From d26f4ddb48463e2ff798859505af1cc520e75685 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Fabian=20Silva=20Delgado?= Date: Wed, 23 Nov 2016 01:35:55 -0300 Subject: Linux-libre 4.8.10-gnu --- Documentation/block/bfq-iosched.txt | 516 +++++++++++++++ Documentation/block/queue-sysfs.txt | 13 + Makefile | 2 +- arch/arc/kernel/time.c | 19 +- arch/arc/mm/dma.c | 26 + arch/s390/hypfs/hypfs_diag.c | 6 +- arch/s390/include/asm/processor.h | 2 +- arch/s390/kernel/dumpstack.c | 17 +- arch/s390/kernel/perf_event.c | 2 +- arch/s390/kernel/stacktrace.c | 4 +- arch/s390/oprofile/init.c | 2 +- arch/sparc/include/asm/uaccess_64.h | 28 +- arch/sparc/kernel/head_64.S | 36 -- arch/sparc/kernel/jump_label.c | 23 +- arch/sparc/kernel/sparc_ksyms_64.c | 1 - arch/sparc/lib/GENcopy_from_user.S | 4 +- arch/sparc/lib/GENcopy_to_user.S | 4 +- arch/sparc/lib/GENmemcpy.S | 48 +- arch/sparc/lib/Makefile | 2 +- arch/sparc/lib/NG2copy_from_user.S | 8 +- arch/sparc/lib/NG2copy_to_user.S | 8 +- arch/sparc/lib/NG2memcpy.S | 228 ++++--- arch/sparc/lib/NG4copy_from_user.S | 8 +- arch/sparc/lib/NG4copy_to_user.S | 8 +- arch/sparc/lib/NG4memcpy.S | 294 ++++++--- arch/sparc/lib/NGcopy_from_user.S | 4 +- arch/sparc/lib/NGcopy_to_user.S | 4 +- arch/sparc/lib/NGmemcpy.S | 233 ++++--- arch/sparc/lib/U1copy_from_user.S | 8 +- arch/sparc/lib/U1copy_to_user.S | 8 +- arch/sparc/lib/U1memcpy.S | 345 ++++++---- arch/sparc/lib/U3copy_from_user.S | 8 +- arch/sparc/lib/U3copy_to_user.S | 8 +- arch/sparc/lib/U3memcpy.S | 227 ++++--- arch/sparc/lib/copy_in_user.S | 35 +- arch/sparc/lib/user_fixup.c | 71 --- arch/sparc/mm/tsb.c | 17 + arch/sparc/mm/ultra.S | 374 ++++++++--- arch/x86/configs/i386_defconfig | 2 +- arch/x86/configs/x86_64_defconfig | 2 +- arch/x86/entry/Makefile | 4 +- arch/x86/kernel/acpi/boot.c | 1 + block/Kconfig | 1 + block/Makefile | 2 +- block/bfq-cgroup.c | 12 + block/blk-core.c | 21 +- block/blk-mq-sysfs.c | 47 ++ block/blk-mq.c | 40 +- block/blk-mq.h | 3 + block/blk-settings.c | 15 + block/blk-stat.c | 221 +++++++ block/blk-stat.h | 18 + block/blk-sysfs.c | 151 +++++ block/cfq-iosched.c | 13 + drivers/acpi/apei/ghes.c | 2 +- drivers/acpi/pci_link.c | 38 +- drivers/ata/libata-core.c | 4 - drivers/block/drbd/drbd_main.c | 2 +- drivers/char/agp/intel-gtt.c | 2 + drivers/char/hw_random/core.c | 6 +- drivers/clk/clk-qoriq.c | 13 +- drivers/clk/samsung/clk-exynos-audss.c | 1 + drivers/clocksource/timer-sun5i.c | 16 +- drivers/cpufreq/cpufreq_conservative.c | 6 - drivers/cpufreq/cpufreq_ondemand.c | 5 - drivers/gpio/gpio-mvebu.c | 92 ++- drivers/gpio/gpiolib-of.c | 14 +- drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 1 + drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 12 - drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 6 +- drivers/gpu/drm/amd/scheduler/sched_fence.c | 19 + drivers/gpu/drm/i915/i915_drv.c | 4 +- drivers/gpu/drm/i915/intel_display.c | 29 +- drivers/gpu/drm/i915/intel_hdmi.c | 84 +-- drivers/gpu/drm/radeon/radeon_device.c | 13 + drivers/iio/accel/st_accel_core.c | 12 +- .../iio/common/hid-sensors/hid-sensor-attributes.c | 56 +- drivers/iio/common/st_sensors/st_sensors_core.c | 8 +- drivers/iio/orientation/hid-sensor-rotation.c | 1 + drivers/input/rmi4/rmi_i2c.c | 38 +- drivers/input/rmi4/rmi_spi.c | 22 +- drivers/iommu/amd_iommu.c | 3 + drivers/iommu/intel-iommu.c | 14 +- drivers/iommu/io-pgtable-arm-v7s.c | 4 + drivers/media/usb/dvb-usb/dib0700_core.c | 5 +- drivers/misc/mei/bus-fixup.c | 2 +- drivers/mmc/core/mmc.c | 3 + drivers/mmc/host/mxs-mmc.c | 4 +- drivers/mmc/host/sdhci-msm.c | 1 + drivers/mmc/host/sdhci.c | 28 +- drivers/net/ethernet/broadcom/bgmac.c | 5 +- drivers/net/ethernet/broadcom/bnx2.c | 48 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 22 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 + drivers/nfc/mei_phy.c | 2 +- drivers/nvme/host/pci.c | 9 +- drivers/pci/setup-res.c | 8 + drivers/pinctrl/bcm/pinctrl-iproc-gpio.c | 2 +- drivers/pinctrl/bcm/pinctrl-nsp-gpio.c | 2 +- drivers/pinctrl/intel/pinctrl-cherryview.c | 17 +- drivers/platform/x86/toshiba-wmi.c | 26 +- drivers/rtc/rtc-pcf2123.c | 5 +- drivers/scsi/device_handler/scsi_dh_alua.c | 5 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 4 +- drivers/scsi/qla2xxx/qla_os.c | 2 + drivers/scsi/scsi.c | 3 + drivers/staging/comedi/drivers/ni_tio.c | 3 +- drivers/staging/iio/impedance-analyzer/ad5933.c | 17 +- drivers/staging/nvec/nvec_ps2.c | 8 +- drivers/staging/sm750fb/ddk750_reg.h | 8 +- drivers/tty/serial/atmel_serial.c | 27 +- drivers/usb/class/cdc-acm.c | 4 +- drivers/usb/dwc3/core.c | 5 +- drivers/usb/gadget/function/f_fs.c | 107 +++- drivers/usb/gadget/function/u_ether.c | 8 - drivers/watchdog/watchdog_core.c | 2 +- fs/buffer.c | 2 +- fs/coredump.c | 3 + fs/f2fs/data.c | 2 +- fs/f2fs/node.c | 2 +- fs/gfs2/meta_io.c | 3 +- fs/mpage.c | 2 +- fs/nfs/nfs4session.c | 10 +- fs/xfs/xfs_aops.c | 7 +- include/linux/acpi.h | 1 + include/linux/backing-dev-defs.h | 2 + include/linux/blk_types.h | 16 +- include/linux/blkdev.h | 21 +- include/linux/frontswap.h | 5 +- include/linux/fs.h | 3 + include/linux/sunrpc/svc_rdma.h | 9 + include/linux/wbt.h | 141 +++++ include/linux/writeback.h | 10 + include/net/ip.h | 1 - include/net/ip6_tunnel.h | 1 + include/net/sock.h | 4 +- include/net/tcp.h | 1 + include/trace/events/wbt.h | 153 +++++ include/uapi/linux/atm_zatm.h | 1 - init/Kconfig | 3 +- kernel/Kconfig.hz | 15 +- kernel/bpf/hashtab.c | 3 +- kernel/sched/MuQSS.c | 228 +++---- lib/Kconfig | 3 + lib/Makefile | 1 + lib/genalloc.c | 3 +- lib/wbt.c | 703 +++++++++++++++++++++ mm/backing-dev.c | 1 + mm/hugetlb.c | 66 ++ mm/memory-failure.c | 12 +- mm/page-writeback.c | 1 + mm/shmem.c | 2 + mm/slab_common.c | 4 +- mm/swapfile.c | 2 + net/batman-adv/originator.c | 2 +- net/ceph/ceph_fs.c | 3 +- net/core/dev.c | 2 +- net/core/flow_dissector.c | 11 +- net/core/sock.c | 6 +- net/dccp/ipv4.c | 16 +- net/dccp/ipv6.c | 19 +- net/dccp/proto.c | 4 + net/ipv4/fib_trie.c | 21 +- net/ipv4/icmp.c | 4 +- net/ipv4/ip_forward.c | 2 +- net/ipv4/ip_output.c | 6 +- net/ipv4/ip_tunnel_core.c | 11 - net/ipv4/ipmr.c | 2 +- net/ipv4/route.c | 4 +- net/ipv4/tcp.c | 4 +- net/ipv4/tcp_dctcp.c | 13 +- net/ipv4/tcp_ipv4.c | 19 +- net/ipv6/icmp.c | 2 +- net/ipv6/tcp_ipv6.c | 6 +- net/netfilter/nf_log.c | 6 +- net/sctp/socket.c | 22 +- net/socket.c | 2 + net/sunrpc/xprtrdma/frwr_ops.c | 39 +- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 2 +- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 2 +- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 24 +- net/sunrpc/xprtrdma/svc_rdma_transport.c | 18 +- net/sunrpc/xprtrdma/xprt_rdma.h | 3 +- sound/core/info.c | 9 +- sound/soc/codecs/cs4270.c | 8 +- sound/soc/intel/skylake/skl.c | 3 +- sound/soc/sunxi/sun4i-codec.c | 7 +- tools/perf/ui/browsers/hists.c | 3 +- tools/power/cpupower/utils/cpufreq-set.c | 7 +- tools/spi/spidev_test.c | 1 + virt/kvm/arm/vgic/vgic-mmio.c | 41 +- virt/kvm/arm/vgic/vgic-mmio.h | 14 +- 198 files changed, 4612 insertions(+), 1349 deletions(-) create mode 100644 Documentation/block/bfq-iosched.txt delete mode 100644 arch/sparc/lib/user_fixup.c create mode 100644 block/blk-stat.c create mode 100644 block/blk-stat.h create mode 100644 include/linux/wbt.h create mode 100644 include/trace/events/wbt.h create mode 100644 lib/wbt.c diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt new file mode 100644 index 000000000..5ba67af3d --- /dev/null +++ b/Documentation/block/bfq-iosched.txt @@ -0,0 +1,516 @@ +BFQ (Budget Fair Queueing) +========================== + +BFQ is a proportional-share I/O scheduler, with some extra +low-latency capabilities. In addition to cgroups support (blkio or io +controllers), BFQ's main features are: +- BFQ guarantees a high system and application responsiveness, and a + low latency for time-sensitive applications, such as audio or video + players; +- BFQ distributes bandwidth, and not just time, among processes or + groups (switching back to time distribution when needed to keep + throughput high). + +On average CPUs, the current version of BFQ can handle devices +performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a +reference, 30-50 KIOPS correspond to very high bandwidths with +sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and +to 120-200 MB/s with 4KB random I/O. + +The table of contents follow. Impatients can just jump to Section 3. + +CONTENTS + +1. When may BFQ be useful? + 1-1 Personal systems + 1-2 Server systems +2. How does BFQ work? +3. What are BFQ's tunable? +4. BFQ group scheduling + 4-1 Service guarantees provided + 4-2 Interface + +1. When may BFQ be useful? +========================== + +BFQ provides the following benefits on personal and server systems. + +1-1 Personal systems +-------------------- + +Low latency for interactive applications + +Regardless of the actual background workload, BFQ guarantees that, for +interactive tasks, the storage device is virtually as responsive as if +it was idle. For example, even if one or more of the following +background workloads are being executed: +- one or more large files are being read, written or copied, +- a tree of source files is being compiled, +- one or more virtual machines are performing I/O, +- a software update is in progress, +- indexing daemons are scanning filesystems and updating their + databases, +starting an application or loading a file from within an application +takes about the same time as if the storage device was idle. As a +comparison, with CFQ, NOOP or DEADLINE, and in the same conditions, +applications experience high latencies, or even become unresponsive +until the background workload terminates (also on SSDs). + +Low latency for soft real-time applications + +Also soft real-time applications, such as audio and video +players/streamers, enjoy a low latency and a low drop rate, regardless +of the background I/O workload. As a consequence, these applications +do not suffer from almost any glitch due to the background workload. + +Higher speed for code-development tasks + +If some additional workload happens to be executed in parallel, then +BFQ executes the I/O-related components of typical code-development +tasks (compilation, checkout, merge, ...) much more quickly than CFQ, +NOOP or DEADLINE. + +High throughput + +On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and +up to 150% higher throughput than DEADLINE and NOOP, with all the +sequential workloads considered in our tests. With random workloads, +and with all the workloads on flash-based devices, BFQ achieves, +instead, about the same throughput as the other schedulers. + +Strong fairness, bandwidth and delay guarantees + +BFQ distributes the device throughput, and not just the device time, +among I/O-bound applications in proportion their weights, with any +workload and regardless of the device parameters. From these bandwidth +guarantees, it is possible to compute tight per-I/O-request delay +guarantees by a simple formula. If not configured for strict service +guarantees, BFQ switches to time-based resource sharing (only) for +applications that would otherwise cause a throughput loss. + +1-2 Server systems +------------------ + +Most benefits for server systems follow from the same service +properties as above. In particular, regardless of whether additional, +possibly heavy workloads are being served, BFQ guarantees: + +. audio and video-streaming with zero or very low jitter and drop + rate; + +. fast retrieval of WEB pages and embedded objects; + +. real-time recording of data in live-dumping applications (e.g., + packet logging); + +. responsiveness in local and remote access to a server. + + +2. How does BFQ work? +===================== + +BFQ is a proportional-share I/O scheduler, whose general structure, +plus a lot of code, are borrowed from CFQ. + +- Each process doing I/O on a device is associated with a weight and a + (bfq_)queue. + +- BFQ grants exclusive access to the device, for a while, to one queue + (process) at a time, and implements this service model by + associating every queue with a budget, measured in number of + sectors. + + - After a queue is granted access to the device, the budget of the + queue is decremented, on each request dispatch, by the size of the + request. + + - The in-service queue is expired, i.e., its service is suspended, + only if one of the following events occurs: 1) the queue finishes + its budget, 2) the queue empties, 3) a "budget timeout" fires. + + - The budget timeout prevents processes doing random I/O from + holding the device for too long and dramatically reducing + throughput. + + - Actually, as in CFQ, a queue associated with a process issuing + sync requests may not be expired immediately when it empties. In + contrast, BFQ may idle the device for a short time interval, + giving the process the chance to go on being served if it issues + a new request in time. Device idling typically boosts the + throughput on rotational devices, if processes do synchronous + and sequential I/O. In addition, under BFQ, device idling is + also instrumental in guaranteeing the desired throughput + fraction to processes issuing sync requests (see the description + of the slice_idle tunable in this document, or [1, 2], for more + details). + + - With respect to idling for service guarantees, if several + processes are competing for the device at the same time, but + all processes (and groups, after the following commit) have + the same weight, then BFQ guarantees the expected throughput + distribution without ever idling the device. Throughput is + thus as high as possible in this common scenario. + + - If low-latency mode is enabled (default configuration), BFQ + executes some special heuristics to detect interactive and soft + real-time applications (e.g., video or audio players/streamers), + and to reduce their latency. The most important action taken to + achieve this goal is to give to the queues associated with these + applications more than their fair share of the device + throughput. For brevity, we call just "weight-raising" the whole + sets of actions taken by BFQ to privilege these queues. In + particular, BFQ provides a milder form of weight-raising for + interactive applications, and a stronger form for soft real-time + applications. + + - BFQ automatically deactivates idling for queues born in a burst of + queue creations. In fact, these queues are usually associated with + the processes of applications and services that benefit mostly + from a high throughput. Examples are systemd during boot, or git + grep. + + - As CFQ, BFQ merges queues performing interleaved I/O, i.e., + performing random I/O that becomes mostly sequential if + merged. Differently from CFQ, BFQ achieves this goal with a more + reactive mechanism, called Early Queue Merge (EQM). EQM is so + responsive in detecting interleaved I/O (cooperating processes), + that it enables BFQ to achieve a high throughput, by queue + merging, even for queues for which CFQ needs a different + mechanism, preemption, to get a high throughput. As such EQM is a + unified mechanism to achieve a high throughput with interleaved + I/O. + + - Queues are scheduled according to a variant of WF2Q+, named + B-WF2Q+, and implemented using an augmented rb-tree to preserve an + O(log N) overall complexity. See [2] for more details. B-WF2Q+ is + also ready for hierarchical scheduling. However, for a cleaner + logical breakdown, the code that enables and completes + hierarchical support is provided in the next commit, which focuses + exactly on this feature. + + - B-WF2Q+ guarantees a tight deviation with respect to an ideal, + perfectly fair, and smooth service. In particular, B-WF2Q+ + guarantees that each queue receives a fraction of the device + throughput proportional to its weight, even if the throughput + fluctuates, and regardless of: the device parameters, the current + workload and the budgets assigned to the queue. + + - The last, budget-independence, property (although probably + counterintuitive in the first place) is definitely beneficial, for + the following reasons: + + - First, with any proportional-share scheduler, the maximum + deviation with respect to an ideal service is proportional to + the maximum budget (slice) assigned to queues. As a consequence, + BFQ can keep this deviation tight not only because of the + accurate service of B-WF2Q+, but also because BFQ *does not* + need to assign a larger budget to a queue to let the queue + receive a higher fraction of the device throughput. + + - Second, BFQ is free to choose, for every process (queue), the + budget that best fits the needs of the process, or best + leverages the I/O pattern of the process. In particular, BFQ + updates queue budgets with a simple feedback-loop algorithm that + allows a high throughput to be achieved, while still providing + tight latency guarantees to time-sensitive applications. When + the in-service queue expires, this algorithm computes the next + budget of the queue so as to: + + - Let large budgets be eventually assigned to the queues + associated with I/O-bound applications performing sequential + I/O: in fact, the longer these applications are served once + got access to the device, the higher the throughput is. + + - Let small budgets be eventually assigned to the queues + associated with time-sensitive applications (which typically + perform sporadic and short I/O), because, the smaller the + budget assigned to a queue waiting for service is, the sooner + B-WF2Q+ will serve that queue (Subsec 3.3 in [2]). + +- If several processes are competing for the device at the same time, + but all processes and groups have the same weight, then BFQ + guarantees the expected throughput distribution without ever idling + the device. It uses preemption instead. Throughput is then much + higher in this common scenario. + +- ioprio classes are served in strict priority order, i.e., + lower-priority queues are not served as long as there are + higher-priority queues. Among queues in the same class, the + bandwidth is distributed in proportion to the weight of each + queue. A very thin extra bandwidth is however guaranteed to + the Idle class, to prevent it from starving. + + +3. What are BFQ's tunable? +========================== + +The tunables back_seek-max, back_seek_penalty, fifo_expire_async and +fifo_expire_sync below are the same as in CFQ. Their description is +just copied from that for CFQ. Some considerations in the description +of slice_idle are copied from CFQ too. + +per-process ioprio and weight +----------------------------- + +Unless the cgroups interface is used, weights can be assigned to +processes only indirectly, through I/O priorities, and according to +the relation: weight = (IOPRIO_BE_NR - ioprio) * 10. + +slice_idle +---------- + +This parameter specifies how long BFQ should idle for next I/O +request, when certain sync BFQ queues become empty. By default +slice_idle is a non-zero value. Idling has a double purpose: boosting +throughput and making sure that the desired throughput distribution is +respected (see the description of how BFQ works, and, if needed, the +papers referred there). + +As for throughput, idling can be very helpful on highly seeky media +like single spindle SATA/SAS disks where we can cut down on overall +number of seeks and see improved throughput. + +Setting slice_idle to 0 will remove all the idling on queues and one +should see an overall improved throughput on faster storage devices +like multiple SATA/SAS disks in hardware RAID configuration. + +So depending on storage and workload, it might be useful to set +slice_idle=0. In general for SATA/SAS disks and software RAID of +SATA/SAS disks keeping slice_idle enabled should be useful. For any +configurations where there are multiple spindles behind single LUN +(Host based hardware RAID controller or for storage arrays), setting +slice_idle=0 might end up in better throughput and acceptable +latencies. + +Idling is however necessary to have service guarantees enforced in +case of differentiated weights or differentiated I/O-request lengths. +To see why, suppose that a given BFQ queue A must get several I/O +requests served for each request served for another queue B. Idling +ensures that, if A makes a new I/O request slightly after becoming +empty, then no request of B is dispatched in the middle, and thus A +does not lose the possibility to get more than one request dispatched +before the next request of B is dispatched. Note that idling +guarantees the desired differentiated treatment of queues only in +terms of I/O-request dispatches. To guarantee that the actual service +order then corresponds to the dispatch order, the strict_guarantees +tunable must be set too. + +There is an important flipside for idling: apart from the above cases +where it is beneficial also for throughput, idling can severely impact +throughput. One important case is random workload. Because of this +issue, BFQ tends to avoid idling as much as possible, when it is not +beneficial also for throughput. As a consequence of this behavior, and +of further issues described for the strict_guarantees tunable, +short-term service guarantees may be occasionally violated. And, in +some cases, these guarantees may be more important than guaranteeing +maximum throughput. For example, in video playing/streaming, a very +low drop rate may be more important than maximum throughput. In these +cases, consider setting the strict_guarantees parameter. + +strict_guarantees +----------------- + +If this parameter is set (default: unset), then BFQ + +- always performs idling when the in-service queue becomes empty; + +- forces the device to serve one I/O request at a time, by dispatching a + new request only if there is no outstanding request. + +In the presence of differentiated weights or I/O-request sizes, both +the above conditions are needed to guarantee that every BFQ queue +receives its allotted share of the bandwidth. The first condition is +needed for the reasons explained in the description of the slice_idle +tunable. The second condition is needed because all modern storage +devices reorder internally-queued requests, which may trivially break +the service guarantees enforced by the I/O scheduler. + +Setting strict_guarantees may evidently affect throughput. + +back_seek_max +------------- + +This specifies, given in Kbytes, the maximum "distance" for backward seeking. +The distance is the amount of space from the current head location to the +sectors that are backward in terms of distance. + +This parameter allows the scheduler to anticipate requests in the "backward" +direction and consider them as being the "next" if they are within this +distance from the current head location. + +back_seek_penalty +----------------- + +This parameter is used to compute the cost of backward seeking. If the +backward distance of request is just 1/back_seek_penalty from a "front" +request, then the seeking cost of two requests is considered equivalent. + +So scheduler will not bias toward one or the other request (otherwise scheduler +will bias toward front request). Default value of back_seek_penalty is 2. + +fifo_expire_async +----------------- + +This parameter is used to set the timeout of asynchronous requests. Default +value of this is 248ms. + +fifo_expire_sync +---------------- + +This parameter is used to set the timeout of synchronous requests. Default +value of this is 124ms. In case to favor synchronous requests over asynchronous +one, this value should be decreased relative to fifo_expire_async. + +low_latency +----------- + +This parameter is used to enable/disable BFQ's low latency mode. By +default, low latency mode is enabled. If enabled, interactive and soft +real-time applications are privileged and experience a lower latency, +as explained in more detail in the description of how BFQ works. + +timeout_sync +------------ + +Maximum amount of device time that can be given to a task (queue) once +it has been selected for service. On devices with costly seeks, +increasing this time usually increases maximum throughput. On the +opposite end, increasing this time coarsens the granularity of the +short-term bandwidth and latency guarantees, especially if the +following parameter is set to zero. + +max_budget +---------- + +Maximum amount of service, measured in sectors, that can be provided +to a BFQ queue once it is set in service (of course within the limits +of the above timeout). According to what said in the description of +the algorithm, larger values increase the throughput in proportion to +the percentage of sequential I/O requests issued. The price of larger +values is that they coarsen the granularity of short-term bandwidth +and latency guarantees. + +The default value is 0, which enables auto-tuning: BFQ sets max_budget +to the maximum number of sectors that can be served during +timeout_sync, according to the estimated peak rate. + +weights +------- + +Read-only parameter, used to show the weights of the currently active +BFQ queues. + + +wr_ tunables +------------ + +BFQ exports a few parameters to control/tune the behavior of +low-latency heuristics. + +wr_coeff + +Factor by which the weight of a weight-raised queue is multiplied. If +the queue is deemed soft real-time, then the weight is further +multiplied by an additional, constant factor. + +wr_max_time + +Maximum duration of a weight-raising period for an interactive task +(ms). If set to zero (default value), then this value is computed +automatically, as a function of the peak rate of the device. In any +case, when the value of this parameter is read, it always reports the +current duration, regardless of whether it has been set manually or +computed automatically. + +wr_max_softrt_rate + +Maximum service rate below which a queue is deemed to be associated +with a soft real-time application, and is then weight-raised +accordingly (sectors/sec). + +wr_min_idle_time + +Minimum idle period after which interactive weight-raising may be +reactivated for a queue (in ms). + +wr_rt_max_time + +Maximum weight-raising duration for soft real-time queues (in ms). The +start time from which this duration is considered is automatically +moved forward if the queue is detected to be still soft real-time +before the current soft real-time weight-raising period finishes. + +wr_min_inter_arr_async + +Minimum period between I/O request arrivals after which weight-raising +may be reactivated for an already busy async queue (in ms). + + +4. Group scheduling with BFQ +============================ + +BFQ supports both cgroup-v1 and cgroup-v2 io controllers, namely blkio +and io. In particular, BFQ supports weight-based proportional +share. + +4-1 Service guarantees provided +------------------------------- + +With BFQ, proportional share means true proportional share of the +device bandwidth, according to group weights. For example, a group +with weight 200 gets twice the bandwidth, and not just twice the time, +of a group with weight 100. + +BFQ supports hierarchies (group trees) of any depth. Bandwidth is +distributed among groups and processes in the expected way: for each +group, the children of the group share the whole bandwidth of the +group in proportion to their weights. In particular, this implies +that, for each leaf group, every process of the group receives the +same share of the whole group bandwidth, unless the ioprio of the +process is modified. + +The resource-sharing guarantee for a group may partially or totally +switch from bandwidth to time, if providing bandwidth guarantees to +the group lowers the throughput too much. This switch occurs on a +per-process basis: if a process of a leaf group causes throughput loss +if served in such a way to receive its share of the bandwidth, then +BFQ switches back to just time-based proportional share for that +process. + +4-2 Interface +------------- + +To get proportional sharing of bandwidth with BFQ for a given device, +BFQ must of course be the active scheduler for that device. + +Within each group directory, the names of the files associated with +BFQ-specific cgroup parameters and stats begin with the "bfq." +prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for +BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group +parameter to set the weight of a group with BFQ is blkio.bfq.weight +or io.bfq.weight. + +Parameters to set +----------------- + +For each group, there is only the following parameter to set. + +weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the +group inside its parent. Available values: 1..10000 (default 100). The +linear mapping between ioprio and weights, described at the beginning +of the tunable section, is still valid, but all weights higher than +IOPRIO_BE_NR*10 are mapped to ioprio 0. + + +[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O + Scheduler", Proceedings of the First Workshop on Mobile System + Technologies (MST-2015), May 2015. + http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf + +[2] P. Valente and M. Andreolini, "Improving Application + Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of + the 5th Annual International Systems and Storage Conference + (SYSTOR '12), June 2012. + Slightly extended version: + http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite- + results.pdf diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index 2a3904030..2847219eb 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -169,5 +169,18 @@ This is the number of bytes the device can write in a single write-same command. A value of '0' means write-same is not supported by this device. +wb_lat_usec (RW) +---------------- +If the device is registered for writeback throttling, then this file shows +the target minimum read latency. If this latency is exceeded in a given +window of time (see wb_window_usec), then the writeback throttling will start +scaling back writes. + +wb_window_usec (RW) +------------------- +If the device is registered for writeback throttling, then this file shows +the value of the monitoring window in which we'll look at the target +latency. See wb_lat_usec. + Jens Axboe , February 2009 diff --git a/Makefile b/Makefile index 2549a0c68..77f100168 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 8 -SUBLEVEL = 8 +SUBLEVEL = 10 EXTRAVERSION = -gnu NAME = Psychotic Stoned Sheep diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index f927b8dc6..c10390d1d 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -152,14 +152,17 @@ static cycle_t arc_read_rtc(struct clocksource *cs) cycle_t full; } stamp; - - __asm__ __volatile( - "1: \n" - " lr %0, [AUX_RTC_LOW] \n" - " lr %1, [AUX_RTC_HIGH] \n" - " lr %2, [AUX_RTC_CTRL] \n" - " bbit0.nt %2, 31, 1b \n" - : "=r" (stamp.low), "=r" (stamp.high), "=r" (status)); + /* + * hardware has an internal state machine which tracks readout of + * low/high and updates the CTRL.status if + * - interrupt/exception taken between the two reads + * - high increments after low has been read + */ + do { + stamp.low = read_aux_reg(AUX_RTC_LOW); + stamp.high = read_aux_reg(AUX_RTC_HIGH); + status = read_aux_reg(AUX_RTC_CTRL); + } while (!