #endif /* #else #ifdef CONFIG_RCU_TRACE */ -static unsigned long shutdown_time; /* jiffies to system shutdown. */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ @@ -242,51 +176,6 @@ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); -/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ - -#define FULLSTOP_DONTSTOP 0 /* Normal operation. */ -#define FULLSTOP_SHUTDOWN 1 /* System shutdown with rcutorture running. */ -#define FULLSTOP_RMMOD 2 /* Normal rmmod of rcutorture. */ -static int fullstop = FULLSTOP_RMMOD; -/* - * Protect fullstop transitions and spawning of kthreads. - */ -static DEFINE_MUTEX(fullstop_mutex); - -/* Forward reference. */ -static void rcu_torture_cleanup(void); - -/* - * Detect and respond to a system shutdown. - */ -static int -rcutorture_shutdown_notify(struct notifier_block *unused1, - unsigned long unused2, void *unused3) -{ - mutex_lock(&fullstop_mutex); - if (fullstop == FULLSTOP_DONTSTOP) - fullstop = FULLSTOP_SHUTDOWN; - else - pr_warn(/* but going down anyway, so... */ - "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); - mutex_unlock(&fullstop_mutex); - return NOTIFY_DONE; -} - -/* - * Absorb kthreads into a kernel function that won't return, so that - * they won't ever access module text or data again. - */ -static void rcutorture_shutdown_absorb(const char *title) -{ - if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { - pr_notice( - "rcutorture thread %s parking due to system shutdown\n", - title); - schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); - } -} - /* * Allocate an element from the rcu_tortures pool. */ @@ -320,44 +209,6 @@ rcu_torture_free(struct rcu_torture *p) spin_unlock_bh(&rcu_torture_lock); } -struct rcu_random_state { - unsigned long rrs_state; - long rrs_count; -}; - -#define RCU_RANDOM_MULT 39916801 /* prime */ -#define RCU_RANDOM_ADD 479001701 /* prime */ -#define RCU_RANDOM_REFRESH 10000 - -#define DEFINE_RCU_RANDOM(name) struct rcu_random_state name = { 0, 0 } - -/* - * Crude but fast random-number generator. Uses a linear congruential - * generator, with occasional help from cpu_clock(). - */ -static unsigned long -rcu_random(struct rcu_random_state *rrsp) -{ - if (--rrsp->rrs_count < 0) { - rrsp->rrs_state += (unsigned long)local_clock(); - rrsp->rrs_count = RCU_RANDOM_REFRESH; - } - rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD; - return swahw32(rrsp->rrs_state); -} - -static void -rcu_stutter_wait(const char *title) -{ - while (stutter_pause_test || !rcutorture_runnable) { - if (rcutorture_runnable) - schedule_timeout_interruptible(1); - else - schedule_timeout_interruptible(round_jiffies_relative(HZ)); - rcutorture_shutdown_absorb(title); - } -} - /* * Operations vector for selecting different types of tests. */ @@ -365,7 +216,7 @@ rcu_stutter_wait(const char *title) struct rcu_torture_ops { void (*init)(void); int (*readlock)(void); - void (*read_delay)(struct rcu_random_state *rrsp); + void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); int (*completed)(void); void (*deferred_free)(struct rcu_torture *p); @@ -392,7 +243,7 @@ static int rcu_torture_read_lock(void) __acquires(RCU) return 0; } -static void rcu_read_delay(struct rcu_random_state *rrsp) +static void rcu_read_delay(struct torture_random_state *rrsp) { const unsigned long shortdelay_us = 200; const unsigned long longdelay_ms = 50; @@ -401,12 +252,13 @@ static void rcu_read_delay(struct rcu_random_state *rrsp) * period, and we want a long delay occasionally to trigger * force_quiescent_state. */ - if (!(rcu_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) + if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) mdelay(longdelay_ms); - if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) + if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) udelay(shortdelay_us); #ifdef CONFIG_PREEMPT - if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000))) + if (!preempt_count() && + !(torture_random(rrsp) % (nrealreaders * 20000))) preempt_schedule(); /* No QS if preempt_disable() in effect */ #endif } @@ -427,7 +279,7 @@ rcu_torture_cb(struct rcu_head *p) int i; struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu); - if (fullstop != FULLSTOP_DONTSTOP) { + if (torture_must_stop_irq()) { /* Test is ending, just drop callbacks on the floor. */ /* The next initialization will pick up the pieces. */ return; @@ -520,6 +372,48 @@ static struct rcu_torture_ops rcu_bh_ops = { }; /* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! + * The only purpose of these functions is to provide a buggy RCU + * implementation to make sure that rcutorture correctly emits + * buggy-RCU error messages. + */ +static void rcu_busted_torture_deferred_free(struct rcu_torture *p) +{ + /* This is a deliberate bug for testing purposes only! */ + rcu_torture_cb(&p->rtort_rcu); +} + +static void synchronize_rcu_busted(void) +{ + /* This is a deliberate bug for testing purposes only! */ +} + +static void +call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + /* This is a deliberate bug for testing purposes only! */ + func(head); +} + +static struct rcu_torture_ops rcu_busted_ops = { + .init = rcu_sync_torture_init, + .readlock = rcu_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock, + .completed = rcu_no_completed, + .deferred_free = rcu_busted_torture_deferred_free, + .sync = synchronize_rcu_busted, + .exp_sync = synchronize_rcu_busted, + .call = call_rcu_busted, + .cb_barrier = NULL, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_busted" +}; + +/* * Definitions for srcu torture testing. */ @@ -530,7 +424,7 @@ static int srcu_torture_read_lock(void) __acquires(&srcu_ctl) return srcu_read_lock(&srcu_ctl); } -static void srcu_read_delay(struct rcu_random_state *rrsp) +static void srcu_read_delay(struct torture_random_state *rrsp) { long delay; const long uspertick = 1000000 / HZ; @@ -538,7 +432,8 @@ static void srcu_read_delay(struct rcu_random_state *rrsp) /* We want there to be long-running readers, but not all the time. */ - delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick); + delay = torture_random(rrsp) % + (nrealreaders * 2 * longdelay * uspertick); if (!delay) schedule_timeout_interruptible(longdelay); else @@ -677,12 +572,12 @@ static int rcu_torture_boost(void *arg) struct rcu_boost_inflight rbi = { .inflight = 0 }; struct sched_param sp; - VERBOSE_PRINTK_STRING("rcu_torture_boost started"); + VERBOSE_TOROUT_STRING("rcu_torture_boost started"); /* Set real-time priority. */ sp.sched_priority = 1; if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) { - VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!"); + VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!"); n_rcu_torture_boost_rterror++; } @@ -693,9 +588,8 @@ static int rcu_torture_boost(void *arg) oldstarttime = boost_starttime; while (ULONG_CMP_LT(jiffies, oldstarttime)) { schedule_timeout_interruptible(oldstarttime - jiffies); - rcu_stutter_wait("rcu_torture_boost"); - if (kthread_should_stop() || - fullstop != FULLSTOP_DONTSTOP) + stutter_wait("rcu_torture_boost"); + if (torture_must_stop()) goto checkwait; } @@ -710,15 +604,14 @@ static int rcu_torture_boost(void *arg) call_rcu(&rbi.rcu, rcu_torture_boost_cb); if (jiffies - call_rcu_time > test_boost_duration * HZ - HZ / 2) { - VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed"); + VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); n_rcu_torture_boost_failure++; } call_rcu_time = jiffies; } cond_resched(); - rcu_stutter_wait("rcu_torture_boost"); - if (kthread_should_stop() || - fullstop != FULLSTOP_DONTSTOP) + stutter_wait("rcu_torture_boost"); + if (torture_must_stop()) goto checkwait; } @@ -742,16 +635,17 @@ static int rcu_torture_boost(void *arg) } /* Go do the stutter. */ -checkwait: rcu_stutter_wait("rcu_torture_boost"); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); +checkwait: stutter_wait("rcu_torture_boost"); + } while (!torture_must_stop()); /* Clean up and exit. */ - VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping"); - rcutorture_shutdown_absorb("rcu_torture_boost"); - while (!kthread_should_stop() || rbi.inflight) + while (!kthread_should_stop() || rbi.inflight) { + torture_shutdown_absorb("rcu_torture_boost"); schedule_timeout_uninterruptible(1); + } smp_mb(); /* order accesses to ->inflight before stack-frame death. */ destroy_rcu_head_on_stack(&rbi.rcu); + torture_kthread_stopping("rcu_torture_boost"); return 0; } @@ -766,7 +660,7 @@ rcu_torture_fqs(void *arg) unsigned long fqs_resume_time; int fqs_burst_remaining; - VERBOSE_PRINTK_STRING("rcu_torture_fqs task started"); + VERBOSE_TOROUT_STRING("rcu_torture_fqs task started"); do { fqs_resume_time = jiffies + fqs_stutter * HZ; while (ULONG_CMP_LT(jiffies, fqs_resume_time) && @@ -780,12 +674,9 @@ rcu_torture_fqs(void *arg) udelay(fqs_holdoff); fqs_burst_remaining -= fqs_holdoff; } - rcu_stutter_wait("rcu_torture_fqs"); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); - VERBOSE_PRINTK_STRING("rcu_torture_fqs task stopping"); - rcutorture_shutdown_absorb("rcu_torture_fqs"); - while (!kthread_should_stop()) - schedule_timeout_uninterruptible(1); + stutter_wait("rcu_torture_fqs"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_fqs"); return 0; } @@ -802,10 +693,10 @@ rcu_torture_writer(void *arg) struct rcu_torture *rp; struct rcu_torture *rp1; struct rcu_torture *old_rp; - static DEFINE_RCU_RANDOM(rand); + static DEFINE_TORTURE_RANDOM(rand); - VERBOSE_PRINTK_STRING("rcu_torture_writer task started"); - set_user_nice(current, 19); + VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); + set_user_nice(current, MAX_NICE); do { schedule_timeout_uninterruptible(1); @@ -813,7 +704,7 @@ rcu_torture_writer(void *arg) if (rp == NULL) continue; rp->rtort_pipe_count = 0; - udelay(rcu_random(&rand) & 0x3ff); + udelay(torture_random(&rand) & 0x3ff); old_rp = rcu_dereference_check(rcu_torture_current, current == writer_task); rp->rtort_mbtest = 1; @@ -826,7 +717,7 @@ rcu_torture_writer(void *arg) atomic_inc(&rcu_torture_wcount[i]); old_rp->rtort_pipe_count++; if (gp_normal == gp_exp) - exp = !!(rcu_random(&rand) & 0x80); + exp = !!(torture_random(&rand) & 0x80); else exp = gp_exp; if (!exp) { @@ -852,12 +743,9 @@ rcu_torture_writer(void *arg) } } rcutorture_record_progress(++rcu_torture_current_version); - rcu_stutter_wait("rcu_torture_writer"); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); - VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping"); - rcutorture_shutdown_absorb("rcu_torture_writer"); - while (!kthread_should_stop()) - schedule_timeout_uninterruptible(1); + stutter_wait("rcu_torture_writer"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_writer"); return 0; } @@ -868,19 +756,19 @@ rcu_torture_writer(void *arg) static int rcu_torture_fakewriter(void *arg) { - DEFINE_RCU_RANDOM(rand); + DEFINE_TORTURE_RANDOM(rand); - VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task started"); - set_user_nice(current, 19); + VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started"); + set_user_nice(current, MAX_NICE); do { - schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); - udelay(rcu_random(&rand) & 0x3ff); + schedule_timeout_uninterruptible(1 + torture_random(&rand)%10); + udelay(torture_random(&rand) & 0x3ff); if (cur_ops->cb_barrier != NULL && - rcu_random(&rand) % (nfakewriters * 8) == 0) { + torture_random(&rand) % (nfakewriters * 8) == 0) { cur_ops->cb_barrier(); } else if (gp_normal == gp_exp) { - if (rcu_random(&rand) & 0x80) + if (torture_random(&rand) & 0x80) cur_ops->sync(); else cur_ops->exp_sync(); @@ -889,13 +777,10 @@ rcu_torture_fakewriter(void *arg) } else { cur_ops->exp_sync(); } - rcu_stutter_wait("rcu_torture_fakewriter"); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); + stutter_wait("rcu_torture_fakewriter"); + } while (!torture_must_stop()); - VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping"); - rcutorture_shutdown_absorb("rcu_torture_fakewriter"); - while (!kthread_should_stop()) - schedule_timeout_uninterruptible(1); + torture_kthread_stopping("rcu_torture_fakewriter"); return 0; } @@ -921,7 +806,7 @@ static void rcu_torture_timer(unsigned long unused) int idx; int completed; int completed_end; - static DEFINE_RCU_RANDOM(rand); + static DEFINE_TORTURE_RANDOM(rand); static DEFINE_SPINLOCK(rand_lock); struct rcu_torture *p; int pipe_count; @@ -980,14 +865,14 @@ rcu_torture_reader(void *arg) int completed; int completed_end; int idx; - DEFINE_RCU_RANDOM(rand); + DEFINE_TORTURE_RANDOM(rand); struct rcu_torture *p; int pipe_count; struct timer_list t; unsigned long long ts; - VERBOSE_PRINTK_STRING("rcu_torture_reader task started"); - set_user_nice(current, 19); + VERBOSE_TOROUT_STRING("rcu_torture_reader task started"); + set_user_nice(current, MAX_NICE); if (irqreader && cur_ops->irq_capable) setup_timer_on_stack(&t, rcu_torture_timer, 0); @@ -1034,14 +919,11 @@ rcu_torture_reader(void *arg) preempt_enable(); cur_ops->readunlock(idx); schedule(); - rcu_stutter_wait("rcu_torture_reader"); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); - VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping"); - rcutorture_shutdown_absorb("rcu_torture_reader"); + stutter_wait("rcu_torture_reader"); + } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) del_timer_sync(&t); - while (!kthread_should_stop()) - schedule_timeout_uninterruptible(1); + torture_kthread_stopping("rcu_torture_reader"); return 0; } @@ -1083,13 +965,7 @@ rcu_torture_printk(char *page) n_rcu_torture_boost_failure, n_rcu_torture_boosts, n_rcu_torture_timers); - page += sprintf(page, - "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", - n_online_successes, n_online_attempts, - n_offline_successes, n_offline_attempts, - min_online, max_online, - min_offline, max_offline, - sum_online, sum_offline, HZ); + page = torture_onoff_stats(page); page += sprintf(page, "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, @@ -1150,123 +1026,17 @@ rcu_torture_stats_print(void) /* * Periodically prints torture statistics, if periodic statistics printing * was specified via the stat_interval module parameter. - * - * No need to worry about fullstop here, since this one doesn't reference - * volatile state or register callbacks. */ static int rcu_torture_stats(void *arg) { - VERBOSE_PRINTK_STRING("rcu_torture_stats task started"); + VERBOSE_TOROUT_STRING("rcu_torture_stats task started"); do { schedule_timeout_interruptible(stat_interval * HZ); rcu_torture_stats_print(); - rcutorture_shutdown_absorb("rcu_torture_stats"); - } while (!kthread_should_stop()); - VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping"); - return 0; -} - -static int rcu_idle_cpu; /* Force all torture tasks off this CPU */ - -/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case - * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs. - */ -static void rcu_torture_shuffle_tasks(void) -{ - int i; - - cpumask_setall(shuffle_tmp_mask); - get_online_cpus(); - - /* No point in shuffling if there is only one online CPU (ex: UP) */ - if (num_online_cpus() == 1) { - put_online_cpus(); - return; - } - - if (rcu_idle_cpu != -1) - cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask); - - set_cpus_allowed_ptr(current, shuffle_tmp_mask); - - if (reader_tasks) { - for (i = 0; i < nrealreaders; i++) - if (reader_tasks[i]) - set_cpus_allowed_ptr(reader_tasks[i], - shuffle_tmp_mask); - } - if (fakewriter_tasks) { - for (i = 0; i < nfakewriters; i++) - if (fakewriter_tasks[i]) - set_cpus_allowed_ptr(fakewriter_tasks[i], - shuffle_tmp_mask); - } - if (writer_task) - set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask); - if (stats_task) - set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask); - if (stutter_task) - set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask); - if (fqs_task) - set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask); - if (shutdown_task) - set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask); -#ifdef CONFIG_HOTPLUG_CPU - if (onoff_task) - set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - if (stall_task) - set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask); - if (barrier_cbs_tasks) - for (i = 0; i < n_barrier_cbs; i++) - if (barrier_cbs_tasks[i]) - set_cpus_allowed_ptr(barrier_cbs_tasks[i], - shuffle_tmp_mask); - if (barrier_task) - set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask); - - if (rcu_idle_cpu == -1) - rcu_idle_cpu = num_online_cpus() - 1; - else - rcu_idle_cpu--; - - put_online_cpus(); -} - -/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the - * system to become idle at a time and cut off its timer ticks. This is meant - * to test the support for such tickless idle CPU in RCU. - */ -static int -rcu_torture_shuffle(void *arg) -{ - VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started"); - do { - schedule_timeout_interruptible(shuffle_interval * HZ); - rcu_torture_shuffle_tasks(); - rcutorture_shutdown_absorb("rcu_torture_shuffle"); - } while (!kthread_should_stop()); - VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping"); - return 0; -} - -/* Cause the rcutorture test to "stutter", starting and stopping all - * threads periodically. - */ -static int -rcu_torture_stutter(void *arg) -{ - VERBOSE_PRINTK_STRING("rcu_torture_stutter task started"); - do { - schedule_timeout_interruptible(stutter * HZ); - stutter_pause_test = 1; - if (!kthread_should_stop()) - schedule_timeout_interruptible(stutter * HZ); - stutter_pause_test = 0; - rcutorture_shutdown_absorb("rcu_torture_stutter"); - } while (!kthread_should_stop()); - VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping"); + torture_shutdown_absorb("rcu_torture_stats"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_stats"); return 0; } @@ -1293,10 +1063,6 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) onoff_interval, onoff_holdoff); } -static struct notifier_block rcutorture_shutdown_nb = { - .notifier_call = rcutorture_shutdown_notify, -}; - static void rcutorture_booster_cleanup(int cpu) { struct task_struct *t; @@ -1304,14 +1070,12 @@ static void rcutorture_booster_cleanup(int cpu) if (boost_tasks[cpu] == NULL) return; mutex_lock(&boost_mutex); - VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task"); t = boost_tasks[cpu]; boost_tasks[cpu] = NULL; mutex_unlock(&boost_mutex); /* This must be outside of the mutex, otherwise deadlock! */ - kthread_stop(t); - boost_tasks[cpu] = NULL; + torture_stop_kthread(rcu_torture_boost, t); } static int rcutorture_booster_init(int cpu) @@ -1323,13 +1087,13 @@ static int rcutorture_booster_init(int cpu) /* Don't allow time recalculation while creating a new task. */ mutex_lock(&boost_mutex); - VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task"); + VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, cpu_to_node(cpu), "rcu_torture_boost"); if (IS_ERR(boost_tasks[cpu])) { retval = PTR_ERR(boost_tasks[cpu]); - VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed"); + VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed"); n_rcu_torture_boost_ktrerror++; boost_tasks[cpu] = NULL; mutex_unlock(&boost_mutex); @@ -1342,175 +1106,6 @@ static int rcutorture_booster_init(int cpu) } /* - * Cause the rcutorture test to shutdown the system after the test has - * run for the time specified by the shutdown_secs module parameter. - */ -static int -rcu_torture_shutdown(void *arg) -{ - long delta; - unsigned long jiffies_snap; - - VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started"); - jiffies_snap = ACCESS_ONCE(jiffies); - while (ULONG_CMP_LT(jiffies_snap, shutdown_time) && - !kthread_should_stop()) { - delta = shutdown_time - jiffies_snap; - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu jiffies remaining\n", - torture_type, delta); - schedule_timeout_interruptible(delta); - jiffies_snap = ACCESS_ONCE(jiffies); - } - if (kthread_should_stop()) { - VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping"); - return 0; - } - - /* OK, shut down the system. */ - - VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system"); - shutdown_task = NULL; /* Avoid self-kill deadlock. */ - rcu_torture_cleanup(); /* Get the success/failure message. */ - kernel_power_off(); /* Shut down the system. */ - return 0; -} - -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Execute random CPU-hotplug operations at the interval specified - * by the onoff_interval. - */ -static int -rcu_torture_onoff(void *arg) -{ - int cpu; - unsigned long delta; - int maxcpu = -1; - DEFINE_RCU_RANDOM(rand); - int ret; - unsigned long starttime; - - VERBOSE_PRINTK_STRING("rcu_torture_onoff task started"); - for_each_online_cpu(cpu) - maxcpu = cpu; - WARN_ON(maxcpu < 0); - if (onoff_holdoff > 0) { - VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff"); - schedule_timeout_interruptible(onoff_holdoff * HZ); - VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff"); - } - while (!kthread_should_stop()) { - cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); - if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: offlining %d\n", - torture_type, cpu); - starttime = jiffies; - n_offline_attempts++; - ret = cpu_down(cpu); - if (ret) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: offline %d failed: errno %d\n", - torture_type, cpu, ret); - } else { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: offlined %d\n", - torture_type, cpu); - n_offline_successes++; - delta = jiffies - starttime; - sum_offline += delta; - if (min_offline < 0) { - min_offline = delta; - max_offline = delta; - } - if (min_offline > delta) - min_offline = delta; - if (max_offline < delta) - max_offline = delta; - } - } else if (cpu_is_hotpluggable(cpu)) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: onlining %d\n", - torture_type, cpu); - starttime = jiffies; - n_online_attempts++; - ret = cpu_up(cpu); - if (ret) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: online %d failed: errno %d\n", - torture_type, cpu, ret); - } else { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "rcu_torture_onoff task: onlined %d\n", - torture_type, cpu); - n_online_successes++; - delta = jiffies - starttime; - sum_online += delta; - if (min_online < 0) { - min_online = delta; - max_online = delta; - } - if (min_online > delta) - min_online = delta; - if (max_online < delta) - max_online = delta; - } - } - schedule_timeout_interruptible(onoff_interval * HZ); - } - VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping"); - return 0; -} - -static int -rcu_torture_onoff_init(void) -{ - int ret; - - if (onoff_interval <= 0) - return 0; - onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff"); - if (IS_ERR(onoff_task)) { - ret = PTR_ERR(onoff_task); - onoff_task = NULL; - return ret; - } - return 0; -} - -static void rcu_torture_onoff_cleanup(void) -{ - if (onoff_task == NULL) - return; - VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task"); - kthread_stop(onoff_task); - onoff_task = NULL; -} - -#else /* #ifdef CONFIG_HOTPLUG_CPU */ - -static int -rcu_torture_onoff_init(void) -{ - return 0; -} - -static void rcu_torture_onoff_cleanup(void) -{ -} - -#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ - -/* * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then * induces a CPU stall for the time specified by stall_cpu. */ @@ -1518,11 +1113,11 @@ static int rcu_torture_stall(void *args) { unsigned long stop_at; - VERBOSE_PRINTK_STRING("rcu_torture_stall task started"); + VERBOSE_TOROUT_STRING("rcu_torture_stall task started"); if (stall_cpu_holdoff > 0) { - VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff"); + VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff"); schedule_timeout_interruptible(stall_cpu_holdoff * HZ); - VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff"); + VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff"); } if (!kthread_should_stop()) { stop_at = get_seconds() + stall_cpu; @@ -1536,7 +1131,7 @@ static int rcu_torture_stall(void *args) rcu_read_unlock(); pr_alert("rcu_torture_stall end.\n"); } - rcutorture_shutdown_absorb("rcu_torture_stall"); + torture_shutdown_absorb("rcu_torture_stall"); while (!kthread_should_stop()) schedule_timeout_interruptible(10 * HZ); return 0; @@ -1545,27 +1140,9 @@ static int rcu_torture_stall(void *args) /* Spawn CPU-stall kthread, if stall_cpu specified. */ static int __init rcu_torture_stall_init(void) { - int ret; - if (stall_cpu <= 0) return 0; - stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall"); - if (IS_ERR(stall_task)) { - ret = PTR_ERR(stall_task); - stall_task = NULL; - return ret; - } - return 0; -} - -/* Clean up after the CPU-stall kthread, if one was spawned. */ -static void rcu_torture_stall_cleanup(void) -{ - if (stall_task == NULL) - return; - VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task."); - kthread_stop(stall_task); - stall_task = NULL; + return torture_create_kthread(rcu_torture_stall, NULL, stall_task); } /* Callback function for RCU barrier testing. */ @@ -1583,28 +1160,24 @@ static int rcu_torture_barrier_cbs(void *arg) struct rcu_head rcu; init_rcu_head_on_stack(&rcu); - VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started"); - set_user_nice(current, 19); + VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started"); + set_user_nice(current, MAX_NICE); do { wait_event(barrier_cbs_wq[myid], (newphase = ACCESS_ONCE(barrier_phase)) != lastphase || - kthread_should_stop() || - fullstop != FULLSTOP_DONTSTOP); + torture_must_stop()); lastphase = newphase; smp_mb(); /* ensure barrier_phase load before ->call(). */ - if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) + if (torture_must_stop()) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); - VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); - while (!kthread_should_stop()) - schedule_timeout_interruptible(1); + } while (!torture_must_stop()); cur_ops->cb_barrier(); destroy_rcu_head_on_stack(&rcu); + torture_kthread_stopping("rcu_torture_barrier_cbs"); return 0; } @@ -1613,7 +1186,7 @@ static int rcu_torture_barrier(void *arg) { int i; - VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting"); + VERBOSE_TOROUT_STRING("rcu_torture_barrier task starting"); do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); @@ -1623,9 +1196,8 @@ static int rcu_torture_barrier(void *arg) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, atomic_read(&barrier_cbs_count) == 0 || - kthread_should_stop() || - fullstop != FULLSTOP_DONTSTOP); - if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) + torture_must_stop()); + if (torture_must_stop()) break; n_barrier_attempts++; cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */ @@ -1635,11 +1207,8 @@ static int rcu_torture_barrier(void *arg) } n_barrier_successes++; schedule_timeout_interruptible(HZ / 10); - } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); - VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier"); - while (!kthread_should_stop()) - schedule_timeout_interruptible(1); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_barrier"); return 0; } @@ -1672,24 +1241,13 @@ static int rcu_torture_barrier_init(void) return -ENOMEM; for (i = 0; i < n_barrier_cbs; i++) { init_waitqueue_head(&barrier_cbs_wq[i]); - barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs, - (void *)(long)i, - "rcu_torture_barrier_cbs"); - if (IS_ERR(barrier_cbs_tasks[i])) { - ret = PTR_ERR(barrier_cbs_tasks[i]); - VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs"); - barrier_cbs_tasks[i] = NULL; + ret = torture_create_kthread(rcu_torture_barrier_cbs, + (void *)(long)i, + barrier_cbs_tasks[i]); + if (ret) return ret; - } } - barrier_task = kthread_run(rcu_torture_barrier, NULL, - "rcu_torture_barrier"); - if (IS_ERR(barrier_task)) { - ret = PTR_ERR(barrier_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier"); - barrier_task = NULL; - } - return 0; + return torture_create_kthread(rcu_torture_barrier, NULL, barrier_task); } /* Clean up after RCU barrier testing. */ @@ -1697,19 +1255,11 @@ static void rcu_torture_barrier_cleanup(void) { int i; - if (barrier_task != NULL) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task"); - kthread_stop(barrier_task); - barrier_task = NULL; - } + torture_stop_kthread(rcu_torture_barrier, barrier_task); if (barrier_cbs_tasks != NULL) { - for (i = 0; i < n_barrier_cbs; i++) { - if (barrier_cbs_tasks[i] != NULL) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task"); - kthread_stop(barrier_cbs_tasks[i]); - barrier_cbs_tasks[i] = NULL; - } - } + for (i = 0; i < n_barrier_cbs; i++) + torture_stop_kthread(rcu_torture_barrier_cbs, + barrier_cbs_tasks[i]); kfree(barrier_cbs_tasks); barrier_cbs_tasks = NULL; } @@ -1747,90 +1297,42 @@ rcu_torture_cleanup(void) { int i; - mutex_lock(&fullstop_mutex); rcutorture_record_test_transition(); - if (fullstop == FULLSTOP_SHUTDOWN) { - pr_warn(/* but going down anyway, so... */ - "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); - mutex_unlock(&fullstop_mutex); - schedule_timeout_uninterruptible(10); + if (torture_cleanup()) { if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); return; } - fullstop = FULLSTOP_RMMOD; - mutex_unlock(&fullstop_mutex); - unregister_reboot_notifier(&rcutorture_shutdown_nb); - rcu_torture_barrier_cleanup(); - rcu_torture_stall_cleanup(); - if (stutter_task) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); - kthread_stop(stutter_task); - } - stutter_task = NULL; - if (shuffler_task) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task"); - kthread_stop(shuffler_task); - free_cpumask_var(shuffle_tmp_mask); - } - shuffler_task = NULL; - if (writer_task) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task"); - kthread_stop(writer_task); - } - writer_task = NULL; + rcu_torture_barrier_cleanup(); + torture_stop_kthread(rcu_torture_stall, stall_task); + torture_stop_kthread(rcu_torture_writer, writer_task); if (reader_tasks) { - for (i = 0; i < nrealreaders; i++) { - if (reader_tasks[i]) { - VERBOSE_PRINTK_STRING( - "Stopping rcu_torture_reader task"); - kthread_stop(reader_tasks[i]); - } - reader_tasks[i] = NULL; - } + for (i = 0; i < nrealreaders; i++) + torture_stop_kthread(rcu_torture_reader, + reader_tasks[i]); kfree(reader_tasks); - reader_tasks = NULL; } rcu_torture_current = NULL; if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) { - if (fakewriter_tasks[i]) { - VERBOSE_PRINTK_STRING( - "Stopping rcu_torture_fakewriter task"); - kthread_stop(fakewriter_tasks[i]); - } - fakewriter_tasks[i] = NULL; + torture_stop_kthread(rcu_torture_fakewriter, + fakewriter_tasks[i]); } kfree(fakewriter_tasks); fakewriter_tasks = NULL; } - if (stats_task) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task"); - kthread_stop(stats_task); - } - stats_task = NULL; - - if (fqs_task) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_fqs task"); - kthread_stop(fqs_task); - } - fqs_task = NULL; + torture_stop_kthread(rcu_torture_stats, stats_task); + torture_stop_kthread(rcu_torture_fqs, fqs_task); if ((test_boost == 1 && cur_ops->can_boost) || test_boost == 2) { unregister_cpu_notifier(&rcutorture_cpu_nb); for_each_possible_cpu(i) rcutorture_booster_cleanup(i); } - if (shutdown_task != NULL) { - VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task"); - kthread_stop(shutdown_task); - } - shutdown_task = NULL; - rcu_torture_onoff_cleanup(); /* Wait for all RCU callbacks to fire. */ @@ -1841,8 +1343,7 @@ rcu_torture_cleanup(void) if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); - else if (n_online_successes != n_online_attempts || - n_offline_successes != n_offline_attempts) + else if (torture_onoff_failures()) rcu_torture_print_module_parms(cur_ops, "End of test: RCU_HOTPLUG"); else @@ -1911,12 +1412,11 @@ rcu_torture_init(void) int i; int cpu; int firsterr = 0; - int retval; static struct rcu_torture_ops *torture_ops[] = { - &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops, + &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, }; - mutex_lock(&fullstop_mutex); + torture_init_begin(torture_type, verbose, &rcutorture_runnable); /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { @@ -1931,7 +1431,7 @@ rcu_torture_init(void) for (i = 0; i < ARRAY_SIZE(torture_ops); i++) pr_alert(" %s", torture_ops[i]->name); pr_alert("\n"); - mutex_unlock(&fullstop_mutex); + torture_init_end(); return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { @@ -1946,7 +1446,6 @@ rcu_torture_init(void) else nrealreaders = 2 * num_online_cpus(); rcu_torture_print_module_parms(cur_ops, "Start of test"); - fullstop = FULLSTOP_DONTSTOP; /* Set up the freelist. */ @@ -1982,108 +1481,61 @@ rcu_torture_init(void) /* Start up the kthreads. */ - VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task"); - writer_task = kthread_create(rcu_torture_writer, NULL, - "rcu_torture_writer"); - if (IS_ERR(writer_task)) { - firsterr = PTR_ERR(writer_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create writer"); - writer_task = NULL; + firsterr = torture_create_kthread(rcu_torture_writer, NULL, + writer_task); + if (firsterr) goto unwind; - } - wake_up_process(writer_task); fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]), GFP_KERNEL); if (fakewriter_tasks == NULL) { - VERBOSE_PRINTK_ERRSTRING("out of memory"); + VERBOSE_TOROUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } for (i = 0; i < nfakewriters; i++) { - VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task"); - fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL, - "rcu_torture_fakewriter"); - if (IS_ERR(fakewriter_tasks[i])) { - firsterr = PTR_ERR(fakewriter_tasks[i]); - VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter"); - fakewriter_tasks[i] = NULL; + firsterr = torture_create_kthread(rcu_torture_fakewriter, + NULL, fakewriter_tasks[i]); + if (firsterr) goto unwind; - } } reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { - VERBOSE_PRINTK_ERRSTRING("out of memory"); + VERBOSE_TOROUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } for (i = 0; i < nrealreaders; i++) { - VERBOSE_PRINTK_STRING("Creating rcu_torture_reader task"); - reader_tasks[i] = kthread_run(rcu_torture_reader, NULL, - "rcu_torture_reader"); - if (IS_ERR(reader_tasks[i])) { - firsterr = PTR_ERR(reader_tasks[i]); - VERBOSE_PRINTK_ERRSTRING("Failed to create reader"); - reader_tasks[i] = NULL; + firsterr = torture_create_kthread(rcu_torture_reader, NULL, + reader_tasks[i]); + if (firsterr) goto unwind; - } } if (stat_interval > 0) { - VERBOSE_PRINTK_STRING("Creating rcu_torture_stats task"); - stats_task = kthread_run(rcu_torture_stats, NULL, - "rcu_torture_stats"); - if (IS_ERR(stats_task)) { - firsterr = PTR_ERR(stats_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create stats"); - stats_task = NULL; + firsterr = torture_create_kthread(rcu_torture_stats, NULL, + stats_task); + if (firsterr) goto unwind; - } } if (test_no_idle_hz) { - rcu_idle_cpu = num_online_cpus() - 1; - - if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) { - firsterr = -ENOMEM; - VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask"); - goto unwind; - } - - /* Create the shuffler thread */ - shuffler_task = kthread_run(rcu_torture_shuffle, NULL, - "rcu_torture_shuffle"); - if (IS_ERR(shuffler_task)) { - free_cpumask_var(shuffle_tmp_mask); - firsterr = PTR_ERR(shuffler_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler"); - shuffler_task = NULL; + firsterr = torture_shuffle_init(shuffle_interval * HZ); + if (firsterr) goto unwind; - } } if (stutter < 0) stutter = 0; if (stutter) { - /* Create the stutter thread */ - stutter_task = kthread_run(rcu_torture_stutter, NULL, - "rcu_torture_stutter"); - if (IS_ERR(stutter_task)) { - firsterr = PTR_ERR(stutter_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create stutter"); - stutter_task = NULL; + firsterr = torture_stutter_init(stutter * HZ); + if (firsterr) goto unwind; - } } if (fqs_duration < 0) fqs_duration = 0; if (fqs_duration) { - /* Create the stutter thread */ - fqs_task = kthread_run(rcu_torture_fqs, NULL, - "rcu_torture_fqs"); - if (IS_ERR(fqs_task)) { - firsterr = PTR_ERR(fqs_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create fqs"); - fqs_task = NULL; + /* Create the fqs thread */ + torture_create_kthread(rcu_torture_fqs, NULL, fqs_task); + if (firsterr) goto unwind; - } } if (test_boost_interval < 1) test_boost_interval = 1; @@ -2097,49 +1549,31 @@ rcu_torture_init(void) for_each_possible_cpu(i) { if (cpu_is_offline(i)) continue; /* Heuristic: CPU can go offline. */ - retval = rcutorture_booster_init(i); - if (retval < 0) { - firsterr = retval; + firsterr = rcutorture_booster_init(i); + if (firsterr) goto unwind; - } } } - if (shutdown_secs > 0) { - shutdown_time = jiffies + shutdown_secs * HZ; - shutdown_task = kthread_create(rcu_torture_shutdown, NULL, - "rcu_torture_shutdown"); - if (IS_ERR(shutdown_task)) { - firsterr = PTR_ERR(shutdown_task); - VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown"); - shutdown_task = NULL; - goto unwind; - } - wake_up_process(shutdown_task); - } - i = rcu_torture_onoff_init(); - if (i != 0) { - firsterr = i; + firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); + if (firsterr) goto unwind; - } - register_reboot_notifier(&rcutorture_shutdown_nb); - i = rcu_torture_stall_init(); - if (i != 0) { - firsterr = i; + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); + if (firsterr) goto unwind; - } - retval = rcu_torture_barrier_init(); - if (retval != 0) { - firsterr = retval; + firsterr = rcu_torture_stall_init(); + if (firsterr) + goto unwind; + firsterr = rcu_torture_barrier_init(); + if (firsterr) goto unwind; - } if (object_debug) rcu_test_debug_objects(); rcutorture_record_test_transition(); - mutex_unlock(&fullstop_mutex); + torture_init_end(); return 0; unwind: - mutex_unlock(&fullstop_mutex); + torture_init_end(); rcu_torture_cleanup(); return firsterr; } diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index 3318d8284384..c639556f3fa0 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 @@ -36,8 +36,6 @@ #include <linux/delay.h> #include <linux/srcu.h> -#include <trace/events/rcu.h> - #include "rcu.h" /* @@ -398,7 +396,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, rcu_batch_queue(&sp->batch_queue, head); if (!sp->running) { sp->running = true; - schedule_delayed_work(&sp->work, 0); + queue_delayed_work(system_power_efficient_wq, &sp->work, 0); } spin_unlock_irqrestore(&sp->queue_lock, flags); } @@ -674,7 +672,8 @@ static void srcu_reschedule(struct srcu_struct *sp) } if (pending) - schedule_delayed_work(&sp->work, SRCU_INTERVAL); + queue_delayed_work(system_power_efficient_wq, + &sp->work, SRCU_INTERVAL); } /* diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 1254f312d024..d9efcc13008c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * @@ -37,10 +37,6 @@ #include <linux/prefetch.h> #include <linux/ftrace_event.h> -#ifdef CONFIG_RCU_TRACE -#include <trace/events/rcu.h> -#endif /* #else #ifdef CONFIG_RCU_TRACE */ - #include "rcu.h" /* Forward declarations for tiny_plugin.h. */ diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 280d06cae352..431528520562 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -14,8 +14,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright (c) 2010 Linaro * diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b3d116cd072d..0c47e300210a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * @@ -58,8 +58,6 @@ #include <linux/suspend.h> #include "tree.h" -#include <trace/events/rcu.h> - #include "rcu.h" MODULE_ALIAS("rcutree"); @@ -837,7 +835,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, * to the next. Only do this for the primary flavor of RCU. */ if (rdp->rsp == rcu_state && - ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) { + ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { rdp->rsp->jiffies_resched += 5; resched_cpu(rdp->cpu); } @@ -847,7 +845,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, static void record_gp_stall_check_time(struct rcu_state *rsp) { - unsigned long j = ACCESS_ONCE(jiffies); + unsigned long j = jiffies; unsigned long j1; rsp->gp_start = j; @@ -1005,7 +1003,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp)) return; - j = ACCESS_ONCE(jiffies); + j = jiffies; /* * Lots of memory barriers to reject false positives. @@ -1423,13 +1421,14 @@ static int rcu_gp_init(struct rcu_state *rsp) /* Advance to a new grace period and initialize state. */ record_gp_stall_check_time(rsp); - smp_wmb(); /* Record GP times before starting GP. */ - rsp->gpnum++; + /* Record GP times before starting GP, hence smp_store_release(). */ + smp_store_release(&rsp->gpnum, rsp->gpnum + 1); trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); raw_spin_unlock_irq(&rnp->lock); /* Exclude any concurrent CPU-hotplug operations. */ mutex_lock(&rsp->onoff_mutex); + smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */ /* * Set the quiescent-state-needed bits in all the rcu_node @@ -1557,10 +1556,11 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) } rnp = rcu_get_root(rsp); raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */ rcu_nocb_gp_set(rnp, nocb); - rsp->completed = rsp->gpnum; /* Declare grace period done. */ + /* Declare grace period done. */ + ACCESS_ONCE(rsp->completed) = rsp->gpnum; trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); rsp->fqs_state = RCU_GP_IDLE; rdp = this_cpu_ptr(rsp->rda); @@ -2304,7 +2304,7 @@ static void force_quiescent_state(struct rcu_state *rsp) if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); if (ret) { - rsp->n_force_qs_lh++; + ACCESS_ONCE(rsp->n_force_qs_lh)++; return; } rnp_old = rnp; @@ -2316,7 +2316,7 @@ static void force_quiescent_state(struct rcu_state *rsp) smp_mb__after_unlock_lock(); raw_spin_unlock(&rnp_old->fqslock); if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { - rsp->n_force_qs_lh++; + ACCESS_ONCE(rsp->n_force_qs_lh)++; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } @@ -2639,6 +2639,58 @@ void synchronize_rcu_bh(void) } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +/** + * get_state_synchronize_rcu - Snapshot current RCU state + * + * Returns a cookie that is used by a later call to cond_synchronize_rcu() + * to determine whether or not a full grace period has elapsed in the + * meantime. + */ +unsigned long get_state_synchronize_rcu(void) +{ + /* + * Any prior manipulation of RCU-protected data must happen + * before the load from ->gpnum. + */ + smp_mb(); /* ^^^ */ + + /* + * Make sure this load happens before the purportedly + * time-consuming work between get_state_synchronize_rcu() + * and cond_synchronize_rcu(). + */ + return smp_load_acquire(&rcu_state->gpnum); +} +EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); + +/** + * cond_synchronize_rcu - Conditionally wait for an RCU grace period + * + * @oldstate: return value from earlier call to get_state_synchronize_rcu() + * + * If a full RCU grace period has elapsed since the earlier call to + * get_state_synchronize_rcu(), just return. Otherwise, invoke + * synchronize_rcu() to wait for a full grace period. + * + * Yes, this function does not take counter wrap into account. But + * counter wrap is harmless. If the counter wraps, we have waited for + * more than 2 billion grace periods (and way more on a 64-bit system!), + * so waiting for one additional grace period should be just fine. + */ +void cond_synchronize_rcu(unsigned long oldstate) +{ + unsigned long newstate; + + /* + * Ensure that this load happens before any RCU-destructive + * actions the caller might carry out after we return. + */ + newstate = smp_load_acquire(&rcu_state->completed); + if (ULONG_CMP_GE(oldstate, newstate)) + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(cond_synchronize_rcu); + static int synchronize_sched_expedited_cpu_stop(void *data) { /* @@ -2880,7 +2932,7 @@ static int rcu_pending(int cpu) * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) */ -static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy) +static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy) { bool al = true; bool hc = false; diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 8c19873f1ac9..75dc3c39a02a 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -13,8 +13,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6e2ef4b2b920..962d1d589929 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -14,8 +14,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright Red Hat, 2009 * Copyright IBM Corporation, 2009 @@ -1586,11 +1586,13 @@ static void rcu_prepare_kthreads(int cpu) * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs * any flavor of RCU. */ +#ifndef CONFIG_RCU_NOCB_CPU_ALL int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) { *delta_jiffies = ULONG_MAX; return rcu_cpu_has_callbacks(cpu, NULL); } +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up @@ -1656,7 +1658,7 @@ extern int tick_nohz_active; * only if it has been awhile since the last time we did so. Afterwards, * if there are any callbacks ready for immediate invocation, return true. */ -static bool rcu_try_advance_all_cbs(void) +static bool __maybe_unused rcu_try_advance_all_cbs(void) { bool cbs_ready = false; struct rcu_data *rdp; @@ -1696,6 +1698,7 @@ static bool rcu_try_advance_all_cbs(void) * * The caller must have disabled interrupts. */ +#ifndef CONFIG_RCU_NOCB_CPU_ALL int rcu_needs_cpu(int cpu, unsigned long *dj) { struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); @@ -1726,6 +1729,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) } return 0; } +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Prepare a CPU for idle from an RCU perspective. The first major task @@ -1739,6 +1743,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) */ static void rcu_prepare_for_idle(int cpu) { +#ifndef CONFIG_RCU_NOCB_CPU_ALL struct rcu_data *rdp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); struct rcu_node *rnp; @@ -1790,6 +1795,7 @@ static void rcu_prepare_for_idle(int cpu) rcu_accelerate_cbs(rsp, rnp, rdp); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } /* @@ -1799,11 +1805,12 @@ static void rcu_prepare_for_idle(int cpu) */ static void rcu_cleanup_after_idle(int cpu) { - +#ifndef CONFIG_RCU_NOCB_CPU_ALL if (rcu_is_nocb_cpu(cpu)) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } /* @@ -2101,6 +2108,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_waitqueue_head(&rnp->nocb_gp_wq[1]); } +#ifndef CONFIG_RCU_NOCB_CPU_ALL /* Is the specified CPU a no-CPUs CPU? */ bool rcu_is_nocb_cpu(int cpu) { @@ -2108,6 +2116,7 @@ bool rcu_is_nocb_cpu(int cpu) return cpumask_test_cpu(cpu, rcu_nocb_mask); return false; } +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Enqueue the specified string of rcu_head structures onto the specified @@ -2893,7 +2902,7 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) * CPU unless the grace period has extended for too long. * * This code relies on the fact that all NO_HZ_FULL CPUs are also - * CONFIG_RCU_NOCB_CPUs. + * CONFIG_RCU_NOCB_CPU CPUs. */ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) { diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 4def475336d4..5cdc62e1beeb 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 * @@ -273,7 +273,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, - rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); + ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen); for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index c54609faf233..4c0a9b0af469 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -12,8 +12,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2001 * @@ -49,7 +49,6 @@ #include <linux/module.h> #define CREATE_TRACE_POINTS -#include <trace/events/rcu.h> #include "rcu.h" diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 9a95c8c2af2a..ab32b7b0db5c 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -13,7 +13,7 @@ endif obj-y += core.o proc.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o completion.o +obj-y += wait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 4a073539c58e..e73efba98301 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -203,7 +203,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) struct autogroup *ag; int err; - if (nice < -20 || nice > 19) + if (nice < MIN_NICE || nice > MAX_NICE) return -EINVAL; err = security_task_setnice(current, nice); diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 43c2bcc35761..b30a2924ef14 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu) if (unlikely(!sched_clock_running)) return 0ull; - preempt_disable(); + preempt_disable_notrace(); scd = cpu_sdc(cpu); if (cpu != smp_processor_id()) clock = sched_clock_remote(scd); else clock = sched_clock_local(scd); - preempt_enable(); + preempt_enable_notrace(); return clock; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6edbef296ece..ae365aaa8181 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1745,8 +1745,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; - p->numa_faults = NULL; - p->numa_faults_buffer = NULL; + p->numa_faults_memory = NULL; + p->numa_faults_buffer_memory = NULL; + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; INIT_LIST_HEAD(&p->numa_entry); p->numa_group = NULL; @@ -2149,8 +2151,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) if (mm) mmdrop(mm); if (unlikely(prev_state == TASK_DEAD)) { - task_numa_free(prev); - if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); @@ -2167,13 +2167,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) #ifdef CONFIG_SMP -/* assumes rq->lock is held */ -static inline void pre_schedule(struct rq *rq, struct task_struct *prev) -{ - if (prev->sched_class->pre_schedule) - prev->sched_class->pre_schedule(rq, prev); -} - /* rq->lock is NOT held, but preemption is disabled */ static inline void post_schedule(struct rq *rq) { @@ -2191,10 +2184,6 @@ static inline void post_schedule(struct rq *rq) #else -static inline void pre_schedule(struct rq *rq, struct task_struct *p) -{ -} - static inline void post_schedule(struct rq *rq) { } @@ -2510,8 +2499,13 @@ void __kprobes preempt_count_add(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } } EXPORT_SYMBOL(preempt_count_add); @@ -2554,6 +2548,13 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } @@ -2577,36 +2578,34 @@ static inline void schedule_debug(struct task_struct *prev) schedstat_inc(this_rq(), sched_count); } -static void put_prev_task(struct rq *rq, struct task_struct *prev) -{ - if (prev->on_rq || rq->skip_clock_update < 0) - update_rq_clock(rq); - prev->sched_class->put_prev_task(rq, prev); -} - /* * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq) +pick_next_task(struct rq *rq, struct task_struct *prev) { - const struct sched_class *class; + const struct sched_class *class = &fair_sched_class; struct task_struct *p; /* * Optimization: we know that if all tasks are in * the fair class we can call that function directly: */ - if (likely(rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq); - if (likely(p)) + if (likely(prev->sched_class == class && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev); + if (likely(p && p != RETRY_TASK)) return p; } +again: for_each_class(class) { - p = class->pick_next_task(rq); - if (p) + p = class->pick_next_task(rq, prev); + if (p) { + if (unlikely(p == RETRY_TASK)) + goto again; return p; + } } BUG(); /* the idle class will always have a runnable task */ @@ -2700,13 +2699,10 @@ need_resched: switch_count = &prev->nvcsw; } - pre_schedule(rq, prev); - - if (unlikely(!rq->nr_running)) - idle_balance(cpu, rq); + if (prev->on_rq || rq->skip_clock_update < 0) + update_rq_clock(rq); - put_prev_task(rq, prev); - next = pick_next_task(rq); + next = pick_next_task(rq, prev); clear_tsk_need_resched(prev); clear_preempt_need_resched(); rq->skip_clock_update = 0; @@ -2908,7 +2904,8 @@ EXPORT_SYMBOL(sleep_on_timeout); * This function changes the 'effective' priority of a task. It does * not touch ->normal_prio like __setscheduler(). * - * Used by the rt_mutex code to implement priority inheritance logic. + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. */ void rt_mutex_setprio(struct task_struct *p, int prio) { @@ -2998,7 +2995,7 @@ void set_user_nice(struct task_struct *p, long nice) unsigned long flags; struct rq *rq; - if (TASK_NICE(p) == nice || nice < -20 || nice > 19) + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) return; /* * We have to be careful, if called from sys_setpriority(), @@ -3076,11 +3073,11 @@ SYSCALL_DEFINE1(nice, int, increment) if (increment > 40) increment = 40; - nice = TASK_NICE(current) + increment; - if (nice < -20) - nice = -20; - if (nice > 19) - nice = 19; + nice = task_nice(current) + increment; + if (nice < MIN_NICE) + nice = MIN_NICE; + if (nice > MAX_NICE) + nice = MAX_NICE; if (increment < 0 && !can_nice(current, nice)) return -EPERM; @@ -3109,18 +3106,6 @@ int task_prio(const struct task_struct *p) } /** - * task_nice - return the nice value of a given task. - * @p: the task in question. - * - * Return: The nice value [ -20 ... 0 ... 