diff --git a/.gitignore b/.gitignore index 42fa0d5626a9..f4c0b091dcf4 100644 --- a/.gitignore +++ b/.gitignore @@ -22,7 +22,6 @@ *.lst *.symtypes *.order -modules.builtin *.elf *.bin *.gz @@ -33,6 +32,8 @@ modules.builtin *.lzo *.patch *.gcno +modules.builtin +Module.symvers # # Top-level generic files @@ -44,7 +45,6 @@ modules.builtin /vmlinuz /System.map /Module.markers -/Module.symvers # # Debian directory (make deb-pkg) diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index d922060e455d..416c5d59f52e 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -169,6 +169,14 @@ Description: "unknown", "notpresent", "down", "lowerlayerdown", "testing", "dormant", "up". +What: /sys/class/net//phys_port_id +Date: July 2013 +KernelVersion: 3.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the interface unique physical port identifier within + the NIC, as a string. + What: /sys/class/net//speed Date: October 2009 KernelVersion: 2.6.33 diff --git a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm new file mode 100644 index 000000000000..5cedf72df358 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm @@ -0,0 +1,149 @@ +What: /sys/class/net//cdc_ncm/min_tx_pkt +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + The driver will pad NCM Transfer Blocks (NTBs) longer + than this to tx_max, allowing the device to receive + tx_max sized frames with no terminating short + packet. NTBs shorter than this limit are transmitted + as-is, without any padding, and are terminated with a + short USB packet. + + Padding to tx_max allows the driver to transmit NTBs + back-to-back without any interleaving short USB + packets. This reduces the number of short packet + interrupts in the device, and represents a tradeoff + between USB bus bandwidth and device DMA optimization. + + Set to 0 to pad all frames. Set greater than tx_max to + disable all padding. + +What: /sys/class/net//cdc_ncm/rx_max +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + The maximum NTB size for RX. Cannot exceed the + maximum value supported by the device. Must allow at + least one max sized datagram plus headers. + + The actual limits are device dependent. See + dwNtbInMaxSize. + + Note: Some devices will silently ignore changes to + this value, resulting in oversized NTBs and + corresponding framing errors. + +What: /sys/class/net//cdc_ncm/tx_max +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + The maximum NTB size for TX. Cannot exceed the + maximum value supported by the device. Must allow at + least one max sized datagram plus headers. + + The actual limits are device dependent. See + dwNtbOutMaxSize. + +What: /sys/class/net//cdc_ncm/tx_timer_usecs +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Datagram aggregation timeout in µs. The driver will + wait up to 3 times this timeout for more datagrams to + aggregate before transmitting an NTB frame. + + Valid range: 5 to 4000000 + + Set to 0 to disable aggregation. + +The following read-only attributes all represent fields of the +structure defined in section 6.2.1 "GetNtbParameters" of "Universal +Serial Bus Communications Class Subclass Specifications for Network +Control Model Devices" (CDC NCM), Revision 1.0 (Errata 1), November +24, 2010 from USB Implementers Forum, Inc. The descriptions are +quoted from table 6-3 of CDC NCM: "NTB Parameter Structure". + +What: /sys/class/net//cdc_ncm/bmNtbFormatsSupported +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Bit 0: 16-bit NTB supported (set to 1) + Bit 1: 32-bit NTB supported + Bits 2 – 15: reserved (reset to zero; must be ignored by host) + +What: /sys/class/net//cdc_ncm/dwNtbInMaxSize +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + IN NTB Maximum Size in bytes + +What: /sys/class/net//cdc_ncm/wNdpInDivisor +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Divisor used for IN NTB Datagram payload alignment + +What: /sys/class/net//cdc_ncm/wNdpInPayloadRemainder +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Remainder used to align input datagram payload within + the NTB: (Payload Offset) mod (wNdpInDivisor) = + wNdpInPayloadRemainder + +What: /sys/class/net//cdc_ncm/wNdpInAlignment +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + NDP alignment modulus for NTBs on the IN pipe. Shall + be a power of 2, and shall be at least 4. + +What: /sys/class/net//cdc_ncm/dwNtbOutMaxSize +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + OUT NTB Maximum Size + +What: /sys/class/net//cdc_ncm/wNdpOutDivisor +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + OUT NTB Datagram alignment modulus + +What: /sys/class/net//cdc_ncm/wNdpOutPayloadRemainder +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Remainder used to align output datagram payload + offsets within the NTB: Padding, shall be transmitted + as zero by function, and ignored by host. (Payload + Offset) mod (wNdpOutDivisor) = wNdpOutPayloadRemainder + +What: /sys/class/net//cdc_ncm/wNdpOutAlignment +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + NDP alignment modulus for use in NTBs on the OUT + pipe. Shall be a power of 2, and shall be at least 4. + +What: /sys/class/net//cdc_ncm/wNtbOutMaxDatagrams +Date: May 2014 +KernelVersion: 3.16 +Contact: Bjørn Mork +Description: + Maximum number of datagrams that the host may pack + into a single OUT NTB. Zero means that the device + imposes no limit. diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues new file mode 100644 index 000000000000..5e9aeb91d355 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -0,0 +1,79 @@ +What: /sys/class//queues/rx-/rps_cpus +Date: March 2010 +KernelVersion: 2.6.35 +Contact: netdev@vger.kernel.org +Description: + Mask of the CPU(s) currently enabled to participate into the + Receive Packet Steering packet processing flow for this + network device queue. Possible values depend on the number + of available CPU(s) in the system. + +What: /sys/class//queues/rx-/rps_flow_cnt +Date: April 2010 +KernelVersion: 2.6.35 +Contact: netdev@vger.kernel.org +Description: + Number of Receive Packet Steering flows being currently + processed by this particular network device receive queue. + +What: /sys/class//queues/tx-/tx_timeout +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of transmit timeout events seen by this + network interface transmit queue. + +What: /sys/class//queues/tx-/xps_cpus +Date: November 2010 +KernelVersion: 2.6.38 +Contact: netdev@vger.kernel.org +Description: + Mask of the CPU(s) currently enabled to participate into the + Transmit Packet Steering packet processing flow for this + network device transmit queue. Possible vaules depend on the + number of available CPU(s) in the system. + +What: /sys/class//queues/tx-/byte_queue_limits/hold_time +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the hold time in milliseconds to measure the slack + of this particular network device transmit queue. + Default value is 1000. + +What: /sys/class//queues/tx-/byte_queue_limits/inflight +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of bytes (objects) in flight on this + network device transmit queue. + +What: /sys/class//queues/tx-/byte_queue_limits/limit +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the current limit of bytes allowed to be queued + on this network device transmit queue. This value is clamped + to be within the bounds defined by limit_max and limit_min. + +What: /sys/class//queues/tx-/byte_queue_limits/limit_max +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the absolute maximum limit of bytes allowed to be + queued on this network device transmit queue. See + include/linux/dynamic_queue_limits.h for the default value. + +What: /sys/class//queues/tx-/byte_queue_limits/limit_min +Date: November 2011 +KernelVersion: 3.3 +Contact: netdev@vger.kernel.org +Description: + Indicates the absolute minimum limit of bytes allowed to be + queued on this network device transmit queue. Default value is + 0. diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics new file mode 100644 index 000000000000..397118de7b5e --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -0,0 +1,201 @@ +What: /sys/class//statistics/collisions +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of collisions seen by this network device. + This value might not be relevant with all MAC layers. + +What: /sys/class//statistics/multicast +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of multicast packets received by this + network device. + +What: /sys/class//statistics/rx_bytes +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of bytes received by this network device. + See the network driver for the exact meaning of when this + value is incremented. + +What: /sys/class//statistics/rx_compressed +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of compressed packets received by this + network device. This value might only be relevant for interfaces + that support packet compression (e.g: PPP). + +What: /sys/class//statistics/rx_crc_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets received with a CRC (FCS) error + by this network device. Note that the specific meaning might + depend on the MAC layer used by the interface. + +What: /sys/class//statistics/rx_dropped +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets received by the network device + but dropped, that are not forwarded to the upper layers for + packet processing. See the network driver for the exact + meaning of this value. + +What: /sys/class//statistics/rx_fifo_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of receive FIFO errors seen by this + network device. See the network driver for the exact + meaning of this value. + +What: /sys/class//statistics/rx_frame_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of received frames with error, such as + alignment errors. Note that the specific meaning depends on + on the MAC layer protocol used. See the network driver for + the exact meaning of this value. + +What: /sys/class//statistics/rx_length_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of received error packet with a length + error, oversized or undersized. See the network driver for the + exact meaning of this value. + +What: /sys/class//statistics/rx_missed_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of received packets that have been missed + due to lack of capacity in the receive side. See the network + driver for the exact meaning of this value. + +What: /sys/class//statistics/rx_over_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of received packets that are oversized + compared to what the network device is configured to accept + (e.g: larger than MTU). See the network driver for the exact + meaning of this value. + +What: /sys/class//statistics/rx_packets +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the total number of good packets received by this + network device. + +What: /sys/class//statistics/tx_aborted_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets that have been aborted + during transmission by a network device (e.g: because of + a medium collision). See the network driver for the exact + meaning of this value. + +What: /sys/class//statistics/tx_bytes +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of bytes transmitted by a network + device. See the network driver for the exact meaning of this + value, in particular whether this accounts for all successfully + transmitted packets or all packets that have been queued for + transmission. + +What: /sys/class//statistics/tx_carrier_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets that could not be transmitted + because of carrier errors (e.g: physical link down). See the + network driver for the exact meaning of this value. + +What: /sys/class//statistics/tx_compressed +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of transmitted compressed packets. Note + this might only be relevant for devices that support + compression (e.g: PPP). + +What: /sys/class//statistics/tx_dropped +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets dropped during transmission. + See the driver for the exact reasons as to why the packets were + dropped. + +What: /sys/class//statistics/tx_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets in error during transmission by + a network device. See the driver for the exact reasons as to + why the packets were dropped. + +What: /sys/class//statistics/tx_fifo_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets having caused a transmit + FIFO error. See the driver for the exact reasons as to why the + packets were dropped. + +What: /sys/class//statistics/tx_heartbeat_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets transmitted that have been + reported as heartbeat errors. See the driver for the exact + reasons as to why the packets were dropped. + +What: /sys/class//statistics/tx_packets +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets transmitted by a network + device. See the driver for whether this reports the number of all + attempted or successful transmissions. + +What: /sys/class//statistics/tx_window_errors +Date: April 2005 +KernelVersion: 2.6.12 +Contact: netdev@vger.kernel.org +Description: + Indicates the number of packets not successfully transmitted + due to a window collision. The specific meaning depends on the + MAC layer used. On Ethernet this is usually used to report + late collisions errors. diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index 044b76436e83..d9b9416c989f 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -100,6 +100,7 @@ !Finclude/net/cfg80211.h wdev_priv !Finclude/net/cfg80211.h ieee80211_iface_limit !Finclude/net/cfg80211.h ieee80211_iface_combination +!Finclude/net/cfg80211.h cfg80211_check_combinations Actions and configuration diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl index ba60d93c1855..7df3134ebc0e 100644 --- a/Documentation/DocBook/drm.tmpl +++ b/Documentation/DocBook/drm.tmpl @@ -141,6 +141,12 @@ and then pass it to one of the drm_*_init() functions to register it with the DRM subsystem. + + Newer drivers that no longer require a drm_bus + structure can alternatively use the low-level device initialization and + registration functions such as drm_dev_alloc() and + drm_dev_register() directly. + The drm_driver structure contains static information that describes the driver and features it supports, and @@ -281,6 +287,36 @@ char *date; + + Device Registration + + A number of functions are provided to help with device registration. + The functions deal with PCI, USB and platform devices, respectively. + +!Edrivers/gpu/drm/drm_pci.c +!Edrivers/gpu/drm/drm_usb.c +!Edrivers/gpu/drm/drm_platform.c + + New drivers that no longer rely on the services provided by the + drm_bus structure can call the low-level + device registration functions directly. The + drm_dev_alloc() function can be used to allocate + and initialize a new drm_device structure. + Drivers will typically want to perform some additional setup on this + structure, such as allocating driver-specific data and storing a + pointer to it in the DRM device's dev_private + field. Drivers should also set the device's unique name using the + drm_dev_set_unique() function. After it has been + set up a device can be registered with the DRM subsystem by calling + drm_dev_register(). This will cause the device to + be exposed to userspace and will call the driver's + .load() implementation. When a device is + removed, the DRM device can safely be unregistered and freed by calling + drm_dev_unregister() followed by a call to + drm_dev_unref(). + +!Edrivers/gpu/drm/drm_stub.c + Driver Load @@ -341,14 +377,6 @@ char *date; Managed IRQ Registration - - Both the drm_irq_install and - drm_irq_uninstall functions get the device IRQ by - calling drm_dev_to_irq. This inline function will - call a bus-specific operation to retrieve the IRQ number. For platform - devices, platform_get_irq(..., 0) is used to - retrieve the IRQ number. - drm_irq_install starts by calling the irq_preinstall driver operation. The operation @@ -356,7 +384,7 @@ char *date; clearing all pending interrupt flags or disabling the interrupt. - The IRQ will then be requested by a call to + The passed-in IRQ will then be requested by a call to request_irq. If the DRIVER_IRQ_SHARED driver feature flag is set, a shared (IRQF_SHARED) IRQ handler will be requested. @@ -1799,6 +1827,12 @@ void intel_crt_init(struct drm_device *dev) KMS API Functions !Edrivers/gpu/drm/drm_crtc.c + + KMS Locking +!Pdrivers/gpu/drm/drm_modeset_lock.c kms locking +!Iinclude/drm/drm_modeset_lock.h +!Edrivers/gpu/drm/drm_modeset_lock.c + @@ -1903,8 +1937,8 @@ void intel_crt_init(struct drm_device *dev) The function filters out modes larger than max_width and max_height - if specified. It then calls the connector - mode_valid helper operation for each mode in + if specified. It then calls the optional connector + mode_valid helper operation for each mode in the probed list to check whether the mode is valid for the connector. @@ -2265,7 +2299,7 @@ void intel_crt_init(struct drm_device *dev) Verify whether a mode is valid for the connector. Return MODE_OK for supported modes and one of the enum drm_mode_status values (MODE_*) - for unsupported modes. This operation is mandatory. + for unsupported modes. This operation is optional. As the mode rejection reason is currently not used beside for @@ -2450,6 +2484,863 @@ void intel_crt_init(struct drm_device *dev) pointer to the target object, a pointer to the previously created property and an initial instance value. + + Existing KMS Properties + + The following table gives description of drm properties exposed by various + modules/drivers. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Owner Module/DriversGroupProperty NameTypeProperty ValuesObject attachedDescription/Restrictions
DRMGeneric“EDID”BLOB | IMMUTABLE0ConnectorContains id of edid blob ptr object.
“DPMS”ENUM{ “On”, “Standby”, “Suspend”, “Off” }ConnectorContains DPMS operation mode value.
Plane“type”ENUM | IMMUTABLE{ "Overlay", "Primary", "Cursor" }PlanePlane type
DVI-I“subconnector”ENUM{ “Unknown”, “DVI-D”, “DVI-A” }ConnectorTBD
“select subconnector”ENUM{ “Automatic”, “DVI-D”, “DVI-A” }ConnectorTBD
TV“subconnector”ENUM{ "Unknown", "Composite", "SVIDEO", "Component", "SCART" }ConnectorTBD
“select subconnector”ENUM{ "Automatic", "Composite", "SVIDEO", "Component", "SCART" }ConnectorTBD
“mode”ENUM{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.ConnectorTBD
“left margin”RANGEMin=0, Max=100ConnectorTBD
“right margin”RANGEMin=0, Max=100ConnectorTBD
“top margin”RANGEMin=0, Max=100ConnectorTBD
“bottom margin”RANGEMin=0, Max=100ConnectorTBD
“brightness”RANGEMin=0, Max=100ConnectorTBD
“contrast”RANGEMin=0, Max=100ConnectorTBD
“flicker reduction”RANGEMin=0, Max=100ConnectorTBD
“overscan”RANGEMin=0, Max=100ConnectorTBD
“saturation”RANGEMin=0, Max=100ConnectorTBD
“hue”RANGEMin=0, Max=100ConnectorTBD
Optional“scaling mode”ENUM{ "None", "Full", "Center", "Full aspect" }ConnectorTBD
“dirty”ENUM | IMMUTABLE{ "Off", "On", "Annotate" }ConnectorTBD
i915Generic"Broadcast RGB"ENUM{ "Automatic", "Full", "Limited 16:235" }ConnectorTBD
“audio”ENUM{ "force-dvi", "off", "auto", "on" }ConnectorTBD
Standard name as in DRMStandard type as in DRMStandard value as in DRMStandard Object as in DRMTBD
SDVO-TV“mode”ENUM{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.ConnectorTBD
"left_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"right_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"top_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"bottom_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
“hpos”RANGEMin=0, Max= SDVO dependentConnectorTBD
“vpos”RANGEMin=0, Max= SDVO dependentConnectorTBD
“contrast”RANGEMin=0, Max= SDVO dependentConnectorTBD
“saturation”RANGEMin=0, Max= SDVO dependentConnectorTBD
“hue”RANGEMin=0, Max= SDVO dependentConnectorTBD
“sharpness”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter_adaptive”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter_2d”RANGEMin=0, Max= SDVO dependentConnectorTBD
“tv_chroma_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“tv_luma_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“dot_crawl”RANGEMin=0, Max=1ConnectorTBD
SDVO-TV/LVDS“brightness”RANGEMin=0, Max= SDVO dependentConnectorTBD
CDV gma-500Generic"Broadcast RGB"ENUM{ “Full”, “Limited 16:235” }ConnectorTBD
"Broadcast RGB"ENUM{ “off”, “auto”, “on” }ConnectorTBD
Standard name as in DRMStandard type as in DRMStandard value as in DRMStandard Object as in DRMTBD
PoulsboGeneric“backlight”RANGEMin=0, Max=100ConnectorTBD
Standard name as in DRMStandard type as in DRMStandard value as in DRMStandard Object as in DRMTBD
SDVO-TV“mode”ENUM{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.ConnectorTBD
"left_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"right_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"top_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
"bottom_margin"RANGEMin=0, Max= SDVO dependentConnectorTBD
“hpos”RANGEMin=0, Max= SDVO dependentConnectorTBD
“vpos”RANGEMin=0, Max= SDVO dependentConnectorTBD
“contrast”RANGEMin=0, Max= SDVO dependentConnectorTBD
“saturation”RANGEMin=0, Max= SDVO dependentConnectorTBD
“hue”RANGEMin=0, Max= SDVO dependentConnectorTBD
“sharpness”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter_adaptive”RANGEMin=0, Max= SDVO dependentConnectorTBD
“flicker_filter_2d”RANGEMin=0, Max= SDVO dependentConnectorTBD
“tv_chroma_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“tv_luma_filter”RANGEMin=0, Max= SDVO dependentConnectorTBD
“dot_crawl”RANGEMin=0, Max=1ConnectorTBD
SDVO-TV/LVDS“brightness”RANGEMin=0, Max= SDVO dependentConnectorTBD
armadaCRTC"CSC_YUV"ENUM{ "Auto" , "CCIR601", "CCIR709" }CRTCTBD
"CSC_RGB"ENUM{ "Auto", "Computer system", "Studio" }CRTCTBD
Overlay"colorkey"RANGEMin=0, Max=0xffffffPlaneTBD
"colorkey_min"RANGEMin=0, Max=0xffffffPlaneTBD
"colorkey_max"RANGEMin=0, Max=0xffffffPlaneTBD
"colorkey_val"RANGEMin=0, Max=0xffffffPlaneTBD
"colorkey_alpha"RANGEMin=0, Max=0xffffffPlaneTBD
"colorkey_mode"ENUM{ "disabled", "Y component", "U component" + , "V component", "RGB", “R component", "G component", "B component" }PlaneTBD
"brightness"RANGEMin=0, Max=256 + 255PlaneTBD
"contrast"RANGEMin=0, Max=0x7fffPlaneTBD
"saturation"RANGEMin=0, Max=0x7fffPlaneTBD
exynosCRTC“mode”ENUM{ "normal", "blank" }CRTCTBD
Overlay“zpos”RANGEMin=0, Max=MAX_PLANE-1PlaneTBD
i2c/ch7006_drvGeneric“scale”RANGEMin=0, Max=2ConnectorTBD
TVStandard names as in DRMStandard types as in DRMStandard Values as in DRMStandard object as in DRMTBD
“mode”ENUM{ "PAL", "PAL-M","PAL-N"}, ”PAL-Nc" + , "PAL-60", "NTSC-M", "NTSC-J" }ConnectorTBD
nouveauNV10 Overlay"colorkey"RANGEMin=0, Max=0x01ffffffPlaneTBD
“contrast”RANGEMin=0, Max=8192-1PlaneTBD
“brightness”RANGEMin=0, Max=1024PlaneTBD
“hue”RANGEMin=0, Max=359PlaneTBD
“saturation”RANGEMin=0, Max=8192-1PlaneTBD
“iturbt_709”RANGEMin=0, Max=1PlaneTBD
Nv04 Overlay“colorkey”RANGEMin=0, Max=0x01ffffffPlaneTBD
“brightness”RANGEMin=0, Max=1024PlaneTBD
Display“dithering mode”ENUM{ "auto", "off", "on" }ConnectorTBD
“dithering depth”ENUM{ "auto", "off", "on", "static 2x2", "dynamic 2x2", "temporal" }ConnectorTBD
“underscan”ENUM{ "auto", "6 bpc", "8 bpc" }ConnectorTBD
“underscan hborder”RANGEMin=0, Max=128ConnectorTBD
“underscan vborder”RANGEMin=0, Max=128ConnectorTBD
“vibrant hue”RANGEMin=0, Max=180ConnectorTBD
“color vibrance”RANGEMin=0, Max=200ConnectorTBD
GenericStandard name as in DRMStandard type as in DRMStandard value as in DRMStandard Object as in DRMTBD
omapGeneric“rotation”BITMASK{ 0, "rotate-0" }, + { 1, "rotate-90" }, + { 2, "rotate-180" }, + { 3, "rotate-270" }, + { 4, "reflect-x" }, + { 5, "reflect-y" }CRTC, PlaneTBD
“zorder”RANGEMin=0, Max=3CRTC, PlaneTBD
qxlGeneric“hotplug_mode_update"RANGEMin=0, Max=1ConnectorTBD
radeonDVI-I“coherent”RANGEMin=0, Max=1ConnectorTBD
DAC enable load detect“load detection”RANGEMin=0, Max=1ConnectorTBD
TV Standard"tv standard"ENUM{ "ntsc", "pal", "pal-m", "pal-60", "ntsc-j" + , "scart-pal", "pal-cn", "secam" }ConnectorTBD
legacy TMDS PLL detect"tmds_pll"ENUM{ "driver", "bios" }-TBD
Underscan"underscan"ENUM{ "off", "on", "auto" }ConnectorTBD
"underscan hborder"RANGEMin=0, Max=128ConnectorTBD
"underscan vborder"RANGEMin=0, Max=128ConnectorTBD
Audio“audio”ENUM{ "off", "on", "auto" }ConnectorTBD
FMT Dithering“dither”ENUM{ "off", "on" }ConnectorTBD
GenericStandard name as in DRMStandard type as in DRMStandard value as in DRMStandard Object as in DRMTBD
rcar-duGeneric"alpha"RANGEMin=0, Max=255PlaneTBD
"colorkey"RANGEMin=0, Max=0x01ffffffPlaneTBD
"zpos"RANGEMin=1, Max=7PlaneTBD
+ @@ -2527,6 +3418,10 @@ void (*disable_vblank) (struct drm_device *dev, int crtc); with a call to drm_vblank_cleanup in the driver unload operation handler. + + Vertical Blanking and Interrupt Handling Functions Reference +!Edrivers/gpu/drm/drm_irq.c + @@ -2869,17 +3764,16 @@ int num_ioctls; DRM_IOCTL_MODESET_CTL - This should be called by application level drivers before and - after mode setting, since on many devices the vertical blank - counter is reset at that time. Internally, the DRM snapshots - the last vblank count when the ioctl is called with the - _DRM_PRE_MODESET command, so that the counter won't go backwards - (which is dealt with when _DRM_POST_MODESET is used). + This was only used for user-mode-settind drivers around + modesetting changes to allow the kernel to update the vblank + interrupt after mode setting, since on many devices the vertical + blank counter is reset to 0 at some point during modeset. Modern + drivers should not call this any more since with kernel mode + setting it is a no-op. - @@ -2942,6 +3836,96 @@ int num_ioctls; probing, so those sections fully apply. + + DPIO +!Pdrivers/gpu/drm/i915/i915_reg.h DPIO + + Dual channel PHY (VLV/CHV) + + + + + + + + + + + + + + + + + + CH0 + CH1 + + + + + CMN/PLL/REF + CMN/PLL/REF + + + PCS01 + PCS23 + PCS01 + PCS23 + + + TX0 + TX1 + TX2 + TX3 + TX0 + TX1 + TX2 + TX3 + + + DDI0 + DDI1 + + + +
+ + Single channel PHY (CHV) + + + + + + + + + + + CH0 + + + + + CMN/PLL/REF + + + PCS01 + PCS23 + + + TX0 + TX1 + TX2 + TX3 + + + DDI2 + + + +
+ @@ -2950,6 +3934,11 @@ int num_ioctls; This sections covers all things related to the GEM implementation in the i915 driver. + + Batchbuffer Parsing +!Pdrivers/gpu/drm/i915/i915_cmd_parser.c batch buffer command parser +!Idrivers/gpu/drm/i915/i915_cmd_parser.c + diff --git a/Documentation/EDID/1024x768.S b/Documentation/EDID/1024x768.S index 4b486fe31b32..6f3e4b75e49e 100644 --- a/Documentation/EDID/1024x768.S +++ b/Documentation/EDID/1024x768.S @@ -36,7 +36,7 @@ #define DPI 72 #define VFREQ 60 /* Hz */ #define TIMING_NAME "Linux XGA" -#define ESTABLISHED_TIMINGS_BITS 0x08 /* Bit 3 -> 1024x768 @60 Hz */ +#define ESTABLISHED_TIMING2_BITS 0x08 /* Bit 3 -> 1024x768 @60 Hz */ #define HSYNC_POL 0 #define VSYNC_POL 0 #define CRC 0x55 diff --git a/Documentation/EDID/1280x1024.S b/Documentation/EDID/1280x1024.S index a2799fe33a4d..bd9bef2a65af 100644 --- a/Documentation/EDID/1280x1024.S +++ b/Documentation/EDID/1280x1024.S @@ -36,7 +36,7 @@ #define DPI 72 #define VFREQ 60 /* Hz */ #define TIMING_NAME "Linux SXGA" -#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */ +/* No ESTABLISHED_TIMINGx_BITS */ #define HSYNC_POL 1 #define VSYNC_POL 1 #define CRC 0xa0 diff --git a/Documentation/EDID/1600x1200.S b/Documentation/EDID/1600x1200.S index 0ded64cfd1f5..a45101c6160c 100644 --- a/Documentation/EDID/1600x1200.S +++ b/Documentation/EDID/1600x1200.S @@ -36,7 +36,7 @@ #define DPI 72 #define VFREQ 60 /* Hz */ #define TIMING_NAME "Linux UXGA" -#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */ +/* No ESTABLISHED_TIMINGx_BITS */ #define HSYNC_POL 1 #define VSYNC_POL 1 #define CRC 0x9d diff --git a/Documentation/EDID/1680x1050.S b/Documentation/EDID/1680x1050.S index 96f67cafcf2e..b0d7c69282b4 100644 --- a/Documentation/EDID/1680x1050.S +++ b/Documentation/EDID/1680x1050.S @@ -36,7 +36,7 @@ #define DPI 96 #define VFREQ 60 /* Hz */ #define TIMING_NAME "Linux WSXGA" -#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */ +/* No ESTABLISHED_TIMINGx_BITS */ #define HSYNC_POL 1 #define VSYNC_POL 1 #define CRC 0x26 diff --git a/Documentation/EDID/1920x1080.S b/Documentation/EDID/1920x1080.S index 36ed5d571d0a..3084355e81e7 100644 --- a/Documentation/EDID/1920x1080.S +++ b/Documentation/EDID/1920x1080.S @@ -36,7 +36,7 @@ #define DPI 96 #define VFREQ 60 /* Hz */ #define TIMING_NAME "Linux FHD" -#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */ +/* No ESTABLISHED_TIMINGx_BITS */ #define HSYNC_POL 1 #define VSYNC_POL 1 #define CRC 0x05 diff --git a/Documentation/EDID/800x600.S b/Documentation/EDID/800x600.S new file mode 100644 index 000000000000..6644e26d5801 --- /dev/null +++ b/Documentation/EDID/800x600.S @@ -0,0 +1,41 @@ +/* + 800x600.S: EDID data set for standard 800x600 60 Hz monitor + + Copyright (C) 2011 Carsten Emde + Copyright (C) 2014 Linaro Limited + + This program is free software; you can redistribute it and/or + modify it under the terms of the GNU General Public License + as published by the Free Software Foundation; either version 2 + of the License, or (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. +*/ + +/* EDID */ +#define VERSION 1 +#define REVISION 3 + +/* Display */ +#define CLOCK 40000 /* kHz */ +#define XPIX 800 +#define YPIX 600 +#define XY_RATIO XY_RATIO_4_3 +#define XBLANK 256 +#define YBLANK 28 +#define XOFFSET 40 +#define XPULSE 128 +#define YOFFSET (63+1) +#define YPULSE (63+4) +#define DPI 72 +#define VFREQ 60 /* Hz */ +#define TIMING_NAME "Linux SVGA" +#define ESTABLISHED_TIMING1_BITS 0x01 /* Bit 0: 800x600 @ 60Hz */ +#define HSYNC_POL 1 +#define VSYNC_POL 1 +#define CRC 0xc2 + +#include "edid.S" diff --git a/Documentation/EDID/HOWTO.txt b/Documentation/EDID/HOWTO.txt index 7146db1d9e8c..835db332289b 100644 --- a/Documentation/EDID/HOWTO.txt +++ b/Documentation/EDID/HOWTO.txt @@ -18,7 +18,7 @@ CONFIG_DRM_LOAD_EDID_FIRMWARE was introduced. It allows to provide an individually prepared or corrected EDID data set in the /lib/firmware directory from where it is loaded via the firmware interface. The code (see drivers/gpu/drm/drm_edid_load.c) contains built-in data sets for -commonly used screen resolutions (1024x768, 1280x1024, 1600x1200, +commonly used screen resolutions (800x600, 1024x768, 1280x1024, 1600x1200, 1680x1050, 1920x1080) as binary blobs, but the kernel source tree does not contain code to create these data. In order to elucidate the origin of the built-in binary EDID blobs and to facilitate the creation of diff --git a/Documentation/EDID/edid.S b/Documentation/EDID/edid.S index ea97ae275fca..7ac03276d7a2 100644 --- a/Documentation/EDID/edid.S +++ b/Documentation/EDID/edid.S @@ -33,6 +33,17 @@ #define XY_RATIO_5_4 0b10 #define XY_RATIO_16_9 0b11 +/* Provide defaults for the timing bits */ +#ifndef ESTABLISHED_TIMING1_BITS +#define ESTABLISHED_TIMING1_BITS 0x00 +#endif +#ifndef ESTABLISHED_TIMING2_BITS +#define ESTABLISHED_TIMING2_BITS 0x00 +#endif +#ifndef ESTABLISHED_TIMING3_BITS +#define ESTABLISHED_TIMING3_BITS 0x00 +#endif + #define mfgname2id(v1,v2,v3) \ ((((v1-'@')&0x1f)<<10)+(((v2-'@')&0x1f)<<5)+((v3-'@')&0x1f)) #define swap16(v1) ((v1>>8)+((v1&0xff)<<8)) @@ -139,7 +150,7 @@ white_x_y_msb: .byte 0x50,0x54 Bit 2 640x480 @ 75 Hz Bit 1 800x600 @ 56 Hz Bit 0 800x600 @ 60 Hz */ -estbl_timing1: .byte 0x00 +estbl_timing1: .byte ESTABLISHED_TIMING1_BITS /* Bit 7 800x600 @ 72 Hz Bit 6 800x600 @ 75 Hz @@ -149,11 +160,11 @@ estbl_timing1: .byte 0x00 Bit 2 1024x768 @ 72 Hz Bit 1 1024x768 @ 75 Hz Bit 0 1280x1024 @ 75 Hz */ -estbl_timing2: .byte ESTABLISHED_TIMINGS_BITS +estbl_timing2: .byte ESTABLISHED_TIMING2_BITS /* Bit 7 1152x870 @ 75 Hz (Apple Macintosh II) Bits 6-0 Other manufacturer-specific display mod */ -estbl_timing3: .byte 0x00 +estbl_timing3: .byte ESTABLISHED_TIMING3_BITS /* Standard timing */ /* X resolution, less 31, divided by 8 (256-2288 pixels) */ diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index b045fe54986a..14f4e6336d88 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -26,6 +26,7 @@ Contents: 1.4 target/target_index or setpolicy? 1.5 target/target_index 1.6 setpolicy +1.7 get_intermediate and target_intermediate 2. Frequency Table Helpers @@ -79,6 +80,10 @@ cpufreq_driver.attr - A pointer to a NULL-terminated list of "struct freq_attr" which allow to export values to sysfs. +cpufreq_driver.get_intermediate +and target_intermediate Used to switch to stable frequency while + changing CPU frequency. + 1.2 Per-CPU Initialization -------------------------- @@ -151,7 +156,7 @@ Some cpufreq-capable processors switch the frequency between certain limits on their own. These shall use the ->setpolicy call -1.4. target/target_index +1.5. target/target_index ------------- The target_index call has two arguments: struct cpufreq_policy *policy, @@ -160,6 +165,9 @@ and unsigned int index (into the exposed frequency table). The CPUfreq driver must set the new frequency when called here. The actual frequency must be determined by freq_table[index].frequency. +It should always restore to earlier frequency (i.e. policy->restore_freq) in +case of errors, even if we switched to intermediate frequency earlier. + Deprecated: ---------- The target call has three arguments: struct cpufreq_policy *policy, @@ -179,7 +187,7 @@ Here again the frequency table helper might assist you - see section 2 for details. -1.5 setpolicy +1.6 setpolicy --------------- The setpolicy call only takes a struct cpufreq_policy *policy as @@ -190,6 +198,23 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check the reference implementation in drivers/cpufreq/longrun.c +1.7 get_intermediate and target_intermediate +-------------------------------------------- + +Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset. + +get_intermediate should return a stable intermediate frequency platform wants to +switch to, and target_intermediate() should set CPU to to that frequency, before +jumping to the frequency corresponding to 'index'. Core will take care of +sending notifications and driver doesn't have to handle them in +target_intermediate() or target_index(). + +Drivers can return '0' from get_intermediate() in case they don't wish to switch +to intermediate frequency for some target frequency. In that case core will +directly call ->target_index(). + +NOTE: ->target_index() should restore to policy->restore_freq in case of +failures as core would send notifications for that. 2. Frequency Table Helpers diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt index a5160d8cbb5f..b9ec668bfe62 100644 --- a/Documentation/devicetree/bindings/clock/sunxi.txt +++ b/Documentation/devicetree/bindings/clock/sunxi.txt @@ -20,12 +20,15 @@ Required properties: "allwinner,sun5i-a13-ahb-gates-clk" - for the AHB gates on A13 "allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s "allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20 + "allwinner,sun6i-a31-ar100-clk" - for the AR100 on A31 "allwinner,sun6i-a31-ahb1-mux-clk" - for the AHB1 multiplexer on A31 "allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31 "allwinner,sun4i-a10-apb0-clk" - for the APB0 clock + "allwinner,sun6i-a31-apb0-clk" - for the APB0 clock on A31 "allwinner,sun4i-a10-apb0-gates-clk" - for the APB0 gates on A10 "allwinner,sun5i-a13-apb0-gates-clk" - for the APB0 gates on A13 "allwinner,sun5i-a10s-apb0-gates-clk" - for the APB0 gates on A10s + "allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31 "allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20 "allwinner,sun4i-a10-apb1-clk" - for the APB1 clock "allwinner,sun4i-a10-apb1-mux-clk" - for the APB1 clock muxing @@ -41,6 +44,7 @@ Required properties: "allwinner,sun7i-a20-gmac-clk" - for the GMAC clock module on A20/A31 "allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20 "allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13 + "allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31 Required properties for all clocks: - reg : shall be the control register address for the clock. diff --git a/Documentation/devicetree/bindings/clock/ti/apll.txt b/Documentation/devicetree/bindings/clock/ti/apll.txt index 7faf5a68b3be..ade4dd4c30f0 100644 --- a/Documentation/devicetree/bindings/clock/ti/apll.txt +++ b/Documentation/devicetree/bindings/clock/ti/apll.txt @@ -14,18 +14,32 @@ a subtype of a DPLL [2], although a simplified one at that. [2] Documentation/devicetree/bindings/clock/ti/dpll.txt Required properties: -- compatible : shall be "ti,dra7-apll-clock" +- compatible : shall be "ti,dra7-apll-clock" or "ti,omap2-apll-clock" - #clock-cells : from common clock binding; shall be set to 0. - clocks : link phandles of parent clocks (clk-ref and clk-bypass) - reg : address and length of the register set for controlling the APLL. It contains the information of registers in the following order: - "control" - contains the control register base address - "idlest" - contains the idlest register base address + "control" - contains the control register offset + "idlest" - contains the idlest register offset + "autoidle" - contains the autoidle register offset (OMAP2 only) +- ti,clock-frequency : static clock frequency for the clock (OMAP2 only) +- ti,idlest-shift : bit-shift for the idlest field (OMAP2 only) +- ti,bit-shift : bit-shift for enable and autoidle fields (OMAP2 only) Examples: - apll_pcie_ck: apll_pcie_ck@4a008200 { + apll_pcie_ck: apll_pcie_ck { #clock-cells = <0>; clocks = <&apll_pcie_in_clk_mux>, <&dpll_pcie_ref_ck>; - reg = <0x4a00821c 0x4>, <0x4a008220 0x4>; + reg = <0x021c>, <0x0220>; compatible = "ti,dra7-apll-clock"; }; + + apll96_ck: apll96_ck { + #clock-cells = <0>; + compatible = "ti,omap2-apll-clock"; + clocks = <&sys_ck>; + ti,bit-shift = <2>; + ti,idlest-shift = <8>; + ti,clock-frequency = <96000000>; + reg = <0x0500>, <0x0530>, <0x0520>; + }; diff --git a/Documentation/devicetree/bindings/clock/ti/dpll.txt b/Documentation/devicetree/bindings/clock/ti/dpll.txt index 30bfdb7c9f18..df57009ff8e7 100644 --- a/Documentation/devicetree/bindings/clock/ti/dpll.txt +++ b/Documentation/devicetree/bindings/clock/ti/dpll.txt @@ -24,12 +24,14 @@ Required properties: "ti,omap4-dpll-core-clock", "ti,omap4-dpll-m4xen-clock", "ti,omap4-dpll-j-type-clock", + "ti,omap5-mpu-dpll-clock", "ti,am3-dpll-no-gate-clock", "ti,am3-dpll-j-type-clock", "ti,am3-dpll-no-gate-j-type-clock", "ti,am3-dpll-clock", "ti,am3-dpll-core-clock", "ti,am3-dpll-x2-clock", + "ti,omap2-dpll-core-clock", - #clock-cells : from common clock binding; shall be set to 0. - clocks : link phandles of parent clocks, first entry lists reference clock @@ -41,6 +43,7 @@ Required properties: "mult-div1" - contains the multiplier / divider register base address "autoidle" - contains the autoidle register base address (optional) ti,am3-* dpll types do not have autoidle register + ti,omap2-* dpll type does not support idlest / autoidle registers Optional properties: - DPLL mode setting - defining any one or more of the following overrides @@ -73,3 +76,10 @@ Examples: clocks = <&sys_clkin_ck>, <&sys_clkin_ck>; reg = <0x90>, <0x5c>, <0x68>; }; + + dpll_ck: dpll_ck { + #clock-cells = <0>; + compatible = "ti,omap2-dpll-core-clock"; + clocks = <&sys_ck>, <&sys_ck>; + reg = <0x0500>, <0x0540>; + }; diff --git a/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt new file mode 100644 index 000000000000..585e8c191f50 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt @@ -0,0 +1,96 @@ +Device Tree Clock bindings for ATL (Audio Tracking Logic) of DRA7 SoC. + +The ATL IP is used to generate clock to be used to synchronize baseband and +audio codec. A single ATL IP provides four ATL clock instances sharing the same +functional clock but can be configured to provide different clocks. +ATL can maintain a clock averages to some desired frequency based on the bws/aws +signals - can compensate the drift between the two ws signal. + +In order to provide the support for ATL and it's output clocks (which can be used +internally within the SoC or external components) two sets of bindings is needed: + +Clock tree binding: +This binding uses the common clock binding[1]. +To be able to integrate the ATL clocks with DT clock tree. +Provides ccf level representation of the ATL clocks to be used by drivers. +Since the clock instances are part of a single IP this binding is used as a node +for the DT clock tree, the IP driver is needed to handle the actual configuration +of the IP. + +[1] Documentation/devicetree/bindings/clock/clock-bindings.txt + +Required properties: +- compatible : shall be "ti,dra7-atl-clock" +- #clock-cells : from common clock binding; shall be set to 0. +- clocks : link phandles to functional clock of ATL + +Binding for the IP driver: +This binding is used to configure the IP driver which is going to handle the +configuration of the IP for the ATL clock instances. + +Required properties: +- compatible : shall be "ti,dra7-atl" +- reg : base address for the ATL IP +- ti,provided-clocks : List of phandles to the clocks associated with the ATL +- clocks : link phandles to functional clock of ATL +- clock-names : Shall be set to "fck" +- ti,hwmods : Shall be set to "atl" + +Optional properties: +Configuration of ATL instances: +- atl{0/1/2/3} { + - bws : Baseband word select signal selection + - aws : Audio word select signal selection +}; + +For valid word select signals, see the dt-bindings/clk/ti-dra7-atl.h include +file. + +Examples: +/* clock bindings for atl provided clocks */ +atl_clkin0_ck: atl_clkin0_ck { + #clock-cells = <0>; + compatible = "ti,dra7-atl-clock"; + clocks = <&atl_gfclk_mux>; +}; + +atl_clkin1_ck: atl_clkin1_ck { + #clock-cells = <0>; + compatible = "ti,dra7-atl-clock"; + clocks = <&atl_gfclk_mux>; +}; + +atl_clkin2_ck: atl_clkin2_ck { + #clock-cells = <0>; + compatible = "ti,dra7-atl-clock"; + clocks = <&atl_gfclk_mux>; +}; + +atl_clkin3_ck: atl_clkin3_ck { + #clock-cells = <0>; + compatible = "ti,dra7-atl-clock"; + clocks = <&atl_gfclk_mux>; +}; + +/* binding for the IP */ +atl: atl@4843c000 { + compatible = "ti,dra7-atl"; + reg = <0x4843c000 0x3ff>; + ti,hwmods = "atl"; + ti,provided-clocks = <&atl_clkin0_ck>, <&atl_clkin1_ck>, + <&atl_clkin2_ck>, <&atl_clkin3_ck>; + clocks = <&atl_gfclk_mux>; + clock-names = "fck"; + status = "disabled"; +}; + +#include + +&atl { + status = "okay"; + + atl2 { + bws = ; + aws = ; + }; +}; diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt index 125281aaa4ca..03f8fdee62a7 100644 --- a/Documentation/devicetree/bindings/clock/ti/gate.txt +++ b/Documentation/devicetree/bindings/clock/ti/gate.txt @@ -25,6 +25,11 @@ Required properties: to map clockdomains properly "ti,hsdiv-gate-clock" - gate clock with OMAP36xx specific hardware handling, required for a hardware errata + "ti,composite-gate-clock" - composite gate clock, to be part of composite + clock + "ti,composite-no-wait-gate-clock" - composite gate clock that does not wait + for clock to be active before returning + from clk_enable() - #clock-cells : from common clock binding; shall be set to 0 - clocks : link to phandle of parent clock - reg : offset for register controlling adjustable gate, not needed for @@ -41,7 +46,7 @@ Examples: #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&core_96m_fck>; - reg = <0x48004a00 0x4>; + reg = <0x0a00>; ti,bit-shift = <25>; }; @@ -57,7 +62,7 @@ Examples: #clock-cells = <0>; compatible = "ti,dss-gate-clock"; clocks = <&dpll4_m4x2_ck>; - reg = <0x48004e00 0x4>; + reg = <0x0e00>; ti,bit-shift = <0>; }; @@ -65,7 +70,7 @@ Examples: #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x4800259c 0x4>; + reg = <0x059c>; ti,bit-shift = <1>; }; @@ -80,6 +85,22 @@ Examples: compatible = "ti,hsdiv-gate-clock"; clocks = <&dpll4_m2x2_mul_ck>; ti,bit-shift = <0x1b>; - reg = <0x48004d00 0x4>; + reg = <0x0d00>; ti,set-bit-to-disable; }; + + vlynq_gate_fck: vlynq_gate_fck { + #clock-cells = <0>; + compatible = "ti,composite-gate-clock"; + clocks = <&core_ck>; + ti,bit-shift = <3>; + reg = <0x0200>; + }; + + sys_clkout2_src_gate: sys_clkout2_src_gate { + #clock-cells = <0>; + compatible = "ti,composite-no-wait-gate-clock"; + clocks = <&core_ck>; + ti,bit-shift = <15>; + reg = <0x0070>; + }; diff --git a/Documentation/devicetree/bindings/clock/ti/interface.txt b/Documentation/devicetree/bindings/clock/ti/interface.txt index 064e8caccac3..3111a409fea6 100644 --- a/Documentation/devicetree/bindings/clock/ti/interface.txt +++ b/Documentation/devicetree/bindings/clock/ti/interface.txt @@ -21,6 +21,8 @@ Required properties: "ti,omap3-dss-interface-clock" - interface clock with DSS specific HW handling "ti,omap3-ssi-interface-clock" - interface clock with SSI specific HW handling "ti,am35xx-interface-clock" - interface clock with AM35xx specific HW handling + "ti,omap2430-interface-clock" - interface clock with OMAP2430 specific HW + handling - #clock-cells : from common clock binding; shall be set to 0 - clocks : link to phandle of parent clock - reg : base address for the control register diff --git a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt index efa8b8451f93..b48f4ef31d93 100644 --- a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt +++ b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt @@ -136,6 +136,7 @@ of the following host1x client modules: - compatible: "nvidia,tegra-hdmi" - reg: Physical base address and length of the controller's registers. - interrupts: The interrupt outputs from the controller. + - hdmi-supply: supply for the +5V HDMI connector pin - vdd-supply: regulator for supply voltage - pll-supply: regulator for PLL - clocks: Must contain an entry for each entry in clock-names. @@ -180,6 +181,7 @@ of the following host1x client modules: See ../reset/reset.txt for details. - reset-names: Must include the following entries: - dsi + - avdd-dsi-supply: phandle of a supply that powers the DSI controller - nvidia,mipi-calibrate: Should contain a phandle and a specifier specifying which pads are used by this DSI output and need to be calibrated. See also ../mipi/nvidia,tegra114-mipi.txt. diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt index c55b8c016a9e..1b66a413fb9d 100644 --- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt +++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt @@ -1,7 +1,13 @@ Binding for TI/National Semiconductor LP55xx Led Drivers Required properties: -- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562" or "ti,lp8501" +- compatible: one of + national,lp5521 + national,lp5523 + ti,lp55231 + ti,lp5562 + ti,lp8501 + - reg: I2C slave address - clock-mode: Input clock mode, (0: automode, 1: internal, 2: external) diff --git a/Documentation/devicetree/bindings/leds/leds-pwm.txt b/Documentation/devicetree/bindings/leds/leds-pwm.txt index 7297107cf832..6c6583c35f2f 100644 --- a/Documentation/devicetree/bindings/leds/leds-pwm.txt +++ b/Documentation/devicetree/bindings/leds/leds-pwm.txt @@ -13,6 +13,8 @@ LED sub-node properties: For the pwms and pwm-names property please refer to: Documentation/devicetree/bindings/pwm/pwm.txt - max-brightness : Maximum brightness possible for the LED +- active-low : (optional) For PWMs where the LED is wired to supply + rather than ground. - label : (optional) see Documentation/devicetree/bindings/leds/common.txt - linux,default-trigger : (optional) diff --git a/Documentation/devicetree/bindings/mfd/twl4030-power.txt b/Documentation/devicetree/bindings/mfd/twl4030-power.txt index 8e15ec35ac99..b9ee7b98d3e2 100644 --- a/Documentation/devicetree/bindings/mfd/twl4030-power.txt +++ b/Documentation/devicetree/bindings/mfd/twl4030-power.txt @@ -5,7 +5,22 @@ to control the power resources, including power scripts. For now, the binding only supports the complete shutdown of the system after poweroff. Required properties: -- compatible : must be "ti,twl4030-power" +- compatible : must be one of the following + "ti,twl4030-power" + "ti,twl4030-power-reset" + "ti,twl4030-power-idle" + "ti,twl4030-power-idle-osc-off" + +The use of ti,twl4030-power-reset is recommended at least on +3530 that needs a special configuration for warm reset to work. + +When using ti,twl4030-power-idle, the TI recommended configuration +for idle modes is loaded to the tlw4030 PMIC. + +When using ti,twl4030-power-idle-osc-off, the TI recommended +configuration is used with the external oscillator being shut +down during off-idle. Note that this does not work on all boards +depending on how the external oscillator is wired. Optional properties: - ti,use_poweroff: With this flag, the chip will initiates an ACTIVE-to-OFF or diff --git a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt new file mode 100644 index 000000000000..d01ed63d3ebb --- /dev/null +++ b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt @@ -0,0 +1,17 @@ +* AMD 10GbE PHY driver (amd-xgbe-phy) + +Required properties: +- compatible: Should be "amd,xgbe-phy-seattle-v1a" and + "ethernet-phy-ieee802.3-c45" +- reg: Address and length of the register sets for the device + - SerDes Rx/Tx registers + - SerDes integration registers (1/2) + - SerDes integration registers (2/2) + +Example: + xgbe_phy@e1240800 { + compatible = "amd,xgbe-phy-seattle-v1a", "ethernet-phy-ieee802.3-c45"; + reg = <0 0xe1240800 0 0x00400>, + <0 0xe1250000 0 0x00060>, + <0 0xe1250080 0 0x00004>; + }; diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt new file mode 100644 index 000000000000..ea0c7908a3b8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/amd-xgbe.txt @@ -0,0 +1,34 @@ +* AMD 10GbE driver (amd-xgbe) + +Required properties: +- compatible: Should be "amd,xgbe-seattle-v1a" +- reg: Address and length of the register sets for the device + - MAC registers + - PCS registers +- interrupt-parent: Should be the phandle for the interrupt controller + that services interrupts for this device +- interrupts: Should contain the amd-xgbe interrupt +- clocks: Should be the DMA clock for the amd-xgbe device (used for + calculating the correct Rx interrupt watchdog timer value on a DMA + channel for coalescing) +- clock-names: Should be the name of the DMA clock, "dma_clk" +- phy-handle: See ethernet.txt file in the same directory +- phy-mode: See ethernet.txt file in the same directory + +Optional properties: +- mac-address: mac address to be assigned to the device. Can be overridden + by UEFI. + +Example: + xgbe@e0700000 { + compatible = "amd,xgbe-seattle-v1a"; + reg = <0 0xe0700000 0 0x80000>, + <0 0xe0780000 0 0x80000>; + interrupt-parent = <&gic>; + interrupts = <0 325 4>; + clocks = <&xgbe_clk>; + clock-names = "dma_clk"; + phy-handle = <&phy>; + phy-mode = "xgmii"; + mac-address = [ 02 a1 a2 a3 a4 a5 ]; + }; diff --git a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt index f2febb94550e..451fef26b4df 100644 --- a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt @@ -24,7 +24,7 @@ Optional properties: - fixed-link: When the GENET interface is connected to a MoCA hardware block or when operating in a RGMII to RGMII type of connection, or when the MDIO bus is voluntarily disabled, this property should be used to describe the "fixed link". - See Documentation/devicetree/bindings/net/fsl-tsec-phy.txt for information on + See Documentation/devicetree/bindings/net/fixed-link.txt for information on the property specifics Required child nodes: diff --git a/Documentation/devicetree/bindings/net/broadcom-systemport.txt b/Documentation/devicetree/bindings/net/broadcom-systemport.txt new file mode 100644 index 000000000000..c183ea90d9bc --- /dev/null +++ b/Documentation/devicetree/bindings/net/broadcom-systemport.txt @@ -0,0 +1,29 @@ +* Broadcom BCM7xxx Ethernet Systemport Controller (SYSTEMPORT) + +Required properties: +- compatible: should be one of "brcm,systemport-v1.00" or "brcm,systemport" +- reg: address and length of the register set for the device. +- interrupts: interrupts for the device, first cell must be for the the rx + interrupts, and the second cell should be for the transmit queues +- local-mac-address: Ethernet MAC address (48 bits) of this adapter +- phy-mode: Should be a string describing the PHY interface to the + Ethernet switch/PHY, see Documentation/devicetree/bindings/net/ethernet.txt +- fixed-link: see Documentation/devicetree/bindings/net/fixed-link.txt for + the property specific details + +Optional properties: +- systemport,num-tier2-arb: number of tier 2 arbiters, an integer +- systemport,num-tier1-arb: number of tier 1 arbiters, an integer +- systemport,num-txq: number of HW transmit queues, an integer +- systemport,num-rxq: number of HW receive queues, an integer + +Example: +ethernet@f04a0000 { + compatible = "brcm,systemport-v1.00"; + reg = <0xf04a0000 0x4650>; + local-mac-address = [ 00 11 22 33 44 55 ]; + fixed-link = <0 1 1000 0 0>; + phy-mode = "gmii"; + interrupts = <0x0 0x16 0x0>, + <0x0 0x17 0x0>; +}; diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt new file mode 100644 index 000000000000..fe38847d8e26 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt @@ -0,0 +1,44 @@ +Xilinx Axi CAN/Zynq CANPS controller Device Tree Bindings +--------------------------------------------------------- + +Required properties: +- compatible : Should be "xlnx,zynq-can-1.0" for Zynq CAN + controllers and "xlnx,axi-can-1.00.a" for Axi CAN + controllers. +- reg : Physical base address and size of the Axi CAN/Zynq + CANPS registers map. +- interrupts : Property with a value describing the interrupt + number. +- interrupt-parent : Must be core interrupt controller +- clock-names : List of input clock names - "can_clk", "pclk" + (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN) + (See clock bindings for details). +- clocks : Clock phandles (see clock bindings for details). +- tx-fifo-depth : Can Tx fifo depth. +- rx-fifo-depth : Can Rx fifo depth. + + +Example: + +For Zynq CANPS Dts file: + zynq_can_0: can@e0008000 { + compatible = "xlnx,zynq-can-1.0"; + clocks = <&clkc 19>, <&clkc 36>; + clock-names = "can_clk", "pclk"; + reg = <0xe0008000 0x1000>; + interrupts = <0 28 4>; + interrupt-parent = <&intc>; + tx-fifo-depth = <0x40>; + rx-fifo-depth = <0x40>; + }; +For Axi CAN Dts file: + axi_can_0: axi-can@40000000 { + compatible = "xlnx,axi-can-1.00.a"; + clocks = <&clkc 0>, <&clkc 1>; + clock-names = "can_clk","s_axi_aclk" ; + reg = <0x40000000 0x10000>; + interrupt-parent = <&intc>; + interrupts = <0 59 1>; + tx-fifo-depth = <0x40>; + rx-fifo-depth = <0x40>; + }; diff --git a/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt b/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt index 7ff57a119f81..764c0c79b43d 100644 --- a/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt +++ b/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt @@ -2,7 +2,9 @@ TI CPSW Phy mode Selection Device Tree Bindings ----------------------------------------------- Required properties: -- compatible : Should be "ti,am3352-cpsw-phy-sel" +- compatible : Should be "ti,am3352-cpsw-phy-sel" for am335x platform and + "ti,dra7xx-cpsw-phy-sel" for dra7xx platform + "ti,am43xx-cpsw-phy-sel" for am43xx platform - reg : physical base address and size of the cpsw registers map - reg-names : names of the register map given in "reg" node diff --git a/Documentation/devicetree/bindings/net/fixed-link.txt b/Documentation/devicetree/bindings/net/fixed-link.txt new file mode 100644 index 000000000000..82bf7e0f47b6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/fixed-link.txt @@ -0,0 +1,42 @@ +Fixed link Device Tree binding +------------------------------ + +Some Ethernet MACs have a "fixed link", and are not connected to a +normal MDIO-managed PHY device. For those situations, a Device Tree +binding allows to describe a "fixed link". + +Such a fixed link situation is described by creating a 'fixed-link' +sub-node of the Ethernet MAC device node, with the following +properties: + +* 'speed' (integer, mandatory), to indicate the link speed. Accepted + values are 10, 100 and 1000 +* 'full-duplex' (boolean, optional), to indicate that full duplex is + used. When absent, half duplex is assumed. +* 'pause' (boolean, optional), to indicate that pause should be + enabled. +* 'asym-pause' (boolean, optional), to indicate that asym_pause should + be enabled. + +Old, deprecated 'fixed-link' binding: + +* A 'fixed-link' property in the Ethernet MAC node, with 5 cells, of the + form with the following accepted values: + - a: emulated PHY ID, choose any but but unique to the all specified + fixed-links, from 0 to 31 + - b: duplex configuration: 0 for half duplex, 1 for full duplex + - c: link speed in Mbits/sec, accepted values are: 10, 100 and 1000 + - d: pause configuration: 0 for no pause, 1 for pause + - e: asymmetric pause configuration: 0 for no asymmetric pause, 1 for + asymmetric pause + +Example: + +ethernet@0 { + ... + fixed-link { + speed = <1000>; + full-duplex; + }; + ... +}; diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index 737cdef4f903..be6ea8960f20 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -42,10 +42,7 @@ Properties: interrupt. For TSEC and eTSEC devices, the first interrupt is transmit, the second is receive, and the third is error. - phy-handle : See ethernet.txt file in the same directory. - - fixed-link : where a is emulated phy id - choose any, - but unique to the all specified fixed-links, b is duplex - 0 half, - 1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no - pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause. + - fixed-link : See fixed-link.txt in the same directory. - phy-connection-type : See ethernet.txt file in the same directory. This property is only really needed if the connection is of type "rgmii-id", as all other connection types are detected by hardware. diff --git a/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt new file mode 100644 index 000000000000..75d398bb1fbb --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt @@ -0,0 +1,36 @@ +Hisilicon hix5hd2 gmac controller + +Required properties: +- compatible: should be "hisilicon,hix5hd2-gmac". +- reg: specifies base physical address(s) and size of the device registers. + The first region is the MAC register base and size. + The second region is external interface control register. +- interrupts: should contain the MAC interrupt. +- #address-cells: must be <1>. +- #size-cells: must be <0>. +- phy-mode: see ethernet.txt [1]. +- phy-handle: see ethernet.txt [1]. +- mac-address: see ethernet.txt [1]. +- clocks: clock phandle and specifier pair. + +- PHY subnode: inherits from phy binding [2] + +[1] Documentation/devicetree/bindings/net/ethernet.txt +[2] Documentation/devicetree/bindings/net/phy.txt + +Example: + gmac0: ethernet@f9840000 { + compatible = "hisilicon,hix5hd2-gmac"; + reg = <0xf9840000 0x1000>,<0xf984300c 0x4>; + interrupts = <0 71 4>; + #address-cells = <1>; + #size-cells = <0>; + phy-mode = "mii"; + phy-handle = <&phy2>; + mac-address = [00 00 00 00 00 00]; + clocks = <&clock HIX5HD2_MAC0_CLK>; + + phy2: ethernet-phy@2 { + reg = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt new file mode 100644 index 000000000000..d3bbdded4cbe --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt @@ -0,0 +1,23 @@ +* AT86RF230 IEEE 802.15.4 * + +Required properties: + - compatible: should be "atmel,at86rf230", "atmel,at86rf231", + "atmel,at86rf233" or "atmel,at86rf212" + - spi-max-frequency: maximal bus speed, should be set to 7500000 depends + sync or async operation mode + - reg: the chipselect index + - interrupts: the interrupt generated by the device + +Optional properties: + - reset-gpio: GPIO spec for the rstn pin + - sleep-gpio: GPIO spec for the slp_tr pin + +Example: + + at86rf231@0 { + compatible = "atmel,at86rf231"; + spi-max-frequency = <7500000>; + reg = <0>; + interrupts = <19 1>; + interrupt-parent = <&gpio3>; + }; diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt index d54d0cc79487..bbdf9a7359a2 100644 --- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt +++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt @@ -1,9 +1,18 @@ -Micrel KS8851 Ethernet mac +Micrel KS8851 Ethernet mac (MLL) Required properties: -- compatible = "micrel,ks8851-ml" of parallel interface +- compatible = "micrel,ks8851-mll" of parallel interface - reg : 2 physical address and size of registers for data and command - interrupts : interrupt connection +Micrel KS8851 Ethernet mac (SPI) + +Required properties: +- compatible = "micrel,ks8851" or the deprecated "ks8851" +- reg : chip select number +- interrupts : interrupt connection + Optional properties: -- vdd-supply: supply for Ethernet mac +- vdd-supply: analog 3.3V supply for Ethernet mac +- vdd-io-supply: digital 1.8V IO supply for Ethernet mac +- reset-gpios: reset_n input pin diff --git a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt deleted file mode 100644 index 997a63f1aea1..000000000000 --- a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt +++ /dev/null @@ -1,49 +0,0 @@ -Micrel KSZ9021 Gigabit Ethernet PHY - -Some boards require special tuning values, particularly when it comes to -clock delays. You can specify clock delay values by adding -micrel-specific properties to an Ethernet OF device node. - -All skew control options are specified in picoseconds. The minimum -value is 0, and the maximum value is 3000. - -Optional properties: - - rxc-skew-ps : Skew control of RXC pad - - rxdv-skew-ps : Skew control of RX CTL pad - - txc-skew-ps : Skew control of TXC pad - - txen-skew-ps : Skew control of TX_CTL pad - - rxd0-skew-ps : Skew control of RX data 0 pad - - rxd1-skew-ps : Skew control of RX data 1 pad - - rxd2-skew-ps : Skew control of RX data 2 pad - - rxd3-skew-ps : Skew control of RX data 3 pad - - txd0-skew-ps : Skew control of TX data 0 pad - - txd1-skew-ps : Skew control of TX data 1 pad - - txd2-skew-ps : Skew control of TX data 2 pad - - txd3-skew-ps : Skew control of TX data 3 pad - -Examples: - - /* Attach to an Ethernet device with autodetected PHY */ - &enet { - rxc-skew-ps = <3000>; - rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; - txen-skew-ps = <0>; - status = "okay"; - }; - - /* Attach to an explicitly-specified PHY */ - mdio { - phy0: ethernet-phy@0 { - rxc-skew-ps = <3000>; - rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; - txen-skew-ps = <0>; - reg = <0>; - }; - }; - ethernet@70000 { - status = "okay"; - phy = <&phy0>; - phy-mode = "rgmii-id"; - }; diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt new file mode 100644 index 000000000000..692076fda0e5 --- /dev/null +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -0,0 +1,83 @@ +Micrel KSZ9021/KSZ9031 Gigabit Ethernet PHY + +Some boards require special tuning values, particularly when it comes to +clock delays. You can specify clock delay values by adding +micrel-specific properties to an Ethernet OF device node. + +Note that these settings are applied after any phy-specific fixup from +phy_fixup_list (see phy_init_hw() from drivers/net/phy/phy_device.c), +and therefore may overwrite them. + +KSZ9021: + + All skew control options are specified in picoseconds. The minimum + value is 0, the maximum value is 3000, and it is incremented by 200ps + steps. + + Optional properties: + + - rxc-skew-ps : Skew control of RXC pad + - rxdv-skew-ps : Skew control of RX CTL pad + - txc-skew-ps : Skew control of TXC pad + - txen-skew-ps : Skew control of TX CTL pad + - rxd0-skew-ps : Skew control of RX data 0 pad + - rxd1-skew-ps : Skew control of RX data 1 pad + - rxd2-skew-ps : Skew control of RX data 2 pad + - rxd3-skew-ps : Skew control of RX data 3 pad + - txd0-skew-ps : Skew control of TX data 0 pad + - txd1-skew-ps : Skew control of TX data 1 pad + - txd2-skew-ps : Skew control of TX data 2 pad + - txd3-skew-ps : Skew control of TX data 3 pad + +KSZ9031: + + All skew control options are specified in picoseconds. The minimum + value is 0, and the maximum is property-dependent. The increment + step is 60ps. + + Optional properties: + + Maximum value of 1860: + + - rxc-skew-ps : Skew control of RX clock pad + - txc-skew-ps : Skew control of TX clock pad + + Maximum value of 900: + + - rxdv-skew-ps : Skew control of RX CTL pad + - txen-skew-ps : Skew control of TX CTL pad + - rxd0-skew-ps : Skew control of RX data 0 pad + - rxd1-skew-ps : Skew control of RX data 1 pad + - rxd2-skew-ps : Skew control of RX data 2 pad + - rxd3-skew-ps : Skew control of RX data 3 pad + - txd0-skew-ps : Skew control of TX data 0 pad + - txd1-skew-ps : Skew control of TX data 1 pad + - txd2-skew-ps : Skew control of TX data 2 pad + - txd3-skew-ps : Skew control of TX data 3 pad + +Examples: + + /* Attach to an Ethernet device with autodetected PHY */ + &enet { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + status = "okay"; + }; + + /* Attach to an explicitly-specified PHY */ + mdio { + phy0: ethernet-phy@0 { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + reg = <0>; + }; + }; + ethernet@70000 { + status = "okay"; + phy = <&phy0>; + phy-mode = "rgmii-id"; + }; diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt new file mode 100644 index 000000000000..dab69f36167c --- /dev/null +++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt @@ -0,0 +1,35 @@ +* NXP Semiconductors PN544 NFC Controller + +Required properties: +- compatible: Should be "nxp,pn544-i2c". +- clock-frequency: IC work frequency. +- reg: address on the bus +- interrupt-parent: phandle for the interrupt gpio controller +- interrupts: GPIO interrupt to which the chip is connected +- enable-gpios: Output GPIO pin used for enabling/disabling the PN544 +- firmware-gpios: Output GPIO pin used to enter firmware download mode + +Optional SoC Specific Properties: +- pinctrl-names: Contains only one value - "default". +- pintctrl-0: Specifies the pin control groups used for this controller. + +Example (for ARM-based BeagleBone with PN544 on I2C2): + +&i2c2 { + + status = "okay"; + + pn544: pn544@28 { + + compatible = "nxp,pn544-i2c"; + + reg = <0x28>; + clock-frequency = <400000>; + + interrupt-parent = <&gpio1>; + interrupts = <17 GPIO_ACTIVE_HIGH>; + + enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; + }; +}; diff --git a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt new file mode 100644 index 000000000000..e4faa2e8dfeb --- /dev/null +++ b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt @@ -0,0 +1,33 @@ +* STMicroelectronics SAS. ST21NFCA NFC Controller + +Required properties: +- compatible: Should be "st,st21nfca_i2c". +- clock-frequency: I²C work frequency. +- reg: address on the bus +- interrupt-parent: phandle for the interrupt gpio controller +- interrupts: GPIO interrupt to which the chip is connected +- enable-gpios: Output GPIO pin used for enabling/disabling the ST21NFCA + +Optional SoC Specific Properties: +- pinctrl-names: Contains only one value - "default". +- pintctrl-0: Specifies the pin control groups used for this controller. + +Example (for ARM-based BeagleBoard xM with ST21NFCA on I2C2): + +&i2c2 { + + status = "okay"; + + st21nfca: st21nfca@1 { + + compatible = "st,st21nfca_i2c"; + + reg = <0x01>; + clock-frequency = <400000>; + + interrupt-parent = <&gpio5>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + + enable-gpios = <&gpio5 29 GPIO_ACTIVE_HIGH>; + }; +}; diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt index 8dd3ef7bc56b..1e436133685f 100644 --- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt +++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt @@ -12,6 +12,7 @@ Required properties: Optional SoC Specific Properties: - pinctrl-names: Contains only one value - "default". - pintctrl-0: Specifies the pin control groups used for this controller. +- autosuspend-delay: Specify autosuspend delay in milliseconds. Example (for ARM-based BeagleBone with TRF7970A on SPI1): @@ -29,6 +30,7 @@ Example (for ARM-based BeagleBone with TRF7970A on SPI1): ti,enable-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>, <&gpio2 5 GPIO_ACTIVE_LOW>; vin-supply = <&ldo3_reg>; + autosuspend-delay = <30000>; status = "okay"; }; }; diff --git a/Documentation/devicetree/bindings/net/via-rhine.txt b/Documentation/devicetree/bindings/net/via-rhine.txt new file mode 100644 index 000000000000..334eca2bf937 --- /dev/null +++ b/Documentation/devicetree/bindings/net/via-rhine.txt @@ -0,0 +1,17 @@ +* VIA Rhine 10/100 Network Controller + +Required properties: +- compatible : Should be "via,vt8500-rhine" for integrated + Rhine controllers found in VIA VT8500, WonderMedia WM8950 + and similar. These are listed as 1106:3106 rev. 0x84 on the + virtual PCI bus under vendor-provided kernels +- reg : Address and length of the io space +- interrupts : Should contain the controller interrupt line + +Examples: + +ethernet@d8004000 { + compatible = "via,vt8500-rhine"; + reg = <0xd8004000 0x100>; + interrupts = <10>; +}; diff --git a/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt b/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt new file mode 100644 index 000000000000..7443b7c76769 --- /dev/null +++ b/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt @@ -0,0 +1,7 @@ +AU Optronics Corporation 13.3" WXGA (1366x768) TFT LCD panel + +Required properties: +- compatible: should be "auo,b133xtn01" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt b/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt new file mode 100644 index 000000000000..4903d7b1d947 --- /dev/null +++ b/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt @@ -0,0 +1,7 @@ +Emerging Display Technology Corp. 5.7" VGA TFT LCD panel + +Required properties: +- compatible: should be "edt,et057090dhu" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt b/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt new file mode 100644 index 000000000000..20cb38e836e4 --- /dev/null +++ b/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt @@ -0,0 +1,10 @@ +Emerging Display Technology Corp. ET070080DH6 7.0" WVGA TFT LCD panel + +Required properties: +- compatible: should be "edt,et070080dh6" + +This panel is the same as ETM0700G0DH6 except for the touchscreen. +ET070080DH6 is the model with resistive touch. + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt b/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt new file mode 100644 index 000000000000..ee4b18053e40 --- /dev/null +++ b/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt @@ -0,0 +1,10 @@ +Emerging Display Technology Corp. ETM0700G0DH6 7.0" WVGA TFT LCD panel + +Required properties: +- compatible: should be "edt,etm0700g0dh6" + +This panel is the same as ET070080DH6 except for the touchscreen. +ETM0700G0DH6 is the model with capacitive multitouch. + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt index d6fae13ff062..d0d15ee42834 100644 --- a/Documentation/devicetree/bindings/pci/designware-pcie.txt +++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -1,15 +1,7 @@ * Synopsys Designware PCIe interface Required properties: -- compatible: should contain "snps,dw-pcie" to identify the - core, plus an identifier for the specific instance, such - as "samsung,exynos5440-pcie" or "fsl,imx6q-pcie". -- reg: base addresses and lengths of the pcie controller, - the phy controller, additional register for the phy controller. -- interrupts: interrupt values for level interrupt, - pulse interrupt, special interrupt. -- clocks: from common clock binding: handle to pci clock. -- clock-names: from common clock binding: should be "pcie" and "pcie_bus". +- compatible: should contain "snps,dw-pcie" to identify the core. - #address-cells: set to <3> - #size-cells: set to <2> - device_type: set to "pci" @@ -19,65 +11,11 @@ Required properties: to define the mapping of the PCIe interface to interrupt numbers. - num-lanes: number of lanes to use +- clocks: Must contain an entry for each entry in clock-names. + See ../clocks/clock-bindings.txt for details. +- clock-names: Must include the following entries: + - "pcie" + - "pcie_bus" Optional properties: - reset-gpio: gpio pin number of power good signal - -Optional properties for fsl,imx6q-pcie -- power-on-gpio: gpio pin number of power-enable signal -- wake-up-gpio: gpio pin number of incoming wakeup signal -- disable-gpio: gpio pin number of outgoing rfkill/endpoint disable signal - -Example: - -SoC specific DT Entry: - - pcie@290000 { - compatible = "samsung,exynos5440-pcie", "snps,dw-pcie"; - reg = <0x290000 0x1000 - 0x270000 0x1000 - 0x271000 0x40>; - interrupts = <0 20 0>, <0 21 0>, <0 22 0>; - clocks = <&clock 28>, <&clock 27>; - clock-names = "pcie", "pcie_bus"; - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - ranges = <0x00000800 0 0x40000000 0x40000000 0 0x00001000 /* configuration space */ - 0x81000000 0 0 0x40001000 0 0x00010000 /* downstream I/O */ - 0x82000000 0 0x40011000 0x40011000 0 0x1ffef000>; /* non-prefetchable memory */ - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0x0 0 &gic 53>; - num-lanes = <4>; - }; - - pcie@2a0000 { - compatible = "samsung,exynos5440-pcie", "snps,dw-pcie"; - reg = <0x2a0000 0x1000 - 0x272000 0x1000 - 0x271040 0x40>; - interrupts = <0 23 0>, <0 24 0>, <0 25 0>; - clocks = <&clock 29>, <&clock 27>; - clock-names = "pcie", "pcie_bus"; - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - ranges = <0x00000800 0 0x60000000 0x60000000 0 0x00001000 /* configuration space */ - 0x81000000 0 0 0x60001000 0 0x00010000 /* downstream I/O */ - 0x82000000 0 0x60011000 0x60011000 0 0x1ffef000>; /* non-prefetchable memory */ - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0x0 0 &gic 56>; - num-lanes = <4>; - }; - -Board specific DT Entry: - - pcie@290000 { - reset-gpio = <&pin_ctrl 5 0>; - }; - - pcie@2a0000 { - reset-gpio = <&pin_ctrl 22 0>; - }; diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt new file mode 100644 index 000000000000..9455fd0ec830 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt @@ -0,0 +1,38 @@ +* Freescale i.MX6 PCIe interface + +This PCIe host controller is based on the Synopsis Designware PCIe IP +and thus inherits all the common properties defined in designware-pcie.txt. + +Required properties: +- compatible: "fsl,imx6q-pcie" +- reg: base addresse and length of the pcie controller +- interrupts: A list of interrupt outputs of the controller. Must contain an + entry for each entry in the interrupt-names property. +- interrupt-names: Must include the following entries: + - "msi": The interrupt that is asserted when an MSI is received +- clock-names: Must include the following additional entries: + - "pcie_phy" + +Example: + + pcie@0x01000000 { + compatible = "fsl,imx6q-pcie", "snps,dw-pcie"; + reg = <0x01ffc000 0x4000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x00000800 0 0x01f00000 0x01f00000 0 0x00080000 + 0x81000000 0 0 0x01f80000 0 0x00010000 + 0x82000000 0 0x01000000 0x01000000 0 0x00f00000>; + num-lanes = <1>; + interrupts = ; + interrupt-names = "msi"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks 144>, <&clks 206>, <&clks 189>; + clock-names = "pcie", "pcie_bus", "pcie_phy"; + }; diff --git a/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt b/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt new file mode 100644 index 000000000000..4f9d23d2ed67 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt @@ -0,0 +1,65 @@ +* Samsung Exynos 5440 PCIe interface + +This PCIe host controller is based on the Synopsis Designware PCIe IP +and thus inherits all the common properties defined in designware-pcie.txt. + +Required properties: +- compatible: "samsung,exynos5440-pcie" +- reg: base addresses and lengths of the pcie controller, + the phy controller, additional register for the phy controller. +- interrupts: A list of interrupt outputs for level interrupt, + pulse interrupt, special interrupt. + +Example: + +SoC specific DT Entry: + + pcie@290000 { + compatible = "samsung,exynos5440-pcie", "snps,dw-pcie"; + reg = <0x290000 0x1000 + 0x270000 0x1000 + 0x271000 0x40>; + interrupts = <0 20 0>, <0 21 0>, <0 22 0>; + clocks = <&clock 28>, <&clock 27>; + clock-names = "pcie", "pcie_bus"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x00000800 0 0x40000000 0x40000000 0 0x00001000 /* configuration space */ + 0x81000000 0 0 0x40001000 0 0x00010000 /* downstream I/O */ + 0x82000000 0 0x40011000 0x40011000 0 0x1ffef000>; /* non-prefetchable memory */ + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>; + num-lanes = <4>; + }; + + pcie@2a0000 { + compatible = "samsung,exynos5440-pcie", "snps,dw-pcie"; + reg = <0x2a0000 0x1000 + 0x272000 0x1000 + 0x271040 0x40>; + interrupts = <0 23 0>, <0 24 0>, <0 25 0>; + clocks = <&clock 29>, <&clock 27>; + clock-names = "pcie", "pcie_bus"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x00000800 0 0x60000000 0x60000000 0 0x00001000 /* configuration space */ + 0x81000000 0 0 0x60001000 0 0x00010000 /* downstream I/O */ + 0x82000000 0 0x60011000 0x60011000 0 0x1ffef000>; /* non-prefetchable memory */ + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; + num-lanes = <4>; + }; + +Board specific DT Entry: + + pcie@290000 { + reset-gpio = <&pin_ctrl 5 0>; + }; + + pcie@2a0000 { + reset-gpio = <&pin_ctrl 22 0>; + }; diff --git a/Documentation/devicetree/bindings/video/exynos_dp.txt b/Documentation/devicetree/bindings/video/exynos_dp.txt index 57ccdde02c3a..53dbccfa80ca 100644 --- a/Documentation/devicetree/bindings/video/exynos_dp.txt +++ b/Documentation/devicetree/bindings/video/exynos_dp.txt @@ -62,6 +62,10 @@ Optional properties for dp-controller: -hsync-active-high: HSYNC polarity configuration. High if defined, Low if not defined + -samsung,hpd-gpio: + Hotplug detect GPIO. + Indicates which GPIO should be used for hotplug + detection Example: diff --git a/Documentation/devicetree/bindings/video/exynos_hdmi.txt b/Documentation/devicetree/bindings/video/exynos_hdmi.txt index f9187a259259..1fd8cf9cbfac 100644 --- a/Documentation/devicetree/bindings/video/exynos_hdmi.txt +++ b/Documentation/devicetree/bindings/video/exynos_hdmi.txt @@ -5,6 +5,7 @@ Required properties: 1) "samsung,exynos5-hdmi" 2) "samsung,exynos4210-hdmi" 3) "samsung,exynos4212-hdmi" + 4) "samsung,exynos5420-hdmi" - reg: physical base address of the hdmi and length of memory mapped region. - interrupts: interrupt number to the cpu. @@ -27,6 +28,7 @@ Required properties: "hdmi", "sclk_hdmi", "sclk_pixel", "sclk_hdmiphy" and "mout_hdmi". - ddc: phandle to the hdmi ddc node - phy: phandle to the hdmi phy node +- samsung,syscon-phandle: phandle for system controller node for PMU. Example: @@ -37,4 +39,5 @@ Example: hpd-gpio = <&gpx3 7 1>; ddc = <&hdmi_ddc_node>; phy = <&hdmi_phy_node>; + samsung,syscon-phandle = <&pmu_system_controller>; }; diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index 89472558011e..1525e30483fd 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -318,3 +318,8 @@ GPIO devm_gpiod_get_optional() devm_gpiod_get_index_optional() devm_gpiod_put() + +MDIO + devm_mdiobus_alloc() + devm_mdiobus_alloc_size() + devm_mdiobus_free() diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index eba790134253..b18dd1779029 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -196,8 +196,7 @@ prototypes: void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - int (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); + int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); int (*migratepage)(struct address_space *, struct page *, struct page *); @@ -431,6 +430,8 @@ prototypes: ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); + ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iterate) (struct file *, struct dir_context *); unsigned int (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 617f6d70c077..a1d0d7a30165 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -589,8 +589,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, int); void (*freepage)(struct page *); - ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); + ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); struct page* (*get_xip_page)(struct address_space *, sector_t, int); /* migrate the contents of a page to the specified target */ @@ -807,6 +806,8 @@ struct file_operations { ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); + ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iterate) (struct file *, struct dir_context *); unsigned int (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); @@ -837,11 +838,15 @@ otherwise noted. read: called by read(2) and related system calls - aio_read: called by io_submit(2) and other asynchronous I/O operations + aio_read: vectored, possibly asynchronous read + + read_iter: possibly asynchronous read with iov_iter as destination write: called by write(2) and related system calls - aio_write: called by io_submit(2) and other asynchronous I/O operations + aio_write: vectored, possibly asynchronous write + + write_iter: possibly asynchronous write with iov_iter as source iterate: called when the VFS needs to read the directory contents diff --git a/Documentation/hwmon/shtc1 b/Documentation/hwmon/shtc1 new file mode 100644 index 000000000000..6b1e05458f0f --- /dev/null +++ b/Documentation/hwmon/shtc1 @@ -0,0 +1,43 @@ +Kernel driver shtc1 +=================== + +Supported chips: + * Sensirion SHTC1 + Prefix: 'shtc1' + Addresses scanned: none + Datasheet: http://www.sensirion.com/file/datasheet_shtc1 + + * Sensirion SHTW1 + Prefix: 'shtw1' + Addresses scanned: none + Datasheet: Not publicly available + +Author: + Johannes Winkelmann + +Description +----------- + +This driver implements support for the Sensirion SHTC1 chip, a humidity and +temperature sensor. Temperature is measured in degrees celsius, relative +humidity is expressed as a percentage. Driver can be used as well for SHTW1 +chip, which has the same electrical interface. + +The device communicates with the I2C protocol. All sensors are set to I2C +address 0x70. See Documentation/i2c/instantiating-devices for methods to +instantiate the device. + +There are two options configurable by means of shtc1_platform_data: +1. blocking (pull the I2C clock line down while performing the measurement) or + non-blocking mode. Blocking mode will guarantee the fastest result but + the I2C bus will be busy during that time. By default, non-blocking mode + is used. Make sure clock-stretching works properly on your device if you + want to use blocking mode. +2. high or low accuracy. High accuracy is used by default and using it is + strongly recommended. + +sysfs-Interface +--------------- + +temp1_input - temperature input +humidity1_input - humidity input diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt index 69372fb98cf8..3fb39e0116b4 100644 --- a/Documentation/kbuild/modules.txt +++ b/Documentation/kbuild/modules.txt @@ -470,7 +470,7 @@ build. Sometimes, an external module uses exported symbols from another external module. kbuild needs to have full knowledge of - all symbols to avoid spliitting out warnings about undefined + all symbols to avoid spitting out warnings about undefined symbols. Three solutions exist for this situation. NOTE: The method with a top-level kbuild file is recommended diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index b9f67781c577..6eaa9cdb7094 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1,27 +1,37 @@ Kernel Parameters ~~~~~~~~~~~~~~~~~ -The following is a consolidated list of the kernel parameters as implemented -(mostly) by the __setup() macro and sorted into English Dictionary order -(defined as ignoring all punctuation and sorting digits before letters in a -case insensitive manner), and with descriptions where known. +The following is a consolidated list of the kernel parameters as +implemented by the __setup(), core_param() and module_param() macros +and sorted into English Dictionary order (defined as ignoring all +punctuation and sorting digits before letters in a case insensitive +manner), and with descriptions where known. -Module parameters for loadable modules are specified only as the -parameter name with optional '=' and value as appropriate, such as: +The kernel parses parameters from the kernel command line up to "--"; +if it doesn't recognize a parameter and it doesn't contain a '.', the +parameter gets passed to init: parameters with '=' go into init's +environment, others are passed as command line arguments to init. +Everything after "--" is passed as an argument to init. - modprobe usbcore blinkenlights=1 +Module parameters can be specified in two ways: via the kernel command +line with a module name prefix, or via modprobe, e.g.: -Module parameters for modules that are built into the kernel image -are specified on the kernel command line with the module name plus -'.' plus parameter name, with '=' and value if appropriate, such as: + (kernel command line) usbcore.blinkenlights=1 + (modprobe command line) modprobe usbcore blinkenlights=1 - usbcore.blinkenlights=1 +Parameters for modules which are built into the kernel need to be +specified on the kernel command line. modprobe looks through the +kernel command line (/proc/cmdline) and collects module parameters +when it loads a module, so the kernel command line can be used for +loadable modules too. Hyphens (dashes) and underscores are equivalent in parameter names, so log_buf_len=1M print-fatal-signals=1 can also be entered as log-buf-len=1M print_fatal_signals=1 +Double-quotes can be used to protect spaces in values, e.g.: + param="spaces in here" This document may not be entirely up to date and comprehensive. The command "modinfo -p ${modulename}" shows a current list of all parameters of a loadable diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 0cfb00fd86ff..4bbeca8483ed 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -22,8 +22,9 @@ Appendix B: The kprobes sysctl interface Kprobes enables you to dynamically break into any kernel routine and collect debugging and performance information non-disruptively. You -can trap at almost any kernel code address, specifying a handler +can trap at almost any kernel code address(*), specifying a handler routine to be invoked when the breakpoint is hit. +(*: some parts of the kernel code can not be trapped, see 1.5 Blacklist) There are currently three types of probes: kprobes, jprobes, and kretprobes (also called return probes). A kprobe can be inserted @@ -273,6 +274,19 @@ using one of the following techniques: or - Execute 'sysctl -w debug.kprobes_optimization=n' +1.5 Blacklist + +Kprobes can probe most of the kernel except itself. This means +that there are some functions where kprobes cannot probe. Probing +(trapping) such functions can cause a recursive trap (e.g. double +fault) or the nested probe handler may never be called. +Kprobes manages such functions as a blacklist. +If you want to add a function into the blacklist, you just need +to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro +to specify a blacklisted function. +Kprobes checks the given probe address against the blacklist and +rejects registering it, if the given address is in the blacklist. + 2. Architectures Supported Kprobes, jprobes, and return probes are implemented on the following diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt index 1dfe62c3641d..ee231ed09ec6 100644 --- a/Documentation/mutex-design.txt +++ b/Documentation/mutex-design.txt @@ -1,139 +1,157 @@ Generic Mutex Subsystem started by Ingo Molnar +updated by Davidlohr Bueso - "Why on earth do we need a new mutex subsystem, and what's wrong - with semaphores?" +What are mutexes? +----------------- -firstly, there's nothing wrong with semaphores. But if the simpler -mutex semantics are sufficient for your code, then there are a couple -of advantages of mutexes: +In the Linux kernel, mutexes refer to a particular locking primitive +that enforces serialization on shared memory systems, and not only to +the generic term referring to 'mutual exclusion' found in academia +or similar theoretical text books. Mutexes are sleeping locks which +behave similarly to binary semaphores, and were introduced in 2006[1] +as an alternative to these. This new data structure provided a number +of advantages, including simpler interfaces, and at that time smaller +code (see Disadvantages). - - 'struct mutex' is smaller on most architectures: E.g. on x86, - 'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes. - A smaller structure size means less RAM footprint, and better - CPU-cache utilization. +[1] http://lwn.net/Articles/164802/ - - tighter code. On x86 i get the following .text sizes when - switching all mutex-alike semaphores in the kernel to the mutex - subsystem: +Implementation +-------------- - text data bss dec hex filename - 3280380 868188 396860 4545428 455b94 vmlinux-semaphore - 3255329 865296 396732 4517357 44eded vmlinux-mutex +Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h +and implemented in kernel/locking/mutex.c. These locks use a three +state atomic counter (->count) to represent the different possible +transitions that can occur during the lifetime of a lock: - that's 25051 bytes of code saved, or a 0.76% win - off the hottest - codepaths of the kernel. (The .data savings are 2892 bytes, or 0.33%) - Smaller code means better icache footprint, which is one of the - major optimization goals in the Linux kernel currently. + 1: unlocked + 0: locked, no waiters + negative: locked, with potential waiters - - the mutex subsystem is slightly faster and has better scalability for - contended workloads. On an 8-way x86 system, running a mutex-based - kernel and testing creat+unlink+close (of separate, per-task files) - in /tmp with 16 parallel tasks, the average number of ops/sec is: +In its most basic form it also includes a wait-queue and a spinlock +that serializes access to it. CONFIG_SMP systems can also include +a pointer to the lock task owner (->owner) as well as a spinner MCS +lock (->osq), both described below in (ii). - Semaphores: Mutexes: +When acquiring a mutex, there are three possible paths that can be +taken, depending on the state of the lock: - $ ./test-mutex V 16 10 $ ./test-mutex V 16 10 - 8 CPUs, running 16 tasks. 8 CPUs, running 16 tasks. - checking VFS performance. checking VFS performance. - avg loops/sec: 34713 avg loops/sec: 84153 - CPU utilization: 63% CPU utilization: 22% +(i) fastpath: tries to atomically acquire the lock by decrementing the + counter. If it was already taken by another task it goes to the next + possible path. This logic is architecture specific. On x86-64, the + locking fastpath is 2 instructions: - i.e. in this workload, the mutex based kernel was 2.4 times faster - than the semaphore based kernel, _and_ it also had 2.8 times less CPU - utilization. (In terms of 'ops per CPU cycle', the semaphore kernel - performed 551 ops/sec per 1% of CPU time used, while the mutex kernel - performed 3825 ops/sec per 1% of CPU time used - it was 6.9 times - more efficient.) - - the scalability difference is visible even on a 2-way P4 HT box: - - Semaphores: Mutexes: - - $ ./test-mutex V 16 10 $ ./test-mutex V 16 10 - 4 CPUs, running 16 tasks. 8 CPUs, running 16 tasks. - checking VFS performance. checking VFS performance. - avg loops/sec: 127659 avg loops/sec: 181082 - CPU utilization: 100% CPU utilization: 34% - - (the straight performance advantage of mutexes is 41%, the per-cycle - efficiency of mutexes is 4.1 times better.) - - - there are no fastpath tradeoffs, the mutex fastpath is just as tight - as the semaphore fastpath. On x86, the locking fastpath is 2 - instructions: - - c0377ccb : - c0377ccb: f0 ff 08 lock decl (%eax) - c0377cce: 78 0e js c0377cde <.text..lock.mutex> - c0377cd0: c3 ret + 0000000000000e10 : + e21: f0 ff 0b lock decl (%rbx) + e24: 79 08 jns e2e the unlocking fastpath is equally tight: - c0377cd1 : - c0377cd1: f0 ff 00 lock incl (%eax) - c0377cd4: 7e 0f jle c0377ce5 <.text..lock.mutex+0x7> - c0377cd6: c3 ret + 0000000000000bc0 : + bc8: f0 ff 07 lock incl (%rdi) + bcb: 7f 0a jg bd7 - - 'struct mutex' semantics are well-defined and are enforced if - CONFIG_DEBUG_MUTEXES is turned on. Semaphores on the other hand have - virtually no debugging code or instrumentation. The mutex subsystem - checks and enforces the following rules: - * - only one task can hold the mutex at a time - * - only the owner can unlock the mutex - * - multiple unlocks are not permitted - * - recursive locking is not permitted - * - a mutex object must be initialized via the API - * - a mutex object must not be initialized via memset or copying - * - task may not exit with mutex held - * - memory areas where held locks reside must not be freed - * - held mutexes must not be reinitialized - * - mutexes may not be used in hardware or software interrupt - * contexts such as tasklets and timers +(ii) midpath: aka optimistic spinning, tries to spin for acquisition + while the lock owner is running and there are no other tasks ready + to run that have higher priority (need_resched). The rationale is + that if the lock owner is running, it is likely to release the lock + soon. The mutex spinners are queued up using MCS lock so that only + one spinner can compete for the mutex. - furthermore, there are also convenience features in the debugging - code: + The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spinlock + with the desirable properties of being fair and with each cpu trying + to acquire the lock spinning on a local variable. It avoids expensive + cacheline bouncing that common test-and-set spinlock implementations + incur. An MCS-like lock is specially tailored for optimistic spinning + for sleeping lock implementation. An important feature of the customized + MCS lock is that it has the extra property that spinners are able to exit + the MCS spinlock queue when they need to reschedule. This further helps + avoid situations where MCS spinners that need to reschedule would continue + waiting to spin on mutex owner, only to go directly to slowpath upon + obtaining the MCS lock. - * - uses symbolic names of mutexes, whenever they are printed in debug output - * - point-of-acquire tracking, symbolic lookup of function names - * - list of all locks held in the system, printout of them - * - owner tracking - * - detects self-recursing locks and prints out all relevant info - * - detects multi-task circular deadlocks and prints out all affected - * locks and tasks (and only those tasks) + +(iii) slowpath: last resort, if the lock is still unable to be acquired, + the task is added to the wait-queue and sleeps until woken up by the + unlock path. Under normal circumstances it blocks as TASK_UNINTERRUPTIBLE. + +While formally kernel mutexes are sleepable locks, it is path (ii) that +makes them more practically a hybrid type. By simply not interrupting a +task and busy-waiting for a few cycles instead of immediately sleeping, +the performance of this lock has been seen to significantly improve a +number of workloads. Note that this technique is also used for rw-semaphores. + +Semantics +--------- + +The mutex subsystem checks and enforces the following rules: + + - Only one task can hold the mutex at a time. + - Only the owner can unlock the mutex. + - Multiple unlocks are not permitted. + - Recursive locking/unlocking is not permitted. + - A mutex must only be initialized via the API (see below). + - A task may not exit with a mutex held. + - Memory areas where held locks reside must not be freed. + - Held mutexes must not be reinitialized. + - Mutexes may not be used in hardware or software interrupt + contexts such as tasklets and timers. + +These semantics are fully enforced when CONFIG DEBUG_MUTEXES is enabled. +In addition, the mutex debugging code also implements a number of other +features that make lock debugging easier and faster: + + - Uses symbolic names of mutexes, whenever they are printed + in debug output. + - Point-of-acquire tracking, symbolic lookup of function names, + list of all locks held in the system, printout of them. + - Owner tracking. + - Detects self-recursing locks and prints out all relevant info. + - Detects multi-task circular deadlocks and prints out all affected + locks and tasks (and only those tasks). + + +Interfaces +---------- +Statically define the mutex: + DEFINE_MUTEX(name); + +Dynamically initialize the mutex: + mutex_init(mutex); + +Acquire the mutex, uninterruptible: + void mutex_lock(struct mutex *lock); + void mutex_lock_nested(struct mutex *lock, unsigned int subclass); + int mutex_trylock(struct mutex *lock); + +Acquire the mutex, interruptible: + int mutex_lock_interruptible_nested(struct mutex *lock, + unsigned int subclass); + int mutex_lock_interruptible(struct mutex *lock); + +Acquire the mutex, interruptible, if dec to 0: + int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + +Unlock the mutex: + void mutex_unlock(struct mutex *lock); + +Test if the mutex is taken: + int mutex_is_locked(struct mutex *lock); Disadvantages ------------- -The stricter mutex API means you cannot use mutexes the same way you -can use semaphores: e.g. they cannot be used from an interrupt context, -nor can they be unlocked from a different context that which acquired -it. [ I'm not aware of any other (e.g. performance) disadvantages from -using mutexes at the moment, please let me know if you find any. ] +Unlike its original design and purpose, 'struct mutex' is larger than +most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice +as large as 'struct semaphore' (24 bytes) and 8 bytes shy of the +'struct rw_semaphore' variant. Larger structure sizes mean more CPU +cache and memory footprint. -Implementation of mutexes -------------------------- +When to use mutexes +------------------- -'struct mutex' is the new mutex type, defined in include/linux/mutex.h and -implemented in kernel/locking/mutex.c. It is a counter-based mutex with a -spinlock and a wait-list. The counter has 3 states: 1 for "unlocked", 0 for -"locked" and negative numbers (usually -1) for "locked, potential waiters -queued". - -the APIs of 'struct mutex' have been streamlined: - - DEFINE_MUTEX(name); - - mutex_init(mutex); - - void mutex_lock(struct mutex *lock); - int mutex_lock_interruptible(struct mutex *lock); - int mutex_trylock(struct mutex *lock); - void mutex_unlock(struct mutex *lock); - int mutex_is_locked(struct mutex *lock); - void mutex_lock_nested(struct mutex *lock, unsigned int subclass); - int mutex_lock_interruptible_nested(struct mutex *lock, - unsigned int subclass); - int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +Unless the strict semantics of mutexes are unsuitable and/or the critical +region prevents the lock from being shared, always prefer them to any other +locking primitive. diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index a383c00392d0..9c723ecd0025 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -585,13 +585,19 @@ mode balance-tlb or 5 Adaptive transmit load balancing: channel bonding that - does not require any special switch support. The - outgoing traffic is distributed according to the - current load (computed relative to the speed) on each - slave. Incoming traffic is received by the current - slave. If the receiving slave fails, another slave - takes over the MAC address of the failed receiving - slave. + does not require any special switch support. + + In tlb_dynamic_lb=1 mode; the outgoing traffic is + distributed according to the current load (computed + relative to the speed) on each slave. + + In tlb_dynamic_lb=0 mode; the load balancing based on + current load is disabled and the load is distributed + only using the hash distribution. + + Incoming traffic is received by the current slave. + If the receiving slave fails, another slave takes over + the MAC address of the failed receiving slave. Prerequisite: @@ -736,6 +742,28 @@ primary_reselect This option was added for bonding version 3.6.0. +tlb_dynamic_lb + + Specifies if dynamic shuffling of flows is enabled in tlb + mode. The value has no effect on any other modes. + + The default behavior of tlb mode is to shuffle active flows across + slaves based on the load in that interval. This gives nice lb + characteristics but can cause packet reordering. If re-ordering is + a concern use this variable to disable flow shuffling and rely on + load balancing provided solely by the hash distribution. + xmit-hash-policy can be used to select the appropriate hashing for + the setup. + + The sysfs entry can be used to change the setting per bond device + and the initial value is derived from the module parameter. The + sysfs entry is allowed to be changed only if the bond device is + down. + + The default value is "1" that enables flow shuffling while value "0" + disables it. This option was added in bonding driver 3.7.1 + + updelay Specifies the time, in milliseconds, to wait before enabling a @@ -769,7 +797,7 @@ use_carrier xmit_hash_policy Selects the transmit hash policy to use for slave selection in - balance-xor and 802.3ad modes. Possible values are: + balance-xor, 802.3ad, and tlb modes. Possible values are: layer2 diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index 4f7ae5261364..2236d6dcb7da 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -469,6 +469,41 @@ solution for a couple of reasons: having this 'send only' use-case we may remove the receive list in the Kernel to save a little (really a very little!) CPU usage. + 4.1.1.1 CAN filter usage optimisation + + The CAN filters are processed in per-device filter lists at CAN frame + reception time. To reduce the number of checks that need to be performed + while walking through the filter lists the CAN core provides an optimized + filter handling when the filter subscription focusses on a single CAN ID. + + For the possible 2048 SFF CAN identifiers the identifier is used as an index + to access the corresponding subscription list without any further checks. + For the 2^29 possible EFF CAN identifiers a 10 bit XOR folding is used as + hash function to retrieve the EFF table index. + + To benefit from the optimized filters for single CAN identifiers the + CAN_SFF_MASK or CAN_EFF_MASK have to be set into can_filter.mask together + with set CAN_EFF_FLAG and CAN_RTR_FLAG bits. A set CAN_EFF_FLAG bit in the + can_filter.mask makes clear that it matters whether a SFF or EFF CAN ID is + subscribed. E.g. in the example from above + + rfilter[0].can_id = 0x123; + rfilter[0].can_mask = CAN_SFF_MASK; + + both SFF frames with CAN ID 0x123 and EFF frames with 0xXXXXX123 can pass. + + To filter for only 0x123 (SFF) and 0x12345678 (EFF) CAN identifiers the + filter has to be defined in this way to benefit from the optimized filters: + + struct can_filter rfilter[2]; + + rfilter[0].can_id = 0x123; + rfilter[0].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_SFF_MASK); + rfilter[1].can_id = 0x12345678 | CAN_EFF_FLAG; + rfilter[1].