UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/dma/ti/k3-udma-glue.c

1437 lines
39 KiB
C
Raw Normal View History

dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* K3 NAVSS DMA glue interface
*
* Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
*
*/
#include <linux/atomic.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/io.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/soc/ti/k3-ringacc.h>
#include <linux/dma/ti-cppi5.h>
#include <linux/dma/k3-udma-glue.h>
#include "k3-udma.h"
#include "k3-psil-priv.h"
struct k3_udma_glue_common {
struct device *dev;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
struct device chan_dev;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
struct udma_dev *udmax;
const struct udma_tisci_rm *tisci_rm;
struct k3_ringacc *ringacc;
u32 src_thread;
u32 dst_thread;
u32 hdesc_size;
bool epib;
u32 psdata_size;
u32 swdata_size;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
u32 atype_asel;
struct psil_endpoint_config *ep_config;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
};
struct k3_udma_glue_tx_channel {
struct k3_udma_glue_common common;
struct udma_tchan *udma_tchanx;
int udma_tchan_id;
struct k3_ring *ringtx;
struct k3_ring *ringtxcq;
bool psil_paired;
int virq;
atomic_t free_pkts;
bool tx_pause_on_err;
bool tx_filt_einfo;
bool tx_filt_pswords;
bool tx_supr_tdpkt;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
int udma_tflow_id;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
};
struct k3_udma_glue_rx_flow {
struct udma_rflow *udma_rflow;
int udma_rflow_id;
struct k3_ring *ringrx;
struct k3_ring *ringrxfdq;
int virq;
};
struct k3_udma_glue_rx_channel {
struct k3_udma_glue_common common;
struct udma_rchan *udma_rchanx;
int udma_rchan_id;
bool remote;
bool psil_paired;
u32 swdata_size;
int flow_id_base;
struct k3_udma_glue_rx_flow *flows;
u32 flow_num;
u32 flows_ready;
};
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
static void k3_udma_chan_dev_release(struct device *dev)
{
/* The struct containing the device is devm managed */
}
static struct class k3_udma_glue_devclass = {
.name = "k3_udma_glue_chan",
.dev_release = k3_udma_chan_dev_release,
};
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
#define K3_UDMAX_TDOWN_TIMEOUT_US 1000
static int of_k3_udma_glue_parse(struct device_node *udmax_np,
struct k3_udma_glue_common *common)
{
common->udmax = of_xudma_dev_get(udmax_np, NULL);
if (IS_ERR(common->udmax))
return PTR_ERR(common->udmax);
dmaengine: ti: k3-udma-glue: Get the ringacc from udma_dev If of_xudma_dev_get() returns with the valid udma_dev then the driver already got the ringacc, there is no need to execute of_k3_ringacc_get_by_phandle() for each channel via the glue layer. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-6-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:25 +08:00
common->ringacc = xudma_get_ringacc(common->udmax);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
common->tisci_rm = xudma_dev_get_tisci_rm(common->udmax);
return 0;
}
static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
const char *name, struct k3_udma_glue_common *common,
bool tx_chn)
{
struct of_phandle_args dma_spec;
u32 thread_id;
int ret = 0;
int index;
if (unlikely(!name))
return -EINVAL;
index = of_property_match_string(chn_np, "dma-names", name);
if (index < 0)
return index;
if (of_parse_phandle_with_args(chn_np, "dmas", "#dma-cells", index,
&dma_spec))
return -ENOENT;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
ret = of_k3_udma_glue_parse(dma_spec.np, common);
if (ret)
goto out_put_spec;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
thread_id = dma_spec.args[0];
dmaengine: ti: k3-udma: Implement support for atype (for virtualization) The DT for virtualized hosts have dma-cells == 2 where the second parameter is the ATYPE for the channel. In case of dma-cells == 1 we can configure the ATYPE as 0 (reset value). The ATYPE defined for j721e are: 0: pointers are physical addresses (no translation) 1: pointers are intermediate addresses (PVU) 2: pointers are virtual addresses (SMMU) Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200218143126.11361-3-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-18 22:31:26 +08:00
if (dma_spec.args_count == 2) {
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (dma_spec.args[1] > 2 && !xudma_is_pktdma(common->udmax)) {
dmaengine: ti: k3-udma: Implement support for atype (for virtualization) The DT for virtualized hosts have dma-cells == 2 where the second parameter is the ATYPE for the channel. In case of dma-cells == 1 we can configure the ATYPE as 0 (reset value). The ATYPE defined for j721e are: 0: pointers are physical addresses (no translation) 1: pointers are intermediate addresses (PVU) 2: pointers are virtual addresses (SMMU) Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200218143126.11361-3-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-18 22:31:26 +08:00
dev_err(common->dev, "Invalid channel atype: %u\n",
dma_spec.args[1]);
ret = -EINVAL;
goto out_put_spec;
}
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (dma_spec.args[1] > 15 && xudma_is_pktdma(common->udmax)) {
dev_err(common->dev, "Invalid channel asel: %u\n",
dma_spec.args[1]);
ret = -EINVAL;
goto out_put_spec;
}
common->atype_asel = dma_spec.args[1];
dmaengine: ti: k3-udma: Implement support for atype (for virtualization) The DT for virtualized hosts have dma-cells == 2 where the second parameter is the ATYPE for the channel. In case of dma-cells == 1 we can configure the ATYPE as 0 (reset value). The ATYPE defined for j721e are: 0: pointers are physical addresses (no translation) 1: pointers are intermediate addresses (PVU) 2: pointers are virtual addresses (SMMU) Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200218143126.11361-3-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-18 22:31:26 +08:00