(status & _BITUL(31))); return stamp.full; } diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 20afc65e2..9288851d4 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -105,6 +105,31 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr, __free_pages(page, get_order(size)); } +static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr)); + unsigned long off = vma->vm_pgoff; + int ret = -ENXIO; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (off < count && user_count <= (count - off)) { + ret = remap_pfn_range(vma, vma->vm_start, + pfn + off, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + + return ret; +} + /* * streaming DMA Mapping API... * CPU accesses page via normal paddr, thus needs to explicitly made @@ -193,6 +218,7 @@ static int arc_dma_supported(struct device *dev, u64 dma_mask) struct dma_map_ops arc_dma_ops = { .alloc = arc_dma_alloc, .free = arc_dma_free, + .mmap = arc_dma_mmap, .map_page = arc_dma_map_page, .map_sg = arc_dma_map_sg, .sync_single_for_device = arc_dma_sync_single_for_device, diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 28f03ca60..794bebb43 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -363,11 +363,11 @@ out: static int diag224_get_name_table(void) { /* memory must be below 2GB */ - diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA); + diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA); if (!diag224_cpu_names) return -ENOMEM; if (diag224(diag224_cpu_names)) { - kfree(diag224_cpu_names); + free_page((unsigned long) diag224_cpu_names); return -EOPNOTSUPP; } EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16); @@ -376,7 +376,7 @@ static int diag224_get_name_table(void) static void diag224_delete_name_table(void) { - kfree(diag224_cpu_names); + free_page((unsigned long) diag224_cpu_names); } static int diag224_idx2name(int index, char *name) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 03323175d..602af692e 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -192,7 +192,7 @@ struct task_struct; struct mm_struct; struct seq_file; -typedef int (*dump_trace_func_t)(void *data, unsigned long address); +typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable); void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task, unsigned long sp); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 6693383bc..518f615ad 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -38,10 +38,10 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 0)) + return sp; /* Follow the backchain. */ while (1) { - if (func(data, sf->gprs[8])) - return sp; low = sp; sp = sf->back_chain; if (!sp) @@ -49,6 +49,8 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 1)) + return sp; } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); @@ -56,7 +58,7 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, return sp; regs = (struct pt_regs *) sp; if (!user_mode(regs)) { - if (func(data, regs->psw.addr)) + if (func(data, regs->psw.addr, 1)) return sp; } low = sp; @@ -90,7 +92,7 @@ struct return_address_data { int depth; }; -static int __return_address(void *data, unsigned long address) +static int __return_address(void *data, unsigned long address, int reliable) { struct return_address_data *rd = data; @@ -109,9 +111,12 @@ unsigned long return_address(int depth) } EXPORT_SYMBOL_GPL(return_address); -static int show_address(void *data, unsigned long address) +static int show_address(void *data, unsigned long address, int reliable) { - printk("([<%016lx>] %pSR)\n", address, (void *)address); + if (reliable) + printk(" [<%016lx>] %pSR \n", address, (void *)address); + else + printk("([<%016lx>] %pSR)\n", address, (void *)address); return 0; } diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 17431f63d..955a7b6fa 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -222,7 +222,7 @@ static int __init service_level_perf_register(void) } arch_initcall(service_level_perf_register); -static int __perf_callchain_kernel(void *data, unsigned long address) +static int __perf_callchain_kernel(void *data, unsigned long address, int reliable) { struct perf_callchain_entry_ctx *entry = data; diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 44f84b23d..355db9db8 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -27,12 +27,12 @@ static int __save_address(void *data, unsigned long address, int nosched) return 1; } -static int save_address(void *data, unsigned long address) +static int save_address(void *data, unsigned long address, int reliable) { return __save_address(data, address, 0); } -static int save_address_nosched(void *data, unsigned long address) +static int save_address_nosched(void *data, unsigned long address, int reliable) { return __save_address(data, address, 1); } diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 16f4c3960..9a4de4599 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -13,7 +13,7 @@ #include #include -static int __s390_backtrace(void *data, unsigned long address) +static int __s390_backtrace(void *data, unsigned long address, int reliable) { unsigned int *depth = data; diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 37a315d0d..a6847fc05 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -98,7 +98,6 @@ struct exception_table_entry { unsigned int insn, fixup; }; -void __ret_efault(void); void __retl_efault(void); /* Uh, these should become the main single-value transfer routines.. @@ -205,55 +204,34 @@ int __get_user_bad(void); unsigned long __must_check ___copy_from_user(void *to, const void __user *from, unsigned long size); -unsigned long copy_from_user_fixup(void *to, const void __user *from, - unsigned long size); static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long size) { - unsigned long ret; - check_object_size(to, size, false); - ret = ___copy_from_user(to, from, size); - if (unlikely(ret)) - ret = copy_from_user_fixup(to, from, size); - - return ret; + return ___copy_from_user(to, from, size); } #define __copy_from_user copy_from_user unsigned long __must_check ___copy_to_user(void __user *to, const void *from, unsigned long size); -unsigned long copy_to_user_fixup(void __user *to, const void *from, - unsigned long size); static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long size) { - unsigned long ret; - check_object_size(from, size, true); - ret = ___copy_to_user(to, from, size); - if (unlikely(ret)) - ret = copy_to_user_fixup(to, from, size); - return ret; + return ___copy_to_user(to, from, size); } #define __copy_to_user copy_to_user unsigned long __must_check ___copy_in_user(void __user *to, const void __user *from, unsigned long size); -unsigned long copy_in_user_fixup(void __user *to, void __user *from, - unsigned long size); static inline unsigned long __must_check copy_in_user(void __user *to, void __user *from, unsigned long size) { - unsigned long ret = ___copy_in_user(to, from, size); - - if (unlikely(ret)) - ret = copy_in_user_fixup(to, from, size); - return ret; + return ___copy_in_user(to, from, size); } #define __copy_in_user copy_in_user diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index a076b4249..5f1f3ae21 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -922,47 +922,11 @@ prom_tba: .xword 0 tlb_type: .word 0 /* Must NOT end up in BSS */ .section ".fixup",#alloc,#execinstr - .globl __ret_efault, __retl_efault, __ret_one, __retl_one -ENTRY(__ret_efault) - ret - restore %g0, -EFAULT, %o0 -ENDPROC(__ret_efault) - ENTRY(__retl_efault) retl mov -EFAULT, %o0 ENDPROC(__retl_efault) -ENTRY(__retl_one) - retl - mov 1, %o0 -ENDPROC(__retl_one) - -ENTRY(__retl_one_fp) - VISExitHalf - retl - mov 1, %o0 -ENDPROC(__retl_one_fp) - -ENTRY(__ret_one_asi) - wr %g0, ASI_AIUS, %asi - ret - restore %g0, 1, %o0 -ENDPROC(__ret_one_asi) - -ENTRY(__retl_one_asi) - wr %g0, ASI_AIUS, %asi - retl - mov 1, %o0 -ENDPROC(__retl_one_asi) - -ENTRY(__retl_one_asi_fp) - wr %g0, ASI_AIUS, %asi - VISExitHalf - retl - mov 1, %o0 -ENDPROC(__retl_one_asi_fp) - ENTRY(__retl_o1) retl mov %o1, %o0 diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c index 59bbeff55..07933b9e9 100644 --- a/arch/sparc/kernel/jump_label.c +++ b/arch/sparc/kernel/jump_label.c @@ -13,19 +13,30 @@ void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - u32 val; u32 *insn = (u32 *) (unsigned long) entry->code; + u32 val; if (type == JUMP_LABEL_JMP) { s32 off = (s32)entry->target - (s32)entry->code; + bool use_v9_branch = false; + + BUG_ON(off & 3); #ifdef CONFIG_SPARC64 - /* ba,pt %xcc, . + (off << 2) */ - val = 0x10680000 | ((u32) off >> 2); -#else - /* ba . + (off << 2) */ - val = 0x10800000 | ((u32) off >> 2); + if (off <= 0xfffff && off >= -0x100000) + use_v9_branch = true; #endif + if (use_v9_branch) { + /* WDISP19 - target is . + immed << 2 */ + /* ba,pt %xcc, . + off */ + val = 0x10680000 | (((u32) off >> 2) & 0x7ffff); + } else { + /* WDISP22 - target is . + immed << 2 */ + BUG_ON(off > 0x7fffff); + BUG_ON(off < -0x800000); + /* ba . + off */ + val = 0x10800000 | (((u32) off >> 2) & 0x3fffff); + } } else { val = 0x01000000; } diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index 9e034f29d..20ffb052f 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -27,7 +27,6 @@ EXPORT_SYMBOL(__flushw_user); EXPORT_SYMBOL_GPL(real_hard_smp_processor_id); /* from head_64.S */ -EXPORT_SYMBOL(__ret_efault); EXPORT_SYMBOL(tlb_type); EXPORT_SYMBOL(sun4v_chip_type); EXPORT_SYMBOL(prom_root_node); diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S index b7d0bd6b1..69a439fa2 100644 --- a/arch/sparc/lib/GENcopy_from_user.S +++ b/arch/sparc/lib/GENcopy_from_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S index 780550e1a..9947427ce 100644 --- a/arch/sparc/lib/GENcopy_to_user.S +++ b/arch/sparc/lib/GENcopy_to_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S index 89358ee94..059ea24ad 100644 --- a/arch/sparc/lib/GENmemcpy.S +++ b/arch/sparc/lib/GENmemcpy.S @@ -4,21 +4,18 @@ */ #ifdef __KERNEL__ +#include #define GLOBAL_SPARE %g7 #else #define GLOBAL_SPARE %g5 #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST(x,y) x #endif #ifndef LOAD @@ -45,6 +42,29 @@ .register %g3,#scratch .text + +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +ENTRY(GEN_retl_o4_1) + add %o4, %o2, %o4 + retl + add %o4, 1, %o0 +ENDPROC(GEN_retl_o4_1) +ENTRY(GEN_retl_g1_8) + add %g1, %o2, %g1 + retl + add %g1, 8, %o0 +ENDPROC(GEN_retl_g1_8) +ENTRY(GEN_retl_o2_4) + retl + add %o2, 4, %o0 +ENDPROC(GEN_retl_o2_4) +ENTRY(GEN_retl_o2_1) + retl + add %o2, 1, %o0 +ENDPROC(GEN_retl_o2_1) +#endif + .align 64 .globl FUNC_NAME @@ -73,8 +93,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %o4, %o4 sub %o2, %o4, %o2 1: subcc %o4, 1, %o4 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1) + EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1) add %o1, 1, %o1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -82,8 +102,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x7, %g1 sub %o2, %g1, %o2 1: subcc %g1, 0x8, %g1 - EX_LD(LOAD(ldx, %o1, %g2)) - EX_ST(STORE(stx, %g2, %o0)) + EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8) + EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8) add %o1, 0x8, %o1 bne,pt %XCC, 1b add %o0, 0x8, %o0 @@ -100,8 +120,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4) + EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -111,8 +131,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1) + EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 3269b0234..4f2384a42 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -38,7 +38,7 @@ lib-$(CONFIG_SPARC64) += NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o -lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o +lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-$(CONFIG_SPARC64) += iomap.o diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index d5242b8c4..b79a6998d 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 4e962d993..dcec55f25 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index d5f585df2..c629dbd12 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include #include #include #define GLOBAL_SPARE %g7 @@ -32,21 +33,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -140,45 +137,110 @@ fsrc2 %x6, %f12; \ fsrc2 %x7, %f14; #define FREG_LOAD_1(base, x0) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)) + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1) #define FREG_LOAD_2(base, x0, x1) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); #define FREG_LOAD_3(base, x0, x1, x2) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); #define FREG_LOAD_4(base, x0, x1, x2, x3) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \ - EX_LD_FP(LOAD(ldd, base + 0x30, %x6)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1); .register %g2,#scratch .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_fp: + VISExitHalf +__restore_asi: + retl + wr %g0, ASI_AIUS, %asi +ENTRY(NG2_retl_o2) + ba,pt %xcc, __restore_asi + mov %o2, %o0 +ENDPROC(NG2_retl_o2) +ENTRY(NG2_retl_o2_plus_1) + ba,pt %xcc, __restore_asi + add %o2, 1, %o0 +ENDPROC(NG2_retl_o2_plus_1) +ENTRY(NG2_retl_o2_plus_4) + ba,pt %xcc, __restore_asi + add %o2, 4, %o0 +ENDPROC(NG2_retl_o2_plus_4) +ENTRY(NG2_retl_o2_plus_8) + ba,pt %xcc, __restore_asi + add %o2, 8, %o0 +ENDPROC(NG2_retl_o2_plus_8) +ENTRY(NG2_retl_o2_plus_o4_plus_1) + add %o4, 1, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_1) +ENTRY(NG2_retl_o2_plus_o4_plus_8) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_8) +ENTRY(NG2_retl_o2_plus_o4_plus_16) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_16) +ENTRY(NG2_retl_o2_plus_g1_fp) + ba,pt %xcc, __restore_fp + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_fp) +ENTRY(NG2_retl_o2_plus_g1_plus_64_fp) + add %g1, 64, %g1 + ba,pt %xcc, __restore_fp + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp) +ENTRY(NG2_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_plus_1) +ENTRY(NG2_retl_o2_and_7_plus_o4) + and %o2, 7, %o2 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_and_7_plus_o4) +ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8) + and %o2, 7, %o2 + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8) +#endif + .align 64 .globl FUNC_NAME @@ -230,8 +292,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %o4, %o4 ! bytes to align dst sub %o2, %o4, %o2 1: subcc %o4, 1, %o4 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1) + EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1) add %o1, 1, %o1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -281,11 +343,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop /* fall through for 0 < low bits < 8 */ 110: sub %o4, 64, %g2 - EX_LD_FP(LOAD_BLK(%g2, %f0)) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) + EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -296,10 +358,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 120: sub %o4, 56, %g2 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -310,10 +372,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 130: sub %o4, 48, %g2 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_6(f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -324,10 +386,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 140: sub %o4, 40, %g2 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_5(f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -338,10 +400,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 150: sub %o4, 32, %g2 FREG_LOAD_4(%g2, f0, f2, f4, f6) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_4(f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -352,10 +414,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 160: sub %o4, 24, %g2 FREG_LOAD_3(%g2, f0, f2, f4) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_3(f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -366,10 +428,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 170: sub %o4, 16, %g2 FREG_LOAD_2(%g2, f0, f2) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_2(f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -380,10 +442,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 180: sub %o4, 8, %g2 FREG_LOAD_1(%g2, f0) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_1(f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -393,10 +455,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop 190: -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) subcc %g1, 64, %g1 - EX_LD_FP(LOAD_BLK(%o4, %f0)) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64) add %o4, 64, %o4 bne,pt %xcc, 1b LOAD(prefetch, %o4 + 64, #one_read) @@ -423,28 +485,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0xf, %o4 and %o2, 0xf, %o2 1: subcc %o4, 0x10, %o4 - EX_LD(LOAD(ldx, %o1, %o5)) + EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16) add %o1, 0x08, %o1 - EX_LD(LOAD(ldx, %o1, %g1)) + EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16) sub %o1, 0x08, %o1 - EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE)) + EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE)) + EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop sub %o2, 0x8, %o2 - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8) + EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4) + EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -460,8 +522,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g1, %o2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %o1, %o5)) - EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1) + EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -477,16 +539,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, GLOBAL_SPARE andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2) sub GLOBAL_SPARE, %g1, GLOBAL_SPARE andn %o2, 0x7, %o4 sllx %g2, %g1, %g2 1: add %o1, 0x8, %o1 - EX_LD(LOAD(ldx, %o1, %g3)) + EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4) subcc %o4, 0x8, %o4 srlx %g3, GLOBAL_SPARE, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -506,8 +568,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4) + EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -517,8 +579,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1) + EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index 2e8ee7ad0..16a286c1a 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2012 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x, y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index be0bf4590..6b0276ffc 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2012 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 8e13ee1f4..75bb93b14 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include #include #include #define GLOBAL_SPARE %g7 @@ -46,22 +47,19 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x +#define EX_ST_FP(x,y) x #endif -#ifndef EX_RETVAL -#define EX_RETVAL(x) x -#endif #ifndef LOAD #define LOAD(type,addr,dest) type [addr], dest @@ -94,6 +92,158 @@ .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_asi_fp: + VISExitHalf +__restore_asi: + retl + wr %g0, ASI_AIUS, %asi + +ENTRY(NG4_retl_o2) + ba,pt %xcc, __restore_asi + mov %o2, %o0 +ENDPROC(NG4_retl_o2) +ENTRY(NG4_retl_o2_plus_1) + ba,pt %xcc, __restore_asi + add %o2, 1, %o0 +ENDPROC(NG4_retl_o2_plus_1) +ENTRY(NG4_retl_o2_plus_4) + ba,pt %xcc, __restore_asi + add %o2, 4, %o0 +ENDPROC(NG4_retl_o2_plus_4) +ENTRY(NG4_retl_o2_plus_o5) + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5) +ENTRY(NG4_retl_o2_plus_o5_plus_4) + add %o5, 4, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_4) +ENTRY(NG4_retl_o2_plus_o5_plus_8) + add %o5, 8, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_8) +ENTRY(NG4_retl_o2_plus_o5_plus_16) + add %o5, 16, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_16) +ENTRY(NG4_retl_o2_plus_o5_plus_24) + add %o5, 24, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_24) +ENTRY(NG4_retl_o2_plus_o5_plus_32) + add %o5, 32, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_32) +ENTRY(NG4_retl_o2_plus_g1) + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1) +ENTRY(NG4_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1_plus_1) +ENTRY(NG4_retl_o2_plus_g1_plus_8) + add %g1, 8, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1_plus_8) +ENTRY(NG4_retl_o2_plus_o4) + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4) +ENTRY(NG4_retl_o2_plus_o4_plus_8) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_8) +ENTRY(NG4_retl_o2_plus_o4_plus_16) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_16) +ENTRY(NG4_retl_o2_plus_o4_plus_24) + add %o4, 24, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_24) +ENTRY(NG4_retl_o2_plus_o4_plus_32) + add %o4, 32, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_32) +ENTRY(NG4_retl_o2_plus_o4_plus_40) + add %o4, 40, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_40) +ENTRY(NG4_retl_o2_plus_o4_plus_48) + add %o4, 48, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_48) +ENTRY(NG4_retl_o2_plus_o4_plus_56) + add %o4, 56, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_56) +ENTRY(NG4_retl_o2_plus_o4_plus_64) + add %o4, 64, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_64) +ENTRY(NG4_retl_o2_plus_o4_fp) + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_8_fp) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_16_fp) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_24_fp) + add %o4, 24, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_32_fp) + add %o4, 32, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_40_fp) + add %o4, 40, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_48_fp) + add %o4, 48, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_56_fp) + add %o4, 56, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_64_fp) + add %o4, 64, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp) +#endif .align 64 .globl FUNC_NAME @@ -124,12 +274,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, 51f sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2)) + +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 1, %o1 subcc %g1, 1, %g1 add %o0, 1, %o0 bne,pt %icc, 1b - EX_ST(STORE(stb, %g2, %o0 - 0x01)) + EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1) 51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong) LOAD(prefetch, %o1 + 0x080, #n_reads_strong) @@ -154,43 +305,43 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, .Llarge_aligned sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 8, %o1 subcc %g1, 8, %g1 add %o0, 8, %o0 bne,pt %icc, 1b - EX_ST(STORE(stx, %g2, %o0 - 0x08)) + EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8) .Llarge_aligned: /* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */ andn %o2, 0x3f, %o4 sub %o2, %o4, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4) add %o1, 0x40, %o1 - EX_LD(LOAD(ldx, %o1 - 0x38, %g2)) + EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4) subcc %o4, 0x40, %o4 - EX_LD(LOAD(ldx, %o1 - 0x30, %g3)) - EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE)) - EX_LD(LOAD(ldx, %o1 - 0x20, %o5)) - EX_ST(STORE_INIT(%g1, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64) + EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g2, %o0)) + EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x18, %g2)) - EX_ST(STORE_INIT(%g3, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48) + EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x10, %g3)) - EX_ST(STORE_INIT(GLOBAL_SPARE, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40) + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE)) - EX_ST(STORE_INIT(%o5, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32) + EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g2, %o0)) + EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g3, %o0)) + EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(GLOBAL_SPARE, %o0)) + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8) add %o0, 0x08, %o0 bne,pt %icc, 1b LOAD(prefetch, %o1 + 0x200, #n_reads_strong) @@ -216,17 +367,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %o4, %o2 alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 - EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0)) -1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2)) + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4) subcc %o4, 0x40, %o4 - EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4)) - EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6)) - EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8)) - EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10)) - EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12)) - EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14)) + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0)) + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64) faligndata %f2, %f4, %f18 add %g1, 0x40, %g1 faligndata %f4, %f6, %f20 @@ -235,14 +386,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST_FP(STORE(std, %f16, %o0 + 0x00)) - EX_ST_FP(STORE(std, %f18, %o0 + 0x08)) - EX_ST_FP(STORE(std, %f20, %o0 + 0x10)) - EX_ST_FP(STORE(std, %f22, %o0 + 0x18)) - EX_ST_FP(STORE(std, %f24, %o0 + 0x20)) - EX_ST_FP(STORE(std, %f26, %o0 + 0x28)) - EX_ST_FP(STORE(std, %f28, %o0 + 0x30)) - EX_ST_FP(STORE(std, %f30, %o0 + 0x38)) + EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8) add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) @@ -270,37 +421,38 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andncc %o2, 0x20 - 1, %o5 be,pn %icc, 2f sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g2)) - EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE)) - EX_LD(LOAD(ldx, %o1 + 0x18, %o4)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5) add %o1, 0x20, %o1 subcc %o5, 0x20, %o5 - EX_ST(STORE(stx, %g1, %o0 + 0x00)) - EX_ST(STORE(stx, %g2, %o0 + 0x08)) - EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10)) - EX_ST(STORE(stx, %o4, %o0 + 0x18)) + EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32) + EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8) bne,pt %icc, 1b add %o0, 0x20, %o0 2: andcc %o2, 0x18, %o5 be,pt %icc, 3f sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) + +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) add %o1, 0x08, %o1 add %o0, 0x08, %o0 subcc %o5, 0x08, %o5 bne,pt %icc, 1b - EX_ST(STORE(stx, %g1, %o0 - 0x08)) + EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8) 3: brz,pt %o2, .Lexit cmp %o2, 0x04 bl,pn %icc, .Ltiny nop - EX_LD(LOAD(lduw, %o1 + 0x00, %g1)) + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2) add %o1, 0x04, %o1 add %o0, 0x04, %o0 subcc %o2, 0x04, %o2 bne,pn %icc, .Ltiny - EX_ST(STORE(stw, %g1, %o0 - 0x04)) + EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4) ba,a,pt %icc, .Lexit .Lmedium_unaligned: /* First get dest 8 byte aligned. */ @@ -309,12 +461,12 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, 2f sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2)) +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 1, %o1 subcc %g1, 1, %g1 add %o0, 1, %o0 bne,pt %icc, 1b - EX_ST(STORE(stb, %g2, %o0 - 0x01)) + EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1) 2: and %o1, 0x7, %g1 brz,pn %g1, .Lmedium_noprefetch @@ -322,16 +474,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov 64, %g2 sub %g2, %g1, %g2 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1 + 0x00, %o4)) + EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2) sllx %o4, %g1, %o4 andn %o2, 0x08 - 1, %o5 sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5) add %o1, 0x08, %o1 subcc %o5, 0x08, %o5 srlx %g3, %g2, GLOBAL_SPARE or GLOBAL_SPARE, %o4, GLOBAL_SPARE - EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00)) + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8) add %o0, 0x08, %o0 bne,pt %icc, 1b sllx %g3, %g1, %o4 @@ -342,17 +494,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ ba,pt %icc, .Lsmall_unaligned .Ltiny: - EX_LD(LOAD(ldub, %o1 + 0x00, %g1)) + EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2) subcc %o2, 1, %o2 be,pn %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x00)) - EX_LD(LOAD(ldub, %o1 + 0x01, %g1)) + EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2) subcc %o2, 1, %o2 be,pn %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x01)) - EX_LD(LOAD(ldub, %o1 + 0x02, %g1)) + EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2) ba,pt %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x02)) + EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2) .Lsmall: andcc %g2, 0x3, %g0 @@ -360,22 +512,22 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x4 - 1, %o5 sub %o2, %o5, %o2 1: - EX_LD(LOAD(lduw, %o1 + 0x00, %g1)) + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) add %o1, 0x04, %o1 subcc %o5, 0x04, %o5 add %o0, 0x04, %o0 bne,pt %icc, 1b - EX_ST(STORE(stw, %g1, %o0 - 0x04)) + EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4) brz,pt %o2, .Lexit nop ba,a,pt %icc, .Ltiny .Lsmall_unaligned: -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1)) +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2) add %o1, 1, %o1 add %o0, 1, %o0 subcc %o2, 1, %o2 bne,pt %icc, 1b - EX_ST(STORE(stb, %g1, %o0 - 0x01)) + EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1) ba,a,pt %icc, .Lexit .size FUNC_NAME, .-FUNC_NAME diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S index 5d1e4d1ac..9cd42fcbc 100644 --- a/arch/sparc/lib/NGcopy_from_user.S +++ b/arch/sparc/lib/NGcopy_from_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __ret_one_asi;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S index ff630dcb2..5c358afd4 100644 --- a/arch/sparc/lib/NGcopy_to_user.S +++ b/arch/sparc/lib/NGcopy_to_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __ret_one_asi;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S index 96a14caf6..d88c4ed50 100644 --- a/arch/sparc/lib/NGmemcpy.S +++ b/arch/sparc/lib/NGmemcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include #include #include #define GLOBAL_SPARE %g7 @@ -27,15 +28,11 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST(x,y) x #endif #ifndef LOAD @@ -79,6 +76,92 @@ .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_asi: + ret + wr %g0, ASI_AIUS, %asi + restore +ENTRY(NG_ret_i2_plus_i4_plus_1) + ba,pt %xcc, __restore_asi + add %i2, %i5, %i0 +ENDPROC(NG_ret_i2_plus_i4_plus_1) +ENTRY(NG_ret_i2_plus_g1) + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1) +ENTRY(NG_ret_i2_plus_g1_minus_8) + sub %g1, 8, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_8) +ENTRY(NG_ret_i2_plus_g1_minus_16) + sub %g1, 16, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_16) +ENTRY(NG_ret_i2_plus_g1_minus_24) + sub %g1, 24, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_24) +ENTRY(NG_ret_i2_plus_g1_minus_32) + sub %g1, 32, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_32) +ENTRY(NG_ret_i2_plus_g1_minus_40) + sub %g1, 40, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_40) +ENTRY(NG_ret_i2_plus_g1_minus_48) + sub %g1, 48, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_48) +ENTRY(NG_ret_i2_plus_g1_minus_56) + sub %g1, 56, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_56) +ENTRY(NG_ret_i2_plus_i4) + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_plus_i4) +ENTRY(NG_ret_i2_plus_i4_minus_8) + sub %i4, 8, %i4 + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_plus_i4_minus_8) +ENTRY(NG_ret_i2_plus_8) + ba,pt %xcc, __restore_asi + add %i2, 8, %i0 +ENDPROC(NG_ret_i2_plus_8) +ENTRY(NG_ret_i2_plus_4) + ba,pt %xcc, __restore_asi + add %i2, 4, %i0 +ENDPROC(NG_ret_i2_plus_4) +ENTRY(NG_ret_i2_plus_1) + ba,pt %xcc, __restore_asi + add %i2, 1, %i0 +ENDPROC(NG_ret_i2_plus_1) +ENTRY(NG_ret_i2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_plus_1) +ENTRY(NG_ret_i2) + ba,pt %xcc, __restore_asi + mov %i2, %i0 +ENDPROC(NG_ret_i2) +ENTRY(NG_ret_i2_and_7_plus_i4) + and %i2, 7, %i2 + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_and_7_plus_i4) +#endif + .align 64 .globl FUNC_NAME @@ -126,8 +209,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ sub %g0, %i4, %i4 ! bytes to align dst sub %i2, %i4, %i2 1: subcc %i4, 1, %i4 - EX_LD(LOAD(ldub, %i1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1) + EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1) add %i1, 1, %i1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -160,7 +243,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ and %i4, 0x7, GLOBAL_SPARE sll GLOBAL_SPARE, 3, GLOBAL_SPARE mov 64, %i5 - EX_LD(LOAD_TWIN(%i1, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1) sub %i5, GLOBAL_SPARE, %i5 mov 16, %o4 mov 32, %o5 @@ -178,31 +261,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ srlx WORD3, PRE_SHIFT, TMP; \ or WORD2, TMP, WORD2; -8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3)) +8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1) MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1) LOAD(prefetch, %i1 + %i3, #one_read) - EX_ST(STORE_INIT(%g2, %o0 + 0x00)) - EX_ST(STORE_INIT(%g3, %o0 + 0x08)) + EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1) + EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) - EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16) MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o2, %o0 + 0x10)) - EX_ST(STORE_INIT(%o3, %o0 + 0x18)) + EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32) MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%g2, %o0 + 0x20)) - EX_ST(STORE_INIT(%g3, %o0 + 0x28)) + EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) - EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o2, %o0 + 0x30)) - EX_ST(STORE_INIT(%o3, %o0 + 0x38)) + EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 8b @@ -211,31 +294,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ ba,pt %XCC, 60f add %i1, %i4, %i1 -9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3)) +9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1) MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1) LOAD(prefetch, %i1 + %i3, #one_read) - EX_ST(STORE_INIT(%g3, %o0 + 0x00)) - EX_ST(STORE_INIT(%o2, %o0 + 0x08)) + EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1) + EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) - EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16) MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o3, %o0 + 0x10)) - EX_ST(STORE_INIT(%g2, %o0 + 0x18)) + EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32) MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%g3, %o0 + 0x20)) - EX_ST(STORE_INIT(%o2, %o0 + 0x28)) + EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) - EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o3, %o0 + 0x30)) - EX_ST(STORE_INIT(%g2, %o0 + 0x38)) + EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 9b @@ -249,25 +332,25 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ * one twin load ahead, then add 8 back into source when * we finish the loop. */ - EX_LD(LOAD_TWIN(%i1, %o4, %o5)) + EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1) mov 16, %o7 mov 32, %g2 mov 48, %g3 mov 64, %o1 -1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) +1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1) LOAD(prefetch, %i1 + %o1, #one_read) - EX_ST(STORE_INIT(%o5, %o0 + 0x00)) ! initializes cache line - EX_ST(STORE_INIT(%o2, %o0 + 0x08)) - EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5)) - EX_ST(STORE_INIT(%o3, %o0 + 0x10)) - EX_ST(STORE_INIT(%o4, %o0 + 0x18)) - EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3)) - EX_ST(STORE_INIT(%o5, %o0 + 0x20)) - EX_ST(STORE_INIT(%o2, %o0 + 0x28)) - EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5)) + EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line + EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) + EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) + EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) + EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 - EX_ST(STORE_INIT(%o3, %o0 + 0x30)) - EX_ST(STORE_INIT(%o4, %o0 + 0x38)) + EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 1b add %o0, 64, %o0 @@ -282,20 +365,20 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ mov 32, %g2 mov 48, %g3 mov 64, %o1 -1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5)) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) +1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1) LOAD(prefetch, %i1 + %o1, #one_read) - EX_ST(STORE_INIT(%o4, %o0 + 0x00)) ! initializes cache line - EX_ST(STORE_INIT(%o5, %o0 + 0x08)) - EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5)) - EX_ST(STORE_INIT(%o2, %o0 + 0x10)) - EX_ST(STORE_INIT(%o3, %o0 + 0x18)) - EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3)) + EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line + EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) + EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) + EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32) add %i1, 64, %i1 - EX_ST(STORE_INIT(%o4, %o0 + 0x20)) - EX_ST(STORE_INIT(%o5, %o0 + 0x28)) - EX_ST(STORE_INIT(%o2, %o0 + 0x30)) - EX_ST(STORE_INIT(%o3, %o0 + 0x38)) + EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) + EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 1b add %o0, 64, %o0 @@ -321,28 +404,28 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ andn %i2, 0xf, %i4 and %i2, 0xf, %i2 1: subcc %i4, 0x10, %i4 - EX_LD(LOAD(ldx, %i1, %o4)) + EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4) add %i1, 0x08, %i1 - EX_LD(LOAD(ldx, %i1, %g1)) + EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4) sub %i1, 0x08, %i1 - EX_ST(STORE(stx, %o4, %i1 + %i3)) + EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4) add %i1, 0x8, %i1 - EX_ST(STORE(stx, %g1, %i1 + %i3)) + EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8) bgu,pt %XCC, 1b add %i1, 0x8, %i1 73: andcc %i2, 0x8, %g0 be,pt %XCC, 1f nop sub %i2, 0x8, %i2 - EX_LD(LOAD(ldx, %i1, %o4)) - EX_ST(STORE(stx, %o4, %i1 + %i3)) + EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8) + EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8) add %i1, 0x8, %i1 1: andcc %i2, 0x4, %g0 be,pt %XCC, 1f nop sub %i2, 0x4, %i2 - EX_LD(LOAD(lduw, %i1, %i5)) - EX_ST(STORE(stw, %i5, %i1 + %i3)) + EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4) + EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4) add %i1, 0x4, %i1 1: cmp %i2, 0 be,pt %XCC, 85f @@ -358,8 +441,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ sub %i2, %g1, %i2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %i1, %i5)) - EX_ST(STORE(stb, %i5, %i1 + %i3)) + EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1) + EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1) bgu,pt %icc, 1b add %i1, 1, %i1 @@ -375,16 +458,16 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ 8: mov 64, %i3 andn %i1, 0x7, %i1 - EX_LD(LOAD(ldx, %i1, %g2)) + EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2) sub %i3, %g1, %i3 andn %i2, 0x7, %i4 sllx %g2, %g1, %g2 1: add %i1, 0x8, %i1 - EX_LD(LOAD(ldx, %i1, %g3)) + EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4) subcc %i4, 0x8, %i4 srlx %g3, %i3, %i5 or %i5, %g2, %i5 - EX_ST(STORE(stx, %i5, %o0)) + EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -404,8 +487,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ 1: subcc %i2, 4, %i2 - EX_LD(LOAD(lduw, %i1, %g1)) - EX_ST(STORE(stw, %g1, %i1 + %i3)) + EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4) + EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4) bgu,pt %XCC, 1b add %i1, 4, %i1 @@ -415,8 +498,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ .align 32 90: subcc %i2, 1, %i2 - EX_LD(LOAD(ldub, %i1, %g1)) - EX_ST(STORE(stb, %g1, %i1 + %i3)) + EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1) + EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1) bgu,pt %XCC, 90b add %i1, 1, %i1 ret diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index ecc5692fa..bb6ff7322 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index 9eea392e4..ed92ce739 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S index 3e6209ebb..f30d2ab2c 100644 --- a/arch/sparc/lib/U1memcpy.S +++ b/arch/sparc/lib/U1memcpy.S @@ -5,6 +5,7 @@ */ #ifdef __KERNEL__ +#include #include #include #define GLOBAL_SPARE g7 @@ -23,21 +24,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -78,53 +75,169 @@ faligndata %f7, %f8, %f60; \ faligndata %f8, %f9, %f62; -#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \ - EX_LD_FP(LOAD_BLK(%src, %fdest)); \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ - add %src, 0x40, %src; \ - subcc %len, 0x40, %len; \ - be,pn %xcc, jmptgt; \ - add %dest, 0x40, %dest; \ - -#define LOOP_CHUNK1(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest) -#define LOOP_CHUNK2(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest) -#define LOOP_CHUNK3(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest) +#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt) \ + EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \ + add %src, 0x40, %src; \ + subcc %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE; \ + be,pn %xcc, jmptgt; \ + add %dest, 0x40, %dest; \ + +#define LOOP_CHUNK1(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f0, f48, branch_dest) +#define LOOP_CHUNK2(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest) +#define LOOP_CHUNK3(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest) #define DO_SYNC membar #Sync; #define STORE_SYNC(dest, fsrc) \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \ add %dest, 0x40, %dest; \ DO_SYNC #define STORE_JUMP(dest, fsrc, target) \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp); \ add %dest, 0x40, %dest; \ ba,pt %xcc, target; \ nop; -#define FINISH_VISCHUNK(dest, f0, f1, left) \ - subcc %left, 8, %left;\ - bl,pn %xcc, 95f; \ - faligndata %f0, %f1, %f48; \ - EX_ST_FP(STORE(std, %f48, %dest)); \ +#define FINISH_VISCHUNK(dest, f0, f1) \ + subcc %g3, 8, %g3; \ + bl,pn %xcc, 95f; \ + faligndata %f0, %f1, %f48; \ + EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp); \ add %dest, 8, %dest; -#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ - subcc %left, 8, %left; \ - bl,pn %xcc, 95f; \ +#define UNEVEN_VISCHUNK_LAST(dest, f0, f1) \ + subcc %g3, 8, %g3; \ + bl,pn %xcc, 95f; \ fsrc2 %f0, %f1; -#define UNEVEN_VISCHUNK(dest, f0, f1, left) \ - UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ +#define UNEVEN_VISCHUNK(dest, f0, f1) \ + UNEVEN_VISCHUNK_LAST(dest, f0, f1) \ ba,a,pt %xcc, 93f; .register %g2,#scratch .