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_EFF_MASK); + + setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter)); + 4.1.2 RAW socket option CAN_RAW_ERR_FILTER As described in chapter 3.4 the CAN interface driver can generate so diff --git a/Documentation/networking/cdc_mbim.txt b/Documentation/networking/cdc_mbim.txt new file mode 100644 index 000000000000..a15ea602aa52 --- /dev/null +++ b/Documentation/networking/cdc_mbim.txt @@ -0,0 +1,339 @@ + cdc_mbim - Driver for CDC MBIM Mobile Broadband modems + ======================================================== + +The cdc_mbim driver supports USB devices conforming to the "Universal +Serial Bus Communications Class Subclass Specification for Mobile +Broadband Interface Model" [1], which is a further development of +"Universal Serial Bus Communications Class Subclass Specifications for +Network Control Model Devices" [2] optimized for Mobile Broadband +devices, aka "3G/LTE modems". + + +Command Line Parameters +======================= + +The cdc_mbim driver has no parameters of its own. But the probing +behaviour for NCM 1.0 backwards compatible MBIM functions (an +"NCM/MBIM function" as defined in section 3.2 of [1]) is affected +by a cdc_ncm driver parameter: + +prefer_mbim +----------- +Type: Boolean +Valid Range: N/Y (0-1) +Default Value: Y (MBIM is preferred) + +This parameter sets the system policy for NCM/MBIM functions. Such +functions will be handled by either the cdc_ncm driver or the cdc_mbim +driver depending on the prefer_mbim setting. Setting prefer_mbim=N +makes the cdc_mbim driver ignore these functions and lets the cdc_ncm +driver handle them instead. + +The parameter is writable, and can be changed at any time. A manual +unbind/bind is required to make the change effective for NCM/MBIM +functions bound to the "wrong" driver + + +Basic usage +=========== + +MBIM functions are inactive when unmanaged. The cdc_mbim driver only +provides an userspace interface to the MBIM control channel, and will +not participate in the management of the function. This implies that a +userspace MBIM management application always is required to enable a +MBIM function. + +Such userspace applications includes, but are not limited to: + - mbimcli (included with the libmbim [3] library), and + - ModemManager [4] + +Establishing a MBIM IP session reequires at least these actions by the +management application: + - open the control channel + - configure network connection settings + - connect to network + - configure IP interface + +Management application development +---------------------------------- +The driver <-> userspace interfaces are described below. The MBIM +control channel protocol is described in [1]. + + +MBIM control channel userspace ABI +================================== + +/dev/cdc-wdmX character device +------------------------------ +The driver creates a two-way pipe to the MBIM function control channel +using the cdc-wdm driver as a subdriver. The userspace end of the +control channel pipe is a /dev/cdc-wdmX character device. + +The cdc_mbim driver does not process or police messages on the control +channel. The channel is fully delegated to the userspace management +application. It is therefore up to this application to ensure that it +complies with all the control channel requirements in [1]. + +The cdc-wdmX device is created as a child of the MBIM control +interface USB device. The character device associated with a specific +MBIM function can be looked up using sysfs. For example: + + bjorn@nemi:~$ ls /sys/bus/usb/drivers/cdc_mbim/2-4:2.12/usbmisc + cdc-wdm0 + + bjorn@nemi:~$ grep . /sys/bus/usb/drivers/cdc_mbim/2-4:2.12/usbmisc/cdc-wdm0/dev + 180:0 + + +USB configuration descriptors +----------------------------- +The wMaxControlMessage field of the CDC MBIM functional descriptor +limits the maximum control message size. The managament application is +responsible for negotiating a control message size complying with the +requirements in section 9.3.1 of [1], taking this descriptor field +into consideration. + +The userspace application can access the CDC MBIM functional +descriptor of a MBIM function using either of the two USB +configuration descriptor kernel interfaces described in [6] or [7]. + +See also the ioctl documentation below. + + +Fragmentation +------------- +The userspace application is responsible for all control message +fragmentation and defragmentaion, as described in section 9.5 of [1]. + + +/dev/cdc-wdmX write() +--------------------- +The MBIM control messages from the management application *must not* +exceed the negotiated control message size. + + +/dev/cdc-wdmX read() +-------------------- +The management application *must* accept control messages of up the +negotiated control message size. + + +/dev/cdc-wdmX ioctl() +-------------------- +IOCTL_WDM_MAX_COMMAND: Get Maximum Command Size +This ioctl returns the wMaxControlMessage field of the CDC MBIM +functional descriptor for MBIM devices. This is intended as a +convenience, eliminating the need to parse the USB descriptors from +userspace. + + #include + #include + #include + #include + #include + int main() + { + __u16 max; + int fd = open("/dev/cdc-wdm0", O_RDWR); + if (!ioctl(fd, IOCTL_WDM_MAX_COMMAND, &max)) + printf("wMaxControlMessage is %d\n", max); + } + + +Custom device services +---------------------- +The MBIM specification allows vendors to freely define additional +services. This is fully supported by the cdc_mbim driver. + +Support for new MBIM services, including vendor specified services, is +implemented entirely in userspace, like the rest of the MBIM control +protocol + +New services should be registered in the MBIM Registry [5]. + + + +MBIM data channel userspace ABI +=============================== + +wwanY network device +-------------------- +The cdc_mbim driver represents the MBIM data channel as a single +network device of the "wwan" type. This network device is initially +mapped to MBIM IP session 0. + + +Multiplexed IP sessions (IPS) +----------------------------- +MBIM allows multiplexing up to 256 IP sessions over a single USB data +channel. The cdc_mbim driver models such IP sessions as 802.1q VLAN +subdevices of the master wwanY device, mapping MBIM IP session Z to +VLAN ID Z for all values of Z greater than 0. + +The device maximum Z is given in the MBIM_DEVICE_CAPS_INFO structure +described in section 10.5.1 of [1]. + +The userspace management application is responsible for adding new +VLAN links prior to establishing MBIM IP sessions where the SessionId +is greater than 0. These links can be added by using the normal VLAN +kernel interfaces, either ioctl or netlink. + +For example, adding a link for a MBIM IP session with SessionId 3: + + ip link add link wwan0 name wwan0.3 type vlan id 3 + +The driver will automatically map the "wwan0.3" network device to MBIM +IP session 3. + + +Device Service Streams (DSS) +---------------------------- +MBIM also allows up to 256 non-IP data streams to be multiplexed over +the same shared USB data channel. The cdc_mbim driver models these +sessions as another set of 802.1q VLAN subdevices of the master wwanY +device, mapping MBIM DSS session A to VLAN ID (256 + A) for all values +of A. + +The device maximum A is given in the MBIM_DEVICE_SERVICES_INFO +structure described in section 10.5.29 of [1]. + +The DSS VLAN subdevices are used as a practical interface between the +shared MBIM data channel and a MBIM DSS aware userspace application. +It is not intended to be presented as-is to an end user. The +assumption is that an userspace application initiating a DSS session +also takes care of the necessary framing of the DSS data, presenting +the stream to the end user in an appropriate way for the stream type. + +The network device ABI requires a dummy ethernet header for every DSS +data frame being transported. The contents of this header is +arbitrary, with the following exceptions: + - TX frames using an IP protocol (0x0800 or 0x86dd) will be dropped + - RX frames will have the protocol field set to ETH_P_802_3 (but will + not be properly formatted 802.3 frames) + - RX frames will have the destination address set to the hardware + address of the master device + +The DSS supporting userspace management application is responsible for +adding the dummy ethernet header on TX and stripping it on RX. + +This is a simple example using tools commonly available, exporting +DssSessionId 5 as a pty character device pointed to by a /dev/nmea +symlink: + + ip link add link wwan0 name wwan0.dss5 type vlan id 261 + ip link set dev wwan0.dss5 up + socat INTERFACE:wwan0.dss5,type=2 PTY:,echo=0,link=/dev/nmea + +This is only an example, most suitable for testing out a DSS +service. Userspace applications supporting specific MBIM DSS services +are expected to use the tools and programming interfaces required by +that service. + +Note that adding VLAN links for DSS sessions is entirely optional. A +management application may instead choose to bind a packet socket +directly to the master network device, using the received VLAN tags to +map frames to the correct DSS session and adding 18 byte VLAN ethernet +headers with the appropriate tag on TX. In this case using a socket +filter is recommended, matching only the DSS VLAN subset. This avoid +unnecessary copying of unrelated IP session data to userspace. For +example: + + static struct sock_filter dssfilter[] = { + /* use special negative offsets to get VLAN tag */ + BPF_STMT(BPF_LD|BPF_B|BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, 1, 0, 6), /* true */ + + /* verify DSS VLAN range */ + BPF_STMT(BPF_LD|BPF_H|BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG), + BPF_JUMP(BPF_JMP|BPF_JGE|BPF_K, 256, 0, 4), /* 256 is first DSS VLAN */ + BPF_JUMP(BPF_JMP|BPF_JGE|BPF_K, 512, 3, 0), /* 511 is last DSS VLAN */ + + /* verify ethertype */ + BPF_STMT(BPF_LD|BPF_H|BPF_ABS, 2 * ETH_ALEN), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, ETH_P_802_3, 0, 1), + + BPF_STMT(BPF_RET|BPF_K, (u_int)-1), /* accept */ + BPF_STMT(BPF_RET|BPF_K, 0), /* ignore */ + }; + + + +Tagged IP session 0 VLAN +------------------------ +As described above, MBIM IP session 0 is treated as special by the +driver. It is initially mapped to untagged frames on the wwanY +network device. + +This mapping implies a few restrictions on multiplexed IPS and DSS +sessions, which may not always be practical: + - no IPS or DSS session can use a frame size greater than the MTU on + IP session 0 + - no IPS or DSS session can be in the up state unless the network + device representing IP session 0 also is up + +These problems can be avoided by optionally making the driver map IP +session 0 to a VLAN subdevice, similar to all other IP sessions. This +behaviour is triggered by adding a VLAN link for the magic VLAN ID +4094. The driver will then immediately start mapping MBIM IP session +0 to this VLAN, and will drop untagged frames on the master wwanY +device. + +Tip: It might be less confusing to the end user to name this VLAN +subdevice after the MBIM SessionID instead of the VLAN ID. For +example: + + ip link add link wwan0 name wwan0.0 type vlan id 4094 + + +VLAN mapping +------------ + +Summarizing the cdc_mbim driver mapping described above, we have this +relationship between VLAN tags on the wwanY network device and MBIM +sessions on the shared USB data channel: + + VLAN ID MBIM type MBIM SessionID Notes + --------------------------------------------------------- + untagged IPS 0 a) + 1 - 255 IPS 1 - 255 + 256 - 511 DSS 0 - 255 + 512 - 4093 b) + 4094 IPS 0 c) + + a) if no VLAN ID 4094 link exists, else dropped + b) unsupported VLAN range, unconditionally dropped + c) if a VLAN ID 4094 link exists, else dropped + + + + +References +========== + +[1] USB Implementers Forum, Inc. - "Universal Serial Bus + Communications Class Subclass Specification for Mobile Broadband + Interface Model", Revision 1.0 (Errata 1), May 1, 2013 + - http://www.usb.org/developers/docs/devclass_docs/ + +[2] USB Implementers Forum, Inc. - "Universal Serial Bus + Communications Class Subclass Specifications for Network Control + Model Devices", Revision 1.0 (Errata 1), November 24, 2010 + - http://www.usb.org/developers/docs/devclass_docs/ + +[3] libmbim - "a glib-based library for talking to WWAN modems and + devices which speak the Mobile Interface Broadband Model (MBIM) + protocol" + - http://www.freedesktop.org/wiki/Software/libmbim/ + +[4] ModemManager - "a DBus-activated daemon which controls mobile + broadband (2G/3G/4G) devices and connections" + - http://www.freedesktop.org/wiki/Software/ModemManager/ + +[5] "MBIM (Mobile Broadband Interface Model) Registry" + - http://compliance.usb.org/mbim/ + +[6] "/proc/bus/usb filesystem output" + - Documentation/usb/proc_usb_info.txt + +[7] "/sys/bus/usb/devices/.../descriptors" + - Documentation/ABI/stable/sysfs-bus-usb diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index e3ba753cb714..ee78eba78a9d 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -281,6 +281,7 @@ Possible BPF extensions are shown in the following table: cpu raw_smp_processor_id() vlan_tci vlan_tx_tag_get(skb) vlan_pr vlan_tx_tag_present(skb) + rand prandom_u32() These extensions can also be prefixed with '#'. Examples for low-level BPF: @@ -308,6 +309,18 @@ Examples for low-level BPF: ret #-1 drop: ret #0 +** icmp random packet sampling, 1 in 4 + ldh [12] + jne #0x800, drop + ldb [23] + jneq #1, drop + # get a random uint32 number + ld rand + mod #4 + jneq #1, drop + ret #-1 + drop: ret #0 + ** SECCOMP filter example: ld [4] /* offsetof(struct seccomp_data, arch) */ @@ -548,42 +561,43 @@ toolchain for developing and testing the kernel's JIT compiler. BPF kernel internals -------------------- -Internally, for the kernel interpreter, a different BPF instruction set +Internally, for the kernel interpreter, a different instruction set format with similar underlying principles from BPF described in previous paragraphs is being used. However, the instruction set format is modelled closer to the underlying architecture to mimic native instruction sets, so -that a better performance can be achieved (more details later). +that a better performance can be achieved (more details later). This new +ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF which +originates from [e]xtended BPF is not the same as BPF extensions! While +eBPF is an ISA, BPF extensions date back to classic BPF's 'overloading' +of BPF_LD | BPF_{B,H,W} | BPF_ABS instruction.) It is designed to be JITed with one to one mapping, which can also open up -the possibility for GCC/LLVM compilers to generate optimized BPF code through -a BPF backend that performs almost as fast as natively compiled code. +the possibility for GCC/LLVM compilers to generate optimized eBPF code through +an eBPF backend that performs almost as fast as natively compiled code. The new instruction set was originally designed with the possible goal in -mind to write programs in "restricted C" and compile into BPF with a optional +mind to write programs in "restricted C" and compile into eBPF with a optional GCC/LLVM backend, so that it can just-in-time map to modern 64-bit CPUs with -minimal performance overhead over two steps, that is, C -> BPF -> native code. +minimal performance overhead over two steps, that is, C -> eBPF -> native code. Currently, the new format is being used for running user BPF programs, which includes seccomp BPF, classic socket filters, cls_bpf traffic classifier, team driver's classifier for its load-balancing mode, netfilter's xt_bpf extension, PTP dissector/classifier, and much more. They are all internally converted by the kernel into the new instruction set representation and run -in the extended interpreter. For in-kernel handlers, this all works -transparently by using sk_unattached_filter_create() for setting up the -filter, resp. sk_unattached_filter_destroy() for destroying it. The macro -SK_RUN_FILTER(filter, ctx) transparently invokes the right BPF function to -run the filter. 'filter' is a pointer to struct sk_filter that we got from -sk_unattached_filter_create(), and 'ctx' the given context (e.g. skb pointer). -All constraints and restrictions from sk_chk_filter() apply before a -conversion to the new layout is being done behind the scenes! +in the eBPF interpreter. For in-kernel handlers, this all works transparently +by using sk_unattached_filter_create() for setting up the filter, resp. +sk_unattached_filter_destroy() for destroying it. The macro +SK_RUN_FILTER(filter, ctx) transparently invokes eBPF interpreter or JITed +code to run the filter. 'filter' is a pointer to struct sk_filter that we +got from sk_unattached_filter_create(), and 'ctx' the given context (e.g. +skb pointer). All constraints and restrictions from sk_chk_filter() apply +before a conversion to the new layout is being done behind the scenes! -Currently, for JITing, the user BPF format is being used and current BPF JIT -compilers reused whenever possible. In other words, we do not (yet!) perform -a JIT compilation in the new layout, however, future work will successively -migrate traditional JIT compilers into the new instruction format as well, so -that they will profit from the very same benefits. Thus, when speaking about -JIT in the following, a JIT compiler (TBD) for the new instruction format is -meant in this context. +Currently, the classic BPF format is being used for JITing on most of the +architectures. Only x86-64 performs JIT compilation from eBPF instruction set, +however, future work will migrate other JIT compilers as well, so that they +will profit from the very same benefits. Some core changes of the new internal format: @@ -592,35 +606,35 @@ Some core changes of the new internal format: The old format had two registers A and X, and a hidden frame pointer. The new layout extends this to be 10 internal registers and a read-only frame pointer. Since 64-bit CPUs are passing arguments to functions via registers - the number of args from BPF program to in-kernel function is restricted + the number of args from eBPF program to in-kernel function is restricted to 5 and one register is used to accept return value from an in-kernel function. Natively, x86_64 passes first 6 arguments in registers, aarch64/ sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers. - Therefore, BPF calling convention is defined as: + Therefore, eBPF calling convention is defined as: - * R0 - return value from in-kernel function - * R1 - R5 - arguments from BPF program to in-kernel function + * R0 - return value from in-kernel function, and exit value for eBPF program + * R1 - R5 - arguments from eBPF program to in-kernel function * R6 - R9 - callee saved registers that in-kernel function will preserve * R10 - read-only frame pointer to access stack - Thus, all BPF registers map one to one to HW registers on x86_64, aarch64, - etc, and BPF calling convention maps directly to ABIs used by the kernel on + Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64, + etc, and eBPF calling convention maps directly to ABIs used by the kernel on 64-bit architectures. On 32-bit architectures JIT may map programs that use only 32-bit arithmetic and may let more complex programs to be interpreted. - R0 - R5 are scratch registers and BPF program needs spill/fill them if - necessary across calls. Note that there is only one BPF program (== one BPF - main routine) and it cannot call other BPF functions, it can only call - predefined in-kernel functions, though. + R0 - R5 are scratch registers and eBPF program needs spill/fill them if + necessary across calls. Note that there is only one eBPF program (== one + eBPF main routine) and it cannot call other eBPF functions, it can only + call predefined in-kernel functions, though. - Register width increases from 32-bit to 64-bit: Still, the semantics of the original 32-bit ALU operations are preserved - via 32-bit subregisters. All BPF registers are 64-bit with 32-bit lower + via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower subregisters that zero-extend into 64-bit if they are being written to. That behavior maps directly to x86_64 and arm64 subregister definition, but makes other JITs more difficult. @@ -631,8 +645,8 @@ Some core changes of the new internal format: Operation is 64-bit, because on 64-bit architectures, pointers are also 64-bit wide, and we want to pass 64-bit values in/out of kernel functions, - so 32-bit BPF registers would otherwise require to define register-pair - ABI, thus, there won't be able to use a direct BPF register to HW register + so 32-bit eBPF registers would otherwise require to define register-pair + ABI, thus, there won't be able to use a direct eBPF register to HW register mapping and JIT would need to do combine/split/move operations for every register in and out of the function, which is complex, bug prone and slow. Another reason is the use of atomic 64-bit counters. @@ -646,14 +660,145 @@ Some core changes of the new internal format: - Introduces bpf_call insn and register passing convention for zero overhead calls from/to other kernel functions: - After a kernel function call, R1 - R5 are reset to unreadable and R0 has a - return type of the function. Since R6 - R9 are callee saved, their state is - preserved across the call. + Before an in-kernel function call, the internal BPF program needs to + place function arguments into R1 to R5 registers to satisfy calling + convention, then the interpreter will take them from registers and pass + to in-kernel function. If R1 - R5 registers are mapped to CPU registers + that are used for argument passing on given architecture, the JIT compiler + doesn't need to emit extra moves. Function arguments will be in the correct + registers and BPF_CALL instruction will be JITed as single 'call' HW + instruction. This calling convention was picked to cover common call + situations without performance penalty. -Also in the new design, BPF is limited to 4096 insns, which means that any + After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has + a return value of the function. Since R6 - R9 are callee saved, their state + is preserved across the call. + + For example, consider three C functions: + + u64 f1() { return (*_f2)(1); } + u64 f2(u64 a) { return f3(a + 1, a); } + u64 f3(u64 a, u64 b) { return a - b; } + + GCC can compile f1, f3 into x86_64: + + f1: + movl $1, %edi + movq _f2(%rip), %rax + jmp *%rax + f3: + movq %rdi, %rax + subq %rsi, %rax + ret + + Function f2 in eBPF may look like: + + f2: + bpf_mov R2, R1 + bpf_add R1, 1 + bpf_call f3 + bpf_exit + + If f2 is JITed and the pointer stored to '_f2'. The calls f1 -> f2 -> f3 and + returns will be seamless. Without JIT, __sk_run_filter() interpreter needs to + be used to call into f2. + + For practical reasons all eBPF programs have only one argument 'ctx' which is + already placed into R1 (e.g. on __sk_run_filter() startup) and the programs + can call kernel functions with up to 5 arguments. Calls with 6 or more arguments + are currently not supported, but these restrictions can be lifted if necessary + in the future. + + On 64-bit architectures all register map to HW registers one to one. For + example, x86_64 JIT compiler can map them as ... + + R0 - rax + R1 - rdi + R2 - rsi + R3 - rdx + R4 - rcx + R5 - r8 + R6 - rbx + R7 - r13 + R8 - r14 + R9 - r15 + R10 - rbp + + ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing + and rbx, r12 - r15 are callee saved. + + Then the following internal BPF pseudo-program: + + bpf_mov R6, R1 /* save ctx */ + bpf_mov R2, 2 + bpf_mov R3, 3 + bpf_mov R4, 4 + bpf_mov R5, 5 + bpf_call foo + bpf_mov R7, R0 /* save foo() return value */ + bpf_mov R1, R6 /* restore ctx for next call */ + bpf_mov R2, 6 + bpf_mov R3, 7 + bpf_mov R4, 8 + bpf_mov R5, 9 + bpf_call bar + bpf_add R0, R7 + bpf_exit + + After JIT to x86_64 may look like: + + push %rbp + mov %rsp,%rbp + sub $0x228,%rsp + mov %rbx,-0x228(%rbp) + mov %r13,-0x220(%rbp) + mov %rdi,%rbx + mov $0x2,%esi + mov $0x3,%edx + mov $0x4,%ecx + mov $0x5,%r8d + callq foo + mov %rax,%r13 + mov %rbx,%rdi + mov $0x2,%esi + mov $0x3,%edx + mov $0x4,%ecx + mov $0x5,%r8d + callq bar + add %r13,%rax + mov -0x228(%rbp),%rbx + mov -0x220(%rbp),%r13 + leaveq + retq + + Which is in this example equivalent in C to: + + u64 bpf_filter(u64 ctx) + { + return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9); + } + + In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64 + arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper + registers and place their return value into '%rax' which is R0 in eBPF. + Prologue and epilogue are emitted by JIT and are implicit in the + interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve + them across the calls as defined by calling convention. + + For example the following program is invalid: + + bpf_mov R1, 1 + bpf_call foo + bpf_mov R0, R1 + bpf_exit + + After the call the registers R1-R5 contain junk values and cannot be read. + In the future an eBPF verifier can be used to validate internal BPF programs. + +Also in the new design, eBPF is limited to 4096 insns, which means that any program will terminate quickly and will only call a fixed number of kernel functions. Original BPF and the new format are two operand instructions, -which helps to do one-to-one mapping between BPF insn and x86 insn during JIT. +which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT. The input context pointer for invoking the interpreter function is generic, its content is defined by a specific use case. For seccomp register R1 points @@ -661,7 +806,26 @@ to seccomp_data, for converted BPF filters R1 points to a skb. A program, that is translated internally consists of the following elements: - op:16, jt:8, jf:8, k:32 ==> op:8, a_reg:4, x_reg:4, off:16, imm:32 + op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32 + +So far 87 internal BPF instructions were implemented. 8-bit 'op' opcode field +has room for new instructions. Some of them may use 16/24/32 byte encoding. New +instructions must be multiple of 8 bytes to preserve backward compatibility. + +Internal BPF is a general purpose RISC instruction set. Not every register and +every instruction are used during translation from original BPF to new format. +For example, socket filters are not using 'exclusive add' instruction, but +tracing filters may do to maintain counters of events, for example. Register R9 +is not used by socket filters either, but more complex filters may be running +out of registers and would have to resort to spill/fill to stack. + +Internal BPF can used as generic assembler for last step performance +optimizations, socket filters and seccomp are using it as assembler. Tracing +filters may use it as assembler to generate code from kernel. In kernel usage +may not be bounded by security considerations, since generated internal BPF code +may be optimizing internal code path and not being exposed to the user space. +Safety of internal BPF can come from a verifier (TBD). In such use cases as +described, it may be used as safe instruction set. Just like the original BPF, the new format runs within a controlled environment, is deterministic and the kernel can easily prove that. The safety of the program @@ -670,6 +834,181 @@ loops and other CFG validation; second step starts from the first insn and descends all possible paths. It simulates execution of every insn and observes the state change of registers and stack. +eBPF opcode encoding +-------------------- + +eBPF is reusing most of the opcode encoding from classic to simplify conversion +of classic BPF to eBPF. For arithmetic and jump instructions the 8-bit 'code' +field is divided into three parts: + + +----------------+--------+--------------------+ + | 4 bits | 1 bit | 3 bits | + | operation code | source | instruction class | + +----------------+--------+--------------------+ + (MSB) (LSB) + +Three LSB bits store instruction class which is one of: + + Classic BPF classes: eBPF classes: + + BPF_LD 0x00 BPF_LD 0x00 + BPF_LDX 0x01 BPF_LDX 0x01 + BPF_ST 0x02 BPF_ST 0x02 + BPF_STX 0x03 BPF_STX 0x03 + BPF_ALU 0x04 BPF_ALU 0x04 + BPF_JMP 0x05 BPF_JMP 0x05 + BPF_RET 0x06 [ class 6 unused, for future if needed ] + BPF_MISC 0x07 BPF_ALU64 0x07 + +When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ... + + BPF_K 0x00 + BPF_X 0x08 + + * in classic BPF, this means: + + BPF_SRC(code) == BPF_X - use register X as source operand + BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand + + * in eBPF, this means: + + BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand + BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand + +... and four MSB bits store operation code. + +If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of: + + BPF_ADD 0x00 + BPF_SUB 0x10 + BPF_MUL 0x20 + BPF_DIV 0x30 + BPF_OR 0x40 + BPF_AND 0x50 + BPF_LSH 0x60 + BPF_RSH 0x70 + BPF_NEG 0x80 + BPF_MOD 0x90 + BPF_XOR 0xa0 + BPF_MOV 0xb0 /* eBPF only: mov reg to reg */ + BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */ + BPF_END 0xd0 /* eBPF only: endianness conversion */ + +If BPF_CLASS(code) == BPF_JMP, BPF_OP(code) is one of: + + BPF_JA 0x00 + BPF_JEQ 0x10 + BPF_JGT 0x20 + BPF_JGE 0x30 + BPF_JSET 0x40 + BPF_JNE 0x50 /* eBPF only: jump != */ + BPF_JSGT 0x60 /* eBPF only: signed '>' */ + BPF_JSGE 0x70 /* eBPF only: signed '>=' */ + BPF_CALL 0x80 /* eBPF only: function call */ + BPF_EXIT 0x90 /* eBPF only: function return */ + +So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF +and eBPF. There are only two registers in classic BPF, so it means A += X. +In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly, +BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous +src_reg = (u32) src_reg ^ (u32) imm32 in eBPF. + +Classic BPF is using BPF_MISC class to represent A = X and X = A moves. +eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no +BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean +exactly the same operations as BPF_ALU, but with 64-bit wide operands +instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.: +dst_reg = dst_reg + src_reg + +Classic BPF wastes the whole BPF_RET class to represent a single 'ret' +operation. Classic BPF_RET | BPF_K means copy imm32 into return register +and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT +in eBPF means function exit only. The eBPF program needs to store return +value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is currently +unused and reserved for future use. + +For load and store instructions the 8-bit 'code' field is divided as: + + +--------+--------+-------------------+ + | 3 bits | 2 bits | 3 bits | + | mode | size | instruction class | + +--------+--------+-------------------+ + (MSB) (LSB) + +Size modifier is one of ... + + BPF_W 0x00 /* word */ + BPF_H 0x08 /* half word */ + BPF_B 0x10 /* byte */ + BPF_DW 0x18 /* eBPF only, double word */ + +... which encodes size of load/store operation: + + B - 1 byte + H - 2 byte + W - 4 byte + DW - 8 byte (eBPF only) + +Mode modifier is one of: + + BPF_IMM 0x00 /* classic BPF only, reserved in eBPF */ + BPF_ABS 0x20 + BPF_IND 0x40 + BPF_MEM 0x60 + BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */ + BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */ + BPF_XADD 0xc0 /* eBPF only, exclusive add */ + +eBPF has two non-generic instructions: (BPF_ABS | | BPF_LD) and +(BPF_IND | | BPF_LD) which are used to access packet data. + +They had to be carried over from classic to have strong performance of +socket filters running in eBPF interpreter. These instructions can only +be used when interpreter context is a pointer to 'struct sk_buff' and +have seven implicit operands. Register R6 is an implicit input that must +contain pointer to sk_buff. Register R0 is an implicit output which contains +the data fetched from the packet. Registers R1-R5 are scratch registers +and must not be used to store the data across BPF_ABS | BPF_LD or +BPF_IND | BPF_LD instructions. + +These instructions have implicit program exit condition as well. When +eBPF program is trying to access the data beyond the packet boundary, +the interpreter will abort the execution of the program. JIT compilers +therefore must preserve this property. src_reg and imm32 fields are +explicit inputs to these instructions. + +For example: + + BPF_IND | BPF_W | BPF_LD means: + + R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32)) + and R1 - R5 were scratched. + +Unlike classic BPF instruction set, eBPF has generic load/store operations: + +BPF_MEM | | BPF_STX: *(size *) (dst_reg + off) = src_reg +BPF_MEM | | BPF_ST: *(size *) (dst_reg + off) = imm32 +BPF_MEM | | BPF_LDX: dst_reg = *(size *) (src_reg + off) +BPF_XADD | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg +BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg + +Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and +2 byte atomic increments are not supported. + +Testing +------- + +Next to the BPF toolchain, the kernel also ships a test module that contains +various test cases for classic and internal BPF that can be executed against +the BPF interpreter and JIT compiler. It can be found in lib/test_bpf.c and +enabled via Kconfig: + + CONFIG_TEST_BPF=m + +After the module has been built and installed, the test suite can be executed +via insmod or modprobe against 'test_bpf' module. Results of the test cases +including timings in nsec can be found in the kernel log (dmesg). + Misc ---- diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt index e13dafc8e8f1..2850df3bf957 100644 --- a/Documentation/power/suspend-and-cpuhotplug.txt +++ b/Documentation/power/suspend-and-cpuhotplug.txt @@ -1,6 +1,6 @@ Interaction of Suspend code (S3) with the CPU hotplug infrastructure - (C) 2011 Srivatsa S. Bhat + (C) 2011 - 2014 Srivatsa S. Bhat I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM diff --git a/Documentation/vDSO/parse_vdso.c b/Documentation/vDSO/parse_vdso.c index 85870208edcf..1dbb4b87268f 100644 --- a/Documentation/vDSO/parse_vdso.c +++ b/Documentation/vDSO/parse_vdso.c @@ -1,6 +1,6 @@ /* * parse_vdso.c: Linux reference vDSO parser - * Written by Andrew Lutomirski, 2011. + * Written by Andrew Lutomirski, 2011-2014. * * This code is meant to be linked in to various programs that run on Linux. * As such, it is available with as few restrictions as possible. This file @@ -11,13 +11,14 @@ * it starts a program. It works equally well in statically and dynamically * linked binaries. * - * This code is tested on x86_64. In principle it should work on any 64-bit + * This code is tested on x86. In principle it should work on any * architecture that has a vDSO. */ #include #include #include +#include #include /* @@ -45,11 +46,18 @@ extern void *vdso_sym(const char *version, const char *name); /* And here's the code. */ - -#ifndef __x86_64__ -# error Not yet ported to non-x86_64 architectures +#ifndef ELF_BITS +# if ULONG_MAX > 0xffffffffUL +# define ELF_BITS 64 +# else +# define ELF_BITS 32 +# endif #endif +#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x +#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x) +#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x) + static struct vdso_info { bool valid; @@ -59,14 +67,14 @@ static struct vdso_info uintptr_t load_offset; /* load_addr - recorded vaddr */ /* Symbol table */ - Elf64_Sym *symtab; + ELF(Sym) *symtab; const char *symstrings; - Elf64_Word *bucket, *chain; - Elf64_Word nbucket, nchain; + ELF(Word) *bucket, *chain; + ELF(Word) nbucket, nchain; /* Version table */ - Elf64_Versym *versym; - Elf64_Verdef *verdef; + ELF(Versym) *versym; + ELF(Verdef) *verdef; } vdso_info; /* Straight from the ELF specification. */ @@ -92,9 +100,14 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) vdso_info.load_addr = base; - Elf64_Ehdr *hdr = (Elf64_Ehdr*)base; - Elf64_Phdr *pt = (Elf64_Phdr*)(vdso_info.load_addr + hdr->e_phoff); - Elf64_Dyn *dyn = 0; + ELF(Ehdr) *hdr = (ELF(Ehdr)*)base; + if (hdr->e_ident[EI_CLASS] != + (ELF_BITS == 32 ? ELFCLASS32 : ELFCLASS64)) { + return; /* Wrong ELF class -- check ELF_BITS */ + } + + ELF(Phdr) *pt = (ELF(Phdr)*)(vdso_info.load_addr + hdr->e_phoff); + ELF(Dyn) *dyn = 0; /* * We need two things from the segment table: the load offset @@ -108,7 +121,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) + (uintptr_t)pt[i].p_offset - (uintptr_t)pt[i].p_vaddr; } else if (pt[i].p_type == PT_DYNAMIC) { - dyn = (Elf64_Dyn*)(base + pt[i].p_offset); + dyn = (ELF(Dyn)*)(base + pt[i].p_offset); } } @@ -118,7 +131,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) /* * Fish out the useful bits of the dynamic table. */ - Elf64_Word *hash = 0; + ELF(Word) *hash = 0; vdso_info.symstrings = 0; vdso_info.symtab = 0; vdso_info.versym = 0; @@ -131,22 +144,22 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) + vdso_info.load_offset); break; case DT_SYMTAB: - vdso_info.symtab = (Elf64_Sym *) + vdso_info.symtab = (ELF(Sym) *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; case DT_HASH: - hash = (Elf64_Word *) + hash = (ELF(Word) *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; case DT_VERSYM: - vdso_info.versym = (Elf64_Versym *) + vdso_info.versym = (ELF(Versym) *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; case DT_VERDEF: - vdso_info.verdef = (Elf64_Verdef *) + vdso_info.verdef = (ELF(Verdef) *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; @@ -168,8 +181,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) vdso_info.valid = true; } -static bool vdso_match_version(Elf64_Versym ver, - const char *name, Elf64_Word hash) +static bool vdso_match_version(ELF(Versym) ver, + const char *name, ELF(Word) hash) { /* * This is a helper function to check if the version indexed by @@ -188,7 +201,7 @@ static bool vdso_match_version(Elf64_Versym ver, /* First step: find the version definition */ ver &= 0x7fff; /* Apparently bit 15 means "hidden" */ - Elf64_Verdef *def = vdso_info.verdef; + ELF(Verdef) *def = vdso_info.verdef; while(true) { if ((def->vd_flags & VER_FLG_BASE) == 0 && (def->vd_ndx & 0x7fff) == ver) @@ -197,11 +210,11 @@ static bool vdso_match_version(Elf64_Versym ver, if (def->vd_next == 0) return false; /* No definition. */ - def = (Elf64_Verdef *)((char *)def + def->vd_next); + def = (ELF(Verdef) *)((char *)def + def->vd_next); } /* Now figure out whether it matches. */ - Elf64_Verdaux *aux = (Elf64_Verdaux*)((char *)def + def->vd_aux); + ELF(Verdaux) *aux = (ELF(Verdaux)*)((char *)def + def->vd_aux); return def->vd_hash == hash && !strcmp(name, vdso_info.symstrings + aux->vda_name); } @@ -213,10 +226,10 @@ void *vdso_sym(const char *version, const char *name) return 0; ver_hash = elf_hash(version); - Elf64_Word chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) { - Elf64_Sym *sym = &vdso_info.symtab[chain]; + ELF(Sym) *sym = &vdso_info.symtab[chain]; /* Check for a defined global or weak function w/ right name. */ if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) @@ -243,7 +256,7 @@ void *vdso_sym(const char *version, const char *name) void vdso_init_from_auxv(void *auxv) { - Elf64_auxv_t *elf_auxv = auxv; + ELF(auxv_t) *elf_auxv = auxv; for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++) { if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) { diff --git a/Documentation/vDSO/vdso_standalone_test_x86.c b/Documentation/vDSO/vdso_standalone_test_x86.c new file mode 100644 index 000000000000..d46240265c50 --- /dev/null +++ b/Documentation/vDSO/vdso_standalone_test_x86.c @@ -0,0 +1,128 @@ +/* + * vdso_test.c: Sample code to test parse_vdso.c on x86 + * Copyright (c) 2011-2014 Andy Lutomirski + * Subject to the GNU General Public License, version 2 + * + * You can amuse yourself by compiling with: + * gcc -std=gnu99 -nostdlib + * -Os -fno-asynchronous-unwind-tables -flto -lgcc_s + * vdso_standalone_test_x86.c parse_vdso.c + * to generate a small binary. On x86_64, you can omit -lgcc_s + * if you want the binary to be completely standalone. + */ + +#include +#include +#include +#include + +extern void *vdso_sym(const char *version, const char *name); +extern void vdso_init_from_sysinfo_ehdr(uintptr_t base); +extern void vdso_init_from_auxv(void *auxv); + +/* We need a libc functions... */ +int strcmp(const char *a, const char *b) +{ + /* This implementation is buggy: it never returns -1. */ + while (*a || *b) { + if (*a != *b) + return 1; + if (*a == 0 || *b == 0) + return 1; + a++; + b++; + } + + return 0; +} + +/* ...and two syscalls. This is x86-specific. */ +static inline long x86_syscall3(long nr, long a0, long a1, long a2) +{ + long ret; +#ifdef __x86_64__ + asm volatile ("syscall" : "=a" (ret) : "a" (nr), + "D" (a0), "S" (a1), "d" (a2) : + "cc", "memory", "rcx", + "r8", "r9", "r10", "r11" ); +#else + asm volatile ("int $0x80" : "=a" (ret) : "a" (nr), + "b" (a0), "c" (a1), "d" (a2) : + "cc", "memory" ); +#endif + return ret; +} + +static inline long linux_write(int fd, const void *data, size_t len) +{ + return x86_syscall3(__NR_write, fd, (long)data, (long)len); +} + +static inline void linux_exit(int code) +{ + x86_syscall3(__NR_exit, code, 0, 0); +} + +void to_base10(char *lastdig, uint64_t n) +{ + while (n) { + *lastdig = (n % 10) + '0'; + n /= 10; + lastdig--; + } +} + +__attribute__((externally_visible)) void c_main(void **stack) +{ + /* Parse the stack */ + long argc = (long)*stack; + stack += argc + 2; + + /* Now we're pointing at the environment. Skip it. */ + while(*stack) + stack++; + stack++; + + /* Now we're pointing at auxv. Initialize the vDSO parser. */ + vdso_init_from_auxv((void *)stack); + + /* Find gettimeofday. */ + typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); + gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday"); + + if (!gtod) + linux_exit(1); + + struct timeval tv; + long ret = gtod(&tv, 0); + + if (ret == 0) { + char buf[] = "The time is .000000\n"; + to_base10(buf + 31, tv.tv_sec); + to_base10(buf + 38, tv.tv_usec); + linux_write(1, buf, sizeof(buf) - 1); + } else { + linux_exit(ret); + } + + linux_exit(0); +} + +/* + * This is the real entry point. It passes the initial stack into + * the C entry point. + */ +asm ( + ".text\n" + ".global _start\n" + ".type _start,@function\n" + "_start:\n\t" +#ifdef __x86_64__ + "mov %rsp,%rdi\n\t" + "jmp c_main" +#else + "push %esp\n\t" + "call c_main\n\t" + "int $3" +#endif + ); diff --git a/Documentation/vDSO/vdso_test.c b/Documentation/vDSO/vdso_test.c index fff633432dff..8daeb7d7032c 100644 --- a/Documentation/vDSO/vdso_test.c +++ b/Documentation/vDSO/vdso_test.c @@ -1,111 +1,52 @@ /* - * vdso_test.c: Sample code to test parse_vdso.c on x86_64 - * Copyright (c) 2011 Andy Lutomirski + * vdso_test.c: Sample code to test parse_vdso.c + * Copyright (c) 2014 Andy Lutomirski * Subject to the GNU General Public License, version 2 * - * You can amuse yourself by compiling with: - * gcc -std=gnu99 -nostdlib - * -Os -fno-asynchronous-unwind-tables -flto - * vdso_test.c parse_vdso.c -o vdso_test - * to generate a small binary with no dependencies at all. + * Compile with: + * gcc -std=gnu99 vdso_test.c parse_vdso.c + * + * Tested on x86, 32-bit and 64-bit. It may work on other architectures, too. */ -#include -#include -#include #include +#include +#include +#include +#include extern void *vdso_sym(const char *version, const char *name); extern void vdso_init_from_sysinfo_ehdr(uintptr_t base); extern void vdso_init_from_auxv(void *auxv); -/* We need a libc functions... */ -int strcmp(const char *a, const char *b) +int main(int argc, char **argv) { - /* This implementation is buggy: it never returns -1. */ - while (*a || *b) { - if (*a != *b) - return 1; - if (*a == 0 || *b == 0) - return 1; - a++; - b++; + unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); + if (!sysinfo_ehdr) { + printf("AT_SYSINFO_EHDR is not present!\n"); + return 0; } - return 0; -} - -/* ...and two syscalls. This is x86_64-specific. */ -static inline long linux_write(int fd, const void *data, size_t len) -{ - - long ret; - asm volatile ("syscall" : "=a" (ret) : "a" (__NR_write), - "D" (fd), "S" (data), "d" (len) : - "cc", "memory", "rcx", - "r8", "r9", "r10", "r11" ); - return ret; -} - -static inline void linux_exit(int code) -{ - asm volatile ("syscall" : : "a" (__NR_exit), "D" (code)); -} - -void to_base10(char *lastdig, uint64_t n) -{ - while (n) { - *lastdig = (n % 10) + '0'; - n /= 10; - lastdig--; - } -} - -__attribute__((externally_visible)) void c_main(void **stack) -{ - /* Parse the stack */ - long argc = (long)*stack; - stack += argc + 2; - - /* Now we're pointing at the environment. Skip it. */ - while(*stack) - stack++; - stack++; - - /* Now we're pointing at auxv. Initialize the vDSO parser. */ - vdso_init_from_auxv((void *)stack); + vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); /* Find gettimeofday. */ typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday"); - if (!gtod) - linux_exit(1); + if (!gtod) { + printf("Could not find __vdso_gettimeofday\n"); + return 1; + } struct timeval tv; long ret = gtod(&tv, 0); if (ret == 0) { - char buf[] = "The time is .000000\n"; - to_base10(buf + 31, tv.tv_sec); - to_base10(buf + 38, tv.tv_usec); - linux_write(1, buf, sizeof(buf) - 1); + printf("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); } else { - linux_exit(ret); + printf("__vdso_gettimeofday failed\n"); } - linux_exit(0); + return 0; } - -/* - * This is the real entry point. It passes the initial stack into - * the C entry point. - */ -asm ( - ".text\n" - ".global _start\n" - ".type _start,@function\n" - "_start:\n\t" - "mov %rsp,%rdi\n\t" - "jmp c_main" - ); diff --git a/MAINTAINERS b/MAINTAINERS index b4a66b9d6b4d..134483f206e4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -604,6 +604,13 @@ L: amd64-microcode@amd64.org S: Maintained F: arch/x86/kernel/microcode_amd.c +AMD XGBE DRIVER +M: Tom Lendacky +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/amd/xgbe/ +F: drivers/net/phy/amd-xgbe-phy.c + AMS (Apple Motion Sensor) DRIVER M: Michael Hanselmann S: Supported @@ -1894,7 +1901,7 @@ F: drivers/net/ethernet/broadcom/bnx2.* F: drivers/net/ethernet/broadcom/bnx2_* BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -M: Ariel Elior +M: Ariel Elior L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ @@ -1974,6 +1981,12 @@ S: Maintained F: drivers/bcma/ F: include/linux/bcma/ +BROADCOM SYSTEMPORT ETHERNET DRIVER +M: Florian Fainelli +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/broadcom/bcmsysport.* + BROCADE BFA FC SCSI DRIVER M: Anil Gurumurthy M: Sudarsana Kalluru @@ -2230,9 +2243,8 @@ F: drivers/platform/chrome/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti M: Sujith Sankar -M: Govindarajulu Varadarajan +M: Govindarajulu Varadarajan <_govind@gmx.com> M: Neel Patel -M: Nishank Trivedi S: Supported F: drivers/net/ethernet/cisco/enic/ @@ -2582,7 +2594,7 @@ S: Supported F: drivers/infiniband/hw/cxgb3/ CXGB4 ETHERNET DRIVER (CXGB4) -M: Dimitris Michailidis +M: Hariprasad S L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -2952,6 +2964,7 @@ L: dri-devel@lists.freedesktop.org T: git git://people.freedesktop.org/~airlied/linux S: Maintained F: drivers/gpu/drm/ +F: drivers/gpu/vga/ F: include/drm/ F: include/uapi/drm/ @@ -6167,6 +6180,7 @@ F: include/uapi/linux/netdevice.h F: tools/net/ F: tools/testing/selftests/net/ F: lib/random32.c +F: lib/test_bpf.c NETWORKING [IPv4/IPv6] M: "David S. Miller" diff --git a/Makefile b/Makefile index c761fb1abfb6..97b286128c1e 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 -PATCHLEVEL = 15 +PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Shuffling Zombie Juror # *DOCUMENTATION* @@ -105,10 +105,6 @@ ifeq ("$(origin O)", "command line") KBUILD_OUTPUT := $(O) endif -ifeq ("$(origin W)", "command line") - export KBUILD_ENABLE_EXTRA_GCC_CHECKS := $(W) -endif - # That's our default target when none is given on the command line PHONY := _all _all: @@ -153,8 +149,18 @@ else _all: modules endif -srctree := $(if $(KBUILD_SRC),$(KBUILD_SRC),$(CURDIR)) -objtree := $(CURDIR) +ifeq ($(KBUILD_SRC),) + # building in the source tree + srctree := . +else + ifeq ($(KBUILD_SRC)/,$(dir $(CURDIR))) + # building in a subdirectory of the source tree + srctree := .. + else + srctree := $(KBUILD_SRC) + endif +endif +objtree := . src := $(srctree) obj := $(objtree) @@ -166,7 +172,7 @@ export srctree objtree VPATH # SUBARCH tells the usermode build what the underlying arch is. That is set # first, and if a usermode build is happening, the "ARCH=um" on the command # line overrides the setting of ARCH below. If a native build is happening, -# then ARCH is assigned, getting whatever value it gets normally, and +# then ARCH is assigned, getting whatever value it gets normally, and # SUBARCH is subsequently ignored. SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ @@ -259,18 +265,18 @@ endif KBUILD_MODULES := KBUILD_BUILTIN := 1 -# If we have only "make modules", don't compile built-in objects. -# When we're building modules with modversions, we need to consider -# the built-in objects during the descend as well, in order to -# make sure the checksums are up to date before we record them. +# If we have only "make modules", don't compile built-in objects. +# When we're building modules with modversions, we need to consider +# the built-in objects during the descend as well, in order to +# make sure the checksums are up to date before we record them. ifeq ($(MAKECMDGOALS),modules) KBUILD_BUILTIN := $(if $(CONFIG_MODVERSIONS),1) endif -# If we have "make modules", compile modules -# in addition to whatever we do anyway. -# Just "make" or "make all" shall build modules as well +# If we have "make modules", compile modules +# in addition to whatever we do anyway. +# Just "make" or "make all" shall build modules as well ifneq ($(filter all _all modules,$(MAKECMDGOALS)),) KBUILD_MODULES := 1 @@ -294,7 +300,7 @@ export KBUILD_CHECKSRC KBUILD_SRC KBUILD_EXTMOD # cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< # # If $(quiet) is empty, the whole command will be printed. -# If it is set to "quiet_", only the short version will be printed. +# If it is set to "quiet_", only the short version will be printed. # If it is set to "silent_", nothing will be printed at all, since # the variable $(silent_cmd_cc_o_c) doesn't exist. # @@ -346,7 +352,6 @@ $(srctree)/scripts/Kbuild.include: ; include $(srctree)/scripts/Kbuild.include # Make variables (CC, etc...) - AS = $(CROSS_COMPILE)as LD = $(CROSS_COMPILE)ld CC = $(CROSS_COMPILE)gcc @@ -395,8 +400,8 @@ KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ - -Wno-format-security \ - $(call cc-option,-fno-delete-null-pointer-checks,) + -Wno-format-security + KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := KBUILD_AFLAGS := -D__ASSEMBLY__ @@ -504,8 +509,16 @@ ifeq ($(mixed-targets),1) # We're called with mixed targets (*config and build targets). # Handle them one by one. -%:: FORCE - $(Q)$(MAKE) -C $(srctree) KBUILD_SRC= $@ +PHONY += $(MAKECMDGOALS) __build_one_by_one + +$(filter-out __build_one_by_one, $(MAKECMDGOALS)): __build_one_by_one + @: + +__build_one_by_one: + $(Q)set -e; \ + for i in $(MAKECMDGOALS); do \ + $(MAKE) -f $(srctree)/Makefile $$i; \ + done else ifeq ($(config-targets),1) @@ -520,11 +533,9 @@ include $(srctree)/arch/$(SRCARCH)/Makefile export KBUILD_DEFCONFIG KBUILD_KCONFIG config: scripts_basic outputmakefile FORCE - $(Q)mkdir -p include/linux include/config $(Q)$(MAKE) $(build)=scripts/kconfig $@ %config: scripts_basic outputmakefile FORCE - $(Q)mkdir -p include/linux include/config $(Q)$(MAKE) $(build)=scripts/kconfig $@ else @@ -594,14 +605,16 @@ endif # $(dot-config) # Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux +include $(srctree)/arch/$(SRCARCH)/Makefile + +KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,) + ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,) else KBUILD_CFLAGS += -O2 endif -include $(srctree)/arch/$(SRCARCH)/Makefile - ifdef CONFIG_READABLE_ASM # Disable optimizations that make assembler listings hard to read. # reorder blocks reorders the control in the function @@ -731,6 +744,8 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO endif +include $(srctree)/scripts/Makefile.extrawarn + # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments KBUILD_CPPFLAGS += $(KCPPFLAGS) KBUILD_AFLAGS += $(KAFLAGS) @@ -775,10 +790,10 @@ MODLIB = $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE) export MODLIB # -# INSTALL_MOD_STRIP, if defined, will cause modules to be -# stripped after they are installed. If INSTALL_MOD_STRIP is '1', then -# the default option --strip-debug will be used. Otherwise, -# INSTALL_MOD_STRIP value will be used as the options to the strip command. +# INSTALL_MOD_STRIP, if defined, will cause modules to be +# stripped after they are installed. If INSTALL_MOD_STRIP is '1', then +# the default option --strip-debug will be used. Otherwise, +# INSTALL_MOD_STRIP value will be used as the options to the strip command. ifdef INSTALL_MOD_STRIP ifeq ($(INSTALL_MOD_STRIP),1) @@ -863,7 +878,7 @@ ifdef CONFIG_BUILD_DOCSRC endif +$(call if_changed,link-vmlinux) -# The actual objects are generated when descending, +# The actual objects are generated when descending, # make sure no implicit rule kicks in $(sort $(vmlinux-deps)): $(vmlinux-dirs) ; @@ -1021,11 +1036,11 @@ ifdef CONFIG_MODULES all: modules -# Build modules +# Build modules # -# A module can be listed more than once in obj-m resulting in -# duplicate lines in modules.order files. Those are removed -# using awk while concatenating to the final file. +# A module can be listed more than once in obj-m resulting in +# duplicate lines in modules.order files. Those are removed +# using awk while concatenating to the final file. PHONY += modules modules: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) modules.builtin @@ -1054,10 +1069,10 @@ _modinst_: @rm -rf $(MODLIB)/kernel @rm -f $(MODLIB)/source @mkdir -p $(MODLIB)/kernel - @ln -s $(srctree) $(MODLIB)/source + @ln -s `cd $(srctree) && /bin/pwd` $(MODLIB)/source @if [ ! $(objtree) -ef $(MODLIB)/build ]; then \ rm -f $(MODLIB)/build ; \ - ln -s $(objtree) $(MODLIB)/build ; \ + ln -s $(CURDIR) $(MODLIB)/build ; \ fi @cp -f $(objtree)/modules.order $(MODLIB)/ @cp -f $(objtree)/modules.builtin $(MODLIB)/ @@ -1104,7 +1119,7 @@ CLEAN_DIRS += $(MODVERDIR) # Directories & files removed with 'make mrproper' MRPROPER_DIRS += include/config usr/include include/generated \ - arch/*/include/generated .tmp_objdiff + arch/*/include/generated .tmp_objdiff MRPROPER_FILES += .config .config.old .version .old_version $(version_h) \ Module.symvers tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS \ signing_key.priv signing_key.x509 x509.genkey \ @@ -1478,7 +1493,7 @@ endif $(build)=$(build-dir) $(@:.ko=.o) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost -# FIXME Should go into a make.lib or something +# FIXME Should go into a make.lib or something # =========================================================================== quiet_cmd_rmdirs = $(if $(wildcard $(rm-dirs)),CLEAN $(wildcard $(rm-dirs))) diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 9f53e824b037..4a4e02d0ce9e 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -662,6 +662,8 @@ ehrpwm2: ehrpwm@48304200 { mac: ethernet@4a100000 { compatible = "ti,cpsw"; ti,hwmods = "cpgmac0"; + clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>; + clock-names = "fck", "cpts"; cpdma_channels = <8>; ale_entries = <1024>; bd_ram_size = <0x2000>; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index db464d7eaca8..49fa59622254 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -490,6 +490,8 @@ GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH #address-cells = <1>; #size-cells = <1>; ti,hwmods = "cpgmac0"; + clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>; + clock-names = "fck", "cpts"; status = "disabled"; cpdma_channels = <8>; ale_entries = <1024>; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 25674fe81f70..7e291e2ef4b3 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -57,6 +57,10 @@ sata@a0000 { ethernet@30000 { status = "okay"; phy-mode = "sgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; }; pcie-controller { diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index c7676871d9c0..b03cfe49d22b 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -26,7 +26,7 @@ atl_clkin2_ck: atl_clkin2_ck { clock-frequency = <0>; }; - atlclkin3_ck: atlclkin3_ck { + atl_clkin3_ck: atl_clkin3_ck { #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <0>; @@ -277,7 +277,7 @@ mpu_dpll_hs_clk_div: mpu_dpll_hs_clk_div { dpll_mpu_ck: dpll_mpu_ck { #clock-cells = <0>; - compatible = "ti,omap4-dpll-clock"; + compatible = "ti,omap5-mpu-dpll-clock"; clocks = <&sys_clkin1>, <&mpu_dpll_hs_clk_div>; reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>; }; @@ -730,7 +730,7 @@ ipu1_gfclk_mux: ipu1_gfclk_mux { mcasp1_ahclkr_mux: mcasp1_ahclkr_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <28>; reg = <0x0550>; }; @@ -738,7 +738,7 @@ mcasp1_ahclkr_mux: mcasp1_ahclkr_mux { mcasp1_ahclkx_mux: mcasp1_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x0550>; }; @@ -1639,7 +1639,7 @@ l3instr_ts_gclk_div: l3instr_ts_gclk_div { mcasp2_ahclkr_mux: mcasp2_ahclkr_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <28>; reg = <0x1860>; }; @@ -1647,7 +1647,7 @@ mcasp2_ahclkr_mux: mcasp2_ahclkr_mux { mcasp2_ahclkx_mux: mcasp2_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1860>; }; @@ -1663,7 +1663,7 @@ mcasp2_aux_gfclk_mux: mcasp2_aux_gfclk_mux { mcasp3_ahclkx_mux: mcasp3_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1868>; }; @@ -1679,7 +1679,7 @@ mcasp3_aux_gfclk_mux: mcasp3_aux_gfclk_mux { mcasp4_ahclkx_mux: mcasp4_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1898>; }; @@ -1695,7 +1695,7 @@ mcasp4_aux_gfclk_mux: mcasp4_aux_gfclk_mux { mcasp5_ahclkx_mux: mcasp5_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1878>; }; @@ -1711,7 +1711,7 @@ mcasp5_aux_gfclk_mux: mcasp5_aux_gfclk_mux { mcasp6_ahclkx_mux: mcasp6_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1904>; }; @@ -1727,7 +1727,7 @@ mcasp6_aux_gfclk_mux: mcasp6_aux_gfclk_mux { mcasp7_ahclkx_mux: mcasp7_ahclkx_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1908>; }; @@ -1743,7 +1743,7 @@ mcasp7_aux_gfclk_mux: mcasp7_aux_gfclk_mux { mcasp8_ahclk_mux: mcasp8_ahclk_mux { #clock-cells = <0>; compatible = "ti,mux-clock"; - clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; + clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <22>; reg = <0x1890>; }; diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi index aeb142ce8e9d..e67a23b5d788 100644 --- a/arch/arm/boot/dts/omap54xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi @@ -335,7 +335,7 @@ mpu_dpll_hs_clk_div: mpu_dpll_hs_clk_div { dpll_mpu_ck: dpll_mpu_ck { #clock-cells = <0>; - compatible = "ti,omap4-dpll-clock"; + compatible = "ti,omap5-mpu-dpll-clock"; clocks = <&sys_clkin>, <&mpu_dpll_hs_clk_div>; reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>; }; diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi index 51d0e912c8f5..1929ad390d88 100644 --- a/arch/arm/boot/dts/vt8500.dtsi +++ b/arch/arm/boot/dts/vt8500.dtsi @@ -165,5 +165,11 @@ rtc@d8100000 { reg = <0xd8100000 0x10000>; interrupts = <48>; }; + + ethernet@d8004000 { + compatible = "via,vt8500-rhine"; + reg = <0xd8004000 0x100>; + interrupts = <10>; + }; }; }; diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index 7525982262ac..b1c59a766a13 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -218,5 +218,11 @@ rtc@d8100000 { reg = <0xd8100000 0x10000>; interrupts = <48>; }; + + ethernet@d8004000 { + compatible = "via,vt8500-rhine"; + reg = <0xd8004000 0x100>; + interrupts = <10>; + }; }; }; diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi index d98386dd2882..8fbccfbe75f3 100644 --- a/arch/arm/boot/dts/wm8850.dtsi +++ b/arch/arm/boot/dts/wm8850.dtsi @@ -298,5 +298,11 @@ sdhc@d800a000 { bus-width = <4>; sdon-inverted; }; + + ethernet@d8004000 { + compatible = "via,vt8500-rhine"; + reg = <0xd8004000 0x100>; + interrupts = <10>; + }; }; }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index a6bc431cde70..4238bcba9d60 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -410,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event) */ hwc->config_base |= (unsigned long)mapping; - if (!hwc->sample_period) { + if (!is_sampling_event(event)) { /* * For non-sampling runs, limit the sample_period to half * of the counter width. That way, the new counter value diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index a71ae1523620..af9e35e8836f 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -126,8 +126,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) irqs = min(pmu_device->num_resources, num_possible_cpus()); if (irqs < 1) { - pr_err("no irqs for PMUs defined\n"); - return -ENODEV; + printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n"); + return 0; } irq = platform_get_irq(pmu_device, 0); @@ -191,6 +191,10 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) /* Ensure the PMU has sane values out of reset. */ if (cpu_pmu->reset) on_each_cpu(cpu_pmu->reset, cpu_pmu, 1); + + /* If no interrupts available, set the corresponding capability flag */ + if (!platform_get_irq(cpu_pmu->plat_device, 0)) + cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } /* diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 3997c411c140..9d853189028b 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -26,30 +26,30 @@ #include /* - * cpu power scale management + * cpu capacity scale management */ /* - * cpu power table + * cpu capacity table * This per cpu data structure describes the relative capacity of each core. * On a heteregenous system, cores don't have the same computation capacity - * and we reflect that difference in the cpu_power field so the scheduler can - * take this difference into account during load balance. A per cpu structure - * is preferred because each CPU updates its own cpu_power field during the - * load balance except for idle cores. One idle core is selected to run the - * rebalance_domains for all idle cores and the cpu_power can be updated - * during this sequence. + * and we reflect that difference in the cpu_capacity field so the scheduler + * can take this difference into account during load balance. A per cpu + * structure is preferred because each CPU updates its own cpu_capacity field + * during the load balance except for idle cores. One idle core is selected + * to run the rebalance_domains for all idle cores and the cpu_capacity can be + * updated during this sequence. */ static DEFINE_PER_CPU(unsigned long, cpu_scale); -unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { return per_cpu(cpu_scale, cpu); } -static void set_power_scale(unsigned int cpu, unsigned long power) +static void set_capacity_scale(unsigned int cpu, unsigned long capacity) { - per_cpu(cpu_scale, cpu) = power; + per_cpu(cpu_scale, cpu) = capacity; } #ifdef CONFIG_OF @@ -62,11 +62,11 @@ struct cpu_efficiency { * Table of relative efficiency of each processors * The efficiency value must fit in 20bit and the final * cpu_scale value must be in the range - * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * 0 < cpu_scale < 3*SCHED_CAPACITY_SCALE/2 * in order to return at most 1 when DIV_ROUND_CLOSEST * is used to compute the capacity of a CPU. * Processors that are not defined in the table, - * use the default SCHED_POWER_SCALE value for cpu_scale. + * use the default SCHED_CAPACITY_SCALE value for cpu_scale. */ static const struct cpu_efficiency table_efficiency[] = { {"arm,cortex-a15", 3891}, @@ -83,9 +83,9 @@ static unsigned long middle_capacity = 1; * Iterate all CPUs' descriptor in DT and compute the efficiency * (as per table_efficiency). Also calculate a middle efficiency * as close as possible to (max{eff_i} - min{eff_i}) / 2 - * This is later used to scale the cpu_power field such that an - * 'average' CPU is of middle power. Also see the comments near - * table_efficiency[] and update_cpu_power(). + * This is later used to scale the cpu_capacity field such that an + * 'average' CPU is of middle capacity. Also see the comments near + * table_efficiency[] and update_cpu_capacity(). */ static void __init parse_dt_topology(void) { @@ -141,15 +141,15 @@ static void __init parse_dt_topology(void) * cpu_scale because all CPUs have the same capacity. Otherwise, we * compute a middle_capacity factor that will ensure that the capacity * of an 'average' CPU of the system will be as close as possible to - * SCHED_POWER_SCALE, which is the default value, but with the + * SCHED_CAPACITY_SCALE, which is the default value, but with the * constraint explained near table_efficiency[]. */ if (4*max_capacity < (3*(max_capacity + min_capacity))) middle_capacity = (min_capacity + max_capacity) - >> (SCHED_POWER_SHIFT+1); + >> (SCHED_CAPACITY_SHIFT+1); else middle_capacity = ((max_capacity / 3) - >> (SCHED_POWER_SHIFT-1)) + 1; + >> (SCHED_CAPACITY_SHIFT-1)) + 1; } @@ -158,20 +158,20 @@ static void __init parse_dt_topology(void) * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the * function returns directly for SMP system. */ -static void update_cpu_power(unsigned int cpu) +static void update_cpu_capacity(unsigned int cpu) { if (!cpu_capacity(cpu)) return; - set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); - printk(KERN_INFO "CPU%u: update cpu_power %lu\n", - cpu, arch_scale_freq_power(NULL, cpu)); + printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n", + cpu, arch_scale_freq_capacity(NULL, cpu)); } #else static inline void parse_dt_topology(void) {} -static inline void update_cpu_power(unsigned int cpuid) {} +static inline void update_cpu_capacity(unsigned int cpuid) {} #endif /* @@ -267,7 +267,7 @@ void store_cpu_topology(unsigned int cpuid) update_siblings_masks(cpuid); - update_cpu_power(cpuid); + update_cpu_capacity(cpuid); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -297,7 +297,7 @@ void __init init_cpu_topology(void) { unsigned int cpu; - /* init core mask and power*/ + /* init core mask and capacity */ for_each_possible_cpu(cpu) { struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); @@ -307,7 +307,7 @@ void __init init_cpu_topology(void) cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); - set_power_scale(cpu, SCHED_POWER_SCALE); + set_capacity_scale(cpu, SCHED_CAPACITY_SCALE); } smp_wmb(); diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c index b935ed2922d8..85e0b0c06718 100644 --- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c +++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c @@ -208,3 +208,56 @@ void omap2xxx_clkt_vps_late_init(void) clk_put(c); } } + +#ifdef CONFIG_OF +#include +#include + +static const struct clk_ops virt_prcm_set_ops = { + .recalc_rate = &omap2_table_mpu_recalc, + .set_rate = &omap2_select_table_rate, + .round_rate = &omap2_round_to_table_rate, +}; + +/** + * omap2xxx_clkt_vps_init - initialize virt_prcm_set clock + * + * Does a manual init for the virtual prcm DVFS clock for OMAP2. This + * function is called only from omap2 DT clock init, as the virtual + * node is not modelled in the DT clock data. + */ +void omap2xxx_clkt_vps_init(void) +{ + struct clk_init_data init = { NULL }; + struct clk_hw_omap *hw = NULL; + struct clk *clk; + const char *parent_name = "mpu_ck"; + struct clk_lookup *lookup = NULL; + + omap2xxx_clkt_vps_late_init(); + omap2xxx_clkt_vps_check_bootloader_rates(); + + hw = kzalloc(sizeof(*hw), GFP_KERNEL); + lookup = kzalloc(sizeof(*lookup), GFP_KERNEL); + if (!hw || !lookup) + goto cleanup; + init.name = "virt_prcm_set"; + init.ops = &virt_prcm_set_ops; + init.parent_names = &parent_name; + init.num_parents = 1; + + hw->hw.init = &init; + + clk = clk_register(NULL, &hw->hw); + + lookup->dev_id = NULL; + lookup->con_id = "cpufreq_ck"; + lookup->clk = clk; + + clkdev_add(lookup); + return; +cleanup: + kfree(hw); + kfree(lookup); +} +#endif diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h index bda767a9dea8..12f54d428d7c 100644 --- a/arch/arm/mach-omap2/clock.h +++ b/arch/arm/mach-omap2/clock.h @@ -178,17 +178,6 @@ struct clksel { const struct clksel_rate *rates; }; -struct clk_hw_omap_ops { - void (*find_idlest)(struct clk_hw_omap *oclk, - void __iomem **idlest_reg, - u8 *idlest_bit, u8 *idlest_val); - void (*find_companion)(struct clk_hw_omap *oclk, - void __iomem **other_reg, - u8 *other_bit); - void (*allow_idle)(struct clk_hw_omap *oclk); - void (*deny_idle)(struct clk_hw_omap *oclk); -}; - unsigned long omap_fixed_divisor_recalc(struct clk_hw *hw, unsigned long parent_rate); @@ -279,8 +268,6 @@ extern const struct clk_hw_omap_ops clkhwops_omap3430es2_hsotgusb_wait; extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait; extern const struct clk_hw_omap_ops clkhwops_apll54; extern const struct clk_hw_omap_ops clkhwops_apll96; -extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; -extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait; /* clksel_rate blocks shared between OMAP44xx and AM33xx */ extern const struct clksel_rate div_1_0_rates[]; diff --git a/arch/arm/mach-omap2/clock2xxx.h b/arch/arm/mach-omap2/clock2xxx.h index 539dc08afbba..45f41a411603 100644 --- a/arch/arm/mach-omap2/clock2xxx.h +++ b/arch/arm/mach-omap2/clock2xxx.h @@ -21,10 +21,6 @@ unsigned long omap2xxx_sys_clk_recalc(struct clk_hw *clk, unsigned long parent_rate); unsigned long omap2_osc_clk_recalc(struct clk_hw *clk, unsigned long parent_rate); -unsigned long omap2_dpllcore_recalc(struct clk_hw *hw, - unsigned long parent_rate); -int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate, - unsigned long parent_rate); void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw); unsigned long omap2_clk_apll54_recalc(struct clk_hw *hw, unsigned long parent_rate); diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c index fcd8036af910..6d7ba37e2257 100644 --- a/arch/arm/mach-omap2/dpll3xxx.c +++ b/arch/arm/mach-omap2/dpll3xxx.c @@ -319,6 +319,15 @@ static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel) /* Set DPLL multiplier, divider */ v = omap2_clk_readl(clk, dd->mult_div1_reg); + + /* Handle Duty Cycle Correction */ + if (dd->dcc_mask) { + if (dd->last_rounded_rate >= dd->dcc_rate) + v |= dd->dcc_mask; /* Enable DCC */ + else + v &= ~dd->dcc_mask; /* Disable DCC */ + } + v &= ~(dd->mult_mask | dd->div1_mask); v |= dd->last_rounded_m << __ffs(dd->mult_mask); v |= (dd->last_rounded_n - 1) << __ffs(dd->div1_mask); diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c index e4dec9fcb084..9c6029ba526f 100644 --- a/arch/arm/mach-tegra/board-paz00.c +++ b/arch/arm/mach-tegra/board-paz00.c @@ -23,9 +23,7 @@ #include "board.h" static struct rfkill_gpio_platform_data wifi_rfkill_platform_data = { - .name = "wifi_rfkill", - .reset_gpio = 25, /* PD1 */ - .shutdown_gpio = 85, /* PK5 */ + .name = "wifi_rfkill", .type = RFKILL_TYPE_WLAN, }; diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6f879c319a9d..fb5503ce016f 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -136,7 +136,7 @@ static u16 saved_regs(struct jit_ctx *ctx) u16 ret = 0; if ((ctx->skf->len > 1) || - (ctx->skf->insns[0].code == BPF_S_RET_A)) + (ctx->skf->insns[0].code == (BPF_RET | BPF_A))) ret |= 1 << r_A; #ifdef CONFIG_FRAME_POINTER @@ -164,18 +164,10 @@ static inline int mem_words_used(struct jit_ctx *ctx) static inline bool is_load_to_a(u16 inst) { switch (inst) { - case BPF_S_LD_W_LEN: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - case BPF_S_ANC_CPU: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_QUEUE: + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: return true; default: return false; @@ -215,7 +207,7 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst))) + if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ @@ -480,36 +472,39 @@ static int build_body(struct jit_ctx *ctx) u32 k; for (i = 0; i < prog->len; i++) { + u16 code; + inst = &(prog->insns[i]); /* K as an immediate value operand */ k = inst->k; + code = bpf_anc_helper(inst); /* compute offsets only in the fake pass */ if (ctx->target == NULL) ctx->offsets[i] = ctx->idx * 4; - switch (inst->code) { - case BPF_S_LD_IMM: + switch (code) { + case BPF_LD | BPF_IMM: emit_mov_i(r_A, k, ctx); break; - case BPF_S_LD_W_LEN: + case BPF_LD | BPF_W | BPF_LEN: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); emit(ARM_LDR_I(r_A, r_skb, offsetof(struct sk_buff, len)), ctx); break; - case BPF_S_LD_MEM: + case BPF_LD | BPF_MEM: /* A = scratch[k] */ ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: load_order = 2; goto load; - case BPF_S_LD_H_ABS: + case BPF_LD | BPF_H | BPF_ABS: load_order = 1; goto load; - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_B | BPF_ABS: load_order = 0; load: /* the interpreter will deal with the negative K */ @@ -552,31 +547,31 @@ static int build_body(struct jit_ctx *ctx) emit_err_ret(ARM_COND_NE, ctx); emit(ARM_MOV_R(r_A, ARM_R0), ctx); break; - case BPF_S_LD_W_IND: + case BPF_LD | BPF_W | BPF_IND: load_order = 2; goto load_ind; - case BPF_S_LD_H_IND: + case BPF_LD | BPF_H | BPF_IND: load_order = 1; goto load_ind; - case BPF_S_LD_B_IND: + case BPF_LD | BPF_B | BPF_IND: load_order = 0; load_ind: OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); goto load_common; - case BPF_S_LDX_IMM: + case BPF_LDX | BPF_IMM: ctx->seen |= SEEN_X; emit_mov_i(r_X, k, ctx); break; - case BPF_S_LDX_W_LEN: + case BPF_LDX | BPF_W | BPF_LEN: ctx->seen |= SEEN_X | SEEN_SKB; emit(ARM_LDR_I(r_X, r_skb, offsetof(struct sk_buff, len)), ctx); break; - case BPF_S_LDX_MEM: + case BPF_LDX | BPF_MEM: ctx->seen |= SEEN_X | SEEN_MEM_WORD(k); emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: /* x = ((*(frame + k)) & 0xf) << 2; */ ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; /* the interpreter should deal with the negative K */ @@ -606,113 +601,113 @@ static int build_body(struct jit_ctx *ctx) emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx); emit(ARM_LSL_I(r_X, r_X, 2), ctx); break; - case BPF_S_ST: + case BPF_ST: ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_STX: + case BPF_STX: update_on_xread(ctx); ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_ALU_ADD_K: + case BPF_ALU | BPF_ADD | BPF_K: /* A += K */ OP_IMM3(ARM_ADD, r_A, r_A, k, ctx); break; - case BPF_S_ALU_ADD_X: + case BPF_ALU | BPF_ADD | BPF_X: update_on_xread(ctx); emit(ARM_ADD_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_SUB_K: + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ OP_IMM3(ARM_SUB, r_A, r_A, k, ctx); break; - case BPF_S_ALU_SUB_X: + case BPF_ALU | BPF_SUB | BPF_X: update_on_xread(ctx); emit(ARM_SUB_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_MUL_K: + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ emit_mov_i(r_scratch, k, ctx); emit(ARM_MUL(r_A, r_A, r_scratch), ctx); break; - case BPF_S_ALU_MUL_X: + case BPF_ALU | BPF_MUL | BPF_X: update_on_xread(ctx); emit(ARM_MUL(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_DIV_K: + case BPF_ALU | BPF_DIV | BPF_K: if (k == 1) break; emit_mov_i(r_scratch, k, ctx); emit_udiv(r_A, r_A, r_scratch, ctx); break; - case BPF_S_ALU_DIV_X: + case BPF_ALU | BPF_DIV | BPF_X: update_on_xread(ctx); emit(ARM_CMP_I(r_X, 0), ctx); emit_err_ret(ARM_COND_EQ, ctx); emit_udiv(r_A, r_A, r_X, ctx); break; - case BPF_S_ALU_OR_K: + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ OP_IMM3(ARM_ORR, r_A, r_A, k, ctx); break; - case BPF_S_ALU_OR_X: + case BPF_ALU | BPF_OR | BPF_X: update_on_xread(ctx); emit(ARM_ORR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_XOR_K: + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K; */ OP_IMM3(ARM_EOR, r_A, r_A, k, ctx); break; - case BPF_S_ANC_ALU_XOR_X: - case BPF_S_ALU_XOR_X: + case BPF_ANC | SKF_AD_ALU_XOR_X: + case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */ update_on_xread(ctx); emit(ARM_EOR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_AND_K: + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ OP_IMM3(ARM_AND, r_A, r_A, k, ctx); break; - case BPF_S_ALU_AND_X: + case BPF_ALU | BPF_AND | BPF_X: update_on_xread(ctx); emit(ARM_AND_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_LSH_K: + case BPF_ALU | BPF_LSH | BPF_K: if (unlikely(k > 31)) return -1; emit(ARM_LSL_I(r_A, r_A, k), ctx); break; - case BPF_S_ALU_LSH_X: + case BPF_ALU | BPF_LSH | BPF_X: update_on_xread(ctx); emit(ARM_LSL_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_RSH_K: + case BPF_ALU | BPF_RSH | BPF_K: if (unlikely(k > 31)) return -1; emit(ARM_LSR_I(r_A, r_A, k), ctx); break; - case BPF_S_ALU_RSH_X: + case BPF_ALU | BPF_RSH | BPF_X: update_on_xread(ctx); emit(ARM_LSR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_NEG: + case BPF_ALU | BPF_NEG: /* A = -A */ emit(ARM_RSB_I(r_A, r_A, 0), ctx); break; - case BPF_S_JMP_JA: + case BPF_JMP | BPF_JA: /* pc += K */ emit(ARM_B(b_imm(i + k + 1, ctx)), ctx); break; - case BPF_S_JMP_JEQ_K: + case BPF_JMP | BPF_JEQ | BPF_K: /* pc += (A == K) ? pc->jt : pc->jf */ condt = ARM_COND_EQ; goto cmp_imm; - case BPF_S_JMP_JGT_K: + case BPF_JMP | BPF_JGT | BPF_K: /* pc += (A > K) ? pc->jt : pc->jf */ condt = ARM_COND_HI; goto cmp_imm; - case BPF_S_JMP_JGE_K: + case BPF_JMP | BPF_JGE | BPF_K: /* pc += (A >= K) ? pc->jt : pc->jf */ condt = ARM_COND_HS; cmp_imm: @@ -731,22 +726,22 @@ static int build_body(struct jit_ctx *ctx) _emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1, ctx)), ctx); break; - case BPF_S_JMP_JEQ_X: + case BPF_JMP | BPF_JEQ | BPF_X: /* pc += (A == X) ? pc->jt : pc->jf */ condt = ARM_COND_EQ; goto cmp_x; - case BPF_S_JMP_JGT_X: + case BPF_JMP | BPF_JGT | BPF_X: /* pc += (A > X) ? pc->jt : pc->jf */ condt = ARM_COND_HI; goto cmp_x; - case BPF_S_JMP_JGE_X: + case BPF_JMP | BPF_JGE | BPF_X: /* pc += (A >= X) ? pc->jt : pc->jf */ condt = ARM_COND_CS; cmp_x: update_on_xread(ctx); emit(ARM_CMP_R(r_A, r_X), ctx); goto cond_jump; - case BPF_S_JMP_JSET_K: + case BPF_JMP | BPF_JSET | BPF_K: /* pc += (A & K) ? pc->jt : pc->jf */ condt = ARM_COND_NE; /* not set iff all zeroes iff Z==1 iff EQ */ @@ -759,16 +754,16 @@ static int build_body(struct jit_ctx *ctx) emit(ARM_TST_I(r_A, imm12), ctx); } goto cond_jump; - case BPF_S_JMP_JSET_X: + case BPF_JMP | BPF_JSET | BPF_X: /* pc += (A & X) ? pc->jt : pc->jf */ update_on_xread(ctx); condt = ARM_COND_NE; emit(ARM_TST_R(r_A, r_X), ctx); goto cond_jump; - case BPF_S_RET_A: + case BPF_RET | BPF_A: emit(ARM_MOV_R(ARM_R0, r_A), ctx); goto b_epilogue; - case BPF_S_RET_K: + case BPF_RET | BPF_K: if ((k == 0) && (ctx->ret0_fp_idx < 0)) ctx->ret0_fp_idx = i; emit_mov_i(ARM_R0, k, ctx); @@ -776,17 +771,17 @@ static int build_body(struct jit_ctx *ctx) if (i != ctx->skf->len - 1) emit(ARM_B(b_imm(prog->len, ctx)), ctx); break; - case BPF_S_MISC_TAX: + case BPF_MISC | BPF_TAX: /* X = A */ ctx->seen |= SEEN_X; emit(ARM_MOV_R(r_X, r_A), ctx); break; - case BPF_S_MISC_TXA: + case BPF_MISC | BPF_TXA: /* A = X */ update_on_xread(ctx); emit(ARM_MOV_R(r_A, r_X), ctx); break; - case BPF_S_ANC_PROTOCOL: + case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol) */ ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, @@ -795,7 +790,7 @@ static int build_body(struct jit_ctx *ctx) emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx); emit_swap16(r_A, r_scratch, ctx); break; - case BPF_S_ANC_CPU: + case BPF_ANC | SKF_AD_CPU: /* r_scratch = current_thread_info() */ OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx); /* A = current_thread_info()->cpu */ @@ -803,7 +798,7 @@ static int build_body(struct jit_ctx *ctx) off = offsetof(struct thread_info, cpu); emit(ARM_LDR_I(r_A, r_scratch, off), ctx); break; - case BPF_S_ANC_IFINDEX: + case BPF_ANC | SKF_AD_IFINDEX: /* A = skb->dev->ifindex */ ctx->seen |= SEEN_SKB; off = offsetof(struct sk_buff, dev); @@ -817,30 +812,30 @@ static int build_body(struct jit_ctx *ctx) off = offsetof(struct net_device, ifindex); emit(ARM_LDR_I(r_A, r_scratch, off), ctx); break; - case BPF_S_ANC_MARK: + case BPF_ANC | SKF_AD_MARK: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); off = offsetof(struct sk_buff, mark); emit(ARM_LDR_I(r_A, r_skb, off), ctx); break; - case BPF_S_ANC_RXHASH: + case BPF_ANC | SKF_AD_RXHASH: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); off = offsetof(struct sk_buff, hash); emit(ARM_LDR_I(r_A, r_skb, off), ctx); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); off = offsetof(struct sk_buff, vlan_tci); emit(ARM_LDRH_I(r_A, r_skb, off), ctx); - if (inst->code == BPF_S_ANC_VLAN_TAG) + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx); else OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx); break; - case BPF_S_ANC_QUEUE: + case BPF_ANC | SKF_AD_QUEUE: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); diff --git a/arch/blackfin/configs/BF526-EZBRD_defconfig b/arch/blackfin/configs/BF526-EZBRD_defconfig index 1759fad54017..e66ba31ef84d 100644 --- a/arch/blackfin/configs/BF526-EZBRD_defconfig +++ b/arch/blackfin/configs/BF526-EZBRD_defconfig @@ -53,7 +53,6 @@ CONFIG_IP_PNP=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -63,6 +62,7 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=m +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_RAM=y CONFIG_SCSI=y # CONFIG_SCSI_PROC_FS is not set diff --git a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig index 357729682c00..0207c588c19f 100644 --- a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig +++ b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig @@ -58,7 +58,6 @@ CONFIG_BFIN_SIR0=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=m CONFIG_MTD_BLOCK=y CONFIG_MTD_JEDECPROBE=m CONFIG_MTD_RAM=y @@ -66,6 +65,7 @@ CONFIG_MTD_ROM=m CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=m +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_RAM=y CONFIG_SCSI=y # CONFIG_SCSI_PROC_FS is not set diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig index 2e73a5d33da8..99c131ba7d90 100644 --- a/arch/blackfin/configs/BF527-EZKIT_defconfig +++ b/arch/blackfin/configs/BF527-EZKIT_defconfig @@ -57,7 +57,6 @@ CONFIG_BFIN_SIR0=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=m CONFIG_MTD_BLOCK=y CONFIG_MTD_JEDECPROBE=m CONFIG_MTD_RAM=y @@ -65,6 +64,7 @@ CONFIG_MTD_ROM=m CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=m +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_RAM=y CONFIG_SCSI=y # CONFIG_SCSI_PROC_FS is not set diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig index f0a2ddf5de46..38cb17d218d4 100644 --- a/arch/blackfin/configs/BF548-EZKIT_defconfig +++ b/arch/blackfin/configs/BF548-EZKIT_defconfig @@ -64,7 +64,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -75,6 +74,7 @@ CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_BF5XX=y # CONFIG_MTD_NAND_BF5XX_HWECC is not set +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_RAM=y # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig index 4ca39ab6b2bf..a7e9bfd84183 100644 --- a/arch/blackfin/configs/BF609-EZKIT_defconfig +++ b/arch/blackfin/configs/BF609-EZKIT_defconfig @@ -57,7 +57,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -65,6 +64,7 @@ CONFIG_MTD_CFI_STAA=y CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_M25P80=y +CONFIG_MTD_SPI_NOR=y CONFIG_MTD_UBI=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y diff --git a/arch/blackfin/configs/BlackStamp_defconfig b/arch/blackfin/configs/BlackStamp_defconfig index 3853c473b443..f4a9200e1ab1 100644 --- a/arch/blackfin/configs/BlackStamp_defconfig +++ b/arch/blackfin/configs/BlackStamp_defconfig @@ -45,7 +45,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=m CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=m CONFIG_MTD_CFI_AMDSTD=m @@ -53,7 +52,7 @@ CONFIG_MTD_RAM=y CONFIG_MTD_ROM=m CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_M25P80=y -# CONFIG_M25PXX_USE_FAST_READ is not set +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/blackfin/configs/H8606_defconfig b/arch/blackfin/configs/H8606_defconfig index f754e490bbfd..0ff97d8d047a 100644 --- a/arch/blackfin/configs/H8606_defconfig +++ b/arch/blackfin/configs/H8606_defconfig @@ -36,13 +36,12 @@ CONFIG_IRTTY_SIR=m # CONFIG_WIRELESS is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_RAM=y CONFIG_MTD_ROM=y CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_M25P80=y -# CONFIG_M25PXX_USE_FAST_READ is not set +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_RAM=y CONFIG_MISC_DEVICES=y CONFIG_EEPROM_AT25=y diff --git a/arch/blackfin/include/asm/dma.h b/arch/blackfin/include/asm/dma.h index 8d1e4c2d2c36..40e9c2bbc6e3 100644 --- a/arch/blackfin/include/asm/dma.h +++ b/arch/blackfin/include/asm/dma.h @@ -316,6 +316,8 @@ static inline void disable_dma(unsigned int channel) } static inline void enable_dma(unsigned int channel) { + dma_ch[channel].regs->curr_x_count = 0; + dma_ch[channel].regs->curr_y_count = 0; dma_ch[channel].regs->cfg |= DMAEN; } int set_dma_callback(unsigned int channel, irq_handler_t callback, void *data); diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c index d0989290f54c..6f4bac969bf7 100644 --- a/arch/blackfin/mach-bf533/boards/stamp.c +++ b/arch/blackfin/mach-bf533/boards/stamp.c @@ -17,6 +17,7 @@ #if IS_ENABLED(CONFIG_USB_ISP1362_HCD) #include #endif +#include #include #include #include diff --git a/arch/mips/bcm47xx/sprom.c b/arch/mips/bcm47xx/sprom.c index a8b5408dd349..da4cdb16844e 100644 --- a/arch/mips/bcm47xx/sprom.c +++ b/arch/mips/bcm47xx/sprom.c @@ -168,6 +168,7 @@ static void nvram_read_alpha2(const char *prefix, const char *name, static void bcm47xx_fill_sprom_r1234589(struct ssb_sprom *sprom, const char *prefix, bool fallback) { + nvram_read_u16(prefix, NULL, "devid", &sprom->dev_id, 0, fallback); nvram_read_u8(prefix, NULL, "ledbh0", &sprom->gpio0, 0xff, fallback); nvram_read_u8(prefix, NULL, "ledbh1", &sprom->gpio1, 0xff, fallback); nvram_read_u8(prefix, NULL, "ledbh2", &sprom->gpio2, 0xff, fallback); diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 21c9f304e96c..790352f93700 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -235,11 +235,6 @@ config PPC_EARLY_DEBUG_USBGECKO Select this to enable early debugging for Nintendo GameCube/Wii consoles via an external USB Gecko adapter. -config PPC_EARLY_DEBUG_WSP - bool "Early debugging via WSP's internal UART" - depends on PPC_WSP - select PPC_UDBG_16550 - config PPC_EARLY_DEBUG_PS3GELIC bool "Early debugging through the PS3 Ethernet port" depends on PPC_PS3 diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 426dce7ae7c4..ccc25eddbcb8 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -333,8 +333,8 @@ $(addprefix $(obj)/, $(initrd-y)): $(obj)/ramdisk.image.gz $(obj)/zImage.initrd.%: vmlinux $(wrapperbits) $(call if_changed,wrap,$*,,,$(obj)/ramdisk.image.gz) -$(obj)/zImage.%: vmlinux $(wrapperbits) - $(call if_changed,wrap,$*) +$(addprefix $(obj)/, $(sort $(filter zImage.%, $(image-y)))): vmlinux $(wrapperbits) + $(call if_changed,wrap,$(subst $(obj)/zImage.,,$@)) # dtbImage% - a dtbImage is a zImage with an embedded device tree blob $(obj)/dtbImage.initrd.%: vmlinux $(wrapperbits) $(obj)/%.dtb diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig deleted file mode 100644 index 4f35fc462385..000000000000 --- a/arch/powerpc/configs/chroma_defconfig +++ /dev/null @@ -1,307 +0,0 @@ -CONFIG_PPC64=y -CONFIG_PPC_BOOK3E_64=y -# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set -CONFIG_SMP=y -CONFIG_NR_CPUS=256 -CONFIG_EXPERIMENTAL=y -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y -CONFIG_TASKSTATS=y -CONFIG_TASK_DELAY_ACCT=y -CONFIG_TASK_XACCT=y -CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_AUDIT=y -CONFIG_AUDITSYSCALL=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=19 -CONFIG_CGROUPS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEMCG=y -CONFIG_CGROUP_MEMCG_SWAP=y -CONFIG_NAMESPACES=y -CONFIG_RELAY=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_INITRAMFS_COMPRESSION_GZIP=y -CONFIG_KALLSYMS_ALL=y -CONFIG_EMBEDDED=y -CONFIG_PERF_EVENTS=y -CONFIG_PROFILING=y -CONFIG_OPROFILE=y -CONFIG_KPROBES=y -CONFIG_MODULES=y -CONFIG_MODULE_FORCE_LOAD=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_SCOM_DEBUGFS=y -CONFIG_PPC_A2_DD2=y -CONFIG_KVM_GUEST=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_HZ_100=y -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_BINFMT_MISC=y -CONFIG_NUMA=y -# CONFIG_MIGRATION is not set -CONFIG_PPC_64K_PAGES=y -CONFIG_SCHED_SMT=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" -# CONFIG_SECCOMP is not set -CONFIG_PCIEPORTBUS=y -# CONFIG_PCIEASPM is not set -CONFIG_PCI_MSI=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_XFRM_SUB_POLICY=y -CONFIG_XFRM_STATISTICS=y -CONFIG_NET_KEY=m -CONFIG_NET_KEY_MIGRATE=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_ROUTE_MULTIPATH=y -CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_NET_IPIP=y -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_IPV6=y -CONFIG_IPV6_PRIVACY=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y -CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_INET6_AH=y -CONFIG_INET6_ESP=y -CONFIG_INET6_IPCOMP=y -CONFIG_IPV6_MIP6=y -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=y -CONFIG_IPV6_TUNNEL=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_IPV6_MROUTE=y -CONFIG_IPV6_PIMSM_V2=y -CONFIG_NETFILTER=y -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_UDPLITE=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_CONNMARK=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_IPRANGE=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_OWNER=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_RATEEST=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_RECENT=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_NET_TCPPROBE=y -# CONFIG_WIRELESS is not set -CONFIG_NET_9P=y -CONFIG_NET_9P_DEBUG=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_DEVTMPFS=y -CONFIG_MTD=y -CONFIG_MTD_CHAR=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_LE_BYTE_SWAP=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_CFI_STAA=y -CONFIG_MTD_PHYSMAP_OF=y -CONFIG_PROC_DEVICETREE=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=65536 -CONFIG_CDROM_PKTCDVD=y -CONFIG_MISC_DEVICES=y -CONFIG_BLK_DEV_SD=y -CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=y -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_SPI_ATTRS=y -CONFIG_SCSI_FC_ATTRS=y -CONFIG_SCSI_ISCSI_ATTRS=m -CONFIG_SCSI_SAS_ATTRS=m -CONFIG_SCSI_SRP_ATTRS=y -CONFIG_ATA=y -CONFIG_SATA_AHCI=y -CONFIG_SATA_SIL24=y -CONFIG_SATA_MV=y -CONFIG_SATA_SIL=y -CONFIG_PATA_CMD64X=y -CONFIG_PATA_MARVELL=y -CONFIG_PATA_SIL680=y -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=y -CONFIG_BLK_DEV_DM=y -CONFIG_DM_CRYPT=y -CONFIG_DM_SNAPSHOT=y -CONFIG_DM_MIRROR=y -CONFIG_DM_ZERO=y -CONFIG_DM_UEVENT=y -CONFIG_NETDEVICES=y -CONFIG_TUN=y -CONFIG_E1000E=y -CONFIG_TIGON3=y -# CONFIG_WLAN is not set -# CONFIG_INPUT is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_HW_RANDOM=y -CONFIG_RAW_DRIVER=y -CONFIG_MAX_RAW_DEVS=1024 -# CONFIG_HWMON is not set -# CONFIG_VGA_ARB is not set -# CONFIG_USB_SUPPORT is not set -CONFIG_EDAC=y -CONFIG_EDAC_MM_EDAC=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_DS1511=y -CONFIG_RTC_DRV_DS1553=y -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT2_FS_XIP=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y -CONFIG_EXT4_FS=y -# CONFIG_DNOTIFY is not set -CONFIG_FUSE_FS=y -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_CONFIGFS_FS=m -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=y -CONFIG_NFS_V4_1=y -CONFIG_ROOT_NFS=y -CONFIG_CIFS=y -CONFIG_CIFS_WEAK_PW_HASH=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=y -CONFIG_CRC_CCITT=m -CONFIG_CRC_T10DIF=y -CONFIG_LIBCRC32C=m -CONFIG_PRINTK_TIME=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_STRIP_ASM_SYMS=y -CONFIG_DETECT_HUNG_TASK=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_INFO=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_PPC_EMULATED_STATS=y -CONFIG_XMON=y -CONFIG_XMON_DEFAULT=y -CONFIG_IRQ_DOMAIN_DEBUG=y -CONFIG_PPC_EARLY_DEBUG=y -CONFIG_KEYS_DEBUG_PROC_KEYS=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CCM=m -CONFIG_CRYPTO_GCM=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_LZO=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_VIRTUALIZATION=y diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h index f42e9baf3a4e..7c8608b09694 100644 --- a/arch/powerpc/include/asm/cpm2.h +++ b/arch/powerpc/include/asm/cpm2.h @@ -489,7 +489,6 @@ typedef struct scc_trans { #define FCC_GFMR_TCI ((uint)0x20000000) #define FCC_GFMR_TRX ((uint)0x10000000) #define FCC_GFMR_TTX ((uint)0x08000000) -#define FCC_GFMR_TTX ((uint)0x08000000) #define FCC_GFMR_CDP ((uint)0x04000000) #define FCC_GFMR_CTSP ((uint)0x02000000) #define FCC_GFMR_CDS ((uint)0x01000000) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index b76f58c124ca..fab7743c2640 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -254,6 +254,7 @@ void *eeh_pe_traverse(struct eeh_pe *root, void *eeh_pe_dev_traverse(struct eeh_pe *root, eeh_traverse_func fn, void *flag); void eeh_pe_restore_bars(struct eeh_pe *pe); +const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); void *eeh_dev_init(struct device_node *dn, void *data); diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h index 89d5670b2eeb..1e551a2d6f82 100644 --- a/arch/powerpc/include/asm/eeh_event.h +++ b/arch/powerpc/include/asm/eeh_event.h @@ -33,7 +33,7 @@ struct eeh_event { int eeh_event_init(void); int eeh_send_failure_event(struct eeh_pe *pe); -void eeh_remove_event(struct eeh_pe *pe); +void eeh_remove_event(struct eeh_pe *pe, bool force); void eeh_handle_event(struct eeh_pe *pe); #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index 901dac6b6cb7..d0918e09557f 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -223,10 +223,6 @@ typedef struct { unsigned int id; unsigned int active; unsigned long vdso_base; -#ifdef CONFIG_PPC_ICSWX - struct spinlock *cop_lockp; /* guard cop related stuff */ - unsigned long acop; /* mask of enabled coprocessor types */ -#endif /* CONFIG_PPC_ICSWX */ #ifdef CONFIG_PPC_MM_SLICES u64 low_slices_psize; /* SLB page size encodings */ u64 high_slices_psize; /* 4 bits per slice for now */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index cb15cbb51600..460018889ba9 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -599,9 +599,9 @@ enum { }; struct OpalIoPhbErrorCommon { - uint32_t version; - uint32_t ioType; - uint32_t len; + __be32 version; + __be32 ioType; + __be32 len; }; struct OpalIoP7IOCPhbErrorData { @@ -666,64 +666,64 @@ struct OpalIoP7IOCPhbErrorData { struct OpalIoPhb3ErrorData { struct OpalIoPhbErrorCommon common; - uint32_t brdgCtl; + __be32 brdgCtl; /* PHB3 UTL regs */ - uint32_t portStatusReg; - uint32_t rootCmplxStatus; - uint32_t busAgentStatus; + __be32 portStatusReg; + __be32 rootCmplxStatus; + __be32 busAgentStatus; /* PHB3 cfg regs */ - uint32_t deviceStatus; - uint32_t slotStatus; - uint32_t linkStatus; - uint32_t devCmdStatus; - uint32_t devSecStatus; + __be32 deviceStatus; + __be32 slotStatus; + __be32 linkStatus; + __be32 devCmdStatus; + __be32 devSecStatus; /* cfg AER regs */ - uint32_t rootErrorStatus; - uint32_t uncorrErrorStatus; - uint32_t corrErrorStatus; - uint32_t tlpHdr1; - uint32_t tlpHdr2; - uint32_t tlpHdr3; - uint32_t tlpHdr4; - uint32_t sourceId; + __be32 rootErrorStatus; + __be32 uncorrErrorStatus; + __be32 corrErrorStatus; + __be32 tlpHdr1; + __be32 tlpHdr2; + __be32 tlpHdr3; + __be32 tlpHdr4; + __be32 sourceId; - uint32_t rsv3; + __be32 rsv3; /* Record data about the call to allocate a buffer */ - uint64_t errorClass; - uint64_t correlator; + __be64 errorClass; + __be64 correlator; - uint64_t nFir; /* 000 */ - uint64_t nFirMask; /* 003 */ - uint64_t nFirWOF; /* 008 */ + __be64 nFir; /* 000 */ + __be64 nFirMask; /* 003 */ + __be64 nFirWOF; /* 008 */ /* PHB3 MMIO Error Regs */ - uint64_t phbPlssr; /* 120 */ - uint64_t phbCsr; /* 110 */ - uint64_t lemFir; /* C00 */ - uint64_t lemErrorMask; /* C18 */ - uint64_t lemWOF; /* C40 */ - uint64_t phbErrorStatus; /* C80 */ - uint64_t phbFirstErrorStatus; /* C88 */ - uint64_t phbErrorLog0; /* CC0 */ - uint64_t phbErrorLog1; /* CC8 */ - uint64_t mmioErrorStatus; /* D00 */ - uint64_t mmioFirstErrorStatus; /* D08 */ - uint64_t mmioErrorLog0; /* D40 */ - uint64_t mmioErrorLog1; /* D48 */ - uint64_t dma0ErrorStatus; /* D80 */ - uint64_t dma0FirstErrorStatus; /* D88 */ - uint64_t dma0ErrorLog0; /* DC0 */ - uint64_t dma0ErrorLog1; /* DC8 */ - uint64_t dma1ErrorStatus; /* E00 */ - uint64_t dma1FirstErrorStatus; /* E08 */ - uint64_t dma1ErrorLog0; /* E40 */ - uint64_t dma1ErrorLog1; /* E48 */ - uint64_t pestA[OPAL_PHB3_NUM_PEST_REGS]; - uint64_t pestB[OPAL_PHB3_NUM_PEST_REGS]; + __be64 phbPlssr; /* 120 */ + __be64 phbCsr; /* 110 */ + __be64 lemFir; /* C00 */ + __be64 lemErrorMask; /* C18 */ + __be64 lemWOF; /* C40 */ + __be64 phbErrorStatus; /* C80 */ + __be64 phbFirstErrorStatus; /* C88 */ + __be64 phbErrorLog0; /* CC0 */ + __be64 phbErrorLog1; /* CC8 */ + __be64 mmioErrorStatus; /* D00 */ + __be64 mmioFirstErrorStatus; /* D08 */ + __be64 mmioErrorLog0; /* D40 */ + __be64 mmioErrorLog1; /* D48 */ + __be64 dma0ErrorStatus; /* D80 */ + __be64 dma0FirstErrorStatus; /* D88 */ + __be64 dma0ErrorLog0; /* DC0 */ + __be64 dma0ErrorLog1; /* DC8 */ + __be64 dma1ErrorStatus; /* E00 */ + __be64 dma1FirstErrorStatus; /* E08 */ + __be64 dma1ErrorLog0; /* E40 */ + __be64 dma1ErrorLog1; /* E48 */ + __be64 pestA[OPAL_PHB3_NUM_PEST_REGS]; + __be64 pestB[OPAL_PHB3_NUM_PEST_REGS]; }; enum { @@ -851,8 +851,8 @@ int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t erro int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action); int64_t opal_get_epow_status(__be64 *status); int64_t opal_set_system_attention_led(uint8_t led_action); -int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, - uint16_t *pci_error_type, uint16_t *severity); +int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe, + __be16 *pci_error_type, __be16 *severity); int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); int64_t opal_reinit_cpus(uint64_t flags); diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h index 3d52a1132f3d..3ba9c6f096fc 100644 --- a/arch/powerpc/include/asm/reg_a2.h +++ b/arch/powerpc/include/asm/reg_a2.h @@ -110,15 +110,6 @@ #define TLB1_UR ASM_CONST(0x0000000000000002) #define TLB1_SR ASM_CONST(0x0000000000000001) -#ifdef CONFIG_PPC_EARLY_DEBUG_WSP -#define WSP_UART_PHYS 0xffc000c000 -/* This needs to be careful chosen to hit a !0 congruence class - * in the TLB since we bolt it in way 3, which is already occupied - * by our linear mapping primary bolted entry in CC 0. - */ -#define WSP_UART_VIRT 0xf000000000001000 -#endif - /* A2 erativax attributes definitions */ #define ERATIVAX_RS_IS_ALL 0x000 #define ERATIVAX_RS_IS_TID 0x040 diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 0e83e7d8c73f..58abeda64cb7 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -16,13 +16,15 @@ struct thread_struct; extern struct task_struct *_switch(struct thread_struct *prev, struct thread_struct *next); #ifdef CONFIG_PPC_BOOK3S_64 -static inline void save_tar(struct thread_struct *prev) +static inline void save_early_sprs(struct thread_struct *prev) { if (cpu_has_feature(CPU_FTR_ARCH_207S)) prev->tar = mfspr(SPRN_TAR); + if (cpu_has_feature(CPU_FTR_DSCR)) + prev->dscr = mfspr(SPRN_DSCR); } #else -static inline void save_tar(struct thread_struct *prev) {} +static inline void save_early_sprs(struct thread_struct *prev) {} #endif extern void enable_kernel_fp(void); @@ -84,6 +86,8 @@ static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 /* EBB perf events are not inherited, so clear all EBB state. */ + t->thread.ebbrr = 0; + t->thread.ebbhr = 0; t->thread.bescr = 0; t->thread.mmcr2 = 0; t->thread.mmcr0 = 0; diff --git a/arch/powerpc/include/asm/wsp.h b/arch/powerpc/include/asm/wsp.h deleted file mode 100644 index c7dc83088a33..000000000000 --- a/arch/powerpc/include/asm/wsp.