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
ret = -EINVAL;
goto out_put_spec;
}
if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
ret = -EINVAL;
goto out_put_spec;
}
/* get psil endpoint config */
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
common->ep_config = psil_get_ep_config(thread_id);
if (IS_ERR(common->ep_config)) {
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
dev_err(common->dev,
"No configuration for psi-l thread 0x%04x\n",
thread_id);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
ret = PTR_ERR(common->ep_config);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
goto out_put_spec;
}
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
common->epib = common->ep_config->needs_epib;
common->psdata_size = common->ep_config->psd_size;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (tx_chn)
common->dst_thread = thread_id;
else
common->src_thread = thread_id;
out_put_spec:
of_node_put(dma_spec.np);
return ret;
};
static void k3_udma_glue_dump_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
{
struct device *dev = tx_chn->common.dev;
dev_dbg(dev, "dump_tx_chn:\n"
"udma_tchan_id: %d\n"
"src_thread: %08x\n"
"dst_thread: %08x\n",
tx_chn->udma_tchan_id,
tx_chn->common.src_thread,
tx_chn->common.dst_thread);
}
static void k3_udma_glue_dump_tx_rt_chn(struct k3_udma_glue_tx_channel *chn,
char *mark)
{
struct device *dev = chn->common.dev;
dev_dbg(dev, "=== dump ===> %s\n", mark);
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_CTL_REG,
xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PEER_RT_EN_REG,
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
xudma_tchanrt_read(chn->udma_tchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PCNT_REG,
xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_PCNT_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_BCNT_REG,
xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_BCNT_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_SBCNT_REG,
xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_SBCNT_REG));
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
{
const struct udma_tisci_rm *tisci_rm = tx_chn->common.tisci_rm;
struct ti_sci_msg_rm_udmap_tx_ch_cfg req;
memset(&req, 0, sizeof(req));
req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |
dmaengine: ti: k3-udma: Implement support for atype (for virtualization) The DT for virtualized hosts have dma-cells == 2 where the second parameter is the ATYPE for the channel. In case of dma-cells == 1 we can configure the ATYPE as 0 (reset value). The ATYPE defined for j721e are: 0: pointers are physical addresses (no translation) 1: pointers are intermediate addresses (PVU) 2: pointers are virtual addresses (SMMU) Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200218143126.11361-3-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-18 22:31:26 +08:00
TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
req.nav_id = tisci_rm->tisci_dev_id;
req.index = tx_chn->udma_tchan_id;
if (tx_chn->tx_pause_on_err)
req.tx_pause_on_err = 1;
if (tx_chn->tx_filt_einfo)
req.tx_filt_einfo = 1;
if (tx_chn->tx_filt_pswords)
req.tx_filt_pswords = 1;
req.tx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
if (tx_chn->tx_supr_tdpkt)
req.tx_supr_tdpkt = 1;
req.tx_fetch_size = tx_chn->common.hdesc_size >> 2;
req.txcq_qnum = k3_ringacc_get_ring_id(tx_chn->ringtxcq);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
req.tx_atype = tx_chn->common.atype_asel;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
}
struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
const char *name, struct k3_udma_glue_tx_channel_cfg *cfg)
{
struct k3_udma_glue_tx_channel *tx_chn;
int ret;
tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
if (!tx_chn)
return ERR_PTR(-ENOMEM);
tx_chn->common.dev = dev;
tx_chn->common.swdata_size = cfg->swdata_size;
tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
/* parse of udmap channel */
ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
&tx_chn->common, true);
if (ret)
goto err;
tx_chn->common.hdesc_size = cppi5_hdesc_calc_size(tx_chn->common.epib,
tx_chn->common.psdata_size,
tx_chn->common.swdata_size);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(tx_chn->common.udmax))
tx_chn->udma_tchan_id = tx_chn->common.ep_config->mapped_channel_id;
else
tx_chn->udma_tchan_id = -1;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/* request and cfg UDMAP TX channel */
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax,
tx_chn->udma_tchan_id);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (IS_ERR(tx_chn->udma_tchanx)) {
ret = PTR_ERR(tx_chn->udma_tchanx);
dev_err(dev, "UDMAX tchanx get err %d\n", ret);
goto err;
}
tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
tx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
tx_chn->common.chan_dev.parent = xudma_get_device(tx_chn->common.udmax);
dev_set_name(&tx_chn->common.chan_dev, "tchan%d-0x%04x",
tx_chn->udma_tchan_id, tx_chn->common.dst_thread);
ret = device_register(&tx_chn->common.chan_dev);
if (ret) {
dev_err(dev, "Channel Device registration failed %d\n", ret);
tx_chn->common.chan_dev.parent = NULL;
goto err;
}
if (xudma_is_pktdma(tx_chn->common.udmax)) {
/* prepare the channel device as coherent */
tx_chn->common.chan_dev.dma_coherent = true;
dma_coerce_mask_and_coherent(&tx_chn->common.chan_dev,
DMA_BIT_MASK(48));
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