19 ]. - */ -int task_nice(const struct task_struct *p) -{ - return TASK_NICE(p); -} -EXPORT_SYMBOL(task_nice); - -/** * idle_cpu - is a given cpu idle currently? * @cpu: the processor in question. * @@ -3189,9 +3174,8 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_new = 1; } -/* Actually do priority change: must hold pi & rq lock. */ -static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr) +static void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) { int policy = attr->sched_policy; @@ -3211,9 +3195,21 @@ static void __setscheduler(struct rq *rq, struct task_struct *p, * getparam()/getattr() don't report silly values for !rt tasks. */ p->rt_priority = attr->sched_priority; - p->normal_prio = normal_prio(p); - p->prio = rt_mutex_getprio(p); + set_load_weight(p); +} + +/* Actually do priority change: must hold pi & rq lock. */ +static void __setscheduler(struct rq *rq, struct task_struct *p, + const struct sched_attr *attr) +{ + __setscheduler_params(p, attr); + + /* + * If we get here, there was no pi waiters boosting the + * task. It is safe to use the normal prio. + */ + p->prio = normal_prio(p); if (dl_prio(p->prio)) p->sched_class = &dl_sched_class; @@ -3221,8 +3217,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p, p->sched_class = &rt_sched_class; else p->sched_class = &fair_sched_class; - - set_load_weight(p); } static void @@ -3275,6 +3269,8 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user) { + int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : + MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, on_rq, running; int policy = attr->sched_policy; unsigned long flags; @@ -3319,7 +3315,7 @@ recheck: */ if (user && !capable(CAP_SYS_NICE)) { if (fair_policy(policy)) { - if (attr->sched_nice < TASK_NICE(p) && + if (attr->sched_nice < task_nice(p) && !can_nice(p, attr->sched_nice)) return -EPERM; } @@ -3338,12 +3334,21 @@ recheck: return -EPERM; } + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + return -EPERM; + /* * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { - if (!can_nice(p, TASK_NICE(p))) + if (!can_nice(p, task_nice(p))) return -EPERM; } @@ -3380,16 +3385,18 @@ recheck: } /* - * If not changing anything there's no need to proceed further: + * If not changing anything there's no need to proceed further, + * but store a possible modification of reset_on_fork. */ if (unlikely(policy == p->policy)) { - if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p)) + if (fair_policy(policy) && attr->sched_nice != task_nice(p)) goto change; if (rt_policy(policy) && attr->sched_priority != p->rt_priority) goto change; if (dl_policy(policy)) goto change; + p->sched_reset_on_fork = reset_on_fork; task_rq_unlock(rq, p, &flags); return 0; } @@ -3443,6 +3450,24 @@ change: return -EBUSY; } + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Special case for priority boosted tasks. + * + * If the new priority is lower or equal (user space view) + * than the current (boosted) priority, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + if (rt_mutex_check_prio(p, newprio)) { + __setscheduler_params(p, attr); + task_rq_unlock(rq, p, &flags); + return 0; + } + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) @@ -3450,16 +3475,18 @@ change: if (running) p->sched_class->put_prev_task(rq, p); - p->sched_reset_on_fork = reset_on_fork; - - oldprio = p->prio; prev_class = p->sched_class; __setscheduler(rq, p, attr); if (running) p->sched_class->set_curr_task(rq); - if (on_rq) - enqueue_task(rq, p, 0); + if (on_rq) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } check_class_changed(rq, p, prev_class, oldprio); task_rq_unlock(rq, p, &flags); @@ -3615,7 +3642,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr, * XXX: do we want to be lenient like existing syscalls; or do we want * to be strict and return an error on out-of-bounds values? */ - attr->sched_nice = clamp(attr->sched_nice, -20, 19); + attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); out: return ret; @@ -3836,7 +3863,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, else if (task_has_rt_policy(p)) attr.sched_priority = p->rt_priority; else - attr.sched_nice = TASK_NICE(p); + attr.sched_nice = task_nice(p); rcu_read_unlock(); @@ -4474,6 +4501,7 @@ void init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; + idle->on_rq = 1; #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif @@ -4712,6 +4740,22 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } +static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +{ +} + +static const struct sched_class fake_sched_class = { + .put_prev_task = put_prev_task_fake, +}; + +static struct task_struct fake_task = { + /* + * Avoid pull_{rt,dl}_task() + */ + .prio = MAX_PRIO + 1, + .sched_class = &fake_sched_class, +}; + /* * Migrate all tasks from the rq, sleeping tasks will be migrated by * try_to_wake_up()->select_task_rq(). @@ -4752,7 +4796,7 @@ static void migrate_tasks(unsigned int dead_cpu) if (rq->nr_running == 1) break; - next = pick_next_task(rq); + next = pick_next_task(rq, &fake_task); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -4842,7 +4886,7 @@ set_table_entry(struct ctl_table *entry, static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(13); + struct ctl_table *table = sd_alloc_ctl_entry(14); if (table == NULL) return NULL; @@ -4870,9 +4914,12 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "name", sd->name, + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[12] is terminator */ + /* &table[13] is terminator */ return table; } @@ -6849,7 +6896,6 @@ void __init sched_init(void) rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; #ifdef CONFIG_RT_GROUP_SCHED - INIT_LIST_HEAD(&rq->leaf_rt_rq_list); init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif @@ -6938,7 +6984,8 @@ void __might_sleep(const char *file, int line, int preempt_offset) static unsigned long prev_jiffy; /* ratelimiting */ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ - if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) @@ -6956,6 +7003,13 @@ void __might_sleep(const char *file, int line, int preempt_offset) debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); } EXPORT_SYMBOL(__might_sleep); @@ -7009,7 +7063,7 @@ void normalize_rt_tasks(void) * Renice negative nice level userspace * tasks back to 0: */ - if (TASK_NICE(p) < 0 && p->mm) + if (task_nice(p) < 0 && p->mm) set_user_nice(p, 0); continue; } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5b8838b56d1c..5b9bb42b2d47 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx) static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) { - WARN_ON(!cpu_present(idx) || idx == IDX_INVALID); + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); if (dl_time_before(new_dl, cp->elements[idx].dl)) { cp->elements[idx].dl = new_dl; @@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, } out: - WARN_ON(!cpu_present(best_cpu) && best_cpu != -1); + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); return best_cpu; } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 99947919e30b..58624a65f124 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime, p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); - index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; /* Add user time to cpustat. */ task_group_account_field(p, index, (__force u64) cputime); @@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime += cputime; /* Add guest time to cpustat. */ - if (TASK_NICE(p) > 0) { + if (task_nice(p) > 0) { cpustat[CPUTIME_NICE] += (__force u64) cputime; cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; } else { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 15cbc17fbf84..27ef40925525 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -135,7 +135,6 @@ static void update_dl_migration(struct dl_rq *dl_rq) static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory++; @@ -146,7 +145,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory--; @@ -212,6 +210,16 @@ static inline int has_pushable_dl_tasks(struct rq *rq) static int push_dl_task(struct rq *rq); +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return dl_task(prev); +} + +static inline void set_post_schedule(struct rq *rq) +{ + rq->post_schedule = has_pushable_dl_tasks(rq); +} + #else static inline @@ -234,6 +242,19 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { } +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_dl_task(struct rq *rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); @@ -564,6 +585,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) return 1; } +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + /* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). @@ -586,8 +609,8 @@ static void update_curr_dl(struct rq *rq) * approach need further study. */ delta_exec = rq_clock_task(rq) - curr->se.exec_start; - if (unlikely((s64)delta_exec < 0)) - delta_exec = 0; + if (unlikely((s64)delta_exec <= 0)) + return; schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); @@ -627,11 +650,13 @@ static void update_curr_dl(struct rq *rq) struct rt_rq *rt_rq = &rq->rt; raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; /* * We'll let actual RT tasks worry about the overflow here, we - * have our own CBS to keep us inline -- see above. + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; raw_spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -940,6 +965,8 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) resched_task(rq->curr); } +static int pull_dl_task(struct rq *this_rq); + #endif /* CONFIG_SMP */ /* @@ -986,7 +1013,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, return rb_entry(left, struct sched_dl_entity, rb_node); } -struct task_struct *pick_next_task_dl(struct rq *rq) +struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) { struct sched_dl_entity *dl_se; struct task_struct *p; @@ -994,9 +1021,20 @@ struct task_struct *pick_next_task_dl(struct rq *rq) dl_rq = &rq->dl; + if (need_pull_dl_task(rq, prev)) + pull_dl_task(rq); + /* + * When prev is DL, we may throttle it in put_prev_task(). + * So, we update time before we check for dl_nr_running. + */ + if (prev->sched_class == &dl_sched_class) + update_curr_dl(rq); + if (unlikely(!dl_rq->dl_nr_running)) return NULL; + put_prev_task(rq, prev); + dl_se = pick_next_dl_entity(rq, dl_rq); BUG_ON(!dl_se); @@ -1011,9 +1049,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq) start_hrtick_dl(rq, p); #endif -#ifdef CONFIG_SMP - rq->post_schedule = has_pushable_dl_tasks(rq); -#endif /* CONFIG_SMP */ + set_post_schedule(rq); return p; } @@ -1422,13 +1458,6 @@ skip: return ret; } -static void pre_schedule_dl(struct rq *rq, struct task_struct *prev) -{ - /* Try to pull other tasks here */ - if (dl_task(prev)) - pull_dl_task(rq); -} - static void post_schedule_dl(struct rq *rq) { push_dl_tasks(rq); @@ -1556,7 +1585,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (unlikely(p->dl.dl_throttled)) return; - if (p->on_rq || rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p)) /* Only reschedule if pushing failed */ @@ -1621,7 +1650,6 @@ const struct sched_class dl_sched_class = { .set_cpus_allowed = set_cpus_allowed_dl, .rq_online = rq_online_dl, .rq_offline = rq_offline_dl, - .pre_schedule = pre_schedule_dl, .post_schedule = post_schedule_dl, .task_woken = task_woken_dl, #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index dd52e7ffb10e..f3344c31632a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -321,6 +321,7 @@ do { \ P(sched_goidle); #ifdef CONFIG_SMP P64(avg_idle); + P64(max_idle_balance_cost); #endif P(ttwu_count); @@ -533,15 +534,15 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m) unsigned long nr_faults = -1; int cpu_current, home_node; - if (p->numa_faults) - nr_faults = p->numa_faults[2*node + i]; + if (p->numa_faults_memory) + nr_faults = p->numa_faults_memory[2*node + i]; cpu_current = !i ? (task_node(p) == node) : (pol && node_isset(node, pol->v.nodes)); home_node = (p->numa_preferred_nid == node); - SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n", + SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", i, node, cpu_current, home_node, nr_faults); } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 78157099b167..7e9bd0b1fa9e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) /* Do the two (enqueued) entities belong to the same group ? */ -static inline int +static inline struct cfs_rq * is_same_group(struct sched_entity *se, struct sched_entity *pse) { if (se->cfs_rq == pse->cfs_rq) - return 1; + return se->cfs_rq; - return 0; + return NULL; } static inline struct sched_entity *parent_entity(struct sched_entity *se) @@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) return se->parent; } -/* return depth at which a sched entity is present in the hierarchy */ -static inline int depth_se(struct sched_entity *se) -{ - int depth = 0; - - for_each_sched_entity(se) - depth++; - - return depth; -} - static void find_matching_se(struct sched_entity **se, struct sched_entity **pse) { @@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) */ /* First walk up until both entities are at same depth */ - se_depth = depth_se(*se); - pse_depth = depth_se(*pse); + se_depth = (*se)->depth; + pse_depth = (*pse)->depth; while (se_depth > pse_depth) { se_depth--; @@ -426,12 +415,6 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) #define for_each_leaf_cfs_rq(rq, cfs_rq) \ for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) -static inline int -is_same_group(struct sched_entity *se, struct sched_entity *pse) -{ - return 1; -} - static inline struct sched_entity *parent_entity(struct sched_entity *se) { return NULL; @@ -819,14 +802,6 @@ unsigned int sysctl_numa_balancing_scan_size = 256; /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ unsigned int sysctl_numa_balancing_scan_delay = 1000; -/* - * After skipping a page migration on a shared page, skip N more numa page - * migrations unconditionally. This reduces the number of NUMA migrations - * in shared memory workloads, and has the effect of pulling tasks towards - * where their memory lives, over pulling the memory towards the task. - */ -unsigned int sysctl_numa_balancing_migrate_deferred = 16; - static unsigned int task_nr_scan_windows(struct task_struct *p) { unsigned long rss = 0; @@ -893,10 +868,26 @@ struct numa_group { struct list_head task_list; struct rcu_head rcu; + nodemask_t active_nodes; unsigned long total_faults; + /* + * Faults_cpu is used to decide whether memory should move + * towards the CPU. As a consequence, these stats are weighted + * more by CPU use than by memory faults. + */ + unsigned long *faults_cpu; unsigned long faults[0]; }; +/* Shared or private faults. */ +#define NR_NUMA_HINT_FAULT_TYPES 2 + +/* Memory and CPU locality */ +#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2) + +/* Averaged statistics, and temporary buffers. */ +#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2) + pid_t task_numa_group_id(struct task_struct *p) { return p->numa_group ? p->numa_group->gid : 0; @@ -904,16 +895,16 @@ pid_t task_numa_group_id(struct task_struct *p) static inline int task_faults_idx(int nid, int priv) { - return 2 * nid + priv; + return NR_NUMA_HINT_FAULT_TYPES * nid + priv; } static inline unsigned long task_faults(struct task_struct *p, int nid) { - if (!p->numa_faults) + if (!p->numa_faults_memory) return 0; - return p->numa_faults[task_faults_idx(nid, 0)] + - p->numa_faults[task_faults_idx(nid, 1)]; + return p->numa_faults_memory[task_faults_idx(nid, 0)] + + p->numa_faults_memory[task_faults_idx(nid, 1)]; } static inline unsigned long group_faults(struct task_struct *p, int nid) @@ -925,6 +916,12 @@ static inline unsigned long group_faults(struct task_struct *p, int nid) p->numa_group->faults[task_faults_idx(nid, 1)]; } +static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) +{ + return group->faults_cpu[task_faults_idx(nid, 0)] + + group->faults_cpu[task_faults_idx(nid, 1)]; +} + /* * These return the fraction of accesses done by a particular task, or * task group, on a particular numa node. The group weight is given a @@ -935,7 +932,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid) { unsigned long total_faults; - if (!p->numa_faults) + if (!p->numa_faults_memory) return 0; total_faults = p->total_numa_faults; @@ -954,6 +951,69 @@ static inline unsigned long group_weight(struct task_struct *p, int nid) return 1000 * group_faults(p, nid) / p->numa_group->total_faults; } +bool should_numa_migrate_memory(struct task_struct *p, struct page * page, + int src_nid, int dst_cpu) +{ + struct numa_group *ng = p->numa_group; + int dst_nid = cpu_to_node(dst_cpu); + int last_cpupid, this_cpupid; + + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + + /* + * Multi-stage node selection is used in conjunction with a periodic + * migration fault to build a temporal task<->page relation. By using + * a two-stage filter we remove short/unlikely relations. + * + * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate + * a task's usage of a particular page (n_p) per total usage of this + * page (n_t) (in a given time-span) to a probability. + * + * Our periodic faults will sample this probability and getting the + * same result twice in a row, given these samples are fully + * independent, is then given by P(n)^2, provided our sample period + * is sufficiently short compared to the usage pattern. + * + * This quadric squishes small probabilities, making it less likely we + * act on an unlikely task<->page relation. + */ + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!cpupid_pid_unset(last_cpupid) && + cpupid_to_nid(last_cpupid) != dst_nid) + return false; + + /* Always allow migrate on private faults */ + if (cpupid_match_pid(p, last_cpupid)) + return true; + + /* A shared fault, but p->numa_group has not been set up yet. */ + if (!ng) + return true; + + /* + * Do not migrate if the destination is not a node that + * is actively used by this numa group. + */ + if (!node_isset(dst_nid, ng->active_nodes)) + return false; + + /* + * Source is a node that is not actively used by this + * numa group, while the destination is. Migrate. + */ + if (!node_isset(src_nid, ng->active_nodes)) + return true; + + /* + * Both source and destination are nodes in active + * use by this numa group. Maximize memory bandwidth + * by migrating from more heavily used groups, to less + * heavily used ones, spreading the load around. + * Use a 1/4 hysteresis to avoid spurious page movement. + */ + return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); +} + static unsigned long weighted_cpuload(const int cpu); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); @@ -1267,7 +1327,7 @@ static int task_numa_migrate(struct task_struct *p) static void numa_migrate_preferred(struct task_struct *p) { /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) return; /* Periodically retry migrating the task to the preferred node */ @@ -1282,6 +1342,38 @@ static void numa_migrate_preferred(struct task_struct *p) } /* + * Find the nodes on which the workload is actively running. We do this by + * tracking the nodes from which NUMA hinting faults are triggered. This can + * be different from the set of nodes where the workload's memory is currently + * located. + * + * The bitmask is used to make smarter decisions on when to do NUMA page + * migrations, To prevent flip-flopping, and excessive page migrations, nodes + * are added when they cause over 6/16 of the maximum number of faults, but + * only removed when they drop below 3/16. + */ +static void update_numa_active_node_mask(struct numa_group *numa_group) +{ + unsigned long faults, max_faults = 0; + int nid; + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (faults > max_faults) + max_faults = faults; + } + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (!node_isset(nid, numa_group->active_nodes)) { + if (faults > max_faults * 6 / 16) + node_set(nid, numa_group->active_nodes); + } else if (faults < max_faults * 3 / 16) + node_clear(nid, numa_group->active_nodes); + } +} + +/* * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS * increments. The more local the fault statistics are, the higher the scan * period will be for the next scan window. If local/remote ratio is below @@ -1355,11 +1447,41 @@ static void update_task_scan_period(struct task_struct *p, memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); } +/* + * Get the fraction of time the task has been running since the last + * NUMA placement cycle. The scheduler keeps similar statistics, but + * decays those on a 32ms period, which is orders of magnitude off + * from the dozens-of-seconds NUMA balancing period. Use the scheduler + * stats only if the task is so new there are no NUMA statistics yet. + */ +static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) +{ + u64 runtime, delta, now; + /* Use the start of this time slice to avoid calculations. */ + now = p->se.exec_start; + runtime = p->se.sum_exec_runtime; + + if (p->last_task_numa_placement) { + delta = runtime - p->last_sum_exec_runtime; + *period = now - p->last_task_numa_placement; + } else { + delta = p->se.avg.runnable_avg_sum; + *period = p->se.avg.runnable_avg_period; + } + + p->last_sum_exec_runtime = runtime; + p->last_task_numa_placement = now; + + return delta; +} + static void task_numa_placement(struct task_struct *p) { int seq, nid, max_nid = -1, max_group_nid = -1; unsigned long max_faults = 0, max_group_faults = 0; unsigned long fault_types[2] = { 0, 0 }; + unsigned long total_faults; + u64 runtime, period; spinlock_t *group_lock = NULL; seq = ACCESS_ONCE(p->mm->numa_scan_seq); @@ -1368,6 +1490,10 @@ static void task_numa_placement(struct task_struct *p) p->numa_scan_seq = seq; p->numa_scan_period_max = task_scan_max(p); + total_faults = p->numa_faults_locality[0] + + p->numa_faults_locality[1]; + runtime = numa_get_avg_runtime(p, &period); + /* If the task is part of a group prevent parallel updates to group stats */ if (p->numa_group) { group_lock = &p->numa_group->lock; @@ -1379,24 +1505,37 @@ static void task_numa_placement(struct task_struct *p) unsigned long faults = 0, group_faults = 0; int priv, i; - for (priv = 0; priv < 2; priv++) { - long diff; + for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { + long diff, f_diff, f_weight; i = task_faults_idx(nid, priv); - diff = -p->numa_faults[i]; /* Decay existing window, copy faults since last scan */ - p->numa_faults[i] >>= 1; - p->numa_faults[i] += p->numa_faults_buffer[i]; - fault_types[priv] += p->numa_faults_buffer[i]; - p->numa_faults_buffer[i] = 0; + diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2; + fault_types[priv] += p->numa_faults_buffer_memory[i]; + p->numa_faults_buffer_memory[i] = 0; - faults += p->numa_faults[i]; - diff += p->numa_faults[i]; + /* + * Normalize the faults_from, so all tasks in a group + * count according to CPU use, instead of by the raw + * number of faults. Tasks with little runtime have + * little over-all impact on throughput, and thus their + * faults are less important. + */ + f_weight = div64_u64(runtime << 16, period + 1); + f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) / + (total_faults + 1); + f_diff = f_weight - p->numa_faults_cpu[i] / 2; + p->numa_faults_buffer_cpu[i] = 0; + + p->numa_faults_memory[i] += diff; + p->numa_faults_cpu[i] += f_diff; + faults += p->numa_faults_memory[i]; p->total_numa_faults += diff; if (p->numa_group) { /* safe because we can only change our own group */ p->numa_group->faults[i] += diff; + p->numa_group->faults_cpu[i] += f_diff; p->numa_group->total_faults += diff; group_faults += p->numa_group->faults[i]; } @@ -1416,6 +1555,7 @@ static void task_numa_placement(struct task_struct *p) update_task_scan_period(p, fault_types[0], fault_types[1]); if (p->numa_group) { + update_numa_active_node_mask(p->numa_group); /* * If the preferred task and group nids are different, * iterate over the nodes again to find the best place. @@ -1465,7 +1605,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (unlikely(!p->numa_group)) { unsigned int size = sizeof(struct numa_group) + - 2*nr_node_ids*sizeof(unsigned long); + 4*nr_node_ids*sizeof(unsigned long); grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!grp) @@ -1475,9 +1615,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, spin_lock_init(&grp->lock); INIT_LIST_HEAD(&grp->task_list); grp->gid = p->pid; + /* Second half of the array tracks nids where faults happen */ + grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * + nr_node_ids; + + node_set(task_node(current), grp->active_nodes); - for (i = 0; i < 2*nr_node_ids; i++) - grp->faults[i] = p->numa_faults[i]; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] = p->numa_faults_memory[i]; grp->total_faults = p->total_numa_faults; @@ -1534,9 +1679,9 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, double_lock(&my_grp->lock, &grp->lock); - for (i = 0; i < 2*nr_node_ids; i++) { - my_grp->faults[i] -= p->numa_faults[i]; - grp->faults[i] += p->numa_faults[i]; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { + my_grp->faults[i] -= p->numa_faults_memory[i]; + grp->faults[i] += p->numa_faults_memory[i]; } my_grp->total_faults -= p->total_numa_faults; grp->total_faults += p->total_numa_faults; @@ -1562,12 +1707,12 @@ void task_numa_free(struct task_struct *p) { struct numa_group *grp = p->numa_group; int i; - void *numa_faults = p->numa_faults; + void *numa_faults = p->numa_faults_memory; if (grp) { spin_lock(&grp->lock); - for (i = 0; i < 2*nr_node_ids; i++) - grp->faults[i] -= p->numa_faults[i]; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] -= p->numa_faults_memory[i]; grp->total_faults -= p->total_numa_faults; list_del(&p->numa_entry); @@ -1577,18 +1722,21 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - p->numa_faults_buffer = NULL; + p->numa_faults_memory = NULL; + p->numa_faults_buffer_memory = NULL; + p->numa_faults_cpu= NULL; + p->numa_faults_buffer_cpu = NULL; kfree(numa_faults); } /* * Got a PROT_NONE fault for a page on @node. */ -void task_numa_fault(int last_cpupid, int node, int pages, int flags) +void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) { struct task_struct *p = current; bool migrated = flags & TNF_MIGRATED; + int cpu_node = task_node(current); int priv; if (!numabalancing_enabled) @@ -1603,16 +1751,24 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags) return; /* Allocate buffer to track faults on a per-node basis */ - if (unlikely(!p->numa_faults)) { - int size = sizeof(*p->numa_faults) * 2 * nr_node_ids; + if (unlikely(!p->numa_faults_memory)) { + int size = sizeof(*p->numa_faults_memory) * + NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; - /* numa_faults and numa_faults_buffer share the allocation */ - p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN); - if (!p->numa_faults) + p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults_memory) return; - BUG_ON(p->numa_faults_buffer); - p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids); + BUG_ON(p->numa_faults_buffer_memory); + /* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ + p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids); + p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids); + p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids); p->total_numa_faults = 0; memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); } @@ -1641,7 +1797,8 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; - p->numa_faults_buffer[task_faults_idx(node, priv)] += pages; + p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; + p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages; } @@ -2219,13 +2376,20 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) se->avg.load_avg_contrib >>= NICE_0_SHIFT; } } -#else + +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) +{ + __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); + __update_tg_runnable_avg(&rq->avg, &rq->cfs); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, int force_update) {} static inline void __update_tg_runnable_avg(struct sched_avg *sa, struct cfs_rq *cfs_rq) {} static inline void __update_group_entity_contrib(struct sched_entity *se) {} -#endif +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +#endif /* CONFIG_FAIR_GROUP_SCHED */ static inline void __update_task_entity_contrib(struct sched_entity *se) { @@ -2323,12 +2487,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) __update_cfs_rq_tg_load_contrib(cfs_rq, force_update); } -static inline void update_rq_runnable_avg(struct rq *rq, int runnable) -{ - __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); - __update_tg_runnable_avg(&rq->avg, &rq->cfs); -} - /* Add the load generated by se into cfs_rq's child load-average */ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, @@ -2416,7 +2574,10 @@ void idle_exit_fair(struct rq *this_rq) update_rq_runnable_avg(this_rq, 0); } -#else +static int idle_balance(struct rq *this_rq); + +#else /* CONFIG_SMP */ + static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) {} static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} @@ -2428,7 +2589,13 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, int sleep) {} static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) {} -#endif + +static inline int idle_balance(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SMP */ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -2578,10 +2745,10 @@ static void __clear_buddies_last(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->last == se) - cfs_rq->last = NULL; - else + if (cfs_rq->last != se) break; + + cfs_rq->last = NULL; } } @@ -2589,10 +2756,10 @@ static void __clear_buddies_next(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->next == se) - cfs_rq->next = NULL; - else + if (cfs_rq->next != se) break; + + cfs_rq->next = NULL; } } @@ -2600,10 +2767,10 @@ static void __clear_buddies_skip(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->skip == se) - cfs_rq->skip = NULL; - else + if (cfs_rq->skip != se) break; + + cfs_rq->skip = NULL; } } @@ -2746,17 +2913,36 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); * 3) pick the "last" process, for cache locality * 4) do not run the "skip" process, if something else is available */ -static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) +static struct sched_entity * +pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) { - struct sched_entity *se = __pick_first_entity(cfs_rq); - struct sched_entity *left = se; + struct sched_entity *left = __pick_first_entity(cfs_rq); + struct sched_entity *se; + + /* + * If curr is set we have to see if its left of the leftmost entity + * still in the tree, provided there was anything in the tree at all. + */ + if (!left || (curr && entity_before(curr, left))) + left = curr; + + se = left; /* ideally we run the leftmost entity */ /* * Avoid running the skip buddy, if running something else can * be done without getting too unfair. */ if (cfs_rq->skip == se) { - struct sched_entity *second = __pick_next_entity(se); + struct sched_entity *second; + + if (se == curr) { + second = __pick_first_entity(cfs_rq); + } else { + second = __pick_next_entity(se); + if (!second || (curr && entity_before(curr, second))) + second = curr; + } + if (second && wakeup_preempt_entity(second, left) < 1) se = second; } @@ -2778,7 +2964,7 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) return se; } -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq); +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) { @@ -3433,22 +3619,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) } /* conditionally throttle active cfs_rq's from put_prev_entity() */ -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { if (!cfs_bandwidth_used()) - return; + return false; if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) - return; + return false; /* * it's possible for a throttled entity to be forced into a running * state (e.g. set_curr_task), in this case we're finished. */ if (cfs_rq_throttled(cfs_rq)) - return; + return true; throttle_cfs_rq(cfs_rq); + return true; } static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) @@ -3558,7 +3745,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) } static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} @@ -4213,13 +4400,14 @@ done: } /* - * sched_balance_self: balance the current task (running on cpu) in domains - * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and - * SD_BALANCE_EXEC. + * select_task_rq_fair: Select target runqueue for the waking task in domains + * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, + * SD_BALANCE_FORK, or SD_BALANCE_EXEC. * - * Balance, ie. select the least loaded group. + * Balances load by selecting the idlest cpu in the idlest group, or under + * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set. * - * Returns the target CPU number, or the same CPU if no balancing is needed. + * Returns the target cpu number. * * preempt must be disabled. */ @@ -4494,26 +4682,124 @@ preempt: set_last_buddy(se); } -static struct task_struct *pick_next_task_fair(struct rq *rq) +static struct task_struct * +pick_next_task_fair(struct rq *rq, struct task_struct *prev) { - struct task_struct *p; struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; + struct task_struct *p; + int new_tasks; +again: +#ifdef CONFIG_FAIR_GROUP_SCHED if (!cfs_rq->nr_running) - return NULL; + goto idle; + + if (prev->sched_class != &fair_sched_class) + goto simple; + + /* + * Because of the set_next_buddy() in dequeue_task_fair() it is rather + * likely that a next task is from the same cgroup as the current. + * + * Therefore attempt to avoid putting and setting the entire cgroup + * hierarchy, only change the part that actually changes. + */ + + do { + struct sched_entity *curr = cfs_rq->curr; + + /* + * Since we got here without doing put_prev_entity() we also + * have to consider cfs_rq->curr. If it is still a runnable + * entity, update_curr() will update its vruntime, otherwise + * forget we've ever seen it. + */ + if (curr && curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + /* + * This call to check_cfs_rq_runtime() will do the throttle and + * dequeue its entity in the parent(s). Therefore the 'simple' + * nr_running test will indeed be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + /* + * Since we haven't yet done put_prev_entity and if the selected task + * is a different task than we started out with, try and touch the + * least amount of cfs_rqs. + */ + if (prev != p) { + struct sched_entity *pse = &prev->se; + + while (!(cfs_rq = is_same_group(se, pse))) { + int se_depth = se->depth; + int pse_depth = pse->depth; + + if (se_depth <= pse_depth) { + put_prev_entity(cfs_rq_of(pse), pse); + pse = parent_entity(pse); + } + if (se_depth >= pse_depth) { + set_next_entity(cfs_rq_of(se), se); + se = parent_entity(se); + } + } + + put_prev_entity(cfs_rq, pse); + set_next_entity(cfs_rq, se); + } + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; +simple: + cfs_rq = &rq->cfs; +#endif + + if (!cfs_rq->nr_running) + goto idle; + + put_prev_task(rq, prev); do { - se = pick_next_entity(cfs_rq); + se = pick_next_entity(cfs_rq, NULL); set_next_entity(cfs_rq, se); cfs_rq = group_cfs_rq(se); } while (cfs_rq); p = task_of(se); + if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); return p; + +idle: + new_tasks = idle_balance(rq); + /* + * Because idle_balance() releases (and re-acquires) rq->lock, it is + * possible for any higher priority task to appear. In that case we + * must re-start the pick_next_entity() loop. + */ + if (new_tasks < 0) + return RETRY_TASK; + + if (new_tasks > 0) + goto again; + + return NULL; } /* @@ -4751,7 +5037,7 @@ static void move_task(struct task_struct *p, struct lb_env *env) * Is this task likely cache-hot: */ static int -task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) +task_hot(struct task_struct *p, u64 now) { s64 delta; @@ -4785,7 +5071,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) { int src_nid, dst_nid; - if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || !(env->sd->flags & SD_NUMA)) { return false; } @@ -4816,7 +5102,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) return false; - if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) + if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA)) return false; src_nid = cpu_to_node(env->src_cpu); @@ -4912,7 +5198,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 2) task is cache cold, or * 3) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd); + tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq)); if (!tsk_cache_hot) tsk_cache_hot = migrate_degrades_locality(p, env); @@ -5775,12 +6061,10 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) pwr_now /= SCHED_POWER_SCALE; /* Amount of load we'd subtract */ - tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / - busiest->group_power; - if (busiest->avg_load > tmp) { + if (busiest->avg_load > scaled_busy_load_per_task) { pwr_move += busiest->group_power * min(busiest->load_per_task, - busiest->avg_load - tmp); + busiest->avg_load - scaled_busy_load_per_task); } /* Amount of load we'd add */ @@ -6359,17 +6643,23 @@ out: * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -void idle_balance(int this_cpu, struct rq *this_rq) +static int idle_balance(struct rq *this_rq) { struct sched_domain *sd; int pulled_task = 0; unsigned long next_balance = jiffies + HZ; u64 curr_cost = 0; + int this_cpu = this_rq->cpu; + idle_enter_fair(this_rq); + /* + * We must set idle_stamp _before_ calling idle_balance(), such that we + * measure the duration of idle_balance() as idle time. + */ this_rq->idle_stamp = rq_clock(this_rq); if (this_rq->avg_idle < sysctl_sched_migration_cost) - return; + goto out; /* * Drop the rq->lock, but keep IRQ/preempt disabled. @@ -6407,15 +6697,22 @@ void idle_balance(int this_cpu, struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) { - this_rq->idle_stamp = 0; + if (pulled_task) break; - } } rcu_read_unlock(); raw_spin_lock(&this_rq->lock); + /* + * While browsing the domains, we released the rq lock. + * A task could have be enqueued in the meantime + */ + if (this_rq->cfs.h_nr_running && !pulled_task) { + pulled_task = 1; + goto out; + } + if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* * We are going idle. next_balance may be set based on @@ -6426,6 +6723,20 @@ void idle_balance(int this_cpu, struct rq *this_rq) if (curr_cost > this_rq->max_idle_balance_cost) this_rq->max_idle_balance_cost = curr_cost; + +out: + /* Is there a task of a high priority class? */ + if (this_rq->nr_running != this_rq->cfs.h_nr_running && + (this_rq->dl.dl_nr_running || + (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt)))) + pulled_task = -1; + + if (pulled_task) { + idle_exit_fair(this_rq); + this_rq->idle_stamp = 0; + } + + return pulled_task; } /* @@ -6496,6 +6807,11 @@ out_unlock: return 0; } +static inline int on_null_domain(struct rq *rq) +{ + return unlikely(!rcu_dereference_sched(rq->sd)); +} + #ifdef CONFIG_NO_HZ_COMMON /* * idle load balancing details @@ -6550,8 +6866,13 @@ static void nohz_balancer_kick(void) static inline void nohz_balance_exit_idle(int cpu) { if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { - cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); - atomic_dec(&nohz.nr_cpus); + /* + * Completely isolated CPUs don't ever set, so we must test. + */ + if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) { + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); + atomic_dec(&nohz.nr_cpus); + } clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } } @@ -6605,6 +6926,12 @@ void nohz_balance_enter_idle(int cpu) if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) return; + /* + * If we're a completely isolated CPU, we don't play. + */ + if (on_null_domain(cpu_rq(cpu))) + return; + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); atomic_inc(&nohz.nr_cpus); set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); @@ -6867,11 +7194,6 @@ static void run_rebalance_domains(struct softirq_action *h) nohz_idle_balance(this_rq, idle); } -static inline int on_null_domain(struct rq *rq) -{ - return !rcu_dereference_sched(rq->sd); -} - /* * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. */ @@ -7001,15 +7323,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) struct cfs_rq *cfs_rq = cfs_rq_of(se); /* - * Ensure the task's vruntime is normalized, so that when its + * Ensure the task's vruntime is normalized, so that when it's * switched back to the fair class the enqueue_entity(.flags=0) will * do the right thing. * - * If it was on_rq, then the dequeue_entity(.flags=0) will already - * have normalized the vruntime, if it was !on_rq, then only when + * If it's on_rq, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !on_rq, then only when * the task is sleeping will it still have non-normalized vruntime. */ - if (!se->on_rq && p->state != TASK_RUNNING) { + if (!p->on_rq && p->state != TASK_RUNNING) { /* * Fix up our vruntime so that the current sleep doesn't * cause 'unlimited' sleep bonus. @@ -7036,7 +7358,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) */ static void switched_to_fair(struct rq *rq, struct task_struct *p) { - if (!p->se.on_rq) + struct sched_entity *se = &p->se; +#ifdef CONFIG_FAIR_GROUP_SCHED + /* + * Since the real-depth could have been changed (only FAIR + * class maintain depth value), reset depth properly. + */ + se->depth = se->parent ? se->parent->depth + 1 : 0; +#endif + if (!se->on_rq) return; /* @@ -7084,7 +7414,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) #ifdef CONFIG_FAIR_GROUP_SCHED static void task_move_group_fair(struct task_struct *p, int on_rq) { + struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq; + /* * If the task was not on the rq at the time of this cgroup movement * it must have been asleep, sleeping tasks keep their ->vruntime @@ -7110,23 +7442,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq) * To prevent boost or penalty in the new cfs_rq caused by delta * min_vruntime between the two cfs_rqs, we skip vruntime adjustment. */ - if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING)) + if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING)) on_rq = 1; if (!on_rq) - p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime; + se->vruntime -= cfs_rq_of(se)->min_vruntime; set_task_rq(p, task_cpu(p)); + se->depth = se->parent ? se->parent->depth + 1 : 0; if (!on_rq) { - cfs_rq = cfs_rq_of(&p->se); - p->se.vruntime += cfs_rq->min_vruntime; + cfs_rq = cfs_rq_of(se); + se->vruntime += cfs_rq->min_vruntime; #ifdef CONFIG_SMP /* * migrate_task_rq_fair() will have removed our previous * contribution, but we must synchronize for ongoing future * decay. */ - p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter); - cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib; + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; #endif } } @@ -7222,10 +7555,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, if (!se) return; - if (!parent) + if (!parent) { se->cfs_rq = &rq->cfs; - else + se->depth = 0; + } else { se->cfs_rq = parent->my_q; + se->depth = parent->depth + 1; + } se->my_q = cfs_rq; /* guarantee group entities always have weight */ diff --git a/kernel/cpu/idle.c b/kernel/sched/idle.c index 277f494c2a9a..b7976a127178 100644 --- a/kernel/cpu/idle.c +++ b/kernel/sched/idle.c @@ -3,6 +3,7 @@ */ #include <linux/sched.h> #include <linux/cpu.h> +#include <linux/cpuidle.h> #include <linux/tick.h> #include <linux/mm.h> #include <linux/stackprotector.h> @@ -95,8 +96,10 @@ static void cpu_idle_loop(void) if (!current_clr_polling_and_test()) { stop_critical_timings(); rcu_idle_enter(); - arch_cpu_idle(); - WARN_ON_ONCE(irqs_disabled()); + if (cpuidle_idle_call()) + arch_cpu_idle(); + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); rcu_idle_exit(); start_critical_timings(); } else { diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 516c3d9ceea1..879f2b75266a 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } - -static void pre_schedule_idle(struct rq *rq, struct task_struct *prev) -{ - idle_exit_fair(rq); - rq_last_tick_reset(rq); -} - -static void post_schedule_idle(struct rq *rq) -{ - idle_enter_fair(rq); -} #endif /* CONFIG_SMP */ + /* * Idle tasks are unconditionally rescheduled: */ @@ -33,13 +23,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_task(rq->idle); } -static struct task_struct *pick_next_task_idle(struct rq *rq) +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev) { + put_prev_task(rq, prev); + schedstat_inc(rq, sched_goidle); -#ifdef CONFIG_SMP - /* Trigger the post schedule to do an idle_enter for CFS */ - rq->post_schedule = 1; -#endif return rq->idle; } @@ -58,6 +47,8 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { + idle_exit_fair(rq); + rq_last_tick_reset(rq); } static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) @@ -101,8 +92,6 @@ const struct sched_class idle_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, - .pre_schedule = pre_schedule_idle, - .post_schedule = post_schedule_idle, #endif .set_curr_task = set_curr_task_idle, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a2740b775b45..d8cdf1618551 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -229,6 +229,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) #ifdef CONFIG_SMP +static int pull_rt_task(struct rq *this_rq); + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + /* Try to pull RT tasks here if we lower this rq's prio */ + return rq->rt.highest_prio.curr > prev->prio; +} + static inline int rt_overloaded(struct rq *rq) { return atomic_read(&rq->rd->rto_count); @@ -315,6 +323,15 @@ static inline int has_pushable_tasks(struct rq *rq) return !plist_head_empty(&rq->rt.pushable_tasks); } +static inline void set_post_schedule(struct rq *rq) +{ + /* + * We detect this state here so that we can avoid taking the RQ + * lock again later if there is no need to push + */ + rq->post_schedule = has_pushable_tasks(rq); +} + static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) { plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); @@ -359,6 +376,19 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { } +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_rt_task(struct rq *this_rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ static inline int on_rt_rq(struct sched_rt_entity *rt_se) @@ -440,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) dequeue_rt_entity(rt_se); } -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; -} - static int rt_se_boosted(struct sched_rt_entity *rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); @@ -515,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { } -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled; -} - static inline const struct cpumask *sched_rt_period_mask(void) { return cpu_online_mask; @@ -538,6 +558,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) #endif /* CONFIG_RT_GROUP_SCHED */ +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + #ifdef CONFIG_SMP /* * We ran out of runtime, see if we can borrow some from our neighbours. @@ -1310,15 +1338,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) { struct sched_rt_entity *rt_se; struct task_struct *p; - struct rt_rq *rt_rq; - - rt_rq = &rq->rt; - - if (!rt_rq->rt_nr_running) - return NULL; - - if (rt_rq_throttled(rt_rq)) - return NULL; + struct rt_rq *rt_rq = &rq->rt; do { rt_se = pick_next_rt_entity(rq, rt_rq); @@ -1332,21 +1352,45 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) return p; } -static struct task_struct *pick_next_task_rt(struct rq *rq) +static struct task_struct * +pick_next_task_rt(struct rq *rq, struct task_struct *prev) { - struct task_struct *p = _pick_next_task_rt(rq); + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + if (need_pull_rt_task(rq, prev)) { + pull_rt_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a dl task can slip in, in which case we need to + * re-start task selection. + */ + if (unlikely(rq->dl.dl_nr_running)) + return RETRY_TASK; + } + + /* + * We may dequeue prev's rt_rq in put_prev_task(). + * So, we update time before rt_nr_running check. + */ + if (prev->sched_class == &rt_sched_class) + update_curr_rt(rq); + + if (!rt_rq->rt_nr_running) + return NULL; + + if (rt_rq_throttled(rt_rq)) + return NULL; + + put_prev_task(rq, prev); + + p = _pick_next_task_rt(rq); /* The running task is never eligible for pushing */ if (p) dequeue_pushable_task(rq, p); -#ifdef CONFIG_SMP - /* - * We detect this state here so that we can avoid taking the RQ - * lock again later if there is no need to push - */ - rq->post_schedule = has_pushable_tasks(rq); -#endif + set_post_schedule(rq); return p; } @@ -1716,13 +1760,6 @@ skip: return ret; } -static void pre_schedule_rt(struct rq *rq, struct task_struct *prev) -{ - /* Try to pull RT tasks here if we lower this rq's prio */ - if (rq->rt.highest_prio.curr > prev->prio) - pull_rt_task(rq); -} - static void post_schedule_rt(struct rq *rq) { push_rt_tasks(rq); @@ -1825,7 +1862,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) resched_task(rq->curr); } -void init_sched_rt_class(void) +void __init init_sched_rt_class(void) { unsigned int i; @@ -1999,7 +2036,6 @@ const struct sched_class rt_sched_class = { .set_cpus_allowed = set_cpus_allowed_rt, .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, - .pre_schedule = pre_schedule_rt, .post_schedule = post_schedule_rt, .task_woken = task_woken_rt, .switched_from = switched_from_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f964add50f38..f2de7a175620 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -24,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq); extern void update_cpu_load_active(struct rq *this_rq); /* - * Convert user-nice values [ -20 ... 0 ... 19 ] - * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], - * and back. - */ -#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) -#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) -#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) - -/* - * 'User priority' is the nice value converted to something we - * can work with better when scaling various scheduler parameters, - * it's a [ 0 ... 39 ] range. - */ -#define USER_PRIO(p) ((p)-MAX_RT_PRIO) -#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) -#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) - -/* * Helpers for converting nanosecond timing to jiffy resolution */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) @@ -441,6 +423,18 @@ struct rt_rq { #endif }; +#ifdef CONFIG_RT_GROUP_SCHED +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; +} +#else +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled; +} +#endif + /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ @@ -558,11 +552,9 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; -#endif /* CONFIG_FAIR_GROUP_SCHED */ -#ifdef CONFIG_RT_GROUP_SCHED - struct list_head leaf_rt_rq_list; -#endif + struct sched_avg avg; +#endif /* CONFIG_FAIR_GROUP_SCHED */ /* * This is part of a global counter where only the total sum @@ -651,8 +643,6 @@ struct rq { #ifdef CONFIG_SMP struct llist_head wake_list; #endif - - struct sched_avg avg; }; static inline int cpu_of(struct rq *rq) @@ -1112,6 +1102,8 @@ static const u32 prio_to_wmult[40] = { #define DEQUEUE_SLEEP 1 +#define RETRY_TASK ((void *)-1UL) + struct sched_class { const struct sched_class *next; @@ -1122,14 +1114,22 @@ struct sched_class { void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); - struct task_struct * (*pick_next_task) (struct rq *rq); + /* + * It is the responsibility of the pick_next_task() method that will + * return the next task to call put_prev_task() on the @prev task or + * something equivalent. + * + * May return RETRY_TASK when it finds a higher prio class has runnable + * tasks. + */ + struct task_struct * (*pick_next_task) (struct rq *rq, + struct task_struct *prev); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); @@ -1159,6 +1159,11 @@ struct sched_class { #endif }; +static inline void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + prev->sched_class->put_prev_task(rq, prev); +} + #define sched_class_highest (&stop_sched_class) #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) @@ -1175,16 +1180,14 @@ extern const struct sched_class idle_sched_class; extern void update_group_power(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); -extern void idle_balance(int this_cpu, struct rq *this_rq); extern void idle_enter_fair(struct rq *this_rq); extern void idle_exit_fair(struct rq *this_rq); -#else /* CONFIG_SMP */ +#else -static inline void idle_balance(int cpu, struct rq *rq) -{ -} +static inline void idle_enter_fair(struct rq *rq) { } +static inline void idle_exit_fair(struct rq *rq) { } #endif diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index fdb6bb0b3356..d6ce65dde541 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -23,16 +23,19 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) /* we're never preempted */ } -static struct task_struct *pick_next_task_stop(struct rq *rq) +static struct task_struct * +pick_next_task_stop(struct rq *rq, struct task_struct *prev) { struct task_struct *stop = rq->stop; - if (stop && stop->on_rq) { - stop->se.exec_start = rq_clock_task(rq); - return stop; - } + if (!stop || !stop->on_rq) + return NULL; - return NULL; + put_prev_task(rq, prev); + + stop->se.exec_start = rq_clock_task(rq); + + return stop; } static void diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 84571e09c907..01fbae5b97b7 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * */ smp_call_function_single(min(cpu1, cpu2), &irq_cpu_stop_queue_work, - &call_args, 0); + &call_args, 1); lg_local_unlock(&stop_cpus_lock); preempt_enable(); diff --git a/kernel/sys.c b/kernel/sys.c index c0a58be780a4..adaeab6f7a87 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -174,10 +174,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; - if (niceval < -20) - niceval = -20; - if (niceval > 19) - niceval = 19; + if (niceval < MIN_NICE) + niceval = MIN_NICE; + if (niceval > MAX_NICE) + niceval = MAX_NICE; rcu_read_lock(); read_lock(&tasklist_lock); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 49e13e1f8fe6..7754ff16f334 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -386,13 +386,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, { - .procname = "numa_balancing_migrate_deferred", - .data = &sysctl_numa_balancing_migrate_deferred, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "numa_balancing", .data = NULL, /* filled in by handler */ .maxlen = sizeof(unsigned int), diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0aa4ce81bc16..5b40279ecd71 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1435,7 +1435,8 @@ void update_wall_time(void) out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) - clock_was_set(); + /* Have to call _delayed version, since in irq context*/ + clock_was_set_delayed(); } /** diff --git a/kernel/timer.c b/kernel/timer.c index accfd241b9e5..d78de047599b 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -52,7 +52,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/timer.h> -u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; +__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); diff --git a/kernel/torture.c b/kernel/torture.c new file mode 100644 index 000000000000..acc9afc2f26e --- /dev/null +++ b/kernel/torture.c @@ -0,0 +1,719 @@ +/* + * Common functions for in-kernel torture tests. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2014 + * + * Author: Paul E. McKenney <paulmck@us.ibm.com> + * Based on kernel/rcu/torture.c. + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kthread.h> +#include <linux/err.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/reboot.h> +#include <linux/freezer.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include <linux/trace_clock.h> +#include <asm/byteorder.h> +#include <linux/torture.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); + +static char *torture_type; +static bool verbose; + +/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ +#define FULLSTOP_DONTSTOP 0 /* Normal operation. */ +#define FULLSTOP_SHUTDOWN 1 /* System shutdown with torture running. */ +#define FULLSTOP_RMMOD 2 /* Normal rmmod of torture. */ +static int fullstop = FULLSTOP_RMMOD; +static DEFINE_MUTEX(fullstop_mutex); +static int *torture_runnable; + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Variables for online-offline handling. Only present if CPU hotplug + * is enabled, otherwise does nothing. + */ + +static struct task_struct *onoff_task; +static long onoff_holdoff; +static long onoff_interval; +static long n_offline_attempts; +static long n_offline_successes; +static unsigned long sum_offline; +static int min_offline = -1; +static int max_offline; +static long n_online_attempts; +static long n_online_successes; +static unsigned long sum_online; +static int min_online = -1; +static int max_online; + +/* + * Execute random CPU-hotplug operations at the interval specified + * by the onoff_interval. + */ +static int +torture_onoff(void *arg) +{ + int cpu; + unsigned long delta; + int maxcpu = -1; + DEFINE_TORTURE_RANDOM(rand); + int ret; + unsigned long starttime; + + VERBOSE_TOROUT_STRING("torture_onoff task started"); + for_each_online_cpu(cpu) + maxcpu = cpu; + WARN_ON(maxcpu < 0); + if (onoff_holdoff > 0) { + VERBOSE_TOROUT_STRING("torture_onoff begin holdoff"); + schedule_timeout_interruptible(onoff_holdoff); + VERBOSE_TOROUT_STRING("torture_onoff end holdoff"); + } + while (!torture_must_stop()) { + cpu = (torture_random(&rand) >> 4) % (maxcpu + 1); + if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlining %d\n", + torture_type, cpu); + starttime = jiffies; + n_offline_attempts++; + ret = cpu_down(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offline %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlined %d\n", + torture_type, cpu); + n_offline_successes++; + delta = jiffies - starttime; + sum_offline += delta; + if (min_offline < 0) { + min_offline = delta; + max_offline = delta; + } + if (min_offline > delta) + min_offline = delta; + if (max_offline < delta) + max_offline = delta; + } + } else if (cpu_is_hotpluggable(cpu)) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlining %d\n", + torture_type, cpu); + starttime = jiffies; + n_online_attempts++; + ret = cpu_up(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: online %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlined %d\n", + torture_type, cpu); + n_online_successes++; + delta = jiffies - starttime; + sum_online += delta; + if (min_online < 0) { + min_online = delta; + max_online = delta; + } + if (min_online > delta) + min_online = delta; + if (max_online < delta) + max_online = delta; + } + } + schedule_timeout_interruptible(onoff_interval); + } + torture_kthread_stopping("torture_onoff"); + return 0; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +/* + * Initiate online-offline handling. + */ +int torture_onoff_init(long ooholdoff, long oointerval) +{ + int ret = 0; + +#ifdef CONFIG_HOTPLUG_CPU + onoff_holdoff = ooholdoff; + onoff_interval = oointerval; + if (onoff_interval <= 0) + return 0; + ret = torture_create_kthread(torture_onoff, NULL, onoff_task); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + return ret; +} +EXPORT_SYMBOL_GPL(torture_onoff_init); + +/* + * Clean up after online/offline testing. + */ +static void torture_onoff_cleanup(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (onoff_task == NULL) + return; + VERBOSE_TOROUT_STRING("Stopping torture_onoff task"); + kthread_stop(onoff_task); + onoff_task = NULL; +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ +} +EXPORT_SYMBOL_GPL(torture_onoff_cleanup); + +/* + * Print online/offline testing statistics. + */ +char *torture_onoff_stats(char *page) +{ +#ifdef CONFIG_HOTPLUG_CPU + page += sprintf(page, + "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + return page; +} +EXPORT_SYMBOL_GPL(torture_onoff_stats); + +/* + * Were all the online/offline operations successful? + */ +bool torture_onoff_failures(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + return n_online_successes != n_online_attempts || + n_offline_successes != n_offline_attempts; +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + return false; +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ +} +EXPORT_SYMBOL_GPL(torture_onoff_failures); + +#define TORTURE_RANDOM_MULT 39916801 /* prime */ +#define TORTURE_RANDOM_ADD 479001701 /* prime */ +#define TORTURE_RANDOM_REFRESH 10000 + +/* + * Crude but fast random-number generator. Uses a linear congruential + * generator, with occasional help from cpu_clock(). + */ +unsigned long +torture_random(struct torture_random_state *trsp) +{ + if (--trsp->trs_count < 0) { + trsp->trs_state += (unsigned long)local_clock(); + trsp->trs_count = TORTURE_RANDOM_REFRESH; + } + trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT + + TORTURE_RANDOM_ADD; + return swahw32(trsp->trs_state); +} +EXPORT_SYMBOL_GPL(torture_random); + +/* + * Variables for shuffling. The idea is to ensure that each CPU stays + * idle for an extended period to test interactions with dyntick idle, + * as well as interactions with any per-CPU varibles. + */ +struct shuffle_task { + struct list_head st_l; + struct task_struct *st_t; +}; + +static long shuffle_interval; /* In jiffies. */ +static struct task_struct *shuffler_task; +static cpumask_var_t shuffle_tmp_mask; +static int shuffle_idle_cpu; /* Force all torture tasks off this CPU */ +static struct list_head shuffle_task_list = LIST_HEAD_INIT(shuffle_task_list); +static DEFINE_MUTEX(shuffle_task_mutex); + +/* + * Register a task to be shuffled. If there is no memory, just splat + * and don't bother registering. + */ +void torture_shuffle_task_register(struct task_struct *tp) +{ + struct shuffle_task *stp; + + if (WARN_ON_ONCE(tp == NULL)) + return; + stp = kmalloc(sizeof(*stp), GFP_KERNEL); + if (WARN_ON_ONCE(stp == NULL)) + return; + stp->st_t = tp; + mutex_lock(&shuffle_task_mutex); + list_add(&stp->st_l, &shuffle_task_list); + mutex_unlock(&shuffle_task_mutex); +} +EXPORT_SYMBOL_GPL(torture_shuffle_task_register); + +/* + * Unregister all tasks, for example, at the end of the torture run. + */ +static void torture_shuffle_task_unregister_all(void) +{ + struct shuffle_task *stp; + struct shuffle_task *p; + + mutex_lock(&shuffle_task_mutex); + list_for_each_entry_safe(stp, p, &shuffle_task_list, st_l) { + list_del(&stp->st_l); + kfree(stp); + } + mutex_unlock(&shuffle_task_mutex); +} + +/* Shuffle tasks such that we allow shuffle_idle_cpu to become idle. + * A special case is when shuffle_idle_cpu = -1, in which case we allow + * the tasks to run on all CPUs. + */ +static void torture_shuffle_tasks(void) +{ + struct shuffle_task *stp; + + cpumask_setall(shuffle_tmp_mask); + get_online_cpus(); + + /* No point in shuffling if there is only one online CPU (ex: UP) */ + if (num_online_cpus() == 1) { + put_online_cpus(); + return; + } + + /* Advance to the next CPU. Upon overflow, don't idle any CPUs. */ + shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask); + if (shuffle_idle_cpu >= nr_cpu_ids) + shuffle_idle_cpu = -1; + if (shuffle_idle_cpu != -1) { + cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask); + if (cpumask_empty(shuffle_tmp_mask)) { + put_online_cpus(); + return; + } + } + + mutex_lock(&shuffle_task_mutex); + list_for_each_entry(stp, &shuffle_task_list, st_l) + set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask); + mutex_unlock(&shuffle_task_mutex); + + put_online_cpus(); +} + +/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the + * system to become idle at a time and cut off its timer ticks. This is meant + * to test the support for such tickless idle CPU in RCU. + */ +static int torture_shuffle(void *arg) +{ + VERBOSE_TOROUT_STRING("torture_shuffle task started"); + do { + schedule_timeout_interruptible(shuffle_interval); + torture_shuffle_tasks(); + torture_shutdown_absorb("torture_shuffle"); + } while (!torture_must_stop()); + torture_kthread_stopping("torture_shuffle"); + return 0; +} + +/* + * Start the shuffler, with shuffint in jiffies. + */ +int torture_shuffle_init(long shuffint) +{ + shuffle_interval = shuffint; + + shuffle_idle_cpu = -1; + + if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) { + VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask"); + return -ENOMEM; + } + + /* Create the shuffler thread */ + return torture_create_kthread(torture_shuffle, NULL, shuffler_task); +} +EXPORT_SYMBOL_GPL(torture_shuffle_init); + +/* + * Stop the shuffling. + */ +static void torture_shuffle_cleanup(void) +{ + torture_shuffle_task_unregister_all(); + if (shuffler_task) { + VERBOSE_TOROUT_STRING("Stopping torture_shuffle task"); + kthread_stop(shuffler_task); + free_cpumask_var(shuffle_tmp_mask); + } + shuffler_task = NULL; +} +EXPORT_SYMBOL_GPL(torture_shuffle_cleanup); + +/* + * Variables for auto-shutdown. This allows "lights out" torture runs + * to be fully scripted. + */ +static int shutdown_secs; /* desired test duration in seconds. */ +static struct task_struct *shutdown_task; +static unsigned long shutdown_time; /* jiffies to system shutdown. */ +static void (*torture_shutdown_hook)(void); + +/* + * Absorb kthreads into a kernel function that won't return, so that + * they won't ever access module text or data again. + */ +void torture_shutdown_absorb(const char *title) +{ + while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + pr_notice("torture thread %s parking due to system shutdown\n", + title); + schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); + } +} +EXPORT_SYMBOL_GPL(torture_shutdown_absorb); + +/* + * Cause the torture test to shutdown the system after the test has + * run for the time specified by the shutdown_secs parameter. + */ +static int torture_shutdown(void *arg) +{ + long delta; + unsigned long jiffies_snap; + + VERBOSE_TOROUT_STRING("torture_shutdown task started"); + jiffies_snap = jiffies; + while (ULONG_CMP_LT(jiffies_snap, shutdown_time) && + !torture_must_stop()) { + delta = shutdown_time - jiffies_snap; + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_shutdown task: %lu jiffies remaining\n", + torture_type, delta); + schedule_timeout_interruptible(delta); + jiffies_snap = jiffies; + } + if (torture_must_stop()) { + torture_kthread_stopping("torture_shutdown"); + return 0; + } + + /* OK, shut down the system. */ + + VERBOSE_TOROUT_STRING("torture_shutdown task shutting down system"); + shutdown_task = NULL; /* Avoid self-kill deadlock. */ + if (torture_shutdown_hook) + torture_shutdown_hook(); + else + VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping."); + kernel_power_off(); /* Shut down the system. */ + return 0; +} + +/* + * Start up the shutdown task. + */ +int torture_shutdown_init(int ssecs, void (*cleanup)(void)) +{ + int ret = 0; + + shutdown_secs = ssecs; + torture_shutdown_hook = cleanup; + if (shutdown_secs > 0) { + shutdown_time = jiffies + shutdown_secs * HZ; + ret = torture_create_kthread(torture_shutdown, NULL, + shutdown_task); + } + return ret; +} +EXPORT_SYMBOL_GPL(torture_shutdown_init); + +/* + * Detect and respond to a system shutdown. + */ +static int torture_shutdown_notify(struct notifier_block *unused1, + unsigned long unused2, void *unused3) +{ + mutex_lock(&fullstop_mutex); + if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) { + VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected"); + ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN; + } else { + pr_warn("Concurrent rmmod and shutdown illegal!