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright 2011 Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#ifndef __ASM_POWERPC_WSP_H -#define __ASM_POWERPC_WSP_H - -extern int wsp_get_chip_id(struct device_node *dn); - -#endif /* __ASM_POWERPC_WSP_H */ diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 5b7657959faa..de2c0e4ee1aa 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -41,5 +41,6 @@ #define PPC_FEATURE2_EBB 0x10000000 #define PPC_FEATURE2_ISEL 0x08000000 #define PPC_FEATURE2_TAR 0x04000000 +#define PPC_FEATURE2_VEC_CRYPTO 0x02000000 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fab19ec25597..670c312d914e 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -43,7 +43,6 @@ obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o -obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S deleted file mode 100644 index 61f079e05b61..000000000000 --- a/arch/powerpc/kernel/cpu_setup_a2.S +++ /dev/null @@ -1,120 +0,0 @@ -/* - * A2 specific assembly support code - * - * Copyright 2009 Ben Herrenschmidt, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include - -/* - * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity. - * This also prevents external LPID accesses but that isn't a problem when not a - * guest. Under PV, this setting will be ignored and MMUCR will return the right - * number of PID bits we can use. - */ -#define MMUCR1_EXTEND_PID \ - (MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \ - MMUCR1_DTTID | MMUCR1_DCCD) - -/* - * Use extended PIDs if enabled. - * Don't clear the ERATs on context sync events and enable I & D LRU. - * Enable ERAT back invalidate when tlbwe overwrites an entry. - */ -#define INITIAL_MMUCR1 \ - (MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \ - MMUCR1_DRRE | MMUCR1_TLBWE_BINV) - -_GLOBAL(__setup_cpu_a2) - /* Some of these are actually thread local and some are - * core local but doing it always won't hurt - */ - -#ifdef CONFIG_PPC_ICSWX - /* Make sure ACOP starts out as zero */ - li r3,0 - mtspr SPRN_ACOP,r3 - - /* Skip the following if we are in Guest mode */ - mfmsr r3 - andis. r0,r3,MSR_GS@h - bne _icswx_skip_guest - - /* Enable icswx instruction */ - mfspr r3,SPRN_A2_CCR2 - ori r3,r3,A2_CCR2_ENABLE_ICSWX - mtspr SPRN_A2_CCR2,r3 - - /* Unmask all CTs in HACOP */ - li r3,-1 - mtspr SPRN_HACOP,r3 -_icswx_skip_guest: -#endif /* CONFIG_PPC_ICSWX */ - - /* Enable doorbell */ - mfspr r3,SPRN_A2_CCR2 - oris r3,r3,A2_CCR2_ENABLE_PC@h - mtspr SPRN_A2_CCR2,r3 - isync - - /* Setup CCR0 to disable power saving for now as it's busted - * in the current implementations. Setup CCR1 to wake on - * interrupts normally (we write the default value but who - * knows what FW may have clobbered...) - */ - li r3,0 - mtspr SPRN_A2_CCR0, r3 - LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f) - mtspr SPRN_A2_CCR1, r3 - - /* Initialise MMUCR1 */ - lis r3,INITIAL_MMUCR1@h - ori r3,r3,INITIAL_MMUCR1@l - mtspr SPRN_MMUCR1,r3 - - /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ - LOAD_REG_IMMEDIATE(r3, 0x000a7531) - mtspr SPRN_MMUCR2,r3 - - /* Set MMUCR3 to write all thids bit to the TLB */ - LOAD_REG_IMMEDIATE(r3, 0x0000000f) - mtspr SPRN_MMUCR3,r3 - - /* Don't do ERAT stuff if running guest mode */ - mfmsr r3 - andis. r0,r3,MSR_GS@h - bne 1f - - /* Now set the I-ERAT watermark to 15 */ - lis r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h - mtspr SPRN_MMUCR0, r4 - li r4,A2_IERAT_SIZE-1 - PPC_ERATWE(R4,R4,3) - - /* Now set the D-ERAT watermark to 31 */ - lis r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h - mtspr SPRN_MMUCR0, r4 - li r4,A2_DERAT_SIZE-1 - PPC_ERATWE(R4,R4,3) - - /* And invalidate the beast just in case. That won't get rid of - * a bolted entry though it will be in LRU and so will go away eventually - * but let's not bother for now - */ - PPC_ERATILX(0,0,R0) -1: - blr - -_GLOBAL(__restore_cpu_a2) - b __setup_cpu_a2 diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 1557e7c2c7e1..46733535cc0b 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -56,6 +56,7 @@ _GLOBAL(__setup_cpu_power8) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH bl __init_LPCR bl __init_HFSCR bl __init_tlb_power8 @@ -74,6 +75,7 @@ _GLOBAL(__restore_cpu_power8) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH bl __init_LPCR bl __init_HFSCR bl __init_tlb_power8 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index c1faade6506d..965291b4c2fa 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -109,7 +109,8 @@ extern void __restore_cpu_e6500(void); PPC_FEATURE_PSERIES_PERFMON_COMPAT) #define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR) + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) @@ -2148,44 +2149,6 @@ static struct cpu_spec __initdata cpu_specs[] = { } #endif /* CONFIG_PPC32 */ #endif /* CONFIG_E500 */ - -#ifdef CONFIG_PPC_A2 - { /* Standard A2 (>= DD2) + FPU core */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00480000, - .cpu_name = "A2 (>= DD2)", - .cpu_features = CPU_FTRS_A2, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTRS_A2, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 0, - .cpu_setup = __setup_cpu_a2, - .cpu_restore = __restore_cpu_a2, - .machine_check = machine_check_generic, - .platform = "ppca2", - }, - { /* This is a default entry to get going, to be replaced by - * a real one at some stage - */ -#define CPU_FTRS_BASE_BOOK3E (CPU_FTR_USE_TB | \ - CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_SMT | \ - CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "Book3E", - .cpu_features = CPU_FTRS_BASE_BOOK3E, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX | - MMU_FTR_USE_TLBIVAX_BCAST | - MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 0, - .machine_check = machine_check_generic, - .platform = "power6", - }, -#endif /* CONFIG_PPC_A2 */ }; static struct cpu_spec the_cpu_spec; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 7051ea3101b9..86e25702aaca 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -330,8 +330,8 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED); eeh_serialize_unlock(flags); - pr_err("EEH: PHB#%x failure detected\n", - phb_pe->phb->global_number); + pr_err("EEH: PHB#%x failure detected, location: %s\n", + phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe)); dump_stack(); eeh_send_failure_event(phb_pe); @@ -358,10 +358,11 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) int eeh_dev_check_failure(struct eeh_dev *edev) { int ret; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); unsigned long flags; struct device_node *dn; struct pci_dev *dev; - struct eeh_pe *pe; + struct eeh_pe *pe, *parent_pe, *phb_pe; int rc = 0; const char *location; @@ -439,14 +440,34 @@ int eeh_dev_check_failure(struct eeh_dev *edev) */ if ((ret < 0) || (ret == EEH_STATE_NOT_SUPPORT) || - (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == - (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { + ((ret & active_flags) == active_flags)) { eeh_stats.false_positives++; pe->false_positives++; rc = 0; goto dn_unlock; } + /* + * It should be corner case that the parent PE has been + * put into frozen state as well. We should take care + * that at first. + */ + parent_pe = pe->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + ret = eeh_ops->get_state(parent_pe, NULL); + if (ret > 0 && + (ret & active_flags) != active_flags) + pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + eeh_stats.slot_resets++; /* Avoid repeated reports of this failure, including problems @@ -460,8 +481,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * a stack trace will help the device-driver authors figure * out what happened. So print that out. */ - pr_err("EEH: Frozen PE#%x detected on PHB#%x\n", - pe->addr, pe->phb->global_number); + phb_pe = eeh_phb_pe_get(pe->phb); + pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pe->phb->global_number, pe->addr); + pr_err("EEH: PE location: %s, PHB location: %s\n", + eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); dump_stack(); eeh_send_failure_event(pe); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7100a5b96e70..420da61d4ce0 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -447,8 +447,9 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) * PE reset (for 3 times), we try to clear the frozen state * for 3 times as well. */ -static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) +static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { + struct eeh_pe *pe = (struct eeh_pe *)data; int i, rc; for (i = 0; i < 3; i++) { @@ -461,13 +462,24 @@ static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) } /* The PE has been isolated, clear it */ - if (rc) + if (rc) { pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n", __func__, pe->phb->global_number, pe->addr, rc); - else + return (void *)pe; + } + + return NULL; +} + +static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) +{ + void *rc; + + rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL); + if (!rc) eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - return rc; + return rc ? -EIO : 0; } /** @@ -758,7 +770,7 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events */ - eeh_remove_event(NULL); + eeh_remove_event(NULL, true); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -777,7 +789,7 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events of the PHB */ - eeh_remove_event(pe); + eeh_remove_event(pe, true); if (rc == EEH_NEXT_ERR_DEAD_PHB) eeh_pe_state_mark(pe, EEH_PE_ISOLATED); diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 72d748b56c86..4eefb6e34dbb 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -152,24 +152,33 @@ int eeh_send_failure_event(struct eeh_pe *pe) /** * eeh_remove_event - Remove EEH event from the queue * @pe: Event binding to the PE + * @force: Event will be removed unconditionally * * On PowerNV platform, we might have subsequent coming events * is part of the former one. For that case, those subsequent * coming events are totally duplicated and unnecessary, thus * they should be removed. */ -void eeh_remove_event(struct eeh_pe *pe) +void eeh_remove_event(struct eeh_pe *pe, bool force) { unsigned long flags; struct eeh_event *event, *tmp; + /* + * If we have NULL PE passed in, we have dead IOC + * or we're sure we can report all existing errors + * by the caller. + * + * With "force", the event with associated PE that + * have been isolated, the event won't be removed + * to avoid event lost. + */ spin_lock_irqsave(&eeh_eventlist_lock, flags); list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) { - /* - * If we don't have valid PE passed in, that means - * we already have event corresponding to dead IOC - * and all events should be purged. - */ + if (!force && event->pe && + (event->pe->state & EEH_PE_ISOLATED)) + continue; + if (!pe) { list_del(&event->list); kfree(event); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 995c2a284630..fbd01eba4473 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -791,6 +791,66 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL); } +/** + * eeh_pe_loc_get - Retrieve location code binding to the given PE + * @pe: EEH PE + * + * Retrieve the location code of the given PE. If the primary PE bus + * is root bus, we will grab location code from PHB device tree node + * or root port. Otherwise, the upstream bridge's device tree node + * of the primary PE bus will be checked for the location code. + */ +const char *eeh_pe_loc_get(struct eeh_pe *pe) +{ + struct pci_controller *hose; + struct pci_bus *bus = eeh_pe_bus_get(pe); + struct pci_dev *pdev; + struct device_node *dn; + const char *loc; + + if (!bus) + return "N/A"; + + /* PHB PE or root PE ? */ + if (pci_is_root_bus(bus)) { + hose = pci_bus_to_host(bus); + loc = of_get_property(hose->dn, + "ibm,loc-code", NULL); + if (loc) + return loc; + loc = of_get_property(hose->dn, + "ibm,io-base-loc-code", NULL); + if (loc) + return loc; + + pdev = pci_get_slot(bus, 0x0); + } else { + pdev = bus->self; + } + + if (!pdev) { + loc = "N/A"; + goto out; + } + + dn = pci_device_to_OF_node(pdev); + if (!dn) { + loc = "N/A"; + goto out; + } + + loc = of_get_property(dn, "ibm,loc-code", NULL); + if (!loc) + loc = of_get_property(dn, "ibm,slot-location-code", NULL); + if (!loc) + loc = "N/A"; + +out: + if (pci_is_root_bus(bus) && pdev) + pci_dev_put(pdev); + return loc; +} + /** * eeh_pe_bus_get - Retrieve PCI bus according to the given PE * @pe: EEH PE diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 911d45366f59..6528c5e2cc44 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -428,12 +428,6 @@ BEGIN_FTR_SECTION std r24,THREAD_VRSAVE(r3) END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_PPC64 -BEGIN_FTR_SECTION - mfspr r25,SPRN_DSCR - std r25,THREAD_DSCR(r3) -END_FTR_SECTION_IFSET(CPU_FTR_DSCR) -#endif and. r0,r0,r22 beq+ 1f andc r22,r22,r0 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 771b4e92e5d9..bb9cac6c8051 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -1467,22 +1467,6 @@ a2_tlbinit_after_linear_map: .globl a2_tlbinit_after_iprot_flush a2_tlbinit_after_iprot_flush: -#ifdef CONFIG_PPC_EARLY_DEBUG_WSP - /* Now establish early debug mappings if applicable */ - /* Restore the MAS0 we used for linear mapping load */ - mtspr SPRN_MAS0,r11 - - lis r3,(MAS1_VALID | MAS1_IPROT)@h - ori r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT) - mtspr SPRN_MAS1,r3 - LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G) - mtspr SPRN_MAS2,r3 - LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW) - mtspr SPRN_MAS7_MAS3,r3 - /* re-use the MAS8 value from the linear mapping */ - tlbwe -#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ - PPC_TLBILX(0,0,R0) sync isync diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 20f11eb4dff7..a7d36b19221d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -439,9 +439,9 @@ BEGIN_FTR_SECTION * R9 = CR * Original R9 to R13 is saved on PACA_EXMC * - * Switch to mc_emergency stack and handle re-entrancy (though we - * currently don't test for overflow). Save MCE registers srr1, - * srr0, dar and dsisr and then set ME=1 + * Switch to mc_emergency stack and handle re-entrancy (we limit + * the nested MCE upto level 4 to avoid stack overflow). + * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1 * * We use paca->in_mce to check whether this is the first entry or * nested machine check. We increment paca->in_mce to track nested @@ -464,6 +464,9 @@ BEGIN_FTR_SECTION 0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ addi r10,r10,1 /* increment paca->in_mce */ sth r10,PACA_IN_MCE(r13) + /* Limit nested MCE to level 4 to avoid stack overflow */ + cmpwi r10,4 + bgt 2f /* Check if we hit limit of 4 */ std r11,GPR1(r1) /* Save r1 on the stack. */ std r11,0(r1) /* make stack chain pointer */ mfspr r11,SPRN_SRR0 /* Save SRR0 */ @@ -482,10 +485,23 @@ BEGIN_FTR_SECTION ori r11,r11,MSR_RI /* turn on RI bit */ ld r12,PACAKBASE(r13) /* get high part of &label */ LOAD_HANDLER(r12, machine_check_handle_early) - mtspr SPRN_SRR0,r12 +1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 rfid b . /* prevent speculative execution */ +2: + /* Stack overflow. Stay on emergency stack and panic. + * Keep the ME bit off while panic-ing, so that if we hit + * another machine check we checkstop. + */ + addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */ + ld r11,PACAKMSR(r13) + ld r12,PACAKBASE(r13) + LOAD_HANDLER(r12, unrecover_mce) + li r10,MSR_ME + andc r11,r11,r10 /* Turn off MSR_ME */ + b 1b + b . /* prevent speculative execution */ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) machine_check_pSeries: @@ -1389,6 +1405,7 @@ machine_check_handle_early: bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_early + std r3,RESULT(r1) /* Save result */ ld r12,_MSR(r1) #ifdef CONFIG_PPC_P7_NAP /* @@ -1443,10 +1460,32 @@ machine_check_handle_early: */ andi. r11,r12,MSR_RI bne 2f -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl unrecoverable_exception - b 1b +1: mfspr r11,SPRN_SRR0 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10,unrecover_mce) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + /* + * We are going down. But there are chances that we might get hit by + * another MCE during panic path and we may run into unstable state + * with no way out. Hence, turn ME bit off while going down, so that + * when another MCE is hit during panic path, system will checkstop + * and hypervisor will get restarted cleanly by SP. + */ + li r3,MSR_ME + andc r10,r10,r3 /* Turn off MSR_ME */ + mtspr SPRN_SRR1,r10 + rfid + b . 2: + /* + * Check if we have successfully handled/recovered from error, if not + * then stay on emergency stack and panic. + */ + ld r3,RESULT(r1) /* Load result */ + cmpdi r3,0 /* see if we handled MCE successfully */ + + beq 1b /* if !handled then panic */ /* * Return from MC interrupt. * Queue up the MCE event so that we can log it later, while @@ -1460,6 +1499,17 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP b machine_check_pSeries +unrecover_mce: + /* Invoke machine_check_exception to print MCE event and panic. */ + addi r3,r1,STACK_FRAME_OVERHEAD + bl machine_check_exception + /* + * We will not reach here. Even if we did, there is no way out. Call + * unrecoverable_exception and die. + */ +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl unrecoverable_exception + b 1b /* * r13 points to the PACA, r9 contains the saved CR, * r12 contain the saved SRR1, SRR0 is still ready for return diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 67ee0d6c1070..7d7d8635227a 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -930,25 +930,6 @@ initial_mmu: tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ -#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE) - - /* Load a TLB entry for the UART, so that ppc4xx_progress() can use - * the UARTs nice and early. We use a 4k real==virtual mapping. */ - - lis r3,SERIAL_DEBUG_IO_BASE@h - ori r3,r3,SERIAL_DEBUG_IO_BASE@l - mr r4,r3 - clrrwi r4,r4,12 - ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G) - - clrrwi r3,r3,12 - ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K)) - - li r0,0 /* TLB slot 0 */ - tlbwe r4,r0,TLB_DATA - tlbwe r3,r0,TLB_TAG -#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */ - isync /* Establish the exception vector base diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8a1edbe26b8f..be99774d3f44 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -755,15 +755,15 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); - /* Back up the TAR across context switches. + /* Back up the TAR and DSCR across context switches. * Note that the TAR is not available for use in the kernel. (To * provide this, the TAR should be backed up/restored on exception * entry/exit instead, and be in pt_regs. FIXME, this should be in * pt_regs anyway (for debug).) - * Save the TAR here before we do treclaim/trecheckpoint as these - * will change the TAR. + * Save the TAR and DSCR here before we do treclaim/trecheckpoint as + * these will change them. */ - save_tar(&prev->thread); + save_early_sprs(&prev->thread); __switch_to_tm(prev); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index d4d418376f99..e239df3768ac 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -471,7 +471,7 @@ void __init smp_setup_cpu_maps(void) for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, be32_to_cpu(intserv[j])); - set_cpu_present(cpu, true); + set_cpu_present(cpu, of_device_is_available(dn)); set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); cpu++; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 7753af2d2613..51a3ff78838a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -749,7 +749,7 @@ int setup_profiling_timer(unsigned int multiplier) /* cpumask of CPUs with asymetric SMT dependancy */ static const int powerpc_smt_flags(void) { - int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES; + int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 7e711bdcc6da..9fff9cdcc519 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -551,7 +551,7 @@ void timer_interrupt(struct pt_regs * regs) may_hard_irq_enable(); -#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); #endif diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 1bd7ca298fa1..239f1cde3fff 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -295,6 +295,8 @@ long machine_check_early(struct pt_regs *regs) { long handled = 0; + __get_cpu_var(irq_stat).mce_exceptions++; + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); return handled; diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index a15837519dca..b7aa07279a63 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -62,8 +62,6 @@ void __init udbg_early_init(void) udbg_init_cpm(); #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO) udbg_init_usbgecko(); -#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) - udbg_init_wsp(); #elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS) /* In memory console */ udbg_init_memcons(); diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 75702e207b29..6e7c4923b5ea 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -296,14 +296,3 @@ void __init udbg_init_40x_realmode(void) } #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ - - -#ifdef CONFIG_PPC_EARLY_DEBUG_WSP - -void __init udbg_init_wsp(void) -{ - udbg_uart_init_mmio((void *)WSP_UART_VIRT, 1); - udbg_uart_setup(57600, 50000000); -} - -#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 768a9f977c00..3a5c568b1e89 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -113,10 +113,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) * We assume that if the condition is recovered then linux host * will have generated an error log event that we will pick * up and log later. - * Don't release mce event now. In case if condition is not - * recovered we do guest exit and go back to linux host machine - * check handler. Hence we need make sure that current mce event - * is available for linux host to consume. + * Don't release mce event now. We will queue up the event so that + * we can log the MCE event info on host console. */ if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE)) goto out; @@ -128,11 +126,12 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) out: /* - * If we have handled the error, then release the mce event because - * we will be delivering machine check to guest. + * We are now going enter guest either through machine check + * interrupt (for unhandled errors) or will continue from + * current HSRR0 (for handled errors) in guest. Hence + * queue up the event so that we can log it from host console later. */ - if (handled) - release_mce_event(); + machine_check_queue_event(); return handled; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 77356fd25ccc..868347ef09fd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2257,15 +2257,28 @@ machine_check_realmode: mr r3, r9 /* get vcpu pointer */ bl kvmppc_realmode_machine_check nop - cmpdi r3, 0 /* continue exiting from guest? */ + cmpdi r3, 0 /* Did we handle MCE ? */ ld r9, HSTATE_KVM_VCPU(r13) li r12, BOOK3S_INTERRUPT_MACHINE_CHECK - beq mc_cont + /* + * Deliver unhandled/fatal (e.g. UE) MCE errors to guest through + * machine check interrupt (set HSRR0 to 0x200). And for handled + * errors (no-fatal), just go back to guest execution with current + * HSRR0 instead of exiting guest. This new approach will inject + * machine check to guest for fatal error causing guest to crash. + * + * The old code used to return to host for unhandled errors which + * was causing guest to hang with soft lockups inside guest and + * makes it difficult to recover guest instance. + */ + ld r10, VCPU_PC(r9) + ld r11, VCPU_MSR(r9) + bne 2f /* Continue guest execution. */ /* If not, deliver a machine check. SRR0/1 are already set */ li r10, BOOK3S_INTERRUPT_MACHINE_CHECK ld r11, VCPU_MSR(r9) bl kvmppc_msr_interrupt - b fast_interrupt_c_return +2: b fast_interrupt_c_return /* * Check the reason we woke from nap, and take appropriate action. diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index c0511c27a733..412dd46dd0b7 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1470,7 +1470,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) regs->gpr[rd] = byterev_4(val); goto ldst_done; -#ifdef CONFIG_PPC_CPU +#ifdef CONFIG_PPC_FPU case 535: /* lfsx */ case 567: /* lfsux */ if (!(regs->msr & MSR_FP)) diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S index e76eba74d9da..8f87d9217122 100644 --- a/arch/powerpc/net/bpf_jit_64.S +++ b/arch/powerpc/net/bpf_jit_64.S @@ -78,7 +78,7 @@ sk_load_byte_positive_offset: blr /* - * BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf) + * BPF_LDX | BPF_B | BPF_MSH: ldxb 4*([offset]&0xf) * r_addr is the offset value */ .globl sk_load_byte_msh diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 808ce1cae21a..6dcdadefd8d0 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -79,19 +79,11 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, } switch (filter[0].code) { - case BPF_S_RET_K: - case BPF_S_LD_W_LEN: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_CPU: - case BPF_S_ANC_QUEUE: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: /* first instruction sets A register (or is RET 'constant') */ break; default: @@ -144,6 +136,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, for (i = 0; i < flen; i++) { unsigned int K = filter[i].k; + u16 code = bpf_anc_helper(&filter[i]); /* * addrs[] maps a BPF bytecode address into a real offset from @@ -151,35 +144,35 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, */ addrs[i] = ctx->idx * 4; - switch (filter[i].code) { + switch (code) { /*** ALU ops ***/ - case BPF_S_ALU_ADD_X: /* A += X; */ + case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */ ctx->seen |= SEEN_XREG; PPC_ADD(r_A, r_A, r_X); break; - case BPF_S_ALU_ADD_K: /* A += K; */ + case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */ if (!K) break; PPC_ADDI(r_A, r_A, IMM_L(K)); if (K >= 32768) PPC_ADDIS(r_A, r_A, IMM_HA(K)); break; - case BPF_S_ALU_SUB_X: /* A -= X; */ + case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */ ctx->seen |= SEEN_XREG; PPC_SUB(r_A, r_A, r_X); break; - case BPF_S_ALU_SUB_K: /* A -= K */ + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ if (!K) break; PPC_ADDI(r_A, r_A, IMM_L(-K)); if (K >= 32768) PPC_ADDIS(r_A, r_A, IMM_HA(-K)); break; - case BPF_S_ALU_MUL_X: /* A *= X; */ + case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */ ctx->seen |= SEEN_XREG; PPC_MUL(r_A, r_A, r_X); break; - case BPF_S_ALU_MUL_K: /* A *= K */ + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ if (K < 32768) PPC_MULI(r_A, r_A, K); else { @@ -187,7 +180,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_MUL(r_A, r_A, r_scratch1); } break; - case BPF_S_ALU_MOD_X: /* A %= X; */ + case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */ ctx->seen |= SEEN_XREG; PPC_CMPWI(r_X, 0); if (ctx->pc_ret0 != -1) { @@ -201,13 +194,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_MUL(r_scratch1, r_X, r_scratch1); PPC_SUB(r_A, r_A, r_scratch1); break; - case BPF_S_ALU_MOD_K: /* A %= K; */ + case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */ PPC_LI32(r_scratch2, K); PPC_DIVWU(r_scratch1, r_A, r_scratch2); PPC_MUL(r_scratch1, r_scratch2, r_scratch1); PPC_SUB(r_A, r_A, r_scratch1); break; - case BPF_S_ALU_DIV_X: /* A /= X; */ + case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */ ctx->seen |= SEEN_XREG; PPC_CMPWI(r_X, 0); if (ctx->pc_ret0 != -1) { @@ -223,17 +216,17 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, } PPC_DIVWU(r_A, r_A, r_X); break; - case BPF_S_ALU_DIV_K: /* A /= K */ + case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */ if (K == 1) break; PPC_LI32(r_scratch1, K); PPC_DIVWU(r_A, r_A, r_scratch1); break; - case BPF_S_ALU_AND_X: + case BPF_ALU | BPF_AND | BPF_X: ctx->seen |= SEEN_XREG; PPC_AND(r_A, r_A, r_X); break; - case BPF_S_ALU_AND_K: + case BPF_ALU | BPF_AND | BPF_K: if (!IMM_H(K)) PPC_ANDI(r_A, r_A, K); else { @@ -241,51 +234,51 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_AND(r_A, r_A, r_scratch1); } break; - case BPF_S_ALU_OR_X: + case BPF_ALU | BPF_OR | BPF_X: ctx->seen |= SEEN_XREG; PPC_OR(r_A, r_A, r_X); break; - case BPF_S_ALU_OR_K: + case BPF_ALU | BPF_OR | BPF_K: if (IMM_L(K)) PPC_ORI(r_A, r_A, IMM_L(K)); if (K >= 65536) PPC_ORIS(r_A, r_A, IMM_H(K)); break; - case BPF_S_ANC_ALU_XOR_X: - case BPF_S_ALU_XOR_X: /* A ^= X */ + case BPF_ANC | SKF_AD_ALU_XOR_X: + case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */ ctx->seen |= SEEN_XREG; PPC_XOR(r_A, r_A, r_X); break; - case BPF_S_ALU_XOR_K: /* A ^= K */ + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ if (IMM_L(K)) PPC_XORI(r_A, r_A, IMM_L(K)); if (K >= 65536) PPC_XORIS(r_A, r_A, IMM_H(K)); break; - case BPF_S_ALU_LSH_X: /* A <<= X; */ + case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */ ctx->seen |= SEEN_XREG; PPC_SLW(r_A, r_A, r_X); break; - case BPF_S_ALU_LSH_K: + case BPF_ALU | BPF_LSH | BPF_K: if (K == 0) break; else PPC_SLWI(r_A, r_A, K); break; - case BPF_S_ALU_RSH_X: /* A >>= X; */ + case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */ ctx->seen |= SEEN_XREG; PPC_SRW(r_A, r_A, r_X); break; - case BPF_S_ALU_RSH_K: /* A >>= K; */ + case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */ if (K == 0) break; else PPC_SRWI(r_A, r_A, K); break; - case BPF_S_ALU_NEG: + case BPF_ALU | BPF_NEG: PPC_NEG(r_A, r_A); break; - case BPF_S_RET_K: + case BPF_RET | BPF_K: PPC_LI32(r_ret, K); if (!K) { if (ctx->pc_ret0 == -1) @@ -312,7 +305,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_BLR(); } break; - case BPF_S_RET_A: + case BPF_RET | BPF_A: PPC_MR(r_ret, r_A); if (i != flen - 1) { if (ctx->seen) @@ -321,53 +314,53 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_BLR(); } break; - case BPF_S_MISC_TAX: /* X = A */ + case BPF_MISC | BPF_TAX: /* X = A */ PPC_MR(r_X, r_A); break; - case BPF_S_MISC_TXA: /* A = X */ + case BPF_MISC | BPF_TXA: /* A = X */ ctx->seen |= SEEN_XREG; PPC_MR(r_A, r_X); break; /*** Constant loads/M[] access ***/ - case BPF_S_LD_IMM: /* A = K */ + case BPF_LD | BPF_IMM: /* A = K */ PPC_LI32(r_A, K); break; - case BPF_S_LDX_IMM: /* X = K */ + case BPF_LDX | BPF_IMM: /* X = K */ PPC_LI32(r_X, K); break; - case BPF_S_LD_MEM: /* A = mem[K] */ + case BPF_LD | BPF_MEM: /* A = mem[K] */ PPC_MR(r_A, r_M + (K & 0xf)); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; - case BPF_S_LDX_MEM: /* X = mem[K] */ + case BPF_LDX | BPF_MEM: /* X = mem[K] */ PPC_MR(r_X, r_M + (K & 0xf)); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; - case BPF_S_ST: /* mem[K] = A */ + case BPF_ST: /* mem[K] = A */ PPC_MR(r_M + (K & 0xf), r_A); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; - case BPF_S_STX: /* mem[K] = X */ + case BPF_STX: /* mem[K] = X */ PPC_MR(r_M + (K & 0xf), r_X); ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); break; - case BPF_S_LD_W_LEN: /* A = skb->len; */ + case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; - case BPF_S_LDX_W_LEN: /* X = skb->len; */ + case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); break; /*** Ancillary info loads ***/ - case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff, protocol)); break; - case BPF_S_ANC_IFINDEX: + case BPF_ANC | SKF_AD_IFINDEX: PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, dev)); PPC_CMPDI(r_scratch1, 0); @@ -384,33 +377,33 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_LWZ_OFFS(r_A, r_scratch1, offsetof(struct net_device, ifindex)); break; - case BPF_S_ANC_MARK: + case BPF_ANC | SKF_AD_MARK: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, mark)); break; - case BPF_S_ANC_RXHASH: + case BPF_ANC | SKF_AD_RXHASH: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, hash)); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, vlan_tci)); - if (filter[i].code == BPF_S_ANC_VLAN_TAG) + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) PPC_ANDI(r_A, r_A, VLAN_VID_MASK); else PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT); break; - case BPF_S_ANC_QUEUE: + case BPF_ANC | SKF_AD_QUEUE: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, queue_mapping)); break; - case BPF_S_ANC_CPU: + case BPF_ANC | SKF_AD_CPU: #ifdef CONFIG_SMP /* * PACA ptr is r13: @@ -426,13 +419,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, break; /*** Absolute loads from packet header/data ***/ - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, sk_load_word); goto common_load; - case BPF_S_LD_H_ABS: + case BPF_LD | BPF_H | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, sk_load_half); goto common_load; - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_B | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, sk_load_byte); common_load: /* Load from [K]. */ @@ -449,13 +442,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, break; /*** Indirect loads from packet header/data ***/ - case BPF_S_LD_W_IND: + case BPF_LD | BPF_W | BPF_IND: func = sk_load_word; goto common_load_ind; - case BPF_S_LD_H_IND: + case BPF_LD | BPF_H | BPF_IND: func = sk_load_half; goto common_load_ind; - case BPF_S_LD_B_IND: + case BPF_LD | BPF_B | BPF_IND: func = sk_load_byte; common_load_ind: /* @@ -473,31 +466,31 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_BCC(COND_LT, exit_addr); break; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh); goto common_load; break; /*** Jump and branches ***/ - case BPF_S_JMP_JA: + case BPF_JMP | BPF_JA: if (K != 0) PPC_JMP(addrs[i + 1 + K]); break; - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: true_cond = COND_GT; goto cond_branch; - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: true_cond = COND_GE; goto cond_branch; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: true_cond = COND_EQ; goto cond_branch; - case BPF_S_JMP_JSET_K: - case BPF_S_JMP_JSET_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; /* Fall through */ cond_branch: @@ -508,20 +501,20 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, break; } - switch (filter[i].code) { - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JEQ_X: + switch (code) { + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_X: ctx->seen |= SEEN_XREG; PPC_CMPLW(r_A, r_X); break; - case BPF_S_JMP_JSET_X: + case BPF_JMP | BPF_JSET | BPF_X: ctx->seen |= SEEN_XREG; PPC_AND_DOT(r_scratch1, r_A, r_X); break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGE_K: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: if (K < 32768) PPC_CMPLWI(r_A, K); else { @@ -529,7 +522,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, PPC_CMPLW(r_A, r_scratch1); } break; - case BPF_S_JMP_JSET_K: + case BPF_JMP | BPF_JSET | BPF_K: if (K < 32768) /* PPC_ANDI is /only/ dot-form */ PPC_ANDI(r_scratch1, r_A, K); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index bf9c6d4cd26c..391b3f6b54a3 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -19,7 +19,6 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig" source "arch/powerpc/platforms/44x/Kconfig" source "arch/powerpc/platforms/40x/Kconfig" source "arch/powerpc/platforms/amigaone/Kconfig" -source "arch/powerpc/platforms/wsp/Kconfig" config KVM_GUEST bool "KVM Guest support" diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 43b65ad1970a..a41bd023647a 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -148,10 +148,6 @@ config POWER4 depends on PPC64 && PPC_BOOK3S def_bool y -config PPC_A2 - bool - depends on PPC_BOOK3E_64 - config TUNE_CELL bool "Optimize for Cell Broadband Engine" depends on PPC64 && PPC_BOOK3S @@ -280,7 +276,7 @@ config VSX config PPC_ICSWX bool "Support for PowerPC icswx coprocessor instruction" - depends on POWER4 || PPC_A2 + depends on POWER4 default n ---help--- diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index 879b4a448498..469ef170d218 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -22,4 +22,3 @@ obj-$(CONFIG_PPC_CELL) += cell/ obj-$(CONFIG_PPC_PS3) += ps3/ obj-$(CONFIG_EMBEDDED6xx) += embedded6xx/ obj-$(CONFIG_AMIGAONE) += amigaone/ -obj-$(CONFIG_PPC_WSP) += wsp/ diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 0ba3c9598358..bcfd6f063efa 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -35,7 +35,6 @@ #define SPUFS_PS_MAP_SIZE 0x20000 #define SPUFS_MFC_MAP_SIZE 0x1000 #define SPUFS_CNTL_MAP_SIZE 0x1000 -#define SPUFS_CNTL_MAP_SIZE 0x1000 #define SPUFS_SIGNAL_MAP_SIZE PAGE_SIZE #define SPUFS_MSS_MAP_SIZE 0x1000 diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index c252ee95bddf..45a8ed0585cd 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -17,6 +17,7 @@ config PPC_POWERNV select CPU_FREQ_GOV_USERSPACE select CPU_FREQ_GOV_ONDEMAND select CPU_FREQ_GOV_CONSERVATIVE + select PPC_DOORBELL default y config PPC_POWERNV_RTAS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 4ad0d345bc96..d55891f89a2c 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,9 +1,9 @@ obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o -obj-y += opal-msglog.o subcore.o subcore-asm.o +obj-y += opal-msglog.o -obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 753f08e36dfa..8ad0c5b891f4 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -267,7 +267,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) { s64 ret = 0; u8 fstate; - u16 pcierr; + __be16 pcierr; u32 pe_no; int result; struct pci_controller *hose = pe->phb; @@ -316,7 +316,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) result = 0; result &= ~EEH_STATE_RESET_ACTIVE; - if (pcierr != OPAL_EEH_PHB_ERROR) { + if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { result |= EEH_STATE_MMIO_ACTIVE; result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; @@ -705,18 +705,19 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose; struct pnv_phb *phb; - struct eeh_pe *phb_pe; - u64 frozen_pe_no; - u16 err_type, severity; + struct eeh_pe *phb_pe, *parent_pe; + __be64 frozen_pe_no; + __be16 err_type, severity; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); long rc; - int ret = EEH_NEXT_ERR_NONE; + int state, ret = EEH_NEXT_ERR_NONE; /* * While running here, it's safe to purge the event queue. * And we should keep the cached OPAL notifier event sychronized * between the kernel and firmware. */ - eeh_remove_event(NULL); + eeh_remove_event(NULL, false); opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry(hose, &hose_list, list_node) { @@ -742,8 +743,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) } /* If the PHB doesn't have error, stop processing */ - if (err_type == OPAL_EEH_NO_ERROR || - severity == OPAL_EEH_SEV_NO_ERROR) { + if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || + be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { pr_devel("%s: No error found on PHB#%x\n", __func__, hose->global_number); continue; @@ -755,14 +756,14 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) * specific PHB. */ pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", - __func__, err_type, severity, - frozen_pe_no, hose->global_number); - switch (err_type) { + __func__, be16_to_cpu(err_type), be16_to_cpu(severity), + be64_to_cpu(frozen_pe_no), hose->global_number); + switch (be16_to_cpu(err_type)) { case OPAL_EEH_IOC_ERROR: - if (severity == OPAL_EEH_SEV_IOC_DEAD) { + if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { pr_err("EEH: dead IOC detected\n"); ret = EEH_NEXT_ERR_DEAD_IOC; - } else if (severity == OPAL_EEH_SEV_INF) { + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { pr_info("EEH: IOC informative error " "detected\n"); ioda_eeh_hub_diag(hose); @@ -771,20 +772,26 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) break; case OPAL_EEH_PHB_ERROR: - if (severity == OPAL_EEH_SEV_PHB_DEAD) { + if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { *pe = phb_pe; - pr_err("EEH: dead PHB#%x detected\n", - hose->global_number); + pr_err("EEH: dead PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); ret = EEH_NEXT_ERR_DEAD_PHB; - } else if (severity == OPAL_EEH_SEV_PHB_FENCED) { + } else if (be16_to_cpu(severity) == + OPAL_EEH_SEV_PHB_FENCED) { *pe = phb_pe; - pr_err("EEH: fenced PHB#%x detected\n", - hose->global_number); + pr_err("EEH: Fenced PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); ret = EEH_NEXT_ERR_FENCED_PHB; - } else if (severity == OPAL_EEH_SEV_INF) { + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { pr_info("EEH: PHB#%x informative error " - "detected\n", - hose->global_number); + "detected, location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); ioda_eeh_phb_diag(hose); ret = EEH_NEXT_ERR_NONE; } @@ -792,34 +799,33 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) break; case OPAL_EEH_PE_ERROR: /* - * If we can't find the corresponding PE, the - * PEEV / PEST would be messy. So we force an - * fenced PHB so that it can be recovered. - * - * If the PE has been marked as isolated, that - * should have been removed permanently or in - * progress with recovery. We needn't report - * it again. + * If we can't find the corresponding PE, we + * just try to unfreeze. */ - if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) { - *pe = phb_pe; - pr_err("EEH: Escalated fenced PHB#%x " - "detected for PE#%llx\n", - hose->global_number, - frozen_pe_no); - ret = EEH_NEXT_ERR_FENCED_PHB; + if (ioda_eeh_get_pe(hose, + be64_to_cpu(frozen_pe_no), pe)) { + /* Try best to clear it */ + pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", + hose->global_number, frozen_pe_no); + pr_info("EEH: PHB location: %s\n", + eeh_pe_loc_get(phb_pe)); + opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + ret = EEH_NEXT_ERR_NONE; } else if ((*pe)->state & EEH_PE_ISOLATED) { ret = EEH_NEXT_ERR_NONE; } else { pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", (*pe)->addr, (*pe)->phb->global_number); + pr_err("EEH: PE location: %s, PHB location: %s\n", + eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe)); ret = EEH_NEXT_ERR_FROZEN_PE; } break; default: pr_warn("%s: Unexpected error type %d\n", - __func__, err_type); + __func__, be16_to_cpu(err_type)); } /* @@ -836,6 +842,31 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) ioda_eeh_phb_diag(hose); } + /* + * We probably have the frozen parent PE out there and + * we need have to handle frozen parent PE firstly. + */ + if (ret == EEH_NEXT_ERR_FROZEN_PE) { + parent_pe = (*pe)->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + state = ioda_eeh_get_state(parent_pe); + if (state > 0 && + (state & active_flags) != active_flags) + *pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + + /* We possibly migrate to another PE */ + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + } + /* * If we have no errors on the specific PHB or only * informative error there, we continue poking it. diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index 1bb25b952504..44ed78af1a0d 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -37,7 +37,8 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, { struct memcons *mc = bin_attr->private; const char *conbuf; - size_t ret, first_read = 0; + ssize_t ret; + size_t first_read = 0; uint32_t out_pos, avail; if (!mc) @@ -69,6 +70,9 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, to += first_read; count -= first_read; pos -= avail; + + if (count <= 0) + goto out; } /* Sanity check. The firmware should not do this to us. */ diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index d202f9bc3683..9d1acf22a099 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -260,10 +260,10 @@ void __init opal_sys_param_init(void) attr[i].kobj_attr.attr.mode = S_IRUGO; break; case OPAL_SYSPARAM_WRITE: - attr[i].kobj_attr.attr.mode = S_IWUGO; + attr[i].kobj_attr.attr.mode = S_IWUSR; break; case OPAL_SYSPARAM_RW: - attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUGO; + attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUSR; break; default: break; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index eefbfcc3fd8c..f91a4e5d872e 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -206,72 +206,91 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, data = (struct OpalIoPhb3ErrorData*)common; pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n", - hose->global_number, common->version); + hose->global_number, be32_to_cpu(common->version)); if (data->brdgCtl) pr_info("brdgCtl: %08x\n", - data->brdgCtl); + be32_to_cpu(data->brdgCtl)); if (data->portStatusReg || data->rootCmplxStatus || data->busAgentStatus) pr_info("UtlSts: %08x %08x %08x\n", - data->portStatusReg, data->rootCmplxStatus, - data->busAgentStatus); + be32_to_cpu(data->portStatusReg), + be32_to_cpu(data->rootCmplxStatus), + be32_to_cpu(data->busAgentStatus)); if (data->deviceStatus || data->slotStatus || data->linkStatus || data->devCmdStatus || data->devSecStatus) pr_info("RootSts: %08x %08x %08x %08x %08x\n", - data->deviceStatus, data->slotStatus, - data->linkStatus, data->devCmdStatus, - data->devSecStatus); + be32_to_cpu(data->deviceStatus), + be32_to_cpu(data->slotStatus), + be32_to_cpu(data->linkStatus), + be32_to_cpu(data->devCmdStatus), + be32_to_cpu(data->devSecStatus)); if (data->rootErrorStatus || data->uncorrErrorStatus || data->corrErrorStatus) pr_info("RootErrSts: %08x %08x %08x\n", - data->rootErrorStatus, data->uncorrErrorStatus, - data->corrErrorStatus); + be32_to_cpu(data->rootErrorStatus), + be32_to_cpu(data->uncorrErrorStatus), + be32_to_cpu(data->corrErrorStatus)); if (data->tlpHdr1 || data->tlpHdr2 || data->tlpHdr3 || data->tlpHdr4) pr_info("RootErrLog: %08x %08x %08x %08x\n", - data->tlpHdr1, data->tlpHdr2, - data->tlpHdr3, data->tlpHdr4); + be32_to_cpu(data->tlpHdr1), + be32_to_cpu(data->tlpHdr2), + be32_to_cpu(data->tlpHdr3), + be32_to_cpu(data->tlpHdr4)); if (data->sourceId || data->errorClass || data->correlator) pr_info("RootErrLog1: %08x %016llx %016llx\n", - data->sourceId, data->errorClass, - data->correlator); + be32_to_cpu(data->sourceId), + be64_to_cpu(data->errorClass), + be64_to_cpu(data->correlator)); if (data->nFir) pr_info("nFir: %016llx %016llx %016llx\n", - data->nFir, data->nFirMask, - data->nFirWOF); + be64_to_cpu(data->nFir), + be64_to_cpu(data->nFirMask), + be64_to_cpu(data->nFirWOF)); if (data->phbPlssr || data->phbCsr) pr_info("PhbSts: %016llx %016llx\n", - data->phbPlssr, data->phbCsr); + be64_to_cpu(data->phbPlssr), + be64_to_cpu(data->phbCsr)); if (data->lemFir) pr_info("Lem: %016llx %016llx %016llx\n", - data->lemFir, data->lemErrorMask, - data->lemWOF); + be64_to_cpu(data->lemFir), + be64_to_cpu(data->lemErrorMask), + be64_to_cpu(data->lemWOF)); if (data->phbErrorStatus) pr_info("PhbErr: %016llx %016llx %016llx %016llx\n", - data->phbErrorStatus, data->phbFirstErrorStatus, - data->phbErrorLog0, data->phbErrorLog1); + be64_to_cpu(data->phbErrorStatus), + be64_to_cpu(data->phbFirstErrorStatus), + be64_to_cpu(data->phbErrorLog0), + be64_to_cpu(data->phbErrorLog1)); if (data->mmioErrorStatus) pr_info("OutErr: %016llx %016llx %016llx %016llx\n", - data->mmioErrorStatus, data->mmioFirstErrorStatus, - data->mmioErrorLog0, data->mmioErrorLog1); + be64_to_cpu(data->mmioErrorStatus), + be64_to_cpu(data->mmioFirstErrorStatus), + be64_to_cpu(data->mmioErrorLog0), + be64_to_cpu(data->mmioErrorLog1)); if (data->dma0ErrorStatus) pr_info("InAErr: %016llx %016llx %016llx %016llx\n", - data->dma0ErrorStatus, data->dma0FirstErrorStatus, - data->dma0ErrorLog0, data->dma0ErrorLog1); + be64_to_cpu(data->dma0ErrorStatus), + be64_to_cpu(data->dma0FirstErrorStatus), + be64_to_cpu(data->dma0ErrorLog0), + be64_to_cpu(data->dma0ErrorLog1)); if (data->dma1ErrorStatus) pr_info("InBErr: %016llx %016llx %016llx %016llx\n", - data->dma1ErrorStatus, data->dma1FirstErrorStatus, - data->dma1ErrorLog0, data->dma1ErrorLog1); + be64_to_cpu(data->dma1ErrorStatus), + be64_to_cpu(data->dma1FirstErrorStatus), + be64_to_cpu(data->dma1ErrorLog0), + be64_to_cpu(data->dma1ErrorLog1)); for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { - if ((data->pestA[i] >> 63) == 0 && - (data->pestB[i] >> 63) == 0) + if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 && + (be64_to_cpu(data->pestB[i]) >> 63) == 0) continue; pr_info("PE[%3d] A/B: %016llx %016llx\n", - i, data->pestA[i], data->pestB[i]); + i, be64_to_cpu(data->pestA[i]), + be64_to_cpu(data->pestB[i])); } } @@ -284,7 +303,7 @@ void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, return; common = (struct OpalIoPhbErrorCommon *)log_buff; - switch (common->ioType) { + switch (be32_to_cpu(common->ioType)) { case OPAL_PHB_ERROR_DATA_TYPE_P7IOC: pnv_pci_dump_p7ioc_diag_data(hose, common); break; @@ -293,7 +312,7 @@ void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, break; default: pr_warn("%s: Unrecognized ioType %d\n", - __func__, common->ioType); + __func__, be32_to_cpu(common->ioType)); } } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 8c16a5f96728..d9b88fa7c5a3 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -35,11 +35,14 @@ #include #include #include +#include #include "powernv.h" static void __init pnv_setup_arch(void) { + set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 0062a43a2e0d..5fcfcf44e3a9 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "powernv.h" @@ -46,6 +47,11 @@ static void pnv_smp_setup_cpu(int cpu) { if (cpu != boot_cpuid) xics_setup_cpu(); + +#ifdef CONFIG_PPC_DOORBELL + if (cpu_has_feature(CPU_FTR_DBELL)) + doorbell_setup_this_cpu(); +#endif } int pnv_smp_kick_cpu(int nr) diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 2cb8b776c84a..756b482f819a 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -21,6 +21,7 @@ config PPC_PSERIES select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP select ARCH_RANDOM + select PPC_DOORBELL default y config PPC_SPLPAR diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig deleted file mode 100644 index 422a175b10ee..000000000000 --- a/arch/powerpc/platforms/wsp/Kconfig +++ /dev/null @@ -1,30 +0,0 @@ -config PPC_WSP - bool - select PPC_A2 - select GENERIC_TBSYNC - select PPC_ICSWX - select PPC_SCOM - select PPC_XICS - select PPC_ICP_NATIVE - select PCI - select PPC_IO_WORKAROUNDS if PCI - select PPC_INDIRECT_PIO if PCI - default n - -menu "WSP platform selection" - depends on PPC_BOOK3E_64 - -config PPC_PSR2 - bool "PowerEN System Reference Platform 2" - select EPAPR_BOOT - select PPC_WSP - default y - -config PPC_CHROMA - bool "PowerEN PCIe Chroma Card" - select EPAPR_BOOT - select PPC_WSP - select OF_DYNAMIC - default y - -endmenu diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile deleted file mode 100644 index 162fc60125a2..000000000000 --- a/arch/powerpc/platforms/wsp/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -ccflags-y += $(NO_MINIMAL_TOC) - -obj-y += setup.o ics.o wsp.o -obj-$(CONFIG_PPC_PSR2) += psr2.o -obj-$(CONFIG_PPC_CHROMA) += chroma.o h8.o -obj-$(CONFIG_PPC_WSP) += opb_pic.o -obj-$(CONFIG_PPC_WSP) += scom_wsp.o -obj-$(CONFIG_SMP) += smp.o scom_smp.o -obj-$(CONFIG_PCI) += wsp_pci.o -obj-$(CONFIG_PCI_MSI) += msi.o diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c deleted file mode 100644 index aaa46b353715..000000000000 --- a/arch/powerpc/platforms/wsp/chroma.c +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright 2008-2011, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include "ics.h" -#include "wsp.h" - -void __init chroma_setup_arch(void) -{ - wsp_setup_arch(); - wsp_setup_h8(); - -} - -static int __init chroma_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "ibm,wsp-chroma")) - return 0; - - return 1; -} - -define_machine(chroma_md) { - .name = "Chroma PCIe", - .probe = chroma_probe, - .setup_arch = chroma_setup_arch, - .restart = wsp_h8_restart, - .power_off = wsp_h8_power_off, - .halt = wsp_halt, - .calibrate_decr = generic_calibrate_decr, - .init_IRQ = wsp_setup_irq, - .progress = udbg_progress, - .power_save = book3e_idle, -}; - -machine_arch_initcall(chroma_md, wsp_probe_devices); diff --git a/arch/powerpc/platforms/wsp/h8.c b/arch/powerpc/platforms/wsp/h8.c deleted file mode 100644 index a3c87f395750..000000000000 --- a/arch/powerpc/platforms/wsp/h8.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Copyright 2008-2011, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include - -#include "wsp.h" - -/* - * The UART connection to the H8 is over ttyS1 which is just a 16550. - * We assume that FW has it setup right and no one messes with it. - */ - - -static u8 __iomem *h8; - -#define RBR 0 /* Receiver Buffer Register */ -#define THR 0 /* Transmitter Holding Register */ -#define LSR 5 /* Line Status Register */ -#define LSR_DR 0x01 /* LSR value for Data-Ready */ -#define LSR_THRE 0x20 /* LSR value for Transmitter-Holding-Register-Empty */ -static void wsp_h8_putc(int c) -{ - u8 lsr; - - do { - lsr = readb(h8 + LSR); - } while ((lsr & LSR_THRE) != LSR_THRE); - writeb(c, h8 + THR); -} - -static int wsp_h8_getc(void) -{ - u8 lsr; - - do { - lsr = readb(h8 + LSR); - } while ((lsr & LSR_DR) != LSR_DR); - - return readb(h8 + RBR); -} - -static void wsp_h8_puts(const char *s, int sz) -{ - int i; - - for (i = 0; i < sz; i++) { - wsp_h8_putc(s[i]); - - /* no flow control so wait for echo */ - wsp_h8_getc(); - } - wsp_h8_putc('\r'); - wsp_h8_putc('\n'); -} - -static void wsp_h8_terminal_cmd(const char *cmd, int sz) -{ - hard_irq_disable(); - wsp_h8_puts(cmd, sz); - /* should never return, but just in case */ - for (;;) - continue; -} - - -void wsp_h8_restart(char *cmd) -{ - static const char restart[] = "warm-reset"; - - (void)cmd; - wsp_h8_terminal_cmd(restart, sizeof(restart) - 1); -} - -void wsp_h8_power_off(void) -{ - static const char off[] = "power-off"; - - wsp_h8_terminal_cmd(off, sizeof(off) - 1); -} - -static void __iomem *wsp_h8_getaddr(void) -{ - struct device_node *aliases; - struct device_node *uart; - struct property *path; - void __iomem *va = NULL; - - /* - * there is nothing in the devtree to tell us which is mapped - * to the H8, but se know it is the second serial port. - */ - - aliases = of_find_node_by_path("/aliases"); - if (aliases == NULL) - return NULL; - - path = of_find_property(aliases, "serial1", NULL); - if (path == NULL) - goto out; - - uart = of_find_node_by_path(path->value); - if (uart == NULL) - goto out; - - va = of_iomap(uart, 0); - - /* remove it so no one messes with it */ - of_detach_node(uart); - of_node_put(uart); - -out: - of_node_put(aliases); - - return va; -} - -void __init wsp_setup_h8(void) -{ - h8 = wsp_h8_getaddr(); - - /* Devtree change? lets hard map it anyway */ - if (h8 == NULL) { - pr_warn("UART to H8 could not be found"); - h8 = ioremap(0xffc0008000ULL, 0x100); - } -} diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c deleted file mode 100644 index 9cd92e645028..000000000000 --- a/arch/powerpc/platforms/wsp/ics.c +++ /dev/null @@ -1,762 +0,0 @@ -/* - * Copyright 2008-2011 IBM Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include "wsp.h" -#include "ics.h" - - -/* WSP ICS */ - -struct wsp_ics { - struct ics ics; - struct device_node *dn; - void __iomem *regs; - spinlock_t lock; - unsigned long *bitmap; - u32 chip_id; - u32 lsi_base; - u32 lsi_count; - u64 hwirq_start; - u64 count; -#ifdef CONFIG_SMP - int *hwirq_cpu_map; -#endif -}; - -#define to_wsp_ics(ics) container_of(ics, struct wsp_ics, ics) - -#define INT_SRC_LAYER_BUID_REG(base) ((base) + 0x00) -#define IODA_TBL_ADDR_REG(base) ((base) + 0x18) -#define IODA_TBL_DATA_REG(base) ((base) + 0x20) -#define XIVE_UPDATE_REG(base) ((base) + 0x28) -#define ICS_INT_CAPS_REG(base) ((base) + 0x30) - -#define TBL_AUTO_INCREMENT ((1UL << 63) | (1UL << 15)) -#define TBL_SELECT_XIST (1UL << 48) -#define TBL_SELECT_XIVT (1UL << 49) - -#define IODA_IRQ(irq) ((irq) & (0x7FFULL)) /* HRM 5.1.3.4 */ - -#define XIST_REQUIRED 0x8 -#define XIST_REJECTED 0x4 -#define XIST_PRESENTED 0x2 -#define XIST_PENDING 0x1 - -#define XIVE_SERVER_SHIFT 42 -#define XIVE_SERVER_MASK 0xFFFFULL -#define XIVE_PRIORITY_MASK 0xFFULL -#define XIVE_PRIORITY_SHIFT 32 -#define XIVE_WRITE_ENABLE (1ULL << 63) - -/* - * The docs refer to a 6 bit field called ChipID, which consists of a - * 3 bit NodeID and a 3 bit ChipID. On WSP the ChipID is always zero - * so we ignore it, and every where we use "chip id" in this code we - * mean the NodeID. - */ -#define WSP_ICS_CHIP_SHIFT 17 - - -static struct wsp_ics *ics_list; -static int num_ics; - -/* ICS Source controller accessors */ - -static u64 wsp_ics_get_xive(struct wsp_ics *ics, unsigned int irq) -{ - unsigned long flags; - u64 xive; - - spin_lock_irqsave(&ics->lock, flags); - out_be64(IODA_TBL_ADDR_REG(ics->regs), TBL_SELECT_XIVT | IODA_IRQ(irq)); - xive = in_be64(IODA_TBL_DATA_REG(ics->regs)); - spin_unlock_irqrestore(&ics->lock, flags); - - return xive; -} - -static void wsp_ics_set_xive(struct wsp_ics *ics, unsigned int irq, u64 xive) -{ - xive &= ~XIVE_ADDR_MASK; - xive |= (irq & XIVE_ADDR_MASK); - xive |= XIVE_WRITE_ENABLE; - - out_be64(XIVE_UPDATE_REG(ics->regs), xive); -} - -static u64 xive_set_server(u64 xive, unsigned int server) -{ - u64 mask = ~(XIVE_SERVER_MASK << XIVE_SERVER_SHIFT); - - xive &= mask; - xive |= (server & XIVE_SERVER_MASK) << XIVE_SERVER_SHIFT; - - return xive; -} - -static u64 xive_set_priority(u64 xive, unsigned int priority) -{ - u64 mask = ~(XIVE_PRIORITY_MASK << XIVE_PRIORITY_SHIFT); - - xive &= mask; - xive |= (priority & XIVE_PRIORITY_MASK) << XIVE_PRIORITY_SHIFT; - - return xive; -} - - -#ifdef CONFIG_SMP -/* Find logical CPUs within mask on a given chip and store result in ret */ -void cpus_on_chip(int chip_id, cpumask_t *mask, cpumask_t *ret) -{ - int cpu, chip; - struct device_node *cpu_dn, *dn; - const u32 *prop; - - cpumask_clear(ret); - for_each_cpu(cpu, mask) { - cpu_dn = of_get_cpu_node(cpu, NULL); - if (!cpu_dn) - continue; - - prop = of_get_property(cpu_dn, "at-node", NULL); - if (!prop) { - of_node_put(cpu_dn); - continue; - } - - dn = of_find_node_by_phandle(*prop); - of_node_put(cpu_dn); - - chip = wsp_get_chip_id(dn); - if (chip == chip_id) - cpumask_set_cpu(cpu, ret); - - of_node_put(dn); - } -} - -/* Store a suitable CPU to handle a hwirq in the ics->hwirq_cpu_map cache */ -static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, - const cpumask_t *affinity) -{ - cpumask_var_t avail, newmask; - int ret = -ENOMEM, cpu, cpu_rover = 0, target; - int index = hwirq - ics->hwirq_start; - unsigned int nodeid; - - BUG_ON(index < 0 || index >= ics->count); - - if (!ics->hwirq_cpu_map) - return -ENOMEM; - - if (!distribute_irqs) { - ics->hwirq_cpu_map[hwirq - ics->hwirq_start] = xics_default_server; - return 0; - } - - /* Allocate needed CPU masks */ - if (!alloc_cpumask_var(&avail, GFP_KERNEL)) - goto ret; - if (!alloc_cpumask_var(&newmask, GFP_KERNEL)) - goto freeavail; - - /* Find PBus attached to the source of this IRQ */ - nodeid = (hwirq >> WSP_ICS_CHIP_SHIFT) & 0x3; /* 12:14 */ - - /* Find CPUs that could handle this IRQ */ - if (affinity) - cpumask_and(avail, cpu_online_mask, affinity); - else - cpumask_copy(avail, cpu_online_mask); - - /* Narrow selection down to logical CPUs on the same chip */ - cpus_on_chip(nodeid, avail, newmask); - - /* Ensure we haven't narrowed it down to 0 */ - if (unlikely(cpumask_empty(newmask))) { - if (unlikely(cpumask_empty(avail))) { - ret = -1; - goto out; - } - cpumask_copy(newmask, avail); - } - - /* Choose a CPU out of those we narrowed it down to in round robin */ - target = hwirq % cpumask_weight(newmask); - for_each_cpu(cpu, newmask) { - if (cpu_rover++ >= target) { - ics->hwirq_cpu_map[index] = get_hard_smp_processor_id(cpu); - ret = 0; - goto out; - } - } - - /* Shouldn't happen */ - WARN_ON(1); - -out: - free_cpumask_var(newmask); -freeavail: - free_cpumask_var(avail); -ret: - if (ret < 0) { - ics->hwirq_cpu_map[index] = cpumask_first(cpu_online_mask); - pr_warning("Error, falling hwirq 0x%x routing back to CPU %i\n", - hwirq, ics->hwirq_cpu_map[index]); - } - return ret; -} - -static void alloc_irq_map(struct wsp_ics *ics) -{ - int i; - - ics->hwirq_cpu_map = kmalloc(sizeof(int) * ics->count, GFP_KERNEL); - if (!ics->hwirq_cpu_map) { - pr_warning("Allocate hwirq_cpu_map failed, " - "IRQ balancing disabled\n"); - return; - } - - for (i=0; i < ics->count; i++) - ics->hwirq_cpu_map[i] = xics_default_server; -} - -static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) -{ - int index = hwirq - ics->hwirq_start; - - BUG_ON(index < 0 || index >= ics->count); - - if (!ics->hwirq_cpu_map) - return xics_default_server; - - return ics->hwirq_cpu_map[index]; -} -#else /* !CONFIG_SMP */ -static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, - const cpumask_t *affinity) -{ - return 0; -} - -static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) -{ - return xics_default_server; -} - -static void alloc_irq_map(struct wsp_ics *ics) { } -#endif - -static void wsp_chip_unmask_irq(struct irq_data *d) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics; - int server; - u64 xive; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return; - - ics = d->chip_data; - if (WARN_ON(!ics)) - return; - - server = get_irq_server(ics, hw_irq); - - xive = wsp_ics_get_xive(ics, hw_irq); - xive = xive_set_server(xive, server); - xive = xive_set_priority(xive, DEFAULT_PRIORITY); - wsp_ics_set_xive(ics, hw_irq, xive); -} - -static unsigned int wsp_chip_startup(struct irq_data *d) -{ - /* unmask it */ - wsp_chip_unmask_irq(d); - return 0; -} - -static void wsp_mask_real_irq(unsigned int hw_irq, struct wsp_ics *ics) -{ - u64 xive; - - if (hw_irq == XICS_IPI) - return; - - if (WARN_ON(!ics)) - return; - xive = wsp_ics_get_xive(ics, hw_irq); - xive = xive_set_server(xive, xics_default_server); - xive = xive_set_priority(xive, LOWEST_PRIORITY); - wsp_ics_set_xive(ics, hw_irq, xive); -} - -static void wsp_chip_mask_irq(struct irq_data *d) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics = d->chip_data; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return; - - wsp_mask_real_irq(hw_irq, ics); -} - -static int wsp_chip_set_affinity(struct irq_data *d, - const struct cpumask *cpumask, bool force) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics; - int ret; - u64 xive; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return -1; - - ics = d->chip_data; - if (WARN_ON(!ics)) - return -1; - xive = wsp_ics_get_xive(ics, hw_irq); - - /* - * For the moment only implement delivery to all cpus or one cpu. - * Get current irq_server for the given irq - */ - ret = cache_hwirq_map(ics, hw_irq, cpumask); - if (ret == -1) { - char cpulist[128]; - cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); - pr_warning("%s: No online cpus in the mask %s for irq %d\n", - __func__, cpulist, d->irq); - return -1; - } else if (ret == -ENOMEM) { - pr_warning("%s: Out of memory\n", __func__); - return -1; - } - - xive = xive_set_server(xive, get_irq_server(ics, hw_irq)); - wsp_ics_set_xive(ics, hw_irq, xive); - - return IRQ_SET_MASK_OK; -} - -static struct irq_chip wsp_irq_chip = { - .name = "WSP ICS", - .irq_startup = wsp_chip_startup, - .irq_mask = wsp_chip_mask_irq, - .irq_unmask = wsp_chip_unmask_irq, - .irq_set_affinity = wsp_chip_set_affinity -}; - -static int wsp_ics_host_match(struct ics *ics, struct device_node *dn) -{ - /* All ICSs in the system implement a global irq number space, - * so match against them all. */ - return of_device_is_compatible(dn, "ibm,ppc-xics"); -} - -static int wsp_ics_match_hwirq(struct wsp_ics *wsp_ics, unsigned int hwirq) -{ - if (hwirq >= wsp_ics->hwirq_start && - hwirq < wsp_ics->hwirq_start + wsp_ics->count) - return 1; - - return 0; -} - -static int wsp_ics_map(struct ics *ics, unsigned int virq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - unsigned int hw_irq = virq_to_hw(virq); - unsigned long flags; - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return -ENOENT; - - irq_set_chip_and_handler(virq, &wsp_irq_chip, handle_fasteoi_irq); - - irq_set_chip_data(virq, wsp_ics); - - spin_lock_irqsave(&wsp_ics->lock, flags); - bitmap_allocate_region(wsp_ics->bitmap, hw_irq - wsp_ics->hwirq_start, 0); - spin_unlock_irqrestore(&wsp_ics->lock, flags); - - return 0; -} - -static void wsp_ics_mask_unknown(struct ics *ics, unsigned long hw_irq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return; - - pr_err("%s: IRQ %lu (real) is invalid, disabling it.\n", __func__, hw_irq); - wsp_mask_real_irq(hw_irq, wsp_ics); -} - -static long wsp_ics_get_server(struct ics *ics, unsigned long hw_irq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return -ENOENT; - - return get_irq_server(wsp_ics, hw_irq); -} - -/* HW Number allocation API */ - -static struct wsp_ics *wsp_ics_find_dn_ics(struct device_node *dn) -{ - struct device_node *iparent; - int i; - - iparent = of_irq_find_parent(dn); - if (!iparent) { - pr_err("wsp_ics: Failed to find interrupt parent!\n"); - return NULL; - } - - for(i = 0; i < num_ics; i++) { - if(ics_list[i].dn == iparent) - break; - } - - if (i >= num_ics) { - pr_err("wsp_ics: Unable to find parent bitmap!\n"); - return NULL; - } - - return &ics_list[i]; -} - -int wsp_ics_alloc_irq(struct device_node *dn, int num) -{ - struct wsp_ics *ics; - int order, offset; - - ics = wsp_ics_find_dn_ics(dn); - if (!ics) - return -ENODEV; - - /* Fast, but overly strict if num isn't a power of two */ - order = get_count_order(num); - - spin_lock_irq(&ics->lock); - offset = bitmap_find_free_region(ics->bitmap, ics->count, order); - spin_unlock_irq(&ics->lock); - - if (offset < 0) - return offset; - - return offset + ics->hwirq_start; -} - -void wsp_ics_free_irq(struct device_node *dn, unsigned int irq) -{ - struct wsp_ics *ics; - - ics = wsp_ics_find_dn_ics(dn); - if (WARN_ON(!ics)) - return; - - spin_lock_irq(&ics->lock); - bitmap_release_region(ics->bitmap, irq, 0); - spin_unlock_irq(&ics->lock); -} - -/* Initialisation */ - -static int __init wsp_ics_bitmap_setup(struct wsp_ics *ics, - struct device_node *dn) -{ - int len, i, j, size; - u32 start, count; - const u32 *p; - - size = BITS_TO_LONGS(ics->count) * sizeof(long); - ics->bitmap = kzalloc(size, GFP_KERNEL); - if (!ics->bitmap) { - pr_err("wsp_ics: ENOMEM allocating IRQ bitmap!\n"); - return -ENOMEM; - } - - spin_lock_init(&ics->lock); - - p = of_get_property(dn, "available-ranges", &len); - if (!p || !len) { - /* FIXME this should be a WARN() once mambo is updated */ - pr_err("wsp_ics: No available-ranges defined for %s\n", - dn->full_name); - return 0; - } - - if (len % (2 * sizeof(u32)) != 0) { - /* FIXME this should be a WARN() once mambo is updated */ - pr_err("wsp_ics: Invalid available-ranges for %s\n", - dn->full_name); - return 0; - } - - bitmap_fill(ics->bitmap, ics->count); - - for (i = 0; i < len / sizeof(u32); i += 2) { - start = of_read_number(p + i, 1); - count = of_read_number(p + i + 1, 1); - - pr_devel("%s: start: %d count: %d\n", __func__, start, count); - - if ((start + count) > (ics->hwirq_start + ics->count) || - start < ics->hwirq_start) { - pr_err("wsp_ics: Invalid range! -> %d to %d\n", - start, start + count); - break; - } - - for (j = 0; j < count; j++) - bitmap_release_region(ics->bitmap, - (start + j) - ics->hwirq_start, 0); - } - - /* Ensure LSIs are not available for allocation */ - bitmap_allocate_region(ics->bitmap, ics->lsi_base, - get_count_order(ics->lsi_count)); - - return 0; -} - -static int __init wsp_ics_setup(struct wsp_ics *ics, struct device_node *dn) -{ - u32 lsi_buid, msi_buid, msi_base, msi_count; - void __iomem *regs; - const u32 *p; - int rc, len, i; - u64 caps, buid; - - p = of_get_property(dn, "interrupt-ranges", &len); - if (!p || len < (2 * sizeof(u32))) { - pr_err("wsp_ics: No/bad interrupt-ranges found on %s\n", - dn->full_name); - return -ENOENT; - } - - if (len > (2 * sizeof(u32))) { - pr_err("wsp_ics: Multiple ics ranges not supported.\n"); - return -EINVAL; - } - - regs = of_iomap(dn, 0); - if (!regs) { - pr_err("wsp_ics: of_iomap(%s) failed\n", dn->full_name); - return -ENXIO; - } - - ics->hwirq_start = of_read_number(p, 1); - ics->count = of_read_number(p + 1, 1); - ics->regs = regs; - - ics->chip_id = wsp_get_chip_id(dn); - if (WARN_ON(ics->chip_id < 0)) - ics->chip_id = 0; - - /* Get some informations about the critter */ - caps = in_be64(ICS_INT_CAPS_REG(ics->regs)); - buid = in_be64(INT_SRC_LAYER_BUID_REG(ics->regs)); - ics->lsi_count = caps >> 56; - msi_count = (caps >> 44) & 0x7ff; - - /* Note: LSI BUID is 9 bits, but really only 3 are BUID and the - * rest is mixed in the interrupt number. We store the whole - * thing though - */ - lsi_buid = (buid >> 48) & 0x1ff; - ics->lsi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | lsi_buid << 5; - msi_buid = (buid >> 37) & 0x7; - msi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | msi_buid << 11; - - pr_info("wsp_ics: Found %s\n", dn->full_name); - pr_info("wsp_ics: irq range : 0x%06llx..0x%06llx\n", - ics->hwirq_start, ics->hwirq_start + ics->count - 1); - pr_info("wsp_ics: %4d LSIs : 0x%06x..0x%06x\n", - ics->lsi_count, ics->lsi_base, - ics->lsi_base + ics->lsi_count - 1); - pr_info("wsp_ics: %4d MSIs : 0x%06x..0x%06x\n", - msi_count, msi_base, - msi_base + msi_count - 1); - - /* Let's check the HW config is sane */ - if (ics->lsi_base < ics->hwirq_start || - (ics->lsi_base + ics->lsi_count) > (ics->hwirq_start + ics->count)) - pr_warning("wsp_ics: WARNING ! LSIs out of interrupt-ranges !\n"); - if (msi_base < ics->hwirq_start || - (msi_base + msi_count) > (ics->hwirq_start + ics->count)) - pr_warning("wsp_ics: WARNING ! MSIs out of interrupt-ranges !\n"); - - /* We don't check for overlap between LSI and MSI, which will happen - * if we use the same BUID, I'm not sure yet how legit that is. - */ - - rc = wsp_ics_bitmap_setup(ics, dn); - if (rc) { - iounmap(regs); - return rc; - } - - ics->dn = of_node_get(dn); - alloc_irq_map(ics); - - for(i = 0; i < ics->count; i++) - wsp_mask_real_irq(ics->hwirq_start + i, ics); - - ics->ics.map = wsp_ics_map; - ics->ics.mask_unknown = wsp_ics_mask_unknown; - ics->ics.get_server = wsp_ics_get_server; - ics->ics.host_match = wsp_ics_host_match; - - xics_register_ics(&ics->ics); - - return 0; -} - -static void __init wsp_ics_set_default_server(void) -{ - struct device_node *np; - u32 hwid; - - /* Find the server number for the boot cpu. */ - np = of_get_cpu_node(boot_cpuid, NULL); - BUG_ON(!np); - - hwid = get_hard_smp_processor_id(boot_cpuid); - - pr_info("wsp_ics: default server is %#x, CPU %s\n", hwid, np->full_name); - xics_default_server = hwid; - - of_node_put(np); -} - -static int __init wsp_ics_init(void) -{ - struct device_node *dn; - struct wsp_ics *ics; - int rc, found; - - wsp_ics_set_default_server(); - - found = 0; - for_each_compatible_node(dn, NULL, "ibm,ppc-xics") - found++; - - if (found == 0) { - pr_err("wsp_ics: No ICS's found!\n"); - return -ENODEV; - } - - ics_list = kmalloc(sizeof(*ics) * found, GFP_KERNEL); - if (!ics_list) { - pr_err("wsp_ics: No memory for structs.\n"); - return -ENOMEM; - } - - num_ics = 0; - ics = ics_list; - for_each_compatible_node(dn, NULL, "ibm,wsp-xics") { - rc = wsp_ics_setup(ics, dn); - if (rc == 0) { - ics++; - num_ics++; - } - } - - if (found != num_ics) { - pr_err("wsp_ics: Failed setting up %d ICS's\n", - found - num_ics); - return -1; - } - - return 0; -} - -void __init wsp_init_irq(void) -{ - wsp_ics_init(); - xics_init(); - - /* We need to patch our irq chip's EOI to point to the right ICP */ - wsp_irq_chip.irq_eoi = icp_ops->eoi; -} - -#ifdef CONFIG_PCI_MSI -static void wsp_ics_msi_unmask_irq(struct irq_data *d) -{ - wsp_chip_unmask_irq(d); - unmask_msi_irq(d); -} - -static unsigned int wsp_ics_msi_startup(struct irq_data *d) -{ - wsp_ics_msi_unmask_irq(d); - return 0; -} - -static void wsp_ics_msi_mask_irq(struct irq_data *d) -{ - mask_msi_irq(d); - wsp_chip_mask_irq(d); -} - -/* - * we do it this way because we reassinge default EOI handling in - * irq_init() above - */ -static void wsp_ics_eoi(struct irq_data *data) -{ - wsp_irq_chip.irq_eoi(data); -} - -static struct irq_chip wsp_ics_msi = { - .name = "WSP ICS MSI", - .irq_startup = wsp_ics_msi_startup, - .irq_mask = wsp_ics_msi_mask_irq, - .irq_unmask = wsp_ics_msi_unmask_irq, - .irq_eoi = wsp_ics_eoi, - .irq_set_affinity = wsp_chip_set_affinity -}; - -void wsp_ics_set_msi_chip(unsigned int irq) -{ - irq_set_chip(irq, &wsp_ics_msi); -} - -void wsp_ics_set_std_chip(unsigned int irq) -{ - irq_set_chip(irq, &wsp_irq_chip); -} -#endif /* CONFIG_PCI_MSI */ diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h deleted file mode 100644 index 07b644e0cf97..000000000000 --- a/arch/powerpc/platforms/wsp/ics.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Copyright 2009 IBM Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef __ICS_H -#define __ICS_H - -#define XIVE_ADDR_MASK 0x7FFULL - -extern void wsp_init_irq(void); - -extern int wsp_ics_alloc_irq(struct device_node *dn, int num); -extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq); - -#ifdef CONFIG_PCI_MSI -extern void wsp_ics_set_msi_chip(unsigned int irq); -extern void wsp_ics_set_std_chip(unsigned int irq); -#endif /* CONFIG_PCI_MSI */ - -#endif /* __ICS_H */ diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c deleted file mode 100644 index 380882f27add..000000000000 --- a/arch/powerpc/platforms/wsp/msi.c +++ /dev/null @@ -1,102 +0,0 @@ -/* - * Copyright 2011 Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include - -#include "msi.h" -#include "ics.h" -#include "wsp_pci.h" - -/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */ -#define MSI_ADDR_32 0xFFFF0000ul -#define MSI_ADDR_64 0x1000000000000000ul - -int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - struct pci_controller *phb; - struct msi_desc *entry; - struct msi_msg msg; - unsigned int virq; - int hwirq; - - phb = pci_bus_to_host(dev->bus); - if (!phb) - return -ENOENT; - - entry = list_first_entry(&dev->msi_list, struct msi_desc, list); - if (entry->msi_attrib.is_64) { - msg.address_lo = 0; - msg.address_hi = MSI_ADDR_64 >> 32; - } else { - msg.address_lo = MSI_ADDR_32; - msg.address_hi = 0; - } - - list_for_each_entry(entry, &dev->msi_list, list) { - hwirq = wsp_ics_alloc_irq(phb->dn, 1); - if (hwirq < 0) { - dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n"); - return hwirq; - } - - virq = irq_create_mapping(NULL, hwirq); - if (virq == NO_IRQ) { - dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n"); - return -1; - } - - dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n", - hwirq, virq); - - wsp_ics_set_msi_chip(virq); - irq_set_msi_desc(virq, entry); - msg.data = hwirq & XIVE_ADDR_MASK; - write_msi_msg(virq, &msg); - } - - return 0; -} - -void wsp_teardown_msi_irqs(struct pci_dev *dev) -{ - struct pci_controller *phb; - struct msi_desc *entry; - int hwirq; - - phb = pci_bus_to_host(dev->bus); - - dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n"); - - list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq == NO_IRQ) - continue; - - irq_set_msi_desc(entry->irq, NULL); - wsp_ics_set_std_chip(entry->irq); - - hwirq = virq_to_hw(entry->irq); - /* In this order to avoid racing with irq_create_mapping() */ - irq_dispose_mapping(entry->irq); - wsp_ics_free_irq(phb->dn, hwirq); - } -} - -void wsp_setup_phb_msi(struct pci_controller *phb) -{ - /* Create a single MVE at offset 0 that matches everything */ - out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT); - out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63); - - ppc_md.setup_msi_irqs = wsp_setup_msi_irqs; - ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs; -} diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h deleted file mode 100644 index 0ab27b71b24d..000000000000 --- a/arch/powerpc/platforms/wsp/msi.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Copyright 2011 Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef __WSP_MSI_H -#define __WSP_MSI_H - -#ifdef CONFIG_PCI_MSI -extern void wsp_setup_phb_msi(struct pci_controller *phb); -#else -static inline void wsp_setup_phb_msi(struct pci_controller *phb) { } -#endif - -#endif /* __WSP_MSI_H */ diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c deleted file mode 100644 index 3f6729807938..000000000000 --- a/arch/powerpc/platforms/wsp/opb_pic.c +++ /dev/null @@ -1,321 +0,0 @@ -/* - * IBM Onboard Peripheral Bus Interrupt Controller - * - * Copyright 2010 Jack Miller, IBM Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#define OPB_NR_IRQS 32 - -#define OPB_MLSASIER 0x04 /* MLS Accumulated Status IER */ -#define OPB_MLSIR 0x50 /* MLS Interrupt Register */ -#define OPB_MLSIER 0x54 /* MLS Interrupt Enable Register */ -#define OPB_MLSIPR 0x58 /* MLS Interrupt Polarity Register */ -#define OPB_MLSIIR 0x5c /* MLS Interrupt Inputs Register */ - -static int opb_index = 0; - -struct opb_pic { - struct irq_domain *host; - void *regs; - int index; - spinlock_t lock; -}; - -static u32 opb_in(struct opb_pic *opb, int offset) -{ - return in_be32(opb->regs + offset); -} - -static void opb_out(struct opb_pic *opb, int offset, u32 val) -{ - out_be32(opb->regs + offset, val); -} - -static void opb_unmask_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 ier, bitset; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier | bitset); - ier = opb_in(opb, OPB_MLSIER); - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_mask_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 ier, mask; - - opb = d->chip_data; - mask = ~(1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier & mask); - ier = opb_in(opb, OPB_MLSIER); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_ack_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 bitset; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - opb_out(opb, OPB_MLSIR, bitset); - opb_in(opb, OPB_MLSIR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_mask_ack_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 bitset; - u32 ier, ir; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier & ~bitset); - ier = opb_in(opb, OPB_MLSIER); // Flush posted writes - - opb_out(opb, OPB_MLSIR, bitset); - ir = opb_in(opb, OPB_MLSIR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static int opb_set_irq_type(struct irq_data *d, unsigned int flow) -{ - struct opb_pic *opb; - unsigned long flags; - int invert, ipr, mask, bit; - - opb = d->chip_data; - - /* The only information we're interested in in the type is whether it's - * a high or low trigger. For high triggered interrupts, the polarity - * set for it in the MLS Interrupt Polarity Register is 0, for low - * interrupts it's 1 so that the proper input in the MLS Interrupt Input - * Register is interrupted as asserting the interrupt. */ - - switch (flow) { - case IRQ_TYPE_NONE: - opb_mask_irq(d); - return 0; - - case IRQ_TYPE_LEVEL_HIGH: - invert = 0; - break; - - case IRQ_TYPE_LEVEL_LOW: - invert = 1; - break; - - default: - return -EINVAL; - } - - bit = (1 << (31 - irqd_to_hwirq(d))); - mask = ~bit; - - spin_lock_irqsave(&opb->lock, flags); - - ipr = opb_in(opb, OPB_MLSIPR); - ipr = (ipr & mask) | (invert ? bit : 0); - opb_out(opb, OPB_MLSIPR, ipr); - ipr = opb_in(opb, OPB_MLSIPR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); - - /* Record the type in the interrupt descriptor */ - irqd_set_trigger_type(d, flow); - - return 0; -} - -static struct irq_chip opb_irq_chip = { - .name = "OPB", - .irq_mask = opb_mask_irq, - .irq_unmask = opb_unmask_irq, - .irq_mask_ack = opb_mask_ack_irq, - .irq_ack = opb_ack_irq, - .irq_set_type = opb_set_irq_type -}; - -static int opb_host_map(struct irq_domain *host, unsigned int virq, - irq_hw_number_t hwirq) -{ - struct opb_pic *opb; - - opb = host->host_data; - - /* Most of the important stuff is handled by the generic host code, like - * the lookup, so just attach some info to the virtual irq */ - - irq_set_chip_data(virq, opb); - irq_set_chip_and_handler(virq, &opb_irq_chip, handle_level_irq); - irq_set_irq_type(virq, IRQ_TYPE_NONE); - - return 0; -} - -static const struct irq_domain_ops opb_host_ops = { - .map = opb_host_map, - .xlate = irq_domain_xlate_twocell, -}; - -irqreturn_t opb_irq_handler(int irq, void *private) -{ - struct opb_pic *opb; - u32 ir, src, subvirq; - - opb = (struct opb_pic *) private; - - /* Read the OPB MLS Interrupt Register for - * asserted interrupts */ - ir = opb_in(opb, OPB_MLSIR); - if (!ir) - return IRQ_NONE; - - do { - /* Get 1 - 32 source, *NOT* bit */ - src = 32 - ffs(ir); - - /* Translate from the OPB's conception of interrupt number to - * Linux's virtual IRQ */ - - subvirq = irq_linear_revmap(opb->host, src); - - generic_handle_irq(subvirq); - } while ((ir = opb_in(opb, OPB_MLSIR))); - - return IRQ_HANDLED; -} - -struct opb_pic *opb_pic_init_one(struct device_node *dn) -{ - struct opb_pic *opb; - struct resource res; - - if (of_address_to_resource(dn, 0, &res)) { - printk(KERN_ERR "opb: Couldn't translate resource\n"); - return NULL; - } - - opb = kzalloc(sizeof(struct opb_pic), GFP_KERNEL); - if (!opb) { - printk(KERN_ERR "opb: Failed to allocate opb struct!\n"); - return NULL; - } - - /* Get access to the OPB MMIO registers */ - opb->regs = ioremap(res.start + 0x10000, 0x1000); - if (!opb->regs) { - printk(KERN_ERR "opb: Failed to allocate register space!\n"); - goto free_opb; - } - - /* Allocate an irq domain so that Linux knows that despite only - * having one interrupt to issue, we're the controller for multiple - * hardware IRQs, so later we can lookup their virtual IRQs. */ - - opb->host = irq_domain_add_linear(dn, OPB_NR_IRQS, &opb_host_ops, opb); - if (!opb->host) { - printk(KERN_ERR "opb: Failed to allocate IRQ host!\n"); - goto free_regs; - } - - opb->index = opb_index++; - spin_lock_init(&opb->lock); - - /* Disable all interrupts by default */ - opb_out(opb, OPB_MLSASIER, 0); - opb_out(opb, OPB_MLSIER, 0); - - /* ACK any interrupts left by FW */ - opb_out(opb, OPB_MLSIR, 0xFFFFFFFF); - - return opb; - -free_regs: - iounmap(opb->regs); -free_opb: - kfree(opb); - return NULL; -} - -void __init opb_pic_init(void) -{ - struct device_node *dn; - struct opb_pic *opb; - int virq; - int rc; - - /* Call init_one for each OPB device */ - for_each_compatible_node(dn, NULL, "ibm,opb") { - - /* Fill in an OPB struct */ - opb = opb_pic_init_one(dn); - if (!opb) { - printk(KERN_WARNING "opb: Failed to init node, skipped!\n"); - continue; - } - - /* Map / get opb's hardware virtual irq */ - virq = irq_of_parse_and_map(dn, 0); - if (virq <= 0) { - printk("opb: irq_op_parse_and_map failed!\n"); - continue; - } - - /* Attach opb interrupt handler to new virtual IRQ */ - rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD, - "OPB LS Cascade", opb); - if (rc) { - printk("opb: request_irq failed: %d\n", rc); - continue; - } - - printk("OPB%d init with %d IRQs at %p\n", opb->index, - OPB_NR_IRQS, opb->regs); - } -} diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c deleted file mode 100644 index a87b414c766a..000000000000 --- a/arch/powerpc/platforms/wsp/psr2.c +++ /dev/null @@ -1,67 +0,0 @@ -/* - * Copyright 2008-2011, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include "ics.h" -#include "wsp.h" - - -static void psr2_spin(void) -{ - hard_irq_disable(); - for (;;) - continue; -} - -static void psr2_restart(char *cmd) -{ - psr2_spin(); -} - -static int __init psr2_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (of_flat_dt_is_compatible(root, "ibm,wsp-chroma")) { - /* chroma systems also claim they are psr2s */ - return 0; - } - - if (!of_flat_dt_is_compatible(root, "ibm,psr2")) - return 0; - - return 1; -} - -define_machine(psr2_md) { - .name = "PSR2 A2", - .probe = psr2_probe, - .setup_arch = wsp_setup_arch, - .restart = psr2_restart, - .power_off = psr2_spin, - .halt = psr2_spin, - .calibrate_decr = generic_calibrate_decr, - .init_IRQ = wsp_setup_irq, - .progress = udbg_progress, - .power_save = book3e_idle, -}; - -machine_arch_initcall(psr2_md, wsp_probe_devices); diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c deleted file mode 100644 index 8c79ce016cf1..000000000000 --- a/arch/powerpc/platforms/wsp/scom_smp.c +++ /dev/null @@ -1,435 +0,0 @@ -/* - * SCOM support for A2 platforms - * - * Copyright 2007-2011 Benjamin Herrenschmidt, David Gibson, - * Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include "wsp.h" - -#define SCOM_RAMC 0x2a /* Ram Command */ -#define SCOM_RAMC_TGT1_EXT 0x80000000 -#define SCOM_RAMC_SRC1_EXT 0x40000000 -#define SCOM_RAMC_SRC2_EXT 0x20000000 -#define SCOM_RAMC_SRC3_EXT 0x10000000 -#define SCOM_RAMC_ENABLE 0x00080000 -#define SCOM_RAMC_THREADSEL 0x00060000 -#define SCOM_RAMC_EXECUTE 0x00010000 -#define SCOM_RAMC_MSR_OVERRIDE 0x00008000 -#define SCOM_RAMC_MSR_PR 0x00004000 -#define SCOM_RAMC_MSR_GS 0x00002000 -#define SCOM_RAMC_FORCE 0x00001000 -#define SCOM_RAMC_FLUSH 0x00000800 -#define SCOM_RAMC_INTERRUPT 0x00000004 -#define SCOM_RAMC_ERROR 0x00000002 -#define SCOM_RAMC_DONE 0x00000001 -#define SCOM_RAMI 0x29 /* Ram Instruction */ -#define SCOM_RAMIC 0x28 /* Ram Instruction and Command */ -#define SCOM_RAMIC_INSN 0xffffffff00000000 -#define SCOM_RAMD 0x2d /* Ram Data */ -#define SCOM_RAMDH 0x2e /* Ram Data High */ -#define SCOM_RAMDL 0x2f /* Ram Data Low */ -#define SCOM_PCCR0 0x33 /* PC Configuration Register 0 */ -#define SCOM_PCCR0_ENABLE_DEBUG 0x80000000 -#define SCOM_PCCR0_ENABLE_RAM 0x40000000 -#define SCOM_THRCTL 0x30 /* Thread Control and Status */ -#define SCOM_THRCTL_T0_STOP 0x80000000 -#define SCOM_THRCTL_T1_STOP 0x40000000 -#define SCOM_THRCTL_T2_STOP 0x20000000 -#define SCOM_THRCTL_T3_STOP 0x10000000 -#define SCOM_THRCTL_T0_STEP 0x08000000 -#define SCOM_THRCTL_T1_STEP 0x04000000 -#define SCOM_THRCTL_T2_STEP 0x02000000 -#define SCOM_THRCTL_T3_STEP 0x01000000 -#define SCOM_THRCTL_T0_RUN 0x00800000 -#define SCOM_THRCTL_T1_RUN 0x00400000 -#define SCOM_THRCTL_T2_RUN 0x00200000 -#define SCOM_THRCTL_T3_RUN 0x00100000 -#define SCOM_THRCTL_T0_PM 0x00080000 -#define SCOM_THRCTL_T1_PM 0x00040000 -#define SCOM_THRCTL_T2_PM 0x00020000 -#define SCOM_THRCTL_T3_PM 0x00010000 -#define SCOM_THRCTL_T0_UDE 0x00008000 -#define SCOM_THRCTL_T1_UDE 0x00004000 -#define SCOM_THRCTL_T2_UDE 0x00002000 -#define SCOM_THRCTL_T3_UDE 0x00001000 -#define SCOM_THRCTL_ASYNC_DIS 0x00000800 -#define SCOM_THRCTL_TB_DIS 0x00000400 -#define SCOM_THRCTL_DEC_DIS 0x00000200 -#define SCOM_THRCTL_AND 0x31 /* Thread Control and Status */ -#define SCOM_THRCTL_OR 0x32 /* Thread Control and Status */ - - -static DEFINE_PER_CPU(scom_map_t, scom_ptrs); - -static scom_map_t get_scom(int cpu, struct device_node *np, int *first_thread) -{ - scom_map_t scom = per_cpu(scom_ptrs, cpu); - int tcpu; - - if (scom_map_ok(scom)) { - *first_thread = 0; - return scom; - } - - *first_thread = 1; - - scom = scom_map_device(np, 0); - - for (tcpu = cpu_first_thread_sibling(cpu); - tcpu <= cpu_last_thread_sibling(cpu); tcpu++) - per_cpu(scom_ptrs, tcpu) = scom; - - /* Hack: for the boot core, this will actually get called on - * the second thread up, not the first so our test above will - * set first_thread incorrectly. */ - if (cpu_first_thread_sibling(cpu) == 0) - *first_thread = 0; - - return scom; -} - -static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask) -{ - u64 cmd, mask, val; - int n = 0; - - cmd = ((u64)insn << 32) | (((u64)extmask & 0xf) << 28) - | ((u64)thread << 17) | SCOM_RAMC_ENABLE | SCOM_RAMC_EXECUTE; - mask = SCOM_RAMC_DONE | SCOM_RAMC_INTERRUPT | SCOM_RAMC_ERROR; - - scom_write(scom, SCOM_RAMIC, cmd); - - for (;;) { - if (scom_read(scom, SCOM_RAMC, &val) != 0) { - pr_err("SCOM error on instruction 0x%08x, thread %d\n", - insn, thread); - return -1; - } - if (val & mask) - break; - pr_devel("Waiting on RAMC = 0x%llx\n", val); - if (++n == 3) { - pr_err("RAMC timeout on instruction 0x%08x, thread %d\n", - insn, thread); - return -1; - } - } - - if (val & SCOM_RAMC_INTERRUPT) { - pr_err("RAMC interrupt on instruction 0x%08x, thread %d\n", - insn, thread); - return -SCOM_RAMC_INTERRUPT; - } - - if (val & SCOM_RAMC_ERROR) { - pr_err("RAMC error on instruction 0x%08x, thread %d\n", - insn, thread); - return -SCOM_RAMC_ERROR; - } - - return 0; -} - -static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt, - u64 *out_gpr) -{ - int rc; - - /* or rN, rN, rN */ - u32 insn = 0x7c000378 | (gpr << 21) | (gpr << 16) | (gpr << 11); - rc = a2_scom_ram(scom, thread, insn, alt ? 0xf : 0x0); - if (rc) - return rc; - - return scom_read(scom, SCOM_RAMD, out_gpr); -} - -static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr) -{ - int rc, sprhi, sprlo; - u32 insn; - - sprhi = spr >> 5; - sprlo = spr & 0x1f; - insn = 0x7c2002a6 | (sprlo << 16) | (sprhi << 11); /* mfspr r1,spr */ - - if (spr == 0x0ff0) - insn = 0x7c2000a6; /* mfmsr r1 */ - - rc = a2_scom_ram(scom, thread, insn, 0xf); - if (rc) - return rc; - return a2_scom_getgpr(scom, thread, 1, 1, out_spr); -} - -static int a2_scom_setgpr(scom_map_t scom, int thread, int gpr, - int alt, u64 val) -{ - u32 lis = 0x3c000000 | (gpr << 21); - u32 li = 0x38000000 | (gpr << 21); - u32 oris = 0x64000000 | (gpr << 21) | (gpr << 16); - u32 ori = 0x60000000 | (gpr << 21) | (gpr << 16); - u32 rldicr32 = 0x780007c6 | (gpr << 21) | (gpr << 16); - u32 highest = val >> 48; - u32 higher = (val >> 32) & 0xffff; - u32 high = (val >> 16) & 0xffff; - u32 low = val & 0xffff; - int lext = alt ? 0x8 : 0x0; - int oext = alt ? 0xf : 0x0; - int rc = 0; - - if (highest) - rc |= a2_scom_ram(scom, thread, lis | highest, lext); - - if (higher) { - if (highest) - rc |= a2_scom_ram(scom, thread, oris | higher, oext); - else - rc |= a2_scom_ram(scom, thread, li | higher, lext); - } - - if (highest || higher) - rc |= a2_scom_ram(scom, thread, rldicr32, oext); - - if (high) { - if (highest || higher) - rc |= a2_scom_ram(scom, thread, oris | high, oext); - else - rc |= a2_scom_ram(scom, thread, lis | high, lext); - } - - if (highest || higher || high) - rc |= a2_scom_ram(scom, thread, ori | low, oext); - else - rc |= a2_scom_ram(scom, thread, li | low, lext); - - return rc; -} - -static int a2_scom_setspr(scom_map_t scom, int thread, int spr, u64 val) -{ - int sprhi = spr >> 5; - int sprlo = spr & 0x1f; - /* mtspr spr, r1 */ - u32 insn = 0x7c2003a6 | (sprlo << 16) | (sprhi << 11); - - if (spr == 0x0ff0) - insn = 0x7c200124; /* mtmsr r1 */ - - if (a2_scom_setgpr(scom, thread, 1, 1, val)) - return -1; - - return a2_scom_ram(scom, thread, insn, 0xf); -} - -static int a2_scom_initial_tlb(scom_map_t scom, int thread) -{ - extern u32 a2_tlbinit_code_start[], a2_tlbinit_code_end[]; - extern u32 a2_tlbinit_after_iprot_flush[]; - extern u32 a2_tlbinit_after_linear_map[]; - u32 assoc, entries, i; - u64 epn, tlbcfg; - u32 *p; - int rc; - - /* Invalidate all entries (including iprot) */ - - rc = a2_scom_getspr(scom, thread, SPRN_TLB0CFG, &tlbcfg); - if (rc) - goto scom_fail; - entries = tlbcfg & TLBnCFG_N_ENTRY; - assoc = (tlbcfg & TLBnCFG_ASSOC) >> 24; - epn = 0; - - /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ - a2_scom_setspr(scom, thread, SPRN_MMUCR2, 0x000a7531); - /* Set MMUCR3 to write all thids bit to the TLB */ - a2_scom_setspr(scom, thread, SPRN_MMUCR3, 0x0000000f); - - /* Set MAS1 for 1G page size, and MAS2 to our initial EPN */ - a2_scom_setspr(scom, thread, SPRN_MAS1, MAS1_TSIZE(BOOK3E_PAGESZ_1GB)); - a2_scom_setspr(scom, thread, SPRN_MAS2, epn); - for (i = 0; i < entries; i++) { - - a2_scom_setspr(scom, thread, SPRN_MAS0, MAS0_ESEL(i % assoc)); - - /* tlbwe */ - rc = a2_scom_ram(scom, thread, 0x7c0007a4, 0); - if (rc) - goto scom_fail; - - /* Next entry is new address? */ - if((i + 1) % assoc == 0) { - epn += (1 << 30); - a2_scom_setspr(scom, thread, SPRN_MAS2, epn); - } - } - - /* Setup args for linear mapping */ - rc = a2_scom_setgpr(scom, thread, 3, 0, MAS0_TLBSEL(0)); - if (rc) - goto scom_fail; - - /* Linear mapping */ - for (p = a2_tlbinit_code_start; p < a2_tlbinit_after_linear_map; p++) { - rc = a2_scom_ram(scom, thread, *p, 0); - if (rc) - goto scom_fail; - } - - /* - * For the boot thread, between the linear mapping and the debug - * mappings there is a loop to flush iprot mappings. Ramming doesn't do - * branches, but the secondary threads don't need to be nearly as smart - * (i.e. we don't need to worry about invalidating the mapping we're - * standing on). - */ - - /* Debug mappings. Expects r11 = MAS0 from linear map (set above) */ - for (p = a2_tlbinit_after_iprot_flush; p < a2_tlbinit_code_end; p++) { - rc = a2_scom_ram(scom, thread, *p, 0); - if (rc) - goto scom_fail; - } - -scom_fail: - if (rc) - pr_err("Setting up initial TLB failed, err %d\n", rc); - - if (rc == -SCOM_RAMC_INTERRUPT) { - /* Interrupt, dump some status */ - int rc[10]; - u64 iar, srr0, srr1, esr, mas0, mas1, mas2, mas7_3, mas8, ccr2; - rc[0] = a2_scom_getspr(scom, thread, SPRN_IAR, &iar); - rc[1] = a2_scom_getspr(scom, thread, SPRN_SRR0, &srr0); - rc[2] = a2_scom_getspr(scom, thread, SPRN_SRR1, &srr1); - rc[3] = a2_scom_getspr(scom, thread, SPRN_ESR, &esr); - rc[4] = a2_scom_getspr(scom, thread, SPRN_MAS0, &mas0); - rc[5] = a2_scom_getspr(scom, thread, SPRN_MAS1, &mas1); - rc[6] = a2_scom_getspr(scom, thread, SPRN_MAS2, &mas2); - rc[7] = a2_scom_getspr(scom, thread, SPRN_MAS7_MAS3, &mas7_3); - rc[8] = a2_scom_getspr(scom, thread, SPRN_MAS8, &mas8); - rc[9] = a2_scom_getspr(scom, thread, SPRN_A2_CCR2, &ccr2); - pr_err(" -> retreived IAR =0x%llx (err %d)\n", iar, rc[0]); - pr_err(" retreived SRR0=0x%llx (err %d)\n", srr0, rc[1]); - pr_err(" retreived SRR1=0x%llx (err %d)\n", srr1, rc[2]); - pr_err(" retreived ESR =0x%llx (err %d)\n", esr, rc[3]); - pr_err(" retreived MAS0=0x%llx (err %d)\n", mas0, rc[4]); - pr_err(" retreived MAS1=0x%llx (err %d)\n", mas1, rc[5]); - pr_err(" retreived MAS2=0x%llx (err %d)\n", mas2, rc[6]); - pr_err(" retreived MS73=0x%llx (err %d)\n", mas7_3, rc[7]); - pr_err(" retreived MAS8=0x%llx (err %d)\n", mas8, rc[8]); - pr_err(" retreived CCR2=0x%llx (err %d)\n", ccr2, rc[9]); - } - - return rc; -} - -int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np) -{ - u64 init_iar, init_msr, init_ccr2; - unsigned long start_here; - int rc, core_setup; - scom_map_t scom; - u64 pccr0; - - scom = get_scom(lcpu, np, &core_setup); - if (!scom) { - printk(KERN_ERR "Couldn't map SCOM for CPU%d\n", lcpu); - return -1; - } - - pr_devel("Bringing up CPU%d using SCOM...\n", lcpu); - - if (scom_read(scom, SCOM_PCCR0, &pccr0) != 0) { - printk(KERN_ERR "XSCOM failure readng PCCR0 on CPU%d\n", lcpu); - return -1; - } - scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG | - SCOM_PCCR0_ENABLE_RAM); - - /* Stop the thead with THRCTL. If we are setting up the TLB we stop all - * threads. We also disable asynchronous interrupts while RAMing. - */ - if (core_setup) - scom_write(scom, SCOM_THRCTL_OR, - SCOM_THRCTL_T0_STOP | - SCOM_THRCTL_T1_STOP | - SCOM_THRCTL_T2_STOP | - SCOM_THRCTL_T3_STOP | - SCOM_THRCTL_ASYNC_DIS); - else - scom_write(scom, SCOM_THRCTL_OR, SCOM_THRCTL_T0_STOP >> thr_idx); - - /* Flush its pipeline just in case */ - scom_write(scom, SCOM_RAMC, ((u64)thr_idx << 17) | - SCOM_RAMC_FLUSH | SCOM_RAMC_ENABLE); - - a2_scom_getspr(scom, thr_idx, SPRN_IAR, &init_iar); - a2_scom_getspr(scom, thr_idx, 0x0ff0, &init_msr); - a2_scom_getspr(scom, thr_idx, SPRN_A2_CCR2, &init_ccr2); - - /* Set MSR to MSR_CM (0x0ff0 is magic value for MSR_CM) */ - rc = a2_scom_setspr(scom, thr_idx, 0x0ff0, MSR_CM); - if (rc) { - pr_err("Failed to set MSR ! err %d\n", rc); - return rc; - } - - /* RAM in an sync/isync for the sake of it */ - a2_scom_ram(scom, thr_idx, 0x7c0004ac, 0); - a2_scom_ram(scom, thr_idx, 0x4c00012c, 0); - - if (core_setup) { - pr_devel("CPU%d is first thread in core, initializing TLB...\n", - lcpu); - rc = a2_scom_initial_tlb(scom, thr_idx); - if (rc) - goto fail; - } - - start_here = ppc_function_entry(core_setup ? generic_secondary_smp_init - : generic_secondary_thread_init); - pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here); - - rc |= a2_scom_setspr(scom, thr_idx, SPRN_IAR, start_here); - rc |= a2_scom_setgpr(scom, thr_idx, 3, 0, - get_hard_smp_processor_id(lcpu)); - /* - * Tell book3e_secondary_core_init not to set up the TLB, we've - * already done that. - */ - rc |= a2_scom_setgpr(scom, thr_idx, 4, 0, 1); - - rc |= a2_scom_setspr(scom, thr_idx, SPRN_TENS, 0x1 << thr_idx); - - scom_write(scom, SCOM_RAMC, 0); - scom_write(scom, SCOM_THRCTL_AND, ~(SCOM_THRCTL_T0_STOP >> thr_idx)); - scom_write(scom, SCOM_PCCR0, pccr0); -fail: - pr_devel(" SCOM initialization %s\n", rc ? "failed" : "succeeded"); - if (rc) { - pr_err("Old IAR=0x%08llx MSR=0x%08llx CCR2=0x%08llx\n", - init_iar, init_msr, init_ccr2); - } - - return rc; -} diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c deleted file mode 100644 index 6538b4de34fc..000000000000 --- a/arch/powerpc/platforms/wsp/scom_wsp.c +++ /dev/null @@ -1,82 +0,0 @@ -/* - * SCOM backend for WSP - * - * Copyright 2010 Benjamin Herrenschmidt, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include "wsp.h" - - -static scom_map_t wsp_scom_map(struct device_node *dev, u64 reg, u64 count) -{ - struct resource r; - u64 xscom_addr; - - if (!of_get_property(dev, "scom-controller", NULL)) { - pr_err("%s: device %s is not a SCOM controller\n", - __func__, dev->full_name); - return SCOM_MAP_INVALID; - } - - if (of_address_to_resource(dev, 0, &r)) { - pr_debug("Failed to find SCOM controller address\n"); - return 0; - } - - /* Transform the SCOM address into an XSCOM offset */ - xscom_addr = ((reg & 0x7f000000) >> 1) | ((reg & 0xfffff) << 3); - - return (scom_map_t)ioremap(r.start + xscom_addr, count << 3); -} - -static void wsp_scom_unmap(scom_map_t map) -{ - iounmap((void *)map); -} - -static int wsp_scom_read(scom_map_t map, u64 reg, u64 *value) -{ - u64 __iomem *addr = (u64 __iomem *)map; - - *value = in_be64(addr + reg); - - return 0; -} - -static int wsp_scom_write(scom_map_t map, u64 reg, u64 value) -{ - u64 __iomem *addr = (u64 __iomem *)map; - - out_be64(addr + reg, value); - - return 0; -} - -static const struct scom_controller wsp_scom_controller = { - .map = wsp_scom_map, - .unmap = wsp_scom_unmap, - .read = wsp_scom_read, - .write = wsp_scom_write -}; - -void scom_init_wsp(void) -{ - scom_init(&wsp_scom_controller); -} diff --git a/arch/powerpc/platforms/wsp/setup.c b/arch/powerpc/platforms/wsp/setup.c deleted file mode 100644 index 11ac2f05e01c..000000000000 --- a/arch/powerpc/platforms/wsp/setup.c +++ /dev/null @@ -1,36 +0,0 @@ -/* - * Copyright 2010 Michael Ellerman, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include - -#include "wsp.h" - -/* - * Find chip-id by walking up device tree looking for ibm,wsp-chip-id property. - * Won't work for nodes that are not a descendant of a wsp node. - */ -int wsp_get_chip_id(struct device_node *dn) -{ - const u32 *p; - int rc; - - /* Start looking at the specified node, not its parent */ - dn = of_node_get(dn); - while (dn && !(p = of_get_property(dn, "ibm,wsp-chip-id", NULL))) - dn = of_get_next_parent(dn); - - if (!dn) - return -1; - - rc = *p; - of_node_put(dn); - - return rc; -} diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c deleted file mode 100644 index 332a18b81403..000000000000 --- a/arch/powerpc/platforms/wsp/smp.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * SMP Support for A2 platforms - * - * Copyright 2007 Benjamin Herrenschmidt, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include -#include -#include -#include - -#include -#include -#include - -#include "ics.h" -#include "wsp.h" - -static void smp_a2_setup_cpu(int cpu) -{ - doorbell_setup_this_cpu(); - - if (cpu != boot_cpuid) - xics_setup_cpu(); -} - -int smp_a2_kick_cpu(int nr) -{ - const char *enable_method; - struct device_node *np; - int thr_idx; - - if (nr < 0 || nr >= NR_CPUS) - return -ENOENT; - - np = of_get_cpu_node(nr, &thr_idx); - if (!np) - return -ENODEV; - - enable_method = of_get_property(np, "enable-method", NULL); - pr_devel("CPU%d has enable-method: \"%s\"\n", nr, enable_method); - - if (!enable_method) { - printk(KERN_ERR "CPU%d has no enable-method\n", nr); - return -ENOENT; - } else if (strcmp(enable_method, "ibm,a2-scom") == 0) { - if (a2_scom_startup_cpu(nr, thr_idx, np)) - return -1; - } else { - printk(KERN_ERR "CPU%d: Don't understand enable-method \"%s\"\n", - nr, enable_method); - return -EINVAL; - } - - /* - * The processor is currently spinning, waiting for the - * cpu_start field to become non-zero After we set cpu_start, - * the processor will continue on to secondary_start - */ - paca[nr].cpu_start = 1; - - return 0; -} - -static int __init smp_a2_probe(void) -{ - return num_possible_cpus(); -} - -static struct smp_ops_t a2_smp_ops = { - .message_pass = NULL, /* Use smp_muxed_ipi_message_pass */ - .cause_ipi = doorbell_cause_ipi, - .probe = smp_a2_probe, - .kick_cpu = smp_a2_kick_cpu, - .setup_cpu = smp_a2_setup_cpu, -}; - -void __init a2_setup_smp(void) -{ - smp_ops = &a2_smp_ops; -} diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c deleted file mode 100644 index 58cd1f00e1ef..000000000000 --- a/arch/powerpc/platforms/wsp/wsp.c +++ /dev/null @@ -1,117 +0,0 @@ -/* - * Copyright 2008-2011, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include - -#include - -#include "wsp.h" -#include "ics.h" - -#define WSP_SOC_COMPATIBLE "ibm,wsp-soc" -#define PBIC_COMPATIBLE "ibm,wsp-pbic" -#define COPRO_COMPATIBLE "ibm,wsp-coprocessor" - -static int __init wsp_probe_buses(void) -{ - static __initdata struct of_device_id bus_ids[] = { - /* - * every node in between needs to be here or you won't - * find it - */ - { .compatible = WSP_SOC_COMPATIBLE, }, - { .compatible = PBIC_COMPATIBLE, }, - { .compatible = COPRO_COMPATIBLE, }, - {}, - }; - of_platform_bus_probe(NULL, bus_ids, NULL); - - return 0; -} - -void __init wsp_setup_arch(void) -{ - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - - scom_init_wsp(); - - /* Setup SMP callback */ -#ifdef CONFIG_SMP - a2_setup_smp(); -#endif -#ifdef CONFIG_PCI - wsp_setup_pci(); -#endif -} - -void __init wsp_setup_irq(void) -{ - wsp_init_irq(); - opb_pic_init(); -} - - -int __init wsp_probe_devices(void) -{ - struct device_node *np; - - /* Our RTC is a ds1500. It seems to be programatically compatible - * with the ds1511 for which we have a driver so let's use that - */ - np = of_find_compatible_node(NULL, NULL, "dallas,ds1500"); - if (np != NULL) { - struct resource res; - if (of_address_to_resource(np, 0, &res) == 0) - platform_device_register_simple("ds1511", 0, &res, 1); - } - - wsp_probe_buses(); - - return 0; -} - -void wsp_halt(void) -{ - u64 val; - scom_map_t m; - struct device_node *dn; - struct device_node *mine; - struct device_node *me; - int rc; - - me = of_get_cpu_node(smp_processor_id(), NULL); - mine = scom_find_parent(me); - - /* This will halt all the A2s but not power off the chip */ - for_each_node_with_property(dn, "scom-controller") { - if (dn == mine) - continue; - m = scom_map(dn, 0, 1); - - /* read-modify-write it so the HW probe does not get - * confused */ - rc = scom_read(m, 0, &val); - if (rc == 0) - scom_write(m, 0, val | 1); - scom_unmap(m); - } - m = scom_map(mine, 0, 1); - rc = scom_read(m, 0, &val); - if (rc == 0) - scom_write(m, 0, val | 1); - /* should never return */ - scom_unmap(m); -} diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h deleted file mode 100644 index a563a8aaf812..000000000000 --- a/arch/powerpc/platforms/wsp/wsp.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __WSP_H -#define __WSP_H - -#include - -/* Devtree compatible strings for major devices */ -#define PCIE_COMPATIBLE "ibm,wsp-pciex" - -extern void wsp_setup_arch(void); -extern void wsp_setup_irq(void); -extern int wsp_probe_devices(void); -extern void wsp_halt(void); - -extern void wsp_setup_pci(void); -extern void scom_init_wsp(void); - -extern void a2_setup_smp(void); -extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, - struct device_node *np); -extern int smp_a2_kick_cpu(int nr); - -extern void opb_pic_init(void); - -/* chroma specific managment */ -extern void wsp_h8_restart(char *cmd); -extern void wsp_h8_power_off(void); -extern void __init wsp_setup_h8(void); - -#endif /* __WSP_H */ diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c deleted file mode 100644 index 9a15e5b39bb8..000000000000 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ /dev/null @@ -1,1134 +0,0 @@ -/* - * Copyright 2010 Ben Herrenschmidt, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#define DEBUG - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "wsp.h" -#include "wsp_pci.h" -#include "msi.h" - - -/* Max number of TVTs for one table. Only 32-bit tables can use - * multiple TVTs and so the max currently supported is thus 8 - * since only 2G of DMA space is supported - */ -#define MAX_TABLE_TVT_COUNT 8 - -struct wsp_dma_table { - struct list_head link; - struct iommu_table table; - struct wsp_phb *phb; - struct page *tces[MAX_TABLE_TVT_COUNT]; -}; - -/* We support DMA regions from 0...2G in 32bit space (no support for - * 64-bit DMA just yet). Each device gets a separate TCE table (TVT - * entry) with validation enabled (though not supported by SimiCS - * just yet). - * - * To simplify things, we divide this 2G space into N regions based - * on the constant below which could be turned into a tunable eventually - * - * We then assign dynamically those regions to devices as they show up. - * - * We use a bitmap as an allocator for these. - * - * Tables are allocated/created dynamically as devices are discovered, - * multiple TVT entries are used if needed - * - * When 64-bit DMA support is added we should simply use a separate set - * of larger regions (the HW supports 64 TVT entries). We can - * additionally create a bypass region in 64-bit space for performances - * though that would have a cost in term of security. - * - * If you set NUM_DMA32_REGIONS to 1, then a single table is shared - * for all devices and bus/dev/fn validation is disabled - * - * Note that a DMA32 region cannot be smaller than 256M so the max - * supported here for now is 8. We don't yet support sharing regions - * between multiple devices so the max number of devices supported - * is MAX_TABLE_TVT_COUNT. - */ -#define NUM_DMA32_REGIONS 1 - -struct wsp_phb { - struct pci_controller *hose; - - /* Lock controlling access to the list of dma tables. - * It does -not- protect against dma_* operations on - * those tables, those should be stopped before an entry - * is removed from the list. - * - * The lock is also used for error handling operations - */ - spinlock_t lock; - struct list_head dma_tables; - unsigned long dma32_map; - unsigned long dma32_base; - unsigned int dma32_num_regions; - unsigned long dma32_region_size; - - /* Debugfs stuff */ - struct dentry *ddir; - - struct list_head all; -}; -static LIST_HEAD(wsp_phbs); - -//#define cfg_debug(fmt...) pr_debug(fmt) -#define cfg_debug(fmt...) - - -static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - struct pci_controller *hose; - int suboff; - u64 addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = PCIE_REG_CA_ENABLE | - ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT | - ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT | - ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT; - suboff = offset & 3; - - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - - switch (len) { - case 1: - addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA) - >> (suboff << 3)) & 0xff; - cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - case 2: - addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA) - >> (suboff << 3)) & 0xffff; - cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - default: - addr |= 0xful << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA); - cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 val) -{ - struct pci_controller *hose; - int suboff; - u64 addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = PCIE_REG_CA_ENABLE | - ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT | - ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT | - ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT; - suboff = offset & 3; - - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT; - val <<= suboff << 3; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - case 2: - addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT; - val <<= suboff << 3; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - default: - addr |= 0xful << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops wsp_pcie_pci_ops = -{ - .read = wsp_pcie_read_config, - .write = wsp_pcie_write_config, -}; - -#define TCE_SHIFT 12 -#define TCE_PAGE_SIZE (1 << TCE_SHIFT) -#define TCE_PCI_WRITE 0x2 /* write from PCI allowed */ -#define TCE_PCI_READ 0x1 /* read from PCI allowed */ -#define TCE_RPN_MASK 0x3fffffffffful /* 42-bit RPN (4K pages) */ -#define TCE_RPN_SHIFT 12 - -//#define dma_debug(fmt...) pr_debug(fmt) -#define dma_debug(fmt...) - -static int tce_build_wsp(struct iommu_table *tbl, long index, long npages, - unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - struct wsp_dma_table *ptbl = container_of(tbl, - struct wsp_dma_table, - table); - u64 proto_tce; - u64 *tcep; - u64 rpn; - - proto_tce = TCE_PCI_READ; -#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - proto_tce |= TCE_PCI_WRITE; -#else - if (direction != DMA_TO_DEVICE) - proto_tce |= TCE_PCI_WRITE; -#endif - - /* XXX Make this faster by factoring out the page address for - * within a TCE table - */ - while (npages--) { - /* We don't use it->base as the table can be scattered */ - tcep = (u64 *)page_address(ptbl->tces[index >> 16]); - tcep += (index & 0xffff); - - /* can't move this out since we might cross LMB boundary */ - rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; - - dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n", - tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT_4K); - - uaddr += TCE_PAGE_SIZE; - index++; - } - return 0; -} - -static void tce_free_wsp(struct iommu_table *tbl, long index, long npages) -{ - struct wsp_dma_table *ptbl = container_of(tbl, - struct wsp_dma_table, - table); -#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - struct pci_controller *hose = ptbl->phb->hose; -#endif - u64 *tcep; - - /* XXX Make this faster by factoring out the page address for - * within a TCE table. Also use line-kill option to kill multiple - * TCEs at once - */ - while (npages--) { - /* We don't use it->base as the table can be scattered */ - tcep = (u64 *)page_address(ptbl->tces[index >> 16]); - tcep += (index & 0xffff); - dma_debug("[DMA] TCE %p cleared\n", tcep); - *tcep = 0; -#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - /* Don't write there since it would pollute other MMIO accesses */ - out_be64(hose->cfg_data + PCIE_REG_TCE_KILL, - PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K | - (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK)); -#endif - index++; - } -} - -static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb, - unsigned int region, - struct pci_dev *validate) -{ - struct pci_controller *hose = phb->hose; - unsigned long size = phb->dma32_region_size; - unsigned long addr = phb->dma32_region_size * region + phb->dma32_base; - struct wsp_dma_table *tbl; - int tvts_per_table, i, tvt, nid; - unsigned long flags; - - nid = of_node_to_nid(phb->hose->dn); - - /* Calculate how many TVTs are needed */ - tvts_per_table = size / 0x10000000; - if (tvts_per_table == 0) - tvts_per_table = 1; - - /* Calculate the base TVT index. We know all tables have the same - * size so we just do a simple multiply here - */ - tvt = region * tvts_per_table; - - pr_debug(" Region : %d\n", region); - pr_debug(" DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1); - pr_debug(" Number of TVTs : %d\n", tvts_per_table); - pr_debug(" Base TVT : %d\n", tvt); - pr_debug(" Node : %d\n", nid); - - tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid); - if (!tbl) - return ERR_PTR(-ENOMEM); - tbl->phb = phb; - - /* Create as many TVTs as needed, each represents 256M at most */ - for (i = 0; i < tvts_per_table; i++) { - u64 tvt_data1, tvt_data0; - - /* Allocate table. We use a 4K TCE size for now always so - * one table is always 8 * (258M / 4K) == 512K - */ - tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000)); - if (tbl->tces[i] == NULL) - goto fail; - memset(page_address(tbl->tces[i]), 0, 0x80000); - - pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i])); - - /* Table size. We currently set it to be the whole 256M region */ - tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT; - /* IO page size set to 4K */ - tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT; - /* Shift in the address */ - tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT; - - /* Validation stuff. We only validate fully bus/dev/fn for now - * one day maybe we can group devices but that isn't the case - * at the moment - */ - if (validate) { - tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK; - tvt_data0 |= validate->bus->number; - tvt_data1 |= IODA_TVT1_DEVNUM_VALID; - tvt_data1 |= ((u64)PCI_SLOT(validate->devfn)) - << IODA_TVT1_DEVNUM_VALUE_SHIFT; - tvt_data1 |= IODA_TVT1_FUNCNUM_VALID; - tvt_data1 |= ((u64)PCI_FUNC(validate->devfn)) - << IODA_TVT1_FUNCNUM_VALUE_SHIFT; - } - - /* XX PE number is always 0 for now */ - - /* Program the values using the PHB lock */ - spin_lock_irqsave(&phb->lock, flags); - out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR, - (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0); - spin_unlock_irqrestore(&phb->lock, flags); - } - - /* Init bits and pieces */ - tbl->table.it_blocksize = 16; - tbl->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; - tbl->table.it_offset = addr >> tbl->table.it_page_shift; - tbl->table.it_size = size >> tbl->table.it_page_shift; - - /* - * It's already blank but we clear it anyway. - * Consider an aditiona interface that makes cleaing optional - */ - iommu_init_table(&tbl->table, nid); - - list_add(&tbl->link, &phb->dma_tables); - return tbl; - - fail: - pr_debug(" Failed to allocate a 256M TCE table !