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +ENTRY(U1_g1_1_fp) + VISExitHalf + add %g1, 1, %g1 + add %g1, %g2, %g1 + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_1_fp) +ENTRY(U1_g2_0_fp) + VISExitHalf + retl + add %g2, %o2, %o0 +ENDPROC(U1_g2_0_fp) +ENTRY(U1_g2_8_fp) + VISExitHalf + add %g2, 8, %g2 + retl + add %g2, %o2, %o0 +ENDPROC(U1_g2_8_fp) +ENTRY(U1_gs_0_fp) + VISExitHalf + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_0_fp) +ENTRY(U1_gs_80_fp) + VISExitHalf + add %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_80_fp) +ENTRY(U1_gs_40_fp) + VISExitHalf + add %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_40_fp) +ENTRY(U1_g3_0_fp) + VISExitHalf + retl + add %g3, %o2, %o0 +ENDPROC(U1_g3_0_fp) +ENTRY(U1_g3_8_fp) + VISExitHalf + add %g3, 8, %g3 + retl + add %g3, %o2, %o0 +ENDPROC(U1_g3_8_fp) +ENTRY(U1_o2_0_fp) + VISExitHalf + retl + mov %o2, %o0 +ENDPROC(U1_o2_0_fp) +ENTRY(U1_o2_1_fp) + VISExitHalf + retl + add %o2, 1, %o0 +ENDPROC(U1_o2_1_fp) +ENTRY(U1_gs_0) + VISExitHalf + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_0) +ENTRY(U1_gs_8) + VISExitHalf + add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, 0x8, %o0 +ENDPROC(U1_gs_8) +ENTRY(U1_gs_10) + VISExitHalf + add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, 0x10, %o0 +ENDPROC(U1_gs_10) +ENTRY(U1_o2_0) + retl + mov %o2, %o0 +ENDPROC(U1_o2_0) +ENTRY(U1_o2_8) + retl + add %o2, 8, %o0 +ENDPROC(U1_o2_8) +ENTRY(U1_o2_4) + retl + add %o2, 4, %o0 +ENDPROC(U1_o2_4) +ENTRY(U1_o2_1) + retl + add %o2, 1, %o0 +ENDPROC(U1_o2_1) +ENTRY(U1_g1_0) + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_0) +ENTRY(U1_g1_1) + add %g1, 1, %g1 + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_1) +ENTRY(U1_gs_0_o2_adj) + and %o2, 7, %o2 + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_0_o2_adj) +ENTRY(U1_gs_8_o2_adj) + and %o2, 7, %o2 + add %GLOBAL_SPARE, 8, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_8_o2_adj) +#endif + .align 64 .globl FUNC_NAME @@ -166,8 +279,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp) + EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -178,20 +291,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD_FP(LOAD(ldd, %o1, %f4)) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -214,13 +327,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %g1, %GLOBAL_SPARE, %g1 subcc %o2, %g3, %o2 - EX_LD_FP(LOAD_BLK(%o1, %f0)) + EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp) add %o1, 0x40, %o1 add %g1, %g3, %g1 - EX_LD_FP(LOAD_BLK(%o1, %f16)) + EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp) add %o1, 0x40, %o1 sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE - EX_LD_FP(LOAD_BLK(%o1, %f32)) + EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp) add %o1, 0x40, %o1 /* There are 8 instances of the unrolled loop, @@ -240,11 +353,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f0, %f2, %f48 1: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) @@ -261,11 +374,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 56f) 1: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f2, %f4, %f48 1: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) @@ -282,11 +395,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 57f) 1: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f4, %f6, %f48 1: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) @@ -303,11 +416,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 58f) 1: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f6, %f8, %f48 1: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) @@ -324,11 +437,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 59f) 1: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f8, %f10, %f48 1: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) @@ -345,11 +458,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 60f) 1: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f10, %f12, %f48 1: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) @@ -366,11 +479,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 61f) 1: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f12, %f14, %f48 1: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) @@ -387,11 +500,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 62f) 1: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f14, %f16, %f48 1: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) @@ -407,53 +520,53 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) STORE_JUMP(o0, f48, 63f) -40: FINISH_VISCHUNK(o0, f0, f2, g3) -41: FINISH_VISCHUNK(o0, f2, f4, g3) -42: FINISH_VISCHUNK(o0, f4, f6, g3) -43: FINISH_VISCHUNK(o0, f6, f8, g3) -44: FINISH_VISCHUNK(o0, f8, f10, g3) -45: FINISH_VISCHUNK(o0, f10, f12, g3) -46: FINISH_VISCHUNK(o0, f12, f14, g3) -47: UNEVEN_VISCHUNK(o0, f14, f0, g3) -48: FINISH_VISCHUNK(o0, f16, f18, g3) -49: FINISH_VISCHUNK(o0, f18, f20, g3) -50: FINISH_VISCHUNK(o0, f20, f22, g3) -51: FINISH_VISCHUNK(o0, f22, f24, g3) -52: FINISH_VISCHUNK(o0, f24, f26, g3) -53: FINISH_VISCHUNK(o0, f26, f28, g3) -54: FINISH_VISCHUNK(o0, f28, f30, g3) -55: UNEVEN_VISCHUNK(o0, f30, f0, g3) -56: FINISH_VISCHUNK(o0, f32, f34, g3) -57: FINISH_VISCHUNK(o0, f34, f36, g3) -58: FINISH_VISCHUNK(o0, f36, f38, g3) -59: FINISH_VISCHUNK(o0, f38, f40, g3) -60: FINISH_VISCHUNK(o0, f40, f42, g3) -61: FINISH_VISCHUNK(o0, f42, f44, g3) -62: FINISH_VISCHUNK(o0, f44, f46, g3) -63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3) - -93: EX_LD_FP(LOAD(ldd, %o1, %f2)) +40: FINISH_VISCHUNK(o0, f0, f2) +41: FINISH_VISCHUNK(o0, f2, f4) +42: FINISH_VISCHUNK(o0, f4, f6) +43: FINISH_VISCHUNK(o0, f6, f8) +44: FINISH_VISCHUNK(o0, f8, f10) +45: FINISH_VISCHUNK(o0, f10, f12) +46: FINISH_VISCHUNK(o0, f12, f14) +47: UNEVEN_VISCHUNK(o0, f14, f0) +48: FINISH_VISCHUNK(o0, f16, f18) +49: FINISH_VISCHUNK(o0, f18, f20) +50: FINISH_VISCHUNK(o0, f20, f22) +51: FINISH_VISCHUNK(o0, f22, f24) +52: FINISH_VISCHUNK(o0, f24, f26) +53: FINISH_VISCHUNK(o0, f26, f28) +54: FINISH_VISCHUNK(o0, f28, f30) +55: UNEVEN_VISCHUNK(o0, f30, f0) +56: FINISH_VISCHUNK(o0, f32, f34) +57: FINISH_VISCHUNK(o0, f34, f36) +58: FINISH_VISCHUNK(o0, f36, f38) +59: FINISH_VISCHUNK(o0, f38, f40) +60: FINISH_VISCHUNK(o0, f40, f42) +61: FINISH_VISCHUNK(o0, f42, f44) +62: FINISH_VISCHUNK(o0, f44, f46) +63: UNEVEN_VISCHUNK_LAST(o0, f46, f0) + +93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f0, %f2, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp) bl,pn %xcc, 95f add %o0, 8, %o0 - EX_LD_FP(LOAD(ldd, %o1, %f0)) + EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f2, %f0, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp) bge,pt %xcc, 93b add %o0, 8, %o0 95: brz,pt %o2, 2f mov %g1, %o1 -1: EX_LD_FP(LOAD(ldub, %o1, %o3)) +1: EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp) add %o1, 1, %o1 subcc %o2, 1, %o2 - EX_ST_FP(STORE(stb, %o3, %o0)) + EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp) bne,pt %xcc, 1b add %o0, 1, %o0 @@ -469,27 +582,27 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 72: andn %o2, 0xf, %GLOBAL_SPARE and %o2, 0xf, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g1)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0) + EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0) subcc %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + %o3)) + EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop - EX_LD(LOAD(ldx, %o1, %o5)) + EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0) sub %o2, 0x8, %o2 - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop - EX_LD(LOAD(lduw, %o1, %o5)) + EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0) sub %o2, 0x4, %o2 - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -503,9 +616,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %g1, %g1 sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1, %o5)) +1: EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0) subcc %g1, 1, %g1 - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -521,16 +634,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, %o3 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0) sub %o3, %g1, %o3 andn %o2, 0x7, %GLOBAL_SPARE sllx %g2, %g1, %g2 -1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj) subcc %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE add %o1, 0x8, %o1 srlx %g3, %o3, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -548,9 +661,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ bne,pn %XCC, 90f sub %o0, %o1, %o3 -1: EX_LD(LOAD(lduw, %o1, %g1)) +1: EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0) subcc %o2, 4, %o2 - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -558,9 +671,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov EX_RETVAL(%o4), %o0 .align 32 -90: EX_LD(LOAD(ldub, %o1, %g1)) +90: EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0) subcc %o2, 1, %o2 - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index 88ad73d86..db73010a1 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index 845139d75..c4ee858e3 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S index 491ee69e4..54f98706b 100644 --- a/arch/sparc/lib/U3memcpy.S +++ b/arch/sparc/lib/U3memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include #include #include #define GLOBAL_SPARE %g7 @@ -22,21 +23,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -77,6 +74,87 @@ */ .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_fp: + VISExitHalf + retl + nop +ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) + add %g1, 1, %g1 + add %g2, %g1, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) +ENTRY(U3_retl_o2_plus_g2_fp) + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_fp) +ENTRY(U3_retl_o2_plus_g2_plus_8_fp) + add %g2, 8, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_8_fp) +ENTRY(U3_retl_o2) + retl + mov %o2, %o0 +ENDPROC(U3_retl_o2) +ENTRY(U3_retl_o2_plus_1) + retl + add %o2, 1, %o0 +ENDPROC(U3_retl_o2_plus_1) +ENTRY(U3_retl_o2_plus_4) + retl + add %o2, 4, %o0 +ENDPROC(U3_retl_o2_plus_4) +ENTRY(U3_retl_o2_plus_8) + retl + add %o2, 8, %o0 +ENDPROC(U3_retl_o2_plus_8) +ENTRY(U3_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + retl + add %o2, %g1, %o0 +ENDPROC(U3_retl_o2_plus_g1_plus_1) +ENTRY(U3_retl_o2_fp) + ba,pt %xcc, __restore_fp + mov %o2, %o0 +ENDPROC(U3_retl_o2_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) + sll %o3, 6, %o3 + add %o3, 0x80, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) + sll %o3, 6, %o3 + add %o3, 0x40, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) +ENTRY(U3_retl_o2_plus_GS_plus_0x10) + add GLOBAL_SPARE, 0x10, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x10) +ENTRY(U3_retl_o2_plus_GS_plus_0x08) + add GLOBAL_SPARE, 0x08, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x08) +ENTRY(U3_retl_o2_and_7_plus_GS) + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o2 +ENDPROC(U3_retl_o2_and_7_plus_GS) +ENTRY(U3_retl_o2_and_7_plus_GS_plus_8) + add GLOBAL_SPARE, 8, GLOBAL_SPARE + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o2 +ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8) +#endif + .align 64 /* The cheetah's flexible spine, oversized liver, enlarged heart, @@ -126,8 +204,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -138,20 +216,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD_FP(LOAD(ldd, %o1, %f4)) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f2 - EX_ST_FP(STORE(std, %f2, %o0)) + EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -161,25 +239,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ LOAD(prefetch, %o1 + 0x080, #one_read) LOAD(prefetch, %o1 + 0x0c0, #one_read) LOAD(prefetch, %o1 + 0x100, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2) LOAD(prefetch, %o1 + 0x140, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2) LOAD(prefetch, %o1 + 0x180, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2) faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2) faligndata %f8, %f10, %f24 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2) faligndata %f10, %f12, %f26 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2) subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE add %o1, 0x40, %o1 @@ -190,26 +268,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f12, %f14, %f28 - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f0, %f2, %f16 add %o0, 0x40, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) subcc %o3, 0x01, %o3 faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f8, %f10, %f24 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f10, %f12, %f26 bg,pt %XCC, 1b @@ -217,29 +295,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ /* Finally we copy the last full 64-byte block. */ 2: - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f12, %f14, %f28 - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f8, %f10, %f24 cmp %g1, 0 be,pt %XCC, 1f add %o0, 0x40, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40) 1: faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40) add %o0, 0x40, %o0 add %o1, 0x40, %o1 membar #Sync @@ -259,20 +337,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g2, %o2 be,a,pt %XCC, 1f - EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f0, %f2, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) be,pn %XCC, 2f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f2, %f0, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) bne,pn %XCC, 1b add %o0, 0x8, %o0 @@ -292,30 +370,33 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andcc %o2, 0x8, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x8, %o1 + sub %o2, 8, %o2 1: andcc %o2, 0x4, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x4, %o1 + sub %o2, 4, %o2 1: andcc %o2, 0x2, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(lduh, %o1, %o5)) - EX_ST(STORE(sth, %o5, %o1 + %o3)) + EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2) + EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x2, %o1 + sub %o2, 2, %o2 1: andcc %o2, 0x1, %g0 be,pt %icc, 85f nop - EX_LD(LOAD(ldub, %o1, %o5)) + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2) ba,pt %xcc, 85f - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2) .align 64 70: /* 16 < len <= 64 */ @@ -326,26 +407,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0xf, GLOBAL_SPARE and %o2, 0xf, %o2 1: subcc GLOBAL_SPARE, 0x10, GLOBAL_SPARE - EX_LD(LOAD(ldx, %o1 + 0x00, %o5)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g1)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10) + EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + %o3)) + EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop sub %o2, 0x8, %o2 - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -361,8 +442,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g1, %o2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %o1, %o5)) - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1) + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -378,16 +459,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, %o3 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2) sub %o3, %g1, %o3 andn %o2, 0x7, GLOBAL_SPARE sllx %g2, %g1, %g2 -1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS) subcc GLOBAL_SPARE, 0x8, GLOBAL_SPARE add %o1, 0x8, %o1 srlx %g3, %o3, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -407,8 +488,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -418,8 +499,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1) + EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S index 302c0e60d..4c89b486f 100644 --- a/arch/sparc/lib/copy_in_user.S +++ b/arch/sparc/lib/copy_in_user.S @@ -8,18 +8,33 @@ #define XCC xcc -#define EX(x,y) \ +#define EX(x,y,z) \ 98: x,y; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, z; \ .text; \ .align 4; +#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8) +#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4) +#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1) + .register %g2,#scratch .register %g3,#scratch .text +__retl_o4_plus_8: + add %o4, %o2, %o4 + retl + add %o4, 8, %o0 +__retl_o2_plus_4: + retl + add %o2, 4, %o0 +__retl_o2_plus_1: + retl + add %o2, 1, %o0 + .align 32 /* Don't try to get too fancy here, just nice and @@ -44,8 +59,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x7, %o4 and %o2, 0x7, %o2 1: subcc %o4, 0x8, %o4 - EX(ldxa [%o1] %asi, %o5) - EX(stxa %o5, [%o0] %asi) + EX_O4(ldxa [%o1] %asi, %o5) + EX_O4(stxa %o5, [%o0] %asi) add %o1, 0x8, %o1 bgu,pt %XCC, 1b add %o0, 0x8, %o0 @@ -53,8 +68,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX(lduwa [%o1] %asi, %o5) - EX(stwa %o5, [%o0] %asi) + EX_O2_4(lduwa [%o1] %asi, %o5) + EX_O2_4(stwa %o5, [%o0] %asi) add %o1, 0x4, %o1 add %o0, 0x4, %o0 1: cmp %o2, 0 @@ -70,8 +85,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ 82: subcc %o2, 4, %o2 - EX(lduwa [%o1] %asi, %g1) - EX(stwa %g1, [%o0] %asi) + EX_O2_4(lduwa [%o1] %asi, %g1) + EX_O2_4(stwa %g1, [%o0] %asi) add %o1, 4, %o1 bgu,pt %XCC, 82b add %o0, 4, %o0 @@ -82,8 +97,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX(lduba [%o1] %asi, %g1) - EX(stba %g1, [%o0] %asi) + EX_O2_1(lduba [%o1] %asi, %g1) + EX_O2_1(stba %g1, [%o0] %asi) add %o1, 1, %o1 bgu,pt %XCC, 90b add %o0, 1, %o0 diff --git a/arch/sparc/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c deleted file mode 100644 index ac96ae236..000000000 --- a/arch/sparc/lib/user_fixup.c +++ /dev/null @@ -1,71 +0,0 @@ -/* user_fixup.c: Fix up user copy faults. - * - * Copyright (C) 2004 David S. Miller - */ - -#include -#include -#include -#include -#include - -#include - -/* Calculating the exact fault address when using - * block loads and stores can be very complicated. - * - * Instead of trying to be clever and handling all - * of the cases, just fix things up simply here. - */ - -static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset) -{ - unsigned long fault_addr = current_thread_info()->fault_address; - unsigned long end = start + size; - - if (fault_addr < start || fault_addr >= end) { - *offset = 0; - } else { - *offset = fault_addr - start; - size = end - fault_addr; - } - return size; -} - -unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size) -{ - unsigned long offset; - - size = compute_size((unsigned long) from, size, &offset); - if (likely(size)) - memset(to + offset, 0, size); - - return size; -} -EXPORT_SYMBOL(copy_from_user_fixup); - -unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size) -{ - unsigned long offset; - - return compute_size((unsigned long) to, size, &offset); -} -EXPORT_SYMBOL(copy_to_user_fixup); - -unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size) -{ - unsigned long fault_addr = current_thread_info()->fault_address; - unsigned long start = (unsigned long) to; - unsigned long end = start + size; - - if (fault_addr >= start && fault_addr < end) - return end - fault_addr; - - start = (unsigned long) from; - end = start + size; - if (fault_addr >= start && fault_addr < end) - return end - fault_addr; - - return size; -} -EXPORT_SYMBOL(copy_in_user_fixup); diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index f2b77112e..e20fbbafb 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr) return (tag == (vaddr >> 22)); } +static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end) +{ + unsigned long idx; + + for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) { + struct tsb *ent = &swapper_tsb[idx]; + unsigned long match = idx << 13; + + match |= (ent->tag << 22); + if (match >= start && match < end) + ent->tag = (1UL << TSB_TAG_INVALID_BIT); + } +} + /* TSB flushes need only occur on the processor initiating the address * space modification, not on each cpu the address space has run on. * Only the TLB flush needs that treatment. @@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) { unsigned long v; + if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES) + return flush_tsb_kernel_range_scan(start, end); + for (v = start; v < end; v += PAGE_SIZE) { unsigned long hash = tsb_hash(v, PAGE_SHIFT, KERNEL_TSB_NENTRIES); diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index b4f4733ab..5d2fd6cd3 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -30,7 +30,7 @@ .text .align 32 .globl __flush_tlb_mm -__flush_tlb_mm: /* 18 insns */ +__flush_tlb_mm: /* 19 insns */ /* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */ ldxa [%o1] ASI_DMMU, %g2 cmp %g2, %o0 @@ -81,7 +81,7 @@ __flush_tlb_page: /* 22 insns */ .align 32 .globl __flush_tlb_pending -__flush_tlb_pending: /* 26 insns */ +__flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 sllx %o1, 3, %o1 @@ -113,12 +113,14 @@ __flush_tlb_pending: /* 26 insns */ .align 32 .globl __flush_tlb_kernel_range -__flush_tlb_kernel_range: /* 16 insns */ +__flush_tlb_kernel_range: /* 31 insns */ /* %o0=start, %o1=end */ cmp %o0, %o1 be,pn %xcc, 2f + sub %o1, %o0, %o3 + srlx %o3, 18, %o4 + brnz,pn %o4, __spitfire_flush_tlb_kernel_range_slow sethi %hi(PAGE_SIZE), %o4 - sub %o1, %o0, %o3 sub %o3, %o4, %o3 or %o0, 0x20, %o0 ! Nucleus 1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP @@ -131,6 +133,41 @@ __flush_tlb_kernel_range: /* 16 insns */ retl nop nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + +__spitfire_flush_tlb_kernel_range_slow: + mov 63 * 8, %o4 +1: ldxa [%o4] ASI_ITLB_DATA_ACCESS, %o3 + andcc %o3, 0x40, %g0 /* _PAGE_L_4U */ + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %o3 + stxa %g0, [%o3] ASI_IMMU + stxa %g0, [%o4] ASI_ITLB_DATA_ACCESS + membar #Sync +2: ldxa [%o4] ASI_DTLB_DATA_ACCESS, %o3 + andcc %o3, 0x40, %g0 + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %o3 + stxa %g0, [%o3] ASI_DMMU + stxa %g0, [%o4] ASI_DTLB_DATA_ACCESS + membar #Sync +2: sub %o4, 8, %o4 + brgez,pt %o4, 1b + nop + retl + nop __spitfire_flush_tlb_mm_slow: rdpr %pstate, %g1 @@ -285,6 +322,40 @@ __cheetah_flush_tlb_pending: /* 27 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_kernel_range: /* 31 insns */ + /* %o0=start, %o1=end */ + cmp %o0, %o1 + be,pn %xcc, 2f + sub %o1, %o0, %o3 + srlx %o3, 18, %o4 + brnz,pn %o4, 3f + sethi %hi(PAGE_SIZE), %o4 + sub %o3, %o4, %o3 + or %o0, 0x20, %o0 ! Nucleus +1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP + stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %o3, 1b + sub %o3, %o4, %o3 +2: sethi %hi(KERNBASE), %o3 + flush %o3 + retl + nop +3: mov 0x80, %o4 + stxa %g0, [%o4] ASI_DMMU_DEMAP + membar #Sync + stxa %g0, [%o4] ASI_IMMU_DEMAP + membar #Sync + retl + nop + nop + nop + nop + nop + nop + nop + nop + #ifdef DCACHE_ALIASING_POSSIBLE __cheetah_flush_dcache_page: /* 11 insns */ sethi %hi(PAGE_OFFSET), %g1 @@ -309,19 +380,28 @@ __hypervisor_tlb_tl0_error: ret restore -__hypervisor_flush_tlb_mm: /* 10 insns */ +__hypervisor_flush_tlb_mm: /* 19 insns */ mov %o0, %o2 /* ARG2: mmu context */ mov 0, %o0 /* ARG0: CPU lists unimplemented */ mov 0, %o1 /* ARG1: CPU lists unimplemented */ mov HV_MMU_ALL, %o3 /* ARG3: flags */ mov HV_FAST_MMU_DEMAP_CTX, %o5 ta HV_FAST_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_FAST_MMU_DEMAP_CTX, %o1 retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o5 + jmpl %o5 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_page: /* 11 insns */ +__hypervisor_flush_tlb_page: /* 22 insns */ /* %o0 = context, %o1 = vaddr */ mov %o0, %g2 mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ @@ -330,12 +410,23 @@ __hypervisor_flush_tlb_page: /* 11 insns */ srlx %o0, PAGE_SHIFT, %o0 sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_pending: /* 16 insns */ +__hypervisor_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 mov %o2, %g2 @@ -347,31 +438,57 @@ __hypervisor_flush_tlb_pending: /* 16 insns */ srlx %o0, PAGE_SHIFT, %o0 sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 brnz,pt %g1, 1b nop retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_kernel_range: /* 16 insns */ +__hypervisor_flush_tlb_kernel_range: /* 31 insns */ /* %o0=start, %o1=end */ cmp %o0, %o1 be,pn %xcc, 2f - sethi %hi(PAGE_SIZE), %g3 - mov %o0, %g1 - sub %o1, %g1, %g2 + sub %o1, %o0, %g2 + srlx %g2, 18, %g3 + brnz,pn %g3, 4f + mov %o0, %g1 + sethi %hi(PAGE_SIZE), %g3 sub %g2, %g3, %g2 1: add %g1, %g2, %o0 /* ARG0: virtual address */ mov 0, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 3f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 brnz,pt %g2, 1b sub %g2, %g3, %g2 2: retl nop +3: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop +4: mov 0, %o0 /* ARG0: CPU lists unimplemented */ + mov 0, %o1 /* ARG1: CPU lists unimplemented */ + mov 0, %o2 /* ARG2: mmu context == nucleus */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + brnz,pn %o0, 3b + mov HV_FAST_MMU_DEMAP_CTX, %o1 + retl + nop #ifdef DCACHE_ALIASING_POSSIBLE /* XXX Niagara and friends have an 8K cache, so no aliasing is @@ -394,43 +511,6 @@ tlb_patch_one: retl nop - .globl cheetah_patch_cachetlbops -cheetah_patch_cachetlbops: - save %sp, -128, %sp - - sethi %hi(__flush_tlb_mm), %o0 - or %o0, %lo(__flush_tlb_mm), %o0 - sethi %hi(__cheetah_flush_tlb_mm), %o1 - or %o1, %lo(__cheetah_flush_tlb_mm), %o1 - call tlb_patch_one - mov 19, %o2 - - sethi %hi(__flush_tlb_page), %o0 - or %o0, %lo(__flush_tlb_page), %o0 - sethi %hi(__cheetah_flush_tlb_page), %o1 - or %o1, %lo(__cheetah_flush_tlb_page), %o1 - call tlb_patch_one - mov 22, %o2 - - sethi %hi(__flush_tlb_pending), %o0 - or %o0, %lo(__flush_tlb_pending), %o0 - sethi %hi(__cheetah_flush_tlb_pending), %o1 - or %o1, %lo(__cheetah_flush_tlb_pending), %o1 - call tlb_patch_one - mov 27, %o2 - -#ifdef DCACHE_ALIASING_POSSIBLE - sethi %hi(__flush_dcache_page), %o0 - or %o0, %lo(__flush_dcache_page), %o0 - sethi %hi(__cheetah_flush_dcache_page), %o1 - or %o1, %lo(__cheetah_flush_dcache_page), %o1 - call tlb_patch_one - mov 11, %o2 -#endif /* DCACHE_ALIASING_POSSIBLE */ - - ret - restore - #ifdef CONFIG_SMP /* These are all called by the slaves of a cross call, at * trap level 1, with interrupts fully disabled. @@ -447,7 +527,7 @@ cheetah_patch_cachetlbops: */ .align 32 .globl xcall_flush_tlb_mm -xcall_flush_tlb_mm: /* 21 insns */ +xcall_flush_tlb_mm: /* 24 insns */ mov PRIMARY_CONTEXT, %g2 ldxa [%g2] ASI_DMMU, %g3 srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -469,9 +549,12 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop nop + nop + nop + nop .globl xcall_flush_tlb_page -xcall_flush_tlb_page: /* 17 insns */ +xcall_flush_tlb_page: /* 20 insns */ /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 @@ -490,15 +573,20 @@ xcall_flush_tlb_page: /* 17 insns */ retry nop nop + nop + nop + nop .globl xcall_flush_tlb_kernel_range -xcall_flush_tlb_kernel_range: /* 25 insns */ +xcall_flush_tlb_kernel_range: /* 44 insns */ sethi %hi(PAGE_SIZE - 1), %g2 or %g2, %lo(PAGE_SIZE - 1), %g2 andn %g1, %g2, %g1 andn %g7, %g2, %g7 sub %g7, %g1, %g3 - add %g2, 1, %g2 + srlx %g3, 18, %g2 + brnz,pn %g2, 2f + add %g2, 1, %g2 sub %g3, %g2, %g3 or %g1, 0x20, %g1 ! Nucleus 1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP @@ -507,8 +595,25 @@ xcall_flush_tlb_kernel_range: /* 25 insns */ brnz,pt %g3, 1b sub %g3, %g2, %g3 retry - nop - nop +2: mov 63 * 8, %g1 +1: ldxa [%g1] ASI_ITLB_DATA_ACCESS, %g2 + andcc %g2, 0x40, %g0 /* _PAGE_L_4U */ + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %g2 + stxa %g0, [%g2] ASI_IMMU + stxa %g0, [%g1] ASI_ITLB_DATA_ACCESS + membar #Sync +2: ldxa [%g1] ASI_DTLB_DATA_ACCESS, %g2 + andcc %g2, 0x40, %g0 + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %g2 + stxa %g0, [%g2] ASI_DMMU + stxa %g0, [%g1] ASI_DTLB_DATA_ACCESS + membar #Sync +2: sub %g1, 8, %g1 + brgez,pt %g1, 1b + nop + retry nop nop nop @@ -637,6 +742,52 @@ xcall_fetch_glob_pmu_n4: retry +__cheetah_xcall_flush_tlb_kernel_range: /* 44 insns */ + sethi %hi(PAGE_SIZE - 1), %g2 + or %g2, %lo(PAGE_SIZE - 1), %g2 + andn %g1, %g2, %g1 + andn %g7, %g2, %g7 + sub %g7, %g1, %g3 + srlx %g3, 18, %g2 + brnz,pn %g2, 2f + add %g2, 1, %g2 + sub %g3, %g2, %g3 + or %g1, 0x20, %g1 ! Nucleus +1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP + stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %g3, 1b + sub %g3, %g2, %g3 + retry +2: mov 0x80, %g2 + stxa %g0, [%g2] ASI_DMMU_DEMAP + membar #Sync + stxa %g0, [%g2] ASI_IMMU_DEMAP + membar #Sync + retry + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + #ifdef DCACHE_ALIASING_POSSIBLE .align 32 .globl xcall_flush_dcache_page_cheetah @@ -700,7 +851,7 @@ __hypervisor_tlb_xcall_error: ba,a,pt %xcc, rtrap .globl __hypervisor_xcall_flush_tlb_mm -__hypervisor_xcall_flush_tlb_mm: /* 21 insns */ +__hypervisor_xcall_flush_tlb_mm: /* 24 insns */ /* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */ mov %o0, %g2 mov %o1, %g3 @@ -714,7 +865,7 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ mov HV_FAST_MMU_DEMAP_CTX, %o5 ta HV_FAST_TRAP mov HV_FAST_MMU_DEMAP_CTX, %g6 - brnz,pn %o0, __hypervisor_tlb_xcall_error + brnz,pn %o0, 1f mov %o0, %g5 mov %g2, %o0 mov %g3, %o1 @@ -723,9 +874,12 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ mov %g7, %o5 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop .globl __hypervisor_xcall_flush_tlb_page -__hypervisor_xcall_flush_tlb_page: /* 17 insns */ +__hypervisor_xcall_flush_tlb_page: /* 20 insns */ /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 @@ -737,42 +891,64 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */ sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP mov HV_MMU_UNMAP_ADDR_TRAP, %g6 - brnz,a,pn %o0, __hypervisor_tlb_xcall_error + brnz,a,pn %o0, 1f mov %o0, %g5 mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop .globl __hypervisor_xcall_flush_tlb_kernel_range -__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */ +__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */ /* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */ sethi %hi(PAGE_SIZE - 1), %g2 or %g2, %lo(PAGE_SIZE - 1), %g2 andn %g1, %g2, %g1 andn %g7, %g2, %g7 sub %g7, %g1, %g3 + srlx %g3, 18, %g7 add %g2, 1, %g2 sub %g3, %g2, %g3 mov %o0, %g2 mov %o1, %g4 - mov %o2, %g7 + brnz,pn %g7, 2f + mov %o2, %g7 1: add %g1, %g3, %o0 /* ARG0: virtual address */ mov 0, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ ta HV_MMU_UNMAP_ADDR_TRAP mov HV_MMU_UNMAP_ADDR_TRAP, %g6 - brnz,pn %o0, __hypervisor_tlb_xcall_error + brnz,pn %o0, 1f mov %o0, %g5 sethi %hi(PAGE_SIZE), %o2 brnz,pt %g3, 1b sub %g3, %o2, %g3 - mov %g2, %o0 +5: mov %g2, %o0 mov %g4, %o1 mov %g7, %o2 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop +2: mov %o3, %g1 + mov %o5, %g3 + mov 0, %o0 /* ARG0: CPU lists unimplemented */ + mov 0, %o1 /* ARG1: CPU lists unimplemented */ + mov 0, %o2 /* ARG2: mmu context == nucleus */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + mov %g1, %o3 + brz,pt %o0, 5b + mov %g3, %o5 + mov HV_FAST_MMU_DEMAP_CTX, %g6 + ba,pt %xcc, 1b + clr %g5 /* These just get rescheduled to PIL vectors. */ .globl xcall_call_function @@ -809,6 +985,58 @@ xcall_kgdb_capture: #endif /* CONFIG_SMP */ + .globl cheetah_patch_cachetlbops +cheetah_patch_cachetlbops: + save %sp, -128, %sp + + sethi %hi(__flush_tlb_mm), %o0 + or %o0, %lo(__flush_tlb_mm), %o0 + sethi %hi(__cheetah_flush_tlb_mm), %o1 + or %o1, %lo(__cheetah_flush_tlb_mm), %o1 + call tlb_patch_one + mov 19, %o2 + + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + + sethi %hi(__flush_tlb_pending), %o0 + or %o0, %lo(__flush_tlb_pending), %o0 + sethi %hi(__cheetah_flush_tlb_pending), %o1 + or %o1, %lo(__cheetah_flush_tlb_pending), %o1 + call tlb_patch_one + mov 27, %o2 + + sethi %hi(__flush_tlb_kernel_range), %o0 + or %o0, %lo(__flush_tlb_kernel_range), %o0 + sethi %hi(__cheetah_flush_tlb_kernel_range), %o1 + or %o1, %lo(__cheetah_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 31, %o2 + +#ifdef DCACHE_ALIASING_POSSIBLE + sethi %hi(__flush_dcache_page), %o0 + or %o0, %lo(__flush_dcache_page), %o0 + sethi %hi(__cheetah_flush_dcache_page), %o1 + or %o1, %lo(__cheetah_flush_dcache_page), %o1 + call tlb_patch_one + mov 11, %o2 +#endif /* DCACHE_ALIASING_POSSIBLE */ + +#ifdef CONFIG_SMP + sethi %hi(xcall_flush_tlb_kernel_range), %o0 + or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 + sethi %hi(__cheetah_xcall_flush_tlb_kernel_range), %o1 + or %o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 44, %o2 +#endif /* CONFIG_SMP */ + + ret + restore .globl hypervisor_patch_cachetlbops hypervisor_patch_cachetlbops: @@ -819,28 +1047,28 @@ hypervisor_patch_cachetlbops: sethi %hi(__hypervisor_flush_tlb_mm), %o1 or %o1, %lo(__hypervisor_flush_tlb_mm), %o1 call tlb_patch_one - mov 10, %o2 + mov 19, %o2 sethi %hi(__flush_tlb_page), %o0 or %o0, %lo(__flush_tlb_page), %o0 sethi %hi(__hypervisor_flush_tlb_page), %o1 or %o1, %lo(__hypervisor_flush_tlb_page), %o1 call tlb_patch_one - mov 11, %o2 + mov 22, %o2 sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 or %o1, %lo(__hypervisor_flush_tlb_pending), %o1 call tlb_patch_one - mov 16, %o2 + mov 27, %o2 sethi %hi(__flush_tlb_kernel_range), %o0 or %o0, %lo(__flush_tlb_kernel_range), %o0 sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1 or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1 call tlb_patch_one - mov 16, %o2 + mov 31, %o2 #ifdef DCACHE_ALIASING_POSSIBLE sethi %hi(__flush_dcache_page), %o0 @@ -857,21 +1085,21 @@ hypervisor_patch_cachetlbops: sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1 call tlb_patch_one - mov 21, %o2 + mov 24, %o2 sethi %hi(xcall_flush_tlb_page), %o0 or %o0, %lo(xcall_flush_tlb_page), %o0 sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 17, %o2 + mov 20, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1 call tlb_patch_one - mov 25, %o2 + mov 44, %o2 #endif /* CONFIG_SMP */ ret diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 824c48d6a..5fa6ee2c2 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -54,7 +54,7 @@ CONFIG_HIGHPTE=y CONFIG_X86_CHECK_BIOS_CORRUPTION=y # CONFIG_MTRR_SANITIZER is not set CONFIG_EFI=y -CONFIG_HZ_100=y +CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y # CONFIG_COMPAT_VDSO is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index b8c4f668c..d28bdabcc 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -52,7 +52,7 @@ CONFIG_NUMA=y CONFIG_X86_CHECK_BIOS_CORRUPTION=y # CONFIG_MTRR_SANITIZER is not set CONFIG_EFI=y -CONFIG_HZ_100=y +CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y # CONFIG_COMPAT_VDSO is not set diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 77f28ce9c..9976fcecd 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,8 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y -CFLAGS_syscall_64.o += -Wno-override-init -CFLAGS_syscall_32.o += -Wno-override-init +CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index fbd194444..d99ca57cb 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -453,6 +453,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here diff --git a/block/Kconfig b/block/Kconfig index 161491d0a..6da79e670 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -4,6 +4,7 @@ menuconfig BLOCK bool "Enable the block layer" if EXPERT default y + select WBT help Provide block layer support for the kernel. diff --git a/block/Makefile b/block/Makefile index 4a3668393..b7aa613b4 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-flush.