\n"); + } + mutex_unlock(&fullstop_mutex); + return NOTIFY_DONE; +} + +static struct notifier_block torture_shutdown_nb = { + .notifier_call = torture_shutdown_notify, +}; + +/* + * Shut down the shutdown task. Say what??? Heh! This can happen if + * the torture module gets an rmmod before the shutdown time arrives. ;-) + */ +static void torture_shutdown_cleanup(void) +{ + unregister_reboot_notifier(&torture_shutdown_nb); + if (shutdown_task != NULL) { + VERBOSE_TOROUT_STRING("Stopping torture_shutdown task"); + kthread_stop(shutdown_task); + } + shutdown_task = NULL; +} + +/* + * Variables for stuttering, which means to periodically pause and + * restart testing in order to catch bugs that appear when load is + * suddenly applied to or removed from the system. + */ +static struct task_struct *stutter_task; +static int stutter_pause_test; +static int stutter; + +/* + * Block until the stutter interval ends. This must be called periodically + * by all running kthreads that need to be subject to stuttering. + */ +void stutter_wait(const char *title) +{ + while (ACCESS_ONCE(stutter_pause_test) || + (torture_runnable && !ACCESS_ONCE(*torture_runnable))) { + if (stutter_pause_test) + schedule_timeout_interruptible(1); + else + schedule_timeout_interruptible(round_jiffies_relative(HZ)); + torture_shutdown_absorb(title); + } +} +EXPORT_SYMBOL_GPL(stutter_wait); + +/* + * Cause the torture test to "stutter", starting and stopping all + * threads periodically. + */ +static int torture_stutter(void *arg) +{ + VERBOSE_TOROUT_STRING("torture_stutter task started"); + do { + if (!torture_must_stop()) { + schedule_timeout_interruptible(stutter); + ACCESS_ONCE(stutter_pause_test) = 1; + } + if (!torture_must_stop()) + schedule_timeout_interruptible(stutter); + ACCESS_ONCE(stutter_pause_test) = 0; + torture_shutdown_absorb("torture_stutter"); + } while (!torture_must_stop()); + torture_kthread_stopping("torture_stutter"); + return 0; +} + +/* + * Initialize and kick off the torture_stutter kthread. + */ +int torture_stutter_init(int s) +{ + int ret; + + stutter = s; + ret = torture_create_kthread(torture_stutter, NULL, stutter_task); + return ret; +} +EXPORT_SYMBOL_GPL(torture_stutter_init); + +/* + * Cleanup after the torture_stutter kthread. + */ +static void torture_stutter_cleanup(void) +{ + if (!stutter_task) + return; + VERBOSE_TOROUT_STRING("Stopping torture_stutter task"); + kthread_stop(stutter_task); + stutter_task = NULL; +} + +/* + * Initialize torture module. Please note that this is -not- invoked via + * the usual module_init() mechanism, but rather by an explicit call from + * the client torture module. This call must be paired with a later + * torture_init_end(). + * + * The runnable parameter points to a flag that controls whether or not + * the test is currently runnable. If there is no such flag, pass in NULL. + */ +void __init torture_init_begin(char *ttype, bool v, int *runnable) +{ + mutex_lock(&fullstop_mutex); + torture_type = ttype; + verbose = v; + torture_runnable = runnable; + fullstop = FULLSTOP_DONTSTOP; + +} +EXPORT_SYMBOL_GPL(torture_init_begin); + +/* + * Tell the torture module that initialization is complete. + */ +void __init torture_init_end(void) +{ + mutex_unlock(&fullstop_mutex); + register_reboot_notifier(&torture_shutdown_nb); +} +EXPORT_SYMBOL_GPL(torture_init_end); + +/* + * Clean up torture module. Please note that this is -not- invoked via + * the usual module_exit() mechanism, but rather by an explicit call from + * the client torture module. Returns true if a race with system shutdown + * is detected, otherwise, all kthreads started by functions in this file + * will be shut down. + * + * This must be called before the caller starts shutting down its own + * kthreads. + */ +bool torture_cleanup(void) +{ + mutex_lock(&fullstop_mutex); + if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + pr_warn("Concurrent rmmod and shutdown illegal!\n"); + mutex_unlock(&fullstop_mutex); + schedule_timeout_uninterruptible(10); + return true; + } + ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD; + mutex_unlock(&fullstop_mutex); + torture_shutdown_cleanup(); + torture_shuffle_cleanup(); + torture_stutter_cleanup(); + torture_onoff_cleanup(); + return false; +} +EXPORT_SYMBOL_GPL(torture_cleanup); + +/* + * Is it time for the current torture test to stop? + */ +bool torture_must_stop(void) +{ + return torture_must_stop_irq() || kthread_should_stop(); +} +EXPORT_SYMBOL_GPL(torture_must_stop); + +/* + * Is it time for the current torture test to stop? This is the irq-safe + * version, hence no check for kthread_should_stop(). + */ +bool torture_must_stop_irq(void) +{ + return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP; +} +EXPORT_SYMBOL_GPL(torture_must_stop_irq); + +/* + * Each kthread must wait for kthread_should_stop() before returning from + * its top-level function, otherwise segfaults ensue. This function + * prints a "stopping" message and waits for kthread_should_stop(), and + * should be called from all torture kthreads immediately prior to + * returning. + */ +void torture_kthread_stopping(char *title) +{ + if (verbose) + VERBOSE_TOROUT_STRING(title); + while (!kthread_should_stop()) { + torture_shutdown_absorb(title); + schedule_timeout_uninterruptible(1); + } +} +EXPORT_SYMBOL_GPL(torture_kthread_stopping); + +/* + * Create a generic torture kthread that is immediately runnable. If you + * need the kthread to be stopped so that you can do something to it before + * it starts, you will need to open-code your own. + */ +int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, + char *f, struct task_struct **tp) +{ + int ret = 0; + + VERBOSE_TOROUT_STRING(m); + *tp = kthread_run(fn, arg, s); + if (IS_ERR(*tp)) { + ret = PTR_ERR(*tp); + VERBOSE_TOROUT_ERRSTRING(f); + *tp = NULL; + } + torture_shuffle_task_register(*tp); + return ret; +} +EXPORT_SYMBOL_GPL(_torture_create_kthread); + +/* + * Stop a generic kthread, emitting a message. + */ +void _torture_stop_kthread(char *m, struct task_struct **tp) +{ + if (*tp == NULL) + return; + VERBOSE_TOROUT_STRING(m); + kthread_stop(*tp); + *tp = NULL; +} +EXPORT_SYMBOL_GPL(_torture_stop_kthread); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index a5457d577b98..0434ff1b808e 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -40,8 +40,8 @@ static int write_iteration = 50; module_param(write_iteration, uint, 0644); MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings"); -static int producer_nice = 19; -static int consumer_nice = 19; +static int producer_nice = MAX_NICE; +static int consumer_nice = MAX_NICE; static int producer_fifo = -1; static int consumer_fifo = -1; @@ -308,7 +308,7 @@ static void ring_buffer_producer(void) /* Let the user know that the test is running at low priority */ if (producer_fifo < 0 && consumer_fifo < 0 && - producer_nice == 19 && consumer_nice == 19) + producer_nice == MAX_NICE && consumer_nice == MAX_NICE) trace_printk("WARNING!!! This test is running at lowest priority.\n"); trace_printk("Time: %lld (usecs)\n", time); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 815c878f409b..24c1f2382557 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1600,15 +1600,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); +static struct ring_buffer *temp_buffer; + struct ring_buffer_event * trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, struct ftrace_event_file *ftrace_file, int type, unsigned long len, unsigned long flags, int pc) { + struct ring_buffer_event *entry; + *current_rb = ftrace_file->tr->trace_buffer.buffer; - return trace_buffer_lock_reserve(*current_rb, + entry = trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); + /* + * If tracing is off, but we have triggers enabled + * we still need to look at the event data. Use the temp_buffer + * to store the trace event for the tigger to use. It's recusive + * safe and will not be recorded anywhere. + */ + if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) { + *current_rb = temp_buffer; + entry = trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); + } + return entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); @@ -6494,11 +6510,16 @@ __init static int tracer_alloc_buffers(void) raw_spin_lock_init(&global_trace.start_lock); + /* Used for event triggers */ + temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); + if (!temp_buffer) + goto out_free_cpumask; + /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); - goto out_free_cpumask; + goto out_free_temp_buffer; } if (global_trace.buffer_disabled) @@ -6540,6 +6561,8 @@ __init static int tracer_alloc_buffers(void) return 0; +out_free_temp_buffer: + ring_buffer_free(temp_buffer); out_free_cpumask: free_percpu(global_trace.trace_buffer.data); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index e854f420e033..c894614de14d 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, } /* The ftrace function trace is allowed only for root. */ - if (ftrace_event_is_function(tp_event) && - perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + if (ftrace_event_is_function(tp_event)) { + if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (!p_event->attr.exclude_callchain_user) + return -EINVAL; + + /* + * Same reason to disable user stack dump as for user space + * callchains above. + */ + if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER) + return -EINVAL; + } /* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e71ffd4eccb5..7b16d40bd64d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -27,12 +27,6 @@ DEFINE_MUTEX(event_mutex); -DEFINE_MUTEX(event_storage_mutex); -EXPORT_SYMBOL_GPL(event_storage_mutex); - -char event_storage[EVENT_STORAGE_SIZE]; -EXPORT_SYMBOL_GPL(event_storage); - LIST_HEAD(ftrace_events); static LIST_HEAD(ftrace_common_fields); @@ -1777,6 +1771,16 @@ static void trace_module_add_events(struct module *mod) { struct ftrace_event_call **call, **start, **end; + if (!mod->num_trace_events) + return; + + /* Don't add infrastructure for mods without tracepoints */ + if (trace_module_has_bad_taint(mod)) { + pr_err("%s: module has bad taint, not creating trace events\n", + mod->name); + return; + } + start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 7c3e3e72e2b6..ee0a5098ac43 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __array #define __array(type, item, len) \ do { \ + char *type_str = #type"["__stringify(len)"]"; \ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - mutex_lock(&event_storage_mutex); \ - snprintf(event_storage, sizeof(event_storage), \ - "%s[%d]", #type, len); \ - ret = trace_define_field(event_call, event_storage, #item, \ + ret = trace_define_field(event_call, type_str, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), filter_type); \ - mutex_unlock(&event_storage_mutex); \ if (ret) \ return ret; \ } while (0); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 2aefbee93a6d..887ef88b0bc7 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -498,14 +498,14 @@ void trace_hardirqs_off(void) } EXPORT_SYMBOL(trace_hardirqs_off); -void trace_hardirqs_on_caller(unsigned long caller_addr) +__visible void trace_hardirqs_on_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); -void trace_hardirqs_off_caller(unsigned long caller_addr) +__visible void trace_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 29f26540e9c9..031cc5655a51 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) EXPORT_SYMBOL_GPL(tracepoint_iter_reset); #ifdef CONFIG_MODULES +bool trace_module_has_bad_taint(struct module *mod) +{ + return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)); +} + static int tracepoint_module_coming(struct module *mod) { struct tp_module *tp_mod, *iter; @@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod) * module headers (for forced load), to make sure we don't cause a crash. * Staging and out-of-tree GPL modules are fine. */ - if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP))) + if (trace_module_has_bad_taint(mod)) return 0; mutex_lock(&tracepoints_mutex); tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 193e977a10ea..3fa5b8f3aae3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3225,7 +3225,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, return -ENOMEM; if (sscanf(buf, "%d", &attrs->nice) == 1 && - attrs->nice >= -20 && attrs->nice <= 19) + attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs(wq, attrs); else ret = -EINVAL; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a48abeac753f..dd7f8858188a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -980,6 +980,21 @@ config DEBUG_LOCKING_API_SELFTESTS The following locking APIs are covered: spinlocks, rwlocks, mutexes and rwsems. +config LOCK_TORTURE_TEST + tristate "torture tests for locking" + depends on DEBUG_KERNEL + select TORTURE_TEST + default n + help + This option provides a kernel module that runs torture tests + on kernel locking primitives. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want kernel locking-primitive torture tests + to be built into the kernel. + Say M if you want these torture tests to build as a module. + Say N if you are unsure. + endmenu # lock debugging config TRACE_IRQFLAGS @@ -1141,9 +1156,14 @@ config SPARSE_RCU_POINTER Say N if you are unsure. +config TORTURE_TEST + tristate + default n + config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL + select TORTURE_TEST default n help This option provides a kernel module that runs torture tests diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 2defd1308b04..98f2d7e91a91 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -424,111 +424,134 @@ void debug_dma_dump_mappings(struct device *dev) EXPORT_SYMBOL(debug_dma_dump_mappings); /* - * For each page mapped (initial page in the case of - * dma_alloc_coherent/dma_map_{single|page}, or each page in a - * scatterlist) insert into this tree using the pfn as the key. At + * For each mapping (initial cacheline in the case of + * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a + * scatterlist, or the cacheline specified in dma_map_single) insert + * into this tree using the cacheline as the key. At * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If - * the pfn already exists at insertion time add a tag as a reference + * the entry already exists at insertion time add a tag as a reference * count for the overlapping mappings. For now, the overlap tracking - * just ensures that 'unmaps' balance 'maps' before marking the pfn - * idle, but we should also be flagging overlaps as an API violation. + * just ensures that 'unmaps' balance 'maps' before marking the + * cacheline idle, but we should also be flagging overlaps as an API + * violation. * * Memory usage is mostly constrained by the maximum number of available * dma-debug entries in that we need a free dma_debug_entry before - * inserting into the tree. In the case of dma_map_{single|page} and - * dma_alloc_coherent there is only one dma_debug_entry and one pfn to - * track per event. dma_map_sg(), on the other hand, - * consumes a single dma_debug_entry, but inserts 'nents' entries into - * the tree. + * inserting into the tree. In the case of dma_map_page and + * dma_alloc_coherent there is only one dma_debug_entry and one + * dma_active_cacheline entry to track per event. dma_map_sg(), on the + * other hand, consumes a single dma_debug_entry, but inserts 'nents' + * entries into the tree. * * At any time debug_dma_assert_idle() can be called to trigger a - * warning if the given page is in the active set. + * warning if any cachelines in the given page are in the active set. */ -static RADIX_TREE(dma_active_pfn, GFP_NOWAIT); +static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT); static DEFINE_SPINLOCK(radix_lock); -#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) +#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT) -static int active_pfn_read_overlap(unsigned long pfn) +static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry) +{ + return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) + + (entry->offset >> L1_CACHE_SHIFT); +} + +static int active_cacheline_read_overlap(phys_addr_t cln) { int overlap = 0, i; for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) - if (radix_tree_tag_get(&dma_active_pfn, pfn, i)) + if (radix_tree_tag_get(&dma_active_cacheline, cln, i)) overlap |= 1 << i; return overlap; } -static int active_pfn_set_overlap(unsigned long pfn, int overlap) +static int active_cacheline_set_overlap(phys_addr_t cln, int overlap) { int i; - if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0) + if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0) return overlap; for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) if (overlap & 1 << i) - radix_tree_tag_set(&dma_active_pfn, pfn, i); + radix_tree_tag_set(&dma_active_cacheline, cln, i); else - radix_tree_tag_clear(&dma_active_pfn, pfn, i); + radix_tree_tag_clear(&dma_active_cacheline, cln, i); return overlap; } -static void active_pfn_inc_overlap(unsigned long pfn) +static void active_cacheline_inc_overlap(phys_addr_t cln) { - int overlap = active_pfn_read_overlap(pfn); + int overlap = active_cacheline_read_overlap(cln); - overlap = active_pfn_set_overlap(pfn, ++overlap); + overlap = active_cacheline_set_overlap(cln, ++overlap); /* If we overflowed the overlap counter then we're potentially * leaking dma-mappings. Otherwise, if maps and unmaps are * balanced then this overflow may cause false negatives in - * debug_dma_assert_idle() as the pfn may be marked idle + * debug_dma_assert_idle() as the cacheline may be marked idle * prematurely. */ - WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP, - "DMA-API: exceeded %d overlapping mappings of pfn %lx\n", - ACTIVE_PFN_MAX_OVERLAP, pfn); + WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, + "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n", + ACTIVE_CACHELINE_MAX_OVERLAP, &cln); } -static int active_pfn_dec_overlap(unsigned long pfn) +static int active_cacheline_dec_overlap(phys_addr_t cln) { - int overlap = active_pfn_read_overlap(pfn); + int overlap = active_cacheline_read_overlap(cln); - return active_pfn_set_overlap(pfn, --overlap); + return active_cacheline_set_overlap(cln, --overlap); } -static int active_pfn_insert(struct dma_debug_entry *entry) +static int active_cacheline_insert(struct dma_debug_entry *entry) { + phys_addr_t cln = to_cacheline_number(entry); unsigned long flags; int rc; + /* If the device is not writing memory then we don't have any + * concerns about the cpu consuming stale data. This mitigates + * legitimate usages of overlapping mappings. + */ + if (entry->direction == DMA_TO_DEVICE) + return 0; + spin_lock_irqsave(&radix_lock, flags); - rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry); + rc = radix_tree_insert(&dma_active_cacheline, cln, entry); if (rc == -EEXIST) - active_pfn_inc_overlap(entry->pfn); + active_cacheline_inc_overlap(cln); spin_unlock_irqrestore(&radix_lock, flags); return rc; } -static void active_pfn_remove(struct dma_debug_entry *entry) +static void active_cacheline_remove(struct dma_debug_entry *entry) { + phys_addr_t cln = to_cacheline_number(entry); unsigned long flags; + /* ...mirror the insert case */ + if (entry->direction == DMA_TO_DEVICE) + return; + spin_lock_irqsave(&radix_lock, flags); /* since we are counting overlaps the final put of the - * entry->pfn will occur when the overlap count is 0. - * active_pfn_dec_overlap() returns -1 in that case + * cacheline will occur when the overlap count is 0. + * active_cacheline_dec_overlap() returns -1 in that case */ - if (active_pfn_dec_overlap(entry->pfn) < 0) - radix_tree_delete(&dma_active_pfn, entry->pfn); + if (active_cacheline_dec_overlap(cln) < 0) + radix_tree_delete(&dma_active_cacheline, cln); spin_unlock_irqrestore(&radix_lock, flags); } /** * debug_dma_assert_idle() - assert that a page is not undergoing dma - * @page: page to lookup in the dma_active_pfn tree + * @page: page to lookup in the dma_active_cacheline tree * * Place a call to this routine in cases where the cpu touching the page * before the dma completes (page is dma_unmapped) will lead to data @@ -536,22 +559,38 @@ static void active_pfn_remove(struct dma_debug_entry *entry) */ void debug_dma_assert_idle(struct page *page) { + static struct dma_debug_entry *ents[CACHELINES_PER_PAGE]; + struct dma_debug_entry *entry = NULL; + void **results = (void **) &ents; + unsigned int nents, i; unsigned long flags; - struct dma_debug_entry *entry; + phys_addr_t cln; if (!page) return; + cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT; spin_lock_irqsave(&radix_lock, flags); - entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page)); + nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln, + CACHELINES_PER_PAGE); + for (i = 0; i < nents; i++) { + phys_addr_t ent_cln = to_cacheline_number(ents[i]); + + if (ent_cln == cln) { + entry = ents[i]; + break; + } else if (ent_cln >= cln + CACHELINES_PER_PAGE) + break; + } spin_unlock_irqrestore(&radix_lock, flags); if (!entry) return; + cln = to_cacheline_number(entry); err_printk(entry->dev, entry, - "DMA-API: cpu touching an active dma mapped page " - "[pfn=0x%lx]\n", entry->pfn); + "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n", + &cln); } /* @@ -568,9 +607,9 @@ static void add_dma_entry(struct dma_debug_entry *entry) hash_bucket_add(bucket, entry); put_hash_bucket(bucket, &flags); - rc = active_pfn_insert(entry); + rc = active_cacheline_insert(entry); if (rc == -ENOMEM) { - pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n"); + pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } @@ -631,7 +670,7 @@ static void dma_entry_free(struct dma_debug_entry *entry) { unsigned long flags; - active_pfn_remove(entry); + active_cacheline_remove(entry); /* * add to beginning of the list - this way the entries are diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig index 4dc1b990aa23..34fd931b54b5 100644 --- a/lib/fonts/Kconfig +++ b/lib/fonts/Kconfig @@ -9,7 +9,7 @@ if FONT_SUPPORT config FONTS bool "Select compiled-in fonts" - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE help Say Y here if you would like to use fonts other than the default your frame buffer console usually use. @@ -22,7 +22,7 @@ config FONTS config FONT_8x8 bool "VGA 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE default y if !SPARC && !FONTS help This is the "high resolution" font for the VGA frame buffer (the one @@ -45,7 +45,7 @@ config FONT_8x16 config FONT_6x11 bool "Mac console 6x11 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE default y if !SPARC && !FONTS && MAC help Small console font with Macintosh-style high-half glyphs. Some Mac diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 7811ed3b4e70..bd4a8dfdf0b8 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1253,8 +1253,10 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) node = indirect_to_ptr(node); max_index = radix_tree_maxindex(node->height); - if (cur_index > max_index) + if (cur_index > max_index) { + rcu_read_unlock(); break; + } cur_index = __locate(node, item, cur_index, &found_index); rcu_read_unlock(); diff --git a/lib/random32.c b/lib/random32.c index 1e5b2df44291..614896778700 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -244,8 +244,19 @@ static void __prandom_reseed(bool late) static bool latch = false; static DEFINE_SPINLOCK(lock); + /* Asking for random bytes might result in bytes getting + * moved into the nonblocking pool and thus marking it + * as initialized. In this case we would double back into + * this function and attempt to do a late reseed. + * Ignore the pointless attempt to reseed again if we're + * already waiting for bytes when the nonblocking pool + * got initialized. + */ + /* only allow initial seeding (late == false) once */ - spin_lock_irqsave(&lock, flags); + if (!spin_trylock_irqsave(&lock, flags)) + return; + if (latch && !late) goto out; latch = true; diff --git a/lib/string.c b/lib/string.c index e5878de4f101..9b1f9062a202 100644 --- a/lib/string.c +++ b/lib/string.c @@ -648,7 +648,7 @@ EXPORT_SYMBOL(memmove); * @count: The size of the area. */ #undef memcmp -int memcmp(const void *cs, const void *ct, size_t count) +__visible int memcmp(const void *cs, const void *ct, size_t count) { const unsigned char *su1, *su2; int res = 0; diff --git a/mm/Kconfig b/mm/Kconfig index 2d9f1504d75e..2888024e0b0a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -575,5 +575,5 @@ config PGTABLE_MAPPING then you should select this. This causes zsmalloc to use page table mapping rather than copying for object mapping. - You can check speed with zsmalloc benchmark[1]. - [1] https://github.com/spartacus06/zsmalloc + You can check speed with zsmalloc benchmark: + https://github.com/spartacus06/zsmapbench diff --git a/mm/compaction.c b/mm/compaction.c index b48c5259ea33..918577595ea8 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -251,7 +251,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, { int nr_scanned = 0, total_isolated = 0; struct page *cursor, *valid_page = NULL; - unsigned long nr_strict_required = end_pfn - blockpfn; unsigned long flags; bool locked = false; @@ -264,11 +263,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, nr_scanned++; if (!pfn_valid_within(blockpfn)) - continue; + goto isolate_fail; + if (!valid_page) valid_page = page; if (!PageBuddy(page)) - continue; + goto isolate_fail; /* * The zone lock must be held to isolate freepages. @@ -289,12 +289,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) - continue; + goto isolate_fail; /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); - if (!isolated && strict) - break; total_isolated += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); @@ -305,7 +303,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (isolated) { blockpfn += isolated - 1; cursor += isolated - 1; + continue; } + +isolate_fail: + if (strict) + break; + else + continue; + } trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); @@ -315,7 +321,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, * pages requested were isolated. If there were any failures, 0 is * returned and CMA will fail. */ - if (strict && nr_strict_required > total_isolated) + if (strict && blockpfn < end_pfn) total_isolated = 0; if (locked) diff --git a/mm/fremap.c b/mm/fremap.c index bbc4d660221a..34feba60a17e 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -23,28 +23,44 @@ #include "internal.h" +static int mm_counter(struct page *page) +{ + return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; +} + static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page; + swp_entry_t entry; if (pte_present(pte)) { - struct page *page; - flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); page = vm_normal_page(vma, addr, pte); if (page) { if (pte_dirty(pte)) set_page_dirty(page); + update_hiwater_rss(mm); + dec_mm_counter(mm, mm_counter(page)); page_remove_rmap(page); page_cache_release(page); + } + } else { /* zap_pte() is not called when pte_none() */ + if (!pte_file(pte)) { update_hiwater_rss(mm); - dec_mm_counter(mm, MM_FILEPAGES); + entry = pte_to_swp_entry(pte); + if (non_swap_entry(entry)) { + if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + dec_mm_counter(mm, mm_counter(page)); + } + } else { + free_swap_and_cache(entry); + dec_mm_counter(mm, MM_SWAPENTS); + } } - } else { - if (!pte_file(pte)) - free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear_not_present_full(mm, addr, ptep, 0); } } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4df39b1bde91..1546655a2d78 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1961,7 +1961,7 @@ out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) @@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item) static struct page *page_trans_compound_anon(struct page *page) { if (PageTransCompound(page)) { - struct page *head = compound_trans_head(page); + struct page *head = compound_head(page); /* * head may actually be splitted and freed from under * us but it's ok here. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ce7a8cc7b404..5b6b0039f725 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1127,8 +1127,8 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css->flags & CSS_ONLINE) && - (next_css == &root->css || css_tryget(next_css))) + if ((next_css == &root->css) || + ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -6595,6 +6595,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event, *tmp; + struct cgroup_subsys_state *iter; /* * Unregister events and notify userspace. @@ -6611,7 +6612,14 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) kmem_cgroup_css_offline(memcg); mem_cgroup_invalidate_reclaim_iterators(memcg); - mem_cgroup_reparent_charges(memcg); + + /* + * This requires that offlining is serialized. Right now that is + * guaranteed because css_killed_work_fn() holds the cgroup_mutex. + */ + css_for_each_descendant_post(iter, css) + mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); + mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2f2f34a4e77d..90002ea43638 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1651,7 +1651,7 @@ int soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); + struct page *hpage = compound_head(page); if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index eeb2e3d2c962..4755c8576942 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2301,35 +2301,6 @@ static void sp_free(struct sp_node *n) kmem_cache_free(sn_cache, n); } -#ifdef CONFIG_NUMA_BALANCING -static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) -{ - /* Never defer a private fault */ - if (cpupid_match_pid(p, last_cpupid)) - return false; - - if (p->numa_migrate_deferred) { - p->numa_migrate_deferred--; - return true; - } - return false; -} - -static inline void defer_numa_migrate(struct task_struct *p) -{ - p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred; -} -#else -static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) -{ - return false; -} - -static inline void defer_numa_migrate(struct task_struct *p) -{ -} -#endif /* CONFIG_NUMA_BALANCING */ - /** * mpol_misplaced - check whether current page node is valid in policy * @@ -2403,52 +2374,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { - int last_cpupid; - int this_cpupid; - polnid = thisnid; - this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid); - - /* - * Multi-stage node selection is used in conjunction - * with a periodic migration fault to build a temporal - * task<->page relation. By using a two-stage filter we - * remove short/unlikely relations. - * - * Using P(p) ~ n_p / n_t as per frequentist - * probability, we can equate a task's usage of a - * particular page (n_p) per total usage of this - * page (n_t) (in a given time-span) to a probability. - * - * Our periodic faults will sample this probability and - * getting the same result twice in a row, given these - * samples are fully independent, is then given by - * P(n)^2, provided our sample period is sufficiently - * short compared to the usage pattern. - * - * This quadric squishes small probabilities, making - * it less likely we act on an unlikely task<->page - * relation. - */ - last_cpupid = page_cpupid_xchg_last(page, this_cpupid); - if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) { - /* See sysctl_numa_balancing_migrate_deferred comment */ - if (!cpupid_match_pid(current, last_cpupid)) - defer_numa_migrate(current); - - goto out; - } - - /* - * The quadratic filter above reduces extraneous migration - * of shared pages somewhat. This code reduces it even more, - * reducing the overhead of page migrations of shared pages. - * This makes workloads with shared pages rely more on - * "move task near its memory", and less on "move memory - * towards its task", which is exactly what we want. - */ - if (numa_migrate_deferred(current, last_cpupid)) + if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } diff --git a/mm/migrate.c b/mm/migrate.c index 482a33d89134..bed48809e5d0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -178,6 +178,37 @@ out: } /* + * Congratulations to trinity for discovering this bug. + * mm/fremap.c's remap_file_pages() accepts any range within a single vma to + * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then + * replace the specified range by file ptes throughout (maybe populated after). + * If page migration finds a page within that range, while it's still located + * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: + * zap_pte() clears the temporary migration entry before mmap_sem is dropped. + * But if the migrating page is in a part of the vma outside the range to be + * remapped, then it will not be cleared, and remove_migration_ptes() needs to + * deal with it. Fortunately, this part of the vma is of course still linear, + * so we just need to use linear location on the nonlinear list. + */ +static int remove_linear_migration_ptes_from_nonlinear(struct page *page, + struct address_space *mapping, void *arg) +{ + struct vm_area_struct *vma; + /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ + pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + unsigned long addr; + + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + if (addr >= vma->vm_start && addr < vma->vm_end) + remove_migration_pte(page, vma, addr, arg); + } + return SWAP_AGAIN; +} + +/* * Get rid of all migration entries and replace them by * references to the indicated page. */ @@ -186,6 +217,7 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, + .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); @@ -1158,7 +1190,7 @@ static struct page *new_page_node(struct page *p, unsigned long private, pm->node); else return alloc_pages_exact_node(pm->node, - GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); + GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } /* @@ -1544,9 +1576,9 @@ static struct page *alloc_misplaced_dst_page(struct page *page, struct page *newpage; newpage = alloc_pages_exact_node(nid, - (GFP_HIGHUSER_MOVABLE | GFP_THISNODE | - __GFP_NOMEMALLOC | __GFP_NORETRY | - __GFP_NOWARN) & + (GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_NOWARN) & ~GFP_IOFS, 0); return newpage; @@ -1747,7 +1779,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_dropref; new_page = alloc_pages_node(node, - (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); + (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT, + HPAGE_PMD_ORDER); if (!new_page) goto out_fail; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3758a09a009..3bac76ae4b30 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - __SetPageTail(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } @@ -1236,6 +1238,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) } local_irq_restore(flags); } +static bool gfp_thisnode_allocation(gfp_t gfp_mask) +{ + return (gfp_mask & GFP_THISNODE) == GFP_THISNODE; +} +#else +static bool gfp_thisnode_allocation(gfp_t gfp_mask) +{ + return false; +} #endif /* @@ -1572,7 +1583,13 @@ again: get_pageblock_migratetype(page)); } - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + /* + * NOTE: GFP_THISNODE allocations do not partake in the kswapd + * aging protocol, so they can't be fair. + */ + if (!gfp_thisnode_allocation(gfp_flags)) + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); @@ -1944,8 +1961,12 @@ zonelist_scan: * ultimately fall back to remote zones that do not * partake in the fairness round-robin cycle of this * zonelist. + * + * NOTE: GFP_THISNODE allocations do not partake in + * the kswapd aging protocol, so they can't be fair. */ - if (alloc_flags & ALLOC_WMARK_LOW) { + if ((alloc_flags & ALLOC_WMARK_LOW) && + !gfp_thisnode_allocation(gfp_mask)) { if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) continue; if (!zone_local(preferred_zone, zone)) @@ -2501,8 +2522,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * allowed per node queues are empty and that nodes are * over allocated. */ - if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + if (gfp_thisnode_allocation(gfp_mask)) goto nopage; restart: diff --git a/mm/rmap.c b/mm/rmap.c index d9d42316a99a..8fc049f9a5a6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1360,8 +1360,9 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, } static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, struct vm_area_struct *vma) + struct address_space *mapping, void *arg) { + struct vm_area_struct *vma; int ret = SWAP_AGAIN; unsigned long cursor; unsigned long max_nl_cursor = 0; @@ -1663,7 +1664,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) if (list_empty(&mapping->i_mmap_nonlinear)) goto done; - ret = rwc->file_nonlinear(page, mapping, vma); + ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: mutex_unlock(&mapping->i_mmap_mutex); diff --git a/mm/swap.c b/mm/swap.c index b31ba67d440a..0092097b3f4c 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -98,7 +98,7 @@ static void put_compound_page(struct page *page) } /* __split_huge_page_refcount can run under us */ - page_head = compound_trans_head(page); + page_head = compound_head(page); /* * THP can not break up slab pages so avoid taking @@ -253,7 +253,7 @@ bool __get_page_tail(struct page *page) */ unsigned long flags; bool got; - struct page *page_head = compound_trans_head(page); + struct page *page_head = compound_head(page); /* Ref to put_compound_page() comment. */ if (!__compound_tail_refcounted(page_head)) { diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ec9909935fb6..175273f38cb1 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -307,9 +307,11 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { + struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); + vlandev->gso_max_size = dev->gso_max_size; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index de51c48c4393..27bfe2f8e2de 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -538,6 +538,9 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; + if (saddr == NULL) + saddr = dev->dev_addr; + return dev_hard_header(skb, real_dev, type, daddr, saddr, len); } @@ -575,6 +578,9 @@ static int vlan_dev_init(struct net_device *dev) dev->features |= real_dev->vlan_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; + if (dev->features & NETIF_F_VLAN_FEATURES) + netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); + /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; @@ -589,7 +595,8 @@ static int vlan_dev_init(struct net_device *dev) #endif dev->needed_headroom = real_dev->needed_headroom; - if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) { + if (vlan_hw_offload_capable(real_dev->features, + vlan_dev_priv(dev)->vlan_proto)) { dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 63f0455c0bc3..8fe8b71b487a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -49,14 +49,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) brstats->tx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); - if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) - goto out; - BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); + if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + goto out; + if (is_broadcast_ether_addr(dest)) br_flood_deliver(br, skb, false); else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 28d544627422..d0cca3c65f01 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -29,6 +29,7 @@ static int br_pass_frame_up(struct sk_buff *skb) struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); + struct net_port_vlans *pv; u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; @@ -39,18 +40,18 @@ static int br_pass_frame_up(struct sk_buff *skb) * packet is allowed except in promisc modue when someone * may be running packet capture. */ + pv = br_get_vlan_info(br); if (!(brdev->flags & IFF_PROMISC) && - !br_allowed_egress(br, br_get_vlan_info(br), skb)) { + !br_allowed_egress(br, pv, skb)) { kfree_skb(skb); return NET_RX_DROP; } - skb = br_handle_vlan(br, br_get_vlan_info(br), skb); - if (!skb) - return NET_RX_DROP; - indev = skb->dev; skb->dev = brdev; + skb = br_handle_vlan(br, pv, skb); + if (!skb) + return NET_RX_DROP; return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, netif_receive_skb); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ef66365b7354..93067ecdb9a2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1127,9 +1127,10 @@ static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_querier *querier, int saddr, + bool is_general_query, unsigned long max_delay) { - if (saddr) + if (saddr && is_general_query) br_multicast_update_querier_timer(br, querier, max_delay); else if (timer_pending(&querier->timer)) return; @@ -1181,8 +1182,16 @@ static int br_ip4_multicast_query(struct net_bridge *br, IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr, - max_delay); + !group, max_delay); if (!group) goto out; @@ -1228,6 +1237,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long max_delay; unsigned long now = jiffies; const struct in6_addr *group = NULL; + bool is_general_query; int err = 0; spin_lock(&br->multicast_lock); @@ -1235,6 +1245,12 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { + err = -EINVAL; + goto out; + } + if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1256,8 +1272,19 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } + is_general_query = group && ipv6_addr_any(group); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip6_querier, - !ipv6_addr_any(&ip6h->saddr), max_delay); + !ipv6_addr_any(&ip6h->saddr), + is_general_query, max_delay); if (!group) goto out; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 8249ca764c79..f23c74b3a953 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -119,22 +119,6 @@ static void __vlan_flush(struct net_port_vlans *v) kfree_rcu(v, rcu); } -/* Strip the tag from the packet. Will return skb with tci set 0. */ -static struct sk_buff *br_vlan_untag(struct sk_buff *skb) -{ - if (skb->protocol != htons(ETH_P_8021Q)) { - skb->vlan_tci = 0; - return skb; - } - - skb->vlan_tci = 0; - skb = vlan_untag(skb); - if (skb) - skb->vlan_tci = 0; - - return skb; -} - struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_port_vlans *pv, struct sk_buff *skb) @@ -144,13 +128,27 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, if (!br->vlan_enabled) goto out; + /* Vlan filter table must be configured at this point. The + * only exception is the bridge is set in promisc mode and the + * packet is destined for the bridge device. In this case + * pass the packet as is. + */ + if (!pv) { + if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { + goto out; + } else { + kfree_skb(skb); + return NULL; + } + } + /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id is set in the untagged bitmap, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); if (test_bit(vid, pv->untagged_bitmap)) - skb = br_vlan_untag(skb); + skb->vlan_tci = 0; out: return skb; @@ -174,6 +172,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) return false; + /* If vlan tx offload is disabled on bridge device and frame was + * sent from vlan device on the bridge device, it does not have + * HW accelerated vlan tag. + */ + if (unlikely(!vlan_tx_tag_present(skb) && + (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)))) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + return false; + } + err = br_vlan_get_tag(skb, vid); if (!*vid) { u16 pvid = br_get_pvid(v); diff --git a/net/can/raw.c b/net/can/raw.c index 8be757cca2ec..081e81fd017f 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -121,13 +121,9 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->recv_own_msgs && oskb->sk == sk) return; - /* do not pass frames with DLC > 8 to a legacy socket */ - if (!ro->fd_frames) { - struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; - - if (unlikely(cfd->len > CAN_MAX_DLEN)) - return; - } + /* do not pass non-CAN2.0 frames to a legacy socket */ + if (!ro->fd_frames && oskb->len != CAN_MTU) + return; /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); @@ -738,9 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct raw_sock *ro = raw_sk(sk); struct sk_buff *skb; - int rxmtu; int err = 0; int noblock; @@ -751,20 +745,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - /* - * when serving a legacy socket the DLC <= 8 is already checked inside - * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy - * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU - */ - if (!ro->fd_frames) - rxmtu = CAN_MTU; - else - rxmtu = skb->len; - - if (size < rxmtu) + if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else - size = rxmtu; + size = skb->len; err = memcpy_toiovec(msg->msg_iov, skb->data, size); if (err < 0) { diff --git a/net/core/dev.c b/net/core/dev.c index b1b0c8d4d7df..45fa2f11f84d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2286,7 +2286,7 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -__be16 skb_network_protocol(struct sk_buff *skb) +__be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; int vlan_depth = ETH_HLEN; @@ -2313,6 +2313,8 @@ __be16 skb_network_protocol(struct sk_buff *skb) vlan_depth += VLAN_HLEN; } + *depth = vlan_depth; + return type; } @@ -2326,12 +2328,13 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; - __be16 type = skb_network_protocol(skb); + int vlan_depth = skb->mac_len; + __be16 type = skb_network_protocol(skb, &vlan_depth); if (unlikely(!type)) return ERR_PTR(-EINVAL); - __skb_pull(skb, skb->mac_len); + __skb_pull(skb, vlan_depth); rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { @@ -2498,8 +2501,10 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, const struct net_device *dev, netdev_features_t features) { + int tmp; + if (skb->ip_summed != CHECKSUM_NONE && - !can_checksum_protocol(features, skb_network_protocol(skb))) { + !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) { features &= ~NETIF_F_ALL_CSUM; } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b9e9e0d38672..e16129019c66 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -766,9 +766,6 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) - goto out; - /* * periodically recompute ReachableTime from random function */ @@ -781,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; @@ -3046,7 +3046,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (!t) goto err; - for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; t->neigh_vars[i].extra2 = p; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a664f7829a6d..df9e6b1a9759 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -742,7 +742,7 @@ static bool pkt_is_ns(struct sk_buff *skb) struct nd_msg *msg; struct ipv6hdr *hdr; - if (skb->protocol != htons(ETH_P_ARP)) + if (skb->protocol != htons(ETH_P_IPV6)) return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) return false; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1a0dac2ef9ad..120eecc0f5a4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2121,12 +2121,13 @@ EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u32 pid, u32 seq, - int type, unsigned int flags) + int type, unsigned int flags, + int nlflags) { struct nlmsghdr *nlh; struct ndmsg *ndm; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags); if (!nlh) return -EMSGSIZE; @@ -2164,7 +2165,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) if (!skb) goto errout; - err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF); + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); if (err < 0) { kfree_skb(skb); goto errout; @@ -2389,7 +2390,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, portid, seq, - RTM_NEWNEIGH, NTF_SELF); + RTM_NEWNEIGH, NTF_SELF, + NLM_F_MULTI); if (err < 0) return err; skip: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5976ef0846bd..90b96a11b974 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT @@ -2130,25 +2127,31 @@ EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. + * + * Return value: + * 0: everything is OK + * -ENOMEM: couldn't orphan frags of @from due to lack of memory + * -EFAULT: skb_copy_bits() found some problem with skb geometry */ -void -skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) +int +skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ + int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ - if (len <= skb_tailroom(to)) { - skb_copy_bits(from, 0, skb_put(to, len), len); - return; - } + if (len <= skb_tailroom(to)) + return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { - skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + if (unlikely(ret)) + return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); @@ -2166,6 +2169,11 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) to->len += len + plen; to->data_len += len + plen; + if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { + skb_tx_error(from); + return -ENOMEM; + } + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { if (!len) break; @@ -2176,6 +2184,8 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) j++; } skb_shinfo(to)->nr_frags = j; + + return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); @@ -2841,81 +2851,85 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); /** * skb_segment - Perform protocol segmentation on skb. - * @skb: buffer to segment + * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) +struct sk_buff *skb_segment(struct sk_buff *head_skb, + netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; - struct sk_buff *fskb = skb_shinfo(skb)->frag_list; - skb_frag_t *skb_frag = skb_shinfo(skb)->frags; - unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int doffset = skb->data - skb_mac_header(skb); + struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; + skb_frag_t *frag = skb_shinfo(head_skb)->frags; + unsigned int mss = skb_shinfo(head_skb)->gso_size; + unsigned int doffset = head_skb->data - skb_mac_header(head_skb); + struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; - unsigned int tnl_hlen = skb_tnl_header_len(skb); + unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int headroom; unsigned int len; __be16 proto; bool csum; int sg = !!