summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/stable/sysfs-driver-dma-idxd35
-rw-r--r--Documentation/arm/index.rst1
-rw-r--r--Documentation/arm/stm32/stm32-dma-mdma-chaining.rst415
-rw-r--r--Documentation/devicetree/bindings/dma/apple,admac.yaml7
-rw-r--r--Documentation/devicetree/bindings/dma/arm,pl330.yaml6
-rw-r--r--Documentation/devicetree/bindings/dma/mediatek,uart-dma.yaml1
-rw-r--r--Documentation/devicetree/bindings/dma/qcom,adm.yaml99
-rw-r--r--Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml8
-rw-r--r--Documentation/devicetree/bindings/dma/qcom,gpi.yaml1
-rw-r--r--Documentation/devicetree/bindings/dma/qcom_adm.txt61
-rw-r--r--Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml1
-rw-r--r--Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt2
-rw-r--r--MAINTAINERS1
-rw-r--r--drivers/dma/Kconfig2
-rw-r--r--drivers/dma/amba-pl08x.c2
-rw-r--r--drivers/dma/apple-admac.c45
-rw-r--r--drivers/dma/at_xdmac.c5
-rw-r--r--drivers/dma/dw-edma/dw-edma-core.c12
-rw-r--r--drivers/dma/hisi_dma.c650
-rw-r--r--drivers/dma/hsu/hsu.c8
-rw-r--r--drivers/dma/hsu/hsu.h12
-rw-r--r--drivers/dma/hsu/pci.c47
-rw-r--r--drivers/dma/idxd/device.c38
-rw-r--r--drivers/dma/idxd/idxd.h10
-rw-r--r--drivers/dma/idxd/init.c36
-rw-r--r--drivers/dma/idxd/irq.c13
-rw-r--r--drivers/dma/idxd/registers.h35
-rw-r--r--drivers/dma/idxd/sysfs.c187
-rw-r--r--drivers/dma/ioat/dma.c6
-rw-r--r--drivers/dma/ioat/dma.h2
-rw-r--r--drivers/dma/mxs-dma.c11
-rw-r--r--drivers/dma/pl330.c4
-rw-r--r--drivers/dma/qcom/gpi.c7
-rw-r--r--drivers/dma/qcom/qcom_adm.c22
-rw-r--r--drivers/dma/s3c24xx-dma.c2
-rw-r--r--drivers/dma/sf-pdma/sf-pdma.c8
-rw-r--r--drivers/dma/sh/rcar-dmac.c4
-rw-r--r--drivers/dma/stm32-dma.c136
-rw-r--r--drivers/dma/stm32-dmamux.c12
-rw-r--r--drivers/dma/stm32-mdma.c70
-rw-r--r--drivers/dma/ti/edma.c40
-rw-r--r--drivers/dma/ti/k3-psil-j7200.c67
-rw-r--r--drivers/dma/ti/k3-psil-j721e.c79
-rw-r--r--drivers/dma/ti/k3-udma.c37
-rw-r--r--drivers/dma/xilinx/zynqmp_dma.c12
-rw-r--r--include/linux/dma/hsu.h6
-rw-r--r--include/linux/platform_data/dma-hsu.h2
47 files changed, 1854 insertions, 413 deletions
diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd
index 0c2b613f2373..8e2c2c405db2 100644
--- a/Documentation/ABI/stable/sysfs-driver-dma-idxd
+++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd
@@ -227,6 +227,17 @@ Contact: dmaengine@vger.kernel.org
Description: Indicate the number of retires for an enqcmds submission on a sharedwq.
A max value to set attribute is capped at 64.
+What: /sys/bus/dsa/devices/wq<m>.<n>/op_config
+Date: Sept 14, 2022
+KernelVersion: 6.0.0
+Contact: dmaengine@vger.kernel.org
+Description: Shows the operation capability bits displayed in bitmap format
+ presented by %*pb printk() output format specifier.
+ The attribute can be configured when the WQ is disabled in
+ order to configure the WQ to accept specific bits that
+ correlates to the operations allowed. It's visible only
+ on platforms that support the capability.
+
What: /sys/bus/dsa/devices/engine<m>.<n>/group_id
Date: Oct 25, 2019
KernelVersion: 5.6.0
@@ -255,3 +266,27 @@ Contact: dmaengine@vger.kernel.org
Description: Indicates the number of Read Buffers reserved for the use of
engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read Buffers
Reserved.
+
+What: /sys/bus/dsa/devices/group<m>.<n>/desc_progress_limit
+Date: Sept 14, 2022
+KernelVersion: 6.0.0
+Contact: dmaengine@vger.kernel.org
+Description: Allows control of the number of work descriptors that can be
+ concurrently processed by an engine in the group as a fraction
+ of the Maximum Work Descriptors in Progress value specified in
+ the ENGCAP register. The acceptable values are 0 (default),
+ 1 (1/2 of max value), 2 (1/4 of the max value), and 3 (1/8 of
+ the max value). It's visible only on platforms that support
+ the capability.
+
+What: /sys/bus/dsa/devices/group<m>.<n>/batch_progress_limit
+Date: Sept 14, 2022
+KernelVersion: 6.0.0
+Contact: dmaengine@vger.kernel.org
+Description: Allows control of the number of batch descriptors that can be
+ concurrently processed by an engine in the group as a fraction
+ of the Maximum Batch Descriptors in Progress value specified in
+ the ENGCAP register. The acceptable values are 0 (default),
+ 1 (1/2 of max value), 2 (1/4 of the max value), and 3 (1/8 of
+ the max value). It's visible only on platforms that support
+ the capability.
diff --git a/Documentation/arm/index.rst b/Documentation/arm/index.rst
index 495ada7915e1..8c636d4a061f 100644
--- a/Documentation/arm/index.rst
+++ b/Documentation/arm/index.rst
@@ -59,6 +59,7 @@ SoC-specific documents
stm32/stm32f429-overview
stm32/stm32mp13-overview
stm32/stm32mp157-overview
+ stm32/stm32-dma-mdma-chaining
sunxi
diff --git a/Documentation/arm/stm32/stm32-dma-mdma-chaining.rst b/Documentation/arm/stm32/stm32-dma-mdma-chaining.rst
new file mode 100644
index 000000000000..2945e0e33104
--- /dev/null
+++ b/Documentation/arm/stm32/stm32-dma-mdma-chaining.rst
@@ -0,0 +1,415 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+STM32 DMA-MDMA chaining
+=======================
+
+
+Introduction
+------------
+
+ This document describes the STM32 DMA-MDMA chaining feature. But before going
+ further, let's introduce the peripherals involved.
+
+ To offload data transfers from the CPU, STM32 microprocessors (MPUs) embed
+ direct memory access controllers (DMA).
+
+ STM32MP1 SoCs embed both STM32 DMA and STM32 MDMA controllers. STM32 DMA
+ request routing capabilities are enhanced by a DMA request multiplexer
+ (STM32 DMAMUX).
+
+ **STM32 DMAMUX**
+
+ STM32 DMAMUX routes any DMA request from a given peripheral to any STM32 DMA
+ controller (STM32MP1 counts two STM32 DMA controllers) channels.
+
+ **STM32 DMA**
+
+ STM32 DMA is mainly used to implement central data buffer storage (usually in
+ the system SRAM) for different peripheral. It can access external RAMs but
+ without the ability to generate convenient burst transfer ensuring the best
+ load of the AXI.
+
+ **STM32 MDMA**
+
+ STM32 MDMA (Master DMA) is mainly used to manage direct data transfers between
+ RAM data buffers without CPU intervention. It can also be used in a
+ hierarchical structure that uses STM32 DMA as first level data buffer
+ interfaces for AHB peripherals, while the STM32 MDMA acts as a second level
+ DMA with better performance. As a AXI/AHB master, STM32 MDMA can take control
+ of the AXI/AHB bus.
+
+
+Principles
+----------
+
+ STM32 DMA-MDMA chaining feature relies on the strengths of STM32 DMA and
+ STM32 MDMA controllers.
+
+ STM32 DMA has a circular Double Buffer Mode (DBM). At each end of transaction
+ (when DMA data counter - DMA_SxNDTR - reaches 0), the memory pointers
+ (configured with DMA_SxSM0AR and DMA_SxM1AR) are swapped and the DMA data
+ counter is automatically reloaded. This allows the SW or the STM32 MDMA to
+ process one memory area while the second memory area is being filled/used by
+ the STM32 DMA transfer.
+
+ With STM32 MDMA linked-list mode, a single request initiates the data array
+ (collection of nodes) to be transferred until the linked-list pointer for the
+ channel is null. The channel transfer complete of the last node is the end of
+ transfer, unless first and last nodes are linked to each other, in such a
+ case, the linked-list loops on to create a circular MDMA transfer.
+
+ STM32 MDMA has direct connections with STM32 DMA. This enables autonomous
+ communication and synchronization between peripherals, thus saving CPU
+ resources and bus congestion. Transfer Complete signal of STM32 DMA channel
+ can triggers STM32 MDMA transfer. STM32 MDMA can clear the request generated
+ by the STM32 DMA by writing to its Interrupt Clear register (whose address is
+ stored in MDMA_CxMAR, and bit mask in MDMA_CxMDR).
+
+ .. table:: STM32 MDMA interconnect table with STM32 DMA
+
+ +--------------+----------------+-----------+------------+
+ | STM32 DMAMUX | STM32 DMA | STM32 DMA | STM32 MDMA |
+ | channels | channels | Transfer | request |
+ | | | complete | |
+ | | | signal | |
+ +==============+================+===========+============+
+ | Channel *0* | DMA1 channel 0 | dma1_tcf0 | *0x00* |
+ +--------------+----------------+-----------+------------+
+ | Channel *1* | DMA1 channel 1 | dma1_tcf1 | *0x01* |
+ +--------------+----------------+-----------+------------+
+ | Channel *2* | DMA1 channel 2 | dma1_tcf2 | *0x02* |
+ +--------------+----------------+-----------+------------+
+ | Channel *3* | DMA1 channel 3 | dma1_tcf3 | *0x03* |
+ +--------------+----------------+-----------+------------+
+ | Channel *4* | DMA1 channel 4 | dma1_tcf4 | *0x04* |
+ +--------------+----------------+-----------+------------+
+ | Channel *5* | DMA1 channel 5 | dma1_tcf5 | *0x05* |
+ +--------------+----------------+-----------+------------+
+ | Channel *6* | DMA1 channel 6 | dma1_tcf6 | *0x06* |
+ +--------------+----------------+-----------+------------+
+ | Channel *7* | DMA1 channel 7 | dma1_tcf7 | *0x07* |
+ +--------------+----------------+-----------+------------+
+ | Channel *8* | DMA2 channel 0 | dma2_tcf0 | *0x08* |
+ +--------------+----------------+-----------+------------+
+ | Channel *9* | DMA2 channel 1 | dma2_tcf1 | *0x09* |
+ +--------------+----------------+-----------+------------+
+ | Channel *10* | DMA2 channel 2 | dma2_tcf2 | *0x0A* |
+ +--------------+----------------+-----------+------------+
+ | Channel *11* | DMA2 channel 3 | dma2_tcf3 | *0x0B* |
+ +--------------+----------------+-----------+------------+
+ | Channel *12* | DMA2 channel 4 | dma2_tcf4 | *0x0C* |
+ +--------------+----------------+-----------+------------+
+ | Channel *13* | DMA2 channel 5 | dma2_tcf5 | *0x0D* |
+ +--------------+----------------+-----------+------------+
+ | Channel *14* | DMA2 channel 6 | dma2_tcf6 | *0x0E* |
+ +--------------+----------------+-----------+------------+
+ | Channel *15* | DMA2 channel 7 | dma2_tcf7 | *0x0F* |
+ +--------------+----------------+-----------+------------+
+
+ STM32 DMA-MDMA chaining feature then uses a SRAM buffer. STM32MP1 SoCs embed
+ three fast access static internal RAMs of various size, used for data storage.
+ Due to STM32 DMA legacy (within microcontrollers), STM32 DMA performances are
+ bad with DDR, while they are optimal with SRAM. Hence the SRAM buffer used
+ between STM32 DMA and STM32 MDMA. This buffer is split in two equal periods
+ and STM32 DMA uses one period while STM32 MDMA uses the other period
+ simultaneously.
+ ::
+
+ dma[1:2]-tcf[0:7]
+ .----------------.
+ ____________ ' _________ V____________
+ | STM32 DMA | / __|>_ \ | STM32 MDMA |
+ |------------| | / \ | |------------|
+ | DMA_SxM0AR |<=>| | SRAM | |<=>| []-[]...[] |
+ | DMA_SxM1AR | | \_____/ | | |
+ |____________| \___<|____/ |____________|
+
+ STM32 DMA-MDMA chaining uses (struct dma_slave_config).peripheral_config to
+ exchange the parameters needed to configure MDMA. These parameters are
+ gathered into a u32 array with three values:
+
+ * the STM32 MDMA request (which is actually the DMAMUX channel ID),
+ * the address of the STM32 DMA register to clear the Transfer Complete
+ interrupt flag,
+ * the mask of the Transfer Complete interrupt flag of the STM32 DMA channel.
+
+Device Tree updates for STM32 DMA-MDMA chaining support
+-------------------------------------------------------
+
+ **1. Allocate a SRAM buffer**
+
+ SRAM device tree node is defined in SoC device tree. You can refer to it in
+ your board device tree to define your SRAM pool.
+ ::
+
+ &sram {
+ my_foo_device_dma_pool: dma-sram@0 {
+ reg = <0x0 0x1000>;
+ };
+ };
+
+ Be careful of the start index, in case there are other SRAM consumers.
+ Define your pool size strategically: to optimise chaining, the idea is that
+ STM32 DMA and STM32 MDMA can work simultaneously, on each buffer of the
+ SRAM.
+ If the SRAM period is greater than the expected DMA transfer, then STM32 DMA
+ and STM32 MDMA will work sequentially instead of simultaneously. It is not a
+ functional issue but it is not optimal.
+
+ Don't forget to refer to your SRAM pool in your device node. You need to
+ define a new property.
+ ::
+
+ &my_foo_device {
+ ...
+ my_dma_pool = &my_foo_device_dma_pool;
+ };
+
+ Then get this SRAM pool in your foo driver and allocate your SRAM buffer.
+
+ **2. Allocate a STM32 DMA channel and a STM32 MDMA channel**
+
+ You need to define an extra channel in your device tree node, in addition to
+ the one you should already have for "classic" DMA operation.
+
+ This new channel must be taken from STM32 MDMA channels, so, the phandle of
+ the DMA controller to use is the MDMA controller's one.
+ ::
+
+ &my_foo_device {
+ [...]
+ my_dma_pool = &my_foo_device_dma_pool;
+ dmas = <&dmamux1 ...>, // STM32 DMA channel
+ <&mdma1 0 0x3 0x1200000a 0 0>; // + STM32 MDMA channel
+ };
+
+ Concerning STM32 MDMA bindings:
+
+ 1. The request line number : whatever the value here, it will be overwritten
+ by MDMA driver with the STM32 DMAMUX channel ID passed through
+ (struct dma_slave_config).peripheral_config
+
+ 2. The priority level : choose Very High (0x3) so that your channel will
+ take priority other the other during request arbitration
+
+ 3. A 32bit mask specifying the DMA channel configuration : source and
+ destination address increment, block transfer with 128 bytes per single
+ transfer
+
+ 4. The 32bit value specifying the register to be used to acknowledge the
+ request: it will be overwritten by MDMA driver, with the DMA channel
+ interrupt flag clear register address passed through
+ (struct dma_slave_config).peripheral_config
+
+ 5. The 32bit mask specifying the value to be written to acknowledge the
+ request: it will be overwritten by MDMA driver, with the DMA channel
+ Transfer Complete flag passed through
+ (struct dma_slave_config).peripheral_config
+
+Driver updates for STM32 DMA-MDMA chaining support in foo driver
+----------------------------------------------------------------
+
+ **0. (optional) Refactor the original sg_table if dmaengine_prep_slave_sg()**
+
+ In case of dmaengine_prep_slave_sg(), the original sg_table can't be used as
+ is. Two new sg_tables must be created from the original one. One for
+ STM32 DMA transfer (where memory address targets now the SRAM buffer instead
+ of DDR buffer) and one for STM32 MDMA transfer (where memory address targets
+ the DDR buffer).
+
+ The new sg_list items must fit SRAM period length. Here is an example for
+ DMA_DEV_TO_MEM:
+ ::
+
+ /*
+ * Assuming sgl and nents, respectively the initial scatterlist and its
+ * length.
+ * Assuming sram_dma_buf and sram_period, respectively the memory
+ * allocated from the pool for DMA usage, and the length of the period,
+ * which is half of the sram_buf size.
+ */
+ struct sg_table new_dma_sgt, new_mdma_sgt;
+ struct scatterlist *s, *_sgl;
+ dma_addr_t ddr_dma_buf;
+ u32 new_nents = 0, len;
+ int i;
+
+ /* Count the number of entries needed */
+ for_each_sg(sgl, s, nents, i)
+ if (sg_dma_len(s) > sram_period)
+ new_nents += DIV_ROUND_UP(sg_dma_len(s), sram_period);
+ else
+ new_nents++;
+
+ /* Create sg table for STM32 DMA channel */
+ ret = sg_alloc_table(&new_dma_sgt, new_nents, GFP_ATOMIC);
+ if (ret)
+ dev_err(dev, "DMA sg table alloc failed\n");
+
+ for_each_sg(new_dma_sgt.sgl, s, new_dma_sgt.nents, i) {
+ _sgl = sgl;
+ sg_dma_len(s) = min(sg_dma_len(_sgl), sram_period);
+ /* Targets the beginning = first half of the sram_buf */
+ s->dma_address = sram_buf;
+ /*
+ * Targets the second half of the sram_buf
+ * for odd indexes of the item of the sg_list
+ */
+ if (i & 1)
+ s->dma_address += sram_period;
+ }
+
+ /* Create sg table for STM32 MDMA channel */
+ ret = sg_alloc_table(&new_mdma_sgt, new_nents, GFP_ATOMIC);
+ if (ret)
+ dev_err(dev, "MDMA sg_table alloc failed\n");
+
+ _sgl = sgl;
+ len = sg_dma_len(sgl);
+ ddr_dma_buf = sg_dma_address(sgl);
+ for_each_sg(mdma_sgt.sgl, s, mdma_sgt.nents, i) {
+ size_t bytes = min_t(size_t, len, sram_period);
+
+ sg_dma_len(s) = bytes;
+ sg_dma_address(s) = ddr_dma_buf;
+ len -= bytes;
+
+ if (!len && sg_next(_sgl)) {
+ _sgl = sg_next(_sgl);
+ len = sg_dma_len(_sgl);
+ ddr_dma_buf = sg_dma_address(_sgl);
+ } else {
+ ddr_dma_buf += bytes;
+ }
+ }
+
+ Don't forget to release these new sg_tables after getting the descriptors
+ with dmaengine_prep_slave_sg().
+
+ **1. Set controller specific parameters**
+
+ First, use dmaengine_slave_config() with a struct dma_slave_config to
+ configure STM32 DMA channel. You just have to take care of DMA addresses,
+ the memory address (depending on the transfer direction) must point on your
+ SRAM buffer, and set (struct dma_slave_config).peripheral_size != 0.
+
+ STM32 DMA driver will check (struct dma_slave_config).peripheral_size to
+ determine if chaining is being used or not. If it is used, then STM32 DMA
+ driver fills (struct dma_slave_config).peripheral_config with an array of
+ three u32 : the first one containing STM32 DMAMUX channel ID, the second one
+ the channel interrupt flag clear register address, and the third one the
+ channel Transfer Complete flag mask.
+
+ Then, use dmaengine_slave_config with another struct dma_slave_config to
+ configure STM32 MDMA channel. Take care of DMA addresses, the device address
+ (depending on the transfer direction) must point on your SRAM buffer, and
+ the memory address must point to the buffer originally used for "classic"
+ DMA operation. Use the previous (struct dma_slave_config).peripheral_size
+ and .peripheral_config that have been updated by STM32 DMA driver, to set
+ (struct dma_slave_config).peripheral_size and .peripheral_config of the
+ struct dma_slave_config to configure STM32 MDMA channel.
+ ::
+
+ struct dma_slave_config dma_conf;
+ struct dma_slave_config mdma_conf;
+
+ memset(&dma_conf, 0, sizeof(dma_conf));
+ [...]
