diff options
71 files changed, 1286 insertions, 1045 deletions
diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt new file mode 100644 index 00000000000..c1e9545c59b --- /dev/null +++ b/Documentation/crypto/async-tx-api.txt @@ -0,0 +1,219 @@ + Asynchronous Transfers/Transforms API + +1 INTRODUCTION + +2 GENEALOGY + +3 USAGE +3.1 General format of the API +3.2 Supported operations +3.3 Descriptor management +3.4 When does the operation execute? +3.5 When does the operation complete? +3.6 Constraints +3.7 Example + +4 DRIVER DEVELOPER NOTES +4.1 Conformance points +4.2 "My application needs finer control of hardware channels" + +5 SOURCE + +--- + +1 INTRODUCTION + +The async_tx API provides methods for describing a chain of asynchronous +bulk memory transfers/transforms with support for inter-transactional +dependencies. It is implemented as a dmaengine client that smooths over +the details of different hardware offload engine implementations. Code +that is written to the API can optimize for asynchronous operation and +the API will fit the chain of operations to the available offload +resources. + +2 GENEALOGY + +The API was initially designed to offload the memory copy and +xor-parity-calculations of the md-raid5 driver using the offload engines +present in the Intel(R) Xscale series of I/O processors. It also built +on the 'dmaengine' layer developed for offloading memory copies in the +network stack using Intel(R) I/OAT engines. The following design +features surfaced as a result: +1/ implicit synchronous path: users of the API do not need to know if + the platform they are running on has offload capabilities. The + operation will be offloaded when an engine is available and carried out + in software otherwise. +2/ cross channel dependency chains: the API allows a chain of dependent + operations to be submitted, like xor->copy->xor in the raid5 case. The + API automatically handles cases where the transition from one operation + to another implies a hardware channel switch. +3/ dmaengine extensions to support multiple clients and operation types + beyond 'memcpy' + +3 USAGE + +3.1 General format of the API: +struct dma_async_tx_descriptor * +async_<operation>(<op specific parameters>, + enum async_tx_flags flags, + struct dma_async_tx_descriptor *dependency, + dma_async_tx_callback callback_routine, + void *callback_parameter); + +3.2 Supported operations: +memcpy - memory copy between a source and a destination buffer +memset - fill a destination buffer with a byte value +xor - xor a series of source buffers and write the result to a + destination buffer +xor_zero_sum - xor a series of source buffers and set a flag if the + result is zero. The implementation attempts to prevent + writes to memory + +3.3 Descriptor management: +The return value is non-NULL and points to a 'descriptor' when the operation +has been queued to execute asynchronously. Descriptors are recycled +resources, under control of the offload engine driver, to be reused as +operations complete. When an application needs to submit a chain of +operations it must guarantee that the descriptor is not automatically recycled +before the dependency is submitted. This requires that all descriptors be +acknowledged by the application before the offload engine driver is allowed to +recycle (or free) the descriptor. A descriptor can be acked by one of the +following methods: +1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted +2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent + descriptor of a new operation. +3/ calling async_tx_ack() on the descriptor. + +3.4 When does the operation execute? +Operations do not immediately issue after return from the +async_<operation> call. Offload engine drivers batch operations to +improve performance by reducing the number of mmio cycles needed to +manage the channel. Once a driver-specific threshold is met the driver +automatically issues pending operations. An application can force this +event by calling async_tx_issue_pending_all(). This operates on all +channels since the application has no knowledge of channel to operation +mapping. + +3.5 When does the operation complete? +There are two methods for an application to learn about the completion +of an operation. +1/ Call dma_wait_for_async_tx(). This call causes the CPU to spin while + it polls for the completion of the operation. It handles dependency + chains and issuing pending operations. +2/ Specify a completion callback. The callback routine runs in tasklet + context if the offload engine driver supports interrupts, or it is + called in application context if the operation is carried out + synchronously in software. The callback can be set in the call to + async_<operation>, or when the application needs to submit a chain of + unknown length it can use the async_trigger_callback() routine to set a + completion interrupt/callback at the end of the chain. + +3.6 Constraints: +1/ Calls to async_<operation> are not permitted in IRQ context. Other + contexts are permitted provided constraint #2 is not violated. +2/ Completion callback routines cannot submit new operations. This + results in recursion in the synchronous case and spin_locks being + acquired twice in the asynchronous case. + +3.7 Example: +Perform a xor->copy->xor operation where each operation depends on the +result from the previous operation: + +void complete_xor_copy_xor(void *param) +{ + printk("complete\n"); +} + +int run_xor_copy_xor(struct page **xor_srcs, + int xor_src_cnt, + struct page *xor_dest, + size_t xor_len, + struct page *copy_src, + struct page *copy_dest, + size_t copy_len) +{ + struct dma_async_tx_descriptor *tx; + + tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, + ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL); + tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, + ASYNC_TX_DEP_ACK, tx, NULL, NULL); + tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, + ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, + tx, complete_xor_copy_xor, NULL); + + async_tx_issue_pending_all(); +} + +See include/linux/async_tx.h for more information on the flags. See the +ops_run_* and ops_complete_* routines in drivers/md/raid5.c for more +implementation examples. + +4 DRIVER DEVELOPMENT NOTES +4.1 Conformance points: +There are a few conformance points required in dmaengine drivers to +accommodate assumptions made by applications using the async_tx API: +1/ Completion callbacks are expected to happen in tasklet context +2/ dma_async_tx_descriptor fields are never manipulated in IRQ context +3/ Use async_tx_run_dependencies() in the descriptor clean up path to + handle submission of dependent operations + +4.2 "My application needs finer control of hardware channels" +This requirement seems to arise from cases where a DMA engine driver is +trying to support device-to-memory DMA. The dmaengine and async_tx +implementations were designed for offloading memory-to-memory +operations; however, there are some capabilities of the dmaengine layer +that can be used for platform-specific channel management. +Platform-specific constraints can be handled by registering the +application as a 'dma_client' and implementing a 'dma_event_callback' to +apply a filter to the available channels in the system. Before showing +how to implement a custom dma_event callback some background of +dmaengine's client support is required. + +The following routines in dmaengine support multiple clients requesting +use of a channel: +- dma_async_client_register(struct dma_client *client) +- dma_async_client_chan_request(struct dma_client *client) + +dma_async_client_register takes a pointer to an initialized dma_client +structure. It expects that the 'event_callback' and 'cap_mask' fields +are already initialized. + +dma_async_client_chan_request triggers dmaengine to notify the client of +all channels that satisfy the capability mask. It is up to the client's +event_callback routine to track how many channels the client needs and +how many it is currently using. The dma_event_callback routine returns a +dma_state_client code to let dmaengine know the status of the +allocation. + +Below is the example of how to extend this functionality for +platform-specific filtering of the available channels beyond the +standard capability mask: + +static enum dma_state_client +my_dma_client_callback(struct dma_client *client, + struct dma_chan *chan, enum dma_state state) +{ + struct dma_device *dma_dev; + struct my_platform_specific_dma *plat_dma_dev; + + dma_dev = chan->device; + plat_dma_dev = container_of(dma_dev, + struct my_platform_specific_dma, + dma_dev); + + if (!plat_dma_dev->platform_specific_capability) + return DMA_DUP; + + . . . +} + +5 SOURCE +include/linux/dmaengine.h: core header file for DMA drivers and clients +drivers/dma/dmaengine.c: offload engine channel management routines +drivers/dma/: location for offload engine drivers +include/linux/async_tx.h: core header file for the async_tx api +crypto/async_tx/async_tx.c: async_tx interface to dmaengine and common code +crypto/async_tx/async_memcpy.c: copy offload +crypto/async_tx/async_memset.c: memory fill offload +crypto/async_tx/async_xor.c: xor and xor zero sum offload diff --git a/Documentation/input/iforce-protocol.txt b/Documentation/input/iforce-protocol.txt index 95df4ca70e7..8777d2d321e 100644 --- a/Documentation/input/iforce-protocol.txt +++ b/Documentation/input/iforce-protocol.txt @@ -1,254 +1,254 @@ -** Introduction
-This document describes what I managed to discover about the protocol used to
-specify force effects to I-Force 2.0 devices. None of this information comes
-from Immerse. That's why you should not trust what is written in this
-document. This document is intended to help understanding the protocol.
-This is not a reference. Comments and corrections are welcome. To contact me,
-send an email to: deneux@ifrance.com
-
-** WARNING **
-I may not be held responsible for any dammage or harm caused if you try to
-send data to your I-Force device based on what you read in this document.
-
-** Preliminary Notes:
-All values are hexadecimal with big-endian encoding (msb on the left). Beware,
-values inside packets are encoded using little-endian. Bytes whose roles are
-unknown are marked ??? Information that needs deeper inspection is marked (?)
-
-** General form of a packet **
-This is how packets look when the device uses the rs232 to communicate.
-2B OP LEN DATA CS
-CS is the checksum. It is equal to the exclusive or of all bytes.
-
-When using USB:
-OP DATA
-The 2B, LEN and CS fields have disappeared, probably because USB handles frames and
-data corruption is handled or unsignificant.
-
-First, I describe effects that are sent by the device to the computer
-
-** Device input state
-This packet is used to indicate the state of each button and the value of each
-axis
-OP= 01 for a joystick, 03 for a wheel
-LEN= Varies from device to device
-00 X-Axis lsb
-01 X-Axis msb
-02 Y-Axis lsb, or gas pedal for a wheel
-03 Y-Axis msb, or brake pedal for a wheel
-04 Throttle
-05 Buttons
-06 Lower 4 bits: Buttons
- Upper 4 bits: Hat
-07 Rudder
-
-** Device effects states
-OP= 02
-LEN= Varies
-00 ? Bit 1 (Value 2) is the value of the deadman switch
-01 Bit 8 is set if the effect is playing. Bits 0 to 7 are the effect id.
-02 ??
-03 Address of parameter block changed (lsb)
-04 Address of parameter block changed (msb)
-05 Address of second parameter block changed (lsb)
-... depending on the number of parameter blocks updated
-
-** Force effect **
-OP= 01
-LEN= 0e
-00 Channel (when playing several effects at the same time, each must be assigned a channel)
-01 Wave form
- Val 00 Constant
- Val 20 Square
- Val 21 Triangle
- Val 22 Sine
- Val 23 Sawtooth up
- Val 24 Sawtooth down
- Val 40 Spring (Force = f(pos))
- Val 41 Friction (Force = f(velocity)) and Inertia (Force = f(acceleration))
-
-
-02 Axes affected and trigger
- Bits 4-7: Val 2 = effect along one axis. Byte 05 indicates direction
- Val 4 = X axis only. Byte 05 must contain 5a
- Val 8 = Y axis only. Byte 05 must contain b4
- Val c = X and Y axes. Bytes 05 must contain 60
- Bits 0-3: Val 0 = No trigger
- Val x+1 = Button x triggers the effect
- When the whole byte is 0, cancel the previously set trigger
-
-03-04 Duration of effect (little endian encoding, in ms)
-
-05 Direction of effect, if applicable. Else, see 02 for value to assign.
-
-06-07 Minimum time between triggering.
-
-08-09 Address of periodicity or magnitude parameters
-0a-0b Address of attack and fade parameters, or ffff if none.
-*or*
-08-09 Address of interactive parameters for X-axis, or ffff if not applicable
-0a-0b Address of interactive parameters for Y-axis, or ffff if not applicable
-
-0c-0d Delay before execution of effect (little endian encoding, in ms)
-
-
-** Time based parameters **
-
-*** Attack and fade ***
-OP= 02
-LEN= 08
-00-01 Address where to store the parameteres
-02-03 Duration of attack (little endian encoding, in ms)
-04 Level at end of attack. Signed byte.
-05-06 Duration of fade.
-07 Level at end of fade.
-
-*** Magnitude ***
-OP= 03
-LEN= 03
-00-01 Address
-02 Level. Signed byte.
-
-*** Periodicity ***
-OP= 04
-LEN= 07
-00-01 Address
-02 Magnitude. Signed byte.
-03 Offset. Signed byte.
-04 Phase. Val 00 = 0 deg, Val 40 = 90 degs.
-05-06 Period (little endian encoding, in ms)
-
-** Interactive parameters **
-OP= 05
-LEN= 0a
-00-01 Address
-02 Positive Coeff
-03 Negative Coeff
-04+05 Offset (center)
-06+07 Dead band (Val 01F4 = 5000 (decimal))
-08 Positive saturation (Val 0a = 1000 (decimal) Val 64 = 10000 (decimal))
-09 Negative saturation
-
-The encoding is a bit funny here: For coeffs, these are signed values. The
-maximum value is 64 (100 decimal), the min is 9c.
-For the offset, the minimum value is FE0C, the maximum value is 01F4.
-For the deadband, the minimum value is 0, the max is 03E8.
-
-** Controls **
-OP= 41
-LEN= 03
-00 Channel
-01 Start/Stop
- Val 00: Stop
- Val 01: Start and play once.
- Val 41: Start and play n times (See byte 02 below)
-02 Number of iterations n.
-
-** Init **
-
-*** Querying features ***
-OP= ff
-Query command. Length varies according to the query type.
-The general format of this packet is:
-ff 01 QUERY [INDEX] CHECKSUM
-reponses are of the same form:
-FF LEN QUERY VALUE_QUERIED CHECKSUM2
-where LEN = 1 + length(VALUE_QUERIED)
-
-**** Query ram size ****
-QUERY = 42 ('B'uffer size)
-The device should reply with the same packet plus two additionnal bytes
-containing the size of the memory:
-ff 03 42 03 e8 CS would mean that the device has 1000 bytes of ram available.
-
-**** Query number of effects ****
-QUERY = 4e ('N'umber of effects)
-The device should respond by sending the number of effects that can be played
-at the same time (one byte)
-ff 02 4e 14 CS would stand for 20 effects.
-
-**** Vendor's id ****
-QUERY = 4d ('M'anufacturer)
-Query the vendors'id (2 bytes)
-
-**** Product id *****
-QUERY = 50 ('P'roduct)
-Query the product id (2 bytes)
-
-**** Open device ****
-QUERY = 4f ('O'pen)
-No data returned.
-
-**** Close device *****
-QUERY = 43 ('C')lose
-No data returned.
-
-**** Query effect ****
-QUERY = 45 ('E')
-Send effect type.
-Returns nonzero if supported (2 bytes)
-
-**** Firmware Version ****
-QUERY = 56 ('V'ersion)
-Sends back 3 bytes - major, minor, subminor
-
-*** Initialisation of the device ***
-
-**** Set Control ****
-!!! Device dependent, can be different on different models !!!
-OP= 40 <idx> <val> [<val>]
-LEN= 2 or 3
-00 Idx
- Idx 00 Set dead zone (0..2048)
- Idx 01 Ignore Deadman sensor (0..1)
- Idx 02 Enable comm watchdog (0..1)
- Idx 03 Set the strength of the spring (0..100)
- Idx 04 Enable or disable the spring (0/1)
- Idx 05 Set axis saturation threshold (0..2048)
-
-**** Set Effect State ****
-OP= 42 <val>
-LEN= 1
-00 State
- Bit 3 Pause force feedback
- Bit 2 Enable force feedback
- Bit 0 Stop all effects
-
-**** Set overall gain ****
-OP= 43 <val>
-LEN= 1
-00 Gain
- Val 00 = 0%
- Val 40 = 50%
- Val 80 = 100%
-
-** Parameter memory **
-
-Each device has a certain amount of memory to store parameters of effects.
-The amount of RAM may vary, I encountered values from 200 to 1000 bytes. Below
-is the amount of memory apparently needed for every set of parameters:
- - period : 0c
- - magnitude : 02
- - attack and fade : 0e
- - interactive : 08
-
-** Appendix: How to study the protocol ? **
-
-1. Generate effects using the force editor provided with the DirectX SDK, or use Immersion Studio (freely available at their web site in the developer section: www.immersion.com)
-2. Start a soft spying RS232 or USB (depending on where you connected your joystick/wheel). I used ComPortSpy from fCoder (alpha version!)
-3. Play the effect, and watch what happens on the spy screen.
-
-A few words about ComPortSpy:
-At first glance, this soft seems, hum, well... buggy. In fact, data appear with a few seconds latency. Personnaly, I restart it every time I play an effect.
-Remember it's free (as in free beer) and alpha!
-
-** URLS **
-Check www.immerse.com for Immersion Studio, and www.fcoder.com for ComPortSpy.
-
-** Author of this document **
-Johann Deneux <deneux@ifrance.com>
-Home page at http://www.esil.univ-mrs.fr/~jdeneux/projects/ff/
-
-Additions by Vojtech Pavlik.
-
-I-Force is trademark of Immersion Corp.