(features & NETIF_F_SG); - int nfrags = skb_shinfo(skb)->nr_frags; + int nfrags = skb_shinfo(head_skb)->nr_frags; int err = -ENOMEM; int i = 0; int pos; + int dummy; - proto = skb_network_protocol(skb); + proto = skb_network_protocol(head_skb, &dummy); if (unlikely(!proto)) return ERR_PTR(-EINVAL); csum = !!can_checksum_protocol(features, proto); - __skb_push(skb, doffset); - headroom = skb_headroom(skb); - pos = skb_headlen(skb); + __skb_push(head_skb, doffset); + headroom = skb_headroom(head_skb); + pos = skb_headlen(head_skb); do { struct sk_buff *nskb; - skb_frag_t *frag; + skb_frag_t *nskb_frag; int hsize; int size; - len = skb->len - offset; + len = head_skb->len - offset; if (len > mss) len = mss; - hsize = skb_headlen(skb) - offset; + hsize = skb_headlen(head_skb) - offset; if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; - if (!hsize && i >= nfrags && skb_headlen(fskb) && - (skb_headlen(fskb) == len || sg)) { - BUG_ON(skb_headlen(fskb) > len); + if (!hsize && i >= nfrags && skb_headlen(list_skb) && + (skb_headlen(list_skb) == len || sg)) { + BUG_ON(skb_headlen(list_skb) > len); i = 0; - nfrags = skb_shinfo(fskb)->nr_frags; - skb_frag = skb_shinfo(fskb)->frags; - pos += skb_headlen(fskb); + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); - size = skb_frag_size(skb_frag); + size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; - skb_frag++; + frag++; } - nskb = skb_clone(fskb, GFP_ATOMIC); - fskb = fskb->next; + nskb = skb_clone(list_skb, GFP_ATOMIC); + list_skb = list_skb->next; if (unlikely(!nskb)) goto err; @@ -2936,7 +2950,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) __skb_push(nskb, doffset); } else { nskb = __alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC, skb_alloc_rx_flag(skb), + GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) @@ -2952,12 +2966,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) segs = nskb; tail = nskb; - __copy_skb_header(nskb, skb); - nskb->mac_len = skb->mac_len; + __copy_skb_header(nskb, head_skb); + nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); - skb_copy_from_linear_data_offset(skb, -tnl_hlen, + skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); @@ -2966,30 +2980,32 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (!sg) { nskb->ip_summed = CHECKSUM_NONE; - nskb->csum = skb_copy_and_csum_bits(skb, offset, + nskb->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len, 0); continue; } - frag = skb_shinfo(nskb)->frags; + nskb_frag = skb_shinfo(nskb)->frags; - skb_copy_from_linear_data_offset(skb, offset, + skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags & + SKBTX_SHARED_FRAG; while (pos < offset + len) { if (i >= nfrags) { - BUG_ON(skb_headlen(fskb)); + BUG_ON(skb_headlen(list_skb)); i = 0; - nfrags = skb_shinfo(fskb)->nr_frags; - skb_frag = skb_shinfo(fskb)->frags; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; BUG_ON(!nfrags); - fskb = fskb->next; + list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= @@ -3000,27 +3016,30 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) goto err; } - *frag = *skb_frag; - __skb_frag_ref(frag); - size = skb_frag_size(frag); + if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) + goto err; + + *nskb_frag = *frag; + __skb_frag_ref(nskb_frag); + size = skb_frag_size(nskb_frag); if (pos < offset) { - frag->page_offset += offset - pos; - skb_frag_size_sub(frag, offset - pos); + nskb_frag->page_offset += offset - pos; + skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; - skb_frag++; + frag++; pos += size; } else { - skb_frag_size_sub(frag, pos + size - (offset + len)); + skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } - frag++; + nskb_frag++; } skip_fraglist: @@ -3034,7 +3053,7 @@ perform_csum_check: nskb->len - doffset, 0); nskb->ip_summed = CHECKSUM_NONE; } - } while ((offset += len) < skb->len); + } while ((offset += len) < head_skb->len); return segs; diff --git a/net/core/sock.c b/net/core/sock.c index 5b6a9431b017..c0fc6bdad1e3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2357,10 +2357,13 @@ void release_sock(struct sock *sk) if (sk->sk_backlog.tail) __release_sock(sk); + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); - sk->sk_lock.owned = 0; + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 327060c6c874..7ae0d7f6dbd0 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -297,7 +297,7 @@ static bool seq_nr_after(u16 a, u16 b) void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx) { - if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) { + if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) { WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx); return; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ecd2c3f245ce..19ab78aca547 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - /* Note : following gso_segment() might change skb->encapsulation */ - udpfrag = !skb->encapsulation && proto == IPPROTO_UDP; + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 1863422fb7d5..250be7421ab3 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -182,6 +182,14 @@ static int gre_cisco_rcv(struct sk_buff *skb) int i; bool csum_err = false; +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + if (parse_gre_header(skb, &tpi, &csum_err) < 0) goto drop; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bb075fc9a14f..3b01959bf4bb 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780aec7c..73c6b63bba74 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 50228be5c17b..a82a22d8f77f 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { @@ -119,52 +120,6 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) return (struct rtable *)dst; } -/* Often modified stats are per cpu, other are shared (netdev->stats) */ -struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; - } - - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - - return tot; -} -EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); - static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) { @@ -461,9 +416,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } @@ -759,7 +711,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -1088,7 +1040,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6156f4ef5e91..8d69626f2206 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -148,3 +148,49 @@ error: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); + +/* Often modified stats are per cpu, other are shared (netdev->stats) */ +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_errors; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + tot->collisions = dev->stats.collisions; + + return tot; +} +EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b9b3472975ba..28863570dd60 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2255,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c, int cmd) + u32 portid, u32 seq, struct mfc_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2329,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, if (skb == NULL) goto errout; - err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2368,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2382,7 +2384,8 @@ next_entry: if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31b416e..7c676671329d 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9f3a2db9109e..97c8f5620c43 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index ad37bf18ae4b..2388275adb9b 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size && - left < sk->sk_gso_max_segs) + left < tp->xmit_size_goal_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 227cba79fa6b..eeaac399420d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1945,8 +1945,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3cf976510497..1e4eac779f51 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2628,7 +2628,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, { __be32 dest, src; __u16 destp, srcp; - long delta = tw->tw_ttd - jiffies; + s32 delta = tw->tw_ttd - inet_tw_time_stamp(); dest = tw->tw_daddr; src = tw->tw_rcv_saddr; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3be16727f058..17a11e65e57f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -767,6 +767,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); @@ -864,8 +875,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (unlikely(skb->fclone == SKB_FCLONE_ORIG && fclone->fclone == SKB_FCLONE_CLONE)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -2337,6 +2348,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2400,11 +2412,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + + if (likely(!err)) + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -2908,7 +2924,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index d92e5586783e..438a73aa777c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION config IPV6_VTI tristate "Virtual (secure) IPv6: tunneling" select IPV6_TUNNEL + select NET_IP_TUNNEL depends on INET6_XFRM_MODE_TUNNEL ---help--- Tunneling means encapsulating data of one protocol type within diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index fdbfeca36d63..6c7fa0853fc7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -133,10 +133,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev); static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; static DEFINE_SPINLOCK(addrconf_hash_lock); -static void addrconf_verify(unsigned long); +static void addrconf_verify(void); +static void addrconf_verify_rtnl(void); +static void addrconf_verify_work(struct work_struct *); -static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0); -static DEFINE_SPINLOCK(addrconf_verify_lock); +static struct workqueue_struct *addrconf_wq; +static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); @@ -151,7 +153,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, u32 flags, u32 noflags); static void addrconf_dad_start(struct inet6_ifaddr *ifp); -static void addrconf_dad_timer(unsigned long data); +static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(unsigned long data); @@ -247,9 +249,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev) __in6_dev_put(idev); } -static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp) +static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) { - if (del_timer(&ifp->dad_timer)) + if (cancel_delayed_work(&ifp->dad_work)) __in6_ifa_put(ifp); } @@ -261,12 +263,12 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev, mod_timer(&idev->rs_timer, jiffies + when); } -static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp, - unsigned long when) +static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, + unsigned long delay) { - if (!timer_pending(&ifp->dad_timer)) + if (!delayed_work_pending(&ifp->dad_work)) in6_ifa_hold(ifp); - mod_timer(&ifp->dad_timer, jiffies + when); + mod_delayed_work(addrconf_wq, &ifp->dad_work, delay); } static int snmp6_alloc_dev(struct inet6_dev *idev) @@ -751,8 +753,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) in6_dev_put(ifp->idev); - if (del_timer(&ifp->dad_timer)) - pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); + if (cancel_delayed_work(&ifp->dad_work)) + pr_notice("delayed DAD work was pending while freeing ifa=%p\n", + ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { pr_warn("Freeing alive inet6 address %p\n", ifp); @@ -849,8 +852,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); - setup_timer(&ifa->dad_timer, addrconf_dad_timer, - (unsigned long)ifa); + INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; ifa->prefix_len = pfxlen; @@ -990,6 +992,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; unsigned long expires; + ASSERT_RTNL(); + spin_lock_bh(&ifp->state_lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; @@ -1021,7 +1025,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) write_unlock_bh(&ifp->idev->lock); - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); ipv6_ifa_notify(RTM_DELADDR, ifp); @@ -1103,8 +1107,11 @@ retry: * Lifetime is greater than REGEN_ADVANCE time units. In particular, * an implementation must not create a temporary address with a zero * Preferred Lifetime. + * Use age calculation as in addrconf_verify to avoid unnecessary + * temporary addresses being generated. */ - if (tmp_prefered_lft <= regen_advance) { + age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if (tmp_prefered_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; @@ -1601,7 +1608,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; if (dad_failed) ifp->flags |= IFA_F_DADFAILED; @@ -1622,20 +1629,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); - } else + } else { ipv6_del_addr(ifp); + } } static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; - spin_lock(&ifp->state_lock); + spin_lock_bh(&ifp->state_lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } - spin_unlock(&ifp->state_lock); + spin_unlock_bh(&ifp->state_lock); return err; } @@ -1668,7 +1676,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - addrconf_dad_stop(ifp, 1); + spin_lock_bh(&ifp->state_lock); + /* transition from _POSTDAD to _ERRDAD */ + ifp->state = INET6_IFADDR_STATE_ERRDAD; + spin_unlock_bh(&ifp->state_lock); + + addrconf_mod_dad_work(ifp, 0); } /* Join to solicited addr multicast group. */ @@ -1677,6 +1690,8 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; + ASSERT_RTNL(); + if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1688,6 +1703,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; + ASSERT_RTNL(); + if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1698,6 +1715,9 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + + ASSERT_RTNL(); + if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1709,6 +1729,9 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + + ASSERT_RTNL(); + if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -2268,11 +2291,13 @@ ok: return; } - ifp->flags |= IFA_F_MANAGETEMPADDR; update_lft = 0; create = 1; + spin_lock_bh(&ifp->lock); + ifp->flags |= IFA_F_MANAGETEMPADDR; ifp->cstamp = jiffies; ifp->tokenized = tokenized; + spin_unlock_bh(&ifp->lock); addrconf_dad_start(ifp); } @@ -2323,7 +2348,7 @@ ok: create, now); in6_ifa_put(ifp); - addrconf_verify(0); + addrconf_verify(); } } inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo); @@ -2472,7 +2497,7 @@ static int inet6_addr_add(struct net *net, int ifindex, manage_tempaddrs(idev, ifp, valid_lft, prefered_lft, true, jiffies); in6_ifa_put(ifp); - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } @@ -3008,7 +3033,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { hlist_del_init_rcu(&ifa->addr_lst); - addrconf_del_dad_timer(ifa); + addrconf_del_dad_work(ifa); goto restart; } } @@ -3046,7 +3071,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) while (!list_empty(&idev->addr_list)) { ifa = list_first_entry(&idev->addr_list, struct inet6_ifaddr, if_list); - addrconf_del_dad_timer(ifa); + addrconf_del_dad_work(ifa); list_del(&ifa->if_list); @@ -3145,10 +3170,10 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); ifp->dad_probes = idev->cnf.dad_transmits; - addrconf_mod_dad_timer(ifp, rand_num); + addrconf_mod_dad_work(ifp, rand_num); } -static void addrconf_dad_start(struct inet6_ifaddr *ifp) +static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; @@ -3200,25 +3225,68 @@ out: read_unlock_bh(&idev->lock); } -static void addrconf_dad_timer(unsigned long data) +static void addrconf_dad_start(struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; + bool begin_dad = false; + + spin_lock_bh(&ifp->state_lock); + if (ifp->state != INET6_IFADDR_STATE_DEAD) { + ifp->state = INET6_IFADDR_STATE_PREDAD; + begin_dad = true; + } + spin_unlock_bh(&ifp->state_lock); + + if (begin_dad) + addrconf_mod_dad_work(ifp, 0); +} + +static void addrconf_dad_work(struct work_struct *w) +{ + struct inet6_ifaddr *ifp = container_of(to_delayed_work(w), + struct inet6_ifaddr, + dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + enum { + DAD_PROCESS, + DAD_BEGIN, + DAD_ABORT, + } action = DAD_PROCESS; + + rtnl_lock(); + + spin_lock_bh(&ifp->state_lock); + if (ifp->state == INET6_IFADDR_STATE_PREDAD) { + action = DAD_BEGIN; + ifp->state = INET6_IFADDR_STATE_DAD; + } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { + action = DAD_ABORT; + ifp->state = INET6_IFADDR_STATE_POSTDAD; + } + spin_unlock_bh(&ifp->state_lock); + + if (action == DAD_BEGIN) { + addrconf_dad_begin(ifp); + goto out; + } else if (action == DAD_ABORT) { + addrconf_dad_stop(ifp, 1); + goto out; + } + if (!ifp->dad_probes && addrconf_dad_end(ifp)) goto out; - write_lock(&idev->lock); + write_lock_bh(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); goto out; } spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); goto out; } @@ -3229,7 +3297,7 @@ static void addrconf_dad_timer(unsigned long data) ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); addrconf_dad_completed(ifp); @@ -3237,16 +3305,17 @@ static void addrconf_dad_timer(unsigned long data) } ifp->dad_probes--; - addrconf_mod_dad_timer(ifp, - NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); + addrconf_mod_dad_work(ifp, + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any); out: in6_ifa_put(ifp); + rtnl_unlock(); } /* ifp->idev must be at least read locked */ @@ -3273,7 +3342,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) struct in6_addr lladdr; bool send_rs, send_mld; - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); /* * Configure the address for reception. Now it is valid. @@ -3514,23 +3583,23 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) * Periodic address status verification */ -static void addrconf_verify(unsigned long foo) +static void addrconf_verify_rtnl(void) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; int i; + ASSERT_RTNL(); + rcu_read_lock_bh(); - spin_lock(&addrconf_verify_lock); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - del_timer(&addr_chk_timer); + cancel_delayed_work(&addr_chk_work); for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, - &inet6_addr_lst[i], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { unsigned long age; /* When setting preferred_lft to a value not zero or @@ -3625,13 +3694,22 @@ restart: ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", now, next, next_sec, next_sched); - - addr_chk_timer.expires = next_sched; - add_timer(&addr_chk_timer); - spin_unlock(&addrconf_verify_lock); + mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } +static void addrconf_verify_work(struct work_struct *w) +{ + rtnl_lock(); + addrconf_verify_rtnl(); + rtnl_unlock(); +} + +static void addrconf_verify(void) +{ + mod_delayed_work(addrconf_wq, &addr_chk_work, 0); +} + static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, struct in6_addr **peer_pfx) { @@ -3688,6 +3766,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, bool was_managetempaddr; bool had_prefixroute; + ASSERT_RTNL(); + if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; @@ -3753,7 +3833,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, !was_managetempaddr, jiffies); } - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } @@ -4383,6 +4463,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) bool update_rs = false; struct in6_addr ll_addr; + ASSERT_RTNL(); + if (token == NULL) return -EINVAL; if (ipv6_addr_any(token)) @@ -4431,7 +4513,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) } write_unlock_bh(&idev->lock); - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } @@ -4633,6 +4715,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); + if (event) + ASSERT_RTNL(); + inet6_ifa_notify(event ? : RTM_NEWADDR, ifp); switch (event) { @@ -5241,6 +5326,12 @@ int __init addrconf_init(void) if (err < 0) goto out_addrlabel; + addrconf_wq = create_workqueue("ipv6_addrconf"); + if (!addrconf_wq) { + err = -ENOMEM; + goto out_nowq; + } + /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup * before it can bring up and give link-local addresses @@ -5271,7 +5362,7 @@ int __init addrconf_init(void) register_netdevice_notifier(&ipv6_dev_notf); - addrconf_verify(0); + addrconf_verify(); rtnl_af_register(&inet6_ops); @@ -5299,6 +5390,8 @@ errout: rtnl_af_unregister(&inet6_ops); unregister_netdevice_notifier(&ipv6_dev_notf); errlo: + destroy_workqueue(addrconf_wq); +out_nowq: unregister_pernet_subsys(&addrconf_ops); out_addrlabel: ipv6_addr_label_cleanup(); @@ -5334,7 +5427,8 @@ void addrconf_cleanup(void) for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON(!hlist_empty(&inet6_addr_lst[i])); spin_unlock_bh(&addrconf_hash_lock); - - del_timer(&addr_chk_timer); + cancel_delayed_work(&addr_chk_work); rtnl_unlock(); + + destroy_workqueue(addrconf_wq); } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 140748debc4a..8af3eb57f438 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, found = (nexthdr == target); if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) + if (target < 0 || found) break; return -ENOENT; } diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index cf77f3abfd06..447a7fbd1bb6 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void) int ret; ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); - if (!ret) + if (ret) goto out; ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); - if (!ret) + if (ret) goto out_rt; out: diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1e8683b135bb..59f95affceb0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, unsigned int unfrag_ip6hlen; u8 *prevhdr; int offset = 0; - bool tunnel; + bool encap, udpfrag; int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & @@ -110,8 +110,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; - tunnel = SKB_GSO_CB(skb)->encap_level > 0; - if (tunnel) + encap = SKB_GSO_CB(skb)->encap_level > 0; + if (encap) features = skb->dev->hw_enc_features & netif_skb_features(skb); SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); @@ -121,6 +121,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); @@ -133,13 +139,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); - if (tunnel) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } skb->network_header = (u8 *)ipv6h - skb->head; - if (!tunnel && proto == IPPROTO_UDP) { + if (udpfrag) { unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); @@ -148,6 +150,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); } + if (encap) + skb_reset_inner_headers(skb); } out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 070a2fae2375..64d6073731d3 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -530,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif skb_copy_secmark(to, from); } @@ -1104,21 +1101,19 @@ static void ip6_append_data_mtu(unsigned int *mtu, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, - bool pmtuprobe) + unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { /* first fragment, reserve header_len */ - *mtu = *mtu - rt->dst.header_len; + *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ - *mtu = min(*mtu, pmtuprobe ? - rt->dst.dev->mtu : - dst_mtu(rt->dst.path)); + *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1135,7 +1130,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen, mtu; + unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; int dst_exthdrlen; int hh_len; @@ -1217,6 +1212,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, dst_exthdrlen = 0; mtu = cork->fragsize; } + orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1314,8 +1310,7 @@ alloc_new_skb: if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, - np->pmtudisc >= - IPV6_PMTUDISC_PROBE); + orig_mtu); skb_prev = skb; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0eb4038a4d63..8737400af0a0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2349,13 +2349,14 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c, int cmd) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2423,7 +2424,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, if (skb == NULL) goto errout; - err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2462,7 +2463,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2476,7 +2478,8 @@ next_entry: if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fb9beb78f00b..587bbdcb22b4 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -135,6 +135,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 11dac21e6586..fba54a407bb2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1513,7 +1513,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3dfbcf1dcb1c..b4d74c86586c 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } + ip_tunnel_dst_reset_all(tunnel); dev_put(dev); } @@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) t->parms.link = p->link; ipip6_tunnel_bind_dev(t->dev); } + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); } @@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); return 0; } @@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); break; @@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = { static void ipip6_dev_free(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1375,6 +1382,12 @@ static int ipip6_tunnel_init(struct net_device *dev) u64_stats_init(&ipip6_tunnel_stats->syncp); } + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + return 0; } @@ -1405,6 +1418,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) u64_stats_init(&ipip6_fb_stats->syncp); } + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + dev_hold(dev); rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index e7359f9eaa8d..b261ee8b83fc 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -113,7 +113,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/key/af_key.c b/net/key/af_key.c index 1a04c1329362..79326978517a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -433,12 +433,13 @@ static inline int verify_sec_ctx_len(const void *p) return 0; } -static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx) +static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx, + gfp_t gfp) { struct xfrm_user_sec_ctx *uctx = NULL; int ctx_size = sec_ctx->sadb_x_ctx_len; - uctx = kmalloc((sizeof(*uctx)+ctx_size), GFP_KERNEL); + uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp); if (!uctx) return NULL; @@ -1124,7 +1125,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { - struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); + struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) goto out; @@ -2231,14 +2232,14 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { - struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); + struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) { err = -ENOBUFS; goto out; } - err = security_xfrm_policy_alloc(&xp->security, uctx); + err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL); kfree(uctx); if (err) @@ -2335,12 +2336,12 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { - struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); + struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) return -ENOMEM; - err = security_xfrm_policy_alloc(&pol_ctx, uctx); + err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL); kfree(uctx); if (err) return err; @@ -3239,8 +3240,8 @@ static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, } if ((*dir = verify_sec_ctx_len(p))) goto out; - uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); - *dir = security_xfrm_policy_alloc(&xp->security, uctx); + uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC); + *dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC); kfree(uctx); if (*dir) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 735d0f60c83a..85d9d94c0a3c 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -112,7 +112,6 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; -static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) @@ -1863,7 +1862,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_len parameters are set. */ -static void l2tp_session_set_header_len(struct l2tp_session *session, int version) +void l2tp_session_set_header_len(struct l2tp_session *session, int version) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; @@ -1876,6 +1875,7 @@ static void l2tp_session_set_header_len(struct l2tp_session *session, int versio } } +EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 1f01ba3435bc..3f93ccd6ba97 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -263,6 +263,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int length, int (*payload_hook)(struct sk_buff *skb)); int l2tp_session_queue_purge(struct l2tp_session *session); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); +void l2tp_session_set_header_len(struct l2tp_session *session, int version); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 4cfd722e9153..bd7387adea9e 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -578,8 +578,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); - if (info->attrs[L2TP_ATTR_SEND_SEQ]) + if (info->attrs[L2TP_ATTR_SEND_SEQ]) { session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]); + l2tp_session_set_header_len(session, session->tunnel->version); + } if (info->attrs[L2TP_ATTR_LNS_MODE]) session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index be5fadf34739..5990919356a5 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -254,12 +254,14 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n", - session->name); + l2tp_dbg(session, PPPOL2TP_MSG_DATA, + "%s: recv %d byte data frame, passing to L2TP socket\n", + session->name, data_len); - /* Not bound. Nothing we can do, so discard. */ - atomic_long_inc(&session->stats.rx_errors); - kfree_skb(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { + atomic_long_inc(&session->stats.rx_errors); + kfree_skb(skb); + } } return; @@ -1312,6 +1314,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } + l2tp_session_set_header_len(session, session->tunnel->version); l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set send_seq=%d\n", session->name, session->send_seq); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index f43613a97dd6..0c1ecfdf9a12 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -100,6 +100,12 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, } max_bw = max(max_bw, width); } + + /* use the configured bandwidth in case of monitor interface */ + sdata = rcu_dereference(local->monitor_sdata); + if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf) + max_bw = max(max_bw, conf->def.width); + rcu_read_unlock(); return max_bw; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3701930c6649..5e44e3179e02 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1692,14 +1692,8 @@ void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); -void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data); -static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs) -{ - ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); -} +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs); void ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 2802f9d9279d..ad8b377b4b9f 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) sdata->vif.addr); nullfunc->frame_control = fc; nullfunc->duration_id = 0; + nullfunc->seq_ctrl = 0; /* no address resolution for this frame -> set addr 1 immediately */ memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memset(skb_put(skb, 2), 0, 2); /* append QoS control field */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index fc1d82465b3c..245dce969b31 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -222,6 +222,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, switch (vht_oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: vht_chandef.width = chandef->width; + vht_chandef.center_freq1 = chandef->center_freq1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: vht_chandef.width = NL80211_CHAN_WIDTH_80; @@ -271,6 +272,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; out: + /* + * When tracking the current AP, don't do any further checks if the + * new chandef is identical to the one we're currently using for the + * connection. This keeps us from playing ping-pong with regulatory, + * without it the following can happen (for example): + * - connect to an AP with 80 MHz, world regdom allows 80 MHz + * - AP advertises regdom US + * - CRDA loads regdom US with 80 MHz prohibited (old database) + * - the code below detects an unsupported channel, downgrades, and + * we disconnect from the AP in the caller + * - disconnect causes CRDA to reload world regdomain and the game + * starts anew. + * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * + * It seems possible that there are still scenarios with CSA or real + * bandwidth changes where a this could happen, but those cases are + * less common and wouldn't completely prevent using the AP. + */ + if (tracking && + cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef)) + return ret; + /* don't print the message below for VHT mismatch if VHT is disabled */ if (ret & IEEE80211_STA_DISABLE_VHT) vht_chandef = *chandef; @@ -3753,6 +3776,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (WARN_ON(!chanctx_conf)) { rcu_read_unlock(); + sta_info_free(local, new_sta); return -EINVAL; } rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c24ca0d0f469..3e57f96c9666 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1128,6 +1128,13 @@ static void sta_ps_end(struct sta_info *sta) sta->sta.addr, sta->sta.aid); if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + /* + * Clear the flag only if the other one is still set + * so that the TX path won't start TX'ing new frames + * directly ... In the case that the driver flag isn't + * set ieee80211_sta_ps_deliver_wakeup() will clear it. + */ + clear_sta_flag(sta, WLAN_STA_PS_STA); ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n", sta->sta.addr, sta->sta.aid); return; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index decd30c1e290..137a192e64bc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -91,7 +91,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, return -ENOENT; } -static void cleanup_single_sta(struct sta_info *sta) +static void __cleanup_single_sta(struct sta_info *sta) { int ac, i; struct tid_ampdu_tx *tid_tx; @@ -99,7 +99,8 @@ static void cleanup_single_sta(struct sta_info *sta) struct ieee80211_local *local = sdata->local; struct ps_data *ps; - if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + if (test_sta_flag(sta, WLAN_STA_PS_STA) || + test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ps = &sdata->bss->ps; @@ -109,6 +110,7 @@ static void cleanup_single_sta(struct sta_info *sta) return; clear_sta_flag(sta, WLAN_STA_PS_STA); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); atomic_dec(&ps->num_sta_ps); sta_info_recalc_tim(sta); @@ -139,7 +141,14 @@ static void cleanup_single_sta(struct sta_info *sta) ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending); kfree(tid_tx); } +} +static void cleanup_single_sta(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + + __cleanup_single_sta(sta); sta_info_free(local, sta); } @@ -330,6 +339,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); spin_lock_init(&sta->lock); + spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -487,21 +497,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) goto out_err; } - /* notify driver */ - err = sta_info_insert_drv_state(local, sdata, sta); - if (err) - goto out_err; - local->num_sta++; local->sta_generation++; smp_mb(); + /* simplify things and don't accept BA sessions yet */ + set_sta_flag(sta, WLAN_STA_BLOCK_BA); + /* make the station visible */ sta_info_hash_add(local, sta); list_add_rcu(&sta->list, &local->sta_list); + /* notify driver */ + err = sta_info_insert_drv_state(local, sdata, sta); + if (err) + goto out_remove; + set_sta_flag(sta, WLAN_STA_INSERTED); + /* accept BA sessions now */ + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_recalc_min_chandef(sdata); ieee80211_sta_debugfs_add(sta); @@ -522,6 +537,12 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) mesh_accept_plinks_update(sdata); return 0; + out_remove: + sta_info_hash_del(local, sta); + list_del_rcu(&sta->list); + local->num_sta--; + synchronize_net(); + __cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); rcu_read_lock(); @@ -1071,10 +1092,14 @@ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, } EXPORT_SYMBOL(ieee80211_find_sta); -static void clear_sta_ps_flags(void *_sta) +/* powersave support code */ +void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) { - struct sta_info *sta = _sta; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + struct sk_buff_head pending; + int filtered = 0, buffered = 0, ac; + unsigned long flags; struct ps_data *ps; if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -1085,20 +1110,6 @@ static void clear_sta_ps_flags(void *_sta) else return; - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); - if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA)) - atomic_dec(&ps->num_sta_ps); -} - -/* powersave support code */ -void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) -{ - struct ieee80211_sub_if_data *sdata = sta->sdata; - struct ieee80211_local *local = sdata->local; - struct sk_buff_head pending; - int filtered = 0, buffered = 0, ac; - unsigned long flags; - clear_sta_flag(sta, WLAN_STA_SP); BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1); @@ -1109,6 +1120,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) skb_queue_head_init(&pending); + /* sync with ieee80211_tx_h_unicast_ps_buf */ + spin_lock(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; @@ -1127,7 +1140,12 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) buffered += tmp - count; } - ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta); + ieee80211_add_pending_skbs(local, &pending); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + clear_sta_flag(sta, WLAN_STA_PS_STA); + spin_unlock(&sta->ps_lock); + + atomic_dec(&ps->num_sta_ps); /* This station just woke up and isn't aware of our SMPS state */ if (!ieee80211_smps_is_restrictive(sta->known_smps_mode, @@ -1188,6 +1206,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); + nullfunc->seq_ctrl = 0; skb->priority = tid; skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index d77ff7090630..d3a6d8208f2f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -267,6 +267,7 @@ struct ieee80211_tx_latency_stat { * @drv_unblock_wk: used for driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly + * @ps_lock: used for powersave (when mac80211 is the AP) related locking * @ps_tx_buf: buffers (per AC) of frames to transmit to this station * when it leaves power saving state or polls * @tx_filtered: buffers (per AC) of frames we already tried to @@ -356,10 +357,8 @@ struct sta_info { /* use the accessors defined below */ unsigned long _flags; - /* - * STA powersave frame queues, no more than the internal - * locking required. - */ + /* STA powersave lock and frame queues */ + spinlock_t ps_lock; struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 97a02d3f7d87..4080c615636f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -478,6 +478,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); + + /* sync with ieee80211_sta_ps_deliver_wakeup */ + spin_lock(&sta->ps_lock); + /* + * STA woke up the meantime and all the frames on ps_tx_buf have + * been queued to pending queue. No reordering can happen, go + * ahead and Tx the packet. + */ + if (!test_sta_flag(sta, WLAN_STA_PS_STA) && + !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + spin_unlock(&sta->ps_lock); + return TX_CONTINUE; + } + if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); ps_dbg(tx->sdata, @@ -492,6 +506,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); + spin_unlock(&sta->ps_lock); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 676dc0967f37..b8700d417a9c 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -435,9 +435,8 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } -void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data) +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) { struct ieee80211_hw *hw = &local->hw; struct sk_buff *skb; @@ -461,9 +460,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, __skb_queue_tail(&local->pending[queue], skb); } - if (fn) - fn(data); - for (i = 0; i < hw->queues; i++) __ieee80211_wake_queue(hw, i, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); @@ -1741,6 +1737,26 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_QUEUE_STOP_REASON_SUSPEND); /* + * Reconfigure sched scan if it was interrupted by FW restart or + * suspend. + */ + mutex_lock(&local->mtx); + sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, + lockdep_is_held(&local->mtx)); + if (sched_scan_sdata && local->sched_scan_req) + /* + * Sched scan stopped, but we don't want to report it. Instead, + * we're trying to reschedule. + */ + if (__ieee80211_request_sched_scan_start(sched_scan_sdata, + local->sched_scan_req)) + sched_scan_stopped = true; + mutex_unlock(&local->mtx); + + if (sched_scan_stopped) + cfg80211_sched_scan_stopped(local->hw.wiphy); + + /* * If this is for hw restart things are still running. * We may want to change that later, however. */ @@ -1768,26 +1784,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(1); #endif - /* - * Reconfigure sched scan if it was interrupted by FW restart or - * suspend. - */ - mutex_lock(&local->mtx); - sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, - lockdep_is_held(&local->mtx)); - if (sched_scan_sdata && local->sched_scan_req) - /* - * Sched scan stopped, but we don't want to report it. Instead, - * we're trying to reschedule. - */ - if (__ieee80211_request_sched_scan_start(sched_scan_sdata, - local->sched_scan_req)) - sched_scan_stopped = true; - mutex_unlock(&local->mtx); - - if (sched_scan_stopped) - cfg80211_sched_scan_stopped(local->hw.wiphy); - return 0; } diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 21211c60ca98..d51422c778de 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -154,6 +154,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return IEEE80211_AC_BE; } + if (skb->protocol == sdata->control_port_protocol) { + skb->priority = 7; + return ieee80211_downgrade_queue(sdata, skb); + } + /* use the data classifier to determine what 802.1d tag the * data frame has */ rcu_read_lock(); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index bb322d0beb48..b9f0e0374322 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1310,27 +1310,22 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) } static int -ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[]) +ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_NAT_NEEDED int ret; - if (cda[CTA_NAT_DST]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_DST, - cda[CTA_NAT_DST]); - if (ret < 0) - return ret; - } - if (cda[CTA_NAT_SRC]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_SRC, - cda[CTA_NAT_SRC]); - if (ret < 0) - return ret; - } - return 0; + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, + cda[CTA_NAT_DST]); + if (ret < 0) + return ret; + + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, + cda[CTA_NAT_SRC]); + return ret; #else + if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) + return 0; return -EOPNOTSUPP; #endif } @@ -1659,11 +1654,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } - if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) { - err = ctnetlink_change_nat(ct, cda); - if (err < 0) - goto err2; - } + err = ctnetlink_setup_nat(ct, cda); + if (err < 0) + goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d3f5cd6dd962..52ca952b802c 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -432,15 +432,15 @@ nf_nat_setup_info(struct nf_conn *ct, } EXPORT_SYMBOL(nf_nat_setup_info); -unsigned int -nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +static unsigned int +__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) { /* Force range to this IP; let proto decide mapping for * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). * Use reply in case it's already been mangled (eg local packet). */ union nf_inet_addr ip = - (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); struct nf_nat_range range = { @@ -448,7 +448,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) .min_addr = ip, .max_addr = ip, }; - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); + return nf_nat_setup_info(ct, &range, manip); +} + +unsigned int +nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum)); } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); @@ -702,9 +708,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range) + const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_nat_l3proto *l3proto) { - const struct nf_nat_l3proto *l3proto; struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -714,38 +720,46 @@ nfnetlink_parse_nat(const struct nlattr *nat, if (err < 0) return err; - rcu_read_lock(); - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - if (l3proto == NULL) { - err = -EAGAIN; - goto out; - } err = l3proto->nlattr_to_range(tb, range); if (err < 0) - goto out; + return err; if (!tb[CTA_NAT_PROTO]) - goto out; + return 0; - err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); -out: - rcu_read_unlock(); - return err; + return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); } +/* This function is called under rcu_read_lock() */ static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { struct nf_nat_range range; + const struct nf_nat_l3proto *l3proto; int err; - err = nfnetlink_parse_nat(attr, ct, &range); + /* Should not happen, restricted to creating new conntracks + * via ctnetlink. + */ + if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) + return -EEXIST; + + /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to + * attach the null binding, otherwise this may oops. + */ + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) + return -EAGAIN; + + /* No NAT information has been passed, allocate the null-binding */ + if (attr == NULL) + return __nf_nat_alloc_null_binding(ct, manip); + + err = nfnetlink_parse_nat(attr, ct, &range, l3proto); if (err < 0) return err; - if (nf_nat_initialized(ct, manip)) - return -EEXIST; return nf_nat_setup_info(ct, &range, manip); } diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index f072fe803510..108120f216b1 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -354,13 +354,16 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, skb = nfnetlink_alloc_skb(net, size, queue->peer_portid, GFP_ATOMIC); - if (!skb) + if (!skb) { + skb_tx_error(entskb); return NULL; + } nlh = nlmsg_put(skb, 0, 0, NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET, sizeof(struct nfgenmsg), 0); if (!nlh) { + skb_tx_error(entskb); kfree_skb(skb); return NULL; } @@ -488,13 +491,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); - skb_zerocopy(skb, entskb, data_len, hlen); + if (skb_zerocopy(skb, entskb, data_len, hlen)) + goto nla_put_failure; } nlh->nlmsg_len = skb->len; return skb; nla_put_failure: + skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); return NULL; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e8254ad2e5a9..425cf39af890 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -116,7 +116,7 @@ static void nft_meta_get_eval(const struct nft_expr *expr, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); break; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: { const struct dst_entry *dst = skb_dst(skb); @@ -199,7 +199,7 @@ static int nft_meta_init_validate_get(uint32_t key) case NFT_META_OIFTYPE: case NFT_META_SKUID: case NFT_META_SKGID: -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: #endif #ifdef CONFIG_NETWORK_SECMARK diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a2aeb318678f..85daa84bfdfe 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data)) return ERR_PTR(-EINVAL); - if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) + if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && + base != NFT_PAYLOAD_LL_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 8a310f239c93..b718a52a4654 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -21,9 +21,9 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, { switch (pkt->ops->pf) { case NFPROTO_IPV4: - nft_reject_ipv4_eval(expr, data, pkt); + return nft_reject_ipv4_eval(expr, data, pkt); case NFPROTO_IPV6: - nft_reject_ipv6_eval(expr, data, pkt); + return nft_reject_ipv6_eval(expr, data, pkt); } } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fdf51353cf78..04748ab649c2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1489,8 +1489,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family != AF_NETLINK) return -EINVAL; - /* Only superuser is allowed to send multicasts */ - if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + if ((nladdr->nl_groups || nladdr->nl_pid) && + !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 46bda010bf11..56db888b1cd5 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -301,7 +301,7 @@ static int nci_open_device(struct nci_dev *ndev) rc = __nci_request(ndev, nci_reset_req, 0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); - if (ndev->ops->setup(ndev)) + if (ndev->ops->setup) ndev->ops->setup(ndev); if (!rc) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e9a48baf8551..270b77dfac30 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -464,7 +464,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, } nla->nla_len = nla_attr_size(skb->len); - skb_zerocopy(user_skb, skb, skb->len, hlen); + err = skb_zerocopy(user_skb, skb, skb->len, hlen); + if (err) + goto out; /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */ if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { @@ -478,6 +480,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); out: + if (err) + skb_tx_error(skb); kfree_skb(nskb); return err; } @@ -1174,7 +1178,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in struct datapath *dp; dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); - if (!dp) + if (IS_ERR(dp)) return; WARN(dp->user_features, "Dropping previously announced user features\n"); @@ -1762,11 +1766,12 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) int bucket = cb->args[0], skip = cb->args[1]; int i, j = 0; + rcu_read_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) + if (!dp) { + rcu_read_unlock(); return -ENODEV; - - rcu_read_lock(); + } for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 16f4b46161d4..2998989e76db 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -73,6 +73,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb) if ((flow->key.eth.type == htons(ETH_P_IP) || flow->key.eth.type == htons(ETH_P_IPV6)) && + flow->key.ip.frag != OVS_FRAG_TYPE_LATER && flow->key.ip.proto == IPPROTO_TCP && likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) { tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb)); @@ -91,7 +92,7 @@ static void stats_read(struct flow_stats *stats, unsigned long *used, __be16 *tcp_flags) { spin_lock(&stats->lock); - if (time_after(stats->used, *used)) + if (!*used || time_after(stats->used, *used)) *used = stats->used; *tcp_flags |= stats->tcp_flags; ovs_stats->n_packets += stats->packet_count; @@ -102,30 +103,24 @@ static void stats_read(struct flow_stats *stats, void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, unsigned long *used, __be16 *tcp_flags) { - int cpu, cur_cpu; + int cpu; *used = 0; *tcp_flags = 0; memset(ovs_stats, 0, sizeof(*ovs_stats)); + local_bh_disable(); if (!flow->stats.is_percpu) { stats_read(flow->stats.stat, ovs_stats, used, tcp_flags); } else { - cur_cpu = get_cpu(); for_each_possible_cpu(cpu) { struct flow_stats *stats; - if (cpu == cur_cpu) - local_bh_disable(); - stats = per_cpu_ptr(flow->stats.cpu_stats, cpu); stats_read(stats, ovs_stats, used, tcp_flags); - - if (cpu == cur_cpu) - local_bh_enable(); } - put_cpu(); } + local_bh_enable(); } static void stats_reset(struct flow_stats *stats) @@ -140,25 +135,17 @@ static void stats_reset(struct flow_stats *stats) void ovs_flow_stats_clear(struct sw_flow *flow) { - int cpu, cur_cpu; + int cpu; + local_bh_disable(); if (!flow->stats.is_percpu) { stats_reset(flow->stats.stat); } else { - cur_cpu = get_cpu(); - for_each_possible_cpu(cpu) { - - if (cpu == cur_cpu) - local_bh_disable(); - stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu)); - - if (cpu == cur_cpu) - local_bh_enable(); } - put_cpu(); } + local_bh_enable(); } static int check_header(struct sk_buff *skb, int len) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1313145e3b86..a07d55e75698 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -273,11 +273,12 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) void qdisc_list_add(struct Qdisc *q) { - struct Qdisc *root = qdisc_dev(q)->qdisc; + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + struct Qdisc *root = qdisc_dev(q)->qdisc; - WARN_ON_ONCE(root == &noop_qdisc); - if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) + WARN_ON_ONCE(root == &noop_qdisc); list_add_tail(&q->list, &root->list); + } } EXPORT_SYMBOL(qdisc_list_add); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 08ef7a42c0e4..21e251766eb1 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -601,6 +601,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; + void *old_fq_root; u32 idx; if (q->fq_root && log == q->fq_trees_log) @@ -615,13 +616,19 @@ static int fq_resize(struct Qdisc *sch, u32 log) for (idx = 0; idx < (1U << log); idx++) array[idx] = RB_ROOT; - if (q->fq_root) { - fq_rehash(q, q->fq_root, q->fq_trees_log, array, log); - fq_free(q->fq_root); - } + sch_tree_lock(sch); + + old_fq_root = q->fq_root; + if (old_fq_root) + fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); + q->fq_root = array; q->fq_trees_log = log; + sch_tree_unlock(sch); + + fq_free(old_fq_root); + return 0; } @@ -697,9 +704,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } - if (!err) + if (!err) { + sch_tree_unlock(sch); err = fq_resize(sch, fq_log); - + sch_tree_lock(sch); + } while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 1cb413fead89..4f505a006896 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -334,18 +334,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB])); - if (q->qdisc != &noop_qdisc) { - err = fifo_set_limit(q->qdisc, qopt->limit); - if (err) - goto done; - } else if (qopt->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); - if (IS_ERR(child)) { - err = PTR_ERR(child); - goto done; - } - } - buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); @@ -390,6 +378,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) goto done; } + if (q->qdisc != &noop_qdisc) { + err = fifo_set_limit(q->qdisc, qopt->limit); + if (err) + goto done; + } else if (qopt->limit > 0) { + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); + if (IS_ERR(child)) { + err = PTR_ERR(child); + goto done; + } + } + sch_tree_lock(sch); if (child) { qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index f558433537b8..ee13d28d39d1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1239,78 +1239,107 @@ void sctp_assoc_update(struct sctp_association *asoc, } /* Update the retran path for sending a retransmitted packet. - * Round-robin through the active transports, else round-robin - * through the inactive transports as this is the next best thing - * we can try. + * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: + * + * When there is outbound data to send and the primary path + * becomes inactive (e.g., due to failures), or where the + * SCTP user explicitly requests to send data to an + * inactive destination transport address, before reporting + * an error to its ULP, the SCTP endpoint should try to send + * the data to an alternate active destination transport + * address if one exists. + * + * When retransmitting data that timed out, if the endpoint + * is multihomed, it should consider each source-destination + * address pair in its retransmission selection policy. + * When retransmitting timed-out data, the endpoint should + * attempt to pick the most divergent source-destination + * pair from the original source-destination pair to which + * the packet was transmitted. + * + * Note: Rules for picking the most divergent source-destination + * pair are an implementation decision and are not specified + * within this document. + * + * Our basic strategy is to round-robin transports in priorities + * according to sctp_state_prio_map[] e.g., if no such + * transport with state SCTP_ACTIVE exists, round-robin through + * SCTP_UNKNOWN, etc. You get the picture. */ -void sctp_assoc_update_retran_path(struct sctp_association *asoc) +static const u8 sctp_trans_state_to_prio_map[] = { + [SCTP_ACTIVE] = 3, /* best case */ + [SCTP_UNKNOWN] = 2, + [SCTP_PF] = 1, + [SCTP_INACTIVE] = 0, /* worst case */ +}; + +static u8 sctp_trans_score(const struct sctp_transport *trans) { - struct sctp_transport *t, *next; - struct list_head *head = &asoc->peer.transport_addr_list; - struct list_head *pos; + return sctp_trans_state_to_prio_map[trans->state]; +} - if (asoc->peer.transport_count == 1) - return; +static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, + struct sctp_transport *best) +{ + if (best == NULL) + return curr; - /* Find the next transport in a round-robin fashion. */ - t = asoc->peer.retran_path; - pos = &t->transports; - next = NULL; + return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best; +} - while (1) { - /* Skip the head. */ - if (pos->next == head) - pos = head->next; - else - pos = pos->next; +void sctp_assoc_update_retran_path(struct sctp_association *asoc) +{ + struct sctp_transport *trans = asoc->peer.retran_path; + struct sctp_transport *trans_next = NULL; - t = list_entry(pos, struct sctp_transport, transports); + /* We're done as we only have the one and only path. */ + if (asoc->peer.transport_count == 1) + return; + /* If active_path and retran_path are the same and active, + * then this is the only active path. Use it. + */ + if (asoc->peer.active_path == asoc->peer.retran_path && + asoc->peer.active_path->state == SCTP_ACTIVE) + return; - /* We have exhausted the list, but didn't find any - * other active transports. If so, use the next - * transport. - */ - if (t == asoc->peer.retran_path) { - t = next; + /* Iterate from retran_path's successor back to retran_path. */ + for (trans = list_next_entry(trans, transports); 1; + trans = list_next_entry(trans, transports)) { + /* Manually skip the head element. */ + if (&trans->transports == &asoc->peer.transport_addr_list) + continue; + if (trans->state == SCTP_UNCONFIRMED) + continue; + trans_next = sctp_trans_elect_best(trans, trans_next); + /* Active is good enough for immediate return. */ + if (trans_next->state == SCTP_ACTIVE) break; - } - - /* Try to find an active transport. */ - - if ((t->state == SCTP_ACTIVE) || - (t->state == SCTP_UNKNOWN)) { + /* We've reached the end, time to update path. */ + if (trans == asoc->peer.retran_path) break; - } else { - /* Keep track of the next transport in case - * we don't find any active transport. - */ - if (t->state != SCTP_UNCONFIRMED && !next) - next = t; - } } - if (t) - asoc->peer.retran_path = t; - else - t = asoc->peer.retran_path; + if (trans_next != NULL) + asoc->peer.retran_path = trans_next; - pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, - &t->ipaddr.sa); + pr_debug("%s: association:%p updated new path to addr:%pISpc\n", + __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } -/* Choose the transport for sending retransmit packet. */ -struct sctp_transport *sctp_assoc_choose_alter_transport( - struct sctp_association *asoc, struct sctp_transport *last_sent_to) +struct sctp_transport * +sctp_assoc_choose_alter_transport(struct sctp_association *asoc, + struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ - if (!last_sent_to) + if (last_sent_to == NULL) { return asoc->peer.active_path; - else { + } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); + return asoc->peer.retran_path; } } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 632090b961c3..3a1767ef3201 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1421,8 +1421,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk) BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); - /* Free the chunk skb data and the SCTP_chunk stub itself. */ - dev_kfree_skb(chunk->skb); + consume_skb(chunk->skb); + consume_skb(chunk->auth_chunk); SCTP_DBG_OBJCNT_DEC(chunk); kmem_cache_free(sctp_chunk_cachep, chunk); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index bd859154000e..5d6883ff00c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -495,11 +495,12 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, } /* If the transport error count is greater than the pf_retrans - * threshold, and less than pathmaxrtx, then mark this transport - * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1, - * point 1 + * threshold, and less than pathmaxrtx, and if the current state + * is not SCTP_UNCONFIRMED, then mark this transport as Partially + * Failed, see SCTP Quick Failover Draft, section 5.1 */ if ((transport->state != SCTP_PF) && + (transport->state != SCTP_UNCONFIRMED) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 591b44d3b7de..01e002430c85 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -758,6 +758,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, struct sctp_chunk auth; sctp_ierror_t ret; + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; @@ -768,10 +774,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - - /* We can now safely free the auth_chunk clone */ - kfree_skb(chunk->auth_chunk); - if (ret != SCTP_IERROR_NO_ERROR) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); diff --git a/net/socket.c b/net/socket.c index 879933aaed4c..a19ae1968d37 100644 --- a/net/socket.c +++ b/net/socket.c @@ -450,16 +450,17 @@ EXPORT_SYMBOL(sockfd_lookup); static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) { - struct file *file; + struct fd f = fdget(fd); struct socket *sock; *err = -EBADF; - file = fget_light(fd, fput_needed); - if (file) { - sock = sock_from_file(file, err); - if (sock) + if (f.file) { + sock = sock_from_file(f.file, err); + if (likely(sock)) { + *fput_needed = f.flags; return sock; - fput_light(file, *fput_needed); + } + fdput(f); } return NULL; } @@ -1985,6 +1986,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, { if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a38c89969c68..574b86193b15 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -610,8 +610,13 @@ static struct notifier_block notifier = { int tipc_bearer_setup(void) { + int err; + + err = register_netdevice_notifier(¬ifier); + if (err) + return err; dev_add_pack(&tipc_packet_type); - return register_netdevice_notifier(¬ifier); + return 0; } void tipc_bearer_cleanup(void) diff --git a/net/tipc/config.c b/net/tipc/config.c index c301a9a592d8..e6d721692ae0 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -181,7 +181,7 @@ static struct sk_buff *cfg_set_own_addr(void) if (tipc_own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change node address once assigned)"); - tipc_core_start_net(addr); + tipc_net_start(addr); return tipc_cfg_reply_none(); } @@ -376,7 +376,6 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, struct tipc_cfg_msg_hdr *req_hdr; struct tipc_cfg_msg_hdr *rep_hdr; struct sk_buff *rep_buf; - int ret; /* Validate configuration message header (ignore invalid message) */ req_hdr = (struct tipc_cfg_msg_hdr *)buf; @@ -398,12 +397,8 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr)); rep_hdr->tcm_len = htonl(rep_buf->len); rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST); - - ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, - rep_buf->len); - if (ret < 0) - pr_err("Sending cfg reply message failed, no memory\n"); - + tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, + rep_buf->len); kfree_skb(rep_buf); } } diff --git a/net/tipc/core.c b/net/tipc/core.c index f9e88d8b04ca..80c20647b3d2 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -77,37 +77,13 @@ struct sk_buff *tipc_buf_acquire(u32 size) } /** - * tipc_core_stop_net - shut down TIPC networking sub-systems - */ -static void tipc_core_stop_net(void) -{ - tipc_net_stop(); - tipc_bearer_cleanup(); -} - -/** - * start_net - start TIPC networking sub-systems - */ -int tipc_core_start_net(unsigned long addr) -{ - int res; - - tipc_net_start(addr); - res = tipc_bearer_setup(); - if (res < 0) - goto err; - return res; - -err: - tipc_core_stop_net(); - return res; -} - -/** * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode */ static void tipc_core_stop(void) { + tipc_handler_stop(); + tipc_net_stop(); + tipc_bearer_cleanup(); tipc_netlink_stop(); tipc_cfg_stop(); tipc_subscr_stop(); @@ -122,30 +98,65 @@ static void tipc_core_stop(void) */ static int tipc_core_start(void) { - int res; + int err; get_random_bytes(&tipc_random, sizeof(tipc_random)); - res = tipc_handler_start(); - if (!res) - res = tipc_ref_table_init(tipc_max_ports, tipc_random); - if (!res) - res = tipc_nametbl_init(); - if (!res) - res = tipc_netlink_start(); - if (!res) - res = tipc_socket_init(); - if (!res) - res = tipc_register_sysctl(); - if (!res) - res = tipc_subscr_start(); - if (!res) - res = tipc_cfg_init(); - if (res) { - tipc_handler_stop(); - tipc_core_stop(); - } - return res; + err = tipc_handler_start(); + if (err) + goto out_handler; + + err = tipc_ref_table_init(tipc_max_ports, tipc_random); + if (err) + goto out_reftbl; + + err = tipc_nametbl_init(); + if (err) + goto out_nametbl; + + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_socket_init(); + if (err) + goto out_socket; + + err = tipc_register_sysctl(); + if (err) + goto out_sysctl; + + err = tipc_subscr_start(); + if (err) + goto out_subscr; + + err = tipc_cfg_init(); + if (err) + goto out_cfg; + + err = tipc_bearer_setup(); + if (err) + goto out_bearer; + + return 0; +out_bearer: + tipc_cfg_stop(); +out_cfg: + tipc_subscr_stop(); +out_subscr: + tipc_unregister_sysctl(); +out_sysctl: + tipc_socket_stop(); +out_socket: + tipc_netlink_stop(); +out_netlink: + tipc_nametbl_stop(); +out_nametbl: + tipc_ref_table_stop(); +out_reftbl: + tipc_handler_stop(); +out_handler: + return err; } static int __init tipc_init(void) @@ -174,8 +185,6 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { - tipc_handler_stop(); - tipc_core_stop_net(); tipc_core_stop(); pr_info("Deactivated\n"); } diff --git a/net/tipc/core.h b/net/tipc/core.h index 5569d96b4da3..4dfe137587bb 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -90,7 +90,6 @@ extern int tipc_random __read_mostly; /* * Routines available to privileged subsystems */ -int tipc_core_start_net(unsigned long); int tipc_handler_start(void); void tipc_handler_stop(void); int tipc_netlink_start(void); diff --git a/net/tipc/handler.c b/net/tipc/handler.c index e4bc8a296744..1fabf160501f 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -58,7 +58,6 @@ unsigned int tipc_k_signal(Handler routine, unsigned long argument) spin_lock_bh(&qitem_lock); if (!handler_enabled) { - pr_err("Signal request ignored by handler\n"); spin_unlock_bh(&qitem_lock); return -ENOPROTOOPT; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92a1533af4e0..042e8e3cabc0 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -941,20 +941,48 @@ int tipc_nametbl_init(void) return 0; } -void tipc_nametbl_stop(void) +/** + * tipc_purge_publications - remove all publications for a given type + * + * tipc_nametbl_lock must be held when calling this function + */ +static void tipc_purge_publications(struct name_seq *seq) { - u32 i; + struct publication *publ, *safe; + struct sub_seq *sseq; + struct name_info *info; - if (!table.types) + if (!seq->sseqs) { + nameseq_delete_empty(seq); return; + } + sseq = seq->sseqs; + info = sseq->info; + list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { + tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, + publ->ref, publ->key); + } +} + +void tipc_nametbl_stop(void) +{ + u32 i; + struct name_seq *seq; + struct hlist_head *seq_head; + struct hlist_node *safe; - /* Verify name table is empty, then release it */ + /* Verify name table is empty and purge any lingering + * publications, then release the name table + */ write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { if (hlist_empty(&table.types[i])) continue; - pr_err("nametbl_stop(): orphaned hash chain detected\n"); - break; + seq_head = &table.types[i]; + hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) { + tipc_purge_publications(seq); + } + continue; } kfree(table.types); table.types = NULL; diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 9f72a6376362..3aaf73de9e2d 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -83,8 +83,6 @@ static struct genl_ops tipc_genl_ops[] = { }, }; -static int tipc_genl_family_registered; - int tipc_netlink_start(void) { int res; @@ -94,16 +92,10 @@ int tipc_netlink_start(void) pr_err("Failed to register netlink interface\n"); return res; } - - tipc_genl_family_registered = 1; return 0; } void tipc_netlink_stop(void) { - if (!tipc_genl_family_registered) - return; - genl_unregister_family(&tipc_genl_family); - tipc_genl_family_registered = 0; } diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 2a2a938dc22c..de3d593e2fee 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -126,9 +126,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start) */ void tipc_ref_table_stop(void) { - if (!tipc_ref_table.entries) - return; - vfree(tipc_ref_table.entries); tipc_ref_table.entries = NULL; } diff --git a/net/tipc/server.c b/net/tipc/server.c index b635ca347a87..646a930eefbf 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -87,7 +87,6 @@ static void tipc_clean_outqueues(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct tipc_server *s = con->server; if (con->sock) { tipc_sock_release_local(con->sock); @@ -95,10 +94,6 @@ static void tipc_conn_kref_release(struct kref *kref) } tipc_clean_outqueues(con); - - if (con->conid) - s->tipc_conn_shutdown(con->conid, con->usr_data); - kfree(con); } @@ -181,6 +176,9 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { + if (con->conid) + s->tipc_conn_shutdown(con->conid, con->usr_data); + spin_lock_bh(&s->idr_lock); idr_remove(&s->conn_idr, con->conid); s->idr_in_use--; @@ -429,10 +427,12 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); - if (test_bit(CF_CONNECTED, &con->flags)) + if (test_bit(CF_CONNECTED, &con->flags)) { if (!queue_work(s->send_wq, &con->swork)) conn_put(con); - + } else { + conn_put(con); + } return 0; } @@ -573,7 +573,6 @@ int tipc_server_start(struct tipc_server *s) kmem_cache_destroy(s->rcvbuf_cache); return ret; } - s->enabled = 1; return ret; } @@ -583,10 +582,6 @@ void tipc_server_stop(struct tipc_server *s) int total = 0; int id; - if (!s->enabled) - return; - - s->enabled = 0; spin_lock_bh(&s->idr_lock); for (id = 0; total < s->idr_in_use; id++) { con = idr_find(&s->conn_idr, id); diff --git a/net/tipc/server.h b/net/tipc/server.h index 98b23f20bc0f..be817b0b547e 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -56,7 +56,6 @@ * @name: server name * @imp: message importance * @type: socket type - * @enabled: identify whether server is launched or not */ struct tipc_server { struct idr conn_idr; @@ -74,7 +73,6 @@ struct tipc_server { const char name[TIPC_SERVER_NAME_LEN]; int imp; int type; - int enabled; }; int tipc_conn_sendmsg(struct tipc_server *s, int conid, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index aab4948f0aff..0ed0eaa62f29 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -70,8 +70,6 @@ static const struct proto_ops msg_ops; static struct proto tipc_proto; static struct proto tipc_proto_kern; -static int sockets_enabled; - /* * Revised TIPC socket locking policy: * @@ -999,7 +997,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sock->state == SS_DISCONNECTING) { err = -ENOTCONN; break; @@ -1625,7 +1623,7 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); @@ -2027,8 +2025,6 @@ int tipc_socket_init(void) proto_unregister(&tipc_proto); goto out; } - - sockets_enabled = 1; out: return res; } @@ -2038,10 +2034,6 @@ int tipc_socket_init(void) */ void tipc_socket_stop(void) { - if (!sockets_enabled) - return; - - sockets_enabled = 0; sock_unregister(tipc_family_ops.family); proto_unregister(&tipc_proto); } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 7cb0bd5b1176..642437231ad5 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -96,20 +96,16 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, { struct tipc_subscriber *subscriber = sub->subscriber; struct kvec msg_sect; - int ret; msg_sect.iov_base = (void *)&sub->evt; msg_sect.iov_len = sizeof(struct tipc_event); - sub->evt.event = htohl(event, sub->swap); sub->evt.found_lower = htohl(found_lower, sub->swap); sub->evt.found_upper = htohl(found_upper, sub->swap); sub->evt.port.ref = htohl(port_ref, sub->swap); sub->evt.port.node = htohl(node, sub->swap); - ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, - msg_sect.iov_base, msg_sect.iov_len); - if (ret < 0) - pr_err("Sending subscription event failed, no memory\n"); + tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base, + msg_sect.iov_len); } /** @@ -153,14 +149,6 @@ static void subscr_timeout(struct tipc_subscription *sub) /* The spin lock per subscriber is used to protect its members */ spin_lock_bh(&subscriber->lock); - /* Validate if the connection related to the subscriber is - * closed (in case subscriber is terminating) - */ - if (subscriber->conid == 0) { - spin_unlock_bh(&subscriber->lock); - return; - } - /* Validate timeout (in case subscription is being cancelled) */ if (sub->timeout == TIPC_WAIT_FOREVER) { spin_unlock_bh(&subscriber->lock); @@ -215,9 +203,6 @@ static void subscr_release(struct tipc_subscriber *subscriber) spin_lock_bh(&subscriber->lock); - /* Invalidate subscriber reference */ - subscriber->conid = 0; - /* Destroy any existing subscriptions for subscriber */ list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, subscription_list) { @@ -278,9 +263,9 @@ static void subscr_cancel(struct tipc_subscr *s, * * Called with subscriber lock held. */ -static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, - struct tipc_subscriber *subscriber) -{ +static int subscr_subscribe(struct tipc_subscr *s, + struct tipc_subscriber *subscriber, + struct tipc_subscription **sub_p) { struct tipc_subscription *sub; int swap; @@ -291,23 +276,21 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); subscr_cancel(s, subscriber); - return NULL; + return 0; } /* Refuse subscription if global limit exceeded */ if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { pr_warn("Subscription rejected, limit reached (%u)\n", TIPC_MAX_SUBSCRIPTIONS); - subscr_terminate(subscriber); - return NULL; + return -EINVAL; } /* Allocate subscription object */ sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { pr_warn("Subscription rejected, no memory\n"); - subscr_terminate(subscriber); - return NULL; + return -ENOMEM; } /* Initialize subscription object */ @@ -321,8 +304,7 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, (sub->seq.lower > sub->seq.upper)) { pr_warn("Subscription rejected, illegal request\n"); kfree(sub); - subscr_terminate(subscriber); - return NULL; + return -EINVAL; } INIT_LIST_HEAD(&sub->nameseq_list); list_add(&sub->subscription_list, &subscriber->subscription_list); @@ -335,8 +317,8 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, (Handler)subscr_timeout, (unsigned long)sub); k_start_timer(&sub->timer, sub->timeout); } - - return sub; + *sub_p = sub; + return 0; } /* Handle one termination request for the subscriber */ @@ -350,10 +332,14 @@ static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { struct tipc_subscriber *subscriber = usr_data; - struct tipc_subscription *sub; + struct tipc_subscription *sub = NULL; spin_lock_bh(&subscriber->lock); - sub = subscr_subscribe((struct tipc_subscr *)buf, subscriber); + if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) { + spin_unlock_bh(&subscriber->lock); + subscr_terminate(subscriber); + return; + } if (sub) tipc_nametbl_subscribe(sub); spin_unlock_bh(&subscriber->lock); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 29fc8bee9702..94404f19f9de 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -163,9 +163,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) static inline unsigned int unix_hash_fold(__wsum n) { - unsigned int hash = (__force unsigned int)n; + unsigned int hash = (__force unsigned int)csum_fold(n); - hash ^= hash>>16; hash ^= hash>>8; return hash&(UNIX_HASH_SIZE-1); } @@ -1788,8 +1787,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } @@ -1914,6 +1916,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct unix_sock *u = unix_sk(sk); DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); int copied = 0; + int noblock = flags & MSG_DONTWAIT; int check_creds = 0; int target; int err = 0; @@ -1929,7 +1932,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); - timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, noblock); /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg @@ -1941,8 +1944,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, } err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(timeo); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 010892b81a06..a3bf18d11609 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -788,8 +788,6 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, default: break; } - - wdev->beacon_interval = 0; } static int cfg80211_netdev_notifier_call(struct notifier_block *nb, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 9b897fca7487..f0541370e68e 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1700,7 +1700,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) return; case NL80211_REGDOM_SET_BY_USER: treatment = reg_process_hint_user(reg_request); - if (treatment == REG_REQ_OK || + if (treatment == REG_REQ_IGNORE || treatment == REG_REQ_ALREADY_SET) return; schedule_delayed_work(®_timeout, msecs_to_jiffies(3142)); @@ -2373,6 +2373,7 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, int set_regdom(const struct ieee80211_regdomain *rd) { struct regulatory_request *lr; + bool user_reset = false; int r; if (!reg_is_valid_request(rd->alpha2)) { @@ -2389,6 +2390,7 @@ int set_regdom(const struct ieee80211_regdomain *rd) break; case NL80211_REGDOM_SET_BY_USER: r = reg_set_rd_user(rd, lr); + user_reset = true; break; case NL80211_REGDOM_SET_BY_DRIVER: r = reg_set_rd_driver(rd, lr); @@ -2402,8 +2404,14 @@ int set_regdom(const struct ieee80211_regdomain *rd) } if (r) { - if (r == -EALREADY) + switch (r) { + case -EALREADY: reg_set_request_processed(); + break; + default: + /* Back to world regulatory in case of errors */ + restore_regulatory_settings(user_reset); + } kfree(rd); return r; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4b98b25793c5..1d5c7bf29938 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1158,7 +1158,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, if (hlist_unhashed(&pol->bydst)) return NULL; - hlist_del(&pol->bydst); + hlist_del_init(&pol->bydst); hlist_del(&pol->byidx); list_del(&pol->walk.all); net->xfrm.policy_count[dir]--; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a26b7aa79475..40f1b3e92e78 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1159,6 +1159,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } x->props.aalgo = orig->props.aalgo; + if (orig->aead) { + x->aead = xfrm_algo_aead_clone(orig->aead); + if (!x->aead) + goto error; + } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) @@ -1201,6 +1206,9 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->tfcpad = orig->tfcpad; + x->replay_maxdiff = orig->replay_maxdiff; + x->replay_maxage = orig->replay_maxage; x->curlft.add_time = orig->curlft.add_time; x->km.state = orig->km.state; x->km.seq = orig->km.seq; @@ -1215,11 +1223,12 @@ out: return NULL; } -/* net->xfrm.xfrm_state_lock is held */ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) { unsigned int h; - struct xfrm_state *x; + struct xfrm_state *x = NULL; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, @@ -1236,7 +1245,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, @@ -1251,11 +1260,13 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } - return NULL; + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); @@ -1451,7 +1462,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - struct net *net = xs_net(*dst); + struct net *net = xs_net(*src); if (!afinfo) return -EAFNOSUPPORT; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ae3ec7c18b0..2f7ddc3a59b4 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -32,11 +32,6 @@ #include <linux/in6.h> #endif -static inline int aead_len(struct xfrm_algo_aead *alg) -{ - return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); -} - static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) { struct nlattr *rt = attrs[type]; @@ -1226,7 +1221,7 @@ static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs return 0; uctx = nla_data(rt); - return security_xfrm_policy_alloc(&pol->security, uctx); + return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL); } static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, @@ -1631,7 +1626,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (rt) { struct xfrm_user_sec_ctx *uctx = nla_data(rt); - err = security_xfrm_policy_alloc(&ctx, uctx); + err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL); if (err) return err; } @@ -1933,7 +1928,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (rt) { struct xfrm_user_sec_ctx *uctx = nla_data(rt); - err = security_xfrm_policy_alloc(&ctx, uctx); + err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL); if (err) return err; } diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 547e15daf03d..93a0da26582b 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -155,6 +155,15 @@ ld-option = $(call try-run,\ # Important: no spaces around options ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2)) +# ld-version +# Usage: $(call ld-version) +# Note this is mainly for HJ Lu's 3 number binutil versions +ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) + +# ld-ifversion +# Usage: $(call ld-ifversion, -ge, 22252, y) +ld-ifversion = $(shell [ $(call ld-version) $(1) $(2) ] && echo $(3)) + ###### ### diff --git a/scripts/Makefile.build b/scripts/Makefile.build index d5d859c80729..9f0ee22b914f 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -198,7 +198,7 @@ $(multi-objs-y:.o=.s) : modname = $(modname-multi) $(multi-objs-y:.o=.lst) : modname = $(modname-multi) quiet_cmd_cc_s_c = CC $(quiet_modtag) $@ -cmd_cc_s_c = $(CC) $(c_flags) -fverbose-asm -S -o $@ $< +cmd_cc_s_c = $(CC) $(c_flags) $(DISABLE_LTO) -fverbose-asm -S -o $@ $< $(obj)/%.s: $(src)/%.c FORCE $(call if_changed_dep,cc_s_c) diff --git a/scripts/gcc-ld b/scripts/gcc-ld new file mode 100644 index 000000000000..cadab9a13ed7 --- /dev/null +++ b/scripts/gcc-ld @@ -0,0 +1,29 @@ +#!/bin/sh +# run gcc with ld options +# used as a wrapper to execute link time optimizations +# yes virginia, this is not pretty + +ARGS="-nostdlib" + +while [ "$1" != "" ] ; do + case "$1" in + -save-temps|-m32|-m64) N="$1" ;; + -r) N="$1" ;; + -[Wg]*) N="$1" ;; + -[olv]|-[Ofd]*|-nostdlib) N="$1" ;; + --end-group|--start-group) + N="-Wl,$1" ;; + -[RTFGhIezcbyYu]*|\ +--script|--defsym|-init|-Map|--oformat|-rpath|\ +-rpath-link|--sort-section|--section-start|-Tbss|-Tdata|-Ttext|\ +--version-script|--dynamic-list|--version-exports-symbol|--wrap|-m) + A="$1" ; shift ; N="-Wl,$A,$1" ;; + -[m]*) N="$1" ;; + -*) N="-Wl,$1" ;; + *) N="$1" ;; + esac + ARGS="$ARGS $N" + shift +done + +exec $CC $ARGS diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh index ef474098d9f1..17fa901418ae 100644 --- a/scripts/gen_initramfs_list.sh +++ b/scripts/gen_initramfs_list.sh @@ -257,7 +257,7 @@ case "$arg" in && compr="lzop -9 -f" echo "$output_file" | grep -q "\.lz4$" \ && [ -x "`which lz4 2> /dev/null`" ] \ - && compr="lz4 -9 -f" + && compr="lz4 -l -9 -f" echo "$output_file" | grep -q "\.cpio$" && compr="cat" shift ;; diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh new file mode 100755 index 000000000000..198580d245e0 --- /dev/null +++ b/scripts/ld-version.sh @@ -0,0 +1,8 @@ +#!/usr/bin/awk -f +# extract linker version number from stdin and turn into single number + { + gsub(".*)", ""); + split($1,a, "."); + print a[1]*10000000 + a[2]*100000 + a[3]*10000 + a[4]*100 + a[5]; + exit + } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 40610984a1b5..066355673930 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -623,7 +623,10 @@ static void handle_modversions(struct module *mod, struct elf_info *info, switch (sym->st_shndx) { case SHN_COMMON: - warn("\"%s\" [%s] is COMMON symbol\n", symname, mod->name); + if (!strncmp(symname, "__gnu_lto_", sizeof("__gnu_lto_")-1)) { + /* Should warn here, but modpost runs before the linker */ + } else + warn("\"%s\" [%s] is COMMON symbol\n", symname, mod->name); break; case SHN_UNDEF: /* undefined symbol */ @@ -849,6 +852,7 @@ static const char *section_white_list[] = ".xt.lit", /* xtensa */ ".arcextmap*", /* arc */ ".gnu.linkonce.arcext*", /* arc : modules */ + ".gnu.lto*", NULL }; @@ -1455,6 +1459,10 @@ static void check_section_mismatch(const char *modname, struct elf_info *elf, to = find_elf_symbol(elf, r->r_addend, sym); tosym = sym_name(elf, to); + if (!strncmp(fromsym, "reference___initcall", + sizeof("reference___initcall")-1)) + return; + /* check whitelist - we may ignore it */ if (secref_whitelist(mismatch, fromsec, fromsym, tosec, tosym)) { @@ -1502,6 +1510,16 @@ static int addend_386_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) #define R_ARM_JUMP24 29 #endif +#ifndef R_ARM_THM_CALL +#define R_ARM_THM_CALL 10 +#endif +#ifndef R_ARM_THM_JUMP24 +#define R_ARM_THM_JUMP24 30 +#endif +#ifndef R_ARM_THM_JUMP19 +#define R_ARM_THM_JUMP19 51 +#endif + static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) { unsigned int r_typ = ELF_R_TYPE(r->r_info); @@ -1515,6 +1533,9 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: + case R_ARM_THM_CALL: + case R_ARM_THM_JUMP24: + case R_ARM_THM_JUMP19: /* From ARM ABI: ((S + A) | T) - P */ r->r_addend = (int)(long)(elf->hdr + sechdr->sh_offset + @@ -1680,6 +1701,19 @@ static void check_sec_ref(struct module *mod, const char *modname, } } +static char *remove_dot(char *s) +{ + char *end; + int n = strcspn(s, "."); + + if (n > 0 && s[n] != 0) { + strtoul(s + n + 1, &end, 10); + if (end > s + n + 1 && (*end == '.' || *end == 0)) + s[n] = 0; + } + return s; +} + static void read_symbols(char *modname) { const char *symname; @@ -1718,7 +1752,7 @@ static void read_symbols(char *modname) } for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { - symname = info.strtab + sym->st_name; + symname = remove_dot(info.strtab + sym->st_name); handle_modversions(mod, &info, sym, symname); handle_moddevtable(mod, &info, sym, symname); diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 51207e4d5f8b..168b43dc0a59 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -127,7 +127,7 @@ struct elf_info { Elf_Section export_gpl_sec; Elf_Section export_unused_gpl_sec; Elf_Section export_gpl_future_sec; - const char *strtab; + char *strtab; char *modinfo; unsigned int modinfo_len; diff --git a/security/capability.c b/security/capability.c index 8b4f24ae4338..21e2b9cae685 100644 --- a/security/capability.c +++ b/security/capability.c @@ -757,7 +757,8 @@ static void cap_skb_owned_by(struct sk_buff *skb, struct sock *sk) #ifdef CONFIG_SECURITY_NETWORK_XFRM static int cap_xfrm_policy_alloc_security(struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *sec_ctx) + struct xfrm_user_sec_ctx *sec_ctx, + gfp_t gfp) { return 0; } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index d46cbc5e335e..2fb2576dc644 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1000,7 +1000,11 @@ static int keyring_detect_cycle_iterator(const void *object, kenter("{%d}", key->serial); - BUG_ON(key != ctx->match_data); + /* We might get a keyring with matching index-key that is nonetheless a + * different keyring. */ + if (key != ctx->match_data) + return 0; + ctx->result = ERR_PTR(-EDEADLK); return 1; } diff --git a/security/security.c b/security/security.c index 15b6928592ef..919cad93ac82 100644 --- a/security/security.c +++ b/security/security.c @@ -1317,9 +1317,11 @@ void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) #ifdef CONFIG_SECURITY_NETWORK_XFRM -int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx) +int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, + gfp_t gfp) { - return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx); + return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4b34847208cc..b332e2cc0954 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -668,7 +668,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, if (flags[i] == SBLABEL_MNT) continue; rc = security_context_to_sid(mount_options[i], - strlen(mount_options[i]), &sid); + strlen(mount_options[i]), &sid, GFP_KERNEL); if (rc) { printk(KERN_WARNING "SELinux: security_context_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n", @@ -2489,7 +2489,8 @@ static int selinux_sb_remount(struct super_block *sb, void *data) if (flags[i] == SBLABEL_MNT) continue; len = strlen(mount_options[i]); - rc = security_context_to_sid(mount_options[i], len, &sid); + rc = security_context_to_sid(mount_options[i], len, &sid, + GFP_KERNEL); if (rc) { printk(KERN_WARNING "SELinux: security_context_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n", @@ -2893,7 +2894,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, if (rc) return rc; - rc = security_context_to_sid(value, size, &newsid); + rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!capable(CAP_MAC_ADMIN)) { struct audit_buffer *ab; @@ -3050,7 +3051,7 @@ static int selinux_inode_setsecurity(struct inode *inode, const char *name, if (!value || !size) return -EACCES; - rc = security_context_to_sid((void *)value, size, &newsid); + rc = security_context_to_sid((void *)value, size, &newsid, GFP_KERNEL); if (rc) return rc; @@ -5529,7 +5530,7 @@ static int selinux_setprocattr(struct task_struct *p, str[size-1] = 0; size--; } - error = security_context_to_sid(value, size, &sid); + error = security_context_to_sid(value, size, &sid, GFP_KERNEL); if (error == -EINVAL && !strcmp(name, "fscreate")) { if (!capable(CAP_MAC_ADMIN)) { struct audit_buffer *ab; @@ -5638,7 +5639,7 @@ static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { - return security_context_to_sid(secdata, seclen, secid); + return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index 8ed8daf7f1ee..ce7852cf526b 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -134,7 +134,7 @@ int security_sid_to_context(u32 sid, char **scontext, int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len); int security_context_to_sid(const char *scontext, u32 scontext_len, - u32 *out_sid); + u32 *out_sid, gfp_t gfp); int security_context_to_sid_default(const char *scontext, u32 scontext_len, u32 *out_sid, u32 def_sid, gfp_t gfp_flags); diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 48c3cc94c168..9f0584710c85 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -10,7 +10,8 @@ #include <net/flow.h> int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *uctx); + struct xfrm_user_sec_ctx *uctx, + gfp_t gfp); int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp); void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 5122affe06a8..d60c0ee66387 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -576,7 +576,7 @@ static ssize_t sel_write_context(struct file *file, char *buf, size_t size) if (length) goto out; - length = security_context_to_sid(buf, size, &sid); + length = security_context_to_sid(buf, size, &sid, GFP_KERNEL); if (length) goto out; @@ -731,11 +731,13 @@ static ssize_t sel_write_access(struct file *file, char *buf, size_t size) if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; - length = security_context_to_sid(scon, strlen(scon) + 1, &ssid); + length = security_context_to_sid(scon, strlen(scon) + 1, &ssid, + GFP_KERNEL); if (length) goto out; - length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid); + length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid, + GFP_KERNEL); if (length) goto out; @@ -817,11 +819,13 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size) objname = namebuf; } - length = security_context_to_sid(scon, strlen(scon) + 1, &ssid); + length = security_context_to_sid(scon, strlen(scon) + 1, &ssid, + GFP_KERNEL); if (length) goto out; - length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid); + length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid, + GFP_KERNEL); if (length) goto out; @@ -878,11 +882,13 @@ static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size) if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; - length = security_context_to_sid(scon, strlen(scon) + 1, &ssid); + length = security_context_to_sid(scon, strlen(scon) + 1, &ssid, + GFP_KERNEL); if (length) goto out; - length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid); + length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid, + GFP_KERNEL); if (length) goto out; @@ -934,7 +940,7 @@ static ssize_t sel_write_user(struct file *file, char *buf, size_t size) if (sscanf(buf, "%s %s", con, user) != 2) goto out; - length = security_context_to_sid(con, strlen(con) + 1, &sid); + length = security_context_to_sid(con, strlen(con) + 1, &sid, GFP_KERNEL); if (length) goto out; @@ -994,11 +1000,13 @@ static ssize_t sel_write_member(struct file *file, char *buf, size_t size) if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; - length = security_context_to_sid(scon, strlen(scon) + 1, &ssid); + length = security_context_to_sid(scon, strlen(scon) + 1, &ssid, + GFP_KERNEL); if (length) goto out; - length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid); + length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid, + GFP_KERNEL); if (length) goto out; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 5d0144ee8ed6..4bca49414a40 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -1289,16 +1289,18 @@ out: * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID + * @gfp: context for the allocation * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ -int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid) +int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid, + gfp_t gfp) { return security_context_to_sid_core(scontext, scontext_len, - sid, SECSID_NULL, GFP_KERNEL, 0); + sid, SECSID_NULL, gfp, 0); } /** diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index 0462cb3ff0a7..98b042630a9e 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -78,7 +78,8 @@ static inline int selinux_authorizable_xfrm(struct xfrm_state *x) * xfrm_user_sec_ctx context. */ static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *uctx) + struct xfrm_user_sec_ctx *uctx, + gfp_t gfp) { int rc; const struct task_security_struct *tsec = current_security(); @@ -94,7 +95,7 @@ static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp, if (str_len >= PAGE_SIZE) return -ENOMEM; - ctx = kmalloc(sizeof(*ctx) + str_len + 1, GFP_KERNEL); + ctx = kmalloc(sizeof(*ctx) + str_len + 1, gfp); if (!ctx) return -ENOMEM; @@ -103,7 +104,7 @@ static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp, ctx->ctx_len = str_len; memcpy(ctx->ctx_str, &uctx[1], str_len); ctx->ctx_str[str_len] = '\0'; - rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid); + rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid, gfp); if (rc) goto err; @@ -282,9 +283,10 @@ int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid) * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy. */ int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *uctx) + struct xfrm_user_sec_ctx *uctx, + gfp_t gfp) { - return selinux_xfrm_alloc_user(ctxp, uctx); + return selinux_xfrm_alloc_user(ctxp, uctx, gfp); } /* @@ -332,7 +334,7 @@ int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *uctx) { - return selinux_xfrm_alloc_user(&x->security, uctx); + return selinux_xfrm_alloc_user(&x->security, uctx, GFP_KERNEL); } /* diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 7a20897d33db..7403f348ed14 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -133,7 +133,7 @@ static int snd_compr_open(struct inode *inode, struct file *f) kfree(data); } snd_card_unref(compr->card); - return 0; + return ret; } static int snd_compr_free(struct inode *inode, struct file *f) diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index df3652ad15ef..8ed0bcc01386 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -1026,6 +1026,9 @@ static void ad1884_fixup_thinkpad(struct hda_codec *codec, spec->gen.keep_eapd_on = 1; spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook; spec->eapd_nid = 0x12; + /* Analog PC Beeper - allow firmware/ACPI beeps */ + spec->beep_amp = HDA_COMPOSE_AMP_VAL(0x20, 3, 3, HDA_INPUT); + spec->gen.beep_nid = 0; /* no digital beep */ } } @@ -1092,6 +1095,7 @@ static int patch_ad1884(struct hda_codec *codec) spec = codec->spec; spec->gen.mixer_nid = 0x20; + spec->gen.mixer_merge_nid = 0x21; spec->gen.beep_nid = 0x10; set_beep_amp(spec, 0x10, 0, HDA_OUTPUT); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ec304f3ae3b4..8d0a84436674 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3616,6 +3616,19 @@ static void alc_fixup_auto_mute_via_amp(struct hda_codec *codec, } } +static void alc_no_shutup(struct hda_codec *codec) +{ +} + +static void alc_fixup_no_shutup(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + struct alc_spec *spec = codec->spec; + spec->shutup = alc_no_shutup; + } +} + static void alc_fixup_headset_mode_alc668(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -3844,6 +3857,7 @@ enum { ALC269_FIXUP_HP_GPIO_LED, ALC269_FIXUP_INV_DMIC, ALC269_FIXUP_LENOVO_DOCK, + ALC269_FIXUP_NO_SHUTUP, ALC286_FIXUP_SONY_MIC_NO_PRESENCE, ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT, ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, @@ -4020,6 +4034,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_inv_dmic_0x12, }, + [ALC269_FIXUP_NO_SHUTUP] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_no_shutup, + }, [ALC269_FIXUP_LENOVO_DOCK] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4253,6 +4271,7 @@ static const struct hda_fixup alc269_fixups[] = { }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { + SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700), @@ -4404,6 +4423,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -5163,7 +5183,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE), - SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP), diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c index ed6f199f8a38..4cf3200e988b 100644 --- a/sound/pci/oxygen/xonar_dg.c +++ b/sound/pci/oxygen/xonar_dg.c @@ -238,11 +238,21 @@ void set_cs4245_adc_params(struct oxygen *chip, cs4245_write_spi(chip, CS4245_MCLK_FREQ); } +static inline unsigned int shift_bits(unsigned int value, + unsigned int shift_from, + unsigned int shift_to, + unsigned int mask) +{ + if (shift_from < shift_to) + return (value << (shift_to - shift_from)) & mask; + else + return (value >> (shift_from - shift_to)) & mask; +} + unsigned int adjust_dg_dac_routing(struct oxygen *chip, unsigned int play_routing) { struct dg *data = chip->model_data; - unsigned int routing = 0; switch (data->output_sel) { case PLAYBACK_DST_HP: @@ -252,15 +262,23 @@ unsigned int adjust_dg_dac_routing(struct oxygen *chip, OXYGEN_PLAY_MUTE67, OXYGEN_PLAY_MUTE_MASK); break; case PLAYBACK_DST_MULTICH: - routing = (0 << OXYGEN_PLAY_DAC0_SOURCE_SHIFT) | - (2 << OXYGEN_PLAY_DAC1_SOURCE_SHIFT) | - (1 << OXYGEN_PLAY_DAC2_SOURCE_SHIFT) | - (0 << OXYGEN_PLAY_DAC3_SOURCE_SHIFT); oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING, OXYGEN_PLAY_MUTE01, OXYGEN_PLAY_MUTE_MASK); break; } - return routing; + return (play_routing & OXYGEN_PLAY_DAC0_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC2_SOURCE_SHIFT, + OXYGEN_PLAY_DAC1_SOURCE_SHIFT, + OXYGEN_PLAY_DAC1_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC1_SOURCE_SHIFT, + OXYGEN_PLAY_DAC2_SOURCE_SHIFT, + OXYGEN_PLAY_DAC2_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC0_SOURCE_SHIFT, + OXYGEN_PLAY_DAC3_SOURCE_SHIFT, + OXYGEN_PLAY_DAC3_SOURCE_MASK); } void dump_cs4245_registers(struct oxygen *chip, diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c index 75d0ad5d2dcb..647a72cda005 100644 --- a/sound/soc/codecs/88pm860x-codec.c +++ b/sound/soc/codecs/88pm860x-codec.c @@ -1328,6 +1328,9 @@ static int pm860x_probe(struct snd_soc_codec *codec) pm860x->codec = codec; codec->control_data = pm860x->regmap; + ret = snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP); + if (ret) + return ret; for (i = 0; i < 4; i++) { ret = request_threaded_irq(pm860x->irq[i], NULL, diff --git a/sound/soc/codecs/si476x.c b/sound/soc/codecs/si476x.c index 52e7cb08434b..fa2b8e07f420 100644 --- a/sound/soc/codecs/si476x.c +++ b/sound/soc/codecs/si476x.c @@ -210,7 +210,7 @@ out: static int si476x_codec_probe(struct snd_soc_codec *codec) { codec->control_data = dev_get_regmap(codec->dev->parent, NULL); - return 0; + return snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP); } static struct snd_soc_dai_ops si476x_dai_ops = { diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c index 3fde9e402710..d163e18d85d4 100644 --- a/sound/soc/omap/n810.c +++ b/sound/soc/omap/n810.c @@ -305,7 +305,9 @@ static int __init n810_soc_init(void) int err; struct device *dev; - if (!(machine_is_nokia_n810() || machine_is_nokia_n810_wimax())) + if (!of_have_populated_dt() || + (!of_machine_is_compatible("nokia,n810") && + !of_machine_is_compatible("nokia,n810-wimax"))) return -ENODEV; n810_snd_device = platform_device_alloc("soc-audio", -1); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 47e1ce771e65..28522bd03b8e 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1989,6 +1989,7 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card) paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list); if (paths < 0) { + dpcm_path_put(&list); dev_warn(fe->dev, "ASoC: %s no valid %s path\n", fe->dai_link->name, "playback"); mutex_unlock(&card->mutex); @@ -2018,6 +2019,7 @@ capture: paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list); if (paths < 0) { + dpcm_path_put(&list); dev_warn(fe->dev, "ASoC: %s no valid %s path\n", fe->dai_link->name, "capture"); mutex_unlock(&card->mutex); @@ -2082,6 +2084,7 @@ static int dpcm_fe_dai_open(struct snd_pcm_substream *fe_substream) fe->dpcm[stream].runtime = fe_substream->runtime; if (dpcm_path_get(fe, stream, &list) <= 0) { + dpcm_path_put(&list); dev_dbg(fe->dev, "ASoC: %s no valid %s route\n", fe->dai_link->name, stream ? "capture" : "playback"); } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 44b0ba4feab3..1bed780e21d9 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -883,6 +883,7 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, } break; + case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */ case USB_ID(0x046d, 0x0808): case USB_ID(0x046d, 0x0809): case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */ diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h new file mode 100644 index 000000000000..d026c6573018 --- /dev/null +++ b/tools/include/linux/hash.h @@ -0,0 +1,5 @@ +#include "../../../include/linux/hash.h" + +#ifndef _TOOLS_LINUX_HASH_H +#define _TOOLS_LINUX_HASH_H +#endif diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index ed2f51e11b80..ce00f7ee6455 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -9,8 +9,10 @@ LIB_H= LIB_OBJS= LIB_H += fs/debugfs.h +LIB_H += fs/fs.h LIB_OBJS += $(OUTPUT)fs/debugfs.o +LIB_OBJS += $(OUTPUT)fs/fs.o LIBFILE = libapikfs.a diff --git a/tools/perf/util/fs.c b/tools/lib/api/fs/fs.c index f5be1f26e724..5b5eb788996e 100644 --- a/tools/perf/util/fs.c +++ b/tools/lib/api/fs/fs.c @@ -1,8 +1,13 @@ +/* TODO merge/factor in debugfs.c here */ -/* TODO merge/factor into tools/lib/lk/debugfs.c */ +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <sys/vfs.h> -#include "util.h" -#include "util/fs.h" +#include "debugfs.h" +#include "fs.h" static const char * const sysfs__fs_known_mountpoints[] = { "/sys", diff --git a/tools/perf/util/include/linux/magic.h b/tools/lib/api/fs/fs.h index 07d63cf3e0f6..cb7049551f33 100644 --- a/tools/perf/util/include/linux/magic.h +++ b/tools/lib/api/fs/fs.h @@ -1,9 +1,5 @@ -#ifndef _PERF_LINUX_MAGIC_H_ -#define _PERF_LINUX_MAGIC_H_ - -#ifndef DEBUGFS_MAGIC -#define DEBUGFS_MAGIC 0x64626720 -#endif +#ifndef __API_FS__ +#define __API_FS__ #ifndef SYSFS_MAGIC #define SYSFS_MAGIC 0x62656572 @@ -13,4 +9,6 @@ #define PROC_SUPER_MAGIC 0x9fa0 #endif -#endif +const char *sysfs__mountpoint(void); +const char *procfs__mountpoint(void); +#endif /* __API_FS__ */ diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index da8b7aa3d351..07b0b7542511 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -87,8 +87,8 @@ endif # BUILD_SRC # We process the rest of the Makefile if this is the final invocation of make ifeq ($(skip-makefile),) -srctree := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)) -objtree := $(CURDIR) +srctree := $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))) +objtree := $(realpath $(CURDIR)) src := $(srctree) obj := $(objtree) @@ -112,7 +112,7 @@ export Q VERBOSE LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION) -INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES) +INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index f8465a811aa5..23bd69cb5ade 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -418,7 +418,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) __attribute__((constructor)) static void init_preload(void) { - if (__init_state != done) + if (__init_state == done) return; #ifndef __GLIBC__ diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 5334ad9d39b7..5334ad9d39b7 100644..100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h new file mode 100644 index 000000000000..d82b170bb216 --- /dev/null +++ b/tools/lib/lockdep/uinclude/asm/hash.h @@ -0,0 +1,6 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +/* Stub */ + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h index 4c99fcb5da27..042ee8e463c9 100644 --- a/tools/lib/lockdep/uinclude/linux/rcu.h +++ b/tools/lib/lockdep/uinclude/linux/rcu.h @@ -13,4 +13,9 @@ static inline int rcu_is_cpu_idle(void) return 1; } +static inline bool rcu_is_watching(void) +{ + return false; +} + #endif diff --git a/tools/net/Makefile b/tools/net/Makefile index 004cd74734b6..ee577ea03ba5 100644 --- a/tools/net/Makefile +++ b/tools/net/Makefile @@ -12,7 +12,7 @@ YACC = bison all : bpf_jit_disasm bpf_dbg bpf_asm -bpf_jit_disasm : CFLAGS = -Wall -O2 +bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm' bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl bpf_jit_disasm : bpf_jit_disasm.o diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 888d51137fbe..1d78a4064da4 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -18,6 +18,10 @@ from it, into perf.data. Perf record options are accepted and are passed through "perf mem -t <TYPE> report" displays the result. It invokes perf report with the right set of options to display a memory access profile. +Note that on Intel systems the memory latency reported is the use-latency, +not the pure load (or store latency). Use latency includes any pipeline +queueing delays in addition to the memory subsystem latency. + OPTIONS ------- <command>...:: diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index b715cb71592b..1513935c399b 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -136,6 +136,8 @@ Each probe argument follows below syntax. 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f41572d0dd76..c0c87c87b60f 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -6,6 +6,7 @@ tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/include/asm/bug.h tools/include/linux/compiler.h +tools/include/linux/hash.h include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 7257e7e9e38a..50d875d970c4 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -7,6 +7,8 @@ include config/utilities.mak # Define V to have a more verbose compile. # +# Define VF to have a more verbose feature check output. +# # Define O to save output files in a separate directory. # # Define ARCH as name of target architecture if you want cross-builds. @@ -55,6 +57,9 @@ include config/utilities.mak # Define NO_LIBAUDIT if you do not want libaudit support # # Define NO_LIBBIONIC if you do not want bionic support +# +# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support +# for dwarf backtrace post unwind. ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -208,7 +213,7 @@ LIB_H += ../../include/uapi/linux/perf_event.h LIB_H += ../../include/linux/rbtree.h LIB_H += ../../include/linux/list.h LIB_H += ../../include/uapi/linux/const.h -LIB_H += ../../include/linux/hash.h +LIB_H += ../include/linux/hash.h LIB_H += ../../include/linux/stringify.h LIB_H += util/include/linux/bitmap.h LIB_H += util/include/linux/bitops.h @@ -218,9 +223,7 @@ LIB_H += util/include/linux/ctype.h LIB_H += util/include/linux/kernel.h LIB_H += util/include/linux/list.h LIB_H += util/include/linux/export.h -LIB_H += util/include/linux/magic.h LIB_H += util/include/linux/poison.h -LIB_H += util/include/linux/prefetch.h LIB_H += util/include/linux/rbtree.h LIB_H += util/include/linux/rbtree_augmented.h LIB_H += util/include/linux/string.h @@ -244,7 +247,6 @@ LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h -LIB_H += util/fs.h LIB_H += util/pmu.h LIB_H += util/event.h LIB_H += util/evsel.h @@ -306,7 +308,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/fs.o LIB_OBJS += $(OUTPUT)util/pmu.o LIB_OBJS += $(OUTPUT)util/environment.o LIB_OBJS += $(OUTPUT)util/event.o @@ -408,6 +409,11 @@ endif LIB_OBJS += $(OUTPUT)tests/code-reading.o LIB_OBJS += $(OUTPUT)tests/sample-parsing.o LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o +ifndef NO_DWARF_UNWIND +ifeq ($(ARCH),x86) +LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o +endif +endif BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -420,6 +426,9 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o +BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o +BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o +BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o BUILTIN_OBJS += $(OUTPUT)builtin-diff.o BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o @@ -475,8 +484,13 @@ ifndef NO_DWARF endif # NO_DWARF endif # NO_LIBELF +ifndef NO_LIBDW_DWARF_UNWIND + LIB_OBJS += $(OUTPUT)util/unwind-libdw.o + LIB_H += util/unwind-libdw.h +endif + ifndef NO_LIBUNWIND - LIB_OBJS += $(OUTPUT)util/unwind.o + LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o endif LIB_OBJS += $(OUTPUT)tests/keep-tracking.o @@ -533,6 +547,7 @@ ifeq ($(NO_PERF_REGS),0) ifeq ($(ARCH),x86) LIB_H += arch/x86/include/perf_regs.h endif + LIB_OBJS += $(OUTPUT)util/perf_regs.o endif ifndef NO_LIBNUMA @@ -655,6 +670,9 @@ $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS -DPYTHON='"$(PYTHON_WORD)"' \ $< +$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $< + $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< @@ -707,9 +725,15 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) # we depend the various files onto their directories. DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS) DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS))) +# no need to add flex objects, because they depend on bison ones +DIRECTORY_DEPS += $(OUTPUT)util/parse-events-bison.c +DIRECTORY_DEPS += $(OUTPUT)util/pmu-bison.c + +OUTPUT_DIRECTORIES := $(sort $(dir $(DIRECTORY_DEPS))) + +$(DIRECTORY_DEPS): | $(OUTPUT_DIRECTORIES) # In the second step, we make a rule to actually create these directories -$(sort $(dir $(DIRECTORY_DEPS))): +$(OUTPUT_DIRECTORIES): $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null $(LIB_FILE): $(LIB_OBJS) @@ -886,7 +910,7 @@ config-clean: clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf - $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* + $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index fe9b61e322a5..67e9b3d38e89 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -3,5 +3,5 @@ PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif ifndef NO_LIBUNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o endif diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index da3dc950550c..729ed69a6664 100644 --- a/tools/perf/arch/arm/util/unwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -4,7 +4,7 @@ #include "perf_regs.h" #include "../../util/unwind.h" -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { switch (regnum) { case UNW_ARM_R0: diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 8801fe02f206..1641542e3636 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -3,7 +3,14 @@ PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif ifndef NO_LIBUNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o +endif +ifndef NO_LIBDW_DWARF_UNWIND +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o +endif +ifndef NO_DWARF_UNWIND +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index e84ca76aae77..fc819ca34a7e 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -5,14 +5,20 @@ #include "../../util/types.h" #include <asm/perf_regs.h> +void perf_regs_load(u64 *regs); + #ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_X86_32_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ (1ULL << PERF_REG_X86_ES) | \ (1ULL << PERF_REG_X86_FS) | \ (1ULL << PERF_REG_X86_GS)) #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) +#define PERF_REGS_MAX PERF_REG_X86_64_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 #endif #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c new file mode 100644 index 000000000000..b602ad93ce63 --- /dev/null +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -0,0 +1,59 @@ +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 + +static int sample_ustack(struct perf_sample *sample, + struct thread *thread, u64 *regs) +{ + struct stack_dump *stack = &sample->user_stack; + struct map *map; + unsigned long sp; + u64 stack_size, *buf; + + buf = malloc(STACK_SIZE); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + sp = (unsigned long) regs[PERF_REG_X86_SP]; + + map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp); + if (!map) { + pr_debug("failed to get stack map\n"); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + stack->data = (char *) buf; + stack->size = stack_size; + return 0; +} + +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread) +{ + struct regs_dump *regs = &sample->user_regs; + u64 *buf; + + buf = malloc(sizeof(u64) * PERF_REGS_MAX); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + perf_regs_load(buf); + regs->abi = PERF_SAMPLE_REGS_ABI; + regs->regs = buf; + regs->mask = PERF_REGS_MASK; + + return sample_ustack(sample, thread, buf); +} diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S new file mode 100644 index 000000000000..99167bf644ea --- /dev/null +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -0,0 +1,92 @@ + +#include <linux/linkage.h> + +#define AX 0 +#define BX 1 * 8 +#define CX 2 * 8 +#define DX 3 * 8 +#define SI 4 * 8 +#define DI 5 * 8 +#define BP 6 * 8 +#define SP 7 * 8 +#define IP 8 * 8 +#define FLAGS 9 * 8 +#define CS 10 * 8 +#define SS 11 * 8 +#define DS 12 * 8 +#define ES 13 * 8 +#define FS 14 * 8 +#define GS 15 * 8 +#define R8 16 * 8 +#define R9 17 * 8 +#define R10 18 * 8 +#define R11 19 * 8 +#define R12 20 * 8 +#define R13 21 * 8 +#define R14 22 * 8 +#define R15 23 * 8 + +.text +#ifdef HAVE_ARCH_X86_64_SUPPORT +ENTRY(perf_regs_load) + movq %rax, AX(%rdi) + movq %rbx, BX(%rdi) + movq %rcx, CX(%rdi) + movq %rdx, DX(%rdi) + movq %rsi, SI(%rdi) + movq %rdi, DI(%rdi) + movq %rbp, BP(%rdi) + + leaq 8(%rsp), %rax /* exclude this call. */ + movq %rax, SP(%rdi) + + movq 0(%rsp), %rax + movq %rax, IP(%rdi) + + movq $0, FLAGS(%rdi) + movq $0, CS(%rdi) + movq $0, SS(%rdi) + movq $0, DS(%rdi) + movq $0, ES(%rdi) + movq $0, FS(%rdi) + movq $0, GS(%rdi) + + movq %r8, R8(%rdi) + movq %r9, R9(%rdi) + movq %r10, R10(%rdi) + movq %r11, R11(%rdi) + movq %r12, R12(%rdi) + movq %r13, R13(%rdi) + movq %r14, R14(%rdi) + movq %r15, R15(%rdi) + ret +ENDPROC(perf_regs_load) +#else +ENTRY(perf_regs_load) + push %edi + movl 8(%esp), %edi + movl %eax, AX(%edi) + movl %ebx, BX(%edi) + movl %ecx, CX(%edi) + movl %edx, DX(%edi) + movl %esi, SI(%edi) + pop %eax + movl %eax, DI(%edi) + movl %ebp, BP(%edi) + + leal 4(%esp), %eax /* exclude this call. */ + movl %eax, SP(%edi) + + movl 0(%esp), %eax + movl %eax, IP(%edi) + + movl $0, FLAGS(%edi) + movl $0, CS(%edi) + movl $0, SS(%edi) + movl $0, DS(%edi) + movl $0, ES(%edi) + movl $0, FS(%edi) + movl $0, GS(%edi) + ret +ENDPROC(perf_regs_load) +#endif diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c new file mode 100644 index 000000000000..c4b72176ca83 --- /dev/null +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -0,0 +1,51 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[17]; + unsigned nregs; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_X86_##r); \ + val; \ +}) + + if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) { + dwarf_regs[0] = REG(AX); + dwarf_regs[1] = REG(CX); + dwarf_regs[2] = REG(DX); + dwarf_regs[3] = REG(BX); + dwarf_regs[4] = REG(SP); + dwarf_regs[5] = REG(BP); + dwarf_regs[6] = REG(SI); + dwarf_regs[7] = REG(DI); + dwarf_regs[8] = REG(IP); + nregs = 9; + } else { + dwarf_regs[0] = REG(AX); + dwarf_regs[1] = REG(DX); + dwarf_regs[2] = REG(CX); + dwarf_regs[3] = REG(BX); + dwarf_regs[4] = REG(SI); + dwarf_regs[5] = REG(DI); + dwarf_regs[6] = REG(BP); + dwarf_regs[7] = REG(SP); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(IP); + nregs = 17; + } + + return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs); +} diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 456a88cf5b37..3261f68c6a7c 100644 --- a/tools/perf/arch/x86/util/unwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -5,7 +5,7 @@ #include "../../util/unwind.h" #ifdef HAVE_ARCH_X86_64_SUPPORT -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { int id; @@ -69,7 +69,7 @@ int unwind__arch_reg_id(int regnum) return id; } #else -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { int id; diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 0fdc85269c4d..eba46709b279 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -31,6 +31,9 @@ extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused); extern int bench_mem_memset(int argc, const char **argv, const char *prefix); +extern int bench_futex_hash(int argc, const char **argv, const char *prefix); +extern int bench_futex_wake(int argc, const char **argv, const char *prefix); +extern int bench_futex_requeue(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c new file mode 100644 index 000000000000..a84206e9c4aa --- /dev/null +++ b/tools/perf/bench/futex-hash.c @@ -0,0 +1,212 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-hash: Stress the hell out of the Linux kernel futex uaddr hashing. + * + * This program is particularly useful for measuring the kernel's futex hash + * table/function implementation. In order for it to make sense, use with as + * many threads and futexes as possible. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +static unsigned int nthreads = 0; +static unsigned int nsecs = 10; +/* amount of futexes per thread */ +static unsigned int nfutexes = 1024; +static bool fshared = false, done = false, silent = false; + +struct timeval start, end, runtime; +static pthread_mutex_t thread_lock; +static unsigned int threads_starting; +static struct stats throughput_stats; +static pthread_cond_t thread_parent, thread_worker; + +struct worker { + int tid; + u_int32_t *futex; + pthread_t thread; + unsigned long ops; +}; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"), + OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"), + OPT_END() +}; + +static const char * const bench_futex_hash_usage[] = { + "perf bench futex hash <options>", + NULL +}; + +static void *workerfn(void *arg) +{ + int ret; + unsigned int i; + struct worker *w = (struct worker *) arg; + + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + do { + for (i = 0; i < nfutexes; i++, w->ops++) { + /* + * We want the futex calls to fail in order to stress + * the hashing of uaddr and not measure other steps, + * such as internal waitqueue handling, thus enlarging + * the critical region protected by hb->lock. + */ + ret = futex_wait(&w->futex[i], 1234, NULL, + fshared ? 0 : FUTEX_PRIVATE_FLAG); + if (!silent && + (!ret || errno != EAGAIN || errno != EWOULDBLOCK)) + warn("Non-expected futex return call"); + } + } while (!done); + + return NULL; +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + /* inform all threads that we're done for the day */ + done = true; + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); +} + +static void print_summary(void) +{ + unsigned long avg = avg_stats(&throughput_stats); + double stddev = stddev_stats(&throughput_stats); + + printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", + !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), + (int) runtime.tv_sec); +} + +int bench_futex_hash(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + cpu_set_t cpu; + struct sigaction act; + unsigned int i, ncpus; + pthread_attr_t thread_attr; + struct worker *worker = NULL; + + argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); + if (argc) { + usage_with_options(bench_futex_hash_usage, options); + exit(EXIT_FAILURE); + } + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) /* default to the number of CPUs */ + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + goto errmem; + + printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n", + getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs); + + init_stats(&throughput_stats); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + threads_starting = nthreads; + pthread_attr_init(&thread_attr); + gettimeofday(&start, NULL); + for (i = 0; i < nthreads; i++) { + worker[i].tid = i; + worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); + if (!worker[i].futex) + goto errmem; + + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu); + if (ret) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, + (void *)(struct worker *) &worker[i]); + if (ret) + err(EXIT_FAILURE, "pthread_create"); + + } + pthread_attr_destroy(&thread_attr); + + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + sleep(nsecs); + toggle_done(0, NULL, NULL); + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i].thread, NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + + for (i = 0; i < nthreads; i++) { + unsigned long t = worker[i].ops/runtime.tv_sec; + update_stats(&throughput_stats, t); + if (!silent) { + if (nfutexes == 1) + printf("[thread %2d] futex: %p [ %ld ops/sec ]\n", + worker[i].tid, &worker[i].futex[0], t); + else + printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n", + worker[i].tid, &worker[i].futex[0], + &worker[i].futex[nfutexes-1], t); + } + + free(worker[i].futex); + } + + print_summary(); + + free(worker); + return ret; +errmem: + err(EXIT_FAILURE, "calloc"); +} diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c new file mode 100644 index 000000000000..a16255876f1d --- /dev/null +++ b/tools/perf/bench/futex-requeue.c @@ -0,0 +1,211 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-requeue: Block a bunch of threads on futex1 and requeue them + * on futex2, N at a time. + * + * This program is particularly useful to measure the latency of nthread + * requeues without waking up any tasks -- thus mimicking a regular futex_wait. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +static u_int32_t futex1 = 0, futex2 = 0; + +/* + * How many tasks to requeue at a time. + * Default to 1 in order to make the kernel work more. + */ +static unsigned int nrequeue = 1; + +/* + * There can be significant variance from run to run, + * the more repeats, the more exact the overall avg and + * the better idea of the futex latency. + */ +static unsigned int repeat = 10; + +static pthread_t *worker; +static bool done = 0, silent = 0; +static pthread_mutex_t thread_lock; +static pthread_cond_t thread_parent, thread_worker; +static struct stats requeuetime_stats, requeued_stats; +static unsigned int ncpus, threads_starting, nthreads = 0; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"), + OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_END() +}; + +static const char * const bench_futex_requeue_usage[] = { + "perf bench futex requeue <options>", + NULL +}; + +static void print_summary(void) +{ + double requeuetime_avg = avg_stats(&requeuetime_stats); + double requeuetime_stddev = stddev_stats(&requeuetime_stats); + unsigned int requeued_avg = avg_stats(&requeued_stats); + + printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n", + requeued_avg, + nthreads, + requeuetime_avg/1e3, + rel_stddev_stats(requeuetime_stddev, requeuetime_avg)); +} + +static void *workerfn(void *arg __maybe_unused) +{ + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + return NULL; +} + +static void block_threads(pthread_t *w, + pthread_attr_t thread_attr) +{ + cpu_set_t cpu; + unsigned int i; + + threads_starting = nthreads; + + /* create and block all threads */ + for (i = 0; i < nthreads; i++) { + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu)) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + err(EXIT_FAILURE, "pthread_create"); + } +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + done = true; +} + +int bench_futex_requeue(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + unsigned int i, j; + struct sigaction act; + pthread_attr_t thread_attr; + + argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0); + if (argc) + goto err; + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + err(EXIT_FAILURE, "calloc"); + + printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), " + "%d at a time.