+ config.direction = DMA_DEV_TO_MEM;
+ config.dst_addr = sram_dma_buf; // SRAM buffer
+ config.peripheral_size = 1; // peripheral_size != 0 => chaining
+
+ dmaengine_slave_config(dma_chan, &dma_config);
+
+ memset(&mdma_conf, 0, sizeof(mdma_conf));
+ config.direction = DMA_DEV_TO_MEM;
+ mdma_conf.src_addr = sram_dma_buf; // SRAM buffer
+ mdma_conf.dst_addr = rx_dma_buf; // original memory buffer
+ mdma_conf.peripheral_size = dma_conf.peripheral_size; // <- dma_conf
+ mdma_conf.peripheral_config = dma_config.peripheral_config; // <- dma_conf
+
+ dmaengine_slave_config(mdma_chan, &mdma_conf);
+
+ **2. Get a descriptor for STM32 DMA channel transaction**
+
+ In the same way you get your descriptor for your "classic" DMA operation,
+ you just have to replace the original sg_list (in case of
+ dmaengine_prep_slave_sg()) with the new sg_list using SRAM buffer, or to
+ replace the original buffer address, length and period (in case of
+ dmaengine_prep_dma_cyclic()) with the new SRAM buffer.
+
+ **3. Get a descriptor for STM32 MDMA channel transaction**
+
+ If you previously get descriptor (for STM32 DMA) with
+
+ * dmaengine_prep_slave_sg(), then use dmaengine_prep_slave_sg() for
+ STM32 MDMA;
+ * dmaengine_prep_dma_cyclic(), then use dmaengine_prep_dma_cyclic() for
+ STM32 MDMA.
+
+ Use the new sg_list using SRAM buffer (in case of dmaengine_prep_slave_sg())
+ or, depending on the transfer direction, either the original DDR buffer (in
+ case of DMA_DEV_TO_MEM) or the SRAM buffer (in case of DMA_MEM_TO_DEV), the
+ source address being previously set with dmaengine_slave_config().
+
+ **4. Submit both transactions**
+
+ Before submitting your transactions, you may need to define on which
+ descriptor you want a callback to be called at the end of the transfer
+ (dmaengine_prep_slave_sg()) or the period (dmaengine_prep_dma_cyclic()).
+ Depending on the direction, set the callback on the descriptor that finishes
+ the overal transfer:
+
+ * DMA_DEV_TO_MEM: set the callback on the "MDMA" descriptor
+ * DMA_MEM_TO_DEV: set the callback on the "DMA" descriptor
+
+ Then, submit the descriptors whatever the order, with dmaengine_tx_submit().
+
+ **5. Issue pending requests (and wait for callback notification)**
+
+ As STM32 MDMA channel transfer is triggered by STM32 DMA, you must issue
+ STM32 MDMA channel before STM32 DMA channel.
+
+ If any, your callback will be called to warn you about the end of the overal
+ transfer or the period completion.
+
+ Don't forget to terminate both channels. STM32 DMA channel is configured in
+ cyclic Double-Buffer mode so it won't be disabled by HW, you need to terminate
+ it. STM32 MDMA channel will be stopped by HW in case of sg transfer, but not
+ in case of cyclic transfer. You can terminate it whatever the kind of transfer.
+
+ **STM32 DMA-MDMA chaining DMA_MEM_TO_DEV special case**
+
+ STM32 DMA-MDMA chaining in DMA_MEM_TO_DEV is a special case. Indeed, the
+ STM32 MDMA feeds the SRAM buffer with the DDR data, and the STM32 DMA reads
+ data from SRAM buffer. So some data (the first period) have to be copied in
+ SRAM buffer when the STM32 DMA starts to read.
+
+ A trick could be pausing the STM32 DMA channel (that will raise a Transfer
+ Complete signal, triggering the STM32 MDMA channel), but the first data read
+ by the STM32 DMA could be "wrong". The proper way is to prepare the first SRAM
+ period with dmaengine_prep_dma_memcpy(). Then this first period should be
+ "removed" from the sg or the cyclic transfer.
+
+ Due to this complexity, rather use the STM32 DMA-MDMA chaining for
+ DMA_DEV_TO_MEM and keep the "classic" DMA usage for DMA_MEM_TO_DEV, unless
+ you're not afraid.
+
+Resources
+---------
+
+ Application note, datasheet and reference manual are available on ST website
+ (STM32MP1_).
+
+ Dedicated focus on three application notes (AN5224_, AN4031_ & AN5001_)
+ dealing with STM32 DMAMUX, STM32 DMA and STM32 MDMA.
+
+.. _STM32MP1: https://www.st.com/en/microcontrollers-microprocessors/stm32mp1-series.html
+.. _AN5224: https://www.st.com/resource/en/application_note/an5224-stm32-dmamux-the-dma-request-router-stmicroelectronics.pdf
+.. _AN4031: https://www.st.com/resource/en/application_note/dm00046011-using-the-stm32f2-stm32f4-and-stm32f7-series-dma-controller-stmicroelectronics.pdf
+.. _AN5001: https://www.st.com/resource/en/application_note/an5001-stm32cube-expansion-package-for-stm32h7-series-mdma-stmicroelectronics.pdf
+
+:Authors:
+
+- Amelie Delaunay <amelie.delaunay@foss.st.com> \ No newline at end of file
diff --git a/Documentation/devicetree/bindings/dma/apple,admac.yaml b/Documentation/devicetree/bindings/dma/apple,admac.yaml
index bdc8c129c4f5..3b1e667f7ea0 100644
--- a/Documentation/devicetree/bindings/dma/apple,admac.yaml
+++ b/Documentation/devicetree/bindings/dma/apple,admac.yaml
@@ -49,6 +49,13 @@ properties:
in an interrupts-extended list the disconnected positions will contain
an empty phandle reference <0>.
+ iommus:
+ minItems: 1
+ maxItems: 2
+
+ power-domains:
+ maxItems: 1
+
required:
- compatible
- reg
diff --git a/Documentation/devicetree/bindings/dma/arm,pl330.yaml b/Documentation/devicetree/bindings/dma/arm,pl330.yaml
index 2bec69b308f8..4a3dd6f5309b 100644
--- a/Documentation/devicetree/bindings/dma/arm,pl330.yaml
+++ b/Documentation/devicetree/bindings/dma/arm,pl330.yaml
@@ -55,6 +55,12 @@ properties:
dma-coherent: true
+ iommus:
+ minItems: 1
+ maxItems: 9
+ description: Up to 1 IOMMU entry per DMA channel for writes and 1
+ IOMMU entry for reads.
+
power-domains:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/dma/mediatek,uart-dma.yaml b/Documentation/devicetree/bindings/dma/mediatek,uart-dma.yaml
index 19ea8dcbcbce..9ab4d81ead35 100644
--- a/Documentation/devicetree/bindings/dma/mediatek,uart-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/mediatek,uart-dma.yaml
@@ -22,6 +22,7 @@ properties:
- items:
- enum:
- mediatek,mt2712-uart-dma
+ - mediatek,mt6795-uart-dma
- mediatek,mt8365-uart-dma
- mediatek,mt8516-uart-dma
- const: mediatek,mt6577-uart-dma
diff --git a/Documentation/devicetree/bindings/dma/qcom,adm.yaml b/Documentation/devicetree/bindings/dma/qcom,adm.yaml
new file mode 100644
index 000000000000..6a9d7bc74aff
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/qcom,adm.yaml
@@ -0,0 +1,99 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/qcom,adm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm ADM DMA Controller
+
+maintainers:
+ - Christian Marangi <ansuelsmth@gmail.com>
+ - Bjorn Andersson <bjorn.andersson@linaro.org>
+
+description: |
+ QCOM ADM DMA controller provides DMA capabilities for
+ peripheral buses such as NAND and SPI.
+
+properties:
+ compatible:
+ const: qcom,adm
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ maxItems: 1
+
+ "#dma-cells":
+ const: 1
+
+ clocks:
+ items:
+ - description: phandle to the core clock
+ - description: phandle to the iface clock
+
+ clock-names:
+ items:
+ - const: core
+ - const: iface
+
+ resets:
+ items:
+ - description: phandle to the clk reset
+ - description: phandle to the pbus reset
+ - description: phandle to the c0 reset
+ - description: phandle to the c1 reset
+ - description: phandle to the c2 reset
+
+ reset-names:
+ items:
+ - const: clk
+ - const: pbus
+ - const: c0
+ - const: c1
+ - const: c2
+
+ qcom,ee:
+ $ref: /schemas/types.yaml#/definitions/uint32
+ description: indicates the security domain identifier used in the secure world.
+ minimum: 0
+ maximum: 255
+
+required:
+ - compatible
+ - reg
+ - interrupts
+ - "#dma-cells"
+ - clocks
+ - clock-names
+ - resets
+ - reset-names
+ - qcom,ee
+
+additionalProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/clock/qcom,gcc-ipq806x.h>
+ #include <dt-bindings/reset/qcom,gcc-ipq806x.h>
+
+ adm_dma: dma-controller@18300000 {
+ compatible = "qcom,adm";
+ reg = <0x18300000 0x100000>;
+ interrupts = <0 170 0>;
+ #dma-cells = <1>;
+
+ clocks = <&gcc ADM0_CLK>,
+ <&gcc ADM0_PBUS_CLK>;
+ clock-names = "core", "iface";
+
+ resets = <&gcc ADM0_RESET>,
+ <&gcc ADM0_PBUS_RESET>,
+ <&gcc ADM0_C0_RESET>,
+ <&gcc ADM0_C1_RESET>,
+ <&gcc ADM0_C2_RESET>;
+ reset-names = "clk", "pbus", "c0", "c1", "c2";
+ qcom,ee = <0>;
+ };
+
+...
diff --git a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
index 9bf3a1b164f1..003098caf709 100644
--- a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
@@ -8,7 +8,7 @@ title: Qualcomm Technologies Inc BAM DMA controller
maintainers:
- Andy Gross <agross@kernel.org>
- - Bjorn Andersson <bjorn.andersson@linaro.org>
+ - Bjorn Andersson <andersson@kernel.org>
allOf:
- $ref: "dma-controller.yaml#"
@@ -20,7 +20,7 @@ properties:
- qcom,bam-v1.3.0
# MSM8974, APQ8074 and APQ8084
- qcom,bam-v1.4.0
- # MSM8916
+ # MSM8916 and SDM845
- qcom,bam-v1.7.0
clocks:
@@ -90,8 +90,8 @@ examples:
dma-controller@f9944000 {
compatible = "qcom,bam-v1.4.0";
- reg = <0xf9944000 0x15000>;
- interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+ reg = <0xf9944000 0x19000>;
+ interrupts = <GIC_SPI 239 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_BLSP2_AHB_CLK>;
clock-names = "bam_clk";
#dma-cells = <1>;
diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 7d2fc4eb5530..eabf8a76d3a0 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -21,6 +21,7 @@ properties:
enum:
- qcom,sc7280-gpi-dma
- qcom,sdm845-gpi-dma
+ - qcom,sm6350-gpi-dma
- qcom,sm8150-gpi-dma
- qcom,sm8250-gpi-dma
- qcom,sm8350-gpi-dma
diff --git a/Documentation/devicetree/bindings/dma/qcom_adm.txt b/Documentation/devicetree/bindings/dma/qcom_adm.txt
deleted file mode 100644
index 9d3b2f917b7b..000000000000
--- a/Documentation/devicetree/bindings/dma/qcom_adm.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-QCOM ADM DMA Controller
-
-Required properties:
-- compatible: must contain "qcom,adm" for IPQ/APQ8064 and MSM8960
-- reg: Address range for DMA registers
-- interrupts: Should contain one interrupt shared by all channels
-- #dma-cells: must be <2>. First cell denotes the channel number. Second cell
- denotes CRCI (client rate control interface) flow control assignment.
-- clocks: Should contain the core clock and interface clock.
-- clock-names: Must contain "core" for the core clock and "iface" for the
- interface clock.
-- resets: Must contain an entry for each entry in reset names.
-- reset-names: Must include the following entries:
- - clk
- - c0
- - c1
- - c2
-- qcom,ee: indicates the security domain identifier used in the secure world.
-
-Example:
- adm_dma: dma@18300000 {
- compatible = "qcom,adm";
- reg = <0x18300000 0x100000>;
- interrupts = <0 170 0>;
- #dma-cells = <2>;
-
- clocks = <&gcc ADM0_CLK>, <&gcc ADM0_PBUS_CLK>;
- clock-names = "core", "iface";
-
- resets = <&gcc ADM0_RESET>,
- <&gcc ADM0_C0_RESET>,
- <&gcc ADM0_C1_RESET>,
- <&gcc ADM0_C2_RESET>;
- reset-names = "clk", "c0", "c1", "c2";
- qcom,ee = <0>;
- };
-
-DMA clients must use the format descripted in the dma.txt file, using a three
-cell specifier for each channel.
-
-Each dmas request consists of 3 cells:
- 1. phandle pointing to the DMA controller
- 2. channel number
- 3. CRCI assignment, if applicable. If no CRCI flow control is required, use 0.
- The CRCI is used for flow control. It identifies the peripheral device that
- is the source/destination for the transferred data.
-
-Example:
-
- spi4: spi@1a280000 {
- spi-max-frequency = <50000000>;
-
- pinctrl-0 = <&spi_pins>;
- pinctrl-names = "default";
-
- cs-gpios = <&qcom_pinmux 20 0>;
-
- dmas = <&adm_dma 6 9>,
- <&adm_dma 5 10>;
- dma-names = "rx", "tx";
- };
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
index 7202cd68e759..89b591a05bce 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
@@ -45,6 +45,7 @@ properties:
- enum:
- renesas,dmac-r8a779a0 # R-Car V3U
- renesas,dmac-r8a779f0 # R-Car S4-8
+ - renesas,dmac-r8a779g0 # R-Car V4H
- const: renesas,rcar-gen4-dmac # R-Car Gen4
reg: true
diff --git a/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
index b849a1ed389d..47e477cce6d2 100644
--- a/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
+++ b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
@@ -4,7 +4,7 @@ Required properties:
- compatible: "ti,dra7-dma-crossbar" for DRA7xx DMA crossbar
"ti,am335x-edma-crossbar" for AM335x and AM437x
- reg: Memory map for accessing module
-- #dma-cells: Should be set to to match with the DMA controller's dma-cells
+- #dma-cells: Should be set to match with the DMA controller's dma-cells
for ti,dra7-dma-crossbar and <3> for ti,am335x-edma-crossbar.
- dma-requests: Number of DMA requests the crossbar can receive
- dma-masters: phandle pointing to the DMA controller
diff --git a/MAINTAINERS b/MAINTAINERS
index a79d3f97a914..20fbb44b184e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9157,6 +9157,7 @@ F: net/dsa/tag_hellcreek.c
HISILICON DMA DRIVER
M: Zhou Wang <wangzhou1@hisilicon.com>
+M: Jie Hai <haijie1@hisilicon.com>
L: dmaengine@vger.kernel.org
S: Maintained
F: drivers/dma/hisi_dma.c
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index a06d2a7627aa..7524b62a8870 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -180,7 +180,7 @@ config DMA_SUN6I
config DW_AXI_DMAC
tristate "Synopsys DesignWare AXI DMA support"
- depends on OF || COMPILE_TEST
+ depends on OF
depends on HAS_IOMEM
select DMA_ENGINE
select DMA_VIRTUAL_CHANNELS
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 487a01aa207d..eea8bd33b4b7 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -2367,7 +2367,7 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
INIT_LIST_HEAD(&dmadev->channels);
/*
- * Register as many many memcpy as we have physical channels,
+ * Register as many memcpy as we have physical channels,
* we won't always be able to use all but the code will have
* to cope with that situation.