atomic_set(&tx_chn->free_pkts, cfg->txcq_cfg.size);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(tx_chn->common.udmax))
tx_chn->udma_tflow_id = tx_chn->common.ep_config->default_flow_id;
else
tx_chn->udma_tflow_id = tx_chn->udma_tchan_id;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/* request and cfg rings */
dmaengine: ti: k3-udma: Switch to k3_ringacc_request_rings_pair We only request ring pairs via K3 DMA driver, switch to use the new k3_ringacc_request_rings_pair() to simplify the code. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Vinod Koul <vkoul@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
2020-07-25 05:20:24 +08:00
ret = k3_ringacc_request_rings_pair(tx_chn->common.ringacc,
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
tx_chn->udma_tflow_id, -1,
dmaengine: ti: k3-udma: Switch to k3_ringacc_request_rings_pair We only request ring pairs via K3 DMA driver, switch to use the new k3_ringacc_request_rings_pair() to simplify the code. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Vinod Koul <vkoul@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
2020-07-25 05:20:24 +08:00
&tx_chn->ringtx,
&tx_chn->ringtxcq);
if (ret) {
dev_err(dev, "Failed to get TX/TXCQ rings %d\n", ret);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
goto err;
}
dmaengine: ti: k3-udma-glue: Configure the dma_dev for rings Rings in RING mode should be using the DMA device for DMA API as in this mode the ringacc will not access the ring memory in any ways, but the DMA is. Fix up the ring configuration and set the dma_dev unconditionally and let the ringacc driver to select the correct device to use for DMA API. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-7-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:26 +08:00
/* Set the dma_dev for the rings to be configured */
cfg->tx_cfg.dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn);
cfg->txcq_cfg.dma_dev = cfg->tx_cfg.dma_dev;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
/* Set the ASEL value for DMA rings of PKTDMA */
if (xudma_is_pktdma(tx_chn->common.udmax)) {
cfg->tx_cfg.asel = tx_chn->common.atype_asel;
cfg->txcq_cfg.asel = tx_chn->common.atype_asel;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
if (ret) {
dev_err(dev, "Failed to cfg ringtx %d\n", ret);
goto err;
}
ret = k3_ringacc_ring_cfg(tx_chn->ringtxcq, &cfg->txcq_cfg);
if (ret) {
dev_err(dev, "Failed to cfg ringtx %d\n", ret);
goto err;
}
/* request and cfg psi-l */
tx_chn->common.src_thread =
xudma_dev_get_psil_base(tx_chn->common.udmax) +
tx_chn->udma_tchan_id;
ret = k3_udma_glue_cfg_tx_chn(tx_chn);
if (ret) {
dev_err(dev, "Failed to cfg tchan %d\n", ret);
goto err;
}
k3_udma_glue_dump_tx_chn(tx_chn);
return tx_chn;
err:
k3_udma_glue_release_tx_chn(tx_chn);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn);
void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
{
if (tx_chn->psil_paired) {
xudma_navss_psil_unpair(tx_chn->common.udmax,
tx_chn->common.src_thread,
tx_chn->common.dst_thread);
tx_chn->psil_paired = false;
}
if (!IS_ERR_OR_NULL(tx_chn->udma_tchanx))
xudma_tchan_put(tx_chn->common.udmax,
tx_chn->udma_tchanx);
if (tx_chn->ringtxcq)
k3_ringacc_ring_free(tx_chn->ringtxcq);
if (tx_chn->ringtx)
k3_ringacc_ring_free(tx_chn->ringtx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (tx_chn->common.chan_dev.parent) {
device_unregister(&tx_chn->common.chan_dev);
tx_chn->common.chan_dev.parent = NULL;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
EXPORT_SYMBOL_GPL(k3_udma_glue_release_tx_chn);
int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
struct cppi5_host_desc_t *desc_tx,
dma_addr_t desc_dma)
{
u32 ringtxcq_id;
if (!atomic_add_unless(&tx_chn->free_pkts, -1, 0))
return -ENOMEM;
ringtxcq_id = k3_ringacc_get_ring_id(tx_chn->ringtxcq);
cppi5_desc_set_retpolicy(&desc_tx->hdr, 0, ringtxcq_id);
return k3_ringacc_ring_push(tx_chn->ringtx, &desc_dma);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_push_tx_chn);
int k3_udma_glue_pop_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
dma_addr_t *desc_dma)
{
int ret;
ret = k3_ringacc_ring_pop(tx_chn->ringtxcq, desc_dma);
if (!ret)
atomic_inc(&tx_chn->free_pkts);
return ret;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_pop_tx_chn);
int k3_udma_glue_enable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
{
dmaengine: ti: k3-udma-glue: move psi-l pairing in channel en/dis functions The NAVSS UDMA will stuck if target IP module is disabled by PM while PSI-L threads are paired UDMA<->IP and no further transfers is possible. This could be the case for IPs J721E Main CPSW (cpsw9g). Hence, to avoid such situation do PSI-L threads pairing only when UDMA channel is going to be enabled as at this time DMA consumer module expected to be active already. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201030203000.4281-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-10-31 04:30:00 +08:00
int ret;
ret = xudma_navss_psil_pair(tx_chn->common.udmax,
tx_chn->common.src_thread,
tx_chn->common.dst_thread);
if (ret) {
dev_err(tx_chn->common.dev, "PSI-L request err %d\n", ret);
return ret;
}
tx_chn->psil_paired = true;
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_PEER_RT_EN_REG,