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ - blk-lib.o blk-mq.o blk-mq-tag.o \ + blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \ genhd.o scsi_ioctl.o partition-generic.o ioprio.o \ badblocks.o partitions/ diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index b50ae8ec6..569988bda 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -649,6 +649,18 @@ static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) goto out; + /* + * If we have a non-root cgroup, we can depend on that to + * do proper throttling of writes. Turn off wbt for that + * case. + */ + if (bio_blkcg(bio) != &blkcg_root) { + struct request_queue *q = bfqd->queue; + + if (q->rq_wb) + wbt_disable(q->rq_wb); + } + bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio)); bic->blkcg_serial_nr = serial_nr; out: diff --git a/block/blk-core.c b/block/blk-core.c index 36c7ac328..cdcb188e8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -33,6 +33,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -882,6 +883,8 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, fail: blk_free_flush_queue(q->fq); + wbt_exit(q->rq_wb); + q->rq_wb = NULL; return NULL; } EXPORT_SYMBOL(blk_init_allocated_queue); @@ -1346,6 +1349,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) blk_delete_timer(rq); blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); + wbt_requeue(q->rq_wb, &rq->wb_stat); if (rq->cmd_flags & REQ_QUEUED) blk_queue_end_tag(q, rq); @@ -1436,6 +1440,8 @@ void __blk_put_request(struct request_queue *q, struct request *req) /* this is a bio leak */ WARN_ON(req->bio != NULL); + wbt_done(q->rq_wb, &req->wb_stat); + /* * Request may not have originated from ll_rw_blk. if not, * it didn't come out of our reserved rq pools @@ -1667,6 +1673,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT; struct request *req; unsigned int request_count = 0; + unsigned int wb_acct; /* * low level driver can indicate that it wants pages above a @@ -1719,6 +1726,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) } get_rq: + wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, q->queue_lock); + /* * This sync check and mask will be re-done in init_request_from_bio(), * but we need to set it earlier to expose the sync flag to the @@ -1738,11 +1747,14 @@ get_rq: */ req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO); if (IS_ERR(req)) { + __wbt_done(q->rq_wb, wb_acct); bio->bi_error = PTR_ERR(req); bio_endio(bio); goto out_unlock; } + wbt_track(&req->wb_stat, wb_acct); + /* * After dropping the lock and possibly sleeping here, our request * may now be mergeable after it had proven unmergeable (above). @@ -2475,6 +2487,8 @@ void blk_start_request(struct request *req) { blk_dequeue_request(req); + wbt_issue(req->q->rq_wb, &req->wb_stat); + /* * We are now handing the request to the hardware, initialize * resid_len to full count and add the timeout handler. @@ -2542,6 +2556,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) trace_block_rq_complete(req->q, req, nr_bytes); + blk_stat_add(&req->q->rq_stats[rq_data_dir(req)], req); + if (!req->bio) return false; @@ -2709,9 +2725,10 @@ void blk_finish_request(struct request *req, int error) blk_account_io_done(req); - if (req->end_io) + if (req->end_io) { + wbt_done(req->q->rq_wb, &req->wb_stat); req->end_io(req, error); - else { + } else { if (blk_bidi_rq(req)) __blk_put_request(req->next_rq->q, req->next_rq); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index fe822aa5b..b66bbf13c 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -247,6 +247,47 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) return ret; } +static void blk_mq_stat_clear(struct blk_mq_hw_ctx *hctx) +{ + struct blk_mq_ctx *ctx; + unsigned int i; + + hctx_for_each_ctx(hctx, ctx, i) { + blk_stat_init(&ctx->stat[0]); + blk_stat_init(&ctx->stat[1]); + } +} + +static ssize_t blk_mq_hw_sysfs_stat_store(struct blk_mq_hw_ctx *hctx, + const char *page, size_t count) +{ + blk_mq_stat_clear(hctx); + return count; +} + +static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre) +{ + return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n", + pre, (long long) stat->nr_samples, + (long long) stat->mean, (long long) stat->min, + (long long) stat->max); +} + +static ssize_t blk_mq_hw_sysfs_stat_show(struct blk_mq_hw_ctx *hctx, char *page) +{ + struct blk_rq_stat stat[2]; + ssize_t ret; + + blk_stat_init(&stat[0]); + blk_stat_init(&stat[1]); + + blk_hctx_stat_get(hctx, stat); + + ret = print_stat(page, &stat[0], "read :"); + ret += print_stat(page + ret, &stat[1], "write:"); + return ret; +} + static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = { .attr = {.name = "dispatched", .mode = S_IRUGO }, .show = blk_mq_sysfs_dispatched_show, @@ -304,6 +345,11 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = { .attr = {.name = "io_poll", .mode = S_IRUGO }, .show = blk_mq_hw_sysfs_poll_show, }; +static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_stat = { + .attr = {.name = "stats", .mode = S_IRUGO | S_IWUSR }, + .show = blk_mq_hw_sysfs_stat_show, + .store = blk_mq_hw_sysfs_stat_store, +}; static struct attribute *default_hw_ctx_attrs[] = { &blk_mq_hw_sysfs_queued.attr, @@ -314,6 +360,7 @@ static struct attribute *default_hw_ctx_attrs[] = { &blk_mq_hw_sysfs_cpus.attr, &blk_mq_hw_sysfs_active.attr, &blk_mq_hw_sysfs_poll.attr, + &blk_mq_hw_sysfs_stat.attr, NULL, }; diff --git a/block/blk-mq.c b/block/blk-mq.c index c207fa987..815e2ac02 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -29,6 +30,7 @@ #include "blk.h" #include "blk-mq.h" #include "blk-mq-tag.h" +#include "blk-stat.h" static DEFINE_MUTEX(all_q_mutex); static LIST_HEAD(all_q_list); @@ -330,6 +332,8 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, if (rq->cmd_flags & REQ_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); + + wbt_done(q->rq_wb, &rq->wb_stat); rq->cmd_flags = 0; clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); @@ -362,6 +366,7 @@ inline void __blk_mq_end_request(struct request *rq, int error) blk_account_io_done(rq); if (rq->end_io) { + wbt_done(rq->q->rq_wb, &rq->wb_stat); rq->end_io(rq, error); } else { if (unlikely(blk_bidi_rq(rq))) @@ -412,10 +417,19 @@ static void blk_mq_ipi_complete_request(struct request *rq) put_cpu(); } +static void blk_mq_stat_add(struct request *rq) +{ + struct blk_rq_stat *stat = &rq->mq_ctx->stat[rq_data_dir(rq)]; + + blk_stat_add(stat, rq); +} + static void __blk_mq_complete_request(struct request *rq) { struct request_queue *q = rq->q; + blk_mq_stat_add(rq); + if (!q->softirq_done_fn) blk_mq_end_request(rq, rq->errors); else @@ -459,6 +473,8 @@ void blk_mq_start_request(struct request *rq) if (unlikely(blk_bidi_rq(rq))) rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq); + wbt_issue(q->rq_wb, &rq->wb_stat); + blk_add_timer(rq); /* @@ -494,6 +510,7 @@ static void __blk_mq_requeue_request(struct request *rq) struct request_queue *q = rq->q; trace_block_rq_requeue(q, rq); + wbt_requeue(q->rq_wb, &rq->wb_stat); if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) { if (q->dma_drain_size && blk_rq_bytes(rq)) @@ -1312,6 +1329,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) struct blk_plug *plug; struct request *same_queue_rq = NULL; blk_qc_t cookie; + unsigned int wb_acct; blk_queue_bounce(q, &bio); @@ -1326,9 +1344,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) return BLK_QC_T_NONE; + wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, NULL); + rq = blk_mq_map_request(q, bio, &data); - if (unlikely(!rq)) + if (unlikely(!rq)) { + __wbt_done(q->rq_wb, wb_acct); return BLK_QC_T_NONE; + } + + wbt_track(&rq->wb_stat, wb_acct); cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); @@ -1405,6 +1429,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) struct blk_map_ctx data; struct request *rq; blk_qc_t cookie; + unsigned int wb_acct; blk_queue_bounce(q, &bio); @@ -1421,9 +1446,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) } else request_count = blk_plug_queued_count(q); + wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, NULL); + rq = blk_mq_map_request(q, bio, &data); - if (unlikely(!rq)) + if (unlikely(!rq)) { + __wbt_done(q->rq_wb, wb_acct); return BLK_QC_T_NONE; + } + + wbt_track(&rq->wb_stat, wb_acct); cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); @@ -1807,6 +1838,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, spin_lock_init(&__ctx->lock); INIT_LIST_HEAD(&__ctx->rq_list); __ctx->queue = q; + blk_stat_init(&__ctx->stat[0]); + blk_stat_init(&__ctx->stat[1]); /* If the cpu isn't online, the cpu is mapped to first hctx */ if (!cpu_online(i)) @@ -2145,6 +2178,9 @@ void blk_mq_free_queue(struct request_queue *q) list_del_init(&q->all_q_node); mutex_unlock(&all_q_mutex); + wbt_exit(q->rq_wb); + q->rq_wb = NULL; + blk_mq_del_queue_tag_set(q); blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); diff --git a/block/blk-mq.h b/block/blk-mq.h index 9087b1103..e107f700f 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -1,6 +1,8 @@ #ifndef INT_BLK_MQ_H #define INT_BLK_MQ_H +#include "blk-stat.h" + struct blk_mq_tag_set; struct blk_mq_ctx { @@ -20,6 +22,7 @@ struct blk_mq_ctx { /* incremented at completion time */ unsigned long ____cacheline_aligned_in_smp rq_completed[2]; + struct blk_rq_stat stat[2]; struct request_queue *queue; struct kobject kobj; diff --git a/block/blk-settings.c b/block/blk-settings.c index f679ae122..746dc9fee 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -831,6 +831,19 @@ void blk_queue_flush_queueable(struct request_queue *q, bool queueable) } EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); +/** + * blk_set_queue_depth - tell the block layer about the device queue depth + * @q: the request queue for the device + * @depth: queue depth + * + */ +void blk_set_queue_depth(struct request_queue *q, unsigned int depth) +{ + q->queue_depth = depth; + wbt_set_queue_depth(q->rq_wb, depth); +} +EXPORT_SYMBOL(blk_set_queue_depth); + /** * blk_queue_write_cache - configure queue's write cache * @q: the request queue for the device @@ -851,6 +864,8 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) else queue_flag_clear(QUEUE_FLAG_FUA, q); spin_unlock_irq(q->queue_lock); + + wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); } EXPORT_SYMBOL_GPL(blk_queue_write_cache); diff --git a/block/blk-stat.c b/block/blk-stat.c new file mode 100644 index 000000000..bdb16d84b --- /dev/null +++ b/block/blk-stat.c @@ -0,0 +1,221 @@ +/* + * Block stat tracking code + * + * Copyright (C) 2016 Jens Axboe + */ +#include +#include + +#include "blk-stat.h" +#include "blk-mq.h" + +static void blk_stat_flush_batch(struct blk_rq_stat *stat) +{ + if (!stat->nr_batch) + return; + if (!stat->nr_samples) + stat->mean = div64_s64(stat->batch, stat->nr_batch); + else { + stat->mean = div64_s64((stat->mean * stat->nr_samples) + + stat->batch, + stat->nr_samples + stat->nr_batch); + } + + stat->nr_samples += stat->nr_batch; + stat->nr_batch = stat->batch = 0; +} + +void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) +{ + if (!src->nr_samples) + return; + + blk_stat_flush_batch(src); + + dst->min = min(dst->min, src->min); + dst->max = max(dst->max, src->max); + + if (!dst->nr_samples) + dst->mean = src->mean; + else { + dst->mean = div64_s64((src->mean * src->nr_samples) + + (dst->mean * dst->nr_samples), + dst->nr_samples + src->nr_samples); + } + dst->nr_samples += src->nr_samples; +} + +static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst) +{ + struct blk_mq_hw_ctx *hctx; + struct blk_mq_ctx *ctx; + uint64_t latest = 0; + int i, j, nr; + + blk_stat_init(&dst[0]); + blk_stat_init(&dst[1]); + + nr = 0; + do { + uint64_t newest = 0; + + queue_for_each_hw_ctx(q, hctx, i) { + hctx_for_each_ctx(hctx, ctx, j) { + if (!ctx->stat[0].nr_samples && + !ctx->stat[1].nr_samples) + continue; + if (ctx->stat[0].time > newest) + newest = ctx->stat[0].time; + if (ctx->stat[1].time > newest) + newest = ctx->stat[1].time; + } + } + + /* + * No samples + */ + if (!newest) + break; + + if (newest > latest) + latest = newest; + + queue_for_each_hw_ctx(q, hctx, i) { + hctx_for_each_ctx(hctx, ctx, j) { + if (ctx->stat[0].time == newest) { + blk_stat_sum(&dst[0], &ctx->stat[0]); + nr++; + } + if (ctx->stat[1].time == newest) { + blk_stat_sum(&dst[1], &ctx->stat[1]); + nr++; + } + } + } + /* + * If we race on finding an entry, just loop back again. + * Should be very rare. + */ + } while (!nr); + + dst[0].time = dst[1].time = latest; +} + +void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst) +{ + if (q->mq_ops) + blk_mq_stat_get(q, dst); + else { + memcpy(&dst[0], &q->rq_stats[0], sizeof(struct blk_rq_stat)); + memcpy(&dst[1], &q->rq_stats[1], sizeof(struct blk_rq_stat)); + } +} + +void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst) +{ + struct blk_mq_ctx *ctx; + unsigned int i, nr; + + nr = 0; + do { + uint64_t newest = 0; + + hctx_for_each_ctx(hctx, ctx, i) { + if (!ctx->stat[0].nr_samples && + !ctx->stat[1].nr_samples) + continue; + + if (ctx->stat[0].time > newest) + newest = ctx->stat[0].time; + if (ctx->stat[1].time > newest) + newest = ctx->stat[1].time; + } + + if (!newest) + break; + + hctx_for_each_ctx(hctx, ctx, i) { + if (ctx->stat[0].time == newest) { + blk_stat_sum(&dst[0], &ctx->stat[0]); + nr++; + } + if (ctx->stat[1].time == newest) { + blk_stat_sum(&dst[1], &ctx->stat[1]); + nr++; + } + } + /* + * If we race on finding an entry, just loop back again. + * Should be very rare, as the window is only updated + * occasionally + */ + } while (!nr); +} + +static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now) +{ + stat->min = -1ULL; + stat->max = stat->nr_samples = stat->mean = 0; + stat->batch = stat->nr_batch = 0; + stat->time = time_now & BLK_STAT_MASK; +} + +void blk_stat_init(struct blk_rq_stat *stat) +{ + __blk_stat_init(stat, ktime_to_ns(ktime_get())); +} + +static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now) +{ + return (now & BLK_STAT_MASK) == (stat->time & BLK_STAT_MASK); +} + +bool blk_stat_is_current(struct blk_rq_stat *stat) +{ + return __blk_stat_is_current(stat, ktime_to_ns(ktime_get())); +} + +void blk_stat_add(struct blk_rq_stat *stat, struct request *rq) +{ + s64 now, value; + u64 rq_time = wbt_issue_stat_get_time(&rq->wb_stat); + + now = ktime_to_ns(ktime_get()); + if (now < rq_time) + return; + + if (!__blk_stat_is_current(stat, now)) + __blk_stat_init(stat, now); + + value = now - rq_time; + if (value > stat->max) + stat->max = value; + if (value < stat->min) + stat->min = value; + + if (stat->batch + value < stat->batch || + stat->nr_batch + 1 == BLK_RQ_STAT_BATCH) + blk_stat_flush_batch(stat); + + stat->batch += value; + stat->nr_batch++; +} + +void blk_stat_clear(struct request_queue *q) +{ + if (q->mq_ops) { + struct blk_mq_hw_ctx *hctx; + struct blk_mq_ctx *ctx; + int i, j; + + queue_for_each_hw_ctx(q, hctx, i) { + hctx_for_each_ctx(hctx, ctx, j) { + blk_stat_init(&ctx->stat[0]); + blk_stat_init(&ctx->stat[1]); + } + } + } else { + blk_stat_init(&q->rq_stats[0]); + blk_stat_init(&q->rq_stats[1]); + } +} diff --git a/block/blk-stat.h b/block/blk-stat.h new file mode 100644 index 000000000..376a6ccd9 --- /dev/null +++ b/block/blk-stat.h @@ -0,0 +1,18 @@ +#ifndef BLK_STAT_H +#define BLK_STAT_H + +/* + * ~0.13s window as a power-of-2 (2^27 nsecs) + */ +#define BLK_STAT_NSEC 134217728ULL +#define BLK_STAT_MASK ~(BLK_STAT_NSEC - 1) + +void blk_stat_add(struct blk_rq_stat *, struct request *); +void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *); +void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *); +void blk_stat_clear(struct request_queue *q); +void blk_stat_init(struct blk_rq_stat *); +void blk_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *); +bool blk_stat_is_current(struct blk_rq_stat *); + +#endif diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index f87a7e747..85c3dc223 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "blk.h" #include "blk-mq.h" @@ -41,6 +42,19 @@ queue_var_store(unsigned long *var, const char *page, size_t count) return count; } +static ssize_t queue_var_store64(u64 *var, const char *page) +{ + int err; + u64 v; + + err = kstrtou64(page, 10, &v); + if (err < 0) + return err; + + *var = v; + return 0; +} + static ssize_t queue_requests_show(struct request_queue *q, char *page) { return queue_var_show(q->nr_requests, (page)); @@ -347,6 +361,58 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page, return ret; } +static ssize_t queue_wb_win_show(struct request_queue *q, char *page) +{ + if (!q->rq_wb) + return -EINVAL; + + return sprintf(page, "%llu\n", div_u64(q->rq_wb->win_nsec, 1000)); +} + +static ssize_t queue_wb_win_store(struct request_queue *q, const char *page, + size_t count) +{ + ssize_t ret; + u64 val; + + if (!q->rq_wb) + return -EINVAL; + + ret = queue_var_store64(&val, page); + if (ret < 0) + return ret; + + q->rq_wb->win_nsec = val * 1000ULL; + wbt_update_limits(q->rq_wb); + return count; +} + +static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) +{ + if (!q->rq_wb) + return -EINVAL; + + return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000)); +} + +static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, + size_t count) +{ + ssize_t ret; + u64 val; + + if (!q->rq_wb) + return -EINVAL; + + ret = queue_var_store64(&val, page); + if (ret < 0) + return ret; + + q->rq_wb->min_lat_nsec = val * 1000ULL; + wbt_update_limits(q->rq_wb); + return count; +} + static ssize_t queue_wc_show(struct request_queue *q, char *page) { if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) @@ -384,6 +450,26 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page) return queue_var_show(blk_queue_dax(q), page); } +static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre) +{ + return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n", + pre, (long long) stat->nr_samples, + (long long) stat->mean, (long long) stat->min, + (long long) stat->max); +} + +static ssize_t queue_stats_show(struct request_queue *q, char *page) +{ + struct blk_rq_stat stat[2]; + ssize_t ret; + + blk_queue_stat_get(q, stat); + + ret = print_stat(page, &stat[0], "read :"); + ret += print_stat(page + ret, &stat[1], "write:"); + return ret; +} + static struct queue_sysfs_entry queue_requests_entry = { .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR }, .show = queue_requests_show, @@ -526,6 +612,23 @@ static struct queue_sysfs_entry queue_dax_entry = { .show = queue_dax_show, }; +static struct queue_sysfs_entry queue_stats_entry = { + .attr = {.name = "stats", .mode = S_IRUGO }, + .show = queue_stats_show, +}; + +static struct queue_sysfs_entry queue_wb_lat_entry = { + .attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR }, + .show = queue_wb_lat_show, + .store = queue_wb_lat_store, +}; + +static struct queue_sysfs_entry queue_wb_win_entry = { + .attr = {.name = "wbt_window_usec", .mode = S_IRUGO | S_IWUSR }, + .show = queue_wb_win_show, + .store = queue_wb_win_store, +}; + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -553,6 +656,9 @@ static struct attribute *default_attrs[] = { &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_dax_entry.attr, + &queue_stats_entry.attr, + &queue_wb_lat_entry.attr, + &queue_wb_win_entry.attr, NULL, }; @@ -667,6 +773,49 @@ struct kobj_type blk_queue_ktype = { .release = blk_release_queue, }; +static void blk_wb_stat_get(void *data, struct blk_rq_stat *stat) +{ + blk_queue_stat_get(data, stat); +} + +static void blk_wb_stat_clear(void *data) +{ + blk_stat_clear(data); +} + +static bool blk_wb_stat_is_current(struct blk_rq_stat *stat) +{ + return blk_stat_is_current(stat); +} + +static struct wb_stat_ops wb_stat_ops = { + .get = blk_wb_stat_get, + .is_current = blk_wb_stat_is_current, + .clear = blk_wb_stat_clear, +}; + +static void blk_wb_init(struct request_queue *q) +{ + struct rq_wb *rwb; + + rwb = wbt_init(&q->backing_dev_info, &wb_stat_ops, q); + + /* + * If this fails, we don't get throttling + */ + if (IS_ERR(rwb)) + return; + + if (blk_queue_nonrot(q)) + rwb->min_lat_nsec = 2000000ULL; + else + rwb->min_lat_nsec = 75000000ULL; + + wbt_set_queue_depth(rwb, blk_queue_depth(q)); + wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); + q->rq_wb = rwb; +} + int blk_register_queue(struct gendisk *disk) { int ret; @@ -706,6 +855,8 @@ int blk_register_queue(struct gendisk *disk) if (q->mq_ops) blk_mq_register_disk(disk); + blk_wb_init(q); + if (!q->request_fn) return 0; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 5e24d8803..f336dcbed 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3771,9 +3771,11 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; uint64_t serial_nr; + bool nonroot_cg; rcu_read_lock(); serial_nr = bio_blkcg(bio)->css.serial_nr; + nonroot_cg = bio_blkcg(bio) != &blkcg_root; rcu_read_unlock(); /* @@ -3783,6 +3785,17 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr)) return; + /* + * If we have a non-root cgroup, we can depend on that to + * do proper throttling of writes. Turn off wbt for that + * case. + */ + if (nonroot_cg) { + struct request_queue *q = cfqd->queue; + + wbt_disable(q->rq_wb); + } + /* * Drop reference to queues. New queues will be assigned in new * group upon arrival of fresh requests. diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 60746ef90..caea575f2 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -662,7 +662,7 @@ static int ghes_proc(struct ghes *ghes) ghes_do_proc(ghes, ghes->estatus); out: ghes_clear_estatus(ghes); - return 0; + return rc; } static void ghes_add_timer(struct ghes *ghes) diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index c983bf733..bc3d914df 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -87,6 +87,7 @@ struct acpi_pci_link { static LIST_HEAD(acpi_link_list); static DEFINE_MUTEX(acpi_link_lock); +static int sci_irq = -1, sci_penalty; /* -------------------------------------------------------------------------- PCI Link Device Management @@ -496,25 +497,13 @@ static int acpi_irq_get_penalty(int irq) { int penalty = 0; - /* - * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict - * with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be - * use for PCI IRQs. - */ - if (irq == acpi_gbl_FADT.sci_interrupt) { - u32 type = irq_get_trigger_type(irq) & IRQ_TYPE_SENSE_MASK; - - if (type != IRQ_TYPE_LEVEL_LOW) - penalty += PIRQ_PENALTY_ISA_ALWAYS; - else - penalty += PIRQ_PENALTY_PCI_USING; - } + if (irq == sci_irq) + penalty += sci_penalty; if (irq < ACPI_MAX_ISA_IRQS) return penalty + acpi_isa_irq_penalty[irq]; - penalty += acpi_irq_pci_sharing_penalty(irq); - return penalty; + return penalty + acpi_irq_pci_sharing_penalty(irq); } int __init acpi_irq_penalty_init(void) @@ -619,6 +608,10 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) acpi_device_bid(link->device)); return -ENODEV; } else { + if (link->irq.active < ACPI_MAX_ISA_IRQS) + acpi_isa_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_USING; + printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n", acpi_device_name(link->device), acpi_device_bid(link->device), link->irq.active); @@ -849,7 +842,7 @@ static int __init acpi_irq_penalty_update(char *str, int used) continue; if (used) - new_penalty = acpi_irq_get_penalty(irq) + + new_penalty = acpi_isa_irq_penalty[irq] + PIRQ_PENALTY_ISA_USED; else new_penalty = 0; @@ -871,7 +864,7 @@ static int __init acpi_irq_penalty_update(char *str, int used) void acpi_penalize_isa_irq(int irq, int active) { if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty))) - acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) + + acpi_isa_irq_penalty[irq] += (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); } @@ -881,6 +874,17 @@ bool acpi_isa_irq_available(int irq) acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS); } +void acpi_penalize_sci_irq(int irq, int trigger, int polarity) +{ + sci_irq = irq; + + if (trigger == ACPI_MADT_TRIGGER_LEVEL && + polarity == ACPI_MADT_POLARITY_ACTIVE_LOW) + sci_penalty = PIRQ_PENALTY_PCI_USING; + else + sci_penalty = PIRQ_PENALTY_ISA_ALWAYS; +} + /* * Over-ride default table to reserve additional IRQs for use by ISA * e.g. acpi_irq_isa=5 diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 9f8b07029..223a770f7 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2173,11 +2173,7 @@ static int ata_dev_config_ncq(struct ata_device *dev, return 0; } if (ap->flags & ATA_FLAG_NCQ) { -#ifdef CONFIG_PCK_INTERACTIVE - hdepth = min(ap->scsi_host->can_queue, 8); -#else hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE - 1); -#endif dev->flags |= ATA_DFLAG_NCQ; } diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 100be556e..83482721b 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1871,7 +1871,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, drbd_update_congested(connection); } do { - rv = kernel_sendmsg(sock, &msg, &iov, 1, size); + rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len); if (rv == -EAGAIN) { if (we_should_drop_the_connection(connection, sock)) break; diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index 44311296e..0f7d28a98 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -845,6 +845,8 @@ void intel_gtt_insert_page(dma_addr_t addr, unsigned int flags) { intel_private.driver->write_entry(addr, pg, flags); + if (intel_private.driver->chipset_flush) + intel_private.driver->chipset_flush(); } EXPORT_SYMBOL(intel_gtt_insert_page); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 9203f2d13..340f96e44 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -84,14 +84,14 @@ static size_t rng_buffer_size(void) static void add_early_randomness(struct hwrng *rng) { - unsigned char bytes[16]; int bytes_read; + size_t size = min_t(size_t, 16, rng_buffer_size()); mutex_lock(&reading_mutex); - bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1); + bytes_read = rng_get_data(rng, rng_buffer, size, 1); mutex_unlock(&reading_mutex); if (bytes_read > 0) - add_device_randomness(bytes, bytes_read); + add_device_randomness(rng_buffer, bytes_read); } static inline void cleanup_rng(struct kref *kref) diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c index 20b105584..80ae2a514 100644 --- a/drivers/clk/clk-qoriq.c +++ b/drivers/clk/clk-qoriq.c @@ -700,6 +700,7 @@ static struct clk * __init create_mux_common(struct clockgen *cg, struct mux_hwclock *hwc, const struct clk_ops *ops, unsigned long min_rate, + unsigned long max_rate, unsigned long pct80_rate, const char *fmt, int idx) { @@ -728,6 +729,8 @@ static struct clk * __init create_mux_common(struct clockgen *cg, continue; if (rate < min_rate) continue; + if (rate > max_rate) + continue; parent_names[j] = div->name; hwc->parent_to_clksel[j] = i; @@ -759,7 +762,7 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx) struct mux_hwclock *hwc; const struct clockgen_pll_div *div; unsigned long plat_rate, min_rate; - u64 pct80_rate; + u64 max_rate, pct80_rate; u32 clksel; hwc = kzalloc(sizeof(*hwc), GFP_KERNEL); @@ -787,8 +790,8 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx) return NULL; } - pct80_rate = clk_get_rate(div->clk); - pct80_rate *= 8; + max_rate = clk_get_rate(div->clk); + pct80_rate = max_rate * 8; do_div(pct80_rate, 10); plat_rate = clk_get_rate(cg->pll[PLATFORM_PLL].div[PLL_DIV1].clk); @@ -798,7 +801,7 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx) else min_rate = plat_rate / 2; - return create_mux_common(cg, hwc, &cmux_ops, min_rate, + return create_mux_common(cg, hwc, &cmux_ops, min_rate, max_rate, pct80_rate, "cg-cmux%d", idx); } @@ -813,7 +816,7 @@ static struct clk * __init create_one_hwaccel(struct clockgen *cg, int idx) hwc->reg = cg->regs + 0x20 * idx + 0x10; hwc->info = cg->info.hwaccel[idx]; - return create_mux_common(cg, hwc, &hwaccel_ops, 0, 0, + return create_mux_common(cg, hwc, &hwaccel_ops, 0, ULONG_MAX, 0, "cg-hwaccel%d", idx); } diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index bdf8b971f..0fa91f378 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -82,6 +82,7 @@ static const struct of_device_id exynos_audss_clk_of_match[] = { .data = (void *)TYPE_EXYNOS5420, }, {}, }; +MODULE_DEVICE_TABLE(of, exynos_audss_clk_of_match); static void exynos_audss_clk_teardown(void) { diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index c184eb841..4f87f3e76 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -152,6 +152,13 @@ static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static cycle_t sun5i_clksrc_read(struct clocksource *clksrc) +{ + struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc); + + return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1)); +} + static int sun5i_rate_cb_clksrc(struct notifier_block *nb, unsigned long event, void *data) { @@ -210,8 +217,13 @@ static int __init sun5i_setup_clocksource(struct device_node *node, writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, base + TIMER_CTL_REG(1)); - ret = clocksource_mmio_init(base + TIMER_CNTVAL_LO_REG(1), node->name, - rate, 340, 32, clocksource_mmio_readl_down); + cs->clksrc.name = node->name; + cs->clksrc.rating = 340; + cs->clksrc.read = sun5i_clksrc_read; + cs->clksrc.mask = CLOCKSOURCE_MASK(32); + cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; + + ret = clocksource_register_hz(&cs->clksrc, rate); if (ret) { pr_err("Couldn't register clock source.\n"); goto err_remove_notifier; diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index f40450d26..13475890d 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -31,14 +31,8 @@ struct cs_dbs_tuners { }; /* Conservative governor macros */ -#ifdef CONFIG_SCHED_MUQSS -#define DEF_FREQUENCY_UP_THRESHOLD (63) -#define DEF_FREQUENCY_DOWN_THRESHOLD (26) -#else #define DEF_FREQUENCY_UP_THRESHOLD (80) #define DEF_FREQUENCY_DOWN_THRESHOLD (20) -#endif - #define DEF_FREQUENCY_STEP (5) #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 6fd9fc111..79dc7cf54 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -20,12 +20,7 @@ #include "cpufreq_ondemand.h" /* On-demand governor macros */ -#ifdef CONFIG_SCHED_MUQSS -#define DEF_FREQUENCY_UP_THRESHOLD (63) -#else #define DEF_FREQUENCY_UP_THRESHOLD (80) -#endif - #ifdef CONFIG_PCK_INTERACTIVE #define DEF_SAMPLING_DOWN_FACTOR (10) #else diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index cd5dc2732..1ed6132b9 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -293,10 +293,10 @@ static void mvebu_gpio_irq_ack(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; - u32 mask = ~(1 << (d->irq - gc->irq_base)); + u32 mask = d->mask; irq_gc_lock(gc); - writel_relaxed(mask, mvebu_gpioreg_edge_cause(mvchip)); + writel_relaxed(~mask, mvebu_gpioreg_edge_cause(mvchip)); irq_gc_unlock(gc); } @@ -305,7 +305,7 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d) struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; struct irq_chip_type *ct = irq_data_get_chip_type(d); - u32 mask = 1 << (d->irq - gc->irq_base); + u32 mask = d->mask; irq_gc_lock(gc); ct->mask_cache_priv &= ~mask; @@ -319,8 +319,7 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d) struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; struct irq_chip_type *ct = irq_data_get_chip_type(d); - - u32 mask = 1 << (d->irq - gc->irq_base); + u32 mask = d->mask; irq_gc_lock(gc); ct->mask_cache_priv |= mask; @@ -333,8 +332,7 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d) struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; struct irq_chip_type *ct = irq_data_get_chip_type(d); - - u32 mask = 1 << (d->irq - gc->irq_base); + u32 mask = d->mask; irq_gc_lock(gc); ct->mask_cache_priv &= ~mask; @@ -347,8 +345,7 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d) struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mvebu_gpio_chip *mvchip = gc->private; struct irq_chip_type *ct = irq_data_get_chip_type(d); - - u32 mask = 1 << (d->irq - gc->irq_base); + u32 mask = d->mask; irq_gc_lock(gc); ct->mask_cache_priv |= mask; @@ -462,7 +459,7 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc) for (i = 0; i < mvchip->chip.ngpio; i++) { int irq; - irq = mvchip->irqbase + i; + irq = irq_find_mapping(mvchip->domain, i); if (!