*/
diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c
index d1f74a3aa999..317ca76ccafd 100644
--- a/drivers/dma/apple-admac.c
+++ b/drivers/dma/apple-admac.c
@@ -12,8 +12,9 @@
#include <linux/module.h>
#include <linux/of_device.h>
#include <linux/of_dma.h>
-#include <linux/interrupt.h>
+#include <linux/reset.h>
#include <linux/spinlock.h>
+#include <linux/interrupt.h>
#include "dmaengine.h"
@@ -95,7 +96,9 @@ struct admac_data {
struct dma_device dma;
struct device *dev;
__iomem void *base;
+ struct reset_control *rstc;
+ int irq;
int irq_index;
int nchannels;
struct admac_chan channels[];
@@ -724,18 +727,17 @@ static int admac_probe(struct platform_device *pdev)
if (irq < 0)
return dev_err_probe(&pdev->dev, irq, "no usable interrupt\n");
-
- err = devm_request_irq(&pdev->dev, irq, admac_interrupt,
- 0, dev_name(&pdev->dev), ad);
- if (err)
- return dev_err_probe(&pdev->dev, err,
- "unable to register interrupt\n");
+ ad->irq = irq;
ad->base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(ad->base))
return dev_err_probe(&pdev->dev, PTR_ERR(ad->base),
"unable to obtain MMIO resource\n");
+ ad->rstc = devm_reset_control_get_optional_shared(&pdev->dev, NULL);
+ if (IS_ERR(ad->rstc))
+ return PTR_ERR(ad->rstc);
+
dma = &ad->dma;
dma_cap_set(DMA_PRIVATE, dma->cap_mask);
@@ -774,17 +776,38 @@ static int admac_probe(struct platform_device *pdev)
tasklet_setup(&adchan->tasklet, admac_chan_tasklet);
}
- err = dma_async_device_register(&ad->dma);
+ err = reset_control_reset(ad->rstc);
if (err)
- return dev_err_probe(&pdev->dev, err, "failed to register DMA device\n");
+ return dev_err_probe(&pdev->dev, err,
+ "unable to trigger reset\n");
+
+ err = request_irq(irq, admac_interrupt, 0, dev_name(&pdev->dev), ad);
+ if (err) {
+ dev_err_probe(&pdev->dev, err,
+ "unable to register interrupt\n");
+ goto free_reset;
+ }
+
+ err = dma_async_device_register(&ad->dma);
+ if (err) {
+ dev_err_probe(&pdev->dev, err, "failed to register DMA device\n");
+ goto free_irq;
+ }
err = of_dma_controller_register(pdev->dev.of_node, admac_dma_of_xlate, ad);
if (err) {
dma_async_device_unregister(&ad->dma);
- return dev_err_probe(&pdev->dev, err, "failed to register with OF\n");
+ dev_err_probe(&pdev->dev, err, "failed to register with OF\n");
+ goto free_irq;
}
return 0;
+
+free_irq:
+ free_irq(ad->irq, ad);
+free_reset:
+ reset_control_rearm(ad->rstc);
+ return err;
}
static int admac_remove(struct platform_device *pdev)
@@ -793,6 +816,8 @@ static int admac_remove(struct platform_device *pdev)
of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(&ad->dma);
+ free_irq(ad->irq, ad);
+ reset_control_rearm(ad->rstc);
return 0;
}
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b102d8eb5d83..d6c9781cd46a 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -1470,10 +1470,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
bool initd;
ret = dma_cookie_status(chan, cookie, txstate);
- if (ret == DMA_COMPLETE)
- return ret;
-
- if (!txstate)
+ if (ret == DMA_COMPLETE || !txstate)
return ret;
spin_lock_irqsave(&atchan->lock, flags);
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 07f756479663..c54b24ff5206 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -9,7 +9,6 @@
#include <linux/module.h>
#include <linux/device.h>
#include <linux/kernel.h>
-#include <linux/pm_runtime.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/interrupt.h>
@@ -682,15 +681,12 @@ static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
if (chan->status != EDMA_ST_IDLE)
return -EBUSY;
- pm_runtime_get(chan->dw->chip->dev);
-
return 0;
}
static void dw_edma_free_chan_resources(struct dma_chan *dchan)
{
unsigned long timeout = jiffies + msecs_to_jiffies(5000);
- struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
int ret;
while (time_before(jiffies, timeout)) {
@@ -703,8 +699,6 @@ static void dw_edma_free_chan_resources(struct dma_chan *dchan)
cpu_relax();
}
-
- pm_runtime_put(chan->dw->chip->dev);
}
static int dw_edma_channel_setup(struct dw_edma *dw, bool write,
@@ -977,9 +971,6 @@ int dw_edma_probe(struct dw_edma_chip *chip)
if (err)
goto err_irq_free;
- /* Power management */
- pm_runtime_enable(dev);
-
/* Turn debugfs on */
dw_edma_v0_core_debugfs_on(dw);
@@ -1009,9 +1000,6 @@ int dw_edma_remove(struct dw_edma_chip *chip)
for (i = (dw->nr_irqs - 1); i >= 0; i--)
free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
- /* Power management */
- pm_runtime_disable(dev);
-
/* Deregister eDMA device */
dma_async_device_unregister(&dw->wr_edma);
list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c
index 43817ced3a3e..c1350a36fddd 100644
--- a/drivers/dma/hisi_dma.c
+++ b/drivers/dma/hisi_dma.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright(c) 2019 HiSilicon Limited. */
+/* Copyright(c) 2019-2022 HiSilicon Limited. */
+
#include <linux/bitfield.h>
#include <linux/dmaengine.h>
#include <linux/init.h>
@@ -9,32 +10,87 @@
#include <linux/spinlock.h>
#include "virt-dma.h"
-#define HISI_DMA_SQ_BASE_L 0x0
-#define HISI_DMA_SQ_BASE_H 0x4
-#define HISI_DMA_SQ_DEPTH 0x8
-#define HISI_DMA_SQ_TAIL_PTR 0xc
-#define HISI_DMA_CQ_BASE_L 0x10
-#define HISI_DMA_CQ_BASE_H 0x14
-#define HISI_DMA_CQ_DEPTH 0x18
-#define HISI_DMA_CQ_HEAD_PTR 0x1c
-#define HISI_DMA_CTRL0 0x20
-#define HISI_DMA_CTRL0_QUEUE_EN_S 0
-#define HISI_DMA_CTRL0_QUEUE_PAUSE_S 4
-#define HISI_DMA_CTRL1 0x24
-#define HISI_DMA_CTRL1_QUEUE_RESET_S 0
-#define HISI_DMA_Q_FSM_STS 0x30
-#define HISI_DMA_FSM_STS_MASK GENMASK(3, 0)
-#define HISI_DMA_INT_STS 0x40
-#define HISI_DMA_INT_STS_MASK GENMASK(12, 0)
-#define HISI_DMA_INT_MSK 0x44
-#define HISI_DMA_MODE 0x217c
-#define HISI_DMA_OFFSET 0x100
-
-#define HISI_DMA_MSI_NUM 32
-#define HISI_DMA_CHAN_NUM 30
-#define HISI_DMA_Q_DEPTH_VAL 1024
-
-#define PCI_BAR_2 2
+/* HiSilicon DMA register common field define */
+#define HISI_DMA_Q_SQ_BASE_L 0x0
+#define HISI_DMA_Q_SQ_BASE_H 0x4
+#define HISI_DMA_Q_SQ_DEPTH 0x8
+#define HISI_DMA_Q_SQ_TAIL_PTR 0xc
+#define HISI_DMA_Q_CQ_BASE_L 0x10
+#define HISI_DMA_Q_CQ_BASE_H 0x14
+#define HISI_DMA_Q_CQ_DEPTH 0x18
+#define HISI_DMA_Q_CQ_HEAD_PTR 0x1c
+#define HISI_DMA_Q_CTRL0 0x20
+#define HISI_DMA_Q_CTRL0_QUEUE_EN BIT(0)
+#define HISI_DMA_Q_CTRL0_QUEUE_PAUSE BIT(4)
+#define HISI_DMA_Q_CTRL1 0x24
+#define HISI_DMA_Q_CTRL1_QUEUE_RESET BIT(0)
+#define HISI_DMA_Q_FSM_STS 0x30
+#define HISI_DMA_Q_FSM_STS_MASK GENMASK(3, 0)
+#define HISI_DMA_Q_ERR_INT_NUM0 0x84
+#define HISI_DMA_Q_ERR_INT_NUM1 0x88
+#define HISI_DMA_Q_ERR_INT_NUM2 0x8c
+
+/* HiSilicon IP08 DMA register and field define */
+#define HISI_DMA_HIP08_MODE 0x217C
+#define HISI_DMA_HIP08_Q_BASE 0x0
+#define HISI_DMA_HIP08_Q_CTRL0_ERR_ABORT_EN BIT(2)
+#define HISI_DMA_HIP08_Q_INT_STS 0x40
+#define HISI_DMA_HIP08_Q_INT_MSK 0x44
+#define HISI_DMA_HIP08_Q_INT_STS_MASK GENMASK(14, 0)
+#define HISI_DMA_HIP08_Q_ERR_INT_NUM3 0x90
+#define HISI_DMA_HIP08_Q_ERR_INT_NUM4 0x94
+#define HISI_DMA_HIP08_Q_ERR_INT_NUM5 0x98
+#define HISI_DMA_HIP08_Q_ERR_INT_NUM6 0x48
+#define HISI_DMA_HIP08_Q_CTRL0_SQCQ_DRCT BIT(24)
+
+/* HiSilicon IP09 DMA register and field define */
+#define HISI_DMA_HIP09_DMA_FLR_DISABLE 0xA00
+#define HISI_DMA_HIP09_DMA_FLR_DISABLE_B BIT(0)
+#define HISI_DMA_HIP09_Q_BASE 0x2000
+#define HISI_DMA_HIP09_Q_CTRL0_ERR_ABORT_EN GENMASK(31, 28)
+#define HISI_DMA_HIP09_Q_CTRL0_SQ_DRCT BIT(26)
+#define HISI_DMA_HIP09_Q_CTRL0_CQ_DRCT BIT(27)
+#define HISI_DMA_HIP09_Q_CTRL1_VA_ENABLE BIT(2)
+#define HISI_DMA_HIP09_Q_INT_STS 0x40
+#define HISI_DMA_HIP09_Q_INT_MSK 0x44
+#define HISI_DMA_HIP09_Q_INT_STS_MASK 0x1
+#define HISI_DMA_HIP09_Q_ERR_INT_STS 0x48
+#define HISI_DMA_HIP09_Q_ERR_INT_MSK 0x4C
+#define HISI_DMA_HIP09_Q_ERR_INT_STS_MASK GENMASK(18, 1)
+#define HISI_DMA_HIP09_PORT_CFG_REG(port_id) (0x800 + \
+ (port_id) * 0x20)
+#define HISI_DMA_HIP09_PORT_CFG_LINK_DOWN_MASK_B BIT(16)
+
+#define HISI_DMA_HIP09_MAX_PORT_NUM 16
+
+#define HISI_DMA_HIP08_MSI_NUM 32
+#define HISI_DMA_HIP08_CHAN_NUM 30
+#define HISI_DMA_HIP09_MSI_NUM 4
+#define HISI_DMA_HIP09_CHAN_NUM 4
+#define HISI_DMA_REVISION_HIP08B 0x21
+#define HISI_DMA_REVISION_HIP09A 0x30
+
+#define HISI_DMA_Q_OFFSET 0x100
+#define HISI_DMA_Q_DEPTH_VAL 1024
+
+#define PCI_BAR_2 2
+
+#define HISI_DMA_POLL_Q_STS_DELAY_US 10
+#define HISI_DMA_POLL_Q_STS_TIME_OUT_US 1000
+
+#define HISI_DMA_MAX_DIR_NAME_LEN 128
+
+/*
+ * The HIP08B(HiSilicon IP08) and HIP09A(HiSilicon IP09) are DMA iEPs, they
+ * have the same pci device id but different pci revision.
+ * Unfortunately, they have different register layouts, so two layout
+ * enumerations are defined.
+ */
+enum hisi_dma_reg_layout {
+ HISI_DMA_REG_LAYOUT_INVALID = 0,
+ HISI_DMA_REG_LAYOUT_HIP08,
+ HISI_DMA_REG_LAYOUT_HIP09
+};
enum hisi_dma_mode {
EP = 0,
@@ -105,9 +161,162 @@ struct hisi_dma_dev {
struct dma_device dma_dev;
u32 chan_num;
u32 chan_depth;
+ enum hisi_dma_reg_layout reg_layout;
+ void __iomem *queue_base; /* queue region start of register */
struct hisi_dma_chan chan[];
};
+#ifdef CONFIG_DEBUG_FS
+
+static const struct debugfs_reg32 hisi_dma_comm_chan_regs[] = {
+ {"DMA_QUEUE_SQ_DEPTH ", 0x0008ull},
+ {"DMA_QUEUE_SQ_TAIL_PTR ", 0x000Cull},
+ {"DMA_QUEUE_CQ_DEPTH ", 0x0018ull},
+ {"DMA_QUEUE_CQ_HEAD_PTR ", 0x001Cull},
+ {"DMA_QUEUE_CTRL0 ", 0x0020ull},
+ {"DMA_QUEUE_CTRL1 ", 0x0024ull},
+ {"DMA_QUEUE_FSM_STS ", 0x0030ull},
+ {"DMA_QUEUE_SQ_STS ", 0x0034ull},
+ {"DMA_QUEUE_CQ_TAIL_PTR ", 0x003Cull},
+ {"DMA_QUEUE_INT_STS ", 0x0040ull},
+ {"DMA_QUEUE_INT_MSK ", 0x0044ull},
+ {"DMA_QUEUE_INT_RO ", 0x006Cull},
+};
+
+static const struct debugfs_reg32 hisi_dma_hip08_chan_regs[] = {
+ {"DMA_QUEUE_BYTE_CNT ", 0x0038ull},
+ {"DMA_ERR_INT_NUM6 ", 0x0048ull},
+ {"DMA_QUEUE_DESP0 ", 0x0050ull},
+ {"DMA_QUEUE_DESP1 ", 0x0054ull},
+ {"DMA_QUEUE_DESP2 ", 0x0058ull},
+ {"DMA_QUEUE_DESP3 ", 0x005Cull},
+ {"DMA_QUEUE_DESP4 ", 0x0074ull},
+ {"DMA_QUEUE_DESP5 ", 0x0078ull},
+ {"DMA_QUEUE_DESP6 ", 0x007Cull},
+ {"DMA_QUEUE_DESP7 ", 0x0080ull},
+ {"DMA_ERR_INT_NUM0 ", 0x0084ull},
+ {"DMA_ERR_INT_NUM1 ", 0x0088ull},
+ {"DMA_ERR_INT_NUM2 ", 0x008Cull},
+ {"DMA_ERR_INT_NUM3 ", 0x0090ull},
+ {"DMA_ERR_INT_NUM4 ", 0x0094ull},
+ {"DMA_ERR_INT_NUM5 ", 0x0098ull},
+ {"DMA_QUEUE_SQ_STS2 ", 0x00A4ull},
+};
+
+static const struct debugfs_reg32 hisi_dma_hip09_chan_regs[] = {
+ {"DMA_QUEUE_ERR_INT_STS ", 0x0048ull},
+ {"DMA_QUEUE_ERR_INT_MSK ", 0x004Cull},
+ {"DFX_SQ_READ_ERR_PTR ", 0x0068ull},
+ {"DFX_DMA_ERR_INT_NUM0 ", 0x0084ull},
+ {"DFX_DMA_ERR_INT_NUM1 ", 0x0088ull},
+ {"DFX_DMA_ERR_INT_NUM2 ", 0x008Cull},
+ {"DFX_DMA_QUEUE_SQ_STS2 ", 0x00A4ull},
+};
+
+static const struct debugfs_reg32 hisi_dma_hip08_comm_regs[] = {
+ {"DMA_ECC_ERR_ADDR ", 0x2004ull},
+ {"DMA_ECC_ECC_CNT ", 0x2014ull},
+ {"COMMON_AND_CH_ERR_STS ", 0x2030ull},
+ {"LOCAL_CPL_ID_STS_0 ", 0x20E0ull},
+ {"LOCAL_CPL_ID_STS_1 ", 0x20E4ull},
+ {"LOCAL_CPL_ID_STS_2 ", 0x20E8ull},
+ {"LOCAL_CPL_ID_STS_3 ", 0x20ECull},
+ {"LOCAL_TLP_NUM ", 0x2158ull},
+ {"SQCQ_TLP_NUM ", 0x2164ull},
+ {"CPL_NUM ", 0x2168ull},
+ {"INF_BACK_PRESS_STS ", 0x2170ull},
+ {"DMA_CH_RAS_LEVEL ", 0x2184ull},
+ {"DMA_CM_RAS_LEVEL ", 0x2188ull},
+ {"DMA_CH_ERR_STS ", 0x2190ull},
+ {"DMA_CH_DONE_STS ", 0x2194ull},
+ {"DMA_SQ_TAG_STS_0 ", 0x21A0ull},
+ {"DMA_SQ_TAG_STS_1 ", 0x21A4ull},
+ {"DMA_SQ_TAG_STS_2 ", 0x21A8ull},
+ {"DMA_SQ_TAG_STS_3 ", 0x21ACull},
+ {"LOCAL_P_ID_STS_0 ", 0x21B0ull},
+ {"LOCAL_P_ID_STS_1 ", 0x21B4ull},
+ {"LOCAL_P_ID_STS_2 ", 0x21B8ull},
+ {"LOCAL_P_ID_STS_3 ", 0x21BCull},
+ {"DMA_PREBUFF_INFO_0 ", 0x2200ull},
+ {"DMA_CM_TABLE_INFO_0 ", 0x2220ull},
+ {"DMA_CM_CE_RO ", 0x2244ull},
+ {"DMA_CM_NFE_RO ", 0x2248ull},
+ {"DMA_CM_FE_RO ", 0x224Cull},
+};
+
+static const struct debugfs_reg32 hisi_dma_hip09_comm_regs[] = {
+ {"COMMON_AND_CH_ERR_STS ", 0x0030ull},
+ {"DMA_PORT_IDLE_STS ", 0x0150ull},
+ {"DMA_CH_RAS_LEVEL ", 0x0184ull},
+ {"DMA_CM_RAS_LEVEL ", 0x0188ull},
+ {"DMA_CM_CE_RO ", 0x0244ull},
+ {"DMA_CM_NFE_RO ", 0x0248ull},
+ {"DMA_CM_FE_RO ", 0x024Cull},
+ {"DFX_INF_BACK_PRESS_STS0 ", 0x1A40ull},
+ {"DFX_INF_BACK_PRESS_STS1 ", 0x1A44ull},
+ {"DFX_INF_BACK_PRESS_STS2 ", 0x1A48ull},
+ {"DFX_DMA_WRR_DISABLE ", 0x1A4Cull},
+ {"DFX_PA_REQ_TLP_NUM ", 0x1C00ull},
+ {"DFX_PA_BACK_TLP_NUM ", 0x1C04ull},
+ {"DFX_PA_RETRY_TLP_NUM ", 0x1C08ull},
+ {"DFX_LOCAL_NP_TLP_NUM ", 0x1C0Cull},
+ {"DFX_LOCAL_CPL_HEAD_TLP_NUM ", 0x1C10ull},
+ {"DFX_LOCAL_CPL_DATA_TLP_NUM ", 0x1C14ull},
+ {"DFX_LOCAL_CPL_EXT_DATA_TLP_NUM ", 0x1C18ull},
+ {"DFX_LOCAL_P_HEAD_TLP_NUM ", 0x1C1Cull},
+ {"DFX_LOCAL_P_ACK_TLP_NUM ", 0x1C20ull},
+ {"DFX_BUF_ALOC_PORT_REQ_NUM ", 0x1C24ull},
+ {"DFX_BUF_ALOC_PORT_RESULT_NUM ", 0x1C28ull},
+ {"DFX_BUF_FAIL_SIZE_NUM ", 0x1C2Cull},
+ {"DFX_BUF_ALOC_SIZE_NUM ", 0x1C30ull},
+ {"DFX_BUF_NP_RELEASE_SIZE_NUM ", 0x1C34ull},
+ {"DFX_BUF_P_RELEASE_SIZE_NUM ", 0x1C38ull},
+ {"DFX_BUF_PORT_RELEASE_SIZE_NUM ", 0x1C3Cull},
+ {"DFX_DMA_PREBUF_MEM0_ECC_ERR_ADDR ", 0x1CA8ull},
+ {"DFX_DMA_PREBUF_MEM0_ECC_CNT ", 0x1CACull},
+ {"DFX_DMA_LOC_NP_OSTB_ECC_ERR_ADDR ", 0x1CB0ull},
+ {"DFX_DMA_LOC_NP_OSTB_ECC_CNT ", 0x1CB4ull},
+ {"DFX_DMA_PREBUF_MEM1_ECC_ERR_ADDR ", 0x1CC0ull},
+ {"DFX_DMA_PREBUF_MEM1_ECC_CNT ", 0x1CC4ull},
+ {"DMA_CH_DONE_STS ", 0x02E0ull},
+ {"DMA_CH_ERR_STS ", 0x0320ull},
+};
+#endif /* CONFIG_DEBUG_FS*/
+
+static enum hisi_dma_reg_layout hisi_dma_get_reg_layout(struct pci_dev *pdev)
+{
+ if (pdev->revision == HISI_DMA_REVISION_HIP08B)
+ return HISI_DMA_REG_LAYOUT_HIP08;
+ else if (pdev->revision >= HISI_DMA_REVISION_HIP09A)
+ return HISI_DMA_REG_LAYOUT_HIP09;
+
+ return HISI_DMA_REG_LAYOUT_INVALID;
+}
+
+static u32 hisi_dma_get_chan_num(struct pci_dev *pdev)
+{
+ if (pdev->revision == HISI_DMA_REVISION_HIP08B)
+ return HISI_DMA_HIP08_CHAN_NUM;
+
+ return HISI_DMA_HIP09_CHAN_NUM;
+}
+
+static u32 hisi_dma_get_msi_num(struct pci_dev *pdev)
+{
+ if (pdev->revision == HISI_DMA_REVISION_HIP08B)
+ return HISI_DMA_HIP08_MSI_NUM;
+
+ return HISI_DMA_HIP09_MSI_NUM;
+}
+
+static u32 hisi_dma_get_queue_base(struct pci_dev *pdev)
+{
+ if (pdev->revision == HISI_DMA_REVISION_HIP08B)
+ return HISI_DMA_HIP08_Q_BASE;
+
+ return HISI_DMA_HIP09_Q_BASE;
+}
+
static inline struct hisi_dma_chan *to_hisi_dma_chan(struct dma_chan *c)
{
return container_of(c, struct hisi_dma_chan, vc.chan);
@@ -121,7 +330,7 @@ static inline struct hisi_dma_desc *to_hisi_dma_desc(struct virt_dma_desc *vd)
static inline void hisi_dma_chan_write(void __iomem *base, u32 reg, u32 index,
u32 val)
{
- writel_relaxed(val, base + reg + index * HISI_DMA_OFFSET);
+ writel_relaxed(val, base + reg + index * HISI_DMA_Q_OFFSET);
}
static inline void hisi_dma_update_bit(void __iomem *addr, u32 pos, bool val)
@@ -129,70 +338,103 @@ static inline void hisi_dma_update_bit(void __iomem *addr, u32 pos, bool val)
u32 tmp;
tmp = readl_relaxed(addr);
- tmp = val ? tmp | BIT(pos) : tmp & ~BIT(pos);
+ tmp = val ? tmp | pos : tmp & ~pos;
writel_relaxed(tmp, addr);
}
static void hisi_dma_pause_dma(struct hisi_dma_dev *hdma_dev, u32 index,
bool pause)
{
- void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL0 + index *
- HISI_DMA_OFFSET;
+ void __iomem *addr;
- hisi_dma_update_bit(addr, HISI_DMA_CTRL0_QUEUE_PAUSE_S, pause);
+ addr = hdma_dev->queue_base + HISI_DMA_Q_CTRL0 +
+ index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_Q_CTRL0_QUEUE_PAUSE, pause);
}
static void hisi_dma_enable_dma(struct hisi_dma_dev *hdma_dev, u32 index,
bool enable)
{
- void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL0 + index *
- HISI_DMA_OFFSET;
+ void __iomem *addr;
- hisi_dma_update_bit(addr, HISI_DMA_CTRL0_QUEUE_EN_S, enable);
+ addr = hdma_dev->queue_base + HISI_DMA_Q_CTRL0 +
+ index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_Q_CTRL0_QUEUE_EN, enable);
}
static void hisi_dma_mask_irq(struct hisi_dma_dev *hdma_dev, u32 qp_index)
{
- hisi_dma_chan_write(hdma_dev->base, HISI_DMA_INT_MSK, qp_index,
- HISI_DMA_INT_STS_MASK);
+ void __iomem *q_base = hdma_dev->queue_base;
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08)
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_INT_MSK,
+ qp_index, HISI_DMA_HIP08_Q_INT_STS_MASK);
+ else {
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_INT_MSK,
+ qp_index, HISI_DMA_HIP09_Q_INT_STS_MASK);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_ERR_INT_MSK,
+ qp_index,
+ HISI_DMA_HIP09_Q_ERR_INT_STS_MASK);
+ }
}
static void hisi_dma_unmask_irq(struct hisi_dma_dev *hdma_dev, u32 qp_index)
{
- void __iomem *base = hdma_dev->base;
-
- hisi_dma_chan_write(base, HISI_DMA_INT_STS, qp_index,
- HISI_DMA_INT_STS_MASK);
- hisi_dma_chan_write(base, HISI_DMA_INT_MSK, qp_index, 0);
+ void __iomem *q_base = hdma_dev->queue_base;
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08) {