dmaengine: ti: k3-udma-glue: fix channel enable functions Now the K3 UDMA glue layer enable functions perform RMW operation on UDMA RX/TX RT_CTL registers to set EN bit and enable channel, which is incorrect, because only EN bit has to be set in those registers to enable channel (all other bits should be cleared 0). More over, this causes issues when bootloader leaves UDMA channel RX/TX RT_CTL registers in incorrect state - TDOWN bit set, for example. As result, UDMA channel will just perform teardown right after it's enabled. Hence, fix it by writing correct values (EN=1) directly in UDMA channel RX/TX RT_CTL registers in k3_udma_glue_enable_tx/rx_chn() functions. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine users") Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200916120955.7963-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-09-16 20:09:55 +08:00
UDMA_PEER_RT_EN_ENABLE);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG,
dmaengine: ti: k3-udma-glue: fix channel enable functions Now the K3 UDMA glue layer enable functions perform RMW operation on UDMA RX/TX RT_CTL registers to set EN bit and enable channel, which is incorrect, because only EN bit has to be set in those registers to enable channel (all other bits should be cleared 0). More over, this causes issues when bootloader leaves UDMA channel RX/TX RT_CTL registers in incorrect state - TDOWN bit set, for example. As result, UDMA channel will just perform teardown right after it's enabled. Hence, fix it by writing correct values (EN=1) directly in UDMA channel RX/TX RT_CTL registers in k3_udma_glue_enable_tx/rx_chn() functions. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine users") Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200916120955.7963-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-09-16 20:09:55 +08:00
UDMA_CHAN_RT_CTL_EN);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn en");
return 0;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_enable_tx_chn);
void k3_udma_glue_disable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
{
k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis1");
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG, 0);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
xudma_tchanrt_write(tx_chn->udma_tchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG, 0);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis2");
dmaengine: ti: k3-udma-glue: move psi-l pairing in channel en/dis functions The NAVSS UDMA will stuck if target IP module is disabled by PM while PSI-L threads are paired UDMA<->IP and no further transfers is possible. This could be the case for IPs J721E Main CPSW (cpsw9g). Hence, to avoid such situation do PSI-L threads pairing only when UDMA channel is going to be enabled as at this time DMA consumer module expected to be active already. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201030203000.4281-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-10-31 04:30:00 +08:00
if (tx_chn->psil_paired) {
xudma_navss_psil_unpair(tx_chn->common.udmax,
tx_chn->common.src_thread,
tx_chn->common.dst_thread);
tx_chn->psil_paired = false;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
EXPORT_SYMBOL_GPL(k3_udma_glue_disable_tx_chn);
void k3_udma_glue_tdown_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
bool sync)
{
int i = 0;
u32 val;
k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown1");
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG,
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
UDMA_CHAN_RT_CTL_EN | UDMA_CHAN_RT_CTL_TDOWN);
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
val = xudma_tchanrt_read(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
val = xudma_tchanrt_read(tx_chn->udma_tchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_CTL_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
udelay(1);
if (i > K3_UDMAX_TDOWN_TIMEOUT_US) {
dev_err(tx_chn->common.dev, "TX tdown timeout\n");
break;
}
i++;
}
val = xudma_tchanrt_read(tx_chn->udma_tchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (sync && (val & UDMA_PEER_RT_EN_ENABLE))
dev_err(tx_chn->common.dev, "TX tdown peer not stopped\n");
k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown2");
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_tx_chn);
void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
void *data,
void (*cleanup)(void *data, dma_addr_t desc_dma))
{
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
struct device *dev = tx_chn->common.dev;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
dma_addr_t desc_dma;
int occ_tx, i, ret;
/*
* TXQ reset need to be special way as it is input for udma and its
* state cached by udma, so:
* 1) save TXQ occ
* 2) clean up TXQ and call callback .cleanup() for each desc
* 3) reset TXQ in a special way
*/
occ_tx = k3_ringacc_ring_get_occ(tx_chn->ringtx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
dev_dbg(dev, "TX reset occ_tx %u\n", occ_tx);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
for (i = 0; i < occ_tx; i++) {
ret = k3_ringacc_ring_pop(tx_chn->ringtx, &desc_dma);
if (ret) {
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (ret != -ENODATA)
dev_err(dev, "TX reset pop %d\n", ret);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
break;
}
cleanup(data, desc_dma);
}
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
/* reset TXCQ as it is not input for udma - expected to be empty */
k3_ringacc_ring_reset(tx_chn->ringtxcq);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
k3_ringacc_ring_reset_dma(tx_chn->ringtx, occ_tx);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_reset_tx_chn);
u32 k3_udma_glue_tx_get_hdesc_size(struct k3_udma_glue_tx_channel *tx_chn)
{
return tx_chn->common.hdesc_size;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_hdesc_size);
u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn)
{
return k3_ringacc_get_ring_id(tx_chn->ringtxcq);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_txcq_id);