+** Introduction +This document describes what I managed to discover about the protocol used to +specify force effects to I-Force 2.0 devices. None of this information comes +from Immerse. That's why you should not trust what is written in this +document. This document is intended to help understanding the protocol. +This is not a reference. Comments and corrections are welcome. To contact me, +send an email to: deneux@ifrance.com + +** WARNING ** +I may not be held responsible for any dammage or harm caused if you try to +send data to your I-Force device based on what you read in this document. + +** Preliminary Notes: +All values are hexadecimal with big-endian encoding (msb on the left). Beware, +values inside packets are encoded using little-endian. Bytes whose roles are +unknown are marked ??? Information that needs deeper inspection is marked (?) + +** General form of a packet ** +This is how packets look when the device uses the rs232 to communicate. +2B OP LEN DATA CS +CS is the checksum. It is equal to the exclusive or of all bytes. + +When using USB: +OP DATA +The 2B, LEN and CS fields have disappeared, probably because USB handles frames and +data corruption is handled or unsignificant. + +First, I describe effects that are sent by the device to the computer + +** Device input state +This packet is used to indicate the state of each button and the value of each +axis +OP= 01 for a joystick, 03 for a wheel +LEN= Varies from device to device +00 X-Axis lsb +01 X-Axis msb +02 Y-Axis lsb, or gas pedal for a wheel +03 Y-Axis msb, or brake pedal for a wheel +04 Throttle +05 Buttons +06 Lower 4 bits: Buttons + Upper 4 bits: Hat +07 Rudder + +** Device effects states +OP= 02 +LEN= Varies +00 ? Bit 1 (Value 2) is the value of the deadman switch +01 Bit 8 is set if the effect is playing. Bits 0 to 7 are the effect id. +02 ?? +03 Address of parameter block changed (lsb) +04 Address of parameter block changed (msb) +05 Address of second parameter block changed (lsb) +... depending on the number of parameter blocks updated + +** Force effect ** +OP= 01 +LEN= 0e +00 Channel (when playing several effects at the same time, each must be assigned a channel) +01 Wave form + Val 00 Constant + Val 20 Square + Val 21 Triangle + Val 22 Sine + Val 23 Sawtooth up + Val 24 Sawtooth down + Val 40 Spring (Force = f(pos)) + Val 41 Friction (Force = f(velocity)) and Inertia (Force = f(acceleration)) + + +02 Axes affected and trigger + Bits 4-7: Val 2 = effect along one axis. Byte 05 indicates direction + Val 4 = X axis only. Byte 05 must contain 5a + Val 8 = Y axis only. Byte 05 must contain b4 + Val c = X and Y axes. Bytes 05 must contain 60 + Bits 0-3: Val 0 = No trigger + Val x+1 = Button x triggers the effect + When the whole byte is 0, cancel the previously set trigger + +03-04 Duration of effect (little endian encoding, in ms) + +05 Direction of effect, if applicable. Else, see 02 for value to assign. + +06-07 Minimum time between triggering. + +08-09 Address of periodicity or magnitude parameters +0a-0b Address of attack and fade parameters, or ffff if none. +*or* +08-09 Address of interactive parameters for X-axis, or ffff if not applicable +0a-0b Address of interactive parameters for Y-axis, or ffff if not applicable + +0c-0d Delay before execution of effect (little endian encoding, in ms) + + +** Time based parameters ** + +*** Attack and fade *** +OP= 02 +LEN= 08 +00-01 Address where to store the parameteres +02-03 Duration of attack (little endian encoding, in ms) +04 Level at end of attack. Signed byte. +05-06 Duration of fade. +07 Level at end of fade. + +*** Magnitude *** +OP= 03 +LEN= 03 +00-01 Address +02 Level. Signed byte. + +*** Periodicity *** +OP= 04 +LEN= 07 +00-01 Address +02 Magnitude. Signed byte. +03 Offset. Signed byte. +04 Phase. Val 00 = 0 deg, Val 40 = 90 degs. +05-06 Period (little endian encoding, in ms) + +** Interactive parameters ** +OP= 05 +LEN= 0a +00-01 Address +02 Positive Coeff +03 Negative Coeff +04+05 Offset (center) +06+07 Dead band (Val 01F4 = 5000 (decimal)) +08 Positive saturation (Val 0a = 1000 (decimal) Val 64 = 10000 (decimal)) +09 Negative saturation + +The encoding is a bit funny here: For coeffs, these are signed values. The +maximum value is 64 (100 decimal), the min is 9c. +For the offset, the minimum value is FE0C, the maximum value is 01F4. +For the deadband, the minimum value is 0, the max is 03E8. + +** Controls ** +OP= 41 +LEN= 03 +00 Channel +01 Start/Stop + Val 00: Stop + Val 01: Start and play once. + Val 41: Start and play n times (See byte 02 below) +02 Number of iterations n. + +** Init ** + +*** Querying features *** +OP= ff +Query command. Length varies according to the query type. +The general format of this packet is: +ff 01 QUERY [INDEX] CHECKSUM +reponses are of the same form: +FF LEN QUERY VALUE_QUERIED CHECKSUM2 +where LEN = 1 + length(VALUE_QUERIED) + +**** Query ram size **** +QUERY = 42 ('B'uffer size) +The device should reply with the same packet plus two additionnal bytes +containing the size of the memory: +ff 03 42 03 e8 CS would mean that the device has 1000 bytes of ram available. + +**** Query number of effects **** +QUERY = 4e ('N'umber of effects) +The device should respond by sending the number of effects that can be played +at the same time (one byte) +ff 02 4e 14 CS would stand for 20 effects. + +**** Vendor's id **** +QUERY = 4d ('M'anufacturer) +Query the vendors'id (2 bytes) + +**** Product id ***** +QUERY = 50 ('P'roduct) +Query the product id (2 bytes) + +**** Open device **** +QUERY = 4f ('O'pen) +No data returned. + +**** Close device ***** +QUERY = 43 ('C')lose +No data returned. + +**** Query effect **** +QUERY = 45 ('E') +Send effect type. +Returns nonzero if supported (2 bytes) + +**** Firmware Version **** +QUERY = 56 ('V'ersion) +Sends back 3 bytes - major, minor, subminor + +*** Initialisation of the device *** + +**** Set Control **** +!!! Device dependent, can be different on different models !!! +OP= 40 <idx> <val> [<val>] +LEN= 2 or 3 +00 Idx + Idx 00 Set dead zone (0..2048) + Idx 01 Ignore Deadman sensor (0..1) + Idx 02 Enable comm watchdog (0..1) + Idx 03 Set the strength of the spring (0..100) + Idx 04 Enable or disable the spring (0/1) + Idx 05 Set axis saturation threshold (0..2048) + +**** Set Effect State **** +OP= 42 <val> +LEN= 1 +00 State + Bit 3 Pause force feedback + Bit 2 Enable force feedback + Bit 0 Stop all effects + +**** Set overall gain **** +OP= 43 <val> +LEN= 1 +00 Gain + Val 00 = 0% + Val 40 = 50% + Val 80 = 100% + +** Parameter memory ** + +Each device has a certain amount of memory to store parameters of effects. +The amount of RAM may vary, I encountered values from 200 to 1000 bytes. Below +is the amount of memory apparently needed for every set of parameters: + - period : 0c + - magnitude : 02 + - attack and fade : 0e + - interactive : 08 + +** Appendix: How to study the protocol ? ** + +1. Generate effects using the force editor provided with the DirectX SDK, or use Immersion Studio (freely available at their web site in the developer section: www.immersion.com) +2. Start a soft spying RS232 or USB (depending on where you connected your joystick/wheel). I used ComPortSpy from fCoder (alpha version!) +3. Play the effect, and watch what happens on the spy screen. + +A few words about ComPortSpy: +At first glance, this soft seems, hum, well... buggy. In fact, data appear with a few seconds latency. Personnaly, I restart it every time I play an effect. +Remember it's free (as in free beer) and alpha! + +** URLS ** +Check www.immerse.com for Immersion Studio, and www.fcoder.com for ComPortSpy. + +** Author of this document ** +Johann Deneux <deneux@ifrance.com> +Home page at http://www.esil.univ-mrs.fr/~jdeneux/projects/ff/ + +Additions by Vojtech Pavlik. + +I-Force is trademark of Immersion Corp. diff --git a/MAINTAINERS b/MAINTAINERS index 9c54a5ef0ba..9a91d9e3f1f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2622,8 +2622,8 @@ P: Harald Welte P: Jozsef Kadlecsik P: Patrick McHardy M: kaber@trash.net -L: netfilter-devel@lists.netfilter.org -L: netfilter@lists.netfilter.org (subscribers-only) +L: netfilter-devel@vger.kernel.org +L: netfilter@vger.kernel.org L: coreteam@netfilter.org W: http://www.netfilter.org/ W: http://www.iptables.org/ @@ -2676,7 +2676,7 @@ M: jmorris@namei.org P: Hideaki YOSHIFUJI M: yoshfuji@linux-ipv6.org P: Patrick McHardy -M: kaber@coreworks.de +M: kaber@trash.net L: netdev@vger.kernel.org T: git kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6.git S: Maintained @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 23 -EXTRAVERSION =-rc7 +EXTRAVERSION =-rc8 NAME = Arr Matey! A Hairy Bilge Rat! # *DOCUMENTATION* diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 851cc7158ca..70b2c780111 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -336,7 +336,7 @@ static int ep93xx_gpio_irq_type(unsigned int irq, unsigned int type) if (line >= 0 && line < 16) { gpio_line_config(line, GPIO_IN); } else { - gpio_line_config(EP93XX_GPIO_LINE_F(line), GPIO_IN); + gpio_line_config(EP93XX_GPIO_LINE_F(line-16), GPIO_IN); } port = line >> 3; diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index b4e9b734e0b..76b800a9519 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -57,7 +57,17 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) { unsigned long addr; - start &= ~(CACHE_LINE_SIZE - 1); + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + sync_writel(start, L2X0_CLEAN_INV_LINE_PA, 1); + start += CACHE_LINE_SIZE; + } + + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + sync_writel(end, L2X0_CLEAN_INV_LINE_PA, 1); + } + for (addr = start; addr < end; addr += CACHE_LINE_SIZE) sync_writel(addr, L2X0_INV_LINE_PA, 1); cache_sync(); diff --git a/arch/i386/boot/header.S b/arch/i386/boot/header.S index 7f4a2c53bd7..f3140e596d4 100644 --- a/arch/i386/boot/header.S +++ b/arch/i386/boot/header.S @@ -275,7 +275,7 @@ die: hlt jmp die - .size die, .-due + .size die, .-die .section ".initdata", "a" setup_corrupt: diff --git a/arch/i386/boot/video.c b/arch/i386/boot/video.c index 693f20d3102..e4ba897bf9a 100644 --- a/arch/i386/boot/video.c +++ b/arch/i386/boot/video.c @@ -147,7 +147,7 @@ int mode_defined(u16 mode) } /* Set mode (without recalc) */ -static int raw_set_mode(u16 mode) +static int raw_set_mode(u16 mode, u16 *real_mode) { int nmode, i; struct card_info *card; @@ -165,8 +165,10 @@ static int raw_set_mode(u16 mode) if ((mode == nmode && visible) || mode == mi->mode || - mode == (mi->y << 8)+mi->x) + mode == (mi->y << 8)+mi->x) { + *real_mode = mi->mode; return card->set_mode(mi); + } if (visible) nmode++; @@ -178,7 +180,7 @@ static int raw_set_mode(u16 mode) if (mode >= card->xmode_first && mode < card->xmode_first+card->xmode_n) { struct mode_info mix; - mix.mode = mode; + *real_mode = mix.mode = mode; mix.x = mix.y = 0; return card->set_mode(&mix); } @@ -223,6 +225,7 @@ static void vga_recalc_vertical(void) static int set_mode(u16 mode) { int rv; + u16 real_mode; /* Very special mode numbers... */ if (mode == VIDEO_CURRENT_MODE) @@ -232,13 +235,16 @@ static int set_mode(u16 mode) else if (mode == EXTENDED_VGA) mode = VIDEO_8POINT; - rv = raw_set_mode(mode); + rv = raw_set_mode(mode, &real_mode); if (rv) return rv; if (mode & VIDEO_RECALC) vga_recalc_vertical(); + /* Save the canonical mode number for the kernel, not + an alias, size specification or menu position */ + boot_params.hdr.vid_mode = real_mode; return 0; } diff --git a/arch/i386/kernel/acpi/wakeup.S b/arch/i386/kernel/acpi/wakeup.S index ed0a0f2c159..f22ba8534d2 100644 --- a/arch/i386/kernel/acpi/wakeup.S +++ b/arch/i386/kernel/acpi/wakeup.S @@ -151,51 +151,30 @@ bogus_real_magic: #define VIDEO_FIRST_V7 0x0900 # Setting of user mode (AX=mode ID) => CF=success + +# For now, we only handle VESA modes (0x0200..0x03ff). To handle other +# modes, we should probably compile in the video code from the boot +# directory. mode_set: movw %ax, %bx -#if 0 - cmpb $0xff, %ah - jz setalias - - testb $VIDEO_RECALC>>8, %ah - jnz _setrec - - cmpb $VIDEO_FIRST_RESOLUTION>>8, %ah - jnc setres - - cmpb $VIDEO_FIRST_SPECIAL>>8, %ah - jz setspc - - cmpb $VIDEO_FIRST_V7>>8, %ah - jz setv7 -#endif - - cmpb $VIDEO_FIRST_VESA>>8, %ah - jnc check_vesa -#if 0 - orb %ah, %ah - jz setmenu -#endif - - decb %ah -# jz setbios Add bios modes later + subb $VIDEO_FIRST_VESA>>8, %bh + cmpb $2, %bh + jb check_vesa -setbad: clc +setbad: + clc ret check_vesa: - subb $VIDEO_FIRST_VESA>>8, %bh orw $0x4000, %bx # Use linear frame buffer movw $0x4f02, %ax # VESA BIOS mode set call int $0x10 cmpw $0x004f, %ax # AL=4f if implemented - jnz _setbad # AH=0 if OK + jnz setbad # AH=0 if OK stc ret -_setbad: jmp setbad - .code32 ALIGN diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index b6c30800c66..3a2d255361b 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -177,10 +177,7 @@ handle_real_irq: outb(cached_master_mask, PIC_MASTER_IMR); outb(0x60+irq,PIC_MASTER_CMD); /* 'Specific EOI to master */ } -#ifdef CONFIG_MIPS_MT_SMTC - if (irq_hwmask[irq] & ST0_IM) - set_c0_status(irq_hwmask[irq] & ST0_IM); -#endif /* CONFIG_MIPS_MT_SMTC */ + smtc_im_ack_irq(irq); spin_unlock_irqrestore(&i8259A_lock, flags); return; diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c index 410868b5ea5..1ecdd50bfc6 100644 --- a/arch/mips/kernel/irq-msc01.c +++ b/arch/mips/kernel/irq-msc01.c @@ -52,11 +52,8 @@ static void level_mask_and_ack_msc_irq(unsigned int irq) mask_msc_irq(irq); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); -#ifdef CONFIG_MIPS_MT_SMTC /* This actually needs to be a call into platform code */ - if (irq_hwmask[irq] & ST0_IM) - set_c0_status(irq_hwmask[irq] & ST0_IM); -#endif /* CONFIG_MIPS_MT_SMTC */ + smtc_im_ack_irq(irq); } /* @@ -73,10 +70,7 @@ static void edge_mask_and_ack_msc_irq(unsigned int irq) MSCIC_WRITE(MSC01_IC_SUP+irq*8, r | ~MSC01_IC_SUP_EDGE_BIT); MSCIC_WRITE(MSC01_IC_SUP+irq*8, r); } -#ifdef CONFIG_MIPS_MT_SMTC - if (irq_hwmask[irq] & ST0_IM) - set_c0_status(irq_hwmask[irq] & ST0_IM); -#endif /* CONFIG_MIPS_MT_SMTC */ + smtc_im_ack_irq(irq); } /* diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index aeded6c17de..a990aad2f04 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -74,20 +74,12 @@ EXPORT_SYMBOL_GPL(free_irqno); */ void ack_bad_irq(unsigned int irq) { + smtc_im_ack_irq(irq); printk("unexpected IRQ # %d\n", irq); } atomic_t irq_err_count; -#ifdef CONFIG_MIPS_MT_SMTC -/* - * SMTC Kernel needs to manipulate low-level CPU interrupt mask - * in do_IRQ. These are passed in setup_irq_smtc() and stored - * in this table. - */ -unsigned long irq_hwmask[NR_IRQS]; -#endif /* CONFIG_MIPS_MT_SMTC */ - /* * Generic, controller-independent functions: */ diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 43826c16101..f09404377ef 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -25,8 +25,11 @@ #include <asm/smtc_proc.h> /* - * This file should be built into the kernel only if CONFIG_MIPS_MT_SMTC is set. + * SMTC Kernel needs to manipulate low-level CPU interrupt mask + * in do_IRQ. These are passed in setup_irq_smtc() and stored + * in this table. */ +unsigned long irq_hwmask[NR_IRQS]; #define LOCK_MT_PRA() \ local_irq_save(flags); \ diff --git a/arch/mips/sibyte/bcm1480/setup.c b/arch/mips/sibyte/bcm1480/setup.c index bb28f28e804..7e1aa348b8e 100644 --- a/arch/mips/sibyte/bcm1480/setup.c +++ b/arch/mips/sibyte/bcm1480/setup.c @@ -15,6 +15,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ +#include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/reboot.h> @@ -35,6 +36,7 @@ unsigned int soc_type; EXPORT_SYMBOL(soc_type); unsigned int periph_rev; unsigned int zbbus_mhz; +EXPORT_SYMBOL(zbbus_mhz); static unsigned int part_type; diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index ffa03640628..b4d9089a6a0 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -60,14 +60,6 @@ config ZONE_DMA bool default y -config QUICKLIST - bool - default y - -config NR_QUICK - int - default 2 - config ISA bool diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 938278697e2..18b23181090 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -38,6 +38,18 @@ movq %rax,R8(%rsp) .endm + .macro LOAD_ARGS32 offset + movl \offset(%rsp),%r11d + movl \offset+8(%rsp),%r10d + movl \offset+16(%rsp),%r9d + movl \offset+24(%rsp),%r8d + movl \offset+40(%rsp),%ecx + movl \offset+48(%rsp),%edx + movl \offset+56(%rsp),%esi + movl \offset+64(%rsp),%edi + movl \offset+72(%rsp),%eax + .endm + .macro CFI_STARTPROC32 simple CFI_STARTPROC \simple CFI_UNDEFINED r8 @@ -152,7 +164,7 @@ sysenter_tracesys: movq $-ENOSYS,RAX(%rsp) /* really needed? */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST movl %ebp, %ebp /* no need to do an access_ok check here because rbp has been @@ -255,7 +267,7 @@ cstar_tracesys: movq $-ENOSYS,RAX(%rsp) /* really needed? */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST movl RSP-ARGOFFSET(%rsp), %r8d /* no need to do an access_ok check here because r8 has been @@ -334,7 +346,7 @@ ia32_tracesys: movq $-ENOSYS,RAX(%rsp) /* really needed? */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST jmp ia32_do_syscall END(ia32_syscall) diff --git a/arch/x86_64/kernel/acpi/wakeup.S b/arch/x86_64/kernel/acpi/wakeup.S index 13f1480cbec..a06f2bcabef 100644 --- a/arch/x86_64/kernel/acpi/wakeup.S +++ b/arch/x86_64/kernel/acpi/wakeup.S @@ -81,7 +81,7 @@ wakeup_code: testl $2, realmode_flags - wakeup_code jz 1f mov video_mode - wakeup_code, %ax - call mode_seta + call mode_set 1: movw $0xb800, %ax @@ -291,52 +291,31 @@ no_longmode: #define VIDEO_FIRST_V7 0x0900 # Setting of user mode (AX=mode ID) => CF=success + +# For now, we only handle VESA modes (0x0200..0x03ff). To handle other +# modes, we should probably compile in the video code from the boot +# directory. .code16 -mode_seta: +mode_set: movw %ax, %bx -#if 0 - cmpb $0xff, %ah - jz setalias - - testb $VIDEO_RECALC>>8, %ah - jnz _setrec - - cmpb $VIDEO_FIRST_RESOLUTION>>8, %ah - jnc setres - - cmpb $VIDEO_FIRST_SPECIAL>>8, %ah - jz setspc - - cmpb $VIDEO_FIRST_V7>>8, %ah - jz setv7 -#endif - - cmpb $VIDEO_FIRST_VESA>>8, %ah - jnc check_vesaa -#if 0 - orb %ah, %ah - jz setmenu -#endif - - decb %ah -# jz setbios Add bios modes later + subb $VIDEO_FIRST_VESA>>8, %bh + cmpb $2, %bh + jb check_vesa -setbada: clc +setbad: + clc ret -check_vesaa: - subb $VIDEO_FIRST_VESA>>8, %bh +check_vesa: orw $0x4000, %bx # Use linear frame buffer movw $0x4f02, %ax # VESA BIOS mode set call int $0x10 cmpw $0x004f, %ax # AL=4f if implemented - jnz _setbada # AH=0 if OK + jnz setbad # AH=0 if OK stc ret -_setbada: jmp setbada - wakeup_stack_begin: # Stack grows down .org 0xff0 diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 2842f50cbe3..98956555450 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -208,7 +208,6 @@ void cpu_idle (void) if (__get_cpu_var(cpu_idle_state)) __get_cpu_var(cpu_idle_state) = 0; - check_pgt_cache(); rmb(); idle = pm_idle; if (!idle) diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c index e83cc67155a..eea3702427b 100644 --- a/arch/x86_64/kernel/ptrace.c +++ b/arch/x86_64/kernel/ptrace.c @@ -232,10 +232,6 @@ static int putreg(struct task_struct *child, { unsigned long tmp; - /* Some code in the 64bit emulation may not be 64bit clean. - Don't take any chances. */ - if (test_tsk_thread_flag(child, TIF_IA32)) - value &= 0xffffffff; switch (regno) { case offsetof(struct user_regs_struct,fs): if (value && (value & 3) != 3) diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c index 673a300b594..df4a82812ad 100644 --- a/arch/x86_64/kernel/smp.c +++ b/arch/x86_64/kernel/smp.c @@ -241,7 +241,7 @@ void flush_tlb_mm (struct mm_struct * mm) } if (!cpus_empty(cpu_mask)) flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - check_pgt_cache(); + preempt_enable(); } EXPORT_SYMBOL(flush_tlb_mm); diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index 035007145e7..bc18cbb8ea7 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -80,6 +80,7 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { enum dma_status status; struct dma_async_tx_descriptor *iter; + struct dma_async_tx_descriptor *parent; if (!tx) return DMA_SUCCESS; @@ -87,8 +88,15 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) /* poll through the dependency chain, return when tx is complete */ do { iter = tx; - while (iter->cookie == -EBUSY) - iter = iter->parent; + + /* find the root of the unsubmitted dependency chain */ + while (iter->cookie == -EBUSY) { + parent = iter->parent; + if (parent && parent->cookie == -EBUSY) + iter = iter->parent; + else + break; + } status = dma_sync_wait(iter->chan, iter->cookie); } while (status == DMA_IN_PROGRESS || (iter != tx)); diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 2afb3d2086b..9f11dc296cd 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -102,6 +102,8 @@ static struct acpi_driver acpi_processor_driver = { .add = acpi_processor_add, .remove = acpi_processor_remove, .start = acpi_processor_start, + .suspend = acpi_processor_suspend, + .resume = acpi_processor_resume, }, }; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index d9b8af763e1..f18261368e7 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -325,6 +325,23 @@ static void acpi_state_timer_broadcast(struct acpi_processor *pr, #endif +/* + * Suspend / resume control + */ +static int acpi_idle_suspend; + +int acpi_processor_suspend(struct acpi_device * device, pm_message_t state) +{ + acpi_idle_suspend = 1; + return 0; +} + +int acpi_processor_resume(struct acpi_device * device) +{ + acpi_idle_suspend = 0; + return 0; +} + static void acpi_processor_idle(void) { struct acpi_processor *pr = NULL; @@ -355,7 +372,7 @@ static void acpi_processor_idle(void) } cx = pr->power.state; - if (!cx) { + if (!cx || acpi_idle_suspend) { if (pm_idle_save) pm_idle_save(); else diff --git a/drivers/acpi/sleep/Makefile b/drivers/acpi/sleep/Makefile index 195a4f69c0f..ba9bd403d44 100644 --- a/drivers/acpi/sleep/Makefile +++ b/drivers/acpi/sleep/Makefile @@ -1,4 +1,4 @@ -obj-y := poweroff.o wakeup.o +obj-y := wakeup.o obj-$(CONFIG_ACPI_SLEEP) += main.o obj-$(CONFIG_ACPI_SLEEP) += proc.o diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c index c52ade816fb..85633c585aa 100644 --- a/drivers/acpi/sleep/main.c +++ b/drivers/acpi/sleep/main.c @@ -15,6 +15,9 @@ #include <linux/dmi.h> #include <linux/device.h> #include <linux/suspend.h> + +#include <asm/io.h> + #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include "sleep.h" @@ -57,6 +60,27 @@ static int acpi_pm_set_target(suspend_state_t pm_state) return error; } +int acpi_sleep_prepare(u32 acpi_state) +{ +#ifdef CONFIG_ACPI_SLEEP + /* do we have a wakeup address for S2 and S3? */ + if (acpi_state == ACPI_STATE_S3) { + if (!acpi_wakeup_address) { + return -EFAULT; + } + acpi_set_firmware_waking_vector((acpi_physical_address) + virt_to_phys((void *) + acpi_wakeup_address)); + + } + ACPI_FLUSH_CPU_CACHE(); + acpi_enable_wakeup_device_prep(acpi_state); +#endif + acpi_gpe_sleep_prepare(acpi_state); + acpi_enter_sleep_state_prep(acpi_state); + return 0; +} + /** * acpi_pm_prepare - Do preliminary suspend work. * @pm_state: ignored @@ -350,6 +374,20 @@ int acpi_pm_device_sleep_state(struct device *dev, int wake, int *d_min_p) return d_max; } +static void acpi_power_off_prepare(void) +{ + /* Prepare to power off the system */ + acpi_sleep_prepare(ACPI_STATE_S5); +} + +static void acpi_power_off(void) +{ + /* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */ + printk("%s called\n", __FUNCTION__); + local_irq_disable(); + acpi_enter_sleep_state(ACPI_STATE_S5); +} + int __init acpi_sleep_init(void) { acpi_status status; @@ -363,16 +401,17 @@ int __init acpi_sleep_init(void) if (acpi_disabled) return 0; + sleep_states[ACPI_STATE_S0] = 1; + printk(KERN_INFO PREFIX "(supports S0"); + #ifdef CONFIG_SUSPEND - printk(KERN_INFO PREFIX "(supports"); - for (i = ACPI_STATE_S0; i < ACPI_STATE_S4; i++) { + for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) { status = acpi_get_sleep_type_data(i, &type_a, &type_b); if (ACPI_SUCCESS(status)) { sleep_states[i] = 1; printk(" S%d", i); } } - printk(")\n"); pm_set_ops(&acpi_pm_ops); #endif @@ -382,10 +421,16 @@ int __init acpi_sleep_init(void) if (ACPI_SUCCESS(status)) { hibernation_set_ops(&acpi_hibernation_ops); sleep_states[ACPI_STATE_S4] = 1; + printk(" S4"); } -#else - sleep_states[ACPI_STATE_S4] = 0; #endif - + status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b); + if (ACPI_SUCCESS(status)) { + sleep_states[ACPI_STATE_S5] = 1; + printk(" S5"); + pm_power_off_prepare = acpi_power_off_prepare; + pm_power_off = acpi_power_off; + } + printk(")\n"); return 0; } diff --git a/drivers/acpi/sleep/poweroff.c b/drivers/acpi/sleep/poweroff.c deleted file mode 100644 index 39e40d56b03..00000000000 --- a/drivers/acpi/sleep/poweroff.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * poweroff.c - ACPI handler for powering off the system. - * - * AKA S5, but it is independent of whether or not the kernel supports - * any other sleep support in the system. - * - * Copyright (c) 2005 Alexey Starikovskiy <alexey.y.starikovskiy@intel.com> - * - * This file is released under the GPLv2. - */ - -#include <linux/pm.h> -#include <linux/init.h> -#include <acpi/acpi_bus.h> -#include <linux/sysdev.h> -#include <asm/io.h> -#include "sleep.h" - -int acpi_sleep_prepare(u32 acpi_state) -{ -#ifdef CONFIG_ACPI_SLEEP - /* do we have a wakeup address for S2 and S3? */ - if (acpi_state == ACPI_STATE_S3) { - if (!acpi_wakeup_address) { - return -EFAULT; - } - acpi_set_firmware_waking_vector((acpi_physical_address) - virt_to_phys((void *) - acpi_wakeup_address)); - - } - ACPI_FLUSH_CPU_CACHE(); - acpi_enable_wakeup_device_prep(acpi_state); -#endif - acpi_gpe_sleep_prepare(acpi_state); - acpi_enter_sleep_state_prep(acpi_state); - return 0; -} - -#ifdef CONFIG_PM - -static void acpi_power_off_prepare(void) -{ - /* Prepare to power off the system */ - acpi_sleep_prepare(ACPI_STATE_S5); -} - -static void acpi_power_off(void) -{ - /* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */ - printk("%s called\n", __FUNCTION__); - local_irq_disable(); - /* Some SMP machines only can poweroff in boot CPU */ - acpi_enter_sleep_state(ACPI_STATE_S5); -} - -static int acpi_poweroff_init(void) -{ - if (!acpi_disabled) { - u8 type_a, type_b; - acpi_status status; - - status = - acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b); - if (ACPI_SUCCESS(status)) { - pm_power_off_prepare = acpi_power_off_prepare; - pm_power_off = acpi_power_off; - } - } - return 0; -} - -late_initcall(acpi_poweroff_init); - -#endif /* CONFIG_PM */ diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 3c9bb85a6a9..d05891f1628 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -417,7 +417,6 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level) arg0.integer.value = level; status = acpi_evaluate_object(device->dev->handle, "_BCM", &args, NULL); - printk(KERN_DEBUG "set_level status: %x\n", status); return status; } @@ -1754,7 +1753,7 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video) static int acpi_video_bus_start_devices(struct acpi_video_bus *video) { - return acpi_video_bus_DOS(video, 1, 0); + return acpi_video_bus_DOS(video, 0, 0); } static int acpi_video_bus_stop_devices(struct acpi_video_bus *video) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 06f212ff2b4..c16820325d7 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -418,10 +418,12 @@ static const struct pci_device_id ahci_pci_tbl[] = { /* ATI */ { PCI_VDEVICE(ATI, 0x4380), board_ahci_sb600 }, /* ATI SB600 */ - { PCI_VDEVICE(ATI, 0x4390), board_ahci_sb600 }, /* ATI SB700 IDE */ - { PCI_VDEVICE(ATI, 0x4391), board_ahci_sb600 }, /* ATI SB700 AHCI */ - { PCI_VDEVICE(ATI, 0x4392), board_ahci_sb600 }, /* ATI SB700 nraid5 */ - { PCI_VDEVICE(ATI, 0x4393), board_ahci_sb600 }, /* ATI SB700 raid5 */ + { PCI_VDEVICE(ATI, 0x4390), board_ahci_sb600 }, /* ATI SB700/800 */ + { PCI_VDEVICE(ATI, 0x4391), board_ahci_sb600 }, /* ATI SB700/800 */ + { PCI_VDEVICE(ATI, 0x4392), board_ahci_sb600 }, /* ATI SB700/800 */ + { PCI_VDEVICE(ATI, 0x4393), board_ahci_sb600 }, /* ATI SB700/800 */ + { PCI_VDEVICE(ATI, 0x4394), board_ahci_sb600 }, /* ATI SB700/800 */ + { PCI_VDEVICE(ATI, 0x4395), board_ahci_sb600 }, /* ATI SB700/800 */ /* VIA */ { PCI_VDEVICE(VIA, 0x3349), board_ahci_vt8251 }, /* VIA VT8251 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index c43de9a710d..772be09b468 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3778,6 +3778,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Maxtor 6L250S0", "BANC1G10", ATA_HORKAGE_NONCQ }, { "Maxtor 6B200M0", "BANC1BM0", ATA_HORKAGE_NONCQ }, { "Maxtor 6B200M0", "BANC1B10", ATA_HORKAGE_NONCQ }, + { "Maxtor 7B250S0", "BANC1B70", ATA_HORKAGE_NONCQ, }, + { "Maxtor 7B300S0", "BANC1B70", ATA_HORKAGE_NONCQ }, + { "Maxtor 7V300F0", "VA111630", ATA_HORKAGE_NONCQ }, { "HITACHI HDS7250SASUN500G 0621KTAWSD", "K2AOAJ0AHITACHI", ATA_HORKAGE_NONCQ }, /* NCQ hard hangs device under heavier load, needs hard power cycle */ @@ -3794,6 +3797,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, }, { "FUJITSU MHV2080BH", "00840028", ATA_HORKAGE_NONCQ, }, { "ST9160821AS", "3.CLF", ATA_HORKAGE_NONCQ, }, + { "ST3160812AS", "3.AD", ATA_HORKAGE_NONCQ, }, { "SAMSUNG HD401LJ", "ZZ100-15", ATA_HORKAGE_NONCQ, }, /* devices which puke on READ_NATIVE_MAX */ diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 1cce2198baa..8023167bbbe 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -297,7 +297,7 @@ void ata_bmdma_start (struct ata_queued_cmd *qc) dmactl = ioread8(ap->ioaddr.bmdma_addr + ATA_DMA_CMD); iowrite8(dmactl | ATA_DMA_START, ap->ioaddr.bmdma_addr + ATA_DMA_CMD); - /* Strictly, one may wish to issue a readb() here, to + /* Strictly, one may wish to issue an ioread8() here, to * flush the mmio write. However, control also passes * to the hardware at this point, and it will interrupt * us when we are to resume control. So, in effect, @@ -307,6 +307,9 @@ void ata_bmdma_start (struct ata_queued_cmd *qc) * is expected, so I think it is best to not add a readb() * without first all the MMIO ATA cards/mobos. * Or maybe I'm just being paranoid. + * + * FIXME: The posting of this write means I/O starts are + * unneccessarily delayed for MMIO */ } diff --git a/drivers/ieee1394/ieee1394_core.c b/drivers/ieee1394/ieee1394_core.c index ee45259573c..98fd985a32f 100644 --- a/drivers/ieee1394/ieee1394_core.c +++ b/drivers/ieee1394/ieee1394_core.c @@ -1273,7 +1273,7 @@ static void __exit ieee1394_cleanup(void) unregister_chrdev_region(IEEE1394_CORE_DEV, 256); } -fs_initcall(ieee1394_init); /* same as ohci1394 */ +module_init(ieee1394_init); module_exit(ieee1394_cleanup); /* Exported symbols */ diff --git a/drivers/ieee1394/ohci1394.c b/drivers/ieee1394/ohci1394.c index 5667c8102ef..372c5c16eb3 100644 --- a/drivers/ieee1394/ohci1394.c +++ b/drivers/ieee1394/ohci1394.c @@ -3537,7 +3537,5 @@ static int __init ohci1394_init(void) return pci_register_driver(&ohci1394_pci_driver); } -/* Register before most other device drivers. - * Useful for remote debugging via physical DMA, e.g. using firescope. */ -fs_initcall(ohci1394_init); +module_init(ohci1394_init); module_exit(ohci1394_cleanup); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index ba0428d872a..85c51bdc36f 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1211,12 +1211,42 @@ static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg, dseg->qkey = cpu_to_be32(wr->wr.ud.remote_qkey); } -static void set_data_seg(struct mlx4_wqe_data_seg *dseg, - struct ib_sge *sg) +static void set_mlx_icrc_seg(void *dseg) +{ + u32 *t = dseg; + struct mlx4_wqe_inline_seg *iseg = dseg; + + t[1] = 0; + + /* + * Need a barrier here before writing the byte_count field to + * make sure that all the data is visible before the + * byte_count field is set. Otherwise, if the segment begins + * a new cacheline, the HCA prefetcher could grab the 64-byte + * chunk and get a valid (!