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_INT_STS,
+ qp_index, HISI_DMA_HIP08_Q_INT_STS_MASK);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_INT_MSK,
+ qp_index, 0);
+ } else {
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_INT_STS,
+ qp_index, HISI_DMA_HIP09_Q_INT_STS_MASK);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_ERR_INT_STS,
+ qp_index,
+ HISI_DMA_HIP09_Q_ERR_INT_STS_MASK);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_INT_MSK,
+ qp_index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP09_Q_ERR_INT_MSK,
+ qp_index, 0);
+ }
}
static void hisi_dma_do_reset(struct hisi_dma_dev *hdma_dev, u32 index)
{
- void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL1 + index *
- HISI_DMA_OFFSET;
+ void __iomem *addr;
- hisi_dma_update_bit(addr, HISI_DMA_CTRL1_QUEUE_RESET_S, 1);
+ addr = hdma_dev->queue_base +
+ HISI_DMA_Q_CTRL1 + index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_Q_CTRL1_QUEUE_RESET, 1);
}
static void hisi_dma_reset_qp_point(struct hisi_dma_dev *hdma_dev, u32 index)
{
- hisi_dma_chan_write(hdma_dev->base, HISI_DMA_SQ_TAIL_PTR, index, 0);
- hisi_dma_chan_write(hdma_dev->base, HISI_DMA_CQ_HEAD_PTR, index, 0);
+ void __iomem *q_base = hdma_dev->queue_base;
+
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_SQ_TAIL_PTR, index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_HEAD_PTR, index, 0);
}
-static void hisi_dma_reset_hw_chan(struct hisi_dma_chan *chan)
+static void hisi_dma_reset_or_disable_hw_chan(struct hisi_dma_chan *chan,
+ bool disable)
{
struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
u32 index = chan->qp_num, tmp;
+ void __iomem *addr;
int ret;
hisi_dma_pause_dma(hdma_dev, index, true);
hisi_dma_enable_dma(hdma_dev, index, false);
hisi_dma_mask_irq(hdma_dev, index);
- ret = readl_relaxed_poll_timeout(hdma_dev->base +
- HISI_DMA_Q_FSM_STS + index * HISI_DMA_OFFSET, tmp,
- FIELD_GET(HISI_DMA_FSM_STS_MASK, tmp) != RUN, 10, 1000);
+ addr = hdma_dev->queue_base +
+ HISI_DMA_Q_FSM_STS + index * HISI_DMA_Q_OFFSET;
+
+ ret = readl_relaxed_poll_timeout(addr, tmp,
+ FIELD_GET(HISI_DMA_Q_FSM_STS_MASK, tmp) != RUN,
+ HISI_DMA_POLL_Q_STS_DELAY_US, HISI_DMA_POLL_Q_STS_TIME_OUT_US);
if (ret) {
dev_err(&hdma_dev->pdev->dev, "disable channel timeout!\n");
WARN_ON(1);
@@ -201,12 +443,15 @@ static void hisi_dma_reset_hw_chan(struct hisi_dma_chan *chan)
hisi_dma_do_reset(hdma_dev, index);
hisi_dma_reset_qp_point(hdma_dev, index);
hisi_dma_pause_dma(hdma_dev, index, false);
- hisi_dma_enable_dma(hdma_dev, index, true);
- hisi_dma_unmask_irq(hdma_dev, index);
- ret = readl_relaxed_poll_timeout(hdma_dev->base +
- HISI_DMA_Q_FSM_STS + index * HISI_DMA_OFFSET, tmp,
- FIELD_GET(HISI_DMA_FSM_STS_MASK, tmp) == IDLE, 10, 1000);
+ if (!disable) {
+ hisi_dma_enable_dma(hdma_dev, index, true);
+ hisi_dma_unmask_irq(hdma_dev, index);
+ }
+
+ ret = readl_relaxed_poll_timeout(addr, tmp,
+ FIELD_GET(HISI_DMA_Q_FSM_STS_MASK, tmp) == IDLE,
+ HISI_DMA_POLL_Q_STS_DELAY_US, HISI_DMA_POLL_Q_STS_TIME_OUT_US);
if (ret) {
dev_err(&hdma_dev->pdev->dev, "reset channel timeout!\n");
WARN_ON(1);
@@ -218,7 +463,7 @@ static void hisi_dma_free_chan_resources(struct dma_chan *c)
struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
- hisi_dma_reset_hw_chan(chan);
+ hisi_dma_reset_or_disable_hw_chan(chan, false);
vchan_free_chan_resources(&chan->vc);
memset(chan->sq, 0, sizeof(struct hisi_dma_sqe) * hdma_dev->chan_depth);
@@ -267,7 +512,6 @@ static void hisi_dma_start_transfer(struct hisi_dma_chan *chan)
vd = vchan_next_desc(&chan->vc);
if (!vd) {
- dev_err(&hdma_dev->pdev->dev, "no issued task!\n");
chan->desc = NULL;
return;
}
@@ -288,8 +532,8 @@ static void hisi_dma_start_transfer(struct hisi_dma_chan *chan)
chan->sq_tail = (chan->sq_tail + 1) % hdma_dev->chan_depth;
/* update sq_tail to trigger a new task */
- hisi_dma_chan_write(hdma_dev->base, HISI_DMA_SQ_TAIL_PTR, chan->qp_num,
- chan->sq_tail);
+ hisi_dma_chan_write(hdma_dev->queue_base, HISI_DMA_Q_SQ_TAIL_PTR,
+ chan->qp_num, chan->sq_tail);
}
static void hisi_dma_issue_pending(struct dma_chan *c)
@@ -299,7 +543,7 @@ static void hisi_dma_issue_pending(struct dma_chan *c)
spin_lock_irqsave(&chan->vc.lock, flags);
- if (vchan_issue_pending(&chan->vc))
+ if (vchan_issue_pending(&chan->vc) && !chan->desc)
hisi_dma_start_transfer(chan);
spin_unlock_irqrestore(&chan->vc.lock, flags);
@@ -363,26 +607,86 @@ static int hisi_dma_alloc_qps_mem(struct hisi_dma_dev *hdma_dev)
static void hisi_dma_init_hw_qp(struct hisi_dma_dev *hdma_dev, u32 index)
{
struct hisi_dma_chan *chan = &hdma_dev->chan[index];
+ void __iomem *q_base = hdma_dev->queue_base;
u32 hw_depth = hdma_dev->chan_depth - 1;
- void __iomem *base = hdma_dev->base;
+ void __iomem *addr;
+ u32 tmp;
/* set sq, cq base */
- hisi_dma_chan_write(base, HISI_DMA_SQ_BASE_L, index,
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_SQ_BASE_L, index,
lower_32_bits(chan->sq_dma));
- hisi_dma_chan_write(base, HISI_DMA_SQ_BASE_H, index,
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_SQ_BASE_H, index,
upper_32_bits(chan->sq_dma));
- hisi_dma_chan_write(base, HISI_DMA_CQ_BASE_L, index,
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_BASE_L, index,
lower_32_bits(chan->cq_dma));
- hisi_dma_chan_write(base, HISI_DMA_CQ_BASE_H, index,
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_BASE_H, index,
upper_32_bits(chan->cq_dma));
/* set sq, cq depth */
- hisi_dma_chan_write(base, HISI_DMA_SQ_DEPTH, index, hw_depth);
- hisi_dma_chan_write(base, HISI_DMA_CQ_DEPTH, index, hw_depth);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_SQ_DEPTH, index, hw_depth);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_DEPTH, index, hw_depth);
/* init sq tail and cq head */
- hisi_dma_chan_write(base, HISI_DMA_SQ_TAIL_PTR, index, 0);
- hisi_dma_chan_write(base, HISI_DMA_CQ_HEAD_PTR, index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_SQ_TAIL_PTR, index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_HEAD_PTR, index, 0);
+
+ /* init error interrupt stats */
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_ERR_INT_NUM0, index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_ERR_INT_NUM1, index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_ERR_INT_NUM2, index, 0);
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08) {
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_ERR_INT_NUM3,
+ index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_ERR_INT_NUM4,
+ index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_ERR_INT_NUM5,
+ index, 0);
+ hisi_dma_chan_write(q_base, HISI_DMA_HIP08_Q_ERR_INT_NUM6,
+ index, 0);
+ /*
+ * init SQ/CQ direction selecting register.
+ * "0" is to local side and "1" is to remote side.
+ */
+ addr = q_base + HISI_DMA_Q_CTRL0 + index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_HIP08_Q_CTRL0_SQCQ_DRCT, 0);
+
+ /*
+ * 0 - Continue to next descriptor if error occurs.
+ * 1 - Abort the DMA queue if error occurs.
+ */
+ hisi_dma_update_bit(addr,
+ HISI_DMA_HIP08_Q_CTRL0_ERR_ABORT_EN, 0);
+ } else {
+ addr = q_base + HISI_DMA_Q_CTRL0 + index * HISI_DMA_Q_OFFSET;
+
+ /*
+ * init SQ/CQ direction selecting register.
+ * "0" is to local side and "1" is to remote side.
+ */
+ hisi_dma_update_bit(addr, HISI_DMA_HIP09_Q_CTRL0_SQ_DRCT, 0);
+ hisi_dma_update_bit(addr, HISI_DMA_HIP09_Q_CTRL0_CQ_DRCT, 0);
+
+ /*
+ * 0 - Continue to next descriptor if error occurs.
+ * 1 - Abort the DMA queue if error occurs.
+ */
+
+ tmp = readl_relaxed(addr);
+ tmp &= ~HISI_DMA_HIP09_Q_CTRL0_ERR_ABORT_EN;
+ writel_relaxed(tmp, addr);
+
+ /*
+ * 0 - dma should process FLR whith CPU.
+ * 1 - dma not process FLR, only cpu process FLR.
+ */
+ addr = q_base + HISI_DMA_HIP09_DMA_FLR_DISABLE +
+ index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_HIP09_DMA_FLR_DISABLE_B, 0);
+
+ addr = q_base + HISI_DMA_Q_CTRL1 + index * HISI_DMA_Q_OFFSET;
+ hisi_dma_update_bit(addr, HISI_DMA_HIP09_Q_CTRL1_VA_ENABLE, 1);
+ }
}
static void hisi_dma_enable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index)
@@ -394,7 +698,7 @@ static void hisi_dma_enable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index)
static void hisi_dma_disable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index)
{
- hisi_dma_reset_hw_chan(&hdma_dev->chan[qp_index]);
+ hisi_dma_reset_or_disable_hw_chan(&hdma_dev->chan[qp_index], true);
}
static void hisi_dma_enable_qps(struct hisi_dma_dev *hdma_dev)
@@ -426,24 +730,23 @@ static irqreturn_t hisi_dma_irq(int irq, void *data)
struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
struct hisi_dma_desc *desc;
struct hisi_dma_cqe *cqe;
+ void __iomem *q_base;
spin_lock(&chan->vc.lock);
desc = chan->desc;
cqe = chan->cq + chan->cq_head;
+ q_base = hdma_dev->queue_base;
if (desc) {
+ chan->cq_head = (chan->cq_head + 1) % hdma_dev->chan_depth;
+ hisi_dma_chan_write(q_base, HISI_DMA_Q_CQ_HEAD_PTR,
+ chan->qp_num, chan->cq_head);
if (FIELD_GET(STATUS_MASK, cqe->w0) == STATUS_SUCC) {
- chan->cq_head = (chan->cq_head + 1) %
- hdma_dev->chan_depth;
- hisi_dma_chan_write(hdma_dev->base,
- HISI_DMA_CQ_HEAD_PTR, chan->qp_num,
- chan->cq_head);
vchan_cookie_complete(&desc->vd);
+ hisi_dma_start_transfer(chan);
} else {
dev_err(&hdma_dev->pdev->dev, "task error!\n");
}
-
- chan->desc = NULL;
}
spin_unlock(&chan->vc.lock);
@@ -497,16 +800,169 @@ static void hisi_dma_disable_hw_channels(void *data)
static void hisi_dma_set_mode(struct hisi_dma_dev *hdma_dev,
enum hisi_dma_mode mode)
{
- writel_relaxed(mode == RC ? 1 : 0, hdma_dev->base + HISI_DMA_MODE);
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08)
+ writel_relaxed(mode == RC ? 1 : 0,
+ hdma_dev->base + HISI_DMA_HIP08_MODE);
}
+static void hisi_dma_init_hw(struct hisi_dma_dev *hdma_dev)
+{
+ void __iomem *addr;
+ int i;
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP09) {
+ for (i = 0; i < HISI_DMA_HIP09_MAX_PORT_NUM; i++) {
+ addr = hdma_dev->base + HISI_DMA_HIP09_PORT_CFG_REG(i);
+ hisi_dma_update_bit(addr,
+ HISI_DMA_HIP09_PORT_CFG_LINK_DOWN_MASK_B, 1);
+ }
+ }
+}
+
+static void hisi_dma_init_dma_dev(struct hisi_dma_dev *hdma_dev)
+{
+ struct dma_device *dma_dev;
+
+ dma_dev = &hdma_dev->dma_dev;
+ dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+ dma_dev->device_free_chan_resources = hisi_dma_free_chan_resources;
+ dma_dev->device_prep_dma_memcpy = hisi_dma_prep_dma_memcpy;
+ dma_dev->device_tx_status = hisi_dma_tx_status;
+ dma_dev->device_issue_pending = hisi_dma_issue_pending;
+ dma_dev->device_terminate_all = hisi_dma_terminate_all;
+ dma_dev->device_synchronize = hisi_dma_synchronize;
+ dma_dev->directions = BIT(DMA_MEM_TO_MEM);
+ dma_dev->dev = &hdma_dev->pdev->dev;
+ INIT_LIST_HEAD(&dma_dev->channels);
+}
+
+/* --- debugfs implementation --- */
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+static struct debugfs_reg32 *hisi_dma_get_ch_regs(struct hisi_dma_dev *hdma_dev,
+ u32 *regs_sz)
+{
+ struct device *dev = &hdma_dev->pdev->dev;
+ struct debugfs_reg32 *regs;
+ u32 regs_sz_comm;
+
+ regs_sz_comm = ARRAY_SIZE(hisi_dma_comm_chan_regs);
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08)
+ *regs_sz = regs_sz_comm + ARRAY_SIZE(hisi_dma_hip08_chan_regs);
+ else
+ *regs_sz = regs_sz_comm + ARRAY_SIZE(hisi_dma_hip09_chan_regs);
+
+ regs = devm_kcalloc(dev, *regs_sz, sizeof(struct debugfs_reg32),
+ GFP_KERNEL);
+ if (!regs)
+ return NULL;
+ memcpy(regs, hisi_dma_comm_chan_regs, sizeof(hisi_dma_comm_chan_regs));
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08)
+ memcpy(regs + regs_sz_comm, hisi_dma_hip08_chan_regs,
+ sizeof(hisi_dma_hip08_chan_regs));
+ else
+ memcpy(regs + regs_sz_comm, hisi_dma_hip09_chan_regs,
+ sizeof(hisi_dma_hip09_chan_regs));
+
+ return regs;
+}
+
+static int hisi_dma_create_chan_dir(struct hisi_dma_dev *hdma_dev)
+{
+ char dir_name[HISI_DMA_MAX_DIR_NAME_LEN];
+ struct debugfs_regset32 *regsets;
+ struct debugfs_reg32 *regs;
+ struct dentry *chan_dir;
+ struct device *dev;
+ u32 regs_sz;
+ int ret;
+ int i;
+
+ dev = &hdma_dev->pdev->dev;
+
+ regsets = devm_kcalloc(dev, hdma_dev->chan_num,
+ sizeof(*regsets), GFP_KERNEL);
+ if (!regsets)
+ return -ENOMEM;
+
+ regs = hisi_dma_get_ch_regs(hdma_dev, &regs_sz);
+ if (!regs)
+ return -ENOMEM;
+
+ for (i = 0; i < hdma_dev->chan_num; i++) {
+ regsets[i].regs = regs;
+ regsets[i].nregs = regs_sz;
+ regsets[i].base = hdma_dev->queue_base + i * HISI_DMA_Q_OFFSET;
+ regsets[i].dev = dev;
+
+ memset(dir_name, 0, HISI_DMA_MAX_DIR_NAME_LEN);
+ ret = sprintf(dir_name, "channel%d", i);
+ if (ret < 0)
+ return ret;
+
+ chan_dir = debugfs_create_dir(dir_name,
+ hdma_dev->dma_dev.dbg_dev_root);
+ debugfs_create_regset32("regs", 0444, chan_dir, &regsets[i]);
+ }
+
+ return 0;
+}
+
+static void hisi_dma_create_debugfs(struct hisi_dma_dev *hdma_dev)
+{
+ struct debugfs_regset32 *regset;
+ struct device *dev;
+ int ret;
+
+ dev = &hdma_dev->pdev->dev;
+
+ if (hdma_dev->dma_dev.dbg_dev_root == NULL)
+ return;
+
+ regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+ if (!regset)
+ return;
+
+ if (hdma_dev->reg_layout == HISI_DMA_REG_LAYOUT_HIP08) {
+ regset->regs = hisi_dma_hip08_comm_regs;
+ regset->nregs = ARRAY_SIZE(hisi_dma_hip08_comm_regs);
+ } else {
+ regset->regs = hisi_dma_hip09_comm_regs;
+ regset->nregs = ARRAY_SIZE(hisi_dma_hip09_comm_regs);
+ }
+ regset->base = hdma_dev->base;
+ regset->dev = dev;
+
+ debugfs_create_regset32("regs", 0444,
+ hdma_dev->dma_dev.dbg_dev_root, regset);
+
+ ret = hisi_dma_create_chan_dir(hdma_dev);
+ if (ret < 0)
+ dev_info(&hdma_dev->pdev->dev, "fail to create debugfs for channels!\n");
+}
+#else
+static void hisi_dma_create_debugfs(struct hisi_dma_dev *hdma_dev) { }
+#endif /* CONFIG_DEBUG_FS*/
+/* --- debugfs implementation --- */
+
static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
+ enum hisi_dma_reg_layout reg_layout;
struct device *dev = &pdev->dev;
struct hisi_dma_dev *hdma_dev;
struct dma_device *dma_dev;
+ u32 chan_num;
+ u32 msi_num;
int ret;
+ reg_layout = hisi_dma_get_reg_layout(pdev);
+ if (reg_layout == HISI_DMA_REG_LAYOUT_INVALID) {
+ dev_err(dev, "unsupported device!\n");
+ return -EINVAL;
+ }
+
ret = pcim_enable_device(pdev);
if (ret) {
dev_err(dev, "failed to enable device mem!\n");
@@ -523,40 +979,37 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (ret)
return ret;
- hdma_dev = devm_kzalloc(dev, struct_size(hdma_dev, chan, HISI_DMA_CHAN_NUM), GFP_KERNEL);
+ chan_num = hisi_dma_get_chan_num(pdev);
+ hdma_dev = devm_kzalloc(dev, struct_size(hdma_dev, chan, chan_num),
+ GFP_KERNEL);
if (!hdma_dev)
return -EINVAL;
hdma_dev->base = pcim_iomap_table(pdev)[PCI_BAR_2];
hdma_dev->pdev = pdev;
- hdma_dev->chan_num = HISI_DMA_CHAN_NUM;
hdma_dev->chan_depth = HISI_DMA_Q_DEPTH_VAL;
+ hdma_dev->chan_num = chan_num;
+ hdma_dev->reg_layout = reg_layout;
+ hdma_dev->queue_base = hdma_dev->base + hisi_dma_get_queue_base(pdev);
pci_set_drvdata(pdev, hdma_dev);
pci_set_master(pdev);
+ msi_num = hisi_dma_get_msi_num(pdev);
+
/* This will be freed by 'pcim_release()'. See 'pcim_enable_device()' */
- ret = pci_alloc_irq_vectors(pdev, HISI_DMA_MSI_NUM, HISI_DMA_MSI_NUM,
- PCI_IRQ_MSI);
+ ret = pci_alloc_irq_vectors(pdev, msi_num, msi_num, PCI_IRQ_MSI);
if (ret < 0) {
dev_err(dev, "Failed to allocate MSI vectors!\n");
return ret;
}
- dma_dev = &hdma_dev->dma_dev;
- dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
- dma_dev->device_free_chan_resources = hisi_dma_free_chan_resources;
- dma_dev->device_prep_dma_memcpy = hisi_dma_prep_dma_memcpy;
- dma_dev->device_tx_status = hisi_dma_tx_status;
- dma_dev->device_issue_pending = hisi_dma_issue_pending;
- dma_dev->device_terminate_all = hisi_dma_terminate_all;
- dma_dev->device_synchronize = hisi_dma_synchronize;
- dma_dev->directions = BIT(DMA_MEM_TO_MEM);
- dma_dev->dev = dev;
- INIT_LIST_HEAD(&dma_dev->channels);
+ hisi_dma_init_dma_dev(hdma_dev);
hisi_dma_set_mode(hdma_dev, RC);
+ hisi_dma_init_hw(hdma_dev);
+
ret = hisi_dma_enable_hw_channels(hdma_dev);
if (ret < 0) {
dev_err(dev, "failed to enable hw channel!\n");
@@ -568,11 +1021,16 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (ret)
return ret;
+ dma_dev = &hdma_dev->dma_dev;
ret = dmaenginem_async_device_register(dma_dev);
- if (ret < 0)
+ if (ret < 0) {
dev_err(dev, "failed to register device!\n");
+ return ret;
+ }
+
+ hisi_dma_create_debugfs(hdma_dev);
- return ret;
+ return 0;
}
static const struct pci_device_id hisi_dma_pci_tbl[] = {
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 92caae55aece..af5a2e252c25 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -16,12 +16,20 @@
* port 3, and so on.