(cause & (1 << i))) continue; @@ -655,6 +652,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev) struct irq_chip_type *ct; struct clk *clk; unsigned int ngpios; + bool have_irqs; int soc_variant; int i, cpu, id; int err; @@ -665,6 +663,9 @@ static int mvebu_gpio_probe(struct platform_device *pdev) else soc_variant = MVEBU_GPIO_SOC_VARIANT_ORION; + /* Some gpio controllers do not provide irq support */ + have_irqs = of_irq_count(np) != 0; + mvchip = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_gpio_chip), GFP_KERNEL); if (!mvchip) @@ -697,7 +698,8 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip->chip.get = mvebu_gpio_get; mvchip->chip.direction_output = mvebu_gpio_direction_output; mvchip->chip.set = mvebu_gpio_set; - mvchip->chip.to_irq = mvebu_gpio_to_irq; + if (have_irqs) + mvchip->chip.to_irq = mvebu_gpio_to_irq; mvchip->chip.base = id * MVEBU_MAX_GPIO_PER_BANK; mvchip->chip.ngpio = ngpios; mvchip->chip.can_sleep = false; @@ -758,34 +760,30 @@ static int mvebu_gpio_probe(struct platform_device *pdev) devm_gpiochip_add_data(&pdev->dev, &mvchip->chip, mvchip); /* Some gpio controllers do not provide irq support */ - if (!of_irq_count(np)) + if (!have_irqs) return 0; - /* Setup the interrupt handlers. Each chip can have up to 4 - * interrupt handlers, with each handler dealing with 8 GPIO - * pins. */ - for (i = 0; i < 4; i++) { - int irq = platform_get_irq(pdev, i); - - if (irq < 0) - continue; - irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler, - mvchip); - } - - mvchip->irqbase = irq_alloc_descs(-1, 0, ngpios, -1); - if (mvchip->irqbase < 0) { - dev_err(&pdev->dev, "no irqs\n"); - return mvchip->irqbase; + mvchip->domain = + irq_domain_add_linear(np, ngpios, &irq_generic_chip_ops, NULL); + if (!mvchip->domain) { + dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n", + mvchip->chip.label); + return -ENODEV; } - gc = irq_alloc_generic_chip("mvebu_gpio_irq", 2, mvchip->irqbase, - mvchip->membase, handle_level_irq); - if (!gc) { - dev_err(&pdev->dev, "Cannot allocate generic irq_chip\n"); - return -ENOMEM; + err = irq_alloc_domain_generic_chips( + mvchip->domain, ngpios, 2, np->name, handle_level_irq, + IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_LEVEL, 0, 0); + if (err) { + dev_err(&pdev->dev, "couldn't allocate irq chips %s (DT).\n", + mvchip->chip.label); + goto err_domain; } + /* NOTE: The common accessors cannot be used because of the percpu + * access to the mask registers + */ + gc = irq_get_domain_generic_chip(mvchip->domain, 0); gc->private = mvchip; ct = &gc->chip_types[0]; ct->type = IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW; @@ -803,27 +801,23 @@ static int mvebu_gpio_probe(struct platform_device *pdev) ct->handler = handle_edge_irq; ct->chip.name = mvchip->chip.label; - irq_setup_generic_chip(gc, IRQ_MSK(ngpios), 0, - IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE); + /* Setup the interrupt handlers. Each chip can have up to 4 + * interrupt handlers, with each handler dealing with 8 GPIO + * pins. + */ + for (i = 0; i < 4; i++) { + int irq = platform_get_irq(pdev, i); - /* Setup irq domain on top of the generic chip. */ - mvchip->domain = irq_domain_add_simple(np, mvchip->chip.ngpio, - mvchip->irqbase, - &irq_domain_simple_ops, - mvchip); - if (!mvchip->domain) { - dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n", - mvchip->chip.label); - err = -ENODEV; - goto err_generic_chip; + if (irq < 0) + continue; + irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler, + mvchip); } return 0; -err_generic_chip: - irq_remove_generic_chip(gc, IRQ_MSK(ngpios), IRQ_NOREQUEST, - IRQ_LEVEL | IRQ_NOPROBE); - kfree(gc); +err_domain: + irq_domain_remove(mvchip->domain); return err; } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index a28feb3ed..e3fc90130 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -26,14 +26,18 @@ #include "gpiolib.h" -static int of_gpiochip_match_node(struct gpio_chip *chip, void *data) +static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data) { - return chip->gpiodev->dev.of_node == data; + struct of_phandle_args *gpiospec = data; + + return chip->gpiodev->dev.of_node == gpiospec->np && + chip->of_xlate(chip, gpiospec, NULL) >= 0; } -static struct gpio_chip *of_find_gpiochip_by_node(struct device_node *np) +static struct gpio_chip *of_find_gpiochip_by_xlate( + struct of_phandle_args *gpiospec) { - return gpiochip_find(np, of_gpiochip_match_node); + return gpiochip_find(gpiospec, of_gpiochip_match_node_and_xlate); } static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip, @@ -79,7 +83,7 @@ struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np, return ERR_PTR(ret); } - chip = of_find_gpiochip_by_node(gpiospec.np); + chip = of_find_gpiochip_by_xlate(&gpiospec); if (!chip) { desc = ERR_PTR(-EPROBE_DEFER); goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index 892d60fb2..2057683f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -395,9 +395,12 @@ static int acp_hw_fini(void *handle) { int i, ret; struct device *dev; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* return early if no ACP */ + if (!adev->acp.acp_genpd) + return 0; + for (i = 0; i < ACP_DEVS ; i++) { dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i); ret = pm_genpd_remove_device(&adev->acp.acp_genpd->gpd, dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 9aa533cf4..414a1600d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -605,6 +605,7 @@ static int __init amdgpu_init(void) { amdgpu_sync_init(); amdgpu_fence_slab_init(); + amd_sched_fence_slab_init(); if (vgacon_text_force()) { DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n"); return -EINVAL; @@ -624,6 +625,7 @@ static void __exit amdgpu_exit(void) drm_pci_exit(driver, pdriver); amdgpu_unregister_atpx_handler(); amdgpu_sync_fini(); + amd_sched_fence_slab_fini(); amdgpu_fence_slab_fini(); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 0b109aebf..c82b95b83 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -68,6 +68,7 @@ int amdgpu_fence_slab_init(void) void amdgpu_fence_slab_fini(void) { + rcu_barrier(); kmem_cache_destroy(amdgpu_fence_slab); } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index e24a8af72..1ed64aedb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -99,6 +99,8 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) if ((amdgpu_runtime_pm != 0) && amdgpu_has_atpx() && + (amdgpu_is_atpx_hybrid() || + amdgpu_has_atpx_dgpu_power_cntl()) && ((flags & AMD_IS_APU) == 0)) flags |= AMD_IS_PX; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 80120fa40..e86ca392a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1654,5 +1654,6 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev) fence_put(adev->vm_manager.ids[i].first); amdgpu_sync_free(&adev->vm_manager.ids[i].active); fence_put(id->flushed_updates); + fence_put(id->last_flush); } } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 963a24d46..ffe1f85ce 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -34,9 +34,6 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity); static void amd_sched_wakeup(struct amd_gpu_scheduler *sched); static void amd_sched_process_job(struct fence *f, struct fence_cb *cb); -struct kmem_cache *sched_fence_slab; -atomic_t sched_fence_slab_ref = ATOMIC_INIT(0); - /* Initialize a given run queue struct */ static void amd_sched_rq_init(struct amd_sched_rq *rq) { @@ -618,13 +615,6 @@ int amd_sched_init(struct amd_gpu_scheduler *sched, INIT_LIST_HEAD(&sched->ring_mirror_list); spin_lock_init(&sched->job_list_lock); atomic_set(&sched->hw_rq_count, 0); - if (atomic_inc_return(&sched_fence_slab_ref) == 1) { - sched_fence_slab = kmem_cache_create( - "amd_sched_fence", sizeof(struct amd_sched_fence), 0, - SLAB_HWCACHE_ALIGN, NULL); - if (!sched_fence_slab) - return -ENOMEM; - } /* Each scheduler will run on a seperate kernel thread */ sched->thread = kthread_run(amd_sched_main, sched, sched->name); @@ -645,6 +635,4 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched) { if (sched->thread) kthread_stop(sched->thread); - if (atomic_dec_and_test(&sched_fence_slab_ref)) - kmem_cache_destroy(sched_fence_slab); } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 7cbbbfb50..51068e6c3 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -30,9 +30,6 @@ struct amd_gpu_scheduler; struct amd_sched_rq; -extern struct kmem_cache *sched_fence_slab; -extern atomic_t sched_fence_slab_ref; - /** * A scheduler entity is a wrapper around a job queue or a group * of other entities. Entities take turns emitting jobs from their @@ -145,6 +142,9 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched, struct amd_sched_entity *entity); void amd_sched_entity_push_job(struct amd_sched_job *sched_job); +int amd_sched_fence_slab_init(void); +void amd_sched_fence_slab_fini(void); + struct amd_sched_fence *amd_sched_fence_create( struct amd_sched_entity *s_entity, void *owner); void amd_sched_fence_scheduled(struct amd_sched_fence *fence); diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c index 6b63beaf7..93ad2e1f8 100644 --- a/drivers/gpu/drm/amd/scheduler/sched_fence.c +++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c @@ -27,6 +27,25 @@ #include #include "gpu_scheduler.h" +static struct kmem_cache *sched_fence_slab; + +int amd_sched_fence_slab_init(void) +{ + sched_fence_slab = kmem_cache_create( + "amd_sched_fence", sizeof(struct amd_sched_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!sched_fence_slab) + return -ENOMEM; + + return 0; +} + +void amd_sched_fence_slab_fini(void) +{ + rcu_barrier(); + kmem_cache_destroy(sched_fence_slab); +} + struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *entity, void *owner) { diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 5de36d8dc..d46fa2206 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1490,8 +1490,6 @@ static int i915_drm_suspend(struct drm_device *dev) dev_priv->suspend_count++; - intel_display_set_init_power(dev_priv, false); - intel_csr_ucode_suspend(dev_priv); out: @@ -1508,6 +1506,8 @@ static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation) disable_rpm_wakeref_asserts(dev_priv); + intel_display_set_init_power(dev_priv, false); + fw_csr = !IS_BROXTON(dev_priv) && suspend_to_idle(dev_priv) && dev_priv->csr.dmc_payload; /* diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 63462f279..e26f88965 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -9737,6 +9737,29 @@ static void bxt_modeset_commit_cdclk(struct drm_atomic_state *old_state) bxt_set_cdclk(to_i915(dev), req_cdclk); } +static int bdw_adjust_min_pipe_pixel_rate(struct intel_crtc_state *crtc_state, + int pixel_rate) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + + /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */ + if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled) + pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95); + + /* BSpec says "Do not use DisplayPort with CDCLK less than + * 432 MHz, audio enabled, port width x4, and link rate + * HBR2 (5.4 GHz), or else there may be audio corruption or + * screen corruption." + */ + if (intel_crtc_has_dp_encoder(crtc_state) && + crtc_state->has_audio && + crtc_state->port_clock >= 540000 && + crtc_state->lane_count == 4) + pixel_rate = max(432000, pixel_rate); + + return pixel_rate; +} + /* compute the max rate for new configuration */ static int ilk_max_pixel_rate(struct drm_atomic_state *state) { @@ -9762,9 +9785,9 @@ static int ilk_max_pixel_rate(struct drm_atomic_state *state) pixel_rate = ilk_pipe_pixel_rate(crtc_state); - /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */ - if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled) - pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95); + if (IS_BROADWELL(dev_priv) || IS_GEN9(dev_priv)) + pixel_rate = bdw_adjust_min_pipe_pixel_rate(crtc_state, + pixel_rate); intel_state->min_pixclk[i] = pixel_rate; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index c3aa9e670..142127007 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1759,6 +1759,50 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; } +static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + const struct ddi_vbt_port_info *info = + &dev_priv->vbt.ddi_port_info[port]; + u8 ddc_pin; + + if (info->alternate_ddc_pin) { + DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (VBT)\n", + info->alternate_ddc_pin, port_name(port)); + return info->alternate_ddc_pin; + } + + switch (port) { + case PORT_B: + if (IS_BROXTON(dev_priv)) + ddc_pin = GMBUS_PIN_1_BXT; + else + ddc_pin = GMBUS_PIN_DPB; + break; + case PORT_C: + if (IS_BROXTON(dev_priv)) + ddc_pin = GMBUS_PIN_2_BXT; + else + ddc_pin = GMBUS_PIN_DPC; + break; + case PORT_D: + if (IS_CHERRYVIEW(dev_priv)) + ddc_pin = GMBUS_PIN_DPD_CHV; + else + ddc_pin = GMBUS_PIN_DPD; + break; + default: + MISSING_CASE(port); + ddc_pin = GMBUS_PIN_DPB; + break; + } + + DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (platform default)\n", + ddc_pin, port_name(port)); + + return ddc_pin; +} + void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, struct intel_connector *intel_connector) { @@ -1768,7 +1812,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); enum port port = intel_dig_port->port; - uint8_t alternate_ddc_pin; DRM_DEBUG_KMS("Adding HDMI connector on port %c\n", port_name(port)); @@ -1786,12 +1829,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, connector->doublescan_allowed = 0; connector->stereo_allowed = 1; + intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port); + switch (port) { case PORT_B: - if (IS_BROXTON(dev_priv)) - intel_hdmi->ddc_bus = GMBUS_PIN_1_BXT; - else - intel_hdmi->ddc_bus = GMBUS_PIN_DPB; /* * On BXT A0/A1, sw needs to activate DDIA HPD logic and * interrupts to check the external panel connection. @@ -1802,46 +1843,17 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_encoder->hpd_pin = HPD_PORT_B; break; case PORT_C: - if (IS_BROXTON(dev_priv)) - intel_hdmi->ddc_bus = GMBUS_PIN_2_BXT; - else - intel_hdmi->ddc_bus = GMBUS_PIN_DPC; intel_encoder->hpd_pin = HPD_PORT_C; break; case PORT_D: - if (WARN_ON(IS_BROXTON(dev_priv))) - intel_hdmi->ddc_bus = GMBUS_PIN_DISABLED; - else if (IS_CHERRYVIEW(dev_priv)) - intel_hdmi->ddc_bus = GMBUS_PIN_DPD_CHV; - else - intel_hdmi->ddc_bus = GMBUS_PIN_DPD; intel_encoder->hpd_pin = HPD_PORT_D; break; case PORT_E: - /* On SKL PORT E doesn't have seperate GMBUS pin - * We rely on VBT to set a proper alternate GMBUS pin. */ - alternate_ddc_pin = - dev_priv->vbt.ddi_port_info[PORT_E].alternate_ddc_pin; - switch (alternate_ddc_pin) { - case DDC_PIN_B: - intel_hdmi->ddc_bus = GMBUS_PIN_DPB; - break; - case DDC_PIN_C: - intel_hdmi->ddc_bus = GMBUS_PIN_DPC; - break; - case DDC_PIN_D: - intel_hdmi->ddc_bus = GMBUS_PIN_DPD; - break; - default: - MISSING_CASE(alternate_ddc_pin); - } intel_encoder->hpd_pin = HPD_PORT_E; break; - case PORT_A: - intel_encoder->hpd_pin = HPD_PORT_A; - /* Internal port only for eDP. */ default: - BUG(); + MISSING_CASE(port); + return; } if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 554ca7115..edd2d0396 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -104,6 +104,14 @@ static const char radeon_family_name[][16] = { "LAST", }; +#if defined(CONFIG_VGA_SWITCHEROO) +bool radeon_has_atpx_dgpu_power_cntl(void); +bool radeon_is_atpx_hybrid(void); +#else +static inline bool radeon_has_atpx_dgpu_power_cntl(void) { return false; } +static inline bool radeon_is_atpx_hybrid(void) { return false; } +#endif + #define RADEON_PX_QUIRK_DISABLE_PX (1 << 0) #define RADEON_PX_QUIRK_LONG_WAKEUP (1 << 1) @@ -160,6 +168,11 @@ static void radeon_device_handle_px_quirks(struct radeon_device *rdev) if (rdev->px_quirk_flags & RADEON_PX_QUIRK_DISABLE_PX) rdev->flags &= ~RADEON_IS_PX; + + /* disable PX is the system doesn't support dGPU power control or hybrid gfx */ + if (!radeon_is_atpx_hybrid() && + !radeon_has_atpx_dgpu_power_cntl()) + rdev->flags &= ~RADEON_IS_PX; } /** diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index da3fb069e..ce69048c8 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -743,8 +743,8 @@ static int st_accel_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: - *val = 0; - *val2 = adata->current_fullscale->gain; + *val = adata->current_fullscale->gain / 1000000; + *val2 = adata->current_fullscale->gain % 1000000; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SAMP_FREQ: *val = adata->odr; @@ -763,9 +763,13 @@ static int st_accel_write_raw(struct iio_dev *indio_dev, int err; switch (mask) { - case IIO_CHAN_INFO_SCALE: - err = st_sensors_set_fullscale_by_gain(indio_dev, val2); + case IIO_CHAN_INFO_SCALE: { + int gain; + + gain = val * 1000000 + val2; + err = st_sensors_set_fullscale_by_gain(indio_dev, gain); break; + } case IIO_CHAN_INFO_SAMP_FREQ: if (val2) return -EINVAL; diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c index dc33c1dd5..b5beea53d 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c @@ -30,26 +30,26 @@ static struct { u32 usage_id; int unit; /* 0 for default others from HID sensor spec */ int scale_val0; /* scale, whole number */ - int scale_val1; /* scale, fraction in micros */ + int scale_val1; /* scale, fraction in nanos */ } unit_conversion[] = { - {HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650}, + {HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650000}, {HID_USAGE_SENSOR_ACCEL_3D, HID_USAGE_SENSOR_UNITS_METERS_PER_SEC_SQRD, 1, 0}, {HID_USAGE_SENSOR_ACCEL_3D, - HID_USAGE_SENSOR_UNITS_G, 9, 806650}, + HID_USAGE_SENSOR_UNITS_G, 9, 806650000}, - {HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453}, + {HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453293}, {HID_USAGE_SENSOR_GYRO_3D, HID_USAGE_SENSOR_UNITS_RADIANS_PER_SECOND, 1, 0}, {HID_USAGE_SENSOR_GYRO_3D, - HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453}, + HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453293}, - {HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000}, + {HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000000}, {HID_USAGE_SENSOR_COMPASS_3D, HID_USAGE_SENSOR_UNITS_GAUSS, 1, 0}, - {HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453}, + {HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453293}, {HID_USAGE_SENSOR_INCLINOMETER_3D, - HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453}, + HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293}, {HID_USAGE_SENSOR_INCLINOMETER_3D, HID_USAGE_SENSOR_UNITS_RADIANS, 1, 0}, @@ -57,7 +57,7 @@ static struct { {HID_USAGE_SENSOR_ALS, HID_USAGE_SENSOR_UNITS_LUX, 1, 0}, {HID_USAGE_SENSOR_PRESSURE, 0, 100, 0}, - {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000}, + {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000000}, }; static int pow_10(unsigned power) @@ -266,15 +266,15 @@ EXPORT_SYMBOL(hid_sensor_write_raw_hyst_value); /* * This fuction applies the unit exponent to the scale. * For example: - * 9.806650 ->exp:2-> val0[980]val1[665000] - * 9.000806 ->exp:2-> val0[900]val1[80600] - * 0.174535 ->exp:2-> val0[17]val1[453500] - * 1.001745 ->exp:0-> val0[1]val1[1745] - * 1.001745 ->exp:2-> val0[100]val1[174500] - * 1.001745 ->exp:4-> val0[10017]val1[450000] - * 9.806650 ->exp:-2-> val0[0]val1[98066] + * 9.806650000 ->exp:2-> val0[980]val1[665000000] + * 9.000806000 ->exp:2-> val0[900]val1[80600000] + * 0.174535293 ->exp:2-> val0[17]val1[453529300] + * 1.001745329 ->exp:0-> val0[1]val1[1745329] + * 1.001745329 ->exp:2-> val0[100]val1[174532900] + * 1.001745329 ->exp:4-> val0[10017]val1[453290000] + * 9.806650000 ->exp:-2-> val0[0]val1[98066500] */ -static void adjust_exponent_micro(int *val0, int *val1, int scale0, +static void adjust_exponent_nano(int *val0, int *val1, int scale0, int scale1, int exp) { int i; @@ -285,32 +285,32 @@ static void adjust_exponent_micro(int *val0, int *val1, int scale0, if (exp > 0) { *val0 = scale0 * pow_10(exp); res = 0; - if (exp > 6) { + if (exp > 9) { *val1 = 0; return; } for (i = 0; i < exp; ++i) { - x = scale1 / pow_10(5 - i); + x = scale1 / pow_10(8 - i); res += (pow_10(exp - 1 - i) * x); - scale1 = scale1 % pow_10(5 - i); + scale1 = scale1 % pow_10(8 - i); } *val0 += res; *val1 = scale1 * pow_10(exp); } else if (exp < 0) { exp = abs(exp); - if (exp > 6) { + if (exp > 9) { *val0 = *val1 = 0; return; } *val0 = scale0 / pow_10(exp); rem = scale0 % pow_10(exp); res = 0; - for (i = 0; i < (6 - exp); ++i) { - x = scale1 / pow_10(5 - i); - res += (pow_10(5 - exp - i) * x); - scale1 = scale1 % pow_10(5 - i); + for (i = 0; i < (9 - exp); ++i) { + x = scale1 / pow_10(8 - i); + res += (pow_10(8 - exp - i) * x); + scale1 = scale1 % pow_10(8 - i); } - *val1 = rem * pow_10(6 - exp) + res; + *val1 = rem * pow_10(9 - exp) + res; } else { *val0 = scale0; *val1 = scale1; @@ -332,14 +332,14 @@ int hid_sensor_format_scale(u32 usage_id, unit_conversion[i].unit == attr_info->units) { exp = hid_sensor_convert_exponent( attr_info->unit_expo); - adjust_exponent_micro(val0, val1, + adjust_exponent_nano(val0, val1, unit_conversion[i].scale_val0, unit_conversion[i].scale_val1, exp); break; } } - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } EXPORT_SYMBOL(hid_sensor_format_scale); diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 2d5282e05..32a594675 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -619,7 +619,7 @@ EXPORT_SYMBOL(st_sensors_sysfs_sampling_frequency_avail); ssize_t st_sensors_sysfs_scale_avail(struct device *dev, struct device_attribute *attr, char *buf) { - int i, len = 0; + int i, len = 0, q, r; struct iio_dev *indio_dev = dev_get_drvdata(dev); struct st_sensor_data *sdata = iio_priv(indio_dev); @@ -628,8 +628,10 @@ ssize_t st_sensors_sysfs_scale_avail(struct device *dev, if (sdata->sensor_settings->fs.fs_avl[i].num == 0) break; - len += scnprintf(buf + len, PAGE_SIZE - len, "0.%06u ", - sdata->sensor_settings->fs.fs_avl[i].gain); + q = sdata->sensor_settings->fs.fs_avl[i].gain / 1000000; + r = sdata->sensor_settings->fs.fs_avl[i].gain % 1000000; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%u.%06u ", q, r); } mutex_unlock(&indio_dev->mlock); buf[len - 1] = '\n'; diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c index b98b9d94d..a97e802ca 100644 --- a/drivers/iio/orientation/hid-sensor-rotation.c +++ b/drivers/iio/orientation/hid-sensor-rotation.c @@ -335,6 +335,7 @@ static struct platform_driver hid_dev_rot_platform_driver = { .id_table = hid_dev_rot_ids, .driver = { .name = KBUILD_MODNAME, + .pm = &hid_sensor_pm_ops, }, .probe = hid_dev_rot_probe, .remove = hid_dev_rot_remove, diff --git a/drivers/input/rmi4/rmi_i2c.c b/drivers/input/rmi4/rmi_i2c.c index 6f2e0e4f0..1ebc2c1de 100644 --- a/drivers/input/rmi4/rmi_i2c.c +++ b/drivers/input/rmi4/rmi_i2c.c @@ -221,6 +221,21 @@ static const struct of_device_id rmi_i2c_of_match[] = { MODULE_DEVICE_TABLE(of, rmi_i2c_of_match); #endif +static void rmi_i2c_regulator_bulk_disable(void *data) +{ + struct rmi_i2c_xport *rmi_i2c = data; + + regulator_bulk_disable(ARRAY_SIZE(rmi_i2c->supplies), + rmi_i2c->supplies); +} + +static void rmi_i2c_unregister_transport(void *data) +{ + struct rmi_i2c_xport *rmi_i2c = data; + + rmi_unregister_transport_device(&rmi_i2c->xport); +} + static int rmi_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -264,6 +279,12 @@ static int rmi_i2c_probe(struct i2c_client *client, if (retval < 0) return retval; + retval = devm_add_action_or_reset(&client->dev, + rmi_i2c_regulator_bulk_disable, + rmi_i2c); + if (retval) + return retval; + of_property_read_u32(client->dev.of_node, "syna,startup-delay-ms", &rmi_i2c->startup_delay); @@ -294,6 +315,11 @@ static int rmi_i2c_probe(struct i2c_client *client, client->addr); return retval; } + retval = devm_add_action_or_reset(&client->dev, + rmi_i2c_unregister_transport, + rmi_i2c); + if (retval) + return retval; retval = rmi_i2c_init_irq(client); if (retval < 0) @@ -304,17 +330,6 @@ static int rmi_i2c_probe(struct i2c_client *client, return 0; } -static int rmi_i2c_remove(struct i2c_client *client) -{ - struct rmi_i2c_xport *rmi_i2c = i2c_get_clientdata(client); - - rmi_unregister_transport_device(&rmi_i2c->xport); - regulator_bulk_disable(ARRAY_SIZE(rmi_i2c->supplies), - rmi_i2c->supplies); - - return 0; -} - #ifdef CONFIG_PM_SLEEP static int rmi_i2c_suspend(struct device *dev) { @@ -431,7 +446,6 @@ static struct i2c_driver rmi_i2c_driver = { }, .id_table = rmi_id, .probe = rmi_i2c_probe, - .remove = rmi_i2c_remove, }; module_i2c_driver(rmi_i2c_driver); diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c index 55bd1b349..4ebef607e 100644 --- a/drivers/input/rmi4/rmi_spi.c +++ b/drivers/input/rmi4/rmi_spi.c @@ -396,6 +396,13 @@ static inline int rmi_spi_of_probe(struct spi_device *spi, } #endif +static void rmi_spi_unregister_transport(void *data) +{ + struct rmi_spi_xport *rmi_spi = data; + + rmi_unregister_transport_device(&rmi_spi->xport); +} + static int rmi_spi_probe(struct spi_device *spi) { struct rmi_spi_xport *rmi_spi; @@ -464,6 +471,11 @@ static int rmi_spi_probe(struct spi_device *spi) dev_err(&spi->dev, "failed to register transport.\n"); return retval; } + retval = devm_add_action_or_reset(&spi->dev, + rmi_spi_unregister_transport, + rmi_spi); + if (retval) + return retval; retval = rmi_spi_init_irq(spi); if (retval < 0) @@ -473,15 +485,6 @@ static int rmi_spi_probe(struct spi_device *spi) return 0; } -static int rmi_spi_remove(struct spi_device *spi) -{ - struct rmi_spi_xport *rmi_spi = spi_get_drvdata(spi); - - rmi_unregister_transport_device(&rmi_spi->xport); - - return 0; -} - #ifdef CONFIG_PM_SLEEP static int rmi_spi_suspend(struct device *dev) { @@ -577,7 +580,6 @@ static struct spi_driver rmi_spi_driver = { }, .id_table = rmi_id, .probe = rmi_spi_probe, - .remove = rmi_spi_remove, }; module_spi_driver(rmi_spi_driver); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 96de97a46..822fc4afa 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1654,6 +1654,9 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) free_pagetable(&dom->domain); + if (dom->domain.id) + domain_id_free(dom->domain.id); + kfree(dom); } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ebb5bf3dd..1257b0b80 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1711,6 +1711,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) if (!iommu->domains || !iommu->domain_ids) return; +again: spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry_safe(info, tmp, &device_domain_list, global) { struct dmar_domain *domain; @@ -1723,10 +1724,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) domain = info->domain; - dmar_remove_one_dev_info(domain, info->dev); + __dmar_remove_one_dev_info(info); - if (!domain_type_is_vm_or_si(domain)) + if (!domain_type_is_vm_or_si(domain)) { + /* + * The domain_exit() function can't be called under + * device_domain_lock, as it takes this lock itself. + * So release the lock here and re-run the loop + * afterwards. + */ + spin_unlock_irqrestore(&device_domain_lock, flags); domain_exit(domain); + goto again; + } } spin_unlock_irqrestore(&device_domain_lock, flags); diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index def8ca1c9..f50e51c1a 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -633,6 +633,10 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, { struct arm_v7s_io_pgtable *data; +#ifdef PHYS_OFFSET + if (upper_32_bits(PHYS_OFFSET)) + return NULL; +#endif if (cfg->ias > ARM_V7S_ADDR_BITS || cfg->oas > ARM_V7S_ADDR_BITS) return NULL; diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c index 128e89613..430014ca6 100644 --- a/drivers/media/usb/dvb-usb/dib0700_core.c +++ b/drivers/media/usb/dvb-usb/dib0700_core.c @@ -677,7 +677,7 @@ static void dib0700_rc_urb_completion(struct urb *purb) struct dvb_usb_device *d = purb->context; struct dib0700_rc_response *poll_reply; enum rc_type protocol; - u32 uninitialized_var(keycode); + u32 keycode; u8 toggle; deb_info("%s()\n", __func__); @@ -719,7 +719,8 @@ static void dib0700_rc_urb_completion(struct urb *purb) poll_reply->nec.data == 0x00 && poll_reply->nec.not_data == 0xff) { poll_reply->data_state = 2; - break; + rc_repeat(d->rc_dev); + goto resubmit; } if ((poll_reply->nec.data ^ poll_reply->nec.not_data) != 0xff) { diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index e9e6ea3ab..75b9d4ac8 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -178,7 +178,7 @@ static int mei_nfc_if_version(struct mei_cl *cl, ret = 0; bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length); - if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) { + if (bytes_recv < if_version_length) { dev_err(bus->dev, "Could not read IF version\n"); ret = -EIO; goto err; diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index c57eb32dc..6ef1e3c73 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -26,6 +26,8 @@ #include "mmc_ops.h" #include "sd_ops.h" +#define DEFAULT_CMD6_TIMEOUT_MS 500 + static const unsigned int tran_exp[] = { 10000, 100000, 1000000, 10000000, 0, 0, 0, 0 @@ -571,6 +573,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) card->erased_byte = 0x0; /* eMMC v4.5 or later */ + card->ext_csd.generic_cmd6_time = DEFAULT_CMD6_TIMEOUT_MS; if (card->ext_csd.rev >= 6) { card->ext_csd.feature_support |= MMC_DISCARD_FEATURE; diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c index d839147e5..44ecebd1e 100644 --- a/drivers/mmc/host/mxs-mmc.c +++ b/drivers/mmc/host/mxs-mmc.c @@ -661,13 +661,13 @@ static int mxs_mmc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, mmc); + spin_lock_init(&host->lock); + ret = devm_request_irq(&pdev->dev, irq_err, mxs_mmc_irq_handler, 0, dev_name(&pdev->dev), host); if (ret) goto out_free_dma; - spin_lock_init(&host->lock); - ret = mmc_add_host(mmc); if (ret) goto out_free_dma; diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 8ef44a2a2..90ed2e12d 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -647,6 +647,7 @@ static int sdhci_msm_probe(struct platform_device *pdev) if (msm_host->pwr_irq < 0) { dev_err(&pdev->dev, "Get pwr_irq failed (%d)\n", msm_host->pwr_irq); + ret = msm_host->pwr_irq; goto clk_disable; } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index a8a022a73..6eb8f0705 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2269,10 +2269,8 @@ static bool sdhci_request_done(struct sdhci_host *host) for (i = 0; i < SDHCI_MAX_MRQS; i++) { mrq = host->mrqs_done[i]; - if (mrq) { - host->mrqs_done[i] = NULL; + if (mrq) break; - } } if (!mrq) { @@ -2303,6 +2301,17 @@ static bool sdhci_request_done(struct sdhci_host *host) * upon error conditions. */ if (sdhci_needs_reset(host, mrq)) { + /* + * Do not finish until command and data lines are available for + * reset. Note there can only be one other mrq, so it cannot + * also be in mrqs_done, otherwise host->cmd and host->data_cmd + * would both be null. + */ + if (host->cmd || host->data_cmd) { + spin_unlock_irqrestore(&host->lock, flags); + return true; + } + /* Some controllers need this kick or reset won't work here */ if (host->quirks & SDHCI_QUIRK_CLOCK_BEFORE_RESET) /* This is to force an update */ @@ -2310,10 +2319,8 @@ static bool sdhci_request_done(struct sdhci_host *host) /* Spec says we should do both at the same time, but Ricoh controllers do not like that. */ - if (!host->cmd) - sdhci_do_reset(host, SDHCI_RESET_CMD); - if (!host->data_cmd) - sdhci_do_reset(host, SDHCI_RESET_DATA); + sdhci_do_reset(host, SDHCI_RESET_CMD); + sdhci_do_reset(host, SDHCI_RESET_DATA); host->pending_reset = false; } @@ -2321,6 +2328,8 @@ static bool sdhci_request_done(struct sdhci_host *host) if (!sdhci_has_requests(host)) sdhci_led_deactivate(host); + host->mrqs_done[i] = NULL; + mmiowb(); spin_unlock_irqrestore(&host->lock, flags); @@ -2500,9 +2509,6 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask) if (!host->data) { struct mmc_command *data_cmd = host->data_cmd; - if (data_cmd) - host->data_cmd = NULL; - /* * The "data complete" interrupt is also used to * indicate that a busy state has ended. See comment @@ -2510,11 +2516,13 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask) */ if (data_cmd && (data_cmd->flags & MMC_RSP_BUSY)) { if (intmask & SDHCI_INT_DATA_TIMEOUT) { + host->data_cmd = NULL; data_cmd->error = -ETIMEDOUT; sdhci_finish_mrq(host, data_cmd->mrq); return; } if (intmask & SDHCI_INT_DATA_END) { + host->data_cmd = NULL; /* * Some cards handle busy-end interrupt * before the command completed, so make diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index c4751ece7..45e87c9cc 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac, u32 ctl; ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL); + + /* preserve ONLY bits 16-17 from current hardware value */ + ctl &= BGMAC_DMA_RX_ADDREXT_MASK; + if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) { ctl &= ~BGMAC_DMA_RX_BL_MASK; ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT; @@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac, ctl &= ~BGMAC_DMA_RX_PT_MASK; ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT; } - ctl &= BGMAC_DMA_RX_ADDREXT_MASK; ctl |= BGMAC_DMA_RX_ENABLE; ctl |= BGMAC_DMA_RX_PARITY_DISABLE; ctl |= BGMAC_DMA_RX_OVERFLOW_CONT; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 8c2220b59..8508813e7 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -49,6 +49,7 @@ #include #include #include +#include #if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE) #define BCM_CNIC 1 @@ -4755,15 +4756,16 @@ bnx2_setup_msix_tbl(struct bnx2 *bp) BNX2_WR(bp, BNX2_PCI_GRC_WINDOW3_ADDR, BNX2_MSIX_PBA_ADDR); } -static int -bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) +static void +bnx2_wait_dma_complete(struct bnx2 *bp) { u32 val; - int i, rc = 0; - u8 old_port; + int i; - /* Wait for the current PCI transaction to complete before - * issuing a reset. */ + /* + * Wait for the current PCI transaction to complete before + * issuing a reset. + */ if ((BNX2_CHIP(bp) == BNX2_CHIP_5706) || (BNX2_CHIP(bp) == BNX2_CHIP_5708)) { BNX2_WR(bp, BNX2_MISC_ENABLE_CLR_BITS, @@ -4787,6 +4789,21 @@ bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) } } + return; +} + + +static int +bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) +{ + u32 val; + int i, rc = 0; + u8 old_port; + + /* Wait for the current PCI transaction to complete before + * issuing a reset. */ + bnx2_wait_dma_complete(bp); + /* Wait for the firmware to tell us it is ok to issue a reset. */ bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT0 | reset_code, 1, 1); @@ -6352,6 +6369,10 @@ bnx2_open(struct net_device *dev) struct bnx2 *bp = netdev_priv(dev); int rc; + rc = bnx2_request_firmware(bp); + if (rc < 0) + goto out; + netif_carrier_off(dev); bnx2_disable_int(bp); @@ -6420,6 +6441,7 @@ open_err: bnx2_free_irq(bp); bnx2_free_mem(bp); bnx2_del_napi(bp); + bnx2_release_firmware(bp); goto out; } @@ -8566,12 +8588,15 