= * 0xffffffff) byte count but + * stale data, and end up sending the wrong data. + */ + wmb(); + + iseg->byte_count = cpu_to_be32((1 << 31) | 4); +} + +static void set_data_seg(struct mlx4_wqe_data_seg *dseg, struct ib_sge *sg) { - dseg->byte_count = cpu_to_be32(sg->length); dseg->lkey = cpu_to_be32(sg->lkey); dseg->addr = cpu_to_be64(sg->addr); + + /* + * Need a barrier here before writing the byte_count field to + * make sure that all the data is visible before the + * byte_count field is set. Otherwise, if the segment begins + * a new cacheline, the HCA prefetcher could grab the 64-byte + * chunk and get a valid (!= * 0xffffffff) byte count but + * stale data, and end up sending the wrong data. + */ + wmb(); + + dseg->byte_count = cpu_to_be32(sg->length); } int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, @@ -1225,6 +1255,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct mlx4_ib_qp *qp = to_mqp(ibqp); void *wqe; struct mlx4_wqe_ctrl_seg *ctrl; + struct mlx4_wqe_data_seg *dseg; unsigned long flags; int nreq; int err = 0; @@ -1324,22 +1355,27 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, break; } - for (i = 0; i < wr->num_sge; ++i) { - set_data_seg(wqe, wr->sg_list + i); + /* + * Write data segments in reverse order, so as to + * overwrite cacheline stamp last within each + * cacheline. This avoids issues with WQE + * prefetching. + */ - wqe += sizeof (struct mlx4_wqe_data_seg); - size += sizeof (struct mlx4_wqe_data_seg) / 16; - } + dseg = wqe; + dseg += wr->num_sge - 1; + size += wr->num_sge * (sizeof (struct mlx4_wqe_data_seg) / 16); /* Add one more inline data segment for ICRC for MLX sends */ - if (qp->ibqp.qp_type == IB_QPT_SMI || qp->ibqp.qp_type == IB_QPT_GSI) { - ((struct mlx4_wqe_inline_seg *) wqe)->byte_count = - cpu_to_be32((1 << 31) | 4); - ((u32 *) wqe)[1] = 0; - wqe += sizeof (struct mlx4_wqe_data_seg); + if (unlikely(qp->ibqp.qp_type == IB_QPT_SMI || + qp->ibqp.qp_type == IB_QPT_GSI)) { + set_mlx_icrc_seg(dseg + 1); size += sizeof (struct mlx4_wqe_data_seg) / 16; } + for (i = wr->num_sge - 1; i >= 0; --i, --dseg) + set_data_seg(dseg, wr->sg_list + i); + ctrl->fence_size = (wr->send_flags & IB_SEND_FENCE ? MLX4_WQE_CTRL_FENCE : 0) | size; diff --git a/drivers/kvm/Kconfig b/drivers/kvm/Kconfig index 7b64fd4aa2f..0a419a0de60 100644 --- a/drivers/kvm/Kconfig +++ b/drivers/kvm/Kconfig @@ -6,7 +6,8 @@ menuconfig VIRTUALIZATION depends on X86 default y ---help--- - Say Y here to get to see options for virtualization guest drivers. + Say Y here to get to see options for using your Linux host to run other + operating systems inside virtual machines (guests). This option alone does not add any kernel code. If you say N, all options in this submenu will be skipped and disabled. diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4d63773ee73..f96dea975fa 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -514,7 +514,7 @@ static void ops_complete_biofill(void *stripe_head_ref) struct stripe_head *sh = stripe_head_ref; struct bio *return_bi = NULL; raid5_conf_t *conf = sh->raid_conf; - int i, more_to_read = 0; + int i; pr_debug("%s: stripe %llu\n", __FUNCTION__, (unsigned long long)sh->sector); @@ -522,16 +522,14 @@ static void ops_complete_biofill(void *stripe_head_ref) /* clear completed biofills */ for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - /* check if this stripe has new incoming reads */ - if (dev->toread) - more_to_read++; /* acknowledge completion of a biofill operation */ - /* and check if we need to reply to a read request - */ - if (test_bit(R5_Wantfill, &dev->flags) && !dev->toread) { + /* and check if we need to reply to a read request, + * new R5_Wantfill requests are held off until + * !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending) + */ + if (test_and_clear_bit(R5_Wantfill, &dev->flags)) { struct bio *rbi, *rbi2; - clear_bit(R5_Wantfill, &dev->flags); /* The access to dev->read is outside of the * spin_lock_irq(&conf->device_lock), but is protected @@ -558,8 +556,7 @@ static void ops_complete_biofill(void *stripe_head_ref) return_io(return_bi); - if (more_to_read) - set_bit(STRIPE_HANDLE, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); } diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 854d80c330e..66eed22cbd2 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -54,8 +54,8 @@ #define DRV_MODULE_NAME "bnx2" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "1.6.4" -#define DRV_MODULE_RELDATE "August 3, 2007" +#define DRV_MODULE_VERSION "1.6.5" +#define DRV_MODULE_RELDATE "September 20, 2007" #define RUN_AT(x) (jiffies + (x)) @@ -6727,7 +6727,8 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) } else if (CHIP_NUM(bp) == CHIP_NUM_5706 || CHIP_NUM(bp) == CHIP_NUM_5708) bp->phy_flags |= PHY_CRC_FIX_FLAG; - else if (CHIP_ID(bp) == CHIP_ID_5709_A0) + else if (CHIP_ID(bp) == CHIP_ID_5709_A0 || + CHIP_ID(bp) == CHIP_ID_5709_A1) bp->phy_flags |= PHY_DIS_EARLY_DAC_FLAG; if ((CHIP_ID(bp) == CHIP_ID_5708_A0) || diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 1c42266bf88..556962f9612 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -3094,9 +3094,12 @@ static void myri10ge_remove(struct pci_dev *pdev) } #define PCI_DEVICE_ID_MYRICOM_MYRI10GE_Z8E 0x0008 +#define PCI_DEVICE_ID_MYRICOM_MYRI10GE_Z8E_9 0x0009 static struct pci_device_id myri10ge_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_MYRICOM, PCI_DEVICE_ID_MYRICOM_MYRI10GE_Z8E)}, + {PCI_DEVICE + (PCI_VENDOR_ID_MYRICOM, PCI_DEVICE_ID_MYRICOM_MYRI10GE_Z8E_9)}, {0}, }; diff --git a/drivers/net/pcmcia/3c589_cs.c b/drivers/net/pcmcia/3c589_cs.c index c06cae3f0b5..503f2685fb7 100644 --- a/drivers/net/pcmcia/3c589_cs.c +++ b/drivers/net/pcmcia/3c589_cs.c @@ -116,7 +116,7 @@ struct el3_private { spinlock_t lock; }; -static const char *if_names[] = { "auto", "10base2", "10baseT", "AUI" }; +static const char *if_names[] = { "auto", "10baseT", "10base2", "AUI" }; /*====================================================================*/ diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 0cc4369cacb..cb230f44d6f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -409,6 +409,7 @@ int phy_mii_ioctl(struct phy_device *phydev, return 0; } +EXPORT_SYMBOL(phy_mii_ioctl); /** * phy_start_aneg - start auto-negotiation for this PHY device diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index 0d7f570b9a5..9b30cd600a6 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -879,8 +879,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb) dev->hard_header(skb, dev, ETH_P_PPP_SES, po->pppoe_pa.remote, NULL, data_len); - if (dev_queue_xmit(skb) < 0) - goto abort; + dev_queue_xmit(skb); return 1; diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index 266e8b38fe1..abe91cb595f 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -491,44 +491,46 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) u16 hdrflags; u16 tunnel_id, session_id; int length; - struct udphdr *uh; + int offset; tunnel = pppol2tp_sock_to_tunnel(sock); if (tunnel == NULL) goto error; + /* UDP always verifies the packet length. */ + __skb_pull(skb, sizeof(struct udphdr)); + /* Short packet? */ - if (skb->len < sizeof(struct udphdr)) { + if (!pskb_may_pull(skb, 12)) { PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); goto error; } /* Point to L2TP header */ - ptr = skb->data + sizeof(struct udphdr); + ptr = skb->data; /* Get L2TP header flags */ hdrflags = ntohs(*(__be16*)ptr); /* Trace packet contents, if enabled */ if (tunnel->debug & PPPOL2TP_MSG_DATA) { + length = min(16u, skb->len); + if (!pskb_may_pull(skb, length)) + goto error; + printk(KERN_DEBUG "%s: recv: ", tunnel->name); - for (length = 0; length < 16; length++) - printk(" %02X", ptr[length]); + offset = 0; + do { + printk(" %02X", ptr[offset]); + } while (++offset < length); + printk("\n"); } /* Get length of L2TP packet */ - uh = (struct udphdr *) skb_transport_header(skb); - length = ntohs(uh->len) - sizeof(struct udphdr); - - /* Too short? */ - if (length < 12) { - PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO, - "%s: recv short L2TP packet (len=%d)\n", tunnel->name, length); - goto error; - } + length = skb->len; /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) { @@ -606,7 +608,6 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) "%s: recv data has no seq numbers when required. " "Discarding\n", session->name); session->stats.rx_seq_discards++; - session->stats.rx_errors++; goto discard; } @@ -625,7 +626,6 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) "%s: recv data has no seq numbers when required. " "Discarding\n", session->name); session->stats.rx_seq_discards++; - session->stats.rx_errors++; goto discard; } @@ -634,10 +634,14 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) } /* If offset bit set, skip it. */ - if (hdrflags & L2TP_HDRFLAG_O) - ptr += 2 + ntohs(*(__be16 *) ptr); + if (hdrflags & L2TP_HDRFLAG_O) { + offset = ntohs(*(__be16 *)ptr); + skb->transport_header += 2 + offset; + if (!pskb_may_pull(skb, skb_transport_offset(skb) + 2)) + goto discard; + } - skb_pull(skb, ptr - skb->data); + __skb_pull(skb, skb_transport_offset(skb)); /* Skip PPP header, if present. In testing, Microsoft L2TP clients * don't send the PPP header (PPP header compression enabled), but @@ -673,7 +677,6 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) */ if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) { session->stats.rx_seq_discards++; - session->stats.rx_errors++; PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG, "%s: oos pkt %hu len %d discarded, " "waiting for %hu, reorder_q_len=%d\n", @@ -698,6 +701,7 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb) return 0; discard: + session->stats.rx_errors++; kfree_skb(skb); sock_put(session->sock); @@ -958,7 +962,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) int data_len = skb->len; struct inet_sock *inet; __wsum csum = 0; - struct sk_buff *skb2 = NULL; struct udphdr *uh; unsigned int len; @@ -989,41 +992,30 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) */ headroom = NET_SKB_PAD + sizeof(struct iphdr) + sizeof(struct udphdr) + hdr_len + sizeof(ppph); - if (skb_headroom(skb) < headroom) { - skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) - goto abort; - } else - skb2 = skb; - - /* Check that the socket has room */ - if (atomic_read(&sk_tun->sk_wmem_alloc) < sk_tun->sk_sndbuf) - skb_set_owner_w(skb2, sk_tun); - else - goto discard; + if (skb_cow_head(skb, headroom)) + goto abort; /* Setup PPP header */ - skb_push(skb2, sizeof(ppph)); - skb2->data[0] = ppph[0]; - skb2->data[1] = ppph[1]; + __skb_push(skb, sizeof(ppph)); + skb->data[0] = ppph[0]; + skb->data[1] = ppph[1]; /* Setup L2TP header */ - skb_push(skb2, hdr_len); - pppol2tp_build_l2tp_header(session, skb2->data); + pppol2tp_build_l2tp_header(session, __skb_push(skb, hdr_len)); /* Setup UDP header */ inet = inet_sk(sk_tun); - skb_push(skb2, sizeof(struct udphdr)); - skb_reset_transport_header(skb2); - uh = (struct udphdr *) skb2->data; + __skb_push(skb, sizeof(*uh)); + skb_reset_transport_header(skb); + uh = udp_hdr(skb); uh->source = inet->sport; uh->dest = inet->dport; uh->len = htons(sizeof(struct udphdr) + hdr_len + sizeof(ppph) + data_len); uh->check = 0; - /* Calculate UDP checksum if configured to do so */ + /* *BROKEN* Calculate UDP checksum if configured to do so */ if (sk_tun->sk_no_check != UDP_CSUM_NOXMIT) - csum = udp_csum_outgoing(sk_tun, skb2); + csum = udp_csum_outgoing(sk_tun, skb); /* Debug */ if (session->send_seq) @@ -1036,7 +1028,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (session->debug & PPPOL2TP_MSG_DATA) { int i; - unsigned char *datap = skb2->data; + unsigned char *datap = skb->data; printk(KERN_DEBUG "%s: xmit:", session->name); for (i = 0; i < data_len; i++) { @@ -1049,18 +1041,18 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) printk("\n"); } - memset(&(IPCB(skb2)->opt), 0, sizeof(IPCB(skb2)->opt)); - IPCB(skb2)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | - IPSKB_REROUTED); - nf_reset(skb2); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); + nf_reset(skb); /* Get routing info from the tunnel socket */ - dst_release(skb2->dst); - skb2->dst = sk_dst_get(sk_tun); + dst_release(skb->dst); + skb->dst = sk_dst_get(sk_tun); /* Queue the packet to IP for output */ - len = skb2->len; - rc = ip_queue_xmit(skb2, 1); + len = skb->len; + rc = ip_queue_xmit(skb, 1); /* Update stats */ if (rc >= 0) { @@ -1073,17 +1065,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) session->stats.tx_errors++; } - /* Free the original skb */ - kfree_skb(skb); - return 1; -discard: - /* Free the new skb. Caller will free original skb. */ - if (skb2 != skb) - kfree_skb(skb2); abort: - return 0; + /* Free the original skb */ + kfree_skb(skb); + return 1; } /***************************************************************************** @@ -1326,12 +1313,14 @@ static struct sock *pppol2tp_prepare_tunnel_socket(int fd, u16 tunnel_id, goto err; } + sk = sock->sk; + /* Quick sanity checks */ - err = -ESOCKTNOSUPPORT; - if (sock->type != SOCK_DGRAM) { + err = -EPROTONOSUPPORT; + if (sk->sk_protocol != IPPROTO_UDP) { PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR, - "tunl %hu: fd %d wrong type, got %d, expected %d\n", - tunnel_id, fd, sock->type, SOCK_DGRAM); + "tunl %hu: fd %d wrong protocol, got %d, expected %d\n", + tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); goto err; } err = -EAFNOSUPPORT; @@ -1343,7 +1332,6 @@ static struct sock *pppol2tp_prepare_tunnel_socket(int fd, u16 tunnel_id, } err = -ENOTCONN; - sk = sock->sk; /* Check if this socket has already been prepped */ tunnel = (struct pppol2tp_tunnel *)sk->sk_user_data; diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index b85ab4a8f2a..c921ec32c23 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -1228,7 +1228,10 @@ static void rtl8169_hw_phy_config(struct net_device *dev) return; } - /* phy config for RTL8169s mac_version C chip */ + if ((tp->mac_version != RTL_GIGA_MAC_VER_02) && + (tp->mac_version != RTL_GIGA_MAC_VER_03)) + return; + mdio_write(ioaddr, 31, 0x0001); //w 31 2 0 1 mdio_write(ioaddr, 21, 0x1000); //w 21 15 0 1000 mdio_write(ioaddr, 24, 0x65c7); //w 24 15 0 65c7 @@ -2567,6 +2570,15 @@ static void rtl8169_tx_interrupt(struct net_device *dev, (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)) { netif_wake_queue(dev); } + /* + * 8168 hack: TxPoll requests are lost when the Tx packets are + * too close. Let's kick an extra TxPoll request when a burst + * of start_xmit activity is detected (if it is not detected, + * it is slow enough). -- FR + */ + smp_rmb(); + if (tp->cur_tx != dirty_tx) + RTL_W8(TxPoll, NPQ); } } diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 5d812de65d9..0792031a5cf 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -51,7 +51,7 @@ #include "sky2.h" #define DRV_NAME "sky2" -#define DRV_VERSION "1.17" +#define DRV_VERSION "1.18" #define PFX DRV_NAME " " /* @@ -118,12 +118,15 @@ static const struct pci_device_id sky2_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4351) }, /* 88E8036 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4352) }, /* 88E8038 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4353) }, /* 88E8039 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4354) }, /* 88E8040 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4356) }, /* 88EC033 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x435A) }, /* 88E8048 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4360) }, /* 88E8052 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4361) }, /* 88E8050 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4362) }, /* 88E8053 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4363) }, /* 88E8055 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4364) }, /* 88E8056 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4365) }, /* 88E8070 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4366) }, /* 88EC036 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4367) }, /* 88EC032 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4368) }, /* 88EC034 */ @@ -147,6 +150,7 @@ static const char *yukon2_name[] = { "Extreme", /* 0xb5 */ "EC", /* 0xb6 */ "FE", /* 0xb7 */ + "FE+", /* 0xb8 */ }; static void sky2_set_multicast(struct net_device *dev); @@ -217,8 +221,7 @@ static void sky2_power_on(struct sky2_hw *hw) else sky2_write8(hw, B2_Y2_CLK_GATE, 0); - if (hw->chip_id == CHIP_ID_YUKON_EC_U || - hw->chip_id == CHIP_ID_YUKON_EX) { + if (hw->flags & SKY2_HW_ADV_POWER_CTL) { u32 reg; sky2_pci_write32(hw, PCI_DEV_REG3, 0); @@ -311,10 +314,8 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) struct sky2_port *sky2 = netdev_priv(hw->dev[port]); u16 ctrl, ct1000, adv, pg, ledctrl, ledover, reg; - if (sky2->autoneg == AUTONEG_ENABLE - && !