\n\n", + getpid(), nthreads, &futex1, &futex2, nrequeue); + + init_stats(&requeued_stats); + init_stats(&requeuetime_stats); + pthread_attr_init(&thread_attr); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + for (j = 0; j < repeat && !done; j++) { + unsigned int nrequeued = 0; + struct timeval start, end, runtime; + + /* create, launch & block all threads */ + block_threads(worker, thread_attr); + + /* make sure all threads are already blocked */ + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + usleep(100000); + + /* Ok, all threads are patiently blocked, start requeueing */ + gettimeofday(&start, NULL); + for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) + /* + * Do not wakeup any tasks blocked on futex1, allowing + * us to really measure futex_wait functionality. + */ + futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue, + FUTEX_PRIVATE_FLAG); + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); + + update_stats(&requeued_stats, nrequeued); + update_stats(&requeuetime_stats, runtime.tv_usec); + + if (!silent) { + printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n", + j + 1, nrequeued, nthreads, runtime.tv_usec/1e3); + } + + /* everybody should be blocked on futex2, wake'em up */ + nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG); + if (nthreads != nrequeued) + warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads); + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i], NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + pthread_attr_destroy(&thread_attr); + + print_summary(); + + free(worker); + return ret; +err: + usage_with_options(bench_futex_requeue_usage, options); + exit(EXIT_FAILURE); +} diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c new file mode 100644 index 000000000000..d096169b161e --- /dev/null +++ b/tools/perf/bench/futex-wake.c @@ -0,0 +1,201 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time. + * + * This program is particularly useful to measure the latency of nthread wakeups + * in non-error situations: all waiters are queued and all wake calls wakeup + * one or more tasks, and thus the waitqueue is never empty. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +/* all threads will block on the same futex */ +static u_int32_t futex1 = 0; + +/* + * How many wakeups to do at a time. + * Default to 1 in order to make the kernel work more. + */ +static unsigned int nwakes = 1; + +/* + * There can be significant variance from run to run, + * the more repeats, the more exact the overall avg and + * the better idea of the futex latency. + */ +static unsigned int repeat = 10; + +pthread_t *worker; +static bool done = 0, silent = 0; +static pthread_mutex_t thread_lock; +static pthread_cond_t thread_parent, thread_worker; +static struct stats waketime_stats, wakeup_stats; +static unsigned int ncpus, threads_starting, nthreads = 0; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"), + OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_END() +}; + +static const char * const bench_futex_wake_usage[] = { + "perf bench futex wake <options>", + NULL +}; + +static void *workerfn(void *arg __maybe_unused) +{ + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + return NULL; +} + +static void print_summary(void) +{ + double waketime_avg = avg_stats(&waketime_stats); + double waketime_stddev = stddev_stats(&waketime_stats); + unsigned int wakeup_avg = avg_stats(&wakeup_stats); + + printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n", + wakeup_avg, + nthreads, + waketime_avg/1e3, + rel_stddev_stats(waketime_stddev, waketime_avg)); +} + +static void block_threads(pthread_t *w, + pthread_attr_t thread_attr) +{ + cpu_set_t cpu; + unsigned int i; + + threads_starting = nthreads; + + /* create and block all threads */ + for (i = 0; i < nthreads; i++) { + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu)) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + err(EXIT_FAILURE, "pthread_create"); + } +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + done = true; +} + +int bench_futex_wake(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + unsigned int i, j; + struct sigaction act; + pthread_attr_t thread_attr; + + argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0); + if (argc) { + usage_with_options(bench_futex_wake_usage, options); + exit(EXIT_FAILURE); + } + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + err(EXIT_FAILURE, "calloc"); + + printf("Run summary [PID %d]: blocking on %d threads (at futex %p), " + "waking up %d at a time.\n\n", + getpid(), nthreads, &futex1, nwakes); + + init_stats(&wakeup_stats); + init_stats(&waketime_stats); + pthread_attr_init(&thread_attr); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + for (j = 0; j < repeat && !done; j++) { + unsigned int nwoken = 0; + struct timeval start, end, runtime; + + /* create, launch & block all threads */ + block_threads(worker, thread_attr); + + /* make sure all threads are already blocked */ + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + usleep(100000); + + /* Ok, all threads are patiently blocked, start waking folks up */ + gettimeofday(&start, NULL); + while (nwoken != nthreads) + nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG); + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); + + update_stats(&wakeup_stats, nwoken); + update_stats(&waketime_stats, runtime.tv_usec); + + if (!silent) { + printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n", + j + 1, nwoken, nthreads, runtime.tv_usec/1e3); + } + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i], NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + pthread_attr_destroy(&thread_attr); + + print_summary(); + + free(worker); + return ret; +} diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h new file mode 100644 index 000000000000..71f2844cf97f --- /dev/null +++ b/tools/perf/bench/futex.h @@ -0,0 +1,71 @@ +/* + * Glibc independent futex library for testing kernel functionality. + * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com> + * http://git.kernel.org/cgit/linux/kernel/git/dvhart/futextest.git/ + */ + +#ifndef _FUTEX_H +#define _FUTEX_H + +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <linux/futex.h> + +/** + * futex() - SYS_futex syscall wrapper + * @uaddr: address of first futex + * @op: futex op code + * @val: typically expected value of uaddr, but varies by op + * @timeout: typically an absolute struct timespec (except where noted + * otherwise). Overloaded by some ops + * @uaddr2: address of second futex for some ops\ + * @val3: varies by op + * @opflags: flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG + * + * futex() is used by all the following futex op wrappers. It can also be + * used for misuse and abuse testing. Generally, the specific op wrappers + * should be used instead. It is a macro instead of an static inline function as + * some of the types over overloaded (timeout is used for nr_requeue for + * example). + * + * These argument descriptions are the defaults for all + * like-named arguments in the following wrappers except where noted below. + */ +#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \ + syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3) + +/** + * futex_wait() - block on uaddr with optional timeout + * @timeout: relative timeout + */ +static inline int +futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags) +{ + return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); +} + +/** + * futex_wake() - wake one or more tasks blocked on uaddr + * @nr_wake: wake up to this many tasks + */ +static inline int +futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) +{ + return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); +} + +/** +* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2 +* @nr_wake: wake up to this many tasks +* @nr_requeue: requeue up to this many tasks +*/ +static inline int +futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake, + int nr_requeue, int opflags) +{ + return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, + val, opflags); +} + +#endif /* _FUTEX_H */ diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index d4c83c60b9b2..97d86d828190 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -1593,6 +1593,7 @@ static void init_params(struct params *p, const char *name, int argc, const char p->data_rand_walk = true; p->nr_loops = -1; p->init_random = true; + p->run_all = argc == 1; } static int run_bench_numa(const char *name, const char **argv) diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index e47f90cc7b98..1e6e77710545 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -12,6 +12,7 @@ * sched ... scheduler and IPC performance * mem ... memory access performance * numa ... NUMA scheduling and MM performance + * futex ... Futex performance */ #include "perf.h" #include "util/util.h" @@ -54,6 +55,14 @@ static struct bench mem_benchmarks[] = { { NULL, NULL, NULL } }; +static struct bench futex_benchmarks[] = { + { "hash", "Benchmark for futex hash table", bench_futex_hash }, + { "wake", "Benchmark for futex wake calls", bench_futex_wake }, + { "requeue", "Benchmark for futex requeue calls", bench_futex_requeue }, + { "all", "Test all futex benchmarks", NULL }, + { NULL, NULL, NULL } +}; + struct collection { const char *name; const char *summary; @@ -61,11 +70,12 @@ struct collection { }; static struct collection collections[] = { - { "sched", "Scheduler and IPC benchmarks", sched_benchmarks }, + { "sched", "Scheduler and IPC benchmarks", sched_benchmarks }, { "mem", "Memory access benchmarks", mem_benchmarks }, #ifdef HAVE_LIBNUMA_SUPPORT { "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks }, #endif + {"futex", "Futex stressing benchmarks", futex_benchmarks }, { "all", "All benchmarks", NULL }, { NULL, NULL, NULL } }; @@ -76,7 +86,7 @@ static struct collection collections[] = { /* Iterate over all benchmarks within a collection: */ #define for_each_bench(coll, bench) \ - for (bench = coll->benchmarks; bench->name; bench++) + for (bench = coll->benchmarks; bench && bench->name; bench++) static void dump_benchmarks(struct collection *coll) { diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index a77e31246c00..204fffe22532 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -952,8 +952,8 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp, dfmt->header_width, buf); } -static int hpp__header(struct perf_hpp_fmt *fmt, - struct perf_hpp *hpp) +static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel __maybe_unused) { struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); @@ -963,7 +963,8 @@ static int hpp__header(struct perf_hpp_fmt *fmt, } static int hpp__width(struct perf_hpp_fmt *fmt, - struct perf_hpp *hpp __maybe_unused) + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel __maybe_unused) { struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b3466018bbd7..3a7387551369 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -312,7 +312,6 @@ found: sample_sw.period = sample->period; sample_sw.time = sample->time; perf_event__synthesize_sample(event_sw, evsel->attr.sample_type, - evsel->attr.sample_regs_user, evsel->attr.read_format, &sample_sw, false); build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index a7350519c63f..21c164b8f9db 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1691,17 +1691,15 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; - - const char * const kvm_usage[] = { - "perf kvm [<options>] {top|record|report|diff|buildid-list|stat}", - NULL - }; + const char *const kvm_subcommands[] = { "top", "record", "report", "diff", + "buildid-list", "stat", NULL }; + const char *kvm_usage[] = { NULL, NULL }; perf_host = 0; perf_guest = 1; - argc = parse_options(argc, argv, kvm_options, kvm_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, kvm_options, kvm_subcommands, kvm_usage, + PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 78948882e3de..cdcd4eb3a57d 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -268,9 +268,9 @@ static int opt_set_filter(const struct option *opt __maybe_unused, return 0; } -static void init_params(void) +static int init_params(void) { - line_range__init(¶ms.line_range); + return line_range__init(¶ms.line_range); } static void cleanup_params(void) @@ -515,9 +515,11 @@ int cmd_probe(int argc, const char **argv, const char *prefix) { int ret; - init_params(); - ret = __cmd_probe(argc, argv, prefix); - cleanup_params(); + ret = init_params(); + if (!ret) { + ret = __cmd_probe(argc, argv, prefix); + cleanup_params(); + } return ret; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index af47531b82ec..eb524f91bffe 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -649,7 +649,7 @@ error: return ret; } -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT static int get_stack_size(char *str, unsigned long *_size) { char *endptr; @@ -675,7 +675,7 @@ static int get_stack_size(char *str, unsigned long *_size) max_size, str); return -1; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ int record_parse_callchain(const char *arg, struct record_opts *opts) { @@ -704,7 +704,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) "needed for -g fp\n"); break; -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT /* Dwarf style */ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { const unsigned long default_stack_dump_size = 8192; @@ -720,7 +720,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ } else { pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); @@ -735,7 +735,9 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) static void callchain_debug(struct record_opts *opts) { - pr_debug("callchain: type %d\n", opts->call_graph); + static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" }; + + pr_debug("callchain: type %s\n", str[opts->call_graph]); if (opts->call_graph == CALLCHAIN_DWARF) pr_debug("callchain: stack dump size %d\n", @@ -749,6 +751,8 @@ int record_parse_callchain_opt(const struct option *opt, struct record_opts *opts = opt->value; int ret; + opts->call_graph_enabled = !unset; + /* --no-call-graph */ if (unset) { opts->call_graph = CALLCHAIN_NONE; @@ -769,6 +773,8 @@ int record_callchain_opt(const struct option *opt, { struct record_opts *opts = opt->value; + opts->call_graph_enabled = !unset; + if (opts->call_graph == CALLCHAIN_NONE) opts->call_graph = CALLCHAIN_FP; @@ -776,6 +782,16 @@ int record_callchain_opt(const struct option *opt, return 0; } +static int perf_record_config(const char *var, const char *value, void *cb) +{ + struct record *rec = cb; + + if (!strcmp(var, "record.call-graph")) + return record_parse_callchain(value, &rec->opts); + + return perf_default_config(var, value, cb); +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -807,7 +823,7 @@ static struct record record = { #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else const char record_callchain_help[] = CALLCHAIN_HELP "fp"; @@ -907,6 +923,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->evlist == NULL) return -ENOMEM; + perf_config(perf_record_config, rec); + argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && target__none(&rec->opts.target)) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 02f985f3a396..c8f21137dfd8 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -75,13 +75,10 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al, - struct perf_sample *sample, struct perf_evsel *evsel, - union perf_event *event) +static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al, + struct perf_sample *sample, struct perf_evsel *evsel) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct hist_entry *he; struct mem_info *mi, *mx; uint64_t cost; @@ -90,7 +87,7 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati if (err) return err; - mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode); + mi = sample__resolve_mem(sample, al); if (!mi) return -ENOMEM; @@ -131,10 +128,9 @@ out: return err; } -static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, +static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al, struct perf_sample *sample, struct perf_evsel *evsel) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; unsigned i; struct hist_entry *he; @@ -144,8 +140,7 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc if (err) return err; - bi = machine__resolve_bstack(al->machine, al->thread, - sample->branch_stack); + bi = sample__resolve_bstack(sample, al); if (!bi) return -ENOMEM; @@ -190,10 +185,9 @@ out: return err; } -static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel, +static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; struct hist_entry *he; int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack); @@ -237,25 +231,25 @@ static int process_sample_event(struct perf_tool *tool, return -1; } - if (al.filtered || (rep->hide_unresolved && al.sym == NULL)) + if (rep->hide_unresolved && al.sym == NULL) return 0; if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; if (sort__mode == SORT_MODE__BRANCH) { - ret = report__add_branch_hist_entry(tool, &al, sample, evsel); + ret = report__add_branch_hist_entry(rep, &al, sample, evsel); if (ret < 0) pr_debug("problem adding lbr entry, skipping event\n"); } else if (rep->mem_mode == 1) { - ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event); + ret = report__add_mem_hist_entry(rep, &al, sample, evsel); if (ret < 0) pr_debug("problem adding mem entry, skipping event\n"); } else { if (al.map != NULL) al.map->dso->hit = 1; - ret = report__add_hist_entry(tool, evsel, &al, sample); + ret = report__add_hist_entry(rep, evsel, &al, sample); if (ret < 0) pr_debug("problem incrementing symbol period, skipping event\n"); } @@ -934,7 +928,7 @@ repeat: * so don't allocate extra space that won't be used in the stdio * implementation. */ - if (use_browser == 1 && sort__has_sym) { + if (ui__has_annotation()) { symbol_conf.priv_size = sizeof(struct annotation); machines__set_symbol_filter(&session->machines, symbol__annotate_init); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 6a76a07b6789..9ac0a495c954 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1124,7 +1124,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ avg = work_list->total_lat / work_list->nb_atoms; - printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", + printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n", (double)work_list->total_runtime / 1e6, work_list->nb_atoms, (double)avg / 1e6, (double)work_list->max_lat / 1e6, @@ -1527,9 +1527,9 @@ static int perf_sched__lat(struct perf_sched *sched) perf_sched__sort_lat(sched); - printf("\n ---------------------------------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); - printf(" ---------------------------------------------------------------------------------------------------------------\n"); + printf("\n -----------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); next = rb_first(&sched->sorted_atom_root); @@ -1541,7 +1541,7 @@ static int perf_sched__lat(struct perf_sched *sched) next = rb_next(next); } - printf(" -----------------------------------------------------------------------------------------\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", (double)sched->all_runtime / 1e6, sched->all_count); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 25526d6eae59..74db2568b867 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -494,7 +494,7 @@ static const char *cat_backtrace(union perf_event *event, continue; } - tal.filtered = false; + tal.filtered = 0; thread__find_addr_location(al.thread, machine, cpumode, MAP__FUNCTION, ip, &tal); @@ -1238,7 +1238,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar for (i = 0; i < old_power_args_nr; i++) *p++ = strdup(old_power_args[i]); - for (j = 1; j < (unsigned int)argc; j++) + for (j = 0; j < (unsigned int)argc; j++) *p++ = argv[j]; return cmd_record(rec_argc, rec_argv, NULL); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5f989a7d8bc2..65aaa5bbf7ec 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -993,6 +993,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return record_parse_callchain_opt(opt, arg, unset); } +static int perf_top_config(const char *var, const char *value, void *cb) +{ + struct perf_top *top = cb; + + if (!strcmp(var, "top.call-graph")) + return record_parse_callchain(value, &top->record_opts); + + return perf_default_config(var, value, cb); +} + static int parse_percent_limit(const struct option *opt, const char *arg, int unset __maybe_unused) @@ -1117,6 +1127,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.evlist == NULL) return -ENOMEM; + perf_config(perf_top_config, &top); + argc = parse_options(argc, argv, options, top_usage, 0); if (argc) usage_with_options(top_usage, options); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6aa6fb6f7bd9..f954c26de231 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -825,7 +825,6 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal P_SIGNUM(PIPE); P_SIGNUM(ALRM); P_SIGNUM(TERM); - P_SIGNUM(STKFLT); P_SIGNUM(CHLD); P_SIGNUM(CONT); P_SIGNUM(STOP); @@ -841,6 +840,15 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal P_SIGNUM(IO); P_SIGNUM(PWR); P_SIGNUM(SYS); +#ifdef SIGEMT + P_SIGNUM(EMT); +#endif +#ifdef SIGSTKFLT + P_SIGNUM(STKFLT); +#endif +#ifdef SIGSWI + P_SIGNUM(SWI); +#endif default: break; } diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 0331ea2701a3..c23418225c2c 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -59,6 +59,18 @@ ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS_SUPPORT endif +ifndef NO_LIBELF + # for linking with debug library, run like: + # make DEBUG=1 LIBDW_DIR=/opt/libdw/ + ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + + FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) + FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw + endif +endif + # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -147,7 +159,35 @@ CORE_FEATURE_TESTS = \ libunwind \ on-exit \ stackprotector-all \ - timerfd + timerfd \ + libdw-dwarf-unwind + +LIB_FEATURE_TESTS = \ + dwarf \ + glibc \ + gtk2 \ + libaudit \ + libbfd \ + libelf \ + libnuma \ + libperl \ + libpython \ + libslang \ + libunwind \ + libdw-dwarf-unwind + +VF_FEATURE_TESTS = \ + backtrace \ + fortify-source \ + gtk2-infobar \ + libelf-getphdrnum \ + libelf-mmap \ + libpython-version \ + on-exit \ + stackprotector-all \ + timerfd \ + libunwind-debug-frame \ + bionic # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -161,17 +201,6 @@ endef $(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat))) # -# So here we detect whether test-all was rebuilt, to be able -# to skip the print-out of the long features list if the file -# existed before and after it was built: -# -ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all.bin),) - test-all-failed := 1 -else - test-all-failed := 0 -endif - -# # Special fast-path for the 'all features are available' case: # $(call feature_check,all,$(MSG)) @@ -180,15 +209,6 @@ $(call feature_check,all,$(MSG)) # Just in case the build freshly failed, make sure we print the # feature matrix: # -ifeq ($(feature-all), 0) - test-all-failed := 1 -endif - -ifeq ($(test-all-failed),1) - $(info ) - $(info Auto-detecting system features:) -endif - ifeq ($(feature-all), 1) # # test-all.c passed - just set all the core feature flags to 1: @@ -199,27 +219,6 @@ else $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat))) endif -# -# Print the result of the feature test: -# -feature_print = $(eval $(feature_print_code)) $(info $(MSG)) - -define feature_print_code - ifeq ($(feature-$(1)), 1) - MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) - else - MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) - endif -endef - -# -# Only print out our features if we rebuilt the testcases or if a test failed: -# -ifeq ($(test-all-failed), 1) - $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_print,$(feat))) - $(info ) -endif - ifeq ($(feature-stackprotector-all), 1) CFLAGS += -fstack-protector-all endif @@ -264,6 +263,7 @@ ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 NO_LIBUNWIND := 1 + NO_LIBDW_DWARF_UNWIND := 1 else ifeq ($(feature-libelf), 0) ifeq ($(feature-glibc), 1) @@ -282,13 +282,12 @@ else msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); endif else - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + ifndef NO_LIBDW_DWARF_UNWIND + ifneq ($(feature-libdw-dwarf-unwind),1) + NO_LIBDW_DWARF_UNWIND := 1 + msg := $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR); + endif endif - ifneq ($(feature-dwarf), 1) msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); NO_DWARF := 1 @@ -324,25 +323,51 @@ endif # NO_LIBELF ifndef NO_LIBUNWIND ifneq ($(feature-libunwind), 1) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1); + msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR); NO_LIBUNWIND := 1 + endif +endif + +dwarf-post-unwind := 1 +dwarf-post-unwind-text := BUG + +# setup DWARF post unwinder +ifdef NO_LIBUNWIND + ifdef NO_LIBDW_DWARF_UNWIND + msg := $(warning Disabling post unwind, no support found.); + dwarf-post-unwind := 0 else - ifeq ($(ARCH),arm) - $(call feature_check,libunwind-debug-frame) - ifneq ($(feature-libunwind-debug-frame), 1) - msg := $(warning No debug_frame support found in libunwind); - CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME - endif - else - # non-ARM has no dwarf_find_debug_frame() function: + dwarf-post-unwind-text := libdw + endif +else + dwarf-post-unwind-text := libunwind + # Enable libunwind support by default. + ifndef NO_LIBDW_DWARF_UNWIND + NO_LIBDW_DWARF_UNWIND := 1 + endif +endif + +ifeq ($(dwarf-post-unwind),1) + CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT +else + NO_DWARF_UNWIND := 1 +endif + +ifndef NO_LIBUNWIND + ifeq ($(ARCH),arm) + $(call feature_check,libunwind-debug-frame) + ifneq ($(feature-libunwind-debug-frame), 1) + msg := $(warning No debug_frame support found in libunwind); CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME endif - - CFLAGS += -DHAVE_LIBUNWIND_SUPPORT - EXTLIBS += $(LIBUNWIND_LIBS) - CFLAGS += $(LIBUNWIND_CFLAGS) - LDFLAGS += $(LIBUNWIND_LDFLAGS) - endif # ifneq ($(feature-libunwind), 1) + else + # non-ARM has no dwarf_find_debug_frame() function: + CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME + endif + CFLAGS += -DHAVE_LIBUNWIND_SUPPORT + EXTLIBS += $(LIBUNWIND_LIBS) + CFLAGS += $(LIBUNWIND_CFLAGS) + LDFLAGS += $(LIBUNWIND_LDFLAGS) endif ifndef NO_LIBAUDIT @@ -602,3 +627,84 @@ ifdef DESTDIR plugindir=$(libdir)/traceevent/plugins plugindir_SQ= $(subst ','\'',$(plugindir)) endif + +# +# Print the result of the feature test: +# +feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG)) + +define feature_print_status_code + ifeq ($(feature-$(1)), 1) + MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) + else + MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) + endif +endef + +feature_print_var = $(eval $(feature_print_var_code)) $(info $(MSG)) +define feature_print_var_code + MSG = $(shell printf '...%30s: %s' $(1) $($(1))) +endef + +feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG)) +define feature_print_text_code + MSG = $(shell printf '...%30s: %s' $(1) $(2)) +endef + +PERF_FEATURES := $(foreach feat,$(LIB_FEATURE_TESTS),feature-$(feat)($(feature-$(feat)))) +PERF_FEATURES_FILE := $(shell touch $(OUTPUT)PERF-FEATURES; cat $(OUTPUT)PERF-FEATURES) + +ifeq ($(dwarf-post-unwind),1) + PERF_FEATURES += dwarf-post-unwind($(dwarf-post-unwind-text)) +endif + +# The $(display_lib) controls the default detection message +# output. It's set if: +# - detected features differes from stored features from +# last build (in PERF-FEATURES file) +# - one of the $(LIB_FEATURE_TESTS) is not detected +# - VF is enabled + +ifneq ("$(PERF_FEATURES)","$(PERF_FEATURES_FILE)") + $(shell echo "$(PERF_FEATURES)" > $(OUTPUT)PERF-FEATURES) + display_lib := 1 +endif + +feature_check = $(eval $(feature_check_code)) +define feature_check_code + ifneq ($(feature-$(1)), 1) + display_lib := 1 + endif +endef + +$(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_check,$(feat))) + +ifeq ($(VF),1) + display_lib := 1 + display_vf := 1 +endif + +ifeq ($(display_lib),1) + $(info ) + $(info Auto-detecting system features:) + $(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_print_status,$(feat),)) + + ifeq ($(dwarf-post-unwind),1) + $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) + endif +endif + +ifeq ($(display_vf),1) + $(foreach feat,$(VF_FEATURE_TESTS),$(call feature_print_status,$(feat),)) + $(info ) + $(call feature_print_var,prefix) + $(call feature_print_var,bindir) + $(call feature_print_var,libdir) + $(call feature_print_var,sysconfdir) + $(call feature_print_var,LIBUNWIND_DIR) + $(call feature_print_var,LIBDW_DIR) +endif + +ifeq ($(display_lib),1) + $(info ) +endif diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 523b7bc10553..2da103c53f89 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -26,7 +26,8 @@ FILES= \ test-libunwind-debug-frame.bin \ test-on-exit.bin \ test-stackprotector-all.bin \ - test-timerfd.bin + test-timerfd.bin \ + test-libdw-dwarf-unwind.bin CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config @@ -141,6 +142,9 @@ test-backtrace.bin: test-timerfd.bin: $(BUILD) +test-libdw-dwarf-unwind.bin: + $(BUILD) + -include *.d ############################### diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index 9b8a544155bb..fc37eb3ca17b 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -89,6 +89,10 @@ # include "test-stackprotector-all.c" #undef main +#define main main_test_libdw_dwarf_unwind +# include "test-libdw-dwarf-unwind.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -111,6 +115,7 @@ int main(int argc, char *argv[]) main_test_libnuma(); main_test_timerfd(); main_test_stackprotector_all(); + main_test_libdw_dwarf_unwind(); return 0; } diff --git a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c new file mode 100644 index 000000000000..f676a3ff442a --- /dev/null +++ b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c @@ -0,0 +1,13 @@ + +#include <elfutils/libdwfl.h> + +int main(void) +{ + /* + * This function is guarded via: __nonnull_attribute__ (1, 2). + * Passing '1' as arguments value. This code is never executed, + * only compiled. + */ + dwfl_thread_getframes((void *) 1, (void *) 1, NULL); + return 0; +} diff --git a/tools/perf/design.txt b/tools/perf/design.txt index 63a0e6f04a01..a28dca2582aa 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -18,7 +18,7 @@ underlying hardware counters. Performance counters are accessed via special file descriptors. There's one file descriptor per virtual counter used. -The special file descriptor is opened via the perf_event_open() +The special file descriptor is opened via the sys_perf_event_open() system call: int sys_perf_event_open(struct perf_event_attr *hw_event_uptr, @@ -82,7 +82,7 @@ machine-specific. If 'raw_type' is 0, then the 'type' field says what kind of counter this is, with the following encoding: -enum perf_event_types { +enum perf_type_id { PERF_TYPE_HARDWARE = 0, PERF_TYPE_SOFTWARE = 1, PERF_TYPE_TRACEPOINT = 2, @@ -95,7 +95,7 @@ specified by 'event_id': * Generalized performance counter event types, used by the hw_event.event_id * parameter of the sys_perf_event_open() syscall: */ -enum hw_event_ids { +enum perf_hw_id { /* * Common hardware events, generalized by the kernel: */ @@ -129,7 +129,7 @@ software events, selected by 'event_id': * physical and sw events of the kernel (and allow the profiling of them as * well): */ -enum sw_event_ids { +enum perf_sw_ids { PERF_COUNT_SW_CPU_CLOCK = 0, PERF_COUNT_SW_TASK_CLOCK = 1, PERF_COUNT_SW_PAGE_FAULTS = 2, @@ -230,7 +230,7 @@ these events are recorded in the ring-buffer (see below). The 'comm' bit allows tracking of process comm data on process creation. This too is recorded in the ring-buffer (see below). -The 'pid' parameter to the perf_event_open() system call allows the +The 'pid' parameter to the sys_perf_event_open() system call allows the counter to be specific to a task: pid == 0: if the pid parameter is zero, the counter is attached to the @@ -260,7 +260,7 @@ The 'flags' parameter is currently unused and must be zero. The 'group_fd' parameter allows counter "groups" to be set up. A counter group has one counter which is the group "leader". The leader -is created first, with group_fd = -1 in the perf_event_open call +is created first, with group_fd = -1 in the sys_perf_event_open call that creates it. The rest of the group members are created subsequently, with group_fd giving the fd of the group leader. (A single counter on its own is created with group_fd = -1 and is diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 496e2abb5482..ae3a57694b6b 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -123,7 +123,7 @@ __perf_main () __perfcomp_colon "$evts" "$cur" # List subcommands for 'perf kvm' elif [[ $prev == "kvm" ]]; then - subcmds="top record report diff buildid-list stat" + subcmds=$($cmd $prev --list-cmds) __perfcomp_colon "$subcmds" "$cur" # List long option names elif [[ $cur == --* ]]; then diff --git a/tools/perf/perf.h b/tools/perf/perf.h index e84fa26bc1be..e18a8b5e6953 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -12,6 +12,9 @@ #ifndef __NR_perf_event_open # define __NR_perf_event_open 336 #endif +#ifndef __NR_futex +# define __NR_futex 240 +#endif #endif #if defined(__x86_64__) @@ -23,6 +26,9 @@ #ifndef __NR_perf_event_open # define __NR_perf_event_open 298 #endif +#ifndef __NR_futex +# define __NR_futex 202 +#endif #endif #ifdef __powerpc__ @@ -251,12 +257,14 @@ void pthread__unblock_sigwinch(void); enum perf_call_graph_mode { CALLCHAIN_NONE, CALLCHAIN_FP, - CALLCHAIN_DWARF + CALLCHAIN_DWARF, + CALLCHAIN_MAX }; struct record_opts { struct target target; int call_graph; + bool call_graph_enabled; bool group; bool inherit_stat; bool no_buffering; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 1e67437fb4ca..b11bf8a08430 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -115,6 +115,14 @@ static struct test { .desc = "Test parsing with no sample_id_all bit set", .func = test__parse_no_sample_id_all, }, +#if defined(__x86_64__) || defined(__i386__) +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "Test dwarf unwind", + .func = test__dwarf_unwind, + }, +#endif +#endif { .func = NULL, }, diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c new file mode 100644 index 000000000000..c059ee81c038 --- /dev/null +++ b/tools/perf/tests/dwarf-unwind.c @@ -0,0 +1,144 @@ +#include <linux/compiler.h> +#include <sys/types.h> +#include <unistd.h> +#include "tests.h" +#include "debug.h" +#include "machine.h" +#include "event.h" +#include "unwind.h" +#include "perf_regs.h" +#include "map.h" +#include "thread.h" + +static int mmap_handler(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_mmap_event(machine, event, NULL); +} + +static int init_live_machine(struct machine *machine) +{ + union perf_event event; + pid_t pid = getpid(); + + return perf_event__synthesize_mmap_events(NULL, &event, pid, pid, + mmap_handler, machine, true); +} + +#define MAX_STACK 6 + +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + unsigned long *cnt = (unsigned long *) arg; + char *symbol = entry->sym ? entry->sym->name : NULL; + static const char *funcs[MAX_STACK] = { + "test__arch_unwind_sample", + "unwind_thread", + "krava_3", + "krava_2", + "krava_1", + "test__dwarf_unwind" + }; + + if (*cnt >= MAX_STACK) { + pr_debug("failed: crossed the max stack value %d\n", MAX_STACK); + return -1; + } + + if (!symbol) { + pr_debug("failed: got unresolved address 0x%" PRIx64 "\n", + entry->ip); + return -1; + } + + pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip); + return strcmp((const char *) symbol, funcs[(*cnt)++]); +} + +__attribute__ ((noinline)) +static int unwind_thread(struct thread *thread, struct machine *machine) +{ + struct perf_sample sample; + unsigned long cnt = 0; + int err = -1; + + memset(&sample, 0, sizeof(sample)); + + if (test__arch_unwind_sample(&sample, thread)) { + pr_debug("failed to get unwind sample\n"); + goto out; + } + + err = unwind__get_entries(unwind_entry, &cnt, machine, thread, + &sample, MAX_STACK); + if (err) + pr_debug("unwind failed\n"); + else if (cnt != MAX_STACK) { + pr_debug("got wrong number of stack entries %lu != %d\n", + cnt, MAX_STACK); + err = -1; + } + + out: + free(sample.user_stack.data); + free(sample.user_regs.regs); + return err; +} + +__attribute__ ((noinline)) +static int krava_3(struct thread *thread, struct machine *machine) +{ + return unwind_thread(thread, machine); +} + +__attribute__ ((noinline)) +static int krava_2(struct thread *thread, struct machine *machine) +{ + return krava_3(thread, machine); +} + +__attribute__ ((noinline)) +static int krava_1(struct thread *thread, struct machine *machine) +{ + return krava_2(thread, machine); +} + +int test__dwarf_unwind(void) +{ + struct machines machines; + struct machine *machine; + struct thread *thread; + int err = -1; + + machines__init(&machines); + + machine = machines__find(&machines, HOST_KERNEL_ID); + if (!machine) { + pr_err("Could not get machine\n"); + return -1; + } + + if (init_live_machine(machine)) { + pr_err("Could not init machine\n"); + goto out; + } + + if (verbose > 1) + machine__fprintf(machine, stderr); + + thread = machine__find_thread(machine, getpid(), getpid()); + if (!thread) { + pr_err("Could not get thread\n"); + goto out; + } + + err = krava_1(thread, machine); + + out: + machine__delete_threads(machine); + machine__exit(machine); + machines__exit(&machines); + return err; +} diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 2b6519e0e36f..7ccbc7b6ae77 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -101,6 +101,7 @@ static struct machine *setup_fake_machine(struct machines *machines) .mmap = { .header = { .misc = PERF_RECORD_MISC_USER, }, .pid = fake_mmap_info[i].pid, + .tid = fake_mmap_info[i].pid, .start = fake_mmap_info[i].start, .len = 0x1000ULL, .pgoff = 0ULL, diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 00544b8b644b..5daeae1cb4c0 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -27,6 +27,7 @@ make_no_ui := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 make_no_demangle := NO_DEMANGLE=1 make_no_libelf := NO_LIBELF=1 make_no_libunwind := NO_LIBUNWIND=1 +make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1 make_no_backtrace := NO_BACKTRACE=1 make_no_libnuma := NO_LIBNUMA=1 make_no_libaudit := NO_LIBAUDIT=1 @@ -35,8 +36,9 @@ make_tags := tags make_cscope := cscope make_help := help make_doc := doc -make_perf_o := perf.o -make_util_map_o := util/map.o +make_perf_o := perf.o +make_util_map_o := util/map.o +make_util_pmu_bison_o := util/pmu-bison.o make_install := install make_install_bin := install-bin make_install_doc := install-doc @@ -49,6 +51,7 @@ make_install_pdf := install-pdf make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 +make_minimal += NO_LIBDW_DWARF_UNWIND=1 # $(run) contains all available tests run := make_pure @@ -65,6 +68,7 @@ run += make_no_ui run += make_no_demangle run += make_no_libelf run += make_no_libunwind +run += make_no_libdw_dwarf_unwind run += make_no_backtrace run += make_no_libnuma run += make_no_libaudit @@ -73,6 +77,7 @@ run += make_help run += make_doc run += make_perf_o run += make_util_map_o +run += make_util_pmu_bison_o run += make_install run += make_install_bin # FIXME 'install-*' commented out till they're fixed @@ -113,8 +118,9 @@ test_make_doc_O := $(test_ok) test_make_python_perf_so := test -f $(PERF)/python/perf.so -test_make_perf_o := test -f $(PERF)/perf.o -test_make_util_map_o := test -f $(PERF)/util/map.o +test_make_perf_o := test -f $(PERF)/perf.o +test_make_util_map_o := test -f $(PERF)/util/map.o +test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o define test_dest_files for file in $(1); do \ @@ -167,13 +173,10 @@ test_make_install_info_O := $(test_ok) test_make_install_pdf := $(test_ok) test_make_install_pdf_O := $(test_ok) -# Kbuild tests only -#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so -#test_make_perf_o_O := test -f $$TMP/tools/perf/perf.o -#test_make_util_map_o_O := test -f $$TMP/tools/perf/util/map.o - -test_make_perf_o_O := true -test_make_util_map_o_O := true +test_make_python_perf_so_O := test -f $$TMP_O/python/perf.so +test_make_perf_o_O := test -f $$TMP_O/perf.o +test_make_util_map_o_O := test -f $$TMP_O/util/map.o +test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o test_default = test -x $(PERF)/perf test = $(if $(test_$1),$(test_$1),$(test_default)) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 4db0ae617d70..8605ff5572ae 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2,7 +2,7 @@ #include "parse-events.h" #include "evsel.h" #include "evlist.h" -#include "fs.h" +#include <api/fs/fs.h> #include <api/fs/debugfs.h> #include "tests.h" #include <linux/hw_breakpoint.h> diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 1b677202638d..0014d3c8c21c 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -22,8 +22,8 @@ } while (0) static bool samples_same(const struct perf_sample *s1, - const struct perf_sample *s2, u64 type, u64 regs_user, - u64 read_format) + const struct perf_sample *s2, + u64 type, u64 read_format) { size_t i; @@ -95,8 +95,9 @@ static bool samples_same(const struct perf_sample *s1, } if (type & PERF_SAMPLE_REGS_USER) { - size_t sz = hweight_long(regs_user) * sizeof(u64); + size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64); + COMP(user_regs.mask); COMP(user_regs.abi); if (s1->user_regs.abi && (!s1->user_regs.regs || !s2->user_regs.regs || @@ -174,6 +175,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) .branch_stack = &branch_stack.branch_stack, .user_regs = { .abi = PERF_SAMPLE_REGS_ABI_64, + .mask = sample_regs_user, .regs = user_regs, }, .user_stack = { @@ -201,8 +203,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) sample.read.one.id = 99; } - sz = perf_event__sample_event_size(&sample, sample_type, - sample_regs_user, read_format); + sz = perf_event__sample_event_size(&sample, sample_type, read_format); bufsz = sz + 4096; /* Add a bit for overrun checking */ event = malloc(bufsz); if (!event) { @@ -215,8 +216,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) event->header.misc = 0; event->header.size = sz; - err = perf_event__synthesize_sample(event, sample_type, - sample_regs_user, read_format, + err = perf_event__synthesize_sample(event, sample_type, read_format, &sample, false); if (err) { pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", @@ -244,8 +244,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) goto out_free; } - if (!samples_same(&sample, &sample_out, sample_type, - sample_regs_user, read_format)) { + if (!samples_same(&sample, &sample_out, sample_type, read_format)) { pr_debug("parsing failed for sample_type %#"PRIx64"\n", sample_type); goto out_free; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index e0ac713857ba..a24795ca002d 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -40,5 +40,14 @@ int test__code_reading(void); int test__sample_parsing(void); int test__keep_tracking(void); int test__parse_no_sample_id_all(void); +int test__dwarf_unwind(void); +#if defined(__x86_64__) || defined(__i386__) +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread); +#endif +#endif #endif /* TESTS_H */ diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b720b92eba6e..7ec871af3f6f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -587,95 +587,52 @@ struct hpp_arg { bool current_entry; }; -static int __hpp__color_callchain(struct hpp_arg *arg) +static int __hpp__overhead_callback(struct perf_hpp *hpp, bool front) { - if (!symbol_conf.use_callchain) - return 0; - - slsmg_printf("%c ", arg->folded_sign); - return 2; -} - -static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *), - int (*callchain_cb)(struct hpp_arg *)) -{ - int ret = 0; - double percent = 0.0; - struct hists *hists = he->hists; struct hpp_arg *arg = hpp->ptr; - if (hists->stats.total_period) - percent = 100.0 * get_field(he) / hists->stats.total_period; - - ui_browser__set_percent_color(arg->b, percent, arg->current_entry); - - if (callchain_cb) - ret += callchain_cb(arg); - - ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); - slsmg_printf("%s", hpp->buf); - - if (symbol_conf.event_group) { - int prev_idx, idx_delta; - struct perf_evsel *evsel = hists_to_evsel(hists); - struct hist_entry *pair; - int nr_members = evsel->nr_members; - - if (nr_members <= 1) - goto out; + if (arg->current_entry && arg->b->navkeypressed) + ui_browser__set_color(arg->b, HE_COLORSET_SELECTED); + else + ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); - prev_idx = perf_evsel__group_idx(evsel); + if (front) { + if (!symbol_conf.use_callchain) + return 0; - list_for_each_entry(pair, &he->pairs.head, pairs.node) { - u64 period = get_field(pair); - u64 total = pair->hists->stats.total_period; + slsmg_printf("%c ", arg->folded_sign); + return 2; + } - if (!total) - continue; + return 0; +} - evsel = hists_to_evsel(pair->hists); - idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; +static int __hpp__color_callback(struct perf_hpp *hpp, bool front __maybe_unused) +{ + struct hpp_arg *arg = hpp->ptr; - while (idx_delta--) { - /* - * zero-fill group members in the middle which - * have no sample - */ - ui_browser__set_percent_color(arg->b, 0.0, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", 0.0); - slsmg_printf("%s", hpp->buf); - } + if (!arg->current_entry || !arg->b->navkeypressed) + ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); + return 0; +} - percent = 100.0 * period / total; - ui_browser__set_percent_color(arg->b, percent, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", percent); - slsmg_printf("%s", hpp->buf); +static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...) +{ + struct hpp_arg *arg = hpp->ptr; + int ret; + va_list args; + double percent; - prev_idx = perf_evsel__group_idx(evsel); - } + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); - idx_delta = nr_members - prev_idx - 1; + ui_browser__set_percent_color(arg->b, percent, arg->current_entry); - while (idx_delta--) { - /* - * zero-fill group members at last which have no sample - */ - ui_browser__set_percent_color(arg->b, 0.0, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", 0.0); - slsmg_printf("%s", hpp->buf); - } - } -out: - if (!arg->current_entry || !arg->b->navkeypressed) - ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); + ret = scnprintf(hpp->buf, hpp->size, fmt, percent); + slsmg_printf("%s", hpp->buf); + advance_hpp(hpp, ret); return ret; } @@ -690,14 +647,15 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\ struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb); \ + return __hpp__fmt(hpp, he, __hpp_get_##_field, _cb, " %6.2f%%", \ + __hpp__slsmg_color_printf, true); \ } -__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain) -__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL) -__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL) -__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL) -__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL) +__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__overhead_callback) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, __hpp__color_callback) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us, __hpp__color_callback) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, __hpp__color_callback) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, __hpp__color_callback) #undef __HPP_COLOR_PERCENT_FN diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 5b95c44f3435..e395ef9b0ae0 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -8,16 +8,24 @@ #define MAX_COLUMNS 32 -static int __percent_color_snprintf(char *buf, size_t size, double percent) +static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...) { int ret = 0; + va_list args; + double percent; const char *markup; + char *buf = hpp->buf; + size_t size = hpp->size; + + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); markup = perf_gtk__get_percent_color(percent); if (markup) ret += scnprintf(buf, size, markup); - ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent); + ret += scnprintf(buf + ret, size - ret, fmt, percent); if (markup) ret += scnprintf(buf + ret, size - ret, "</span>"); @@ -25,66 +33,6 @@ static int __percent_color_snprintf(char *buf, size_t size, double percent) return ret; } - -static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *)) -{ - int ret; - double percent = 0.0; - struct hists *hists = he->hists; - struct perf_evsel *evsel = hists_to_evsel(hists); - - if (hists->stats.total_period) - percent = 100.0 * get_field(he) / hists->stats.total_period; - - ret = __percent_color_snprintf(hpp->buf, hpp->size, percent); - - if (perf_evsel__is_group_event(evsel)) { - int prev_idx, idx_delta; - struct hist_entry *pair; - int nr_members = evsel->nr_members; - - prev_idx = perf_evsel__group_idx(evsel); - - list_for_each_entry(pair, &he->pairs.head, pairs.node) { - u64 period = get_field(pair); - u64 total = pair->hists->stats.total_period; - - evsel = hists_to_evsel(pair->hists); - idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members in the middle which - * have no sample - */ - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - 0.0); - } - - percent = 100.0 * period / total; - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - percent); - - prev_idx = perf_evsel__group_idx(evsel); - } - - idx_delta = nr_members - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members at last which have no sample - */ - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - 0.0); - } - } - return ret; -} - #define __HPP_COLOR_PERCENT_FN(_type, _field) \ static u64 he_get_##_field(struct hist_entry *he) \ { \ @@ -95,7 +43,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__color_fmt(hpp, he, he_get_##_field); \ + return __hpp__fmt(hpp, he, he_get_##_field, NULL, " %6.2f%%", \ + __percent_color_snprintf, true); \ } __HPP_COLOR_PERCENT_FN(overhead, period) @@ -216,7 +165,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, struct perf_hpp hpp = { .buf = s, .size = sizeof(s), - .ptr = hists_to_evsel(hists), }; nr_cols = 0; @@ -243,7 +191,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - fmt->header(fmt, &hpp); + fmt->header(fmt, &hpp, hists_to_evsel(hists)); gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), -1, ltrim(s), diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 78f4c92e9b73..0f403b83e9d1 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -8,16 +8,27 @@ /* hist period print (hpp) functions */ -typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...); - -static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *), - const char *fmt, hpp_snprint_fn print_fn, - bool fmt_percent) +#define hpp__call_print_fn(hpp, fn, fmt, ...) \ +({ \ + int __ret = fn(hpp, fmt, ##__VA_ARGS__); \ + advance_hpp(hpp, __ret); \ + __ret; \ +}) + +int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, hpp_callback_fn callback, + const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent) { - int ret; + int ret = 0; struct hists *hists = he->hists; struct perf_evsel *evsel = hists_to_evsel(hists); + char *buf = hpp->buf; + size_t size = hpp->size; + + if (callback) { + ret = callback(hpp, true); + advance_hpp(hpp, ret); + } if (fmt_percent) { double percent = 0.0; @@ -26,9 +37,9 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, percent = 100.0 * get_field(he) / hists->stats.total_period; - ret = print_fn(hpp->buf, hpp->size, fmt, percent); + ret += hpp__call_print_fn(hpp, print_fn, fmt, percent); } else - ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he)); + ret += hpp__call_print_fn(hpp, print_fn, fmt, get_field(he)); if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; @@ -52,16 +63,22 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, * zero-fill group members in the middle which * have no sample */ - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 0); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0.0); + } else { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0ULL); + } } - if (fmt_percent) - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 100.0 * period / total); - else - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, period); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, fmt, + 100.0 * period / total); + } else { + ret += hpp__call_print_fn(hpp, print_fn, fmt, + period); + } prev_idx = perf_evsel__group_idx(evsel); } @@ -72,41 +89,87 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, /* * zero-fill group members at last which have no sample */ - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 0); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0.0); + } else { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0ULL); + } } } + + if (callback) { + int __ret = callback(hpp, false); + + advance_hpp(hpp, __ret); + ret += __ret; + } + + /* + * Restore original buf and size as it's where caller expects + * the result will be saved. + */ + hpp->buf = buf; + hpp->size = size; + return ret; } #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp) \ + struct perf_hpp *hpp, \ + struct perf_evsel *evsel) \ { \ int len = _min_width; \ \ - if (symbol_conf.event_group) { \ - struct perf_evsel *evsel = hpp->ptr; \ - \ + if (symbol_conf.event_group) \ len = max(len, evsel->nr_members * _unit_width); \ - } \ + \ return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \ } #define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp __maybe_unused) \ + struct perf_hpp *hpp __maybe_unused, \ + struct perf_evsel *evsel) \ { \ int len = _min_width; \ \ - if (symbol_conf.event_group) { \ - struct perf_evsel *evsel = hpp->ptr; \ - \ + if (symbol_conf.event_group) \ len = max(len, evsel->nr_members * _unit_width); \ - } \ + \ return len; \ } +static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) +{ + va_list args; + ssize_t ssize = hpp->size; + double percent; + int ret; + + va_start(args, fmt); + percent = va_arg(args, double); + ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent); + va_end(args); + + return (ret >= ssize) ? (ssize - 1) : ret; +} + +static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) +{ + va_list args; + ssize_t ssize = hpp->size; + int ret; + + va_start(args, fmt); + ret = vsnprintf(hpp->buf, hpp->size, fmt, args); + va_end(args); + + return (ret >= ssize) ? (ssize - 1) : ret; +} + #define __HPP_COLOR_PERCENT_FN(_type, _field) \ static u64 he_get_##_field(struct hist_entry *he) \ { \ @@ -116,8 +179,8 @@ static u64 he_get_##_field(struct hist_entry *he) \ static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - percent_color_snprintf, true); \ + return __hpp__fmt(hpp, he, he_get_##_field, NULL, " %6.2f%%", \ + hpp_color_scnprintf, true); \ } #define __HPP_ENTRY_PERCENT_FN(_type, _field) \ @@ -125,8 +188,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ - return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ - scnprintf, true); \ + return __hpp__fmt(hpp, he, he_get_##_field, NULL, fmt, \ + hpp_entry_scnprintf, true); \ } #define __HPP_ENTRY_RAW_FN(_type, _field) \ @@ -139,7 +202,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ - return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, NULL, fmt, \ + hpp_entry_scnprintf, false); \ } #define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \ @@ -263,15 +327,13 @@ unsigned int hists__sort_list_width(struct hists *hists) struct perf_hpp_fmt *fmt; struct sort_entry *se; int i = 0, ret = 0; - struct perf_hpp dummy_hpp = { - .ptr = hists_to_evsel(hists), - }; + struct perf_hpp dummy_hpp; perf_hpp__for_each_format(fmt) { if (i) ret += 2; - ret += fmt->width(fmt, &dummy_hpp); + ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); } list_for_each_entry(se, &hist_entry__sort_list, list) diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 831fbb77d1ff..d59893edf031 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -306,12 +306,6 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he, return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); } -static inline void advance_hpp(struct perf_hpp *hpp, int inc) -{ - hpp->buf += inc; - hpp->size -= inc; -} - static int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he) { @@ -385,7 +379,6 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, struct perf_hpp dummy_hpp = { .buf = bf, .size = sizeof(bf), - .ptr = hists_to_evsel(hists), }; bool first = true; size_t linesz; @@ -404,7 +397,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, else first = false; - fmt->header(fmt, &dummy_hpp); + fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); fprintf(fp, "%s", bf); } @@ -449,7 +442,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, else first = false; - width = fmt->width(fmt, &dummy_hpp); + width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); for (i = 0; i < width; i++) fprintf(fp, "."); } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3aa555ff9d89..809b4c50beae 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1236,6 +1236,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, struct dso *dso = map->dso; char *filename; const char *d_filename; + const char *evsel_name = perf_evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); struct disasm_line *pos, *queue = NULL; u64 start = map__rip_2objdump(map, sym->start); @@ -1243,7 +1244,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int more = 0; u64 len; int width = 8; - int namelen; + int namelen, evsel_name_len, graph_dotted_len; filename = strdup(dso->long_name); if (!filename) @@ -1256,14 +1257,17 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, len = symbol__size(sym); namelen = strlen(d_filename); + evsel_name_len = strlen(evsel_name); if (perf_evsel__is_group_event(evsel)) width *= evsel->nr_members; - printf(" %-*.*s| Source code & Disassembly of %s\n", - width, width, "Percent", d_filename); - printf("-%-*.*s-------------------------------------\n", - width+namelen, width+namelen, graph_dotted_line); + printf(" %-*.