\n"); - for (i = 0; i < tvts_per_table; i++) - if (tbl->tces[i]) - __free_pages(tbl->tces[i], get_order(0x80000)); - kfree(tbl); - return ERR_PTR(-ENOMEM); -} - -static void wsp_pci_dma_dev_setup(struct pci_dev *pdev) -{ - struct dev_archdata *archdata = &pdev->dev.archdata; - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct wsp_phb *phb = hose->private_data; - struct wsp_dma_table *table = NULL; - unsigned long flags; - int i; - - /* Don't assign an iommu table to a bridge */ - if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) - return; - - pr_debug("%s: Setting up DMA...\n", pci_name(pdev)); - - spin_lock_irqsave(&phb->lock, flags); - - /* If only one region, check if it already exist */ - if (phb->dma32_num_regions == 1) { - spin_unlock_irqrestore(&phb->lock, flags); - if (list_empty(&phb->dma_tables)) - table = wsp_pci_create_dma32_table(phb, 0, NULL); - else - table = list_first_entry(&phb->dma_tables, - struct wsp_dma_table, - link); - } else { - /* else find a free region */ - for (i = 0; i < phb->dma32_num_regions && !table; i++) { - if (__test_and_set_bit(i, &phb->dma32_map)) - continue; - spin_unlock_irqrestore(&phb->lock, flags); - table = wsp_pci_create_dma32_table(phb, i, pdev); - } - } - - /* Check if we got an error */ - if (IS_ERR(table)) { - pr_err("%s: Failed to create DMA table, err %ld !\n", - pci_name(pdev), PTR_ERR(table)); - return; - } - - /* Or a valid table */ - if (table) { - pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n", - pci_name(pdev), - table->table.it_offset << IOMMU_PAGE_SHIFT_4K, - (table->table.it_offset << IOMMU_PAGE_SHIFT_4K) - + phb->dma32_region_size - 1); - archdata->dma_data.iommu_table_base = &table->table; - return; - } - - /* Or no room */ - spin_unlock_irqrestore(&phb->lock, flags); - pr_err("%s: Out of DMA space !\n", pci_name(pdev)); -} - -static void __init wsp_pcie_configure_hw(struct pci_controller *hose) -{ - u64 val; - int i; - -#define DUMP_REG(x) \ - pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x)) - - /* - * Some WSP variants has a bogus class code by default in the PCI-E - * root complex's built-in P2P bridge - */ - val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1); - pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val); - out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1, - (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8)); - pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1)); - -#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - /* XXX Disable TCE caching, it doesn't work on DD1 */ - out_be64(hose->cfg_data + 0xe50, - in_be64(hose->cfg_data + 0xe50) | (3ull << 62)); - printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50)); -#endif - - /* Configure M32A and IO. IO is hard wired to be 1M for now */ - out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys); - out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK, - (~(hose->io_resource.end - hose->io_resource.start)) & - 0x3fffffff000ul); - out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1); - - out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR, - hose->mem_resources[0].start); - printk("Want to write to M32A_BASE_MASK : 0x%llx\n", - (~(hose->mem_resources[0].end - - hose->mem_resources[0].start)) & 0x3ffffff0000ul); - out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK, - (~(hose->mem_resources[0].end - - hose->mem_resources[0].start)) & 0x3ffffff0000ul); - out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR, - (hose->mem_resources[0].start - hose->mem_offset[0]) | 1); - - /* Clear all TVT entries - * - * XX Might get TVT count from device-tree - */ - for (i = 0; i < IODA_TVT_COUNT; i++) { - out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR, - PCIE_REG_IODA_AD_TBL_TVT | i); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0); - } - - /* Kill the TCE cache */ - out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, - in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) | - PCIE_REG_PHBC_64B_TCE_EN); - - /* Enable 32 & 64-bit MSIs, IO space and M32A */ - val = PCIE_REG_PHBC_32BIT_MSI_EN | - PCIE_REG_PHBC_IO_EN | - PCIE_REG_PHBC_64BIT_MSI_EN | - PCIE_REG_PHBC_M32A_EN; - if (iommu_is_off) - val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS; - pr_debug("Will write config: 0x%llx\n", val); - out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val); - - /* Enable error reporting */ - out_be64(hose->cfg_data + 0xe00, - in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull); - - /* Mask an error that's generated when doing config space probe - * - * XXX Maybe we should only mask it around config space cycles... that or - * ignore it when we know we had a config space cycle recently ? - */ - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull); - - /* Enable UTL errors, for now, all of them got to UTL irq 1 - * - * We similarily mask one UTL error caused apparently during normal - * probing. We also mask the link up error - */ - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0); - out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0); - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0); - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull); - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull); - out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull); - - DUMP_REG(PCIE_REG_IO_BASE_ADDR); - DUMP_REG(PCIE_REG_IO_BASE_MASK); - DUMP_REG(PCIE_REG_IO_START_ADDR); - DUMP_REG(PCIE_REG_M32A_BASE_ADDR); - DUMP_REG(PCIE_REG_M32A_BASE_MASK); - DUMP_REG(PCIE_REG_M32A_START_ADDR); - DUMP_REG(PCIE_REG_M32B_BASE_ADDR); - DUMP_REG(PCIE_REG_M32B_BASE_MASK); - DUMP_REG(PCIE_REG_M32B_START_ADDR); - DUMP_REG(PCIE_REG_M64_BASE_ADDR); - DUMP_REG(PCIE_REG_M64_BASE_MASK); - DUMP_REG(PCIE_REG_M64_START_ADDR); - DUMP_REG(PCIE_REG_PHB_CONFIG); -} - -static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port) -{ - u64 val; - int i; - - for (i = 0; i < 10000; i++) { - val = in_be64(phb->hose->cfg_data + 0xe08); - if ((val & 0x1900000000000000ull) == 0x0100000000000000ull) - return; - udelay(1); - } - pr_warning("PCI IO timeout on domain %d port 0x%lx\n", - phb->hose->global_number, port); -} - -#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa) \ -static ret wsp_pci_##name at \ -{ \ - struct iowa_bus *bus; \ - struct wsp_phb *phb; \ - unsigned long flags; \ - ret rval; \ - bus = iowa_pio_find_bus(aa); \ - WARN_ON(!bus); \ - phb = bus->private; \ - spin_lock_irqsave(&phb->lock, flags); \ - wsp_pci_wait_io_idle(phb, aa); \ - rval = __do_##name al; \ - spin_unlock_irqrestore(&phb->lock, flags); \ - return rval; \ -} - -#define DEF_PCI_AC_NORET_pio(name, at, al, aa) \ -static void wsp_pci_##name at \ -{ \ - struct iowa_bus *bus; \ - struct wsp_phb *phb; \ - unsigned long flags; \ - bus = iowa_pio_find_bus(aa); \ - WARN_ON(!bus); \ - phb = bus->private; \ - spin_lock_irqsave(&phb->lock, flags); \ - wsp_pci_wait_io_idle(phb, aa); \ - __do_##name al; \ - spin_unlock_irqrestore(&phb->lock, flags); \ -} - -#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa) -#define DEF_PCI_AC_NORET_mem(name, at, al, aa) - -#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \ - DEF_PCI_AC_RET_##space(name, ret, at, al, aa) - -#define DEF_PCI_AC_NORET(name, at, al, space, aa) \ - DEF_PCI_AC_NORET_##space(name, at, al, aa) \ - - -#include - -#undef DEF_PCI_AC_RET -#undef DEF_PCI_AC_NORET - -static struct ppc_pci_io wsp_pci_iops = { - .inb = wsp_pci_inb, - .inw = wsp_pci_inw, - .inl = wsp_pci_inl, - .outb = wsp_pci_outb, - .outw = wsp_pci_outw, - .outl = wsp_pci_outl, - .insb = wsp_pci_insb, - .insw = wsp_pci_insw, - .insl = wsp_pci_insl, - .outsb = wsp_pci_outsb, - .outsw = wsp_pci_outsw, - .outsl = wsp_pci_outsl, -}; - -static int __init wsp_setup_one_phb(struct device_node *np) -{ - struct pci_controller *hose; - struct wsp_phb *phb; - - pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name); - - phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL); - if (!phb) - return -ENOMEM; - hose = pcibios_alloc_controller(np); - if (!hose) { - /* Can't really free the phb */ - return -ENOMEM; - } - hose->private_data = phb; - phb->hose = hose; - - INIT_LIST_HEAD(&phb->dma_tables); - spin_lock_init(&phb->lock); - - /* XXX Use bus-range property ? */ - hose->first_busno = 0; - hose->last_busno = 0xff; - - /* We use cfg_data as the address for the whole bridge MMIO space - */ - hose->cfg_data = of_iomap(hose->dn, 0); - - pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data); - - /* Get the ranges of the device-tree */ - pci_process_bridge_OF_ranges(hose, np, 0); - - /* XXX Force re-assigning of everything for now */ - pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC | - PCI_ENABLE_PROC_DOMAINS); - - /* Calculate how the TCE space is divided */ - phb->dma32_base = 0; - phb->dma32_num_regions = NUM_DMA32_REGIONS; - if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) { - pr_warning("IOMMU: Clamped to %d DMA32 regions\n", - MAX_TABLE_TVT_COUNT); - phb->dma32_num_regions = MAX_TABLE_TVT_COUNT; - } - phb->dma32_region_size = 0x80000000 / phb->dma32_num_regions; - - BUG_ON(!is_power_of_2(phb->dma32_region_size)); - - /* Setup config ops */ - hose->ops = &wsp_pcie_pci_ops; - - /* Configure the HW */ - wsp_pcie_configure_hw(hose); - - /* Instanciate IO workarounds */ - iowa_register_bus(hose, &wsp_pci_iops, NULL, phb); -#ifdef CONFIG_PCI_MSI - wsp_setup_phb_msi(hose); -#endif - - /* Add to global list */ - list_add(&phb->all, &wsp_phbs); - - return 0; -} - -void __init wsp_setup_pci(void) -{ - struct device_node *np; - int rc; - - /* Find host bridges */ - for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) { - rc = wsp_setup_one_phb(np); - if (rc) - pr_err("Failed to setup PCIe bridge %s, rc=%d\n", - np->full_name, rc); - } - - /* Establish device-tree linkage */ - pci_devs_phb_init(); - - /* Set DMA ops to use TCEs */ - if (iommu_is_off) { - pr_info("PCI-E: Disabled TCEs, using direct DMA\n"); - set_pci_dma_ops(&dma_direct_ops); - } else { - ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup; - ppc_md.tce_build = tce_build_wsp; - ppc_md.tce_free = tce_free_wsp; - set_pci_dma_ops(&dma_iommu_ops); - } -} - -#define err_debug(fmt...) pr_debug(fmt) -//#define err_debug(fmt...) - -static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np) -{ - const u32 *prop; - int hw_irq; - - /* Ok, no interrupts property, let's try to find our child P2P */ - np = of_get_next_child(np, NULL); - if (np == NULL) - return 0; - - /* Grab it's interrupt map */ - prop = of_get_property(np, "interrupt-map", NULL); - if (prop == NULL) - return 0; - - /* Grab one of the interrupts in there, keep the low 4 bits */ - hw_irq = prop[5] & 0xf; - - /* 0..4 for PHB 0 and 5..9 for PHB 1 */ - if (hw_irq < 5) - hw_irq = 4; - else - hw_irq = 9; - hw_irq |= prop[5] & ~0xf; - - err_debug("PCI: Using 0x%x as error IRQ for %s\n", - hw_irq, np->parent->full_name); - return irq_create_mapping(NULL, hw_irq); -} - -static const struct { - u32 offset; - const char *name; -} wsp_pci_regs[] = { -#define DREG(x) { PCIE_REG_##x, #x } -#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x } - /* Architected registers except CONFIG_ and IODA - * to avoid side effects - */ - DREG(DMA_CHAN_STATUS), - DREG(CPU_LOADSTORE_STATUS), - DREG(LOCK0), - DREG(LOCK1), - DREG(PHB_CONFIG), - DREG(IO_BASE_ADDR), - DREG(IO_BASE_MASK), - DREG(IO_START_ADDR), - DREG(M32A_BASE_ADDR), - DREG(M32A_BASE_MASK), - DREG(M32A_START_ADDR), - DREG(M32B_BASE_ADDR), - DREG(M32B_BASE_MASK), - DREG(M32B_START_ADDR), - DREG(M64_BASE_ADDR), - DREG(M64_BASE_MASK), - DREG(M64_START_ADDR), - DREG(TCE_KILL), - DREG(LOCK2), - DREG(PHB_GEN_CAP), - DREG(PHB_TCE_CAP), - DREG(PHB_IRQ_CAP), - DREG(PHB_EEH_CAP), - DREG(PAPR_ERR_INJ_CONTROL), - DREG(PAPR_ERR_INJ_ADDR), - DREG(PAPR_ERR_INJ_MASK), - - /* UTL core regs */ - DUTL(SYS_BUS_CONTROL), - DUTL(STATUS), - DUTL(SYS_BUS_AGENT_STATUS), - DUTL(SYS_BUS_AGENT_ERR_SEV), - DUTL(SYS_BUS_AGENT_IRQ_EN), - DUTL(SYS_BUS_BURST_SZ_CONF), - DUTL(REVISION_ID), - DUTL(OUT_POST_HDR_BUF_ALLOC), - DUTL(OUT_POST_DAT_BUF_ALLOC), - DUTL(IN_POST_HDR_BUF_ALLOC), - DUTL(IN_POST_DAT_BUF_ALLOC), - DUTL(OUT_NP_BUF_ALLOC), - DUTL(IN_NP_BUF_ALLOC), - DUTL(PCIE_TAGS_ALLOC), - DUTL(GBIF_READ_TAGS_ALLOC), - - DUTL(PCIE_PORT_CONTROL), - DUTL(PCIE_PORT_STATUS), - DUTL(PCIE_PORT_ERROR_SEV), - DUTL(PCIE_PORT_IRQ_EN), - DUTL(RC_STATUS), - DUTL(RC_ERR_SEVERITY), - DUTL(RC_IRQ_EN), - DUTL(EP_STATUS), - DUTL(EP_ERR_SEVERITY), - DUTL(EP_ERR_IRQ_EN), - DUTL(PCI_PM_CTRL1), - DUTL(PCI_PM_CTRL2), - - /* PCIe stack regs */ - DREG(SYSTEM_CONFIG1), - DREG(SYSTEM_CONFIG2), - DREG(EP_SYSTEM_CONFIG), - DREG(EP_FLR), - DREG(EP_BAR_CONFIG), - DREG(LINK_CONFIG), - DREG(PM_CONFIG), - DREG(DLP_CONTROL), - DREG(DLP_STATUS), - DREG(ERR_REPORT_CONTROL), - DREG(SLOT_CONTROL1), - DREG(SLOT_CONTROL2), - DREG(UTL_CONFIG), - DREG(BUFFERS_CONFIG), - DREG(ERROR_INJECT), - DREG(SRIOV_CONFIG), - DREG(PF0_SRIOV_STATUS), - DREG(PF1_SRIOV_STATUS), - DREG(PORT_NUMBER), - DREG(POR_SYSTEM_CONFIG), - - /* Internal logic regs */ - DREG(PHB_VERSION), - DREG(RESET), - DREG(PHB_CONTROL), - DREG(PHB_TIMEOUT_CONTROL1), - DREG(PHB_QUIESCE_DMA), - DREG(PHB_DMA_READ_TAG_ACTV), - DREG(PHB_TCE_READ_TAG_ACTV), - - /* FIR registers */ - DREG(LEM_FIR_ACCUM), - DREG(LEM_FIR_AND_MASK), - DREG(LEM_FIR_OR_MASK), - DREG(LEM_ACTION0), - DREG(LEM_ACTION1), - DREG(LEM_ERROR_MASK), - DREG(LEM_ERROR_AND_MASK), - DREG(LEM_ERROR_OR_MASK), - - /* Error traps registers */ - DREG(PHB_ERR_STATUS), - DREG(PHB_ERR_STATUS), - DREG(PHB_ERR1_STATUS), - DREG(PHB_ERR_INJECT), - DREG(PHB_ERR_LEM_ENABLE), - DREG(PHB_ERR_IRQ_ENABLE), - DREG(PHB_ERR_FREEZE_ENABLE), - DREG(PHB_ERR_SIDE_ENABLE), - DREG(PHB_ERR_LOG_0), - DREG(PHB_ERR_LOG_1), - DREG(PHB_ERR_STATUS_MASK), - DREG(PHB_ERR1_STATUS_MASK), - DREG(MMIO_ERR_STATUS), - DREG(MMIO_ERR1_STATUS), - DREG(MMIO_ERR_INJECT), - DREG(MMIO_ERR_LEM_ENABLE), - DREG(MMIO_ERR_IRQ_ENABLE), - DREG(MMIO_ERR_FREEZE_ENABLE), - DREG(MMIO_ERR_SIDE_ENABLE), - DREG(MMIO_ERR_LOG_0), - DREG(MMIO_ERR_LOG_1), - DREG(MMIO_ERR_STATUS_MASK), - DREG(MMIO_ERR1_STATUS_MASK), - DREG(DMA_ERR_STATUS), - DREG(DMA_ERR1_STATUS), - DREG(DMA_ERR_INJECT), - DREG(DMA_ERR_LEM_ENABLE), - DREG(DMA_ERR_IRQ_ENABLE), - DREG(DMA_ERR_FREEZE_ENABLE), - DREG(DMA_ERR_SIDE_ENABLE), - DREG(DMA_ERR_LOG_0), - DREG(DMA_ERR_LOG_1), - DREG(DMA_ERR_STATUS_MASK), - DREG(DMA_ERR1_STATUS_MASK), - - /* Debug and Trace registers */ - DREG(PHB_DEBUG_CONTROL0), - DREG(PHB_DEBUG_STATUS0), - DREG(PHB_DEBUG_CONTROL1), - DREG(PHB_DEBUG_STATUS1), - DREG(PHB_DEBUG_CONTROL2), - DREG(PHB_DEBUG_STATUS2), - DREG(PHB_DEBUG_CONTROL3), - DREG(PHB_DEBUG_STATUS3), - DREG(PHB_DEBUG_CONTROL4), - DREG(PHB_DEBUG_STATUS4), - DREG(PHB_DEBUG_CONTROL5), - DREG(PHB_DEBUG_STATUS5), - - /* Don't seem to exist ... - DREG(PHB_DEBUG_CONTROL6), - DREG(PHB_DEBUG_STATUS6), - */ -}; - -static int wsp_pci_regs_show(struct seq_file *m, void *private) -{ - struct wsp_phb *phb = m->private; - struct pci_controller *hose = phb->hose; - int i; - - for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) { - /* Skip write-only regs */ - if (wsp_pci_regs[i].offset == 0xc08 || - wsp_pci_regs[i].offset == 0xc10 || - wsp_pci_regs[i].offset == 0xc38 || - wsp_pci_regs[i].offset == 0xc40) - continue; - seq_printf(m, "0x%03x: 0x%016llx %s\n", - wsp_pci_regs[i].offset, - in_be64(hose->cfg_data + wsp_pci_regs[i].offset), - wsp_pci_regs[i].name); - } - return 0; -} - -static int wsp_pci_regs_open(struct inode *inode, struct file *file) -{ - return single_open(file, wsp_pci_regs_show, inode->i_private); -} - -static const struct file_operations wsp_pci_regs_fops = { - .open = wsp_pci_regs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int wsp_pci_reg_set(void *data, u64 val) -{ - out_be64((void __iomem *)data, val); - return 0; -} - -static int wsp_pci_reg_get(void *data, u64 *val) -{ - *val = in_be64((void __iomem *)data); - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n"); - -static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id) -{ - struct wsp_phb *phb = dev_id; - struct pci_controller *hose = phb->hose; - irqreturn_t handled = IRQ_NONE; - struct wsp_pcie_err_log_data ed; - - pr_err("PCI: Error interrupt on %s (PHB %d)\n", - hose->dn->full_name, hose->global_number); - again: - memset(&ed, 0, sizeof(ed)); - - /* Read and clear UTL errors */ - ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS); - if (ed.utl_sys_err) - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err); - ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS); - if (ed.utl_port_err) - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err); - ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS); - if (ed.utl_rc_err) - out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err); - - /* Read and clear main trap errors */ - ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS); - if (ed.phb_err) { - ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS); - ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0); - ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0); - } - ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS); - if (ed.mmio_err) { - ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS); - ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0); - ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0); - } - ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS); - if (ed.dma_err) { - ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS); - ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0); - ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0); - } - - /* Now print things out */ - if (ed.phb_err) { - pr_err(" PHB Error Status : 0x%016llx\n", ed.phb_err); - pr_err(" PHB First Error Status: 0x%016llx\n", ed.phb_err1); - pr_err(" PHB Error Log 0 : 0x%016llx\n", ed.phb_log0); - pr_err(" PHB Error Log 1 : 0x%016llx\n", ed.phb_log1); - } - if (ed.mmio_err) { - pr_err(" MMIO Error Status : 0x%016llx\n", ed.mmio_err); - pr_err(" MMIO First Error Status: 0x%016llx\n", ed.mmio_err1); - pr_err(" MMIO Error Log 0 : 0x%016llx\n", ed.mmio_log0); - pr_err(" MMIO Error Log 1 : 0x%016llx\n", ed.mmio_log1); - } - if (ed.dma_err) { - pr_err(" DMA Error Status : 0x%016llx\n", ed.dma_err); - pr_err(" DMA First Error Status: 0x%016llx\n", ed.dma_err1); - pr_err(" DMA Error Log 0 : 0x%016llx\n", ed.dma_log0); - pr_err(" DMA Error Log 1 : 0x%016llx\n", ed.dma_log1); - } - if (ed.utl_sys_err) - pr_err(" UTL Sys Error Status : 0x%016llx\n", ed.utl_sys_err); - if (ed.utl_port_err) - pr_err(" UTL Port Error Status : 0x%016llx\n", ed.utl_port_err); - if (ed.utl_rc_err) - pr_err(" UTL RC Error Status : 0x%016llx\n", ed.utl_rc_err); - - /* Interrupts are caused by the error traps. If we had any error there - * we loop again in case the UTL buffered some new stuff between - * going there and going to the traps - */ - if (ed.dma_err || ed.mmio_err || ed.phb_err) { - handled = IRQ_HANDLED; - goto again; - } - return handled; -} - -static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb) -{ - struct pci_controller *hose = phb->hose; - int err_irq, i, rc; - char fname[16]; - - /* Create a debugfs file for that PHB */ - sprintf(fname, "phb%d", phb->hose->global_number); - phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root); - - /* Some useful debug output */ - if (phb->ddir) { - struct dentry *d = debugfs_create_dir("regs", phb->ddir); - char tmp[64]; - - for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) { - sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset, - wsp_pci_regs[i].name); - debugfs_create_file(tmp, 0600, d, - hose->cfg_data + wsp_pci_regs[i].offset, - &wsp_pci_reg_fops); - } - debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops); - } - - /* Find the IRQ number for that PHB */ - err_irq = irq_of_parse_and_map(hose->dn, 0); - if (err_irq == 0) - /* XXX Error IRQ lacking from device-tree */ - err_irq = wsp_pci_get_err_irq_no_dt(hose->dn); - if (err_irq == 0) { - pr_err("PCI: Failed to fetch error interrupt for %s\n", - hose->dn->full_name); - return; - } - /* Request it */ - rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb); - if (rc) { - pr_err("PCI: Failed to request interrupt for %s\n", - hose->dn->full_name); - } - /* Enable interrupts for all errors for now */ - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull); -} - -/* - * This is called later to hookup with the error interrupt - */ -static int __init wsp_setup_pci_late(void) -{ - struct wsp_phb *phb; - - list_for_each_entry(phb, &wsp_phbs, all) - wsp_setup_pci_err_reporting(phb); - - return 0; -} -arch_initcall(wsp_setup_pci_late); diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h deleted file mode 100644 index 52e9bd95250d..000000000000 --- a/arch/powerpc/platforms/wsp/wsp_pci.h +++ /dev/null @@ -1,268 +0,0 @@ -/* - * Copyright 2010 Ben Herrenschmidt, IBM Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef __WSP_PCI_H -#define __WSP_PCI_H - -/* Architected registers */ -#define PCIE_REG_DMA_CHAN_STATUS 0x110 -#define PCIE_REG_CPU_LOADSTORE_STATUS 0x120 - -#define PCIE_REG_CONFIG_DATA 0x130 -#define PCIE_REG_LOCK0 0x138 -#define PCIE_REG_CONFIG_ADDRESS 0x140 -#define PCIE_REG_CA_ENABLE 0x8000000000000000ull -#define PCIE_REG_CA_BUS_MASK 0x0ff0000000000000ull -#define PCIE_REG_CA_BUS_SHIFT (20+32) -#define PCIE_REG_CA_DEV_MASK 0x000f800000000000ull -#define PCIE_REG_CA_DEV_SHIFT (15+32) -#define PCIE_REG_CA_FUNC_MASK 0x0000700000000000ull -#define PCIE_REG_CA_FUNC_SHIFT (12+32) -#define PCIE_REG_CA_REG_MASK 0x00000fff00000000ull -#define PCIE_REG_CA_REG_SHIFT ( 0+32) -#define PCIE_REG_CA_BE_MASK 0x00000000f0000000ull -#define PCIE_REG_CA_BE_SHIFT ( 28) -#define PCIE_REG_LOCK1 0x148 - -#define PCIE_REG_PHB_CONFIG 0x160 -#define PCIE_REG_PHBC_64B_TCE_EN 0x2000000000000000ull -#define PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN 0x1000000000000000ull -#define PCIE_REG_PHBC_32BIT_MSI_EN 0x0080000000000000ull -#define PCIE_REG_PHBC_M64_EN 0x0040000000000000ull -#define PCIE_REG_PHBC_IO_EN 0x0008000000000000ull -#define PCIE_REG_PHBC_64BIT_MSI_EN 0x0002000000000000ull -#define PCIE_REG_PHBC_M32A_EN 0x0000800000000000ull -#define PCIE_REG_PHBC_M32B_EN 0x0000400000000000ull -#define PCIE_REG_PHBC_MSI_PE_VALIDATE 0x0000200000000000ull -#define PCIE_REG_PHBC_DMA_XLATE_BYPASS 0x0000100000000000ull - -#define PCIE_REG_IO_BASE_ADDR 0x170 -#define PCIE_REG_IO_BASE_MASK 0x178 -#define PCIE_REG_IO_START_ADDR 0x180 - -#define PCIE_REG_M32A_BASE_ADDR 0x190 -#define PCIE_REG_M32A_BASE_MASK 0x198 -#define PCIE_REG_M32A_START_ADDR 0x1a0 - -#define PCIE_REG_M32B_BASE_ADDR 0x1b0 -#define PCIE_REG_M32B_BASE_MASK 0x1b8 -#define PCIE_REG_M32B_START_ADDR 0x1c0 - -#define PCIE_REG_M64_BASE_ADDR 0x1e0 -#define PCIE_REG_M64_BASE_MASK 0x1e8 -#define PCIE_REG_M64_START_ADDR 0x1f0 - -#define PCIE_REG_TCE_KILL 0x210 -#define PCIE_REG_TCEKILL_SINGLE 0x8000000000000000ull -#define PCIE_REG_TCEKILL_ADDR_MASK 0x000003fffffffff8ull -#define PCIE_REG_TCEKILL_PS_4K 0 -#define PCIE_REG_TCEKILL_PS_64K 1 -#define PCIE_REG_TCEKILL_PS_16M 2 -#define PCIE_REG_TCEKILL_PS_16G 3 - -#define PCIE_REG_IODA_ADDR 0x220 -#define PCIE_REG_IODA_AD_AUTOINC 0x8000000000000000ull -#define PCIE_REG_IODA_AD_TBL_MVT 0x0005000000000000ull -#define PCIE_REG_IODA_AD_TBL_PELT 0x0006000000000000ull -#define PCIE_REG_IODA_AD_TBL_PESTA 0x0007000000000000ull -#define PCIE_REG_IODA_AD_TBL_PESTB 0x0008000000000000ull -#define PCIE_REG_IODA_AD_TBL_TVT 0x0009000000000000ull -#define PCIE_REG_IODA_AD_TBL_TCE 0x000a000000000000ull -#define PCIE_REG_IODA_DATA0 0x228 -#define PCIE_REG_IODA_DATA1 0x230 - -#define PCIE_REG_LOCK2 0x240 - -#define PCIE_REG_PHB_GEN_CAP 0x250 -#define PCIE_REG_PHB_TCE_CAP 0x258 -#define PCIE_REG_PHB_IRQ_CAP 0x260 -#define PCIE_REG_PHB_EEH_CAP 0x268 - -#define PCIE_REG_PAPR_ERR_INJ_CONTROL 0x2b0 -#define PCIE_REG_PAPR_ERR_INJ_ADDR 0x2b8 -#define PCIE_REG_PAPR_ERR_INJ_MASK 0x2c0 - - -#define PCIE_REG_SYS_CFG1 0x600 -#define PCIE_REG_SYS_CFG1_CLASS_CODE 0x0000000000ffffffull - -#define IODA_TVT0_TTA_MASK 0x000fffffffff0000ull -#define IODA_TVT0_TTA_SHIFT 4 -#define IODA_TVT0_BUSNUM_VALID_MASK 0x000000000000e000ull -#define IODA_TVT0_TCE_TABLE_SIZE_MASK 0x0000000000001f00ull -#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT 8 -#define IODA_TVT0_BUSNUM_VALUE_MASK 0x00000000000000ffull -#define IODA_TVT0_BUSNUM_VALID_SHIFT 0 -#define IODA_TVT1_DEVNUM_VALID 0x2000000000000000ull -#define IODA_TVT1_DEVNUM_VALUE_MASK 0x1f00000000000000ull -#define IODA_TVT1_DEVNUM_VALUE_SHIFT 56 -#define IODA_TVT1_FUNCNUM_VALID 0x0008000000000000ull -#define IODA_TVT1_FUNCNUM_VALUE_MASK 0x0007000000000000ull -#define IODA_TVT1_FUNCNUM_VALUE_SHIFT 48 -#define IODA_TVT1_IO_PAGE_SIZE_MASK 0x00001f0000000000ull -#define IODA_TVT1_IO_PAGE_SIZE_SHIFT 40 -#define IODA_TVT1_PE_NUMBER_MASK 0x000000000000003full -#define IODA_TVT1_PE_NUMBER_SHIFT 0 - -#define IODA_TVT_COUNT 64 - -/* UTL Core registers */ -#define PCIE_UTL_SYS_BUS_CONTROL 0x400 -#define PCIE_UTL_STATUS 0x408 -#define PCIE_UTL_SYS_BUS_AGENT_STATUS 0x410 -#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV 0x418 -#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN 0x420 -#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF 0x440 -#define PCIE_UTL_REVISION_ID 0x448 - -#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC 0x4c0 -#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC 0x4d0 -#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC 0x4e0 -#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC 0x4f0 -#define PCIE_UTL_OUT_NP_BUF_ALLOC 0x500 -#define PCIE_UTL_IN_NP_BUF_ALLOC 0x510 -#define PCIE_UTL_PCIE_TAGS_ALLOC 0x520 -#define PCIE_UTL_GBIF_READ_TAGS_ALLOC 0x530 - -#define PCIE_UTL_PCIE_PORT_CONTROL 0x540 -#define PCIE_UTL_PCIE_PORT_STATUS 0x548 -#define PCIE_UTL_PCIE_PORT_ERROR_SEV 0x550 -#define PCIE_UTL_PCIE_PORT_IRQ_EN 0x558 -#define PCIE_UTL_RC_STATUS 0x560 -#define PCIE_UTL_RC_ERR_SEVERITY 0x568 -#define PCIE_UTL_RC_IRQ_EN 0x570 -#define PCIE_UTL_EP_STATUS 0x578 -#define PCIE_UTL_EP_ERR_SEVERITY 0x580 -#define PCIE_UTL_EP_ERR_IRQ_EN 0x588 - -#define PCIE_UTL_PCI_PM_CTRL1 0x590 -#define PCIE_UTL_PCI_PM_CTRL2 0x598 - -/* PCIe stack registers */ -#define PCIE_REG_SYSTEM_CONFIG1 0x600 -#define PCIE_REG_SYSTEM_CONFIG2 0x608 -#define PCIE_REG_EP_SYSTEM_CONFIG 0x618 -#define PCIE_REG_EP_FLR 0x620 -#define PCIE_REG_EP_BAR_CONFIG 0x628 -#define PCIE_REG_LINK_CONFIG 0x630 -#define PCIE_REG_PM_CONFIG 0x640 -#define PCIE_REG_DLP_CONTROL 0x650 -#define PCIE_REG_DLP_STATUS 0x658 -#define PCIE_REG_ERR_REPORT_CONTROL 0x660 -#define PCIE_REG_SLOT_CONTROL1 0x670 -#define PCIE_REG_SLOT_CONTROL2 0x678 -#define PCIE_REG_UTL_CONFIG 0x680 -#define PCIE_REG_BUFFERS_CONFIG 0x690 -#define PCIE_REG_ERROR_INJECT 0x698 -#define PCIE_REG_SRIOV_CONFIG 0x6a0 -#define PCIE_REG_PF0_SRIOV_STATUS 0x6a8 -#define PCIE_REG_PF1_SRIOV_STATUS 0x6b0 -#define PCIE_REG_PORT_NUMBER 0x700 -#define PCIE_REG_POR_SYSTEM_CONFIG 0x708 - -/* PHB internal logic registers */ -#define PCIE_REG_PHB_VERSION 0x800 -#define PCIE_REG_RESET 0x808 -#define PCIE_REG_PHB_CONTROL 0x810 -#define PCIE_REG_PHB_TIMEOUT_CONTROL1 0x878 -#define PCIE_REG_PHB_QUIESCE_DMA 0x888 -#define PCIE_REG_PHB_DMA_READ_TAG_ACTV 0x900 -#define PCIE_REG_PHB_TCE_READ_TAG_ACTV 0x908 - -/* FIR registers */ -#define PCIE_REG_LEM_FIR_ACCUM 0xc00 -#define PCIE_REG_LEM_FIR_AND_MASK 0xc08 -#define PCIE_REG_LEM_FIR_OR_MASK 0xc10 -#define PCIE_REG_LEM_ACTION0 0xc18 -#define PCIE_REG_LEM_ACTION1 0xc20 -#define PCIE_REG_LEM_ERROR_MASK 0xc30 -#define PCIE_REG_LEM_ERROR_AND_MASK 0xc38 -#define PCIE_REG_LEM_ERROR_OR_MASK 0xc40 - -/* PHB Error registers */ -#define PCIE_REG_PHB_ERR_STATUS 0xc80 -#define PCIE_REG_PHB_ERR1_STATUS 0xc88 -#define PCIE_REG_PHB_ERR_INJECT 0xc90 -#define PCIE_REG_PHB_ERR_LEM_ENABLE 0xc98 -#define PCIE_REG_PHB_ERR_IRQ_ENABLE 0xca0 -#define PCIE_REG_PHB_ERR_FREEZE_ENABLE 0xca8 -#define PCIE_REG_PHB_ERR_SIDE_ENABLE 0xcb8 -#define PCIE_REG_PHB_ERR_LOG_0 0xcc0 -#define PCIE_REG_PHB_ERR_LOG_1 0xcc8 -#define PCIE_REG_PHB_ERR_STATUS_MASK 0xcd0 -#define PCIE_REG_PHB_ERR1_STATUS_MASK 0xcd8 - -#define PCIE_REG_MMIO_ERR_STATUS 0xd00 -#define PCIE_REG_MMIO_ERR1_STATUS 0xd08 -#define PCIE_REG_MMIO_ERR_INJECT 0xd10 -#define PCIE_REG_MMIO_ERR_LEM_ENABLE 0xd18 -#define PCIE_REG_MMIO_ERR_IRQ_ENABLE 0xd20 -#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE 0xd28 -#define PCIE_REG_MMIO_ERR_SIDE_ENABLE 0xd38 -#define PCIE_REG_MMIO_ERR_LOG_0 0xd40 -#define PCIE_REG_MMIO_ERR_LOG_1 0xd48 -#define PCIE_REG_MMIO_ERR_STATUS_MASK 0xd50 -#define PCIE_REG_MMIO_ERR1_STATUS_MASK 0xd58 - -#define PCIE_REG_DMA_ERR_STATUS 0xd80 -#define PCIE_REG_DMA_ERR1_STATUS 0xd88 -#define PCIE_REG_DMA_ERR_INJECT 0xd90 -#define PCIE_REG_DMA_ERR_LEM_ENABLE 0xd98 -#define PCIE_REG_DMA_ERR_IRQ_ENABLE 0xda0 -#define PCIE_REG_DMA_ERR_FREEZE_ENABLE 0xda8 -#define PCIE_REG_DMA_ERR_SIDE_ENABLE 0xdb8 -#define PCIE_REG_DMA_ERR_LOG_0 0xdc0 -#define PCIE_REG_DMA_ERR_LOG_1 0xdc8 -#define PCIE_REG_DMA_ERR_STATUS_MASK 0xdd0 -#define PCIE_REG_DMA_ERR1_STATUS_MASK 0xdd8 - -/* Shortcuts for access to the above using the PHB definitions - * with an offset - */ -#define PCIE_REG_ERR_PHB_OFFSET 0x0 -#define PCIE_REG_ERR_MMIO_OFFSET 0x80 -#define PCIE_REG_ERR_DMA_OFFSET 0x100 - -/* Debug and Trace registers */ -#define PCIE_REG_PHB_DEBUG_CONTROL0 0xe00 -#define PCIE_REG_PHB_DEBUG_STATUS0 0xe08 -#define PCIE_REG_PHB_DEBUG_CONTROL1 0xe10 -#define PCIE_REG_PHB_DEBUG_STATUS1 0xe18 -#define PCIE_REG_PHB_DEBUG_CONTROL2 0xe20 -#define PCIE_REG_PHB_DEBUG_STATUS2 0xe28 -#define PCIE_REG_PHB_DEBUG_CONTROL3 0xe30 -#define PCIE_REG_PHB_DEBUG_STATUS3 0xe38 -#define PCIE_REG_PHB_DEBUG_CONTROL4 0xe40 -#define PCIE_REG_PHB_DEBUG_STATUS4 0xe48 -#define PCIE_REG_PHB_DEBUG_CONTROL5 0xe50 -#define PCIE_REG_PHB_DEBUG_STATUS5 0xe58 -#define PCIE_REG_PHB_DEBUG_CONTROL6 0xe60 -#define PCIE_REG_PHB_DEBUG_STATUS6 0xe68 - -/* Definition for PCIe errors */ -struct wsp_pcie_err_log_data { - __u64 phb_err; - __u64 phb_err1; - __u64 phb_log0; - __u64 phb_log1; - __u64 mmio_err; - __u64 mmio_err1; - __u64 mmio_log0; - __u64 mmio_log1; - __u64 dma_err; - __u64 dma_err1; - __u64 dma_log0; - __u64 dma_log1; - __u64 utl_sys_err; - __u64 utl_port_err; - __u64 utl_rc_err; - __u64 unused; -}; - -#endif /* __WSP_PCI_H */ diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 228cf91b91c1..ffd1169ebaab 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -178,37 +177,6 @@ u32 get_baudrate(void) EXPORT_SYMBOL(get_baudrate); #endif /* CONFIG_CPM2 */ -#ifdef CONFIG_FIXED_PHY -static int __init of_add_fixed_phys(void) -{ - int ret; - struct device_node *np; - u32 *fixed_link; - struct fixed_phy_status status = {}; - - for_each_node_by_name(np, "ethernet") { - fixed_link = (u32 *)of_get_property(np, "fixed-link", NULL); - if (!fixed_link) - continue; - - status.link = 1; - status.duplex = fixed_link[1]; - status.speed = fixed_link[2]; - status.pause = fixed_link[3]; - status.asym_pause = fixed_link[4]; - - ret = fixed_phy_add(PHY_POLL, fixed_link[0], &status); - if (ret) { - of_node_put(np); - return ret; - } - } - - return 0; -} -arch_initcall(of_add_fixed_phys); -#endif /* CONFIG_FIXED_PHY */ - #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx) static __be32 __iomem *rstcr; diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 9dee47071af8..de8d9483bbe8 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -26,6 +26,7 @@ #include #include #include +#include struct icp_ipl { union { @@ -145,7 +146,13 @@ static unsigned int icp_native_get_irq(void) static void icp_native_cause_ipi(int cpu, unsigned long data) { kvmppc_set_host_ipi(cpu, 1); - icp_native_set_qirr(cpu, IPI_PRIORITY); +#ifdef CONFIG_PPC_DOORBELL + if (cpu_has_feature(CPU_FTR_DBELL) && + (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id())))) + doorbell_cause_ipi(cpu, data); + else +#endif + icp_native_set_qirr(cpu, IPI_PRIORITY); } void xics_wake_cpu(int cpu) diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c index bce3dcfe5058..c98748617896 100644 --- a/arch/powerpc/xmon/nonstdio.c +++ b/arch/powerpc/xmon/nonstdio.c @@ -122,7 +122,7 @@ void xmon_printf(const char *format, ...) if (n && rc == 0) { /* No udbg hooks, fallback to printk() - dangerous */ - printk(xmon_outbuf); + printk("%s", xmon_outbuf); } } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e9f8fa9337fe..a2cbd875543a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -269,27 +269,17 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) EMIT4(0xa7c80000); /* Clear A if the first register does not set it. */ switch (filter[0].code) { - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - case BPF_S_LD_W_LEN: - case BPF_S_LD_W_IND: - case BPF_S_LD_H_IND: - case BPF_S_LD_B_IND: - case BPF_S_LD_IMM: - case BPF_S_LD_MEM: - case BPF_S_MISC_TXA: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_PKTTYPE: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_QUEUE: - case BPF_S_ANC_HATYPE: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_CPU: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_RET_K: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LD | BPF_W | BPF_IND: + case BPF_LD | BPF_H | BPF_IND: + case BPF_LD | BPF_B | BPF_IND: + case BPF_LD | BPF_IMM: + case BPF_LD | BPF_MEM: + case BPF_MISC | BPF_TXA: + case BPF_RET | BPF_K: /* first instruction sets A register */ break; default: /* A = 0 */ @@ -304,15 +294,18 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, unsigned int K; int offset; unsigned int mask; + u16 code; K = filter->k; - switch (filter->code) { - case BPF_S_ALU_ADD_X: /* A += X */ + code = bpf_anc_helper(filter); + + switch (code) { + case BPF_ALU | BPF_ADD | BPF_X: /* A += X */ jit->seen |= SEEN_XREG; /* ar %r5,%r12 */ EMIT2(0x1a5c); break; - case BPF_S_ALU_ADD_K: /* A += K */ + case BPF_ALU | BPF_ADD | BPF_K: /* A += K */ if (!K) break; if (K <= 16383) @@ -325,12 +318,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* a %r5,(%r13) */ EMIT4_DISP(0x5a50d000, EMIT_CONST(K)); break; - case BPF_S_ALU_SUB_X: /* A -= X */ + case BPF_ALU | BPF_SUB | BPF_X: /* A -= X */ jit->seen |= SEEN_XREG; /* sr %r5,%r12 */ EMIT2(0x1b5c); break; - case BPF_S_ALU_SUB_K: /* A -= K */ + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ if (!K) break; if (K <= 16384) @@ -343,12 +336,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* s %r5,(%r13) */ EMIT4_DISP(0x5b50d000, EMIT_CONST(K)); break; - case BPF_S_ALU_MUL_X: /* A *= X */ + case BPF_ALU | BPF_MUL | BPF_X: /* A *= X */ jit->seen |= SEEN_XREG; /* msr %r5,%r12 */ EMIT4(0xb252005c); break; - case BPF_S_ALU_MUL_K: /* A *= K */ + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ if (K <= 16383) /* mhi %r5,K */ EMIT4_IMM(0xa75c0000, K); @@ -359,7 +352,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* ms %r5,(%r13) */ EMIT4_DISP(0x7150d000, EMIT_CONST(K)); break; - case BPF_S_ALU_DIV_X: /* A /= X */ + case BPF_ALU | BPF_DIV | BPF_X: /* A /= X */ jit->seen |= SEEN_XREG | SEEN_RET0; /* ltr %r12,%r12 */ EMIT2(0x12cc); @@ -370,7 +363,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* dlr %r4,%r12 */ EMIT4(0xb997004c); break; - case BPF_S_ALU_DIV_K: /* A /= K */ + case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */ if (K == 1) break; /* lhi %r4,0 */ @@ -378,7 +371,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* dl %r4,(%r13) */ EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K)); break; - case BPF_S_ALU_MOD_X: /* A %= X */ + case BPF_ALU | BPF_MOD | BPF_X: /* A %= X */ jit->seen |= SEEN_XREG | SEEN_RET0; /* ltr %r12,%r12 */ EMIT2(0x12cc); @@ -391,7 +384,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* lr %r5,%r4 */ EMIT2(0x1854); break; - case BPF_S_ALU_MOD_K: /* A %= K */ + case BPF_ALU | BPF_MOD | BPF_K: /* A %= K */ if (K == 1) { /* lhi %r5,0 */ EMIT4(0xa7580000); @@ -404,12 +397,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* lr %r5,%r4 */ EMIT2(0x1854); break; - case BPF_S_ALU_AND_X: /* A &= X */ + case BPF_ALU | BPF_AND | BPF_X: /* A &= X */ jit->seen |= SEEN_XREG; /* nr %r5,%r12 */ EMIT2(0x145c); break; - case BPF_S_ALU_AND_K: /* A &= K */ + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ if (test_facility(21)) /* nilf %r5, */ EMIT6_IMM(0xc05b0000, K); @@ -417,12 +410,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* n %r5,(%r13) */ EMIT4_DISP(0x5450d000, EMIT_CONST(K)); break; - case BPF_S_ALU_OR_X: /* A |= X */ + case BPF_ALU | BPF_OR | BPF_X: /* A |= X */ jit->seen |= SEEN_XREG; /* or %r5,%r12 */ EMIT2(0x165c); break; - case BPF_S_ALU_OR_K: /* A |= K */ + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ if (test_facility(21)) /* oilf %r5, */ EMIT6_IMM(0xc05d0000, K); @@ -430,55 +423,55 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* o %r5,(%r13) */ EMIT4_DISP(0x5650d000, EMIT_CONST(K)); break; - case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ - case BPF_S_ALU_XOR_X: + case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */ + case BPF_ALU | BPF_XOR | BPF_X: jit->seen |= SEEN_XREG; /* xr %r5,%r12 */ EMIT2(0x175c); break; - case BPF_S_ALU_XOR_K: /* A ^= K */ + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ if (!K) break; /* x %r5,(%r13) */ EMIT4_DISP(0x5750d000, EMIT_CONST(K)); break; - case BPF_S_ALU_LSH_X: /* A <<= X; */ + case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */ jit->seen |= SEEN_XREG; /* sll %r5,0(%r12) */ EMIT4(0x8950c000); break; - case BPF_S_ALU_LSH_K: /* A <<= K */ + case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */ if (K == 0) break; /* sll %r5,K */ EMIT4_DISP(0x89500000, K); break; - case BPF_S_ALU_RSH_X: /* A >>= X; */ + case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */ jit->seen |= SEEN_XREG; /* srl %r5,0(%r12) */ EMIT4(0x8850c000); break; - case BPF_S_ALU_RSH_K: /* A >>= K; */ + case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */ if (K == 0) break; /* srl %r5,K */ EMIT4_DISP(0x88500000, K); break; - case BPF_S_ALU_NEG: /* A = -A */ + case BPF_ALU | BPF_NEG: /* A = -A */ /* lnr %r5,%r5 */ EMIT2(0x1155); break; - case BPF_S_JMP_JA: /* ip += K */ + case BPF_JMP | BPF_JA: /* ip += K */ offset = addrs[i + K] + jit->start - jit->prg; EMIT4_PCREL(0xa7f40000, offset); break; - case BPF_S_JMP_JGT_K: /* ip += (A > K) ? jt : jf */ + case BPF_JMP | BPF_JGT | BPF_K: /* ip += (A > K) ? jt : jf */ mask = 0x200000; /* jh */ goto kbranch; - case BPF_S_JMP_JGE_K: /* ip += (A >= K) ? jt : jf */ + case BPF_JMP | BPF_JGE | BPF_K: /* ip += (A >= K) ? jt : jf */ mask = 0xa00000; /* jhe */ goto kbranch; - case BPF_S_JMP_JEQ_K: /* ip += (A == K) ? jt : jf */ + case BPF_JMP | BPF_JEQ | BPF_K: /* ip += (A == K) ? jt : jf */ mask = 0x800000; /* je */ kbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { @@ -511,7 +504,7 @@ branch: if (filter->jt == filter->jf) { EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset); } break; - case BPF_S_JMP_JSET_K: /* ip += (A & K) ? jt : jf */ + case BPF_JMP | BPF_JSET | BPF_K: /* ip += (A & K) ? jt : jf */ mask = 0x700000; /* jnz */ /* Emit test if the branch targets are different */ if (filter->jt != filter->jf) { @@ -525,13 +518,13 @@ branch: if (filter->jt == filter->jf) { EMIT4_IMM(0xa7510000, K); } goto branch; - case BPF_S_JMP_JGT_X: /* ip += (A > X) ? jt : jf */ + case BPF_JMP | BPF_JGT | BPF_X: /* ip += (A > X) ? jt : jf */ mask = 0x200000; /* jh */ goto xbranch; - case BPF_S_JMP_JGE_X: /* ip += (A >= X) ? jt : jf */ + case BPF_JMP | BPF_JGE | BPF_X: /* ip += (A >= X) ? jt : jf */ mask = 0xa00000; /* jhe */ goto xbranch; - case BPF_S_JMP_JEQ_X: /* ip += (A == X) ? jt : jf */ + case BPF_JMP | BPF_JEQ | BPF_X: /* ip += (A == X) ? jt : jf */ mask = 0x800000; /* je */ xbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { @@ -540,7 +533,7 @@ branch: if (filter->jt == filter->jf) { EMIT2(0x195c); } goto branch; - case BPF_S_JMP_JSET_X: /* ip += (A & X) ? jt : jf */ + case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */ mask = 0x700000; /* jnz */ /* Emit test if the branch targets are different */ if (filter->jt != filter->jf) { @@ -551,15 +544,15 @@ branch: if (filter->jt == filter->jf) { EMIT2(0x144c); } goto branch; - case BPF_S_LD_W_ABS: /* A = *(u32 *) (skb->data+K) */ + case BPF_LD | BPF_W | BPF_ABS: /* A = *(u32 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD; offset = jit->off_load_word; goto load_abs; - case BPF_S_LD_H_ABS: /* A = *(u16 *) (skb->data+K) */ + case BPF_LD | BPF_H | BPF_ABS: /* A = *(u16 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF; offset = jit->off_load_half; goto load_abs; - case BPF_S_LD_B_ABS: /* A = *(u8 *) (skb->data+K) */ + case BPF_LD | BPF_B | BPF_ABS: /* A = *(u8 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE; offset = jit->off_load_byte; load_abs: if ((int) K < 0) @@ -573,19 +566,19 @@ load_abs: if ((int) K < 0) /* jnz */ EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg)); break; - case BPF_S_LD_W_IND: /* A = *(u32 *) (skb->data+K+X) */ + case BPF_LD | BPF_W | BPF_IND: /* A = *(u32 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD; offset = jit->off_load_iword; goto call_fn; - case BPF_S_LD_H_IND: /* A = *(u16 *) (skb->data+K+X) */ + case BPF_LD | BPF_H | BPF_IND: /* A = *(u16 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF; offset = jit->off_load_ihalf; goto call_fn; - case BPF_S_LD_B_IND: /* A = *(u8 *) (skb->data+K+X) */ + case BPF_LD | BPF_B | BPF_IND: /* A = *(u8 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE; offset = jit->off_load_ibyte; goto call_fn; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ jit->seen |= SEEN_RET0; if ((int) K < 0) { @@ -596,17 +589,17 @@ load_abs: if ((int) K < 0) jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH; offset = jit->off_load_bmsh; goto call_fn; - case BPF_S_LD_W_LEN: /* A = skb->len; */ + case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); /* l %r5,(%r2) */ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len)); break; - case BPF_S_LDX_W_LEN: /* X = skb->len; */ + case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ jit->seen |= SEEN_XREG; /* l %r12,(%r2) */ EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len)); break; - case BPF_S_LD_IMM: /* A = K */ + case BPF_LD | BPF_IMM: /* A = K */ if (K <= 16383) /* lhi %r5,K */ EMIT4_IMM(0xa7580000, K); @@ -617,7 +610,7 @@ load_abs: if ((int) K < 0) /* l %r5,(%r13) */ EMIT4_DISP(0x5850d000, EMIT_CONST(K)); break; - case BPF_S_LDX_IMM: /* X = K */ + case BPF_LDX | BPF_IMM: /* X = K */ jit->seen |= SEEN_XREG; if (K <= 16383) /* lhi %r12, */ @@ -629,29 +622,29 @@ load_abs: if ((int) K < 0) /* l %r12,(%r13) */ EMIT4_DISP(0x58c0d000, EMIT_CONST(K)); break; - case BPF_S_LD_MEM: /* A = mem[K] */ + case BPF_LD | BPF_MEM: /* A = mem[K] */ jit->seen |= SEEN_MEM; /* l %r5,(%r15) */ EMIT4_DISP(0x5850f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_LDX_MEM: /* X = mem[K] */ + case BPF_LDX | BPF_MEM: /* X = mem[K] */ jit->seen |= SEEN_XREG | SEEN_MEM; /* l %r12,(%r15) */ EMIT4_DISP(0x58c0f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_MISC_TAX: /* X = A */ + case BPF_MISC | BPF_TAX: /* X = A */ jit->seen |= SEEN_XREG; /* lr %r12,%r5 */ EMIT2(0x18c5); break; - case BPF_S_MISC_TXA: /* A = X */ + case BPF_MISC | BPF_TXA: /* A = X */ jit->seen |= SEEN_XREG; /* lr %r5,%r12 */ EMIT2(0x185c); break; - case BPF_S_RET_K: + case BPF_RET | BPF_K: if (K == 0) { jit->seen |= SEEN_RET0; if (last) @@ -671,33 +664,33 @@ load_abs: if ((int) K < 0) EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); } break; - case BPF_S_RET_A: + case BPF_RET | BPF_A: /* llgfr %r2,%r5 */ EMIT4(0xb9160025); /* j */ EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); break; - case BPF_S_ST: /* mem[K] = A */ + case BPF_ST: /* mem[K] = A */ jit->seen |= SEEN_MEM; /* st %r5,(%r15) */ EMIT4_DISP(0x5050f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ + case BPF_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ jit->seen |= SEEN_XREG | SEEN_MEM; /* st %r12,(%r15) */ EMIT4_DISP(0x50c0f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); /* lhi %r5,0 */ EMIT4(0xa7580000); /* icm %r5,3,(%r2) */ EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol)); break; - case BPF_S_ANC_IFINDEX: /* if (!skb->dev) return 0; - * A = skb->dev->ifindex */ + case BPF_ANC | SKF_AD_IFINDEX: /* if (!skb->dev) return 0; + * A = skb->dev->ifindex */ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); jit->seen |= SEEN_RET0; /* lg %r1,(%r2) */ @@ -709,20 +702,20 @@ load_abs: if ((int) K < 0) /* l %r5,(%r1) */ EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex)); break; - case BPF_S_ANC_MARK: /* A = skb->mark */ + case BPF_ANC | SKF_AD_MARK: /* A = skb->mark */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); /* l %r5,(%r2) */ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark)); break; - case BPF_S_ANC_QUEUE: /* A = skb->queue_mapping */ + case BPF_ANC | SKF_AD_QUEUE: /* A = skb->queue_mapping */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); /* lhi %r5,0 */ EMIT4(0xa7580000); /* icm %r5,3,(%r2) */ EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping)); break; - case BPF_S_ANC_HATYPE: /* if (!skb->dev) return 0; - * A = skb->dev->type */ + case BPF_ANC | SKF_AD_HATYPE: /* if (!skb->dev) return 0; + * A = skb->dev->type */ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); jit->seen |= SEEN_RET0; /* lg %r1,(%r2) */ @@ -736,20 +729,20 @@ load_abs: if ((int) K < 0) /* icm %r5,3,(%r1) */ EMIT4_DISP(0xbf531000, offsetof(struct net_device, type)); break; - case BPF_S_ANC_RXHASH: /* A = skb->hash */ + case BPF_ANC | SKF_AD_RXHASH: /* A = skb->hash */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); /* l %r5,(%r2) */ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash)); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); /* lhi %r5,0 */ EMIT4(0xa7580000); /* icm %r5,3,(%r2) */ EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, vlan_tci)); - if (filter->code == BPF_S_ANC_VLAN_TAG) { + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) { /* nill %r5,0xefff */ EMIT4_IMM(0xa5570000, ~VLAN_TAG_PRESENT); } else { @@ -759,7 +752,7 @@ load_abs: if ((int) K < 0) EMIT4_DISP(0x88500000, 12); } break; - case BPF_S_ANC_PKTTYPE: + case BPF_ANC | SKF_AD_PKTTYPE: if (pkt_type_offset < 0) goto out; /* lhi %r5,0 */ @@ -769,7 +762,7 @@ load_abs: if ((int) K < 0) /* srl %r5,5 */ EMIT4_DISP(0x88500000, 5); break; - case BPF_S_ANC_CPU: /* A = smp_processor_id() */ + case BPF_ANC | SKF_AD_CPU: /* A = smp_processor_id() */ #ifdef CONFIG_SMP /* l %r5, */ EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr)); diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h index bdbda1453aa9..04471dc64847 100644 --- a/arch/sparc/include/asm/checksum_32.h +++ b/arch/sparc/include/asm/checksum_32.h @@ -238,4 +238,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) return csum_fold(csum_partial(buff, len, 0)); } +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + __asm__ __volatile__( + "addcc %0, %1, %0\n" + "addx %0, %%g0, %0" + : "=r" (csum) + : "r" (addend), "0" (csum)); + + return csum; +} + #endif /* !(__SPARC_CHECKSUM_H) */ diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h index 019b9615e43c..2ff81ae8f3af 100644 --- a/arch/sparc/include/asm/checksum_64.h +++ b/arch/sparc/include/asm/checksum_64.h @@ -164,4 +164,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) return csum_fold(csum_partial(buff, len, 0)); } +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + __asm__ __volatile__( + "addcc %0, %1, %0\n" + "addx %0, %%g0, %0" + : "=r" (csum) + : "r" (addend), "0" (csum)); + + return csum; +} + #endif /* !(__SPARC64_CHECKSUM_H) */ diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index a82c6b2a9780..892a102671ad 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_) #define BNE (F2(0, 2) | CONDNE) #ifdef CONFIG_SPARC64 -#define BNE_PTR (F2(0, 1) | CONDNE | (2 << 20)) +#define BE_PTR (F2(0, 1) | CONDE | (2 << 20)) #else -#define BNE_PTR BNE +#define BE_PTR BE #endif #define SETHI(K, REG) \ @@ -415,20 +415,11 @@ void bpf_jit_compile(struct sk_filter *fp) emit_reg_move(O7, r_saved_O7); switch (filter[0].code) { - case BPF_S_RET_K: - case BPF_S_LD_W_LEN: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_PKTTYPE: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_CPU: - case BPF_S_ANC_QUEUE: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: /* The first instruction sets the A register (or is * a "RET 'constant'") */ @@ -445,59 +436,60 @@ void bpf_jit_compile(struct sk_filter *fp) unsigned int t_offset; unsigned int f_offset; u32 t_op, f_op; + u16 code = bpf_anc_helper(&filter[i]); int ilen; - switch (filter[i].code) { - case BPF_S_ALU_ADD_X: /* A += X; */ + switch (code) { + case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */ emit_alu_X(ADD); break; - case BPF_S_ALU_ADD_K: /* A += K; */ + case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */ emit_alu_K(ADD, K); break; - case BPF_S_ALU_SUB_X: /* A -= X; */ + case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */ emit_alu_X(SUB); break; - case BPF_S_ALU_SUB_K: /* A -= K */ + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ emit_alu_K(SUB, K); break; - case BPF_S_ALU_AND_X: /* A &= X */ + case BPF_ALU | BPF_AND | BPF_X: /* A &= X */ emit_alu_X(AND); break; - case BPF_S_ALU_AND_K: /* A &= K */ + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ emit_alu_K(AND, K); break; - case BPF_S_ALU_OR_X: /* A |= X */ + case BPF_ALU | BPF_OR | BPF_X: /* A |= X */ emit_alu_X(OR); break; - case BPF_S_ALU_OR_K: /* A |= K */ + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ emit_alu_K(OR, K); break; - case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ - case BPF_S_ALU_XOR_X: + case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */ + case BPF_ALU | BPF_XOR | BPF_X: emit_alu_X(XOR); break; - case BPF_S_ALU_XOR_K: /* A ^= K */ + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ emit_alu_K(XOR, K); break; - case BPF_S_ALU_LSH_X: /* A <<= X */ + case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X */ emit_alu_X(SLL); break; - case BPF_S_ALU_LSH_K: /* A <<= K */ + case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */ emit_alu_K(SLL, K); break; - case BPF_S_ALU_RSH_X: /* A >>= X */ + case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X */ emit_alu_X(SRL); break; - case BPF_S_ALU_RSH_K: /* A >>= K */ + case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K */ emit_alu_K(SRL, K); break; - case BPF_S_ALU_MUL_X: /* A *= X; */ + case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */ emit_alu_X(MUL); break; - case BPF_S_ALU_MUL_K: /* A *= K */ + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ emit_alu_K(MUL, K); break; - case BPF_S_ALU_DIV_K: /* A /= K with K != 0*/ + case BPF_ALU | BPF_DIV | BPF_K: /* A /= K with K != 0*/ if (K == 1) break; emit_write_y(G0); @@ -512,7 +504,7 @@ void bpf_jit_compile(struct sk_filter *fp) #endif emit_alu_K(DIV, K); break; - case BPF_S_ALU_DIV_X: /* A /= X; */ + case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */ emit_cmpi(r_X, 0); if (pc_ret0 > 0) { t_offset = addrs[pc_ret0 - 1]; @@ -544,10 +536,10 @@ void bpf_jit_compile(struct sk_filter *fp) #endif emit_alu_X(DIV); break; - case BPF_S_ALU_NEG: + case BPF_ALU | BPF_NEG: emit_neg(); break; - case BPF_S_RET_K: + case BPF_RET | BPF_K: if (!K) { if (pc_ret0 == -1) pc_ret0 = i; @@ -556,7 +548,7 @@ void bpf_jit_compile(struct sk_filter *fp) emit_loadimm(K, r_A); } /* Fallthrough */ - case BPF_S_RET_A: + case BPF_RET | BPF_A: if (seen_or_pass0) { if (i != flen - 1) { emit_jump(cleanup_addr); @@ -573,18 +565,18 @@ void bpf_jit_compile(struct sk_filter *fp) emit_jmpl(r_saved_O7, 8, G0); emit_reg_move(r_A, O0); /* delay slot */ break; - case BPF_S_MISC_TAX: + case BPF_MISC | BPF_TAX: seen |= SEEN_XREG; emit_reg_move(r_A, r_X); break; - case BPF_S_MISC_TXA: + case BPF_MISC | BPF_TXA: seen |= SEEN_XREG; emit_reg_move(r_X, r_A); break; - case BPF_S_ANC_CPU: + case BPF_ANC | SKF_AD_CPU: emit_load_cpu(r_A); break; - case BPF_S_ANC_PROTOCOL: + case BPF_ANC | SKF_AD_PROTOCOL: emit_skb_load16(protocol, r_A); break; #if 0 @@ -592,38 +584,38 @@ void bpf_jit_compile(struct sk_filter *fp) * a bit field even though we very much * know what we are doing here. */ - case BPF_S_ANC_PKTTYPE: + case BPF_ANC | SKF_AD_PKTTYPE: __emit_skb_load8(pkt_type, r_A); emit_alu_K(SRL, 5); break; #endif - case BPF_S_ANC_IFINDEX: + case BPF_ANC | SKF_AD_IFINDEX: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load32(r_A, struct net_device, ifindex, r_A); break; - case BPF_S_ANC_MARK: + case BPF_ANC | SKF_AD_MARK: emit_skb_load32(mark, r_A); break; - case BPF_S_ANC_QUEUE: + case BPF_ANC | SKF_AD_QUEUE: emit_skb_load16(queue_mapping, r_A); break; - case BPF_S_ANC_HATYPE: + case BPF_ANC | SKF_AD_HATYPE: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load16(r_A, struct net_device, type, r_A); break; - case BPF_S_ANC_RXHASH: + case BPF_ANC | SKF_AD_RXHASH: emit_skb_load32(hash, r_A); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: emit_skb_load16(vlan_tci, r_A); - if (filter[i].code == BPF_S_ANC_VLAN_TAG) { + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) { emit_andi(r_A, VLAN_VID_MASK, r_A); } else { emit_loadimm(VLAN_TAG_PRESENT, r_TMP); @@ -631,44 +623,44 @@ void bpf_jit_compile(struct sk_filter *fp) } break; - case BPF_S_LD_IMM: + case BPF_LD | BPF_IMM: emit_loadimm(K, r_A); break; - case BPF_S_LDX_IMM: + case BPF_LDX | BPF_IMM: emit_loadimm(K, r_X); break; - case BPF_S_LD_MEM: + case BPF_LD | BPF_MEM: emit_ldmem(K * 4, r_A); break; - case BPF_S_LDX_MEM: + case BPF_LDX | BPF_MEM: emit_ldmem(K * 4, r_X); break; - case BPF_S_ST: + case BPF_ST: emit_stmem(K * 4, r_A); break; - case BPF_S_STX: + case BPF_STX: emit_stmem(K * 4, r_X); break; #define CHOOSE_LOAD_FUNC(K, func) \ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word); common_load: seen |= SEEN_DATAREF; emit_loadimm(K, r_OFF); emit_call(func); break; - case BPF_S_LD_H_ABS: + case BPF_LD | BPF_H | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half); goto common_load; - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_B | BPF_ABS: func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte); goto common_load; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh); goto common_load; - case BPF_S_LD_W_IND: + case BPF_LD | BPF_W | BPF_IND: func = bpf_jit_load_word; common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; if (K) { @@ -683,13 +675,13 @@ common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; } emit_call(func); break; - case BPF_S_LD_H_IND: + case BPF_LD | BPF_H | BPF_IND: func = bpf_jit_load_half; goto common_load_ind; - case BPF_S_LD_B_IND: + case BPF_LD | BPF_B | BPF_IND: func = bpf_jit_load_byte; goto common_load_ind; - case BPF_S_JMP_JA: + case BPF_JMP | BPF_JA: emit_jump(addrs[i + K]); emit_nop(); break; @@ -700,14 +692,14 @@ common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; f_op = FOP; \ goto cond_branch - COND_SEL(BPF_S_JMP_JGT_K, BGU, BLEU); - COND_SEL(BPF_S_JMP_JGE_K, BGEU, BLU); - COND_SEL(BPF_S_JMP_JEQ_K, BE, BNE); - COND_SEL(BPF_S_JMP_JSET_K, BNE, BE); - COND_SEL(BPF_S_JMP_JGT_X, BGU, BLEU); - COND_SEL(BPF_S_JMP_JGE_X, BGEU, BLU); - COND_SEL(BPF_S_JMP_JEQ_X, BE, BNE); - COND_SEL(BPF_S_JMP_JSET_X, BNE, BE); + COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU); + COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU); + COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE); + COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE); + COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU); + COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU); + COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE); + COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE); cond_branch: f_offset = addrs[i + filter[i].jf]; t_offset = addrs[i + filter[i].jt]; @@ -719,20 +711,20 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; break; } - switch (filter[i].code) { - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JEQ_X: + switch (code) { + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_X: seen |= SEEN_XREG; emit_cmp(r_A, r_X); break; - case BPF_S_JMP_JSET_X: + case BPF_JMP | BPF_JSET | BPF_X: seen |= SEEN_XREG; emit_btst(r_A, r_X); break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGE_K: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: if (is_simm13(K)) { emit_cmpi(r_A, K); } else { @@ -740,7 +732,7 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; emit_cmp(r_A, r_TMP); } break; - case BPF_S_JMP_JSET_K: + case BPF_JMP | BPF_JSET | BPF_K: if (is_simm13(K)) { emit_btsti(r_A, K); } else { diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index d767ff9f59b9..48e4fd0f38e4 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -94,7 +94,7 @@ register unsigned long stack_pointer __asm__("sp"); /* Sit on a nap instruction until interrupted. */ extern void smp_nap(void); -/* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */ +/* Enable interrupts racelessly and nap forever: helper for arch_cpu_idle(). */ extern void _cpu_idle(void); #else /* __ASSEMBLY__ */ diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 74c91729a62a..112ababa9e55 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -228,13 +228,10 @@ early_param("isolnodes", setup_isolnodes); #if defined(CONFIG_PCI) && !defined(__tilegx__) static int __init setup_pci_reserve(char* str) { - unsigned long mb; - - if (str == NULL || strict_strtoul(str, 0, &mb) != 0 || - mb > 3 * 1024) + if (str == NULL || kstrtouint(str, 0, &pci_reserve_mb) != 0 || + pci_reserve_mb > 3 * 1024) return -EINVAL; - pci_reserve_mb = mb; pr_info("Reserving %dMB for PCIE root complex mappings\n", pci_reserve_mb); return 0; @@ -691,7 +688,7 @@ static void __init setup_bootmem_allocator(void) /* Reserve any memory excluded by "memmap" arguments. */ for (i = 0; i < memmap_nr; ++i) { struct memmap_entry *m = &memmap_map[i]; - reserve_bootmem(m->addr, m->size, 0); + reserve_bootmem(m->addr, m->size, BOOTMEM_DEFAULT); } #ifdef CONFIG_BLK_DEV_INITRD @@ -715,7 +712,8 @@ static void __init setup_bootmem_allocator(void) #ifdef CONFIG_KEXEC if (crashk_res.start != crashk_res.end) - reserve_bootmem(crashk_res.start, resource_size(&crashk_res), 0); + reserve_bootmem(crashk_res.start, resource_size(&crashk_res), + BOOTMEM_DEFAULT); #endif } diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c index 2d1dbf38a9ab..d1d026f01267 100644 --- a/arch/tile/kernel/signal.c +++ b/arch/tile/kernel/signal.c @@ -321,14 +321,13 @@ int show_unhandled_signals = 1; static int __init crashinfo(char *str) { - unsigned long val; const char *word; if (*str == '\0') - val = 2; - else if (*str != '=' || strict_strtoul(++str, 0, &val) != 0) + show_unhandled_signals = 2; + else if (*str != '=' || kstrtoint(++str, 0, &show_unhandled_signals) != 0) return 0; - show_unhandled_signals = val; + switch (show_unhandled_signals) { case 0: word = "No"; diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c index 6b603d556ca6..f3ceb6308e42 100644 --- a/arch/tile/kernel/traps.c +++ b/arch/tile/kernel/traps.c @@ -42,10 +42,9 @@ static int __init setup_unaligned_fixup(char *str) * will still parse the instruction, then fire a SIGBUS with * the correct address from inside the single_step code. */ - long val; - if (strict_strtol(str, 0, &val) != 0) + if (kstrtoint(str, 0, &unaligned_fixup) != 0) return 0; - unaligned_fixup = val; + pr_info("Fixups for unaligned data accesses are %s\n", unaligned_fixup >= 0 ? (unaligned_fixup ? "enabled" : "disabled") : diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c index b030b4e78845..c02ea2a45f67 100644 --- a/arch/tile/kernel/unaligned.c +++ b/arch/tile/kernel/unaligned.c @@ -182,18 +182,7 @@ static void find_regs(tilegx_bundle_bits bundle, uint64_t *rd, uint64_t *ra, int i; uint64_t reg; uint64_t reg_map = 0, alias_reg_map = 0, map; - bool alias; - - *ra = -1; - *rb = -1; - - if (rd) - *rd = -1; - - *clob1 = -1; - *clob2 = -1; - *clob3 = -1; - alias = false; + bool alias = false; /* * Parse fault bundle, find potential used registers and mark @@ -569,7 +558,7 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle, tilegx_bundle_bits bundle_2 = 0; /* If bundle_2_enable = false, bundle_2 is fnop/nop operation. */ bool bundle_2_enable = true; - uint64_t ra, rb, rd = -1, clob1, clob2, clob3; + uint64_t ra = -1, rb = -1, rd = -1, clob1 = -1, clob2 = -1, clob3 = -1; /* * Indicate if the unalign access * instruction's registers hit with diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 0fa1acfac79a..bfb3127b4df9 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -273,9 +273,9 @@ static pgprot_t __init init_pgprot(ulong address) /* * Otherwise we just hand out consecutive cpus. To avoid * requiring this function to hold state, we just walk forward from - * _sdata by PAGE_SIZE, skipping the readonly and init data, to reach - * the requested address, while walking cpu home around kdata_mask. - * This is typically no more than a dozen or so iterations. + * __end_rodata by PAGE_SIZE, skipping the readonly and init data, to + * reach the requested address, while walking cpu home around + * kdata_mask. This is typically no more than a dozen or so iterations. */ page = (((ulong)__end_rodata) + PAGE_SIZE - 1) & PAGE_MASK; BUG_ON(address < page || address >= (ulong)_end); @@ -912,7 +912,7 @@ static long __write_once initfree = 1; static int __init set_initfree(char *str) { long val; - if (strict_strtol(str, 0, &val) == 0) { + if (kstrtol(str, 0, &val) == 0) { initfree = val; pr_info("initfree: %s free init pages\n", initfree ? "will" : "won't"); diff --git a/arch/um/Makefile b/arch/um/Makefile index 36e658a4291c..e4b1a9639c4d 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -111,8 +111,7 @@ endef KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig archheaders: - $(Q)$(MAKE) -C '$(srctree)' KBUILD_SRC= \ - ARCH=$(HEADER_ARCH) O='$(objtree)' archheaders + $(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders archprepare: include/generated/user_constants.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b660088c220d..fcefdda5136d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -121,6 +121,7 @@ config X86 select MODULES_USE_ELF_RELA if X86_64 select CLONE_BACKWARDS if X86_32 select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_QUEUE_RWLOCK select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 4582e8e1cd1a..7730c1c5c83a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -57,6 +57,12 @@ .long (from) - . ; \ .long (to) - . + 0x7ffffff0 ; \ .popsection + +# define _ASM_NOKPROBE(entry) \ + .pushsection "_kprobe_blacklist","aw" ; \ + _ASM_ALIGN ; \ + _ASM_PTR (entry); \ + .popsection #else # define _ASM_EXTABLE(from,to) \ " .pushsection \"__ex_table\",\"a\"\n" \ @@ -71,6 +77,7 @@ " .long (" #from ") - .\n" \ " .long (" #to ") - . + 0x7ffffff0\n" \ " .popsection\n" +/* For C file, we already have NOKPROBE_SYMBOL macro */ #endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index e6fd8a026c7b..cd00e1774491 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -184,8 +184,15 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b) asm("addl %2,%0\n\t" "adcl $0,%0" : "=r" (a) - : "0" (a), "r" (b)); + : "0" (a), "rm" (b)); return a; } +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + return (__force __wsum)add32_with_carry((__force unsigned)csum, + (__force unsigned)addend); +} + #endif /* _ASM_X86_CHECKSUM_64_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 9454c167629f..53cdfb2857ab 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -116,4 +116,6 @@ struct kprobe_ctlblk { extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); +extern int kprobe_int3_handler(struct pt_regs *regs); +extern int kprobe_debug_handler(struct pt_regs *regs); #endif /* _ASM_X86_KPROBES_H */ diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h new file mode 100644 index 000000000000..70f46f07f94e --- /dev/null +++ b/arch/x86/include/asm/qrwlock.h @@ -0,0 +1,17 @@ +#ifndef _ASM_X86_QRWLOCK_H +#define _ASM_X86_QRWLOCK_H + +#include + +#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) +#define queue_write_unlock queue_write_unlock +static inline void queue_write_unlock(struct qrwlock *lock) +{ + barrier(); + ACCESS_ONCE(*(u8 *)&lock->cnts) = 0; +} +#endif + +#include + +#endif /* _ASM_X86_QRWLOCK_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 0f62f5482d91..54f1c8068c02 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -187,6 +187,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } +#ifndef CONFIG_QUEUE_RWLOCK /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -269,6 +270,9 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0" : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory"); } +#else +#include +#endif /* CONFIG_QUEUE_RWLOCK */ #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 4f1bea19945b..73c4c007200f 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -34,6 +34,10 @@ typedef struct arch_spinlock { #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } +#ifdef CONFIG_QUEUE_RWLOCK +#include +#else #include +#endif #endif /* _ASM_X86_SPINLOCK_TYPES_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 8ba18842c48e..bc8352e7010a 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -68,7 +68,7 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *); +asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); @@ -103,7 +103,6 @@ static inline int get_si_code(unsigned long condition) extern int panic_on_unrecovered_nmi; -void math_error(struct pt_regs *, int, int); void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 asmlinkage void smp_thermal_interrupt(void); diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 93bee7b93854..74f4c2ff6427 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -41,18 +41,18 @@ struct arch_uprobe { u8 ixol[MAX_UINSN_BYTES]; }; - u16 fixups; const struct uprobe_xol_ops *ops; union { -#ifdef CONFIG_X86_64 - unsigned long rip_rela_target_address; -#endif struct { s32 offs; u8 ilen; u8 opc1; - } branch; + } branch; + struct { + u8 fixups; + u8 ilen; + } defparam; }; }; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index df94598ad05a..703130f469ec 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include @@ -551,7 +550,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, * * Note: Must be called under text_mutex. */ -void *__kprobes text_poke(void *addr, const void *opcode, size_t len) +void *text_poke(void *addr, const void *opcode, size_t len) { unsigned long flags; char *vaddr; diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index eab67047dec3..c3fcb5de5083 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -60,7 +60,7 @@ void arch_trigger_all_cpu_backtrace(void) smp_mb__after_atomic(); } -static int __kprobes +static int arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { int cpu; @@ -80,6 +80,7 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) return NMI_DONE; } +NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); static int __init register_trigger_all_cpu_backtrace(void) { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 9d0a9795a0f8..81e08eff05ee 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2297,7 +2297,7 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, int err; if (!config_enabled(CONFIG_SMP)) - return -1; + return -EPERM; if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -2328,7 +2328,7 @@ int native_ioapic_set_affinity(struct irq_data *data, int ret; if (!config_enabled(CONFIG_SMP)) - return -1; + return -EPERM; raw_spin_lock_irqsave(&ioapic_lock, flags); ret = __ioapic_set_affinity(data, mask, &dest); @@ -3001,9 +3001,11 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; __get_cached_msi_msg(data->msi_desc, &msg); @@ -3100,9 +3102,11 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct msi_msg msg; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; dmar_msi_read(irq, &msg); @@ -3149,9 +3153,11 @@ static int hpet_msi_set_affinity(struct irq_data *data, struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; hpet_msi_read(data->handler_data, &msg); @@ -3218,9 +3224,11 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_cfg *cfg = data->chip_data; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; target_ht_irq(data->irq, dest, cfg->vector); return IRQ_SET_MASK_OK_NOCOPY; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2cbbf88d8f2c..ef1b93f18ed1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -1193,6 +1194,7 @@ int is_debug_stack(unsigned long addr) (addr <= __get_cpu_var(debug_stack_addr) && addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); } +NOKPROBE_SYMBOL(is_debug_stack); DEFINE_PER_CPU(u32, debug_idt_ctr); @@ -1201,6 +1203,7 @@ void debug_stack_set_zero(void) this_cpu_inc(debug_idt_ctr); load_current_idt(); } +NOKPROBE_SYMBOL(debug_stack_set_zero); void debug_stack_reset(void) { @@ -1209,6 +1212,7 @@ void debug_stack_reset(void) if (this_cpu_dec_return(debug_idt_ctr) == 0) load_current_idt(); } +NOKPROBE_SYMBOL(debug_stack_reset); #else /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 76f98fe5b35c..a450373e8e91 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -132,15 +132,6 @@ static void __init ms_hyperv_init_platform(void) lapic_timer_frequency = hv_lapic_frequency; printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); - - /* - * On Hyper-V, when we are booting off an EFI firmware stack, - * we do not have many legacy devices including PIC, PIT etc. - */ - if (efi_enabled(EFI_BOOT)) { - printk(KERN_INFO "HyperV: Using null_legacy_pic\n"); - legacy_pic = &null_legacy_pic; - } } #endif diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 89f3b7c1af20..2bdfbff8a4f6 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -303,15 +303,6 @@ int x86_setup_perfctr(struct perf_event *event) hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); - } else { - /* - * If we have a PMU initialized but no APIC - * interrupts, we cannot sample hardware - * events (user-space has to fall back and - * sample via a hrtimer based software event): - */ - if (!x86_pmu.apic) - return -EOPNOTSUPP; } if (attr->type == PERF_TYPE_RAW) @@ -1293,7 +1284,7 @@ void perf_events_lapic_init(void) apic_write(APIC_LVTPC, APIC_DM_NMI); } -static int __kprobes +static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { u64 start_clock; @@ -1311,6 +1302,7 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) return ret; } +NOKPROBE_SYMBOL(perf_event_nmi_handler); struct event_constraint emptyconstraint; struct event_constraint unconstrained; @@ -1366,6 +1358,15 @@ static void __init pmu_check_apic(void) x86_pmu.apic = 0; pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); pr_info("no hardware sampling interrupt available.\n"); + + /* + * If we have a PMU initialized but no APIC + * interrupts, we cannot sample hardware + * events (user-space has to fall back and + * sample via a hrtimer based software event): + */ + pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + } static struct attribute_group x86_pmu_format_group = { diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 4c36bbe3173a..cbb1be3ed9e4 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -593,7 +593,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) return 1; } -static int __kprobes +static int perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs) { int handled = 0; @@ -606,6 +606,7 @@ perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs) return handled; } +NOKPROBE_SYMBOL(perf_ibs_nmi_handler); static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d82d155aca8c..9dd2459a4c73 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -384,6 +384,9 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_NO_TX) mask |= X86_BR_NO_TX; + if (br_type & PERF_SAMPLE_BRANCH_COND) + mask |= X86_BR_JCC; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -678,6 +681,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { * NHM/WSM erratum: must include IND_JMP to capture IND_CALL */ [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { @@ -689,6 +693,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, }; /* core */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index d9c12d3022a7..b74ebc7c4402 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -200,7 +200,7 @@ static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; static unsigned int die_nest_count; -unsigned __kprobes long oops_begin(void) +unsigned long oops_begin(void) { int cpu; unsigned long flags; @@ -223,8 +223,9 @@ unsigned __kprobes long oops_begin(void) return flags; } EXPORT_SYMBOL_GPL(oops_begin); +NOKPROBE_SYMBOL(oops_begin); -void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) +void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { if (regs && kexec_should_crash(current)) crash_kexec(regs); @@ -247,8 +248,9 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) panic("Fatal exception"); do_exit(signr); } +NOKPROBE_SYMBOL(oops_end); -int __kprobes __die(const char *str, struct pt_regs *regs, long err) +int __die(const char *str, struct pt_regs *regs, long err) { #ifdef CONFIG_X86_32 unsigned short ss; @@ -291,6 +293,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #endif return 0; } +NOKPROBE_SYMBOL(__die); /* * This is gone through when something in the kernel has done something bad diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6cda0baeac9d..2e1a6853e00c 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -419,7 +419,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } -static size_t gen8_stolen_size(int num, int slot, int func) +static size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -429,48 +429,73 @@ static size_t gen8_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static size_t __init chv_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} struct intel_stolen_funcs { size_t (*size)(int num, int slot, int func); u32 (*base)(int num, int slot, int func, size_t size); }; -static const struct intel_stolen_funcs i830_stolen_funcs = { +static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { .base = i830_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i845_stolen_funcs = { +static const struct intel_stolen_funcs i845_stolen_funcs __initconst = { .base = i845_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i85x_stolen_funcs = { +static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = { .base = i85x_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs i865_stolen_funcs = { +static const struct intel_stolen_funcs i865_stolen_funcs __initconst = { .base = i865_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen3_stolen_funcs = { +static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen6_stolen_funcs = { +static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen6_stolen_size, }; -static const struct intel_stolen_funcs gen8_stolen_funcs = { +static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen8_stolen_size, }; -static struct pci_device_id intel_stolen_ids[] __initdata = { +static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { + .base = intel_stolen_base, + .size = chv_stolen_size, +}; + +static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_I830_IDS(&i830_stolen_funcs), INTEL_I845G_IDS(&i845_stolen_funcs), INTEL_I85X_IDS(&i85x_stolen_funcs), @@ -496,7 +521,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_HSW_D_IDS(&gen6_stolen_funcs), INTEL_HSW_M_IDS(&gen6_stolen_funcs), INTEL_BDW_M_IDS(&gen8_stolen_funcs), - INTEL_BDW_D_IDS(&gen8_stolen_funcs) + INTEL_BDW_D_IDS(&gen8_stolen_funcs), + INTEL_CHV_IDS(&chv_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 98313ffaae6a..f0da82b8e634 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -314,10 +314,6 @@ ENTRY(ret_from_kernel_thread) CFI_ENDPROC ENDPROC(ret_from_kernel_thread) -/* - * Interrupt exit functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" /* * Return to user mode is not as complex as all this looks, * but we want the default path for a system call return to @@ -372,10 +368,6 @@ need_resched: END(resume_kernel) #endif CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -495,10 +487,6 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) -/* - * syscall stub including irq exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway @@ -690,10 +678,6 @@ syscall_badsys: jmp resume_userspace END(syscall_badsys) CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection .macro FIXUP_ESPFIX_STACK /* @@ -784,10 +768,6 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC -/* - * Irq entries should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ @@ -964,10 +944,6 @@ ENTRY(spurious_interrupt_bug) jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) -/* - * End of kprobes section - */ - .popsection #ifdef CONFIG_XEN /* Xen doesn't set %esp to be precisely what the normal sysenter @@ -1242,11 +1218,6 @@ return_to_handler: jmp *%ecx #endif -/* - * Some functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" - #ifdef CONFIG_TRACING ENTRY(trace_page_fault) RING0_EC_FRAME @@ -1460,7 +1431,3 @@ ENTRY(async_page_fault) END(async_page_fault) #endif -/* - * End of kprobes section - */ - .popsection diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 48a2644a082a..b25ca969edd2 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -284,8 +284,6 @@ ENDPROC(native_usergs_sysret64) TRACE_IRQS_OFF .endm -/* save complete stack frame */ - .pushsection .kprobes.text, "ax" ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld @@ -314,7 +312,6 @@ ENTRY(save_paranoid) 1: ret CFI_ENDPROC END(save_paranoid) - .popsection /* * A newly forked process directly context switches into this address. @@ -772,10 +769,6 @@ END(interrupt) call \func .endm -/* - * Interrupt entry/exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -982,11 +975,6 @@ END(__do_double_fault) # define __do_double_fault do_double_fault #endif -/* - * End of kprobes section - */ - .popsection - /* * APIC interrupts. */ @@ -1321,11 +1309,6 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler #endif /* CONFIG_HYPERV */ -/* - * Some functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" - idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1 @@ -1742,7 +1725,3 @@ ENTRY(ignore_sysret) CFI_ENDPROC END(ignore_sysret) -/* - * End of kprobes section - */ - .popsection diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a67b47c31314..5f9cf20cdb68 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include @@ -424,7 +423,7 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore); * NOTIFY_STOP returned for all other cases * */ -static int __kprobes hw_breakpoint_handler(struct die_args *args) +static int hw_breakpoint_handler(struct die_args *args) { int i, cpu, rc = NOTIFY_STOP; struct perf_event *bp; @@ -511,7 +510,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_exceptions_notify( +int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) { if (val != DIE_DEBUG) diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 2e977b5d61dd..8af817105e29 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -299,13 +299,31 @@ static void unmask_8259A(void) static void init_8259A(int auto_eoi) { unsigned long flags; + unsigned char probe_val = ~(1 << PIC_CASCADE_IR); + unsigned char new_val; i8259A_auto_eoi = auto_eoi; raw_spin_lock_irqsave(&i8259A_lock, flags); - outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ + /* + * Check to see if we have a PIC. + * Mask all except the cascade and read + * back the value we just wrote. If we don't + * have a PIC, we will read 0xff as opposed to the + * value we wrote. + */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ + outb(probe_val, PIC_MASTER_IMR); + new_val = inb(PIC_MASTER_IMR); + if (new_val != probe_val) { + printk(KERN_INFO "Using NULL legacy PIC\n"); + legacy_pic = &null_legacy_pic; + raw_spin_unlock_irqrestore(&i8259A_lock, flags); + return; + } + + outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ /* * outb_pic - this has to work on a wide range of PC hardware. diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 11ccfb0a63e7..922d28581024 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -365,6 +365,7 @@ void fixup_irqs(void) struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; + int ret; for_each_irq_desc(irq, desc) { int break_affinity = 0; @@ -403,10 +404,14 @@ void fixup_irqs(void) if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); - if (chip->irq_set_affinity) - chip->irq_set_affinity(data, affinity, true); - else if (!(warned++)) - set_affinity = 0; + if (chip->irq_set_affinity) { + ret = chip->irq_set_affinity(data, affinity, true); + if (ret == -ENOSPC) + pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq); + } else { + if (!(warned++)) + set_affinity = 0; + } /* * We unmask if the irq was not marked masked by the diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 61b17dc2c277..7596df664901 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -112,7 +112,8 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); -static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) +static nokprobe_inline void +__synthesize_relative_insn(void *from, void *to, u8 op) { struct __arch_relative_insn { u8 op; @@ -125,21 +126,23 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -void __kprobes synthesize_reljump(void *from, void *to) +void synthesize_reljump(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } +NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ -void __kprobes synthesize_relcall(void *from, void *to) +void synthesize_relcall(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); } +NOKPROBE_SYMBOL(synthesize_relcall); /* * Skip the prefixes of the instruction. */ -static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) +static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) { insn_attr_t attr; @@ -154,12 +157,13 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) #endif return insn; } +NOKPROBE_SYMBOL(skip_prefixes); /* * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int __kprobes can_boost(kprobe_opcode_t *opcodes) +int can_boost(kprobe_opcode_t *opcodes) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; @@ -260,7 +264,7 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add } /* Check if paddr is at an instruction boundary */ -static int __kprobes can_probe(unsigned long paddr) +static int can_probe(unsigned long paddr) { unsigned long addr, __addr, offset = 0; struct insn insn; @@ -299,7 +303,7 @@ static int __kprobes can_probe(unsigned long paddr) /* * Returns non-zero if opcode modifies the interrupt flag. */ -static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) +static int is_IF_modifier(kprobe_opcode_t *insn) { /* Skip prefixes */ insn = skip_prefixes(insn); @@ -322,7 +326,7 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) * If not, return null. * Only applicable to 64-bit x86. */ -int __kprobes __copy_instruction(u8 *dest, u8 *src) +int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; @@ -365,7 +369,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) return insn.length; } -static int __kprobes arch_copy_kprobe(struct kprobe *p) +static int arch_copy_kprobe(struct kprobe *p) { int ret; @@ -392,7 +396,7 @@ static int __kprobes arch_copy_kprobe(struct kprobe *p) return 0; } -int __kprobes arch_prepare_kprobe(struct kprobe *p) +int arch_prepare_kprobe(struct kprobe *p) { if (alternatives_text_reserved(p->addr, p->addr)) return -EINVAL; @@ -407,17 +411,17 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return arch_copy_kprobe(p); } -void __kprobes arch_arm_kprobe(struct kprobe *p) +void arch_arm_kprobe(struct kprobe *p) { text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); } -void __kprobes arch_disarm_kprobe(struct kprobe *p) +void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); } -void __kprobes arch_remove_kprobe(struct kprobe *p) +void arch_remove_kprobe(struct kprobe *p) { if (p->ainsn.insn) { free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); @@ -425,7 +429,8 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) } } -static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +static nokprobe_inline void +save_previous_kprobe(struct kprobe_ctlblk *kcb) { kcb->prev_kprobe.kp = kprobe_running(); kcb->prev_kprobe.status = kcb->kprobe_status; @@ -433,7 +438,8 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags; } -static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +static nokprobe_inline void +restore_previous_kprobe(struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; @@ -441,8 +447,9 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; } -static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static nokprobe_inline void +set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags @@ -451,7 +458,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; } -static void __kprobes clear_btf(void) +static nokprobe_inline void clear_btf(void) { if (test_thread_flag(TIF_BLOCKSTEP)) { unsigned long debugctl = get_debugctlmsr(); @@ -461,7 +468,7 @@ static void __kprobes clear_btf(void) } } -static void __kprobes restore_btf(void) +static nokprobe_inline void restore_btf(void) { if (test_thread_flag(TIF_BLOCKSTEP)) { unsigned long debugctl = get_debugctlmsr(); @@ -471,8 +478,7 @@ static void __kprobes restore_btf(void) } } -void __kprobes -arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) +void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { unsigned long *sara = stack_addr(regs); @@ -481,9 +487,10 @@ arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; } +NOKPROBE_SYMBOL(arch_prepare_kretprobe); -static void __kprobes -setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) +static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) { if (setup_detour_execution(p, regs, reenter)) return; @@ -519,22 +526,24 @@ setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k else regs->ip = (unsigned long)p->ainsn.insn; } +NOKPROBE_SYMBOL(setup_singlestep); /* * We have reentered the kprobe_handler(), since another probe was hit while * within the handler. We save the original kprobes variables and just single * step on the instruction of the new probe without calling any user handlers. */ -static int __kprobes -reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SS: kprobes_inc_nmissed_count(p); setup_singlestep(p, regs, kcb, 1); break; - case KPROBE_HIT_SS: + case KPROBE_REENTER: /* A probe has been hit in the codepath leading up to, or just * after, single-stepping of a probed instruction. This entire * codepath should strictly reside in .kprobes.text section. @@ -553,12 +562,13 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +NOKPROBE_SYMBOL(reenter_kprobe); /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. */ -static int __kprobes kprobe_handler(struct pt_regs *regs) +int kprobe_int3_handler(struct pt_regs *regs) { kprobe_opcode_t *addr; struct kprobe *p; @@ -621,12 +631,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); return 0; } +NOKPROBE_SYMBOL(kprobe_int3_handler); /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. */ -static void __used __kprobes kretprobe_trampoline_holder(void) +static void __used kretprobe_trampoline_holder(void) { asm volatile ( ".global kretprobe_trampoline\n" @@ -657,11 +668,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #endif " ret\n"); } +NOKPROBE_SYMBOL(kretprobe_trampoline_holder); +NOKPROBE_SYMBOL(kretprobe_trampoline); /* * Called from kretprobe_trampoline */ -__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) +__visible __used void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; @@ -747,6 +760,7 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) } return (void *)orig_ret_address; } +NOKPROBE_SYMBOL(trampoline_handler); /* * Called after single-stepping. p->addr is the address of the @@ -775,8 +789,8 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) * jump instruction after the copied instruction, that jumps to the next * instruction after the probepoint. */ -static void __kprobes -resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static void resume_execution(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; @@ -851,12 +865,13 @@ resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k no_change: restore_btf(); } +NOKPROBE_SYMBOL(resume_execution); /* * Interrupts are disabled on entry as trap1 is an interrupt gate and they * remain disabled throughout this function. */ -static int __kprobes post_kprobe_handler(struct pt_regs *regs) +int kprobe_debug_handler(struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -891,8 +906,9 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) return 1; } +NOKPROBE_SYMBOL(kprobe_debug_handler); -int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -949,12 +965,13 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) return 0; } +NOKPROBE_SYMBOL(kprobe_fault_handler); /* * Wrapper routine for handling exceptions. */ -int __kprobes -kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) +int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, + void *data) { struct die_args *args = data; int ret = NOTIFY_DONE; @@ -962,22 +979,7 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d if (args->regs && user_mode_vm(args->regs)) return ret; - switch (val) { - case DIE_INT3: - if (kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_DEBUG: - if (post_kprobe_handler(args->regs)) { - /* - * Reset the BS bit in dr6 (pointed by args->err) to - * denote completion of processing - */ - (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; - ret = NOTIFY_STOP; - } - break; - case DIE_GPF: + if (val == DIE_GPF) { /* * To be potentially processing a kprobe fault and to * trust the result from kprobe_running(), we have @@ -986,14 +988,12 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d if (!preemptible() && kprobe_running() && kprobe_fault_handler(args->regs, args->trapnr)) ret = NOTIFY_STOP; - break; - default: - break; } return ret; } +NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr; @@ -1017,8 +1017,9 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->ip = (unsigned long)(jp->entry); return 1; } +NOKPROBE_SYMBOL(setjmp_pre_handler); -void __kprobes jprobe_return(void) +void jprobe_return(void) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -1034,8 +1035,10 @@ void __kprobes jprobe_return(void) " nop \n"::"b" (kcb->jprobe_saved_sp):"memory"); } +NOKPROBE_SYMBOL(jprobe_return); +NOKPROBE_SYMBOL(jprobe_return_end); -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); @@ -1063,13 +1066,22 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } return 0; } +NOKPROBE_SYMBOL(longjmp_break_handler); + +bool arch_within_kprobe_blacklist(unsigned long addr) +{ + return (addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end) || + (addr >= (unsigned long)__entry_text_start && + addr < (unsigned long)__entry_text_end); +} int __init arch_init_kprobes(void) { return 0; } -int __kprobes arch_trampoline_kprobe(struct kprobe *p) +int arch_trampoline_kprobe(struct kprobe *p) { return 0; } diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 23ef5c556f06..717b02a22e67 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,8 +25,9 @@ #include "common.h" -static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static nokprobe_inline +int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { /* * Emulate singlestep (and also recover regs->ip) @@ -41,18 +42,19 @@ static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, return 1; } -int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { if (kprobe_ftrace(p)) return __skip_singlestep(p, regs, kcb); else return 0; } +NOKPROBE_SYMBOL(skip_singlestep); /* Ftrace callback handler for kprobes */ -void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; @@ -84,8 +86,9 @@ void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, end: local_irq_restore(flags); } +NOKPROBE_SYMBOL(kprobe_ftrace_handler); -int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +int arch_prepare_kprobe_ftrace(struct kprobe *p) { p->ainsn.insn = NULL; p->ainsn.boostable = -1; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 898160b42e43..f304773285ae 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -77,7 +77,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) } /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ -static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) { #ifdef CONFIG_X86_64 *addr++ = 0x48; @@ -138,7 +138,8 @@ asm ( #define INT3_SIZE sizeof(kprobe_opcode_t) /* Optimized kprobe call back function: called from optinsn */ -static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +static void +optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long flags; @@ -168,8 +169,9 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_ } local_irq_restore(flags); } +NOKPROBE_SYMBOL(optimized_callback); -static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +static int copy_optimized_instructions(u8 *dest, u8 *src) { int len = 0, ret; @@ -189,7 +191,7 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether insn is indirect jump */ -static int __kprobes insn_is_indirect_jump(struct insn *insn) +static int insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -224,7 +226,7 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) } /* Decode whole function to ensure any instructions don't jump into target */ -static int __kprobes can_optimize(unsigned long paddr) +static int can_optimize(unsigned long paddr) { unsigned long addr, size = 0, offset = 0; struct insn insn; @@ -275,7 +277,7 @@ static int __kprobes can_optimize(unsigned long paddr) } /* Check optimized_kprobe can actually be optimized. */ -int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +int arch_check_optimized_kprobe(struct optimized_kprobe *op) { int i; struct kprobe *p; @@ -290,15 +292,15 @@ int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) } /* Check the addr is within the optimized instructions. */ -int __kprobes -arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) { return ((unsigned long)op->kp.addr <= addr && (unsigned long)op->kp.addr + op->optinsn.size > addr); } /* Free optimized instruction slot */ -static __kprobes +static void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) { if (op->optinsn.insn) { @@ -308,7 +310,7 @@ void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) } } -void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +void arch_remove_optimized_kprobe(struct optimized_kprobe *op) { __arch_remove_optimized_kprobe(op, 1); } @@ -318,7 +320,7 @@ void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) * Target instructions MUST be relocatable (checked inside) * This is called when new aggr(opt)probe is allocated or reused. */ -int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op) { u8 *buf; int ret; @@ -372,7 +374,7 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. */ -void __kprobes arch_optimize_kprobes(struct list_head *oplist) +void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; u8 insn_buf[RELATIVEJUMP_SIZE]; @@ -398,7 +400,7 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist) } /* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +void arch_unoptimize_kprobe(struct optimized_kprobe *op) { u8 insn_buf[RELATIVEJUMP_SIZE]; @@ -424,8 +426,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, } } -int __kprobes -setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { struct optimized_kprobe *op; @@ -441,3 +442,4 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } +NOKPROBE_SYMBOL(setup_detour_execution); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 7e97371387fd..3dd8e2c4d74a 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -251,8 +251,9 @@ u32 kvm_read_and_reset_pf_reason(void) return reason; } EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); +NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); -dotraplinkage void __kprobes +dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { enum ctx_state prev_state; @@ -276,6 +277,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; } } +NOKPROBE_SYMBOL(do_async_page_fault); static void __init paravirt_ops_setup(void) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index b4872b999a71..c3e985d1751c 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w) a->handler, whole_msecs, decimal_msecs); } -static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -146,6 +146,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 /* return total number of NMI events handled */ return handled; } +NOKPROBE_SYMBOL(nmi_handle); int __register_nmi_handler(unsigned int type, struct nmiaction *action) { @@ -208,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) } EXPORT_SYMBOL_GPL(unregister_nmi_handler); -static __kprobes void +static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ @@ -238,8 +239,9 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(pci_serr_error); -static __kprobes void +static void io_check_error(unsigned char reason, struct pt_regs *regs) { unsigned long i; @@ -269,8 +271,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason &= ~NMI_REASON_CLEAR_IOCHK; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(io_check_error); -static __kprobes void +static void unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { int handled; @@ -298,11 +301,12 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Dazed and confused, but trying to continue\n"); } +NOKPROBE_SYMBOL(unknown_nmi_error); static DEFINE_PER_CPU(bool, swallow_nmi); static DEFINE_PER_CPU(unsigned long, last_nmi_rip); -static __kprobes void default_do_nmi(struct pt_regs *regs) +static void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int handled; @@ -401,6 +405,7 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) else unknown_nmi_error(reason, regs); } +NOKPROBE_SYMBOL(default_do_nmi); /* * NMIs can hit breakpoints which will cause it to lose its @@ -520,7 +525,7 @@ static inline void nmi_nesting_postprocess(void) } #endif -dotraplinkage notrace __kprobes void +dotraplinkage notrace void do_nmi(struct pt_regs *regs, long error_code) { nmi_nesting_preprocess(regs); @@ -537,6 +542,7 @@ do_nmi(struct pt_regs *regs, long error_code) /* On i386, may loop back to preprocess */ nmi_nesting_postprocess(); } +NOKPROBE_SYMBOL(do_nmi); void stop_nmi(void) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 1b10af835c31..548d25f00c90 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -389,6 +390,11 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .end_context_switch = paravirt_nop, }; +/* At this point, native_get/set_debugreg has real function entries */ +NOKPROBE_SYMBOL(native_get_debugreg); +NOKPROBE_SYMBOL(native_set_debugreg); +NOKPROBE_SYMBOL(native_load_idt); + struct pv_apic_ops pv_apic_ops = { #ifdef CONFIG_X86_LOCAL_APIC .startup_ipi_hook = paravirt_nop, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 898d077617a9..ca5b02d405c3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -413,12 +413,11 @@ void set_personality_ia32(bool x32) set_thread_flag(TIF_ADDR32); /* Mark the associated mm as containing 32-bit tasks. */ - if (current->mm) - current->mm->context.ia32_compat = 1; - if (x32) { clear_thread_flag(TIF_IA32); set_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_X32; current->personality &= ~READ_IMPLIES_EXEC; /* is_compat_task() uses the presence of the x32 syscall bit flag to determine compat status */ @@ -426,6 +425,8 @@ void set_personality_ia32(bool x32) } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ current_thread_info()->status |= TS_COMPAT; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f73b5d435bdc..c6eb418c5627 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -106,7 +107,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } -static int __kprobes +static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, struct pt_regs *regs, long error_code) { @@ -136,7 +137,38 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, return -1; } -static void __kprobes +static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr, + siginfo_t *info) +{ + unsigned long siaddr; + int sicode; + + switch (trapnr) { + default: + return SEND_SIG_PRIV; + + case X86_TRAP_DE: + sicode = FPE_INTDIV; + siaddr = uprobe_get_trap_addr(regs); + break; + case X86_TRAP_UD: + sicode = ILL_ILLOPN; + siaddr = uprobe_get_trap_addr(regs); + break; + case X86_TRAP_AC: + sicode = BUS_ADRALN; + siaddr = 0; + break; + } + + info->si_signo = signr; + info->si_errno = 0; + info->si_code = sicode; + info->si_addr = (void __user *)siaddr; + return info; +} + +static void do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, long error_code, siginfo_t *info) { @@ -168,60 +200,43 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, } #endif - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); + force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk); +} +NOKPROBE_SYMBOL(do_trap); + +static void do_error_trap(struct pt_regs *regs, long error_code, char *str, + unsigned long trapnr, int signr) +{ + enum ctx_state prev_state = exception_enter(); + siginfo_t info; + + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != + NOTIFY_STOP) { + conditional_sti(regs); + do_trap(trapnr, signr, str, regs, error_code, + fill_trap_info(regs, signr, trapnr, &info)); + } + + exception_exit(prev_state); } #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - enum ctx_state prev_state; \ - \ - prev_state = exception_enter(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, \ - trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(prev_state); \ - return; \ - } \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, NULL); \ - exception_exit(prev_state); \ + do_error_trap(regs, error_code, str, trapnr, signr); \ } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - siginfo_t info; \ - enum ctx_state prev_state; \ - \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - prev_state = exception_enter(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, \ - trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(prev_state); \ - return; \ - } \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, &info); \ - exception_exit(prev_state); \ -} - -DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip ) -DO_ERROR (X86_TRAP_OF, SIGSEGV, "overflow", overflow ) -DO_ERROR (X86_TRAP_BR, SIGSEGV, "bounds", bounds ) -DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip ) -DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) -DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) -DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) +DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error) +DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) +DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) +DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op) +DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun) +DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) #ifdef CONFIG_X86_32 -DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) +DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) #endif -DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) +DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) #ifdef CONFIG_X86_64 /* Runs on IST stack */ @@ -263,7 +278,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif -dotraplinkage void __kprobes +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; @@ -305,13 +320,14 @@ do_general_protection(struct pt_regs *regs, long error_code) pr_cont("\n"); } - force_sig(SIGSEGV, tsk); + force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_general_protection); /* May run on IST stack. */ -dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) +dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { enum ctx_state prev_state; @@ -327,13 +343,18 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co if (poke_int3_handler(regs)) return; - prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ +#ifdef CONFIG_KPROBES + if (kprobe_int3_handler(regs)) + return; +#endif + prev_state = exception_enter(); + if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) goto exit; @@ -350,6 +371,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* @@ -357,7 +379,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -376,6 +398,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } +NOKPROBE_SYMBOL(sync_regs); #endif /* @@ -402,7 +425,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) * * May run on IST stack. */ -dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) +dotraplinkage void do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; enum ctx_state prev_state; @@ -410,8 +433,6 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; - prev_state = exception_enter(); - get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -440,6 +461,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; +#ifdef CONFIG_KPROBES + if (kprobe_debug_handler(regs)) + goto exit; +#endif + prev_state = exception_enter(); + if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, SIGTRAP) == NOTIFY_STOP) goto exit; @@ -482,13 +509,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_debug); /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous * IRQ13 behaviour */ -void math_error(struct pt_regs *regs, int error_code, int trapnr) +static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; siginfo_t info; @@ -518,7 +546,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) task->thread.error_code = error_code; info.si_signo = SIGFPE; info.si_errno = 0; - info.si_addr = (void __user *)regs->ip; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); if (trapnr == X86_TRAP_MF) { unsigned short cwd, swd; /* @@ -645,7 +673,7 @@ void math_state_restore(void) */ if (unlikely(restore_fpu_checking(tsk))) { drop_init_fpu(tsk); - force_sig(SIGSEGV, tsk); + force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); return; } @@ -653,7 +681,7 @@ void math_state_restore(void) } EXPORT_SYMBOL_GPL(math_state_restore); -dotraplinkage void __kprobes +dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { enum ctx_state prev_state; @@ -679,6 +707,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) #endif exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_device_not_available); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index ace22916ade3..5d1cbfe4ae58 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -32,20 +32,20 @@ /* Post-execution fixups. */ -/* No fixup needed */ -#define UPROBE_FIX_NONE 0x0 - /* Adjust IP back to vicinity of actual insn */ -#define UPROBE_FIX_IP 0x1 +#define UPROBE_FIX_IP 0x01 /* Adjust the return address of a call insn */ -#define UPROBE_FIX_CALL 0x2 +#define UPROBE_FIX_CALL 0x02 /* Instruction will modify TF, don't change it */ -#define UPROBE_FIX_SETF 0x4 +#define UPROBE_FIX_SETF 0x04 -#define UPROBE_FIX_RIP_AX 0x8000 -#define UPROBE_FIX_RIP_CX 0x4000 +#define UPROBE_FIX_RIP_SI 0x08 +#define UPROBE_FIX_RIP_DI 0x10 +#define UPROBE_FIX_RIP_BX 0x20 +#define UPROBE_FIX_RIP_MASK \ + (UPROBE_FIX_RIP_SI | UPROBE_FIX_RIP_DI | UPROBE_FIX_RIP_BX) #define UPROBE_TRAP_NR UINT_MAX @@ -67,6 +67,7 @@ * to keep gcc from statically optimizing it out, as variable_test_bit makes * some versions of gcc to think only *(unsigned long*) is used. */ +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static volatile u32 good_insns_32[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ @@ -89,6 +90,37 @@ static volatile u32 good_insns_32[256 / 32] = { /* ---------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; +#else +#define good_insns_32 NULL +#endif + +/* Good-instruction tables for 64-bit apps */ +#if defined(CONFIG_X86_64) +static volatile u32 good_insns_64[256 / 32] = { + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* ---------------------------------------------- */ + W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */ + W(0x10, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 10 */ + W(0x20, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 20 */ + W(0x30, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 30 */ + W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */ + W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */ + W(0x60, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */ + W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */ + W(0x80, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ + W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ + W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */ + W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */ + W(0xc0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */ + W(0xd0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ + W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */ + W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */ + /* ---------------------------------------------- */ + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ +}; +#else +#define good_insns_64 NULL +#endif /* Using this for both 64-bit and 32-bit apps */ static volatile u32 good_2byte_insns[256 / 32] = { @@ -113,32 +145,6 @@ static volatile u32 good_2byte_insns[256 / 32] = { /* ---------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; - -#ifdef CONFIG_X86_64 -/* Good-instruction tables for 64-bit apps */ -static volatile u32 good_insns_64[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ---------------------------------------------- */ - W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */ - W(0x10, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 10 */ - W(0x20, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 20 */ - W(0x30, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 30 */ - W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */ - W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */ - W(0x60, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */ - W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */ - W(0x80, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ - W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ - W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */ - W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */ - W(0xc0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */ - W(0xd0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ - W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */ - W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */ - /* ---------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; -#endif #undef W /* @@ -209,16 +215,25 @@ static bool is_prefix_bad(struct insn *insn) return false; } -static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) +static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64) { - insn_init(insn, auprobe->insn, false); + u32 volatile *good_insns; + + insn_init(insn, auprobe->insn, x86_64); + /* has the side-effect of processing the entire instruction */ + insn_get_length(insn); + if (WARN_ON_ONCE(!insn_complete(insn))) + return -ENOEXEC; - /* Skip good instruction prefixes; reject "bad" ones. */ - insn_get_opcode(insn); if (is_prefix_bad(insn)) return -ENOTSUPP; - if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_32)) + if (x86_64) + good_insns = good_insns_64; + else + good_insns = good_insns_32; + + if (test_bit(OPCODE1(insn), (unsigned long *)good_insns)) return 0; if (insn->opcode.nbytes == 2) { @@ -230,14 +245,18 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) } #ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return !config_enabled(CONFIG_IA32_EMULATION) || + !(mm->context.ia32_compat == TIF_IA32); +} /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses * its memory operand indirectly through a scratch register. Set - * arch_uprobe->fixups and arch_uprobe->rip_rela_target_address - * accordingly. (The contents of the scratch register will be saved - * before we single-step the modified instruction, and restored - * afterward.) + * defparam->fixups accordingly. (The contents of the scratch register + * will be saved before we single-step the modified instruction, + * and restored afterward). * * We do this because a rip-relative instruction can access only a * relatively small area (+/- 2 GB from the instruction), and the XOL @@ -248,164 +267,192 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) * * Some useful facts about rip-relative instructions: * - * - There's always a modrm byte. + * - There's always a modrm byte with bit layout "00 reg 101". * - There's never a SIB byte. * - The displacement is always 4 bytes. + * - REX.B=1 bit in REX prefix, which normally extends r/m field, + * has no effect on rip-relative mode. It doesn't make modrm byte + * with r/m=101 refer to register 1101 = R13. */ -static void -handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn) +static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) { u8 *cursor; u8 reg; + u8 reg2; if (!insn_rip_relative(insn)) return; /* - * insn_rip_relative() would have decoded rex_prefix, modrm. + * insn_rip_relative() would have decoded rex_prefix, vex_prefix, modrm. * Clear REX.b bit (extension of MODRM.rm field): - * we want to encode rax/rcx, not r8/r9. + * we want to encode low numbered reg, not r8+. */ if (insn->rex_prefix.nbytes) { cursor = auprobe->insn + insn_offset_rex_prefix(insn); - *cursor &= 0xfe; /* Clearing REX.B bit */ + /* REX byte has 0100wrxb layout, clearing REX.b bit */ + *cursor &= 0xfe; + } + /* + * Similar treatment for VEX3 prefix. + * TODO: add XOP/EVEX treatment when insn decoder supports them + */ + if (insn->vex_prefix.nbytes == 3) { + /* + * vex2: c5 rvvvvLpp (has no b bit) + * vex3/xop: c4/8f rxbmmmmm wvvvvLpp + * evex: 62 rxbR00mm wvvvv1pp zllBVaaa + * (evex will need setting of both b and x since + * in non-sib encoding evex.x is 4th bit of MODRM.rm) + * Setting VEX3.b (setting because it has inverted meaning): + */ + cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; + *cursor |= 0x20; } + /* + * Convert from rip-relative addressing to register-relative addressing + * via a scratch register. + * + * This is tricky since there are insns with modrm byte + * which also use registers not encoded in modrm byte: + * [i]div/[i]mul: implicitly use dx:ax + * shift ops: implicitly use cx + * cmpxchg: implicitly uses ax + * cmpxchg8/16b: implicitly uses dx:ax and bx:cx + * Encoding: 0f c7/1 modrm + * The code below thinks that reg=1 (cx), chooses si as scratch. + * mulx: implicitly uses dx: mulx r/m,r1,r2 does r1:r2 = dx * r/m. + * First appeared in Haswell (BMI2 insn). It is vex-encoded. + * Example where none of bx,cx,dx can be used as scratch reg: + * c4 e2 63 f6 0d disp32 mulx disp32(%rip),%ebx,%ecx + * [v]pcmpistri: implicitly uses cx, xmm0 + * [v]pcmpistrm: implicitly uses xmm0 + * [v]pcmpestri: implicitly uses ax, dx, cx, xmm0 + * [v]pcmpestrm: implicitly uses ax, dx, xmm0 + * Evil SSE4.2 string comparison ops from hell. + * maskmovq/[v]maskmovdqu: implicitly uses (ds:rdi) as destination. + * Encoding: 0f f7 modrm, 66 0f f7 modrm, vex-encoded: c5 f9 f7 modrm. + * Store op1, byte-masked by op2 msb's in each byte, to (ds:rdi). + * AMD says it has no 3-operand form (vex.vvvv must be 1111) + * and that it can have only register operands, not mem + * (its modrm byte must have mode=11). + * If these restrictions will ever be lifted, + * we'll need code to prevent selection of di as scratch reg! + * + * Summary: I don't know any insns with modrm byte which + * use SI register implicitly. DI register is used only + * by one insn (maskmovq) and BX register is used + * only by one too (cmpxchg8b). + * BP is stack-segment based (may be a problem?). + * AX, DX, CX are off-limits (many implicit users). + * SP is unusable (it's stack pointer - think about "pop mem"; + * also, rsp+disp32 needs sib encoding -> insn length change). + */ + + reg = MODRM_REG(insn); /* Fetch modrm.reg */ + reg2 = 0xff; /* Fetch vex.vvvv */ + if (insn->vex_prefix.nbytes == 2) + reg2 = insn->vex_prefix.bytes[1]; + else if (insn->vex_prefix.nbytes == 3) + reg2 = insn->vex_prefix.bytes[2]; + /* + * TODO: add XOP, EXEV vvvv reading. + * + * vex.vvvv field is in bits 6-3, bits are inverted. + * But in 32-bit mode, high-order bit may be ignored. + * Therefore, let's consider only 3 low-order bits. + */ + reg2 = ((reg2 >> 3) & 0x7) ^ 0x7; + /* + * Register numbering is ax,cx,dx,bx, sp,bp,si,di, r8..r15. + * + * Choose scratch reg. Order is important: must not select bx + * if we can use si (cmpxchg8b case!) + */ + if (reg != 6 && reg2 != 6) { + reg2 = 6; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_SI; + } else if (reg != 7 && reg2 != 7) { + reg2 = 7; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_DI; + /* TODO (paranoia): force maskmovq to not use di */ + } else { + reg2 = 3; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_BX; + } /* * Point cursor at the modrm byte. The next 4 bytes are the * displacement. Beyond the displacement, for some instructions, * is the immediate operand. */ cursor = auprobe->insn + insn_offset_modrm(insn); - insn_get_length(insn); - /* - * Convert from rip-relative addressing to indirect addressing - * via a scratch register. Change the r/m field from 0x5 (%rip) - * to 0x0 (%rax) or 0x1 (%rcx), and squeeze out the offset field. + * Change modrm from "00 reg 101" to "10 reg reg2". Example: + * 89 05 disp32 mov %eax,disp32(%rip) becomes + * 89 86 disp32 mov %eax,disp32(%rsi) */ - reg = MODRM_REG(insn); - if (reg == 0) { - /* - * The register operand (if any) is either the A register - * (%rax, %eax, etc.) or (if the 0x4 bit is set in the - * REX prefix) %r8. In any case, we know the C register - * is NOT the register operand, so we use %rcx (register - * #1) for the scratch register. - */ - auprobe->fixups = UPROBE_FIX_RIP_CX; - /* Change modrm from 00 000 101 to 00 000 001. */ - *cursor = 0x1; - } else { - /* Use %rax (register #0) for the scratch register. */ - auprobe->fixups = UPROBE_FIX_RIP_AX; - /* Change modrm from 00 xxx 101 to 00 xxx 000 */ - *cursor = (reg << 3); - } + *cursor = 0x80 | (reg << 3) | reg2; +} - /* Target address = address of next instruction + (signed) offset */ - auprobe->rip_rela_target_address = (long)insn->length + insn->displacement.value; - - /* Displacement field is gone; slide immediate field (if any) over. */ - if (insn->immediate.nbytes) { - cursor++; - memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes); - } +static inline unsigned long * +scratch_reg(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_SI) + return ®s->si; + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_DI) + return ®s->di; + return ®s->bx; } /* * If we're emulating a rip-relative instruction, save the contents * of the scratch register and store the target address in that register. */ -static void -pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) +static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if (auprobe->fixups & UPROBE_FIX_RIP_AX) { - autask->saved_scratch_register = regs->ax; - regs->ax = current->utask->vaddr; - regs->ax += auprobe->rip_rela_target_address; - } else if (auprobe->fixups & UPROBE_FIX_RIP_CX) { - autask->saved_scratch_register = regs->cx; - regs->cx = current->utask->vaddr; - regs->cx += auprobe->rip_rela_target_address; + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) { + struct uprobe_task *utask = current->utask; + unsigned long *sr = scratch_reg(auprobe, regs); + + utask->autask.saved_scratch_register = *sr; + *sr = utask->vaddr + auprobe->defparam.ilen; } } -static void -handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) +static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if (auprobe->fixups & (UPROBE_FIX_RIP_AX | UPROBE_FIX_RIP_CX)) { - struct arch_uprobe_task *autask; + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) { + struct uprobe_task *utask = current->utask; + unsigned long *sr = scratch_reg(auprobe, regs); - autask = ¤t->utask->autask; - if (auprobe->fixups & UPROBE_FIX_RIP_AX) - regs->ax = autask->saved_scratch_register; - else - regs->cx = autask->saved_scratch_register; - - /* - * The original instruction includes a displacement, and so - * is 4 bytes longer than what we've just single-stepped. - * Caller may need to apply other fixups to handle stuff - * like "jmpq *...(%rip)" and "callq *...(%rip)". - */ - if (correction) - *correction += 4; + *sr = utask->autask.saved_scratch_register; } } - -static int validate_insn_64bits(struct arch_uprobe *auprobe, struct insn *insn) -{ - insn_init(insn, auprobe->insn, true); - - /* Skip good instruction prefixes; reject "bad" ones. */ - insn_get_opcode(insn); - if (is_prefix_bad(insn)) - return -ENOTSUPP; - - if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_64)) - return 0; - - if (insn->opcode.nbytes == 2) { - if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns)) - return 0; - } - return -ENOTSUPP; -} - -static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) -{ - if (mm->context.ia32_compat) - return validate_insn_32bits(auprobe, insn); - return validate_insn_64bits(auprobe, insn); -} #else /* 32-bit: */ +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return false; +} /* * No RIP-relative addressing on 32-bit */ -static void handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn) +static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) { } -static void pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) +static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { } -static void handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, - long *correction) +static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { } - -static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) -{ - return validate_insn_32bits(auprobe, insn); -} #endif /* CONFIG_X86_64 */ struct uprobe_xol_ops { bool (*emulate)(struct arch_uprobe *, struct pt_regs *); int (*pre_xol)(struct arch_uprobe *, struct pt_regs *); int (*post_xol)(struct arch_uprobe *, struct pt_regs *); + void (*abort)(struct arch_uprobe *, struct pt_regs *); }; static inline int sizeof_long(void) @@ -415,50 +462,67 @@ static inline int sizeof_long(void) static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - pre_xol_rip_insn(auprobe, regs, ¤t->utask->autask); + riprel_pre_xol(auprobe, regs); + return 0; +} + +static int push_ret_address(struct pt_regs *regs, unsigned long ip) +{ + unsigned long new_sp = regs->sp - sizeof_long(); + + if (copy_to_user((void __user *)new_sp, &ip, sizeof_long())) + return -EFAULT; + + regs->sp = new_sp; return 0; } /* - * Adjust the return address pushed by a call insn executed out of line. + * We have to fix things up as follows: + * + * Typically, the new ip is relative to the copied instruction. We need + * to make it relative to the original instruction (FIX_IP). Exceptions + * are return instructions and absolute or indirect jump or call instructions. + * + * If the single-stepped instruction was a call, the return address that + * is atop the stack is the address following the copied instruction. We + * need to make it the address following the original instruction (FIX_CALL). + * + * If the original instruction was a rip-relative instruction such as + * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent + * instruction using a scratch register -- e.g., "movl %edx,0xnnnn(%rsi)". + * We need to restore the contents of the scratch register + * (FIX_RIP_reg). */ -static int adjust_ret_addr(unsigned long sp, long correction) +static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - int rasize = sizeof_long(); - long ra; + struct uprobe_task *utask = current->utask; - if (copy_from_user(&ra, (void __user *)sp, rasize)) - return -EFAULT; - - ra += correction; - if (copy_to_user((void __user *)sp, &ra, rasize)) - return -EFAULT; + riprel_post_xol(auprobe, regs); + if (auprobe->defparam.fixups & UPROBE_FIX_IP) { + long correction = utask->vaddr - utask->xol_vaddr; + regs->ip += correction; + } else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) { + regs->sp += sizeof_long(); /* Pop incorrect return address */ + if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen)) + return -ERESTART; + } + /* popf; tell the caller to not touch TF */ + if (auprobe->defparam.fixups & UPROBE_FIX_SETF) + utask->autask.saved_tf = true; return 0; } -static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - struct uprobe_task *utask = current->utask; - long correction = (long)(utask->vaddr - utask->xol_vaddr); - - handle_riprel_post_xol(auprobe, regs, &correction); - if (auprobe->fixups & UPROBE_FIX_IP) - regs->ip += correction; - - if (auprobe->fixups & UPROBE_FIX_CALL) { - if (adjust_ret_addr(regs->sp, correction)) { - regs->sp += sizeof_long(); - return -ERESTART; - } - } - - return 0; + riprel_post_xol(auprobe, regs); } static struct uprobe_xol_ops default_xol_ops = { .pre_xol = default_pre_xol_op, .post_xol = default_post_xol_op, + .abort = default_abort_op, }; static bool branch_is_call(struct arch_uprobe *auprobe) @@ -520,7 +584,6 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long offs = (long)auprobe->branch.offs; if (branch_is_call(auprobe)) { - unsigned long new_sp = regs->sp - sizeof_long(); /* * If it fails we execute this (mangled, see the comment in * branch_clear_offset) insn out-of-line. In the likely case @@ -530,9 +593,8 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs) * * But there is corner case, see the comment in ->post_xol(). */ - if (copy_to_user((void __user *)new_sp, &new_ip, sizeof_long())) + if (push_ret_address(regs, new_ip)) return false; - regs->sp = new_sp; } else if (!check_jmp_cond(auprobe, regs)) { offs = 0; } @@ -583,11 +645,7 @@ static struct uprobe_xol_ops branch_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); - - /* has the side-effect of processing the entire instruction */ - insn_get_length(insn); - if (WARN_ON_ONCE(!insn_complete(insn))) - return -ENOEXEC; + int i; switch (opc1) { case 0xeb: /* jmp 8 */ @@ -612,6 +670,16 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) return -ENOSYS; } + /* + * 16-bit overrides such as CALLW (66 e8 nn nn) are not supported. + * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. + * No one uses these insns, reject any branch insns with such prefix. + */ + for (i = 0; i < insn->prefixes.nbytes; i++) { + if (insn->prefixes.bytes[i] == 0x66) + return -ENOTSUPP; + } + auprobe->branch.opc1 = opc1; auprobe->branch.ilen = insn->length; auprobe->branch.offs = insn->immediate.value; @@ -630,10 +698,10 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) { struct insn insn; - bool fix_ip = true, fix_call = false; + u8 fix_ip_or_call = UPROBE_FIX_IP; int ret; - ret = validate_insn_bits(auprobe, mm, &insn); + ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm)); if (ret) return ret; @@ -642,44 +710,39 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, return ret; /* - * Figure out which fixups arch_uprobe_post_xol() will need to perform, - * and annotate arch_uprobe->fixups accordingly. To start with, ->fixups - * is either zero or it reflects rip-related fixups. + * Figure out which fixups default_post_xol_op() will need to perform, + * and annotate defparam->fixups accordingly. */ switch (OPCODE1(&insn)) { case 0x9d: /* popf */ - auprobe->fixups |= UPROBE_FIX_SETF; + auprobe->defparam.fixups |= UPROBE_FIX_SETF; break; case 0xc3: /* ret or lret -- ip is correct */ case 0xcb: case 0xc2: case 0xca: - fix_ip = false; + case 0xea: /* jmp absolute -- ip is correct */ + fix_ip_or_call = 0; break; case 0x9a: /* call absolute - Fix return addr, not ip */ - fix_call = true; - fix_ip = false; - break; - case 0xea: /* jmp absolute -- ip is correct */ - fix_ip = false; + fix_ip_or_call = UPROBE_FIX_CALL; break; case 0xff: - insn_get_modrm(&insn); switch (MODRM_REG(&insn)) { case 2: case 3: /* call or lcall, indirect */ - fix_call = true; + fix_ip_or_call = UPROBE_FIX_CALL; + break; case 4: case 5: /* jmp or ljmp, indirect */ - fix_ip = false; + fix_ip_or_call = 0; + break; } /* fall through */ default: - handle_riprel_insn(auprobe, &insn); + riprel_analyze(auprobe, &insn); } - if (fix_ip) - auprobe->fixups |= UPROBE_FIX_IP; - if (fix_call) - auprobe->fixups |= UPROBE_FIX_CALL; + auprobe->defparam.ilen = insn.length; + auprobe->defparam.fixups |= fix_ip_or_call; auprobe->ops = &default_xol_ops; return 0; @@ -694,6 +757,12 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; + if (auprobe->ops->pre_xol) { + int err = auprobe->ops->pre_xol(auprobe, regs); + if (err) + return err; + } + regs->ip = utask->xol_vaddr; utask->autask.saved_trap_nr = current->thread.trap_nr; current->thread.trap_nr = UPROBE_TRAP_NR; @@ -703,8 +772,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) set_task_blockstep(current, false); - if (auprobe->ops->pre_xol) - return auprobe->ops->pre_xol(auprobe, regs); return 0; } @@ -732,56 +799,42 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *t) * single-step, we single-stepped a copy of the instruction. * * This function prepares to resume execution after the single-step. - * We have to fix things up as follows: - * - * Typically, the new ip is relative to the copied instruction. We need - * to make it relative to the original instruction (FIX_IP). Exceptions - * are return instructions and absolute or indirect jump or call instructions. - * - * If the single-stepped instruction was a call, the return address that - * is atop the stack is the address following the copied instruction. We - * need to make it the address following the original instruction (FIX_CALL). - * - * If the original instruction was a rip-relative instruction such as - * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent - * instruction using a scratch register -- e.g., "movl %edx,(%rax)". - * We need to restore the contents of the scratch register and adjust - * the ip, keeping in mind that the instruction we executed is 4 bytes - * shorter than the original instruction (since we squeezed out the offset - * field). (FIX_RIP_AX or FIX_RIP_CX) */ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; + bool send_sigtrap = utask->autask.saved_tf; + int err = 0; WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); + current->thread.trap_nr = utask->autask.saved_trap_nr; if (auprobe->ops->post_xol) { - int err = auprobe->ops->post_xol(auprobe, regs); + err = auprobe->ops->post_xol(auprobe, regs); if (err) { - arch_uprobe_abort_xol(auprobe, regs); /* - * Restart the probed insn. ->post_xol() must ensure - * this is really possible if it returns -ERESTART. + * Restore ->ip for restart or post mortem analysis. + * ->post_xol() must not return -ERESTART unless this + * is really possible. */ + regs->ip = utask->vaddr; if (err == -ERESTART) - return 0; - return err; + err = 0; + send_sigtrap = false; } } - - current->thread.trap_nr = utask->autask.saved_trap_nr; /* * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP * so we can get an extra SIGTRAP if we do not clear TF. We need * to examine the opcode to make it right. */ - if (utask->autask.saved_tf) + if (send_sigtrap) send_sig(SIGTRAP, current, 0); - else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + + if (!utask->autask.saved_tf) regs->flags &= ~X86_EFLAGS_TF; - return 0; + return err; } /* callback routine for handling exceptions. */ @@ -815,18 +868,18 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, /* * This function gets called when XOL instruction either gets trapped or - * the thread has a fatal signal, or if arch_uprobe_post_xol() failed. - * Reset the instruction pointer to its probed address for the potential - * restart or for post mortem analysis. + * the thread has a fatal signal. Reset the instruction pointer to its + * probed address for the potential restart or for post mortem analysis. */ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; - current->thread.trap_nr = utask->autask.saved_trap_nr; - handle_riprel_post_xol(auprobe, regs, NULL); - instruction_pointer_set(regs, utask->vaddr); + if (auprobe->ops->abort) + auprobe->ops->abort(auprobe, regs); + current->thread.trap_nr = utask->autask.saved_trap_nr; + regs->ip = utask->vaddr; /* clear TF if it was set by us in arch_uprobe_pre_xol() */ if (!utask->autask.saved_tf) regs->flags &= ~X86_EFLAGS_TF; diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index 2930ae05d773..28f85c916712 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -4,8 +4,8 @@ * (inspired by Andi Kleen's thunk_64.S) * Subject to the GNU public license, v.2. No warranty of any kind. */ - #include + #include #ifdef CONFIG_TRACE_IRQFLAGS /* put return address in eax (arg1) */ @@ -22,6 +22,7 @@ popl %ecx popl %eax ret + _ASM_NOKPROBE(\name) .endm thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index a63efd6bb6a5..92d9feaff42b 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -8,6 +8,7 @@ #include #include #include +#include /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 @@ -25,6 +26,7 @@ call \func jmp restore CFI_ENDPROC + _ASM_NOKPROBE(\name) .endm #ifdef CONFIG_TRACE_IRQFLAGS @@ -43,3 +45,4 @@ restore: RESTORE_ARGS ret CFI_ENDPROC + _ASM_NOKPROBE(restore) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 858b47b5221b..36642793e315 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -8,7 +8,7 @@ #include /* oops_begin/end, ... */ #include /* search_exception_table */ #include /* max_low_pfn */ -#include /* __kprobes, ... */ +#include /* NOKPROBE_SYMBOL, ... */ #include /* kmmio_handler, ... */ #include /* perf_sw_event */ #include /* hstate_index_to_shift */ @@ -46,7 +46,7 @@ enum x86_pf_error_code { * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ -static inline int __kprobes +static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) @@ -55,7 +55,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int __kprobes kprobes_fault(struct pt_regs *regs) +static nokprobe_inline int kprobes_fault(struct pt_regs *regs) { int ret = 0; @@ -262,7 +262,7 @@ void vmalloc_sync_all(void) * * Handle a fault on the vmalloc or module mapping area */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; @@ -292,6 +292,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); /* * Did it hit the DOS screen memory VA from vm86 mode? @@ -359,7 +360,7 @@ void vmalloc_sync_all(void) * * This assumes no large pages in there. */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; pud_t *pud, *pud_ref; @@ -426,6 +427,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = @@ -928,7 +930,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static noinline __kprobes int +static noinline int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; @@ -976,6 +978,7 @@ spurious_fault(unsigned long error_code, unsigned long address) return ret; } +NOKPROBE_SYMBOL(spurious_fault); int show_unhandled_signals = 1; @@ -1031,7 +1034,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * {,trace_}do_page_fault() have notrace on. Having this an actual function * guarantees there's a function trace entry. */ -static void __kprobes noinline +static noinline void __do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { @@ -1254,8 +1257,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, up_read(&mm->mmap_sem); } +NOKPROBE_SYMBOL(__do_page_fault); -dotraplinkage void __kprobes notrace +dotraplinkage void notrace do_page_fault(struct pt_regs *regs, unsigned long error_code) { unsigned long address = read_cr2(); /* Get the faulting address */ @@ -1273,10 +1277,12 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_page_fault); #ifdef CONFIG_TRACING -static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static nokprobe_inline void +trace_page_fault_entries(unsigned long address, struct pt_regs *regs, + unsigned long error_code) { if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); @@ -1284,7 +1290,7 @@ static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs trace_page_fault_kernel(address, regs, error_code); } -dotraplinkage void __kprobes notrace +dotraplinkage void notrace trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) { /* @@ -1301,4 +1307,5 @@ trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(trace_do_page_fault); #endif /* CONFIG_TRACING */ diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 01495755701b..6440221ced0d 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -12,13 +12,16 @@ /* * Calling convention : - * rdi : skb pointer + * rbx : skb pointer (callee saved) * esi : offset of byte(s) to fetch in skb (can be scratched) - * r8 : copy of skb->data + * r10 : copy of skb->data * r9d : hlen = skb->len - skb->data_len */ -#define SKBDATA %r8 +#define SKBDATA %r10 #define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ +#define MAX_BPF_STACK (512 /* from filter.h */ + \ + 32 /* space for rbx,r13,r14,r15 */ + \ + 8 /* space for skb_copy_bits */) sk_load_word: .globl sk_load_word @@ -68,53 +71,31 @@ sk_load_byte_positive_offset: movzbl (SKBDATA,%rsi),%eax ret -/** - * sk_load_byte_msh - BPF_S_LDX_B_MSH helper - * - * Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf) - * Must preserve A accumulator (%eax) - * Inputs : %esi is the offset value - */ -sk_load_byte_msh: - .globl sk_load_byte_msh - test %esi,%esi - js bpf_slow_path_byte_msh_neg - -sk_load_byte_msh_positive_offset: - .globl sk_load_byte_msh_positive_offset - cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */ - jle bpf_slow_path_byte_msh - movzbl (SKBDATA,%rsi),%ebx - and $15,%bl - shl $2,%bl - ret - /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ - push %rdi; /* save skb */ \ + mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ mov $LEN,%ecx; /* len */ \ - lea -12(%rbp),%rdx; \ + lea - MAX_BPF_STACK + 32(%rbp),%rdx; \ call skb_copy_bits; \ test %eax,%eax; \ pop SKBDATA; \ - pop %r9; \ - pop %rdi + pop %r9; bpf_slow_path_word: bpf_slow_path_common(4) js bpf_error - mov -12(%rbp),%eax + mov - MAX_BPF_STACK + 32(%rbp),%eax bswap %eax ret bpf_slow_path_half: bpf_slow_path_common(2) js bpf_error - mov -12(%rbp),%ax + mov - MAX_BPF_STACK + 32(%rbp),%ax rol $8,%ax movzwl %ax,%eax ret @@ -122,21 +103,11 @@ bpf_slow_path_half: bpf_slow_path_byte: bpf_slow_path_common(1) js bpf_error - movzbl -12(%rbp),%eax - ret - -bpf_slow_path_byte_msh: - xchg %eax,%ebx /* dont lose A , X is about to be scratched */ - bpf_slow_path_common(1) - js bpf_error - movzbl -12(%rbp),%eax - and $15,%al - shl $2,%al - xchg %eax,%ebx + movzbl - MAX_BPF_STACK + 32(%rbp),%eax ret #define sk_negative_common(SIZE) \ - push %rdi; /* save skb */ \ + mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ @@ -145,10 +116,8 @@ bpf_slow_path_byte_msh: test %rax,%rax; \ pop SKBDATA; \ pop %r9; \ - pop %rdi; \ jz bpf_error - bpf_slow_path_word_neg: cmp SKF_MAX_NEG_OFF, %esi /* test range */ jl bpf_error /* offset lower -> error */ @@ -179,22 +148,12 @@ sk_load_byte_negative_offset: movzbl (%rax), %eax ret -bpf_slow_path_byte_msh_neg: - cmp SKF_MAX_NEG_OFF, %esi - jl bpf_error -sk_load_byte_msh_negative_offset: - .globl sk_load_byte_msh_negative_offset - xchg %eax,%ebx /* dont lose A , X is about to be scratched */ - sk_negative_common(1) - movzbl (%rax),%eax - and $15,%al - shl $2,%al - xchg %eax,%ebx - ret - bpf_error: # force a return 0 from jit handler - xor %eax,%eax - mov -8(%rbp),%rbx + xor %eax,%eax + mov - MAX_BPF_STACK(%rbp),%rbx + mov - MAX_BPF_STACK + 8(%rbp),%r13 + mov - MAX_BPF_STACK + 16(%rbp),%r14 + mov - MAX_BPF_STACK + 24(%rbp),%r15 leaveq ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6d5663a599a7..99bef86ed6df 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1,6 +1,7 @@ /* bpf_jit_comp.c : BPF JIT compiler * * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com) + * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -14,28 +15,16 @@ #include #include -/* - * Conventions : - * EAX : BPF A accumulator - * EBX : BPF X accumulator - * RDI : pointer to skb (first argument given to JIT function) - * RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) - * ECX,EDX,ESI : scratch registers - * r9d : skb->len - skb->data_len (headlen) - * r8 : skb->data - * -8(RBP) : saved RBX value - * -16(RBP)..-80(RBP) : BPF_MEMWORDS values - */ int bpf_jit_enable __read_mostly; /* * assembly code in arch/x86/net/bpf_jit.S */ -extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[]; -extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[]; +extern u8 sk_load_byte_positive_offset[]; extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[]; -extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[]; +extern u8 sk_load_byte_negative_offset[]; static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -56,30 +45,44 @@ static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) -#define EMIT1_off32(b1, off) do { EMIT1(b1); EMIT(off, 4);} while (0) - -#define CLEAR_A() EMIT2(0x31, 0xc0) /* xor %eax,%eax */ -#define CLEAR_X() EMIT2(0x31, 0xdb) /* xor %ebx,%ebx */ +#define EMIT1_off32(b1, off) \ + do {EMIT1(b1); EMIT(off, 4); } while (0) +#define EMIT2_off32(b1, b2, off) \ + do {EMIT2(b1, b2); EMIT(off, 4); } while (0) +#define EMIT3_off32(b1, b2, b3, off) \ + do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) +#define EMIT4_off32(b1, b2, b3, b4, off) \ + do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) static inline bool is_imm8(int value) { return value <= 127 && value >= -128; } -static inline bool is_near(int offset) +static inline bool is_simm32(s64 value) { - return offset <= 127 && offset >= -128; + return value == (s64) (s32) value; } -#define EMIT_JMP(offset) \ -do { \ - if (offset) { \ - if (is_near(offset)) \ - EMIT2(0xeb, offset); /* jmp .+off8 */ \ - else \ - EMIT1_off32(0xe9, offset); /* jmp .+off32 */ \ - } \ -} while (0) +/* mov dst, src */ +#define EMIT_mov(DST, SRC) \ + do {if (DST != SRC) \ + EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \ + } while (0) + +static int bpf_size_to_x86_bytes(int bpf_size) +{ + if (bpf_size == BPF_W) + return 4; + else if (bpf_size == BPF_H) + return 2; + else if (bpf_size == BPF_B) + return 1; + else if (bpf_size == BPF_DW) + return 4; /* imm32 */ + else + return 0; +} /* list of x86 cond jumps opcodes (. + s8) * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32) @@ -90,27 +93,8 @@ do { \ #define X86_JNE 0x75 #define X86_JBE 0x76 #define X86_JA 0x77 - -#define EMIT_COND_JMP(op, offset) \ -do { \ - if (is_near(offset)) \ - EMIT2(op, offset); /* jxx .+off8 */ \ - else { \ - EMIT2(0x0f, op + 0x10); \ - EMIT(offset, 4); /* jxx .+off32 */ \ - } \ -} while (0) - -#define COND_SEL(CODE, TOP, FOP) \ - case CODE: \ - t_op = TOP; \ - f_op = FOP; \ - goto cond_branch - - -#define SEEN_DATAREF 1 /* might call external helpers */ -#define SEEN_XREG 2 /* ebx is used */ -#define SEEN_MEM 4 /* use mem[] for temporary storage */ +#define X86_JGE 0x7D +#define X86_JG 0x7F static inline void bpf_flush_icache(void *start, void *end) { @@ -125,26 +109,6 @@ static inline void bpf_flush_icache(void *start, void *end) #define CHOOSE_LOAD_FUNC(K, func) \ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) -/* Helper to find the offset of pkt_type in sk_buff - * We want to make sure its still a 3bit field starting at a byte boundary. - */ -#define PKT_TYPE_MAX 7 -static int pkt_type_offset(void) -{ - struct sk_buff skb_probe = { - .pkt_type = ~0, - }; - char *ct = (char *)&skb_probe; - unsigned int off; - - for (off = 0; off < sizeof(struct sk_buff); off++) { - if (ct[off] == PKT_TYPE_MAX) - return off; - } - pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n"); - return -1; -} - struct bpf_binary_header { unsigned int pages; /* Note : for security reasons, bpf code will follow a randomly @@ -178,583 +142,771 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen, return header; } -void bpf_jit_compile(struct sk_filter *fp) +/* pick a register outside of BPF range for JIT internal work */ +#define AUX_REG (MAX_BPF_REG + 1) + +/* the following table maps BPF registers to x64 registers. + * x64 register r12 is unused, since if used as base address register + * in load/store instructions, it always needs an extra byte of encoding + */ +static const int reg2hex[] = { + [BPF_REG_0] = 0, /* rax */ + [BPF_REG_1] = 7, /* rdi */ + [BPF_REG_2] = 6, /* rsi */ + [BPF_REG_3] = 2, /* rdx */ + [BPF_REG_4] = 1, /* rcx */ + [BPF_REG_5] = 0, /* r8 */ + [BPF_REG_6] = 3, /* rbx callee saved */ + [BPF_REG_7] = 5, /* r13 callee saved */ + [BPF_REG_8] = 6, /* r14 callee saved */ + [BPF_REG_9] = 7, /* r15 callee saved */ + [BPF_REG_FP] = 5, /* rbp readonly */ + [AUX_REG] = 3, /* r11 temp register */ +}; + +/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15 + * which need extra byte of encoding. + * rax,rcx,...,rbp have simpler encoding + */ +static inline bool is_ereg(u32 reg) { - u8 temp[64]; - u8 *prog; - unsigned int proglen, oldproglen = 0; - int ilen, i; - int t_offset, f_offset; - u8 t_op, f_op, seen = 0, pass; - u8 *image = NULL; - struct bpf_binary_header *header = NULL; - u8 *func; - int pc_ret0 = -1; /* bpf index of first RET #0 instruction (if any) */ + if (reg == BPF_REG_5 || reg == AUX_REG || + (reg >= BPF_REG_7 && reg <= BPF_REG_9)) + return true; + else + return false; +} + +/* add modifiers if 'reg' maps to x64 registers r8..r15 */ +static inline u8 add_1mod(u8 byte, u32 reg) +{ + if (is_ereg(reg)) + byte |= 1; + return byte; +} + +static inline u8 add_2mod(u8 byte, u32 r1, u32 r2) +{ + if (is_ereg(r1)) + byte |= 1; + if (is_ereg(r2)) + byte |= 4; + return byte; +} + +/* encode 'dst_reg' register into x64 opcode 'byte' */ +static inline u8 add_1reg(u8 byte, u32 dst_reg) +{ + return byte + reg2hex[dst_reg]; +} + +/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */ +static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) +{ + return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); +} + +struct jit_context { unsigned int cleanup_addr; /* epilogue code offset */ - unsigned int *addrs; - const struct sock_filter *filter = fp->insns; - int flen = fp->len; + bool seen_ld_abs; +}; + +static int do_jit(struct sk_filter *bpf_prog, int *addrs, u8 *image, + int oldproglen, struct jit_context *ctx) +{ + struct sock_filter_int *insn = bpf_prog->insnsi; + int insn_cnt = bpf_prog->len; + u8 temp[64]; + int i; + int proglen = 0; + u8 *prog = temp; + int stacksize = MAX_BPF_STACK + + 32 /* space for rbx, r13, r14, r15 */ + + 8 /* space for skb_copy_bits() buffer */; + + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ + + /* sub rsp, stacksize */ + EMIT3_off32(0x48, 0x81, 0xEC, stacksize); + + /* all classic BPF filters use R6(rbx) save it */ + + /* mov qword ptr [rbp-X],rbx */ + EMIT3_off32(0x48, 0x89, 0x9D, -stacksize); + + /* sk_convert_filter() maps classic BPF register X to R7 and uses R8 + * as temporary, so all tcpdump filters need to spill/fill R7(r13) and + * R8(r14). R9(r15) spill could be made conditional, but there is only + * one 'bpf_error' return path out of helper functions inside bpf_jit.S + * The overhead of extra spill is negligible for any filter other + * than synthetic ones. Therefore not worth adding complexity. + */ + + /* mov qword ptr [rbp-X],r13 */ + EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8); + /* mov qword ptr [rbp-X],r14 */ + EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16); + /* mov qword ptr [rbp-X],r15 */ + EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24); + + /* clear A and X registers */ + EMIT2(0x31, 0xc0); /* xor eax, eax */ + EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ + + if (ctx->seen_ld_abs) { + /* r9d : skb->len - skb->data_len (headlen) + * r10 : skb->data + */ + if (is_imm8(offsetof(struct sk_buff, len))) + /* mov %r9d, off8(%rdi) */ + EMIT4(0x44, 0x8b, 0x4f, + offsetof(struct sk_buff, len)); + else + /* mov %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x8b, 0x8f, + offsetof(struct sk_buff, len)); + + if (is_imm8(offsetof(struct sk_buff, data_len))) + /* sub %r9d, off8(%rdi) */ + EMIT4(0x44, 0x2b, 0x4f, + offsetof(struct sk_buff, data_len)); + else + EMIT3_off32(0x44, 0x2b, 0x8f, + offsetof(struct sk_buff, data_len)); + + if (is_imm8(offsetof(struct sk_buff, data))) + /* mov %r10, off8(%rdi) */ + EMIT4(0x4c, 0x8b, 0x57, + offsetof(struct sk_buff, data)); + else + /* mov %r10, off32(%rdi) */ + EMIT3_off32(0x4c, 0x8b, 0x97, + offsetof(struct sk_buff, data)); + } + + for (i = 0; i < insn_cnt; i++, insn++) { + const s32 imm32 = insn->imm; + u32 dst_reg = insn->dst_reg; + u32 src_reg = insn->src_reg; + u8 b1 = 0, b2 = 0, b3 = 0; + s64 jmp_offset; + u8 jmp_cond; + int ilen; + u8 *func; + + switch (insn->code) { + /* ALU */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + switch (BPF_OP(insn->code)) { + case BPF_ADD: b2 = 0x01; break; + case BPF_SUB: b2 = 0x29; break; + case BPF_AND: b2 = 0x21; break; + case BPF_OR: b2 = 0x09; break; + case BPF_XOR: b2 = 0x31; break; + } + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_2mod(0x48, dst_reg, src_reg)); + else if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); + break; + + /* mov dst, src */ + case BPF_ALU64 | BPF_MOV | BPF_X: + EMIT_mov(dst_reg, src_reg); + break; + + /* mov32 dst, src */ + case BPF_ALU | BPF_MOV | BPF_X: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + break; + + /* neg dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT2(0xF7, add_1reg(0xD8, dst_reg)); + break; + + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + + switch (BPF_OP(insn->code)) { + case BPF_ADD: b3 = 0xC0; break; + case BPF_SUB: b3 = 0xE8; break; + case BPF_AND: b3 = 0xE0; break; + case BPF_OR: b3 = 0xC8; break; + case BPF_XOR: b3 = 0xF0; break; + } + + if (is_imm8(imm32)) + EMIT3(0x83, add_1reg(b3, dst_reg), imm32); + else + EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32); + break; + + case BPF_ALU64 | BPF_MOV | BPF_K: + /* optimization: if imm32 is positive, + * use 'mov eax, imm32' (which zero-extends imm32) + * to save 2 bytes + */ + if (imm32 < 0) { + /* 'mov rax, imm32' sign extends imm32 */ + b1 = add_1mod(0x48, dst_reg); + b2 = 0xC7; + b3 = 0xC0; + EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); + break; + } + + case BPF_ALU | BPF_MOV | BPF_K: + /* mov %eax, imm32 */ + if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); + break; + + /* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */ + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_K: + EMIT1(0x50); /* push rax */ + EMIT1(0x52); /* push rdx */ + + if (BPF_SRC(insn->code) == BPF_X) + /* mov r11, src_reg */ + EMIT_mov(AUX_REG, src_reg); + else + /* mov r11, imm32 */ + EMIT3_off32(0x49, 0xC7, 0xC3, imm32); + + /* mov rax, dst_reg */ + EMIT_mov(BPF_REG_0, dst_reg); + + /* xor edx, edx + * equivalent to 'xor rdx, rdx', but one byte less + */ + EMIT2(0x31, 0xd2); + + if (BPF_SRC(insn->code) == BPF_X) { + /* if (src_reg == 0) return 0 */ + + /* cmp r11, 0 */ + EMIT4(0x49, 0x83, 0xFB, 0x00); + + /* jne .+9 (skip over pop, pop, xor and jmp) */ + EMIT2(X86_JNE, 1 + 1 + 2 + 5); + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + EMIT2(0x31, 0xc0); /* xor eax, eax */ + + /* jmp cleanup_addr + * addrs[i] - 11, because there are 11 bytes + * after this insn: div, mov, pop, pop, mov + */ + jmp_offset = ctx->cleanup_addr - (addrs[i] - 11); + EMIT1_off32(0xE9, jmp_offset); + } + + if (BPF_CLASS(insn->code) == BPF_ALU64) + /* div r11 */ + EMIT3(0x49, 0xF7, 0xF3); + else + /* div r11d */ + EMIT3(0x41, 0xF7, 0xF3); + + if (BPF_OP(insn->code) == BPF_MOD) + /* mov r11, rdx */ + EMIT3(0x49, 0x89, 0xD3); + else + /* mov r11, rax */ + EMIT3(0x49, 0x89, 0xC3); + + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + + /* mov dst_reg, r11 */ + EMIT_mov(dst_reg, AUX_REG); + break; + + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + case BPF_ALU64 | BPF_MUL | BPF_X: + EMIT1(0x50); /* push rax */ + EMIT1(0x52); /* push rdx */ + + /* mov r11, dst_reg */ + EMIT_mov(AUX_REG, dst_reg); + + if (BPF_SRC(insn->code) == BPF_X) + /* mov rax, src_reg */ + EMIT_mov(BPF_REG_0, src_reg); + else + /* mov rax, imm32 */ + EMIT3_off32(0x48, 0xC7, 0xC0, imm32); + + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, AUX_REG)); + else if (is_ereg(AUX_REG)) + EMIT1(add_1mod(0x40, AUX_REG)); + /* mul(q) r11 */ + EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); + + /* mov r11, rax */ + EMIT_mov(AUX_REG, BPF_REG_0); + + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + + /* mov dst_reg, r11 */ + EMIT_mov(dst_reg, AUX_REG); + break; + + /* shifts */ + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + + switch (BPF_OP(insn->code)) { + case BPF_LSH: b3 = 0xE0; break; + case BPF_RSH: b3 = 0xE8; break; + case BPF_ARSH: b3 = 0xF8; break; + } + EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); + break; + + case BPF_ALU | BPF_END | BPF_FROM_BE: + switch (imm32) { + case 16: + /* emit 'ror %ax, 8' to swap lower 2 bytes */ + EMIT1(0x66); + if (is_ereg(dst_reg)) + EMIT1(0x41); + EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); + break; + case 32: + /* emit 'bswap eax' to swap lower 4 bytes */ + if (is_ereg(dst_reg)) + EMIT2(0x41, 0x0F); + else + EMIT1(0x0F); + EMIT1(add_1reg(0xC8, dst_reg)); + break; + case 64: + /* emit 'bswap rax' to swap 8 bytes */ + EMIT3(add_1mod(0x48, dst_reg), 0x0F, + add_1reg(0xC8, dst_reg)); + break; + } + break; + + case BPF_ALU | BPF_END | BPF_FROM_LE: + break; + + /* ST: *(u8*)(dst_reg + off) = imm */ + case BPF_ST | BPF_MEM | BPF_B: + if (is_ereg(dst_reg)) + EMIT2(0x41, 0xC6); + else + EMIT1(0xC6); + goto st; + case BPF_ST | BPF_MEM | BPF_H: + if (is_ereg(dst_reg)) + EMIT3(0x66, 0x41, 0xC7); + else + EMIT2(0x66, 0xC7); + goto st; + case BPF_ST | BPF_MEM | BPF_W: + if (is_ereg(dst_reg)) + EMIT2(0x41, 0xC7); + else + EMIT1(0xC7); + goto st; + case BPF_ST | BPF_MEM | BPF_DW: + EMIT2(add_1mod(0x48, dst_reg), 0xC7); + +st: if (is_imm8(insn->off)) + EMIT2(add_1reg(0x40, dst_reg), insn->off); + else + EMIT1_off32(add_1reg(0x80, dst_reg), insn->off); + + EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code))); + break; + + /* STX: *(u8*)(dst_reg + off) = src_reg */ + case BPF_STX | BPF_MEM | BPF_B: + /* emit 'mov byte ptr [rax + off], al' */ + if (is_ereg(dst_reg) || is_ereg(src_reg) || + /* have to add extra byte for x86 SIL, DIL regs */ + src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); + else + EMIT1(0x88); + goto stx; + case BPF_STX | BPF_MEM | BPF_H: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT2(0x66, 0x89); + goto stx; + case BPF_STX | BPF_MEM | BPF_W: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT1(0x89); + goto stx; + case BPF_STX | BPF_MEM | BPF_DW: + EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); +stx: if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), + insn->off); + break; + + /* LDX: dst_reg = *(u8*)(src_reg + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + /* emit 'movzx rax, byte ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_H: + /* emit 'movzx rax, word ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_W: + /* emit 'mov eax, dword ptr [rax+0x14]' */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); + else + EMIT1(0x8B); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_DW: + /* emit 'mov rax, qword ptr [rax+0x14]' */ + EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); +ldx: /* if insn->off == 0 we can save one extra byte, but + * special case of x86 r13 which always needs an offset + * is not worth the hassle + */ + if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), + insn->off); + break; + + /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ + case BPF_STX | BPF_XADD | BPF_W: + /* emit 'lock add dword ptr [rax + off], eax' */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01); + else + EMIT2(0xF0, 0x01); + goto xadd; + case BPF_STX | BPF_XADD | BPF_DW: + EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01); +xadd: if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), + insn->off); + break; + + /* call */ + case BPF_JMP | BPF_CALL: + func = (u8 *) __bpf_call_base + imm32; + jmp_offset = func - (image + addrs[i]); + if (ctx->seen_ld_abs) { + EMIT2(0x41, 0x52); /* push %r10 */ + EMIT2(0x41, 0x51); /* push %r9 */ + /* need to adjust jmp offset, since + * pop %r9, pop %r10 take 4 bytes after call insn + */ + jmp_offset += 4; + } + if (!imm32 || !is_simm32(jmp_offset)) { + pr_err("unsupported bpf func %d addr %p image %p\n", + imm32, func, image); + return -EINVAL; + } + EMIT1_off32(0xE8, jmp_offset); + if (ctx->seen_ld_abs) { + EMIT2(0x41, 0x59); /* pop %r9 */ + EMIT2(0x41, 0x5A); /* pop %r10 */ + } + break; + + /* cond jump */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + /* cmp dst_reg, src_reg */ + EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39, + add_2reg(0xC0, dst_reg, src_reg)); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JSET | BPF_X: + /* test dst_reg, src_reg */ + EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85, + add_2reg(0xC0, dst_reg, src_reg)); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JSET | BPF_K: + /* test dst_reg, imm32 */ + EMIT1(add_1mod(0x48, dst_reg)); + EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: + /* cmp dst_reg, imm8/32 */ + EMIT1(add_1mod(0x48, dst_reg)); + + if (is_imm8(imm32)) + EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32); + else + EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32); + +emit_cond_jmp: /* convert BPF opcode to x86 */ + switch (BPF_OP(insn->code)) { + case BPF_JEQ: + jmp_cond = X86_JE; + break; + case BPF_JSET: + case BPF_JNE: + jmp_cond = X86_JNE; + break; + case BPF_JGT: + /* GT is unsigned '>', JA in x86 */ + jmp_cond = X86_JA; + break; + case BPF_JGE: + /* GE is unsigned '>=', JAE in x86 */ + jmp_cond = X86_JAE; + break; + case BPF_JSGT: + /* signed '>', GT in x86 */ + jmp_cond = X86_JG; + break; + case BPF_JSGE: + /* signed '>=', GE in x86 */ + jmp_cond = X86_JGE; + break; + default: /* to silence gcc warning */ + return -EFAULT; + } + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (is_imm8(jmp_offset)) { + EMIT2(jmp_cond, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); + } else { + pr_err("cond_jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + + break; + + case BPF_JMP | BPF_JA: + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (!jmp_offset) + /* optimize out nop jumps */ + break; +emit_jmp: + if (is_imm8(jmp_offset)) { + EMIT2(0xEB, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT1_off32(0xE9, jmp_offset); + } else { + pr_err("jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + break; + + case BPF_LD | BPF_IND | BPF_W: + func = sk_load_word; + goto common_load; + case BPF_LD | BPF_ABS | BPF_W: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_word); +common_load: ctx->seen_ld_abs = true; + jmp_offset = func - (image + addrs[i]); + if (!func || !is_simm32(jmp_offset)) { + pr_err("unsupported bpf func %d addr %p image %p\n", + imm32, func, image); + return -EINVAL; + } + if (BPF_MODE(insn->code) == BPF_ABS) { + /* mov %esi, imm32 */ + EMIT1_off32(0xBE, imm32); + } else { + /* mov %rsi, src_reg */ + EMIT_mov(BPF_REG_2, src_reg); + if (imm32) { + if (is_imm8(imm32)) + /* add %esi, imm8 */ + EMIT3(0x83, 0xC6, imm32); + else + /* add %esi, imm32 */ + EMIT2_off32(0x81, 0xC6, imm32); + } + } + /* skb pointer is in R6 (%rbx), it will be copied into + * %rdi if skb_copy_bits() call is necessary. + * sk_load_* helpers also use %r10 and %r9d. + * See bpf_jit.S + */ + EMIT1_off32(0xE8, jmp_offset); /* call */ + break; + + case BPF_LD | BPF_IND | BPF_H: + func = sk_load_half; + goto common_load; + case BPF_LD | BPF_ABS | BPF_H: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_half); + goto common_load; + case BPF_LD | BPF_IND | BPF_B: + func = sk_load_byte; + goto common_load; + case BPF_LD | BPF_ABS | BPF_B: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte); + goto common_load; + + case BPF_JMP | BPF_EXIT: + if (i != insn_cnt - 1) { + jmp_offset = ctx->cleanup_addr - addrs[i]; + goto emit_jmp; + } + /* update cleanup_addr */ + ctx->cleanup_addr = proglen; + /* mov rbx, qword ptr [rbp-X] */ + EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize); + /* mov r13, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8); + /* mov r14, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16); + /* mov r15, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24); + + EMIT1(0xC9); /* leave */ + EMIT1(0xC3); /* ret */ + break; + + default: + /* By design x64 JIT should support all BPF instructions + * This error will be seen if new instruction was added + * to interpreter, but not to JIT + * or if there is junk in sk_filter + */ + pr_err("bpf_jit: unknown opcode %02x\n", insn->code); + return -EINVAL; + } + + ilen = prog - temp; + if (image) { + if (unlikely(proglen + ilen > oldproglen)) { + pr_err("bpf_jit_compile fatal error\n"); + return -EFAULT; + } + memcpy(image + proglen, temp, ilen); + } + proglen += ilen; + addrs[i] = proglen; + prog = temp; + } + return proglen; +} + +void bpf_jit_compile(struct sk_filter *prog) +{ +} + +void bpf_int_jit_compile(struct sk_filter *prog) +{ + struct bpf_binary_header *header = NULL; + int proglen, oldproglen = 0; + struct jit_context ctx = {}; + u8 *image = NULL; + int *addrs; + int pass; + int i; if (!bpf_jit_enable) return; - addrs = kmalloc(flen * sizeof(*addrs), GFP_KERNEL); - if (addrs == NULL) + if (!prog || !prog->len) + return; + + addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL); + if (!addrs) return; /* Before first pass, make a rough estimation of addrs[] * each bpf instruction is translated to less than 64 bytes */ - for (proglen = 0, i = 0; i < flen; i++) { + for (proglen = 0, i = 0; i < prog->len; i++) { proglen += 64; addrs[i] = proglen; } - cleanup_addr = proglen; /* epilogue address */ + ctx.cleanup_addr = proglen; for (pass = 0; pass < 10; pass++) { - u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; - /* no prologue/epilogue for trivial filters (RET something) */ - proglen = 0; - prog = temp; - - if (seen_or_pass0) { - EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */ - EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */ - /* note : must save %rbx in case bpf_error is hit */ - if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF)) - EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */ - if (seen_or_pass0 & SEEN_XREG) - CLEAR_X(); /* make sure we dont leek kernel memory */ - - /* - * If this filter needs to access skb data, - * loads r9 and r8 with : - * r9 = skb->len - skb->data_len - * r8 = skb->data - */ - if (seen_or_pass0 & SEEN_DATAREF) { - if (offsetof(struct sk_buff, len) <= 127) - /* mov off8(%rdi),%r9d */ - EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len)); - else { - /* mov off32(%rdi),%r9d */ - EMIT3(0x44, 0x8b, 0x8f); - EMIT(offsetof(struct sk_buff, len), 4); - } - if (is_imm8(offsetof(struct sk_buff, data_len))) - /* sub off8(%rdi),%r9d */ - EMIT4(0x44, 0x2b, 0x4f, offsetof(struct sk_buff, data_len)); - else { - EMIT3(0x44, 0x2b, 0x8f); - EMIT(offsetof(struct sk_buff, data_len), 4); - } - - if (is_imm8(offsetof(struct sk_buff, data))) - /* mov off8(%rdi),%r8 */ - EMIT4(0x4c, 0x8b, 0x47, offsetof(struct sk_buff, data)); - else { - /* mov off32(%rdi),%r8 */ - EMIT3(0x4c, 0x8b, 0x87); - EMIT(offsetof(struct sk_buff, data), 4); - } - } + proglen = do_jit(prog, addrs, image, oldproglen, &ctx); + if (proglen <= 0) { + image = NULL; + if (header) + module_free(NULL, header); + goto out; } - - switch (filter[0].code) { - case BPF_S_RET_K: - case BPF_S_LD_W_LEN: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_CPU: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_QUEUE: - case BPF_S_ANC_PKTTYPE: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - /* first instruction sets A register (or is RET 'constant') */ - break; - default: - /* make sure we dont leak kernel information to user */ - CLEAR_A(); /* A = 0 */ - } - - for (i = 0; i < flen; i++) { - unsigned int K = filter[i].k; - - switch (filter[i].code) { - case BPF_S_ALU_ADD_X: /* A += X; */ - seen |= SEEN_XREG; - EMIT2(0x01, 0xd8); /* add %ebx,%eax */ - break; - case BPF_S_ALU_ADD_K: /* A += K; */ - if (!K) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xc0, K); /* add imm8,%eax */ - else - EMIT1_off32(0x05, K); /* add imm32,%eax */ - break; - case BPF_S_ALU_SUB_X: /* A -= X; */ - seen |= SEEN_XREG; - EMIT2(0x29, 0xd8); /* sub %ebx,%eax */ - break; - case BPF_S_ALU_SUB_K: /* A -= K */ - if (!K) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xe8, K); /* sub imm8,%eax */ - else - EMIT1_off32(0x2d, K); /* sub imm32,%eax */ - break; - case BPF_S_ALU_MUL_X: /* A *= X; */ - seen |= SEEN_XREG; - EMIT3(0x0f, 0xaf, 0xc3); /* imul %ebx,%eax */ - break; - case BPF_S_ALU_MUL_K: /* A *= K */ - if (is_imm8(K)) - EMIT3(0x6b, 0xc0, K); /* imul imm8,%eax,%eax */ - else { - EMIT2(0x69, 0xc0); /* imul imm32,%eax */ - EMIT(K, 4); - } - break; - case BPF_S_ALU_DIV_X: /* A /= X; */ - seen |= SEEN_XREG; - EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 > 0) { - /* addrs[pc_ret0 - 1] is start address of target - * (addrs[i] - 4) is the address following this jmp - * ("xor %edx,%edx; div %ebx" being 4 bytes long) - */ - EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - - (addrs[i] - 4)); - } else { - EMIT_COND_JMP(X86_JNE, 2 + 5); - CLEAR_A(); - EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */ - } - EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */ - break; - case BPF_S_ALU_MOD_X: /* A %= X; */ - seen |= SEEN_XREG; - EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 > 0) { - /* addrs[pc_ret0 - 1] is start address of target - * (addrs[i] - 6) is the address following this jmp - * ("xor %edx,%edx; div %ebx;mov %edx,%eax" being 6 bytes long) - */ - EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - - (addrs[i] - 6)); - } else { - EMIT_COND_JMP(X86_JNE, 2 + 5); - CLEAR_A(); - EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 6)); /* jmp .+off32 */ - } - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT2(0xf7, 0xf3); /* div %ebx */ - EMIT2(0x89, 0xd0); /* mov %edx,%eax */ - break; - case BPF_S_ALU_MOD_K: /* A %= K; */ - if (K == 1) { - CLEAR_A(); - break; - } - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ - EMIT2(0xf7, 0xf1); /* div %ecx */ - EMIT2(0x89, 0xd0); /* mov %edx,%eax */ - break; - case BPF_S_ALU_DIV_K: /* A /= K */ - if (K == 1) - break; - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ - EMIT2(0xf7, 0xf1); /* div %ecx */ - break; - case BPF_S_ALU_AND_X: - seen |= SEEN_XREG; - EMIT2(0x21, 0xd8); /* and %ebx,%eax */ - break; - case BPF_S_ALU_AND_K: - if (K >= 0xFFFFFF00) { - EMIT2(0x24, K & 0xFF); /* and imm8,%al */ - } else if (K >= 0xFFFF0000) { - EMIT2(0x66, 0x25); /* and imm16,%ax */ - EMIT(K, 2); - } else { - EMIT1_off32(0x25, K); /* and imm32,%eax */ - } - break; - case BPF_S_ALU_OR_X: - seen |= SEEN_XREG; - EMIT2(0x09, 0xd8); /* or %ebx,%eax */ - break; - case BPF_S_ALU_OR_K: - if (is_imm8(K)) - EMIT3(0x83, 0xc8, K); /* or imm8,%eax */ - else - EMIT1_off32(0x0d, K); /* or imm32,%eax */ - break; - case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ - case BPF_S_ALU_XOR_X: - seen |= SEEN_XREG; - EMIT2(0x31, 0xd8); /* xor %ebx,%eax */ - break; - case BPF_S_ALU_XOR_K: /* A ^= K; */ - if (K == 0) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xf0, K); /* xor imm8,%eax */ - else - EMIT1_off32(0x35, K); /* xor imm32,%eax */ - break; - case BPF_S_ALU_LSH_X: /* A <<= X; */ - seen |= SEEN_XREG; - EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */ - break; - case BPF_S_ALU_LSH_K: - if (K == 0) - break; - else if (K == 1) - EMIT2(0xd1, 0xe0); /* shl %eax */ - else - EMIT3(0xc1, 0xe0, K); - break; - case BPF_S_ALU_RSH_X: /* A >>= X; */ - seen |= SEEN_XREG; - EMIT4(0x89, 0xd9, 0xd3, 0xe8); /* mov %ebx,%ecx; shr %cl,%eax */ - break; - case BPF_S_ALU_RSH_K: /* A >>= K; */ - if (K == 0) - break; - else if (K == 1) - EMIT2(0xd1, 0xe8); /* shr %eax */ - else - EMIT3(0xc1, 0xe8, K); - break; - case BPF_S_ALU_NEG: - EMIT2(0xf7, 0xd8); /* neg %eax */ - break; - case BPF_S_RET_K: - if (!K) { - if (pc_ret0 == -1) - pc_ret0 = i; - CLEAR_A(); - } else { - EMIT1_off32(0xb8, K); /* mov $imm32,%eax */ - } - /* fallinto */ - case BPF_S_RET_A: - if (seen_or_pass0) { - if (i != flen - 1) { - EMIT_JMP(cleanup_addr - addrs[i]); - break; - } - if (seen_or_pass0 & SEEN_XREG) - EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */ - EMIT1(0xc9); /* leaveq */ - } - EMIT1(0xc3); /* ret */ - break; - case BPF_S_MISC_TAX: /* X = A */ - seen |= SEEN_XREG; - EMIT2(0x89, 0xc3); /* mov %eax,%ebx */ - break; - case BPF_S_MISC_TXA: /* A = X */ - seen |= SEEN_XREG; - EMIT2(0x89, 0xd8); /* mov %ebx,%eax */ - break; - case BPF_S_LD_IMM: /* A = K */ - if (!K) - CLEAR_A(); - else - EMIT1_off32(0xb8, K); /* mov $imm32,%eax */ - break; - case BPF_S_LDX_IMM: /* X = K */ - seen |= SEEN_XREG; - if (!K) - CLEAR_X(); - else - EMIT1_off32(0xbb, K); /* mov $imm32,%ebx */ - break; - case BPF_S_LD_MEM: /* A = mem[K] : mov off8(%rbp),%eax */ - seen |= SEEN_MEM; - EMIT3(0x8b, 0x45, 0xf0 - K*4); - break; - case BPF_S_LDX_MEM: /* X = mem[K] : mov off8(%rbp),%ebx */ - seen |= SEEN_XREG | SEEN_MEM; - EMIT3(0x8b, 0x5d, 0xf0 - K*4); - break; - case BPF_S_ST: /* mem[K] = A : mov %eax,off8(%rbp) */ - seen |= SEEN_MEM; - EMIT3(0x89, 0x45, 0xf0 - K*4); - break; - case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ - seen |= SEEN_XREG | SEEN_MEM; - EMIT3(0x89, 0x5d, 0xf0 - K*4); - break; - case BPF_S_LD_W_LEN: /* A = skb->len; */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, len)); - else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, len), 4); - } - break; - case BPF_S_LDX_W_LEN: /* X = skb->len; */ - seen |= SEEN_XREG; - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov off8(%rdi),%ebx */ - EMIT3(0x8b, 0x5f, offsetof(struct sk_buff, len)); - else { - EMIT2(0x8b, 0x9f); - EMIT(offsetof(struct sk_buff, len), 4); - } - break; - case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - if (is_imm8(offsetof(struct sk_buff, protocol))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, protocol)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, protocol), 4); - } - EMIT2(0x86, 0xc4); /* ntohs() : xchg %al,%ah */ - break; - case BPF_S_ANC_IFINDEX: - if (is_imm8(offsetof(struct sk_buff, dev))) { - /* movq off8(%rdi),%rax */ - EMIT4(0x48, 0x8b, 0x47, offsetof(struct sk_buff, dev)); - } else { - EMIT3(0x48, 0x8b, 0x87); /* movq off32(%rdi),%rax */ - EMIT(offsetof(struct sk_buff, dev), 4); - } - EMIT3(0x48, 0x85, 0xc0); /* test %rax,%rax */ - EMIT_COND_JMP(X86_JE, cleanup_addr - (addrs[i] - 6)); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - EMIT2(0x8b, 0x80); /* mov off32(%rax),%eax */ - EMIT(offsetof(struct net_device, ifindex), 4); - break; - case BPF_S_ANC_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - if (is_imm8(offsetof(struct sk_buff, mark))) { - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, mark)); - } else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, mark), 4); - } - break; - case BPF_S_ANC_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - if (is_imm8(offsetof(struct sk_buff, hash))) { - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash)); - } else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, hash), 4); - } - break; - case BPF_S_ANC_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - if (is_imm8(offsetof(struct sk_buff, queue_mapping))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, queue_mapping)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, queue_mapping), 4); - } - break; - case BPF_S_ANC_CPU: -#ifdef CONFIG_SMP - EMIT4(0x65, 0x8b, 0x04, 0x25); /* mov %gs:off32,%eax */ - EMIT((u32)(unsigned long)&cpu_number, 4); /* A = smp_processor_id(); */ -#else - CLEAR_A(); -#endif - break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - if (is_imm8(offsetof(struct sk_buff, vlan_tci))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, vlan_tci), 4); - } - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); - if (filter[i].code == BPF_S_ANC_VLAN_TAG) { - EMIT3(0x80, 0xe4, 0xef); /* and $0xef,%ah */ - } else { - EMIT3(0xc1, 0xe8, 0x0c); /* shr $0xc,%eax */ - EMIT3(0x83, 0xe0, 0x01); /* and $0x1,%eax */ - } - break; - case BPF_S_ANC_PKTTYPE: - { - int off = pkt_type_offset(); - - if (off < 0) - goto out; - if (is_imm8(off)) { - /* movzbl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb6, 0x47, off); - } else { - /* movbl off32(%rdi),%eax */ - EMIT3(0x0f, 0xb6, 0x87); - EMIT(off, 4); - } - EMIT3(0x83, 0xe0, PKT_TYPE_MAX); /* and $0x7,%eax */ - break; - } - case BPF_S_LD_W_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_word); -common_load: seen |= SEEN_DATAREF; - t_offset = func - (image + addrs[i]); - EMIT1_off32(0xbe, K); /* mov imm32,%esi */ - EMIT1_off32(0xe8, t_offset); /* call */ - break; - case BPF_S_LD_H_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_half); - goto common_load; - case BPF_S_LD_B_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_byte); - goto common_load; - case BPF_S_LDX_B_MSH: - func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh); - seen |= SEEN_DATAREF | SEEN_XREG; - t_offset = func - (image + addrs[i]); - EMIT1_off32(0xbe, K); /* mov imm32,%esi */ - EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */ - break; - case BPF_S_LD_W_IND: - func = sk_load_word; -common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; - t_offset = func - (image + addrs[i]); - if (K) { - if (is_imm8(K)) { - EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */ - } else { - EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */ - EMIT(K, 4); - } - } else { - EMIT2(0x89,0xde); /* mov %ebx,%esi */ - } - EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */ - break; - case BPF_S_LD_H_IND: - func = sk_load_half; - goto common_load_ind; - case BPF_S_LD_B_IND: - func = sk_load_byte; - goto common_load_ind; - case BPF_S_JMP_JA: - t_offset = addrs[i + K] - addrs[i]; - EMIT_JMP(t_offset); - break; - COND_SEL(BPF_S_JMP_JGT_K, X86_JA, X86_JBE); - COND_SEL(BPF_S_JMP_JGE_K, X86_JAE, X86_JB); - COND_SEL(BPF_S_JMP_JEQ_K, X86_JE, X86_JNE); - COND_SEL(BPF_S_JMP_JSET_K,X86_JNE, X86_JE); - COND_SEL(BPF_S_JMP_JGT_X, X86_JA, X86_JBE); - COND_SEL(BPF_S_JMP_JGE_X, X86_JAE, X86_JB); - COND_SEL(BPF_S_JMP_JEQ_X, X86_JE, X86_JNE); - COND_SEL(BPF_S_JMP_JSET_X,X86_JNE, X86_JE); - -cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; - t_offset = addrs[i + filter[i].jt] - addrs[i]; - - /* same targets, can avoid doing the test :) */ - if (filter[i].jt == filter[i].jf) { - EMIT_JMP(t_offset); - break; - } - - switch (filter[i].code) { - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JEQ_X: - seen |= SEEN_XREG; - EMIT2(0x39, 0xd8); /* cmp %ebx,%eax */ - break; - case BPF_S_JMP_JSET_X: - seen |= SEEN_XREG; - EMIT2(0x85, 0xd8); /* test %ebx,%eax */ - break; - case BPF_S_JMP_JEQ_K: - if (K == 0) { - EMIT2(0x85, 0xc0); /* test %eax,%eax */ - break; - } - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGE_K: - if (K <= 127) - EMIT3(0x83, 0xf8, K); /* cmp imm8,%eax */ - else - EMIT1_off32(0x3d, K); /* cmp imm32,%eax */ - break; - case BPF_S_JMP_JSET_K: - if (K <= 0xFF) - EMIT2(0xa8, K); /* test imm8,%al */ - else if (!(K & 0xFFFF00FF)) - EMIT3(0xf6, 0xc4, K >> 8); /* test imm8,%ah */ - else if (K <= 0xFFFF) { - EMIT2(0x66, 0xa9); /* test imm16,%ax */ - EMIT(K, 2); - } else { - EMIT1_off32(0xa9, K); /* test imm32,%eax */ - } - break; - } - if (filter[i].jt != 0) { - if (filter[i].jf && f_offset) - t_offset += is_near(f_offset) ? 2 : 5; - EMIT_COND_JMP(t_op, t_offset); - if (filter[i].jf) - EMIT_JMP(f_offset); - break; - } - EMIT_COND_JMP(f_op, f_offset); - break; - default: - /* hmm, too complex filter, give up with jit compiler */ - goto out; - } - ilen = prog - temp; - if (image) { - if (unlikely(proglen + ilen > oldproglen)) { - pr_err("bpb_jit_compile fatal error\n"); - kfree(addrs); - module_free(NULL, header); - return; - } - memcpy(image + proglen, temp, ilen); - } - proglen += ilen; - addrs[i] = proglen; - prog = temp; - } - /* last bpf instruction is always a RET : - * use it to give the cleanup instruction(s) addr - */ - cleanup_addr = proglen - 1; /* ret */ - if (seen_or_pass0) - cleanup_addr -= 1; /* leaveq */ - if (seen_or_pass0 & SEEN_XREG) - cleanup_addr -= 4; /* mov -8(%rbp),%rbx */ - if (image) { if (proglen != oldproglen) - pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen); + pr_err("bpf_jit: proglen=%d != oldproglen=%d\n", + proglen, oldproglen); break; } if (proglen == oldproglen) { @@ -766,17 +918,16 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; } if (bpf_jit_enable > 1) - bpf_jit_dump(flen, proglen, pass, image); + bpf_jit_dump(prog->len, proglen, 0, image); if (image) { bpf_flush_icache(header, image + proglen); set_memory_ro((unsigned long)header, header->pages); - fp->bpf_func = (void *)image; - fp->jited = 1; + prog->bpf_func = (void *)image; + prog->jited = 1; } out: kfree(addrs); - return; } static void bpf_jit_free_deferred(struct work_struct *work) diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 9769df094035..3c0809a0631f 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -9,18 +9,9 @@ VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y VDSO32-$(CONFIG_COMPAT) := y -vdso-install-$(VDSO64-y) += vdso.so -vdso-install-$(VDSOX32-y) += vdsox32.so -vdso-install-$(VDSO32-y) += $(vdso32-images) - - # files to link into the vdso -vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o - -vobjs-$(VDSOX32-y) += $(vobjx32s-compat) - -# Filter out x32 objects. -vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o +vobjs-nox32 := vdso-fakesections.o # files to link into kernel obj-y += vma.o @@ -34,7 +25,7 @@ vdso_img-$(VDSO32-y) += 32-sysenter obj-$(VDSO32-y) += vdso32-setup.o -vobjs := $(foreach F,$(vobj64s),$(obj)/$F) +vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) $(obj)/vdso.o: $(obj)/vdso.so @@ -104,7 +95,13 @@ VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ -Wl,-z,max-page-size=4096 \ -Wl,-z,common-page-size=4096 -vobjx32s-y := $(vobj64s:.o=-x32.o) +# 64-bit objects to re-brand as x32 +vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y)) + +# x32-rebranded versions +vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o) + +# same thing, but in the output directory vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) # Convert 64bit object file to x32 for x32 vDSO. @@ -176,15 +173,20 @@ VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ GCOV_PROFILE := n # -# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). +# Install the unstripped copies of vdso*.so. # -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ -$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE +quiet_cmd_vdso_install = INSTALL $(@:install_%=%) + cmd_vdso_install = cp $< $(MODLIB)/vdso/$(@:install_%=%) + +vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) + +$(MODLIB)/vdso: FORCE @mkdir -p $(MODLIB)/vdso + +$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE $(call cmd,vdso_install) -PHONY += vdso_install $(vdso-install-y) -vdso_install: $(vdso-install-y) +PHONY += vdso_install $(vdso_img_insttargets) +vdso_install: $(vdso_img_insttargets) FORCE clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c new file mode 100644 index 000000000000..cb8a8d72c24b --- /dev/null +++ b/arch/x86/vdso/vdso-fakesections.c @@ -0,0 +1,32 @@ +/* + * Copyright 2014 Andy Lutomirski + * Subject to the GNU Public License, v.2 + * + * Hack to keep broken Go programs working. + * + * The Go runtime had a couple of bugs: it would read the section table to try + * to figure out how many dynamic symbols there were (it shouldn't have looked + * at the section table at all) and, if there were no SHT_SYNDYM section table + * entry, it would use an uninitialized value for the number of symbols. As a + * workaround, we supply a minimal section table. vdso2c will adjust the + * in-memory image so that "vdso_fake_sections" becomes the section table. + * + * The bug was introduced by: + * https://code.google.com/p/go/source/detail?r=56ea40aac72b (2012-08-31) + * and is being addressed in the Go runtime in this issue: + * https://code.google.com/p/go/issues/detail?id=8197 + */ + +#ifndef __x86_64__ +#error This hack is specific to the 64-bit vDSO +#endif + +#include + +extern const __visible struct elf64_shdr vdso_fake_sections[]; +const __visible struct elf64_shdr vdso_fake_sections[] = { + { + .sh_type = SHT_DYNSYM, + .sh_entsize = sizeof(Elf64_Sym), + } +}; diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c index 450ac6eaf613..7a6bf50f9165 100644 --- a/arch/x86/vdso/vdso2c.c +++ b/arch/x86/vdso/vdso2c.c @@ -54,7 +54,7 @@ static void fail(const char *format, ...) } /* - * Evil macros to do a little-endian read. + * Evil macros for little-endian reads and writes */ #define GLE(x, bits, ifnot) \ __builtin_choose_expr( \ @@ -62,11 +62,24 @@ static void fail(const char *format, ...) (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot) extern void bad_get_le(void); -#define LAST_LE(x) \ +#define LAST_GLE(x) \ __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le()) #define GET_LE(x) \ - GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_LE(x)))) + GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x)))) + +#define PLE(x, val, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + put_unaligned_le##bits((val), (x)), ifnot) + +extern void bad_put_le(void); +#define LAST_PLE(x, val) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le()) + +#define PUT_LE(x, val) \ + PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val)))) + #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h index 8a074637a576..c6eefaf389b9 100644 --- a/arch/x86/vdso/vdso2c.h +++ b/arch/x86/vdso/vdso2c.h @@ -18,6 +18,8 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) const char *secstrings; uint64_t syms[NSYMS] = {}; + uint64_t fake_sections_value = 0, fake_sections_size = 0; + Elf_Phdr *pt = (Elf_Phdr *)(addr + GET_LE(&hdr->e_phoff)); /* Walk the segment table. */ @@ -84,6 +86,7 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) GET_LE(&symtab_hdr->sh_entsize) * i; const char *name = addr + GET_LE(&strtab_hdr->sh_offset) + GET_LE(&sym->st_name); + for (k = 0; k < NSYMS; k++) { if (!strcmp(name, required_syms[k])) { if (syms[k]) { @@ -93,6 +96,13 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) syms[k] = GET_LE(&sym->st_value); } } + + if (!strcmp(name, "vdso_fake_sections")) { + if (fake_sections_value) + fail("duplicate vdso_fake_sections\n"); + fake_sections_value = GET_LE(&sym->st_value); + fake_sections_size = GET_LE(&sym->st_size); + } } /* Validate mapping addresses. */ @@ -112,11 +122,14 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) if (syms[sym_end_mapping] % 4096) fail("end_mapping must be a multiple of 4096\n"); - /* Remove sections. */ - hdr->e_shoff = 0; - hdr->e_shentsize = 0; - hdr->e_shnum = 0; - hdr->e_shstrndx = htole16(SHN_UNDEF); + /* Remove sections or use fakes */ + if (fake_sections_size % sizeof(Elf_Shdr)) + fail("vdso_fake_sections size is not a multiple of %ld\n", + (long)sizeof(Elf_Shdr)); + PUT_LE(&hdr->e_shoff, fake_sections_value); + PUT_LE(&hdr->e_shentsize, fake_sections_value ? sizeof(Elf_Shdr) : 0); + PUT_LE(&hdr->e_shnum, fake_sections_size / sizeof(Elf_Shdr)); + PUT_LE(&hdr->e_shstrndx, SHN_UNDEF); if (!name) { fwrite(addr, load_size, 1, outfile); diff --git a/block/blk-core.c b/block/blk-core.c index 9aca8c71e70b..f6f6b9af3e3f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -43,6 +43,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); DEFINE_IDA(blk_queue_ida); diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 147bc1b91b42..3f2bdc812d23 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -1810,6 +1810,16 @@ acpi_status __init acpi_os_initialize(void) acpi_os_map_generic_address(&acpi_gbl_FADT.xpm1b_event_block); acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe0_block); acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe1_block); + if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) { + /* + * Use acpi_os_map_generic_address to pre-map the reset + * register if it's in system memory. + */ + int rv; + + rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register); + pr_debug(PREFIX "%s: map reset_reg status %d\n", __func__, rv); + } return AE_OK; } @@ -1838,6 +1848,8 @@ acpi_status acpi_os_terminate(void) acpi_os_unmap_generic_address(&acpi_gbl_FADT.xgpe0_block); acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1b_event_block); acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1a_event_block); + if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) + acpi_os_unmap_generic_address(&acpi_gbl_FADT.reset_register); destroy_workqueue(kacpid_wq); destroy_workqueue(kacpi_notify_wq); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index c11e3795431b..b3e3cc73ba79 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "internal.h" #include "sleep.h" @@ -501,6 +502,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state) ACPI_FLUSH_CPU_CACHE(); + trace_suspend_resume(TPS("acpi_suspend"), acpi_state, true); switch (acpi_state) { case ACPI_STATE_S1: barrier(); @@ -516,6 +518,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state) pr_info(PREFIX "Low-level resume complete\n"); break; } + trace_suspend_resume(TPS("acpi_suspend"), acpi_state, false); /* This violates the spec but is required for bug compatibility. */ acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1); diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 101fb090dcb9..fb9ffe9adc64 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -82,7 +82,7 @@ module_param(allow_duplicates, bool, 0644); * For Windows 8 systems: used to decide if video module * should skip registering backlight interface of its own. */ -static int use_native_backlight_param = -1; +static int use_native_backlight_param = 1; module_param_named(use_native_backlight, use_native_backlight_param, int, 0444); static bool use_native_backlight_dmi = false; diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 204814e88e46..d4725fc0395d 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -2780,7 +2780,7 @@ static struct pci_driver fore200e_pca_driver = { static int __init fore200e_module_init(void) { - int err; + int err = 0; printk(FORE200E "FORE Systems 200E-series ATM driver - version " FORE200E_VERSION "\n"); diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 1bdf104e90bb..b621f56a36be 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2551,12 +2551,12 @@ idt77252_close(struct atm_vcc *vcc) timeout = 5 * 1000; while (atomic_read(&vc->scq->used) > 0) { timeout = msleep_interruptible(timeout); - if (!timeout) + if (!timeout) { + pr_warn("%s: SCQ drain timeout: %u used\n", + card->name, atomic_read(&vc->scq->used)); break; + } } - if (!timeout) - printk("%s: SCQ drain timeout: %u used\n", - card->name, atomic_read(&vc->scq->used)); writel(TCMDQ_HALT | vc->index, SAR_REG_TCMDQ); clear_scd(card, vc->scq, vc->class); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 343ffad59377..bf412961a934 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -214,9 +214,6 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime, pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev), error, (unsigned long long)nsecs >> 10); } - - trace_device_pm_report_time(dev, info, nsecs, pm_verb(state.event), - error); } /** @@ -387,7 +384,9 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev, calltime = initcall_debug_start(dev); pm_dev_dbg(dev, state, info); + trace_device_pm_callback_start(dev, info, state.event); error = cb(dev); + trace_device_pm_callback_end(dev, error); suspend_report_result(cb, error); initcall_debug_report(dev, calltime, error, state, info); @@ -545,6 +544,7 @@ static void dpm_resume_noirq(pm_message_t state) struct device *dev; ktime_t starttime = ktime_get(); + trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true); mutex_lock(&dpm_list_mtx); pm_transition = state; @@ -587,6 +587,7 @@ static void dpm_resume_noirq(pm_message_t state) dpm_show_time(starttime, state, "noirq"); resume_device_irqs(); cpuidle_resume(); + trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); } /** @@ -664,6 +665,7 @@ static void dpm_resume_early(pm_message_t state) struct device *dev; ktime_t starttime = ktime_get(); + trace_suspend_resume(TPS("dpm_resume_early"), state.event, true); mutex_lock(&dpm_list_mtx); pm_transition = state; @@ -703,6 +705,7 @@ static void dpm_resume_early(pm_message_t state) mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, "early"); + trace_suspend_resume(TPS("dpm_resume_early"), state.event, false); } /** @@ -834,6 +837,7 @@ void dpm_resume(pm_message_t state) struct device *dev; ktime_t starttime = ktime_get(); + trace_suspend_resume(TPS("dpm_resume"), state.event, true); might_sleep(); mutex_lock(&dpm_list_mtx); @@ -875,6 +879,7 @@ void dpm_resume(pm_message_t state) dpm_show_time(starttime, state, NULL); cpufreq_resume(); + trace_suspend_resume(TPS("dpm_resume"), state.event, false); } /** @@ -913,7 +918,9 @@ static void device_complete(struct device *dev, pm_message_t state) if (callback) { pm_dev_dbg(dev, state, info); + trace_device_pm_callback_start(dev, info, state.event); callback(dev); + trace_device_pm_callback_end(dev, 0); } device_unlock(dev); @@ -932,6 +939,7 @@ void dpm_complete(pm_message_t state) { struct list_head list; + trace_suspend_resume(TPS("dpm_complete"), state.event, true); might_sleep(); INIT_LIST_HEAD(&list); @@ -951,6 +959,7 @@ void dpm_complete(pm_message_t state) } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); + trace_suspend_resume(TPS("dpm_complete"), state.event, false); } /** @@ -1086,6 +1095,7 @@ static int dpm_suspend_noirq(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0; + trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true); cpuidle_pause(); suspend_device_irqs(); mutex_lock(&dpm_list_mtx); @@ -1126,6 +1136,7 @@ static int dpm_suspend_noirq(pm_message_t state) } else { dpm_show_time(starttime, state, "noirq"); } + trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false); return error; } @@ -1222,6 +1233,7 @@ static int dpm_suspend_late(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0; + trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; @@ -1257,6 +1269,7 @@ static int dpm_suspend_late(pm_message_t state) } else { dpm_show_time(starttime, state, "late"); } + trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false); return error; } @@ -1295,7 +1308,9 @@ static int legacy_suspend(struct device *dev, pm_message_t state, calltime = initcall_debug_start(dev); + trace_device_pm_callback_start(dev, info, state.event); error = cb(dev, state); + trace_device_pm_callback_end(dev, error); suspend_report_result(cb, error); initcall_debug_report(dev, calltime, error, state, info); @@ -1461,6 +1476,7 @@ int dpm_suspend(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0; + trace_suspend_resume(TPS("dpm_suspend"), state.event, true); might_sleep(); cpufreq_suspend(); @@ -1498,6 +1514,7 @@ int dpm_suspend(pm_message_t state) dpm_save_failed_step(SUSPEND_SUSPEND); } else dpm_show_time(starttime, state, NULL); + trace_suspend_resume(TPS("dpm_suspend"), state.event, false); return error; } @@ -1549,8 +1566,11 @@ static int device_prepare(struct device *dev, pm_message_t state) callback = dev->driver->pm->prepare; } - if (callback) + if (callback) { + trace_device_pm_callback_start(dev, info, state.event); ret = callback(dev); + trace_device_pm_callback_end(dev, ret); + } device_unlock(dev); @@ -1582,6 +1602,7 @@ int dpm_prepare(pm_message_t state) { int error = 0; + trace_suspend_resume(TPS("dpm_prepare"), state.event, true); might_sleep(); mutex_lock(&dpm_list_mtx); @@ -1612,6 +1633,7 @@ int dpm_prepare(pm_message_t state) put_device(dev); } mutex_unlock(&dpm_list_mtx); + trace_suspend_resume(TPS("dpm_prepare"), state.event, false); return error; } diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c index e8d11b6630ee..dbb8350ea8dc 100644 --- a/drivers/base/syscore.c +++ b/drivers/base/syscore.c @@ -10,6 +10,7 @@ #include #include #include +#include static LIST_HEAD(syscore_ops_list); static DEFINE_MUTEX(syscore_ops_lock); @@ -49,6 +50,7 @@ int syscore_suspend(void) struct syscore_ops *ops; int ret = 0; + trace_suspend_resume(TPS("syscore_suspend"), 0, true); pr_debug("Checking wakeup interrupts\n"); /* Return error code if there are any wakeup interrupts pending. */ @@ -70,6 +72,7 @@ int syscore_suspend(void) "Interrupts enabled after %pF\n", ops->suspend); } + trace_suspend_resume(TPS("syscore_suspend"), 0, false); return 0; err_out: @@ -92,6 +95,7 @@ void syscore_resume(void) { struct syscore_ops *ops; + trace_suspend_resume(TPS("syscore_resume"), 0, true); WARN_ONCE(!irqs_disabled(), "Interrupts enabled before system core resume.\n"); @@ -103,6 +107,7 @@ void syscore_resume(void) WARN_ONCE(!irqs_disabled(), "Interrupts enabled after %pF\n", ops->resume); } + trace_suspend_resume(TPS("syscore_resume"), 0, false); } EXPORT_SYMBOL_GPL(syscore_resume); #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index a842c71dcc21..02351e217165 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -10,10 +10,6 @@ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ #include @@ -46,16 +42,26 @@ #include #include -#define NVME_Q_DEPTH 1024 +#include + +#define NVME_Q_DEPTH 1024 #define SQ_SIZE(depth) (depth * sizeof(struct nvme_command)) #define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion)) -#define ADMIN_TIMEOUT (60 * HZ) -#define IOD_TIMEOUT (4 * NVME_IO_TIMEOUT) +#define ADMIN_TIMEOUT (admin_timeout * HZ) +#define IOD_TIMEOUT (retry_time * HZ) -unsigned char io_timeout = 30; -module_param(io_timeout, byte, 0644); +static unsigned char admin_timeout = 60; +module_param(admin_timeout, byte, 0644); +MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands"); + +unsigned char nvme_io_timeout = 30; +module_param_named(io_timeout, nvme_io_timeout, byte, 0644); MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O"); +static unsigned char retry_time = 30; +module_param(retry_time, byte, 0644); +MODULE_PARM_DESC(retry_time, "time in seconds to retry failed I/O"); + static int nvme_major; module_param(nvme_major, int, 0); @@ -67,6 +73,7 @@ static LIST_HEAD(dev_list); static struct task_struct *nvme_thread; static struct workqueue_struct *nvme_workq; static wait_queue_head_t nvme_kthread_wait; +static struct notifier_block nvme_nb; static void nvme_reset_failed_dev(struct work_struct *ws); @@ -199,16 +206,13 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx, #define CMD_CTX_CANCELLED (0x30C + CMD_CTX_BASE) #define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE) #define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE) -#define CMD_CTX_FLUSH (0x318 + CMD_CTX_BASE) -#define CMD_CTX_ABORT (0x31C + CMD_CTX_BASE) +#define CMD_CTX_ABORT (0x318 + CMD_CTX_BASE) static void special_completion(struct nvme_queue *nvmeq, void *ctx, struct nvme_completion *cqe) { if (ctx == CMD_CTX_CANCELLED) return; - if (ctx == CMD_CTX_FLUSH) - return; if (ctx == CMD_CTX_ABORT) { ++nvmeq->dev->abort_limit; return; @@ -247,8 +251,9 @@ static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid, void *ctx; struct nvme_cmd_info *info = nvme_cmd_info(nvmeq); - if (cmdid >= nvmeq->q_depth) { - *fn = special_completion; + if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) { + if (fn) + *fn = special_completion; return CMD_CTX_INVALID; } if (fn) @@ -281,9 +286,17 @@ static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid) static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU) { + struct nvme_queue *nvmeq; unsigned queue_id = get_cpu_var(*dev->io_queue); + rcu_read_lock(); - return rcu_dereference(dev->queues[queue_id]); + nvmeq = rcu_dereference(dev->queues[queue_id]); + if (nvmeq) + return nvmeq; + + rcu_read_unlock(); + put_cpu_var(*dev->io_queue); + return NULL; } static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU) @@ -295,8 +308,15 @@ static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU) static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx) __acquires(RCU) { + struct nvme_queue *nvmeq; + rcu_read_lock(); - return rcu_dereference(dev->queues[q_idx]); + nvmeq = rcu_dereference(dev->queues[q_idx]); + if (nvmeq) + return nvmeq; + + rcu_read_unlock(); + return NULL; } static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU) @@ -387,25 +407,30 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod) static void nvme_start_io_acct(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; - const int rw = bio_data_dir(bio); - int cpu = part_stat_lock(); - part_round_stats(cpu, &disk->part0); - part_stat_inc(cpu, &disk->part0, ios[rw]); - part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio)); - part_inc_in_flight(&disk->part0, rw); - part_stat_unlock(); + if (blk_queue_io_stat(disk->queue)) { + const int rw = bio_data_dir(bio); + int cpu = part_stat_lock(); + part_round_stats(cpu, &disk->part0); + part_stat_inc(cpu, &disk->part0, ios[rw]); + part_stat_add(cpu, &disk->part0, sectors[rw], + bio_sectors(bio)); + part_inc_in_flight(&disk->part0, rw); + part_stat_unlock(); + } } static void nvme_end_io_acct(struct bio *bio, unsigned long start_time) { struct gendisk *disk = bio->bi_bdev->bd_disk; - const int rw = bio_data_dir(bio); - unsigned long duration = jiffies - start_time; - int cpu = part_stat_lock(); - part_stat_add(cpu, &disk->part0, ticks[rw], duration); - part_round_stats(cpu, &disk->part0); - part_dec_in_flight(&disk->part0, rw); - part_stat_unlock(); + if (blk_queue_io_stat(disk->queue)) { + const int rw = bio_data_dir(bio); + unsigned long duration = jiffies - start_time; + int cpu = part_stat_lock(); + part_stat_add(cpu, &disk->part0, ticks[rw], duration); + part_round_stats(cpu, &disk->part0); + part_dec_in_flight(&disk->part0, rw); + part_stat_unlock(); + } } static void bio_completion(struct nvme_queue *nvmeq, void *ctx, @@ -414,6 +439,7 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx, struct nvme_iod *iod = ctx; struct bio *bio = iod->private; u16 status = le16_to_cpup(&cqe->status) >> 1; + int error = 0; if (unlikely(status)) { if (!(status & NVME_SC_DNR || @@ -426,6 +452,7 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx, wake_up(&nvmeq->sq_full); return; } + error = -EIO; } if (iod->nents) { dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents, @@ -433,10 +460,9 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx, nvme_end_io_acct(bio, iod->start_time); } nvme_free_iod(nvmeq->dev, iod); - if (status) - bio_endio(bio, -EIO); - else - bio_endio(bio, 0); + + trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error); + bio_endio(bio, error); } /* length is in bytes. gfp flags indicates whether we may sleep. */ @@ -525,6 +551,8 @@ static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq, if (!split) return -ENOMEM; + trace_block_split(bdev_get_queue(bio->bi_bdev), bio, + split->bi_iter.bi_sector); bio_chain(split, bio); if (!waitqueue_active(&nvmeq->sq_full)) @@ -627,16 +655,6 @@ static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns, return 0; } -int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns) -{ - int cmdid = alloc_cmdid(nvmeq, (void *)CMD_CTX_FLUSH, - special_completion, NVME_IO_TIMEOUT); - if (unlikely(cmdid < 0)) - return cmdid; - - return nvme_submit_flush(nvmeq, ns, cmdid); -} - static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod) { struct bio *bio = iod->private; @@ -652,7 +670,7 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod) if (bio->bi_rw & REQ_DISCARD) return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid); - if ((bio->bi_rw & REQ_FLUSH) && !iod->nents) + if (bio->bi_rw & REQ_FLUSH) return nvme_submit_flush(nvmeq, ns, cmdid); control = 0; @@ -686,6 +704,26 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod) return 0; } +static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio) +{ + struct bio *split = bio_clone(bio, GFP_ATOMIC); + if (!split) + return -ENOMEM; + + split->bi_iter.bi_size = 0; + split->bi_phys_segments = 0; + bio->bi_rw &= ~REQ_FLUSH; + bio_chain(split, bio); + + if (!waitqueue_active(&nvmeq->sq_full)) + add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait); + bio_list_add(&nvmeq->sq_cong, split); + bio_list_add(&nvmeq->sq_cong, bio); + wake_up_process(nvme_thread); + + return 0; +} + /* * Called with local interrupts disabled and the q_lock held. May not sleep. */ @@ -696,11 +734,8 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns, int psegs = bio_phys_segments(ns->queue, bio); int result; - if ((bio->bi_rw & REQ_FLUSH) && psegs) { - result = nvme_submit_flush_data(nvmeq, ns); - if (result) - return result; - } + if ((bio->bi_rw & REQ_FLUSH) && psegs) + return nvme_split_flush_data(nvmeq, bio); iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC); if (!iod) @@ -795,7 +830,6 @@ static void nvme_make_request(struct request_queue *q, struct bio *bio) int result = -EBUSY; if (!nvmeq) { - put_nvmeq(NULL); bio_endio(bio, -EIO); return; } @@ -870,10 +904,8 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx, struct nvme_queue *nvmeq; nvmeq = lock_nvmeq(dev, q_idx); - if (!nvmeq) { - unlock_nvmeq(nvmeq); + if (!nvmeq) return -ENODEV; - } cmdinfo.task = current; cmdinfo.status = -EINTR; @@ -898,9 +930,10 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx, if (cmdinfo.status == -EINTR) { nvmeq = lock_nvmeq(dev, q_idx); - if (nvmeq) + if (nvmeq) { nvme_abort_command(nvmeq, cmdid); - unlock_nvmeq(nvmeq); + unlock_nvmeq(nvmeq); + } return -EINTR; } @@ -1358,7 +1391,8 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled) return -EINTR; if (time_after(jiffies, timeout)) { dev_err(&dev->pci_dev->dev, - "Device not ready; aborting initialisation\n"); + "Device not ready; aborting %s\n", enabled ? + "initialisation" : "reset"); return -ENODEV; } } @@ -1481,7 +1515,11 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, goto put_pages; } + err = -ENOMEM; iod = nvme_alloc_iod(count, length, GFP_KERNEL); + if (!iod) + goto put_pages; + sg = iod->sg; sg_init_table(sg, count); for (i = 0; i < count; i++) { @@ -1494,7 +1532,6 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, sg_mark_end(&sg[i - 1]); iod->nents = count; - err = -ENOMEM; nents = dma_map_sg(&dev->pci_dev->dev, sg, count, write ? DMA_TO_DEVICE : DMA_FROM_DEVICE); if (!nents) @@ -1894,6 +1931,8 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid, blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); if (dev->max_hw_sectors) blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors); + if (dev->vwc & NVME_CTRL_VWC_PRESENT) + blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA); disk->major = nvme_major; disk->first_minor = 0; @@ -2062,8 +2101,13 @@ static int set_queue_count(struct nvme_dev *dev, int count) status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0, &result); - if (status) - return status < 0 ? -EIO : -EBUSY; + if (status < 0) + return status; + if (status > 0) { + dev_err(&dev->pci_dev->dev, "Could not set queue count (%d)\n", + status); + return -EBUSY; + } return min(result & 0xffff, result >> 16) + 1; } @@ -2072,14 +2116,25 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues) return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride); } +static void nvme_cpu_workfn(struct work_struct *work) +{ + struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work); + if (dev->initialized) + nvme_assign_io_queues(dev); +} + static int nvme_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { - struct nvme_dev *dev = container_of(self, struct nvme_dev, nb); + struct nvme_dev *dev; + switch (action) { case CPU_ONLINE: case CPU_DEAD: - nvme_assign_io_queues(dev); + spin_lock(&dev_list_lock); + list_for_each_entry(dev, &dev_list, node) + schedule_work(&dev->cpu_work); + spin_unlock(&dev_list_lock); break; } return NOTIFY_OK; @@ -2148,11 +2203,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) nvme_free_queues(dev, nr_io_queues + 1); nvme_assign_io_queues(dev); - dev->nb.notifier_call = &nvme_cpu_notify; - result = register_hotcpu_notifier(&dev->nb); - if (result) - goto free_queues; - return 0; free_queues: @@ -2184,6 +2234,7 @@ static int nvme_dev_add(struct nvme_dev *dev) res = nvme_identify(dev, 0, 1, dma_addr); if (res) { + dev_err(&pdev->dev, "Identify Controller failed (%d)\n", res); res = -EIO; goto out; } @@ -2192,6 +2243,7 @@ static int nvme_dev_add(struct nvme_dev *dev) nn = le32_to_cpup(&ctrl->nn); dev->oncs = le16_to_cpup(&ctrl->oncs); dev->abort_limit = ctrl->acl + 1; + dev->vwc = ctrl->vwc; memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn)); memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn)); memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); @@ -2450,8 +2502,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev) int i; dev->initialized = 0; - unregister_hotcpu_notifier(&dev->nb); - nvme_dev_list_remove(dev); if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) { @@ -2722,6 +2772,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) INIT_LIST_HEAD(&dev->namespaces); dev->reset_workfn = nvme_reset_failed_dev; INIT_WORK(&dev->reset_work, nvme_reset_workfn); + INIT_WORK(&dev->cpu_work, nvme_cpu_workfn); dev->pci_dev = pdev; pci_set_drvdata(pdev, dev); result = nvme_set_instance(dev); @@ -2801,6 +2852,7 @@ static void nvme_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); flush_work(&dev->reset_work); + flush_work(&dev->cpu_work); misc_deregister(&dev->miscdev); nvme_dev_remove(dev); nvme_dev_shutdown(dev); @@ -2889,11 +2941,18 @@ static int __init nvme_init(void) else if (result > 0) nvme_major = result; - result = pci_register_driver(&nvme_driver); + nvme_nb.notifier_call = &nvme_cpu_notify; + result = register_hotcpu_notifier(&nvme_nb); if (result) goto unregister_blkdev; + + result = pci_register_driver(&nvme_driver); + if (result) + goto unregister_hotcpu; return 0; + unregister_hotcpu: + unregister_hotcpu_notifier(&nvme_nb); unregister_blkdev: unregister_blkdev(nvme_major, "nvme"); kill_workq: @@ -2904,9 +2963,11 @@ static int __init nvme_init(void) static void __exit nvme_exit(void) { pci_unregister_driver(&nvme_driver); + unregister_hotcpu_notifier(&nvme_nb); unregister_blkdev(nvme_major, "nvme"); destroy_workqueue(nvme_workq); BUG_ON(nvme_thread && !IS_ERR(nvme_thread)); + _nvme_check_size(); } MODULE_AUTHOR("Matthew Wilcox "); diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c index 2c3f5be06da1..a4cd6d691c63 100644 --- a/drivers/block/nvme-scsi.c +++ b/drivers/block/nvme-scsi.c @@ -1,6 +1,6 @@ /* * NVM Express device driver - * Copyright (c) 2011, Intel Corporation. + * Copyright (c) 2011-2014, Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -10,10 +10,6 @@ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ /* @@ -243,8 +239,6 @@ static int sg_version_num = 30534; /* 2 digits for each component */ #define READ_CAP_16_RESP_SIZE 32 /* NVMe Namespace and Command Defines */ -#define NVME_GET_SMART_LOG_PAGE 0x02 -#define NVME_GET_FEAT_TEMP_THRESH 0x04 #define BYTES_TO_DWORDS 4 #define NVME_MAX_FIRMWARE_SLOT 7 @@ -686,6 +680,7 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns, u8 resp_data_format = 0x02; u8 protect; u8 cmdque = 0x01 << 1; + u8 fw_offset = sizeof(dev->firmware_rev); mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), &dma_addr, GFP_KERNEL); @@ -721,7 +716,11 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns, inq_response[7] = cmdque; /* wbus16=0 | sync=0 | vs=0 */ strncpy(&inq_response[8], "NVMe ", 8); strncpy(&inq_response[16], dev->model, 16); - strncpy(&inq_response[32], dev->firmware_rev, 4); + + while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset > 4) + fw_offset--; + fw_offset -= 4; + strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4); xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH); res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len); @@ -1018,8 +1017,8 @@ static int nvme_trans_log_info_exceptions(struct nvme_ns *ns, c.common.opcode = nvme_admin_get_log_page; c.common.nsid = cpu_to_le32(0xFFFFFFFF); c.common.prp1 = cpu_to_le64(dma_addr); - c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) / - BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE); + c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) / + BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART); res = nvme_submit_admin_cmd(dev, &c, NULL); if (res != NVME_SC_SUCCESS) { temp_c = LOG_TEMP_UNKNOWN; @@ -1086,8 +1085,8 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr, c.common.opcode = nvme_admin_get_log_page; c.common.nsid = cpu_to_le32(0xFFFFFFFF); c.common.prp1 = cpu_to_le64(dma_addr); - c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) / - BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE); + c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) / + BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART); res = nvme_submit_admin_cmd(dev, &c, NULL); if (res != NVME_SC_SUCCESS) { temp_c_cur = LOG_TEMP_UNKNOWN; @@ -1477,7 +1476,7 @@ static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr, goto out_dma; } id_ctrl = mem; - lowest_pow_st = id_ctrl->npss - 1; + lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1)); switch (pc) { case NVME_POWER_STATE_START_VALID: @@ -1494,20 +1493,19 @@ static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr, break; case NVME_POWER_STATE_IDLE: /* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */ - /* min of desired state and (lps-1) because lps is STOP */ if (pcmod == 0x0) - ps_desired = min(POWER_STATE_1, (lowest_pow_st - 1)); + ps_desired = POWER_STATE_1; else if (pcmod == 0x1) - ps_desired = min(POWER_STATE_2, (lowest_pow_st - 1)); + ps_desired = POWER_STATE_2; else if (pcmod == 0x2) - ps_desired = min(POWER_STATE_3, (lowest_pow_st - 1)); + ps_desired = POWER_STATE_3; break; case NVME_POWER_STATE_STANDBY: /* Action unspecified if POWER CONDITION MODIFIER != [0,1] */ if (pcmod == 0x0) - ps_desired = max(0, (lowest_pow_st - 2)); + ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2)); else if (pcmod == 0x1) - ps_desired = max(0, (lowest_pow_st - 1)); + ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1)); break; case NVME_POWER_STATE_LU_CONTROL: default: diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4c95b503b09e..bbeb404b3a07 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -541,7 +541,6 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) return -ENOENT; (void) get_device(&rbd_dev->dev); - set_device_ro(bdev, rbd_dev->mapping.read_only); return 0; } @@ -559,10 +558,76 @@ static void rbd_release(struct gendisk *disk, fmode_t mode) put_device(&rbd_dev->dev); } +static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg) +{ + int ret = 0; + int val; + bool ro; + bool ro_changed = false; + + /* get_user() may sleep, so call it before taking rbd_dev->lock */ + if (get_user(val, (int __user *)(arg))) + return -EFAULT; + + ro = val ? true : false; + /* Snapshot doesn't allow to write*/ + if (rbd_dev->spec->snap_id != CEPH_NOSNAP && !ro) + return -EROFS; + + spin_lock_irq(&rbd_dev->lock); + /* prevent others open this device */ + if (rbd_dev->open_count > 1) { + ret = -EBUSY; + goto out; + } + + if (rbd_dev->mapping.read_only != ro) { + rbd_dev->mapping.read_only = ro; + ro_changed = true; + } + +out: + spin_unlock_irq(&rbd_dev->lock); + /* set_disk_ro() may sleep, so call it after releasing rbd_dev->lock */ + if (ret == 0 && ro_changed) + set_disk_ro(rbd_dev->disk, ro ? 