(hw->chip_id == CHIP_ID_YUKON_XL - || hw->chip_id == CHIP_ID_YUKON_EC_U - || hw->chip_id == CHIP_ID_YUKON_EX)) { + if (sky2->autoneg == AUTONEG_ENABLE && + !(hw->flags & SKY2_HW_NEWER_PHY)) { u16 ectrl = gm_phy_read(hw, port, PHY_MARV_EXT_CTRL); ectrl &= ~(PHY_M_EC_M_DSC_MSK | PHY_M_EC_S_DSC_MSK | @@ -334,9 +335,19 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) ctrl = gm_phy_read(hw, port, PHY_MARV_PHY_CTRL); if (sky2_is_copper(hw)) { - if (hw->chip_id == CHIP_ID_YUKON_FE) { + if (!(hw->flags & SKY2_HW_GIGABIT)) { /* enable automatic crossover */ ctrl |= PHY_M_PC_MDI_XMODE(PHY_M_PC_ENA_AUTO) >> 1; + + if (hw->chip_id == CHIP_ID_YUKON_FE_P && + hw->chip_rev == CHIP_REV_YU_FE2_A0) { + u16 spec; + + /* Enable Class A driver for FE+ A0 */ + spec = gm_phy_read(hw, port, PHY_MARV_FE_SPEC_2); + spec |= PHY_M_FESC_SEL_CL_A; + gm_phy_write(hw, port, PHY_MARV_FE_SPEC_2, spec); + } } else { /* disable energy detect */ ctrl &= ~PHY_M_PC_EN_DET_MSK; @@ -346,9 +357,7 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) /* downshift on PHY 88E1112 and 88E1149 is changed */ if (sky2->autoneg == AUTONEG_ENABLE - && (hw->chip_id == CHIP_ID_YUKON_XL - || hw->chip_id == CHIP_ID_YUKON_EC_U - || hw->chip_id == CHIP_ID_YUKON_EX)) { + && (hw->flags & SKY2_HW_NEWER_PHY)) { /* set downshift counter to 3x and enable downshift */ ctrl &= ~PHY_M_PC_DSC_MSK; ctrl |= PHY_M_PC_DSC(2) | PHY_M_PC_DOWN_S_ENA; @@ -364,7 +373,7 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) gm_phy_write(hw, port, PHY_MARV_PHY_CTRL, ctrl); /* special setup for PHY 88E1112 Fiber */ - if (hw->chip_id == CHIP_ID_YUKON_XL && !sky2_is_copper(hw)) { + if (hw->chip_id == CHIP_ID_YUKON_XL && (hw->flags & SKY2_HW_FIBRE_PHY)) { pg = gm_phy_read(hw, port, PHY_MARV_EXT_ADR); /* Fiber: select 1000BASE-X only mode MAC Specific Ctrl Reg. */ @@ -455,7 +464,7 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) gma_write16(hw, port, GM_GP_CTRL, reg); - if (hw->chip_id != CHIP_ID_YUKON_FE) + if (hw->flags & SKY2_HW_GIGABIT) gm_phy_write(hw, port, PHY_MARV_1000T_CTRL, ct1000); gm_phy_write(hw, port, PHY_MARV_AUNE_ADV, adv); @@ -479,6 +488,23 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) gm_phy_write(hw, port, PHY_MARV_FE_LED_PAR, ctrl); break; + case CHIP_ID_YUKON_FE_P: + /* Enable Link Partner Next Page */ + ctrl = gm_phy_read(hw, port, PHY_MARV_PHY_CTRL); + ctrl |= PHY_M_PC_ENA_LIP_NP; + + /* disable Energy Detect and enable scrambler */ + ctrl &= ~(PHY_M_PC_ENA_ENE_DT | PHY_M_PC_DIS_SCRAMB); + gm_phy_write(hw, port, PHY_MARV_PHY_CTRL, ctrl); + + /* set LED2 -> ACT, LED1 -> LINK, LED0 -> SPEED */ + ctrl = PHY_M_FELP_LED2_CTRL(LED_PAR_CTRL_ACT_BL) | + PHY_M_FELP_LED1_CTRL(LED_PAR_CTRL_LINK) | + PHY_M_FELP_LED0_CTRL(LED_PAR_CTRL_SPEED); + + gm_phy_write(hw, port, PHY_MARV_FE_LED_PAR, ctrl); + break; + case CHIP_ID_YUKON_XL: pg = gm_phy_read(hw, port, PHY_MARV_EXT_ADR); @@ -548,7 +574,13 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) /* set page register to 0 */ gm_phy_write(hw, port, PHY_MARV_EXT_ADR, 0); + } else if (hw->chip_id == CHIP_ID_YUKON_FE_P && + hw->chip_rev == CHIP_REV_YU_FE2_A0) { + /* apply workaround for integrated resistors calibration */ + gm_phy_write(hw, port, PHY_MARV_PAGE_ADDR, 17); + gm_phy_write(hw, port, PHY_MARV_PAGE_DATA, 0x3f60); } else if (hw->chip_id != CHIP_ID_YUKON_EX) { + /* no effect on Yukon-XL */ gm_phy_write(hw, port, PHY_MARV_LED_CTRL, ledctrl); if (sky2->autoneg == AUTONEG_DISABLE || sky2->speed == SPEED_100) { @@ -669,25 +701,25 @@ static void sky2_wol_init(struct sky2_port *sky2) static void sky2_set_tx_stfwd(struct sky2_hw *hw, unsigned port) { - if (hw->chip_id == CHIP_ID_YUKON_EX && hw->chip_rev != CHIP_REV_YU_EX_A0) { + struct net_device *dev = hw->dev[port]; + + if (dev->mtu <= ETH_DATA_LEN) sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), - TX_STFW_ENA | - (hw->dev[port]->mtu > ETH_DATA_LEN) ? TX_JUMBO_ENA : TX_JUMBO_DIS); - } else { - if (hw->dev[port]->mtu > ETH_DATA_LEN) { - /* set Tx GMAC FIFO Almost Empty Threshold */ - sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR), - (ECU_JUMBO_WM << 16) | ECU_AE_THR); + TX_JUMBO_DIS | TX_STFW_ENA); - sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), - TX_JUMBO_ENA | TX_STFW_DIS); + else if (hw->chip_id != CHIP_ID_YUKON_EC_U) + sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), + TX_STFW_ENA | TX_JUMBO_ENA); + else { + /* set Tx GMAC FIFO Almost Empty Threshold */ + sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR), + (ECU_JUMBO_WM << 16) | ECU_AE_THR); - /* Can't do offload because of lack of store/forward */ - hw->dev[port]->features &= ~(NETIF_F_TSO | NETIF_F_SG - | NETIF_F_ALL_CSUM); - } else - sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), - TX_JUMBO_DIS | TX_STFW_ENA); + sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), + TX_JUMBO_ENA | TX_STFW_DIS); + + /* Can't do offload because of lack of store/forward */ + dev->features &= ~(NETIF_F_TSO | NETIF_F_SG | NETIF_F_ALL_CSUM); } } @@ -773,7 +805,8 @@ static void sky2_mac_init(struct sky2_hw *hw, unsigned port) /* Configure Rx MAC FIFO */ sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_CLR); rx_reg = GMF_OPER_ON | GMF_RX_F_FL_ON; - if (hw->chip_id == CHIP_ID_YUKON_EX) + if (hw->chip_id == CHIP_ID_YUKON_EX || + hw->chip_id == CHIP_ID_YUKON_FE_P) rx_reg |= GMF_RX_OVER_ON; sky2_write32(hw, SK_REG(port, RX_GMF_CTRL_T), rx_reg); @@ -782,13 +815,19 @@ static void sky2_mac_init(struct sky2_hw *hw, unsigned port) sky2_write16(hw, SK_REG(port, RX_GMF_FL_MSK), GMR_FS_ANY_ERR); /* Set threshold to 0xa (64 bytes) + 1 to workaround pause bug */ - sky2_write16(hw, SK_REG(port, RX_GMF_FL_THR), RX_GMF_FL_THR_DEF+1); + reg = RX_GMF_FL_THR_DEF + 1; + /* Another magic mystery workaround from sk98lin */ + if (hw->chip_id == CHIP_ID_YUKON_FE_P && + hw->chip_rev == CHIP_REV_YU_FE2_A0) + reg = 0x178; + sky2_write16(hw, SK_REG(port, RX_GMF_FL_THR), reg); /* Configure Tx MAC FIFO */ sky2_write8(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_RST_CLR); sky2_write16(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_OPER_ON); - if (hw->chip_id == CHIP_ID_YUKON_EC_U || hw->chip_id == CHIP_ID_YUKON_EX) { + /* On chips without ram buffer, pause is controled by MAC level */ + if (sky2_read8(hw, B2_E_0) == 0) { sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 768/8); sky2_write8(hw, SK_REG(port, RX_GMF_UP_THR), 1024/8); @@ -967,19 +1006,15 @@ static void sky2_rx_unmap_skb(struct pci_dev *pdev, struct rx_ring_info *re) */ static void rx_set_checksum(struct sky2_port *sky2) { - struct sky2_rx_le *le; + struct sky2_rx_le *le = sky2_next_rx(sky2); - if (sky2->hw->chip_id != CHIP_ID_YUKON_EX) { - le = sky2_next_rx(sky2); - le->addr = cpu_to_le32((ETH_HLEN << 16) | ETH_HLEN); - le->ctrl = 0; - le->opcode = OP_TCPSTART | HW_OWNER; - - sky2_write32(sky2->hw, - Q_ADDR(rxqaddr[sky2->port], Q_CSR), - sky2->rx_csum ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); - } + le->addr = cpu_to_le32((ETH_HLEN << 16) | ETH_HLEN); + le->ctrl = 0; + le->opcode = OP_TCPSTART | HW_OWNER; + sky2_write32(sky2->hw, + Q_ADDR(rxqaddr[sky2->port], Q_CSR), + sky2->rx_csum ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); } /* @@ -1175,7 +1210,8 @@ static int sky2_rx_start(struct sky2_port *sky2) sky2_prefetch_init(hw, rxq, sky2->rx_le_map, RX_LE_SIZE - 1); - rx_set_checksum(sky2); + if (!(hw->flags & SKY2_HW_NEW_LE)) + rx_set_checksum(sky2); /* Space needed for frame data + headers rounded up */ size = roundup(sky2->netdev->mtu + ETH_HLEN + VLAN_HLEN, 8); @@ -1246,7 +1282,7 @@ static int sky2_up(struct net_device *dev) struct sky2_port *sky2 = netdev_priv(dev); struct sky2_hw *hw = sky2->hw; unsigned port = sky2->port; - u32 ramsize, imask; + u32 imask, ramsize; int cap, err = -ENOMEM; struct net_device *otherdev = hw->dev[sky2->port^1]; @@ -1303,11 +1339,10 @@ static int sky2_up(struct net_device *dev) /* Register is number of 4K blocks on internal RAM buffer. */ ramsize = sky2_read8(hw, B2_E_0) * 4; - printk(KERN_INFO PFX "%s: ram buffer %dK\n", dev->name, ramsize); - if (ramsize > 0) { u32 rxspace; + pr_debug(PFX "%s: ram buffer %dK\n", dev->name, ramsize); if (ramsize < 16) rxspace = ramsize / 2; else @@ -1436,13 +1471,15 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev) /* Check for TCP Segmentation Offload */ mss = skb_shinfo(skb)->gso_size; if (mss != 0) { - if (hw->chip_id != CHIP_ID_YUKON_EX) + + if (!(hw->flags & SKY2_HW_NEW_LE)) mss += ETH_HLEN + ip_hdrlen(skb) + tcp_hdrlen(skb); if (mss != sky2->tx_last_mss) { le = get_tx_le(sky2); le->addr = cpu_to_le32(mss); - if (hw->chip_id == CHIP_ID_YUKON_EX) + + if (hw->flags & SKY2_HW_NEW_LE) le->opcode = OP_MSS | HW_OWNER; else le->opcode = OP_LRGLEN | HW_OWNER; @@ -1468,8 +1505,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev) /* Handle TCP checksum offload */ if (skb->ip_summed == CHECKSUM_PARTIAL) { /* On Yukon EX (some versions) encoding change. */ - if (hw->chip_id == CHIP_ID_YUKON_EX - && hw->chip_rev != CHIP_REV_YU_EX_B0) + if (hw->flags & SKY2_HW_AUTO_TX_SUM) ctrl |= CALSUM; /* auto checksum */ else { const unsigned offset = skb_transport_offset(skb); @@ -1622,9 +1658,6 @@ static int sky2_down(struct net_device *dev) if (netif_msg_ifdown(sky2)) printk(KERN_INFO PFX "%s: disabling interface\n", dev->name); - if (netif_carrier_ok(dev) && --hw->active == 0) - del_timer(&hw->watchdog_timer); - /* Stop more packets from being queued */ netif_stop_queue(dev); @@ -1708,11 +1741,15 @@ static int sky2_down(struct net_device *dev) static u16 sky2_phy_speed(const struct sky2_hw *hw, u16 aux) { - if (!sky2_is_copper(hw)) + if (hw->flags & SKY2_HW_FIBRE_PHY) return SPEED_1000; - if (hw->chip_id == CHIP_ID_YUKON_FE) - return (aux & PHY_M_PS_SPEED_100) ? SPEED_100 : SPEED_10; + if (!(hw->flags & SKY2_HW_GIGABIT)) { + if (aux & PHY_M_PS_SPEED_100) + return SPEED_100; + else + return SPEED_10; + } switch (aux & PHY_M_PS_SPEED_MSK) { case PHY_M_PS_SPEED_1000: @@ -1745,17 +1782,13 @@ static void sky2_link_up(struct sky2_port *sky2) netif_carrier_on(sky2->netdev); - if (hw->active++ == 0) - mod_timer(&hw->watchdog_timer, jiffies + 1); - + mod_timer(&hw->watchdog_timer, jiffies + 1); /* Turn on link LED */ sky2_write8(hw, SK_REG(port, LNK_LED_REG), LINKLED_ON | LINKLED_BLINK_OFF | LINKLED_LINKSYNC_OFF); - if (hw->chip_id == CHIP_ID_YUKON_XL - || hw->chip_id == CHIP_ID_YUKON_EC_U - || hw->chip_id == CHIP_ID_YUKON_EX) { + if (hw->flags & SKY2_HW_NEWER_PHY) { u16 pg = gm_phy_read(hw, port, PHY_MARV_EXT_ADR); u16 led = PHY_M_LEDC_LOS_CTRL(1); /* link active */ @@ -1800,11 +1833,6 @@ static void sky2_link_down(struct sky2_port *sky2) netif_carrier_off(sky2->netdev); - /* Stop watchdog if both ports are not active */ - if (--hw->active == 0) - del_timer(&hw->watchdog_timer); - - /* Turn on link LED */ sky2_write8(hw, SK_REG(port, LNK_LED_REG), LINKLED_OFF); @@ -1847,7 +1875,7 @@ static int sky2_autoneg_done(struct sky2_port *sky2, u16 aux) /* Since the pause result bits seem to in different positions on * different chips. look at registers. */ - if (!sky2_is_copper(hw)) { + if (hw->flags & SKY2_HW_FIBRE_PHY) { /* Shift for bits in fiber PHY */ advert &= ~(ADVERTISE_PAUSE_CAP|ADVERTISE_PAUSE_ASYM); lpa &= ~(LPA_PAUSE_CAP|LPA_PAUSE_ASYM); @@ -1958,7 +1986,9 @@ static int sky2_change_mtu(struct net_device *dev, int new_mtu) if (new_mtu < ETH_ZLEN || new_mtu > ETH_JUMBO_MTU) return -EINVAL; - if (new_mtu > ETH_DATA_LEN && hw->chip_id == CHIP_ID_YUKON_FE) + if (new_mtu > ETH_DATA_LEN && + (hw->chip_id == CHIP_ID_YUKON_FE || + hw->chip_id == CHIP_ID_YUKON_FE_P)) return -EINVAL; if (!netif_running(dev)) { @@ -1975,7 +2005,7 @@ static int sky2_change_mtu(struct net_device *dev, int new_mtu) synchronize_irq(hw->pdev->irq); - if (hw->chip_id == CHIP_ID_YUKON_EC_U || hw->chip_id == CHIP_ID_YUKON_EX) + if (sky2_read8(hw, B2_E_0) == 0) sky2_set_tx_stfwd(hw, port); ctl = gma_read16(hw, port, GM_GP_CTRL); @@ -2103,6 +2133,13 @@ static struct sk_buff *sky2_receive(struct net_device *dev, struct sky2_port *sky2 = netdev_priv(dev); struct rx_ring_info *re = sky2->rx_ring + sky2->rx_next; struct sk_buff *skb = NULL; + u16 count = (status & GMR_FS_LEN) >> 16; + +#ifdef SKY2_VLAN_TAG_USED + /* Account for vlan tag */ + if (sky2->vlgrp && (status & GMR_FS_VLAN)) + count -= VLAN_HLEN; +#endif if (unlikely(netif_msg_rx_status(sky2))) printk(KERN_DEBUG PFX "%s: rx slot %u status 0x%x len %d\n", @@ -2117,7 +2154,8 @@ static struct sk_buff *sky2_receive(struct net_device *dev, if (!