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); - rc = bnx2_request_firmware(bp); - if (rc < 0) - goto error; - + /* + * In-flight DMA from 1st kernel could continue going in kdump kernel. + * New io-page table has been created before bnx2 does reset at open stage. + * We have to wait for the in-flight DMA to complete to avoid it look up + * into the newly created io-page table. + */ + if (is_kdump_kernel()) + bnx2_wait_dma_complete(bp); - bnx2_reset_chip(bp, BNX2_DRV_MSG_CODE_RESET); memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN); dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | @@ -8604,7 +8629,6 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; error: - bnx2_release_firmware(bp); pci_iounmap(pdev, bp->regview); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c74d16409..6b46a37ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9001,7 +9001,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return 0; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode, - nlflags, 0, 0, filter_mask, NULL); + 0, 0, nlflags, filter_mask, NULL); } /* Hardware supports L4 tunnel length of 128B (=2^7) which includes diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d48873bcb..5cdc96bdd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -231,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) span_entry->used = true; span_entry->id = index; - span_entry->ref_count = 0; + span_entry->ref_count = 1; span_entry->local_port = local_port; return span_entry; } @@ -268,6 +268,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) span_entry = mlxsw_sp_span_entry_find(port); if (span_entry) { + /* Already exists, just take a reference */ span_entry->ref_count++; return span_entry; } @@ -278,6 +279,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_span_entry *span_entry) { + WARN_ON(!span_entry->ref_count); if (--span_entry->ref_count == 0) mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 3f5c51da6..62514b9bf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -777,6 +777,26 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, } } +static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl) +{ + u8 num_rec, last_rec_index, num_entries; + + num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl); + last_rec_index = num_rec - 1; + + if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM) + return false; + if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) == + MLXSW_REG_RAUHTD_TYPE_IPV6) + return true; + + num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl, + last_rec_index); + if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC) + return true; + return false; +} + static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) { char *rauhtd_pl; @@ -803,7 +823,7 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < num_rec; i++) mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, i); - } while (num_rec); + } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); rtnl_unlock(); kfree(rauhtd_pl); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4c8c60af7..fe9e7b197 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -871,6 +871,13 @@ static int stmmac_init_phy(struct net_device *dev) return -ENODEV; } + /* stmmac_adjust_link will change this to PHY_IGNORE_INTERRUPT to avoid + * subsequent PHY polling, make sure we force a link transition if + * we have a UP/DOWN/UP transition + */ + if (phydev->is_pseudo_fixed_link) + phydev->irq = PHY_POLL; + pr_debug("stmmac_init_phy: %s: attached to PHY (UID 0x%x)" " Link = %d\n", dev->name, phydev->phy_id, phydev->link); diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c index 83deda4bb..6f9563a96 100644 --- a/drivers/nfc/mei_phy.c +++ b/drivers/nfc/mei_phy.c @@ -133,7 +133,7 @@ static int mei_nfc_if_version(struct nfc_mei_phy *phy) return -ENOMEM; bytes_recv = mei_cldev_recv(phy->cldev, (u8 *)reply, if_version_length); - if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) { + if (bytes_recv < 0 || bytes_recv < if_version_length) { pr_err("Could not read IF version\n"); r = -EIO; goto err; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 60f7eab11..da134a0df 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1531,9 +1531,9 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) return 0; } -static void nvme_disable_io_queues(struct nvme_dev *dev) +static void nvme_disable_io_queues(struct nvme_dev *dev, int queues) { - int pass, queues = dev->online_queues - 1; + int pass; unsigned long timeout; u8 opcode = nvme_admin_delete_sq; @@ -1678,7 +1678,7 @@ static void nvme_pci_disable(struct nvme_dev *dev) static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) { - int i; + int i, queues; u32 csts = -1; del_timer_sync(&dev->watchdog_timer); @@ -1689,6 +1689,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) csts = readl(dev->bar + NVME_REG_CSTS); } + queues = dev->online_queues - 1; for (i = dev->queue_count - 1; i > 0; i--) nvme_suspend_queue(dev->queues[i]); @@ -1700,7 +1701,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) if (dev->queue_count) nvme_suspend_queue(dev->queues[0]); } else { - nvme_disable_io_queues(dev); + nvme_disable_io_queues(dev, queues); nvme_disable_admin_queue(dev, shutdown); } nvme_pci_disable(dev); diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 66c4d8f42..9526e3419 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -121,6 +121,14 @@ int pci_claim_resource(struct pci_dev *dev, int resource) return -EINVAL; } + /* + * If we have a shadow copy in RAM, the PCI device doesn't respond + * to the shadow range, so we don't need to claim it, and upstream + * bridges don't need to route the range to the device. + */ + if (res->flags & IORESOURCE_ROM_SHADOW) + return 0; + root = pci_find_parent_resource(dev, res); if (!root) { dev_info(&dev->dev, "can't claim BAR %d %pR: no compatible bridge window\n", diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c index 7f7700716..5d1e505c3 100644 --- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c @@ -844,6 +844,6 @@ static struct platform_driver iproc_gpio_driver = { static int __init iproc_gpio_init(void) { - return platform_driver_probe(&iproc_gpio_driver, iproc_gpio_probe); + return platform_driver_register(&iproc_gpio_driver); } arch_initcall_sync(iproc_gpio_init); diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c index 35783db1c..c8deb8be1 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c @@ -741,6 +741,6 @@ static struct platform_driver nsp_gpio_driver = { static int __init nsp_gpio_init(void) { - return platform_driver_probe(&nsp_gpio_driver, nsp_gpio_probe); + return platform_driver_register(&nsp_gpio_driver); } arch_initcall_sync(nsp_gpio_init); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 0fe8fad25..bc3150428 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1634,12 +1634,15 @@ static int chv_pinctrl_remove(struct platform_device *pdev) } #ifdef CONFIG_PM_SLEEP -static int chv_pinctrl_suspend(struct device *dev) +static int chv_pinctrl_suspend_noirq(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct chv_pinctrl *pctrl = platform_get_drvdata(pdev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&chv_lock, flags); + pctrl->saved_intmask = readl(pctrl->regs + CHV_INTMASK); for (i = 0; i < pctrl->community->npins; i++) { @@ -1660,15 +1663,20 @@ static int chv_pinctrl_suspend(struct device *dev) ctx->padctrl1 = readl(reg); } + raw_spin_unlock_irqrestore(&chv_lock, flags); + return 0; } -static int chv_pinctrl_resume(struct device *dev) +static int chv_pinctrl_resume_noirq(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct chv_pinctrl *pctrl = platform_get_drvdata(pdev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&chv_lock, flags); + /* * Mask all interrupts before restoring per-pin configuration * registers because we don't know in which state BIOS left them @@ -1713,12 +1721,15 @@ static int chv_pinctrl_resume(struct device *dev) chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); chv_writel(pctrl->saved_intmask, pctrl->regs + CHV_INTMASK); + raw_spin_unlock_irqrestore(&chv_lock, flags); + return 0; } #endif static const struct dev_pm_ops chv_pinctrl_pm_ops = { - SET_LATE_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend, chv_pinctrl_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend_noirq, + chv_pinctrl_resume_noirq) }; static const struct acpi_device_id chv_pinctrl_acpi_match[] = { diff --git a/drivers/platform/x86/toshiba-wmi.c b/drivers/platform/x86/toshiba-wmi.c index feac4576b..2df07ee8f 100644 --- a/drivers/platform/x86/toshiba-wmi.c +++ b/drivers/platform/x86/toshiba-wmi.c @@ -24,14 +24,15 @@ #include #include #include +#include MODULE_AUTHOR("Azael Avalos"); MODULE_DESCRIPTION("Toshiba WMI Hotkey Driver"); MODULE_LICENSE("GPL"); -#define TOSHIBA_WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100" +#define WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100" -MODULE_ALIAS("wmi:"TOSHIBA_WMI_EVENT_GUID); +MODULE_ALIAS("wmi:"WMI_EVENT_GUID); static struct input_dev *toshiba_wmi_input_dev; @@ -63,6 +64,16 @@ static void toshiba_wmi_notify(u32 value, void *context) kfree(response.pointer); } +static struct dmi_system_id toshiba_wmi_dmi_table[] __initdata = { + { + .ident = "Toshiba laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + }, + }, + {} +}; + static int __init toshiba_wmi_input_setup(void) { acpi_status status; @@ -81,7 +92,7 @@ static int __init toshiba_wmi_input_setup(void) if (err) goto err_free_dev; - status = wmi_install_notify_handler(TOSHIBA_WMI_EVENT_GUID, + status = wmi_install_notify_handler(WMI_EVENT_GUID, toshiba_wmi_notify, NULL); if (ACPI_FAILURE(status)) { err = -EIO; @@ -95,7 +106,7 @@ static int __init toshiba_wmi_input_setup(void) return 0; err_remove_notifier: - wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID); + wmi_remove_notify_handler(WMI_EVENT_GUID); err_free_keymap: sparse_keymap_free(toshiba_wmi_input_dev); err_free_dev: @@ -105,7 +116,7 @@ static int __init toshiba_wmi_input_setup(void) static void toshiba_wmi_input_destroy(void) { - wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID); + wmi_remove_notify_handler(WMI_EVENT_GUID); sparse_keymap_free(toshiba_wmi_input_dev); input_unregister_device(toshiba_wmi_input_dev); } @@ -114,7 +125,8 @@ static int __init toshiba_wmi_init(void) { int ret; - if (!wmi_has_guid(TOSHIBA_WMI_EVENT_GUID)) + if (!wmi_has_guid(WMI_EVENT_GUID) || + !dmi_check_system(toshiba_wmi_dmi_table)) return -ENODEV; ret = toshiba_wmi_input_setup(); @@ -130,7 +142,7 @@ static int __init toshiba_wmi_init(void) static void __exit toshiba_wmi_exit(void) { - if (wmi_has_guid(TOSHIBA_WMI_EVENT_GUID)) + if (wmi_has_guid(WMI_EVENT_GUID)) toshiba_wmi_input_destroy(); } diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c index b4478cc92..8895f7772 100644 --- a/drivers/rtc/rtc-pcf2123.c +++ b/drivers/rtc/rtc-pcf2123.c @@ -182,7 +182,8 @@ static ssize_t pcf2123_show(struct device *dev, struct device_attribute *attr, } static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr, - const char *buffer, size_t count) { + const char *buffer, size_t count) +{ struct pcf2123_sysfs_reg *r; unsigned long reg; unsigned long val; @@ -199,7 +200,7 @@ static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr, if (ret) return ret; - pcf2123_write_reg(dev, reg, val); + ret = pcf2123_write_reg(dev, reg, val); if (ret < 0) return -EIO; return count; diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 752b5c9d1..920c42151 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -792,6 +792,7 @@ static void alua_rtpg_work(struct work_struct *work) WARN_ON(pg->flags & ALUA_PG_RUN_RTPG); WARN_ON(pg->flags & ALUA_PG_RUN_STPG); spin_unlock_irqrestore(&pg->lock, flags); + kref_put(&pg->kref, release_port_group); return; } if (pg->flags & ALUA_SYNC_STPG) @@ -889,6 +890,7 @@ static void alua_rtpg_queue(struct alua_port_group *pg, /* Do not queue if the worker is already running */ if (!(pg->flags & ALUA_PG_RUNNING)) { kref_get(&pg->kref); + sdev = NULL; start_queue = 1; } } @@ -900,7 +902,8 @@ static void alua_rtpg_queue(struct alua_port_group *pg, if (start_queue && !queue_delayed_work(alua_wq, &pg->rtpg_work, msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) { - scsi_device_put(sdev); + if (sdev) + scsi_device_put(sdev); kref_put(&pg->kref, release_port_group); } } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 4cb79902e..46c0f5ecd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -1273,9 +1273,9 @@ scsih_target_alloc(struct scsi_target *starget) sas_target_priv_data->handle = raid_device->handle; sas_target_priv_data->sas_address = raid_device->wwid; sas_target_priv_data->flags |= MPT_TARGET_FLAGS_VOLUME; - sas_target_priv_data->raid_device = raid_device; if (ioc->is_warpdrive) - raid_device->starget = starget; + sas_target_priv_data->raid_device = raid_device; + raid_device->starget = starget; } spin_unlock_irqrestore(&ioc->raid_device_lock, flags); return 0; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index a44c7c9bd..c172be184 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2341,6 +2341,8 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time) { scsi_qla_host_t *vha = shost_priv(shost); + if (test_bit(UNLOADING, &vha->dpc_flags)) + return 1; if (!vha->host) return 1; if (time > vha->hw->loop_reset_delay * HZ) diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 1deb6adc4..75455d4da 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -621,6 +621,9 @@ int scsi_change_queue_depth(struct scsi_device *sdev, int depth) wmb(); } + if (sdev->request_queue) + blk_set_queue_depth(sdev->request_queue, depth); + return sdev->queue_depth; } EXPORT_SYMBOL(scsi_change_queue_depth); diff --git a/drivers/staging/comedi/drivers/ni_tio.c b/drivers/staging/comedi/drivers/ni_tio.c index 7043eb054..5ab49a798 100644 --- a/drivers/staging/comedi/drivers/ni_tio.c +++ b/drivers/staging/comedi/drivers/ni_tio.c @@ -207,7 +207,8 @@ static int ni_tio_clock_period_ps(const struct ni_gpct *counter, * clock period is specified by user with prescaling * already taken into account. */ - return counter->clock_period_ps; + *period_ps = counter->clock_period_ps; + return 0; } switch (generic_clock_source & NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK) { diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 24c348d2f..98d947338 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -655,6 +655,7 @@ static void ad5933_work(struct work_struct *work) __be16 buf[2]; int val[2]; unsigned char status; + int ret; mutex_lock(&indio_dev->mlock); if (st->state == AD5933_CTRL_INIT_START_FREQ) { @@ -662,19 +663,22 @@ static void ad5933_work(struct work_struct *work) ad5933_cmd(st, AD5933_CTRL_START_SWEEP); st->state = AD5933_CTRL_START_SWEEP; schedule_delayed_work(&st->work, st->poll_time_jiffies); - mutex_unlock(&indio_dev->mlock); - return; + goto out; } - ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status); + ret = ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status); + if (ret) + goto out; if (status & AD5933_STAT_DATA_VALID) { int scan_count = bitmap_weight(indio_dev->active_scan_mask, indio_dev->masklength); - ad5933_i2c_read(st->client, + ret = ad5933_i2c_read(st->client, test_bit(1, indio_dev->active_scan_mask) ? AD5933_REG_REAL_DATA : AD5933_REG_IMAG_DATA, scan_count * 2, (u8 *)buf); + if (ret) + goto out; if (scan_count == 2) { val[0] = be16_to_cpu(buf[0]); @@ -686,8 +690,7 @@ static void ad5933_work(struct work_struct *work) } else { /* no data available - try again later */ schedule_delayed_work(&st->work, st->poll_time_jiffies); - mutex_unlock(&indio_dev->mlock); - return; + goto out; } if (status & AD5933_STAT_SWEEP_DONE) { @@ -700,7 +703,7 @@ static void ad5933_work(struct work_struct *work) ad5933_cmd(st, AD5933_CTRL_INC_FREQ); schedule_delayed_work(&st->work, st->poll_time_jiffies); } - +out: mutex_unlock(&indio_dev->mlock); } diff --git a/drivers/staging/nvec/nvec_ps2.c b/drivers/staging/nvec/nvec_ps2.c index a324322ee..499952c8e 100644 --- a/drivers/staging/nvec/nvec_ps2.c +++ b/drivers/staging/nvec/nvec_ps2.c @@ -106,13 +106,12 @@ static int nvec_mouse_probe(struct platform_device *pdev) { struct nvec_chip *nvec = dev_get_drvdata(pdev->dev.parent); struct serio *ser_dev; - char mouse_reset[] = { NVEC_PS2, SEND_COMMAND, PSMOUSE_RST, 3 }; - ser_dev = devm_kzalloc(&pdev->dev, sizeof(struct serio), GFP_KERNEL); + ser_dev = kzalloc(sizeof(struct serio), GFP_KERNEL); if (!ser_dev) return -ENOMEM; - ser_dev->id.type = SERIO_PS_PSTHRU; + ser_dev->id.type = SERIO_8042; ser_dev->write = ps2_sendcommand; ser_dev->start = ps2_startstreaming; ser_dev->stop = ps2_stopstreaming; @@ -127,9 +126,6 @@ static int nvec_mouse_probe(struct platform_device *pdev) serio_register_port(ser_dev); - /* mouse reset */ - nvec_write_async(nvec, mouse_reset, sizeof(mouse_reset)); - return 0; } diff --git a/drivers/staging/sm750fb/ddk750_reg.h b/drivers/staging/sm750fb/ddk750_reg.h index 955247979..4ed6d8d77 100644 --- a/drivers/staging/sm750fb/ddk750_reg.h +++ b/drivers/staging/sm750fb/ddk750_reg.h @@ -601,13 +601,13 @@ #define PANEL_PLANE_TL 0x08001C #define PANEL_PLANE_TL_TOP_SHIFT 16 -#define PANEL_PLANE_TL_TOP_MASK (0xeff << 16) -#define PANEL_PLANE_TL_LEFT_MASK 0xeff +#define PANEL_PLANE_TL_TOP_MASK (0x7ff << 16) +#define PANEL_PLANE_TL_LEFT_MASK 0x7ff #define PANEL_PLANE_BR 0x080020 #define PANEL_PLANE_BR_BOTTOM_SHIFT 16 -#define PANEL_PLANE_BR_BOTTOM_MASK (0xeff << 16) -#define PANEL_PLANE_BR_RIGHT_MASK 0xeff +#define PANEL_PLANE_BR_BOTTOM_MASK (0x7ff << 16) +#define PANEL_PLANE_BR_RIGHT_MASK 0x7ff #define PANEL_HORIZONTAL_TOTAL 0x080024 #define PANEL_HORIZONTAL_TOTAL_TOTAL_SHIFT 16 diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 8bbde52db..21aeac59d 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2026,6 +2026,7 @@ static void atmel_serial_pm(struct uart_port *port, unsigned int state, static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { + struct atmel_uart_port *atmel_port = to_atmel_uart_port(port); unsigned long flags; unsigned int old_mode, mode, imr, quot, baud; @@ -2129,11 +2130,29 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, mode |= ATMEL_US_USMODE_RS485; } else if (termios->c_cflag & CRTSCTS) { /* RS232 with hardware handshake (RTS/CTS) */ - if (atmel_use_dma_rx(port) && !atmel_use_fifo(port)) { - dev_info(port->dev, "not enabling hardware flow control because DMA is used"); - termios->c_cflag &= ~CRTSCTS; - } else { + if (atmel_use_fifo(port) && + !mctrl_gpio_to_gpiod(atmel_port->gpios, UART_GPIO_CTS)) { + /* + * with ATMEL_US_USMODE_HWHS set, the controller will + * be able to drive the RTS pin high/low when the RX + * FIFO is above RXFTHRES/below RXFTHRES2. + * It will also disable the transmitter when the CTS + * pin is high. + * This mode is not activated if CTS pin is a GPIO + * because in this case, the transmitter is always + * disabled (there must be an internal pull-up + * responsible for this behaviour). + * If the RTS pin is a GPIO, the controller won't be + * able to drive it according to the FIFO thresholds, + * but it will be handled by the driver. + */ mode |= ATMEL_US_USMODE_HWHS; + } else { + /* + * For platforms without FIFO, the flow control is + * handled by the driver. + */ + mode |= ATMEL_US_USMODE_NORMAL; } } else { /* RS232 without hadware handshake */ diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 0f3f62e81..3ca9fdb0a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -946,8 +946,6 @@ static int wait_serial_change(struct acm *acm, unsigned long arg) DECLARE_WAITQUEUE(wait, current); struct async_icount old, new; - if (arg & (TIOCM_DSR | TIOCM_RI | TIOCM_CD)) - return -EINVAL; do { spin_lock_irq(&acm->read_lock); old = acm->oldcount; @@ -1175,6 +1173,8 @@ static int acm_probe(struct usb_interface *intf, if (quirks == IGNORE_DEVICE) return -ENODEV; + memset(&h, 0x00, sizeof(struct usb_cdc_parsed_header)); + num_rx_buf = (quirks == SINGLE_RX_URB) ? 1 : ACM_NR; /* handle quirks deadly to normal probing*/ diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 35d092456..2d47010e5 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -669,15 +669,14 @@ static int dwc3_core_init(struct dwc3 *dwc) return 0; err4: - phy_power_off(dwc->usb2_generic_phy); + phy_power_off(dwc->usb3_generic_phy); err3: - phy_power_off(dwc->usb3_generic_phy); + phy_power_off(dwc->usb2_generic_phy); err2: usb_phy_set_suspend(dwc->usb2_phy, 1); usb_phy_set_suspend(dwc->usb3_phy, 1); - dwc3_core_exit(dwc); err1: usb_phy_shutdown(dwc->usb2_phy); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 5c8429f23..3a5530d05 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -133,8 +133,60 @@ struct ffs_epfile { /* * Buffer for holding data from partial reads which may happen since * we’re rounding user read requests to a multiple of a max packet size. + * + * The pointer is initialised with NULL value and may be set by + * __ffs_epfile_read_data function to point to a temporary buffer. + * + * In normal operation, calls to __ffs_epfile_read_buffered will consume + * data from said buffer and eventually free it. Importantly, while the + * function is using the buffer, it sets the pointer to NULL. This is + * all right since __ffs_epfile_read_data and __ffs_epfile_read_buffered + * can never run concurrently (they are synchronised by epfile->mutex) + * so the latter will not assign a new value to the pointer. + * + * Meanwhile ffs_func_eps_disable frees the buffer (if the pointer is + * valid) and sets the pointer to READ_BUFFER_DROP value. This special + * value is crux of the synchronisation between ffs_func_eps_disable and + * __ffs_epfile_read_data. + * + * Once __ffs_epfile_read_data is about to finish it will try to set the + * pointer back to its old value (as described above), but seeing as the + * pointer is not-NULL (namely READ_BUFFER_DROP) it will instead free + * the buffer. + * + * == State transitions == + * + * • ptr == NULL: (initial state) + * ◦ __ffs_epfile_read_buffer_free: go to ptr == DROP + * ◦ __ffs_epfile_read_buffered: nop + * ◦ __ffs_epfile_read_data allocates temp buffer: go to ptr == buf + * ◦ reading finishes: n/a, not in ‘and reading’ state + * • ptr == DROP: + * ◦ __ffs_epfile_read_buffer_free: nop + * ◦ __ffs_epfile_read_buffered: go to ptr == NULL + * ◦ __ffs_epfile_read_data allocates temp buffer: free buf, nop + * ◦ reading finishes: n/a, not in ‘and reading’ state + * • ptr == buf: + * ◦ __ffs_epfile_read_buffer_free: free buf, go to ptr == DROP + * ◦ __ffs_epfile_read_buffered: go to ptr == NULL and reading + * ◦ __ffs_epfile_read_data: n/a, __ffs_epfile_read_buffered + * is always called first + * ◦ reading finishes: n/a, not in ‘and reading’ state + * • ptr == NULL and reading: + * ◦ __ffs_epfile_read_buffer_free: go to ptr == DROP and reading + * ◦ __ffs_epfile_read_buffered: n/a, mutex is held + * ◦ __ffs_epfile_read_data: n/a, mutex is held + * ◦ reading finishes and … + * … all data read: free buf, go to ptr == NULL + * … otherwise: go to ptr == buf and reading + * • ptr == DROP and reading: + * ◦ __ffs_epfile_read_buffer_free: nop + * ◦ __ffs_epfile_read_buffered: n/a, mutex is held + * ◦ __ffs_epfile_read_data: n/a, mutex is held + * ◦ reading finishes: free buf, go to ptr == DROP */ - struct ffs_buffer *read_buffer; /* P: epfile->mutex */ + struct ffs_buffer *read_buffer; +#define READ_BUFFER_DROP ((struct ffs_buffer *)ERR_PTR(-ESHUTDOWN)) char name[5]; @@ -733,25 +785,47 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, schedule_work(&io_data->work); } +static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile) +{ + /* + * See comment in struct ffs_epfile for full read_buffer pointer + * synchronisation story. + */ + struct ffs_buffer *buf = xchg(&epfile->read_buffer, READ_BUFFER_DROP); + if (buf && buf != READ_BUFFER_DROP) + kfree(buf); +} + /* Assumes epfile->mutex is held. */ static ssize_t __ffs_epfile_read_buffered(struct ffs_epfile *epfile, struct iov_iter *iter) { - struct ffs_buffer *buf = epfile->read_buffer; + /* + * Null out epfile->read_buffer so ffs_func_eps_disable does not free + * the buffer while we are using it. See comment in struct ffs_epfile + * for full read_buffer pointer synchronisation story. + */ + struct ffs_buffer *buf = xchg(&epfile->read_buffer, NULL); ssize_t ret; - if (!buf) + if (!buf || buf == READ_BUFFER_DROP) return 0; ret = copy_to_iter(buf->data, buf->length, iter); if (buf->length == ret) { kfree(buf); - epfile->read_buffer = NULL; - } else if (unlikely(iov_iter_count(iter))) { + return ret; + } + + if (unlikely(iov_iter_count(iter))) { ret = -EFAULT; } else { buf->length -= ret; buf->data += ret; } + + if (cmpxchg(&epfile->read_buffer, NULL, buf)) + kfree(buf); + return ret; } @@ -780,7 +854,15 @@ static ssize_t __ffs_epfile_read_data(struct ffs_epfile *epfile, buf->length = data_len; buf->data = buf->storage; memcpy(buf->storage, data + ret, data_len); - epfile->read_buffer = buf; + + /* + * At this point read_buffer is NULL or READ_BUFFER_DROP (if + * ffs_func_eps_disable has been called in the meanwhile). See comment + * in struct ffs_epfile for full read_buffer pointer synchronisation + * story. + */ + if (unlikely(cmpxchg(&epfile->read_buffer, NULL, buf))) + kfree(buf); return ret; } @@ -1094,8 +1176,7 @@ ffs_epfile_release(struct inode *inode, struct file *file) ENTER(); - kfree(epfile->read_buffer); - epfile->read_buffer = NULL; + __ffs_epfile_read_buffer_free(epfile); ffs_data_closed(epfile->ffs); return 0; @@ -1721,24 +1802,20 @@ static void ffs_func_eps_disable(struct ffs_function *func) unsigned count = func->ffs->eps_count; unsigned long flags; + spin_lock_irqsave(&func->ffs->eps_lock, flags); do { - if (epfile) - mutex_lock(&epfile->mutex); - spin_lock_irqsave(&func->ffs->eps_lock, flags); /* pending requests get nuked */ if (likely(ep->ep)) usb_ep_disable(ep->ep); ++ep; - spin_unlock_irqrestore(&func->ffs->eps_lock, flags); if (epfile) { epfile->ep = NULL; - kfree(epfile->read_buffer); - epfile->read_buffer = NULL; - mutex_unlock(&epfile->mutex); + __ffs_epfile_read_buffer_free(epfile); ++epfile; } } while (--count); + spin_unlock_irqrestore(&func->ffs->eps_lock, flags); } static int ffs_func_eps_enable(struct ffs_function *func) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 9b9e71f2c..f590adaab 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -585,14 +585,6 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, req->length = length; - /* throttle high/super speed IRQ rate back slightly */ - if (gadget_is_dualspeed(dev->gadget)) - req->no_interrupt = (((dev->gadget->speed == USB_SPEED_HIGH || - dev->gadget->speed == USB_SPEED_SUPER)) && - !list_empty(&dev->tx_reqs)) - ? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0) - : 0; - retval = usb_ep_queue(in, req, GFP_ATOMIC); switch (retval) { default: diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 6abb83cd7..74265b2f8 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -349,7 +349,7 @@ int devm_watchdog_register_device(struct device *dev, struct watchdog_device **rcwdd; int ret; - rcwdd = devres_alloc(devm_watchdog_unregister_device, sizeof(*wdd), + rcwdd = devres_alloc(devm_watchdog_unregister_device, sizeof(*rcwdd), GFP_KERNEL); if (!rcwdd) return -ENOMEM; diff --git a/fs/buffer.c b/fs/buffer.c index 9c8eb9b6d..6a5f1a011 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1698,7 +1698,7 @@ int __block_write_full_page(struct inode *inode, struct page *page, struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; - int write_flags = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0); + int write_flags = wbc_to_write_flags(wbc); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); diff --git a/fs/coredump.c b/fs/coredump.c index 281b76800..eb9c92c9b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1,6 +1,7 @@ #include #include #include +#include #include #include #include @@ -423,7 +424,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state) if (core_waiters > 0) { struct core_thread *ptr; + freezer_do_not_count(); wait_for_completion(&core_state->startup); + freezer_count(); /* * Wait for all the threads to become inactive, so that * all the thread context (extended register state, like diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ccb401eeb..cb0528b31 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1240,7 +1240,7 @@ static int f2fs_write_data_page(struct page *page, .sbi = sbi, .type = DATA, .op = REQ_OP_WRITE, - .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0, + .op_flags = wbc_to_write_flags(wbc), .page = page, .encrypted_page = NULL, }; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f75d197d5..c1713da25 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1561,7 +1561,7 @@ static int f2fs_write_node_page(struct page *page, .sbi = sbi, .type = NODE, .op = REQ_OP_WRITE, - .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0, + .op_flags = wbc_to_write_flags(wbc), .page = page, .encrypted_page = NULL, }; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 950b8be68..7991c62e9 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -37,8 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb { struct buffer_head *bh, *head; int nr_underway = 0; - int write_flags = REQ_META | REQ_PRIO | - (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0); + int write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc); BUG_ON(!PageLocked(page)); BUG_ON(!page_has_buffers(page)); diff --git a/fs/mpage.c b/fs/mpage.c index d2413af08..d6f1afe33 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -489,7 +489,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, struct buffer_head map_bh; loff_t i_size = i_size_read(inode); int ret = 0; - int op_flags = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0); + int op_flags = wbc_to_write_flags(wbc); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index b62973045..150c5a187 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -178,12 +178,14 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, __must_hold(&tbl->slot_tbl_lock) { struct nfs4_slot *slot; + int ret; slot = nfs4_lookup_slot(tbl, slotid); - if (IS_ERR(slot)) - return PTR_ERR(slot); - *seq_nr = slot->seq_nr; - return 0; + ret = PTR_ERR_OR_ZERO(slot); + if (!ret) + *seq_nr = slot->seq_nr; + + return ret; } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 7575cfc3a..a68645abd 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -447,8 +447,8 @@ xfs_submit_ioend( ioend->io_bio->bi_private = ioend; ioend->io_bio->bi_end_io = xfs_end_bio; - bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE, - (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0); + bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE, wbc_to_write_flags(wbc)); + /* * If we are failing the IO now, just mark the ioend with an * error and finish it. This will run IO completion immediately @@ -519,8 +519,7 @@ xfs_chain_bio( bio_chain(ioend->io_bio, new); bio_get(ioend->io_bio); /* for xfs_destroy_ioend */ - bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE, - (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0); + bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE, wbc_to_write_flags(wbc)); submit_bio(ioend->io_bio); ioend->io_bio = new; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c5eaf2f80..67d1d3ebb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -318,6 +318,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); +void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c357f27d5..dc5f76d7f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -116,6 +116,8 @@ struct bdi_writeback { struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ + unsigned long dirty_sleep; /* last wait */ + struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 436f43f87..95fbfa1fe 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -155,6 +155,7 @@ enum rq_flag_bits { __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ + __REQ_BG, /* background activity */ /* bio only flags */ __REQ_RAHEAD, /* read ahead, can fail anytime */ @@ -198,7 +199,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE) + REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE | REQ_BG) #define REQ_CLONE_MASK REQ_COMMON_MASK /* This mask is used for both bio and request merge checking */ @@ -223,6 +224,7 @@ enum rq_flag_bits { #define REQ_COPY_USER (1ULL << __REQ_COPY_USER) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) +#define REQ_BG (1ULL << __REQ_BG) #define REQ_IO_STAT (1ULL << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) #define REQ_PM (1ULL << __REQ_PM) @@ -264,4 +266,16 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } +#define BLK_RQ_STAT_BATCH 64 + +struct blk_rq_stat { + s64 mean; + u64 min; + u64 max; + s32 nr_samples; + s32 nr_batch; + u64 batch; + s64 time; +}; + #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9de483535..17d4bc5d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -37,10 +38,11 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; +struct rq_wb; #define BLKDEV_MIN_RQ 4 #ifdef CONFIG_PCK_INTERACTIVE -#define BLKDEV_MAX_RQ 16 +#define BLKDEV_MAX_RQ 512 #else #define BLKDEV_MAX_RQ 128 /* Default maximum */ #endif @@ -155,6 +157,7 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; unsigned long start_time; + struct wb_issue_stat wb_stat; #ifdef CONFIG_BLK_CGROUP struct request_list *rl; /* rl this rq is alloced from */ unsigned long long start_time_ns; @@ -306,6 +309,8 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + struct rq_wb *rq_wb; + /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg * is used, root blkg allocates from @q->root_rl and all other @@ -331,6 +336,8 @@ struct request_queue { struct blk_mq_ctx __percpu *queue_ctx; unsigned int nr_queues; + unsigned int queue_depth; + /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; @@ -416,6 +423,9 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; + + struct blk_rq_stat rq_stats[2]; + /* * Number of active block driver functions for which blk_drain_queue() * must wait. Must be incremented around functions that unlock the @@ -687,6 +697,14 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) return false; } +static inline unsigned int blk_queue_depth(struct request_queue *q) +{ + if (q->queue_depth) + return q->queue_depth; + + return q->nr_requests; +} + /* * q->prep_rq_fn return values */ @@ -1003,6 +1021,7 @@ extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); +extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index c46d2aa16..1d18af034 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -106,8 +106,9 @@ static inline void frontswap_invalidate_area(unsigned type) static inline void frontswap_init(unsigned type, unsigned long *map) { - if (frontswap_enabled()) - __frontswap_init(type, map); +#ifdef CONFIG_FRONTSWAP + __frontswap_init(type, map); +#endif } #endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 1b5999474..6f180afdd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -189,6 +189,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded * by a cache flush and data is guaranteed to be