1 : 0); + + return ret; +} + +static int rbd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + struct rbd_device *rbd_dev = bdev->bd_disk->private_data; + int ret = 0; + + switch (cmd) { + case BLKROSET: + ret = rbd_ioctl_set_ro(rbd_dev, arg); + break; + default: + ret = -ENOTTY; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static int rbd_compat_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + return rbd_ioctl(bdev, mode, cmd, arg); +} +#endif /* CONFIG_COMPAT */ + static const struct block_device_operations rbd_bd_ops = { .owner = THIS_MODULE, .open = rbd_open, .release = rbd_release, + .ioctl = rbd_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = rbd_compat_ioctl, +#endif }; /* @@ -1382,6 +1447,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request) kref_put(&obj_request->kref, rbd_obj_request_destroy); } +static void rbd_img_request_get(struct rbd_img_request *img_request) +{ + dout("%s: img %p (was %d)\n", __func__, img_request, + atomic_read(&img_request->kref.refcount)); + kref_get(&img_request->kref); +} + static bool img_request_child_test(struct rbd_img_request *img_request); static void rbd_parent_request_destroy(struct kref *kref); static void rbd_img_request_destroy(struct kref *kref); @@ -2142,6 +2214,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request) img_request->next_completion = which; out: spin_unlock_irq(&img_request->completion_lock); + rbd_img_request_put(img_request); if (!more) rbd_img_request_complete(img_request); @@ -2242,6 +2315,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request, goto out_unwind; obj_request->osd_req = osd_req; obj_request->callback = rbd_img_obj_callback; + rbd_img_request_get(img_request); if (write_request) { osd_req_op_alloc_hint_init(osd_req, which, @@ -2872,56 +2946,55 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data) } /* - * Request sync osd watch/unwatch. The value of "start" determines - * whether a watch request is being initiated or torn down. + * Initiate a watch request, synchronously. */ -static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start) +static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev) { struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; struct rbd_obj_request *obj_request; int ret; - rbd_assert(start ^ !!rbd_dev->watch_event); - rbd_assert(start ^ !!rbd_dev->watch_request); + rbd_assert(!rbd_dev->watch_event); + rbd_assert(!rbd_dev->watch_request); - if (start) { - ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev, - &rbd_dev->watch_event); - if (ret < 0) - return ret; - rbd_assert(rbd_dev->watch_event != NULL); - } + ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev, + &rbd_dev->watch_event); + if (ret < 0) + return ret; + + rbd_assert(rbd_dev->watch_event); - ret = -ENOMEM; obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0, - OBJ_REQUEST_NODATA); - if (!obj_request) + OBJ_REQUEST_NODATA); + if (!obj_request) { + ret = -ENOMEM; goto out_cancel; + } obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1, obj_request); - if (!obj_request->osd_req) - goto out_cancel; + if (!obj_request->osd_req) { + ret = -ENOMEM; + goto out_put; + } - if (start) - ceph_osdc_set_request_linger(osdc, obj_request->osd_req); - else - ceph_osdc_unregister_linger_request(osdc, - rbd_dev->watch_request->osd_req); + ceph_osdc_set_request_linger(osdc, obj_request->osd_req); osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH, - rbd_dev->watch_event->cookie, 0, start ? 1 : 0); + rbd_dev->watch_event->cookie, 0, 1); rbd_osd_req_format_write(obj_request); ret = rbd_obj_request_submit(osdc, obj_request); if (ret) - goto out_cancel; + goto out_linger; + ret = rbd_obj_request_wait(obj_request); if (ret) - goto out_cancel; + goto out_linger; + ret = obj_request->result; if (ret) - goto out_cancel; + goto out_linger; /* * A watch request is set to linger, so the underlying osd @@ -2931,36 +3004,84 @@ static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start) * it. We'll drop that reference (below) after we've * unregistered it. */ - if (start) { - rbd_dev->watch_request = obj_request; + rbd_dev->watch_request = obj_request; - return 0; - } + return 0; - /* We have successfully torn down the watch request */ - - rbd_obj_request_put(rbd_dev->watch_request); - rbd_dev->watch_request = NULL; +out_linger: + ceph_osdc_unregister_linger_request(osdc, obj_request->osd_req); +out_put: + rbd_obj_request_put(obj_request); out_cancel: - /* Cancel the event if we're tearing down, or on error */ ceph_osdc_cancel_event(rbd_dev->watch_event); rbd_dev->watch_event = NULL; - if (obj_request) - rbd_obj_request_put(obj_request); return ret; } -static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev) +/* + * Tear down a watch request, synchronously. + */ +static int __rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev) { - return __rbd_dev_header_watch_sync(rbd_dev, true); + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + struct rbd_obj_request *obj_request; + int ret; + + rbd_assert(rbd_dev->watch_event); + rbd_assert(rbd_dev->watch_request); + + obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0, + OBJ_REQUEST_NODATA); + if (!obj_request) { + ret = -ENOMEM; + goto out_cancel; + } + + obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1, + obj_request); + if (!obj_request->osd_req) { + ret = -ENOMEM; + goto out_put; + } + + osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH, + rbd_dev->watch_event->cookie, 0, 0); + rbd_osd_req_format_write(obj_request); + + ret = rbd_obj_request_submit(osdc, obj_request); + if (ret) + goto out_put; + + ret = rbd_obj_request_wait(obj_request); + if (ret) + goto out_put; + + ret = obj_request->result; + if (ret) + goto out_put; + + /* We have successfully torn down the watch request */ + + ceph_osdc_unregister_linger_request(osdc, + rbd_dev->watch_request->osd_req); + rbd_obj_request_put(rbd_dev->watch_request); + rbd_dev->watch_request = NULL; + +out_put: + rbd_obj_request_put(obj_request); +out_cancel: + ceph_osdc_cancel_event(rbd_dev->watch_event); + rbd_dev->watch_event = NULL; + + return ret; } static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev) { int ret; - ret = __rbd_dev_header_watch_sync(rbd_dev, false); + ret = __rbd_dev_header_unwatch_sync(rbd_dev); if (ret) { rbd_warn(rbd_dev, "unable to tear down watch request: %d\n", ret); @@ -3058,7 +3179,6 @@ static void rbd_request_fn(struct request_queue *q) __releases(q->queue_lock) __acquires(q->queue_lock) { struct rbd_device *rbd_dev = q->queuedata; - bool read_only = rbd_dev->mapping.read_only; struct request *rq; int result; @@ -3094,7 +3214,7 @@ static void rbd_request_fn(struct request_queue *q) if (write_request) { result = -EROFS; - if (read_only) + if (rbd_dev->mapping.read_only) goto end_request; rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP); } @@ -4682,6 +4802,38 @@ static int rbd_add_parse_args(const char *buf, return ret; } +/* + * Return pool id (>= 0) or a negative error code. + */ +static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name) +{ + u64 newest_epoch; + unsigned long timeout = rbdc->client->options->mount_timeout * HZ; + int tries = 0; + int ret; + +again: + ret = ceph_pg_poolid_by_name(rbdc->client->osdc.osdmap, pool_name); + if (ret == -ENOENT && tries++ < 1) { + ret = ceph_monc_do_get_version(&rbdc->client->monc, "osdmap", + &newest_epoch); + if (ret < 0) + return ret; + + if (rbdc->client->osdc.osdmap->epoch < newest_epoch) { + ceph_monc_request_next_osdmap(&rbdc->client->monc); + (void) ceph_monc_wait_osdmap(&rbdc->client->monc, + newest_epoch, timeout); + goto again; + } else { + /* the osdmap we have is new enough */ + return -ENOENT; + } + } + + return ret; +} + /* * An rbd format 2 image has a unique identifier, distinct from the * name given to it by the user. Internally, that identifier is @@ -4752,7 +4904,7 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev) image_id = ceph_extract_encoded_string(&p, p + ret, NULL, GFP_NOIO); - ret = IS_ERR(image_id) ? PTR_ERR(image_id) : 0; + ret = PTR_ERR_OR_ZERO(image_id); if (!ret) rbd_dev->image_format = 2; } else { @@ -4907,6 +5059,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) if (ret) goto err_out_disk; set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE); + set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only); ret = rbd_bus_add_dev(rbd_dev); if (ret) @@ -5053,7 +5206,6 @@ static ssize_t do_rbd_add(struct bus_type *bus, struct rbd_options *rbd_opts = NULL; struct rbd_spec *spec = NULL; struct rbd_client *rbdc; - struct ceph_osd_client *osdc; bool read_only; int rc = -ENOMEM; @@ -5075,8 +5227,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, } /* pick the pool */ - osdc = &rbdc->client->osdc; - rc = ceph_pg_poolid_by_name(osdc->osdmap, spec->pool_name); + rc = rbd_add_get_pool_id(rbdc, spec->pool_name); if (rc < 0) goto err_out_client; spec->pool_id = (u64)rc; @@ -5387,6 +5538,7 @@ static int __init rbd_init(void) static void __exit rbd_exit(void) { + ida_destroy(&rbd_dev_id_ida); rbd_sysfs_cleanup(); if (single_major) unregister_blkdev(rbd_major, RBD_DRV_NAME); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index a83b57e57b63..f98380648cb3 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -193,9 +193,10 @@ static int ath3k_load_firmware(struct usb_device *udev, sent += 20; count -= 20; + pipe = usb_sndbulkpipe(udev, 0x02); + while (count) { size = min_t(uint, count, BULK_SIZE); - pipe = usb_sndbulkpipe(udev, 0x02); memcpy(send_buf, firmware->data + sent, size); err = usb_bulk_msg(udev, pipe, send_buf, size, diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h index 7399303d7d99..dc79f88f8717 100644 --- a/drivers/bluetooth/btmrvl_drv.h +++ b/drivers/bluetooth/btmrvl_drv.h @@ -59,6 +59,8 @@ struct btmrvl_device { }; struct btmrvl_adapter { + void *hw_regs_buf; + u8 *hw_regs; u32 int_count; struct sk_buff_head tx_queue; u8 psmode; @@ -140,7 +142,7 @@ void btmrvl_interrupt(struct btmrvl_private *priv); bool btmrvl_check_evtpkt(struct btmrvl_private *priv, struct sk_buff *skb); int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb); -int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd); +int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, u8 subcmd); int btmrvl_send_hscfg_cmd(struct btmrvl_private *priv); int btmrvl_enable_ps(struct btmrvl_private *priv); int btmrvl_prepare_command(struct btmrvl_private *priv); diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 2c4997ce2484..e9dbddb0b8f1 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -24,6 +24,7 @@ #include #include "btmrvl_drv.h" +#include "btmrvl_sdio.h" #define VERSION "1.0" @@ -201,7 +202,7 @@ static int btmrvl_send_sync_cmd(struct btmrvl_private *priv, u16 opcode, return 0; } -int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd) +int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, u8 subcmd) { int ret; @@ -337,10 +338,25 @@ static int btmrvl_tx_pkt(struct btmrvl_private *priv, struct sk_buff *skb) static void btmrvl_init_adapter(struct btmrvl_private *priv) { + int buf_size; + skb_queue_head_init(&priv->adapter->tx_queue); priv->adapter->ps_state = PS_AWAKE; + buf_size = ALIGN_SZ(SDIO_BLOCK_SIZE, BTSDIO_DMA_ALIGN); + priv->adapter->hw_regs_buf = kzalloc(buf_size, GFP_KERNEL); + if (!priv->adapter->hw_regs_buf) { + priv->adapter->hw_regs = NULL; + BT_ERR("Unable to allocate buffer for hw_regs."); + } else { + priv->adapter->hw_regs = + (u8 *)ALIGN_ADDR(priv->adapter->hw_regs_buf, + BTSDIO_DMA_ALIGN); + BT_DBG("hw_regs_buf=%p hw_regs=%p", + priv->adapter->hw_regs_buf, priv->adapter->hw_regs); + } + init_waitqueue_head(&priv->adapter->cmd_wait_q); } @@ -348,6 +364,7 @@ static void btmrvl_free_adapter(struct btmrvl_private *priv) { skb_queue_purge(&priv->adapter->tx_queue); + kfree(priv->adapter->hw_regs_buf); kfree(priv->adapter); priv->adapter = NULL; diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 1b52c9f5230d..9dedca516ff5 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -64,6 +64,7 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_8688 = { .io_port_0 = 0x00, .io_port_1 = 0x01, .io_port_2 = 0x02, + .int_read_to_clear = false, }; static const struct btmrvl_sdio_card_reg btmrvl_reg_87xx = { .cfg = 0x00, @@ -80,6 +81,7 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_87xx = { .io_port_0 = 0x78, .io_port_1 = 0x79, .io_port_2 = 0x7a, + .int_read_to_clear = false, }; static const struct btmrvl_sdio_card_reg btmrvl_reg_88xx = { @@ -97,6 +99,9 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_88xx = { .io_port_0 = 0xd8, .io_port_1 = 0xd9, .io_port_2 = 0xda, + .int_read_to_clear = true, + .host_int_rsr = 0x01, + .card_misc_cfg = 0xcc, }; static const struct btmrvl_sdio_device btmrvl_sdio_sd8688 = { @@ -667,6 +672,53 @@ static int btmrvl_sdio_process_int_status(struct btmrvl_private *priv) return 0; } +static int btmrvl_sdio_read_to_clear(struct btmrvl_sdio_card *card, u8 *ireg) +{ + struct btmrvl_adapter *adapter = card->priv->adapter; + int ret; + + ret = sdio_readsb(card->func, adapter->hw_regs, 0, SDIO_BLOCK_SIZE); + if (ret) { + BT_ERR("sdio_readsb: read int hw_regs failed: %d", ret); + return ret; + } + + *ireg = adapter->hw_regs[card->reg->host_intstatus]; + BT_DBG("hw_regs[%#x]=%#x", card->reg->host_intstatus, *ireg); + + return 0; +} + +static int btmrvl_sdio_write_to_clear(struct btmrvl_sdio_card *card, u8 *ireg) +{ + int ret; + + *ireg = sdio_readb(card->func, card->reg->host_intstatus, &ret); + if (ret) { + BT_ERR("sdio_readb: read int status failed: %d", ret); + return ret; + } + + if (*ireg) { + /* + * DN_LD_HOST_INT_STATUS and/or UP_LD_HOST_INT_STATUS + * Clear the interrupt status register and re-enable the + * interrupt. + */ + BT_DBG("int_status = 0x%x", *ireg); + + sdio_writeb(card->func, ~(*ireg) & (DN_LD_HOST_INT_STATUS | + UP_LD_HOST_INT_STATUS), + card->reg->host_intstatus, &ret); + if (ret) { + BT_ERR("sdio_writeb: clear int status failed: %d", ret); + return ret; + } + } + + return 0; +} + static void btmrvl_sdio_interrupt(struct sdio_func *func) { struct btmrvl_private *priv; @@ -684,28 +736,13 @@ static void btmrvl_sdio_interrupt(struct sdio_func *func) priv = card->priv; - ireg = sdio_readb(card->func, card->reg->host_intstatus, &ret); - if (ret) { - BT_ERR("sdio_readb: read int status register failed"); + if (card->reg->int_read_to_clear) + ret = btmrvl_sdio_read_to_clear(card, &ireg); + else + ret = btmrvl_sdio_write_to_clear(card, &ireg); + + if (ret) return; - } - - if (ireg != 0) { - /* - * DN_LD_HOST_INT_STATUS and/or UP_LD_HOST_INT_STATUS - * Clear the interrupt status register and re-enable the - * interrupt. - */ - BT_DBG("ireg = 0x%x", ireg); - - sdio_writeb(card->func, ~(ireg) & (DN_LD_HOST_INT_STATUS | - UP_LD_HOST_INT_STATUS), - card->reg->host_intstatus, &ret); - if (ret) { - BT_ERR("sdio_writeb: clear int status register failed"); - return; - } - } spin_lock_irqsave(&priv->driver_lock, flags); sdio_ireg |= ireg; @@ -777,6 +814,30 @@ static int btmrvl_sdio_register_dev(struct btmrvl_sdio_card *card) BT_DBG("SDIO FUNC%d IO port: 0x%x", func->num, card->ioport); + if (card->reg->int_read_to_clear) { + reg = sdio_readb(func, card->reg->host_int_rsr, &ret); + if (ret < 0) { + ret = -EIO; + goto release_irq; + } + sdio_writeb(func, reg | 0x3f, card->reg->host_int_rsr, &ret); + if (ret < 0) { + ret = -EIO; + goto release_irq; + } + + reg = sdio_readb(func, card->reg->card_misc_cfg, &ret); + if (ret < 0) { + ret = -EIO; + goto release_irq; + } + sdio_writeb(func, reg | 0x10, card->reg->card_misc_cfg, &ret); + if (ret < 0) { + ret = -EIO; + goto release_irq; + } + } + sdio_set_drvdata(func, card); sdio_release_host(func); diff --git a/drivers/bluetooth/btmrvl_sdio.h b/drivers/bluetooth/btmrvl_sdio.h index 43d35a609ca9..d4dd3b0fa53d 100644 --- a/drivers/bluetooth/btmrvl_sdio.h +++ b/drivers/bluetooth/btmrvl_sdio.h @@ -78,6 +78,9 @@ struct btmrvl_sdio_card_reg { u8 io_port_0; u8 io_port_1; u8 io_port_2; + bool int_read_to_clear; + u8 host_int_rsr; + u8 card_misc_cfg; }; struct btmrvl_sdio_card { diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a7dfbf9a3afb..a1c80b0c7663 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -49,6 +49,7 @@ static struct usb_driver btusb_driver; #define BTUSB_WRONG_SCO_MTU 0x40 #define BTUSB_ATH3012 0x80 #define BTUSB_INTEL 0x100 +#define BTUSB_BCM_PATCHRAM 0x200 static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -111,7 +112,8 @@ static const struct usb_device_id btusb_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01) }, /* Broadcom devices with vendor specific id */ - { USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, /* Belkin F8065bf - Broadcom based */ { USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) }, @@ -1381,6 +1383,154 @@ static int btusb_setup_intel(struct hci_dev *hdev) return 0; } +static int btusb_setup_bcm_patchram(struct hci_dev *hdev) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + struct usb_device *udev = data->udev; + char fw_name[64]; + const struct firmware *fw; + const u8 *fw_ptr; + size_t fw_size; + const struct hci_command_hdr *cmd; + const u8 *cmd_param; + u16 opcode; + struct sk_buff *skb; + struct hci_rp_read_local_version *ver; + long ret; + + snprintf(fw_name, sizeof(fw_name), "brcm/%s-%04x-%04x.hcd", + udev->product ? udev->product : "BCM", + le16_to_cpu(udev->descriptor.idVendor), + le16_to_cpu(udev->descriptor.idProduct)); + + ret = request_firmware(&fw, fw_name, &hdev->dev); + if (ret < 0) { + BT_INFO("%s: BCM: patch %s not found", hdev->name, + fw_name); + return 0; + } + + /* Reset */ + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: HCI_OP_RESET failed (%ld)", hdev->name, ret); + goto done; + } + kfree_skb(skb); + + /* Read Local Version Info */ + skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)", + hdev->name, ret); + goto done; + } + + if (skb->len != sizeof(*ver)) { + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch", + hdev->name); + kfree_skb(skb); + ret = -EIO; + goto done; + } + + ver = (struct hci_rp_read_local_version *) skb->data; + BT_INFO("%s: BCM: patching hci_ver=%02x hci_rev=%04x lmp_ver=%02x " + "lmp_subver=%04x", hdev->name, ver->hci_ver, ver->hci_rev, + ver->lmp_ver, ver->lmp_subver); + kfree_skb(skb); + + /* Start Download */ + skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: BCM: Download Minidrv command failed (%ld)", + hdev->name, ret); + goto reset_fw; + } + kfree_skb(skb); + + /* 50 msec delay after Download Minidrv completes */ + msleep(50); + + fw_ptr = fw->data; + fw_size = fw->size; + + while (fw_size >= sizeof(*cmd)) { + cmd = (struct hci_command_hdr *) fw_ptr; + fw_ptr += sizeof(*cmd); + fw_size -= sizeof(*cmd); + + if (fw_size < cmd->plen) { + BT_ERR("%s: BCM: patch %s is corrupted", + hdev->name, fw_name); + ret = -EINVAL; + goto reset_fw; + } + + cmd_param = fw_ptr; + fw_ptr += cmd->plen; + fw_size -= cmd->plen; + + opcode = le16_to_cpu(cmd->opcode); + + skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: BCM: patch command %04x failed (%ld)", + hdev->name, opcode, ret); + goto reset_fw; + } + kfree_skb(skb); + } + + /* 250 msec delay after Launch Ram completes */ + msleep(250); + +reset_fw: + /* Reset */ + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: HCI_OP_RESET failed (%ld)", hdev->name, ret); + goto done; + } + kfree_skb(skb); + + /* Read Local Version Info */ + skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)", + hdev->name, ret); + goto done; + } + + if (skb->len != sizeof(*ver)) { + BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch", + hdev->name); + kfree_skb(skb); + ret = -EIO; + goto done; + } + + ver = (struct hci_rp_read_local_version *) skb->data; + BT_INFO("%s: BCM: firmware hci_ver=%02x hci_rev=%04x lmp_ver=%02x " + "lmp_subver=%04x", hdev->name, ver->hci_ver, ver->hci_rev, + ver->lmp_ver, ver->lmp_subver); + kfree_skb(skb); + +done: + release_firmware(fw); + + return ret; +} + static int btusb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -1486,6 +1636,9 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_BCM92035) hdev->setup = btusb_setup_bcm92035; + if (id->driver_info & BTUSB_BCM_PATCHRAM) + hdev->setup = btusb_setup_bcm_patchram; + if (id->driver_info & BTUSB_INTEL) hdev->setup = btusb_setup_intel; diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index 7048a583fe51..66db9a803373 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -55,13 +55,6 @@ struct h4_struct { struct sk_buff_head txq; }; -/* H4 receiver States */ -#define H4_W4_PACKET_TYPE 0 -#define H4_W4_EVENT_HDR 1 -#define H4_W4_ACL_HDR 2 -#define H4_W4_SCO_HDR 3 -#define H4_W4_DATA 4 - /* Initialize protocol */ static int h4_open(struct hci_uart *hu) { diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 2ce0e225e58c..f3e71501de54 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -25,88 +25,115 @@ #include #include -static struct virtqueue *vq; -static unsigned int data_avail; -static DECLARE_COMPLETION(have_data); -static bool busy; +static DEFINE_IDA(rng_index_ida); + +struct virtrng_info { + struct virtio_device *vdev; + struct hwrng hwrng; + struct virtqueue *vq; + unsigned int data_avail; + struct completion have_data; + bool busy; + char name[25]; + int index; +}; static void random_recv_done(struct virtqueue *vq) { + struct virtrng_info *vi = vq->vdev->priv; + /* We can get spurious callbacks, e.g. shared IRQs + virtio_pci. */ - if (!virtqueue_get_buf(vq, &data_avail)) + if (!virtqueue_get_buf(vi->vq, &vi->data_avail)) return; - complete(&have_data); + complete(&vi->have_data); } /* The host will fill any buffer we give it with sweet, sweet randomness. */ -static void register_buffer(u8 *buf, size_t size) +static void register_buffer(struct virtrng_info *vi, u8 *buf, size_t size) { struct scatterlist sg; sg_init_one(&sg, buf, size); /* There should always be room for one buffer. */ - virtqueue_add_inbuf(vq, &sg, 1, buf, GFP_KERNEL); + virtqueue_add_inbuf(vi->vq, &sg, 1, buf, GFP_KERNEL); - virtqueue_kick(vq); + virtqueue_kick(vi->vq); } static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) { int ret; + struct virtrng_info *vi = (struct virtrng_info *)rng->priv; - if (!busy) { - busy = true; - init_completion(&have_data); - register_buffer(buf, size); + if (!vi->busy) { + vi->busy = true; + init_completion(&vi->have_data); + register_buffer(vi, buf, size); } if (!wait) return 0; - ret = wait_for_completion_killable(&have_data); + ret = wait_for_completion_killable(&vi->have_data); if (ret < 0) return ret; - busy = false; + vi->busy = false; - return data_avail; + return vi->data_avail; } static void virtio_cleanup(struct hwrng *rng) { - if (busy) - wait_for_completion(&have_data); + struct virtrng_info *vi = (struct virtrng_info *)rng->priv; + + if (vi->busy) + wait_for_completion(&vi->have_data); } - -static struct hwrng virtio_hwrng = { - .name = "virtio", - .cleanup = virtio_cleanup, - .read = virtio_read, -}; - static int probe_common(struct virtio_device *vdev) { - int err; + int err, index; + struct virtrng_info *vi = NULL; - if (vq) { - /* We only support one device for now */ - return -EBUSY; + vi = kzalloc(sizeof(struct virtrng_info), GFP_KERNEL); + if (!vi) + return -ENOMEM; + + vi->index = index = ida_simple_get(&rng_index_ida, 0, 0, GFP_KERNEL); + if (index < 0) { + kfree(vi); + return index; } + sprintf(vi->name, "virtio_rng.%d", index); + init_completion(&vi->have_data); + + vi->hwrng = (struct hwrng) { + .read = virtio_read, + .cleanup = virtio_cleanup, + .priv = (unsigned long)vi, + .name = vi->name, + }; + vdev->priv = vi; + /* We expect a single virtqueue. */ - vq = virtio_find_single_vq(vdev, random_recv_done, "input"); - if (IS_ERR(vq)) { - err = PTR_ERR(vq); - vq = NULL; + vi->vq = virtio_find_single_vq(vdev, random_recv_done, "input"); + if (IS_ERR(vi->vq)) { + err = PTR_ERR(vi->vq); + vi->vq = NULL; + kfree(vi); + ida_simple_remove(&rng_index_ida, index); return err; } - err = hwrng_register(&virtio_hwrng); + err = hwrng_register(&vi->hwrng); if (err) { vdev->config->del_vqs(vdev); - vq = NULL; + vi->vq = NULL; + kfree(vi); + ida_simple_remove(&rng_index_ida, index); return err; } @@ -115,11 +142,13 @@ static int probe_common(struct virtio_device *vdev) static void remove_common(struct virtio_device *vdev) { + struct virtrng_info *vi = vdev->priv; vdev->config->reset(vdev); - busy = false; - hwrng_unregister(&virtio_hwrng); + vi->busy = false; + hwrng_unregister(&vi->hwrng); vdev->config->del_vqs(vdev); - vq = NULL; + ida_simple_remove(&rng_index_ida, vi->index); + kfree(vi); } static int virtrng_probe(struct virtio_device *vdev) diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 6e8d65e9b1d3..0102dc788608 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -284,10 +284,10 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd, #endif static const struct file_operations raw_fops = { - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = blkdev_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = blkdev_write_iter, .fsync = blkdev_fsync, .open = raw_open, .release = raw_release, diff --git a/drivers/clk/sunxi/Makefile b/drivers/clk/sunxi/Makefile index b5bac917612c..762fd64dbd1f 100644 --- a/drivers/clk/sunxi/Makefile +++ b/drivers/clk/sunxi/Makefile @@ -3,3 +3,7 @@ # obj-y += clk-sunxi.o clk-factors.o +obj-y += clk-a10-hosc.o +obj-y += clk-a20-gmac.o + +obj-$(CONFIG_MFD_SUN6I_PRCM) += clk-sun6i-ar100.o clk-sun6i-apb0.o clk-sun6i-apb0-gates.o diff --git a/drivers/clk/sunxi/clk-a10-hosc.c b/drivers/clk/sunxi/clk-a10-hosc.c new file mode 100644 index 000000000000..0481d5d673d6 --- /dev/null +++ b/drivers/clk/sunxi/clk-a10-hosc.c @@ -0,0 +1,73 @@ +/* + * Copyright 2013 Emilio López + * + * Emilio López + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include + +#define SUNXI_OSC24M_GATE 0 + +static DEFINE_SPINLOCK(hosc_lock); + +static void __init sun4i_osc_clk_setup(struct device_node *node) +{ + struct clk *clk; + struct clk_fixed_rate *fixed; + struct clk_gate *gate; + const char *clk_name = node->name; + u32 rate; + + if (of_property_read_u32(node, "clock-frequency", &rate)) + return; + + /* allocate fixed-rate and gate clock structs */ + fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL); + if (!fixed) + return; + gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL); + if (!gate) + goto err_free_fixed; + + of_property_read_string(node, "clock-output-names", &clk_name); + + /* set up gate and fixed rate properties */ + gate->reg = of_iomap(node, 0); + gate->bit_idx = SUNXI_OSC24M_GATE; + gate->lock = &hosc_lock; + fixed->fixed_rate = rate; + + clk = clk_register_composite(NULL, clk_name, + NULL, 0, + NULL, NULL, + &fixed->hw, &clk_fixed_rate_ops, + &gate->hw, &clk_gate_ops, + CLK_IS_ROOT); + + if (IS_ERR(clk)) + goto err_free_gate; + + of_clk_add_provider(node, of_clk_src_simple_get, clk); + clk_register_clkdev(clk, clk_name, NULL); + + return; + +err_free_gate: + kfree(gate); +err_free_fixed: + kfree(fixed); +} +CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup); diff --git a/drivers/clk/sunxi/clk-a20-gmac.c b/drivers/clk/sunxi/clk-a20-gmac.c new file mode 100644 index 000000000000..633ddc4389ef --- /dev/null +++ b/drivers/clk/sunxi/clk-a20-gmac.c @@ -0,0 +1,119 @@ +/* + * Copyright 2013 Emilio López + * Emilio López + * + * Copyright 2013 Chen-Yu Tsai + * Chen-Yu Tsai + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(gmac_lock); + +/** + * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module + * + * This clock looks something like this + * ________________________ + * MII TX clock from PHY >-----|___________ _________|----> to GMAC core + * GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY + * Ext. 125MHz RGMII TX clk >--|__divider__/ | + * |________________________| + * + * The external 125 MHz reference is optional, i.e. GMAC can use its + * internal TX clock just fine. The A31 GMAC clock module does not have + * the divider controls for the external reference. + * + * To keep it simple, let the GMAC use either the MII TX clock for MII mode, + * and its internal TX clock for GMII and RGMII modes. The GMAC driver should + * select the appropriate source and gate/ungate the output to the PHY. + * + * Only the GMAC should use this clock. Altering the clock so that it doesn't + * match the GMAC's operation parameters will result in the GMAC not being + * able to send traffic out. The GMAC driver should set the clock rate and + * enable/disable this clock to configure the required state. The clock + * driver then responds by auto-reparenting the clock. + */ + +#define SUN7I_A20_GMAC_GPIT 2 +#define SUN7I_A20_GMAC_MASK 0x3 +#define SUN7I_A20_GMAC_PARENTS 2 + +static void __init sun7i_a20_gmac_clk_setup(struct device_node *node) +{ + struct clk *clk; + struct clk_mux *mux; + struct clk_gate *gate; + const char *clk_name = node->name; + const char *parents[SUN7I_A20_GMAC_PARENTS]; + void *reg; + + if (of_property_read_string(node, "clock-output-names", &clk_name)) + return; + + /* allocate mux and gate clock structs */ + mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL); + if (!mux) + return; + + gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL); + if (!gate) + goto free_mux; + + /* gmac clock requires exactly 2 parents */ + parents[0] = of_clk_get_parent_name(node, 0); + parents[1] = of_clk_get_parent_name(node, 1); + if (!parents[0] || !parents[1]) + goto free_gate; + + reg = of_iomap(node, 0); + if (!reg) + goto free_gate; + + /* set up gate and fixed rate properties */ + gate->reg = reg; + gate->bit_idx = SUN7I_A20_GMAC_GPIT; + gate->lock = &gmac_lock; + mux->reg = reg; + mux->mask = SUN7I_A20_GMAC_MASK; + mux->flags = CLK_MUX_INDEX_BIT; + mux->lock = &gmac_lock; + + clk = clk_register_composite(NULL, clk_name, + parents, SUN7I_A20_GMAC_PARENTS, + &mux->hw, &clk_mux_ops, + NULL, NULL, + &gate->hw, &clk_gate_ops, + 0); + + if (IS_ERR(clk)) + goto iounmap_reg; + + of_clk_add_provider(node, of_clk_src_simple_get, clk); + clk_register_clkdev(clk, clk_name, NULL); + + return; + +iounmap_reg: + iounmap(reg); +free_gate: + kfree(gate); +free_mux: + kfree(mux); +} +CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk", + sun7i_a20_gmac_clk_setup); diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c new file mode 100644 index 000000000000..44cd27c5c401 --- /dev/null +++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c @@ -0,0 +1,99 @@ +/* + * Copyright (C) 2014 Free Electrons + * + * License Terms: GNU General Public License v2 + * Author: Boris BREZILLON + * + * Allwinner A31 APB0 clock gates driver + * + */ + +#include +#include +#include +#include + +#define SUN6I_APB0_GATES_MAX_SIZE 32 + +static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct clk_onecell_data *clk_data; + const char *clk_parent; + const char *clk_name; + struct resource *r; + void __iomem *reg; + int gate_id; + int ngates; + int i; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + reg = devm_ioremap_resource(&pdev->dev, r); + if (!reg) + return PTR_ERR(reg); + + clk_parent = of_clk_get_parent_name(np, 0); + if (!clk_parent) + return -EINVAL; + + ngates = of_property_count_strings(np, "clock-output-names"); + if (ngates < 0) + return ngates; + + if (!ngates || ngates > SUN6I_APB0_GATES_MAX_SIZE) + return -EINVAL; + + clk_data = devm_kzalloc(&pdev->dev, sizeof(struct clk_onecell_data), + GFP_KERNEL); + if (!clk_data) + return -ENOMEM; + + clk_data->clks = devm_kzalloc(&pdev->dev, + SUN6I_APB0_GATES_MAX_SIZE * + sizeof(struct clk *), + GFP_KERNEL); + if (!clk_data->clks) + return -ENOMEM; + + for (i = 0; i < ngates; i++) { + of_property_read_string_index(np, "clock-output-names", + i, &clk_name); + + gate_id = i; + of_property_read_u32_index(np, "clock-indices", i, &gate_id); + + WARN_ON(gate_id >= SUN6I_APB0_GATES_MAX_SIZE); + if (gate_id >= SUN6I_APB0_GATES_MAX_SIZE) + continue; + + clk_data->clks[gate_id] = clk_register_gate(&pdev->dev, + clk_name, + clk_parent, 0, + reg, gate_id, + 0, NULL); + WARN_ON(IS_ERR(clk_data->clks[gate_id])); + } + + clk_data->clk_num = ngates; + + return of_clk_add_provider(np, of_clk_src_onecell_get, clk_data); +} + +const struct of_device_id sun6i_a31_apb0_gates_clk_dt_ids[] = { + { .compatible = "allwinner,sun6i-a31-apb0-gates-clk" }, + { /* sentinel */ } +}; + +static struct platform_driver sun6i_a31_apb0_gates_clk_driver = { + .driver = { + .name = "sun6i-a31-apb0-gates-clk", + .owner = THIS_MODULE, + .of_match_table = sun6i_a31_apb0_gates_clk_dt_ids, + }, + .probe = sun6i_a31_apb0_gates_clk_probe, +}; +module_platform_driver(sun6i_a31_apb0_gates_clk_driver); + +MODULE_AUTHOR("Boris BREZILLON "); +MODULE_DESCRIPTION("Allwinner A31 APB0 gate clocks driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/sunxi/clk-sun6i-apb0.c b/drivers/clk/sunxi/clk-sun6i-apb0.c new file mode 100644 index 000000000000..11f17c34c2ae --- /dev/null +++ b/drivers/clk/sunxi/clk-sun6i-apb0.c @@ -0,0 +1,77 @@ +/* + * Copyright (C) 2014 Free Electrons + * + * License Terms: GNU General Public License v2 + * Author: Boris BREZILLON + * + * Allwinner A31 APB0 clock driver + * + */ + +#include +#include +#include +#include + +/* + * The APB0 clk has a configurable divisor. + * + * We must use a clk_div_table and not a regular power of 2 + * divisor here, because the first 2 values divide the clock + * by 2. + */ +static const struct clk_div_table sun6i_a31_apb0_divs[] = { + { .val = 0, .div = 2, }, + { .val = 1, .div = 2, }, + { .val = 2, .div = 4, }, + { .val = 3, .div = 8, }, + { /* sentinel */ }, +}; + +static int sun6i_a31_apb0_clk_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + const char *clk_name = np->name; + const char *clk_parent; + struct resource *r; + void __iomem *reg; + struct clk *clk; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + reg = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(reg)) + return PTR_ERR(reg); + + clk_parent = of_clk_get_parent_name(np, 0); + if (!clk_parent) + return -EINVAL; + + of_property_read_string(np, "clock-output-names", &clk_name); + + clk = clk_register_divider_table(&pdev->dev, clk_name, clk_parent, + 0, reg, 0, 2, 0, sun6i_a31_apb0_divs, + NULL); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + return of_clk_add_provider(np, of_clk_src_simple_get, clk); +} + +const struct of_device_id sun6i_a31_apb0_clk_dt_ids[] = { + { .compatible = "allwinner,sun6i-a31-apb0-clk" }, + { /* sentinel */ } +}; + +static struct platform_driver sun6i_a31_apb0_clk_driver = { + .driver = { + .name = "sun6i-a31-apb0-clk", + .owner = THIS_MODULE, + .of_match_table = sun6i_a31_apb0_clk_dt_ids, + }, + .probe = sun6i_a31_apb0_clk_probe, +}; +module_platform_driver(sun6i_a31_apb0_clk_driver); + +MODULE_AUTHOR("Boris BREZILLON "); +MODULE_DESCRIPTION("Allwinner A31 APB0 clock Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c new file mode 100644 index 000000000000..f73cc051f0dd --- /dev/null +++ b/drivers/clk/sunxi/clk-sun6i-ar100.c @@ -0,0 +1,233 @@ +/* + * Copyright (C) 2014 Free Electrons + * + * License Terms: GNU General Public License v2 + * Author: Boris BREZILLON + * + * Allwinner A31 AR100 clock driver + * + */ + +#include +#include +#include +#include + +#define SUN6I_AR100_MAX_PARENTS 4 +#define SUN6I_AR100_SHIFT_MASK 0x3 +#define SUN6I_AR100_SHIFT_MAX SUN6I_AR100_SHIFT_MASK +#define SUN6I_AR100_SHIFT_SHIFT 4 +#define SUN6I_AR100_DIV_MASK 0x1f +#define SUN6I_AR100_DIV_MAX (SUN6I_AR100_DIV_MASK + 1) +#define SUN6I_AR100_DIV_SHIFT 8 +#define SUN6I_AR100_MUX_MASK 0x3 +#define SUN6I_AR100_MUX_SHIFT 16 + +struct ar100_clk { + struct clk_hw hw; + void __iomem *reg; +}; + +static inline struct ar100_clk *to_ar100_clk(struct clk_hw *hw) +{ + return container_of(hw, struct ar100_clk, hw); +} + +static unsigned long ar100_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct ar100_clk *clk = to_ar100_clk(hw); + u32 val = readl(clk->reg); + int shift = (val >> SUN6I_AR100_SHIFT_SHIFT) & SUN6I_AR100_SHIFT_MASK; + int div = (val >> SUN6I_AR100_DIV_SHIFT) & SUN6I_AR100_DIV_MASK; + + return (parent_rate >> shift) / (div + 1); +} + +static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *best_parent_rate, + struct clk **best_parent_clk) +{ + int nparents = __clk_get_num_parents(hw->clk); + long best_rate = -EINVAL; + int i; + + *best_parent_clk = NULL; + + for (i = 0; i < nparents; i++) { + unsigned long parent_rate; + unsigned long tmp_rate; + struct clk *parent; + unsigned long div; + int shift; + + parent = clk_get_parent_by_index(hw->clk, i); + parent_rate = __clk_get_rate(parent); + div = DIV_ROUND_UP(parent_rate, rate); + + /* + * The AR100 clk contains 2 divisors: + * - one power of 2 divisor + * - one regular divisor + * + * First check if we can safely shift (or divide by a power + * of 2) without losing precision on the requested rate. + */ + shift = ffs(div) - 1; + if (shift > SUN6I_AR100_SHIFT_MAX) + shift = SUN6I_AR100_SHIFT_MAX; + + div >>= shift; + + /* + * Then if the divisor is still bigger than what the HW + * actually supports, use a bigger shift (or power of 2 + * divider) value and accept to lose some precision. + */ + while (div > SUN6I_AR100_DIV_MAX) { + shift++; + div >>= 1; + if (shift > SUN6I_AR100_SHIFT_MAX) + break; + } + + /* + * If the shift value (or power of 2 divider) is bigger + * than what the HW actually support, skip this parent. + */ + if (shift > SUN6I_AR100_SHIFT_MAX) + continue; + + tmp_rate = (parent_rate >> shift) / div; + if (!*best_parent_clk || tmp_rate > best_rate) { + *best_parent_clk = parent; + *best_parent_rate = parent_rate; + best_rate = tmp_rate; + } + } + + return best_rate; +} + +static int ar100_set_parent(struct clk_hw *hw, u8 index) +{ + struct ar100_clk *clk = to_ar100_clk(hw); + u32 val = readl(clk->reg); + + if (index >= SUN6I_AR100_MAX_PARENTS) + return -EINVAL; + + val &= ~(SUN6I_AR100_MUX_MASK << SUN6I_AR100_MUX_SHIFT); + val |= (index << SUN6I_AR100_MUX_SHIFT); + writel(val, clk->reg); + + return 0; +} + +static u8 ar100_get_parent(struct clk_hw *hw) +{ + struct ar100_clk *clk = to_ar100_clk(hw); + return (readl(clk->reg) >> SUN6I_AR100_MUX_SHIFT) & + SUN6I_AR100_MUX_MASK; +} + +static int ar100_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + unsigned long div = parent_rate / rate; + struct ar100_clk *clk = to_ar100_clk(hw); + u32 val = readl(clk->reg); + int shift; + + if (parent_rate % rate) + return -EINVAL; + + shift = ffs(div) - 1; + if (shift > SUN6I_AR100_SHIFT_MAX) + shift = SUN6I_AR100_SHIFT_MAX; + + div >>= shift; + + if (div > SUN6I_AR100_DIV_MAX) + return -EINVAL; + + val &= ~((SUN6I_AR100_SHIFT_MASK << SUN6I_AR100_SHIFT_SHIFT) | + (SUN6I_AR100_DIV_MASK << SUN6I_AR100_DIV_SHIFT)); + val |= (shift << SUN6I_AR100_SHIFT_SHIFT) | + (div << SUN6I_AR100_DIV_SHIFT); + writel(val, clk->reg); + + return 0; +} + +struct clk_ops ar100_ops = { + .recalc_rate = ar100_recalc_rate, + .determine_rate = ar100_determine_rate, + .set_parent = ar100_set_parent, + .get_parent = ar100_get_parent, + .set_rate = ar100_set_rate, +}; + +static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev) +{ + const char *parents[SUN6I_AR100_MAX_PARENTS]; + struct device_node *np = pdev->dev.of_node; + const char *clk_name = np->name; + struct clk_init_data init; + struct ar100_clk *ar100; + struct resource *r; + struct clk *clk; + int nparents; + int i; + + ar100 = devm_kzalloc(&pdev->dev, sizeof(*ar100), GFP_KERNEL); + if (!ar100) + return -ENOMEM; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ar100->reg = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(ar100->reg)) + return PTR_ERR(ar100->reg); + + nparents = of_clk_get_parent_count(np); + if (nparents > SUN6I_AR100_MAX_PARENTS) + nparents = SUN6I_AR100_MAX_PARENTS; + + for (i = 0; i < nparents; i++) + parents[i] = of_clk_get_parent_name(np, i); + + of_property_read_string(np, "clock-output-names", &clk_name); + + init.name = clk_name; + init.ops = &ar100_ops; + init.parent_names = parents; + init.num_parents = nparents; + init.flags = 0; + + ar100->hw.init = &init; + + clk = clk_register(&pdev->dev, &ar100->hw); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + return of_clk_add_provider(np, of_clk_src_simple_get, clk); +} + +const struct of_device_id sun6i_a31_ar100_clk_dt_ids[] = { + { .compatible = "allwinner,sun6i-a31-ar100-clk" }, + { /* sentinel */ } +}; + +static struct platform_driver sun6i_a31_ar100_clk_driver = { + .driver = { + .name = "sun6i-a31-ar100-clk", + .owner = THIS_MODULE, + .of_match_table = sun6i_a31_ar100_clk_dt_ids, + }, + .probe = sun6i_a31_ar100_clk_probe, +}; +module_platform_driver(sun6i_a31_ar100_clk_driver); + +MODULE_AUTHOR("Boris BREZILLON "); +MODULE_DESCRIPTION("Allwinner A31 AR100 clock Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index 426483422d3d..fb2ce8440f0e 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -27,63 +27,6 @@ static DEFINE_SPINLOCK(clk_lock); /* Maximum number of parents our clocks have */ #define SUNXI_MAX_PARENTS 5 -/** - * sun4i_osc_clk_setup() - Setup function for gatable oscillator - */ - -#define SUNXI_OSC24M_GATE 0 - -static void __init sun4i_osc_clk_setup(struct device_node *node) -{ - struct clk *clk; - struct clk_fixed_rate *fixed; - struct clk_gate *gate; - const char *clk_name = node->name; - u32 rate; - - if (of_property_read_u32(node, "clock-frequency", &rate)) - return; - - /* allocate fixed-rate and gate clock structs */ - fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL); - if (!fixed) - return; - gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL); - if (!gate) - goto err_free_fixed; - - of_property_read_string(node, "clock-output-names", &clk_name); - - /* set up gate and fixed rate properties */ - gate->reg = of_iomap(node, 0); - gate->bit_idx = SUNXI_OSC24M_GATE; - gate->lock = &clk_lock; - fixed->fixed_rate = rate; - - clk = clk_register_composite(NULL, clk_name, - NULL, 0, - NULL, NULL, - &fixed->hw, &clk_fixed_rate_ops, - &gate->hw, &clk_gate_ops, - CLK_IS_ROOT); - - if (IS_ERR(clk)) - goto err_free_gate; - - of_clk_add_provider(node, of_clk_src_simple_get, clk); - clk_register_clkdev(clk, clk_name, NULL); - - return; - -err_free_gate: - kfree(gate); -err_free_fixed: - kfree(fixed); -} -CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup); - - - /** * sun4i_get_pll1_factors() - calculates n, k, m, p factors for PLL1 * PLL1 rate is calculated as follows @@ -408,104 +351,6 @@ static void sun7i_a20_get_out_factors(u32 *freq, u32 parent_rate, *p = calcp; } - - -/** - * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module - * - * This clock looks something like this - * ________________________ - * MII TX clock from PHY >-----|___________ _________|----> to GMAC core - * GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY - * Ext. 125MHz RGMII TX clk >--|__divider__/ | - * |________________________| - * - * The external 125 MHz reference is optional, i.e. GMAC can use its - * internal TX clock just fine. The A31 GMAC clock module does not have - * the divider controls for the external reference. - * - * To keep it simple, let the GMAC use either the MII TX clock for MII mode, - * and its internal TX clock for GMII and RGMII modes. The GMAC driver should - * select the appropriate source and gate/ungate the output to the PHY. - * - * Only the GMAC should use this clock. Altering the clock so that it doesn't - * match the GMAC's operation parameters will result in the GMAC not being - * able to send traffic out. The GMAC driver should set the clock rate and - * enable/disable this clock to configure the required state. The clock - * driver then responds by auto-reparenting the clock. - */ - -#define SUN7I_A20_GMAC_GPIT 2 -#define SUN7I_A20_GMAC_MASK 0x3 -#define SUN7I_A20_GMAC_PARENTS 2 - -static void __init sun7i_a20_gmac_clk_setup(struct device_node *node) -{ - struct clk *clk; - struct clk_mux *mux; - struct clk_gate *gate; - const char *clk_name = node->name; - const char *parents[SUN7I_A20_GMAC_PARENTS]; - void *reg; - - if (of_property_read_string(node, "clock-output-names", &clk_name)) - return; - - /* allocate mux and gate clock structs */ - mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL); - if (!mux) - return; - - gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL); - if (!gate) - goto free_mux; - - /* gmac clock requires exactly 2 parents */ - parents[0] = of_clk_get_parent_name(node, 0); - parents[1] = of_clk_get_parent_name(node, 1); - if (!parents[0] || !parents[1]) - goto free_gate; - - reg = of_iomap(node, 0); - if (!reg) - goto free_gate; - - /* set up gate and fixed rate properties */ - gate->reg = reg; - gate->bit_idx = SUN7I_A20_GMAC_GPIT; - gate->lock = &clk_lock; - mux->reg = reg; - mux->mask = SUN7I_A20_GMAC_MASK; - mux->flags = CLK_MUX_INDEX_BIT; - mux->lock = &clk_lock; - - clk = clk_register_composite(NULL, clk_name, - parents, SUN7I_A20_GMAC_PARENTS, - &mux->hw, &clk_mux_ops, - NULL, NULL, - &gate->hw, &clk_gate_ops, - 0); - - if (IS_ERR(clk)) - goto iounmap_reg; - - of_clk_add_provider(node, of_clk_src_simple_get, clk); - clk_register_clkdev(clk, clk_name, NULL); - - return; - -iounmap_reg: - iounmap(reg); -free_gate: - kfree(gate); -free_mux: - kfree(mux); -} -CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk", - sun7i_a20_gmac_clk_setup); - - - /** * clk_sunxi_mmc_phase_control() - configures MMC clock phase control */ @@ -1009,6 +854,11 @@ static const struct gates_data sun5i_a13_usb_gates_data __initconst = { .reset_mask = 0x03, }; +static const struct gates_data sun6i_a31_usb_gates_data __initconst = { + .mask = { BIT(18) | BIT(17) | BIT(16) | BIT(10) | BIT(9) | BIT(8) }, + .reset_mask = BIT(2) | BIT(1) | BIT(0), +}; + static void __init sunxi_gates_clk_setup(struct device_node *node, struct gates_data *data) { @@ -1304,6 +1154,7 @@ static const struct of_device_id clk_gates_match[] __initconst = { {.compatible = "allwinner,sun6i-a31-apb2-gates-clk", .data = &sun6i_a31_apb2_gates_data,}, {.compatible = "allwinner,sun4i-a10-usb-clk", .data = &sun4i_a10_usb_gates_data,}, {.compatible = "allwinner,sun5i-a13-usb-clk", .data = &sun5i_a13_usb_gates_data,}, + {.compatible = "allwinner,sun6i-a31-usb-clk", .data = &sun6i_a31_usb_gates_data,}, {} }; @@ -1321,33 +1172,10 @@ static void __init of_sunxi_table_clock_setup(const struct of_device_id *clk_mat } } -/** - * System clock protection - * - * By enabling these critical clocks, we prevent their accidental gating - * by the framework - */ -static void __init sunxi_clock_protect(void) +static void __init sunxi_init_clocks(const char *clocks[], int nclocks) { - struct clk *clk; + unsigned int i; - /* memory bus clock - sun5i+ */ - clk = clk_get(NULL, "mbus"); - if (!IS_ERR(clk)) { - clk_prepare_enable(clk); - clk_put(clk); - } - - /* DDR clock - sun4i+ */ - clk = clk_get(NULL, "pll5_ddr"); - if (!IS_ERR(clk)) { - clk_prepare_enable(clk); - clk_put(clk); - } -} - -static void __init sunxi_init_clocks(struct device_node *np) -{ /* Register factor clocks */ of_sunxi_table_clock_setup(clk_factors_match, sunxi_factors_clk_setup); @@ -1363,11 +1191,48 @@ static void __init sunxi_init_clocks(struct device_node *np) /* Register gate clocks */ of_sunxi_table_clock_setup(clk_gates_match, sunxi_gates_clk_setup); - /* Enable core system clocks */ - sunxi_clock_protect(); + /* Protect the clocks that needs to stay on */ + for (i = 0; i < nclocks; i++) { + struct clk *clk = clk_get(NULL, clocks[i]); + + if (!IS_ERR(clk)) + clk_prepare_enable(clk); + } } -CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sunxi_init_clocks); -CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sunxi_init_clocks); -CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sunxi_init_clocks); -CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sunxi_init_clocks); -CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sunxi_init_clocks); + +static const char *sun4i_a10_critical_clocks[] __initdata = { + "pll5_ddr", +}; + +static void __init sun4i_a10_init_clocks(struct device_node *node) +{ + sunxi_init_clocks(sun4i_a10_critical_clocks, + ARRAY_SIZE(sun4i_a10_critical_clocks)); +} +CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sun4i_a10_init_clocks); + +static const char *sun5i_critical_clocks[] __initdata = { + "mbus", + "pll5_ddr", +}; + +static void __init sun5i_init_clocks(struct device_node *node) +{ + sunxi_init_clocks(sun5i_critical_clocks, + ARRAY_SIZE(sun5i_critical_clocks)); +} +CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sun5i_init_clocks); +CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sun5i_init_clocks); +CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sun5i_init_clocks); + +static const char *sun6i_critical_clocks[] __initdata = { + "cpu", + "ahb1_sdram", +}; + +static void __init sun6i_init_clocks(struct device_node *node) +{ + sunxi_init_clocks(sun6i_critical_clocks, + ARRAY_SIZE(sun6i_critical_clocks)); +} +CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks); diff --git a/drivers/clk/ti/Makefile b/drivers/clk/ti/Makefile index 4319d4031aa3..ed4d0aaf8916 100644 --- a/drivers/clk/ti/Makefile +++ b/drivers/clk/ti/Makefile @@ -3,9 +3,11 @@ obj-y += clk.o autoidle.o clockdomain.o clk-common = dpll.o composite.o divider.o gate.o \ fixed-factor.o mux.o apll.o obj-$(CONFIG_SOC_AM33XX) += $(clk-common) clk-33xx.o +obj-$(CONFIG_ARCH_OMAP2) += $(clk-common) interface.o clk-2xxx.o obj-$(CONFIG_ARCH_OMAP3) += $(clk-common) interface.o clk-3xxx.o obj-$(CONFIG_ARCH_OMAP4) += $(clk-common) clk-44xx.o obj-$(CONFIG_SOC_OMAP5) += $(clk-common) clk-54xx.o -obj-$(CONFIG_SOC_DRA7XX) += $(clk-common) clk-7xx.o +obj-$(CONFIG_SOC_DRA7XX) += $(clk-common) clk-7xx.o \ + clk-dra7-atl.o obj-$(CONFIG_SOC_AM43XX) += $(clk-common) clk-43xx.o endif diff --git a/drivers/clk/ti/apll.c b/drivers/clk/ti/apll.c index b986f61f5a77..5428c9c547cd 100644 --- a/drivers/clk/ti/apll.c +++ b/drivers/clk/ti/apll.c @@ -221,3 +221,184 @@ static void __init of_dra7_apll_setup(struct device_node *node) kfree(init); } CLK_OF_DECLARE(dra7_apll_clock, "ti,dra7-apll-clock", of_dra7_apll_setup); + +#define OMAP2_EN_APLL_LOCKED 0x3 +#define OMAP2_EN_APLL_STOPPED 0x0 + +static int omap2_apll_is_enabled(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + struct dpll_data *ad = clk->dpll_data; + u32 v; + + v = ti_clk_ll_ops->clk_readl(ad->control_reg); + v &= ad->enable_mask; + + v >>= __ffs(ad->enable_mask); + + return v == OMAP2_EN_APLL_LOCKED ? 1 : 0; +} + +static unsigned long omap2_apll_recalc(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + + if (omap2_apll_is_enabled(hw)) + return clk->fixed_rate; + + return 0; +} + +static int omap2_apll_enable(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + struct dpll_data *ad = clk->dpll_data; + u32 v; + int i = 0; + + v = ti_clk_ll_ops->clk_readl(ad->control_reg); + v &= ~ad->enable_mask; + v |= OMAP2_EN_APLL_LOCKED << __ffs(ad->enable_mask); + ti_clk_ll_ops->clk_writel(v, ad->control_reg); + + while (1) { + v = ti_clk_ll_ops->clk_readl(ad->idlest_reg); + if (v & ad->idlest_mask) + break; + if (i > MAX_APLL_WAIT_TRIES) + break; + i++; + udelay(1); + } + + if (i == MAX_APLL_WAIT_TRIES) { + pr_warn("%s failed to transition to locked\n", + __clk_get_name(clk->hw.clk)); + return -EBUSY; + } + + return 0; +} + +static void omap2_apll_disable(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + struct dpll_data *ad = clk->dpll_data; + u32 v; + + v = ti_clk_ll_ops->clk_readl(ad->control_reg); + v &= ~ad->enable_mask; + v |= OMAP2_EN_APLL_STOPPED << __ffs(ad->enable_mask); + ti_clk_ll_ops->clk_writel(v, ad->control_reg); +} + +static struct clk_ops omap2_apll_ops = { + .enable = &omap2_apll_enable, + .disable = &omap2_apll_disable, + .is_enabled = &omap2_apll_is_enabled, + .recalc_rate = &omap2_apll_recalc, +}; + +static void omap2_apll_set_autoidle(struct clk_hw_omap *clk, u32 val) +{ + struct dpll_data *ad = clk->dpll_data; + u32 v; + + v = ti_clk_ll_ops->clk_readl(ad->autoidle_reg); + v &= ~ad->autoidle_mask; + v |= val << __ffs(ad->autoidle_mask); + ti_clk_ll_ops->clk_writel(v, ad->control_reg); +} + +#define OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP 0x3 +#define OMAP2_APLL_AUTOIDLE_DISABLE 0x0 + +static void omap2_apll_allow_idle(struct clk_hw_omap *clk) +{ + omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP); +} + +static void omap2_apll_deny_idle(struct clk_hw_omap *clk) +{ + omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_DISABLE); +} + +static struct clk_hw_omap_ops omap2_apll_hwops = { + .allow_idle = &omap2_apll_allow_idle, + .deny_idle = &omap2_apll_deny_idle, +}; + +static void __init of_omap2_apll_setup(struct device_node *node) +{ + struct dpll_data *ad = NULL; + struct clk_hw_omap *clk_hw = NULL; + struct clk_init_data *init = NULL; + struct clk *clk; + const char *parent_name; + u32 val; + + ad = kzalloc(sizeof(*clk_hw), GFP_KERNEL); + clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL); + init = kzalloc(sizeof(*init), GFP_KERNEL); + + if (!ad || !clk_hw || !init) + goto cleanup; + + clk_hw->dpll_data = ad; + clk_hw->hw.init = init; + init->ops = &omap2_apll_ops; + init->name = node->name; + clk_hw->ops = &omap2_apll_hwops; + + init->num_parents = of_clk_get_parent_count(node); + if (init->num_parents != 1) { + pr_err("%s must have one parent\n", node->name); + goto cleanup; + } + + parent_name = of_clk_get_parent_name(node, 0); + init->parent_names = &parent_name; + + if (of_property_read_u32(node, "ti,clock-frequency", &val)) { + pr_err("%s missing clock-frequency\n", node->name); + goto cleanup; + } + clk_hw->fixed_rate = val; + + if (of_property_read_u32(node, "ti,bit-shift", &val)) { + pr_err("%s missing bit-shift\n", node->name); + goto cleanup; + } + + clk_hw->enable_bit = val; + ad->enable_mask = 0x3 << val; + ad->autoidle_mask = 0x3 << val; + + if (of_property_read_u32(node, "ti,idlest-shift", &val)) { + pr_err("%s missing idlest-shift\n", node->name); + goto cleanup; + } + + ad->idlest_mask = 1 << val; + + ad->control_reg = ti_clk_get_reg_addr(node, 0); + ad->autoidle_reg = ti_clk_get_reg_addr(node, 1); + ad->idlest_reg = ti_clk_get_reg_addr(node, 2); + + if (!ad->control_reg || !ad->autoidle_reg || !ad->idlest_reg) + goto cleanup; + + clk = clk_register(NULL, &clk_hw->hw); + if (!IS_ERR(clk)) { + of_clk_add_provider(node, of_clk_src_simple_get, clk); + kfree(init); + return; + } +cleanup: + kfree(ad); + kfree(clk_hw); + kfree(init); +} +CLK_OF_DECLARE(omap2_apll_clock, "ti,omap2-apll-clock", + of_omap2_apll_setup); diff --git a/drivers/clk/ti/clk-2xxx.c b/drivers/clk/ti/clk-2xxx.c new file mode 100644 index 000000000000..c808ab3d2bb2 --- /dev/null +++ b/drivers/clk/ti/clk-2xxx.c @@ -0,0 +1,256 @@ +/* + * OMAP2 Clock init + * + * Copyright (C) 2013 Texas Instruments, Inc + * Tero Kristo (t-kristo@ti.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include + +static struct ti_dt_clk omap2xxx_clks[] = { + DT_CLK(NULL, "func_32k_ck", "func_32k_ck"), + DT_CLK(NULL, "secure_32k_ck", "secure_32k_ck"), + DT_CLK(NULL, "virt_12m_ck", "virt_12m_ck"), + DT_CLK(NULL, "virt_13m_ck", "virt_13m_ck"), + DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"), + DT_CLK(NULL, "virt_26m_ck", "virt_26m_ck"), + DT_CLK(NULL, "aplls_clkin_ck", "aplls_clkin_ck"), + DT_CLK(NULL, "aplls_clkin_x2_ck", "aplls_clkin_x2_ck"), + DT_CLK(NULL, "osc_ck", "osc_ck"), + DT_CLK(NULL, "sys_ck", "sys_ck"), + DT_CLK(NULL, "alt_ck", "alt_ck"), + DT_CLK(NULL, "mcbsp_clks", "mcbsp_clks"), + DT_CLK(NULL, "dpll_ck", "dpll_ck"), + DT_CLK(NULL, "apll96_ck", "apll96_ck"), + DT_CLK(NULL, "apll54_ck", "apll54_ck"), + DT_CLK(NULL, "func_54m_ck", "func_54m_ck"), + DT_CLK(NULL, "core_ck", "core_ck"), + DT_CLK(NULL, "func_96m_ck", "func_96m_ck"), + DT_CLK(NULL, "func_48m_ck", "func_48m_ck"), + DT_CLK(NULL, "func_12m_ck", "func_12m_ck"), + DT_CLK(NULL, "sys_clkout_src", "sys_clkout_src"), + DT_CLK(NULL, "sys_clkout", "sys_clkout"), + DT_CLK(NULL, "emul_ck", "emul_ck"), + DT_CLK(NULL, "mpu_ck", "mpu_ck"), + DT_CLK(NULL, "dsp_fck", "dsp_fck"), + DT_CLK(NULL, "gfx_3d_fck", "gfx_3d_fck"), + DT_CLK(NULL, "gfx_2d_fck", "gfx_2d_fck"), + DT_CLK(NULL, "gfx_ick", "gfx_ick"), + DT_CLK("omapdss_dss", "ick", "dss_ick"), + DT_CLK(NULL, "dss_ick", "dss_ick"), + DT_CLK(NULL, "dss1_fck", "dss1_fck"), + DT_CLK(NULL, "dss2_fck", "dss2_fck"), + DT_CLK(NULL, "dss_54m_fck", "dss_54m_fck"), + DT_CLK(NULL, "core_l3_ck", "core_l3_ck"), + DT_CLK(NULL, "ssi_fck", "ssi_ssr_sst_fck"), + DT_CLK(NULL, "usb_l4_ick", "usb_l4_ick"), + DT_CLK(NULL, "l4_ck", "l4_ck"), + DT_CLK(NULL, "ssi_l4_ick", "ssi_l4_ick"), + DT_CLK(NULL, "gpt1_ick", "gpt1_ick"), + DT_CLK(NULL, "gpt1_fck", "gpt1_fck"), + DT_CLK(NULL, "gpt2_ick", "gpt2_ick"), + DT_CLK(NULL, "gpt2_fck", "gpt2_fck"), + DT_CLK(NULL, "gpt3_ick", "gpt3_ick"), + DT_CLK(NULL, "gpt3_fck", "gpt3_fck"), + DT_CLK(NULL, "gpt4_ick", "gpt4_ick"), + DT_CLK(NULL, "gpt4_fck", "gpt4_fck"), + DT_CLK(NULL, "gpt5_ick", "gpt5_ick"), + DT_CLK(NULL, "gpt5_fck", "gpt5_fck"), + DT_CLK(NULL, "gpt6_ick", "gpt6_ick"), + DT_CLK(NULL, "gpt6_fck", "gpt6_fck"), + DT_CLK(NULL, "gpt7_ick", "gpt7_ick"), + DT_CLK(NULL, "gpt7_fck", "gpt7_fck"), + DT_CLK(NULL, "gpt8_ick", "gpt8_ick"), + DT_CLK(NULL, "gpt8_fck", "gpt8_fck"), + DT_CLK(NULL, "gpt9_ick", "gpt9_ick"), + DT_CLK(NULL, "gpt9_fck", "gpt9_fck"), + DT_CLK(NULL, "gpt10_ick", "gpt10_ick"), + DT_CLK(NULL, "gpt10_fck", "gpt10_fck"), + DT_CLK(NULL, "gpt11_ick", "gpt11_ick"), + DT_CLK(NULL, "gpt11_fck", "gpt11_fck"), + DT_CLK(NULL, "gpt12_ick", "gpt12_ick"), + DT_CLK(NULL, "gpt12_fck", "gpt12_fck"), + DT_CLK("omap-mcbsp.1", "ick", "mcbsp1_ick"), + DT_CLK(NULL, "mcbsp1_ick", "mcbsp1_ick"), + DT_CLK(NULL, "mcbsp1_fck", "mcbsp1_fck"), + DT_CLK("omap-mcbsp.2", "ick", "mcbsp2_ick"), + DT_CLK(NULL, "mcbsp2_ick", "mcbsp2_ick"), + DT_CLK(NULL, "mcbsp2_fck", "mcbsp2_fck"), + DT_CLK("omap2_mcspi.1", "ick", "mcspi1_ick"), + DT_CLK(NULL, "mcspi1_ick", "mcspi1_ick"), + DT_CLK(NULL, "mcspi1_fck", "mcspi1_fck"), + DT_CLK("omap2_mcspi.2", "ick", "mcspi2_ick"), + DT_CLK(NULL, "mcspi2_ick", "mcspi2_ick"), + DT_CLK(NULL, "mcspi2_fck", "mcspi2_fck"), + DT_CLK(NULL, "uart1_ick", "uart1_ick"), + DT_CLK(NULL, "uart1_fck", "uart1_fck"), + DT_CLK(NULL, "uart2_ick", "uart2_ick"), + DT_CLK(NULL, "uart2_fck", "uart2_fck"), + DT_CLK(NULL, "uart3_ick", "uart3_ick"), + DT_CLK(NULL, "uart3_fck", "uart3_fck"), + DT_CLK(NULL, "gpios_ick", "gpios_ick"), + DT_CLK(NULL, "gpios_fck", "gpios_fck"), + DT_CLK("omap_wdt", "ick", "mpu_wdt_ick"), + DT_CLK(NULL, "mpu_wdt_ick", "mpu_wdt_ick"), + DT_CLK(NULL, "mpu_wdt_fck", "mpu_wdt_fck"), + DT_CLK(NULL, "sync_32k_ick", "sync_32k_ick"), + DT_CLK(NULL, "wdt1_ick", "wdt1_ick"), + DT_CLK(NULL, "omapctrl_ick", "omapctrl_ick"), + DT_CLK("omap24xxcam", "fck", "cam_fck"), + DT_CLK(NULL, "cam_fck", "cam_fck"), + DT_CLK("omap24xxcam", "ick", "cam_ick"), + DT_CLK(NULL, "cam_ick", "cam_ick"), + DT_CLK(NULL, "mailboxes_ick", "mailboxes_ick"), + DT_CLK(NULL, "wdt4_ick", "wdt4_ick"), + DT_CLK(NULL, "wdt4_fck", "wdt4_fck"), + DT_CLK(NULL, "mspro_ick", "mspro_ick"), + DT_CLK(NULL, "mspro_fck", "mspro_fck"), + DT_CLK(NULL, "fac_ick", "fac_ick"), + DT_CLK(NULL, "fac_fck", "fac_fck"), + DT_CLK("omap_hdq.0", "ick", "hdq_ick"), + DT_CLK(NULL, "hdq_ick", "hdq_ick"), + DT_CLK("omap_hdq.0", "fck", "hdq_fck"), + DT_CLK(NULL, "hdq_fck", "hdq_fck"), + DT_CLK("omap_i2c.1", "ick", "i2c1_ick"), + DT_CLK(NULL, "i2c1_ick", "i2c1_ick"), + DT_CLK("omap_i2c.2", "ick", "i2c2_ick"), + DT_CLK(NULL, "i2c2_ick", "i2c2_ick"), + DT_CLK(NULL, "gpmc_fck", "gpmc_fck"), + DT_CLK(NULL, "sdma_fck", "sdma_fck"), + DT_CLK(NULL, "sdma_ick", "sdma_ick"), + DT_CLK(NULL, "sdrc_ick", "sdrc_ick"), + DT_CLK(NULL, "des_ick", "des_ick"), + DT_CLK("omap-sham", "ick", "sha_ick"), + DT_CLK(NULL, "sha_ick", "sha_ick"), + DT_CLK("omap_rng", "ick", "rng_ick"), + DT_CLK(NULL, "rng_ick", "rng_ick"), + DT_CLK("omap-aes", "ick", "aes_ick"), + DT_CLK(NULL, "aes_ick", "aes_ick"), + DT_CLK(NULL, "pka_ick", "pka_ick"), + DT_CLK(NULL, "usb_fck", "usb_fck"), + DT_CLK(NULL, "timer_32k_ck", "func_32k_ck"), + DT_CLK(NULL, "timer_sys_ck", "sys_ck"), + DT_CLK(NULL, "timer_ext_ck", "alt_ck"), + { .node_name = NULL }, +}; + +static struct ti_dt_clk omap2420_clks[] = { + DT_CLK(NULL, "sys_clkout2_src", "sys_clkout2_src"), + DT_CLK(NULL, "sys_clkout2", "sys_clkout2"), + DT_CLK(NULL, "dsp_ick", "dsp_ick"), + DT_CLK(NULL, "iva1_ifck", "iva1_ifck"), + DT_CLK(NULL, "iva1_mpu_int_ifck", "iva1_mpu_int_ifck"), + DT_CLK(NULL, "wdt3_ick", "wdt3_ick"), + DT_CLK(NULL, "wdt3_fck", "wdt3_fck"), + DT_CLK("mmci-omap.0", "ick", "mmc_ick"), + DT_CLK(NULL, "mmc_ick", "mmc_ick"), + DT_CLK("mmci-omap.0", "fck", "mmc_fck"), + DT_CLK(NULL, "mmc_fck", "mmc_fck"), + DT_CLK(NULL, "eac_ick", "eac_ick"), + DT_CLK(NULL, "eac_fck", "eac_fck"), + DT_CLK(NULL, "i2c1_fck", "i2c1_fck"), + DT_CLK(NULL, "i2c2_fck", "i2c2_fck"), + DT_CLK(NULL, "vlynq_ick", "vlynq_ick"), + DT_CLK(NULL, "vlynq_fck", "vlynq_fck"), + DT_CLK("musb-hdrc", "fck", "osc_ck"), + { .node_name = NULL }, +}; + +static struct ti_dt_clk omap2430_clks[] = { + DT_CLK("twl", "fck", "osc_ck"), + DT_CLK(NULL, "iva2_1_ick", "iva2_1_ick"), + DT_CLK(NULL, "mdm_ick", "mdm_ick"), + DT_CLK(NULL, "mdm_osc_ck", "mdm_osc_ck"), + DT_CLK("omap-mcbsp.3", "ick", "mcbsp3_ick"), + DT_CLK(NULL, "mcbsp3_ick", "mcbsp3_ick"), + DT_CLK(NULL, "mcbsp3_fck", "mcbsp3_fck"), + DT_CLK("omap-mcbsp.4", "ick", "mcbsp4_ick"), + DT_CLK(NULL, "mcbsp4_ick", "mcbsp4_ick"), + DT_CLK(NULL, "mcbsp4_fck", "mcbsp4_fck"), + DT_CLK("omap-mcbsp.5", "ick", "mcbsp5_ick"), + DT_CLK(NULL, "mcbsp5_ick", "mcbsp5_ick"), + DT_CLK(NULL, "mcbsp5_fck", "mcbsp5_fck"), + DT_CLK("omap2_mcspi.3", "ick", "mcspi3_ick"), + DT_CLK(NULL, "mcspi3_ick", "mcspi3_ick"), + DT_CLK(NULL, "mcspi3_fck", "mcspi3_fck"), + DT_CLK(NULL, "icr_ick", "icr_ick"), + DT_CLK(NULL, "i2chs1_fck", "i2chs1_fck"), + DT_CLK(NULL, "i2chs2_fck", "i2chs2_fck"), + DT_CLK("musb-omap2430", "ick", "usbhs_ick"), + DT_CLK(NULL, "usbhs_ick", "usbhs_ick"), + DT_CLK("omap_hsmmc.0", "ick", "mmchs1_ick"), + DT_CLK(NULL, "mmchs1_ick", "mmchs1_ick"), + DT_CLK(NULL, "mmchs1_fck", "mmchs1_fck"), + DT_CLK("omap_hsmmc.1", "ick", "mmchs2_ick"), + DT_CLK(NULL, "mmchs2_ick", "mmchs2_ick"), + DT_CLK(NULL, "mmchs2_fck", "mmchs2_fck"), + DT_CLK(NULL, "gpio5_ick", "gpio5_ick"), + DT_CLK(NULL, "gpio5_fck", "gpio5_fck"), + DT_CLK(NULL, "mdm_intc_ick", "mdm_intc_ick"), + DT_CLK("omap_hsmmc.0", "mmchsdb_fck", "mmchsdb1_fck"), + DT_CLK(NULL, "mmchsdb1_fck", "mmchsdb1_fck"), + DT_CLK("omap_hsmmc.1", "mmchsdb_fck", "mmchsdb2_fck"), + DT_CLK(NULL, "mmchsdb2_fck", "mmchsdb2_fck"), + { .node_name = NULL }, +}; + +static const char *enable_init_clks[] = { + "apll96_ck", + "apll54_ck", + "sync_32k_ick", + "omapctrl_ick", + "gpmc_fck", + "sdrc_ick", +}; + +enum { + OMAP2_SOC_OMAP2420, + OMAP2_SOC_OMAP2430, +}; + +static int __init omap2xxx_dt_clk_init(int soc_type) +{ + ti_dt_clocks_register(omap2xxx_clks); + + if (soc_type == OMAP2_SOC_OMAP2420) + ti_dt_clocks_register(omap2420_clks); + else + ti_dt_clocks_register(omap2430_clks); + + omap2xxx_clkt_vps_init(); + + omap2_clk_disable_autoidle_all(); + + omap2_clk_enable_init_clocks(enable_init_clks, + ARRAY_SIZE(enable_init_clks)); + + pr_info("Clocking rate (Crystal/DPLL/MPU): %ld.%01ld/%ld/%ld MHz\n", + (clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 1000000), + (clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 100000) % 10, + (clk_get_rate(clk_get_sys(NULL, "dpll_ck")) / 1000000), + (clk_get_rate(clk_get_sys(NULL, "mpu_ck")) / 1000000)); + + return 0; +} + +int __init omap2420_dt_clk_init(void) +{ + return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2420); +} + +int __init omap2430_dt_clk_init(void) +{ + return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2430); +} diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c index 527a43da3d33..3795fce8a830 100644 --- a/drivers/clk/ti/clk-43xx.c +++ b/drivers/clk/ti/clk-43xx.c @@ -116,9 +116,25 @@ static struct ti_dt_clk am43xx_clks[] = { int __init am43xx_dt_clk_init(void) { + struct clk *clk1, *clk2; + ti_dt_clocks_register(am43xx_clks); omap2_clk_disable_autoidle_all(); + /* + * cpsw_cpts_rft_clk has got the choice of 3 clocksources + * dpll_core_m4_ck, dpll_core_m5_ck and dpll_disp_m2_ck. + * By default dpll_core_m4_ck is selected, witn this as clock + * source the CPTS doesnot work properly. It gives clockcheck errors + * while running PTP. + * clockcheck: clock jumped backward or running slower than expected! + * By selecting dpll_core_m5_ck as the clocksource fixes this issue. + * In AM335x dpll_core_m5_ck is the default clocksource. + */ + clk1 = clk_get_sys(NULL, "cpsw_cpts_rft_clk"); + clk2 = clk_get_sys(NULL, "dpll_core_m5_ck"); + clk_set_parent(clk1, clk2); + return 0; } diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c index 08f3d1b915b3..5e183993e3ec 100644 --- a/drivers/clk/ti/clk-54xx.c +++ b/drivers/clk/ti/clk-54xx.c @@ -240,6 +240,12 @@ int __init omap5xxx_dt_clk_init(void) if (rc) pr_err("%s: failed to configure ABE DPLL!\n", __func__); + abe_dpll = clk_get_sys(NULL, "dpll_abe_m2x2_ck"); + if (!rc) + rc = clk_set_rate(abe_dpll, OMAP5_DPLL_ABE_DEFFREQ * 2); + if (rc) + pr_err("%s: failed to configure ABE m2x2 DPLL!\n", __func__); + usb_dpll = clk_get_sys(NULL, "dpll_usb_ck"); rc = clk_set_rate(usb_dpll, OMAP5_DPLL_USB_DEFFREQ); if (rc) diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c index f7e40734c819..e1581335937d 100644 --- a/drivers/clk/ti/clk-7xx.c +++ b/drivers/clk/ti/clk-7xx.c @@ -24,7 +24,7 @@ static struct ti_dt_clk dra7xx_clks[] = { DT_CLK(NULL, "atl_clkin0_ck", "atl_clkin0_ck"), DT_CLK(NULL, "atl_clkin1_ck", "atl_clkin1_ck"), DT_CLK(NULL, "atl_clkin2_ck", "atl_clkin2_ck"), - DT_CLK(NULL, "atlclkin3_ck", "atlclkin3_ck"), + DT_CLK(NULL, "atl_clkin3_ck", "atl_clkin3_ck"), DT_CLK(NULL, "hdmi_clkin_ck", "hdmi_clkin_ck"), DT_CLK(NULL, "mlb_clkin_ck", "mlb_clkin_ck"), DT_CLK(NULL, "mlbp_clkin_ck", "mlbp_clkin_ck"), diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c new file mode 100644 index 000000000000..4a65b410e4d5 --- /dev/null +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -0,0 +1,312 @@ +/* + * DRA7 ATL (Audio Tracking Logic) clock driver + * + * Copyright (C) 2013 Texas Instruments, Inc. + * + * Peter Ujfalusi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRA7_ATL_INSTANCES 4 + +#define DRA7_ATL_PPMR_REG(id) (0x200 + (id * 0x80)) +#define DRA7_ATL_BBSR_REG(id) (0x204 + (id * 0x80)) +#define DRA7_ATL_ATLCR_REG(id) (0x208 + (id * 0x80)) +#define DRA7_ATL_SWEN_REG(id) (0x210 + (id * 0x80)) +#define DRA7_ATL_BWSMUX_REG(id) (0x214 + (id * 0x80)) +#define DRA7_ATL_AWSMUX_REG(id) (0x218 + (id * 0x80)) +#define DRA7_ATL_PCLKMUX_REG(id) (0x21c + (id * 0x80)) + +#define DRA7_ATL_SWEN BIT(0) +#define DRA7_ATL_DIVIDER_MASK (0x1f) +#define DRA7_ATL_PCLKMUX BIT(0) +struct dra7_atl_clock_info; + +struct dra7_atl_desc { + struct clk *clk; + struct clk_hw hw; + struct dra7_atl_clock_info *cinfo; + int id; + + bool probed; /* the driver for the IP has been loaded */ + bool valid; /* configured */ + bool enabled; + u32 bws; /* Baseband Word Select Mux */ + u32 aws; /* Audio Word Select Mux */ + u32 divider; /* Cached divider value */ +}; + +struct dra7_atl_clock_info { + struct device *dev; + void __iomem *iobase; + + struct dra7_atl_desc *cdesc; +}; + +#define to_atl_desc(_hw) container_of(_hw, struct dra7_atl_desc, hw) + +static inline void atl_write(struct dra7_atl_clock_info *cinfo, u32 reg, + u32 val) +{ + __raw_writel(val, cinfo->iobase + reg); +} + +static inline int atl_read(struct dra7_atl_clock_info *cinfo, u32 reg) +{ + return __raw_readl(cinfo->iobase + reg); +} + +static int atl_clk_enable(struct clk_hw *hw) +{ + struct dra7_atl_desc *cdesc = to_atl_desc(hw); + + if (!cdesc->probed) + goto out; + + if (unlikely(!cdesc->valid)) + dev_warn(cdesc->cinfo->dev, "atl%d has not been configured\n", + cdesc->id); + pm_runtime_get_sync(cdesc->cinfo->dev); + + atl_write(cdesc->cinfo, DRA7_ATL_ATLCR_REG(cdesc->id), + cdesc->divider - 1); + atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), DRA7_ATL_SWEN); + +out: + cdesc->enabled = true; + + return 0; +} + +static void atl_clk_disable(struct clk_hw *hw) +{ + struct dra7_atl_desc *cdesc = to_atl_desc(hw); + + if (!cdesc->probed) + goto out; + + atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), 0); + pm_runtime_put_sync(cdesc->cinfo->dev); + +out: + cdesc->enabled = false; +} + +static int atl_clk_is_enabled(struct clk_hw *hw) +{ + struct dra7_atl_desc *cdesc = to_atl_desc(hw); + + return cdesc->enabled; +} + +static unsigned long atl_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dra7_atl_desc *cdesc = to_atl_desc(hw); + + return parent_rate / cdesc->divider; +} + +static long atl_clk_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + unsigned divider; + + divider = (*parent_rate + rate / 2) / rate; + if (divider > DRA7_ATL_DIVIDER_MASK + 1) + divider = DRA7_ATL_DIVIDER_MASK + 1; + + return *parent_rate / divider; +} + +static int atl_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dra7_atl_desc *cdesc = to_atl_desc(hw); + u32 divider; + + divider = ((parent_rate + rate / 2) / rate) - 1; + if (divider > DRA7_ATL_DIVIDER_MASK) + divider = DRA7_ATL_DIVIDER_MASK; + + cdesc->divider = divider + 1; + + return 0; +} + +const struct clk_ops atl_clk_ops = { + .enable = atl_clk_enable, + .disable = atl_clk_disable, + .is_enabled = atl_clk_is_enabled, + .recalc_rate = atl_clk_recalc_rate, + .round_rate = atl_clk_round_rate, + .set_rate = atl_clk_set_rate, +}; + +static void __init of_dra7_atl_clock_setup(struct device_node *node) +{ + struct dra7_atl_desc *clk_hw = NULL; + struct clk_init_data init = { 0 }; + const char **parent_names = NULL; + struct clk *clk; + + clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL); + if (!clk_hw) { + pr_err("%s: could not allocate dra7_atl_desc\n", __func__); + return; + } + + clk_hw->hw.init = &init; + clk_hw->divider = 1; + init.name = node->name; + init.ops = &atl_clk_ops; + init.flags = CLK_IGNORE_UNUSED; + init.num_parents = of_clk_get_parent_count(node); + + if (init.num_parents != 1) { + pr_err("%s: atl clock %s must have 1 parent\n", __func__, + node->name); + goto cleanup; + } + + parent_names = kzalloc(sizeof(char *), GFP_KERNEL); + + if (!parent_names) + goto cleanup; + + parent_names[0] = of_clk_get_parent_name(node, 0); + + init.parent_names = parent_names; + + clk = clk_register(NULL, &clk_hw->hw); + + if (!IS_ERR(clk)) { + of_clk_add_provider(node, of_clk_src_simple_get, clk); + return; + } +cleanup: + kfree(parent_names); + kfree(clk_hw); +} +CLK_OF_DECLARE(dra7_atl_clock, "ti,dra7-atl-clock", of_dra7_atl_clock_setup); + +static int of_dra7_atl_clk_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct dra7_atl_clock_info *cinfo; + int i; + int ret = 0; + + if (!node) + return -ENODEV; + + cinfo = devm_kzalloc(&pdev->dev, sizeof(*cinfo), GFP_KERNEL); + if (!cinfo) + return -ENOMEM; + + cinfo->iobase = of_iomap(node, 0); + cinfo->dev = &pdev->dev; + pm_runtime_enable(cinfo->dev); + + pm_runtime_get_sync(cinfo->dev); + atl_write(cinfo, DRA7_ATL_PCLKMUX_REG(0), DRA7_ATL_PCLKMUX); + + for (i = 0; i < DRA7_ATL_INSTANCES; i++) { + struct device_node *cfg_node; + char prop[5]; + struct dra7_atl_desc *cdesc; + struct of_phandle_args clkspec; + struct clk *clk; + int rc; + + rc = of_parse_phandle_with_args(node, "ti,provided-clocks", + NULL, i, &clkspec); + + if (rc) { + pr_err("%s: failed to lookup atl clock %d\n", __func__, + i); + return -EINVAL; + } + + clk = of_clk_get_from_provider(&clkspec); + + cdesc = to_atl_desc(__clk_get_hw(clk)); + cdesc->cinfo = cinfo; + cdesc->id = i; + + /* Get configuration for the ATL instances */ + snprintf(prop, sizeof(prop), "atl%u", i); + cfg_node = of_find_node_by_name(node, prop); + if (cfg_node) { + ret = of_property_read_u32(cfg_node, "bws", + &cdesc->bws); + ret |= of_property_read_u32(cfg_node, "aws", + &cdesc->aws); + if (!ret) { + cdesc->valid = true; + atl_write(cinfo, DRA7_ATL_BWSMUX_REG(i), + cdesc->bws); + atl_write(cinfo, DRA7_ATL_AWSMUX_REG(i), + cdesc->aws); + } + } + + cdesc->probed = true; + /* + * Enable the clock if it has been asked prior to loading the + * hw driver + */ + if (cdesc->enabled) + atl_clk_enable(__clk_get_hw(clk)); + } + pm_runtime_put_sync(cinfo->dev); + + return ret; +} + +static int of_dra7_atl_clk_remove(struct platform_device *pdev) +{ + pm_runtime_disable(&pdev->dev); + + return 0; +} + +static struct of_device_id of_dra7_atl_clk_match_tbl[] = { + { .compatible = "ti,dra7-atl", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_dra7_atl_clk_match_tbl); + +static struct platform_driver dra7_atl_clk_driver = { + .driver = { + .name = "dra7-atl", + .owner = THIS_MODULE, + .of_match_table = of_dra7_atl_clk_match_tbl, + }, + .probe = of_dra7_atl_clk_probe, + .remove = of_dra7_atl_clk_remove, +}; + +module_platform_driver(dra7_atl_clk_driver); + +MODULE_DESCRIPTION("Clock driver for DRA7 Audio Tracking Logic"); +MODULE_ALIAS("platform:dra7-atl-clock"); +MODULE_AUTHOR("Peter Ujfalusi "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c index 7e498a44f97d..abd956d5f838 100644 --- a/drivers/clk/ti/dpll.c +++ b/drivers/clk/ti/dpll.c @@ -25,8 +25,6 @@ #undef pr_fmt #define pr_fmt(fmt) "%s: " fmt, __func__ -#define DPLL_HAS_AUTOIDLE 0x1 - #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \ defined(CONFIG_SOC_DRA7XX) static const struct clk_ops dpll_m4xen_ck_ops = { @@ -37,21 +35,18 @@ static const struct clk_ops dpll_m4xen_ck_ops = { .set_rate = &omap3_noncore_dpll_set_rate, .get_parent = &omap2_init_dpll_parent, }; +#else +static const struct clk_ops dpll_m4xen_ck_ops = {}; #endif +#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_ARCH_OMAP4) || \ + defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX) || \ + defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX) static const struct clk_ops dpll_core_ck_ops = { .recalc_rate = &omap3_dpll_recalc, .get_parent = &omap2_init_dpll_parent, }; -#ifdef CONFIG_ARCH_OMAP3 -static const struct clk_ops omap3_dpll_core_ck_ops = { - .get_parent = &omap2_init_dpll_parent, - .recalc_rate = &omap3_dpll_recalc, - .round_rate = &omap2_dpll_round_rate, -}; -#endif - static const struct clk_ops dpll_ck_ops = { .enable = &omap3_noncore_dpll_enable, .disable = &omap3_noncore_dpll_disable, @@ -67,6 +62,33 @@ static const struct clk_ops dpll_no_gate_ck_ops = { .round_rate = &omap2_dpll_round_rate, .set_rate = &omap3_noncore_dpll_set_rate, }; +#else +static const struct clk_ops dpll_core_ck_ops = {}; +static const struct clk_ops dpll_ck_ops = {}; +static const struct clk_ops dpll_no_gate_ck_ops = {}; +const struct clk_hw_omap_ops clkhwops_omap3_dpll = {}; +#endif + +#ifdef CONFIG_ARCH_OMAP2 +static const struct clk_ops omap2_dpll_core_ck_ops = { + .get_parent = &omap2_init_dpll_parent, + .recalc_rate = &omap2_dpllcore_recalc, + .round_rate = &omap2_dpll_round_rate, + .set_rate = &omap2_reprogram_dpllcore, +}; +#else +static const struct clk_ops omap2_dpll_core_ck_ops = {}; +#endif + +#ifdef CONFIG_ARCH_OMAP3 +static const struct clk_ops omap3_dpll_core_ck_ops = { + .get_parent = &omap2_init_dpll_parent, + .recalc_rate = &omap3_dpll_recalc, + .round_rate = &omap2_dpll_round_rate, +}; +#else +static const struct clk_ops omap3_dpll_core_ck_ops = {}; +#endif #ifdef CONFIG_ARCH_OMAP3 static const struct clk_ops omap3_dpll_ck_ops = { @@ -193,14 +215,12 @@ static void ti_clk_register_dpll_x2(struct device_node *node, * @node: device node containing the DPLL info * @ops: ops for the DPLL * @ddt: DPLL data template to use - * @init_flags: flags for controlling init types * * Initializes a DPLL clock from device tree data. */ static void __init of_ti_dpll_setup(struct device_node *node, const struct clk_ops *ops, - const struct dpll_data *ddt, - u8 init_flags) + const struct dpll_data *ddt) { struct clk_hw_omap *clk_hw = NULL; struct clk_init_data *init = NULL; @@ -241,13 +261,30 @@ static void __init of_ti_dpll_setup(struct device_node *node, init->parent_names = parent_names; dd->control_reg = ti_clk_get_reg_addr(node, 0); - dd->idlest_reg = ti_clk_get_reg_addr(node, 1); - dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2); - if (!dd->control_reg || !dd->idlest_reg || !dd->mult_div1_reg) + /* + * Special case for OMAP2 DPLL, register order is different due to + * missing idlest_reg, also clkhwops is different. Detected from + * missing idlest_mask. + */ + if (!dd->idlest_mask) { + dd->mult_div1_reg = ti_clk_get_reg_addr(node, 1); +#ifdef CONFIG_ARCH_OMAP2 + clk_hw->ops = &clkhwops_omap2xxx_dpll; + omap2xxx_clkt_dpllcore_init(&clk_hw->hw); +#endif + } else { + dd->idlest_reg = ti_clk_get_reg_addr(node, 1); + if (!dd->idlest_reg) + goto cleanup; + + dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2); + } + + if (!dd->control_reg || !dd->mult_div1_reg) goto cleanup; - if (init_flags & DPLL_HAS_AUTOIDLE) { + if (dd->autoidle_mask) { dd->autoidle_reg = ti_clk_get_reg_addr(node, 3); if (!dd->autoidle_reg) goto cleanup; @@ -310,7 +347,7 @@ static void __init of_ti_omap3_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap3_dpll_clock, "ti,omap3-dpll-clock", of_ti_omap3_dpll_setup); @@ -329,7 +366,7 @@ static void __init of_ti_omap3_core_dpll_setup(struct device_node *node) .freqsel_mask = 0xf0, }; - of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap3_core_dpll_clock, "ti,omap3-dpll-core-clock", of_ti_omap3_core_dpll_setup); @@ -349,7 +386,7 @@ static void __init of_ti_omap3_per_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap3_per_dpll_clock, "ti,omap3-dpll-per-clock", of_ti_omap3_per_dpll_setup); @@ -371,7 +408,7 @@ static void __init of_ti_omap3_per_jtype_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap3_per_jtype_dpll_clock, "ti,omap3-dpll-per-j-type-clock", of_ti_omap3_per_jtype_dpll_setup); @@ -391,11 +428,32 @@ static void __init of_ti_omap4_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &dpll_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap4_dpll_clock, "ti,omap4-dpll-clock", of_ti_omap4_dpll_setup); +static void __init of_ti_omap5_mpu_dpll_setup(struct device_node *node) +{ + const struct dpll_data dd = { + .idlest_mask = 0x1, + .enable_mask = 0x7, + .autoidle_mask = 0x7, + .mult_mask = 0x7ff << 8, + .div1_mask = 0x7f, + .max_multiplier = 2047, + .max_divider = 128, + .dcc_mask = BIT(22), + .dcc_rate = 1400000000, /* DCC beyond 1.4GHz */ + .min_divider = 1, + .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), + }; + + of_ti_dpll_setup(node, &dpll_ck_ops, &dd); +} +CLK_OF_DECLARE(of_ti_omap5_mpu_dpll_clock, "ti,omap5-mpu-dpll-clock", + of_ti_omap5_mpu_dpll_setup); + static void __init of_ti_omap4_core_dpll_setup(struct device_node *node) { const struct dpll_data dd = { @@ -410,7 +468,7 @@ static void __init of_ti_omap4_core_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap4_core_dpll_clock, "ti,omap4-dpll-core-clock", of_ti_omap4_core_dpll_setup); @@ -433,7 +491,7 @@ static void __init of_ti_omap4_m4xen_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap4_m4xen_dpll_clock, "ti,omap4-dpll-m4xen-clock", of_ti_omap4_m4xen_dpll_setup); @@ -454,7 +512,7 @@ static void __init of_ti_omap4_jtype_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE); + of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd); } CLK_OF_DECLARE(ti_omap4_jtype_dpll_clock, "ti,omap4-dpll-j-type-clock", of_ti_omap4_jtype_dpll_setup); @@ -465,7 +523,6 @@ static void __init of_ti_am3_no_gate_dpll_setup(struct device_node *node) const struct dpll_data dd = { .idlest_mask = 0x1, .enable_mask = 0x7, - .autoidle_mask = 0x7, .mult_mask = 0x7ff << 8, .div1_mask = 0x7f, .max_multiplier = 2047, @@ -474,7 +531,7 @@ static void __init of_ti_am3_no_gate_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0); + of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd); } CLK_OF_DECLARE(ti_am3_no_gate_dpll_clock, "ti,am3-dpll-no-gate-clock", of_ti_am3_no_gate_dpll_setup); @@ -484,7 +541,6 @@ static void __init of_ti_am3_jtype_dpll_setup(struct device_node *node) const struct dpll_data dd = { .idlest_mask = 0x1, .enable_mask = 0x7, - .autoidle_mask = 0x7, .mult_mask = 0x7ff << 8, .div1_mask = 0x7f, .max_multiplier = 4095, @@ -494,7 +550,7 @@ static void __init of_ti_am3_jtype_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0); + of_ti_dpll_setup(node, &dpll_ck_ops, &dd); } CLK_OF_DECLARE(ti_am3_jtype_dpll_clock, "ti,am3-dpll-j-type-clock", of_ti_am3_jtype_dpll_setup); @@ -504,7 +560,6 @@ static void __init of_ti_am3_no_gate_jtype_dpll_setup(struct device_node *node) const struct dpll_data dd = { .idlest_mask = 0x1, .enable_mask = 0x7, - .autoidle_mask = 0x7, .mult_mask = 0x7ff << 8, .div1_mask = 0x7f, .max_multiplier = 2047, @@ -514,7 +569,7 @@ static void __init of_ti_am3_no_gate_jtype_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0); + of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd); } CLK_OF_DECLARE(ti_am3_no_gate_jtype_dpll_clock, "ti,am3-dpll-no-gate-j-type-clock", @@ -525,7 +580,6 @@ static void __init of_ti_am3_dpll_setup(struct device_node *node) const struct dpll_data dd = { .idlest_mask = 0x1, .enable_mask = 0x7, - .autoidle_mask = 0x7, .mult_mask = 0x7ff << 8, .div1_mask = 0x7f, .max_multiplier = 2047, @@ -534,7 +588,7 @@ static void __init of_ti_am3_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0); + of_ti_dpll_setup(node, &dpll_ck_ops, &dd); } CLK_OF_DECLARE(ti_am3_dpll_clock, "ti,am3-dpll-clock", of_ti_am3_dpll_setup); @@ -543,7 +597,6 @@ static void __init of_ti_am3_core_dpll_setup(struct device_node *node) const struct dpll_data dd = { .idlest_mask = 0x1, .enable_mask = 0x7, - .autoidle_mask = 0x7, .mult_mask = 0x7ff << 8, .div1_mask = 0x7f, .max_multiplier = 2047, @@ -552,7 +605,22 @@ static void __init of_ti_am3_core_dpll_setup(struct device_node *node) .modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED), }; - of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, 0); + of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd); } CLK_OF_DECLARE(ti_am3_core_dpll_clock, "ti,am3-dpll-core-clock", of_ti_am3_core_dpll_setup); + +static void __init of_ti_omap2_core_dpll_setup(struct device_node *node) +{ + const struct dpll_data dd = { + .enable_mask = 0x3, + .mult_mask = 0x3ff << 12, + .div1_mask = 0xf << 8, + .max_divider = 16, + .min_divider = 1, + }; + + of_ti_dpll_setup(node, &omap2_dpll_core_ck_ops, &dd); +} +CLK_OF_DECLARE(ti_omap2_core_dpll_clock, "ti,omap2-dpll-core-clock", + of_ti_omap2_core_dpll_setup); diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c index 58734817d502..b326d2797feb 100644 --- a/drivers/clk/ti/gate.c +++ b/drivers/clk/ti/gate.c @@ -185,7 +185,7 @@ of_ti_composite_no_wait_gate_clk_setup(struct device_node *node) CLK_OF_DECLARE(ti_composite_no_wait_gate_clk, "ti,composite-no-wait-gate-clock", of_ti_composite_no_wait_gate_clk_setup); -#ifdef CONFIG_ARCH_OMAP3 +#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3) static void __init of_ti_composite_interface_clk_setup(struct device_node *node) { _of_ti_composite_gate_clk_setup(node, &clkhwops_iclk_wait); diff --git a/drivers/clk/ti/interface.c b/drivers/clk/ti/interface.c index 320a2b168bb2..9c3e8c4aaa40 100644 --- a/drivers/clk/ti/interface.c +++ b/drivers/clk/ti/interface.c @@ -94,6 +94,7 @@ static void __init of_ti_no_wait_interface_clk_setup(struct device_node *node) CLK_OF_DECLARE(ti_no_wait_interface_clk, "ti,omap3-no-wait-interface-clock", of_ti_no_wait_interface_clk_setup); +#ifdef CONFIG_ARCH_OMAP3 static void __init of_ti_hsotgusb_interface_clk_setup(struct device_node *node) { _of_ti_interface_clk_setup(node, @@ -123,3 +124,13 @@ static void __init of_ti_am35xx_interface_clk_setup(struct device_node *node) } CLK_OF_DECLARE(ti_am35xx_interface_clk, "ti,am35xx-interface-clock", of_ti_am35xx_interface_clk_setup); +#endif + +#ifdef CONFIG_SOC_OMAP2430 +static void __init of_ti_omap2430_interface_clk_setup(struct device_node *node) +{ + _of_ti_interface_clk_setup(node, &clkhwops_omap2430_i2chs_wait); +} +CLK_OF_DECLARE(ti_omap2430_interface_clk, "ti,omap2430-interface-clock", + of_ti_omap2430_interface_clk_setup); +#endif diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 1fbe11f2a146..e473d6555f96 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -185,7 +185,7 @@ config CPU_FREQ_GOV_CONSERVATIVE config GENERIC_CPUFREQ_CPU0 tristate "Generic CPU0 cpufreq driver" - depends on HAVE_CLK && REGULATOR && OF && THERMAL && CPU_THERMAL + depends on HAVE_CLK && OF select PM_OPP help This adds a generic cpufreq driver for CPU0 frequency management. diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 36d20d0fce27..ebac67115009 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -5,8 +5,7 @@ # big LITTLE core layer and glue drivers config ARM_BIG_LITTLE_CPUFREQ tristate "Generic ARM big LITTLE CPUfreq driver" - depends on (BIG_LITTLE && ARM_CPU_TOPOLOGY) || (ARM64 && SMP) - depends on HAVE_CLK + depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK select PM_OPP help This enables the Generic CPUfreq driver for ARM big.LITTLE platforms. diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c index 09b9129c7bd3..ee1ae303a07c 100644 --- a/drivers/cpufreq/cpufreq-cpu0.c +++ b/drivers/cpufreq/cpufreq-cpu0.c @@ -104,7 +104,7 @@ static int cpu0_cpufreq_init(struct cpufreq_policy *policy) } static struct cpufreq_driver cpu0_cpufreq_driver = { - .flags = CPUFREQ_STICKY, + .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = cpu0_set_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index ae11dd51f81d..aed2b0cb83dc 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1816,20 +1816,55 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier); * GOVERNORS * *********************************************************************/ +/* Must set freqs->new to intermediate frequency */ +static int __target_intermediate(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, int index) +{ + int ret; + + freqs->new = cpufreq_driver->get_intermediate(policy, index); + + /* We don't need to switch to intermediate freq */ + if (!freqs->new) + return 0; + + pr_debug("%s: cpu: %d, switching to intermediate freq: oldfreq: %u, intermediate freq: %u\n", + __func__, policy->cpu, freqs->old, freqs->new); + + cpufreq_freq_transition_begin(policy, freqs); + ret = cpufreq_driver->target_intermediate(policy, index); + cpufreq_freq_transition_end(policy, freqs, ret); + + if (ret) + pr_err("%s: Failed to change to intermediate frequency: %d\n", + __func__, ret); + + return ret; +} + static int __target_index(struct cpufreq_policy *policy, struct cpufreq_frequency_table *freq_table, int index) { - struct cpufreq_freqs freqs; + struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0}; + unsigned int intermediate_freq = 0; int retval = -EINVAL; bool notify; notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION); - if (notify) { - freqs.old = policy->cur; - freqs.new = freq_table[index].frequency; - freqs.flags = 0; + /* Handle switching to intermediate frequency */ + if (cpufreq_driver->get_intermediate) { + retval = __target_intermediate(policy, &freqs, index); + if (retval) + return retval; + intermediate_freq = freqs.new; + /* Set old freq to intermediate */ + if (intermediate_freq) + freqs.old = freqs.new; + } + + freqs.new = freq_table[index].frequency; pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n", __func__, policy->cpu, freqs.old, freqs.new); @@ -1841,9 +1876,23 @@ static int __target_index(struct cpufreq_policy *policy, pr_err("%s: Failed to change cpu frequency: %d\n", __func__, retval); - if (notify) + if (notify) { cpufreq_freq_transition_end(policy, &freqs, retval); + /* + * Failed after setting to intermediate freq? Driver should have + * reverted back to initial frequency and so should we. Check + * here for intermediate_freq instead of get_intermediate, in + * case we have't switched to intermediate freq at all. + */ + if (unlikely(retval && intermediate_freq)) { + freqs.old = intermediate_freq; + freqs.new = policy->restore_freq; + cpufreq_freq_transition_begin(policy, &freqs); + cpufreq_freq_transition_end(policy, &freqs, 0); + } + } + return retval; } @@ -1875,6 +1924,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, if (target_freq == policy->cur) return 0; + /* Save last value to restore later on errors */ + policy->restore_freq = policy->cur; + if (cpufreq_driver->target) retval = cpufreq_driver->target(policy, target_freq, relation); else if (cpufreq_driver->target_index) { @@ -2361,7 +2413,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) !(driver_data->setpolicy || driver_data->target_index || driver_data->target) || (driver_data->setpolicy && (driver_data->target_index || - driver_data->target))) + driver_data->target)) || + (!!driver_data->get_intermediate != !!driver_data->target_intermediate)) return -EINVAL; pr_debug("trying to register driver %s\n", driver_data->name); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index e1c6433b16e0..1b44496b2d2b 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -36,14 +36,29 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) struct od_dbs_tuners *od_tuners = dbs_data->tuners; struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; struct cpufreq_policy *policy; + unsigned int sampling_rate; unsigned int max_load = 0; unsigned int ignore_nice; unsigned int j; - if (dbs_data->cdata->governor == GOV_ONDEMAND) + if (dbs_data->cdata->governor == GOV_ONDEMAND) { + struct od_cpu_dbs_info_s *od_dbs_info = + dbs_data->cdata->get_cpu_dbs_info_s(cpu); + + /* + * Sometimes, the ondemand governor uses an additional + * multiplier to give long delays. So apply this multiplier to + * the 'sampling_rate', so as to keep the wake-up-from-idle + * detection logic a bit conservative. + */ + sampling_rate = od_tuners->sampling_rate; + sampling_rate *= od_dbs_info->rate_mult; + ignore_nice = od_tuners->ignore_nice_load; - else + } else { + sampling_rate = cs_tuners->sampling_rate; ignore_nice = cs_tuners->ignore_nice_load; + } policy = cdbs->cur_policy; @@ -96,7 +111,46 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) if (unlikely(!wall_time || wall_time < idle_time)) continue; - load = 100 * (wall_time - idle_time) / wall_time; + /* + * If the CPU had gone completely idle, and a task just woke up + * on this CPU now, it would be unfair to calculate 'load' the + * usual way for this elapsed time-window, because it will show + * near-zero load, irrespective of how CPU intensive that task + * actually is. This is undesirable for latency-sensitive bursty + * workloads. + * + * To avoid this, we reuse the 'load' from the previous + * time-window and give this task a chance to start with a + * reasonably high CPU frequency. (However, we shouldn't over-do + * this copy, lest we get stuck at a high load (high frequency) + * for too long, even when the current system load has actually + * dropped down. So we perform the copy only once, upon the + * first wake-up from idle.) + * + * Detecting this situation is easy: the governor's deferrable + * timer would not have fired during CPU-idle periods. Hence + * an unusually large 'wall_time' (as compared to the sampling + * rate) indicates this scenario. + * + * prev_load can be zero in two cases and we must recalculate it + * for both cases: + * - during long idle intervals + * - explicitly set to zero + */ + if (unlikely(wall_time > (2 * sampling_rate) && + j_cdbs->prev_load)) { + load = j_cdbs->prev_load; + + /* + * Perform a destructive copy, to ensure that we copy + * the previous load only once, upon the first wake-up + * from idle. + */ + j_cdbs->prev_load = 0; + } else { + load = 100 * (wall_time - idle_time) / wall_time; + j_cdbs->prev_load = load; + } if (load > max_load) max_load = load; @@ -318,11 +372,18 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy, for_each_cpu(j, policy->cpus) { struct cpu_dbs_common_info *j_cdbs = dbs_data->cdata->get_cpu_cdbs(j); + unsigned int prev_load; j_cdbs->cpu = j; j_cdbs->cur_policy = policy; j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy); + + prev_load = (unsigned int) + (j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle); + j_cdbs->prev_load = 100 * prev_load / + (unsigned int) j_cdbs->prev_cpu_wall; + if (ignore_nice) j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index bfb9ae14142c..cc401d147e72 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -134,6 +134,13 @@ struct cpu_dbs_common_info { u64 prev_cpu_idle; u64 prev_cpu_wall; u64 prev_cpu_nice; + /* + * Used to keep track of load in the previous interval. However, when + * explicitly set to zero, it is used as a flag to ensure that we copy + * the previous load to the current interval only once, upon the first + * wake-up from idle. + */ + unsigned int prev_load; struct cpufreq_policy *cur_policy; struct delayed_work work; /* diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index aebd4572eb6d..4e7f492ad583 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -691,14 +691,8 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); static int intel_pstate_init_cpu(unsigned int cpunum) { - - const struct x86_cpu_id *id; struct cpudata *cpu; - id = x86_match_cpu(intel_pstate_cpu_ids); - if (!id) - return -ENODEV; - all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL); if (!all_cpu_data[cpunum]) return -ENOMEM; diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c index 0af618abebaf..3607070797af 100644 --- a/drivers/cpufreq/ppc-corenet-cpufreq.c +++ b/drivers/cpufreq/ppc-corenet-cpufreq.c @@ -138,7 +138,7 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy) struct cpufreq_frequency_table *table; struct cpu_data *data; unsigned int cpu = policy->cpu; - u64 transition_latency_hz; + u64 u64temp; np = of_get_cpu_node(cpu, NULL); if (!np) @@ -206,9 +206,10 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy) for_each_cpu(i, per_cpu(cpu_mask, cpu)) per_cpu(cpu_data, i) = data; - transition_latency_hz = 12ULL * NSEC_PER_SEC; - policy->cpuinfo.transition_latency = - do_div(transition_latency_hz, fsl_get_sys_freq()); + /* Minimum transition latency is 12 platform clocks */ + u64temp = 12ULL * NSEC_PER_SEC; + do_div(u64temp, fsl_get_sys_freq()); + policy->cpuinfo.transition_latency = u64temp + 1; of_node_put(np); diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c index 6e774c6ac20b..8084c7f7e206 100644 --- a/drivers/cpufreq/tegra-cpufreq.c +++ b/drivers/cpufreq/tegra-cpufreq.c @@ -45,46 +45,54 @@ static struct clk *cpu_clk; static struct clk *pll_x_clk; static struct clk *pll_p_clk; static struct clk *emc_clk; +static bool pll_x_prepared; -static int tegra_cpu_clk_set_rate(unsigned long rate) +static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy, + unsigned int index) +{ + unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000; + + /* + * Don't switch to intermediate freq if: + * - we are already at it, i.e. policy->cur == ifreq + * - index corresponds to ifreq + */ + if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq)) + return 0; + + return ifreq; +} + +static int tegra_target_intermediate(struct cpufreq_policy *policy, + unsigned int index) { int ret; /* * Take an extra reference to the main pll so it doesn't turn - * off when we move the cpu off of it + * off when we move the cpu off of it as enabling it again while we + * switch to it from tegra_target() would take additional time. + * + * When target-freq is equal to intermediate freq we don't need to + * switch to an intermediate freq and so this routine isn't called. + * Also, we wouldn't be using pll_x anymore and must not take extra + * reference to it, as it can be disabled now to save some power. */ clk_prepare_enable(pll_x_clk); ret = clk_set_parent(cpu_clk, pll_p_clk); - if (ret) { - pr_err("Failed to switch cpu to clock pll_p\n"); - goto out; - } + if (ret) + clk_disable_unprepare(pll_x_clk); + else + pll_x_prepared = true; - if (rate == clk_get_rate(pll_p_clk)) - goto out; - - ret = clk_set_rate(pll_x_clk, rate); - if (ret) { - pr_err("Failed to change pll_x to %lu\n", rate); - goto out; - } - - ret = clk_set_parent(cpu_clk, pll_x_clk); - if (ret) { - pr_err("Failed to switch cpu to clock pll_x\n"); - goto out; - } - -out: - clk_disable_unprepare(pll_x_clk); return ret; } static int tegra_target(struct cpufreq_policy *policy, unsigned int index) { unsigned long rate = freq_table[index].frequency; + unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000; int ret = 0; /* @@ -98,10 +106,30 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index) else clk_set_rate(emc_clk, 100000000); /* emc 50Mhz */ - ret = tegra_cpu_clk_set_rate(rate * 1000); + /* + * target freq == pll_p, don't need to take extra reference to pll_x_clk + * as it isn't used anymore. + */ + if (rate == ifreq) + return clk_set_parent(cpu_clk, pll_p_clk); + + ret = clk_set_rate(pll_x_clk, rate * 1000); + /* Restore to earlier frequency on error, i.e. pll_x */ if (ret) - pr_err("cpu-tegra: Failed to set cpu frequency to %lu kHz\n", - rate); + pr_err("Failed to change pll_x to %lu\n", rate); + + ret = clk_set_parent(cpu_clk, pll_x_clk); + /* This shouldn't fail while changing or restoring */ + WARN_ON(ret); + + /* + * Drop count to pll_x clock only if we switched to intermediate freq + * earlier while transitioning to a target frequency. + */ + if (pll_x_prepared) { + clk_disable_unprepare(pll_x_clk); + pll_x_prepared = false; + } return ret; } @@ -137,16 +165,18 @@ static int tegra_cpu_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver tegra_cpufreq_driver = { - .