(status & GMR_FS_RX_OK)) goto resubmit; - if (status >> 16 != length) + /* if length reported by DMA does not match PHY, packet was truncated */ + if (length != count) goto len_mismatch; if (length < copybreak) @@ -2133,6 +2171,10 @@ len_mismatch: /* Truncation of overlength packets causes PHY length to not match MAC length */ ++sky2->net_stats.rx_length_errors; + if (netif_msg_rx_err(sky2) && net_ratelimit()) + pr_info(PFX "%s: rx length mismatch: length %d status %#x\n", + dev->name, length, status); + goto resubmit; error: ++sky2->net_stats.rx_errors; @@ -2202,7 +2244,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do) } /* This chip reports checksum status differently */ - if (hw->chip_id == CHIP_ID_YUKON_EX) { + if (hw->flags & SKY2_HW_NEW_LE) { if (sky2->rx_csum && (le->css & (CSS_ISIPV4 | CSS_ISIPV6)) && (le->css & CSS_TCPUDPCSOK)) @@ -2243,8 +2285,14 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do) if (!sky2->rx_csum) break; - if (hw->chip_id == CHIP_ID_YUKON_EX) + /* If this happens then driver assuming wrong format */ + if (unlikely(hw->flags & SKY2_HW_NEW_LE)) { + if (net_ratelimit()) + printk(KERN_NOTICE "%s: unexpected" + " checksum status\n", + dev->name); break; + } /* Both checksum counters are programmed to start at * the same offset, so unless there is a problem they @@ -2436,20 +2484,72 @@ static void sky2_le_error(struct sky2_hw *hw, unsigned port, sky2_write32(hw, Q_ADDR(q, Q_CSR), BMU_CLR_IRQ_CHK); } -/* Check for lost IRQ once a second */ +static int sky2_rx_hung(struct net_device *dev) +{ + struct sky2_port *sky2 = netdev_priv(dev); + struct sky2_hw *hw = sky2->hw; + unsigned port = sky2->port; + unsigned rxq = rxqaddr[port]; + u32 mac_rp = sky2_read32(hw, SK_REG(port, RX_GMF_RP)); + u8 mac_lev = sky2_read8(hw, SK_REG(port, RX_GMF_RLEV)); + u8 fifo_rp = sky2_read8(hw, Q_ADDR(rxq, Q_RP)); + u8 fifo_lev = sky2_read8(hw, Q_ADDR(rxq, Q_RL)); + + /* If idle and MAC or PCI is stuck */ + if (sky2->check.last == dev->last_rx && + ((mac_rp == sky2->check.mac_rp && + mac_lev != 0 && mac_lev >= sky2->check.mac_lev) || + /* Check if the PCI RX hang */ + (fifo_rp == sky2->check.fifo_rp && + fifo_lev != 0 && fifo_lev >= sky2->check.fifo_lev))) { + printk(KERN_DEBUG PFX "%s: hung mac %d:%d fifo %d (%d:%d)\n", + dev->name, mac_lev, mac_rp, fifo_lev, fifo_rp, + sky2_read8(hw, Q_ADDR(rxq, Q_WP))); + return 1; + } else { + sky2->check.last = dev->last_rx; + sky2->check.mac_rp = mac_rp; + sky2->check.mac_lev = mac_lev; + sky2->check.fifo_rp = fifo_rp; + sky2->check.fifo_lev = fifo_lev; + return 0; + } +} + static void sky2_watchdog(unsigned long arg) { struct sky2_hw *hw = (struct sky2_hw *) arg; + struct net_device *dev; + /* Check for lost IRQ once a second */ if (sky2_read32(hw, B0_ISRC)) { - struct net_device *dev = hw->dev[0]; - + dev = hw->dev[0]; if (__netif_rx_schedule_prep(dev)) __netif_rx_schedule(dev); + } else { + int i, active = 0; + + for (i = 0; i < hw->ports; i++) { + dev = hw->dev[i]; + if (!netif_running(dev)) + continue; + ++active; + + /* For chips with Rx FIFO, check if stuck */ + if ((hw->flags & SKY2_HW_FIFO_HANG_CHECK) && + sky2_rx_hung(dev)) { + pr_info(PFX "%s: receiver hang detected\n", + dev->name); + schedule_work(&hw->restart_work); + return; + } + } + + if (active == 0) + return; } - if (hw->active > 0) - mod_timer(&hw->watchdog_timer, round_jiffies(jiffies + HZ)); + mod_timer(&hw->watchdog_timer, round_jiffies(jiffies + HZ)); } /* Hardware/software error handling */ @@ -2546,17 +2646,25 @@ static void sky2_netpoll(struct net_device *dev) #endif /* Chip internal frequency for clock calculations */ -static inline u32 sky2_mhz(const struct sky2_hw *hw) +static u32 sky2_mhz(const struct sky2_hw *hw) { switch (hw->chip_id) { case CHIP_ID_YUKON_EC: case CHIP_ID_YUKON_EC_U: case CHIP_ID_YUKON_EX: - return 125; /* 125 Mhz */ + return 125; + case CHIP_ID_YUKON_FE: - return 100; /* 100 Mhz */ - default: /* YUKON_XL */ - return 156; /* 156 Mhz */ + return 100; + + case CHIP_ID_YUKON_FE_P: + return 50; + + case CHIP_ID_YUKON_XL: + return 156; + + default: + BUG(); } } @@ -2581,23 +2689,63 @@ static int __devinit sky2_init(struct sky2_hw *hw) sky2_write8(hw, B0_CTST, CS_RST_CLR); hw->chip_id = sky2_read8(hw, B2_CHIP_ID); - if (hw->chip_id < CHIP_ID_YUKON_XL || hw->chip_id > CHIP_ID_YUKON_FE) { + hw->chip_rev = (sky2_read8(hw, B2_MAC_CFG) & CFG_CHIP_R_MSK) >> 4; + + switch(hw->chip_id) { + case CHIP_ID_YUKON_XL: + hw->flags = SKY2_HW_GIGABIT + | SKY2_HW_NEWER_PHY; + if (hw->chip_rev < 3) + hw->flags |= SKY2_HW_FIFO_HANG_CHECK; + + break; + + case CHIP_ID_YUKON_EC_U: + hw->flags = SKY2_HW_GIGABIT + | SKY2_HW_NEWER_PHY + | SKY2_HW_ADV_POWER_CTL; + break; + + case CHIP_ID_YUKON_EX: + hw->flags = SKY2_HW_GIGABIT + | SKY2_HW_NEWER_PHY + | SKY2_HW_NEW_LE + | SKY2_HW_ADV_POWER_CTL; + + /* New transmit checksum */ + if (hw->chip_rev != CHIP_REV_YU_EX_B0) + hw->flags |= SKY2_HW_AUTO_TX_SUM; + break; + + case CHIP_ID_YUKON_EC: + /* This rev is really old, and requires untested workarounds */ + if (hw->chip_rev == CHIP_REV_YU_EC_A1) { + dev_err(&hw->pdev->dev, "unsupported revision Yukon-EC rev A1\n"); + return -EOPNOTSUPP; + } + hw->flags = SKY2_HW_GIGABIT | SKY2_HW_FIFO_HANG_CHECK; + break; + + case CHIP_ID_YUKON_FE: + break; + + case CHIP_ID_YUKON_FE_P: + hw->flags = SKY2_HW_NEWER_PHY + | SKY2_HW_NEW_LE + | SKY2_HW_AUTO_TX_SUM + | SKY2_HW_ADV_POWER_CTL; + break; + default: dev_err(&hw->pdev->dev, "unsupported chip type 0x%x\n", hw->chip_id); return -EOPNOTSUPP; } - hw->chip_rev = (sky2_read8(hw, B2_MAC_CFG) & CFG_CHIP_R_MSK) >> 4; + hw->pmd_type = sky2_read8(hw, B2_PMD_TYP); + if (hw->pmd_type == 'L' || hw->pmd_type == 'S' || hw->pmd_type == 'P') + hw->flags |= SKY2_HW_FIBRE_PHY; - /* This rev is really old, and requires untested workarounds */ - if (hw->chip_id == CHIP_ID_YUKON_EC && hw->chip_rev == CHIP_REV_YU_EC_A1) { - dev_err(&hw->pdev->dev, "unsupported revision Yukon-%s (0x%x) rev %d\n", - yukon2_name[hw->chip_id - CHIP_ID_YUKON_XL], - hw->chip_id, hw->chip_rev); - return -EOPNOTSUPP; - } - hw->pmd_type = sky2_read8(hw, B2_PMD_TYP); hw->ports = 1; t8 = sky2_read8(hw, B2_Y2_HW_RES); if ((t8 & CFG_DUAL_MAC_MSK) == CFG_DUAL_MAC_MSK) { @@ -2791,7 +2939,9 @@ static int sky2_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) sky2->wol = wol->wolopts; - if (hw->chip_id == CHIP_ID_YUKON_EC_U || hw->chip_id == CHIP_ID_YUKON_EX) + if (hw->chip_id == CHIP_ID_YUKON_EC_U || + hw->chip_id == CHIP_ID_YUKON_EX || + hw->chip_id == CHIP_ID_YUKON_FE_P) sky2_write32(hw, B0_CTST, sky2->wol ? Y2_HW_WOL_ON : Y2_HW_WOL_OFF); @@ -2809,7 +2959,7 @@ static u32 sky2_supported_modes(const struct sky2_hw *hw) | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP; - if (hw->chip_id != CHIP_ID_YUKON_FE) + if (hw->flags & SKY2_HW_GIGABIT) modes |= SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full; return modes; @@ -2829,13 +2979,6 @@ static int sky2_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) ecmd->supported = sky2_supported_modes(hw); ecmd->phy_address = PHY_ADDR_MARV; if (sky2_is_copper(hw)) { - ecmd->supported = SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_1000baseT_Half - | SUPPORTED_1000baseT_Full - | SUPPORTED_Autoneg | SUPPORTED_TP; ecmd->port = PORT_TP; ecmd->speed = sky2->speed; } else { @@ -3791,6 +3934,13 @@ static __devinit struct net_device *sky2_init_netdev(struct sky2_hw *hw, sky2->hw = hw; sky2->msg_enable = netif_msg_init(debug, default_msg); + /* This chip has hardware problems that generates + * bogus PHY receive status so by default shut up the message. + */ + if (hw->chip_id == CHIP_ID_YUKON_FE_P && + hw->chip_rev == CHIP_REV_YU_FE2_A0) + sky2->msg_enable &= ~NETIF_MSG_RX_ERR; + /* Auto speed and flow control */ sky2->autoneg = AUTONEG_ENABLE; sky2->flow_mode = FC_BOTH; @@ -3846,7 +3996,7 @@ static irqreturn_t __devinit sky2_test_intr(int irq, void *dev_id) return IRQ_NONE; if (status & Y2_IS_IRQ_SW) { - hw->msi = 1; + hw->flags |= SKY2_HW_USE_MSI; wake_up(&hw->msi_wait); sky2_write8(hw, B0_CTST, CS_CL_SW_IRQ); } @@ -3874,9 +4024,9 @@ static int __devinit sky2_test_msi(struct sky2_hw *hw) sky2_write8(hw, B0_CTST, CS_ST_SW_IRQ); sky2_read8(hw, B0_CTST); - wait_event_timeout(hw->msi_wait, hw->msi, HZ/10); + wait_event_timeout(hw->msi_wait, (hw->flags & SKY2_HW_USE_MSI), HZ/10); - if (!hw->msi) { + if (!(hw->flags & SKY2_HW_USE_MSI)) { /* MSI test failed, go back to INTx mode */ dev_info(&pdev->dev, "No interrupt generated using MSI, " "switching to INTx mode.\n"); @@ -4009,7 +4159,8 @@ static int __devinit sky2_probe(struct pci_dev *pdev, goto err_out_free_netdev; } - err = request_irq(pdev->irq, sky2_intr, hw->msi ? 0 : IRQF_SHARED, + err = request_irq(pdev->irq, sky2_intr, + (hw->flags & SKY2_HW_USE_MSI) ? 0 : IRQF_SHARED, dev->name, hw); if (err) { dev_err(&pdev->dev, "cannot assign irq %d\n", pdev->irq); @@ -4042,7 +4193,7 @@ static int __devinit sky2_probe(struct pci_dev *pdev, return 0; err_out_unregister: - if (hw->msi) + if (hw->flags & SKY2_HW_USE_MSI) pci_disable_msi(pdev); unregister_netdev(dev); err_out_free_netdev: @@ -4091,7 +4242,7 @@ static void __devexit sky2_remove(struct pci_dev *pdev) sky2_read8(hw, B0_CTST); free_irq(pdev->irq, hw); - if (hw->msi) + if (hw->flags & SKY2_HW_USE_MSI) pci_disable_msi(pdev); pci_free_consistent(pdev, STATUS_LE_BYTES, hw->st_le, hw->st_dma); pci_release_regions(pdev); @@ -4159,7 +4310,9 @@ static int sky2_resume(struct pci_dev *pdev) pci_enable_wake(pdev, PCI_D0, 0); /* Re-enable all clocks */ - if (hw->chip_id == CHIP_ID_YUKON_EX || hw->chip_id == CHIP_ID_YUKON_EC_U) + if (hw->chip_id == CHIP_ID_YUKON_EX || + hw->chip_id == CHIP_ID_YUKON_EC_U || + hw->chip_id == CHIP_ID_YUKON_FE_P) sky2_pci_write32(hw, PCI_DEV_REG3, 0); sky2_reset(hw); diff --git a/drivers/net/sky2.h b/drivers/net/sky2.h index 72e12b7cfa4..8bc5c54e3ef 100644 --- a/drivers/net/sky2.h +++ b/drivers/net/sky2.h @@ -470,18 +470,24 @@ enum { CHIP_ID_YUKON_EX = 0xb5, /* Chip ID for YUKON-2 Extreme */ CHIP_ID_YUKON_EC = 0xb6, /* Chip ID for YUKON-2 EC */ CHIP_ID_YUKON_FE = 0xb7, /* Chip ID for YUKON-2 FE */ - + CHIP_ID_YUKON_FE_P = 0xb8, /* Chip ID for YUKON-2 FE+ */ +}; +enum yukon_ec_rev { CHIP_REV_YU_EC_A1 = 0, /* Chip Rev. for Yukon-EC A1/A0 */ CHIP_REV_YU_EC_A2 = 1, /* Chip Rev. for Yukon-EC A2 */ CHIP_REV_YU_EC_A3 = 2, /* Chip Rev. for Yukon-EC A3 */ - +}; +enum yukon_ec_u_rev { CHIP_REV_YU_EC_U_A0 = 1, CHIP_REV_YU_EC_U_A1 = 2, CHIP_REV_YU_EC_U_B0 = 3, - +}; +enum yukon_fe_rev { CHIP_REV_YU_FE_A1 = 1, CHIP_REV_YU_FE_A2 = 2, - +}; +enum yukon_fe_p_rev { + CHIP_REV_YU_FE2_A0 = 0, }; enum yukon_ex_rev { CHIP_REV_YU_EX_A0 = 1, @@ -1668,7 +1674,7 @@ enum { /* Receive Frame Status Encoding */ enum { - GMR_FS_LEN = 0xffff<<16, /* Bit 31..16: Rx Frame Length */ + GMR_FS_LEN = 0x7fff<<16, /* Bit 30..16: Rx Frame Length */ GMR_FS_VLAN = 1<<13, /* VLAN Packet */ GMR_FS_JABBER = 1<<12, /* Jabber Packet */ GMR_FS_UN_SIZE = 1<<11, /* Undersize Packet */ @@ -1729,6 +1735,10 @@ enum { GMF_RX_CTRL_DEF = GMF_OPER_ON | GMF_RX_F_FL_ON, }; +/* TX_GMF_EA 32 bit Tx GMAC FIFO End Address */ +enum { + TX_DYN_WM_ENA = 3, /* Yukon-FE+ specific */ +}; /* TX_GMF_CTRL_T 32 bit Tx GMAC FIFO Control/Test */ enum { @@ -2017,6 +2027,14 @@ struct sky2_port { u16 rx_tag; struct vlan_group *vlgrp; #endif + struct { + unsigned long last; + u32 mac_rp; + u8 mac_lev; + u8 fifo_rp; + u8 fifo_lev; + } check; + dma_addr_t rx_le_map; dma_addr_t tx_le_map; @@ -2040,12 +2058,20 @@ struct sky2_hw { void __iomem *regs; struct pci_dev *pdev; struct net_device *dev[2]; + unsigned long flags; +#define SKY2_HW_USE_MSI 0x00000001 +#define SKY2_HW_FIBRE_PHY 0x00000002 +#define SKY2_HW_GIGABIT 0x00000004 +#define SKY2_HW_NEWER_PHY 0x00000008 +#define SKY2_HW_FIFO_HANG_CHECK 0x00000010 +#define SKY2_HW_NEW_LE 0x00000020 /* new LSOv2 format */ +#define SKY2_HW_AUTO_TX_SUM 0x00000040 /* new IP decode for Tx */ +#define SKY2_HW_ADV_POWER_CTL 0x00000080 /* additional PHY power regs */ u8 chip_id; u8 chip_rev; u8 pmd_type; u8 ports; - u8 active; struct sky2_status_le *st_le; u32 st_idx; @@ -2053,13 +2079,12 @@ struct sky2_hw { struct timer_list watchdog_timer; struct work_struct restart_work; - int msi; wait_queue_head_t msi_wait; }; static inline int sky2_is_copper(const struct sky2_hw *hw) { - return !(hw->pmd_type == 'L' || hw->pmd_type == 'S' || hw->pmd_type == 'P'); + return !(hw->flags & SKY2_HW_FIBRE_PHY); } /* Register accessor for memory mapped device */ diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c index c7c4574729b..de3155b2128 100644 --- a/drivers/power/power_supply_sysfs.c +++ b/drivers/power/power_supply_sysfs.c @@ -289,6 +289,7 @@ int power_supply_uevent(struct device *dev, char **envp, int num_envp, if (ret) goto out; } + envp[i] = NULL; out: free_page((unsigned long)prop_buf); diff --git a/fs/exec.c b/fs/exec.c index c21a8cc0627..073b0b8c6d0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -50,7 +50,6 @@ #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> -#include <linux/signalfd.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -784,7 +783,6 @@ static int de_thread(struct task_struct *tsk) * and we can just re-use it all. */ if (atomic_read(&oldsighand->count) <= 1) { - signalfd_detach(tsk); exit_itimers(sig); return 0; } @@ -923,7 +921,6 @@ static int de_thread(struct task_struct *tsk) sig->flags = 0; no_thread_group: - signalfd_detach(tsk); exit_itimers(sig); if (leader) release_task(leader); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 50cd8a20901..f37f25c931f 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -930,18 +930,11 @@ static void ocfs2_write_failure(struct inode *inode, loff_t user_pos, unsigned user_len) { int i; - unsigned from, to; + unsigned from = user_pos & (PAGE_CACHE_SIZE - 1), + to = user_pos + user_len; struct page *tmppage; - ocfs2_zero_new_buffers(wc->w_target_page, user_pos, user_len); - - if (wc->w_large_pages) { - from = wc->w_target_from; - to = wc->w_target_to; - } else { - from = 0; - to = PAGE_CACHE_SIZE; - } + ocfs2_zero_new_buffers(wc->w_target_page, from, to); for(i = 0; i < wc->w_num_pages; i++) { tmppage = wc->w_pages[i]; @@ -991,9 +984,6 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, map_from = cluster_start; map_to = cluster_end; } - - wc->w_target_from = map_from; - wc->w_target_to = map_to; } else { /* * If we haven't allocated the new page yet, we @@ -1211,18 +1201,33 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping, loff_t pos, unsigned len) { int ret, i; + loff_t cluster_off; + unsigned int local_len = len; struct ocfs2_write_cluster_desc *desc; + struct ocfs2_super *osb = OCFS2_SB(mapping->host->i_sb); for (i = 0; i < wc->w_clen; i++) { desc = &wc->w_desc[i]; + /* + * We have to make sure that the total write passed in + * doesn't extend past a single cluster. + */ + local_len = len; + cluster_off = pos & (osb->s_clustersize - 1); + if ((cluster_off + local_len) > osb->s_clustersize) + local_len = osb->s_clustersize - cluster_off; + ret = ocfs2_write_cluster(mapping, desc->c_phys, desc->c_unwritten, data_ac, meta_ac, - wc, desc->c_cpos, pos, len); + wc, desc->c_cpos, pos, local_len); if (ret) { mlog_errno(ret); goto out; } + + len -= local_len; + pos += local_len; } ret = 0; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 7e34e66159c..f3bc3658e7a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -491,8 +491,8 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb, goto leave; } - status = ocfs2_claim_clusters(osb, handle, data_ac, 1, - &bit_off, &num_bits); + status = __ocfs2_claim_clusters(osb, handle, data_ac, 1, + clusters_to_add, &bit_off, &num_bits); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 545f7892cdf..de984d27257 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -524,13 +524,12 @@ bail: int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, - u32 min_bits, + u32 bits_wanted, u32 *bit_off, u32 *num_bits) { int status, start; struct inode *local_alloc_inode; - u32 bits_wanted; void *bitmap; struct ocfs2_dinode *alloc; struct ocfs2_local_alloc *la; @@ -538,7 +537,6 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, mlog_entry_void(); BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); - bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; local_alloc_inode = ac->ac_inode; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h index 