on * non-volatile media on completion. + * WRITE_BG Background write. This is for background activity like + * the periodic flush and background threshold writeback * */ #define RW_MASK REQ_OP_WRITE @@ -202,6 +204,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH) #define WRITE_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FUA) #define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) +#define WRITE_BG (REQ_NOIDLE | REQ_BG) /* * Attribute flags. These should be or-ed together to figure out what diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d6917b896..3584bc886 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -86,6 +86,7 @@ struct svc_rdma_op_ctxt { unsigned long flags; enum dma_data_direction direction; int count; + unsigned int mapped_sges; struct ib_sge sge[RPCSVC_MAXPAGES]; struct page *pages[RPCSVC_MAXPAGES]; }; @@ -193,6 +194,14 @@ struct svcxprt_rdma { #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD +/* Track DMA maps for this transport and context */ +static inline void svc_rdma_count_mappings(struct svcxprt_rdma *rdma, + struct svc_rdma_op_ctxt *ctxt) +{ + ctxt->mapped_sges++; + atomic_inc(&rdma->sc_dma_used); +} + /* svc_rdma_backchannel.c */ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct rpcrdma_msg *rmsgp, diff --git a/include/linux/wbt.h b/include/linux/wbt.h new file mode 100644 index 000000000..68ba75e3a --- /dev/null +++ b/include/linux/wbt.h @@ -0,0 +1,141 @@ +#ifndef WB_THROTTLE_H +#define WB_THROTTLE_H + +#include +#include +#include +#include + +enum wbt_flags { + WBT_TRACKED = 1, /* write, tracked for throttling */ + WBT_READ = 2, /* read */ + WBT_KSWAPD = 4, /* write, from kswapd */ + + WBT_NR_BITS = 3, /* number of bits */ +}; + +enum { + /* + * Set aside 3 bits for state, rest is a time stamp + */ + ISSUE_STAT_SHIFT = 64 - WBT_NR_BITS, + ISSUE_STAT_MASK = ~((1ULL << ISSUE_STAT_SHIFT) - 1), + ISSUE_STAT_TIME_MASK = ~ISSUE_STAT_MASK, + + WBT_NUM_RWQ = 2, +}; + +struct wb_issue_stat { + u64 time; +}; + +static inline void wbt_issue_stat_set_time(struct wb_issue_stat *stat) +{ + stat->time = (stat->time & ISSUE_STAT_MASK) | + (ktime_to_ns(ktime_get()) & ISSUE_STAT_TIME_MASK); +} + +static inline u64 wbt_issue_stat_get_time(struct wb_issue_stat *stat) +{ + return stat->time & ISSUE_STAT_TIME_MASK; +} + +static inline void wbt_clear_state(struct wb_issue_stat *stat) +{ + stat->time &= ISSUE_STAT_TIME_MASK; +} + +static inline enum wbt_flags wbt_stat_to_mask(struct wb_issue_stat *stat) +{ + return (stat->time & ISSUE_STAT_MASK) >> ISSUE_STAT_SHIFT; +} + +static inline void wbt_track(struct wb_issue_stat *stat, enum wbt_flags wb_acct) +{ + stat->time |= ((u64) wb_acct) << ISSUE_STAT_SHIFT; +} + +static inline bool wbt_is_tracked(struct wb_issue_stat *stat) +{ + return (stat->time >> ISSUE_STAT_SHIFT) & WBT_TRACKED; +} + +static inline bool wbt_is_read(struct wb_issue_stat *stat) +{ + return (stat->time >> ISSUE_STAT_SHIFT) & WBT_READ; +} + +struct wb_stat_ops { + void (*get)(void *, struct blk_rq_stat *); + bool (*is_current)(struct blk_rq_stat *); + void (*clear)(void *); +}; + +struct rq_wait { + wait_queue_head_t wait; + atomic_t inflight; +}; + +struct rq_wb { + /* + * Settings that govern how we throttle + */ + unsigned int wb_background; /* background writeback */ + unsigned int wb_normal; /* normal writeback */ + unsigned int wb_max; /* max throughput writeback */ + int scale_step; + bool scaled_max; + + /* + * Number of consecutive periods where we don't have enough + * information to make a firm scale up/down decision. + */ + unsigned int unknown_cnt; + + u64 win_nsec; /* default window size */ + u64 cur_win_nsec; /* current window size */ + + struct timer_list window_timer; + + s64 sync_issue; + void *sync_cookie; + + unsigned int wc; + unsigned int queue_depth; + + unsigned long last_issue; /* last non-throttled issue */ + unsigned long last_comp; /* last non-throttled comp */ + unsigned long min_lat_nsec; + struct backing_dev_info *bdi; + struct rq_wait rq_wait[WBT_NUM_RWQ]; + + struct wb_stat_ops *stat_ops; + void *ops_data; +}; + +static inline unsigned int wbt_inflight(struct rq_wb *rwb) +{ + unsigned int i, ret = 0; + + for (i = 0; i < WBT_NUM_RWQ; i++) + ret += atomic_read(&rwb->rq_wait[i].inflight); + + return ret; +} + +struct backing_dev_info; + +void __wbt_done(struct rq_wb *, enum wbt_flags); +void wbt_done(struct rq_wb *, struct wb_issue_stat *); +enum wbt_flags wbt_wait(struct rq_wb *, unsigned int, spinlock_t *); +struct rq_wb *wbt_init(struct backing_dev_info *, struct wb_stat_ops *, void *); +void wbt_exit(struct rq_wb *); +void wbt_update_limits(struct rq_wb *); +void wbt_requeue(struct rq_wb *, struct wb_issue_stat *); +void wbt_issue(struct rq_wb *, struct wb_issue_stat *); +void wbt_disable(struct rq_wb *); + +void wbt_set_queue_depth(struct rq_wb *, unsigned int); +void wbt_set_write_cache(struct rq_wb *, bool); + +#endif diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fc1e16c25..e53abf2bf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -100,6 +100,16 @@ struct writeback_control { #endif }; +static inline int wbc_to_write_flags(struct writeback_control *wbc) +{ + if (wbc->sync_mode == WB_SYNC_ALL) + return WRITE_SYNC; + else if (wbc->for_kupdate || wbc->for_background) + return WRITE_BG; + + return 0; +} + /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global diff --git a/include/net/ip.h b/include/net/ip.h index 156b0c11b..0ccf6daf6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -47,7 +47,6 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) -#define IPSKB_FRAG_SEGS BIT(7) u16 frag_max_size; }; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 43a5a0e45..b01d5d1d7 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -145,6 +145,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/include/net/sock.h b/include/net/sock.h index 8741988e6..c26eab962 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1587,11 +1587,11 @@ static inline void sock_put(struct sock *sk) void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, - unsigned int trim_cap); + unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { - return __sk_receive_skb(sk, skb, nested, 1); + return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) diff --git a/include/net/tcp.h b/include/net/tcp.h index a73218c3a..eb89754be 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1170,6 +1170,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) } bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); +int tcp_filter(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h new file mode 100644 index 000000000..926c7ee0e --- /dev/null +++ b/include/trace/events/wbt.h @@ -0,0 +1,153 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM wbt + +#if !defined(_TRACE_WBT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_WBT_H + +#include +#include + +/** + * wbt_stat - trace stats for blk_wb + * @stat: array of read/write stats + */ +TRACE_EVENT(wbt_stat, + + TP_PROTO(struct backing_dev_info *bdi, struct blk_rq_stat *stat), + + TP_ARGS(bdi, stat), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(s64, rmean) + __field(u64, rmin) + __field(u64, rmax) + __field(s64, rnr_samples) + __field(s64, rtime) + __field(s64, wmean) + __field(u64, wmin) + __field(u64, wmax) + __field(s64, wnr_samples) + __field(s64, wtime) + ), + + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->rmean = stat[0].mean; + __entry->rmin = stat[0].min; + __entry->rmax = stat[0].max; + __entry->rnr_samples = stat[0].nr_samples; + __entry->wmean = stat[1].mean; + __entry->wmin = stat[1].min; + __entry->wmax = stat[1].max; + __entry->wnr_samples = stat[1].nr_samples; + ), + + TP_printk("%s: rmean=%llu, rmin=%llu, rmax=%llu, rsamples=%llu, " + "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu\n", + __entry->name, __entry->rmean, __entry->rmin, __entry->rmax, + __entry->rnr_samples, __entry->wmean, __entry->wmin, + __entry->wmax, __entry->wnr_samples) +); + +/** + * wbt_lat - trace latency event + * @lat: latency trigger + */ +TRACE_EVENT(wbt_lat, + + TP_PROTO(struct backing_dev_info *bdi, unsigned long lat), + + TP_ARGS(bdi, lat), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(unsigned long, lat) + ), + + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->lat = div_u64(lat, 1000); + ), + + TP_printk("%s: latency %lluus\n", __entry->name, + (unsigned long long) __entry->lat) +); + +/** + * wbt_step - trace wb event step + * @msg: context message + * @step: the current scale step count + * @window: the current monitoring window + * @bg: the current background queue limit + * @normal: the current normal writeback limit + * @max: the current max throughput writeback limit + */ +TRACE_EVENT(wbt_step, + + TP_PROTO(struct backing_dev_info *bdi, const char *msg, + int step, unsigned long window, unsigned int bg, + unsigned int normal, unsigned int max), + + TP_ARGS(bdi, msg, step, window, bg, normal, max), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(const char *, msg) + __field(int, step) + __field(unsigned long, window) + __field(unsigned int, bg) + __field(unsigned int, normal) + __field(unsigned int, max) + ), + + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->msg = msg; + __entry->step = step; + __entry->window = div_u64(window, 1000); + __entry->bg = bg; + __entry->normal = normal; + __entry->max = max; + ), + + TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u\n", + __entry->name, __entry->msg, __entry->step, __entry->window, + __entry->bg, __entry->normal, __entry->max) +); + +/** + * wbt_timer - trace wb timer event + * @status: timer state status + * @step: the current scale step count + * @inflight: tracked writes inflight + */ +TRACE_EVENT(wbt_timer, + + TP_PROTO(struct backing_dev_info *bdi, unsigned int status, + int step, unsigned int inflight), + + TP_ARGS(bdi, status, step, inflight), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(unsigned int, status) + __field(int, step) + __field(unsigned int, inflight) + ), + + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->status = status; + __entry->step = step; + __entry->inflight = inflight; + ), + + TP_printk("%s: status=%u, step=%d, inflight=%u\n", __entry->name, + __entry->status, __entry->step, __entry->inflight) +); + +#endif /* _TRACE_WBT_H */ + +/* This part must be outside protection */ +#include diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 5cd4d4d2d..9c9c6ad55 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -14,7 +14,6 @@ #include #include -#include #define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) /* get pool statistics */ diff --git a/init/Kconfig b/init/Kconfig index e442b914c..bc6cd04d1 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -50,8 +50,7 @@ config PCK_INTERACTIVE --- Block Layer ---------------------------------------- - NCQ Queue Depth................: 31 -> 8 - Block Layer Queue Depth........: 128 -> 16 + Block Layer Queue Depth........: 128 -> 512 --- CPU Scheduler (CFS) -------------------------------- diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz index ecde22d15..1532e4e14 100644 --- a/kernel/Kconfig.hz +++ b/kernel/Kconfig.hz @@ -4,8 +4,8 @@ choice prompt "Timer frequency" - default HZ_250 - default HZ_100 if SCHED_MUQSS + default HZ_128 if SCHED_MUQSS + default HZ_250 if !SCHED_MUQSS help Allows the configuration of the timer frequency. It is customary to have the timer interrupt run at 1000 Hz but 100 Hz may be more @@ -24,6 +24,16 @@ choice with lots of processors that may show reduced performance if too many timer interrupts are occurring. + config HZ_128 + bool "128 HZ" + help + 128 Hz is a suitable choice in combination with MuQSS which does + not rely on ticks for rescheduling interrupts, and is not Hz limited + for timeouts and sleeps from both the kernel and userspace. + This allows us to benefit from the lower overhead and higher + throughput of fewer timer ticks and the microoptimisation of Hz + divisions being a power of 2. + config HZ_250 bool "250 HZ" help @@ -51,6 +61,7 @@ endchoice config HZ int default 100 if HZ_100 + default 128 if HZ_128 default 250 if HZ_250 default 300 if HZ_300 default 1000 if HZ_1000 diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 570eeca7b..ad1bc67af 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -687,7 +687,8 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - htab_elem_free(htab, l); + if (l->state != HTAB_EXTRA_ELEM_USED) + htab_elem_free(htab, l); } } } diff --git a/kernel/sched/MuQSS.c b/kernel/sched/MuQSS.c index e256bd60a..ba45cf37b 100644 --- a/kernel/sched/MuQSS.c +++ b/kernel/sched/MuQSS.c @@ -137,7 +137,7 @@ void print_scheduler_version(void) { - printk(KERN_INFO "MuQSS CPU scheduler v0.140 by Con Kolivas.\n"); + printk(KERN_INFO "MuQSS CPU scheduler v0.144 by Con Kolivas.\n"); } /* @@ -2357,6 +2357,76 @@ static void account_task_cpu(struct rq *rq, struct task_struct *p) p->last_ran = rq->niffies; } +static inline int hrexpiry_enabled(struct rq *rq) +{ + if (unlikely(!cpu_active(cpu_of(rq)) || !sched_smp_initialized)) + return 0; + return hrtimer_is_hres_active(&rq->hrexpiry_timer); +} + +/* + * Use HR-timers to deliver accurate preemption points. + */ +static inline void hrexpiry_clear(struct rq *rq) +{ + if (!hrexpiry_enabled(rq)) + return; + if (hrtimer_active(&rq->hrexpiry_timer)) + hrtimer_cancel(&rq->hrexpiry_timer); +} + +/* + * High-resolution time_slice expiry. + * Runs from hardirq context with interrupts disabled. + */ +static enum hrtimer_restart hrexpiry(struct hrtimer *timer) +{ + struct rq *rq = container_of(timer, struct rq, hrexpiry_timer); + struct task_struct *p; + + /* This can happen during CPU hotplug / resume */ + if (unlikely(cpu_of(rq) != smp_processor_id())) + goto out; + + /* + * We're doing this without the runqueue lock but this should always + * be run on the local CPU. Time slice should run out in __schedule + * but we set it to zero here in case niffies is slightly less. + */ + p = rq->curr; + p->time_slice = 0; + __set_tsk_resched(p); +out: + return HRTIMER_NORESTART; +} + +/* + * Called to set the hrexpiry timer state. + * + * called with irqs disabled from the local CPU only + */ +static void hrexpiry_start(struct rq *rq, u64 delay) +{ + if (!hrexpiry_enabled(rq)) + return; + + hrtimer_start(&rq->hrexpiry_timer, ns_to_ktime(delay), + HRTIMER_MODE_REL_PINNED); +} + +static void init_rq_hrexpiry(struct rq *rq) +{ + hrtimer_init(&rq->hrexpiry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrexpiry_timer.function = hrexpiry; +} + +static inline int rq_dither(struct rq *rq) +{ + if (!hrexpiry_enabled(rq)) + return HALF_JIFFY_US; + return 0; +} + /* * wake_up_new_task - wake up a newly created task for the first time. * @@ -2425,8 +2495,14 @@ void wake_up_new_task(struct task_struct *p) * usually avoids a lot of COW overhead. */ __set_tsk_resched(rq_curr); - } else + } else { + /* + * Adjust the hrexpiry since rq_curr will keep + * running and its timeslice has been shortened. + */ + hrexpiry_start(rq, US_TO_NS(rq_curr->time_slice)); try_preempt(p, new_rq); + } } } else { time_slice_expired(p, new_rq); @@ -3108,87 +3184,6 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } -#ifdef CONFIG_HIGH_RES_TIMERS -static inline int hrexpiry_enabled(struct rq *rq) -{ - if (unlikely(!cpu_active(cpu_of(rq)) || !sched_smp_initialized)) - return 0; - return hrtimer_is_hres_active(&rq->hrexpiry_timer); -} - -/* - * Use HR-timers to deliver accurate preemption points. - */ -static void hrexpiry_clear(struct rq *rq) -{ - if (!hrexpiry_enabled(rq)) - return; - if (hrtimer_active(&rq->hrexpiry_timer)) - hrtimer_cancel(&rq->hrexpiry_timer); -} - -/* - * High-resolution time_slice expiry. - * Runs from hardirq context with interrupts disabled. - */ -static enum hrtimer_restart hrexpiry(struct hrtimer *timer) -{ - struct rq *rq = container_of(timer, struct rq, hrexpiry_timer); - struct task_struct *p; - - /* This can happen during CPU hotplug / resume */ - if (unlikely(cpu_of(rq) != smp_processor_id())) - goto out; - - /* - * We're doing this without the runqueue lock but this should always - * be run on the local CPU. Time slice should run out in __schedule - * but we set it to zero here in case niffies is slightly less. - */ - p = rq->curr; - p->time_slice = 0; - __set_tsk_resched(p); -out: - return HRTIMER_NORESTART; -} - -/* - * Called to set the hrexpiry timer state. - * - * called with irqs disabled from the local CPU only - */ -static void hrexpiry_start(struct rq *rq, u64 delay) -{ - if (!hrexpiry_enabled(rq)) - return; - - hrtimer_start(&rq->hrexpiry_timer, ns_to_ktime(delay), - HRTIMER_MODE_REL_PINNED); -} - -static void init_rq_hrexpiry(struct rq *rq) -{ - hrtimer_init(&rq->hrexpiry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rq->hrexpiry_timer.function = hrexpiry; -} - -static inline int rq_dither(struct rq *rq) -{ - if (!hrexpiry_enabled(rq)) - return HALF_JIFFY_US; - return 0; -} -#else /* CONFIG_HIGH_RES_TIMERS */ -static inline void init_rq_hrexpiry(struct rq *rq) -{ -} - -static inline int rq_dither(struct rq *rq) -{ - return HALF_JIFFY_US; -} -#endif /* CONFIG_HIGH_RES_TIMERS */ - /* * Functions to test for when SCHED_ISO tasks have used their allocated * quota as real time scheduling and convert them back to SCHED_NORMAL. All @@ -3491,16 +3486,15 @@ static inline void check_deadline(struct task_struct *p, struct rq *rq) static inline struct task_struct *earliest_deadline_task(struct rq *rq, int cpu, struct task_struct *idle) { + struct rq *locked = NULL, *chosen = NULL; struct task_struct *edt = idle; - struct rq *locked = NULL; int i, best_entries = 0; u64 best_key = ~0ULL; for (i = 0; i < num_possible_cpus(); i++) { struct rq *other_rq = rq_order(rq, i); int entries = other_rq->sl->entries; - struct task_struct *p; - u64 key; + skiplist_node *next; /* * Check for queued entres lockless first. The local runqueue @@ -3534,35 +3528,47 @@ static inline struct task_struct continue; } } - key = other_rq->node.next[0]->key; - /* Reevaluate key after locking */ - if (unlikely(key >= best_key)) { - /* This will always be when rq != other_rq */ - unlock_rq(other_rq); - continue; - } - p = other_rq->node.next[0]->value; - if (!smt_schedule(p, rq)) { - if (i) - unlock_rq(other_rq); - continue; - } + next = &other_rq->node; + /* + * In interactive mode we check beyond the best entry on other + * runqueues if we can't get the best for smt or affinity + * reasons. + */ + while ((next = next->next[0]) != &other_rq->node) { + struct task_struct *p; + u64 key = next->key; - /* Make sure affinity is ok */ - if (i) { - if (needs_other_cpu(p, cpu)) { - unlock_rq(other_rq); + /* Reevaluate key after locking */ + if (key >= best_key) + break; + + p = next->value; + if (!smt_schedule(p, rq)) { + if (i && !sched_interactive) + break; continue; } - if (locked) - unlock_rq(locked); - locked = other_rq; - } - best_entries = entries; - best_key = key; - edt = p; + /* Make sure affinity is ok */ + if (i) { + if (needs_other_cpu(p, cpu)) { + if (sched_interactive) + continue; + break; + } + /* From this point on p is the best so far */ + if (locked) + unlock_rq(locked); + chosen = locked = other_rq; + } + best_entries = entries; + best_key = key; + edt = p; + break; + } + if (i && other_rq != chosen) + unlock_rq(other_rq); } if (likely(edt != idle)) @@ -3640,12 +3646,10 @@ static inline void schedule_debug(struct task_struct *prev) */ static inline void set_rq_task(struct rq *rq, struct task_struct *p) { -#ifdef CONFIG_HIGH_RES_TIMERS if (p == rq->idle || p->policy == SCHED_FIFO) hrexpiry_clear(rq); else hrexpiry_start(rq, US_TO_NS(p->time_slice)); -#endif /* CONFIG_HIGH_RES_TIMERS */ if (rq->clock - rq->last_tick > HALF_JIFFY_NS) rq->dither = 0; else diff --git a/lib/Kconfig b/lib/Kconfig index d79909dc0..c585e4c40 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -550,4 +550,7 @@ config STACKDEPOT bool select STACKTRACE +config WBT + bool + endmenu diff --git a/lib/Makefile b/lib/Makefile index b63a82375..5bd016bd3 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -177,6 +177,7 @@ obj-$(CONFIG_SG_SPLIT) += sg_split.o obj-$(CONFIG_SG_POOL) += sg_pool.o obj-$(CONFIG_STMP_DEVICE) += stmp_device.o obj-$(CONFIG_IRQ_POLL) += irq_poll.o +obj-$(CONFIG_WBT) += wbt.o obj-$(CONFIG_STACKDEPOT) += stackdepot.o KASAN_SANITIZE_stackdepot.o := n diff --git a/lib/genalloc.c b/lib/genalloc.c index 0a1139644..144fe6b1a 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -292,7 +292,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size, struct gen_pool_chunk *chunk; unsigned long addr = 0; int order = pool->min_alloc_order; - int nbits, start_bit = 0, end_bit, remain; + int nbits, start_bit, end_bit, remain; #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG BUG_ON(in_nmi()); @@ -307,6 +307,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size, if (size > atomic_read(&chunk->avail)) continue; + start_bit = 0; end_bit = chunk_size(chunk) >> order; retry: start_bit = algo(chunk->bits, end_bit, start_bit, diff --git a/lib/wbt.c b/lib/wbt.c new file mode 100644 index 000000000..257c7b099 --- /dev/null +++ b/lib/wbt.c @@ -0,0 +1,703 @@ +/* + * buffered writeback throttling. loosely based on CoDel. We can't drop + * packets for IO scheduling, so the logic is something like this: + * + * - Monitor latencies in a defined window of time. + * - If the minimum latency in the above window exceeds some target, increment + * scaling step and scale down queue depth by a factor of 2x. The monitoring + * window is then shrunk to 100 / sqrt(scaling step + 1). + * - For any window where we don't have solid data on what the latencies + * look like, retain status quo. + * - If latencies look good, decrement scaling step. + * - If we're only doing writes, allow the scaling step to go negative. This + * will temporarily boost write performance, snapping back to a stable + * scaling step of 0 if reads show up or the heavy writers finish. Unlike + * positive scaling steps where we shrink the monitoring window, a negative + * scaling step retains the default step==0 window size. + * + * Copyright (C) 2016 Jens Axboe + * + */ +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +enum { + /* + * Default setting, we'll scale up (to 75% of QD max) or down (min 1) + * from here depending on device stats + */ + RWB_DEF_DEPTH = 16, + + /* + * 100msec window + */ + RWB_WINDOW_NSEC = 100 * 1000 * 1000ULL, + + /* + * Disregard stats, if we don't meet this minimum + */ + RWB_MIN_WRITE_SAMPLES = 3, + + /* + * If we have this number of consecutive windows with not enough + * information to scale up or down, scale up. + */ + RWB_UNKNOWN_BUMP = 5, +}; + +static inline bool rwb_enabled(struct rq_wb *rwb) +{ + return rwb && rwb->wb_normal != 0; +} + +/* + * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, + * false if 'v' + 1 would be bigger than 'below'. + */ +static bool atomic_inc_below(atomic_t *v, int below) +{ + int cur = atomic_read(v); + + for (;;) { + int old; + + if (cur >= below) + return false; + old = atomic_cmpxchg(v, cur, cur + 1); + if (old == cur) + break; + cur = old; + } + + return true; +} + +static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) +{ + if (rwb_enabled(rwb)) { + const unsigned long cur = jiffies; + + if (cur != *var) + *var = cur; + } +} + +/* + * If a task was rate throttled in balance_dirty_pages() within the last + * second or so, use that to indicate a higher cleaning rate. + */ +static bool wb_recent_wait(struct rq_wb *rwb) +{ + struct bdi_writeback *wb = &rwb->bdi->wb; + + return time_before(jiffies, wb->dirty_sleep + HZ); +} + +static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd) +{ + return &rwb->rq_wait[is_kswapd]; +} + +static void rwb_wake_all(struct rq_wb *rwb) +{ + int i; + + for (i = 0; i < WBT_NUM_RWQ; i++) { + struct rq_wait *rqw = &rwb->rq_wait[i]; + + if (waitqueue_active(&rqw->wait)) + wake_up_all(&rqw->wait); + } +} + +void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) +{ + struct rq_wait *rqw; + int inflight, limit; + + if (!(wb_acct & WBT_TRACKED)) + return; + + rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD); + inflight = atomic_dec_return(&rqw->inflight); + + /* + * wbt got disabled with IO in flight. Wake up any potential + * waiters, we don't have to do more than that. + */ + if (unlikely(!rwb_enabled(rwb))) { + rwb_wake_all(rwb); + return; + } + + /* + * If the device does write back caching, drop further down + * before we wake people up. + */ + if (rwb->wc && !wb_recent_wait(rwb)) + limit = 0; + else + limit = rwb->wb_normal; + + /* + * Don't wake anyone up if we are above the normal limit. + */ + if (inflight && inflight >= limit) + return; + + if (waitqueue_active(&rqw->wait)) { + int diff = limit - inflight; + + if (!inflight || diff >= rwb->wb_background / 2) + wake_up(&rqw->wait); + } +} + +/* + * Called on completion of a request. Note that it's also called when + * a request is merged, when the request gets freed. + */ +void wbt_done(struct rq_wb *rwb, struct wb_issue_stat *stat) +{ + if (!rwb) + return; + + if (!wbt_is_tracked(stat)) { + if (rwb->sync_cookie == stat) { + rwb->sync_issue = 0; + rwb->sync_cookie = NULL; + } + + if (wbt_is_read(stat)) + wb_timestamp(rwb, &rwb->last_comp); + wbt_clear_state(stat); + } else { + WARN_ON_ONCE(stat == rwb->sync_cookie); + __wbt_done(rwb, wbt_stat_to_mask(stat)); + wbt_clear_state(stat); + } +} + +/* + * Return true, if we can't increase the depth further by scaling + */ +static bool calc_wb_limits(struct rq_wb *rwb) +{ + unsigned int depth; + bool ret = false; + + if (!rwb->min_lat_nsec) { + rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0; + return false; + } + + /* + * For QD=1 devices, this is a special case. It's important for those + * to have one request ready when one completes, so force a depth of + * 2 for those devices. On the backend, it'll be a depth of 1 anyway, + * since the device can't have more than that in flight. If we're + * scaling down, then keep a setting of 1/1/1. + */ + if (rwb->queue_depth == 1) { + if (rwb->scale_step > 0) + rwb->wb_max = rwb->wb_normal = 1; + else { + rwb->wb_max = rwb->wb_normal = 2; + ret = true; + } + rwb->wb_background = 1; + } else { + /* + * scale_step == 0 is our default state. If we have suffered + * latency spikes, step will be > 0, and we shrink the + * allowed write depths. If step is < 0, we're only doing + * writes, and we allow a temporarily higher depth to + * increase performance. + */ + depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth); + if (rwb->scale_step > 0) + depth = 1 + ((depth - 1) >> min(31, rwb->scale_step)); + else if (rwb->scale_step < 0) { + unsigned int maxd = 3 * rwb->queue_depth / 4; + + depth = 1 + ((depth - 1) << -rwb->scale_step); + if (depth > maxd) { + depth = maxd; + ret = true; + } + } + + /* + * Set our max/normal/bg queue depths based on how far + * we have scaled down (->scale_step). + */ + rwb->wb_max = depth; + rwb->wb_normal = (rwb->wb_max + 1) / 2; + rwb->wb_background = (rwb->wb_max + 3) / 4; + } + + return ret; +} + +static bool inline stat_sample_valid(struct blk_rq_stat *stat) +{ + /* + * We need at least one read sample, and a minimum of + * RWB_MIN_WRITE_SAMPLES. We require some write samples to know + * that it's writes impacting us, and not just some sole read on + * a device that is in a lower power state. + */ + return stat[0].nr_samples >= 1 && + stat[1].nr_samples >= RWB_MIN_WRITE_SAMPLES; +} + +static u64 rwb_sync_issue_lat(struct rq_wb *rwb) +{ + u64 now, issue = ACCESS_ONCE(rwb->sync_issue); + + if (!issue || !rwb->sync_cookie) + return 0; + + now = ktime_to_ns(ktime_get()); + return now - issue; +} + +enum { + LAT_OK = 1, + LAT_UNKNOWN, + LAT_UNKNOWN_WRITES, + LAT_EXCEEDED, +}; + +static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) +{ + u64 thislat; + + /* + * If our stored sync issue exceeds the window size, or it + * exceeds our min target AND we haven't logged any entries, + * flag the latency as exceeded. wbt works off completion latencies, + * but for a flooded device, a single sync IO can take a long time + * to complete after being issued. If this time exceeds our + * monitoring window AND we didn't see any other completions in that + * window, then count that sync IO as a violation of the latency. + */ + thislat = rwb_sync_issue_lat(rwb); + if (thislat > rwb->cur_win_nsec || + (thislat > rwb->min_lat_nsec && !stat[0].nr_samples)) { + trace_wbt_lat(rwb->bdi, thislat); + return LAT_EXCEEDED; + } + + /* + * No read/write mix, if stat isn't valid + */ + if (!stat_sample_valid(stat)) { + /* + * If we had writes in this stat window and the window is + * current, we're only doing writes. If a task recently + * waited or still has writes in flights, consider us doing + * just writes as well. + */ + if ((stat[1].nr_samples && rwb->stat_ops->is_current(stat)) || + wb_recent_wait(rwb) || wbt_inflight(rwb)) + return LAT_UNKNOWN_WRITES; + return LAT_UNKNOWN; + } + + /* + * If the 'min' latency exceeds our target, step down. + */ + if (stat[0].min > rwb->min_lat_nsec) { + trace_wbt_lat(rwb->bdi, stat[0].min); + trace_wbt_stat(rwb->bdi, stat); + return LAT_EXCEEDED; + } + + if (rwb->scale_step) + trace_wbt_stat(rwb->bdi, stat); + + return LAT_OK; +} + +static int latency_exceeded(struct rq_wb *rwb) +{ + struct blk_rq_stat stat[2]; + + rwb->stat_ops->get(rwb->ops_data, stat); + return __latency_exceeded(rwb, stat); +} + +static void rwb_trace_step(struct rq_wb *rwb, const char *msg) +{ + trace_wbt_step(rwb->bdi, msg, rwb->scale_step, rwb->cur_win_nsec, + rwb->wb_background, rwb->wb_normal, rwb->wb_max); +} + +static void scale_up(struct rq_wb *rwb) +{ + /* + * Hit max in previous round, stop here + */ + if (rwb->scaled_max) + return; + + rwb->scale_step--; + rwb->unknown_cnt = 0; + rwb->stat_ops->clear(rwb->ops_data); + + rwb->scaled_max = calc_wb_limits(rwb); + + rwb_wake_all(rwb); + + rwb_trace_step(rwb, "step up"); +} + +/* + * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we + * had a latency violation. + */ +static void scale_down(struct rq_wb *rwb, bool hard_throttle) +{ + /* + * Stop scaling down when we've hit the limit. This also prevents + * ->scale_step from going to crazy values, if the device can't + * keep up. + */ + if (rwb->wb_max == 1) + return; + + if (rwb->scale_step < 0 && hard_throttle) + rwb->scale_step = 0; + else + rwb->scale_step++; + + rwb->scaled_max = false; + rwb->unknown_cnt = 0; + rwb->stat_ops->clear(rwb->ops_data); + calc_wb_limits(rwb); + rwb_trace_step(rwb, "step down"); +} + +static void rwb_arm_timer(struct rq_wb *rwb) +{ + unsigned long expires; + + if (rwb->scale_step > 0) { + /* + * We should speed this up, using some variant of a fast + * integer inverse square root calculation. Since we only do + * this for every window expiration, it's not a huge deal, + * though. + */ + rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4, + int_sqrt((rwb->scale_step + 1) << 8)); + } else { + /* + * For step < 0, we don't want to increase/decrease the + * window size. + */ + rwb->cur_win_nsec = rwb->win_nsec; + } + + expires = jiffies + nsecs_to_jiffies(rwb->cur_win_nsec); + mod_timer(&rwb->window_timer, expires); +} + +static void wb_timer_fn(unsigned long data) +{ + struct rq_wb *rwb = (struct rq_wb *) data; + unsigned int inflight = wbt_inflight(rwb); + int status; + + status = latency_exceeded(rwb); + + trace_wbt_timer(rwb->bdi, status, rwb->scale_step, inflight); + + /* + * If we exceeded the latency target, step down. If we did not, + * step one level up. If we don't know enough to say either exceeded + * or ok, then don't do anything. + */ + switch (status) { + case LAT_EXCEEDED: + scale_down(rwb, true); + break; + case LAT_OK: + scale_up(rwb); + break; + case LAT_UNKNOWN_WRITES: + scale_up(rwb); + break; + case LAT_UNKNOWN: + if (++rwb->unknown_cnt < RWB_UNKNOWN_BUMP) + break; + /* + * We get here for two reasons: + * + * 1) We previously scaled reduced depth, and we currently + * don't have a valid read/write sample. For that case, + * slowly return to center state (step == 0). + * 2) We started a the center step, but don't have a valid + * read/write sample, but we do have writes going on. + * Allow step to go negative, to increase write perf. + */ + if (rwb->scale_step > 0) + scale_up(rwb); + else if (rwb->scale_step < 0) + scale_down(rwb, false); + break; + default: + break; + } + + /* + * Re-arm timer, if we have IO in flight + */ + if (rwb->scale_step || inflight) + rwb_arm_timer(rwb); +} + +void wbt_update_limits(struct rq_wb *rwb) +{ + rwb->scale_step = 0; + rwb->scaled_max = false; + calc_wb_limits(rwb); + + rwb_wake_all(rwb); +} + +static bool close_io(struct rq_wb *rwb) +{ + const unsigned long now = jiffies; + + return time_before(now, rwb->last_issue + HZ / 10) || + time_before(now, rwb->last_comp + HZ / 10); +} + +#define REQ_HIPRIO (REQ_SYNC | REQ_META | REQ_PRIO) + +static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) +{ + unsigned int limit; + + /* + * At this point we know it's a buffered write. If this is + * kswapd trying to free memory, or REQ_SYNC is set, set, then + * it's WB_SYNC_ALL writeback, and we'll use the max limit for + * that. If the write is marked as a background write, then use + * the idle limit, or go to normal if we haven't had competing + * IO for a bit. + */ + if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd()) + limit = rwb->wb_max; + else if ((rw & REQ_BG) || close_io(rwb)) { + /* + * If less than 100ms since we completed unrelated IO, + * limit us to half the depth for background writeback. + */ + limit = rwb->wb_background; + } else + limit = rwb->wb_normal; + + return limit; +} + +static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw, + unsigned long rw) +{ + /* + * inc it here even if disabled, since we'll dec it at completion. + * this only happens if the task was sleeping in __wbt_wait(), + * and someone turned it off at the same time. + */ + if (!rwb_enabled(rwb)) { + atomic_inc(&rqw->inflight); + return true; + } + + return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw)); +} + +/* + * Block if we will exceed our limit, or if we are currently waiting for + * the timer to kick off queuing again. + */ +static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock) +{ + struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd()); + DEFINE_WAIT(wait); + + if (may_queue(rwb, rqw, rw)) + return; + + do { + prepare_to_wait_exclusive(&rqw->wait, &wait, + TASK_UNINTERRUPTIBLE); + + if (may_queue(rwb, rqw, rw)) + break; + + if (lock) + spin_unlock_irq(lock); + + io_schedule(); + + if (lock) + spin_lock_irq(lock); + } while (1); + + finish_wait(&rqw->wait, &wait); +} + +static inline bool wbt_should_throttle(struct rq_wb *rwb, unsigned int rw) +{ + const int op = rw >> BIO_OP_SHIFT; + + /* + * If not a WRITE (or a discard), do nothing + */ + if (!