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, - .verify = cpufreq_generic_frequency_table_verify, - .target_index = tegra_target, - .get = cpufreq_generic_get, - .init = tegra_cpu_init, - .exit = tegra_cpu_exit, - .name = "tegra", - .attr = cpufreq_generic_attr, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .verify = cpufreq_generic_frequency_table_verify, + .get_intermediate = tegra_get_intermediate, + .target_intermediate = tegra_target_intermediate, + .target_index = tegra_target, + .get = cpufreq_generic_get, + .init = tegra_cpu_init, + .exit = tegra_cpu_exit, + .name = "tegra", + .attr = cpufreq_generic_attr, #ifdef CONFIG_PM - .suspend = cpufreq_generic_suspend, + .suspend = cpufreq_generic_suspend, #endif }; diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 719f6fb5b1c3..74f5788d50b1 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -73,12 +73,10 @@ static int fastsleep_loop(struct cpuidle_device *dev, return index; new_lpcr = old_lpcr; - new_lpcr &= ~(LPCR_MER | LPCR_PECE); /* lpcr[mer] must be 0 */ - - /* exit powersave upon external interrupt, but not decrementer - * interrupt. + /* Do not exit powersave upon decrementer as we've setup the timer + * offload. */ - new_lpcr |= LPCR_PECE0; + new_lpcr &= ~LPCR_PECE1; mtspr(SPRN_LPCR, new_lpcr); power7_sleep(); diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 136d6a283e0a..9634f20e3926 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -187,8 +187,11 @@ static int poll_idle(struct cpuidle_device *dev, t1 = ktime_get(); local_irq_enable(); - while (!need_resched()) - cpu_relax(); + if (!current_set_polling_and_test()) { + while (!need_resched()) + cpu_relax(); + } + current_clr_polling(); t2 = ktime_get(); diff = ktime_to_us(ktime_sub(t2, t1)); diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index f066fa23cc05..02f177aeb16c 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -313,7 +313,7 @@ config CRYPTO_DEV_S5P config CRYPTO_DEV_NX bool "Support for IBM Power7+ in-Nest cryptographic acceleration" - depends on PPC64 && IBMVIO + depends on PPC64 && IBMVIO && !CPU_LITTLE_ENDIAN default n help Support for Power7+ in-Nest cryptographic acceleration. diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d9c9cb4665db..2ebc9071e354 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2614,7 +2614,7 @@ static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx, &of_flags); - if (!IS_ERR(desc)) + if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER)) break; } diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile index d8a22c2a579d..70da9eb52a42 100644 --- a/drivers/gpu/Makefile +++ b/drivers/gpu/Makefile @@ -1,2 +1,3 @@ obj-y += drm/ vga/ obj-$(CONFIG_TEGRA_HOST1X) += host1x/ +obj-$(CONFIG_IMX_IPUV3_CORE) += ipu-v3/ diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index d1cc2f613a78..f5120046ff80 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -83,6 +83,8 @@ config DRM_KMS_CMA_HELPER source "drivers/gpu/drm/i2c/Kconfig" +source "drivers/gpu/drm/bridge/Kconfig" + config DRM_TDFX tristate "3dfx Banshee/Voodoo3+" depends on DRM && PCI @@ -199,5 +201,3 @@ source "drivers/gpu/drm/msm/Kconfig" source "drivers/gpu/drm/tegra/Kconfig" source "drivers/gpu/drm/panel/Kconfig" - -source "drivers/gpu/drm/bridge/Kconfig" diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 48e38ba22783..dd2ba4269740 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -14,7 +14,7 @@ drm-y := drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \ drm_info.o drm_debugfs.o drm_encoder_slave.o \ drm_trace_points.o drm_global.o drm_prime.o \ drm_rect.o drm_vma_manager.o drm_flip_work.o \ - drm_plane_helper.o + drm_modeset_lock.o drm-$(CONFIG_COMPAT) += drm_ioc32.o drm-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_gem_cma_helper.o @@ -23,7 +23,8 @@ drm-$(CONFIG_DRM_PANEL) += drm_panel.o drm-usb-y := drm_usb.o -drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o +drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \ + drm_plane_helper.o drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o drm_kms_helper-$(CONFIG_DRM_KMS_FB_HELPER) += drm_fb_helper.o drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 32982da82694..8ab3cd1a8cdb 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -173,7 +173,7 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags) if (ret) goto err_kms; - ret = drm_irq_install(dev); + ret = drm_irq_install(dev, platform_get_irq(dev->platformdev, 0)); if (ret) goto err_kms; @@ -402,7 +402,7 @@ static struct platform_driver armada_drm_platform_driver = { static int __init armada_drm_init(void) { - armada_drm_driver.num_ioctls = DRM_ARRAY_SIZE(armada_ioctls); + armada_drm_driver.num_ioctls = ARRAY_SIZE(armada_ioctls); return platform_driver_register(&armada_drm_platform_driver); } module_init(armada_drm_init); diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index 948cb14c561e..fd166f532ab9 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -181,10 +181,8 @@ void armada_fbdev_lastclose(struct drm_device *dev) { struct armada_private *priv = dev->dev_private; - drm_modeset_lock_all(dev); if (priv->fbdev) - drm_fb_helper_restore_fbdev_mode(priv->fbdev); - drm_modeset_unlock_all(dev); + drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev); } void armada_fbdev_fini(struct drm_device *dev) diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 887816f43476..bb9b642d8485 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -433,7 +433,6 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, if (dobj->obj.filp) { struct address_space *mapping; - gfp_t gfp; int count; count = dobj->obj.size / PAGE_SIZE; @@ -441,12 +440,11 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, goto free_sgt; mapping = file_inode(dobj->obj.filp)->i_mapping; - gfp = mapping_gfp_mask(mapping); for_each_sg(sgt->sgl, sg, count, i) { struct page *page; - page = shmem_read_mapping_page_gfp(mapping, i, gfp); + page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) { num = i; goto release; diff --git a/drivers/gpu/drm/ast/Makefile b/drivers/gpu/drm/ast/Makefile index 8df4f284ee24..171aa0622b66 100644 --- a/drivers/gpu/drm/ast/Makefile +++ b/drivers/gpu/drm/ast/Makefile @@ -4,6 +4,6 @@ ccflags-y := -Iinclude/drm -ast-y := ast_drv.o ast_main.o ast_mode.o ast_fb.o ast_ttm.o ast_post.o +ast-y := ast_drv.o ast_main.o ast_mode.o ast_fb.o ast_ttm.o ast_post.o ast_dp501.o -obj-$(CONFIG_DRM_AST) := ast.o \ No newline at end of file +obj-$(CONFIG_DRM_AST) := ast.o diff --git a/drivers/gpu/drm/ast/ast_dp501.c b/drivers/gpu/drm/ast/ast_dp501.c new file mode 100644 index 000000000000..5da4b62285fa --- /dev/null +++ b/drivers/gpu/drm/ast/ast_dp501.c @@ -0,0 +1,410 @@ + +#include +#include +#include "ast_drv.h" +MODULE_FIRMWARE("ast_dp501_fw.bin"); + +int ast_load_dp501_microcode(struct drm_device *dev) +{ + struct ast_private *ast = dev->dev_private; + static char *fw_name = "ast_dp501_fw.bin"; + int err; + err = request_firmware(&ast->dp501_fw, fw_name, dev->dev); + if (err) + return err; + + return 0; +} + +static void send_ack(struct ast_private *ast) +{ + u8 sendack; + sendack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0xff); + sendack |= 0x80; + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0x00, sendack); +} + +static void send_nack(struct ast_private *ast) +{ + u8 sendack; + sendack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0xff); + sendack &= ~0x80; + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0x00, sendack); +} + +static bool wait_ack(struct ast_private *ast) +{ + u8 waitack; + u32 retry = 0; + do { + waitack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff); + waitack &= 0x80; + udelay(100); + } while ((!waitack) && (retry++ < 1000)); + + if (retry < 1000) + return true; + else + return false; +} + +static bool wait_nack(struct ast_private *ast) +{ + u8 waitack; + u32 retry = 0; + do { + waitack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff); + waitack &= 0x80; + udelay(100); + } while ((waitack) && (retry++ < 1000)); + + if (retry < 1000) + return true; + else + return false; +} + +static void set_cmd_trigger(struct ast_private *ast) +{ + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, ~0x40, 0x40); +} + +static void clear_cmd_trigger(struct ast_private *ast) +{ + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, ~0x40, 0x00); +} + +#if 0 +static bool wait_fw_ready(struct ast_private *ast) +{ + u8 waitready; + u32 retry = 0; + do { + waitready = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff); + waitready &= 0x40; + udelay(100); + } while ((!waitready) && (retry++ < 1000)); + + if (retry < 1000) + return true; + else + return false; +} +#endif + +static bool ast_write_cmd(struct drm_device *dev, u8 data) +{ + struct ast_private *ast = dev->dev_private; + int retry = 0; + if (wait_nack(ast)) { + send_nack(ast); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, data); + send_ack(ast); + set_cmd_trigger(ast); + do { + if (wait_ack(ast)) { + clear_cmd_trigger(ast); + send_nack(ast); + return true; + } + } while (retry++ < 100); + } + clear_cmd_trigger(ast); + send_nack(ast); + return false; +} + +static bool ast_write_data(struct drm_device *dev, u8 data) +{ + struct ast_private *ast = dev->dev_private; + + if (wait_nack(ast)) { + send_nack(ast); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, data); + send_ack(ast); + if (wait_ack(ast)) { + send_nack(ast); + return true; + } + } + send_nack(ast); + return false; +} + +#if 0 +static bool ast_read_data(struct drm_device *dev, u8 *data) +{ + struct ast_private *ast = dev->dev_private; + u8 tmp; + + *data = 0; + + if (wait_ack(ast) == false) + return false; + tmp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd3, 0xff); + *data = tmp; + if (wait_nack(ast) == false) { + send_nack(ast); + return false; + } + send_nack(ast); + return true; +} + +static void clear_cmd(struct ast_private *ast) +{ + send_nack(ast); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, 0x00); +} +#endif + +void ast_set_dp501_video_output(struct drm_device *dev, u8 mode) +{ + ast_write_cmd(dev, 0x40); + ast_write_data(dev, mode); + + msleep(10); +} + +static u32 get_fw_base(struct ast_private *ast) +{ + return ast_mindwm(ast, 0x1e6e2104) & 0x7fffffff; +} + +bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size) +{ + struct ast_private *ast = dev->dev_private; + u32 i, data; + u32 boot_address; + + data = ast_mindwm(ast, 0x1e6e2100) & 0x01; + if (data) { + boot_address = get_fw_base(ast); + for (i = 0; i < size; i += 4) + *(u32 *)(addr + i) = ast_mindwm(ast, boot_address + i); + return true; + } + return false; +} + +bool ast_launch_m68k(struct drm_device *dev) +{ + struct ast_private *ast = dev->dev_private; + u32 i, data, len = 0; + u32 boot_address; + u8 *fw_addr = NULL; + u8 jreg; + + data = ast_mindwm(ast, 0x1e6e2100) & 0x01; + if (!data) { + + if (ast->dp501_fw_addr) { + fw_addr = ast->dp501_fw_addr; + len = 32*1024; + } else if (ast->dp501_fw) { + fw_addr = (u8 *)ast->dp501_fw->data; + len = ast->dp501_fw->size; + } + /* Get BootAddress */ + ast_moutdwm(ast, 0x1e6e2000, 0x1688a8a8); + data = ast_mindwm(ast, 0x1e6e0004); + switch (data & 0x03) { + case 0: + boot_address = 0x44000000; + break; + default: + case 1: + boot_address = 0x48000000; + break; + case 2: + boot_address = 0x50000000; + break; + case 3: + boot_address = 0x60000000; + break; + } + boot_address -= 0x200000; /* -2MB */ + + /* copy image to buffer */ + for (i = 0; i < len; i += 4) { + data = *(u32 *)(fw_addr + i); + ast_moutdwm(ast, boot_address + i, data); + } + + /* Init SCU */ + ast_moutdwm(ast, 0x1e6e2000, 0x1688a8a8); + + /* Launch FW */ + ast_moutdwm(ast, 0x1e6e2104, 0x80000000 + boot_address); + ast_moutdwm(ast, 0x1e6e2100, 1); + + /* Update Scratch */ + data = ast_mindwm(ast, 0x1e6e2040) & 0xfffff1ff; /* D[11:9] = 100b: UEFI handling */ + data |= 0x800; + ast_moutdwm(ast, 0x1e6e2040, data); + + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x99, 0xfc); /* D[1:0]: Reserved Video Buffer */ + jreg |= 0x02; + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x99, jreg); + } + return true; +} + +u8 ast_get_dp501_max_clk(struct drm_device *dev) +{ + struct ast_private *ast = dev->dev_private; + u32 boot_address, offset, data; + u8 linkcap[4], linkrate, linklanes, maxclk = 0xff; + + boot_address = get_fw_base(ast); + + /* validate FW version */ + offset = 0xf000; + data = ast_mindwm(ast, boot_address + offset); + if ((data & 0xf0) != 0x10) /* version: 1x */ + return maxclk; + + /* Read Link Capability */ + offset = 0xf014; + *(u32 *)linkcap = ast_mindwm(ast, boot_address + offset); + if (linkcap[2] == 0) { + linkrate = linkcap[0]; + linklanes = linkcap[1]; + data = (linkrate == 0x0a) ? (90 * linklanes) : (54 * linklanes); + if (data > 0xff) + data = 0xff; + maxclk = (u8)data; + } + return maxclk; +} + +bool ast_dp501_read_edid(struct drm_device *dev, u8 *ediddata) +{ + struct ast_private *ast = dev->dev_private; + u32 i, boot_address, offset, data; + + boot_address = get_fw_base(ast); + + /* validate FW version */ + offset = 0xf000; + data = ast_mindwm(ast, boot_address + offset); + if ((data & 0xf0) != 0x10) + return false; + + /* validate PnP Monitor */ + offset = 0xf010; + data = ast_mindwm(ast, boot_address + offset); + if (!(data & 0x01)) + return false; + + /* Read EDID */ + offset = 0xf020; + for (i = 0; i < 128; i += 4) { + data = ast_mindwm(ast, boot_address + offset + i); + *(u32 *)(ediddata + i) = data; + } + + return true; +} + +static bool ast_init_dvo(struct drm_device *dev) +{ + struct ast_private *ast = dev->dev_private; + u8 jreg; + u32 data; + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + ast_write32(ast, 0x12000, 0x1688a8a8); + + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff); + if (!(jreg & 0x80)) { + /* Init SCU DVO Settings */ + data = ast_read32(ast, 0x12008); + /* delay phase */ + data &= 0xfffff8ff; + data |= 0x00000500; + ast_write32(ast, 0x12008, data); + + if (ast->chip == AST2300) { + data = ast_read32(ast, 0x12084); + /* multi-pins for DVO single-edge */ + data |= 0xfffe0000; + ast_write32(ast, 0x12084, data); + + data = ast_read32(ast, 0x12088); + /* multi-pins for DVO single-edge */ + data |= 0x000fffff; + ast_write32(ast, 0x12088, data); + + data = ast_read32(ast, 0x12090); + /* multi-pins for DVO single-edge */ + data &= 0xffffffcf; + data |= 0x00000020; + ast_write32(ast, 0x12090, data); + } else { /* AST2400 */ + data = ast_read32(ast, 0x12088); + /* multi-pins for DVO single-edge */ + data |= 0x30000000; + ast_write32(ast, 0x12088, data); + + data = ast_read32(ast, 0x1208c); + /* multi-pins for DVO single-edge */ + data |= 0x000000cf; + ast_write32(ast, 0x1208c, data); + + data = ast_read32(ast, 0x120a4); + /* multi-pins for DVO single-edge */ + data |= 0xffff0000; + ast_write32(ast, 0x120a4, data); + + data = ast_read32(ast, 0x120a8); + /* multi-pins for DVO single-edge */ + data |= 0x0000000f; + ast_write32(ast, 0x120a8, data); + + data = ast_read32(ast, 0x12094); + /* multi-pins for DVO single-edge */ + data |= 0x00000002; + ast_write32(ast, 0x12094, data); + } + } + + /* Force to DVO */ + data = ast_read32(ast, 0x1202c); + data &= 0xfffbffff; + ast_write32(ast, 0x1202c, data); + + /* Init VGA DVO Settings */ + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); + return true; +} + +void ast_init_3rdtx(struct drm_device *dev) +{ + struct ast_private *ast = dev->dev_private; + u8 jreg; + u32 data; + if (ast->chip == AST2300 || ast->chip == AST2400) { + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff); + switch (jreg & 0x0e) { + case 0x04: + ast_init_dvo(dev); + break; + case 0x08: + ast_launch_m68k(dev); + break; + case 0x0c: + ast_init_dvo(dev); + break; + default: + if (ast->tx_chip_type == AST_TX_SIL164) + ast_init_dvo(dev); + else { + ast_write32(ast, 0x12000, 0x1688a8a8); + data = ast_read32(ast, 0x1202c); + data &= 0xfffcffff; + ast_write32(ast, 0, data); + } + } + } +} diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 5137f15dba19..44074fbcf7ff 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -94,9 +94,7 @@ static int ast_drm_thaw(struct drm_device *dev) ast_post_gpu(dev); drm_mode_config_reset(dev); - drm_modeset_lock_all(dev); drm_helper_resume_force_mode(dev); - drm_modeset_unlock_all(dev); console_lock(); ast_fbdev_set_suspend(dev, 0); @@ -198,7 +196,6 @@ static const struct file_operations ast_fops = { static struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM, - .dev_priv_size = 0, .load = ast_driver_load, .unload = ast_driver_unload, diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 9833a1b1acc1..5d6a87573c33 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -61,9 +61,17 @@ enum ast_chip { AST2200, AST2150, AST2300, + AST2400, AST1180, }; +enum ast_tx_chip { + AST_TX_NONE, + AST_TX_SIL164, + AST_TX_ITE66121, + AST_TX_DP501, +}; + #define AST_DRAM_512Mx16 0 #define AST_DRAM_1Gx16 1 #define AST_DRAM_512Mx32 2 @@ -102,6 +110,12 @@ struct ast_private { * we have. */ struct ttm_bo_kmap_obj cache_kmap; int next_cursor; + bool support_wide_screen; + + enum ast_tx_chip tx_chip_type; + u8 dp501_maxclk; + u8 *dp501_fw_addr; + const struct firmware *dp501_fw; /* dp501 fw */ }; int ast_driver_load(struct drm_device *dev, unsigned long flags); @@ -368,4 +382,14 @@ int ast_mmap(struct file *filp, struct vm_area_struct *vma); /* ast post */ void ast_post_gpu(struct drm_device *dev); +u32 ast_mindwm(struct ast_private *ast, u32 r); +void ast_moutdwm(struct ast_private *ast, u32 r, u32 v); +/* ast dp501 */ +int ast_load_dp501_microcode(struct drm_device *dev); +void ast_set_dp501_video_output(struct drm_device *dev, u8 mode); +bool ast_launch_m68k(struct drm_device *dev); +bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size); +bool ast_dp501_read_edid(struct drm_device *dev, u8 *ediddata); +u8 ast_get_dp501_max_clk(struct drm_device *dev); +void ast_init_3rdtx(struct drm_device *dev); #endif diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 50535fd5a88d..a2cc6be97983 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -66,12 +66,16 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast, static int ast_detect_chip(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; + uint32_t data, jreg; if (dev->pdev->device == PCI_CHIP_AST1180) { ast->chip = AST1100; DRM_INFO("AST 1180 detected\n"); } else { - if (dev->pdev->revision >= 0x20) { + if (dev->pdev->revision >= 0x30) { + ast->chip = AST2400; + DRM_INFO("AST 2400 detected\n"); + } else if (dev->pdev->revision >= 0x20) { ast->chip = AST2300; DRM_INFO("AST 2300 detected\n"); } else if (dev->pdev->revision >= 0x10) { @@ -104,6 +108,59 @@ static int ast_detect_chip(struct drm_device *dev) DRM_INFO("AST 2000 detected\n"); } } + + switch (ast->chip) { + case AST1180: + ast->support_wide_screen = true; + break; + case AST2000: + ast->support_wide_screen = false; + break; + default: + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff); + if (!(jreg & 0x80)) + ast->support_wide_screen = true; + else if (jreg & 0x01) + ast->support_wide_screen = true; + else { + ast->support_wide_screen = false; + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + data = ast_read32(ast, 0x1207c); + data &= 0x300; + if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ + ast->support_wide_screen = true; + if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ + ast->support_wide_screen = true; + } + break; + } + + ast->tx_chip_type = AST_TX_NONE; + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xff); + if (jreg & 0x80) + ast->tx_chip_type = AST_TX_SIL164; + if ((ast->chip == AST2300) || (ast->chip == AST2400)) { + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff); + switch (jreg) { + case 0x04: + ast->tx_chip_type = AST_TX_SIL164; + break; + case 0x08: + ast->dp501_fw_addr = kzalloc(32*1024, GFP_KERNEL); + if (ast->dp501_fw_addr) { + /* backup firmware */ + if (ast_backup_fw(dev, ast->dp501_fw_addr, 32*1024)) { + kfree(ast->dp501_fw_addr); + ast->dp501_fw_addr = NULL; + } + } + /* fallthrough */ + case 0x0c: + ast->tx_chip_type = AST_TX_DP501; + } + } + return 0; } @@ -129,7 +186,7 @@ static int ast_get_dram_info(struct drm_device *dev) else ast->dram_bus_width = 32; - if (ast->chip == AST2300) { + if (ast->chip == AST2300 || ast->chip == AST2400) { switch (data & 0x03) { case 0: ast->dram_type = AST_DRAM_512Mx16; @@ -257,17 +314,32 @@ static u32 ast_get_vram_info(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; u8 jreg; - + u32 vram_size; ast_open_key(ast); + vram_size = AST_VIDMEM_DEFAULT_SIZE; jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xaa, 0xff); switch (jreg & 3) { - case 0: return AST_VIDMEM_SIZE_8M; - case 1: return AST_VIDMEM_SIZE_16M; - case 2: return AST_VIDMEM_SIZE_32M; - case 3: return AST_VIDMEM_SIZE_64M; + case 0: vram_size = AST_VIDMEM_SIZE_8M; break; + case 1: vram_size = AST_VIDMEM_SIZE_16M; break; + case 2: vram_size = AST_VIDMEM_SIZE_32M; break; + case 3: vram_size = AST_VIDMEM_SIZE_64M; break; } - return AST_VIDMEM_DEFAULT_SIZE; + + jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x99, 0xff); + switch (jreg & 0x03) { + case 1: + vram_size -= 0x100000; + break; + case 2: + vram_size -= 0x200000; + break; + case 3: + vram_size -= 0x400000; + break; + } + + return vram_size; } int ast_driver_load(struct drm_device *dev, unsigned long flags) @@ -316,6 +388,7 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags) if (ast->chip == AST2100 || ast->chip == AST2200 || ast->chip == AST2300 || + ast->chip == AST2400 || ast->chip == AST1180) { dev->mode_config.max_width = 1920; dev->mode_config.max_height = 2048; @@ -343,6 +416,7 @@ int ast_driver_unload(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; + kfree(ast->dp501_fw_addr); ast_mode_fini(dev); ast_fbdev_fini(dev); drm_mode_config_cleanup(dev); @@ -411,16 +485,13 @@ static void ast_bo_unref(struct ast_bo **bo) tbo = &((*bo)->bo); ttm_bo_unref(&tbo); - if (tbo == NULL) - *bo = NULL; - + *bo = NULL; } + void ast_gem_free_object(struct drm_gem_object *obj) { struct ast_bo *ast_bo = gem_to_ast_bo(obj); - if (!ast_bo) - return; ast_bo_unref(&ast_bo); } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index a4afdc8bb578..114aee941d46 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -115,11 +115,17 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo else vbios_mode->enh_table = &res_1280x1024[refresh_rate_index]; break; + case 1360: + vbios_mode->enh_table = &res_1360x768[refresh_rate_index]; + break; case 1440: vbios_mode->enh_table = &res_1440x900[refresh_rate_index]; break; case 1600: - vbios_mode->enh_table = &res_1600x1200[refresh_rate_index]; + if (crtc->mode.crtc_vdisplay == 900) + vbios_mode->enh_table = &res_1600x900[refresh_rate_index]; + else + vbios_mode->enh_table = &res_1600x1200[refresh_rate_index]; break; case 1680: vbios_mode->enh_table = &res_1680x1050[refresh_rate_index]; @@ -175,14 +181,17 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff); ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, crtc->primary->fb->bits_per_pixel); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00); + if (vbios_mode->enh_table->flags & NewModeInfo) { + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, crtc->primary->fb->bits_per_pixel); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay); - ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8); + } } return true; @@ -389,7 +398,7 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa8, 0xfd, jregA8); /* Set Threshold */ - if (ast->chip == AST2300) { + if (ast->chip == AST2300 || ast->chip == AST2400) { ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa7, 0x78); ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa6, 0x60); } else if (ast->chip == AST2100 || @@ -451,9 +460,13 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode) case DRM_MODE_DPMS_STANDBY: case DRM_MODE_DPMS_SUSPEND: ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0); + if (ast->tx_chip_type == AST_TX_DP501) + ast_set_dp501_video_output(crtc->dev, 1); ast_crtc_load_lut(crtc); break; case DRM_MODE_DPMS_OFF: + if (ast->tx_chip_type == AST_TX_DP501) + ast_set_dp501_video_output(crtc->dev, 0); ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20); break; } @@ -729,10 +742,24 @@ static int ast_encoder_init(struct drm_device *dev) static int ast_get_modes(struct drm_connector *connector) { struct ast_connector *ast_connector = to_ast_connector(connector); + struct ast_private *ast = connector->dev->dev_private; struct edid *edid; int ret; + bool flags = false; + if (ast->tx_chip_type == AST_TX_DP501) { + ast->dp501_maxclk = 0xff; + edid = kmalloc(128, GFP_KERNEL); + if (!edid) + return -ENOMEM; - edid = drm_get_edid(connector, &ast_connector->i2c->adapter); + flags = ast_dp501_read_edid(connector->dev, (u8 *)edid); + if (flags) + ast->dp501_maxclk = ast_get_dp501_max_clk(connector->dev); + else + kfree(edid); + } + if (!flags) + edid = drm_get_edid(connector, &ast_connector->i2c->adapter); if (edid) { drm_mode_connector_update_edid_property(&ast_connector->base, edid); ret = drm_add_edid_modes(connector, edid); @@ -746,7 +773,56 @@ static int ast_get_modes(struct drm_connector *connector) static int ast_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { - return MODE_OK; + struct ast_private *ast = connector->dev->dev_private; + int flags = MODE_NOMODE; + uint32_t jtemp; + + if (ast->support_wide_screen) { + if ((mode->hdisplay == 1680) && (mode->vdisplay == 1050)) + return MODE_OK; + if ((mode->hdisplay == 1280) && (mode->vdisplay == 800)) + return MODE_OK; + if ((mode->hdisplay == 1440) && (mode->vdisplay == 900)) + return MODE_OK; + if ((mode->hdisplay == 1360) && (mode->vdisplay == 768)) + return MODE_OK; + if ((mode->hdisplay == 1600) && (mode->vdisplay == 900)) + return MODE_OK; + + if ((ast->chip == AST2100) || (ast->chip == AST2200) || (ast->chip == AST2300) || (ast->chip == AST2400) || (ast->chip == AST1180)) { + if ((mode->hdisplay == 1920) && (mode->vdisplay == 1080)) + return MODE_OK; + + if ((mode->hdisplay == 1920) && (mode->vdisplay == 1200)) { + jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff); + if (jtemp & 0x01) + return MODE_NOMODE; + else + return MODE_OK; + } + } + } + switch (mode->hdisplay) { + case 640: + if (mode->vdisplay == 480) flags = MODE_OK; + break; + case 800: + if (mode->vdisplay == 600) flags = MODE_OK; + break; + case 1024: + if (mode->vdisplay == 768) flags = MODE_OK; + break; + case 1280: + if (mode->vdisplay == 1024) flags = MODE_OK; + break; + case 1600: + if (mode->vdisplay == 1200) flags = MODE_OK; + break; + default: + return flags; + } + + return flags; } static void ast_connector_destroy(struct drm_connector *connector) diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 635f6ffc27c2..38d437f3a267 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -78,7 +78,7 @@ ast_set_def_ext_reg(struct drm_device *dev) for (i = 0x81; i <= 0x8f; i++) ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, 0x00); - if (ast->chip == AST2300) { + if (ast->chip == AST2300 || ast->chip == AST2400) { if (dev->pdev->revision >= 0x20) ext_reg_info = extreginfo_ast2300; else @@ -102,23 +102,32 @@ ast_set_def_ext_reg(struct drm_device *dev) /* Enable RAMDAC for A1 */ reg = 0x04; - if (ast->chip == AST2300) + if (ast->chip == AST2300 || ast->chip == AST2400) reg |= 0x20; ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff, reg); } -static inline u32 mindwm(struct ast_private *ast, u32 r) +u32 ast_mindwm(struct ast_private *ast, u32 r) { + uint32_t data; + ast_write32(ast, 0xf004, r & 0xffff0000); ast_write32(ast, 0xf000, 0x1); + do { + data = ast_read32(ast, 0xf004) & 0xffff0000; + } while (data != (r & 0xffff0000)); return ast_read32(ast, 0x10000 + (r & 0x0000ffff)); } -static inline void moutdwm(struct ast_private *ast, u32 r, u32 v) +void ast_moutdwm(struct ast_private *ast, u32 r, u32 v) { + uint32_t data; ast_write32(ast, 0xf004, r & 0xffff0000); ast_write32(ast, 0xf000, 0x1); + do { + data = ast_read32(ast, 0xf004) & 0xffff0000; + } while (data != (r & 0xffff0000)); ast_write32(ast, 0x10000 + (r & 0x0000ffff), v); } @@ -154,28 +163,28 @@ static u32 mmctestburst2_ast2150(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x00000001 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000001 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x40; + data = ast_mindwm(ast, 0x1e6e0070) & 0x40; if (++timeout > TIMEOUT_AST2150) { - moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return 0xffffffff; } } while (!data); - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x00000003 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000003 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x40; + data = ast_mindwm(ast, 0x1e6e0070) & 0x40; if (++timeout > TIMEOUT_AST2150) { - moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return 0xffffffff; } } while (!data); - data = (mindwm(ast, 0x1e6e0070) & 0x80) >> 7; - moutdwm(ast, 0x1e6e0070, 0x00000000); + data = (ast_mindwm(ast, 0x1e6e0070) & 0x80) >> 7; + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return data; } @@ -184,18 +193,18 @@ static u32 mmctestsingle2_ast2150(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x40; + data = ast_mindwm(ast, 0x1e6e0070) & 0x40; if (++timeout > TIMEOUT_AST2150) { - moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return 0xffffffff; } } while (!data); - data = (mindwm(ast, 0x1e6e0070) & 0x80) >> 7; - moutdwm(ast, 0x1e6e0070, 0x00000000); + data = (ast_mindwm(ast, 0x1e6e0070) & 0x80) >> 7; + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return data; } #endif @@ -215,7 +224,7 @@ static int cbrscan_ast2150(struct ast_private *ast, int busw) u32 patcnt, loop; for (patcnt = 0; patcnt < CBR_PATNUM_AST2150; patcnt++) { - moutdwm(ast, 0x1e6e007c, pattern_AST2150[patcnt]); + ast_moutdwm(ast, 0x1e6e007c, pattern_AST2150[patcnt]); for (loop = 0; loop < CBR_PASSNUM_AST2150; loop++) { if (cbrtest_ast2150(ast)) break; @@ -237,7 +246,7 @@ static void cbrdlli_ast2150(struct ast_private *ast, int busw) passcnt = 0; for (dlli = 0; dlli < 100; dlli++) { - moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24)); + ast_moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24)); data = cbrscan_ast2150(ast, busw); if (data != 0) { if (data & 0x1) { @@ -254,7 +263,7 @@ static void cbrdlli_ast2150(struct ast_private *ast, int busw) goto cbr_start; dlli = dll_min[0] + (((dll_max[0] - dll_min[0]) * 7) >> 4); - moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24)); + ast_moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24)); } @@ -365,10 +374,12 @@ void ast_post_gpu(struct drm_device *dev) ast_open_key(ast); ast_set_def_ext_reg(dev); - if (ast->chip == AST2300) + if (ast->chip == AST2300 || ast->chip == AST2400) ast_init_dram_2300(dev); else ast_init_dram_reg(dev); + + ast_init_3rdtx(dev); } /* AST 2300 DRAM settings */ @@ -403,6 +414,7 @@ struct ast2300_dram_param { /* * DQSI DLL CBR Setting */ +#define CBR_SIZE0 ((1 << 10) - 1) #define CBR_SIZE1 ((4 << 10) - 1) #define CBR_SIZE2 ((64 << 10) - 1) #define CBR_PASSNUM 5 @@ -423,88 +435,84 @@ static const u32 pattern[8] = { 0x7C61D253 }; -#if 0 /* unused in DDX, included for completeness */ static int mmc_test_burst(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x000000c1 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x000000c1 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x3000; + data = ast_mindwm(ast, 0x1e6e0070) & 0x3000; if (data & 0x2000) { return 0; } if (++timeout > TIMEOUT) { - moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return 0; } } while (!data); - moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); return 1; } -#endif static int mmc_test_burst2(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x00000041 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000041 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x1000; + data = ast_mindwm(ast, 0x1e6e0070) & 0x1000; if (++timeout > TIMEOUT) { - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return -1; } } while (!data); - data = mindwm(ast, 0x1e6e0078); + data = ast_mindwm(ast, 0x1e6e0078); data = (data | (data >> 16)) & 0xffff; - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return data; } -#if 0 /* Unused in DDX here for completeness */ static int mmc_test_single(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x000000c5 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x000000c5 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x3000; + data = ast_mindwm(ast, 0x1e6e0070) & 0x3000; if (data & 0x2000) return 0; if (++timeout > TIMEOUT) { - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return 0; } } while (!data); - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return 1; } -#endif static int mmc_test_single2(struct ast_private *ast, u32 datagen) { u32 data, timeout; - moutdwm(ast, 0x1e6e0070, 0x00000000); - moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3)); + ast_moutdwm(ast, 0x1e6e0070, 0x00000000); + ast_moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3)); timeout = 0; do { - data = mindwm(ast, 0x1e6e0070) & 0x1000; + data = ast_mindwm(ast, 0x1e6e0070) & 0x1000; if (++timeout > TIMEOUT) { - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return -1; } } while (!data); - data = mindwm(ast, 0x1e6e0078); + data = ast_mindwm(ast, 0x1e6e0078); data = (data | (data >> 16)) & 0xffff; - moutdwm(ast, 0x1e6e0070, 0x0); + ast_moutdwm(ast, 0x1e6e0070, 0x0); return data; } @@ -533,7 +541,7 @@ static int cbr_scan(struct ast_private *ast) data2 = 3; for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) { - moutdwm(ast, 0x1e6e007c, pattern[patcnt]); + ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]); for (loop = 0; loop < CBR_PASSNUM2; loop++) { if ((data = cbr_test(ast)) != 0) { data2 &= data; @@ -568,7 +576,7 @@ static u32 cbr_scan2(struct ast_private *ast) data2 = 0xffff; for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) { - moutdwm(ast, 0x1e6e007c, pattern[patcnt]); + ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]); for (loop = 0; loop < CBR_PASSNUM2; loop++) { if ((data = cbr_test2(ast)) != 0) { data2 &= data; @@ -583,106 +591,35 @@ static u32 cbr_scan2(struct ast_private *ast) return data2; } -#if 0 /* unused in DDX - added for completeness */ -static void finetuneDQI(struct ast_private *ast, struct ast2300_dram_param *param) +static u32 cbr_test3(struct ast_private *ast) { - u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt; + if (!mmc_test_burst(ast, 0)) + return 0; + if (!mmc_test_single(ast, 0)) + return 0; + return 1; +} - gold_sadj[0] = (mindwm(ast, 0x1E6E0024) >> 16) & 0xffff; - gold_sadj[1] = gold_sadj[0] >> 8; - gold_sadj[0] = gold_sadj[0] & 0xff; - gold_sadj[0] = (gold_sadj[0] + gold_sadj[1]) >> 1; - gold_sadj[1] = gold_sadj[0]; - - for (cnt = 0; cnt < 16; cnt++) { - dllmin[cnt] = 0xff; - dllmax[cnt] = 0x0; - } - passcnt = 0; - for (dlli = 0; dlli < 76; dlli++) { - moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24)); - /* Wait DQSI latch phase calibration */ - moutdwm(ast, 0x1E6E0074, 0x00000010); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - - moutdwm(ast, 0x1E6E0074, CBR_SIZE1); - data = cbr_scan2(ast); - if (data != 0) { - mask = 0x00010001; - for (cnt = 0; cnt < 16; cnt++) { - if (data & mask) { - if (dllmin[cnt] > dlli) { - dllmin[cnt] = dlli; - } - if (dllmax[cnt] < dlli) { - dllmax[cnt] = dlli; - } - } - mask <<= 1; - } - passcnt++; - } else if (passcnt >= CBR_THRESHOLD) { - break; - } - } - data = 0; - for (cnt = 0; cnt < 8; cnt++) { - data >>= 3; - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD)) { - dlli = (dllmin[cnt] + dllmax[cnt]) >> 1; - if (gold_sadj[0] >= dlli) { - dlli = (gold_sadj[0] - dlli) >> 1; - if (dlli > 3) { - dlli = 3; - } - } else { - dlli = (dlli - gold_sadj[0]) >> 1; - if (dlli > 4) { - dlli = 4; - } - dlli = (8 - dlli) & 0x7; - } - data |= dlli << 21; - } - } - moutdwm(ast, 0x1E6E0080, data); - - data = 0; - for (cnt = 8; cnt < 16; cnt++) { - data >>= 3; - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD)) { - dlli = (dllmin[cnt] + dllmax[cnt]) >> 1; - if (gold_sadj[1] >= dlli) { - dlli = (gold_sadj[1] - dlli) >> 1; - if (dlli > 3) { - dlli = 3; - } else { - dlli = (dlli - 1) & 0x7; - } - } else { - dlli = (dlli - gold_sadj[1]) >> 1; - dlli += 1; - if (dlli > 4) { - dlli = 4; - } - dlli = (8 - dlli) & 0x7; - } - data |= dlli << 21; - } - } - moutdwm(ast, 0x1E6E0084, data); - -} /* finetuneDQI */ -#endif - -static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *param) +static u32 cbr_scan3(struct ast_private *ast) { - u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt; + u32 patcnt, loop; + for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) { + ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]); + for (loop = 0; loop < 2; loop++) { + if (cbr_test3(ast)) + break; + } + if (loop == 2) + return 0; + } + return 1; +} + +static bool finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *param) +{ + u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt, retry = 0; + bool status = false; FINETUNE_START: for (cnt = 0; cnt < 16; cnt++) { dllmin[cnt] = 0xff; @@ -690,16 +627,8 @@ static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *pa } passcnt = 0; for (dlli = 0; dlli < 76; dlli++) { - moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24)); - /* Wait DQSI latch phase calibration */ - moutdwm(ast, 0x1E6E0074, 0x00000010); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - - moutdwm(ast, 0x1E6E0074, CBR_SIZE1); + ast_moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24)); + ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE1); data = cbr_scan2(ast); if (data != 0) { mask = 0x00010001; @@ -727,9 +656,13 @@ static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *pa passcnt++; } } + if (retry++ > 10) + goto FINETUNE_DONE; if (passcnt != 16) { goto FINETUNE_START; } + status = true; +FINETUNE_DONE: gold_sadj[0] = gold_sadj[0] >> 4; gold_sadj[1] = gold_sadj[0]; @@ -753,7 +686,7 @@ static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *pa data |= dlli << 21; } } - moutdwm(ast, 0x1E6E0080, data); + ast_moutdwm(ast, 0x1E6E0080, data); data = 0; for (cnt = 8; cnt < 16; cnt++) { @@ -778,162 +711,116 @@ static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *pa data |= dlli << 21; } } - moutdwm(ast, 0x1E6E0084, data); - + ast_moutdwm(ast, 0x1E6E0084, data); + return status; } /* finetuneDQI_L */ -static void finetuneDQI_L2(struct ast_private *ast, struct ast2300_dram_param *param) +static void finetuneDQSI(struct ast_private *ast) { - u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt, data2; + u32 dlli, dqsip, dqidly; + u32 reg_mcr18, reg_mcr0c, passcnt[2], diff; + u32 g_dqidly, g_dqsip, g_margin, g_side; + u16 pass[32][2][2]; + char tag[2][76]; + + /* Disable DQI CBR */ + reg_mcr0c = ast_mindwm(ast, 0x1E6E000C); + reg_mcr18 = ast_mindwm(ast, 0x1E6E0018); + reg_mcr18 &= 0x0000ffff; + ast_moutdwm(ast, 0x1E6E0018, reg_mcr18); - for (cnt = 0; cnt < 16; cnt++) { - dllmin[cnt] = 0xff; - dllmax[cnt] = 0x0; - } - passcnt = 0; for (dlli = 0; dlli < 76; dlli++) { - moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24)); - /* Wait DQSI latch phase calibration */ - moutdwm(ast, 0x1E6E0074, 0x00000010); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - - moutdwm(ast, 0x1E6E0074, CBR_SIZE2); - data = cbr_scan2(ast); - if (data != 0) { - mask = 0x00010001; - for (cnt = 0; cnt < 16; cnt++) { - if (data & mask) { - if (dllmin[cnt] > dlli) { - dllmin[cnt] = dlli; - } - if (dllmax[cnt] < dlli) { - dllmax[cnt] = dlli; - } - } - mask <<= 1; - } - passcnt++; - } else if (passcnt >= CBR_THRESHOLD2) { - break; - } + tag[0][dlli] = 0x0; + tag[1][dlli] = 0x0; } - gold_sadj[0] = 0x0; - gold_sadj[1] = 0xFF; - for (cnt = 0; cnt < 8; cnt++) { - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) { - if (gold_sadj[0] < dllmin[cnt]) { - gold_sadj[0] = dllmin[cnt]; - } - if (gold_sadj[1] > dllmax[cnt]) { - gold_sadj[1] = dllmax[cnt]; - } - } + for (dqidly = 0; dqidly < 32; dqidly++) { + pass[dqidly][0][0] = 0xff; + pass[dqidly][0][1] = 0x0; + pass[dqidly][1][0] = 0xff; + pass[dqidly][1][1] = 0x0; } - gold_sadj[0] = (gold_sadj[1] + gold_sadj[0]) >> 1; - gold_sadj[1] = mindwm(ast, 0x1E6E0080); - - data = 0; - for (cnt = 0; cnt < 8; cnt++) { - data >>= 3; - data2 = gold_sadj[1] & 0x7; - gold_sadj[1] >>= 3; - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) { - dlli = (dllmin[cnt] + dllmax[cnt]) >> 1; - if (gold_sadj[0] >= dlli) { - dlli = (gold_sadj[0] - dlli) >> 1; - if (dlli > 0) { - dlli = 1; - } - if (data2 != 3) { - data2 = (data2 + dlli) & 0x7; - } - } else { - dlli = (dlli - gold_sadj[0]) >> 1; - if (dlli > 0) { - dlli = 1; - } - if (data2 != 4) { - data2 = (data2 - dlli) & 0x7; + for (dqidly = 0; dqidly < 32; dqidly++) { + passcnt[0] = passcnt[1] = 0; + for (dqsip = 0; dqsip < 2; dqsip++) { + ast_moutdwm(ast, 0x1E6E000C, 0); + ast_moutdwm(ast, 0x1E6E0018, reg_mcr18 | (dqidly << 16) | (dqsip << 23)); + ast_moutdwm(ast, 0x1E6E000C, reg_mcr0c); + for (dlli = 0; dlli < 76; dlli++) { + ast_moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24)); + ast_moutdwm(ast, 0x1E6E0070, 0); + ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE0); + if (cbr_scan3(ast)) { + if (dlli == 0) + break; + passcnt[dqsip]++; + tag[dqsip][dlli] = 'P'; + if (dlli < pass[dqidly][dqsip][0]) + pass[dqidly][dqsip][0] = (u16) dlli; + if (dlli > pass[dqidly][dqsip][1]) + pass[dqidly][dqsip][1] = (u16) dlli; + } else if (passcnt[dqsip] >= 5) + break; + else { + pass[dqidly][dqsip][0] = 0xff; + pass[dqidly][dqsip][1] = 0x0; } } } - data |= data2 << 21; + if (passcnt[0] == 0 && passcnt[1] == 0) + dqidly++; } - moutdwm(ast, 0x1E6E0080, data); + /* Search margin */ + g_dqidly = g_dqsip = g_margin = g_side = 0; - gold_sadj[0] = 0x0; - gold_sadj[1] = 0xFF; - for (cnt = 8; cnt < 16; cnt++) { - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) { - if (gold_sadj[0] < dllmin[cnt]) { - gold_sadj[0] = dllmin[cnt]; - } - if (gold_sadj[1] > dllmax[cnt]) { - gold_sadj[1] = dllmax[cnt]; + for (dqidly = 0; dqidly < 32; dqidly++) { + for (dqsip = 0; dqsip < 2; dqsip++) { + if (pass[dqidly][dqsip][0] > pass[dqidly][dqsip][1]) + continue; + diff = pass[dqidly][dqsip][1] - pass[dqidly][dqsip][0]; + if ((diff+2) < g_margin) + continue; + passcnt[0] = passcnt[1] = 0; + for (dlli = pass[dqidly][dqsip][0]; dlli > 0 && tag[dqsip][dlli] != 0; dlli--, passcnt[0]++); + for (dlli = pass[dqidly][dqsip][1]; dlli < 76 && tag[dqsip][dlli] != 0; dlli++, passcnt[1]++); + if (passcnt[0] > passcnt[1]) + passcnt[0] = passcnt[1]; + passcnt[1] = 0; + if (passcnt[0] > g_side) + passcnt[1] = passcnt[0] - g_side; + if (diff > (g_margin+1) && (passcnt[1] > 0 || passcnt[0] > 8)) { + g_margin = diff; + g_dqidly = dqidly; + g_dqsip = dqsip; + g_side = passcnt[0]; + } else if (passcnt[1] > 1 && g_side < 8) { + if (diff > g_margin) + g_margin = diff; + g_dqidly = dqidly; + g_dqsip = dqsip; + g_side = passcnt[0]; } } } - gold_sadj[0] = (gold_sadj[1] + gold_sadj[0]) >> 1; - gold_sadj[1] = mindwm(ast, 0x1E6E0084); + reg_mcr18 = reg_mcr18 | (g_dqidly << 16) | (g_dqsip << 23); + ast_moutdwm(ast, 0x1E6E0018, reg_mcr18); - data = 0; - for (cnt = 8; cnt < 16; cnt++) { - data >>= 3; - data2 = gold_sadj[1] & 0x7; - gold_sadj[1] >>= 3; - if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) { - dlli = (dllmin[cnt] + dllmax[cnt]) >> 1; - if (gold_sadj[0] >= dlli) { - dlli = (gold_sadj[0] - dlli) >> 1; - if (dlli > 0) { - dlli = 1; - } - if (data2 != 3) { - data2 = (data2 + dlli) & 0x7; - } - } else { - dlli = (dlli - gold_sadj[0]) >> 1; - if (dlli > 0) { - dlli = 1; - } - if (data2 != 4) { - data2 = (data2 - dlli) & 0x7; - } - } - } - data |= data2 << 21; - } - moutdwm(ast, 0x1E6E0084, data); - -} /* finetuneDQI_L2 */ - -static void cbr_dll2(struct ast_private *ast, struct ast2300_dram_param *param) +} +static bool cbr_dll2(struct ast_private *ast, struct ast2300_dram_param *param) { - u32 dllmin[2], dllmax[2], dlli, data, data2, passcnt; + u32 dllmin[2], dllmax[2], dlli, data, passcnt, retry = 0; + bool status = false; - - finetuneDQI_L(ast, param); - finetuneDQI_L2(ast, param); + finetuneDQSI(ast); + if (finetuneDQI_L(ast, param) == false) + return status; CBR_START2: dllmin[0] = dllmin[1] = 0xff; dllmax[0] = dllmax[1] = 0x0; passcnt = 0; for (dlli = 0; dlli < 76; dlli++) { - moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24)); - /* Wait DQSI latch phase calibration */ - moutdwm(ast, 0x1E6E0074, 0x00000010); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - - moutdwm(ast, 0x1E6E0074, CBR_SIZE2); + ast_moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24)); + ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE2); data = cbr_scan(ast); if (data != 0) { if (data & 0x1) { @@ -957,44 +844,31 @@ static void cbr_dll2(struct ast_private *ast, struct ast2300_dram_param *param) break; } } + if (retry++ > 10) + goto CBR_DONE2; if (dllmax[0] == 0 || (dllmax[0]-dllmin[0]) < CBR_THRESHOLD) { goto CBR_START2; } if (dllmax[1] == 0 || (dllmax[1]-dllmin[1]) < CBR_THRESHOLD) { goto CBR_START2; } + status = true; +CBR_DONE2: dlli = (dllmin[1] + dllmax[1]) >> 1; dlli <<= 8; dlli += (dllmin[0] + dllmax[0]) >> 1; - moutdwm(ast, 0x1E6E0068, (mindwm(ast, 0x1E6E0068) & 0xFFFF) | (dlli << 16)); - - data = (mindwm(ast, 0x1E6E0080) >> 24) & 0x1F; - data2 = (mindwm(ast, 0x1E6E0018) & 0xff80ffff) | (data << 16); - moutdwm(ast, 0x1E6E0018, data2); - moutdwm(ast, 0x1E6E0024, 0x8001 | (data << 1) | (param->dll2_finetune_step << 8)); - - /* Wait DQSI latch phase calibration */ - moutdwm(ast, 0x1E6E0074, 0x00000010); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - moutdwm(ast, 0x1E6E0070, 0x00000003); - do { - data = mindwm(ast, 0x1E6E0070); - } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); + ast_moutdwm(ast, 0x1E6E0068, ast_mindwm(ast, 0x1E720058) | (dlli << 16)); + return status; } /* CBRDLL2 */ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *param) { u32 trap, trap_AC2, trap_MRS; - moutdwm(ast, 0x1E6E2000, 0x1688A8A8); + ast_moutdwm(ast, 0x1E6E2000, 0x1688A8A8); /* Ger trap info */ - trap = (mindwm(ast, 0x1E6E2070) >> 25) & 0x3; + trap = (ast_mindwm(ast, 0x1E6E2070) >> 25) & 0x3; trap_AC2 = 0x00020000 + (trap << 16); trap_AC2 |= 0x00300000 + ((trap & 0x2) << 19); trap_MRS = 0x00000010 + (trap << 4); @@ -1008,22 +882,35 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa switch (param->dram_freq) { case 336: - moutdwm(ast, 0x1E6E2020, 0x0190); + ast_moutdwm(ast, 0x1E6E2020, 0x0190); param->wodt = 0; param->reg_AC1 = 0x22202725; param->reg_AC2 = 0xAA007613 | trap_AC2; param->reg_DQSIC = 0x000000BA; param->reg_MRS = 0x04001400 | trap_MRS; param->reg_EMRS = 0x00000000; - param->reg_IOZ = 0x00000034; + param->reg_IOZ = 0x00000023; param->reg_DQIDLY = 0x00000074; param->reg_FREQ = 0x00004DC0; param->madj_max = 96; param->dll2_finetune_step = 3; + switch (param->dram_chipid) { + default: + case AST_DRAM_512Mx16: + case AST_DRAM_1Gx16: + param->reg_AC2 = 0xAA007613 | trap_AC2; + break; + case AST_DRAM_2Gx16: + param->reg_AC2 = 0xAA00761C | trap_AC2; + break; + case AST_DRAM_4Gx16: + param->reg_AC2 = 0xAA007636 | trap_AC2; + break; + } break; default: case 396: - moutdwm(ast, 0x1E6E2020, 0x03F1); + ast_moutdwm(ast, 0x1E6E2020, 0x03F1); param->wodt = 1; param->reg_AC1 = 0x33302825; param->reg_AC2 = 0xCC009617 | trap_AC2; @@ -1033,7 +920,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->reg_IOZ = 0x00000034; param->reg_DRV = 0x000000FA; param->reg_DQIDLY = 0x00000089; - param->reg_FREQ = 0x000050C0; + param->reg_FREQ = 0x00005040; param->madj_max = 96; param->dll2_finetune_step = 4; @@ -1053,14 +940,14 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa break; case 408: - moutdwm(ast, 0x1E6E2020, 0x01F0); + ast_moutdwm(ast, 0x1E6E2020, 0x01F0); param->wodt = 1; param->reg_AC1 = 0x33302825; param->reg_AC2 = 0xCC009617 | trap_AC2; param->reg_DQSIC = 0x000000E2; param->reg_MRS = 0x04001600 | trap_MRS; param->reg_EMRS = 0x00000000; - param->reg_IOZ = 0x00000034; + param->reg_IOZ = 0x00000023; param->reg_DRV = 0x000000FA; param->reg_DQIDLY = 0x00000089; param->reg_FREQ = 0x000050C0; @@ -1083,7 +970,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa break; case 456: - moutdwm(ast, 0x1E6E2020, 0x0230); + ast_moutdwm(ast, 0x1E6E2020, 0x0230); param->wodt = 0; param->reg_AC1 = 0x33302926; param->reg_AC2 = 0xCD44961A; @@ -1097,7 +984,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 4; break; case 504: - moutdwm(ast, 0x1E6E2020, 0x0270); + ast_moutdwm(ast, 0x1E6E2020, 0x0270); param->wodt = 1; param->reg_AC1 = 0x33302926; param->reg_AC2 = 0xDE44A61D; @@ -1111,7 +998,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 4; break; case 528: - moutdwm(ast, 0x1E6E2020, 0x0290); + ast_moutdwm(ast, 0x1E6E2020, 0x0290); param->wodt = 1; param->rodt = 1; param->reg_AC1 = 0x33302926; @@ -1127,7 +1014,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 576: - moutdwm(ast, 0x1E6E2020, 0x0140); + ast_moutdwm(ast, 0x1E6E2020, 0x0140); param->reg_MADJ = 0x00136868; param->reg_SADJ = 0x00004534; param->wodt = 1; @@ -1145,7 +1032,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 600: - moutdwm(ast, 0x1E6E2020, 0x02E1); + ast_moutdwm(ast, 0x1E6E2020, 0x02E1); param->reg_MADJ = 0x00136868; param->reg_SADJ = 0x00004534; param->wodt = 1; @@ -1163,7 +1050,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 624: - moutdwm(ast, 0x1E6E2020, 0x0160); + ast_moutdwm(ast, 0x1E6E2020, 0x0160); param->reg_MADJ = 0x00136868; param->reg_SADJ = 0x00004534; param->wodt = 1; @@ -1196,7 +1083,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa case AST_DRAM_4Gx16: param->dram_config = 0x133; break; - }; /* switch size */ + } /* switch size */ switch (param->vram_size) { default: @@ -1218,106 +1105,98 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa static void ddr3_init(struct ast_private *ast, struct ast2300_dram_param *param) { - u32 data, data2; + u32 data, data2, retry = 0; - moutdwm(ast, 0x1E6E0000, 0xFC600309); - moutdwm(ast, 0x1E6E0018, 0x00000100); - moutdwm(ast, 0x1E6E0024, 0x00000000); - moutdwm(ast, 0x1E6E0034, 0x00000000); +ddr3_init_start: + ast_moutdwm(ast, 0x1E6E0000, 0xFC600309); + ast_moutdwm(ast, 0x1E6E0018, 0x00000100); + ast_moutdwm(ast, 0x1E6E0024, 0x00000000); + ast_moutdwm(ast, 0x1E6E0034, 0x00000000); udelay(10); - moutdwm(ast, 0x1E6E0064, param->reg_MADJ); - moutdwm(ast, 0x1E6E0068, param->reg_SADJ); + ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ); + ast_moutdwm(ast, 0x1E6E0068, param->reg_SADJ); udelay(10); - moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000); + ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000); udelay(10); - moutdwm(ast, 0x1E6E0004, param->dram_config); - moutdwm(ast, 0x1E6E0008, 0x90040f); - moutdwm(ast, 0x1E6E0010, param->reg_AC1); - moutdwm(ast, 0x1E6E0014, param->reg_AC2); - moutdwm(ast, 0x1E6E0020, param->reg_DQSIC); - moutdwm(ast, 0x1E6E0080, 0x00000000); - moutdwm(ast, 0x1E6E0084, 0x00000000); - moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY); - moutdwm(ast, 0x1E6E0018, 0x4040A170); - moutdwm(ast, 0x1E6E0018, 0x20402370); - moutdwm(ast, 0x1E6E0038, 0x00000000); - moutdwm(ast, 0x1E6E0040, 0xFF444444); - moutdwm(ast, 0x1E6E0044, 0x22222222); - moutdwm(ast, 0x1E6E0048, 0x22222222); - moutdwm(ast, 0x1E6E004C, 0x00000002); - moutdwm(ast, 0x1E6E0050, 0x80000000); - moutdwm(ast, 0x1E6E0050, 0x00000000); - moutdwm(ast, 0x1E6E0054, 0); - moutdwm(ast, 0x1E6E0060, param->reg_DRV); - moutdwm(ast, 0x1E6E006C, param->reg_IOZ); - moutdwm(ast, 0x1E6E0070, 0x00000000); - moutdwm(ast, 0x1E6E0074, 0x00000000); - moutdwm(ast, 0x1E6E0078, 0x00000000); - moutdwm(ast, 0x1E6E007C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0004, param->dram_config); + ast_moutdwm(ast, 0x1E6E0008, 0x90040f); + ast_moutdwm(ast, 0x1E6E0010, param->reg_AC1); + ast_moutdwm(ast, 0x1E6E0014, param->reg_AC2); + ast_moutdwm(ast, 0x1E6E0020, param->reg_DQSIC); + ast_moutdwm(ast, 0x1E6E0080, 0x00000000); + ast_moutdwm(ast, 0x1E6E0084, 0x00000000); + ast_moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY); + ast_moutdwm(ast, 0x1E6E0018, 0x4000A170); + ast_moutdwm(ast, 0x1E6E0018, 0x00002370); + ast_moutdwm(ast, 0x1E6E0038, 0x00000000); + ast_moutdwm(ast, 0x1E6E0040, 0xFF444444); + ast_moutdwm(ast, 0x1E6E0044, 0x22222222); + ast_moutdwm(ast, 0x1E6E0048, 0x22222222); + ast_moutdwm(ast, 0x1E6E004C, 0x00000002); + ast_moutdwm(ast, 0x1E6E0050, 0x80000000); + ast_moutdwm(ast, 0x1E6E0050, 0x00000000); + ast_moutdwm(ast, 0x1E6E0054, 0); + ast_moutdwm(ast, 0x1E6E0060, param->reg_DRV); + ast_moutdwm(ast, 0x1E6E006C, param->reg_IOZ); + ast_moutdwm(ast, 0x1E6E0070, 0x00000000); + ast_moutdwm(ast, 0x1E6E0074, 0x00000000); + ast_moutdwm(ast, 0x1E6E0078, 0x00000000); + ast_moutdwm(ast, 0x1E6E007C, 0x00000000); /* Wait MCLK2X lock to MCLK */ do { - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); } while (!(data & 0x08000000)); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00005C04); - udelay(10); - moutdwm(ast, 0x1E6E000C, 0x00000000); - moutdwm(ast, 0x1E6E0034, 0x00000000); - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); data = (data >> 8) & 0xff; while ((data & 0x08) || ((data & 0x7) < 2) || (data < 4)) { - data2 = (mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4; + data2 = (ast_mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4; if ((data2 & 0xff) > param->madj_max) { break; } - moutdwm(ast, 0x1E6E0064, data2); + ast_moutdwm(ast, 0x1E6E0064, data2); if (data2 & 0x00100000) { data2 = ((data2 & 0xff) >> 3) + 3; } else { data2 = ((data2 & 0xff) >> 2) + 5; } - data = mindwm(ast, 0x1E6E0068) & 0xffff00ff; + data = ast_mindwm(ast, 0x1E6E0068) & 0xffff00ff; data2 += data & 0xff; data = data | (data2 << 8); - moutdwm(ast, 0x1E6E0068, data); + ast_moutdwm(ast, 0x1E6E0068, data); udelay(10); - moutdwm(ast, 0x1E6E0064, mindwm(ast, 0x1E6E0064) | 0xC0000); + ast_moutdwm(ast, 0x1E6E0064, ast_mindwm(ast, 0x1E6E0064) | 0xC0000); udelay(10); - data = mindwm(ast, 0x1E6E0018) & 0xfffff1ff; - moutdwm(ast, 0x1E6E0018, data); + data = ast_mindwm(ast, 0x1E6E0018) & 0xfffff1ff; + ast_moutdwm(ast, 0x1E6E0018, data); data = data | 0x200; - moutdwm(ast, 0x1E6E0018, data); + ast_moutdwm(ast, 0x1E6E0018, data); do { - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); } while (!(data & 0x08000000)); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00005C04); - udelay(10); - moutdwm(ast, 0x1E6E000C, 0x00000000); - moutdwm(ast, 0x1E6E0034, 0x00000000); - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); data = (data >> 8) & 0xff; } - data = mindwm(ast, 0x1E6E0018) | 0xC00; - moutdwm(ast, 0x1E6E0018, data); + ast_moutdwm(ast, 0x1E720058, ast_mindwm(ast, 0x1E6E0068) & 0xffff); + data = ast_mindwm(ast, 0x1E6E0018) | 0xC00; + ast_moutdwm(ast, 0x1E6E0018, data); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00000040); + ast_moutdwm(ast, 0x1E6E0034, 0x00000001); + ast_moutdwm(ast, 0x1E6E000C, 0x00000040); udelay(50); /* Mode Register Setting */ - moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100); - moutdwm(ast, 0x1E6E0030, param->reg_EMRS); - moutdwm(ast, 0x1E6E0028, 0x00000005); - moutdwm(ast, 0x1E6E0028, 0x00000007); - moutdwm(ast, 0x1E6E0028, 0x00000003); - moutdwm(ast, 0x1E6E0028, 0x00000001); - moutdwm(ast, 0x1E6E002C, param->reg_MRS); - moutdwm(ast, 0x1E6E000C, 0x00005C08); - moutdwm(ast, 0x1E6E0028, 0x00000001); + ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100); + ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS); + ast_moutdwm(ast, 0x1E6E0028, 0x00000005); + ast_moutdwm(ast, 0x1E6E0028, 0x00000007); + ast_moutdwm(ast, 0x1E6E0028, 0x00000003); + ast_moutdwm(ast, 0x1E6E0028, 0x00000001); + ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS); + ast_moutdwm(ast, 0x1E6E000C, 0x00005C08); + ast_moutdwm(ast, 0x1E6E0028, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x7FFF5C01); + ast_moutdwm(ast, 0x1E6E000C, 0x00005C01); data = 0; if (param->wodt) { data = 0x300; @@ -1325,30 +1204,23 @@ static void ddr3_init(struct ast_private *ast, struct ast2300_dram_param *param) if (param->rodt) { data = data | 0x3000 | ((param->reg_AC2 & 0x60000) >> 3); } - moutdwm(ast, 0x1E6E0034, data | 0x3); + ast_moutdwm(ast, 0x1E6E0034, data | 0x3); - /* Wait DQI delay lock */ - do { - data = mindwm(ast, 0x1E6E0080); - } while (!(data & 0x40000000)); - /* Wait DQSI delay lock */ - do { - data = mindwm(ast, 0x1E6E0020); - } while (!(data & 0x00000800)); /* Calibrate the DQSI delay */ - cbr_dll2(ast, param); + if ((cbr_dll2(ast, param) == false) && (retry++ < 10)) + goto ddr3_init_start; - moutdwm(ast, 0x1E6E0120, param->reg_FREQ); + ast_moutdwm(ast, 0x1E6E0120, param->reg_FREQ); /* ECC Memory Initialization */ #ifdef ECC - moutdwm(ast, 0x1E6E007C, 0x00000000); - moutdwm(ast, 0x1E6E0070, 0x221); + ast_moutdwm(ast, 0x1E6E007C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0070, 0x221); do { - data = mindwm(ast, 0x1E6E0070); + data = ast_mindwm(ast, 0x1E6E0070); } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - moutdwm(ast, 0x1E6E0050, 0x80000000); - moutdwm(ast, 0x1E6E0050, 0x00000000); + ast_moutdwm(ast, 0x1E6E0070, 0x00000000); + ast_moutdwm(ast, 0x1E6E0050, 0x80000000); + ast_moutdwm(ast, 0x1E6E0050, 0x00000000); #endif @@ -1358,10 +1230,10 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa { u32 trap, trap_AC2, trap_MRS; - moutdwm(ast, 0x1E6E2000, 0x1688A8A8); + ast_moutdwm(ast, 0x1E6E2000, 0x1688A8A8); /* Ger trap info */ - trap = (mindwm(ast, 0x1E6E2070) >> 25) & 0x3; + trap = (ast_mindwm(ast, 0x1E6E2070) >> 25) & 0x3; trap_AC2 = (trap << 20) | (trap << 16); trap_AC2 += 0x00110000; trap_MRS = 0x00000040 | (trap << 4); @@ -1375,7 +1247,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa switch (param->dram_freq) { case 264: - moutdwm(ast, 0x1E6E2020, 0x0130); + ast_moutdwm(ast, 0x1E6E2020, 0x0130); param->wodt = 0; param->reg_AC1 = 0x11101513; param->reg_AC2 = 0x78117011; @@ -1390,7 +1262,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 336: - moutdwm(ast, 0x1E6E2020, 0x0190); + ast_moutdwm(ast, 0x1E6E2020, 0x0190); param->wodt = 1; param->reg_AC1 = 0x22202613; param->reg_AC2 = 0xAA009016 | trap_AC2; @@ -1403,10 +1275,25 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->reg_FREQ = 0x00004DC0; param->madj_max = 96; param->dll2_finetune_step = 3; + switch (param->dram_chipid) { + default: + case AST_DRAM_512Mx16: + param->reg_AC2 = 0xAA009012 | trap_AC2; + break; + case AST_DRAM_1Gx16: + param->reg_AC2 = 0xAA009016 | trap_AC2; + break; + case AST_DRAM_2Gx16: + param->reg_AC2 = 0xAA009023 | trap_AC2; + break; + case AST_DRAM_4Gx16: + param->reg_AC2 = 0xAA00903B | trap_AC2; + break; + } break; default: case 396: - moutdwm(ast, 0x1E6E2020, 0x03F1); + ast_moutdwm(ast, 0x1E6E2020, 0x03F1); param->wodt = 1; param->rodt = 0; param->reg_AC1 = 0x33302714; @@ -1417,7 +1304,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->reg_DRV = 0x000000FA; param->reg_IOZ = 0x00000034; param->reg_DQIDLY = 0x00000089; - param->reg_FREQ = 0x000050C0; + param->reg_FREQ = 0x00005040; param->madj_max = 96; param->dll2_finetune_step = 4; @@ -1440,7 +1327,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa break; case 408: - moutdwm(ast, 0x1E6E2020, 0x01F0); + ast_moutdwm(ast, 0x1E6E2020, 0x01F0); param->wodt = 1; param->rodt = 0; param->reg_AC1 = 0x33302714; @@ -1473,7 +1360,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa break; case 456: - moutdwm(ast, 0x1E6E2020, 0x0230); + ast_moutdwm(ast, 0x1E6E2020, 0x0230); param->wodt = 0; param->reg_AC1 = 0x33302815; param->reg_AC2 = 0xCD44B01E; @@ -1488,7 +1375,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 504: - moutdwm(ast, 0x1E6E2020, 0x0261); + ast_moutdwm(ast, 0x1E6E2020, 0x0261); param->wodt = 1; param->rodt = 1; param->reg_AC1 = 0x33302815; @@ -1504,7 +1391,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 528: - moutdwm(ast, 0x1E6E2020, 0x0120); + ast_moutdwm(ast, 0x1E6E2020, 0x0120); param->wodt = 1; param->rodt = 1; param->reg_AC1 = 0x33302815; @@ -1520,7 +1407,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 552: - moutdwm(ast, 0x1E6E2020, 0x02A1); + ast_moutdwm(ast, 0x1E6E2020, 0x02A1); param->wodt = 1; param->rodt = 1; param->reg_AC1 = 0x43402915; @@ -1536,7 +1423,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa param->dll2_finetune_step = 3; break; case 576: - moutdwm(ast, 0x1E6E2020, 0x0140); + ast_moutdwm(ast, 0x1E6E2020, 0x0140); param->wodt = 1; param->rodt = 1; param->reg_AC1 = 0x43402915; @@ -1567,7 +1454,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa case AST_DRAM_4Gx16: param->dram_config = 0x123; break; - }; /* switch size */ + } /* switch size */ switch (param->vram_size) { default: @@ -1588,110 +1475,102 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa static void ddr2_init(struct ast_private *ast, struct ast2300_dram_param *param) { - u32 data, data2; + u32 data, data2, retry = 0; - moutdwm(ast, 0x1E6E0000, 0xFC600309); - moutdwm(ast, 0x1E6E0018, 0x00000100); - moutdwm(ast, 0x1E6E0024, 0x00000000); - moutdwm(ast, 0x1E6E0064, param->reg_MADJ); - moutdwm(ast, 0x1E6E0068, param->reg_SADJ); +ddr2_init_start: + ast_moutdwm(ast, 0x1E6E0000, 0xFC600309); + ast_moutdwm(ast, 0x1E6E0018, 0x00000100); + ast_moutdwm(ast, 0x1E6E0024, 0x00000000); + ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ); + ast_moutdwm(ast, 0x1E6E0068, param->reg_SADJ); udelay(10); - moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000); + ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000); udelay(10); - moutdwm(ast, 0x1E6E0004, param->dram_config); - moutdwm(ast, 0x1E6E0008, 0x90040f); - moutdwm(ast, 0x1E6E0010, param->reg_AC1); - moutdwm(ast, 0x1E6E0014, param->reg_AC2); - moutdwm(ast, 0x1E6E0020, param->reg_DQSIC); - moutdwm(ast, 0x1E6E0080, 0x00000000); - moutdwm(ast, 0x1E6E0084, 0x00000000); - moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY); - moutdwm(ast, 0x1E6E0018, 0x4040A130); - moutdwm(ast, 0x1E6E0018, 0x20402330); - moutdwm(ast, 0x1E6E0038, 0x00000000); - moutdwm(ast, 0x1E6E0040, 0xFF808000); - moutdwm(ast, 0x1E6E0044, 0x88848466); - moutdwm(ast, 0x1E6E0048, 0x44440008); - moutdwm(ast, 0x1E6E004C, 0x00000000); - moutdwm(ast, 0x1E6E0050, 0x80000000); - moutdwm(ast, 0x1E6E0050, 0x00000000); - moutdwm(ast, 0x1E6E0054, 0); - moutdwm(ast, 0x1E6E0060, param->reg_DRV); - moutdwm(ast, 0x1E6E006C, param->reg_IOZ); - moutdwm(ast, 0x1E6E0070, 0x00000000); - moutdwm(ast, 0x1E6E0074, 0x00000000); - moutdwm(ast, 0x1E6E0078, 0x00000000); - moutdwm(ast, 0x1E6E007C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0004, param->dram_config); + ast_moutdwm(ast, 0x1E6E0008, 0x90040f); + ast_moutdwm(ast, 0x1E6E0010, param->reg_AC1); + ast_moutdwm(ast, 0x1E6E0014, param->reg_AC2); + ast_moutdwm(ast, 0x1E6E0020, param->reg_DQSIC); + ast_moutdwm(ast, 0x1E6E0080, 0x00000000); + ast_moutdwm(ast, 0x1E6E0084, 0x00000000); + ast_moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY); + ast_moutdwm(ast, 0x1E6E0018, 0x4000A130); + ast_moutdwm(ast, 0x1E6E0018, 0x00002330); + ast_moutdwm(ast, 0x1E6E0038, 0x00000000); + ast_moutdwm(ast, 0x1E6E0040, 0xFF808000); + ast_moutdwm(ast, 0x1E6E0044, 0x88848466); + ast_moutdwm(ast, 0x1E6E0048, 0x44440008); + ast_moutdwm(ast, 0x1E6E004C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0050, 0x80000000); + ast_moutdwm(ast, 0x1E6E0050, 0x00000000); + ast_moutdwm(ast, 0x1E6E0054, 0); + ast_moutdwm(ast, 0x1E6E0060, param->reg_DRV); + ast_moutdwm(ast, 0x1E6E006C, param->reg_IOZ); + ast_moutdwm(ast, 0x1E6E0070, 0x00000000); + ast_moutdwm(ast, 0x1E6E0074, 0x00000000); + ast_moutdwm(ast, 0x1E6E0078, 0x00000000); + ast_moutdwm(ast, 0x1E6E007C, 0x00000000); /* Wait MCLK2X lock to MCLK */ do { - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); } while (!(data & 0x08000000)); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00005C04); - udelay(10); - moutdwm(ast, 0x1E6E000C, 0x00000000); - moutdwm(ast, 0x1E6E0034, 0x00000000); - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); data = (data >> 8) & 0xff; while ((data & 0x08) || ((data & 0x7) < 2) || (data < 4)) { - data2 = (mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4; + data2 = (ast_mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4; if ((data2 & 0xff) > param->madj_max) { break; } - moutdwm(ast, 0x1E6E0064, data2); + ast_moutdwm(ast, 0x1E6E0064, data2); if (data2 & 0x00100000) { data2 = ((data2 & 0xff) >> 3) + 3; } else { data2 = ((data2 & 0xff) >> 2) + 5; } - data = mindwm(ast, 0x1E6E0068) & 0xffff00ff; + data = ast_mindwm(ast, 0x1E6E0068) & 0xffff00ff; data2 += data & 0xff; data = data | (data2 << 8); - moutdwm(ast, 0x1E6E0068, data); + ast_moutdwm(ast, 0x1E6E0068, data); udelay(10); - moutdwm(ast, 0x1E6E0064, mindwm(ast, 0x1E6E0064) | 0xC0000); + ast_moutdwm(ast, 0x1E6E0064, ast_mindwm(ast, 0x1E6E0064) | 0xC0000); udelay(10); - data = mindwm(ast, 0x1E6E0018) & 0xfffff1ff; - moutdwm(ast, 0x1E6E0018, data); + data = ast_mindwm(ast, 0x1E6E0018) & 0xfffff1ff; + ast_moutdwm(ast, 0x1E6E0018, data); data = data | 0x200; - moutdwm(ast, 0x1E6E0018, data); + ast_moutdwm(ast, 0x1E6E0018, data); do { - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); } while (!(data & 0x08000000)); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00005C04); - udelay(10); - moutdwm(ast, 0x1E6E000C, 0x00000000); - moutdwm(ast, 0x1E6E0034, 0x00000000); - data = mindwm(ast, 0x1E6E001C); + data = ast_mindwm(ast, 0x1E6E001C); data = (data >> 8) & 0xff; } - data = mindwm(ast, 0x1E6E0018) | 0xC00; - moutdwm(ast, 0x1E6E0018, data); + ast_moutdwm(ast, 0x1E720058, ast_mindwm(ast, 0x1E6E0008) & 0xffff); + data = ast_mindwm(ast, 0x1E6E0018) | 0xC00; + ast_moutdwm(ast, 0x1E6E0018, data); - moutdwm(ast, 0x1E6E0034, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0034, 0x00000001); + ast_moutdwm(ast, 0x1E6E000C, 0x00000000); udelay(50); /* Mode Register Setting */ - moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100); - moutdwm(ast, 0x1E6E0030, param->reg_EMRS); - moutdwm(ast, 0x1E6E0028, 0x00000005); - moutdwm(ast, 0x1E6E0028, 0x00000007); - moutdwm(ast, 0x1E6E0028, 0x00000003); - moutdwm(ast, 0x1E6E0028, 0x00000001); + ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100); + ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS); + ast_moutdwm(ast, 0x1E6E0028, 0x00000005); + ast_moutdwm(ast, 0x1E6E0028, 0x00000007); + ast_moutdwm(ast, 0x1E6E0028, 0x00000003); + ast_moutdwm(ast, 0x1E6E0028, 0x00000001); - moutdwm(ast, 0x1E6E000C, 0x00005C08); - moutdwm(ast, 0x1E6E002C, param->reg_MRS); - moutdwm(ast, 0x1E6E0028, 0x00000001); - moutdwm(ast, 0x1E6E0030, param->reg_EMRS | 0x380); - moutdwm(ast, 0x1E6E0028, 0x00000003); - moutdwm(ast, 0x1E6E0030, param->reg_EMRS); - moutdwm(ast, 0x1E6E0028, 0x00000003); + ast_moutdwm(ast, 0x1E6E000C, 0x00005C08); + ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS); + ast_moutdwm(ast, 0x1E6E0028, 0x00000001); + ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS | 0x380); + ast_moutdwm(ast, 0x1E6E0028, 0x00000003); + ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS); + ast_moutdwm(ast, 0x1E6E0028, 0x00000003); - moutdwm(ast, 0x1E6E000C, 0x7FFF5C01); + ast_moutdwm(ast, 0x1E6E000C, 0x7FFF5C01); data = 0; if (param->wodt) { data = 0x500; @@ -1699,30 +1578,23 @@ static void ddr2_init(struct ast_private *ast, struct ast2300_dram_param *param) if (param->rodt) { data = data | 0x3000 | ((param->reg_AC2 & 0x60000) >> 3); } - moutdwm(ast, 0x1E6E0034, data | 0x3); - moutdwm(ast, 0x1E6E0120, param->reg_FREQ); + ast_moutdwm(ast, 0x1E6E0034, data | 0x3); + ast_moutdwm(ast, 0x1E6E0120, param->reg_FREQ); - /* Wait DQI delay lock */ - do { - data = mindwm(ast, 0x1E6E0080); - } while (!(data & 0x40000000)); - /* Wait DQSI delay lock */ - do { - data = mindwm(ast, 0x1E6E0020); - } while (!(data & 0x00000800)); /* Calibrate the DQSI delay */ - cbr_dll2(ast, param); + if ((cbr_dll2(ast, param) == false) && (retry++ < 10)) + goto ddr2_init_start; /* ECC Memory Initialization */ #ifdef ECC - moutdwm(ast, 0x1E6E007C, 0x00000000); - moutdwm(ast, 0x1E6E0070, 0x221); + ast_moutdwm(ast, 0x1E6E007C, 0x00000000); + ast_moutdwm(ast, 0x1E6E0070, 0x221); do { - data = mindwm(ast, 0x1E6E0070); + data = ast_mindwm(ast, 0x1E6E0070); } while (!(data & 0x00001000)); - moutdwm(ast, 0x1E6E0070, 0x00000000); - moutdwm(ast, 0x1E6E0050, 0x80000000); - moutdwm(ast, 0x1E6E0050, 0x00000000); + ast_moutdwm(ast, 0x1E6E0070, 0x00000000); + ast_moutdwm(ast, 0x1E6E0050, 0x80000000); + ast_moutdwm(ast, 0x1E6E0050, 0x00000000); #endif } @@ -1768,8 +1640,8 @@ static void ast_init_dram_2300(struct drm_device *dev) ddr2_init(ast, ¶m); } - temp = mindwm(ast, 0x1e6e2040); - moutdwm(ast, 0x1e6e2040, temp | 0x40); + temp = ast_mindwm(ast, 0x1e6e2040); + ast_moutdwm(ast, 0x1e6e2040, temp | 0x40); } /* wait ready */ diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h index 95fa6aba26bc..4c761dcea972 100644 --- a/drivers/gpu/drm/ast/ast_tables.h +++ b/drivers/gpu/drm/ast/ast_tables.h @@ -42,7 +42,7 @@ #define HBorder 0x00000020 #define VBorder 0x00000010 #define WideScreenMode 0x00000100 - +#define NewModeInfo 0x00000200 /* DCLK Index */ #define VCLK25_175 0x00 @@ -67,6 +67,11 @@ #define VCLK106_5 0x12 #define VCLK146_25 0x13 #define VCLK148_5 0x14 +#define VCLK71 0x15 +#define VCLK88_75 0x16 +#define VCLK119 0x17 +#define VCLK85_5 0x18 +#define VCLK97_75 0x19 static struct ast_vbios_dclk_info dclk_table[] = { {0x2C, 0xE7, 0x03}, /* 00: VCLK25_175 */ @@ -90,6 +95,10 @@ static struct ast_vbios_dclk_info dclk_table[] = { {0x28, 0x49, 0x80}, /* 12: VCLK106.5 */ {0x37, 0x49, 0x80}, /* 13: VCLK146.25 */ {0x1f, 0x45, 0x80}, /* 14: VCLK148.5 */ + {0x47, 0x6c, 0x80}, /* 15: VCLK71 */ + {0x25, 0x65, 0x80}, /* 16: VCLK88.75 */ + {0x77, 0x58, 0x80}, /* 17: VCLK119 */ + {0x32, 0x67, 0x80}, /* 18: VCLK85_5 */ }; static struct ast_vbios_stdtable vbios_stdtable[] = { @@ -225,41 +234,63 @@ static struct ast_vbios_enhtable res_1600x1200[] = { (SyncPP | Charx8Dot), 0xFF, 1, 0x33 }, }; -static struct ast_vbios_enhtable res_1920x1200[] = { - {2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154, /* 60Hz */ - (SyncNP | Charx8Dot), 60, 1, 0x34 }, - {2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154, /* 60Hz */ - (SyncNP | Charx8Dot), 0xFF, 1, 0x34 }, +/* 16:9 */ +static struct ast_vbios_enhtable res_1360x768[] = { + {1792, 1360, 64,112, 795, 768, 3, 6, VCLK85_5, /* 60Hz */ + (SyncPP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x39 }, + {1792, 1360, 64,112, 795, 768, 3, 6, VCLK85_5, /* end */ + (SyncPP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x39 }, }; +static struct ast_vbios_enhtable res_1600x900[] = { + {1760, 1600, 48, 32, 926, 900, 3, 5, VCLK97_75, /* 60Hz CVT RB */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x3A }, + {1760, 1600, 48, 32, 926, 900, 3, 5, VCLK97_75, /* end */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x3A } +}; + +static struct ast_vbios_enhtable res_1920x1080[] = { + {2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5, /* 60Hz */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x38 }, + {2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5, /* 60Hz */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x38 }, +}; + + /* 16:10 */ static struct ast_vbios_enhtable res_1280x800[] = { + {1440, 1280, 48, 32, 823, 800, 3, 6, VCLK71, /* 60Hz RB */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 35 }, {1680, 1280, 72,128, 831, 800, 3, 6, VCLK83_5, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x35 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x35 }, {1680, 1280, 72,128, 831, 800, 3, 6, VCLK83_5, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x35 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x35 }, }; static struct ast_vbios_enhtable res_1440x900[] = { + {1600, 1440, 48, 32, 926, 900, 3, 6, VCLK88_75, /* 60Hz RB */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 }, {1904, 1440, 80,152, 934, 900, 3, 6, VCLK106_5, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x36 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 }, {1904, 1440, 80,152, 934, 900, 3, 6, VCLK106_5, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x36 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x36 }, }; static struct ast_vbios_enhtable res_1680x1050[] = { + {1840, 1680, 48, 32, 1080, 1050, 3, 6, VCLK119, /* 60Hz RB */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 }, {2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x37 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 }, {2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25, /* 60Hz */ - (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x37 }, + (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x37 }, }; -/* HDTV */ -static struct ast_vbios_enhtable res_1920x1080[] = { - {2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5, /* 60Hz */ - (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x38 }, - {2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5, /* 60Hz */ - (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x38 }, +static struct ast_vbios_enhtable res_1920x1200[] = { + {2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154, /* 60Hz */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x34 }, + {2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154, /* 60Hz */ + (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x34 }, }; + #endif diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c index f488be55d650..b9a695d92792 100644 --- a/drivers/gpu/drm/bochs/bochs_mm.c +++ b/drivers/gpu/drm/bochs/bochs_mm.c @@ -434,17 +434,13 @@ static void bochs_bo_unref(struct bochs_bo **bo) tbo = &((*bo)->bo); ttm_bo_unref(&tbo); - if (tbo == NULL) - *bo = NULL; - + *bo = NULL; } void bochs_gem_free_object(struct drm_gem_object *obj) { struct bochs_bo *bochs_bo = gem_to_bochs_bo(obj); - if (!bochs_bo) - return; bochs_bo_unref(&bochs_bo); } diff --git a/drivers/gpu/drm/bridge/ptn3460.c b/drivers/gpu/drm/bridge/ptn3460.c index b171901a3553..98fd17ae4916 100644 --- a/drivers/gpu/drm/bridge/ptn3460.c +++ b/drivers/gpu/drm/bridge/ptn3460.c @@ -225,12 +225,6 @@ int ptn3460_get_modes(struct drm_connector *connector) return num_modes; } -static int ptn3460_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - return MODE_OK; -} - struct drm_encoder *ptn3460_best_encoder(struct drm_connector *connector) { struct ptn3460_bridge *ptn_bridge; @@ -242,7 +236,6 @@ struct drm_encoder *ptn3460_best_encoder(struct drm_connector *connector) struct drm_connector_helper_funcs ptn3460_connector_helper_funcs = { .get_modes = ptn3460_get_modes, - .mode_valid = ptn3460_mode_valid, .best_encoder = ptn3460_best_encoder, }; diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c index 4b0170cf53fd..99c1983f99d2 100644 --- a/drivers/gpu/drm/cirrus/cirrus_main.c +++ b/drivers/gpu/drm/cirrus/cirrus_main.c @@ -264,17 +264,13 @@ static void cirrus_bo_unref(struct cirrus_bo **bo) tbo = &((*bo)->bo); ttm_bo_unref(&tbo); - if (tbo == NULL) - *bo = NULL; - + *bo = NULL; } void cirrus_gem_free_object(struct drm_gem_object *obj) { struct cirrus_bo *cirrus_bo = gem_to_cirrus_bo(obj); - if (!cirrus_bo) - return; cirrus_bo_unref(&cirrus_bo); } diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index f59433b7610c..49332c5fe35b 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -505,13 +505,6 @@ static int cirrus_vga_get_modes(struct drm_connector *connector) return count; } -static int cirrus_vga_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - /* Any mode we've added is valid */ - return MODE_OK; -} - static struct drm_encoder *cirrus_connector_best_encoder(struct drm_connector *connector) { @@ -546,7 +539,6 @@ static void cirrus_connector_destroy(struct drm_connector *connector) struct drm_connector_helper_funcs cirrus_vga_connector_helper_funcs = { .get_modes = cirrus_vga_get_modes, - .mode_valid = cirrus_vga_mode_valid, .best_encoder = cirrus_connector_best_encoder, }; diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index edec31fe3fed..68175b54504b 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -363,7 +363,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset, list->master = dev->primary->master; *maplist = list; return 0; - } +} int drm_addmap(struct drm_device * dev, resource_size_t offset, unsigned int size, enum drm_map_type type, @@ -656,13 +656,13 @@ int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request) DRM_DEBUG("zone invalid\n"); return -EINVAL; } - spin_lock(&dev->count_lock); + spin_lock(&dev->buf_lock); if (dev->buf_use) { - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); return -EBUSY; } atomic_inc(&dev->buf_alloc); - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); mutex_lock(&dev->struct_mutex); entry = &dma->bufs[order]; @@ -805,13 +805,13 @@ int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request) page_order = order - PAGE_SHIFT > 0 ? order - PAGE_SHIFT : 0; total = PAGE_SIZE << page_order; - spin_lock(&dev->count_lock); + spin_lock(&dev->buf_lock); if (dev->buf_use) { - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); return -EBUSY; } atomic_inc(&dev->buf_alloc); - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); mutex_lock(&dev->struct_mutex); entry = &dma->bufs[order]; @@ -1015,13 +1015,13 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request if (order < DRM_MIN_ORDER || order > DRM_MAX_ORDER) return -EINVAL; - spin_lock(&dev->count_lock); + spin_lock(&dev->buf_lock); if (dev->buf_use) { - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); return -EBUSY; } atomic_inc(&dev->buf_alloc); - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); mutex_lock(&dev->struct_mutex); entry = &dma->bufs[order]; @@ -1175,7 +1175,7 @@ int drm_addbufs(struct drm_device *dev, void *data, * \param arg pointer to a drm_buf_info structure. * \return zero on success or a negative number on failure. * - * Increments drm_device::buf_use while holding the drm_device::count_lock + * Increments drm_device::buf_use while holding the drm_device::buf_lock * lock, preventing of allocating more buffers after this call. Information * about each requested buffer is then copied into user space. */ @@ -1196,13 +1196,13 @@ int drm_infobufs(struct drm_device *dev, void *data, if (!dma) return -EINVAL; - spin_lock(&dev->count_lock); + spin_lock(&dev->buf_lock); if (atomic_read(&dev->buf_alloc)) { - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); return -EBUSY; } ++dev->buf_use; /* Can't allocate more after this call */ - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); for (i = 0, count = 0; i < DRM_MAX_ORDER + 1; i++) { if (dma->bufs[i].buf_count) @@ -1381,13 +1381,13 @@ int drm_mapbufs(struct drm_device *dev, void *data, if (!dma) return -EINVAL; - spin_lock(&dev->count_lock); + spin_lock(&dev->buf_lock); if (atomic_read(&dev->buf_alloc)) { - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); return -EBUSY; } dev->buf_use++; /* Can't allocate more after this call */ - spin_unlock(&dev->count_lock); + spin_unlock(&dev->buf_lock); if (request->count >= dma->buf_count) { if ((dev->agp && (dma->flags & _DRM_DMA_USE_AGP)) diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 534cb89b160d..a6b690626a6b 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -131,14 +131,14 @@ drm_clflush_sg(struct sg_table *st) EXPORT_SYMBOL(drm_clflush_sg); void -drm_clflush_virt_range(char *addr, unsigned long length) +drm_clflush_virt_range(void *addr, unsigned long length) { #if defined(CONFIG_X86) if (cpu_has_clflush) { - char *end = addr + length; + void *end = addr + length; mb(); for (; addr < end; addr += boot_cpu_data.x86_clflush_size) - clflush(addr); + clflushopt(addr); clflushopt(end - 1); mb(); return; diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index d8b7099abece..fe94cc10cd35 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "drm_crtc_internal.h" @@ -50,12 +51,42 @@ */ void drm_modeset_lock_all(struct drm_device *dev) { - struct drm_crtc *crtc; + struct drm_mode_config *config = &dev->mode_config; + struct drm_modeset_acquire_ctx *ctx; + int ret; - mutex_lock(&dev->mode_config.mutex); + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (WARN_ON(!ctx)) + return; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - mutex_lock_nest_lock(&crtc->mutex, &dev->mode_config.mutex); + mutex_lock(&config->mutex); + + drm_modeset_acquire_init(ctx, 0); + +retry: + ret = drm_modeset_lock(&config->connection_mutex, ctx); + if (ret) + goto fail; + ret = drm_modeset_lock_all_crtcs(dev, ctx); + if (ret) + goto fail; + + WARN_ON(config->acquire_ctx); + + /* now we hold the locks, so now that it is safe, stash the + * ctx for drm_modeset_unlock_all(): + */ + config->acquire_ctx = ctx; + + drm_warn_on_modeset_not_all_locked(dev); + + return; + +fail: + if (ret == -EDEADLK) { + drm_modeset_backoff(ctx); + goto retry; + } } EXPORT_SYMBOL(drm_modeset_lock_all); @@ -67,10 +98,17 @@ EXPORT_SYMBOL(drm_modeset_lock_all); */ void drm_modeset_unlock_all(struct drm_device *dev) { - struct drm_crtc *crtc; + struct drm_mode_config *config = &dev->mode_config; + struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - mutex_unlock(&crtc->mutex); + if (WARN_ON(!ctx)) + return; + + config->acquire_ctx = NULL; + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); + + kfree(ctx); mutex_unlock(&dev->mode_config.mutex); } @@ -91,8 +129,9 @@ void drm_warn_on_modeset_not_all_locked(struct drm_device *dev) return; list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - WARN_ON(!mutex_is_locked(&crtc->mutex)); + WARN_ON(!drm_modeset_is_locked(&crtc->mutex)); + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); } EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked); @@ -227,6 +266,7 @@ static const struct drm_prop_enum_list drm_encoder_enum_list[] = { DRM_MODE_ENCODER_TVDAC, "TV" }, { DRM_MODE_ENCODER_VIRTUAL, "Virtual" }, { DRM_MODE_ENCODER_DSI, "DSI" }, + { DRM_MODE_ENCODER_DPMST, "DP MST" }, }; static const struct drm_prop_enum_list drm_subpixel_enum_list[] = @@ -255,46 +295,6 @@ void drm_connector_ida_destroy(void) ida_destroy(&drm_connector_enum_list[i].ida); } -/** - * drm_get_encoder_name - return a string for encoder - * @encoder: encoder to compute name of - * - * Note that the buffer used by this function is globally shared and owned by - * the function itself. - * - * FIXME: This isn't really multithreading safe. - */ -const char *drm_get_encoder_name(const struct drm_encoder *encoder) -{ - static char buf[32]; - - snprintf(buf, 32, "%s-%d", - drm_encoder_enum_list[encoder->encoder_type].name, - encoder->base.id); - return buf; -} -EXPORT_SYMBOL(drm_get_encoder_name); - -/** - * drm_get_connector_name - return a string for connector - * @connector: connector to compute name of - * - * Note that the buffer used by this function is globally shared and owned by - * the function itself. - * - * FIXME: This isn't really multithreading safe. - */ -const char *drm_get_connector_name(const struct drm_connector *connector) -{ - static char buf[32]; - - snprintf(buf, 32, "%s-%d", - drm_connector_enum_list[connector->connector_type].name, - connector->connector_type_id); - return buf; -} -EXPORT_SYMBOL(drm_get_connector_name); - /** * drm_get_connector_status_name - return a string for connector status * @status: connector status to compute name of @@ -409,6 +409,21 @@ void drm_mode_object_put(struct drm_device *dev, mutex_unlock(&dev->mode_config.idr_mutex); } +static struct drm_mode_object *_object_find(struct drm_device *dev, + uint32_t id, uint32_t type) +{ + struct drm_mode_object *obj = NULL; + + mutex_lock(&dev->mode_config.idr_mutex); + obj = idr_find(&dev->mode_config.crtc_idr, id); + if (!obj || (type != DRM_MODE_OBJECT_ANY && obj->type != type) || + (obj->id != id)) + obj = NULL; + mutex_unlock(&dev->mode_config.idr_mutex); + + return obj; +} + /** * drm_mode_object_find - look up a drm object with static lifetime * @dev: drm device @@ -416,7 +431,9 @@ void drm_mode_object_put(struct drm_device *dev, * @type: type of the mode object * * Note that framebuffers cannot be looked up with this functions - since those - * are reference counted, they need special treatment. + * are reference counted, they need special treatment. Even with + * DRM_MODE_OBJECT_ANY (although that will simply return NULL + * rather than WARN_ON()). */ struct drm_mode_object *drm_mode_object_find(struct drm_device *dev, uint32_t id, uint32_t type) @@ -426,13 +443,10 @@ struct drm_mode_object *drm_mode_object_find(struct drm_device *dev, /* Framebuffers are reference counted and need their own lookup * function.*/ WARN_ON(type == DRM_MODE_OBJECT_FB); - - mutex_lock(&dev->mode_config.idr_mutex); - obj = idr_find(&dev->mode_config.crtc_idr, id); - if (!obj || (obj->type != type) || (obj->id != id)) + obj = _object_find(dev, id, type); + /* don't leak out unref'd fb's */ + if (obj && (obj->type == DRM_MODE_OBJECT_FB)) obj = NULL; - mutex_unlock(&dev->mode_config.idr_mutex); - return obj; } EXPORT_SYMBOL(drm_mode_object_find); @@ -538,7 +552,7 @@ EXPORT_SYMBOL(drm_framebuffer_lookup); */ void drm_framebuffer_unreference(struct drm_framebuffer *fb) { - DRM_DEBUG("FB ID: %d\n", fb->base.id); + DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount)); kref_put(&fb->refcount, drm_framebuffer_free); } EXPORT_SYMBOL(drm_framebuffer_unreference); @@ -551,7 +565,7 @@ EXPORT_SYMBOL(drm_framebuffer_unreference); */ void drm_framebuffer_reference(struct drm_framebuffer *fb) { - DRM_DEBUG("FB ID: %d\n", fb->base.id); + DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount)); kref_get(&fb->refcount); } EXPORT_SYMBOL(drm_framebuffer_reference); @@ -563,7 +577,7 @@ static void drm_framebuffer_free_bug(struct kref *kref) static void __drm_framebuffer_unreference(struct drm_framebuffer *fb) { - DRM_DEBUG("FB ID: %d\n", fb->base.id); + DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount)); kref_put(&fb->refcount, drm_framebuffer_free_bug); } @@ -691,6 +705,8 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb) } EXPORT_SYMBOL(drm_framebuffer_remove); +DEFINE_WW_CLASS(crtc_ww_class); + /** * drm_crtc_init_with_planes - Initialise a new CRTC object with * specified primary and cursor planes. @@ -710,6 +726,7 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, void *cursor, const struct drm_crtc_funcs *funcs) { + struct drm_mode_config *config = &dev->mode_config; int ret; crtc->dev = dev; @@ -717,8 +734,9 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, crtc->invert_dimensions = false; drm_modeset_lock_all(dev); - mutex_init(&crtc->mutex); - mutex_lock_nest_lock(&crtc->mutex, &dev->mode_config.mutex); + drm_modeset_lock_init(&crtc->mutex); + /* dropped by _unlock_all(): */ + drm_modeset_lock(&crtc->mutex, config->acquire_ctx); ret = drm_mode_object_get(dev, &crtc->base, DRM_MODE_OBJECT_CRTC); if (ret) @@ -726,8 +744,8 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, crtc->base.properties = &crtc->properties; - list_add_tail(&crtc->head, &dev->mode_config.crtc_list); - dev->mode_config.num_crtc++; + list_add_tail(&crtc->head, &config->crtc_list); + config->num_crtc++; crtc->primary = primary; if (primary) @@ -755,6 +773,8 @@ void drm_crtc_cleanup(struct drm_crtc *crtc) kfree(crtc->gamma_store); crtc->gamma_store = NULL; + drm_modeset_lock_fini(&crtc->mutex); + drm_mode_object_put(dev, &crtc->base); list_del(&crtc->head); dev->mode_config.num_crtc--; @@ -824,7 +844,7 @@ int drm_connector_init(struct drm_device *dev, ret = drm_mode_object_get(dev, &connector->base, DRM_MODE_OBJECT_CONNECTOR); if (ret) - goto out; + goto out_unlock; connector->base.properties = &connector->properties; connector->dev = dev; @@ -834,9 +854,17 @@ int drm_connector_init(struct drm_device *dev, ida_simple_get(connector_ida, 1, 0, GFP_KERNEL); if (connector->connector_type_id < 0) { ret = connector->connector_type_id; - drm_mode_object_put(dev, &connector->base); - goto out; + goto out_put; } + connector->name = + kasprintf(GFP_KERNEL, "%s-%d", + drm_connector_enum_list[connector_type].name, + connector->connector_type_id); + if (!connector->name) { + ret = -ENOMEM; + goto out_put; + } + INIT_LIST_HEAD(&connector->probed_modes); INIT_LIST_HEAD(&connector->modes); connector->edid_blob_ptr = NULL; @@ -853,7 +881,11 @@ int drm_connector_init(struct drm_device *dev, drm_object_attach_property(&connector->base, dev->mode_config.dpms_property, 0); - out: +out_put: + if (ret) + drm_mode_object_put(dev, &connector->base); + +out_unlock: drm_modeset_unlock_all(dev); return ret; @@ -881,6 +913,8 @@ void drm_connector_cleanup(struct drm_connector *connector) connector->connector_type_id); drm_mode_object_put(dev, &connector->base); + kfree(connector->name); + connector->name = NULL; list_del(&connector->head); dev->mode_config.num_connector--; } @@ -982,16 +1016,27 @@ int drm_encoder_init(struct drm_device *dev, ret = drm_mode_object_get(dev, &encoder->base, DRM_MODE_OBJECT_ENCODER); if (ret) - goto out; + goto out_unlock; encoder->dev = dev; encoder->encoder_type = encoder_type; encoder->funcs = funcs; + encoder->name = kasprintf(GFP_KERNEL, "%s-%d", + drm_encoder_enum_list[encoder_type].name, + encoder->base.id); + if (!encoder->name) { + ret = -ENOMEM; + goto out_put; + } list_add_tail(&encoder->head, &dev->mode_config.encoder_list); dev->mode_config.num_encoder++; - out: +out_put: + if (ret) + drm_mode_object_put(dev, &encoder->base); + +out_unlock: drm_modeset_unlock_all(dev); return ret; @@ -1009,6 +1054,8 @@ void drm_encoder_cleanup(struct drm_encoder *encoder) struct drm_device *dev = encoder->dev; drm_modeset_lock_all(dev); drm_mode_object_put(dev, &encoder->base); + kfree(encoder->name); + encoder->name = NULL; list_del(&encoder->head); dev->mode_config.num_encoder--; drm_modeset_unlock_all(dev); @@ -1145,16 +1192,19 @@ EXPORT_SYMBOL(drm_plane_cleanup); */ void drm_plane_force_disable(struct drm_plane *plane) { + struct drm_framebuffer *old_fb = plane->fb; int ret; - if (!plane->fb) + if (!old_fb) return; ret = plane->funcs->disable_plane(plane); - if (ret) + if (ret) { DRM_ERROR("failed to disable plane with busy fb\n"); + return; + } /* disconnect the plane from the fb and crtc: */ - __drm_framebuffer_unreference(plane->fb); + __drm_framebuffer_unreference(old_fb); plane->fb = NULL; plane->crtc = NULL; } @@ -1378,6 +1428,12 @@ static int drm_mode_group_init(struct drm_device *dev, struct drm_mode_group *gr return 0; } +void drm_mode_group_destroy(struct drm_mode_group *group) +{ + kfree(group->id_list); + group->id_list = NULL; +} + /* * NOTE: Driver's shouldn't ever call drm_mode_group_init_legacy_group - it is * the drm core's responsibility to set up mode control groups. @@ -1614,7 +1670,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data, &dev->mode_config.encoder_list, head) { DRM_DEBUG_KMS("[ENCODER:%d:%s]\n", encoder->base.id, - drm_get_encoder_name(encoder)); + encoder->name); if (put_user(encoder->base.id, encoder_id + copied)) { ret = -EFAULT; @@ -1646,7 +1702,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data, head) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, - drm_get_connector_name(connector)); + connector->name); if (put_user(connector->base.id, connector_id + copied)) { ret = -EFAULT; @@ -1695,7 +1751,6 @@ int drm_mode_getcrtc(struct drm_device *dev, { struct drm_mode_crtc *crtc_resp = data; struct drm_crtc *crtc; - struct drm_mode_object *obj; int ret = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) @@ -1703,13 +1758,11 @@ int drm_mode_getcrtc(struct drm_device *dev, drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, crtc_resp->crtc_id, - DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, crtc_resp->crtc_id); + if (!crtc) { ret = -ENOENT; goto out; } - crtc = obj_to_crtc(obj); crtc_resp->x = crtc->x; crtc_resp->y = crtc->y; @@ -1763,7 +1816,6 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_get_connector *out_resp = data; - struct drm_mode_object *obj; struct drm_connector *connector; struct drm_display_mode *mode; int mode_count = 0; @@ -1787,13 +1839,11 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, mutex_lock(&dev->mode_config.mutex); - obj = drm_mode_object_find(dev, out_resp->connector_id, - DRM_MODE_OBJECT_CONNECTOR); - if (!obj) { + connector = drm_connector_find(dev, out_resp->connector_id); + if (!connector) { ret = -ENOENT; goto out; } - connector = obj_to_connector(obj); props_count = connector->properties.count; @@ -1821,10 +1871,12 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, out_resp->mm_height = connector->display_info.height_mm; out_resp->subpixel = connector->display_info.subpixel_order; out_resp->connection = connector->status; + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); if (connector->encoder) out_resp->encoder_id = connector->encoder->base.id; else out_resp->encoder_id = 0; + drm_modeset_unlock(&dev->mode_config.connection_mutex); /* * This ioctl is called twice, once to determine how much space is @@ -1908,7 +1960,6 @@ int drm_mode_getencoder(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_get_encoder *enc_resp = data; - struct drm_mode_object *obj; struct drm_encoder *encoder; int ret = 0; @@ -1916,13 +1967,11 @@ int drm_mode_getencoder(struct drm_device *dev, void *data, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, enc_resp->encoder_id, - DRM_MODE_OBJECT_ENCODER); - if (!obj) { + encoder = drm_encoder_find(dev, enc_resp->encoder_id); + if (!encoder) { ret = -ENOENT; goto out; } - encoder = obj_to_encoder(obj); if (encoder->crtc) enc_resp->crtc_id = encoder->crtc->base.id; @@ -2020,7 +2069,6 @@ int drm_mode_getplane(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_get_plane *plane_resp = data; - struct drm_mode_object *obj; struct drm_plane *plane; uint32_t __user *format_ptr; int ret = 0; @@ -2029,13 +2077,11 @@ int drm_mode_getplane(struct drm_device *dev, void *data, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, plane_resp->plane_id, - DRM_MODE_OBJECT_PLANE); - if (!obj) { + plane = drm_plane_find(dev, plane_resp->plane_id); + if (!plane) { ret = -ENOENT; goto out; } - plane = obj_to_plane(obj); if (plane->crtc) plane_resp->crtc_id = plane->crtc->base.id; @@ -2088,7 +2134,6 @@ int drm_mode_setplane(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_set_plane *plane_req = data; - struct drm_mode_object *obj; struct drm_plane *plane; struct drm_crtc *crtc; struct drm_framebuffer *fb = NULL, *old_fb = NULL; @@ -2103,35 +2148,42 @@ int drm_mode_setplane(struct drm_device *dev, void *data, * First, find the plane, crtc, and fb objects. If not available, * we don't bother to call the driver. */ - obj = drm_mode_object_find(dev, plane_req->plane_id, - DRM_MODE_OBJECT_PLANE); - if (!obj) { + plane = drm_plane_find(dev, plane_req->plane_id); + if (!plane) { DRM_DEBUG_KMS("Unknown plane ID %d\n", plane_req->plane_id); return -ENOENT; } - plane = obj_to_plane(obj); /* No fb means shut it down */ if (!plane_req->fb_id) { drm_modeset_lock_all(dev); old_fb = plane->fb; - plane->funcs->disable_plane(plane); - plane->crtc = NULL; - plane->fb = NULL; + ret = plane->funcs->disable_plane(plane); + if (!ret) { + plane->crtc = NULL; + plane->fb = NULL; + } else { + old_fb = NULL; + } drm_modeset_unlock_all(dev); goto out; } - obj = drm_mode_object_find(dev, plane_req->crtc_id, - DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, plane_req->crtc_id); + if (!crtc) { DRM_DEBUG_KMS("Unknown crtc ID %d\n", plane_req->crtc_id); ret = -ENOENT; goto out; } - crtc = obj_to_crtc(obj); + + /* Check whether this plane is usable on this CRTC */ + if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) { + DRM_DEBUG_KMS("Invalid crtc for plane\n"); + ret = -EINVAL; + goto out; + } fb = drm_framebuffer_lookup(dev, plane_req->fb_id); if (!fb) { @@ -2187,16 +2239,18 @@ int drm_mode_setplane(struct drm_device *dev, void *data, } drm_modeset_lock_all(dev); + old_fb = plane->fb; ret = plane->funcs->update_plane(plane, crtc, fb, plane_req->crtc_x, plane_req->crtc_y, plane_req->crtc_w, plane_req->crtc_h, plane_req->src_x, plane_req->src_y, plane_req->src_w, plane_req->src_h); if (!ret) { - old_fb = plane->fb; plane->crtc = crtc; plane->fb = fb; fb = NULL; + } else { + old_fb = NULL; } drm_modeset_unlock_all(dev); @@ -2239,9 +2293,7 @@ int drm_mode_set_config_internal(struct drm_mode_set *set) ret = crtc->funcs->set_config(set); if (ret == 0) { crtc->primary->crtc = crtc; - - /* crtc->fb must be updated by ->set_config, enforces this. */ - WARN_ON(fb != crtc->primary->fb); + crtc->primary->fb = fb; } list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head) { @@ -2318,7 +2370,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, { struct drm_mode_config *config = &dev->mode_config; struct drm_mode_crtc *crtc_req = data; - struct drm_mode_object *obj; struct drm_crtc *crtc; struct drm_connector **connector_set = NULL, *connector; struct drm_framebuffer *fb = NULL; @@ -2336,14 +2387,12 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, return -ERANGE; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, crtc_req->crtc_id, - DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, crtc_req->crtc_id); + if (!crtc) { DRM_DEBUG_KMS("Unknown CRTC ID %d\n", crtc_req->crtc_id); ret = -ENOENT; goto out; } - crtc = obj_to_crtc(obj); DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id); if (crtc_req->mode_valid) { @@ -2426,18 +2475,16 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } - obj = drm_mode_object_find(dev, out_id, - DRM_MODE_OBJECT_CONNECTOR); - if (!obj) { + connector = drm_connector_find(dev, out_id); + if (!connector) { DRM_DEBUG_KMS("Connector id %d unknown\n", out_id); ret = -ENOENT; goto out; } - connector = obj_to_connector(obj); DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, - drm_get_connector_name(connector)); + connector->name); connector_set[i] = connector; } @@ -2466,7 +2513,6 @@ static int drm_mode_cursor_common(struct drm_device *dev, struct drm_mode_cursor2 *req, struct drm_file *file_priv) { - struct drm_mode_object *obj; struct drm_crtc *crtc; int ret = 0; @@ -2476,14 +2522,13 @@ static int drm_mode_cursor_common(struct drm_device *dev, if (!req->flags || (~DRM_MODE_CURSOR_FLAGS & req->flags)) return -EINVAL; - obj = drm_mode_object_find(dev, req->crtc_id, DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, req->crtc_id); + if (!crtc) { DRM_DEBUG_KMS("Unknown CRTC ID %d\n", req->crtc_id); return -ENOENT; } - crtc = obj_to_crtc(obj); - mutex_lock(&crtc->mutex); + drm_modeset_lock(&crtc->mutex, NULL); if (req->flags & DRM_MODE_CURSOR_BO) { if (!crtc->funcs->cursor_set && !crtc->funcs->cursor_set2) { ret = -ENXIO; @@ -2507,7 +2552,7 @@ static int drm_mode_cursor_common(struct drm_device *dev, } } out: - mutex_unlock(&crtc->mutex); + drm_modeset_unlock(&crtc->mutex); return ret; @@ -3097,6 +3142,8 @@ struct drm_property *drm_property_create(struct drm_device *dev, int flags, if (!property) return NULL; + property->dev = dev; + if (num_values) { property->values = kzalloc(sizeof(uint64_t)*num_values, GFP_KERNEL); if (!property->values) @@ -3117,6 +3164,9 @@ struct drm_property *drm_property_create(struct drm_device *dev, int flags, } list_add_tail(&property->head, &dev->mode_config.property_list); + + WARN_ON(!drm_property_type_valid(property)); + return property; fail: kfree(property->values); @@ -3217,6 +3267,22 @@ struct drm_property *drm_property_create_bitmask(struct drm_device *dev, } EXPORT_SYMBOL(drm_property_create_bitmask); +static struct drm_property *property_create_range(struct drm_device *dev, + int flags, const char *name, + uint64_t min, uint64_t max) +{ + struct drm_property *property; + + property = drm_property_create(dev, flags, name, 2); + if (!property) + return NULL; + + property->values[0] = min; + property->values[1] = max; + + return property; +} + /** * drm_property_create - create a new ranged property type * @dev: drm device @@ -3238,21 +3304,37 @@ EXPORT_SYMBOL(drm_property_create_bitmask); struct drm_property *drm_property_create_range(struct drm_device *dev, int flags, const char *name, uint64_t min, uint64_t max) +{ + return property_create_range(dev, DRM_MODE_PROP_RANGE | flags, + name, min, max); +} +EXPORT_SYMBOL(drm_property_create_range); + +struct drm_property *drm_property_create_signed_range(struct drm_device *dev, + int flags, const char *name, + int64_t min, int64_t max) +{ + return property_create_range(dev, DRM_MODE_PROP_SIGNED_RANGE | flags, + name, I642U64(min), I642U64(max)); +} +EXPORT_SYMBOL(drm_property_create_signed_range); + +struct drm_property *drm_property_create_object(struct drm_device *dev, + int flags, const char *name, uint32_t type) { struct drm_property *property; - flags |= DRM_MODE_PROP_RANGE; + flags |= DRM_MODE_PROP_OBJECT; - property = drm_property_create(dev, flags, name, 2); + property = drm_property_create(dev, flags, name, 1); if (!property) return NULL; - property->values[0] = min; - property->values[1] = max; + property->values[0] = type; return property; } -EXPORT_SYMBOL(drm_property_create_range); +EXPORT_SYMBOL(drm_property_create_object); /** * drm_property_add_enum - add a possible value to an enumeration property @@ -3274,14 +3356,16 @@ int drm_property_add_enum(struct drm_property *property, int index, { struct drm_property_enum *prop_enum; - if (!(property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK))) + if (!(drm_property_type_is(property, DRM_MODE_PROP_ENUM) || + drm_property_type_is(property, DRM_MODE_PROP_BITMASK))) return -EINVAL; /* * Bitmask enum properties have the additional constraint of values * from 0 to 63 */ - if ((property->flags & DRM_MODE_PROP_BITMASK) && (value > 63)) + if (drm_property_type_is(property, DRM_MODE_PROP_BITMASK) && + (value > 63)) return -EINVAL; if (!list_empty(&property->enum_blob_list)) { @@ -3438,7 +3522,6 @@ EXPORT_SYMBOL(drm_object_property_get_value); int drm_mode_getproperty_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct drm_mode_object *obj; struct drm_mode_get_property *out_resp = data; struct drm_property *property; int enum_count = 0; @@ -3457,17 +3540,17 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, out_resp->prop_id, DRM_MODE_OBJECT_PROPERTY); - if (!obj) { + property = drm_property_find(dev, out_resp->prop_id); + if (!property) { ret = -ENOENT; goto done; } - property = obj_to_property(obj); - if (property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK)) { + if (drm_property_type_is(property, DRM_MODE_PROP_ENUM) || + drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) { list_for_each_entry(prop_enum, &property->enum_blob_list, head) enum_count++; - } else if (property->flags & DRM_MODE_PROP_BLOB) { + } else if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) { list_for_each_entry(prop_blob, &property->enum_blob_list, head) blob_count++; } @@ -3489,7 +3572,8 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev, } out_resp->count_values = value_count; - if (property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK)) { + if (drm_property_type_is(property, DRM_MODE_PROP_ENUM) || + drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) { if ((out_resp->count_enum_blobs >= enum_count) && enum_count) { copied = 0; enum_ptr = (struct drm_mode_property_enum __user *)(unsigned long)out_resp->enum_blob_ptr; @@ -3511,7 +3595,7 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev, out_resp->count_enum_blobs = enum_count; } - if (property->flags & DRM_MODE_PROP_BLOB) { + if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) { if ((out_resp->count_enum_blobs >= blob_count) && blob_count) { copied = 0; blob_id_ptr = (uint32_t __user *)(unsigned long)out_resp->enum_blob_ptr; @@ -3590,7 +3674,6 @@ static void drm_property_destroy_blob(struct drm_device *dev, int drm_mode_getblob_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct drm_mode_object *obj; struct drm_mode_get_blob *out_resp = data; struct drm_property_blob *blob; int ret = 0; @@ -3600,12 +3683,11 @@ int drm_mode_getblob_ioctl(struct drm_device *dev, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, out_resp->blob_id, DRM_MODE_OBJECT_BLOB); - if (!obj) { + blob = drm_property_blob_find(dev, out_resp->blob_id); + if (!blob) { ret = -ENOENT; goto done; } - blob = obj_to_blob(obj); if (out_resp->length == blob->length) { blob_ptr = (void __user *)(unsigned long)out_resp->data; @@ -3667,19 +3749,40 @@ static bool drm_property_change_is_valid(struct drm_property *property, { if (property->flags & DRM_MODE_PROP_IMMUTABLE) return false; - if (property->flags & DRM_MODE_PROP_RANGE) { + + if (drm_property_type_is(property, DRM_MODE_PROP_RANGE)) { if (value < property->values[0] || value > property->values[1]) return false; return true; - } else if (property->flags & DRM_MODE_PROP_BITMASK) { + } else if (drm_property_type_is(property, DRM_MODE_PROP_SIGNED_RANGE)) { + int64_t svalue = U642I64(value); + if (svalue < U642I64(property->values[0]) || + svalue > U642I64(property->values[1])) + return false; + return true; + } else if (drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) { int i; uint64_t valid_mask = 0; for (i = 0; i < property->num_values; i++) valid_mask |= (1ULL << property->values[i]); return !