*s| Source code & Disassembly of %s for %s\n", + width, width, "Percent", d_filename, evsel_name); + + graph_dotted_len = width + namelen + evsel_name_len; + printf("-%-*.*s-----------------------------------------\n", + graph_dotted_len, graph_dotted_len, graph_dotted_line); if (verbose) symbol__annotate_hits(sym, evsel); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index a9b48c42e81e..7fe4994eeb63 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,5 +1,5 @@ #include "util.h" -#include "fs.h" +#include <api/fs/fs.h> #include "../perf.h" #include "cpumap.h" #include <assert.h> diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 4045d086d9d9..64453d63b971 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -45,8 +45,8 @@ int dso__read_binary_type_filename(const struct dso *dso, debuglink--; if (*debuglink == '/') debuglink++; - filename__read_debuglink(dso->long_name, debuglink, - size - (debuglink - filename)); + ret = filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - filename)); } break; case DSO_BINARY_TYPE__BUILD_ID_CACHE: diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index cd7d6f078cdd..ab06f1c03655 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -102,6 +102,16 @@ struct dso { char name[0]; }; +/* dso__for_each_symbol - iterate over the symbols of given type + * + * @dso: the 'struct dso *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * @type: the 'enum map_type' type of symbols + */ +#define dso__for_each_symbol(dso, pos, n, type) \ + symbols__for_each_entry(&(dso)->symbols[(type)], pos, n) + static inline void dso__set_loaded(struct dso *dso, enum map_type type) { dso->loaded |= (1 << type); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index b0f3ca850e9e..9d12aa6dd485 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include "event.h" #include "debug.h" +#include "hist.h" #include "machine.h" #include "sort.h" #include "string.h" @@ -94,14 +95,10 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) static pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, - int full, perf_event__handler_t process, struct machine *machine) { - char filename[PATH_MAX]; size_t size; - DIR *tasks; - struct dirent dirent, *next; pid_t tgid; memset(&event->comm, 0, sizeof(event->comm)); @@ -124,55 +121,35 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + machine->id_hdr_size); - if (!full) { - event->comm.tid = pid; + event->comm.tid = pid; - if (process(tool, event, &synth_sample, machine) != 0) - return -1; - - goto out; - } - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task", - machine->root_dir, pid); - - tasks = opendir(filename); - if (tasks == NULL) { - pr_debug("couldn't open %s\n", filename); - return 0; - } + if (process(tool, event, &synth_sample, machine) != 0) + return -1; - while (!readdir_r(tasks, &dirent, &next) && next) { - char *end; - pid = strtol(dirent.d_name, &end, 10); - if (*end) - continue; +out: + return tgid; +} - /* already have tgid; jut want to update the comm */ - (void) perf_event__get_comm_tgid(pid, event->comm.comm, - sizeof(event->comm.comm)); +static int perf_event__synthesize_fork(struct perf_tool *tool, + union perf_event *event, pid_t pid, + pid_t tgid, perf_event__handler_t process, + struct machine *machine) +{ + memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - size = strlen(event->comm.comm) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - memset(event->comm.comm + size, 0, machine->id_hdr_size); - event->comm.header.size = (sizeof(event->comm) - - (sizeof(event->comm.comm) - size) + - machine->id_hdr_size); + /* this is really a clone event but we use fork to synthesize it */ + event->fork.ppid = tgid; + event->fork.ptid = tgid; + event->fork.pid = tgid; + event->fork.tid = pid; + event->fork.header.type = PERF_RECORD_FORK; - event->comm.tid = pid; + event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); - if (process(tool, event, &synth_sample, machine) != 0) { - tgid = -1; - break; - } - } + if (process(tool, event, &synth_sample, machine) != 0) + return -1; - closedir(tasks); -out: - return tgid; + return 0; } int perf_event__synthesize_mmap_events(struct perf_tool *tool, @@ -324,17 +301,71 @@ int perf_event__synthesize_modules(struct perf_tool *tool, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, + union perf_event *fork_event, pid_t pid, int full, perf_event__handler_t process, struct perf_tool *tool, struct machine *machine, bool mmap_data) { - pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full, + char filename[PATH_MAX]; + DIR *tasks; + struct dirent dirent, *next; + pid_t tgid; + + /* special case: only send one comm event using passed in pid */ + if (!full) { + tgid = perf_event__synthesize_comm(tool, comm_event, pid, + process, machine); + + if (tgid == -1) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task", + machine->root_dir, pid); + + tasks = opendir(filename); + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } + + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + int rc = 0; + pid_t _pid; + + _pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + tgid = perf_event__synthesize_comm(tool, comm_event, _pid, + process, machine); + if (tgid == -1) + return -1; + + if (_pid == pid) { + /* process the parent's maps too */ + rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } else { + /* only fork the tid's map, to save time */ + rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, process, machine); - if (tgid == -1) - return -1; - return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data); + } + + if (rc) + return rc; + } + + closedir(tasks); + return 0; } int perf_event__synthesize_thread_map(struct perf_tool *tool, @@ -343,7 +374,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct machine *machine, bool mmap_data) { - union perf_event *comm_event, *mmap_event; + union perf_event *comm_event, *mmap_event, *fork_event; int err = -1, thread, j; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); @@ -354,9 +385,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (mmap_event == NULL) goto out_free_comm; + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, + fork_event, threads->map[thread], 0, process, tool, machine, mmap_data)) { @@ -382,6 +418,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, /* if not, generate events for it */ if (need_leader && __event__synthesize_thread(comm_event, mmap_event, + fork_event, comm_event->comm.pid, 0, process, tool, machine, mmap_data)) { @@ -390,6 +427,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, } } } + free(fork_event); +out_free_mmap: free(mmap_event); out_free_comm: free(comm_event); @@ -404,9 +443,12 @@ int perf_event__synthesize_threads(struct perf_tool *tool, DIR *proc; char proc_path[PATH_MAX]; struct dirent dirent, *next; - union perf_event *comm_event, *mmap_event; + union perf_event *comm_event, *mmap_event, *fork_event; int err = -1; + if (machine__is_default_guest(machine)) + return 0; + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) goto out; @@ -415,14 +457,15 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (mmap_event == NULL) goto out_free_comm; - if (machine__is_default_guest(machine)) - return 0; + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); proc = opendir(proc_path); if (proc == NULL) - goto out_free_mmap; + goto out_free_fork; while (!readdir_r(proc, &dirent, &next) && next) { char *end; @@ -434,12 +477,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool, * We may race with exiting thread, so don't stop just because * one thread couldn't be synthesized. */ - __event__synthesize_thread(comm_event, mmap_event, pid, 1, - process, tool, machine, mmap_data); + __event__synthesize_thread(comm_event, mmap_event, fork_event, pid, + 1, process, tool, machine, mmap_data); } err = 0; closedir(proc); +out_free_fork: + free(fork_event); out_free_mmap: free(mmap_event); out_free_comm: @@ -661,7 +706,7 @@ void thread__find_addr_map(struct thread *thread, al->thread = thread; al->addr = addr; al->cpumode = cpumode; - al->filtered = false; + al->filtered = 0; if (machine == NULL) { al->map = NULL; @@ -687,11 +732,11 @@ void thread__find_addr_map(struct thread *thread, if ((cpumode == PERF_RECORD_MISC_GUEST_USER || cpumode == PERF_RECORD_MISC_GUEST_KERNEL) && !perf_guest) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__GUEST); if ((cpumode == PERF_RECORD_MISC_USER || cpumode == PERF_RECORD_MISC_KERNEL) && !perf_host) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__HOST); return; } @@ -748,9 +793,6 @@ int perf_event__preprocess_sample(const union perf_event *event, if (thread == NULL) return -1; - if (thread__is_filtered(thread)) - goto out_filtered; - dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); /* * Have we already created the kernel maps for this machine? @@ -768,6 +810,10 @@ int perf_event__preprocess_sample(const union perf_event *event, dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); + + if (thread__is_filtered(thread)) + al->filtered |= (1 << HIST_FILTER__THREAD); + al->sym = NULL; al->cpu = sample->cpu; @@ -779,8 +825,9 @@ int perf_event__preprocess_sample(const union perf_event *event, dso->short_name) || (dso->short_name != dso->long_name && strlist__has_entry(symbol_conf.dso_list, - dso->long_name))))) - goto out_filtered; + dso->long_name))))) { + al->filtered |= (1 << HIST_FILTER__DSO); + } al->sym = map__find_symbol(al->map, al->addr, machine->symbol_filter); @@ -788,12 +835,9 @@ int perf_event__preprocess_sample(const union perf_event *event, if (symbol_conf.sym_list && (!al->sym || !strlist__has_entry(symbol_conf.sym_list, - al->sym->name))) - goto out_filtered; - - return 0; + al->sym->name))) { + al->filtered |= (1 << HIST_FILTER__SYMBOL); + } -out_filtered: - al->filtered = true; return 0; } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 851fa06f4a42..38457d447a13 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -85,6 +85,7 @@ struct sample_event { struct regs_dump { u64 abi; + u64 mask; u64 *regs; }; @@ -259,9 +260,9 @@ int perf_event__preprocess_sample(const union perf_event *event, const char *perf_event__name(unsigned int id); size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 sample_regs_user, u64 read_format); + u64 read_format); int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 sample_regs_user, u64 read_format, + u64 read_format, const struct perf_sample *sample, bool swapped); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 55407c594b87..5c28d82b76c4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -500,6 +500,34 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } +static void +perf_evsel__config_callgraph(struct perf_evsel *evsel, + struct record_opts *opts) +{ + bool function = perf_evsel__is_function_event(evsel); + struct perf_event_attr *attr = &evsel->attr; + + perf_evsel__set_sample_bit(evsel, CALLCHAIN); + + if (opts->call_graph == CALLCHAIN_DWARF) { + if (!function) { + perf_evsel__set_sample_bit(evsel, REGS_USER); + perf_evsel__set_sample_bit(evsel, STACK_USER); + attr->sample_regs_user = PERF_REGS_MASK; + attr->sample_stack_user = opts->stack_dump_size; + attr->exclude_callchain_user = 1; + } else { + pr_info("Cannot use DWARF unwind for function trace event," + " falling back to framepointers.\n"); + } + } + + if (function) { + pr_info("Disabling user space callchains for function trace event.\n"); + attr->exclude_callchain_user = 1; + } +} + /* * The enable_on_exec/disabled value strategy: * @@ -595,17 +623,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph) { - perf_evsel__set_sample_bit(evsel, CALLCHAIN); - - if (opts->call_graph == CALLCHAIN_DWARF) { - perf_evsel__set_sample_bit(evsel, REGS_USER); - perf_evsel__set_sample_bit(evsel, STACK_USER); - attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = opts->stack_dump_size; - attr->exclude_callchain_user = 1; - } - } + if (opts->call_graph_enabled) + perf_evsel__config_callgraph(evsel, opts); if (target__has_cpu(&opts->target)) perf_evsel__set_sample_bit(evsel, CPU); @@ -1004,7 +1023,7 @@ retry_sample_id: group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", pid, cpus->map[cpu], group_fd, flags); FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, @@ -1013,7 +1032,7 @@ retry_open: group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; - pr_debug2("perf_event_open failed, error %d\n", + pr_debug2("sys_perf_event_open failed, error %d\n", err); goto try_fallback; } @@ -1220,7 +1239,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; - data->period = 1; + data->period = evsel->attr.sample_period; data->weight = 0; if (event->header.type != PERF_RECORD_SAMPLE) { @@ -1396,10 +1415,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->user_regs.abi) { - u64 regs_user = evsel->attr.sample_regs_user; + u64 mask = evsel->attr.sample_regs_user; - sz = hweight_long(regs_user) * sizeof(u64); + sz = hweight_long(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); + data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; array = (void *)array + sz; } @@ -1451,7 +1471,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 sample_regs_user, u64 read_format) + u64 read_format) { size_t sz, result = sizeof(struct sample_event); @@ -1517,7 +1537,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample_regs_user) * sizeof(u64); + sz = hweight_long(sample->user_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1546,7 +1566,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 sample_regs_user, u64 read_format, + u64 read_format, const struct perf_sample *sample, bool swapped) { @@ -1687,7 +1707,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { *array++ = sample->user_regs.abi; - sz = hweight_long(sample_regs_user) * sizeof(u64); + sz = hweight_long(sample->user_regs.mask) * sizeof(u64); memcpy(array, sample->user_regs.regs, sz); array = (void *)array + sz; } else { diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index f1b325665aae..0c9926cfb292 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -315,6 +315,24 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; } +/** + * perf_evsel__is_function_event - Return whether given evsel is a function + * trace event + * + * @evsel - evsel selector to be tested + * + * Return %true if event is function trace event + */ +static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel) +{ +#define FUNCTION_EVENT "ftrace:function" + + return evsel->name && + !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); + +#undef FUNCTION_EVENT +} + struct perf_attr_details { bool freq; bool verbose; diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h deleted file mode 100644 index 5e09ce1bab0e..000000000000 --- a/tools/perf/util/fs.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __PERF_FS -#define __PERF_FS - -const char *sysfs__mountpoint(void); -const char *procfs__mountpoint(void); - -#endif /* __PERF_FS */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index e4e6249b87d4..f38590d7561b 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -13,13 +13,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); -enum hist_filter { - HIST_FILTER__DSO, - HIST_FILTER__THREAD, - HIST_FILTER__PARENT, - HIST_FILTER__SYMBOL, -}; - struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, .min_percent = 0.5, @@ -290,7 +283,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (he->branch_info) { /* * This branch info is (a part of) allocated from - * machine__resolve_bstack() and will be freed after + * sample__resolve_bstack() and will be freed after * adding new entries. So we need to save a copy. */ he->branch_info = malloc(sizeof(*he->branch_info)); @@ -369,7 +362,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, he_stat__add_period(&he->stat, period, weight); /* - * This mem info was allocated from machine__resolve_mem + * This mem info was allocated from sample__resolve_mem * and will not be used anymore. */ zfree(&entry->mem_info); @@ -429,7 +422,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .weight = weight, }, .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), + .filtered = symbol__parent_filter(sym_parent) | al->filtered, .hists = hists, .branch_info = bi, .mem_info = mi, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a59743fa3ef7..1f1f513dfe7f 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -14,6 +14,15 @@ struct hist_entry; struct addr_location; struct symbol; +enum hist_filter { + HIST_FILTER__DSO, + HIST_FILTER__THREAD, + HIST_FILTER__PARENT, + HIST_FILTER__SYMBOL, + HIST_FILTER__GUEST, + HIST_FILTER__HOST, +}; + /* * The kernel collects the number of events it couldn't send in a stretch and * when possible sends this number in a PERF_RECORD_LOST event. The number of @@ -132,8 +141,10 @@ struct perf_hpp { }; struct perf_hpp_fmt { - int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); - int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); + int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -166,6 +177,20 @@ void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +typedef u64 (*hpp_field_fn)(struct hist_entry *he); +typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); +typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); + +int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, hpp_callback_fn callback, + const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent); + +static inline void advance_hpp(struct perf_hpp *hpp, int inc) +{ + hpp->buf += inc; + hpp->size -= inc; +} + static inline size_t perf_hpp__use_color(void) { return !symbol_conf.field_sep; diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h deleted file mode 100644 index 201f57397997..000000000000 --- a/tools/perf/util/include/linux/hash.h +++ /dev/null @@ -1,5 +0,0 @@ -#include "../../../../include/linux/hash.h" - -#ifndef PERF_HASH_H -#define PERF_HASH_H -#endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index d8c927c868ee..9844c31b7c2b 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -94,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -static inline unsigned long -simple_strtoul(const char *nptr, char **endptr, int base) -{ - return strtoul(nptr, endptr, base); -} - int eprintf(int level, const char *fmt, ...) __attribute__((format(printf, 2, 3))); diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h index 1d928a0ce997..bfe0a2afd0d2 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/perf/util/include/linux/list.h @@ -1,5 +1,4 @@ #include <linux/kernel.h> -#include <linux/prefetch.h> #include "../../../../include/linux/list.h" diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h deleted file mode 100644 index 7841e485d8c3..000000000000 --- a/tools/perf/util/include/linux/prefetch.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_PREFETCH_H -#define PERF_LINUX_PREFETCH_H - -static inline void prefetch(void *a __attribute__((unused))) { } - -#endif diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c872991e0f65..a53cd0b8c151 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -327,9 +327,10 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, return __machine__findnew_thread(machine, pid, tid, true); } -struct thread *machine__find_thread(struct machine *machine, pid_t tid) +struct thread *machine__find_thread(struct machine *machine, pid_t pid, + pid_t tid) { - return __machine__findnew_thread(machine, 0, tid, false); + return __machine__findnew_thread(machine, pid, tid, false); } int machine__process_comm_event(struct machine *machine, union perf_event *event, @@ -1026,7 +1027,7 @@ int machine__process_mmap2_event(struct machine *machine, } thread = machine__findnew_thread(machine, event->mmap2.pid, - event->mmap2.pid); + event->mmap2.tid); if (thread == NULL) goto out_problem; @@ -1074,7 +1075,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event } thread = machine__findnew_thread(machine, event->mmap.pid, - event->mmap.pid); + event->mmap.tid); if (thread == NULL) goto out_problem; @@ -1114,7 +1115,9 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) int machine__process_fork_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) { - struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *thread = machine__find_thread(machine, + event->fork.pid, + event->fork.tid); struct thread *parent = machine__findnew_thread(machine, event->fork.ppid, event->fork.ptid); @@ -1140,7 +1143,9 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event int machine__process_exit_event(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) { - struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *thread = machine__find_thread(machine, + event->fork.pid, + event->fork.tid); if (dump_trace) perf_event__fprintf_task(event, stdout); @@ -1184,39 +1189,22 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex) return 0; } -static const u8 cpumodes[] = { - PERF_RECORD_MISC_USER, - PERF_RECORD_MISC_KERNEL, - PERF_RECORD_MISC_GUEST_USER, - PERF_RECORD_MISC_GUEST_KERNEL -}; -#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) - static void ip__resolve_ams(struct machine *machine, struct thread *thread, struct addr_map_symbol *ams, u64 ip) { struct addr_location al; - size_t i; - u8 m; memset(&al, 0, sizeof(al)); + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al); - for (i = 0; i < NCPUMODES; i++) { - m = cpumodes[i]; - /* - * We cannot use the header.misc hint to determine whether a - * branch stack address is user, kernel, guest, hypervisor. - * Branches may straddle the kernel/user/hypervisor boundaries. - * Thus, we have to try consecutively until we find a match - * or else, the symbol is unknown - */ - thread__find_addr_location(thread, machine, m, MAP__FUNCTION, - ip, &al); - if (al.sym) - goto found; - } -found: ams->addr = ip; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1238,37 +1226,35 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread, ams->map = al.map; } -struct mem_info *machine__resolve_mem(struct machine *machine, - struct thread *thr, - struct perf_sample *sample, - u8 cpumode) +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al) { struct mem_info *mi = zalloc(sizeof(*mi)); if (!mi) return NULL; - ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip); - ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr); + ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip); + ip__resolve_data(al->machine, al->thread, al->cpumode, + &mi->daddr, sample->addr); mi->data_src.val = sample->data_src; return mi; } -struct branch_info *machine__resolve_bstack(struct machine *machine, - struct thread *thr, - struct branch_stack *bs) +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al) { - struct branch_info *bi; unsigned int i; + const struct branch_stack *bs = sample->branch_stack; + struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info)); - bi = calloc(bs->nr, sizeof(struct branch_info)); if (!bi) return NULL; for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from); + ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from); bi[i].flags = bs->entries[i].flags; } return bi; @@ -1326,7 +1312,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, continue; } - al.filtered = false; + al.filtered = 0; thread__find_addr_location(thread, machine, cpumode, MAP__FUNCTION, ip, &al); if (al.sym != NULL) { @@ -1385,8 +1371,7 @@ int machine__resolve_callchain(struct machine *machine, return 0; return unwind__get_entries(unwind_entry, &callchain_cursor, machine, - thread, evsel->attr.sample_regs_user, - sample, max_stack); + thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index f77e91e483dc..c8c74a119398 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -41,7 +41,8 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } -struct thread *machine__find_thread(struct machine *machine, pid_t tid); +struct thread *machine__find_thread(struct machine *machine, pid_t pid, + pid_t tid); int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); @@ -91,12 +92,10 @@ void machine__delete_dead_threads(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); -struct branch_info *machine__resolve_bstack(struct machine *machine, - struct thread *thread, - struct branch_stack *bs); -struct mem_info *machine__resolve_mem(struct machine *machine, - struct thread *thread, - struct perf_sample *sample, u8 cpumode); +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al); +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al); int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 257e513205ce..f00f058afb3b 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -90,6 +90,16 @@ u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +/* map__for_each_symbol - iterate over the symbols in the given map + * + * @map: the 'struct map *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * Note: caller must ensure map->dso is not NULL (map is loaded). + */ +#define map__for_each_symbol(map, pos, n) \ + dso__for_each_symbol(map->dso, pos, n, map->type) + typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index d22e3f8017dc..bf48092983c6 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -407,7 +407,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (internal_help && !strcmp(arg + 2, "help")) return usage_with_options_internal(usagestr, options, 0); if (!strcmp(arg + 2, "list-opts")) - return PARSE_OPT_LIST; + return PARSE_OPT_LIST_OPTS; + if (!strcmp(arg + 2, "list-cmds")) + return PARSE_OPT_LIST_SUBCMDS; switch (parse_long_opt(ctx, arg + 2, options)) { case -1: return parse_options_usage(usagestr, options, arg + 2, 0); @@ -433,25 +435,45 @@ int parse_options_end(struct parse_opt_ctx_t *ctx) return ctx->cpidx + ctx->argc; } -int parse_options(int argc, const char **argv, const struct option *options, - const char * const usagestr[], int flags) +int parse_options_subcommand(int argc, const char **argv, const struct option *options, + const char *const subcommands[], const char *usagestr[], int flags) { struct parse_opt_ctx_t ctx; perf_header__set_cmdline(argc, argv); + /* build usage string if it's not provided */ + if (subcommands && !usagestr[0]) { + struct strbuf buf = STRBUF_INIT; + + strbuf_addf(&buf, "perf %s [<options>] {", argv[0]); + for (int i = 0; subcommands[i]; i++) { + if (i) + strbuf_addstr(&buf, "|"); + strbuf_addstr(&buf, subcommands[i]); + } + strbuf_addstr(&buf, "}"); + + usagestr[0] = strdup(buf.buf); + strbuf_release(&buf); + } + parse_options_start(&ctx, argc, argv, flags); switch (parse_options_step(&ctx, options, usagestr)) { case PARSE_OPT_HELP: exit(129); case PARSE_OPT_DONE: break; - case PARSE_OPT_LIST: + case PARSE_OPT_LIST_OPTS: while (options->type != OPTION_END) { printf("--%s ", options->long_name); options++; } exit(130); + case PARSE_OPT_LIST_SUBCMDS: + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { error("unknown option `%s'", ctx.argv[0] + 2); @@ -464,6 +486,13 @@ int parse_options(int argc, const char **argv, const struct option *options, return parse_options_end(&ctx); } +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + return parse_options_subcommand(argc, argv, options, NULL, + (const char **) usagestr, flags); +} + #define USAGE_OPTS_WIDTH 24 #define USAGE_GAP 2 diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index cbf0149cf221..d8dac8ac5f37 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -140,6 +140,11 @@ extern int parse_options(int argc, const char **argv, const struct option *options, const char * const usagestr[], int flags); +extern int parse_options_subcommand(int argc, const char **argv, + const struct option *options, + const char *const subcommands[], + const char *usagestr[], int flags); + extern NORETURN void usage_with_options(const char * const *usagestr, const struct option *options); @@ -148,7 +153,8 @@ extern NORETURN void usage_with_options(const char * const *usagestr, enum { PARSE_OPT_HELP = -1, PARSE_OPT_DONE, - PARSE_OPT_LIST, + PARSE_OPT_LIST_OPTS, + PARSE_OPT_LIST_SUBCMDS, PARSE_OPT_UNKNOWN, }; diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c new file mode 100644 index 000000000000..a3539ef30b15 --- /dev/null +++ b/tools/perf/util/perf_regs.c @@ -0,0 +1,19 @@ +#include <errno.h> +#include "perf_regs.h" + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) +{ + int i, idx = 0; + u64 mask = regs->mask; + + if (!(mask & (1 << id))) + return -EINVAL; + + for (i = 0; i < id; i++) { + if (mask & (1 << i)) + idx++; + } + + *valp = regs->regs[idx]; + return 0; +} diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index a3d42cd74919..d6e8b6a8d7f3 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,8 +1,14 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H +#include "types.h" +#include "event.h" + #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); + #else #define PERF_REGS_MASK 0 @@ -10,5 +16,12 @@ static inline const char *perf_reg_name(int id __maybe_unused) { return NULL; } + +static inline int perf_reg_value(u64 *valp __maybe_unused, + struct regs_dump *regs __maybe_unused, + int id __maybe_unused) +{ + return 0; +} #endif /* HAVE_PERF_REGS_SUPPORT */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b752ecb40d86..00a7dcb2f55c 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -3,7 +3,7 @@ #include <unistd.h> #include <stdio.h> #include <dirent.h> -#include "fs.h" +#include <api/fs/fs.h> #include <locale.h> #include "util.h" #include "pmu.h" diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d8b048c20cde..0d1542f33d87 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -70,34 +70,32 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) } static char *synthesize_perf_probe_point(struct perf_probe_point *pp); -static int convert_name_to_addr(struct perf_probe_event *pev, - const char *exec); static void clear_probe_trace_event(struct probe_trace_event *tev); -static struct machine machine; +static struct machine *host_machine; /* Initialize symbol maps and path of vmlinux/modules */ -static int init_vmlinux(void) +static int init_symbol_maps(bool user_only) { int ret; symbol_conf.sort_by_name = true; - if (symbol_conf.vmlinux_name == NULL) - symbol_conf.try_vmlinux_path = true; - else - pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); ret = symbol__init(); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); goto out; } - ret = machine__init(&machine, "", HOST_KERNEL_ID); - if (ret < 0) - goto out; + if (host_machine || user_only) /* already initialized */ + return 0; - if (machine__create_kernel_maps(&machine) < 0) { - pr_debug("machine__create_kernel_maps() failed.\n"); - goto out; + if (symbol_conf.vmlinux_name) + pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); + + host_machine = machine__new_host(); + if (!host_machine) { + pr_debug("machine__new_host() failed.\n"); + symbol__exit(); + ret = -1; } out: if (ret < 0) @@ -105,21 +103,66 @@ out: return ret; } +static void exit_symbol_maps(void) +{ + if (host_machine) { + machine__delete(host_machine); + host_machine = NULL; + } + symbol__exit(); +} + static struct symbol *__find_kernel_function_by_name(const char *name, struct map **mapp) { - return machine__find_kernel_function_by_name(&machine, name, mapp, + return machine__find_kernel_function_by_name(host_machine, name, mapp, NULL); } +static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) +{ + return machine__find_kernel_function(host_machine, addr, mapp, NULL); +} + +static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) +{ + /* kmap->ref_reloc_sym should be set if host_machine is initialized */ + struct kmap *kmap; + + if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0) + return NULL; + + kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]); + return kmap->ref_reloc_sym; +} + +static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) +{ + struct ref_reloc_sym *reloc_sym; + struct symbol *sym; + struct map *map; + + /* ref_reloc_sym is just a label. Need a special fix*/ + reloc_sym = kernel_get_ref_reloc_sym(); + if (reloc_sym && strcmp(name, reloc_sym->name) == 0) + return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; + else { + sym = __find_kernel_function_by_name(name, &map); + if (sym) + return map->unmap_ip(map, sym->start) - + (reloc) ? 0 : map->reloc; + } + return 0; +} + static struct map *kernel_get_module_map(const char *module) { struct rb_node *nd; - struct map_groups *grp = &machine.kmaps; + struct map_groups *grp = &host_machine->kmaps; /* A file path -- this is an offline module */ if (module && strchr(module, '/')) - return machine__new_module(&machine, 0, module); + return machine__new_module(host_machine, 0, module); if (!module) module = "kernel"; @@ -141,7 +184,7 @@ static struct dso *kernel_get_module_dso(const char *module) const char *vmlinux_name; if (module) { - list_for_each_entry(dso, &machine.kernel_dsos, node) { + list_for_each_entry(dso, &host_machine->kernel_dsos, node) { if (strncmp(dso->short_name + 1, module, dso->short_name_len - 2) == 0) goto found; @@ -150,7 +193,7 @@ static struct dso *kernel_get_module_dso(const char *module) return NULL; } - map = machine.vmlinux_maps[MAP__FUNCTION]; + map = host_machine->vmlinux_maps[MAP__FUNCTION]; dso = map->dso; vmlinux_name = symbol_conf.vmlinux_name; @@ -173,20 +216,6 @@ const char *kernel_get_module_path(const char *module) return (dso) ? dso->long_name : NULL; } -static int init_user_exec(void) -{ - int ret = 0; - - symbol_conf.try_vmlinux_path = false; - symbol_conf.sort_by_name = true; - ret = symbol__init(); - - if (ret < 0) - pr_debug("Failed to init symbol map.\n"); - - return ret; -} - static int convert_exec_to_group(const char *exec, char **result) { char *ptr1, *ptr2, *exec_copy; @@ -218,32 +247,23 @@ out: return ret; } -static int convert_to_perf_probe_point(struct probe_trace_point *tp, - struct perf_probe_point *pp) +static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) { - pp->function = strdup(tp->symbol); - - if (pp->function == NULL) - return -ENOMEM; - - pp->offset = tp->offset; - pp->retprobe = tp->retprobe; + int i; - return 0; + for (i = 0; i < ntevs; i++) + clear_probe_trace_event(tevs + i); } #ifdef HAVE_DWARF_SUPPORT + /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module) { - const char *path; + const char *path = module; - /* A file path -- this is an offline module */ - if (module && strchr(module, '/')) - path = module; - else { + if (!module || !strchr(module, '/')) { path = kernel_get_module_path(module); - if (!path) { pr_err("Failed to find path of %s module.\n", module ?: "kernel"); @@ -253,46 +273,6 @@ static struct debuginfo *open_debuginfo(const char *module) return debuginfo__new(path); } -/* - * Convert trace point to probe point with debuginfo - * Currently only handles kprobes. - */ -static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, - struct perf_probe_point *pp) -{ - struct symbol *sym; - struct map *map; - u64 addr; - int ret = -ENOENT; - struct debuginfo *dinfo; - - sym = __find_kernel_function_by_name(tp->symbol, &map); - if (sym) { - addr = map->unmap_ip(map, sym->start + tp->offset); - pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol, - tp->offset, addr); - - dinfo = debuginfo__new_online_kernel(addr); - if (dinfo) { - ret = debuginfo__find_probe_point(dinfo, - (unsigned long)addr, pp); - debuginfo__delete(dinfo); - } else { - pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", - addr); - ret = -ENOENT; - } - } - if (ret <= 0) { - pr_debug("Failed to find corresponding probes from " - "debuginfo. Use kprobe event information.\n"); - return convert_to_perf_probe_point(tp, pp); - } - pp->retprobe = tp->retprobe; - - return 0; -} - static int get_text_start_address(const char *exec, unsigned long *address) { Elf *elf; @@ -321,12 +301,62 @@ out: return ret; } +/* + * Convert trace point to probe point with debuginfo + */ +static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + struct debuginfo *dinfo = NULL; + unsigned long stext = 0; + u64 addr = tp->address; + int ret = -ENOENT; + + /* convert the address to dwarf address */ + if (!is_kprobe) { + if (!addr) { + ret = -EINVAL; + goto error; + } + ret = get_text_start_address(tp->module, &stext); + if (ret < 0) + goto error; + addr += stext; + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, false); + if (addr == 0) + goto error; + addr += tp->offset; + } + + pr_debug("try to find information at %" PRIx64 " in %s\n", addr, + tp->module ? : "kernel"); + + dinfo = open_debuginfo(tp->module); + if (dinfo) { + ret = debuginfo__find_probe_point(dinfo, + (unsigned long)addr, pp); + debuginfo__delete(dinfo); + } else { + pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr); + ret = -ENOENT; + } + + if (ret > 0) { + pp->retprobe = tp->retprobe; + return 0; + } +error: + pr_debug("Failed to find corresponding probes from debuginfo.\n"); + return ret ? : -ENOENT; +} + static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *exec) { int i, ret = 0; - unsigned long offset, stext = 0; - char buf[32]; + unsigned long stext = 0; if (!exec) return 0; @@ -337,15 +367,9 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, for (i = 0; i < ntevs && ret >= 0; i++) { /* point.address is the addres of point.symbol + point.offset */ - offset = tevs[i].point.address - stext; - tevs[i].point.offset = 0; - zfree(&tevs[i].point.symbol); - ret = e_snprintf(buf, 32, "0x%lx", offset); - if (ret < 0) - break; + tevs[i].point.address -= stext; tevs[i].point.module = strdup(exec); - tevs[i].point.symbol = strdup(buf); - if (!tevs[i].point.symbol || !tevs[i].point.module) { + if (!tevs[i].point.module) { ret = -ENOMEM; break; } @@ -388,12 +412,40 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) { + struct ref_reloc_sym *reloc_sym; + char *tmp; int i; - for (i = 0; i < ntevs; i++) - clear_probe_trace_event(tevs + i); + if (uprobe) + return add_exec_to_probe_trace_events(tevs, ntevs, module); + + /* Note that currently ref_reloc_sym based probe is not for drivers */ + if (module) + return add_module_to_probe_trace_events(tevs, ntevs, module); + + reloc_sym = kernel_get_ref_reloc_sym(); + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + if (tevs[i].point.address) { + tmp = strdup(reloc_sym->name); + if (!tmp) + return -ENOMEM; + free(tevs[i].point.symbol); + tevs[i].point.symbol = tmp; + tevs[i].point.offset = tevs[i].point.address - + reloc_sym->unrelocated_addr; + } + } + return 0; } /* Try to find perf_probe_event with debuginfo */ @@ -416,21 +468,16 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, return 0; } + pr_debug("Try to find probe point from debuginfo.\n"); /* Searching trace events corresponding to a probe event */ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs); debuginfo__delete(dinfo); if (ntevs > 0) { /* Succeeded to find trace events */ - pr_debug("find %d probe_trace_events.\n", ntevs); - if (target) { - if (pev->uprobes) - ret = add_exec_to_probe_trace_events(*tevs, - ntevs, target); - else - ret = add_module_to_probe_trace_events(*tevs, - ntevs, target); - } + pr_debug("Found %d probe_trace_events.\n", ntevs); + ret = post_process_probe_trace_events(*tevs, ntevs, + target, pev->uprobes); if (ret < 0) { clear_probe_trace_events(*tevs, ntevs); zfree(tevs); @@ -563,20 +610,16 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) * Show line-range always requires debuginfo to find source file and * line number. */ -int show_line_range(struct line_range *lr, const char *module) +static int __show_line_range(struct line_range *lr, const char *module) { int l = 1; - struct line_node *ln; + struct int_node *ln; struct debuginfo *dinfo; FILE *fp; int ret; char *tmp; /* Search a line range */ - ret = init_vmlinux(); - if (ret < 0) - return ret; - dinfo = open_debuginfo(module); if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); @@ -623,8 +666,8 @@ int show_line_range(struct line_range *lr, const char *module) goto end; } - list_for_each_entry(ln, &lr->line_list, list) { - for (; ln->line > l; l++) { + intlist__for_each(ln, lr->line_list) { + for (; ln->i > l; l++) { ret = show_one_line(fp, l - lr->offset); if (ret < 0) goto end; @@ -646,6 +689,19 @@ end: return ret; } +int show_line_range(struct line_range *lr, const char *module) +{ + int ret; + + ret = init_symbol_maps(false); + if (ret < 0) + return ret; + ret = __show_line_range(lr, module); + exit_symbol_maps(); + + return ret; +} + static int show_available_vars_at(struct debuginfo *dinfo, struct perf_probe_event *pev, int max_vls, struct strfilter *_filter, @@ -707,14 +763,15 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, int i, ret = 0; struct debuginfo *dinfo; - ret = init_vmlinux(); + ret = init_symbol_maps(false); if (ret < 0) return ret; dinfo = open_debuginfo(module); if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); - return -ENOENT; + ret = -ENOENT; + goto out; } setup_pager(); @@ -724,23 +781,19 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, externs); debuginfo__delete(dinfo); +out: + exit_symbol_maps(); return ret; } #else /* !HAVE_DWARF_SUPPORT */ -static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, - struct perf_probe_point *pp) +static int +find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused, + struct perf_probe_point *pp __maybe_unused, + bool is_kprobe __maybe_unused) { - struct symbol *sym; - - sym = __find_kernel_function_by_name(tp->symbol, NULL); - if (!sym) { - pr_err("Failed to find symbol %s in kernel.\n", tp->symbol); - return -ENOENT; - } - - return convert_to_perf_probe_point(tp, pp); + return -ENOSYS; } static int try_to_find_probe_trace_events(struct perf_probe_event *pev, @@ -776,24 +829,22 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused, void line_range__clear(struct line_range *lr) { - struct line_node *ln; - free(lr->function); free(lr->file); free(lr->path); free(lr->comp_dir); - while (!list_empty(&lr->line_list)) { - ln = list_first_entry(&lr->line_list, struct line_node, list); - list_del(&ln->list); - free(ln); - } + intlist__delete(lr->line_list); memset(lr, 0, sizeof(*lr)); } -void line_range__init(struct line_range *lr) +int line_range__init(struct line_range *lr) { memset(lr, 0, sizeof(*lr)); - INIT_LIST_HEAD(&lr->line_list); + lr->line_list = intlist__new(NULL); + if (!lr->line_list) + return -ENOMEM; + else + return 0; } static int parse_line_num(char **ptr, int *val, const char *what) @@ -1267,16 +1318,21 @@ static int parse_probe_trace_command(const char *cmd, } else p = argv[1]; fmt1_str = strtok_r(p, "+", &fmt); - tp->symbol = strdup(fmt1_str); - if (tp->symbol == NULL) { - ret = -ENOMEM; - goto out; + if (fmt1_str[0] == '0') /* only the address started with 0x */ + tp->address = strtoul(fmt1_str, NULL, 0); + else { + /* Only the symbol-based probe has offset */ + tp->symbol = strdup(fmt1_str); + if (tp->symbol == NULL) { + ret = -ENOMEM; + goto out; + } + fmt2_str = strtok_r(NULL, "", &fmt); + if (fmt2_str == NULL) + tp->offset = 0; + else + tp->offset = strtoul(fmt2_str, NULL, 10); } - fmt2_str = strtok_r(NULL, "", &fmt); - if (fmt2_str == NULL) - tp->offset = 0; - else - tp->offset = strtoul(fmt2_str, NULL, 10); tev->nargs = argc - 2; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); @@ -1518,20 +1574,27 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev) if (buf == NULL) return NULL; + len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p', + tev->group, tev->event); + if (len <= 0) + goto error; + + /* Uprobes must have tp->address and tp->module */ + if (tev->uprobes && (!tp->address || !tp->module)) + goto error; + + /* Use the tp->address for uprobes */ if (tev->uprobes) - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s:%s", - tp->retprobe ? 'r' : 'p', - tev->group, tev->event, - tp->module, tp->symbol); + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx", + tp->module, tp->address); else - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s%s%s+%lu", - tp->retprobe ? 'r' : 'p', - tev->group, tev->event, + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu", tp->module ?: "", tp->module ? ":" : "", tp->symbol, tp->offset); - if (len <= 0) + if (ret <= 0) goto error; + len += ret; for (i = 0; i < tev->nargs; i++) { ret = synthesize_probe_trace_arg(&tev->args[i], buf + len, @@ -1547,6 +1610,79 @@ error: return NULL; } +static int find_perf_probe_point_from_map(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + struct symbol *sym = NULL; + struct map *map; + u64 addr; + int ret = -ENOENT; + + if (!is_kprobe) { + map = dso__new_map(tp->module); + if (!map) + goto out; + addr = tp->address; + sym = map__find_symbol(map, addr, NULL); + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, true); + if (addr) { + addr += tp->offset; + sym = __find_kernel_function(addr, &map); + } + } + if (!sym) + goto out; + + pp->retprobe = tp->retprobe; + pp->offset = addr - map->unmap_ip(map, sym->start); + pp->function = strdup(sym->name); + ret = pp->function ? 0 : -ENOMEM; + +out: + if (map && !is_kprobe) { + dso__delete(map->dso); + map__delete(map); + } + + return ret; +} + +static int convert_to_perf_probe_point(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + char buf[128]; + int ret; + + ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe); + if (!ret) + return 0; + ret = find_perf_probe_point_from_map(tp, pp, is_kprobe); + if (!ret) + return 0; + + pr_debug("Failed to find probe point from both of dwarf and map.\n"); + + if (tp->symbol) { + pp->function = strdup(tp->symbol); + pp->offset = tp->offset; + } else if (!tp->module && !is_kprobe) { + ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + if (ret < 0) + return ret; + pp->function = strdup(buf); + pp->offset = 0; + } + if (pp->function == NULL) + return -ENOMEM; + + pp->retprobe = tp->retprobe; + + return 0; +} + static int convert_to_perf_probe_event(struct probe_trace_event *tev, struct perf_probe_event *pev, bool is_kprobe) { @@ -1560,11 +1696,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, return -ENOMEM; /* Convert trace_point to probe_point */ - if (is_kprobe) - ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point); - else - ret = convert_to_perf_probe_point(&tev->point, &pev->point); - + ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe); if (ret < 0) return ret; @@ -1731,7 +1863,8 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) } /* Show an event */ -static int show_perf_probe_event(struct perf_probe_event *pev) +static int show_perf_probe_event(struct perf_probe_event *pev, + const char *module) { int i, ret; char buf[128]; @@ -1747,6 +1880,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev) return ret; printf(" %-20s (on %s", buf, place); + if (module) + printf(" in %s", module); if (pev->nargs > 0) { printf(" with"); @@ -1784,7 +1919,8 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) ret = convert_to_perf_probe_event(&tev, &pev, is_kprobe); if (ret >= 0) - ret = show_perf_probe_event(&pev); + ret = show_perf_probe_event(&pev, + tev.point.module); } clear_perf_probe_event(&pev); clear_probe_trace_event(&tev); @@ -1807,7 +1943,7 @@ int show_perf_probe_events(void) if (fd < 0) return fd; - ret = init_vmlinux(); + ret = init_symbol_maps(false); if (ret < 0) return ret; @@ -1820,6 +1956,7 @@ int show_perf_probe_events(void) close(fd); } + exit_symbol_maps(); return ret; } @@ -1982,7 +2119,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, group = pev->group; pev->event = tev->event; pev->group = tev->group; - show_perf_probe_event(pev); + show_perf_probe_event(pev, tev->point.module); /* Trick here - restore current event/group */ pev->event = (char *)event; pev->group = (char *)group; @@ -2008,113 +2145,175 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, return ret; } -static int convert_to_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs, - int max_tevs, const char *target) +static char *looking_function_name; +static int num_matched_functions; + +static int probe_function_filter(struct map *map __maybe_unused, + struct symbol *sym) { + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && + strcmp(looking_function_name, sym->name) == 0) { + num_matched_functions++; + return 0; + } + return 1; +} + +#define strdup_or_goto(str, label) \ + ({ char *__p = strdup(str); if (!__p) goto label; __p; }) + +/* + * Find probe function addresses from map. + * Return an error or the number of found probe_trace_event + */ +static int find_probe_trace_events_from_map(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) +{ + struct map *map = NULL; + struct kmap *kmap = NULL; + struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; - int ret, i; + struct rb_node *nd; struct probe_trace_event *tev; + struct perf_probe_point *pp = &pev->point; + struct probe_trace_point *tp; + int ret, i; - if (pev->uprobes && !pev->group) { - /* Replace group name if not given */ - ret = convert_exec_to_group(target, &pev->group); - if (ret != 0) { - pr_warning("Failed to make a group name.\n"); - return ret; - } + /* Init maps of given executable or kernel */ + if (pev->uprobes) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); + if (!map) { + ret = -EINVAL; + goto out; } - /* Convert perf_probe_event with debuginfo */ - ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); - if (ret != 0) - return ret; /* Found in debuginfo or got an error */ - - if (pev->uprobes) { - ret = convert_name_to_addr(pev, target); - if (ret < 0) - return ret; + /* + * Load matched symbols: Since the different local symbols may have + * same name but different addresses, this lists all the symbols. + */ + num_matched_functions = 0; + looking_function_name = pp->function; + ret = map__load(map, probe_function_filter); + if (ret || num_matched_functions == 0) { + pr_err("Failed to find symbol %s in %s\n", pp->function, + target ? : "kernel"); + ret = -ENOENT; + goto out; + } else if (num_matched_functions > max_tevs) { + pr_err("Too many functions matched in %s\n", + target ? : "kernel"); + ret = -E2BIG; + goto out; } - /* Allocate trace event buffer */ - tev = *tevs = zalloc(sizeof(struct probe_trace_event)); - if (tev == NULL) - return -ENOMEM; + if (!pev->uprobes) { + kmap = map__kmap(map); + reloc_sym = kmap->ref_reloc_sym; + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + ret = -EINVAL; + goto out; + } + } - /* Copy parameters */ - tev->point.symbol = strdup(pev->point.function); - if (tev->point.symbol == NULL) { + /* Setup result trace-probe-events */ + *tevs = zalloc(sizeof(*tev) * num_matched_functions); + if (!*tevs) { ret = -ENOMEM; - goto error; + goto out; } - if (target) { - tev->point.module = strdup(target); - if (tev->point.module == NULL) { - ret = -ENOMEM; - goto error; + ret = 0; + map__for_each_symbol(map, sym, nd) { + tev = (*tevs) + ret; + tp = &tev->point; + if (ret == num_matched_functions) { + pr_warning("Too many symbols are listed. Skip it.\n"); + break; } - } - - tev->point.offset = pev->point.offset; - tev->point.retprobe = pev->point.retprobe; - tev->nargs = pev->nargs; - tev->uprobes = pev->uprobes; + ret++; - if (tev->nargs) { - tev->args = zalloc(sizeof(struct probe_trace_arg) - * tev->nargs); - if (tev->args == NULL) { - ret = -ENOMEM; - goto error; + if (pp->offset > sym->end - sym->start) { + pr_warning("Offset %ld is bigger than the size of %s\n", + pp->offset, sym->name); + ret = -ENOENT; + goto err_out; + } + /* Add one probe point */ + tp->address = map->unmap_ip(map, sym->start) + pp->offset; + if (reloc_sym) { + tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out); + tp->offset = tp->address - reloc_sym->addr; + } else { + tp->symbol = strdup_or_goto(sym->name, nomem_out); + tp->offset = pp->offset; + } + tp->retprobe = pp->retprobe; + if (target) + tev->point.module = strdup_or_goto(target, nomem_out); + tev->uprobes = pev->uprobes; + tev->nargs = pev->nargs; + if (tev->nargs) { + tev->args = zalloc(sizeof(struct probe_trace_arg) * + tev->nargs); + if (tev->args == NULL) + goto nomem_out; } for (i = 0; i < tev->nargs; i++) { - if (pev->args[i].name) { - tev->args[i].name = strdup(pev->args[i].name); - if (tev->args[i].name == NULL) { - ret = -ENOMEM; - goto error; - } - } - tev->args[i].value = strdup(pev->args[i].var); - if (tev->args[i].value == NULL) { - ret = -ENOMEM; - goto error; - } - if (pev->args[i].type) { - tev->args[i].type = strdup(pev->args[i].type); - if (tev->args[i].type == NULL) { - ret = -ENOMEM; - goto error; - } - } + if (pev->args[i].name) + tev->args[i].name = + strdup_or_goto(pev->args[i].name, + nomem_out); + + tev->args[i].value = strdup_or_goto(pev->args[i].var, + nomem_out); + if (pev->args[i].type) + tev->args[i].type = + strdup_or_goto(pev->args[i].type, + nomem_out); } } - if (pev->uprobes) - return 1; +out: + if (map && pev->uprobes) { + /* Only when using uprobe(exec) map needs to be released */ + dso__delete(map->dso); + map__delete(map); + } + return ret; - /* Currently just checking function name from symbol map */ - sym = __find_kernel_function_by_name(tev->point.symbol, NULL); - if (!sym) { - pr_warning("Kernel symbol \'%s\' not found.\n", - tev->point.symbol); - ret = -ENOENT; - goto error; - } else if (tev->point.offset > sym->end - sym->start) { - pr_warning("Offset specified is greater than size of %s\n", - tev->point.symbol); - ret = -ENOENT; - goto error; +nomem_out: + ret = -ENOMEM; +err_out: + clear_probe_trace_events(*tevs, num_matched_functions); + zfree(tevs); + goto out; +} + +static int convert_to_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) +{ + int ret; + if (pev->uprobes && !pev->group) { + /* Replace group name if not given */ + ret = convert_exec_to_group(target, &pev->group); + if (ret != 0) { + pr_warning("Failed to make a group name.\n"); + return ret; + } } - return 1; -error: - clear_probe_trace_event(tev); - free(tev); - *tevs = NULL; - return ret; + /* Convert perf_probe_event with debuginfo */ + ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); + if (ret != 0) + return ret; /* Found in debuginfo or got an error */ + + return find_probe_trace_events_from_map(pev, tevs, max_tevs, target); } struct __event_package { @@ -2135,12 +2334,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, if (pkgs == NULL) return -ENOMEM; - if (!pevs->uprobes) - /* Init vmlinux path */ - ret = init_vmlinux(); - else - ret = init_user_exec(); - + ret = init_symbol_maps(pevs->uprobes); if (ret < 0) { free(pkgs); return ret; @@ -2174,6 +2368,7 @@ end: zfree(&pkgs[i].tevs); } free(pkgs); + exit_symbol_maps(); return ret; } @@ -2323,159 +2518,51 @@ static struct strfilter *available_func_filter; static int filter_available_functions(struct map *map __maybe_unused, struct symbol *sym) { - if (sym->binding == STB_GLOBAL && + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && strfilter__compare(available_func_filter, sym->name)) return 0; return 1; } -static int __show_available_funcs(struct map *map) -{ - if (map__load(map, filter_available_functions)) { - pr_err("Failed to load map.\n"); - return -EINVAL; - } - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); - - dso__fprintf_symbols_by_name(map->dso, map->type, stdout); - return 0; -} - -static int available_kernel_funcs(const char *module) +int show_available_funcs(const char *target, struct strfilter *_filter, + bool user) { struct map *map; int ret; - ret = init_vmlinux(); + ret = init_symbol_maps(user); if (ret < 0) return ret; - map = kernel_get_module_map(module); + /* Get a symbol map */ + if (user) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); if (!map) { - pr_err("Failed to find %s map.\n", (module) ? : "kernel"); + pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; } - return __show_available_funcs(map); -} - -static int available_user_funcs(const char *target) -{ - struct map *map; - int ret; - - ret = init_user_exec(); - if (ret < 0) - return ret; - - map = dso__new_map(target); - ret = __show_available_funcs(map); - dso__delete(map->dso); - map__delete(map); - return ret; -} -int show_available_funcs(const char *target, struct strfilter *_filter, - bool user) -{ - setup_pager(); + /* Load symbols with given filter */ available_func_filter = _filter; - - if (!user) - return available_kernel_funcs(target); - - return available_user_funcs(target); -} - -/* - * uprobe_events only accepts address: - * Convert function and any offset to address - */ -static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec) -{ - struct perf_probe_point *pp = &pev->point; - struct symbol *sym; - struct map *map = NULL; - char *function = NULL; - int ret = -EINVAL; - unsigned long long vaddr = 0; - - if (!pp->function) { - pr_warning("No function specified for uprobes"); - goto out; - } - - function = strdup(pp->function); - if (!function) { - pr_warning("Failed to allocate memory by strdup.\n"); - ret = -ENOMEM; - goto out; - } - - map = dso__new_map(exec); - if (!map) { - pr_warning("Cannot find appropriate DSO for %s.\n", exec); - goto out; - } - available_func_filter = strfilter__new(function, NULL); if (map__load(map, filter_available_functions)) { - pr_err("Failed to load map.\n"); - goto out; - } - - sym = map__find_symbol_by_name(map, function, NULL); - if (!sym) { - pr_warning("Cannot find %s in DSO %s\n", function, exec); - goto out; - } - - if (map->start > sym->start) - vaddr = map->start; - vaddr += sym->start + pp->offset + map->pgoff; - pp->offset = 0; - - if (!pev->event) { - pev->event = function; - function = NULL; - } - if (!pev->group) { - char *ptr1, *ptr2, *exec_copy; - - pev->group = zalloc(sizeof(char *) * 64); - exec_copy = strdup(exec); - if (!exec_copy) { - ret = -ENOMEM; - pr_warning("Failed to copy exec string.\n"); - goto out; - } - - ptr1 = strdup(basename(exec_copy)); - if (ptr1) { - ptr2 = strpbrk(ptr1, "-._"); - if (ptr2) - *ptr2 = '\0'; - e_snprintf(pev->group, 64, "%s_%s", PERFPROBE_GROUP, - ptr1); - free(ptr1); - } - free(exec_copy); - } - free(pp->function); - pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS); - if (!pp->function) { - ret = -ENOMEM; - pr_warning("Failed to allocate memory by zalloc.