*/
+#include <linux/bits.h>
#include <linux/delay.h>
+#include <linux/device.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
#include <linux/module.h>
+#include <linux/percpu-defs.h>
+#include <linux/scatterlist.h>
#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
#include "hsu.h"
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index 9e5956345748..3bca577b98a1 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -10,7 +10,11 @@
#ifndef __DMA_HSU_H__
#define __DMA_HSU_H__
-#include <linux/spinlock.h>
+#include <linux/bits.h>
+#include <linux/container_of.h>
+#include <linux/io.h>
+#include <linux/types.h>
+
#include <linux/dma/hsu.h>
#include "../virt-dma.h"
@@ -36,11 +40,11 @@
/* Bits in HSU_CH_SR */
#define HSU_CH_SR_DESCTO(x) BIT(8 + (x))
-#define HSU_CH_SR_DESCTO_ANY (BIT(11) | BIT(10) | BIT(9) | BIT(8))
+#define HSU_CH_SR_DESCTO_ANY GENMASK(11, 8)
#define HSU_CH_SR_CHE BIT(15)
#define HSU_CH_SR_DESCE(x) BIT(16 + (x))
-#define HSU_CH_SR_DESCE_ANY (BIT(19) | BIT(18) | BIT(17) | BIT(16))
-#define HSU_CH_SR_CDESC_ANY (BIT(31) | BIT(30))
+#define HSU_CH_SR_DESCE_ANY GENMASK(19, 16)
+#define HSU_CH_SR_CDESC_ANY GENMASK(31, 30)
/* Bits in HSU_CH_CR */
#define HSU_CH_CR_CHA BIT(0)
diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c
index 6a2df3dd78d0..0fcc0c0c22fc 100644
--- a/drivers/dma/hsu/pci.c
+++ b/drivers/dma/hsu/pci.c
@@ -10,6 +10,7 @@
#include <linux/bitops.h>
#include <linux/device.h>
+#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pci.h>
@@ -26,29 +27,32 @@
static irqreturn_t hsu_pci_irq(int irq, void *dev)
{
struct hsu_dma_chip *chip = dev;
- u32 dmaisr;
- u32 status;
+ unsigned long dmaisr;
unsigned short i;
+ u32 status;
int ret = 0;
int err;
dmaisr = readl(chip->regs + HSU_PCI_DMAISR);
- for (i = 0; i < chip->hsu->nr_channels; i++) {
- if (dmaisr & 0x1) {
- err = hsu_dma_get_status(chip, i, &status);
- if (err > 0)
- ret |= 1;
- else if (err == 0)
- ret |= hsu_dma_do_irq(chip, i, status);
- }
- dmaisr >>= 1;
+ for_each_set_bit(i, &dmaisr, chip->hsu->nr_channels) {
+ err = hsu_dma_get_status(chip, i, &status);
+ if (err > 0)
+ ret |= 1;
+ else if (err == 0)
+ ret |= hsu_dma_do_irq(chip, i, status);
}
return IRQ_RETVAL(ret);
}
+static void hsu_pci_dma_remove(void *chip)
+{
+ hsu_dma_remove(chip);
+}
+
static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
+ struct device *dev = &pdev->dev;
struct hsu_dma_chip *chip;
int ret;
@@ -87,9 +91,13 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (ret)
return ret;
- ret = request_irq(chip->irq, hsu_pci_irq, 0, "hsu_dma_pci", chip);
+ ret = devm_add_action_or_reset(dev, hsu_pci_dma_remove, chip);
if (ret)
- goto err_register_irq;
+ return ret;
+
+ ret = devm_request_irq(dev, chip->irq, hsu_pci_irq, 0, "hsu_dma_pci", chip);
+ if (ret)
+ return ret;
/*
* On Intel Tangier B0 and Anniedale the interrupt line, disregarding
@@ -105,18 +113,6 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
pci_set_drvdata(pdev, chip);
return 0;
-
-err_register_irq:
- hsu_dma_remove(chip);
- return ret;
-}
-
-static void hsu_pci_remove(struct pci_dev *pdev)
-{
- struct hsu_dma_chip *chip = pci_get_drvdata(pdev);
-
- free_irq(chip->irq, chip);
- hsu_dma_remove(chip);
}
static const struct pci_device_id hsu_pci_id_table[] = {
@@ -130,7 +126,6 @@ static struct pci_driver hsu_pci_driver = {
.name = "hsu_dma_pci",
.id_table = hsu_pci_id_table,
.probe = hsu_pci_probe,
- .remove = hsu_pci_remove,
};
module_pci_driver(hsu_pci_driver);
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5a8cc52c1abf..2c1e6f6daa62 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -196,6 +196,7 @@ int idxd_wq_enable(struct idxd_wq *wq)
}
wq->state = IDXD_WQ_ENABLED;
+ set_bit(wq->id, idxd->wq_enable_map);
dev_dbg(dev, "WQ %d enabled\n", wq->id);
return 0;
}
@@ -223,6 +224,7 @@ int idxd_wq_disable(struct idxd_wq *wq, bool reset_config)
if (reset_config)
idxd_wq_disable_cleanup(wq);
+ clear_bit(wq->id, idxd->wq_enable_map);
wq->state = IDXD_WQ_DISABLED;
dev_dbg(dev, "WQ %d disabled\n", wq->id);
return 0;
@@ -258,7 +260,6 @@ void idxd_wq_reset(struct idxd_wq *wq)
operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL);
idxd_wq_disable_cleanup(wq);
- wq->state = IDXD_WQ_DISABLED;
}
int idxd_wq_map_portal(struct idxd_wq *wq)
@@ -378,17 +379,20 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
struct idxd_device *idxd = wq->idxd;
lockdep_assert_held(&wq->wq_lock);
+ wq->state = IDXD_WQ_DISABLED;
memset(wq->wqcfg, 0, idxd->wqcfg_size);
wq->type = IDXD_WQT_NONE;
wq->threshold = 0;
wq->priority = 0;
- wq->ats_dis = 0;
wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
+ clear_bit(WQ_FLAG_ATS_DISABLE, &wq->flags);
memset(wq->name, 0, WQ_NAME_SIZE);
wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+ if (wq->opcap_bmap)
+ bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
}
static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq)
@@ -705,6 +709,8 @@ static void idxd_groups_clear_state(struct idxd_device *idxd)
group->tc_a = -1;
group->tc_b = -1;
}
+ group->desc_progress_limit = 0;
+ group->batch_progress_limit = 0;
}
}
@@ -761,10 +767,10 @@ static void idxd_group_config_write(struct idxd_group *group)
/* setup GRPFLAGS */
grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
- iowrite32(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset);
- dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
+ iowrite64(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset);
+ dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#llx\n",
group->id, grpcfg_offset,
- ioread32(idxd->reg_base + grpcfg_offset));
+ ioread64(idxd->reg_base + grpcfg_offset));
}
static int idxd_groups_config_write(struct idxd_device *idxd)
@@ -807,7 +813,7 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
struct idxd_device *idxd = wq->idxd;
struct device *dev = &idxd->pdev->dev;
u32 wq_offset;
- int i;
+ int i, n;
if (!wq->group)
return 0;
@@ -859,12 +865,23 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
wq->wqcfg->bof = 1;
if (idxd->hw.wq_cap.wq_ats_support)
- wq->wqcfg->wq_ats_disable = wq->ats_dis;
+ wq->wqcfg->wq_ats_disable = test_bit(WQ_FLAG_ATS_DISABLE, &wq->flags);
/* bytes 12-15 */
wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size);
+ /* bytes 32-63 */
+ if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) {
+ memset(wq->wqcfg->op_config, 0, IDXD_MAX_OPCAP_BITS / 8);
+ for_each_set_bit(n, wq->opcap_bmap, IDXD_MAX_OPCAP_BITS) {
+ int pos = n % BITS_PER_LONG_LONG;
+ int idx = n / BITS_PER_LONG_LONG;
+
+ wq->wqcfg->op_config[idx] |= BIT(pos);
+ }
+ }
+
dev_dbg(dev, "WQ %d CFGs\n", wq->id);
for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
@@ -914,6 +931,9 @@ static void idxd_group_flags_setup(struct idxd_device *idxd)
group->grpcfg.flags.rdbufs_allowed = group->rdbufs_allowed;
else
group->grpcfg.flags.rdbufs_allowed = idxd->max_rdbufs;
+
+ group->grpcfg.flags.desc_progress_limit = group->desc_progress_limit;
+ group->grpcfg.flags.batch_progress_limit = group->batch_progress_limit;
}
}
@@ -1096,8 +1116,8 @@ static void idxd_group_load_config(struct idxd_group *group)
}
grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
- group->grpcfg.flags.bits = ioread32(idxd->reg_base + grpcfg_offset);
- dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
+ group->grpcfg.flags.bits = ioread64(idxd->reg_base + grpcfg_offset);
+ dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#llx\n",
group->id, grpcfg_offset, group->grpcfg.flags.bits);
}
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index fed0dfc1eaa8..1196ab342f01 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -11,6 +11,7 @@
#include <linux/idr.h>
#include <linux/pci.h>
#include <linux/ioasid.h>
+#include <linux/bitmap.h>
#include <linux/perf_event.h>
#include <uapi/linux/idxd.h>
#include "registers.h"
@@ -95,6 +96,8 @@ struct idxd_group {
u8 rdbufs_reserved;
int tc_a;
int tc_b;
+ int desc_progress_limit;
+ int batch_progress_limit;
};
struct idxd_pmu {
@@ -132,6 +135,7 @@ enum idxd_wq_state {
enum idxd_wq_flag {
WQ_FLAG_DEDICATED = 0,
WQ_FLAG_BLOCK_ON_FAULT,
+ WQ_FLAG_ATS_DISABLE,
};
enum idxd_wq_type {
@@ -194,6 +198,8 @@ struct idxd_wq {
enum idxd_wq_state state;
unsigned long flags;
union wqcfg *wqcfg;
+ unsigned long *opcap_bmap;
+
struct dsa_hw_desc **hw_descs;
int num_descs;
union {
@@ -208,7 +214,6 @@ struct idxd_wq {
char name[WQ_NAME_SIZE + 1];
u64 max_xfer_bytes;
u32 max_batch_size;
- bool ats_dis;
};
struct idxd_engine {
@@ -299,6 +304,7 @@ struct idxd_device {
int rdbuf_limit;
int nr_rdbufs; /* non-reserved read buffers */
unsigned int wqcfg_size;
+ unsigned long *wq_enable_map;
union sw_err_reg sw_err;
wait_queue_head_t cmd_waitq;
@@ -308,6 +314,8 @@ struct idxd_device {
struct work_struct work;
struct idxd_pmu *idxd_pmu;
+
+ unsigned long *opcap_bmap;
};
/* IDXD software descriptor */
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index aa3478257ddb..2b18d512cbfc 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -151,6 +151,12 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
if (!idxd->wqs)
return -ENOMEM;
+ idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev));
+ if (!idxd->wq_enable_map) {
+ kfree(idxd->wqs);
+ return -ENOMEM;
+ }
+
for (i = 0; i < idxd->max_wqs; i++) {
wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev));
if (!wq) {
@@ -185,6 +191,16 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
rc = -ENOMEM;
goto err;
}
+
+ if (idxd->hw.wq_cap.op_config) {
+ wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
+ if (!wq->opcap_bmap) {
+ put_device(conf_dev);
+ rc = -ENOMEM;
+ goto err;
+ }
+ bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
+ }
idxd->wqs[i] = wq;
}
@@ -369,6 +385,19 @@ static void idxd_read_table_offsets(struct idxd_device *idxd)
dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset);
}
+static void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count)
+{
+ int i, j, nr;
+
+ for (i = 0, nr = 0; i < count; i++) {
+ for (j = 0; j < BITS_PER_LONG_LONG; j++) {
+ if (val[i] & BIT(j))
+ set_bit(nr, bmap);
+ nr++;
+ }
+ }
+}
+
static void idxd_read_caps(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
@@ -427,6 +456,7 @@ static void idxd_read_caps(struct idxd_device *idxd)
IDXD_OPCAP_OFFSET + i * sizeof(u64));
dev_dbg(dev, "opcap[%d]: %#llx\n", i, idxd->hw.opcap.bits[i]);
}
+ multi_u64_to_bmap(idxd->opcap_bmap, &idxd->hw.opcap.bits[0], 4);
}
static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data)
@@ -448,6 +478,12 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
if (idxd->id < 0)
return NULL;
+ idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev));
+ if (!idxd->opcap_bmap) {
+ ida_free(&idxd_ida, idxd->id);
+ return NULL;
+ }
+
device_initialize(conf_dev);
conf_dev->parent = dev;
conf_dev->bus = &dsa_bus_type;
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 743ead5ebc57..aa314ebec587 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -17,12 +17,6 @@ enum irq_work_type {
IRQ_WORK_PROCESS_FAULT,
};
-struct idxd_fault {
- struct work_struct work;
- u64 addr;
- struct idxd_device *idxd;
-};
-
struct idxd_resubmit {
struct work_struct work;
struct idxd_desc *desc;
@@ -49,11 +43,12 @@ static void idxd_device_reinit(struct work_struct *work)
goto out;
for (i = 0; i < idxd->max_wqs; i++) {
- struct idxd_wq *wq = idxd->wqs[i];
+ if (test_bit(i, idxd->wq_enable_map)) {
+ struct idxd_wq *wq = idxd->wqs[i];
- if (wq->state == IDXD_WQ_ENABLED) {
rc = idxd_wq_enable(wq);
if (rc < 0) {
+ clear_bit(i, idxd->wq_enable_map);
dev_warn(dev, "Unable to re-enable wq %s\n",
dev_name(wq_confdev(wq)));
}
@@ -324,13 +319,11 @@ halt:
idxd->state = IDXD_DEV_HALTED;
idxd_wqs_quiesce(idxd);
idxd_wqs_unmap_portal(idxd);
- spin_lock(&idxd->dev_lock);
idxd_device_clear_state(idxd);
dev_err(&idxd->pdev->dev,
"idxd halted, need %s.\n",
gensts.reset_type == IDXD_DEVICE_RESET_FLR ?
"FLR" : "system reset");
- spin_unlock(&idxd->dev_lock);
return -ENXIO;
}
}
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 02449aa9c454..fe3b8d04f9db 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -54,7 +54,8 @@ union wq_cap_reg {
u64 priority:1;
u64 occupancy:1;
u64 occupancy_int:1;
- u64 rsvd3:10;
+ u64 op_config:1;
+ u64 rsvd3:9;
};
u64 bits;
} __packed;
@@ -67,7 +68,8 @@ union group_cap_reg {
u64 total_rdbufs:8; /* formerly total_tokens */
u64 rdbuf_ctrl:1; /* formerly token_en */
u64 rdbuf_limit:1; /* formerly token_limit */
- u64 rsvd:46;
+ u64 progress_limit:1; /* descriptor and batch descriptor */
+ u64 rsvd:45;
};
u64 bits;
} __packed;
@@ -90,6 +92,8 @@ struct opcap {
u64 bits[4];
};
+#define IDXD_MAX_OPCAP_BITS 256U
+
#define IDXD_OPCAP_OFFSET 0x40
#define IDXD_TABLE_OFFSET 0x60
@@ -285,16 +289,20 @@ union msix_perm {
union group_flags {
struct {
- u32 tc_a:3;
- u32 tc_b:3;
- u32 rsvd:1;
- u32 use_rdbuf_limit:1;
- u32 rdbufs_reserved:8;
- u32 rsvd2:4;
- u32 rdbufs_allowed:8;
- u32 rsvd3:4;
+ u64 tc_a:3;
+ u64 tc_b:3;
+ u64 rsvd:1;
+ u64 use_rdbuf_limit:1;
+ u64 rdbufs_reserved:8;
+ u64 rsvd2:4;
+ u64 rdbufs_allowed:8;
+ u64 rsvd3:4;
+ u64 desc_progress_limit:2;
+ u64 rsvd4:2;
+ u64 batch_progress_limit:2;
+ u64 rsvd5:26;
};
- u32 bits;
+ u64 bits;
} __packed;
struct grpcfg {
@@ -348,8 +356,11 @@ union wqcfg {
/* bytes 28-31 */
u32 rsvd8;
+
+ /* bytes 32-63 */
+ u64 op_config[4];
};
- u32 bits[8];
+ u32 bits[16];
} __packed;
#define WQCFG_PASID_IDX 2
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 3f262a57441b..bdaccf9e0436 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -443,6 +443,67 @@ static struct device_attribute dev_attr_group_traffic_class_b =
__ATTR(traffic_class_b, 0644, group_traffic_class_b_show,
group_traffic_class_b_store);
+static ssize_t group_desc_progress_limit_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+
+ return sysfs_emit(buf, "%d\n", group->desc_progress_limit);
+}
+
+static ssize_t group_desc_progress_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+ int val, rc;
+
+ rc = kstrtoint(buf, 10, &val);
+ if (rc < 0)
+ return -EINVAL;
+
+ if (val & ~GENMASK(1, 0))
+ return -EINVAL;
+
+ group->desc_progress_limit = val;
+ return count;
+}
+
+static struct device_attribute dev_attr_group_desc_progress_limit =
+ __ATTR(desc_progress_limit, 0644, group_desc_progress_limit_show,
+ group_desc_progress_limit_store);
+
+static ssize_t group_batch_progress_limit_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+
+ return sysfs_emit(buf, "%d\n", group->batch_progress_limit);
+}
+
+static ssize_t group_batch_progress_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct idxd_group *group = confdev_to_group(dev);
+ int val, rc;
+
+ rc = kstrtoint(buf, 10, &val);
+ if (rc < 0)
+ return -EINVAL;
+
+ if (val & ~GENMASK(1, 0))
+ return -EINVAL;
+
+ group->batch_progress_limit = val;
+ return count;
+}
+
+static struct device_attribute dev_attr_group_batch_progress_limit =
+ __ATTR(batch_progress_limit, 0644, group_batch_progress_limit_show,
+ group_batch_progress_limit_store);
static struct attribute *idxd_group_attributes[] = {
&dev_attr_group_work_queues.attr,
&dev_attr_group_engines.attr,
@@ -454,11 +515,35 @@ static struct attribute *idxd_group_attributes[] = {
&dev_attr_group_read_buffers_reserved.attr,
&dev_attr_group_traffic_class_a.attr,
&dev_attr_group_traffic_class_b.attr,
+ &dev_attr_group_desc_progress_limit.attr,
+ &dev_attr_group_batch_progress_limit.attr,
NULL,
};
+static bool idxd_group_attr_progress_limit_invisible(struct attribute *attr,
+ struct idxd_device *idxd)
+{
+ return (attr == &dev_attr_group_desc_progress_limit.attr ||
+ attr == &dev_attr_group_batch_progress_limit.attr) &&
+ !idxd->hw.group_cap.progress_limit;
+}
+
+static umode_t idxd_group_attr_visible(struct kobject *kobj,
+ struct attribute *attr, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct idxd_group *group = confdev_to_group(dev);
+ struct idxd_device *idxd = group->idxd;
+
+ if (idxd_group_attr_progress_limit_invisible(attr, idxd))
+ return 0;
+
+ return attr->mode;
+}
+
static const struct attribute_group idxd_group_attribute_group = {
.attrs = idxd_group_attributes,
+ .is_visible = idxd_group_attr_visible,
};
static const struct attribute_group *idxd_group_attribute_groups[] = {
@@ -973,7 +1058,7 @@ static ssize_t wq_ats_disable_show(struct device *dev, struct device_attribute *
{
struct idxd_wq *wq = confdev_to_wq(dev);
- return sysfs_emit(buf, "%u\n", wq->ats_dis);
+ return sysfs_emit(buf, "%u\n", test_bit(WQ_FLAG_ATS_DISABLE, &wq->flags));
}
static ssize_t wq_ats_disable_store(struct device *dev, struct device_attribute *attr,
@@ -994,7 +1079,10 @@ static ssize_t wq_ats_disable_store(struct device *dev, struct device_attribute
if (rc < 0)
return rc;
- wq->ats_dis = ats_dis;
+ if (ats_dis)
+ set_bit(WQ_FLAG_ATS_DISABLE, &wq->flags);
+ else
+ clear_bit(WQ_FLAG_ATS_DISABLE, &wq->flags);
return count;
}
@@ -1055,6 +1143,68 @@ static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attrib
static struct device_attribute dev_attr_wq_enqcmds_retries =
__ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store);
+static ssize_t wq_op_config_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct idxd_wq *wq = confdev_to_wq(dev);
+
+ return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, wq->opcap_bmap);
+}
+
+static int idxd_verify_supported_opcap(struct idxd_device *idxd, unsigned long *opmask)
+{
+ int bit;
+
+ /*
+ * The OPCAP is defined as 256 bits that represents each operation the device
+ * supports per bit. Iterate through all the bits and check if the input mask
+ * is set for bits that are not set in the OPCAP for the device. If no OPCAP
+ * bit is set and input mask has the bit set, then return error.