(value & ~valid_mask); - } else if (property->flags & DRM_MODE_PROP_BLOB) { + } else if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) { /* Only the driver knows */ return true; + } else if (drm_property_type_is(property, DRM_MODE_PROP_OBJECT)) { + struct drm_mode_object *obj; + /* a zero value for an object property translates to null: */ + if (value == 0) + return true; + /* + * NOTE: use _object_find() directly to bypass restriction on + * looking up refcnt'd objects (ie. fb's). For a refcnt'd + * object this could race against object finalization, so it + * simply tells us that the object *was* valid. Which is good + * enough. + */ + obj = _object_find(property->dev, value, property->values[0]); + return obj != NULL; } else { int i; for (i = 0; i < property->num_values; i++) @@ -3987,7 +4090,6 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_crtc_lut *crtc_lut = data; - struct drm_mode_object *obj; struct drm_crtc *crtc; void *r_base, *g_base, *b_base; int size; @@ -3997,12 +4099,11 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, crtc_lut->crtc_id, DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, crtc_lut->crtc_id); + if (!crtc) { ret = -ENOENT; goto out; } - crtc = obj_to_crtc(obj); if (crtc->funcs->gamma_set == NULL) { ret = -ENOSYS; @@ -4061,7 +4162,6 @@ int drm_mode_gamma_get_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_crtc_lut *crtc_lut = data; - struct drm_mode_object *obj; struct drm_crtc *crtc; void *r_base, *g_base, *b_base; int size; @@ -4071,12 +4171,11 @@ int drm_mode_gamma_get_ioctl(struct drm_device *dev, return -EINVAL; drm_modeset_lock_all(dev); - obj = drm_mode_object_find(dev, crtc_lut->crtc_id, DRM_MODE_OBJECT_CRTC); - if (!obj) { + crtc = drm_crtc_find(dev, crtc_lut->crtc_id); + if (!crtc) { ret = -ENOENT; goto out; } - crtc = obj_to_crtc(obj); /* memcpy into gamma store */ if (crtc_lut->gamma_size != crtc->gamma_size) { @@ -4129,7 +4228,6 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_crtc_page_flip *page_flip = data; - struct drm_mode_object *obj; struct drm_crtc *crtc; struct drm_framebuffer *fb = NULL, *old_fb = NULL; struct drm_pending_vblank_event *e = NULL; @@ -4143,12 +4241,11 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, if ((page_flip->flags & DRM_MODE_PAGE_FLIP_ASYNC) && !dev->mode_config.async_page_flip) return -EINVAL; - obj = drm_mode_object_find(dev, page_flip->crtc_id, DRM_MODE_OBJECT_CRTC); - if (!obj) + crtc = drm_crtc_find(dev, page_flip->crtc_id); + if (!crtc) return -ENOENT; - crtc = obj_to_crtc(obj); - mutex_lock(&crtc->mutex); + drm_modeset_lock(&crtc->mutex, NULL); if (crtc->primary->fb == NULL) { /* The framebuffer is currently unbound, presumably * due to a hotplug event, that userspace has not @@ -4232,7 +4329,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, drm_framebuffer_unreference(fb); if (old_fb) drm_framebuffer_unreference(old_fb); - mutex_unlock(&crtc->mutex); + drm_modeset_unlock(&crtc->mutex); return ret; } @@ -4597,6 +4694,7 @@ EXPORT_SYMBOL(drm_format_vert_chroma_subsampling); void drm_mode_config_init(struct drm_device *dev) { mutex_init(&dev->mode_config.mutex); + drm_modeset_lock_init(&dev->mode_config.connection_mutex); mutex_init(&dev->mode_config.idr_mutex); mutex_init(&dev->mode_config.fb_lock); INIT_LIST_HEAD(&dev->mode_config.fb_list); @@ -4696,5 +4794,6 @@ void drm_mode_config_cleanup(struct drm_device *dev) } idr_destroy(&dev->mode_config.crtc_idr); + drm_modeset_lock_fini(&dev->mode_config.connection_mutex); } EXPORT_SYMBOL(drm_mode_config_cleanup); diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index 872ba11c4533..78b37f3febd3 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -93,8 +93,10 @@ bool drm_helper_encoder_in_use(struct drm_encoder *encoder) * We can expect this mutex to be locked if we are not panicking. * Locking is currently fubar in the panic handler. */ - if (!oops_in_progress) + if (!oops_in_progress) { WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + } list_for_each_entry(connector, &dev->mode_config.connector_list, head) if (connector->encoder == encoder) @@ -153,20 +155,14 @@ drm_encoder_disable(struct drm_encoder *encoder) static void __drm_helper_disable_unused_functions(struct drm_device *dev) { struct drm_encoder *encoder; - struct drm_connector *connector; struct drm_crtc *crtc; drm_warn_on_modeset_not_all_locked(dev); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - if (!connector->encoder) - continue; - } - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { if (!drm_helper_encoder_in_use(encoder)) { drm_encoder_disable(encoder); - /* disconnector encoder from any connector */ + /* disconnect encoder from any connector */ encoder->crtc = NULL; } } @@ -349,7 +345,7 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, continue; DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n", - encoder->base.id, drm_get_encoder_name(encoder), + encoder->base.id, encoder->name, mode->base.id, mode->name); encoder_funcs = encoder->helper_private; encoder_funcs->mode_set(encoder, mode, adjusted_mode); @@ -400,8 +396,7 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, } EXPORT_SYMBOL(drm_crtc_helper_set_mode); - -static int +static void drm_crtc_helper_disable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -430,7 +425,6 @@ drm_crtc_helper_disable(struct drm_crtc *crtc) } __drm_helper_disable_unused_functions(dev); - return 0; } /** @@ -481,7 +475,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) (int)set->num_connectors, set->x, set->y); } else { DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id); - return drm_crtc_helper_disable(set->crtc); + drm_crtc_helper_disable(set->crtc); + return 0; } dev = set->crtc->dev; @@ -620,11 +615,11 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) } if (new_crtc) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n", - connector->base.id, drm_get_connector_name(connector), + connector->base.id, connector->name, new_crtc->base.id); } else { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); } } @@ -650,7 +645,7 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) DRM_DEBUG_KMS("Setting connector DPMS state to on\n"); for (i = 0; i < set->num_connectors; i++) { DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id, - drm_get_connector_name(set->connectors[i])); + set->connectors[i]->name); set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON); } } diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 4b6e6f3ba0a1..08e33b8b13a4 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -206,13 +206,17 @@ i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter) * i2c_dp_aux_add_bus() - register an i2c adapter using the aux ch helper * @adapter: i2c adapter to register * - * This registers an i2c adapater that uses dp aux channel as it's underlaying + * This registers an i2c adapter that uses dp aux channel as it's underlaying * transport. The driver needs to fill out the &i2c_algo_dp_aux_data structure * and store it in the algo_data member of the @adapter argument. This will be * used by the i2c over dp aux algorithm to drive the hardware. * * RETURNS: * 0 on success, -ERRNO on failure. + * + * IMPORTANT: + * This interface is deprecated, please switch to the new dp aux helpers and + * drm_dp_aux_register(). */ int i2c_dp_aux_add_bus(struct i2c_adapter *adapter) @@ -378,7 +382,10 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, * transactions. */ for (retry = 0; retry < 7; retry++) { + + mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); + mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; @@ -592,7 +599,9 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) * before giving up the AUX transaction. */ for (retry = 0; retry < 7; retry++) { + mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, msg); + mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; @@ -725,13 +734,15 @@ static const struct i2c_algorithm drm_dp_i2c_algo = { }; /** - * drm_dp_aux_register_i2c_bus() - register an I2C adapter for I2C-over-AUX + * drm_dp_aux_register() - initialise and register aux channel * @aux: DisplayPort AUX channel * * Returns 0 on success or a negative error code on failure. */ -int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux) +int drm_dp_aux_register(struct drm_dp_aux *aux) { + mutex_init(&aux->hw_mutex); + aux->ddc.algo = &drm_dp_i2c_algo; aux->ddc.algo_data = aux; aux->ddc.retries = 3; @@ -746,14 +757,14 @@ int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux) return i2c_add_adapter(&aux->ddc); } -EXPORT_SYMBOL(drm_dp_aux_register_i2c_bus); +EXPORT_SYMBOL(drm_dp_aux_register); /** - * drm_dp_aux_unregister_i2c_bus() - unregister an I2C-over-AUX adapter + * drm_dp_aux_unregister() - unregister an AUX adapter * @aux: DisplayPort AUX channel */ -void drm_dp_aux_unregister_i2c_bus(struct drm_dp_aux *aux) +void drm_dp_aux_unregister(struct drm_dp_aux *aux) { i2c_del_adapter(&aux->ddc); } -EXPORT_SYMBOL(drm_dp_aux_unregister_i2c_bus); +EXPORT_SYMBOL(drm_dp_aux_unregister); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index d4e3f9d9370f..dfa9769b26b5 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -70,6 +70,8 @@ #define EDID_QUIRK_FORCE_REDUCED_BLANKING (1 << 7) /* Force 8bpc */ #define EDID_QUIRK_FORCE_8BPC (1 << 8) +/* Force 12bpc */ +#define EDID_QUIRK_FORCE_12BPC (1 << 9) struct detailed_mode_closure { struct drm_connector *connector; @@ -125,6 +127,9 @@ static struct edid_quirk { { "SAM", 596, EDID_QUIRK_PREFER_LARGE_60 }, { "SAM", 638, EDID_QUIRK_PREFER_LARGE_60 }, + /* Sony PVM-2541A does up to 12 bpc, but only reports max 8 bpc */ + { "SNY", 0x2541, EDID_QUIRK_FORCE_12BPC }, + /* ViewSonic VA2026w */ { "VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING }, @@ -984,9 +989,13 @@ static const u8 edid_header[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 }; - /* - * Sanity check the header of the base EDID block. Return 8 if the header - * is perfect, down to 0 if it's totally wrong. +/** + * drm_edid_header_is_valid - sanity check the header of the base EDID block + * @raw_edid: pointer to raw base EDID block + * + * Sanity check the header of the base EDID block. + * + * Return: 8 if the header is perfect, down to 0 if it's totally wrong. */ int drm_edid_header_is_valid(const u8 *raw_edid) { @@ -1005,9 +1014,16 @@ module_param_named(edid_fixup, edid_fixup, int, 0400); MODULE_PARM_DESC(edid_fixup, "Minimum number of valid EDID header bytes (0-8, default 6)"); -/* - * Sanity check the EDID block (base or extension). Return 0 if the block - * doesn't check out, or 1 if it's valid. +/** + * drm_edid_block_valid - Sanity check the EDID block (base or extension) + * @raw_edid: pointer to raw EDID block + * @block: type of block to validate (0 for base, extension otherwise) + * @print_bad_edid: if true, dump bad EDID blocks to the console + * + * Validate a base or extension EDID block and optionally dump bad blocks to + * the console. + * + * Return: True if the block is valid, false otherwise. */ bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid) { @@ -1077,6 +1093,8 @@ EXPORT_SYMBOL(drm_edid_block_valid); * @edid: EDID data * * Sanity-check an entire EDID record (including extensions) + * + * Return: True if the EDID data is valid, false otherwise. */ bool drm_edid_is_valid(struct edid *edid) { @@ -1096,18 +1114,15 @@ EXPORT_SYMBOL(drm_edid_is_valid); #define DDC_SEGMENT_ADDR 0x30 /** - * Get EDID information via I2C. - * - * @adapter : i2c device adaptor + * drm_do_probe_ddc_edid() - get EDID information via I2C + * @adapter: I2C device adaptor * @buf: EDID data buffer to be filled * @block: 128 byte EDID block to start fetching from * @len: EDID data buffer length to fetch * - * Returns: + * Try to fetch EDID information by calling I2C driver functions. * - * 0 on success or -1 on failure. - * - * Try to fetch EDID information by calling i2c driver function. + * Return: 0 on success or -1 on failure. */ static int drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf, @@ -1118,7 +1133,8 @@ drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf, unsigned char xfers = segment ? 3 : 2; int ret, retries = 5; - /* The core i2c driver will automatically retry the transfer if the + /* + * The core I2C driver will automatically retry the transfer if the * adapter reports EAGAIN. However, we find that bit-banging transfers * are susceptible to errors under a heavily loaded machine and * generate spurious NAKs and timeouts. Retrying the transfer @@ -1144,10 +1160,10 @@ drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf, } }; - /* - * Avoid sending the segment addr to not upset non-compliant ddc - * monitors. - */ + /* + * Avoid sending the segment addr to not upset non-compliant + * DDC monitors. + */ ret = i2c_transfer(adapter, &msgs[3 - xfers], xfers); if (ret == -ENXIO) { @@ -1216,7 +1232,7 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) if (i == 4 && print_bad_edid) { dev_warn(connector->dev->dev, "%s: Ignoring invalid EDID block %d.\n", - drm_get_connector_name(connector), j); + connector->name, j); connector->bad_edid_counter++; } @@ -1236,7 +1252,7 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) carp: if (print_bad_edid) { dev_warn(connector->dev->dev, "%s: EDID block %d invalid.\n", - drm_get_connector_name(connector), j); + connector->name, j); } connector->bad_edid_counter++; @@ -1246,12 +1262,10 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) } /** - * Probe DDC presence. - * @adapter: i2c adapter to probe + * drm_probe_ddc() - probe DDC presence + * @adapter: I2C adapter to probe * - * Returns: - * - * 1 on success + * Return: True on success, false on failure. */ bool drm_probe_ddc(struct i2c_adapter *adapter) @@ -1265,12 +1279,12 @@ EXPORT_SYMBOL(drm_probe_ddc); /** * drm_get_edid - get EDID data, if available * @connector: connector we're probing - * @adapter: i2c adapter to use for DDC + * @adapter: I2C adapter to use for DDC * - * Poke the given i2c channel to grab EDID data if possible. If found, + * Poke the given I2C channel to grab EDID data if possible. If found, * attach it to the connector. * - * Return edid data or NULL if we couldn't find any. + * Return: Pointer to valid EDID or NULL if we couldn't find any. */ struct edid *drm_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) @@ -1288,7 +1302,7 @@ EXPORT_SYMBOL(drm_get_edid); * drm_edid_duplicate - duplicate an EDID and the extensions * @edid: EDID to duplicate * - * Return duplicate edid or NULL on allocation failure. + * Return: Pointer to duplicated EDID or NULL on allocation failure. */ struct edid *drm_edid_duplicate(const struct edid *edid) { @@ -1411,7 +1425,8 @@ mode_is_rb(const struct drm_display_mode *mode) * @rb: Mode reduced-blanking-ness * * Walk the DMT mode list looking for a match for the given parameters. - * Return a newly allocated copy of the mode, or NULL if not found. + * + * Return: A newly allocated copy of the mode, or NULL if not found. */ struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev, int hsize, int vsize, int fresh, @@ -1595,14 +1610,13 @@ bad_std_timing(u8 a, u8 b) * @connector: connector of for the EDID block * @edid: EDID block to scan * @t: standard timing params - * @revision: standard timing level * * Take the standard timing params (in this case width, aspect, and refresh) * and convert them into a real mode using CVT/GTF/DMT. */ static struct drm_display_mode * drm_mode_std(struct drm_connector *connector, struct edid *edid, - struct std_timing *t, int revision) + struct std_timing *t) { struct drm_device *dev = connector->dev; struct drm_display_mode *m, *mode = NULL; @@ -1623,7 +1637,7 @@ drm_mode_std(struct drm_connector *connector, struct edid *edid, vrefresh_rate = vfreq + 60; /* the vdisplay is calculated based on the aspect ratio */ if (aspect_ratio == 0) { - if (revision < 3) + if (edid->revision < 3) vsize = hsize; else vsize = (hsize * 10) / 16; @@ -2140,7 +2154,7 @@ do_established_modes(struct detailed_timing *timing, void *c) /** * add_established_modes - get est. modes from EDID and add them - * @connector: connector of for the EDID block + * @connector: connector to add mode(s) to * @edid: EDID block to scan * * Each EDID block contains a bitmap of the supported "established modes" list @@ -2191,8 +2205,7 @@ do_standard_modes(struct detailed_timing *timing, void *c) struct drm_display_mode *newmode; std = &data->data.timings[i]; - newmode = drm_mode_std(connector, edid, std, - edid->revision); + newmode = drm_mode_std(connector, edid, std); if (newmode) { drm_mode_probed_add(connector, newmode); closure->modes++; @@ -2203,7 +2216,7 @@ do_standard_modes(struct detailed_timing *timing, void *c) /** * add_standard_modes - get std. modes from EDID and add them - * @connector: connector of for the EDID block + * @connector: connector to add mode(s) to * @edid: EDID block to scan * * Standard modes can be calculated using the appropriate standard (DMT, @@ -2221,8 +2234,7 @@ add_standard_modes(struct drm_connector *connector, struct edid *edid) struct drm_display_mode *newmode; newmode = drm_mode_std(connector, edid, - &edid->standard_timings[i], - edid->revision); + &edid->standard_timings[i]); if (newmode) { drm_mode_probed_add(connector, newmode); modes++; @@ -2425,7 +2437,7 @@ cea_mode_alternate_clock(const struct drm_display_mode *cea_mode) * drm_match_cea_mode - look for a CEA mode matching given mode * @to_match: display mode * - * Returns the CEA Video ID (VIC) of the mode or 0 if it isn't a CEA-861 + * Return: The CEA Video ID (VIC) of the mode or 0 if it isn't a CEA-861 * mode. */ u8 drm_match_cea_mode(const struct drm_display_mode *to_match) @@ -2452,6 +2464,22 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match) } EXPORT_SYMBOL(drm_match_cea_mode); +/** + * drm_get_cea_aspect_ratio - get the picture aspect ratio corresponding to + * the input VIC from the CEA mode list + * @video_code: ID given to each of the CEA modes + * + * Returns picture aspect ratio + */ +enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code) +{ + /* return picture aspect ratio for video_code - 1 to access the + * right array element + */ + return edid_cea_modes[video_code-1].picture_aspect_ratio; +} +EXPORT_SYMBOL(drm_get_cea_aspect_ratio); + /* * Calculate the alternate clock for HDMI modes (those from the HDMI vendor * specific block). @@ -3023,11 +3051,9 @@ monitor_name(struct detailed_timing *t, void *data) * @connector: connector corresponding to the HDMI/DP sink * @edid: EDID to parse * - * Fill the ELD (EDID-Like Data) buffer for passing to the audio driver. - * Some ELD fields are left to the graphics driver caller: - * - Conn_Type - * - HDCP - * - Port_ID + * Fill the ELD (EDID-Like Data) buffer for passing to the audio driver. The + * Conn_Type, HDCP and Port_ID ELD fields are left for the graphics driver to + * fill in. */ void drm_edid_to_eld(struct drm_connector *connector, struct edid *edid) { @@ -3111,9 +3137,10 @@ EXPORT_SYMBOL(drm_edid_to_eld); * @sads: pointer that will be set to the extracted SADs * * Looks for CEA EDID block and extracts SADs (Short Audio Descriptors) from it. - * Note: returned pointer needs to be kfreed * - * Return number of found SADs or negative number on error. + * Note: The returned pointer needs to be freed using kfree(). + * + * Return: The number of found SADs or negative number on error. */ int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads) { @@ -3170,9 +3197,11 @@ EXPORT_SYMBOL(drm_edid_to_sad); * @sadb: pointer to the speaker block * * Looks for CEA EDID block and extracts the Speaker Allocation Data Block from it. - * Note: returned pointer needs to be kfreed * - * Return number of found Speaker Allocation Blocks or negative number on error. + * Note: The returned pointer needs to be freed using kfree(). + * + * Return: The number of found Speaker Allocation Blocks or negative number on + * error. */ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb) { @@ -3204,10 +3233,9 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb) /* Speaker Allocation Data Block */ if (dbl == 3) { - *sadb = kmalloc(dbl, GFP_KERNEL); + *sadb = kmemdup(&db[1], dbl, GFP_KERNEL); if (!*sadb) return -ENOMEM; - memcpy(*sadb, &db[1], dbl); count = dbl; break; } @@ -3219,9 +3247,12 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb) EXPORT_SYMBOL(drm_edid_to_speaker_allocation); /** - * drm_av_sync_delay - HDMI/DP sink audio-video sync delay in millisecond + * drm_av_sync_delay - compute the HDMI/DP sink audio-video sync delay * @connector: connector associated with the HDMI/DP sink * @mode: the display mode + * + * Return: The HDMI/DP sink's audio-video sync delay in milliseconds or 0 if + * the sink doesn't support audio or video. */ int drm_av_sync_delay(struct drm_connector *connector, struct drm_display_mode *mode) @@ -3263,6 +3294,9 @@ EXPORT_SYMBOL(drm_av_sync_delay); * * It's possible for one encoder to be associated with multiple HDMI/DP sinks. * The policy is now hard coded to simply use the first HDMI/DP sink's ELD. + * + * Return: The connector associated with the first HDMI/DP sink that has ELD + * attached to it. */ struct drm_connector *drm_select_eld(struct drm_encoder *encoder, struct drm_display_mode *mode) @@ -3270,6 +3304,8 @@ struct drm_connector *drm_select_eld(struct drm_encoder *encoder, struct drm_connector *connector; struct drm_device *dev = encoder->dev; + WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); + list_for_each_entry(connector, &dev->mode_config.connector_list, head) if (connector->encoder == encoder && connector->eld[0]) return connector; @@ -3279,11 +3315,12 @@ struct drm_connector *drm_select_eld(struct drm_encoder *encoder, EXPORT_SYMBOL(drm_select_eld); /** - * drm_detect_hdmi_monitor - detect whether monitor is hdmi. + * drm_detect_hdmi_monitor - detect whether monitor is HDMI * @edid: monitor EDID information * * Parse the CEA extension according to CEA-861-B. - * Return true if HDMI, false if not or unknown. + * + * Return: True if the monitor is HDMI, false if not or unknown. */ bool drm_detect_hdmi_monitor(struct edid *edid) { @@ -3321,6 +3358,7 @@ EXPORT_SYMBOL(drm_detect_hdmi_monitor); * audio format, assume at least 'basic audio' support, even if 'basic * audio' is not defined in EDID. * + * Return: True if the monitor supports audio, false otherwise. */ bool drm_detect_monitor_audio(struct edid *edid) { @@ -3364,6 +3402,8 @@ EXPORT_SYMBOL(drm_detect_monitor_audio); * Check whether the monitor reports the RGB quantization range selection * as supported. The AVI infoframe can then be used to inform the monitor * which quantization range (full or limited) is used. + * + * Return: True if the RGB quantization range is selectable, false otherwise. */ bool drm_rgb_quant_range_selectable(struct edid *edid) { @@ -3389,17 +3429,120 @@ bool drm_rgb_quant_range_selectable(struct edid *edid) } EXPORT_SYMBOL(drm_rgb_quant_range_selectable); +/** + * drm_assign_hdmi_deep_color_info - detect whether monitor supports + * hdmi deep color modes and update drm_display_info if so. + * + * @edid: monitor EDID information + * @info: Updated with maximum supported deep color bpc and color format + * if deep color supported. + * + * Parse the CEA extension according to CEA-861-B. + * Return true if HDMI deep color supported, false if not or unknown. + */ +static bool drm_assign_hdmi_deep_color_info(struct edid *edid, + struct drm_display_info *info, + struct drm_connector *connector) +{ + u8 *edid_ext, *hdmi; + int i; + int start_offset, end_offset; + unsigned int dc_bpc = 0; + + edid_ext = drm_find_cea_extension(edid); + if (!edid_ext) + return false; + + if (cea_db_offsets(edid_ext, &start_offset, &end_offset)) + return false; + + /* + * Because HDMI identifier is in Vendor Specific Block, + * search it from all data blocks of CEA extension. + */ + for_each_cea_db(edid_ext, i, start_offset, end_offset) { + if (cea_db_is_hdmi_vsdb(&edid_ext[i])) { + /* HDMI supports at least 8 bpc */ + info->bpc = 8; + + hdmi = &edid_ext[i]; + if (cea_db_payload_len(hdmi) < 6) + return false; + + if (hdmi[6] & DRM_EDID_HDMI_DC_30) { + dc_bpc = 10; + info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_30; + DRM_DEBUG("%s: HDMI sink does deep color 30.\n", + connector->name); + } + + if (hdmi[6] & DRM_EDID_HDMI_DC_36) { + dc_bpc = 12; + info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_36; + DRM_DEBUG("%s: HDMI sink does deep color 36.\n", + connector->name); + } + + if (hdmi[6] & DRM_EDID_HDMI_DC_48) { + dc_bpc = 16; + info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_48; + DRM_DEBUG("%s: HDMI sink does deep color 48.\n", + connector->name); + } + + if (dc_bpc > 0) { + DRM_DEBUG("%s: Assigning HDMI sink color depth as %d bpc.\n", + connector->name, dc_bpc); + info->bpc = dc_bpc; + + /* + * Deep color support mandates RGB444 support for all video + * modes and forbids YCRCB422 support for all video modes per + * HDMI 1.3 spec. + */ + info->color_formats = DRM_COLOR_FORMAT_RGB444; + + /* YCRCB444 is optional according to spec. */ + if (hdmi[6] & DRM_EDID_HDMI_DC_Y444) { + info->color_formats |= DRM_COLOR_FORMAT_YCRCB444; + DRM_DEBUG("%s: HDMI sink does YCRCB444 in deep color.\n", + connector->name); + } + + /* + * Spec says that if any deep color mode is supported at all, + * then deep color 36 bit must be supported. + */ + if (!(hdmi[6] & DRM_EDID_HDMI_DC_36)) { + DRM_DEBUG("%s: HDMI sink should do DC_36, but does not!\n", + connector->name); + } + + return true; + } + else { + DRM_DEBUG("%s: No deep color support on this HDMI sink.\n", + connector->name); + } + } + } + + return false; +} + /** * drm_add_display_info - pull display info out if present * @edid: EDID data * @info: display info (attached to connector) + * @connector: connector whose edid is used to build display info * * Grab any available display info and stuff it into the drm_display_info * structure that's part of the connector. Useful for tracking bpp and * color spaces. */ static void drm_add_display_info(struct edid *edid, - struct drm_display_info *info) + struct drm_display_info *info, + struct drm_connector *connector) { u8 *edid_ext; @@ -3429,6 +3572,9 @@ static void drm_add_display_info(struct edid *edid, info->color_formats |= DRM_COLOR_FORMAT_YCRCB422; } + /* HDMI deep color modes supported? Assign to info, if so */ + drm_assign_hdmi_deep_color_info(edid, info, connector); + /* Only defined for 1.4 with digital displays */ if (edid->revision < 4) return; @@ -3458,6 +3604,9 @@ static void drm_add_display_info(struct edid *edid, break; } + DRM_DEBUG("%s: Assigning EDID-1.4 digital sink color depth as %d bpc.\n", + connector->name, info->bpc); + info->color_formats |= DRM_COLOR_FORMAT_RGB444; if (edid->features & DRM_EDID_FEATURE_RGB_YCRCB444) info->color_formats |= DRM_COLOR_FORMAT_YCRCB444; @@ -3468,11 +3617,11 @@ static void drm_add_display_info(struct edid *edid, /** * drm_add_edid_modes - add modes from EDID data, if available * @connector: connector we're probing - * @edid: edid data + * @edid: EDID data * * Add the specified modes to the connector's mode list. * - * Return number of modes added or 0 if we couldn't find any. + * Return: The number of modes added or 0 if we couldn't find any. */ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) { @@ -3484,7 +3633,7 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) } if (!drm_edid_is_valid(edid)) { dev_warn(connector->dev->dev, "%s: EDID invalid.\n", - drm_get_connector_name(connector)); + connector->name); return 0; } @@ -3516,11 +3665,14 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) if (quirks & (EDID_QUIRK_PREFER_LARGE_60 | EDID_QUIRK_PREFER_LARGE_75)) edid_fixup_preferred(connector, quirks); - drm_add_display_info(edid, &connector->display_info); + drm_add_display_info(edid, &connector->display_info, connector); if (quirks & EDID_QUIRK_FORCE_8BPC) connector->display_info.bpc = 8; + if (quirks & EDID_QUIRK_FORCE_12BPC) + connector->display_info.bpc = 12; + return num_modes; } EXPORT_SYMBOL(drm_add_edid_modes); @@ -3534,7 +3686,7 @@ EXPORT_SYMBOL(drm_add_edid_modes); * Add the specified modes to the connector's mode list. Only when the * hdisplay/vdisplay is not beyond the given limit, it will be added. * - * Return number of modes added or 0 if we couldn't find any. + * Return: The number of modes added or 0 if we couldn't find any. */ int drm_add_modes_noedid(struct drm_connector *connector, int hdisplay, int vdisplay) @@ -3573,13 +3725,22 @@ int drm_add_modes_noedid(struct drm_connector *connector, } EXPORT_SYMBOL(drm_add_modes_noedid); +/** + * drm_set_preferred_mode - Sets the preferred mode of a connector + * @connector: connector whose mode list should be processed + * @hpref: horizontal resolution of preferred mode + * @vpref: vertical resolution of preferred mode + * + * Marks a mode as preferred if it matches the resolution specified by @hpref + * and @vpref. + */ void drm_set_preferred_mode(struct drm_connector *connector, int hpref, int vpref) { struct drm_display_mode *mode; list_for_each_entry(mode, &connector->probed_modes, head) { - if (mode->hdisplay == hpref && + if (mode->hdisplay == hpref && mode->vdisplay == vpref) mode->type |= DRM_MODE_TYPE_PREFERRED; } @@ -3592,7 +3753,7 @@ EXPORT_SYMBOL(drm_set_preferred_mode); * @frame: HDMI AVI infoframe * @mode: DRM display mode * - * Returns 0 on success or a negative error code on failure. + * Return: 0 on success or a negative error code on failure. */ int drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame, @@ -3613,6 +3774,12 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame, frame->video_code = drm_match_cea_mode(mode); frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE; + + /* Populate picture aspect ratio from CEA mode list */ + if (frame->video_code > 0) + frame->picture_aspect = drm_get_cea_aspect_ratio( + frame->video_code); + frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE; frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN; @@ -3657,7 +3824,7 @@ s3d_structure_from_display_mode(const struct drm_display_mode *mode) * 4k or stereoscopic 3D mode. So when giving any other mode as input this * function will return -EINVAL, error that can be safely ignored. * - * Returns 0 on success or a negative error code on failure. + * Return: 0 on success or a negative error code on failure. */ int drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame, diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c index 1b4c7a5442c5..0a235fe61c9b 100644 --- a/drivers/gpu/drm/drm_edid_load.c +++ b/drivers/gpu/drm/drm_edid_load.c @@ -31,8 +31,9 @@ module_param_string(edid_firmware, edid_firmware, sizeof(edid_firmware), 0644); MODULE_PARM_DESC(edid_firmware, "Do not probe monitor, use specified EDID blob " "from built-in data or /lib/firmware instead. "); -#define GENERIC_EDIDS 5 +#define GENERIC_EDIDS 6 static const char *generic_edid_name[GENERIC_EDIDS] = { + "edid/800x600.bin", "edid/1024x768.bin", "edid/1280x1024.bin", "edid/1600x1200.bin", @@ -41,6 +42,24 @@ static const char *generic_edid_name[GENERIC_EDIDS] = { }; static const u8 generic_edid[GENERIC_EDIDS][128] = { + { + 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, + 0x31, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x05, 0x16, 0x01, 0x03, 0x6d, 0x1b, 0x14, 0x78, + 0xea, 0x5e, 0xc0, 0xa4, 0x59, 0x4a, 0x98, 0x25, + 0x20, 0x50, 0x54, 0x01, 0x00, 0x00, 0x45, 0x40, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0xa0, 0x0f, + 0x20, 0x00, 0x31, 0x58, 0x1c, 0x20, 0x28, 0x80, + 0x14, 0x00, 0x15, 0xd0, 0x10, 0x00, 0x00, 0x1e, + 0x00, 0x00, 0x00, 0xff, 0x00, 0x4c, 0x69, 0x6e, + 0x75, 0x78, 0x20, 0x23, 0x30, 0x0a, 0x20, 0x20, + 0x20, 0x20, 0x00, 0x00, 0x00, 0xfd, 0x00, 0x3b, + 0x3d, 0x24, 0x26, 0x05, 0x00, 0x0a, 0x20, 0x20, + 0x20, 0x20, 0x20, 0x20, 0x00, 0x00, 0x00, 0xfc, + 0x00, 0x4c, 0x69, 0x6e, 0x75, 0x78, 0x20, 0x53, + 0x56, 0x47, 0x41, 0x0a, 0x20, 0x20, 0x00, 0xc2, + }, { 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x31, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -242,7 +261,7 @@ static void *edid_load(struct drm_connector *connector, const char *name, int drm_load_edid_firmware(struct drm_connector *connector) { - const char *connector_name = drm_get_connector_name(connector); + const char *connector_name = connector->name; char *edidname = edid_firmware, *last, *colon; int ret; struct edid *edid; diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index 61b5a47ad239..f27c883be391 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -429,13 +429,8 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini); */ void drm_fbdev_cma_restore_mode(struct drm_fbdev_cma *fbdev_cma) { - if (fbdev_cma) { - struct drm_device *dev = fbdev_cma->fb_helper.dev; - - drm_modeset_lock_all(dev); - drm_fb_helper_restore_fbdev_mode(&fbdev_cma->fb_helper); - drm_modeset_unlock_all(dev); - } + if (fbdev_cma) + drm_fb_helper_restore_fbdev_mode_unlocked(&fbdev_cma->fb_helper); } EXPORT_SYMBOL_GPL(drm_fbdev_cma_restore_mode); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 04d3fd3658f3..d5d8cea1a679 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -45,13 +45,13 @@ static LIST_HEAD(kernel_fb_helper_list); * DOC: fbdev helpers * * The fb helper functions are useful to provide an fbdev on top of a drm kernel - * mode setting driver. They can be used mostly independantely from the crtc + * mode setting driver. They can be used mostly independently from the crtc * helper functions used by many drivers to implement the kernel mode setting * interfaces. * * Initialization is done as a three-step process with drm_fb_helper_init(), * drm_fb_helper_single_add_all_connectors() and drm_fb_helper_initial_config(). - * Drivers with fancier requirements than the default beheviour can override the + * Drivers with fancier requirements than the default behaviour can override the * second step with their own code. Teardown is done with drm_fb_helper_fini(). * * At runtime drivers should restore the fbdev console by calling @@ -59,7 +59,7 @@ static LIST_HEAD(kernel_fb_helper_list); * should also notify the fb helper code from updates to the output * configuration by calling drm_fb_helper_hotplug_event(). For easier * integration with the output polling code in drm_crtc_helper.c the modeset - * code proves a ->output_poll_changed callback. + * code provides a ->output_poll_changed callback. * * All other functions exported by the fb helper library can be used to * implement the fbdev driver interface by the driver. @@ -120,7 +120,7 @@ static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper) mode = &fb_helper_conn->cmdline_mode; /* do something on return - turn off connector maybe */ - if (fb_get_options(drm_get_connector_name(connector), &option)) + if (fb_get_options(connector->name, &option)) continue; if (drm_mode_parse_command_line_for_connector(option, @@ -142,12 +142,12 @@ static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper) } DRM_INFO("forcing %s connector %s\n", - drm_get_connector_name(connector), s); + connector->name, s); connector->force = mode->force; } DRM_DEBUG_KMS("cmdline mode for connector %s %dx%d@%dHz%s%s%s\n", - drm_get_connector_name(connector), + connector->name, mode->xres, mode->yres, mode->refresh_specified ? mode->refresh : 60, mode->rb ? " reduced blanking" : "", @@ -273,15 +273,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info) } EXPORT_SYMBOL(drm_fb_helper_debug_leave); -/** - * drm_fb_helper_restore_fbdev_mode - restore fbdev configuration - * @fb_helper: fbcon to restore - * - * This should be called from driver's drm ->lastclose callback - * when implementing an fbcon on top of kms using this helper. This ensures that - * the user isn't greeted with a black screen when e.g. X dies. - */ -bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper) +static bool restore_fbdev_mode(struct drm_fb_helper *fb_helper) { struct drm_device *dev = fb_helper->dev; struct drm_plane *plane; @@ -311,7 +303,40 @@ bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper) } return error; } -EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode); +/** + * drm_fb_helper_restore_fbdev_mode - restore fbdev configuration + * @fb_helper: fbcon to restore + * + * This should be called from driver's drm ->lastclose callback + * when implementing an fbcon on top of kms using this helper. This ensures that + * the user isn't greeted with a black screen when e.g. X dies. + * + * Use this variant if you need to bypass locking (panic), or already + * hold all modeset locks. Otherwise use drm_fb_helper_restore_fbdev_mode_unlocked() + */ +static bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper) +{ + return restore_fbdev_mode(fb_helper); +} + +/** + * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration + * @fb_helper: fbcon to restore + * + * This should be called from driver's drm ->lastclose callback + * when implementing an fbcon on top of kms using this helper. This ensures that + * the user isn't greeted with a black screen when e.g. X dies. + */ +bool drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +{ + struct drm_device *dev = fb_helper->dev; + bool ret; + drm_modeset_lock_all(dev); + ret = restore_fbdev_mode(fb_helper); + drm_modeset_unlock_all(dev); + return ret; +} +EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); /* * restore fbcon display for all kms driver's using this helper, used for sysrq @@ -326,12 +351,25 @@ static bool drm_fb_helper_force_kernel_mode(void) return false; list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { - if (helper->dev->switch_power_state == DRM_SWITCH_POWER_OFF) + struct drm_device *dev = helper->dev; + + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) continue; + /* NOTE: we use lockless flag below to avoid grabbing other + * modeset locks. So just trylock the underlying mutex + * directly: + */ + if (!mutex_trylock(&dev->mode_config.mutex)) { + error = true; + continue; + } + ret = drm_fb_helper_restore_fbdev_mode(helper); if (ret) error = true; + + mutex_unlock(&dev->mode_config.mutex); } return error; } @@ -811,7 +849,6 @@ EXPORT_SYMBOL(drm_fb_helper_check_var); int drm_fb_helper_set_par(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; - struct drm_device *dev = fb_helper->dev; struct fb_var_screeninfo *var = &info->var; if (var->pixclock != 0) { @@ -819,9 +856,7 @@ int drm_fb_helper_set_par(struct fb_info *info) return -EINVAL; } - drm_modeset_lock_all(dev); - drm_fb_helper_restore_fbdev_mode(fb_helper); - drm_modeset_unlock_all(dev); + drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); if (fb_helper->delayed_hotplug) { fb_helper->delayed_hotplug = false; diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index e1eba0b7cd45..021fe5d11df5 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -43,8 +43,7 @@ DEFINE_MUTEX(drm_global_mutex); EXPORT_SYMBOL(drm_global_mutex); -static int drm_open_helper(struct inode *inode, struct file *filp, - struct drm_minor *minor); +static int drm_open_helper(struct file *filp, struct drm_minor *minor); static int drm_setup(struct drm_device * dev) { @@ -95,7 +94,7 @@ int drm_open(struct inode *inode, struct file *filp) /* share address_space across all char-devs of a single device */ filp->f_mapping = dev->anon_inode->i_mapping; - retcode = drm_open_helper(inode, filp, minor); + retcode = drm_open_helper(filp, minor); if (retcode) goto err_undo; if (need_setup) { @@ -171,7 +170,6 @@ static int drm_cpu_valid(void) /** * Called whenever a process opens /dev/drm. * - * \param inode device inode. * \param filp file pointer. * \param minor acquired minor-object. * \return zero on success or a negative number on failure. @@ -179,8 +177,7 @@ static int drm_cpu_valid(void) * Creates and initializes a drm_file structure for the file private data in \p * filp and add it into the double linked list in \p dev. */ -static int drm_open_helper(struct inode *inode, struct file *filp, - struct drm_minor *minor) +static int drm_open_helper(struct file *filp, struct drm_minor *minor) { struct drm_device *dev = minor->dev; struct drm_file *priv; diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 9909bef59800..f7d71190aad5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -474,21 +474,10 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask) goto fail; pages[i] = p; - /* There is a hypothetical issue w/ drivers that require - * buffer memory in the low 4GB.. if the pages are un- - * pinned, and swapped out, they can end up swapped back - * in above 4GB. If pages are already in memory, then - * shmem_read_mapping_page_gfp will ignore the gfpmask, - * even if the already in-memory page disobeys the mask. - * - * It is only a theoretical issue today, because none of - * the devices with this limitation can be populated with - * enough memory to trigger the issue. But this BUG_ON() - * is here as a reminder in case the problem with - * shmem_read_mapping_page_gfp() isn't solved by the time - * it does become a real issue. - * - * See this thread: http://lkml.org/lkml/2011/7/11/238 + /* Make sure shmem keeps __GFP_DMA32 allocated pages in the + * correct region during swapin. Note that this requires + * __GFP_DMA32 to be set in mapping_gfp_mask(inode->i_mapping) + * so shmem can relocate pages during swapin if required. */ BUG_ON((gfpmask & __GFP_DMA32) && (page_to_pfn(p) >= 0x00100000UL)); diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c index 7473035dd28b..86feedd5e6f6 100644 --- a/drivers/gpu/drm/drm_info.c +++ b/drivers/gpu/drm/drm_info.c @@ -47,18 +47,16 @@ int drm_name_info(struct seq_file *m, void *data) struct drm_minor *minor = node->minor; struct drm_device *dev = minor->dev; struct drm_master *master = minor->master; - const char *bus_name; if (!master) return 0; - bus_name = dev->driver->bus->get_name(dev); if (master->unique) { seq_printf(m, "%s %s %s\n", - bus_name, + dev->driver->name, dev_name(dev->dev), master->unique); } else { seq_printf(m, "%s %s\n", - bus_name, dev_name(dev->dev)); + dev->driver->name, dev_name(dev->dev)); } return 0; } diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 93a42040bedb..69c61f392e66 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -72,9 +72,6 @@ static void drm_unset_busid(struct drm_device *dev, struct drm_master *master) { - kfree(dev->devname); - dev->devname = NULL; - kfree(master->unique); master->unique = NULL; master->unique_len = 0; @@ -93,7 +90,8 @@ drm_unset_busid(struct drm_device *dev, * Copies the bus id from userspace into drm_device::unique, and verifies that * it matches the device this DRM is attached to (EINVAL otherwise). Deprecated * in interface version 1.1 and will return EBUSY when setversion has requested - * version 1.1 or greater. + * version 1.1 or greater. Also note that KMS is all version 1.1 and later and + * UMS was only ever supported on pci devices. */ int drm_setunique(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -108,10 +106,13 @@ int drm_setunique(struct drm_device *dev, void *data, if (!u->unique_len || u->unique_len > 1024) return -EINVAL; - if (!dev->driver->bus->set_unique) + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return 0; + + if (WARN_ON(!dev->pdev)) return -EINVAL; - ret = dev->driver->bus->set_unique(dev, master, u); + ret = drm_pci_set_unique(dev, master, u); if (ret) goto err; @@ -130,13 +131,25 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv) if (master->unique != NULL) drm_unset_busid(dev, master); - ret = dev->driver->bus->set_busid(dev, master); - if (ret) - goto err; + if (dev->driver->bus && dev->driver->bus->set_busid) { + ret = dev->driver->bus->set_busid(dev, master); + if (ret) { + drm_unset_busid(dev, master); + return ret; + } + } else { + if (WARN(dev->unique == NULL, + "No drm_bus.set_busid() implementation provided by " + "%ps. Use drm_dev_set_unique() to set the unique " + "name explicitly.", dev->driver)) + return -EINVAL; + + master->unique = kstrdup(dev->unique, GFP_KERNEL); + if (master->unique) + master->unique_len = strlen(dev->unique); + } + return 0; -err: - drm_unset_busid(dev, master); - return ret; } /** diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index ec5c3f4cdd01..0de123afdb34 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -1,6 +1,5 @@ -/** - * \file drm_irq.c - * IRQ support +/* + * drm_irq.c IRQ and vblank support * * \author Rickard E. (Rik) Faith * \author Gareth Hughes @@ -56,33 +55,6 @@ */ #define DRM_REDUNDANT_VBLIRQ_THRESH_NS 1000000 -/** - * Get interrupt from bus id. - * - * \param inode device inode. - * \param file_priv DRM file private. - * \param cmd command. - * \param arg user argument, pointing to a drm_irq_busid structure. - * \return zero on success or a negative number on failure. - * - * Finds the PCI device with the specified bus id and gets its IRQ number. - * This IOCTL is deprecated, and will now return EINVAL for any busid not equal - * to that of the device that this DRM instance attached to. - */ -int drm_irq_by_busid(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct drm_irq_busid *p = data; - - if (!dev->driver->bus->irq_by_busid) - return -EINVAL; - - if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) - return -EINVAL; - - return dev->driver->bus->irq_by_busid(dev, p); -} - /* * Clear vblank timestamp buffer for a crtc. */ @@ -167,33 +139,40 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc) static void vblank_disable_fn(unsigned long arg) { - struct drm_device *dev = (struct drm_device *)arg; + struct drm_vblank_crtc *vblank = (void *)arg; + struct drm_device *dev = vblank->dev; unsigned long irqflags; - int i; + int crtc = vblank->crtc; if (!dev->vblank_disable_allowed) return; - for (i = 0; i < dev->num_crtcs; i++) { - spin_lock_irqsave(&dev->vbl_lock, irqflags); - if (atomic_read(&dev->vblank[i].refcount) == 0 && - dev->vblank[i].enabled) { - DRM_DEBUG("disabling vblank on crtc %d\n", i); - vblank_disable_and_save(dev, i); - } - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); + spin_lock_irqsave(&dev->vbl_lock, irqflags); + if (atomic_read(&vblank->refcount) == 0 && vblank->enabled) { + DRM_DEBUG("disabling vblank on crtc %d\n", crtc); + vblank_disable_and_save(dev, crtc); } + spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } +/** + * drm_vblank_cleanup - cleanup vblank support + * @dev: DRM device + * + * This function cleans up any resources allocated in drm_vblank_init. + */ void drm_vblank_cleanup(struct drm_device *dev) { + int crtc; + /* Bail if the driver didn't call drm_vblank_init() */ if (dev->num_crtcs == 0) return; - del_timer_sync(&dev->vblank_disable_timer); - - vblank_disable_fn((unsigned long)dev); + for (crtc = 0; crtc < dev->num_crtcs; crtc++) { + del_timer_sync(&dev->vblank[crtc].disable_timer); + vblank_disable_fn((unsigned long)&dev->vblank[crtc]); + } kfree(dev->vblank); @@ -201,12 +180,20 @@ void drm_vblank_cleanup(struct drm_device *dev) } EXPORT_SYMBOL(drm_vblank_cleanup); +/** + * drm_vblank_init - initialize vblank support + * @dev: drm_device + * @num_crtcs: number of crtcs supported by @dev + * + * This function initializes vblank support for @num_crtcs display pipelines. + * + * Returns: + * Zero on success or a negative error code on failure. + */ int drm_vblank_init(struct drm_device *dev, int num_crtcs) { int i, ret = -ENOMEM; - setup_timer(&dev->vblank_disable_timer, vblank_disable_fn, - (unsigned long)dev); spin_lock_init(&dev->vbl_lock); spin_lock_init(&dev->vblank_time_lock); @@ -216,8 +203,13 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs) if (!dev->vblank) goto err; - for (i = 0; i < num_crtcs; i++) + for (i = 0; i < num_crtcs; i++) { + dev->vblank[i].dev = dev; + dev->vblank[i].crtc = i; init_waitqueue_head(&dev->vblank[i].queue); + setup_timer(&dev->vblank[i].disable_timer, vblank_disable_fn, + (unsigned long)&dev->vblank[i]); + } DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n"); @@ -261,42 +253,42 @@ static void drm_irq_vgaarb_nokms(void *cookie, bool state) } /** - * Install IRQ handler. - * - * \param dev DRM device. + * drm_irq_install - install IRQ handler + * @dev: DRM device + * @irq: IRQ number to install the handler for * * Initializes the IRQ related data. Installs the handler, calling the driver - * \c irq_preinstall() and \c irq_postinstall() functions - * before and after the installation. + * irq_preinstall() and irq_postinstall() functions before and after the + * installation. + * + * This is the simplified helper interface provided for drivers with no special + * needs. Drivers which need to install interrupt handlers for multiple + * interrupts must instead set drm_device->irq_enabled to signal the DRM core + * that vblank interrupts are available. + * + * Returns: + * Zero on success or a negative error code on failure. */ -int drm_irq_install(struct drm_device *dev) +int drm_irq_install(struct drm_device *dev, int irq) { int ret; unsigned long sh_flags = 0; - char *irqname; if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) return -EINVAL; - if (drm_dev_to_irq(dev) == 0) + if (irq == 0) return -EINVAL; - mutex_lock(&dev->struct_mutex); - /* Driver must have been initialized */ - if (!dev->dev_private) { - mutex_unlock(&dev->struct_mutex); + if (!dev->dev_private) return -EINVAL; - } - if (dev->irq_enabled) { - mutex_unlock(&dev->struct_mutex); + if (dev->irq_enabled) return -EBUSY; - } dev->irq_enabled = true; - mutex_unlock(&dev->struct_mutex); - DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev)); + DRM_DEBUG("irq=%d\n", irq); /* Before installing handler */ if (dev->driver->irq_preinstall) @@ -306,18 +298,11 @@ int drm_irq_install(struct drm_device *dev) if (drm_core_check_feature(dev, DRIVER_IRQ_SHARED)) sh_flags = IRQF_SHARED; - if (dev->devname) - irqname = dev->devname; - else - irqname = dev->driver->name; - - ret = request_irq(drm_dev_to_irq(dev), dev->driver->irq_handler, - sh_flags, irqname, dev); + ret = request_irq(irq, dev->driver->irq_handler, + sh_flags, dev->driver->name, dev); if (ret < 0) { - mutex_lock(&dev->struct_mutex); dev->irq_enabled = false; - mutex_unlock(&dev->struct_mutex); return ret; } @@ -329,12 +314,12 @@ int drm_irq_install(struct drm_device *dev) ret = dev->driver->irq_postinstall(dev); if (ret < 0) { - mutex_lock(&dev->struct_mutex); dev->irq_enabled = false; - mutex_unlock(&dev->struct_mutex); if (!drm_core_check_feature(dev, DRIVER_MODESET)) vga_client_register(dev->pdev, NULL, NULL, NULL); - free_irq(drm_dev_to_irq(dev), dev); + free_irq(irq, dev); + } else { + dev->irq = irq; } return ret; @@ -342,11 +327,20 @@ int drm_irq_install(struct drm_device *dev) EXPORT_SYMBOL(drm_irq_install); /** - * Uninstall the IRQ handler. + * drm_irq_uninstall - uninstall the IRQ handler + * @dev: DRM device * - * \param dev DRM device. + * Calls the driver's irq_uninstall() function and unregisters the IRQ handler. + * This should only be called by drivers which used drm_irq_install() to set up + * their interrupt handler. Other drivers must only reset + * drm_device->irq_enabled to false. * - * Calls the driver's \c irq_uninstall() function, and stops the irq. + * Note that for kernel modesetting drivers it is a bug if this function fails. + * The sanity checks are only to catch buggy user modesetting drivers which call + * the same function through an ioctl. + * + * Returns: + * Zero on success or a negative error code on failure. */ int drm_irq_uninstall(struct drm_device *dev) { @@ -357,10 +351,8 @@ int drm_irq_uninstall(struct drm_device *dev) if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) return -EINVAL; - mutex_lock(&dev->struct_mutex); irq_enabled = dev->irq_enabled; dev->irq_enabled = false; - mutex_unlock(&dev->struct_mutex); /* * Wake up any waiters so they don't hang. @@ -379,7 +371,7 @@ int drm_irq_uninstall(struct drm_device *dev) if (!irq_enabled) return -EINVAL; - DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev)); + DRM_DEBUG("irq=%d\n", dev->irq); if (!drm_core_check_feature(dev, DRIVER_MODESET)) vga_client_register(dev->pdev, NULL, NULL, NULL); @@ -387,13 +379,13 @@ int drm_irq_uninstall(struct drm_device *dev) if (dev->driver->irq_uninstall) dev->driver->irq_uninstall(dev); - free_irq(drm_dev_to_irq(dev), dev); + free_irq(dev->irq, dev); return 0; } EXPORT_SYMBOL(drm_irq_uninstall); -/** +/* * IRQ control ioctl. * * \param inode device inode. @@ -408,43 +400,52 @@ int drm_control(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_control *ctl = data; + int ret = 0, irq; /* if we haven't irq we fallback for compatibility reasons - * this used to be a separate function in drm_dma.h */ + if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) + return 0; + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return 0; + /* UMS was only ever support on pci devices. */ + if (WARN_ON(!dev->pdev)) + return -EINVAL; switch (ctl->func) { case DRM_INST_HANDLER: - if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) - return 0; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return 0; + irq = dev->pdev->irq; + if (dev->if_version < DRM_IF_VERSION(1, 2) && - ctl->irq != drm_dev_to_irq(dev)) + ctl->irq != irq) return -EINVAL; - return drm_irq_install(dev); + mutex_lock(&dev->struct_mutex); + ret = drm_irq_install(dev, irq); + mutex_unlock(&dev->struct_mutex); + + return ret; case DRM_UNINST_HANDLER: - if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) - return 0; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return 0; - return drm_irq_uninstall(dev); + mutex_lock(&dev->struct_mutex); + ret = drm_irq_uninstall(dev); + mutex_unlock(&dev->struct_mutex); + + return ret; default: return -EINVAL; } } /** - * drm_calc_timestamping_constants - Calculate vblank timestamp constants - * - * @crtc drm_crtc whose timestamp constants should be updated. - * @mode display mode containing the scanout timings + * drm_calc_timestamping_constants - calculate vblank timestamp constants + * @crtc: drm_crtc whose timestamp constants should be updated. + * @mode: display mode containing the scanout timings * * Calculate and store various constants which are later * needed by vblank and swap-completion timestamping, e.g, * by drm_calc_vbltimestamp_from_scanoutpos(). They are - * derived from crtc's true scanout timing, so they take + * derived from CRTC's true scanout timing, so they take * things like panel scaling or other adjustments into account. */ void drm_calc_timestamping_constants(struct drm_crtc *crtc, @@ -489,11 +490,22 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc, EXPORT_SYMBOL(drm_calc_timestamping_constants); /** - * drm_calc_vbltimestamp_from_scanoutpos - helper routine for kms - * drivers. Implements calculation of exact vblank timestamps from - * given drm_display_mode timings and current video scanout position - * of a crtc. This can be called from within get_vblank_timestamp() - * implementation of a kms driver to implement the actual timestamping. + * drm_calc_vbltimestamp_from_scanoutpos - precise vblank timestamp helper + * @dev: DRM device + * @crtc: Which CRTC's vblank timestamp to retrieve + * @max_error: Desired maximum allowable error in timestamps (nanosecs) + * On return contains true maximum error of timestamp + * @vblank_time: Pointer to struct timeval which should receive the timestamp + * @flags: Flags to pass to driver: + * 0 = Default, + * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler + * @refcrtc: CRTC which defines scanout timing + * @mode: mode which defines the scanout timings + * + * Implements calculation of exact vblank timestamps from given drm_display_mode + * timings and current video scanout position of a CRTC. This can be called from + * within get_vblank_timestamp() implementation of a kms driver to implement the + * actual timestamping. * * Should return timestamps conforming to the OML_sync_control OpenML * extension specification. The timestamp corresponds to the end of @@ -508,21 +520,11 @@ EXPORT_SYMBOL(drm_calc_timestamping_constants); * returns as no operation if a doublescan or interlaced video mode is * active. Higher level code is expected to handle this. * - * @dev: DRM device. - * @crtc: Which crtc's vblank timestamp to retrieve. - * @max_error: Desired maximum allowable error in timestamps (nanosecs). - * On return contains true maximum error of timestamp. - * @vblank_time: Pointer to struct timeval which should receive the timestamp. - * @flags: Flags to pass to driver: - * 0 = Default. - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler. - * @refcrtc: drm_crtc* of crtc which defines scanout timing. - * @mode: mode which defines the scanout timings - * - * Returns negative value on error, failure or if not supported in current + * Returns: + * Negative value on error, failure or if not supported in current * video mode: * - * -EINVAL - Invalid crtc. + * -EINVAL - Invalid CRTC. * -EAGAIN - Temporary unavailable, e.g., called before initial modeset. * -ENOTSUPP - Function not supported in current display mode. * -EIO - Failed, e.g., due to failed scanout position query. @@ -671,23 +673,23 @@ static struct timeval get_drm_timestamp(void) /** * drm_get_last_vbltimestamp - retrieve raw timestamp for the most recent - * vblank interval. - * + * vblank interval * @dev: DRM device - * @crtc: which crtc's vblank timestamp to retrieve + * @crtc: which CRTC's vblank timestamp to retrieve * @tvblank: Pointer to target struct timeval which should receive the timestamp * @flags: Flags to pass to driver: - * 0 = Default. - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler. + * 0 = Default, + * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler * * Fetches the system timestamp corresponding to the time of the most recent - * vblank interval on specified crtc. May call into kms-driver to + * vblank interval on specified CRTC. May call into kms-driver to * compute the timestamp with a high-precision GPU specific method. * * Returns zero if timestamp originates from uncorrected do_gettimeofday() * call, i.e., it isn't very precisely locked to the true vblank. * - * Returns non-zero if timestamp is considered to be very precise. + * Returns: + * Non-zero if timestamp is considered to be very precise, zero otherwise. */ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc, struct timeval *tvblank, unsigned flags) @@ -722,6 +724,9 @@ EXPORT_SYMBOL(drm_get_last_vbltimestamp); * Fetches the "cooked" vblank count value that represents the number of * vblank events since the system was booted, including lost events due to * modesetting activity. + * + * Returns: + * The software vblank counter. */ u32 drm_vblank_count(struct drm_device *dev, int crtc) { @@ -740,8 +745,7 @@ EXPORT_SYMBOL(drm_vblank_count); * Fetches the "cooked" vblank count value that represents the number of * vblank events since the system was booted, including lost events due to * modesetting activity. Returns corresponding system timestamp of the time - * of the vblank interval that corresponds to the current value vblank counter - * value. + * of the vblank interval that corresponds to the current vblank counter value. */ u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc, struct timeval *vblanktime) @@ -869,6 +873,42 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) smp_mb__after_atomic(); } +/** + * drm_vblank_enable - enable the vblank interrupt on a CRTC + * @dev: DRM device + * @crtc: CRTC in question + */ +static int drm_vblank_enable(struct drm_device *dev, int crtc) +{ + int ret = 0; + + assert_spin_locked(&dev->vbl_lock); + + spin_lock(&dev->vblank_time_lock); + + if (!dev->vblank[crtc].enabled) { + /* + * Enable vblank irqs under vblank_time_lock protection. + * All vblank count & timestamp updates are held off + * until we are done reinitializing master counter and + * timestamps. Filtercode in drm_handle_vblank() will + * prevent double-accounting of same vblank interval. + */ + ret = dev->driver->enable_vblank(dev, crtc); + DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret); + if (ret) + atomic_dec(&dev->vblank[crtc].refcount); + else { + dev->vblank[crtc].enabled = true; + drm_update_vblank_count(dev, crtc); + } + } + + spin_unlock(&dev->vblank_time_lock); + + return ret; +} + /** * drm_vblank_get - get a reference count on vblank events * @dev: DRM device @@ -877,36 +917,20 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) * Acquire a reference count on vblank events to avoid having them disabled * while in use. * - * RETURNS + * This is the legacy version of drm_crtc_vblank_get(). + * + * Returns: * Zero on success, nonzero on failure. */ int drm_vblank_get(struct drm_device *dev, int crtc) { - unsigned long irqflags, irqflags2; + unsigned long irqflags; int ret = 0; spin_lock_irqsave(&dev->vbl_lock, irqflags); /* Going from 0->1 means we have to enable interrupts again */ if (atomic_add_return(1, &dev->vblank[crtc].refcount) == 1) { - spin_lock_irqsave(&dev->vblank_time_lock, irqflags2); - if (!dev->vblank[crtc].enabled) { - /* Enable vblank irqs under vblank_time_lock protection. - * All vblank count & timestamp updates are held off - * until we are done reinitializing master counter and - * timestamps. Filtercode in drm_handle_vblank() will - * prevent double-accounting of same vblank interval. - */ - ret = dev->driver->enable_vblank(dev, crtc); - DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", - crtc, ret); - if (ret) - atomic_dec(&dev->vblank[crtc].refcount); - else { - dev->vblank[crtc].enabled = true; - drm_update_vblank_count(dev, crtc); - } - } - spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2); + ret = drm_vblank_enable(dev, crtc); } else { if (!dev->vblank[crtc].enabled) { atomic_dec(&dev->vblank[crtc].refcount); @@ -919,6 +943,24 @@ int drm_vblank_get(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_get); +/** + * drm_crtc_vblank_get - get a reference count on vblank events + * @crtc: which CRTC to own + * + * Acquire a reference count on vblank events to avoid having them disabled + * while in use. + * + * This is the native kms version of drm_vblank_off(). + * + * Returns: + * Zero on success, nonzero on failure. + */ +int drm_crtc_vblank_get(struct drm_crtc *crtc) +{ + return drm_vblank_get(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_get); + /** * drm_vblank_put - give up ownership of vblank events * @dev: DRM device @@ -926,6 +968,8 @@ EXPORT_SYMBOL(drm_vblank_get); * * Release ownership of a given vblank counter, turning off interrupts * if possible. Disable interrupts after drm_vblank_offdelay milliseconds. + * + * This is the legacy version of drm_crtc_vblank_put(). */ void drm_vblank_put(struct drm_device *dev, int crtc) { @@ -934,17 +978,39 @@ void drm_vblank_put(struct drm_device *dev, int crtc) /* Last user schedules interrupt disable */ if (atomic_dec_and_test(&dev->vblank[crtc].refcount) && (drm_vblank_offdelay > 0)) - mod_timer(&dev->vblank_disable_timer, + mod_timer(&dev->vblank[crtc].disable_timer, jiffies + ((drm_vblank_offdelay * HZ)/1000)); } EXPORT_SYMBOL(drm_vblank_put); +/** + * drm_crtc_vblank_put - give up ownership of vblank events + * @crtc: which counter to give up + * + * Release ownership of a given vblank counter, turning off interrupts + * if possible. Disable interrupts after drm_vblank_offdelay milliseconds. + * + * This is the native kms version of drm_vblank_put(). + */ +void drm_crtc_vblank_put(struct drm_crtc *crtc) +{ + drm_vblank_put(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_put); + /** * drm_vblank_off - disable vblank events on a CRTC * @dev: DRM device * @crtc: CRTC in question * - * Caller must hold event lock. + * Drivers can use this function to shut down the vblank interrupt handling when + * disabling a crtc. This function ensures that the latest vblank frame count is + * stored so that drm_vblank_on() can restore it again. + * + * Drivers must use this function when the hardware vblank counter can get + * reset, e.g. when suspending. + * + * This is the legacy version of drm_crtc_vblank_off(). */ void drm_vblank_off(struct drm_device *dev, int crtc) { @@ -977,6 +1043,66 @@ void drm_vblank_off(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_off); +/** + * drm_crtc_vblank_off - disable vblank events on a CRTC + * @crtc: CRTC in question + * + * Drivers can use this function to shut down the vblank interrupt handling when + * disabling a crtc. This function ensures that the latest vblank frame count is + * stored so that drm_vblank_on can restore it again. + * + * Drivers must use this function when the hardware vblank counter can get + * reset, e.g. when suspending. + * + * This is the native kms version of drm_vblank_off(). + */ +void drm_crtc_vblank_off(struct drm_crtc *crtc) +{ + drm_vblank_off(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_off); + +/** + * drm_vblank_on - enable vblank events on a CRTC + * @dev: DRM device + * @crtc: CRTC in question + * + * This functions restores the vblank interrupt state captured with + * drm_vblank_off() again. Note that calls to drm_vblank_on() and + * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * in driver load code to reflect the current hardware state of the crtc. + * + * This is the legacy version of drm_crtc_vblank_on(). + */ +void drm_vblank_on(struct drm_device *dev, int crtc) +{ + unsigned long irqflags; + + spin_lock_irqsave(&dev->vbl_lock, irqflags); + /* re-enable interrupts if there's are users left */ + if (atomic_read(&dev->vblank[crtc].refcount) != 0) + WARN_ON(drm_vblank_enable(dev, crtc)); + spin_unlock_irqrestore(&dev->vbl_lock, irqflags); +} +EXPORT_SYMBOL(drm_vblank_on); + +/** + * drm_crtc_vblank_on - enable vblank events on a CRTC + * @crtc: CRTC in question + * + * This functions restores the vblank interrupt state captured with + * drm_vblank_off() again. Note that calls to drm_vblank_on() and + * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * in driver load code to reflect the current hardware state of the crtc. + * + * This is the native kms version of drm_vblank_on(). + */ +void drm_crtc_vblank_on(struct drm_crtc *crtc) +{ + drm_vblank_on(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_on); + /** * drm_vblank_pre_modeset - account for vblanks across mode sets * @dev: DRM device @@ -984,6 +1110,21 @@ EXPORT_SYMBOL(drm_vblank_off); * * Account for vblank events across mode setting events, which will likely * reset the hardware frame counter. + * + * This is done by grabbing a temporary vblank reference to ensure that the + * vblank interrupt keeps running across the modeset sequence. With this the + * software-side vblank frame counting will ensure that there are no jumps or + * discontinuities. + * + * Unfortunately this approach is racy and also doesn't work when the vblank + * interrupt stops running, e.g. across system suspend resume. It is therefore + * highly recommended that drivers use the newer drm_vblank_off() and + * drm_vblank_on() instead. drm_vblank_pre_modeset() only works correctly when + * using "cooked" software vblank frame counters and not relying on any hardware + * counters. + * + * Drivers must call drm_vblank_post_modeset() when re-enabling the same crtc + * again. */ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc) { @@ -1005,6 +1146,14 @@ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_pre_modeset); +/** + * drm_vblank_post_modeset - undo drm_vblank_pre_modeset changes + * @dev: DRM device + * @crtc: CRTC in question + * + * This function again drops the temporary vblank reference acquired in + * drm_vblank_pre_modeset. + */ void drm_vblank_post_modeset(struct drm_device *dev, int crtc) { unsigned long irqflags; @@ -1026,7 +1175,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_post_modeset); -/** +/* * drm_modeset_ctl - handle vblank event counter changes across mode switch * @DRM_IOCTL_ARGS: standard ioctl arguments * @@ -1139,7 +1288,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe, return ret; } -/** +/* * Wait for VBLANK. * * \param inode device inode. @@ -1150,7 +1299,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe, * * This function enables the vblank interrupt on the pipe requested, then * sleeps waiting for the requested sequence number to occur, and drops - * the vblank interrupt refcount afterwards. (vblank irq disable follows that + * the vblank interrupt refcount afterwards. (vblank IRQ disable follows that * after a timeout with no further vblank waits scheduled). */ int drm_wait_vblank(struct drm_device *dev, void *data, @@ -1160,9 +1309,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data, int ret; unsigned int flags, seq, crtc, high_crtc; - if (drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) - if ((!drm_dev_to_irq(dev)) || (!dev->irq_enabled)) - return -EINVAL; + if (!dev->irq_enabled) + return -EINVAL; if (vblwait->request.type & _DRM_VBLANK_SIGNAL) return -EINVAL; @@ -1222,6 +1370,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data, DRM_WAIT_ON(ret, dev->vblank[crtc].queue, 3 * HZ, (((drm_vblank_count(dev, crtc) - vblwait->request.sequence) <= (1 << 23)) || + !dev->vblank[crtc].enabled || !dev->irq_enabled)); if (ret != -EINTR) { diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 09821f46d768..e633df2f68d8 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -282,6 +282,14 @@ static int mipi_dsi_drv_remove(struct device *dev) return drv->remove(dsi); } +static void mipi_dsi_drv_shutdown(struct device *dev) +{ + struct mipi_dsi_driver *drv = to_mipi_dsi_driver(dev->driver); + struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); + + drv->shutdown(dsi); +} + /** * mipi_dsi_driver_register - register a driver for DSI devices * @drv: DSI driver structure @@ -293,6 +301,8 @@ int mipi_dsi_driver_register(struct mipi_dsi_driver *drv) drv->driver.probe = mipi_dsi_drv_probe; if (drv->remove) drv->driver.remove = mipi_dsi_drv_remove; + if (drv->shutdown) + drv->driver.shutdown = mipi_dsi_drv_shutdown; return driver_register(&drv->driver); } diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 8b410576fce4..bedf1894e17e 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1013,6 +1013,7 @@ EXPORT_SYMBOL(drm_mode_sort); /** * drm_mode_connector_list_update - update the mode list for the connector * @connector: the connector to update + * @merge_type_bits: whether to merge or overright type bits. * * This moves the modes from the @connector probed_modes list * to the actual mode list. It compares the probed mode against the current @@ -1021,7 +1022,8 @@ EXPORT_SYMBOL(drm_mode_sort); * This is just a helper functions doesn't validate any modes itself and also * doesn't prune any invalid modes. Callers need to do that themselves. */ -void drm_mode_connector_list_update(struct drm_connector *connector) +void drm_mode_connector_list_update(struct drm_connector *connector, + bool merge_type_bits) { struct drm_display_mode *mode; struct drm_display_mode *pmode, *pt; @@ -1039,7 +1041,10 @@ void drm_mode_connector_list_update(struct drm_connector *connector) /* if equal delete the probed mode */ mode->status = pmode->status; /* Merge type bits together */ - mode->type |= pmode->type; + if (merge_type_bits) + mode->type |= pmode->type; + else + mode->type = pmode->type; list_del(&pmode->head); drm_mode_destroy(connector->dev, pmode); break; diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c new file mode 100644 index 000000000000..7c2497dea1e9 --- /dev/null +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -0,0 +1,247 @@ +/* + * Copyright (C) 2014 Red Hat + * Author: Rob Clark + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include +#include +#include + +/** + * DOC: kms locking + * + * As KMS moves toward more fine grained locking, and atomic ioctl where + * userspace can indirectly control locking order, it becomes necessary + * to use ww_mutex and acquire-contexts to avoid deadlocks. But because + * the locking is more distributed around the driver code, we want a bit + * of extra utility/tracking out of our acquire-ctx. This is provided + * by drm_modeset_lock / drm_modeset_acquire_ctx. + * + * For basic principles of ww_mutex, see: Documentation/ww-mutex-design.txt + * + * The basic usage pattern is to: + * + * drm_modeset_acquire_init(&ctx) + * retry: + * foreach (lock in random_ordered_set_of_locks) { + * ret = drm_modeset_lock(lock, &ctx) + * if (ret == -EDEADLK) { + * drm_modeset_backoff(&ctx); + * goto retry; + * } + * } + * + * ... do stuff ... + * + * drm_modeset_drop_locks(&ctx); + * drm_modeset_acquire_fini(&ctx); + */ + + +/** + * drm_modeset_acquire_init - initialize acquire context + * @ctx: the acquire context + * @flags: for future + */ +void drm_modeset_acquire_init(struct drm_modeset_acquire_ctx *ctx, + uint32_t flags) +{ + ww_acquire_init(&ctx->ww_ctx, &crtc_ww_class); + INIT_LIST_HEAD(&ctx->locked); +} +EXPORT_SYMBOL(drm_modeset_acquire_init); + +/** + * drm_modeset_acquire_fini - cleanup acquire context + * @ctx: the acquire context + */ +void drm_modeset_acquire_fini(struct drm_modeset_acquire_ctx *ctx) +{ + ww_acquire_fini(&ctx->ww_ctx); +} +EXPORT_SYMBOL(drm_modeset_acquire_fini); + +/** + * drm_modeset_drop_locks - drop all locks + * @ctx: the acquire context + * + * Drop all locks currently held against this acquire context. + */ +void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx) +{ + WARN_ON(ctx->contended); + while (!list_empty(&ctx->locked)) { + struct drm_modeset_lock *lock; + + lock = list_first_entry(&ctx->locked, + struct drm_modeset_lock, head); + + drm_modeset_unlock(lock); + } +} +EXPORT_SYMBOL(drm_modeset_drop_locks); + +static inline int modeset_lock(struct drm_modeset_lock *lock, + struct drm_modeset_acquire_ctx *ctx, + bool interruptible, bool slow) +{ + int ret; + + WARN_ON(ctx->contended); + + if (interruptible && slow) { + ret = ww_mutex_lock_slow_interruptible(&lock->mutex, &ctx->ww_ctx); + } else if (interruptible) { + ret = ww_mutex_lock_interruptible(&lock->mutex, &ctx->ww_ctx); + } else if (slow) { + ww_mutex_lock_slow(&lock->mutex, &ctx->ww_ctx); + ret = 0; + } else { + ret = ww_mutex_lock(&lock->mutex, &ctx->ww_ctx); + } + if (!ret) { + WARN_ON(!list_empty(&lock->head)); + list_add(&lock->head, &ctx->locked); + } else if (ret == -EALREADY) { + /* we already hold the lock.. this is fine. For atomic + * we will need to be able to drm_modeset_lock() things + * without having to keep track of what is already locked + * or not. + */ + ret = 0; + } else if (ret == -EDEADLK) { + ctx->contended = lock; + } + + return ret; +} + +static int modeset_backoff(struct drm_modeset_acquire_ctx *ctx, + bool interruptible) +{ + struct drm_modeset_lock *contended = ctx->contended; + + ctx->contended = NULL; + + if (WARN_ON(!contended)) + return 0; + + drm_modeset_drop_locks(ctx); + + return modeset_lock(contended, ctx, interruptible, true); +} + +/** + * drm_modeset_backoff - deadlock avoidance backoff + * @ctx: the acquire context + * + * If deadlock is detected (ie. drm_modeset_lock() returns -EDEADLK), + * you must call this function to drop all currently held locks and + * block until the contended lock becomes available. + */ +void drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx) +{ + modeset_backoff(ctx, false); +} +EXPORT_SYMBOL(drm_modeset_backoff); + +/** + * drm_modeset_backoff_interruptible - deadlock avoidance backoff + * @ctx: the acquire context + * + * Interruptible version of drm_modeset_backoff() + */ +int drm_modeset_backoff_interruptible(struct drm_modeset_acquire_ctx *ctx) +{ + return modeset_backoff(ctx, true); +} +EXPORT_SYMBOL(drm_modeset_backoff_interruptible); + +/** + * drm_modeset_lock - take modeset lock + * @lock: lock to take + * @ctx: acquire ctx + * + * If ctx is not NULL, then its ww acquire context is used and the + * lock will be tracked by the context and can be released by calling + * drm_modeset_drop_locks(). If -EDEADLK is returned, this means a + * deadlock scenario has been detected and it is an error to attempt + * to take any more locks without first calling drm_modeset_backoff(). + */ +int drm_modeset_lock(struct drm_modeset_lock *lock, + struct drm_modeset_acquire_ctx *ctx) +{ + if (ctx) + return modeset_lock(lock, ctx, false, false); + + ww_mutex_lock(&lock->mutex, NULL); + return 0; +} +EXPORT_SYMBOL(drm_modeset_lock); + +/** + * drm_modeset_lock_interruptible - take modeset lock + * @lock: lock to take + * @ctx: acquire ctx + * + * Interruptible version of drm_modeset_lock() + */ +int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock, + struct drm_modeset_acquire_ctx *ctx) +{ + if (ctx) + return modeset_lock(lock, ctx, true, false); + + return ww_mutex_lock_interruptible(&lock->mutex, NULL); +} +EXPORT_SYMBOL(drm_modeset_lock_interruptible); + +/** + * drm_modeset_unlock - drop modeset lock + * @lock: lock to release + */ +void drm_modeset_unlock(struct drm_modeset_lock *lock) +{ + list_del_init(&lock->head); + ww_mutex_unlock(&lock->mutex); +} +EXPORT_SYMBOL(drm_modeset_unlock); + +/* Temporary.. until we have sufficiently fine grained locking, there + * are a couple scenarios where it is convenient to grab all crtc locks. + * It is planned to remove this: + */ +int drm_modeset_lock_all_crtcs(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx) +{ + struct drm_mode_config *config = &dev->mode_config; + struct drm_crtc *crtc; + int ret = 0; + + list_for_each_entry(crtc, &config->crtc_list, head) { + ret = drm_modeset_lock(&crtc->mutex, ctx); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL(drm_modeset_lock_all_crtcs); diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 9c696a5ad74d..020cfd934854 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -1,17 +1,3 @@ -/* drm_pci.h -- PCI DMA memory management wrappers for DRM -*- linux-c -*- */ -/** - * \file drm_pci.c - * \brief Functions and ioctls to manage PCI memory - * - * \warning These interfaces aren't stable yet. - * - * \todo Implement the remaining ioctl's for the PCI pools. - * \todo The wrappers here are so thin that they would be better off inlined.. - * - * \author José Fonseca - * \author Leif Delgass - */ - /* * Copyright 2003 José Fonseca. * Copyright 2003 Leif Delgass. @@ -42,12 +28,14 @@ #include #include -/**********************************************************************/ -/** \name PCI memory */ -/*@{*/ - /** - * \brief Allocate a PCI consistent memory block, for DMA. + * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA. + * @dev: DRM device + * @size: size of block to allocate + * @align: alignment of block + * + * Return: A handle to the allocated memory block on success or NULL on + * failure. */ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align) { @@ -88,8 +76,8 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali EXPORT_SYMBOL(drm_pci_alloc); -/** - * \brief Free a PCI consistent memory block without freeing its descriptor. +/* + * Free a PCI consistent memory block without freeing its descriptor. * * This function is for internal use in the Linux-specific DRM core code. */ @@ -111,7 +99,9 @@ void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah) } /** - * \brief Free a PCI consistent memory block + * drm_pci_free - Free a PCI consistent memory block + * @dev: DRM device + * @dmah: handle to memory block */ void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah) { @@ -137,21 +127,9 @@ static int drm_get_pci_domain(struct drm_device *dev) return pci_domain_nr(dev->pdev->bus); } -static int drm_pci_get_irq(struct drm_device *dev) -{ - return dev->pdev->irq; -} - -static const char *drm_pci_get_name(struct drm_device *dev) -{ - struct pci_driver *pdriver = dev->driver->kdriver.pci; - return pdriver->name; -} - static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master) { int len, ret; - struct pci_driver *pdriver = dev->driver->kdriver.pci; master->unique_len = 40; master->unique_size = master->unique_len; master->unique = kmalloc(master->unique_size, GFP_KERNEL); @@ -173,29 +151,16 @@ static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master) } else master->unique_len = len; - dev->devname = - kmalloc(strlen(pdriver->name) + - master->unique_len + 2, GFP_KERNEL); - - if (dev->devname == NULL) { - ret = -ENOMEM; - goto err; - } - - sprintf(dev->devname, "%s@%s", pdriver->name, - master->unique); - return 0; err: return ret; } -static int drm_pci_set_unique(struct drm_device *dev, - struct drm_master *master, - struct drm_unique *u) +int drm_pci_set_unique(struct drm_device *dev, + struct drm_master *master, + struct drm_unique *u) { int domain, bus, slot, func, ret; - const char *bus_name; master->unique_len = u->unique_len; master->unique_size = u->unique_len + 1; @@ -212,17 +177,6 @@ static int drm_pci_set_unique(struct drm_device *dev, master->unique[master->unique_len] = '\0'; - bus_name = dev->driver->bus->get_name(dev); - dev->devname = kmalloc(strlen(bus_name) + - strlen(master->unique) + 2, GFP_KERNEL); - if (!dev->devname) { - ret = -ENOMEM; - goto err; - } - - sprintf(dev->devname, "%s@%s", bus_name, - master->unique); - /* Return error if the busid submitted doesn't match the device's actual * busid. */ @@ -247,7 +201,6 @@ static int drm_pci_set_unique(struct drm_device *dev, return ret; } - static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p) { if ((p->busnum >> 8) != drm_get_pci_domain(dev) || @@ -262,6 +215,36 @@ static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p) return 0; } +/** + * drm_irq_by_busid - Get interrupt from bus ID + * @dev: DRM device + * @data: IOCTL parameter pointing to a drm_irq_busid structure + * @file_priv: DRM file private. + * + * Finds the PCI device with the specified bus id and gets its IRQ number. + * This IOCTL is deprecated, and will now return EINVAL for any busid not equal + * to that of the device that this DRM instance attached to. + * + * Return: 0 on success or a negative error code on failure. + */ +int drm_irq_by_busid(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_irq_busid *p = data; + + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return -EINVAL; + + /* UMS was only ever support on PCI devices. */ + if (WARN_ON(!dev->pdev)) + return -EINVAL; + + if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) + return -EINVAL; + + return drm_pci_irq_by_busid(dev, p); +} + static void drm_pci_agp_init(struct drm_device *dev) { if (drm_core_check_feature(dev, DRIVER_USE_AGP)) { @@ -287,24 +270,20 @@ void drm_pci_agp_destroy(struct drm_device *dev) } static struct drm_bus drm_pci_bus = { - .bus_type = DRIVER_BUS_PCI, - .get_irq = drm_pci_get_irq, - .get_name = drm_pci_get_name, .set_busid = drm_pci_set_busid, - .set_unique = drm_pci_set_unique, - .irq_by_busid = drm_pci_irq_by_busid, }; /** - * Register. - * - * \param pdev - PCI device structure - * \param ent entry from the PCI ID table with device type flags - * \return zero on success or a negative number on failure. + * drm_get_pci_dev - Register a PCI device with the DRM subsystem + * @pdev: PCI device + * @ent: entry from the PCI ID table that matches @pdev + * @driver: DRM device driver * * Attempt to gets inter module "drm" information. If we are first * then register the character device and inter module information. * Try and register, if we fail to register, backout previous work. + * + * Return: 0 on success or a negative error code on failure. */ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent, struct drm_driver *driver) @@ -357,15 +336,14 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent, EXPORT_SYMBOL(drm_get_pci_dev); /** - * PCI device initialization. Called direct from modules at load time. + * drm_pci_init - Register matching PCI devices with the DRM subsystem + * @driver: DRM device driver + * @pdriver: PCI device driver * - * \return zero on success or a negative number on failure. + * Initializes a drm_device structures, registering the stubs and initializing + * the AGP device. * - * Initializes a drm_device structures,registering the - * stubs and initializing the AGP device. - * - * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and - * after the initialization for driver customization. + * Return: 0 on success or a negative error code on failure. */ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) { @@ -375,7 +353,6 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) DRM_DEBUG("\n"); - driver->kdriver.pci = pdriver; driver->bus = &drm_pci_bus; if (driver->driver_features & DRIVER_MODESET) @@ -453,11 +430,31 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) } void drm_pci_agp_destroy(struct drm_device *dev) {} + +int drm_irq_by_busid(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + return -EINVAL; +} + +int drm_pci_set_unique(struct drm_device *dev, + struct drm_master *master, + struct drm_unique *u) +{ + return -EINVAL; +} #endif EXPORT_SYMBOL(drm_pci_init); -/*@}*/ +/** + * drm_pci_exit - Unregister matching PCI devices from the DRM subsystem + * @driver: DRM device driver + * @pdriver: PCI device driver + * + * Unregisters one or more devices matched by a PCI driver from the DRM + * subsystem. + */ void drm_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver) { struct drm_device *dev, *tmp; diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index d2b1c03b3d71..6d133149cc74 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -25,7 +25,9 @@ #include #include +#include #include +#include #define SUBPIXEL_MASK 0xffff @@ -36,9 +38,9 @@ * creating the primary plane. However drivers that still call * drm_plane_init() will use this minimal format list as the default. */ -const static uint32_t safe_modeset_formats[] = { - DRM_FORMAT_XRGB8888, - DRM_FORMAT_ARGB8888, +static const uint32_t safe_modeset_formats[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, }; /* @@ -54,6 +56,13 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc, struct drm_connector *connector; int count = 0; + /* + * Note: Once we change the plane hooks to more fine-grained locking we + * need to grab the connection_mutex here to be able to make these + * checks. + */ + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + list_for_each_entry(connector, &dev->mode_config.connector_list, head) if (connector->encoder && connector->encoder->crtc == crtc) { if (connector_list != NULL && count < num_connectors) @@ -65,6 +74,79 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc, return count; } +/** + * drm_plane_helper_check_update() - Check plane update for validity + * @plane: plane object to update + * @crtc: owning CRTC of owning plane + * @fb: framebuffer to flip onto plane + * @src: source coordinates in 16.16 fixed point + * @dest: integer destination coordinates + * @clip: integer clipping coordinates + * @min_scale: minimum @src:@dest scaling factor in 16.16 fixed point + * @max_scale: maximum @src:@dest scaling factor in 16.16 fixed point + * @can_position: is it legal to position the plane such that it + * doesn't cover the entire crtc? This will generally + * only be false for primary planes. + * @can_update_disabled: can the plane be updated while the crtc + * is disabled? + * @visible: output parameter indicating whether plane is still visible after + * clipping + * + * Checks that a desired plane update is valid. Drivers that provide + * their own plane handling rather than helper-provided implementations may + * still wish to call this function to avoid duplication of error checking + * code. + * + * RETURNS: + * Zero if update appears valid, error code on failure + */ +int drm_plane_helper_check_update(struct drm_plane *plane, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_rect *src, + struct drm_rect *dest, + const struct drm_rect *clip, + int min_scale, + int max_scale, + bool can_position, + bool can_update_disabled, + bool *visible) +{ + int hscale, vscale; + + if (!crtc->enabled && !can_update_disabled) { + DRM_DEBUG_KMS("Cannot update plane of a disabled CRTC.\n"); + return -EINVAL; + } + + /* Check scaling */ + hscale = drm_rect_calc_hscale(src, dest, min_scale, max_scale); + vscale = drm_rect_calc_vscale(src, dest, min_scale, max_scale); + if (hscale < 0 || vscale < 0) { + DRM_DEBUG_KMS("Invalid scaling of plane\n"); + return -ERANGE; + } + + *visible = drm_rect_clip_scaled(src, dest, clip, hscale, vscale); + if (!*visible) + /* + * Plane isn't visible; some drivers can handle this + * so we just return success here. Drivers that can't + * (including those that use the primary plane helper's + * update function) will return an error from their + * update_plane handler. + */ + return 0; + + if (!can_position && !drm_rect_equals(dest, clip)) { + DRM_DEBUG_KMS("Plane must cover entire CRTC\n"); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(drm_plane_helper_check_update); + /** * drm_primary_helper_update() - Helper for primary plane update * @plane: plane object to update @@ -113,56 +195,42 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc, .x = src_x >> 16, .y = src_y >> 16, }; + struct drm_rect src = { + .x1 = src_x, + .y1 = src_y, + .x2 = src_x + src_w, + .y2 = src_y + src_h, + }; struct drm_rect dest = { .x1 = crtc_x, .y1 = crtc_y, .x2 = crtc_x + crtc_w, .y2 = crtc_y + crtc_h, }; - struct drm_rect clip = { + const struct drm_rect clip = { .x2 = crtc->mode.hdisplay, .y2 = crtc->mode.vdisplay, }; struct drm_connector **connector_list; - struct drm_framebuffer *tmpfb; int num_connectors, ret; + bool visible; - if (!crtc->enabled) { - DRM_DEBUG_KMS("Cannot update primary plane of a disabled CRTC.\n"); - return -EINVAL; - } - - /* Disallow subpixel positioning */ - if ((src_x | src_y | src_w | src_h) & SUBPIXEL_MASK) { - DRM_DEBUG_KMS("Primary plane does not support subpixel positioning\n"); - return -EINVAL; - } - - /* Primary planes are locked to their owning CRTC */ - if (plane->possible_crtcs != drm_crtc_mask(crtc)) { - DRM_DEBUG_KMS("Cannot change primary plane CRTC\n"); - return -EINVAL; - } - - /* Disallow scaling */ - if (crtc_w != src_w || crtc_h != src_h) { - DRM_DEBUG_KMS("Can't scale primary plane\n"); - return -EINVAL; - } - - /* Make sure primary plane covers entire CRTC */ - drm_rect_intersect(&dest, &clip); - if (dest.x1 != 0 || dest.y1 != 0 || - dest.x2 != crtc->mode.hdisplay || dest.y2 != crtc->mode.vdisplay) { - DRM_DEBUG_KMS("Primary plane must cover entire CRTC\n"); - return -EINVAL; - } - - /* Framebuffer must be big enough to cover entire plane */ - ret = drm_crtc_check_viewport(crtc, crtc_x, crtc_y, &crtc->mode, fb); + ret = drm_plane_helper_check_update(plane, crtc, fb, + &src, &dest, &clip, + DRM_PLANE_HELPER_NO_SCALING, + DRM_PLANE_HELPER_NO_SCALING, + false, false, &visible); if (ret) return ret; + if (!visible) + /* + * Primary plane isn't visible. Note that unless a driver + * provides their own disable function, this will just + * wind up returning -EINVAL to userspace. + */ + return plane->funcs->disable_plane(plane); + /* Find current connectors for CRTC */ num_connectors = get_connectors_for_crtc(crtc, NULL, 0); BUG_ON(num_connectors == 0); @@ -176,21 +244,14 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc, set.num_connectors = num_connectors; /* - * set_config() adjusts crtc->primary->fb; however the DRM setplane - * code that called us expects to handle the framebuffer update and - * reference counting; save and restore the current fb before - * calling it. - * - * N.B., we call set_config() directly here rather than using + * We call set_config() directly here rather than using * drm_mode_set_config_internal. We're reprogramming the same * connectors that were already in use, so we shouldn't need the extra * cross-CRTC fb refcounting to accomodate stealing connectors. * drm_mode_setplane() already handles the basic refcounting for the * framebuffers involved in this operation. */ - tmpfb = plane->fb; ret = crtc->funcs->set_config(&set); - plane->fb = tmpfb; kfree(connector_list); return ret; @@ -232,7 +293,6 @@ EXPORT_SYMBOL(drm_primary_helper_disable); */ void drm_primary_helper_destroy(struct drm_plane *plane) { - plane->funcs->disable_plane(plane); drm_plane_cleanup(plane); kfree(plane); } diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c index 319ff5385601..d5b76f148c12 100644 --- a/drivers/gpu/drm/drm_platform.c +++ b/drivers/gpu/drm/drm_platform.c @@ -68,16 +68,6 @@ static int drm_get_platform_dev(struct platform_device *platdev, return ret; } -static int drm_platform_get_irq(struct drm_device *dev) -{ - return platform_get_irq(dev->platformdev, 0); -} - -static const char *drm_platform_get_name(struct drm_device *dev) -{ - return dev->platformdev->name; -} - static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master) { int len, ret, id; @@ -106,46 +96,30 @@ static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *mas goto err; } - dev->devname = - kmalloc(strlen(dev->platformdev->name) + - master->unique_len + 2, GFP_KERNEL); - - if (dev->devname == NULL) { - ret = -ENOMEM; - goto err; - } - - sprintf(dev->devname, "%s@%s", dev->platformdev->name, - master->unique); return 0; err: return ret; } static struct drm_bus drm_platform_bus = { - .bus_type = DRIVER_BUS_PLATFORM, - .get_irq = drm_platform_get_irq, - .get_name = drm_platform_get_name, .set_busid = drm_platform_set_busid, }; /** - * Platform device initialization. Called direct from modules. + * drm_platform_init - Register a platform device with the DRM subsystem + * @driver: DRM device driver + * @platform_device: platform device to register * - * \return zero on success or a negative number on failure. + * Registers the specified DRM device driver and platform device with the DRM + * subsystem, initializing a drm_device structure and calling the driver's + * .load() function. * - * Initializes a drm_device structures,registering the - * stubs - * - * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and - * after the initialization for driver customization. + * Return: 0 on success or a negative error code on failure. */ - int drm_platform_init(struct drm_driver *driver, struct platform_device *platform_device) { DRM_DEBUG("\n"); - driver->kdriver.platform_device = platform_device; driver->bus = &drm_platform_bus; return drm_get_platform_dev(platform_device, driver); } diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index e70f54d4a581..d22676b89cbb 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -82,26 +82,8 @@ static void drm_mode_validate_flag(struct drm_connector *connector, return; } -/** - * drm_helper_probe_single_connector_modes - get complete set of display modes - * @connector: connector to probe - * @maxX: max width for modes - * @maxY: max height for modes - * - * Based on the helper callbacks implemented by @connector try to detect all - * valid modes. Modes will first be added to the connector's probed_modes list, - * then culled (based on validity and the @maxX, @maxY parameters) and put into - * the normal modes list. - * - * Intended to be use as a generic implementation of the ->fill_modes() - * @connector vfunc for drivers that use the crtc helpers for output mode - * filtering and detection. - * - * Returns: - * The number of modes found on @connector. - */ -int drm_helper_probe_single_connector_modes(struct drm_connector *connector, - uint32_t maxX, uint32_t maxY) +static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector, + uint32_t maxX, uint32_t maxY, bool merge_type_bits) { struct drm_device *dev = connector->dev; struct drm_display_mode *mode; @@ -114,7 +96,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, - drm_get_connector_name(connector)); + connector->name); /* set all modes to the unverified state */ list_for_each_entry(mode, &connector->modes, head) mode->status = MODE_UNVERIFIED; @@ -138,7 +120,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, if (connector->status == connector_status_disconnected) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); drm_mode_connector_update_edid_property(connector, NULL); verbose_prune = false; goto prune; @@ -155,7 +137,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, if (count == 0) goto prune; - drm_mode_connector_list_update(connector); + drm_mode_connector_list_update(connector, merge_type_bits); if (maxX && maxY) drm_mode_validate_size(dev, &connector->modes, maxX, maxY); @@ -169,7 +151,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, drm_mode_validate_flag(connector, mode_flags); list_for_each_entry(mode, &connector->modes, head) { - if (mode->status == MODE_OK) + if (mode->status == MODE_OK && connector_funcs->mode_valid) mode->status = connector_funcs->mode_valid(connector, mode); } @@ -186,7 +168,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, drm_mode_sort(&connector->modes); DRM_DEBUG_KMS("[CONNECTOR:%d:%s] probed modes :\n", connector->base.id, - drm_get_connector_name(connector)); + connector->name); list_for_each_entry(mode, &connector->modes, head) { drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); drm_mode_debug_printmodeline(mode); @@ -194,8 +176,48 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, return count; } + +/** + * drm_helper_probe_single_connector_modes - get complete set of display modes + * @connector: connector to probe + * @maxX: max width for modes + * @maxY: max height for modes + * + * Based on the helper callbacks implemented by @connector try to detect all + * valid modes. Modes will first be added to the connector's probed_modes list, + * then culled (based on validity and the @maxX, @maxY parameters) and put into + * the normal modes list. + * + * Intended to be use as a generic implementation of the ->fill_modes() + * @connector vfunc for drivers that use the crtc helpers for output mode + * filtering and detection. + * + * Returns: + * The number of modes found on @connector. + */ +int drm_helper_probe_single_connector_modes(struct drm_connector *connector, + uint32_t maxX, uint32_t maxY) +{ + return drm_helper_probe_single_connector_modes_merge_bits(connector, maxX, maxY, true); +} EXPORT_SYMBOL(drm_helper_probe_single_connector_modes); +/** + * drm_helper_probe_single_connector_modes_nomerge - get complete set of display modes + * @connector: connector to probe + * @maxX: max width for modes + * @maxY: max height for modes + * + * This operates like drm_hehlper_probe_single_connector_modes except it + * replaces the mode bits instead of merging them for preferred modes. + */ +int drm_helper_probe_single_connector_modes_nomerge(struct drm_connector *connector, + uint32_t maxX, uint32_t maxY) +{ + return drm_helper_probe_single_connector_modes_merge_bits(connector, maxX, maxY, false); +} +EXPORT_SYMBOL(drm_helper_probe_single_connector_modes_nomerge); + /** * drm_kms_helper_hotplug_event - fire off KMS hotplug events * @dev: drm_device whose connector state changed @@ -264,7 +286,7 @@ static void output_poll_execute(struct work_struct *work) DRM_DEBUG_KMS("[CONNECTOR:%d:%s] " "status updated from %s to %s\n", connector->base.id, - drm_get_connector_name(connector), + connector->name, old, new); changed = true; @@ -409,7 +431,7 @@ bool drm_helper_hpd_irq_event(struct drm_device *dev) connector->status = connector->funcs->detect(connector, false); DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n", connector->base.id, - drm_get_connector_name(connector), + connector->name, drm_get_connector_status_name(old_status), drm_get_connector_status_name(connector->status)); if (old_status != connector->status) diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index 4c24c3ac1efa..14d16464000a 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -1,16 +1,11 @@ -/** - * \file drm_stub.h - * Stub support - * - * \author Rickard E. (Rik) Faith - */ - /* * Created: Fri Jan 19 10:48:35 2001 by faith@acm.org * * Copyright 2001 VA Linux Systems, Inc., Sunnyvale, California. * All Rights Reserved. * + * Author Rickard E. (Rik) Faith + * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation @@ -128,7 +123,10 @@ struct drm_master *drm_master_create(struct drm_minor *minor) kref_init(&master->refcount); spin_lock_init(&master->lock.spinlock); init_waitqueue_head(&master->lock.lock_queue); - drm_ht_create(&master->magiclist, DRM_MAGIC_HASH_ORDER); + if (drm_ht_create(&master->magiclist, DRM_MAGIC_HASH_ORDER)) { + kfree(master); + return NULL; + } INIT_LIST_HEAD(&master->magicfree); master->minor = minor; @@ -166,9 +164,6 @@ static void drm_master_destroy(struct kref *kref) master->unique_len = 0; } - kfree(dev->devname); - dev->devname = NULL; - list_for_each_entry_safe(pt, next, &master->magicfree, head) { list_del(&pt->head); drm_ht_remove_item(&master->magiclist, &pt->hash_item); @@ -294,6 +289,7 @@ static void drm_minor_free(struct drm_device *dev, unsigned int type) slot = drm_minor_get_slot(dev, type); if (*slot) { + drm_mode_group_destroy(&(*slot)->mode_group); kfree(*slot); *slot = NULL; } @@ -424,11 +420,15 @@ void drm_minor_release(struct drm_minor *minor) } /** - * Called via drm_exit() at module unload time or when pci device is - * unplugged. + * drm_put_dev - Unregister and release a DRM device + * @dev: DRM device + * + * Called at module unload time or when a PCI device is unplugged. + * + * Use of this function is discouraged. It will eventually go away completely. + * Please use drm_dev_unregister() and drm_dev_unref() explicitly instead. * * Cleans up all DRM device, calling drm_lastclose(). - * */ void drm_put_dev(struct drm_device *dev) { @@ -535,7 +535,7 @@ static void drm_fs_inode_free(struct inode *inode) } /** - * drm_dev_alloc - Allocate new drm device + * drm_dev_alloc - Allocate new DRM device * @driver: DRM driver to allocate device for * @parent: Parent device object * @@ -569,7 +569,7 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver, INIT_LIST_HEAD(&dev->maplist); INIT_LIST_HEAD(&dev->vblank_event_list); - spin_lock_init(&dev->count_lock); + spin_lock_init(&dev->buf_lock); spin_lock_init(&dev->event_lock); mutex_init(&dev->struct_mutex); mutex_init(&dev->ctxlist_mutex); @@ -648,9 +648,8 @@ static void drm_dev_release(struct kref *ref) drm_minor_free(dev, DRM_MINOR_RENDER); drm_minor_free(dev, DRM_MINOR_CONTROL); - kfree(dev->devname); - mutex_destroy(&dev->master_mutex); + kfree(dev->unique); kfree(dev); } @@ -690,6 +689,7 @@ EXPORT_SYMBOL(drm_dev_unref); /** * drm_dev_register - Register DRM device * @dev: Device to register + * @flags: Flags passed to the driver's .load() function * * Register the DRM device @dev with the system, advertise device to user-space * and start normal device operation. @dev must be allocated via drm_dev_alloc() @@ -778,3 +778,28 @@ void drm_dev_unregister(struct drm_device *dev) drm_minor_unregister(dev, DRM_MINOR_CONTROL); } EXPORT_SYMBOL(drm_dev_unregister); + +/** + * drm_dev_set_unique - Set the unique name of a DRM device + * @dev: device of which to set the unique name + * @fmt: format string for unique name + * + * Sets the unique name of a DRM device using the specified format string and + * a variable list of arguments. Drivers can use this at driver probe time if + * the unique name of the devices they drive is static. + * + * Return: 0 on success or a negative error code on failure. + */ +int drm_dev_set_unique(struct drm_device *dev, const char *fmt, ...) +{ + va_list ap; + + kfree(dev->unique); + + va_start(ap, fmt); + dev->unique = kvasprintf(GFP_KERNEL, fmt, ap); + va_end(ap); + + return dev->unique ? 0 : -ENOMEM; +} +EXPORT_SYMBOL(drm_dev_set_unique); diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index c22c3097c3e8..369b26278e76 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -380,9 +380,9 @@ int drm_sysfs_connector_add(struct drm_connector *connector) connector->kdev = device_create(drm_class, dev->primary->kdev, 0, connector, "card%d-%s", - dev->primary->index, drm_get_connector_name(connector)); + dev->primary->index, connector->name); DRM_DEBUG("adding \"%s\" to sysfs\n", - drm_get_connector_name(connector)); + connector->name); if (IS_ERR(connector->kdev)) { DRM_ERROR("failed to register connector device: %ld\n", PTR_ERR(connector->kdev)); @@ -460,7 +460,7 @@ void drm_sysfs_connector_remove(struct drm_connector *connector) if (!connector->kdev) return; DRM_DEBUG("removing \"%s\" from sysfs\n", - drm_get_connector_name(connector)); + connector->name); for (i = 0; i < ARRAY_SIZE(connector_attrs); i++) device_remove_file(connector->kdev, &connector_attrs[i]); diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c index c3406aad2944..f2fe94aab901 100644 --- a/drivers/gpu/drm/drm_usb.c +++ b/drivers/gpu/drm/drm_usb.c @@ -36,16 +36,6 @@ int drm_get_usb_dev(struct usb_interface *interface, } EXPORT_SYMBOL(drm_get_usb_dev); -static int drm_usb_get_irq(struct drm_device *dev) -{ - return 0; -} - -static const char *drm_usb_get_name(struct drm_device *dev) -{ - return "USB"; -} - static int drm_usb_set_busid(struct drm_device *dev, struct drm_master *master) { @@ -53,18 +43,24 @@ static int drm_usb_set_busid(struct drm_device *dev, } static struct drm_bus drm_usb_bus = { - .bus_type = DRIVER_BUS_USB, - .get_irq = drm_usb_get_irq, - .get_name = drm_usb_get_name, .set_busid = drm_usb_set_busid, }; - + +/** + * drm_usb_init - Register matching USB devices with the DRM subsystem + * @driver: DRM device driver + * @udriver: USB device driver + * + * Registers one or more devices matched by a USB driver with the DRM + * subsystem. + * + * Return: 0 on success or a negative error code on failure. + */ int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver) { int res; DRM_DEBUG("\n"); - driver->kdriver.usb = udriver; driver->bus = &drm_usb_bus; res = usb_register(udriver); @@ -72,6 +68,14 @@ int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver) } EXPORT_SYMBOL(drm_usb_init); +/** + * drm_usb_exit - Unregister matching USB devices from the DRM subsystem + * @driver: DRM device driver + * @udriver: USB device driver + * + * Unregisters one or more devices matched by a USB driver from the DRM + * subsystem. + */ void drm_usb_exit(struct drm_driver *driver, struct usb_driver *udriver) { diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 5bf5bca94f56..178d2a9672a8 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -26,14 +26,14 @@ config DRM_EXYNOS_DMABUF config DRM_EXYNOS_FIMD bool "Exynos DRM FIMD" - depends on DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM + depends on DRM_EXYNOS && !FB_S3C select FB_MODE_HELPERS help Choose this option if you want to use Exynos FIMD for DRM. config DRM_EXYNOS_DPI bool "EXYNOS DRM parallel output support" - depends on DRM_EXYNOS + depends on DRM_EXYNOS_FIMD select DRM_PANEL default n help @@ -41,7 +41,7 @@ config DRM_EXYNOS_DPI config DRM_EXYNOS_DSI bool "EXYNOS DRM MIPI-DSI driver support" - depends on DRM_EXYNOS + depends on DRM_EXYNOS_FIMD select DRM_MIPI_DSI select DRM_PANEL default n @@ -50,7 +50,7 @@ config DRM_EXYNOS_DSI config DRM_EXYNOS_DP bool "EXYNOS DRM DP driver support" - depends on DRM_EXYNOS && ARCH_EXYNOS + depends on DRM_EXYNOS_FIMD && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS) default DRM_EXYNOS help This enables support for DP device. diff --git a/drivers/gpu/drm/exynos/exynos_ddc.c b/drivers/gpu/drm/exynos/exynos_ddc.c deleted file mode 100644 index 6a8c84e7c839..000000000000 --- a/drivers/gpu/drm/exynos/exynos_ddc.c +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Copyright (C) 2011 Samsung Electronics Co.Ltd - * Authors: - * Seung-Woo Kim - * Inki Dae - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ - -#include - -#include -#include -#include - -#include "exynos_drm_drv.h" -#include "exynos_hdmi.h" - -static int s5p_ddc_probe(struct i2c_client *client, - const struct i2c_device_id *dev_id) -{ - hdmi_attach_ddc_client(client); - - dev_info(&client->adapter->dev, - "attached %s into i2c adapter successfully\n", - client->name); - - return 0; -} - -static int s5p_ddc_remove(struct i2c_client *client) -{ - dev_info(&client->adapter->dev, - "detached %s from i2c adapter successfully\n", - client->name); - - return 0; -} - -static struct of_device_id hdmiddc_match_types[] = { - { - .compatible = "samsung,exynos5-hdmiddc", - }, { - .compatible = "samsung,exynos4210-hdmiddc", - }, { - /* end node */ - } -}; - -struct i2c_driver ddc_driver = { - .driver = { - .name = "exynos-hdmiddc", - .owner = THIS_MODULE, - .of_match_table = hdmiddc_match_types, - }, - .probe = s5p_ddc_probe, - .remove = s5p_ddc_remove, - .command = NULL, -}; diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c index aed533bbfd31..a8ffc8c1477b 100644 --- a/drivers/gpu/drm/exynos/exynos_dp_core.c +++ b/drivers/gpu/drm/exynos/exynos_dp_core.c @@ -18,6 +18,9 @@ #include #include #include +#include +#include +#include #include #include