385a10152f9..3f76631e110 100644 --- a/fs/ocfs2/localalloc.h +++ b/fs/ocfs2/localalloc.h @@ -48,7 +48,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, - u32 min_bits, + u32 bits_wanted, u32 *bit_off, u32 *num_bits); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d9c5c9fcb30..8f09f5235e3 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1486,21 +1486,21 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode, * contig. allocation, set to '1' to indicate we can deal with extents * of any size. */ -int ocfs2_claim_clusters(struct ocfs2_super *osb, - handle_t *handle, - struct ocfs2_alloc_context *ac, - u32 min_clusters, - u32 *cluster_start, - u32 *num_clusters) +int __ocfs2_claim_clusters(struct ocfs2_super *osb, + handle_t *handle, + struct ocfs2_alloc_context *ac, + u32 min_clusters, + u32 max_clusters, + u32 *cluster_start, + u32 *num_clusters) { int status; - unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; + unsigned int bits_wanted = max_clusters; u64 bg_blkno = 0; u16 bg_bit_off; mlog_entry_void(); - BUG_ON(!ac); BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted); BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL @@ -1557,6 +1557,19 @@ bail: return status; } +int ocfs2_claim_clusters(struct ocfs2_super *osb, + handle_t *handle, + struct ocfs2_alloc_context *ac, + u32 min_clusters, + u32 *cluster_start, + u32 *num_clusters) +{ + unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; + + return __ocfs2_claim_clusters(osb, handle, ac, min_clusters, + bits_wanted, cluster_start, num_clusters); +} + static inline int ocfs2_block_group_clear_bits(handle_t *handle, struct inode *alloc_inode, struct ocfs2_group_desc *bg, diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index f212dc01a84..cafe9370309 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -85,6 +85,17 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb, u32 min_clusters, u32 *cluster_start, u32 *num_clusters); +/* + * Use this variant of ocfs2_claim_clusters to specify a maxiumum + * number of clusters smaller than the allocation reserved. + */ +int __ocfs2_claim_clusters(struct ocfs2_super *osb, + handle_t *handle, + struct ocfs2_alloc_context *ac, + u32 min_clusters, + u32 max_clusters, + u32 *cluster_start, + u32 *num_clusters); int ocfs2_free_suballoc_bits(handle_t *handle, struct inode *alloc_inode, diff --git a/fs/ocfs2/vote.c b/fs/ocfs2/vote.c index 66a13ee63d4..c05358538f2 100644 --- a/fs/ocfs2/vote.c +++ b/fs/ocfs2/vote.c @@ -66,7 +66,7 @@ struct ocfs2_vote_msg { struct ocfs2_msg_hdr v_hdr; __be32 v_reserved1; -}; +} __attribute__ ((packed)); /* Responses are given these values to maintain backwards * compatibility with older ocfs2 versions */ @@ -78,7 +78,7 @@ struct ocfs2_response_msg { struct ocfs2_msg_hdr r_hdr; __be32 r_response; -}; +} __attribute__ ((packed)); struct ocfs2_vote_work { struct list_head w_list; diff --git a/fs/signalfd.c b/fs/signalfd.c index a8e293d3003..aefb0be0794 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -11,8 +11,10 @@ * Now using anonymous inode source. * Thanks to Oleg Nesterov for useful code review and suggestions. * More comments and suggestions from Arnd Bergmann. - * Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br> + * Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br> * Retrieve multiple signals with one read() call + * Sun Jul 15, 2007: Davide Libenzi <davidel@xmailserver.org> + * Attach to the sighand only during read() and poll(). */ #include <linux/file.h> @@ -27,102 +29,12 @@ #include <linux/signalfd.h> struct signalfd_ctx { - struct list_head lnk; - wait_queue_head_t wqh; sigset_t sigmask; - struct task_struct *tsk; }; -struct signalfd_lockctx { - struct task_struct *tsk; - unsigned long flags; -}; - -/* - * Tries to acquire the sighand lock. We do not increment the sighand - * use count, and we do not even pin the task struct, so we need to - * do it inside an RCU read lock, and we must be prepared for the - * ctx->tsk going to NULL (in signalfd_deliver()), and for the sighand - * being detached. We return 0 if the sighand has been detached, or - * 1 if we were able to pin the sighand lock. - */ -static int signalfd_lock(struct signalfd_ctx *ctx, struct signalfd_lockctx *lk) -{ - struct sighand_struct *sighand = NULL; - - rcu_read_lock(); - lk->tsk = rcu_dereference(ctx->tsk); - if (likely(lk->tsk != NULL)) - sighand = lock_task_sighand(lk->tsk, &lk->flags); - rcu_read_unlock(); - - if (!sighand) - return 0; - - if (!ctx->tsk) { - unlock_task_sighand(lk->tsk, &lk->flags); - return 0; - } - - if (lk->tsk->tgid == current->tgid) - lk->tsk = current; - - return 1; -} - -static void signalfd_unlock(struct signalfd_lockctx *lk) -{ - unlock_task_sighand(lk->tsk, &lk->flags); -} - -/* - * This must be called with the sighand lock held. - */ -void signalfd_deliver(struct task_struct *tsk, int sig) -{ - struct sighand_struct *sighand = tsk->sighand; - struct signalfd_ctx *ctx, *tmp; - - BUG_ON(!sig); - list_for_each_entry_safe(ctx, tmp, &sighand->signalfd_list, lnk) { - /* - * We use a negative signal value as a way to broadcast that the - * sighand has been orphaned, so that we can notify all the - * listeners about this. Remember the ctx->sigmask is inverted, - * so if the user is interested in a signal, that corresponding - * bit will be zero. - */ - if (sig < 0) { - if (ctx->tsk == tsk) { - ctx->tsk = NULL; - list_del_init(&ctx->lnk); - wake_up(&ctx->wqh); - } - } else { - if (!sigismember(&ctx->sigmask, sig)) - wake_up(&ctx->wqh); - } - } -} - -static void signalfd_cleanup(struct signalfd_ctx *ctx) -{ - struct signalfd_lockctx lk; - - /* - * This is tricky. If the sighand is gone, we do not need to remove - * context from the list, the list itself won't be there anymore. - */ - if (signalfd_lock(ctx, &lk)) { - list_del(&ctx->lnk); - signalfd_unlock(&lk); - } - kfree(ctx); -} - static int signalfd_release(struct inode *inode, struct file *file) { - signalfd_cleanup(file->private_data); + kfree(file->private_data); return 0; } @@ -130,23 +42,15 @@ static unsigned int signalfd_poll(struct file *file, poll_table *wait) { struct signalfd_ctx *ctx = file->private_data; unsigned int events = 0; - struct signalfd_lockctx lk; - poll_wait(file, &ctx->wqh, wait); + poll_wait(file, ¤t->sighand->signalfd_wqh, wait); - /* - * Let the caller get a POLLIN in this case, ala socket recv() when - * the peer disconnects. - */ - if (signalfd_lock(ctx, &lk)) { - if ((lk.tsk == current && - next_signal(&lk.tsk->pending, &ctx->sigmask) > 0) || - next_signal(&lk.tsk->signal->shared_pending, - &ctx->sigmask) > 0) - events |= POLLIN; - signalfd_unlock(&lk); - } else + spin_lock_irq(¤t->sighand->siglock); + if (next_signal(¤t->pending, &ctx->sigmask) || + next_signal(¤t->signal->shared_pending, + &ctx->sigmask)) events |= POLLIN; + spin_unlock_irq(¤t->sighand->siglock); return events; } @@ -219,59 +123,46 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info, int nonblock) { ssize_t ret; - struct signalfd_lockctx lk; DECLARE_WAITQUEUE(wait, current); - if (!signalfd_lock(ctx, &lk)) - return 0; - - ret = dequeue_signal(lk.tsk, &ctx->sigmask, info); + spin_lock_irq(¤t->sighand->siglock); + ret = dequeue_signal(current, &ctx->sigmask, info); switch (ret) { case 0: if (!nonblock) break; ret = -EAGAIN; default: - signalfd_unlock(&lk); + spin_unlock_irq(¤t->sighand->siglock); return ret; } - add_wait_queue(&ctx->wqh, &wait); + add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - ret = dequeue_signal(lk.tsk, &ctx->sigmask, info); - signalfd_unlock(&lk); + ret = dequeue_signal(current, &ctx->sigmask, info); if (ret != 0) break; if (signal_pending(current)) { ret = -ERESTARTSYS; break; } + spin_unlock_irq(¤t->sighand->siglock); schedule(); - ret = signalfd_lock(ctx, &lk); - if (unlikely(!ret)) { - /* - * Let the caller read zero byte, ala socket - * recv() when the peer disconnect. This test - * must be done before doing a dequeue_signal(), - * because if the sighand has been orphaned, - * the dequeue_signal() call is going to crash - * because ->sighand will be long gone. - */ - break; - } + spin_lock_irq(¤t->sighand->siglock); } + spin_unlock_irq(¤t->sighand->siglock); - remove_wait_queue(&ctx->wqh, &wait); + remove_wait_queue(¤t->sighand->signalfd_wqh, &wait); __set_current_state(TASK_RUNNING); return ret; } /* - * Returns either the size of a "struct signalfd_siginfo", or zero if the - * sighand we are attached to, has been orphaned. The "count" parameter - * must be at least the size of a "struct signalfd_siginfo". + * Returns a multiple of the size of a "struct signalfd_siginfo", or a negative + * error code. The "count" parameter must be at least the size of a + * "struct signalfd_siginfo". */ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) @@ -287,7 +178,6 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, return -EINVAL; siginfo = (struct signalfd_siginfo __user *) buf; - do { ret = signalfd_dequeue(ctx, &info, nonblock); if (unlikely(ret <= 0)) @@ -300,7 +190,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, nonblock = 1; } while (--count); - return total ? total : ret; + return total ? total: ret; } static const struct file_operations signalfd_fops = { @@ -309,20 +199,13 @@ static const struct file_operations signalfd_fops = { .read = signalfd_read, }; -/* - * Create a file descriptor that is associated with our signal - * state. We can pass it around to others if we want to, but - * it will always be _our_ signal state. - */ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask) { int error; sigset_t sigmask; struct signalfd_ctx *ctx; - struct sighand_struct *sighand; struct file *file; struct inode *inode; - struct signalfd_lockctx lk; if (sizemask != sizeof(sigset_t) || copy_from_user(&sigmask, user_mask, sizeof(sigmask))) @@ -335,17 +218,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas if (!ctx) return -ENOMEM; - init_waitqueue_head(&ctx->wqh); ctx->sigmask = sigmask; - ctx->tsk = current->group_leader; - - sighand = current->sighand; - /* - * Add this fd to the list of signal listeners. - */ - spin_lock_irq(&sighand->siglock); - list_add_tail(&ctx->lnk, &sighand->signalfd_list); - spin_unlock_irq(&sighand->siglock); /* * When we call this, the initialization must be complete, since @@ -364,23 +237,18 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas fput(file); return -EINVAL; } - /* - * We need to be prepared of the fact that the sighand this fd - * is attached to, has been detched. In that case signalfd_lock() - * will return 0, and we'll just skip setting the new mask. - */ - if (signalfd_lock(ctx, &lk)) { - ctx->sigmask = sigmask; - signalfd_unlock(&lk); - } - wake_up(&ctx->wqh); + spin_lock_irq(¤t->sighand->siglock); + ctx->sigmask = sigmask; + spin_unlock_irq(¤t->sighand->siglock); + + wake_up(¤t->sighand->signalfd_wqh); fput(file); } return ufd; err_fdalloc: - signalfd_cleanup(ctx); + kfree(ctx); return error; } diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index 16f8e175167..36d8f6aa11a 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -350,9 +350,10 @@ _xfs_filestream_update_ag( /* xfs_fstrm_free_func(): callback for freeing cached stream items. */ void xfs_fstrm_free_func( - xfs_ino_t ino, - fstrm_item_t *item) + unsigned long ino, + void *data) { + fstrm_item_t *item = (fstrm_item_t *)data; xfs_inode_t *ip = item->ip; int ref; @@ -438,7 +439,7 @@ xfs_filestream_mount( grp_count = 10; err = xfs_mru_cache_create(&mp->m_filestream, lifetime, grp_count, - (xfs_mru_cache_free_func_t)xfs_fstrm_free_func); + xfs_fstrm_free_func); return err; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index dacb19739cc..7174991f4be 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1920,9 +1920,9 @@ xlog_recover_do_reg_buffer( stale_buf = 1; break; } - if (be16_to_cpu(dip->di_core.di_mode)) + if (dip->di_core.di_mode) mode_count++; - if (be16_to_cpu(dip->di_core.di_gen)) + if (dip->di_core.di_gen) gen_count++; } diff --git a/include/acpi/processor.h b/include/acpi/processor.h index ec3ffdadb4d..99934a999e6 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -320,6 +320,8 @@ int acpi_processor_power_init(struct acpi_processor *pr, int acpi_processor_cst_has_changed(struct acpi_processor *pr); int acpi_processor_power_exit(struct acpi_processor *pr, struct acpi_device *device); +int acpi_processor_suspend(struct acpi_device * device, pm_message_t state); +int acpi_processor_resume(struct acpi_device * device); /* in processor_thermal.c */ int acpi_processor_get_limit_info(struct acpi_processor *pr); diff --git a/include/asm-mips/irq.h b/include/asm-mips/irq.h index 97102ebc54b..2cb52cf8bd4 100644 --- a/include/asm-mips/irq.h +++ b/include/asm-mips/irq.h @@ -24,7 +24,30 @@ static inline int irq_canonicalize(int irq) #define irq_canonicalize(irq) (irq) /* Sane hardware, sane code ... */ #endif +#ifdef CONFIG_MIPS_MT_SMTC + +struct irqaction; + +extern unsigned long irq_hwmask[]; +extern int setup_irq_smtc(unsigned int irq, struct irqaction * new, + unsigned long hwmask); + +static inline void smtc_im_ack_irq(unsigned int irq) +{ + if (irq_hwmask[irq] & ST0_IM) + set_c0_status(irq_hwmask[irq] & ST0_IM); +} + +#else + +static inline void smtc_im_ack_irq(unsigned int irq) +{ +} + +#endif /* CONFIG_MIPS_MT_SMTC */ + #ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP + /* * Clear interrupt mask handling "backstop" if irq_hwmask * entry so indicates. This implies that the ack() or end() @@ -38,6 +61,7 @@ do { \ ~(irq_hwmask[irq] & 0x0000ff00)); \ } while (0) #else + #define __DO_IRQ_SMTC_HOOK(irq) do { } while (0) #endif @@ -60,14 +84,6 @@ do { \ extern void arch_init_irq(void); extern void spurious_interrupt(void); -#ifdef CONFIG_MIPS_MT_SMTC -struct irqaction; - -extern unsigned long irq_hwmask[]; -extern int setup_irq_smtc(unsigned int irq, struct irqaction * new, - unsigned long hwmask); -#endif /* CONFIG_MIPS_MT_SMTC */ - extern int allocate_irqno(void); extern void alloc_legacy_irqno(void); extern void free_irqno(unsigned int irq); diff --git a/include/asm-x86_64/pgalloc.h b/include/asm-x86_64/pgalloc.h index b467be6d367..8bb56468786 100644 --- a/include/asm-x86_64/pgalloc.h +++ b/include/asm-x86_64/pgalloc.h @@ -4,10 +4,6 @@ #include <asm/pda.h> #include <linux/threads.h> #include <linux/mm.h> -#include <linux/quicklist.h> - -#define QUICK_PGD 0 /* We preserve special mappings over free */ -#define QUICK_PT 1 /* Other page table pages that are zero on free */ #define pmd_populate_kernel(mm, pmd, pte) \ set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte))) @@ -24,23 +20,23 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *p static inline void pmd_free(pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - quicklist_free(QUICK_PT, NULL, pmd); + free_page((unsigned long)pmd); } static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); + return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); + return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); } static inline void pud_free (pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - quicklist_free(QUICK_PT, NULL, pud); + free_page((unsigned long)pud); } static inline void pgd_list_add(pgd_t *pgd) @@ -61,57 +57,41 @@ static inline void pgd_list_del(pgd_t *pgd) spin_unlock(&pgd_lock); } -static inline void pgd_ctor(void *x) +static inline pgd_t *pgd_alloc(struct mm_struct *mm) { unsigned boundary; - pgd_t *pgd = x; - struct page *page = virt_to_page(pgd); - + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + if (!pgd) + return