int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn)
{
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(tx_chn->common.udmax)) {
tx_chn->virq = xudma_pktdma_tflow_get_irq(tx_chn->common.udmax,
tx_chn->udma_tflow_id);
} else {
tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq);
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
return tx_chn->virq;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq);
dmaengine: ti: k3-udma-glue: Add function to get device pointer for DMA API Glue layer users should use the device of the DMA for DMA mapping and allocations as it is the DMA which accesses to descriptors and buffers, not the clients Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-5-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:24 +08:00
struct device *
k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn)
{
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(tx_chn->common.udmax) &&
(tx_chn->common.atype_asel == 14 || tx_chn->common.atype_asel == 15))
return &tx_chn->common.chan_dev;
dmaengine: ti: k3-udma-glue: Add function to get device pointer for DMA API Glue layer users should use the device of the DMA for DMA mapping and allocations as it is the DMA which accesses to descriptors and buffers, not the clients Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-5-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:24 +08:00
return xudma_get_device(tx_chn->common.udmax);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_dma_device);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
void k3_udma_glue_tx_dma_to_cppi5_addr(struct k3_udma_glue_tx_channel *tx_chn,
dma_addr_t *addr)
{
if (!xudma_is_pktdma(tx_chn->common.udmax) ||
!tx_chn->common.atype_asel)
return;
*addr |= (u64)tx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_dma_to_cppi5_addr);
void k3_udma_glue_tx_cppi5_to_dma_addr(struct k3_udma_glue_tx_channel *tx_chn,
dma_addr_t *addr)
{
if (!xudma_is_pktdma(tx_chn->common.udmax) ||
!tx_chn->common.atype_asel)
return;
*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tx_cppi5_to_dma_addr);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
{
const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
struct ti_sci_msg_rm_udmap_rx_ch_cfg req;
int ret;
memset(&req, 0, sizeof(req));
req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |
dmaengine: ti: k3-udma: Implement support for atype (for virtualization) The DT for virtualized hosts have dma-cells == 2 where the second parameter is the ATYPE for the channel. In case of dma-cells == 1 we can configure the ATYPE as 0 (reset value). The ATYPE defined for j721e are: 0: pointers are physical addresses (no translation) 1: pointers are intermediate addresses (PVU) 2: pointers are virtual addresses (SMMU) Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200218143126.11361-3-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-18 22:31:26 +08:00
TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
req.nav_id = tisci_rm->tisci_dev_id;
req.index = rx_chn->udma_rchan_id;
req.rx_fetch_size = rx_chn->common.hdesc_size >> 2;
/*
* TODO: we can't support rxcq_qnum/RCHAN[a]_RCQ cfg with current sysfw
* and udmax impl, so just configure it to invalid value.
* req.rxcq_qnum = k3_ringacc_get_ring_id(rx_chn->flows[0].ringrx);
*/
req.rxcq_qnum = 0xFFFF;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (!xudma_is_pktdma(rx_chn->common.udmax) && rx_chn->flow_num &&
rx_chn->flow_id_base != rx_chn->udma_rchan_id) {
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/* Default flow + extra ones */
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
req.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
req.flowid_start = rx_chn->flow_id_base;
req.flowid_cnt = rx_chn->flow_num;
}
req.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
req.rx_atype = rx_chn->common.atype_asel;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
ret = tisci_rm->tisci_udmap_ops->rx_ch_cfg(tisci_rm->tisci, &req);
if (ret)
dev_err(rx_chn->common.dev, "rchan%d cfg failed %d\n",
rx_chn->udma_rchan_id, ret);
return ret;
}
static void k3_udma_glue_release_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_num)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
if (IS_ERR_OR_NULL(flow->udma_rflow))
return;
if (flow->ringrxfdq)
k3_ringacc_ring_free(flow->ringrxfdq);
if (flow->ringrx)
k3_ringacc_ring_free(flow->ringrx);
xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow);
flow->udma_rflow = NULL;
rx_chn->flows_ready--;
}
static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_idx,
struct k3_udma_glue_rx_flow_cfg *flow_cfg)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
struct device *dev = rx_chn->common.dev;
struct ti_sci_msg_rm_udmap_flow_cfg req;
int rx_ring_id;
int rx_ringfdq_id;
int ret = 0;
flow->udma_rflow = xudma_rflow_get(rx_chn->common.udmax,
flow->udma_rflow_id);
if (IS_ERR(flow->udma_rflow)) {
ret = PTR_ERR(flow->udma_rflow);
dev_err(dev, "UDMAX rflow get err %d\n", ret);
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
return ret;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
if (flow->udma_rflow_id != xudma_rflow_get_id(flow->udma_rflow)) {
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
ret = -ENODEV;
goto err_rflow_put;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(rx_chn->common.udmax)) {
rx_ringfdq_id = flow->udma_rflow_id +
xudma_get_rflow_ring_offset(rx_chn->common.udmax);
rx_ring_id = 0;
} else {
rx_ring_id = flow_cfg->ring_rxq_id;
rx_ringfdq_id = flow_cfg->ring_rxfdq0_id;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/* request and cfg rings */