(op == REQ_OP_WRITE || op == REQ_OP_DISCARD)) + return false; + + /* + * Don't throttle WRITE_ODIRECT + */ + if ((rw & (REQ_SYNC | REQ_NOIDLE)) == REQ_SYNC) + return false; + + return true; +} + +/* + * Returns true if the IO request should be accounted, false if not. + * May sleep, if we have exceeded the writeback limits. Caller can pass + * in an irq held spinlock, if it holds one when calling this function. + * If we do sleep, we'll release and re-grab it. + */ +unsigned int wbt_wait(struct rq_wb *rwb, unsigned int rw, spinlock_t *lock) +{ + unsigned int ret = 0; + + if (!rwb_enabled(rwb)) + return 0; + + if ((rw >> BIO_OP_SHIFT) == REQ_OP_READ) + ret = WBT_READ; + + if (!wbt_should_throttle(rwb, rw)) { + if (ret & WBT_READ) + wb_timestamp(rwb, &rwb->last_issue); + return ret; + } + + __wbt_wait(rwb, rw, lock); + + if (!timer_pending(&rwb->window_timer)) + rwb_arm_timer(rwb); + + if (current_is_kswapd()) + ret |= WBT_KSWAPD; + + return ret | WBT_TRACKED; +} + +void wbt_issue(struct rq_wb *rwb, struct wb_issue_stat *stat) +{ + if (!rwb_enabled(rwb)) + return; + + wbt_issue_stat_set_time(stat); + + /* + * Track sync issue, in case it takes a long time to complete. Allows + * us to react quicker, if a sync IO takes a long time to complete. + * Note that this is just a hint. 'stat' can go away when the + * request completes, so it's important we never dereference it. We + * only use the address to compare with, which is why we store the + * sync_issue time locally. + */ + if (wbt_is_read(stat) && !rwb->sync_issue) { + rwb->sync_cookie = stat; + rwb->sync_issue = wbt_issue_stat_get_time(stat); + } +} + +void wbt_requeue(struct rq_wb *rwb, struct wb_issue_stat *stat) +{ + if (!rwb_enabled(rwb)) + return; + if (stat == rwb->sync_cookie) { + rwb->sync_issue = 0; + rwb->sync_cookie = NULL; + } +} + +void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth) +{ + if (rwb) { + rwb->queue_depth = depth; + wbt_update_limits(rwb); + } +} + +void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on) +{ + if (rwb) + rwb->wc = write_cache_on; +} + +void wbt_disable(struct rq_wb *rwb) +{ + if (rwb) { + del_timer_sync(&rwb->window_timer); + rwb->win_nsec = rwb->min_lat_nsec = 0; + wbt_update_limits(rwb); + } +} +EXPORT_SYMBOL_GPL(wbt_disable); + +struct rq_wb *wbt_init(struct backing_dev_info *bdi, struct wb_stat_ops *ops, + void *ops_data) +{ + struct rq_wb *rwb; + int i; + + if (!ops->get || !ops->is_current || !ops->clear) + return ERR_PTR(-EINVAL); + + rwb = kzalloc(sizeof(*rwb), GFP_KERNEL); + if (!rwb) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < WBT_NUM_RWQ; i++) { + atomic_set(&rwb->rq_wait[i].inflight, 0); + init_waitqueue_head(&rwb->rq_wait[i].wait); + } + + setup_timer(&rwb->window_timer, wb_timer_fn, (unsigned long) rwb); + rwb->wc = 1; + rwb->queue_depth = RWB_DEF_DEPTH; + rwb->last_comp = rwb->last_issue = jiffies; + rwb->bdi = bdi; + rwb->win_nsec = RWB_WINDOW_NSEC; + rwb->stat_ops = ops; + rwb->ops_data = ops_data; + wbt_update_limits(rwb); + return rwb; +} + +void wbt_exit(struct rq_wb *rwb) +{ + if (rwb) { + del_timer_sync(&rwb->window_timer); + kfree(rwb); + } +} diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8fde443f3..3bfed5ab2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -310,6 +310,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); + wb->dirty_sleep = jiffies; wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); if (!wb->congested) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 770d83eb3..0ddce6a1c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1826,11 +1826,17 @@ static void return_unused_surplus_pages(struct hstate *h, * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. + * + * vma_add_reservation is used in error paths where a reservation must + * be restored when a newly allocated huge page must be freed. It is + * to be called after calling vma_needs_reservation to determine if a + * reservation exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, + VMA_ADD_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -1856,6 +1862,14 @@ static long __vma_reservation_common(struct hstate *h, region_abort(resv, idx, idx + 1); ret = 0; break; + case VMA_ADD_RESV: + if (vma->vm_flags & VM_MAYSHARE) + ret = region_add(resv, idx, idx + 1); + else { + region_abort(resv, idx, idx + 1); + ret = region_del(resv, idx, idx + 1); + } + break; default: BUG(); } @@ -1903,6 +1917,56 @@ static void vma_end_reservation(struct hstate *h, (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } +static long vma_add_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); +} + +/* + * This routine is called to restore a reservation on error paths. In the + * specific error paths, a huge page was allocated (via alloc_huge_page) + * and is about to be freed. If a reservation for the page existed, + * alloc_huge_page would have consumed the reservation and set PagePrivate + * in the newly allocated page. When the page is freed via free_huge_page, + * the global reservation count will be incremented if PagePrivate is set. + * However, free_huge_page can not adjust the reserve map. Adjust the + * reserve map here to be consistent with global reserve count adjustments + * to be made by free_huge_page. + */ +static void restore_reserve_on_error(struct hstate *h, + struct vm_area_struct *vma, unsigned long address, + struct page *page) +{ + if (unlikely(PagePrivate(page))) { + long rc = vma_needs_reservation(h, vma, address); + + if (unlikely(rc < 0)) { + /* + * Rare out of memory condition in reserve map + * manipulation. Clear PagePrivate so that + * global reserve count will not be incremented + * by free_huge_page. This will make it appear + * as though the reservation for this page was + * consumed. This may prevent the task from + * faulting in the page at a later time. This + * is better than inconsistent global huge page + * accounting of reserve counts. + */ + ClearPagePrivate(page); + } else if (rc) { + rc = vma_add_reservation(h, vma, address); + if (unlikely(rc < 0)) + /* + * See above comment about rare out of + * memory condition. + */ + ClearPagePrivate(page); + } else + vma_end_reservation(h, vma, address); + } +} + struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { @@ -3498,6 +3562,7 @@ retry_avoidcopy: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out_release_all: + restore_reserve_on_error(h, vma, address, new_page); put_page(new_page); out_release_old: put_page(old_page); @@ -3680,6 +3745,7 @@ backout: spin_unlock(ptl); backout_unlocked: unlock_page(page); + restore_reserve_on_error(h, vma, address, page); put_page(page); goto out; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index de88f3351..19e796d36 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1112,10 +1112,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { - lock_page(hpage); - if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { - unlock_page(hpage); - if (!PageAnon(hpage)) + lock_page(p); + if (!PageAnon(p) || unlikely(split_huge_page(p))) { + unlock_page(p); + if (!PageAnon(p)) pr_err("Memory failure: %#lx: non anonymous thp\n", pfn); else @@ -1126,9 +1126,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) put_hwpoison_page(p); return -EBUSY; } - unlock_page(hpage); - get_hwpoison_page(p); - put_hwpoison_page(hpage); + unlock_page(p); VM_BUG_ON_PAGE(!page_count(p), p); hpage = compound_head(p); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 1aeb51d24..56be15224 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1786,6 +1786,7 @@ pause: pause, start_time); __set_current_state(TASK_KILLABLE); + wb->dirty_sleep = now; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; diff --git a/mm/shmem.c b/mm/shmem.c index 971fc83e6..38aa5e0a9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1483,6 +1483,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, copy_highpage(newpage, oldpage); flush_dcache_page(newpage); + __SetPageLocked(newpage); + __SetPageSwapBacked(newpage); SetPageUptodate(newpage); set_page_private(newpage, swap_index); SetPageSwapCache(newpage); diff --git a/mm/slab_common.c b/mm/slab_common.c index 71f0b28a1..329b03843 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -533,8 +533,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, s = create_cache(cache_name, root_cache->object_size, root_cache->size, root_cache->align, - root_cache->flags, root_cache->ctor, - memcg, root_cache); + root_cache->flags & CACHE_CREATE_MASK, + root_cache->ctor, memcg, root_cache); /* * If we could not create a memcg cache, do not complain, because * that's not critical at all as we can always proceed with the root diff --git a/mm/swapfile.c b/mm/swapfile.c index 2657accc6..bf262e494 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2218,6 +2218,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p, swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 3940b5d24..3e9667e46 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -537,7 +537,7 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface, if (bat_priv->algo_ops->neigh.hardif_init) bat_priv->algo_ops->neigh.hardif_init(hardif_neigh); - hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list); + hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list); out: spin_unlock_bh(&hard_iface->neigh_list_lock); diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c index 7d54e944d..dcbe67ff3 100644 --- a/net/ceph/ceph_fs.c +++ b/net/ceph/ceph_fs.c @@ -34,7 +34,8 @@ void ceph_file_layout_from_legacy(struct ceph_file_layout *fl, fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count); fl->object_size = le32_to_cpu(legacy->fl_object_size); fl->pool_id = le32_to_cpu(legacy->fl_pg_pool); - if (fl->pool_id == 0) + if (fl->pool_id == 0 && fl->stripe_unit == 0 && + fl->stripe_count == 0 && fl->object_size == 0) fl->pool_id = -1; } EXPORT_SYMBOL(ceph_file_layout_from_legacy); diff --git a/net/core/dev.c b/net/core/dev.c index 44b3ba462..9ce9d7284 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2484,7 +2484,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out; } - *(__sum16 *)(skb->data + offset) = csum_fold(csum); + *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 52742a028..5550a86f7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -118,7 +118,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_keyid *key_keyid; u8 ip_proto = 0; - bool ret = false; + bool ret; if (!data) { data = skb->data; @@ -481,12 +481,17 @@ ip_proto_again: out_good: ret = true; -out_bad: + key_control->thoff = (u16)nhoff; +out: key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; return ret; + +out_bad: + ret = false; + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); + goto out; } EXPORT_SYMBOL(__skb_flow_dissect); diff --git a/net/core/sock.c b/net/core/sock.c index fd7b41edf..10acaccca 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) EXPORT_SYMBOL(sock_queue_rcv_skb); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, - const int nested, unsigned int trim_cap) + const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; @@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, bh_unlock_sock(sk); out: - sock_put(sk); + if (refcounted) + sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); @@ -1563,6 +1564,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); newsk->sk_err = 0; + newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 345a3aeb8..b567c8725 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; @@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, @@ -868,7 +870,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3828f94b2..715e5d1dc 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; @@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), - ICMP6_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmpv6_notify()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, @@ -738,7 +739,8 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, + refcounted) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -956,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 41e65804d..9fe25bf63 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout) __kfree_skb(skb); } + /* If socket has been already reset kill it. */ + if (sk->sk_state == DCCP_CLOSED) + goto adjudge_to_death; + if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e2ffc2a5c..7ef703102 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2455,22 +2455,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, struct key_vector *l, **tp = &iter->tnode; t_key key; - /* use cache location of next-to-find key */ + /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { - pos -= iter->pos; key = iter->key; } else { - iter->pos = 0; + iter->pos = 1; key = 0; } - while ((l = leaf_walk_rcu(tp, key)) != NULL) { + pos -= iter->pos; + + while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; - - if (--pos <= 0) - break; - l = NULL; /* handle unlikely case of a key wrap */ @@ -2479,7 +2476,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, } if (l) - iter->key = key; /* remember it */ + iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ @@ -2507,7 +2504,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return fib_route_get_idx(iter, *pos); iter->pos = 0; - iter->key = 0; + iter->key = KEY_MAX; return SEQ_START_TOKEN; } @@ -2516,7 +2513,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; - t_key key = iter->key; + t_key key = iter->key + 1; ++*pos; @@ -2525,7 +2522,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) l = leaf_walk_rcu(&iter->tnode, key); if (l) { - iter->key = l->key + 1; + iter->key = l->key; iter->pos++; } else { iter->pos = 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 38abe70e5..48734ee62 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); + fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key_hash(net, fl4, @@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type_dev_table(net, skb_in->dev, + if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 8b4ffd216..9f0a7b966 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index dde37fb34..307daed9a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -223,11 +223,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *segs; int ret = 0; - /* common case: fragmentation of segments is not allowed, - * or seglen is <= mtu + /* common case: seglen is <= mtu */ - if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) || - skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 0f227db0e..afd6b5968 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; - int skb_iif = skb->skb_iif; struct iphdr *iph; int err; @@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && !(df & htons(IP_DF))) { - /* Arrived from an ingress interface, got encapsulated, with - * fragmentation of encapulating frames allowed. - * If skb is gso, the resulting encapsulated network segments - * may exceed dst mtu. - * Allow IP Fragmentation of segments. - */ - IPCB(skb)->flags |= IPSKB_FRAG_SEGS; - } - /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5f006e13d..27089f5eb 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->dev->stats.tx_bytes += skb->len; } - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 62c3ed0b7..2f23ef1a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -753,7 +753,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + if (!n) + n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2fa1a4a6d..ccf8390ec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1146,7 +1146,7 @@ restart: err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto out_err; + goto do_error; sg = !!(sk->sk_route_caps & NETIF_F_SG); @@ -1220,7 +1220,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 10d728b68..ab37c6775 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -56,6 +56,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 delayed_ack_reserved; + u32 loss_cwnd; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->delayed_ack_reserved = 0; + ca->loss_cwnd = 0; ca->ce_state = 0; dctcp_reset(tp, ca); @@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk) static u32 dctcp_ssthresh(struct sock *sk) { - const struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); } @@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } +static u32 dctcp_cwnd_undo(struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + static struct tcp_congestion_ops dctcp __read_mostly = { .init = dctcp_init, .in_ack_event = dctcp_update_alpha, .cwnd_event = dctcp_cwnd_event, .ssthresh = dctcp_ssthresh, .cong_avoid = tcp_reno_cong_avoid, + .undo_cwnd = dctcp_cwnd_undo, .set_state = dctcp_state, .get_info = dctcp_get_info, .flags = TCP_CONG_NEEDS_ECN, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ba2ab6fcf..349ac2a8c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1564,6 +1564,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_prequeue); +int tcp_filter(struct sock *sk, struct sk_buff *skb) +{ + struct tcphdr *th = (struct tcphdr *)skb->data; + unsigned int eaten = skb->len; + int err; + + err = sk_filter_trim_cap(sk, skb, th->doff * 4); + if (!err) { + eaten -= skb->len; + TCP_SKB_CB(skb)->end_seq -= eaten; + } + return err; +} +EXPORT_SYMBOL(tcp_filter); + /* * From tcp_input.c */ @@ -1675,8 +1690,10 @@ process: nf_reset(skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); skb->dev = NULL; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index bd59c343d..7370ad2e6 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -448,7 +448,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; else - iif = l3mdev_master_ifindex(skb->dev); + iif = l3mdev_master_ifindex(skb_dst(skb)->dev); /* * Must not send error if the source does not uniquely diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40a58d7d1..162044030 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1245,7 +1245,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard; /* @@ -1479,8 +1479,10 @@ process: if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + hdr = ipv6_hdr(skb); skb->dev = NULL; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index aa5847a16..1df2c8dac 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -420,7 +420,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; - struct net *net = current->nsproxy->net_ns; + struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; @@ -474,7 +474,6 @@ static int netfilter_log_sysctl_init(struct net *net) 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; - nf_log_sysctl_table[i].data = NULL; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = @@ -484,6 +483,9 @@ static int netfilter_log_sysctl_init(struct net *net) } } + for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) + table[i].extra2 = net; + net->nf.nf_log_dir_header = register_net_sysctl(net, "net/netfilter/nf_log", table); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index baccbf3c1..7b0e059bf 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk, timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); - err = sctp_wait_for_connect(asoc, &timeo); - if ((err == 0 || err == -EINPROGRESS) && assoc_id) + if (assoc_id) *assoc_id = asoc->assoc_id; + err = sctp_wait_for_connect(asoc, &timeo); + /* Note: the asoc may be freed after the return of + * sctp_wait_for_connect. + */ /* Don't free association on exit. */ asoc = NULL; @@ -4278,19 +4281,18 @@ static void sctp_shutdown(struct sock *sk, int how) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; - struct sctp_association *asoc; if (!sctp_style(sk, TCP)) return; - if (how & SEND_SHUTDOWN) { + ep = sctp_sk(sk)->ep; + if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { + struct sctp_association *asoc; + sk->sk_state = SCTP_SS_CLOSING; - ep = sctp_sk(sk)->ep; - if (!list_empty(&ep->asocs)) { - asoc = list_entry(ep->asocs.next, - struct sctp_association, asocs); - sctp_primitive_SHUTDOWN(net, asoc, NULL); - } + asoc = list_entry(ep->asocs.next, + struct sctp_association, asocs); + sctp_primitive_SHUTDOWN(net, asoc, NULL); } } diff --git a/net/socket.c b/net/socket.c index a1bd16106..03bc2c289 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2041,6 +2041,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (err) break; ++datagrams; + if (msg_data_left(&msg_sys)) + break; cond_resched(); } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 892b5e1d9..2761377dc 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -44,18 +44,20 @@ * being done. * * When the underlying transport disconnects, MRs are left in one of - * three states: + * four states: * * INVALID: The MR was not in use before the QP entered ERROR state. - * (Or, the LOCAL_INV WR has not completed or flushed yet). - * - * STALE: The MR was being registered or unregistered when the QP - * entered ERROR state, and the pending WR was flushed. * * VALID: The MR was registered before the QP entered ERROR state. * - * When frwr_op_map encounters STALE and VALID MRs, they are recovered - * with ib_dereg_mr and then are re-initialized. Beause MR recovery + * FLUSHED_FR: The MR was being registered when the QP entered ERROR + * state, and the pending WR was flushed. + * + * FLUSHED_LI: The MR was being invalidated when the QP entered ERROR + * state, and the pending WR was flushed. + * + * When frwr_op_map encounters FLUSHED and VALID MRs, they are recovered + * with ib_dereg_mr and then are re-initialized. Because MR recovery * allocates fresh resources, it is deferred to a workqueue, and the * recovered MRs are placed back on the rb_mws list when recovery is * complete. frwr_op_map allocates another MR for the current RPC while @@ -175,12 +177,15 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) static void frwr_op_recover_mr(struct rpcrdma_mw *mw) { + enum rpcrdma_frmr_state state = mw->frmr.fr_state; struct rpcrdma_xprt *r_xprt = mw->mw_xprt; struct rpcrdma_ia *ia = &r_xprt->rx_ia; int rc; rc = __frwr_reset_mr(ia, mw); - ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); + if (state != FRMR_FLUSHED_LI) + ib_dma_unmap_sg(ia->ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); if (rc) goto out_release; @@ -261,10 +266,8 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) } static void -__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_frmr *frmr, - const char *wr) +__frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr) { - frmr->fr_state = FRMR_IS_STALE; if (wc->status != IB_WC_WR_FLUSH_ERR) pr_err("rpcrdma: %s: %s (%u/0x%x)\n", wr, ib_wc_status_msg(wc->status), @@ -287,7 +290,8 @@ frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) { cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - __frwr_sendcompletion_flush(wc, frmr, "fastreg"); + frmr->fr_state = FRMR_FLUSHED_FR; + __frwr_sendcompletion_flush(wc, "fastreg"); } } @@ -307,7 +311,8 @@ frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) { cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - __frwr_sendcompletion_flush(wc, frmr, "localinv"); + frmr->fr_state = FRMR_FLUSHED_LI; + __frwr_sendcompletion_flush(wc, "localinv"); } } @@ -327,9 +332,11 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wr_cqe and status are reliable at this point */ cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - if (wc->status != IB_WC_SUCCESS) - __frwr_sendcompletion_flush(wc, frmr, "localinv"); - complete_all(&frmr->fr_linv_done); + if (wc->status != IB_WC_SUCCESS) { + frmr->fr_state = FRMR_FLUSHED_LI; + __frwr_sendcompletion_flush(wc, "localinv"); + } + complete(&frmr->fr_linv_done); } /* Post a REG_MR Work Request to register a memory region diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index a2a7519b0..cd0c55814 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -129,7 +129,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, ret = -EIO; goto out_unmap; } - atomic_inc(&rdma->sc_dma_used); + svc_rdma_count_mappings(rdma, ctxt); memset(&send_wr, 0, sizeof(send_wr)); ctxt->cqe.done = svc_rdma_wc_send; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 2c25606f2..ad1df979b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -159,7 +159,7 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, ctxt->sge[pno].addr); if (ret) goto err; - atomic_inc(&xprt->sc_dma_used); + svc_rdma_count_mappings(xprt, ctxt); ctxt->sge[pno].lkey = xprt->sc_pd->local_dma_lkey; ctxt->sge[pno].length = len; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 54d533300..3b95b19fc 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -280,7 +280,7 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, if (ib_dma_mapping_error(xprt->sc_cm_id->device, sge[sge_no].addr)) goto err; - atomic_inc(&xprt->sc_dma_used); + svc_rdma_count_mappings(xprt, ctxt); sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey; ctxt->count++; sge_off = 0; @@ -489,7 +489,7 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[0].length, DMA_TO_DEVICE); if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) goto err; - atomic_inc(&rdma->sc_dma_used); + svc_rdma_count_mappings(rdma, ctxt); ctxt->direction = DMA_TO_DEVICE; @@ -505,7 +505,7 @@ static int send_reply(struct svcxprt_rdma *rdma, if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[sge_no].addr)) goto err; - atomic_inc(&rdma->sc_dma_used); + svc_rdma_count_mappings(rdma, ctxt); ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; ctxt->sge[sge_no].length = sge_bytes; } @@ -523,23 +523,9 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; ctxt->count++; rqstp->rq_respages[page_no] = NULL; - /* - * If there are more pages than SGE, terminate SGE - * list so that svc_rdma_unmap_dma doesn't attempt to - * unmap garbage. - */ - if (page_no+1 >= sge_no) - ctxt->sge[page_no+1].length = 0; } rqstp->rq_next_page = rqstp->rq_respages + 1; - /* The loop above bumps sc_dma_used for each sge. The - * xdr_buf.tail gets a separate sge, but resides in the - * same page as xdr_buf.head. Don't count it twice. - */ - if (sge_no > ctxt->count) - atomic_dec(&rdma->sc_dma_used); - if (sge_no > rdma->sc_max_sge) { pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err; @@ -635,7 +621,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) ret = send_reply(rdma, rqstp, res_page, rdma_resp, vec, inline_bytes); if (ret < 0) - goto err1; + goto err0; svc_rdma_put_req_map(rdma, vec); dprintk("svcrdma: send_reply returns %d\n", ret); @@ -692,7 +678,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, svc_rdma_put_context(ctxt, 1); return; } - atomic_inc(&xprt->sc_dma_used); + svc_rdma_count_mappings(xprt, ctxt); /* Prepare SEND WR */ memset(&err_wr, 0, sizeof(err_wr)); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index dd9440137..924271c9e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -198,6 +198,7 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) out: ctxt->count = 0; + ctxt->mapped_sges = 0; ctxt->frmr = NULL; return ctxt; @@ -221,22 +222,27 @@ out_empty: void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) { struct svcxprt_rdma *xprt = ctxt->xprt; - int i; - for (i = 0; i < ctxt->count && ctxt->sge[i].length; i++) { + struct ib_device *device = xprt->sc_cm_id->device; + u32 lkey = xprt->sc_pd->local_dma_lkey; + unsigned int i, count; + + for (count = 0, i = 0; i < ctxt->mapped_sges; i++) { /* * Unmap the DMA addr in the SGE if the lkey matches * the local_dma_lkey, otherwise, ignore it since it is * an FRMR lkey and will be unmapped later when the * last WR that uses it completes. */ - if (ctxt->sge[i].lkey == xprt->sc_pd->local_dma_lkey) { - atomic_dec(&xprt->sc_dma_used); - ib_dma_unmap_page(xprt->sc_cm_id->device, + if (ctxt->sge[i].lkey == lkey) { + count++; + ib_dma_unmap_page(device, ctxt->sge[i].addr, ctxt->sge[i].length, ctxt->direction); } } + ctxt->mapped_sges = 0; + atomic_sub(count, &xprt->sc_dma_used); } void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) @@ -600,7 +606,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags) DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, pa)) goto err_put_ctxt; - atomic_inc(&xprt->sc_dma_used); + svc_rdma_count_mappings(xprt, ctxt); ctxt->sge[sge_no].addr = pa; ctxt->sge[sge_no].length = PAGE_SIZE; ctxt->sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index a71b0f589..edc03445b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -207,7 +207,8 @@ struct rpcrdma_rep { enum rpcrdma_frmr_state { FRMR_IS_INVALID, /* ready to be used */ FRMR_IS_VALID, /* in use */ - FRMR_IS_STALE, /* failed completion */ + FRMR_FLUSHED_FR, /* flushed FASTREG WR */ + FRMR_FLUSHED_LI, /* flushed LOCALINV WR */ }; struct rpcrdma_frmr { diff --git a/sound/core/info.c b/sound/core/info.c index 895362a69..8ab72e0f5 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -325,10 +325,15 @@ static ssize_t snd_info_text_entry_write(struct file *file, size_t next; int err = 0; + if (!entry->c.text.write) + return -EIO; pos = *offset; if (!valid_pos(pos, count)) return -EIO; next = pos + count; + /* don't handle too large text inputs */ + if (next > 16 * 1024) + return -EIO; mutex_lock(&entry->access); buf = data->wbuffer; if (!buf) { @@ -366,7 +371,9 @@ static int snd_info_seq_show(struct seq_file *seq, void *p) struct snd_info_private_data *data = seq->private; struct snd_info_entry *entry = data->entry; - if (entry->c.text.read) { + if (!entry->c.text.read) { + return -EIO; + } else { data->rbuffer->buffer = (char *)seq; /* XXX hack! */ entry->c.text.read(entry, data->rbuffer); } diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c index e07807d96..3670086b9 100644 --- a/sound/soc/codecs/cs4270.c +++ b/sound/soc/codecs/cs4270.c @@ -148,11 +148,11 @@ SND_SOC_DAPM_OUTPUT("AOUTR"), }; static const struct snd_soc_dapm_route cs4270_dapm_routes[] = { - { "Capture", NULL, "AINA" }, - { "Capture", NULL, "AINB" }, + { "Capture", NULL, "AINL" }, + { "Capture", NULL, "AINR" }, - { "AOUTA", NULL, "Playback" }, - { "AOUTB", NULL, "Playback" }, + { "AOUTL", NULL, "Playback" }, + { "AOUTR", NULL, "Playback" }, }; /** diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 9870963d4..0c0219cbf 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -785,8 +785,7 @@ static void skl_remove(struct pci_dev *pci) release_firmware(skl->tplg); - if (pci_dev_run_wake(pci)) - pm_runtime_get_noresume(&pci->dev); + pm_runtime_get_noresume(&pci->dev); /* codec removal, invoke bus_device_remove */ snd_hdac_ext_bus_device_remove(ebus); diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index 44f170c73..03c18db96 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -738,11 +738,11 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev) card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL); if (!card) - return NULL; + return ERR_PTR(-ENOMEM); card->dai_link = sun4i_codec_create_link(dev, &card->num_links); if (!card->dai_link) - return NULL; + return ERR_PTR(-ENOMEM); card->dev = dev; card->name = "sun4i-codec"; @@ -842,7 +842,8 @@ static int sun4i_codec_probe(struct platform_device *pdev) } card = sun4i_codec_create_card(&pdev->dev); - if (!card) { + if (IS_ERR(card)) { + ret = PTR_ERR(card); dev_err(&pdev->dev, "Failed to create our card\n"); goto err_unregister_codec; } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 7aee954b3..4ad1eac23 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -595,7 +595,8 @@ int hist_browser__run(struct hist_browser *browser, const char *help) u64 nr_entries; hbt->timer(hbt->arg); - if (hist_browser__has_filter(browser)) + if (hist_browser__has_filter(browser) || + symbol_conf.report_hierarchy) hist_browser__update_nr_entries(browser); nr_entries = hist_browser__nr_entries(browser); diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index b4bf76971..1eef0aed6 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -296,7 +296,7 @@ int cmd_freq_set(int argc, char **argv) struct cpufreq_affected_cpus *cpus; if (!bitmask_isbitset(cpus_chosen, cpu) || - cpupower_is_cpu_online(cpu)) + cpupower_is_cpu_online(cpu) != 1) continue; cpus = cpufreq_get_related_cpus(cpu); @@ -316,10 +316,7 @@ int cmd_freq_set(int argc, char **argv) cpu <= bitmask_last(cpus_chosen); cpu++) { if (!bitmask_isbitset(cpus_chosen, cpu) || - cpupower_is_cpu_online(cpu)) - continue; - - if (cpupower_is_cpu_online(cpu) != 1) + cpupower_is_cpu_online(cpu) != 1) continue; printf(_("Setting cpu: %d\n"), cpu); diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c index f3825b676..f046b77cf 100644 --- a/tools/spi/spidev_test.c +++ b/tools/spi/spidev_test.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 3bad3c5ed..d1b080ca8 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -453,17 +453,33 @@ struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) return container_of(dev, struct vgic_io_device, dev); } -static bool check_region(const struct vgic_register_region *region, +static bool check_region(const struct kvm *kvm, + const struct vgic_register_region *region, gpa_t addr, int len) { - if ((region->access_flags & VGIC_ACCESS_8bit) && len == 1) - return true; - if ((region->access_flags & VGIC_ACCESS_32bit) && - len == sizeof(u32) && !(addr & 3)) - return true; - if ((region->access_flags & VGIC_ACCESS_64bit) && - len == sizeof(u64) && !(addr & 7)) - return true; + int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; + + switch (len) { + case sizeof(u8): + flags = VGIC_ACCESS_8bit; + break; + case sizeof(u32): + flags = VGIC_ACCESS_32bit; + break; + case sizeof(u64): + flags = VGIC_ACCESS_64bit; + break; + default: + return false; + } + + if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { + if (!region->bits_per_irq) + return true; + + /* Do we access a non-allocated IRQ? */ + return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; + } return false; } @@ -477,7 +493,7 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, addr - iodev->base_addr); - if (!region || !check_region(region, addr, len)) { + if (!region || !check_region(vcpu->kvm, region, addr, len)) { memset(val, 0, len); return 0; } @@ -510,10 +526,7 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, addr - iodev->base_addr); - if (!region) - return 0; - - if (!check_region(region, addr, len)) + if (!region || !check_region(vcpu->kvm, region, addr, len)) return 0; switch (iodev->iodev_type) { diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 0b3ecf9d1..ba63d91d2 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -50,15 +50,15 @@ extern struct kvm_io_device_ops kvm_io_gic_ops; #define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1) /* - * (addr & mask) gives us the byte offset for the INT ID, so we want to - * divide this with 'bytes per irq' to get the INT ID, which is given - * by '(bits) / 8'. But we do this with fixed-point-arithmetic and - * take advantage of the fact that division by a fraction equals - * multiplication with the inverted fraction, and scale up both the - * numerator and denominator with 8 to support at most 64 bits per IRQ: + * (addr & mask) gives us the _byte_ offset for the INT ID. + * We multiply this by 8 the get the _bit_ offset, then divide this by + * the number of bits to learn the actual INT ID. + * But instead of a division (which requires a "long long div" implementation), + * we shift by the binary logarithm of . + * This assumes that is a power of two. */ #define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \ - 64 / (bits) / 8) + 8 >> ilog2(bits)) /* * Some VGIC registers store per-IRQ information, with a different number -- cgit v1.2.3