NULL; + pgd_list_add(pgd); /* * Copy kernel pointers in from init. + * Could keep a freelist or slab cache of those because the kernel + * part never changes. */ boundary = pgd_index(__PAGE_OFFSET); + memset(pgd, 0, boundary * sizeof(pgd_t)); memcpy(pgd + boundary, - init_level4_pgt + boundary, - (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); - - spin_lock(&pgd_lock); - list_add(&page->lru, &pgd_list); - spin_unlock(&pgd_lock); -} - -static inline void pgd_dtor(void *x) -{ - pgd_t *pgd = x; - struct page *page = virt_to_page(pgd); - - spin_lock(&pgd_lock); - list_del(&page->lru); - spin_unlock(&pgd_lock); -} - -static inline pgd_t *pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = (pgd_t *)quicklist_alloc(QUICK_PGD, - GFP_KERNEL|__GFP_REPEAT, pgd_ctor); + init_level4_pgt + boundary, + (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); return pgd; } static inline void pgd_free(pgd_t *pgd) { BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); - quicklist_free(QUICK_PGD, pgd_dtor, pgd); + pgd_list_del(pgd); + free_page((unsigned long)pgd); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); + return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); } static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { - void *p = (void *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); - + void *p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); if (!p) return NULL; return virt_to_page(p); @@ -123,22 +103,17 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long add static inline void pte_free_kernel(pte_t *pte) { BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - quicklist_free(QUICK_PT, NULL, pte); + free_page((unsigned long)pte); } static inline void pte_free(struct page *pte) { - quicklist_free_page(QUICK_PT, NULL, pte); -} + __free_page(pte); +} -#define __pte_free_tlb(tlb,pte) quicklist_free_page(QUICK_PT, NULL,(pte)) +#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) -#define __pmd_free_tlb(tlb,x) quicklist_free(QUICK_PT, NULL, (x)) -#define __pud_free_tlb(tlb,x) quicklist_free(QUICK_PT, NULL, (x)) +#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) +#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) -static inline void check_pgt_cache(void) -{ - quicklist_trim(QUICK_PGD, pgd_dtor, 25, 16); - quicklist_trim(QUICK_PT, NULL, 25, 16); -} #endif /* _X86_64_PGALLOC_H */ diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h index c9d8764c89d..57dd6b3107e 100644 --- a/include/asm-x86_64/pgtable.h +++ b/include/asm-x86_64/pgtable.h @@ -411,6 +411,7 @@ pte_t *lookup_address(unsigned long addr); #define HAVE_ARCH_UNMAPPED_AREA #define pgtable_cache_init() do { } while (0) +#define check_pgt_cache() do { } while (0) #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/include/linux/init_task.h b/include/linux/init_task.h index cab741c2d60..f8abfa349ef 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -86,7 +86,7 @@ extern struct nsproxy init_nsproxy; .count = ATOMIC_INIT(1), \ .action = { { { .sa_handler = NULL, } }, }, \ .siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \ - .signalfd_list = LIST_HEAD_INIT(sighand.signalfd_list), \ + .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(sighand.signalfd_wqh), \ } extern struct group_info init_groups; diff --git a/include/linux/sched.h b/include/linux/sched.h index 3de79016f2a..a01ac6dd5f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -438,7 +438,7 @@ struct sighand_struct { atomic_t count; struct k_sigaction action[_NSIG]; spinlock_t siglock; - struct list_head signalfd_list; + wait_queue_head_t signalfd_wqh; }; struct pacct_struct { diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index 51042949569..4c9ff0910ae 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -45,49 +45,17 @@ struct signalfd_siginfo { #ifdef CONFIG_SIGNALFD /* - * Deliver the signal to listening signalfd. This must be called - * with the sighand lock held. Same are the following that end up - * calling signalfd_deliver(). - */ -void signalfd_deliver(struct task_struct *tsk, int sig); - -/* - * No need to fall inside signalfd_deliver() if no signal listeners - * are available. + * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { - if (unlikely(!list_empty(&tsk->sighand->signalfd_list))) - signalfd_deliver(tsk, sig); -} - -/* - * The signal -1 is used to notify the signalfd that the sighand - * is on its way to be detached. - */ -static inline void signalfd_detach_locked(struct task_struct *tsk) -{ - if (unlikely(!list_empty(&tsk->sighand->signalfd_list))) - signalfd_deliver(tsk, -1); -} - -static inline void signalfd_detach(struct task_struct *tsk) -{ - struct sighand_struct *sighand = tsk->sighand; - - if (unlikely(!list_empty(&sighand->signalfd_list))) { - spin_lock_irq(&sighand->siglock); - signalfd_deliver(tsk, -1); - spin_unlock_irq(&sighand->siglock); - } + if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) + wake_up(&tsk->sighand->signalfd_wqh); } #else /* CONFIG_SIGNALFD */ -#define signalfd_deliver(t, s) do { } while (0) -#define signalfd_notify(t, s) do { } while (0) -#define signalfd_detach_locked(t) do { } while (0) -#define signalfd_detach(t) do { } while (0) +static inline void signalfd_notify(struct task_struct *tsk, int sig) { } #endif /* CONFIG_SIGNALFD */ diff --git a/kernel/exit.c b/kernel/exit.c index 06b24b3aa37..993369ee94d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -24,7 +24,6 @@ #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> -#include <linux/signalfd.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> @@ -86,14 +85,6 @@ static void __exit_signal(struct task_struct *tsk) sighand = rcu_dereference(tsk->sighand); spin_lock(&sighand->siglock); - /* - * Notify that this sighand has been detached. This must - * be called with the tsk->sighand lock held. Also, this - * access tsk->sighand internally, so it must be called - * before tsk->sighand is reset. - */ - signalfd_detach_locked(tsk); - posix_cpu_timers_exit(tsk); if (atomic_dec_and_test(&sig->count)) posix_cpu_timers_exit_group(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index 7332e236d36..33f12f48684 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1438,7 +1438,7 @@ static void sighand_ctor(void *data, struct kmem_cache *cachep, struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); - INIT_LIST_HEAD(&sighand->signalfd_list); + init_waitqueue_head(&sighand->signalfd_wqh); } void __init proc_caches_init(void) diff --git a/kernel/signal.c b/kernel/signal.c index 3169bed0b4d..9fb91a32edd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -378,8 +378,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - if (likely(tsk == current)) - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info); @@ -407,8 +406,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) } } } - if (likely(tsk == current)) - recalc_sigpending(); + recalc_sigpending(); if (signr && unlikely(sig_kernel_stop(signr))) { /* * Set a marker that we have dequeued a stop signal. Our @@ -425,7 +423,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT)) tsk->signal->flags |= SIGNAL_STOP_DEQUEUED; } - if (signr && likely(tsk == current) && + if (signr && ((info->si_code & __SI_MASK) == __SI_TIMER) && info->si_sys_private){ /* diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index aab881c86a1..0962e057766 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -382,23 +382,8 @@ static int tick_broadcast_set_event(ktime_t expires, int force) int tick_resume_broadcast_oneshot(struct clock_event_device *bc) { - int cpu = smp_processor_id(); - - /* - * If the CPU is marked for broadcast, enforce oneshot - * broadcast mode. The jinxed VAIO does not resume otherwise. - * No idea why it ends up in a lower C State during resume - * without notifying the clock events layer. - */ - if (cpu_isset(cpu, tick_broadcast_mask)) - cpu_set(cpu, tick_broadcast_oneshot_mask); - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); - - if(!cpus_empty(tick_broadcast_oneshot_mask)) - tick_broadcast_set_event(ktime_get(), 1); - - return cpu_isset(cpu, tick_broadcast_oneshot_mask); + return 0; } /* diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e185a5b5591..2351533a850 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -58,7 +58,6 @@ struct nfulnl_instance { unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ - struct nlmsghdr *lastnlh; /* netlink header of last msg in skb */ struct timer_list timer; int peer_pid; /* PID of the peer process */ @@ -345,10 +344,12 @@ static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, static int __nfulnl_send(struct nfulnl_instance *inst) { - int status; + int status = -1; if (inst->qlen > 1) - inst->lastnlh->nlmsg_type = NLMSG_DONE; + NLMSG_PUT(inst->skb, 0, 0, + NLMSG_DONE, + sizeof(struct nfgenmsg)); status = nfnetlink_unicast(inst->skb, inst->peer_pid, MSG_DONTWAIT); if (status < 0) { @@ -358,8 +359,8 @@ __nfulnl_send(struct nfulnl_instance *inst) inst->qlen = 0; inst->skb = NULL; - inst->lastnlh = NULL; +nlmsg_failure: return status; } @@ -538,7 +539,6 @@ __build_packet_message(struct nfulnl_instance *inst, } nlh->nlmsg_len = inst->skb->tail - old_tail; - inst->lastnlh = nlh; return 0; nlmsg_failure: @@ -644,7 +644,8 @@ nfulnl_log_packet(unsigned int pf, } if (inst->qlen >= qthreshold || - (inst->skb && size > skb_tailroom(inst->skb))) { + (inst->skb && size > + skb_tailroom(inst->skb) - sizeof(struct nfgenmsg))) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ UDEBUG("flushing old skb\n"); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 95795730985..3a23e30bc79 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -270,7 +270,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit-1) { + if (++sch->q.qlen <= q->limit) { sch->bstats.bytes += skb->len; sch->bstats.packets++; return 0; @@ -306,7 +306,7 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit - 1) { + if (++sch->q.qlen <= q->limit) { sch->qstats.requeues++; return 0; } @@ -391,10 +391,10 @@ static int sfq_change(struct Qdisc *sch, struct rtattr *opt) q->quantum = ctl->quantum ? : psched_mtu(sch->dev); q->perturb_period = ctl->perturb_period*HZ; if (ctl->limit) - q->limit = min_t(u32, ctl->limit, SFQ_DEPTH); + q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 2); qlen = sch->q.qlen; - while (sch->q.qlen >= q->limit-1) + while (sch->q.qlen > q->limit) sfq_drop(sch); qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); @@ -423,7 +423,7 @@ static int sfq_init(struct Qdisc *sch, struct rtattr *opt) q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH; q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH; } - q->limit = SFQ_DEPTH; + q->limit = SFQ_DEPTH - 2; q->max_depth = 0; q->tail = SFQ_DEPTH; if (opt == NULL) { diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 1a899924023..036ab520df2 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1110,7 +1110,8 @@ svc_tcp_accept(struct svc_sock *svsk) serv->sv_name); printk(KERN_NOTICE "%s: last TCP connect from %s\n", - serv->sv_name, buf); + serv->sv_name, __svc_print_addr(sin, + buf, sizeof(buf))); } /* * Always select the oldest socket. It's not fair, diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index f057430db0d..9b5656d8bcc 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -27,6 +27,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/seq_file.h> #include <asm/uaccess.h> #include <linux/dma-mapping.h> #include <linux/moduleparam.h> @@ -481,53 +482,54 @@ static void free_all_reserved_pages(void) #define SND_MEM_PROC_FILE "driver/snd-page-alloc" static struct proc_dir_entry *snd_mem_proc; -static int snd_mem_proc_read(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int snd_mem_proc_read(struct seq_file *seq, void *offset) { - int len = 0; long pages = snd_allocated_pages >> (PAGE_SHIFT-12); struct snd_mem_list *mem; int devno; static char *types[] = { "UNKNOWN", "CONT", "DEV", "DEV-SG", "SBUS" }; mutex_lock(&list_mutex); - len += snprintf(page + len, count - len, - "pages : %li bytes (%li pages per %likB)\n", - pages * PAGE_SIZE, pages, PAGE_SIZE / 1024); + seq_printf(seq, "pages : %li bytes (%li pages per %likB)\n", + pages * PAGE_SIZE, pages, PAGE_SIZE / 1024); devno = 0; list_for_each_entry(mem, &mem_list_head, list) { devno++; - len += snprintf(page + len, count - len, - "buffer %d : ID %08x : type %s\n", - devno, mem->id, types[mem->buffer.dev.type]); - len += snprintf(page + len, count - len, - " addr = 0x%lx, size = %d bytes\n", - (unsigned long)mem->buffer.addr, (int)mem->buffer.bytes); + seq_printf(seq, "buffer %d : ID %08x : type %s\n", + devno, mem->id, types[mem->buffer.dev.type]); + seq_printf(seq, " addr = 0x%lx, size = %d bytes\n", + (unsigned long)mem->buffer.addr, + (int)mem->buffer.bytes); } mutex_unlock(&list_mutex); - return len; + return 0; +} + +static int snd_mem_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, snd_mem_proc_read, NULL); } /* FIXME: for pci only - other bus? */ #ifdef CONFIG_PCI #define gettoken(bufp) strsep(bufp, " \t\n") -static int snd_mem_proc_write(struct file *file, const char __user *buffer, - unsigned long count, void *data) +static ssize_t snd_mem_proc_write(struct file *file, const char __user * buffer, + size_t count, loff_t * ppos) { char buf[128]; char *token, *p; - if (count > ARRAY_SIZE(buf) - 1) - count = ARRAY_SIZE(buf) - 1; + if (count > sizeof(buf) - 1) + return -EINVAL; if (copy_from_user(buf, buffer, count)) return -EFAULT; - buf[ARRAY_SIZE(buf) - 1] = '\0'; + buf[count] = '\0'; p = buf; token = gettoken(&p); if (! token || *token == '#') - return (int)count; + return count; if (strcmp(token, "add") == 0) { char *endp; int vendor, device, size, buffers; @@ -548,7 +550,7 @@ static int snd_mem_proc_write(struct file *file, const char __user *buffer, (buffers = simple_strtol(token, NULL, 0)) <= 0 || buffers > 4) { printk(KERN_ERR "snd-page-alloc: invalid proc write format\n"); - return (int)count; + return count; } vendor &= 0xffff; device &= 0xffff; @@ -560,7 +562,7 @@ static int snd_mem_proc_write(struct file *file, const char __user *buffer, if (pci_set_dma_mask(pci, mask) < 0 || pci_set_consistent_dma_mask(pci, mask) < 0) { printk(KERN_ERR "snd-page-alloc: cannot set DMA mask %lx for pci %04x:%04x\n", mask, vendor, device); - return (int)count; + return count; } } for (i = 0; i < buffers; i++) { @@ -570,7 +572,7 @@ static int snd_mem_proc_write(struct file *file, const char __user *buffer, size, &dmab) < 0) { printk(KERN_ERR "snd-page-alloc: cannot allocate buffer pages (size = %d)\n", size); pci_dev_put(pci); - return (int)count; + return count; } snd_dma_reserve_buf(&dmab, snd_dma_pci_buf_id(pci)); } @@ -596,9 +598,21 @@ static int snd_mem_proc_write(struct file *file, const char __user *buffer, free_all_reserved_pages(); else printk(KERN_ERR "snd-page-alloc: invalid proc cmd\n"); - return (int)count; + return count; } #endif /* CONFIG_PCI */ + +static const struct file_operations snd_mem_proc_fops = { + .owner = THIS_MODULE, + .open = snd_mem_proc_open, + .read = seq_read, +#ifdef CONFIG_PCI + .write = snd_mem_proc_write, +#endif + .llseek = seq_lseek, + .release = single_release, +}; + #endif /* CONFIG_PROC_FS */ /* @@ -609,12 +623,8 @@ static int __init snd_mem_init(void) { #ifdef CONFIG_PROC_FS snd_mem_proc = create_proc_entry(SND_MEM_PROC_FILE, 0644, NULL); - if (snd_mem_proc) { - snd_mem_proc->read_proc = snd_mem_proc_read; -#ifdef CONFIG_PCI - snd_mem_proc->write_proc = snd_mem_proc_write; -#endif - } + if (snd_mem_proc) + snd_mem_proc->proc_fops = &snd_mem_proc_fops; #endif return 0; } |