dmaengine: ti: k3-udma: Switch to k3_ringacc_request_rings_pair We only request ring pairs via K3 DMA driver, switch to use the new k3_ringacc_request_rings_pair() to simplify the code. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Vinod Koul <vkoul@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
2020-07-25 05:20:24 +08:00
ret = k3_ringacc_request_rings_pair(rx_chn->common.ringacc,
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
rx_ringfdq_id, rx_ring_id,
dmaengine: ti: k3-udma: Switch to k3_ringacc_request_rings_pair We only request ring pairs via K3 DMA driver, switch to use the new k3_ringacc_request_rings_pair() to simplify the code. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Vinod Koul <vkoul@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
2020-07-25 05:20:24 +08:00
&flow->ringrxfdq,
&flow->ringrx);
if (ret) {
dev_err(dev, "Failed to get RX/RXFDQ rings %d\n", ret);
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
goto err_rflow_put;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
dmaengine: ti: k3-udma-glue: Configure the dma_dev for rings Rings in RING mode should be using the DMA device for DMA API as in this mode the ringacc will not access the ring memory in any ways, but the DMA is. Fix up the ring configuration and set the dma_dev unconditionally and let the ringacc driver to select the correct device to use for DMA API. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-7-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:26 +08:00
/* Set the dma_dev for the rings to be configured */
flow_cfg->rx_cfg.dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn);
flow_cfg->rxfdq_cfg.dma_dev = flow_cfg->rx_cfg.dma_dev;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
/* Set the ASEL value for DMA rings of PKTDMA */
if (xudma_is_pktdma(rx_chn->common.udmax)) {
flow_cfg->rx_cfg.asel = rx_chn->common.atype_asel;
flow_cfg->rxfdq_cfg.asel = rx_chn->common.atype_asel;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
ret = k3_ringacc_ring_cfg(flow->ringrx, &flow_cfg->rx_cfg);
if (ret) {
dev_err(dev, "Failed to cfg ringrx %d\n", ret);
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
goto err_ringrxfdq_free;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
ret = k3_ringacc_ring_cfg(flow->ringrxfdq, &flow_cfg->rxfdq_cfg);
if (ret) {
dev_err(dev, "Failed to cfg ringrxfdq %d\n", ret);
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
goto err_ringrxfdq_free;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
if (rx_chn->remote) {
rx_ring_id = TI_SCI_RESOURCE_NULL;
rx_ringfdq_id = TI_SCI_RESOURCE_NULL;
} else {
rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx);
rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq);
}
memset(&req, 0, sizeof(req));
req.valid_params =
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
req.nav_id = tisci_rm->tisci_dev_id;
req.flow_index = flow->udma_rflow_id;
if (rx_chn->common.epib)
req.rx_einfo_present = 1;
if (rx_chn->common.psdata_size)
req.rx_psinfo_present = 1;
if (flow_cfg->rx_error_handling)
req.rx_error_handling = 1;
req.rx_desc_type = 0;
req.rx_dest_qnum = rx_ring_id;
req.rx_src_tag_hi_sel = 0;
req.rx_src_tag_lo_sel = flow_cfg->src_tag_lo_sel;
req.rx_dest_tag_hi_sel = 0;
req.rx_dest_tag_lo_sel = 0;
req.rx_fdq0_sz0_qnum = rx_ringfdq_id;
req.rx_fdq1_qnum = rx_ringfdq_id;
req.rx_fdq2_qnum = rx_ringfdq_id;
req.rx_fdq3_qnum = rx_ringfdq_id;
ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
if (ret) {
dev_err(dev, "flow%d config failed: %d\n", flow->udma_rflow_id,
ret);
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
goto err_ringrxfdq_free;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
rx_chn->flows_ready++;
dev_dbg(dev, "flow%d config done. ready:%d\n",
flow->udma_rflow_id, rx_chn->flows_ready);
return 0;
dmaengine: ti: k3-udma-glue: Fix an error handling path in 'k3_udma_glue_cfg_rx_flow()' All but one error handling paths in the 'k3_udma_glue_cfg_rx_flow()' function 'goto err' and call 'k3_udma_glue_release_rx_flow()'. This not correct because this function has a 'channel->flows_ready--;' at the end, but 'flows_ready' has not been incremented here, when we branch to the error handling path. In order to keep a correct value in 'flows_ready', un-roll 'k3_udma_glue_release_rx_flow()', simplify it, add some labels and branch at the correct places when an error is detected. Doing so, we also NULLify 'flow->udma_rflow' in a path that was lacking it. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine user") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200318191209.1267-1-christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-19 03:12:09 +08:00
err_ringrxfdq_free:
k3_ringacc_ring_free(flow->ringrxfdq);
k3_ringacc_ring_free(flow->ringrx);
err_rflow_put:
xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow);
flow->udma_rflow = NULL;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
return ret;
}
static void k3_udma_glue_dump_rx_chn(struct k3_udma_glue_rx_channel *chn)
{
struct device *dev = chn->common.dev;
dev_dbg(dev, "dump_rx_chn:\n"
"udma_rchan_id: %d\n"
"src_thread: %08x\n"
"dst_thread: %08x\n"
"epib: %d\n"
"hdesc_size: %u\n"
"psdata_size: %u\n"
"swdata_size: %u\n"
"flow_id_base: %d\n"
"flow_num: %d\n",
chn->udma_rchan_id,
chn->common.src_thread,
chn->common.dst_thread,
chn->common.epib,
chn->common.hdesc_size,
chn->common.psdata_size,
chn->common.swdata_size,
chn->flow_id_base,
chn->flow_num);
}
static void k3_udma_glue_dump_rx_rt_chn(struct k3_udma_glue_rx_channel *chn,
char *mark)
{
struct device *dev = chn->common.dev;
dev_dbg(dev, "=== dump ===> %s\n", mark);
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_CTL_REG,
xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PEER_RT_EN_REG,
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
xudma_rchanrt_read(chn->udma_rchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PCNT_REG,
xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_PCNT_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_BCNT_REG,
xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_BCNT_REG));
dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_SBCNT_REG,
xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_SBCNT_REG));
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
static int
k3_udma_glue_allocate_rx_flows(struct k3_udma_glue_rx_channel *rx_chn,
struct k3_udma_glue_rx_channel_cfg *cfg)
{
int ret;
/* default rflow */
if (cfg->flow_id_use_rxchan_id)
return 0;
/* not a GP rflows */
if (rx_chn->flow_id_base != -1 &&
!xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base))
return 0;
/* Allocate range of GP rflows */
ret = xudma_alloc_gp_rflow_range(rx_chn->common.udmax,
rx_chn->flow_id_base,
rx_chn->flow_num);
if (ret < 0) {
dev_err(rx_chn->common.dev, "UDMAX reserve_rflow %d cnt:%d err: %d\n",
rx_chn->flow_id_base, rx_chn->flow_num, ret);
return ret;
}
rx_chn->flow_id_base = ret;
return 0;
}
static struct k3_udma_glue_rx_channel *
k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
struct k3_udma_glue_rx_channel_cfg *cfg)
{
struct k3_udma_glue_rx_channel *rx_chn;
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
struct psil_endpoint_config *ep_cfg;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
int ret, i;
if (cfg->flow_id_num <= 0)
return ERR_PTR(-EINVAL);
if (cfg->flow_id_num != 1 &&
(cfg->def_flow_cfg || cfg->flow_id_use_rxchan_id))
return ERR_PTR(-EINVAL);
rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
if (!rx_chn)
return ERR_PTR(-ENOMEM);
rx_chn->common.dev = dev;
rx_chn->common.swdata_size = cfg->swdata_size;
rx_chn->remote = false;
/* parse of udmap channel */
ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
&rx_chn->common, false);
if (ret)
goto err;
rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
rx_chn->common.psdata_size,
rx_chn->common.swdata_size);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
ep_cfg = rx_chn->common.ep_config;
if (xudma_is_pktdma(rx_chn->common.udmax))
rx_chn->udma_rchan_id = ep_cfg->mapped_channel_id;
else
rx_chn->udma_rchan_id = -1;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/* request and cfg UDMAP RX channel */
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax,
rx_chn->udma_rchan_id);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (IS_ERR(rx_chn->udma_rchanx)) {
ret = PTR_ERR(rx_chn->udma_rchanx);
dev_err(dev, "UDMAX rchanx get err %d\n", ret);
goto err;
}
rx_chn->udma_rchan_id = xudma_rchan_get_id(rx_chn->udma_rchanx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
dev_set_name(&rx_chn->common.chan_dev, "rchan%d-0x%04x",
rx_chn->udma_rchan_id, rx_chn->common.src_thread);
ret = device_register(&rx_chn->common.chan_dev);
if (ret) {
dev_err(dev, "Channel Device registration failed %d\n", ret);
rx_chn->common.chan_dev.parent = NULL;
goto err;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(rx_chn->common.udmax)) {
/* prepare the channel device as coherent */
rx_chn->common.chan_dev.dma_coherent = true;
dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
DMA_BIT_MASK(48));
}
if (xudma_is_pktdma(rx_chn->common.udmax)) {
int flow_start = cfg->flow_id_base;
int flow_end;
if (flow_start == -1)
flow_start = ep_cfg->flow_start;
flow_end = flow_start + cfg->flow_id_num - 1;
if (flow_start < ep_cfg->flow_start ||
flow_end > (ep_cfg->flow_start + ep_cfg->flow_num - 1)) {
dev_err(dev, "Invalid flow range requested\n");
ret = -EINVAL;
goto err;
}
rx_chn->flow_id_base = flow_start;
} else {
rx_chn->flow_id_base = cfg->flow_id_base;
/* Use RX channel id as flow id: target dev can't generate flow_id */
if (cfg->flow_id_use_rxchan_id)
rx_chn->flow_id_base = rx_chn->udma_rchan_id;
}
rx_chn->flow_num = cfg->flow_id_num;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
sizeof(*rx_chn->flows), GFP_KERNEL);
if (!rx_chn->flows) {
ret = -ENOMEM;
goto err;
}
ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
if (ret)
goto err;
for (i = 0; i < rx_chn->flow_num; i++)
rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
/* request and cfg psi-l */
rx_chn->common.dst_thread =
xudma_dev_get_psil_base(rx_chn->common.udmax) +
rx_chn->udma_rchan_id;
ret = k3_udma_glue_cfg_rx_chn(rx_chn);
if (ret) {
dev_err(dev, "Failed to cfg rchan %d\n", ret);
goto err;
}
/* init default RX flow only if flow_num = 1 */
if (cfg->def_flow_cfg) {
ret = k3_udma_glue_cfg_rx_flow(rx_chn, 0, cfg->def_flow_cfg);
if (ret)
goto err;
}
k3_udma_glue_dump_rx_chn(rx_chn);
return rx_chn;
err:
k3_udma_glue_release_rx_chn(rx_chn);
return ERR_PTR(ret);
}
static struct k3_udma_glue_rx_channel *
k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
struct k3_udma_glue_rx_channel_cfg *cfg)
{
struct k3_udma_glue_rx_channel *rx_chn;
int ret, i;
if (cfg->flow_id_num <= 0 ||
cfg->flow_id_use_rxchan_id ||
cfg->def_flow_cfg ||
cfg->flow_id_base < 0)
return ERR_PTR(-EINVAL);
/*
* Remote RX channel is under control of Remote CPU core, so
* Linux can only request and manipulate by dedicated RX flows
*/
rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
if (!rx_chn)
return ERR_PTR(-ENOMEM);
rx_chn->common.dev = dev;
rx_chn->common.swdata_size = cfg->swdata_size;
rx_chn->remote = true;
rx_chn->udma_rchan_id = -1;
rx_chn->flow_num = cfg->flow_id_num;
rx_chn->flow_id_base = cfg->flow_id_base;
rx_chn->psil_paired = false;
/* parse of udmap channel */
ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