+ */
+ for_each_set_bit(bit, opmask, IDXD_MAX_OPCAP_BITS) {
+ if (!test_bit(bit, idxd->opcap_bmap))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static ssize_t wq_op_config_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct idxd_wq *wq = confdev_to_wq(dev);
+ struct idxd_device *idxd = wq->idxd;
+ unsigned long *opmask;
+ int rc;
+
+ if (wq->state != IDXD_WQ_DISABLED)
+ return -EPERM;
+
+ opmask = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
+ if (!opmask)
+ return -ENOMEM;
+
+ rc = bitmap_parse(buf, count, opmask, IDXD_MAX_OPCAP_BITS);
+ if (rc < 0)
+ goto err;
+
+ rc = idxd_verify_supported_opcap(idxd, opmask);
+ if (rc < 0)
+ goto err;
+
+ bitmap_copy(wq->opcap_bmap, opmask, IDXD_MAX_OPCAP_BITS);
+
+ bitmap_free(opmask);
+ return count;
+
+err:
+ bitmap_free(opmask);
+ return rc;
+}
+
+static struct device_attribute dev_attr_wq_op_config =
+ __ATTR(op_config, 0644, wq_op_config_show, wq_op_config_store);
+
static struct attribute *idxd_wq_attributes[] = {
&dev_attr_wq_clients.attr,
&dev_attr_wq_state.attr,
@@ -1072,11 +1222,33 @@ static struct attribute *idxd_wq_attributes[] = {
&dev_attr_wq_ats_disable.attr,
&dev_attr_wq_occupancy.attr,
&dev_attr_wq_enqcmds_retries.attr,
+ &dev_attr_wq_op_config.attr,
NULL,
};
+static bool idxd_wq_attr_op_config_invisible(struct attribute *attr,
+ struct idxd_device *idxd)
+{
+ return attr == &dev_attr_wq_op_config.attr &&
+ !idxd->hw.wq_cap.op_config;
+}
+
+static umode_t idxd_wq_attr_visible(struct kobject *kobj,
+ struct attribute *attr, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct idxd_wq *wq = confdev_to_wq(dev);
+ struct idxd_device *idxd = wq->idxd;
+
+ if (idxd_wq_attr_op_config_invisible(attr, idxd))
+ return 0;
+
+ return attr->mode;
+}
+
static const struct attribute_group idxd_wq_attribute_group = {
.attrs = idxd_wq_attributes,
+ .is_visible = idxd_wq_attr_visible,
};
static const struct attribute_group *idxd_wq_attribute_groups[] = {
@@ -1088,6 +1260,7 @@ static void idxd_conf_wq_release(struct device *dev)
{
struct idxd_wq *wq = confdev_to_wq(dev);
+ bitmap_free(wq->opcap_bmap);
kfree(wq->wqcfg);
kfree(wq);
}
@@ -1177,14 +1350,8 @@ static ssize_t op_cap_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct idxd_device *idxd = confdev_to_idxd(dev);
- int i, rc = 0;
-
- for (i = 0; i < 4; i++)
- rc += sysfs_emit_at(buf, rc, "%#llx ", idxd->hw.opcap.bits[i]);
- rc--;
- rc += sysfs_emit_at(buf, rc, "\n");
- return rc;
+ return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, idxd->opcap_bmap);
}
static DEVICE_ATTR_RO(op_cap);
@@ -1405,9 +1572,11 @@ static void idxd_conf_device_release(struct device *dev)
struct idxd_device *idxd = confdev_to_idxd(dev);
kfree(idxd->groups);
+ bitmap_free(idxd->wq_enable_map);
kfree(idxd->wqs);
kfree(idxd->engines);
ida_free(&idxd_ida, idxd->id);
+ bitmap_free(idxd->opcap_bmap);
kfree(idxd);
}
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 37ff4ec7db76..e2070df6cad2 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -656,7 +656,7 @@ static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete)
if (active - i == 0) {
dev_dbg(to_dev(ioat_chan), "%s: cancel completion timeout\n",
__func__);
- mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+ mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
}
/* microsecond delay by sysfs variable per pending descriptor */
@@ -682,7 +682,7 @@ static void ioat_cleanup(struct ioatdma_chan *ioat_chan)
if (chanerr &
(IOAT_CHANERR_HANDLE_MASK | IOAT_CHANERR_RECOVER_MASK)) {
- mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+ mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
ioat_eh(ioat_chan);
}
}
@@ -879,7 +879,7 @@ static void check_active(struct ioatdma_chan *ioat_chan)
}
if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &ioat_chan->state))
- mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
+ mod_timer_pending(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
}
static void ioat_reboot_chan(struct ioatdma_chan *ioat_chan)
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 140cfe3782fb..35e06b382603 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -196,10 +196,8 @@ extern const struct sysfs_ops ioat_sysfs_ops;
extern struct ioat_sysfs_entry ioat_version_attr;
extern struct ioat_sysfs_entry ioat_cap_attr;
extern int ioat_pending_level;
-extern int ioat_ring_alloc_order;
extern struct kobj_type ioat_ktype;
extern struct kmem_cache *ioat_cache;
-extern int ioat_ring_max_alloc_order;
extern struct kmem_cache *ioat_sed_cache;
static inline struct ioatdma_chan *to_ioat_chan(struct dma_chan *c)
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 994fc4d2aca4..dc147cc2436e 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -670,7 +670,7 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan,
return mxs_chan->status;
}
-static int __init mxs_dma_init(struct mxs_dma_engine *mxs_dma)
+static int mxs_dma_init(struct mxs_dma_engine *mxs_dma)
{
int ret;
@@ -741,7 +741,7 @@ static struct dma_chan *mxs_dma_xlate(struct of_phandle_args *dma_spec,
ofdma->of_node);
}
-static int __init mxs_dma_probe(struct platform_device *pdev)
+static int mxs_dma_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
const struct mxs_dma_type *dma_type;
@@ -839,10 +839,7 @@ static struct platform_driver mxs_dma_driver = {
.name = "mxs-dma",
.of_match_table = mxs_dma_dt_ids,
},
+ .probe = mxs_dma_probe,
};
-static int __init mxs_dma_module_init(void)
-{
- return platform_driver_probe(&mxs_dma_driver, mxs_dma_probe);
-}
-subsys_initcall(mxs_dma_module_init);
+builtin_platform_driver(mxs_dma_driver);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 09915a5cba3e..0d9257fbdfb0 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2752,7 +2752,6 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
return NULL;
pch->cyclic = true;
- desc->txd.flags = flags;
return &desc->txd;
}
@@ -2804,8 +2803,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
desc->bytes_requested = len;
- desc->txd.flags = flags;
-
return &desc->txd;
}
@@ -2889,7 +2886,6 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
}
/* Return the last desc in the chain */
- desc->txd.flags = flg;
return &desc->txd;
}
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 8f0c9c4e2efd..3f56514bbef8 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -1150,9 +1150,9 @@ static void gpi_ev_tasklet(unsigned long data)
{
struct gpii *gpii = (struct gpii *)data;
- read_lock_bh(&gpii->pm_lock);
+ read_lock(&gpii->pm_lock);
if (!REG_ACCESS_VALID(gpii->pm_state)) {
- read_unlock_bh(&gpii->pm_lock);
+ read_unlock(&gpii->pm_lock);
dev_err(gpii->gpi_dev->dev, "not processing any events, pm_state:%s\n",
TO_GPI_PM_STR(gpii->pm_state));
return;
@@ -1163,7 +1163,7 @@ static void gpi_ev_tasklet(unsigned long data)
/* enable IEOB, switching back to interrupts */
gpi_config_interrupts(gpii, MASK_IEOB_SETTINGS, 1);
- read_unlock_bh(&gpii->pm_lock);
+ read_unlock(&gpii->pm_lock);
}
/* marks all pending events for the channel as stale */
@@ -2288,6 +2288,7 @@ static int gpi_probe(struct platform_device *pdev)
static const struct of_device_id gpi_of_match[] = {
{ .compatible = "qcom,sc7280-gpi-dma", .data = (void *)0x10000 },
{ .compatible = "qcom,sdm845-gpi-dma", .data = (void *)0x0 },
+ { .compatible = "qcom,sm6350-gpi-dma", .data = (void *)0x10000 },
{ .compatible = "qcom,sm8150-gpi-dma", .data = (void *)0x0 },
{ .compatible = "qcom,sm8250-gpi-dma", .data = (void *)0x0 },
{ .compatible = "qcom,sm8350-gpi-dma", .data = (void *)0x10000 },
diff --git a/drivers/dma/qcom/qcom_adm.c b/drivers/dma/qcom/qcom_adm.c
index facdacf8aede..d56caf1681ff 100644
--- a/drivers/dma/qcom/qcom_adm.c
+++ b/drivers/dma/qcom/qcom_adm.c
@@ -379,13 +379,13 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
if (blk_size < 0) {
dev_err(adev->dev, "invalid burst value: %d\n",
burst);
- return ERR_PTR(-EINVAL);
+ return NULL;
}
crci = achan->crci & 0xf;
if (!crci || achan->crci > 0x1f) {
dev_err(adev->dev, "invalid crci value\n");
- return ERR_PTR(-EINVAL);
+ return NULL;
}
}
@@ -403,8 +403,10 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
}
async_desc = kzalloc(sizeof(*async_desc), GFP_NOWAIT);
- if (!async_desc)
- return ERR_PTR(-ENOMEM);
+ if (!async_desc) {
+ dev_err(adev->dev, "not enough memory for async_desc struct\n");
+ return NULL;
+ }
async_desc->mux = achan->mux ? ADM_CRCI_CTL_MUX_SEL : 0;
async_desc->crci = crci;
@@ -414,8 +416,10 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
sizeof(*cple) + 2 * ADM_DESC_ALIGN;
async_desc->cpl = kzalloc(async_desc->dma_len, GFP_NOWAIT);
- if (!async_desc->cpl)
+ if (!async_desc->cpl) {
+ dev_err(adev->dev, "not enough memory for cpl struct\n");
goto free;
+ }
async_desc->adev = adev;
@@ -437,8 +441,10 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
async_desc->dma_addr = dma_map_single(adev->dev, async_desc->cpl,
async_desc->dma_len,
DMA_TO_DEVICE);
- if (dma_mapping_error(adev->dev, async_desc->dma_addr))
+ if (dma_mapping_error(adev->dev, async_desc->dma_addr)) {
+ dev_err(adev->dev, "dma mapping error for cpl\n");
goto free;
+ }
cple_addr = async_desc->dma_addr + ((void *)cple - async_desc->cpl);
@@ -454,7 +460,7 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
free:
kfree(async_desc);
- return ERR_PTR(-ENOMEM);
+ return NULL;
}
/**
@@ -494,7 +500,7 @@ static int adm_slave_config(struct dma_chan *chan, struct dma_slave_config *cfg)
spin_lock_irqsave(&achan->vc.lock, flag);
memcpy(&achan->slave, cfg, sizeof(struct dma_slave_config));
- if (cfg->peripheral_size == sizeof(config))
+ if (cfg->peripheral_size == sizeof(*config))
achan->crci = config->crci;
spin_unlock_irqrestore(&achan->vc.lock, flag);
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index f6ed7e889781..a09eeb545f7d 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -1094,7 +1094,7 @@ static int s3c24xx_dma_init_virtual_channels(struct s3c24xx_dma_engine *s3cdma,
INIT_LIST_HEAD(&dmadev->channels);
/*
- * Register as many many memcpy as we have physical channels,
+ * Register as many memcpy as we have physical channels,
* we won't always be able to use all but the code will have
* to cope with that situation.
*/
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 4f8b8498c5c6..6b524eb6bcf3 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -405,10 +405,8 @@ static int sf_pdma_irq_init(struct platform_device *pdev, struct sf_pdma *pdma)
chan = &pdma->chans[i];
irq = platform_get_irq(pdev, i * 2);
- if (irq < 0) {
- dev_err(&pdev->dev, "ch(%d) Can't get done irq.\n", i);
+ if (irq < 0)
return -EINVAL;
- }
r = devm_request_irq(&pdev->dev, irq, sf_pdma_done_isr, 0,
dev_name(&pdev->dev), (void *)chan);
@@ -420,10 +418,8 @@ static int sf_pdma_irq_init(struct platform_device *pdev, struct sf_pdma *pdma)
chan->txirq = irq;
irq = platform_get_irq(pdev, (i * 2) + 1);
- if (irq < 0) {
- dev_err(&pdev->dev, "ch(%d) Can't get err irq.\n", i);
+ if (irq < 0)
return -EINVAL;
- }
r = devm_request_irq(&pdev->dev, irq, sf_pdma_err_isr, 0,
dev_name(&pdev->dev), (void *)chan);
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 13d12d660cc2..641d689d17ff 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -103,8 +103,8 @@ struct rcar_dmac_desc_page {
struct list_head node;
union {
- struct rcar_dmac_desc descs[0];
- struct rcar_dmac_xfer_chunk chunks[0];
+ DECLARE_FLEX_ARRAY(struct rcar_dmac_desc, descs);
+ DECLARE_FLEX_ARRAY(struct rcar_dmac_xfer_chunk, chunks);
};
};
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index adb25a11c70f..4891a1767e5a 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -9,6 +9,7 @@
* Pierre-Yves Mordret <pierre-yves.mordret@st.com>
*/
+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
@@ -32,8 +33,10 @@
#define STM32_DMA_LISR 0x0000 /* DMA Low Int Status Reg */
#define STM32_DMA_HISR 0x0004 /* DMA High Int Status Reg */
+#define STM32_DMA_ISR(n) (((n) & 4) ? STM32_DMA_HISR : STM32_DMA_LISR)
#define STM32_DMA_LIFCR 0x0008 /* DMA Low Int Flag Clear Reg */
#define STM32_DMA_HIFCR 0x000c /* DMA High Int Flag Clear Reg */
+#define STM32_DMA_IFCR(n) (((n) & 4) ? STM32_DMA_HIFCR : STM32_DMA_LIFCR)
#define STM32_DMA_TCI BIT(5) /* Transfer Complete Interrupt */
#define STM32_DMA_HTI BIT(4) /* Half Transfer Interrupt */
#define STM32_DMA_TEI BIT(3) /* Transfer Error Interrupt */
@@ -43,23 +46,22 @@
| STM32_DMA_TEI \
| STM32_DMA_DMEI \
| STM32_DMA_FEI)
+/*
+ * If (chan->id % 4) is 2 or 3, left shift the mask by 16 bits;
+ * if (ch % 4) is 1 or 3, additionally left shift the mask by 6 bits.
+ */
+#define STM32_DMA_FLAGS_SHIFT(n) ({ typeof(n) (_n) = (n); \
+ (((_n) & 2) << 3) | (((_n) & 1) * 6); })
/* DMA Stream x Configuration Register */
#define STM32_DMA_SCR(x) (0x0010 + 0x18 * (x)) /* x = 0..7 */
-#define STM32_DMA_SCR_REQ(n) ((n & 0x7) << 25)
+#define STM32_DMA_SCR_REQ_MASK GENMASK(27, 25)
#define STM32_DMA_SCR_MBURST_MASK GENMASK(24, 23)
-#define STM32_DMA_SCR_MBURST(n) ((n & 0x3) << 23)
#define STM32_DMA_SCR_PBURST_MASK GENMASK(22, 21)
-#define STM32_DMA_SCR_PBURST(n) ((n & 0x3) << 21)
#define STM32_DMA_SCR_PL_MASK GENMASK(17, 16)
-#define STM32_DMA_SCR_PL(n) ((n & 0x3) << 16)
#define STM32_DMA_SCR_MSIZE_MASK GENMASK(14, 13)
-#define STM32_DMA_SCR_MSIZE(n) ((n & 0x3) << 13)
#define STM32_DMA_SCR_PSIZE_MASK GENMASK(12, 11)
-#define STM32_DMA_SCR_PSIZE(n) ((n & 0x3) << 11)
-#define STM32_DMA_SCR_PSIZE_GET(n) ((n & STM32_DMA_SCR_PSIZE_MASK) >> 11)
#define STM32_DMA_SCR_DIR_MASK GENMASK(7, 6)
-#define STM32_DMA_SCR_DIR(n) ((n & 0x3) << 6)
#define STM32_DMA_SCR_TRBUFF BIT(20) /* Bufferable transfer for USART/UART */
#define STM32_DMA_SCR_CT BIT(19) /* Target in double buffer */
#define STM32_DMA_SCR_DBM BIT(18) /* Double Buffer Mode */
@@ -96,7 +98,6 @@
/* DMA stream x FIFO control register */
#define STM32_DMA_SFCR(x) (0x0024 + 0x18 * (x))
#define STM32_DMA_SFCR_FTH_MASK GENMASK(1, 0)
-#define STM32_DMA_SFCR_FTH(n) (n & STM32_DMA_SFCR_FTH_MASK)
#define STM32_DMA_SFCR_FEIE BIT(7) /* FIFO error interrupt enable */
#define STM32_DMA_SFCR_DMDIS BIT(2) /* Direct mode disable */
#define STM32_DMA_SFCR_MASK (STM32_DMA_SFCR_FEIE \
@@ -137,11 +138,9 @@
/* DMA Features */
#define STM32_DMA_THRESHOLD_FTR_MASK GENMASK(1, 0)
-#define STM32_DMA_THRESHOLD_FTR_GET(n) ((n) & STM32_DMA_THRESHOLD_FTR_MASK)
#define STM32_DMA_DIRECT_MODE_MASK BIT(2)
-#define STM32_DMA_DIRECT_MODE_GET(n) (((n) & STM32_DMA_DIRECT_MODE_MASK) >> 2)
#define STM32_DMA_ALT_ACK_MODE_MASK BIT(4)
-#define STM32_DMA_ALT_ACK_MODE_GET(n) (((n) & STM32_DMA_ALT_ACK_MODE_MASK) >> 4)
+#define STM32_DMA_MDMA_STREAM_ID_MASK GENMASK(19, 16)
enum stm32_dma_width {
STM32_DMA_BYTE,
@@ -195,6 +194,19 @@ struct stm32_dma_desc {
struct stm32_dma_sg_req sg_req[];
};
+/**
+ * struct stm32_dma_mdma_config - STM32 DMA MDMA configuration
+ * @stream_id: DMA request to trigger STM32 MDMA transfer
+ * @ifcr: DMA interrupt flag clear register address,
+ * used by STM32 MDMA to clear DMA Transfer Complete flag
+ * @tcf: DMA Transfer Complete flag
+ */
+struct stm32_dma_mdma_config {
+ u32 stream_id;
+ u32 ifcr;
+ u32 tcf;
+};
+
struct stm32_dma_chan {
struct virt_dma_chan vchan;
bool config_init;
@@ -209,6 +221,8 @@ struct stm32_dma_chan {
u32 mem_burst;
u32 mem_width;
enum dma_status status;
+ bool trig_mdma;
+ struct stm32_dma_mdma_config mdma_config;
};
struct stm32_dma_device {
@@ -388,6 +402,13 @@ static int stm32_dma_slave_config(struct dma_chan *c,
memcpy(&chan->dma_sconfig, config, sizeof(*config));
+ /* Check if user is requesting DMA to trigger STM32 MDMA */
+ if (config->peripheral_size) {
+ config->peripheral_config = &chan->mdma_config;
+ config->peripheral_size = sizeof(chan->mdma_config);
+ chan->trig_mdma = true;
+ }
+
chan->config_init = true;
return 0;
@@ -401,17 +422,10 @@ static u32 stm32_dma_irq_status(struct stm32_dma_chan *chan)
/*
* Read "flags" from DMA_xISR register corresponding to the selected
* DMA channel at the correct bit offset inside that register.