\n"); - goto out; + pr_err("Failed to load symbols in %s\n", (target) ? : "kernel"); + goto end; } - e_snprintf(pp->function, MAX_PROBE_ARGS, "0x%llx", vaddr); - ret = 0; + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); -out: - if (map) { + /* Show all (filtered) symbols */ + setup_pager(); + dso__fprintf_symbols_by_name(map->dso, map->type, stdout); +end: + if (user) { dso__delete(map->dso); map__delete(map); } - if (function) - free(function); + exit_symbol_maps(); + return ret; } + diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index fcaf7273e85a..776c9347a3b6 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -2,6 +2,7 @@ #define _PROBE_EVENT_H #include <stdbool.h> +#include "intlist.h" #include "strlist.h" #include "strfilter.h" @@ -76,13 +77,6 @@ struct perf_probe_event { struct perf_probe_arg *args; /* Arguments */ }; - -/* Line number container */ -struct line_node { - struct list_head list; - int line; -}; - /* Line range */ struct line_range { char *file; /* File name */ @@ -92,7 +86,7 @@ struct line_range { int offset; /* Start line offset */ char *path; /* Real path name */ char *comp_dir; /* Compile directory */ - struct list_head line_list; /* Visible lines */ + struct intlist *line_list; /* Visible lines */ }; /* List of variables */ @@ -124,7 +118,7 @@ extern int parse_line_range_desc(const char *cmd, struct line_range *lr); extern void line_range__clear(struct line_range *lr); /* Initialize line range */ -extern void line_range__init(struct line_range *lr); +extern int line_range__init(struct line_range *lr); /* Internal use: Return kernel/module path */ extern const char *kernel_get_module_path(const char *module); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 061edb162b5b..df0238654698 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -34,7 +34,9 @@ #include <linux/bitops.h> #include "event.h" +#include "dso.h" #include "debug.h" +#include "intlist.h" #include "util.h" #include "symbol.h" #include "probe-finder.h" @@ -42,65 +44,6 @@ /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 -/* Line number list operations */ - -/* Add a line to line number list */ -static int line_list__add_line(struct list_head *head, int line) -{ - struct line_node *ln; - struct list_head *p; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry_reverse(ln, head, list) { - if (ln->line < line) { - p = &ln->list; - goto found; - } else if (ln->line == line) /* Already exist */ - return 1; - } - /* List is empty, or the smallest entry */ - p = head; -found: - pr_debug("line list: add a line %u\n", line); - ln = zalloc(sizeof(struct line_node)); - if (ln == NULL) - return -ENOMEM; - ln->line = line; - INIT_LIST_HEAD(&ln->list); - list_add(&ln->list, p); - return 0; -} - -/* Check if the line in line number list */ -static int line_list__has_line(struct list_head *head, int line) -{ - struct line_node *ln; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry(ln, head, list) - if (ln->line == line) - return 1; - - return 0; -} - -/* Init line number list */ -static void line_list__init(struct list_head *head) -{ - INIT_LIST_HEAD(head); -} - -/* Free line number list */ -static void line_list__free(struct list_head *head) -{ - struct line_node *ln; - while (!list_empty(head)) { - ln = list_first_entry(head, struct line_node, list); - list_del(&ln->list); - free(ln); - } -} - /* Dwarf FL wrappers */ static char *debuginfo_path; /* Currently dummy */ @@ -147,80 +90,7 @@ error: return -ENOENT; } -#if _ELFUTILS_PREREQ(0, 148) -/* This method is buggy if elfutils is older than 0.148 */ -static int __linux_kernel_find_elf(Dwfl_Module *mod, - void **userdata, - const char *module_name, - Dwarf_Addr base, - char **file_name, Elf **elfp) -{ - int fd; - const char *path = kernel_get_module_path(module_name); - - pr_debug2("Use file %s for %s\n", path, module_name); - if (path) { - fd = open(path, O_RDONLY); - if (fd >= 0) { - *file_name = strdup(path); - return fd; - } - } - /* If failed, try to call standard method */ - return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base, - file_name, elfp); -} - -static const Dwfl_Callbacks kernel_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, - .debuginfo_path = &debuginfo_path, - - .find_elf = __linux_kernel_find_elf, - .section_address = dwfl_linux_kernel_module_section_address, -}; - -/* Get a Dwarf from live kernel image */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, - Dwarf_Addr addr) -{ - dbg->dwfl = dwfl_begin(&kernel_callbacks); - if (!dbg->dwfl) - return -EINVAL; - - /* Load the kernel dwarves: Don't care the result here */ - dwfl_linux_kernel_report_kernel(dbg->dwfl); - dwfl_linux_kernel_report_modules(dbg->dwfl); - - dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias); - /* Here, check whether we could get a real dwarf */ - if (!dbg->dbg) { - pr_debug("Failed to find kernel dwarf at %lx\n", - (unsigned long)addr); - dwfl_end(dbg->dwfl); - memset(dbg, 0, sizeof(*dbg)); - return -ENOENT; - } - - return 0; -} -#else -/* With older elfutils, this just support kernel module... */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, - Dwarf_Addr addr __maybe_unused) -{ - const char *path = kernel_get_module_path("kernel"); - - if (!path) { - pr_err("Failed to find vmlinux path\n"); - return -ENOENT; - } - - pr_debug2("Use file %s for debuginfo\n", path); - return debuginfo__init_offline_dwarf(dbg, path); -} -#endif - -struct debuginfo *debuginfo__new(const char *path) +static struct debuginfo *__debuginfo__new(const char *path) { struct debuginfo *dbg = zalloc(sizeof(*dbg)); if (!dbg) @@ -228,21 +98,44 @@ struct debuginfo *debuginfo__new(const char *path) if (debuginfo__init_offline_dwarf(dbg, path) < 0) zfree(&dbg); - + if (dbg) + pr_debug("Open Debuginfo file: %s\n", path); return dbg; } -struct debuginfo *debuginfo__new_online_kernel(unsigned long addr) -{ - struct debuginfo *dbg = zalloc(sizeof(*dbg)); +enum dso_binary_type distro_dwarf_types[] = { + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__NOT_FOUND, +}; - if (!dbg) - return NULL; +struct debuginfo *debuginfo__new(const char *path) +{ + enum dso_binary_type *type; + char buf[PATH_MAX], nil = '\0'; + struct dso *dso; + struct debuginfo *dinfo = NULL; + + /* Try to open distro debuginfo files */ + dso = dso__new(path); + if (!dso) + goto out; - if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) - zfree(&dbg); + for (type = distro_dwarf_types; + !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; + type++) { + if (dso__read_binary_type_filename(dso, *type, &nil, + buf, PATH_MAX) < 0) + continue; + dinfo = __debuginfo__new(buf); + } + dso__delete(dso); - return dbg; +out: + /* if failed to open all distro debuginfo, open given binary */ + return dinfo ? : __debuginfo__new(path); } void debuginfo__delete(struct debuginfo *dbg) @@ -880,7 +773,7 @@ static int find_probe_point_by_line(struct probe_finder *pf) } /* Find lines which match lazy pattern */ -static int find_lazy_match_lines(struct list_head *head, +static int find_lazy_match_lines(struct intlist *list, const char *fname, const char *pat) { FILE *fp; @@ -901,7 +794,7 @@ static int find_lazy_match_lines(struct list_head *head, line[len - 1] = '\0'; if (strlazymatch(line, pat)) { - line_list__add_line(head, linenum); + intlist__add(list, linenum); count++; } linenum++; @@ -924,7 +817,7 @@ static int probe_point_lazy_walker(const char *fname, int lineno, Dwarf_Die *sc_die, die_mem; int ret; - if (!line_list__has_line(&pf->lcache, lineno) || + if (!intlist__has_entry(pf->lcache, lineno) || strtailcmp(fname, pf->fname) != 0) return 0; @@ -952,9 +845,9 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { int ret = 0; - if (list_empty(&pf->lcache)) { + if (intlist__empty(pf->lcache)) { /* Matching lazy line pattern */ - ret = find_lazy_match_lines(&pf->lcache, pf->fname, + ret = find_lazy_match_lines(pf->lcache, pf->fname, pf->pev->point.lazy_line); if (ret <= 0) return ret; @@ -1096,7 +989,9 @@ static int debuginfo__find_probes(struct debuginfo *dbg, #endif off = 0; - line_list__init(&pf->lcache); + pf->lcache = intlist__new(NULL); + if (!pf->lcache) + return -ENOMEM; /* Fastpath: lookup by function name from .debug_pubnames section */ if (pp->function) { @@ -1149,7 +1044,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg, } found: - line_list__free(&pf->lcache); + intlist__delete(pf->lcache); + pf->lcache = NULL; return ret; } @@ -1537,7 +1433,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, if (lr->path == NULL) return -ENOMEM; } - return line_list__add_line(&lr->line_list, lineno); + return intlist__add(lr->line_list, lineno); } static int line_range_walk_cb(const char *fname, int lineno, @@ -1565,7 +1461,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) /* Update status */ if (ret >= 0) - if (!list_empty(&lf->lr->line_list)) + if (!intlist__empty(lf->lr->line_list)) ret = lf->found = 1; else ret = 0; /* Lines are not found */ diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index ffc33cdd25cc..92590b2c7e1c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -3,6 +3,7 @@ #include <stdbool.h> #include "util.h" +#include "intlist.h" #include "probe-event.h" #define MAX_PROBE_BUFFER 1024 @@ -29,8 +30,8 @@ struct debuginfo { Dwarf_Addr bias; }; +/* This also tries to open distro debuginfo */ extern struct debuginfo *debuginfo__new(const char *path); -extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr); extern void debuginfo__delete(struct debuginfo *dbg); /* Find probe_trace_events specified by perf_probe_event from debuginfo */ @@ -66,7 +67,7 @@ struct probe_finder { const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ Dwarf_Die sp_die; - struct list_head lcache; /* Line cache for lazy match */ + struct intlist *lcache; /* Line cache for lazy match */ /* For variable searching */ #if _ELFUTILS_PREREQ(0, 142) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 595bfc73d2ed..16a475a7d492 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,6 +17,6 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -util/fs.c +../lib/api/fs/fs.c util/trace-event.c ../../lib/rbtree.c diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 373762501dad..049e0a09ccd3 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -2,7 +2,7 @@ #include "evsel.h" #include "cpumap.h" #include "parse-events.h" -#include "fs.h" +#include <api/fs/fs.h> #include "util.h" typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5da6ce74c676..55960f22233c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -702,11 +702,12 @@ static void regs_dump__printf(u64 mask, u64 *regs) } } -static void regs_user__printf(struct perf_sample *sample, u64 mask) +static void regs_user__printf(struct perf_sample *sample) { struct regs_dump *user_regs = &sample->user_regs; if (user_regs->regs) { + u64 mask = user_regs->mask; printf("... user regs: mask 0x%" PRIx64 "\n", mask); regs_dump__printf(mask, user_regs->regs); } @@ -793,7 +794,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (!dump_trace) return; - printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", + printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); @@ -806,7 +807,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample, evsel->attr.sample_regs_user); + regs_user__printf(sample); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 3e9f336740fa..3b7dbf51d4a9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -151,15 +151,15 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, gelf_getshdr(sec, shp); str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); - if (!strcmp(name, str)) { + if (str && !strcmp(name, str)) { if (idx) *idx = cnt; - break; + return sec; } ++cnt; } - return sec; + return NULL; } #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ @@ -506,6 +506,8 @@ int filename__read_debuglink(const char *filename, char *debuglink, /* the start of this section is a zero-terminated string */ strncpy(debuglink, data->d_buf, size); + err = 0; + out_elf_end: elf_end(elf); out_close: diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e89afc097d8a..95e249779931 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -410,7 +410,7 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { return symbols__first(&dso->symbols[type]); } @@ -1251,6 +1251,46 @@ out_failure: return -1; } +static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, + enum dso_binary_type type) +{ + switch (type) { + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + return !kmod && dso->kernel == DSO_TYPE_USER; + + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__KCORE: + return dso->kernel == DSO_TYPE_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__GUEST_KCORE: + return dso->kernel == DSO_TYPE_GUEST_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + /* + * kernel modules know their symtab type - it's set when + * creating a module dso in machine__new_module(). + */ + return kmod && dso->symtab_type == type; + + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + return true; + + case DSO_BINARY_TYPE__NOT_FOUND: + default: + return false; + } +} + int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { char *name; @@ -1261,6 +1301,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) int ss_pos = 0; struct symsrc ss_[2]; struct symsrc *syms_ss = NULL, *runtime_ss = NULL; + bool kmod; dso__set_loaded(dso, map->type); @@ -1301,7 +1342,11 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!name) return -1; - /* Iterate over candidate debug images. + kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + + /* + * Iterate over candidate debug images. * Keep track of "interesting" ones (those which have a symtab, dynsym, * and/or opd section) for processing. */ @@ -1311,6 +1356,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) enum dso_binary_type symtab_type = binary_type_symtab[i]; + if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type)) + continue; + if (dso__read_binary_type_filename(dso, symtab_type, root_dir, name, PATH_MAX)) continue; @@ -1353,15 +1401,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss) { - int km; - - km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; - ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km); - } else { + if (syms_ss) + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod); + else ret = -1; - } if (ret > 0) { int nr_plt; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fffe2888a1c7..501e4e722e8e 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -79,6 +79,17 @@ struct symbol { void symbol__delete(struct symbol *sym); void symbols__delete(struct rb_root *symbols); +/* symbols__for_each_entry - iterate over symbols (rb_root) + * + * @symbols: the rb_root of symbols + * @pos: the 'struct symbol *' to use as a loop cursor + * @nd: the 'struct rb_node *' to use as a temporary storage + */ +#define symbols__for_each_entry(symbols, pos, nd) \ + for (nd = rb_first(symbols); \ + nd && (pos = rb_entry(nd, struct symbol, rb_node)); \ + nd = rb_next(nd)) + static inline size_t symbol__size(const struct symbol *sym) { return sym->end - sym->start + 1; @@ -175,7 +186,7 @@ struct addr_location { struct symbol *sym; u64 addr; char level; - bool filtered; + u8 filtered; u8 cpumode; s32 cpu; }; @@ -223,7 +234,6 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0358882c8910..3ce0498bdae6 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -142,3 +142,24 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) return 0; } + +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al) +{ + size_t i; + const u8 const cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL + }; + + for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { + thread__find_addr_location(thread, machine, cpumodes[i], type, + addr, al); + if (al->map) + break; + } +} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 5b856bf942e1..9b29f085aede 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -44,12 +44,6 @@ void thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -static inline struct map *thread__find_map(struct thread *thread, - enum map_type type, u64 addr) -{ - return thread ? map_groups__find(&thread->mg, type, addr) : NULL; -} - void thread__find_addr_map(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); @@ -58,6 +52,11 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al); + static inline void *thread__priv(struct thread *thread) { return thread->priv; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index e0d6d07f6848..c36636fd825b 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -126,6 +126,7 @@ void event_format__print(struct event_format *event, trace_seq_init(&s); pevent_event_info(&s, event, &record); trace_seq_do_printf(&s); + trace_seq_destroy(&s); } void parse_proc_kallsyms(struct pevent *pevent, diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c new file mode 100644 index 000000000000..67db73ec3dab --- /dev/null +++ b/tools/perf/util/unwind-libdw.c @@ -0,0 +1,210 @@ +#include <linux/compiler.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <inttypes.h> +#include <errno.h> +#include "unwind.h" +#include "unwind-libdw.h" +#include "machine.h" +#include "thread.h" +#include "types.h" +#include "event.h" +#include "perf_regs.h" + +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .find_debuginfo = dwfl_standard_find_debuginfo, + .debuginfo_path = &debuginfo_path, + .section_address = dwfl_offline_section_address, +}; + +static int __report_module(struct addr_location *al, u64 ip, + struct unwind_info *ui) +{ + Dwfl_Module *mod; + struct dso *dso = NULL; + + thread__find_addr_location(ui->thread, ui->machine, + PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, al); + + if (al->map) + dso = al->map->dso; + + if (!dso) + return 0; + + mod = dwfl_addrmodule(ui->dwfl, ip); + if (!mod) + mod = dwfl_report_elf(ui->dwfl, dso->short_name, + dso->long_name, -1, al->map->start, + false); + + return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; +} + +static int report_module(u64 ip, struct unwind_info *ui) +{ + struct addr_location al; + + return __report_module(&al, ip, ui); +} + +static int entry(u64 ip, struct unwind_info *ui) + +{ + struct unwind_entry e; + struct addr_location al; + + if (__report_module(&al, ip, ui)) + return -1; + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return ui->cb(&e, ui->arg); +} + +static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp) +{ + /* We want only single thread to be processed. */ + if (*thread_argp != NULL) + return 0; + + *thread_argp = arg; + return dwfl_pid(dwfl); +} + +static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, + Dwarf_Word *data) +{ + struct addr_location al; + ssize_t size; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, addr, &al); + if (!al.map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!al.map->dso) + return -1; + + size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result, + void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + u64 start, end; + int offset; + int ret; + + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); + if (ret) + return false; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(Dwarf_Word) < addr) + return false; + + if (addr < start || addr + sizeof(Dwarf_Word) > end) { + ret = access_dso_mem(ui, addr, result); + if (ret) { + pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + addr, start, end); + return false; + } + return true; + } + + offset = addr - start; + *result = *(Dwarf_Word *)&stack->data[offset]; + pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n", + addr, (unsigned long)*result, offset); + return true; +} + +static const Dwfl_Thread_Callbacks callbacks = { + .next_thread = next_thread, + .memory_read = memory_read, + .set_initial_registers = libdw__arch_set_initial_registers, +}; + +static int +frame_callback(Dwfl_Frame *state, void *arg) +{ + struct unwind_info *ui = arg; + Dwarf_Addr pc; + + if (!dwfl_frame_pc(state, &pc, NULL)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + return entry(pc, ui) || !(--ui->max_stack) ? + DWARF_CB_ABORT : DWARF_CB_OK; +} + +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, struct thread *thread, + struct perf_sample *data, + int max_stack) +{ + struct unwind_info ui = { + .sample = data, + .thread = thread, + .machine = machine, + .cb = cb, + .arg = arg, + .max_stack = max_stack, + }; + Dwarf_Word ip; + int err = -EINVAL; + + if (!data->user_regs.regs) + return -EINVAL; + + ui.dwfl = dwfl_begin(&offline_callbacks); + if (!ui.dwfl) + goto out; + + err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); + if (err) + goto out; + + err = report_module(ip, &ui); + if (err) + goto out; + + if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui)) + goto out; + + err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui); + + if (err && !ui.max_stack) + err = 0; + + out: + if (err) + pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1)); + + dwfl_end(ui.dwfl); + return 0; +} diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h new file mode 100644 index 000000000000..417a1426f3ad --- /dev/null +++ b/tools/perf/util/unwind-libdw.h @@ -0,0 +1,21 @@ +#ifndef __PERF_UNWIND_LIBDW_H +#define __PERF_UNWIND_LIBDW_H + +#include <elfutils/libdwfl.h> +#include "event.h" +#include "thread.h" +#include "unwind.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); + +struct unwind_info { + Dwfl *dwfl; + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; + unwind_entry_cb_t cb; + void *arg; + int max_stack; +}; + +#endif /* __PERF_UNWIND_LIBDW_H */ diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind-libunwind.c index 742f23bf35ff..bd5768d74f01 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -86,7 +86,6 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; - u64 sample_uregs; }; #define dw_read(ptr, type, end) ({ \ @@ -391,30 +390,13 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, return !(size == sizeof(*data)); } -static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id, - u64 sample_regs) -{ - int i, idx = 0; - - if (!(sample_regs & (1 << id))) - return -EINVAL; - - for (i = 0; i < id; i++) { - if (sample_regs & (1 << i)) - idx++; - } - - *valp = regs->regs[idx]; - return 0; -} - static int access_mem(unw_addr_space_t __maybe_unused as, unw_word_t addr, unw_word_t *valp, int __write, void *arg) { struct unwind_info *ui = arg; struct stack_dump *stack = &ui->sample->user_stack; - unw_word_t start, end; + u64 start, end; int offset; int ret; @@ -424,8 +406,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as, return 0; } - ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP, - ui->sample_uregs); + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); if (ret) return ret; @@ -438,8 +419,9 @@ static int access_mem(unw_addr_space_t __maybe_unused as, if (addr < start || addr + sizeof(unw_word_t) >= end) { ret = access_dso_mem(ui, addr, valp); if (ret) { - pr_debug("unwind: access_mem %p not inside range %p-%p\n", - (void *)addr, (void *)start, (void *)end); + pr_debug("unwind: access_mem %p not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + (void *) addr, start, end); *valp = 0; return ret; } @@ -448,8 +430,8 @@ static int access_mem(unw_addr_space_t __maybe_unused as, offset = addr - start; *valp = *(unw_word_t *)&stack->data[offset]; - pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n", - (void *)addr, (unsigned long)*valp, offset); + pr_debug("unwind: access_mem addr %p val %lx, offset %d\n", + (void *) addr, (unsigned long)*valp, offset); return 0; } @@ -459,6 +441,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, { struct unwind_info *ui = arg; int id, ret; + u64 val; /* Don't support write, I suspect we don't need it. */ if (__write) { @@ -471,16 +454,17 @@ static int access_reg(unw_addr_space_t __maybe_unused as, return 0; } - id = unwind__arch_reg_id(regnum); + id = libunwind__arch_reg_id(regnum); if (id < 0) return -EINVAL; - ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs); + ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { pr_err("unwind: can't read reg %d\n", regnum); return ret; } + *valp = (unw_word_t) val; pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); return 0; } @@ -563,7 +547,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, unw_word_t ip; unw_get_reg(&c, UNW_REG_IP, &ip); - ret = entry(ip, ui->thread, ui->machine, cb, arg); + ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; } unw_destroy_addr_space(addr_space); @@ -572,13 +556,11 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, - u64 sample_uregs, struct perf_sample *data, - int max_stack) + struct perf_sample *data, int max_stack) { - unw_word_t ip; + u64 ip; struct unwind_info ui = { .sample = data, - .sample_uregs = sample_uregs, .thread = thread, .machine = machine, }; @@ -587,7 +569,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (!data->user_regs.regs) return -EINVAL; - ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs); + ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); if (ret) return ret; @@ -595,5 +577,5 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (ret) return -ENOMEM; - return get_entries(&ui, cb, arg, max_stack); + return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index d5966f49e22c..b031316f221a 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -13,24 +13,25 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, - u64 sample_uregs, struct perf_sample *data, int max_stack); -int unwind__arch_reg_id(int regnum); +/* libunwind specific */ +#ifdef HAVE_LIBUNWIND_SUPPORT +int libunwind__arch_reg_id(int regnum); +#endif #else static inline int unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct machine *machine __maybe_unused, struct thread *thread __maybe_unused, - u64 sample_uregs __maybe_unused, struct perf_sample *data __maybe_unused, int max_stack __maybe_unused) { return 0; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 42ad667bb317..9f66549562bd 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,6 +1,6 @@ #include "../perf.h" #include "util.h" -#include "fs.h" +#include <api/fs/fs.h> #include <sys/mman.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index d66418237d21..aa290c0de6f5 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -201,6 +201,7 @@ int main(int argc, char **argv) msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666); if (msgque.msq_id == -1) { + err = -errno; printf("Can't create queue\n"); goto err_out; } diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 587561d7c035..9b17e810ddc3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -96,6 +96,7 @@ identify_qemu () { echo qemu-system-ppc64 else echo Cannot figure out what qemu command to use! 1>&2 + echo file $1 output: $u # Usually this will be one of /usr/bin/qemu-system-* # Use RCU_QEMU_CMD environment variable or appropriate # argument to top-level script. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh new file mode 100755 index 000000000000..829186e19eb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# +# Analyze a given results directory for locktorture progress. +# +# Usage: sh kvm-recheck-lock.sh resdir +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2014 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +i="$1" +if test -d $i +then + : +else + echo Unreadable results directory: $i + exit 1 +fi + +configfile=`echo $i | sed -e 's/^.*\///'` +ncs=`grep "Writes: Total:" $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* Total: //' -e 's/ .*$//'` +if test -z "$ncs" +then + echo $configfile +else + title="$configfile ------- $ncs acquisitions/releases" + dur=`sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null` + if test -z "$dur" + then + : + else + ncsps=`awk -v ncs=$ncs -v dur=$dur ' + BEGIN { print ncs / dur }' < /dev/null` + title="$title ($ncsps per second)" + fi + echo $title +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh new file mode 100755 index 000000000000..d75b1dc5ae53 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# +# Analyze a given results directory for rcutorture progress. +# +# Usage: sh kvm-recheck-rcu.sh resdir +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2014 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +i="$1" +if test -d $i +then + : +else + echo Unreadable results directory: $i + exit 1 +fi + +configfile=`echo $i | sed -e 's/^.*\///'` +ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'` +if test -z "$ngps" +then + echo $configfile +else + title="$configfile ------- $ngps grace periods" + dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null` + if test -z "$dur" + then + : + else + ngpsps=`awk -v ngps=$ngps -v dur=$dur ' + BEGIN { print ngps / dur }' < /dev/null` + title="$title ($ngpsps per second)" + fi + echo $title +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index baef09f3469b..a44daaa259a9 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -1,6 +1,6 @@ #!/bin/bash # -# Given the results directories for previous KVM runs of rcutorture, +# Given the results directories for previous KVM-based torture runs, # check the build and console output for errors. Given a directory # containing results directories, this recursively checks them all. # @@ -27,11 +27,18 @@ PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH for rd in "$@" do + firsttime=1 dirs=`find $rd -name Make.defconfig.out -print | sort | sed -e 's,/[^/]*$,,' | sort -u` for i in $dirs do - configfile=`echo $i | sed -e 's/^.*\///'` - echo $configfile + if test -n "$firsttime" + then + firsttime="" + resdir=`echo $i | sed -e 's,/$,,' -e 's,/[^/]*$,,'` + head -1 $resdir/log + fi + TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + kvm-recheck-${TORTURE_SUITE}.sh $i configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile parse-rcutorture.sh $i/console.log $configfile diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 151b23788935..94b28bb37d36 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -6,15 +6,15 @@ # Execute this in the source tree. Do not run it as a background task # because qemu does not seem to like that much. # -# Usage: sh kvm-test-1-rcu.sh config builddir resdir minutes qemu-args bootargs +# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args # -# qemu-args defaults to "" -- you will want "-nographic" if running headless. -# bootargs defaults to "root=/dev/sda noapic selinux=0 console=ttyS0" -# "initcall_debug debug rcutorture.stat_interval=15" -# "rcutorture.shutdown_secs=$((minutes * 60))" -# "rcutorture.rcutorture_runnable=1" +# qemu-args defaults to "-nographic", along with arguments specifying the +# number of CPUs and other options generated from +# the underlying CPU architecture. +# boot_args defaults to value returned by the per_version_boot_params +# shell function. # -# Anything you specify for either qemu-args or bootargs is appended to +# Anything you specify for either qemu-args or boot_args is appended to # the default values. The "-smp" value is deduced from the contents of # the config fragment. # @@ -40,32 +40,34 @@ grace=120 -T=/tmp/kvm-test-1-rcu.sh.$$ +T=/tmp/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 . $KVM/bin/functions.sh . $KVPATH/ver_functions.sh config_template=${1} +config_dir=`echo $config_template | sed -e 's,/[^/]*$,,'` title=`echo $config_template | sed -e 's/^.*\///'` builddir=${2} if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir" then - echo "kvm-test-1-rcu.sh :$builddir: Not a writable directory, cannot build into it" + echo "kvm-test-1-run.sh :$builddir: Not a writable directory, cannot build into it" exit 1 fi resdir=${3} if test -z "$resdir" -o ! -d "$resdir" -o ! -w "$resdir" then - echo "kvm-test-1-rcu.sh :$resdir: Not a writable directory, cannot build into it" + echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it" exit 1 fi cp $config_template $resdir/ConfigFragment echo ' ---' `date`: Starting build echo ' ---' Kconfig fragment at: $config_template >> $resdir/log -cat << '___EOF___' >> $T -CONFIG_RCU_TORTURE_TEST=y -___EOF___ +if test -r "$config_dir/CFcommon" +then + cat < $config_dir/CFcommon >> $T +fi # Optimizations below this point # CONFIG_USB=n # CONFIG_SECURITY=n @@ -96,11 +98,23 @@ then cp $builddir/.config $resdir cp $builddir/arch/x86/boot/bzImage $resdir parse-build.sh $resdir/Make.out $title + if test -f $builddir.wait + then + mv $builddir.wait $builddir.ready + fi else cp $builddir/Make*.out $resdir echo Build failed, not running KVM, see $resdir. + if test -f $builddir.wait + then + mv $builddir.wait $builddir.ready + fi exit 1 fi +while test -f $builddir.ready +do + sleep 1 +done minutes=$4 seconds=$(($minutes * 60)) qemu_args=$5 @@ -111,9 +125,10 @@ kstarttime=`awk 'BEGIN { print systime() }' < /dev/null` echo ' ---' `date`: Starting kernel # Determine the appropriate flavor of qemu command. -QEMU="`identify_qemu $builddir/vmlinux.o`" +QEMU="`identify_qemu $builddir/vmlinux`" # Generate -smp qemu argument. +qemu_args="-nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` vcpus=`identify_qemu_vcpus` if test $cpu_count -gt $vcpus @@ -133,12 +148,8 @@ qemu_append="`identify_qemu_append "$QEMU"`" # Pull in Kconfig-fragment boot parameters boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" -# Generate CPU-hotplug boot parameters -boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`" -# Generate rcu_barrier() boot parameter -boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`" -# Pull in standard rcutorture boot arguments -boot_args="$boot_args rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1" +# Generate kernel-version-specific boot parameters +boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`" echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$RCU_BUILDONLY" @@ -188,5 +199,5 @@ then fi cp $builddir/console.log $resdir -parse-rcutorture.sh $resdir/console.log $title +parse-${TORTURE_SUITE}torture.sh $resdir/console.log $title parse-console.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 1b7923bf6a70..5a78cbf55f06 100644 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -30,14 +30,21 @@ scriptname=$0 args="$*" +T=/tmp/kvm.sh.$$ +trap 'rm -rf $T' 0 +mkdir $T + dur=30 +dryrun="" KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM PATH=${KVM}/bin:$PATH; export PATH builddir="${KVM}/b1" RCU_INITRD="$KVM/initrd"; export RCU_INITRD RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG +TORTURE_SUITE=rcu resdir="" configs="" +cpus=0 ds=`date +%Y.%m.%d-%H:%M:%S` kversion="" @@ -49,7 +56,9 @@ usage () { echo " --builddir absolute-pathname" echo " --buildonly" echo " --configs \"config-file list\"" + echo " --cpus N" echo " --datestamp string" + echo " --dryrun sched|script" echo " --duration minutes" echo " --interactive" echo " --kmake-arg kernel-make-arguments" @@ -58,8 +67,9 @@ usage () { echo " --no-initrd" echo " --qemu-args qemu-system-..." echo " --qemu-cmd qemu-system-..." - echo " --results absolute-pathname" echo " --relbuilddir relative-pathname" + echo " --results absolute-pathname" + echo " --torture rcu" exit 1 } @@ -85,11 +95,21 @@ do configs="$2" shift ;; + --cpus) + checkarg --cpus "(number)" "$#" "$2" '^[0-9]*$' '^--' + cpus=$2 + shift + ;; --datestamp) checkarg --datestamp "(relative pathname)" "$#" "$2" '^[^/]*$' '^--' ds=$2 shift ;; + --dryrun) + checkarg --dryrun "sched|script" $# "$2" 'sched\|script' '^--' + dryrun=$2 + shift + ;; --duration) checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error' dur=$2 @@ -138,6 +158,11 @@ do resdir=$2 shift ;; + --torture) + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--' + TORTURE_SUITE=$2 + shift + ;; *) echo Unknown argument $1 usage @@ -146,7 +171,7 @@ do shift done -CONFIGFRAG=${KVM}/configs; export CONFIGFRAG +CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG KVPATH=${CONFIGFRAG}/$kversion; export KVPATH if test -z "$configs" @@ -157,54 +182,231 @@ fi if test -z "$resdir" then resdir=$KVM/res - if ! test -e $resdir - then - mkdir $resdir || : - fi -else +fi + +if test "$dryrun" = "" +then if ! test -e $resdir then mkdir -p "$resdir" || : fi -fi -mkdir $resdir/$ds -touch $resdir/$ds/log -echo $scriptname $args >> $resdir/$ds/log + mkdir $resdir/$ds -pwd > $resdir/$ds/testid.txt -if test -d .git -then - git status >> $resdir/$ds/testid.txt - git rev-parse HEAD >> $resdir/$ds/testid.txt -fi -builddir=$KVM/b1 -if ! test -e $builddir -then - mkdir $builddir || : + # Be noisy only if running the script. + echo Results directory: $resdir/$ds + echo $scriptname $args + + touch $resdir/$ds/log + echo $scriptname $args >> $resdir/$ds/log + echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE + + pwd > $resdir/$ds/testid.txt + if test -d .git + then + git status >> $resdir/$ds/testid.txt + git rev-parse HEAD >> $resdir/$ds/testid.txt + fi fi +# Create a file of test-name/#cpus pairs, sorted by decreasing #cpus. +touch $T/cfgcpu for CF in $configs do - # Running TREE01 multiple times creates TREE01, TREE01.2, TREE01.3, ... - rd=$resdir/$ds/$CF - if test -d "${rd}" + if test -f "$CONFIGFRAG/$kversion/$CF" then - n="`ls -d "${rd}"* | grep '\.[0-9]\+$' | - sed -e 's/^.*\.\([0-9]\+\)/\1/' | - sort -k1n | tail -1`" - if test -z "$n" - then - rd="${rd}.2" - else - n="`expr $n + 1`" - rd="${rd}.${n}" - fi + echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu + else + echo "The --configs file $CF does not exist, terminating." + exit 1 fi - mkdir "${rd}" - echo Results directory: $rd - kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS" done +sort -k2nr $T/cfgcpu > $T/cfgcpu.sort + +# Use a greedy bin-packing algorithm, sorting the list accordingly. +awk < $T/cfgcpu.sort > $T/cfgcpu.pack -v ncpus=$cpus ' +BEGIN { + njobs = 0; +} + +{ + # Read file of tests and corresponding required numbers of CPUs. + cf[njobs] = $1; + cpus[njobs] = $2; + njobs++; +} + +END { + alldone = 0; + batch = 0; + nc = -1; + + # Each pass through the following loop creates on test batch + # that can be executed concurrently given ncpus. Note that a + # given test that requires more than the available CPUs will run in + # their own batch. Such tests just have to make do with what + # is available. + while (nc != ncpus) { + batch++; + nc = ncpus; + + # Each pass through the following loop considers one + # test for inclusion in the current batch. + for (i = 0; i < njobs; i++) { + if (done[i]) + continue; # Already part of a batch. + if (nc >= cpus[i] || nc == ncpus) { + + # This test fits into the current batch. + done[i] = batch; + nc -= cpus[i]; + if (nc <= 0) + break; # Too-big test in its own batch. + } + } + } + + # Dump out the tests in batch order. + for (b = 1; b <= batch; b++) + for (i = 0; i < njobs; i++) + if (done[i] == b) + print cf[i], cpus[i]; +}' + +# Generate a script to execute the tests in appropriate batches. +cat << ___EOF___ > $T/script +TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE +___EOF___ +awk < $T/cfgcpu.pack \ + -v CONFIGDIR="$CONFIGFRAG/$kversion/" \ + -v KVM="$KVM" \ + -v ncpus=$cpus \ + -v rd=$resdir/$ds/ \ + -v dur=$dur \ + -v RCU_QEMU_ARG=$RCU_QEMU_ARG \ + -v RCU_BOOTARGS=$RCU_BOOTARGS \ +'BEGIN { + i = 0; +} + +{ + cf[i] = $1; + cpus[i] = $2; + i++; +} + +# Dump out the scripting required to run one test batch. +function dump(first, pastlast) +{ + print "echo ----Start batch: `date`"; + print "echo ----Start batch: `date` >> " rd "/log"; + jn=1 + for (j = first; j < pastlast; j++) { + builddir=KVM "/b" jn + cpusr[jn] = cpus[j]; + if (cfrep[cf[j]] == "") { + cfr[jn] = cf[j]; + cfrep[cf[j]] = 1; + } else { + cfrep[cf[j]]++; + cfr[jn] = cf[j] "." cfrep[cf[j]]; + } + if (cpusr[jn] > ncpus && ncpus != 0) + ovf = "(!)"; + else + ovf = ""; + print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date`"; + print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date` >> " rd "/log"; + print "rm -f " builddir ".*"; + print "touch " builddir ".wait"; + print "mkdir " builddir " > /dev/null 2>&1 || :"; + print "mkdir " rd cfr[jn] " || :"; + print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" RCU_QEMU_ARG "\" \"" RCU_BOOTARGS "\" > " rd cfr[jn] "/kvm-test-1-run.sh.out 2>&1 &" + print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date`"; + print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` >> " rd "/log"; + print "while test -f " builddir ".wait" + print "do" + print "\tsleep 1" + print "done" + print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date`"; + print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date` >> " rd "/log"; + jn++; + } + for (j = 1; j < jn; j++) { + builddir=KVM "/b" j + print "rm -f " builddir ".ready" + print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; + print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + } + print "wait" + print "echo ---- All kernel runs complete. `date`"; + print "echo ---- All kernel runs complete. `date` >> " rd "/log"; + for (j = 1; j < jn; j++) { + builddir=KVM "/b" j + print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results:"; + print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results: >> " rd "/log"; + print "cat " rd cfr[j] "/kvm-test-1-run.sh.out"; + print "cat " rd cfr[j] "/kvm-test-1-run.sh.out >> " rd "/log"; + } +} + +END { + njobs = i; + nc = ncpus; + first = 0; + + # Each pass through the following loop considers one test. + for (i = 0; i < njobs; i++) { + if (ncpus == 0) { + # Sequential test specified, each test its own batch. + dump(i, i + 1); + first = i; + } else if (nc < cpus[i] && i != 0) { + # Out of CPUs, dump out a batch. + dump(first, i); + first = i; + nc = ncpus; + } + # Account for the CPUs needed by the current test. + nc -= cpus[i]; + } + # Dump the last batch. + if (ncpus != 0) + dump(first, i); +}' >> $T/script + +if test "$dryrun" = script +then + # Dump out the script, but define the environment variables that + # it needs to run standalone. + echo CONFIGFRAG="$CONFIGFRAG; export CONFIGFRAG" + echo KVM="$KVM; export KVM" + echo KVPATH="$KVPATH; export KVPATH" + echo PATH="$PATH; export PATH" + echo RCU_BUILDONLY="$RCU_BUILDONLY; export RCU_BUILDONLY" + echo RCU_INITRD="$RCU_INITRD; export RCU_INITRD" + echo RCU_KMAKE_ARG="$RCU_KMAKE_ARG; export RCU_KMAKE_ARG" + echo RCU_QEMU_CMD="$RCU_QEMU_CMD; export RCU_QEMU_CMD" + echo RCU_QEMU_INTERACTIVE="$RCU_QEMU_INTERACTIVE; export RCU_QEMU_INTERACTIVE" + echo RCU_QEMU_MAC="$RCU_QEMU_MAC; export RCU_QEMU_MAC" + echo "mkdir -p "$resdir" || :" + echo "mkdir $resdir/$ds" + cat $T/script + exit 0 +elif test "$dryrun" = sched +then + # Extract the test run schedule from the script. + egrep 'start batch|Starting build\.' $T/script | + sed -e 's/:.*$//' -e 's/^echo //' + exit 0 +else + # Not a dryru, so run the script. + sh $T/script +fi + # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier +echo +echo echo " --- `date` Test summary:" +echo Results directory: $resdir/$ds kvm-recheck.sh $resdir/$ds diff --git a/tools/testing/selftests/rcutorture/configs/lock/BUSTED b/tools/testing/selftests/rcutorture/configs/lock/BUSTED new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/BUSTED @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot new file mode 100644 index 000000000000..6386c15e9770 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/BUSTED.boot @@ -0,0 +1 @@ +locktorture.torture_type=lock_busted diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST new file mode 100644 index 000000000000..a061b22d1892 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -0,0 +1 @@ +LOCK01 diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFcommon b/tools/testing/selftests/rcutorture/configs/lock/CFcommon new file mode 100644 index 000000000000..e372dc269254 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/CFcommon @@ -0,0 +1,2 @@ +CONFIG_LOCK_TORTURE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK01 b/tools/testing/selftests/rcutorture/configs/lock/LOCK01 new file mode 100644 index 000000000000..a9625e3d6cd9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK01 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=8 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh new file mode 100644 index 000000000000..9746ea1cd6c7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh @@ -0,0 +1,43 @@ +#!/bin/bash +# +# Kernel-version-dependent shell functions for the rest of the scripts. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2014 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +# locktorture_param_onoff bootparam-string config-file +# +# Adds onoff locktorture module parameters to kernels having it. +locktorture_param_onoff () { + if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" + then + echo CPU-hotplug kernel, adding locktorture onoff. 1>&2 + echo locktorture.onoff_interval=3 locktorture.onoff_holdoff=30 + fi +} + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `locktorture_param_onoff "$1" "$2"` \ + locktorture.stat_interval=15 \ + locktorture.shutdown_secs=$3 \ + locktorture.locktorture_runnable=1 \ + locktorture.verbose=1 +} diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED new file mode 100644 index 000000000000..48d8a245c7fa --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED @@ -0,0 +1,7 @@ +CONFIG_RCU_TRACE=n +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot new file mode 100644 index 000000000000..6804f9dcfc1b --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot @@ -0,0 +1 @@ +rcutorture.torture_type=rcu_busted diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index cd3d29cb0a47..cd3d29cb0a47 100644 --- a/tools/testing/selftests/rcutorture/configs/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon new file mode 100644 index 000000000000..d2d2a86139db --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_TORTURE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 10a0e27f4c75..9fbb41b9b314 100644 --- a/tools/testing/selftests/rcutorture/configs/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -1,8 +1,7 @@ CONFIG_RCU_TRACE=n CONFIG_SMP=y -CONFIG_NR_CPUS=8 +CONFIG_NR_CPUS=4 CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot index 238bfe3bd0cc..238bfe3bd0cc 100644 --- a/tools/testing/selftests/rcutorture/configs/SRCU-N.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P index 6650e00c6d91..4b6f272dba27 100644 --- a/tools/testing/selftests/rcutorture/configs/SRCU-P +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P @@ -5,4 +5,3 @@ CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot index 238bfe3bd0cc..238bfe3bd0cc 100644 --- a/tools/testing/selftests/rcutorture/configs/SRCU-P.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot diff --git a/tools/testing/selftests/rcutorture/configs/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 0c2823f21712..0a63e073a00c 100644 --- a/tools/testing/selftests/rcutorture/configs/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -10,4 +10,3 @@ CONFIG_RCU_TRACE=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_PREEMPT_COUNT=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index e5072d7528b6..f4feaee40776 100644 --- a/tools/testing/selftests/rcutorture/configs/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -10,4 +10,3 @@ CONFIG_RCU_TRACE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_PREEMPT_COUNT=y -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 141119a00044..9c827ec59a97 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -20,4 +20,3 @@ CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index 0fc8a3428938..0fc8a3428938 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot diff --git a/tools/testing/selftests/rcutorture/configs/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index 2d4d09608528..1a777b5f68b5 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -7,7 +7,7 @@ CONFIG_PREEMPT=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n -CONFIG_RCU_FAST_NO_HZ=n +CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=n CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n @@ -23,4 +23,3 @@ CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index a47de5be8a04..c1f111c1561b 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -20,4 +20,3 @@ CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=y CONFIG_RCU_BOOST_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 8d839b86a1d5..7dbd27ce17a4 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -22,4 +22,3 @@ CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=y CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot index 0fc8a3428938..0fc8a3428938 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE04.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot diff --git a/tools/testing/selftests/rcutorture/configs/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index b5ba72ea25cb..d0f32e574743 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -22,4 +22,3 @@ CONFIG_PROVE_RCU_DELAY=y CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot index 3b42b8b033cd..3b42b8b033cd 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE05.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot diff --git a/tools/testing/selftests/rcutorture/configs/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index 7c95ab48d29f..2e477dfb9c57 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -23,4 +23,3 @@ CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 1467404bdec1..042f86ef362a 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -21,4 +21,3 @@ CONFIG_PROVE_RCU_DELAY=n CONFIG_RCU_CPU_STALL_INFO=y CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 7d097a61ac2a..3438cee1e3c5 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -23,4 +23,3 @@ CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T index 442c4e450ab3..bf4523d3e44c 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE08-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T @@ -23,4 +23,3 @@ CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index 0d1ec0d3dfee..81e4f7c0bf0b 100644 --- a/tools/testing/selftests/rcutorture/configs/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -18,4 +18,3 @@ CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST index 18223947bbcb..18223947bbcb 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP index d3ef873eb6e7..d3ef873eb6e7 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp index 02e418572b1b..02e418572b1b 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp index b3100f69c8cf..b3100f69c8cf 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP index c56b44530725..c56b44530725 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp index 90d924fea9e9..90d924fea9e9 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh index 023f312a931c..023f312a931c 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH index 6fd0235dae73..6fd0235dae73 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP index f72402d7c13d..f72402d7c13d 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp index 0f3b667d2a9f..0f3b667d2a9f 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp index b035e141bf2a..b035e141bf2a 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP index 3ccf6a9447f5..3ccf6a9447f5 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..ef624ce73d8e 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh index e3361c3894a1..e3361c3894a1 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH index 64abfc3b4d94..64abfc3b4d94 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh index e8052539af54..5ace37a89780 100644 --- a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh @@ -20,16 +20,14 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -# rcutorture_param_n_barrier_cbs bootparam-string -# -# Adds n_barrier_cbs rcutorture module parameter to kernels having it. -rcutorture_param_n_barrier_cbs () { - echo $1 -} - -# rcutorture_param_onoff bootparam-string config-file -# -# Adds onoff rcutorture module parameters to kernels having it. -rcutorture_param_onoff () { - echo $1 +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +# Which old kernels do not. +per_version_boot_params () { + echo rcutorture.stat_interval=15 \ + rcutorture.shutdown_secs=$3 \ + rcutorture.rcutorture_runnable=1 \ + rcutorture.test_no_idle_hz=1 \ + rcutorture.verbose=1 } diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST index da4cbc668f2a..da4cbc668f2a 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP index d81e11d280aa..d81e11d280aa 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp index 02e418572b1b..02e418572b1b 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp index b3100f69c8cf..b3100f69c8cf 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP index c56b44530725..c56b44530725 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp index 90d924fea9e9..90d924fea9e9 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp index 0ccc36d72738..0ccc36d72738 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP index 3f640cf84973..3f640cf84973 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP index 285da2dd8ac3..285da2dd8ac3 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh index 023f312a931c..023f312a931c 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH index 6fd0235dae73..6fd0235dae73 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP index 9647c44cf4b7..9647c44cf4b7 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp index 0f3b667d2a9f..0f3b667d2a9f 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp index b035e141bf2a..b035e141bf2a 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP index 3ccf6a9447f5..3ccf6a9447f5 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..ef624ce73d8e 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp index f4c9175828bf..f4c9175828bf 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP index 77a8c5b75763..77a8c5b75763 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all index 0eecebc6e95f..0eecebc6e95f 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none index 0eecebc6e95f..0eecebc6e95f 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp index 588bc70420cd..588bc70420cd 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh index e3361c3894a1..e3361c3894a1 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH index 64abfc3b4d94..64abfc3b4d94 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST index 18223947bbcb..18223947bbcb 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP index d81e11d280aa..d81e11d280aa 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp index 02e418572b1b..02e418572b1b 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp index b3100f69c8cf..b3100f69c8cf 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP index c56b44530725..c56b44530725 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp index 90d924fea9e9..90d924fea9e9 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh index 023f312a931c..023f312a931c 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH index 6fd0235dae73..6fd0235dae73 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP index 9647c44cf4b7..9647c44cf4b7 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp index 0f3b667d2a9f..0f3b667d2a9f 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp index b035e141bf2a..b035e141bf2a 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP index 3ccf6a9447f5..3ccf6a9447f5 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..ef624ce73d8e 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh index e3361c3894a1..e3361c3894a1 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH index 64abfc3b4d94..64abfc3b4d94 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh index 5e40eadea777..bae55692ce6e 100644 --- a/tools/testing/selftests/rcutorture/configs/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh @@ -20,18 +20,6 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -# rcutorture_param_n_barrier_cbs bootparam-string -# -# Adds n_barrier_cbs rcutorture module parameter to kernels having it. -rcutorture_param_n_barrier_cbs () { - if echo $1 | grep -q "rcutorture\.n_barrier_cbs" - then - echo $1 - else - echo $1 rcutorture.n_barrier_cbs=4 - fi -} - # rcutorture_param_onoff bootparam-string config-file # # Adds onoff rcutorture module parameters to kernels having it. @@ -39,8 +27,18 @@ rcutorture_param_onoff () { if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" then echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 - echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 - else - echo $1 + echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 fi } + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `rcutorture_param_onoff "$1" "$2"` \ + rcutorture.stat_interval=15 \ + rcutorture.shutdown_secs=$3 \ + rcutorture.rcutorture_runnable=1 \ + rcutorture.test_no_idle_hz=1 \ + rcutorture.verbose=1 +} diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST index 18223947bbcb..18223947bbcb 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP index d81e11d280aa..d81e11d280aa 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp index 02e418572b1b..02e418572b1b 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp index b3100f69c8cf..b3100f69c8cf 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP index c56b44530725..c56b44530725 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp index 90d924fea9e9..90d924fea9e9 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh index 023f312a931c..023f312a931c 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH index 6fd0235dae73..6fd0235dae73 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP index 9647c44cf4b7..9647c44cf4b7 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp index 0f3b667d2a9f..0f3b667d2a9f 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp index b035e141bf2a..b035e141bf2a 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP index 3ccf6a9447f5..3ccf6a9447f5 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp index ef624ce73d8e..ef624ce73d8e 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh index e3361c3894a1..e3361c3894a1 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH index 64abfc3b4d94..64abfc3b4d94 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh index 6a5f13aab44d..8977d8d31b19 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh @@ -26,9 +26,9 @@ rcutorture_param_n_barrier_cbs () { if echo $1 | grep -q "rcutorture\.n_barrier_cbs" then - echo $1 + : else - echo $1 rcutorture.n_barrier_cbs=4 + echo rcutorture.n_barrier_cbs=4 fi } @@ -38,9 +38,20 @@ rcutorture_param_n_barrier_cbs () { rcutorture_param_onoff () { if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" then - echo CPU-hotplug kernel, adding rcutorture onoff. - echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 - else - echo $1 + echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 + echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 fi } + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `rcutorture_param_onoff "$1" "$2"` \ + `rcutorture_param_n_barrier_cbs "$1"` \ + rcutorture.stat_interval=15 \ + rcutorture.shutdown_secs=$3 \ + rcutorture.rcutorture_runnable=1 \ + rcutorture.test_no_idle_hz=1 \ + rcutorture.verbose=1 +} diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index c37432f3572c..8977d8d31b19 100644 --- a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -24,7 +24,12 @@ # # Adds n_barrier_cbs rcutorture module parameter to kernels having it. rcutorture_param_n_barrier_cbs () { - echo $1 + if echo $1 | grep -q "rcutorture\.n_barrier_cbs" + then + : + else + echo rcutorture.n_barrier_cbs=4 + fi } # rcutorture_param_onoff bootparam-string config-file @@ -33,9 +38,20 @@ rcutorture_param_n_barrier_cbs () { rcutorture_param_onoff () { if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" then - echo CPU-hotplug kernel, adding rcutorture onoff. - echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 - else - echo $1 + echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 + echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 fi } + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `rcutorture_param_onoff "$1" "$2"` \ + `rcutorture_param_n_barrier_cbs "$1"` \ + rcutorture.stat_interval=15 \ + rcutorture.shutdown_secs=$3 \ + rcutorture.rcutorture_runnable=1 \ + rcutorture.test_no_idle_hz=1 \ + rcutorture.verbose=1 +} diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index adbb76cffb49..adbb76cffb49 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 03a0381b1cb7..b5ec7fb986f6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -102,7 +102,7 @@ static void kvm_release_pfn_dirty(pfn_t pfn); static void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); -bool kvm_rebooting; +__visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; |