- *
- * If (ch % 4) is 2 or 3, left shift the mask by 16 bits.
- * If (ch % 4) is 1 or 3, additionally left shift the mask by 6 bits.
*/
- if (chan->id & 4)
- dma_isr = stm32_dma_read(dmadev, STM32_DMA_HISR);
- else
- dma_isr = stm32_dma_read(dmadev, STM32_DMA_LISR);
-
- flags = dma_isr >> (((chan->id & 2) << 3) | ((chan->id & 1) * 6));
+ dma_isr = stm32_dma_read(dmadev, STM32_DMA_ISR(chan->id));
+ flags = dma_isr >> STM32_DMA_FLAGS_SHIFT(chan->id);
return flags & STM32_DMA_MASKI;
}
@@ -424,17 +438,11 @@ static void stm32_dma_irq_clear(struct stm32_dma_chan *chan, u32 flags)
/*
* Write "flags" to the DMA_xIFCR register corresponding to the selected
* DMA channel at the correct bit offset inside that register.
- *
- * If (ch % 4) is 2 or 3, left shift the mask by 16 bits.
- * If (ch % 4) is 1 or 3, additionally left shift the mask by 6 bits.
*/
flags &= STM32_DMA_MASKI;
- dma_ifcr = flags << (((chan->id & 2) << 3) | ((chan->id & 1) * 6));
+ dma_ifcr = flags << STM32_DMA_FLAGS_SHIFT(chan->id);
- if (chan->id & 4)
- stm32_dma_write(dmadev, STM32_DMA_HIFCR, dma_ifcr);
- else
- stm32_dma_write(dmadev, STM32_DMA_LIFCR, dma_ifcr);
+ stm32_dma_write(dmadev, STM32_DMA_IFCR(chan->id), dma_ifcr);
}
static int stm32_dma_disable_chan(struct stm32_dma_chan *chan)
@@ -576,6 +584,10 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
sg_req = &chan->desc->sg_req[chan->next_sg];
reg = &sg_req->chan_reg;
+ /* When DMA triggers STM32 MDMA, DMA Transfer Complete is managed by STM32 MDMA */
+ if (chan->trig_mdma && chan->dma_sconfig.direction != DMA_MEM_TO_DEV)
+ reg->dma_scr &= ~STM32_DMA_SCR_TCIE;
+
reg->dma_scr &= ~STM32_DMA_SCR_EN;
stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), reg->dma_scr);
stm32_dma_write(dmadev, STM32_DMA_SPAR(chan->id), reg->dma_spar);
@@ -725,6 +737,8 @@ static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan, u32 scr)
if (chan->desc->cyclic) {
vchan_cyclic_callback(&chan->desc->vdesc);
+ if (chan->trig_mdma)
+ return;
stm32_dma_sg_inc(chan);
/* cyclic while CIRC/DBM disable => post resume reconfiguration needed */
if (!(scr & (STM32_DMA_SCR_CIRC | STM32_DMA_SCR_DBM)))
@@ -861,7 +875,8 @@ static int stm32_dma_resume(struct dma_chan *c)
sg_req = &chan->desc->sg_req[chan->next_sg - 1];
ndtr = sg_req->chan_reg.dma_sndtr;
- offset = (ndtr - chan_reg.dma_sndtr) << STM32_DMA_SCR_PSIZE_GET(chan_reg.dma_scr);
+ offset = (ndtr - chan_reg.dma_sndtr);
+ offset <<= FIELD_GET(STM32_DMA_SCR_PSIZE_MASK, chan_reg.dma_scr);
spar = sg_req->chan_reg.dma_spar;
sm0ar = sg_req->chan_reg.dma_sm0ar;
sm1ar = sg_req->chan_reg.dma_sm1ar;
@@ -973,16 +988,16 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
if (src_burst_size < 0)
return src_burst_size;
- dma_scr = STM32_DMA_SCR_DIR(STM32_DMA_MEM_TO_DEV) |
- STM32_DMA_SCR_PSIZE(dst_bus_width) |
- STM32_DMA_SCR_MSIZE(src_bus_width) |
- STM32_DMA_SCR_PBURST(dst_burst_size) |
- STM32_DMA_SCR_MBURST(src_burst_size);
+ dma_scr = FIELD_PREP(STM32_DMA_SCR_DIR_MASK, STM32_DMA_MEM_TO_DEV) |
+ FIELD_PREP(STM32_DMA_SCR_PSIZE_MASK, dst_bus_width) |
+ FIELD_PREP(STM32_DMA_SCR_MSIZE_MASK, src_bus_width) |
+ FIELD_PREP(STM32_DMA_SCR_PBURST_MASK, dst_burst_size) |
+ FIELD_PREP(STM32_DMA_SCR_MBURST_MASK, src_burst_size);
/* Set FIFO threshold */
chan->chan_reg.dma_sfcr &= ~STM32_DMA_SFCR_FTH_MASK;
if (fifoth != STM32_DMA_FIFO_THRESHOLD_NONE)
- chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(fifoth);
+ chan->chan_reg.dma_sfcr |= FIELD_PREP(STM32_DMA_SFCR_FTH_MASK, fifoth);
/* Set peripheral address */
chan->chan_reg.dma_spar = chan->dma_sconfig.dst_addr;
@@ -1030,16 +1045,16 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
if (dst_burst_size < 0)
return dst_burst_size;
- dma_scr = STM32_DMA_SCR_DIR(STM32_DMA_DEV_TO_MEM) |
- STM32_DMA_SCR_PSIZE(src_bus_width) |
- STM32_DMA_SCR_MSIZE(dst_bus_width) |
- STM32_DMA_SCR_PBURST(src_burst_size) |
- STM32_DMA_SCR_MBURST(dst_burst_size);
+ dma_scr = FIELD_PREP(STM32_DMA_SCR_DIR_MASK, STM32_DMA_DEV_TO_MEM) |
+ FIELD_PREP(STM32_DMA_SCR_PSIZE_MASK, src_bus_width) |
+ FIELD_PREP(STM32_DMA_SCR_MSIZE_MASK, dst_bus_width) |
+ FIELD_PREP(STM32_DMA_SCR_PBURST_MASK, src_burst_size) |
+ FIELD_PREP(STM32_DMA_SCR_MBURST_MASK, dst_burst_size);
/* Set FIFO threshold */
chan->chan_reg.dma_sfcr &= ~STM32_DMA_SFCR_FTH_MASK;
if (fifoth != STM32_DMA_FIFO_THRESHOLD_NONE)
- chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(fifoth);
+ chan->chan_reg.dma_sfcr |= FIELD_PREP(STM32_DMA_SFCR_FTH_MASK, fifoth);
/* Set peripheral address */
chan->chan_reg.dma_spar = chan->dma_sconfig.src_addr;
@@ -1099,6 +1114,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
else
chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL;
+ /* Activate Double Buffer Mode if DMA triggers STM32 MDMA and more than 1 sg */
+ if (chan->trig_mdma && sg_len > 1)
+ chan->chan_reg.dma_scr |= STM32_DMA_SCR_DBM;
+
for_each_sg(sgl, sg, sg_len, i) {
ret = stm32_dma_set_xfer_param(chan, direction, &buswidth,
sg_dma_len(sg),
@@ -1120,6 +1139,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
desc->sg_req[i].chan_reg.dma_spar = chan->chan_reg.dma_spar;
desc->sg_req[i].chan_reg.dma_sm0ar = sg_dma_address(sg);
desc->sg_req[i].chan_reg.dma_sm1ar = sg_dma_address(sg);
+ if (chan->trig_mdma)
+ desc->sg_req[i].chan_reg.dma_sm1ar += sg_dma_len(sg);
desc->sg_req[i].chan_reg.dma_sndtr = nb_data_items;
}
@@ -1207,8 +1228,11 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_cyclic(
desc->sg_req[i].chan_reg.dma_spar = chan->chan_reg.dma_spar;
desc->sg_req[i].chan_reg.dma_sm0ar = buf_addr;
desc->sg_req[i].chan_reg.dma_sm1ar = buf_addr;
+ if (chan->trig_mdma)
+ desc->sg_req[i].chan_reg.dma_sm1ar += period_len;
desc->sg_req[i].chan_reg.dma_sndtr = nb_data_items;
- buf_addr += period_len;
+ if (!chan->trig_mdma)
+ buf_addr += period_len;
}
desc->num_sgs = num_periods;
@@ -1247,16 +1271,15 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
desc->sg_req[i].chan_reg.dma_scr =
- STM32_DMA_SCR_DIR(STM32_DMA_MEM_TO_MEM) |
- STM32_DMA_SCR_PBURST(dma_burst) |
- STM32_DMA_SCR_MBURST(dma_burst) |
+ FIELD_PREP(STM32_DMA_SCR_DIR_MASK, STM32_DMA_MEM_TO_MEM) |
+ FIELD_PREP(STM32_DMA_SCR_PBURST_MASK, dma_burst) |
+ FIELD_PREP(STM32_DMA_SCR_MBURST_MASK, dma_burst) |
STM32_DMA_SCR_MINC |
STM32_DMA_SCR_PINC |
STM32_DMA_SCR_TCIE |
STM32_DMA_SCR_TEIE;
desc->sg_req[i].chan_reg.dma_sfcr |= STM32_DMA_SFCR_MASK;
- desc->sg_req[i].chan_reg.dma_sfcr |=
- STM32_DMA_SFCR_FTH(threshold);
+ desc->sg_req[i].chan_reg.dma_sfcr |= FIELD_PREP(STM32_DMA_SFCR_FTH_MASK, threshold);
desc->sg_req[i].chan_reg.dma_spar = src + offset;
desc->sg_req[i].chan_reg.dma_sm0ar = dest + offset;
desc->sg_req[i].chan_reg.dma_sndtr = xfer_count;
@@ -1275,7 +1298,7 @@ static u32 stm32_dma_get_remaining_bytes(struct stm32_dma_chan *chan)
struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
- width = STM32_DMA_SCR_PSIZE_GET(dma_scr);
+ width = FIELD_GET(STM32_DMA_SCR_PSIZE_MASK, dma_scr);
ndtr = stm32_dma_read(dmadev, STM32_DMA_SNDTR(chan->id));
return ndtr << width;
@@ -1481,16 +1504,17 @@ static void stm32_dma_set_config(struct stm32_dma_chan *chan,
stm32_dma_clear_reg(&chan->chan_reg);
chan->chan_reg.dma_scr = cfg->stream_config & STM32_DMA_SCR_CFG_MASK;
- chan->chan_reg.dma_scr |= STM32_DMA_SCR_REQ(cfg->request_line);
+ chan->chan_reg.dma_scr |= FIELD_PREP(STM32_DMA_SCR_REQ_MASK, cfg->request_line);
/* Enable Interrupts */
chan->chan_reg.dma_scr |= STM32_DMA_SCR_TEIE | STM32_DMA_SCR_TCIE;
- chan->threshold = STM32_DMA_THRESHOLD_FTR_GET(cfg->features);
- if (STM32_DMA_DIRECT_MODE_GET(cfg->features))
+ chan->threshold = FIELD_GET(STM32_DMA_THRESHOLD_FTR_MASK, cfg->features);
+ if (FIELD_GET(STM32_DMA_DIRECT_MODE_MASK, cfg->features))
chan->threshold = STM32_DMA_FIFO_THRESHOLD_NONE;
- if (STM32_DMA_ALT_ACK_MODE_GET(cfg->features))
+ if (FIELD_GET(STM32_DMA_ALT_ACK_MODE_MASK, cfg->features))
chan->chan_reg.dma_scr |= STM32_DMA_SCR_TRBUFF;
+ chan->mdma_config.stream_id = FIELD_GET(STM32_DMA_MDMA_STREAM_ID_MASK, cfg->features);
}
static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec,
@@ -1630,6 +1654,12 @@ static int stm32_dma_probe(struct platform_device *pdev)
chan->id = i;
chan->vchan.desc_free = stm32_dma_desc_free;
vchan_init(&chan->vchan, dd);
+
+ chan->mdma_config.ifcr = res->start;
+ chan->mdma_config.ifcr += STM32_DMA_IFCR(chan->id);
+
+ chan->mdma_config.tcf = STM32_DMA_TCI;
+ chan->mdma_config.tcf <<= STM32_DMA_FLAGS_SHIFT(chan->id);
}
ret = dma_async_device_register(dd);
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index eee0c5aa5fb5..ee3cbbf51006 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -39,13 +39,13 @@ struct stm32_dmamux_data {
u32 dma_requests; /* Number of DMA requests connected to DMAMUX */
u32 dmamux_requests; /* Number of DMA requests routed toward DMAs */
spinlock_t lock; /* Protects register access */
- unsigned long *dma_inuse; /* Used DMA channel */
+ DECLARE_BITMAP(dma_inuse, STM32_DMAMUX_MAX_DMA_REQUESTS); /* Used DMA channel */
u32 ccr[STM32_DMAMUX_MAX_DMA_REQUESTS]; /* Used to backup CCR register
* in suspend
*/
u32 dma_reqs[]; /* Number of DMA Request per DMA masters.
* [0] holds number of DMA Masters.
- * To be kept at very end end of this structure
+ * To be kept at very end of this structure
*/
};
@@ -147,7 +147,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec,
mux->request = dma_spec->args[0];
/* craft DMA spec */
- dma_spec->args[3] = dma_spec->args[2];
+ dma_spec->args[3] = dma_spec->args[2] | mux->chan_id << 16;
dma_spec->args[2] = dma_spec->args[1];
dma_spec->args[1] = 0;
dma_spec->args[0] = mux->chan_id - min;
@@ -229,12 +229,6 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
stm32_dmamux->dma_requests = dma_req;
stm32_dmamux->dma_reqs[0] = count;
- stm32_dmamux->dma_inuse = devm_kcalloc(&pdev->dev,
- BITS_TO_LONGS(dma_req),
- sizeof(unsigned long),
- GFP_KERNEL);
- if (!stm32_dmamux->dma_inuse)
- return -ENOMEM;
if (device_property_read_u32(&pdev->dev, "dma-requests",
&stm32_dmamux->dmamux_requests)) {
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index b11927ed4367..e28acbcb53f4 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -199,6 +199,7 @@ struct stm32_mdma_chan_config {
u32 transfer_config;
u32 mask_addr;
u32 mask_data;
+ bool m2m_hw; /* True when MDMA is triggered by STM32 DMA */
};
struct stm32_mdma_hwdesc {
@@ -227,6 +228,12 @@ struct stm32_mdma_desc {
struct stm32_mdma_desc_node node[];
};
+struct stm32_mdma_dma_config {
+ u32 request; /* STM32 DMA channel stream id, triggering MDMA */
+ u32 cmar; /* STM32 DMA interrupt flag clear register address */
+ u32 cmdr; /* STM32 DMA Transfer Complete flag */
+};
+
struct stm32_mdma_chan {
struct virt_dma_chan vchan;
struct dma_pool *desc_pool;
@@ -539,13 +546,23 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan,
dst_addr = chan->dma_config.dst_addr;
/* Set device data size */
+ if (chan_config->m2m_hw)
+ dst_addr_width = stm32_mdma_get_max_width(dst_addr, buf_len,
+ STM32_MDMA_MAX_BUF_LEN);
dst_bus_width = stm32_mdma_get_width(chan, dst_addr_width);
if (dst_bus_width < 0)
return dst_bus_width;
ctcr &= ~STM32_MDMA_CTCR_DSIZE_MASK;
ctcr |= STM32_MDMA_CTCR_DSIZE(dst_bus_width);
+ if (chan_config->m2m_hw) {
+ ctcr &= ~STM32_MDMA_CTCR_DINCOS_MASK;
+ ctcr |= STM32_MDMA_CTCR_DINCOS(dst_bus_width);
+ }
/* Set device burst value */
+ if (chan_config->m2m_hw)
+ dst_maxburst = STM32_MDMA_MAX_BUF_LEN / dst_addr_width;
+
dst_best_burst = stm32_mdma_get_best_burst(buf_len, tlen,
dst_maxburst,
dst_addr_width);
@@ -588,13 +605,24 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan,
src_addr = chan->dma_config.src_addr;
/* Set device data size */
+ if (chan_config->m2m_hw)
+ src_addr_width = stm32_mdma_get_max_width(src_addr, buf_len,
+ STM32_MDMA_MAX_BUF_LEN);
+
src_bus_width = stm32_mdma_get_width(chan, src_addr_width);
if (src_bus_width < 0)
return src_bus_width;
ctcr &= ~STM32_MDMA_CTCR_SSIZE_MASK;
ctcr |= STM32_MDMA_CTCR_SSIZE(src_bus_width);
+ if (chan_config->m2m_hw) {
+ ctcr &= ~STM32_MDMA_CTCR_SINCOS_MASK;
+ ctcr |= STM32_MDMA_CTCR_SINCOS(src_bus_width);
+ }
/* Set device burst value */
+ if (chan_config->m2m_hw)
+ src_maxburst = STM32_MDMA_MAX_BUF_LEN / src_addr_width;
+
src_best_burst = stm32_mdma_get_best_burst(buf_len, tlen,
src_maxburst,
src_addr_width);
@@ -702,11 +730,15 @@ static int stm32_mdma_setup_xfer(struct stm32_mdma_chan *chan,
{
struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
struct dma_slave_config *dma_config = &chan->dma_config;
+ struct stm32_mdma_chan_config *chan_config = &chan->chan_config;
struct scatterlist *sg;
dma_addr_t src_addr, dst_addr;
- u32 ccr, ctcr, ctbr;
+ u32 m2m_hw_period, ccr, ctcr, ctbr;
int i, ret = 0;
+ if (chan_config->m2m_hw)
+ m2m_hw_period = sg_dma_len(sgl);
+
for_each_sg(sgl, sg, sg_len, i) {
if (sg_dma_len(sg) > STM32_MDMA_MAX_BLOCK_LEN) {
dev_err(chan2dev(chan), "Invalid block len\n");
@@ -716,6 +748,8 @@ static int stm32_mdma_setup_xfer(struct stm32_mdma_chan *chan,
if (direction == DMA_MEM_TO_DEV) {
src_addr = sg_dma_address(sg);
dst_addr = dma_config->dst_addr;
+ if (chan_config->m2m_hw && (i & 1))
+ dst_addr += m2m_hw_period;
ret = stm32_mdma_set_xfer_param(chan, direction, &ccr,
&ctcr, &ctbr, src_addr,
sg_dma_len(sg));
@@ -723,6 +757,8 @@ static int stm32_mdma_setup_xfer(struct stm32_mdma_chan *chan,
src_addr);
} else {
src_addr = dma_config->src_addr;
+ if (chan_config->m2m_hw && (i & 1))
+ src_addr += m2m_hw_period;
dst_addr = sg_dma_address(sg);
ret = stm32_mdma_set_xfer_param(chan, direction, &ccr,
&ctcr, &ctbr, dst_addr,
@@ -755,6 +791,7 @@ stm32_mdma_prep_slave_sg(struct dma_chan *c, struct scatterlist *sgl,
unsigned long flags, void *context)
{
struct stm32_mdma_chan *chan = to_stm32_mdma_chan(c);
+ struct stm32_mdma_chan_config *chan_config = &chan->chan_config;
struct stm32_mdma_desc *desc;
int i, ret;
@@ -777,6 +814,21 @@ stm32_mdma_prep_slave_sg(struct dma_chan *c, struct scatterlist *sgl,
if (ret < 0)
goto xfer_setup_err;
+ /*
+ * In case of M2M HW transfer triggered by STM32 DMA, we do not have to clear the
+ * transfer complete flag by hardware in order to let the CPU rearm the STM32 DMA
+ * with the next sg element and update some data in dmaengine framework.
+ */
+ if (chan_config->m2m_hw && direction == DMA_MEM_TO_DEV) {
+ struct stm32_mdma_hwdesc *hwdesc;
+
+ for (i = 0; i < sg_len; i++) {
+ hwdesc = desc->node[i].hwdesc;
+ hwdesc->cmar = 0;
+ hwdesc->cmdr = 0;
+ }
+ }
+
desc->cyclic = false;
return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
@@ -798,6 +850,7 @@ stm32_mdma_prep_dma_cyclic(struct dma_chan *c, dma_addr_t buf_addr,
struct stm32_mdma_chan *chan = to_stm32_mdma_chan(c);
struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
struct dma_slave_config *dma_config = &chan->dma_config;
+ struct stm32_mdma_chan_config *chan_config = &chan->chan_config;
struct stm32_mdma_desc *desc;
dma_addr_t src_addr, dst_addr;
u32 ccr, ctcr, ctbr, count;
@@ -858,8 +911,12 @@ stm32_mdma_prep_dma_cyclic(struct dma_chan *c, dma_addr_t buf_addr,
if (direction == DMA_MEM_TO_DEV) {
src_addr = buf_addr + i * period_len;
dst_addr = dma_config->dst_addr;
+ if (chan_config->m2m_hw && (i & 1))
+ dst_addr += period_len;
} else {
src_addr = dma_config->src_addr;
+ if (chan_config->m2m_hw && (i & 1))
+ src_addr += period_len;
dst_addr = buf_addr + i * period_len;
}
@@ -1244,6 +1301,17 @@ static int stm32_mdma_slave_config(struct dma_chan *c,
memcpy(&chan->dma_config, config, sizeof(*config));
+ /* Check if user is requesting STM32 DMA to trigger MDMA */
+ if (config->peripheral_size) {
+ struct stm32_mdma_dma_config *mdma_config;
+
+ mdma_config = (struct stm32_mdma_dma_config *)chan->dma_config.peripheral_config;
+ chan->chan_config.request = mdma_config->request;
+ chan->chan_config.mask_addr = mdma_config->cmar;
+ chan->chan_config.mask_data = mdma_config->cmdr;
+ chan->chan_config.m2m_hw = true;
+ }
+
return 0;
}
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 4cbca80ee16e..fa06d7e6d8e3 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -352,12 +352,6 @@ static inline void edma_modify_array(struct edma_cc *ecc, int offset, int i,
edma_modify(ecc, offset + (i << 2), and, or);
}
-static inline void edma_or_array(struct edma_cc *ecc, int offset, int i,
- unsigned or)
-{
- edma_or(ecc, offset + (i << 2), or);
-}
-
static inline void edma_or_array2(struct edma_cc *ecc, int offset, int i, int j,
unsigned or)
{
@@ -370,11 +364,6 @@ static inline void edma_write_array2(struct edma_cc *ecc, int offset, int i,
edma_write(ecc, offset + ((i * 2 + j) << 2), val);
}
-static inline unsigned int edma_shadow0_read(struct edma_cc *ecc, int offset)
-{
- return edma_read(ecc, EDMA_SHADOW0 + offset);
-}
-
static inline unsigned int edma_shadow0_read_array(struct edma_cc *ecc,
int offset, int i)
{
@@ -393,36 +382,12 @@ static inline void edma_shadow0_write_array(struct edma_cc *ecc, int offset,
edma_write(ecc, EDMA_SHADOW0 + offset + (i << 2), val);
}
-static inline unsigned int edma_param_read(struct edma_cc *ecc, int offset,
- int param_no)
-{
- return edma_read(ecc, EDMA_PARM + offset + (param_no << 5));
-}
-
-static inline void edma_param_write(struct edma_cc *ecc, int offset,
- int param_no, unsigned val)
-{
- edma_write(ecc, EDMA_PARM + offset + (param_no << 5), val);
-}
-
static inline void edma_param_modify(struct edma_cc *ecc, int offset,
int param_no, unsigned and, unsigned or)
{
edma_modify(ecc, EDMA_PARM + offset + (param_no << 5), and, or);
}
-static inline void edma_param_and(struct edma_cc *ecc, int offset, int param_no,
- unsigned and)
-{
- edma_and(ecc, EDMA_PARM + offset + (param_no << 5), and);
-}
-
-static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
- unsigned or)
-{
- edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
-}
-
static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
int priority)
{
@@ -743,11 +708,6 @@ static void edma_free_channel(struct edma_chan *echan)
edma_setup_interrupt(echan, false);
}
-static inline struct edma_cc *to_edma_cc(struct dma_device *d)
-{
- return container_of(d, struct edma_cc, dma_slave);
-}
-
static inline struct edma_chan *to_edma_chan(struct dma_chan *c)
{
return container_of(c, struct edma_chan, vchan.chan);
diff --git a/drivers/dma/ti/k3-psil-j7200.c b/drivers/dma/ti/k3-psil-j7200.c
index 5ea63ea74822..e3feff869991 100644
--- a/drivers/dma/ti/k3-psil-j7200.c
+++ b/drivers/dma/ti/k3-psil-j7200.c
@@ -143,6 +143,57 @@ static struct psil_ep j7200_src_ep_map[] = {
/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
static struct psil_ep j7200_dst_ep_map[] = {
+ /* PDMA_MCASP - McASP0-2 */
+ PSIL_PDMA_MCASP(0xc400),
+ PSIL_PDMA_MCASP(0xc401),
+ PSIL_PDMA_MCASP(0xc402),
+ /* PDMA_SPI_G0 - SPI0-3 */
+ PSIL_PDMA_XY_PKT(0xc600),
+ PSIL_PDMA_XY_PKT(0xc601),
+ PSIL_PDMA_XY_PKT(0xc602),
+ PSIL_PDMA_XY_PKT(0xc603),
+ PSIL_PDMA_XY_PKT(0xc604),
+ PSIL_PDMA_XY_PKT(0xc605),
+ PSIL_PDMA_XY_PKT(0xc606),
+ PSIL_PDMA_XY_PKT(0xc607),
+ PSIL_PDMA_XY_PKT(0xc608),
+ PSIL_PDMA_XY_PKT(0xc609),
+ PSIL_PDMA_XY_PKT(0xc60a),
+ PSIL_PDMA_XY_PKT(0xc60b),
+ PSIL_PDMA_XY_PKT(0xc60c),
+ PSIL_PDMA_XY_PKT(0xc60d),
+ PSIL_PDMA_XY_PKT(0xc60e),
+ PSIL_PDMA_XY_PKT(0xc60f),
+ /* PDMA_SPI_G1 - SPI4-7 */
+ PSIL_PDMA_XY_PKT(0xc610),
+ PSIL_PDMA_XY_PKT(0xc611),
+ PSIL_PDMA_XY_PKT(0xc612),
+ PSIL_PDMA_XY_PKT(0xc613),
+ PSIL_PDMA_XY_PKT(0xc614),
+ PSIL_PDMA_XY_PKT(0xc615),
+ PSIL_PDMA_XY_PKT(0xc616),
+ PSIL_PDMA_XY_PKT(0xc617),
+ PSIL_PDMA_XY_PKT(0xc618),
+ PSIL_PDMA_XY_PKT(0xc619),
+ PSIL_PDMA_XY_PKT(0xc61a),
+ PSIL_PDMA_XY_PKT(0xc61b),
+ PSIL_PDMA_XY_PKT(0xc61c),
+ PSIL_PDMA_XY_PKT(0xc61d),
+ PSIL_PDMA_XY_PKT(0xc61e),
+ PSIL_PDMA_XY_PKT(0xc61f),
+ /* PDMA_USART_G0 - UART0-1 */
+ PSIL_PDMA_XY_PKT(0xc700),
+ PSIL_PDMA_XY_PKT(0xc701),
+ /* PDMA_USART_G1 - UART2-3 */
+ PSIL_PDMA_XY_PKT(0xc702),
+ PSIL_PDMA_XY_PKT(0xc703),
+ /* PDMA_USART_G2 - UART4-9 */
+ PSIL_PDMA_XY_PKT(0xc704),
+ PSIL_PDMA_XY_PKT(0xc705),
+ PSIL_PDMA_XY_PKT(0xc706),
+ PSIL_PDMA_XY_PKT(0xc707),
+ PSIL_PDMA_XY_PKT(0xc708),
+ PSIL_PDMA_XY_PKT(0xc709),
/* CPSW5 */
PSIL_ETHERNET(0xca00),
PSIL_ETHERNET(0xca01),
@@ -161,6 +212,22 @@ static struct psil_ep j7200_dst_ep_map[] = {
PSIL_ETHERNET(0xf005),
PSIL_ETHERNET(0xf006),
PSIL_ETHERNET(0xf007),
+ /* MCU_PDMA_MISC_G0 - SPI0 */
+ PSIL_PDMA_XY_PKT(0xf100),
+ PSIL_PDMA_XY_PKT(0xf101),
+ PSIL_PDMA_XY_PKT(0xf102),
+ PSIL_PDMA_XY_PKT(0xf103),
+ /* MCU_PDMA_MISC_G1 - SPI1-2 */
+ PSIL_PDMA_XY_PKT(0xf200),
+ PSIL_PDMA_XY_PKT(0xf201),
+ PSIL_PDMA_XY_PKT(0xf202),
+ PSIL_PDMA_XY_PKT(0xf203),
+ PSIL_PDMA_XY_PKT(0xf204),
+ PSIL_PDMA_XY_PKT(0xf205),
+ PSIL_PDMA_XY_PKT(0xf206),
+ PSIL_PDMA_XY_PKT(0xf207),
+ /* MCU_PDMA_MISC_G2 - UART0 */
+ PSIL_PDMA_XY_PKT(0xf300),
/* SA2UL */
PSIL_SA2UL(0xf500, 1),
PSIL_SA2UL(0xf501, 1),
diff --git a/drivers/dma/ti/k3-psil-j721e.c b/drivers/dma/ti/k3-psil-j721e.c
index 34e3fc565a37..e7c83d668bb6 100644
--- a/drivers/dma/ti/k3-psil-j721e.c
+++ b/drivers/dma/ti/k3-psil-j721e.c
@@ -266,6 +266,69 @@ static struct psil_ep j721e_dst_ep_map[] = {
PSIL_ETHERNET(0xc205),
PSIL_ETHERNET(0xc206),
PSIL_ETHERNET(0xc207),
+ /* PDMA6 (PSIL_PDMA_MCASP_G0) - McASP0-2 */
+ PSIL_PDMA_MCASP(0xc400),
+ PSIL_PDMA_MCASP(0xc401),
+ PSIL_PDMA_MCASP(0xc402),
+ /* PDMA7 (PSIL_PDMA_MCASP_G1) - McASP3-11 */
+ PSIL_PDMA_MCASP(0xc500),
+ PSIL_PDMA_MCASP(0xc501),
+ PSIL_PDMA_MCASP(0xc502),
+ PSIL_PDMA_MCASP(0xc503),
+ PSIL_PDMA_MCASP(0xc504),
+ PSIL_PDMA_MCASP(0xc505),
+ PSIL_PDMA_MCASP(0xc506),
+ PSIL_PDMA_MCASP(0xc507),
+ PSIL_PDMA_MCASP(0xc508),
+ /* PDMA8 (PDMA_MISC_G0) - SPI0-1 */
+ PSIL_PDMA_XY_PKT(0xc600),
+ PSIL_PDMA_XY_PKT(0xc601),
+ PSIL_PDMA_XY_PKT(0xc602),
+ PSIL_PDMA_XY_PKT(0xc603),
+ PSIL_PDMA_XY_PKT(0xc604),
+ PSIL_PDMA_XY_PKT(0xc605),
+ PSIL_PDMA_XY_PKT(0xc606),
+ PSIL_PDMA_XY_PKT(0xc607),
+ /* PDMA9 (PDMA_MISC_G1) - SPI2-3 */
+ PSIL_PDMA_XY_PKT(0xc60c),
+ PSIL_PDMA_XY_PKT(0xc60d),
+ PSIL_PDMA_XY_PKT(0xc60e),
+ PSIL_PDMA_XY_PKT(0xc60f),
+ PSIL_PDMA_XY_PKT(0xc610),
+ PSIL_PDMA_XY_PKT(0xc611),
+ PSIL_PDMA_XY_PKT(0xc612),
+ PSIL_PDMA_XY_PKT(0xc613),
+ /* PDMA10 (PDMA_MISC_G2) - SPI4-5 */
+ PSIL_PDMA_XY_PKT(0xc618),
+ PSIL_PDMA_XY_PKT(0xc619),
+ PSIL_PDMA_XY_PKT(0xc61a),
+ PSIL_PDMA_XY_PKT(0xc61b),
+ PSIL_PDMA_XY_PKT(0xc61c),
+ PSIL_PDMA_XY_PKT(0xc61d),
+ PSIL_PDMA_XY_PKT(0xc61e),
+ PSIL_PDMA_XY_PKT(0xc61f),
+ /* PDMA11 (PDMA_MISC_G3) */
+ PSIL_PDMA_XY_PKT(0xc624),
+ PSIL_PDMA_XY_PKT(0xc625),
+ PSIL_PDMA_XY_PKT(0xc626),
+ PSIL_PDMA_XY_PKT(0xc627),
+ PSIL_PDMA_XY_PKT(0xc628),
+ PSIL_PDMA_XY_PKT(0xc629),
+ PSIL_PDMA_XY_PKT(0xc630),
+ PSIL_PDMA_XY_PKT(0xc63a),
+ /* PDMA13 (PDMA_USART_G0) - UART0-1 */
+ PSIL_PDMA_XY_PKT(0xc700),
+ PSIL_PDMA_XY_PKT(0xc701),
+ /* PDMA14 (PDMA_USART_G1) - UART2-3 */
+ PSIL_PDMA_XY_PKT(0xc702),
+ PSIL_PDMA_XY_PKT(0xc703),
+ /* PDMA15 (PDMA_USART_G2) - UART4-9 */
+ PSIL_PDMA_XY_PKT(0xc704),
+ PSIL_PDMA_XY_PKT(0xc705),
+ PSIL_PDMA_XY_PKT(0xc706),
+ PSIL_PDMA_XY_PKT(0xc707),
+ PSIL_PDMA_XY_PKT(0xc708),
+ PSIL_PDMA_XY_PKT(0xc709),
/* CPSW9 */
PSIL_ETHERNET(0xca00),
PSIL_ETHERNET(0xca01),
@@ -284,6 +347,22 @@ static struct psil_ep j721e_dst_ep_map[] = {
PSIL_ETHERNET(0xf005),
PSIL_ETHERNET(0xf006),
PSIL_ETHERNET(0xf007),
+ /* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */
+ PSIL_PDMA_XY_PKT(0xf100),
+ PSIL_PDMA_XY_PKT(0xf101),
+ PSIL_PDMA_XY_PKT(0xf102),
+ PSIL_PDMA_XY_PKT(0xf103),
+ /* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */
+ PSIL_PDMA_XY_PKT(0xf200),
+ PSIL_PDMA_XY_PKT(0xf201),
+ PSIL_PDMA_XY_PKT(0xf202),
+ PSIL_PDMA_XY_PKT(0xf203),
+ PSIL_PDMA_XY_PKT(0xf204),
+ PSIL_PDMA_XY_PKT(0xf205),
+ PSIL_PDMA_XY_PKT(0xf206),
+ PSIL_PDMA_XY_PKT(0xf207),
+ /* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */
+ PSIL_PDMA_XY_PKT(0xf300),
/* SA2UL */
PSIL_SA2UL(0xf500, 1),
PSIL_SA2UL(0xf501, 1),
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 2f0d2c68c93c..7b5081989b3d 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -263,6 +263,7 @@ struct udma_chan_config {
enum udma_tp_level channel_tpl; /* Channel Throughput Level */
u32 tr_trigger_type;
+ unsigned long tx_flags;
/* PKDMA mapped channel */
int mapped_channel_id;
@@ -300,8 +301,6 @@ struct udma_chan {
struct udma_tx_drain tx_drain;
- u32 bcnt; /* number of bytes completed since the start of the channel */
-
/* Channel configuration parameters */
struct udma_chan_config config;
@@ -757,6 +756,20 @@ static void udma_reset_rings(struct udma_chan *uc)
}
}
+static void udma_decrement_byte_counters(struct udma_chan *uc, u32 val)
+{
+ if (uc->desc->dir == DMA_DEV_TO_MEM) {
+ udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+ udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+ udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+ } else {
+ udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+ udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+ if (!uc->bchan)
+ udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+ }
+}
+
static void udma_reset_counters(struct udma_chan *uc)
{
u32 val;
@@ -790,8 +803,6 @@ static void udma_reset_counters(struct udma_chan *uc)
val = udma_rchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
}
-
- uc->bcnt = 0;
}
static int udma_reset_chan(struct udma_chan *uc, bool hard)
@@ -1045,9 +1056,14 @@ static bool udma_is_desc_really_done(struct udma_chan *uc, struct udma_desc *d)
{
u32 peer_bcnt, bcnt;
- /* Only TX towards PDMA is affected */
+ /*
+ * Only TX towards PDMA is affected.
+ * If DMA_PREP_INTERRUPT is not set by consumer then skip the transfer
+ * completion calculation, consumer must ensure that there is no stale
+ * data in DMA fabric in this case.
+ */
if (uc->config.ep_type == PSIL_EP_NATIVE ||
- uc->config.dir != DMA_MEM_TO_DEV)
+ uc->config.dir != DMA_MEM_TO_DEV || !(uc->config.tx_flags & DMA_PREP_INTERRUPT))
return true;
peer_bcnt = udma_tchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
@@ -1115,7 +1131,7 @@ static void udma_check_tx_completion(struct work_struct *work)
if (uc->desc) {
struct udma_desc *d = uc->desc;
- uc->bcnt += d->residue;
+ udma_decrement_byte_counters(uc, d->residue);
udma_start(uc);
vchan_cookie_complete(&d->vd);
break;
@@ -1168,7 +1184,7 @@ static irqreturn_t udma_ring_irq_handler(int irq, void *data)
vchan_cyclic_callback(&d->vd);
} else {
if (udma_is_desc_really_done(uc, d)) {
- uc->bcnt += d->residue;
+ udma_decrement_byte_counters(uc, d->residue);
udma_start(uc);
vchan_cookie_complete(&d->vd);
} else {
@@ -1204,7 +1220,7 @@ static irqreturn_t udma_udma_irq_handler(int irq, void *data)
vchan_cyclic_callback(&d->vd);
} else {
/* TODO: figure out the real amount of data */
- uc->bcnt += d->residue;
+ udma_decrement_byte_counters(uc, d->residue);
udma_start(uc);
vchan_cookie_complete(&d->vd);
}
@@ -3408,6 +3424,8 @@ udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
if (!burst)
burst = 1;
+ uc->config.tx_flags = tx_flags;
+
if (uc->config.pkt_mode)
d = udma_prep_slave_sg_pkt(uc, sgl, sglen, dir, tx_flags,
context);
@@ -3809,7 +3827,6 @@ static enum dma_status udma_tx_status(struct dma_chan *chan,
bcnt = udma_tchanrt_read(uc, UDMA_CHAN_RT_BCNT_REG);
}
- bcnt -= uc->bcnt;
if (bcnt && !(bcnt % uc->desc->residue))
residue = 0;
else
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 3f4ee3954384..21472a5d7636 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -796,6 +796,17 @@ static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan)
}
/**
+ * zynqmp_dma_synchronize - Synchronizes the termination of a transfers to the current context.
+ * @dchan: DMA channel pointer
+ */
+static void zynqmp_dma_synchronize(struct dma_chan *dchan)
+{
+ struct zynqmp_dma_chan *chan = to_chan(dchan);
+
+ tasklet_kill(&chan->tasklet);
+}
+
+/**
* zynqmp_dma_prep_memcpy - prepare descriptors for memcpy transaction
* @dchan: DMA channel
* @dma_dst: Destination buffer address
@@ -1057,6 +1068,7 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
p = &zdev->common;
p->device_prep_dma_memcpy = zynqmp_dma_prep_memcpy;
p->device_terminate_all = zynqmp_dma_device_terminate_all;
+ p->device_synchronize = zynqmp_dma_synchronize;
p->device_issue_pending = zynqmp_dma_issue_pending;
p->device_alloc_chan_resources = zynqmp_dma_alloc_chan_resources;
p->device_free_chan_resources = zynqmp_dma_free_chan_resources;
diff --git a/include/linux/dma/hsu.h b/include/linux/dma/hsu.h
index a6b7bc707356..77ea602c287c 100644
--- a/include/linux/dma/hsu.h
+++ b/include/linux/dma/hsu.h
@@ -8,11 +8,13 @@
#ifndef _DMA_HSU_H
#define _DMA_HSU_H
-#include <linux/device.h>
-#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+#include <linux/types.h>
#include <linux/platform_data/dma-hsu.h>
+struct device;
struct hsu_dma;
/**
diff --git a/include/linux/platform_data/dma-hsu.h b/include/linux/platform_data/dma-hsu.h
index c65b412b2b33..611bae193c1c 100644
--- a/include/linux/platform_data/dma-hsu.h
+++ b/include/linux/platform_data/dma-hsu.h
@@ -8,7 +8,7 @@
#ifndef _PLATFORM_DATA_DMA_HSU_H
#define _PLATFORM_DATA_DMA_HSU_H
-#include <linux/device.h>
+struct device;
struct hsu_dma_slave {
struct device *dma_dev;