&rx_chn->common, false);
if (ret)
goto err;
rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
rx_chn->common.psdata_size,
rx_chn->common.swdata_size);
rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
sizeof(*rx_chn->flows), GFP_KERNEL);
if (!rx_chn->flows) {
ret = -ENOMEM;
goto err;
}
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
dev_set_name(&rx_chn->common.chan_dev, "rchan_remote-0x%04x",
rx_chn->common.src_thread);
ret = device_register(&rx_chn->common.chan_dev);
if (ret) {
dev_err(dev, "Channel Device registration failed %d\n", ret);
rx_chn->common.chan_dev.parent = NULL;
goto err;
}
if (xudma_is_pktdma(rx_chn->common.udmax)) {
/* prepare the channel device as coherent */
rx_chn->common.chan_dev.dma_coherent = true;
dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
DMA_BIT_MASK(48));
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
if (ret)
goto err;
for (i = 0; i < rx_chn->flow_num; i++)
rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
k3_udma_glue_dump_rx_chn(rx_chn);
return rx_chn;
err:
k3_udma_glue_release_rx_chn(rx_chn);
return ERR_PTR(ret);
}
struct k3_udma_glue_rx_channel *
k3_udma_glue_request_rx_chn(struct device *dev, const char *name,
struct k3_udma_glue_rx_channel_cfg *cfg)
{
if (cfg->remote)
return k3_udma_glue_request_remote_rx_chn(dev, name, cfg);
else
return k3_udma_glue_request_rx_chn_priv(dev, name, cfg);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_request_rx_chn);
void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
{
int i;
if (IS_ERR_OR_NULL(rx_chn->common.udmax))
return;
if (rx_chn->psil_paired) {
xudma_navss_psil_unpair(rx_chn->common.udmax,
rx_chn->common.src_thread,
rx_chn->common.dst_thread);
rx_chn->psil_paired = false;
}
for (i = 0; i < rx_chn->flow_num; i++)
k3_udma_glue_release_rx_flow(rx_chn, i);
if (xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base))
xudma_free_gp_rflow_range(rx_chn->common.udmax,
rx_chn->flow_id_base,
rx_chn->flow_num);
if (!IS_ERR_OR_NULL(rx_chn->udma_rchanx))
xudma_rchan_put(rx_chn->common.udmax,
rx_chn->udma_rchanx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (rx_chn->common.chan_dev.parent) {
device_unregister(&rx_chn->common.chan_dev);
rx_chn->common.chan_dev.parent = NULL;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
EXPORT_SYMBOL_GPL(k3_udma_glue_release_rx_chn);
int k3_udma_glue_rx_flow_init(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_idx,
struct k3_udma_glue_rx_flow_cfg *flow_cfg)
{
if (flow_idx >= rx_chn->flow_num)
return -EINVAL;
return k3_udma_glue_cfg_rx_flow(rx_chn, flow_idx, flow_cfg);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_init);
u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_idx)
{
struct k3_udma_glue_rx_flow *flow;
if (flow_idx >= rx_chn->flow_num)
return -EINVAL;
flow = &rx_chn->flows[flow_idx];
return k3_ringacc_get_ring_id(flow->ringrxfdq);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_get_fdq_id);
u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn)
{
return rx_chn->flow_id_base;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_flow_id_base);
int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_idx)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
struct device *dev = rx_chn->common.dev;
struct ti_sci_msg_rm_udmap_flow_cfg req;
int rx_ring_id;
int rx_ringfdq_id;
int ret = 0;
if (!rx_chn->remote)
return -EINVAL;
rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx);
rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq);
memset(&req, 0, sizeof(req));
req.valid_params =
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
req.nav_id = tisci_rm->tisci_dev_id;
req.flow_index = flow->udma_rflow_id;
req.rx_dest_qnum = rx_ring_id;
req.rx_fdq0_sz0_qnum = rx_ringfdq_id;
req.rx_fdq1_qnum = rx_ringfdq_id;
req.rx_fdq2_qnum = rx_ringfdq_id;
req.rx_fdq3_qnum = rx_ringfdq_id;
ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
if (ret) {
dev_err(dev, "flow%d enable failed: %d\n", flow->udma_rflow_id,
ret);
}
return ret;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_enable);
int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_idx)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
struct device *dev = rx_chn->common.dev;
struct ti_sci_msg_rm_udmap_flow_cfg req;
int ret = 0;
if (!rx_chn->remote)
return -EINVAL;
memset(&req, 0, sizeof(req));
req.valid_params =
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
req.nav_id = tisci_rm->tisci_dev_id;
req.flow_index = flow->udma_rflow_id;
req.rx_dest_qnum = TI_SCI_RESOURCE_NULL;
req.rx_fdq0_sz0_qnum = TI_SCI_RESOURCE_NULL;
req.rx_fdq1_qnum = TI_SCI_RESOURCE_NULL;
req.rx_fdq2_qnum = TI_SCI_RESOURCE_NULL;
req.rx_fdq3_qnum = TI_SCI_RESOURCE_NULL;
ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
if (ret) {
dev_err(dev, "flow%d disable failed: %d\n", flow->udma_rflow_id,
ret);
}
return ret;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_disable);
int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
{
dmaengine: ti: k3-udma-glue: move psi-l pairing in channel en/dis functions The NAVSS UDMA will stuck if target IP module is disabled by PM while PSI-L threads are paired UDMA<->IP and no further transfers is possible. This could be the case for IPs J721E Main CPSW (cpsw9g). Hence, to avoid such situation do PSI-L threads pairing only when UDMA channel is going to be enabled as at this time DMA consumer module expected to be active already. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201030203000.4281-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-10-31 04:30:00 +08:00
int ret;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (rx_chn->remote)
return -EINVAL;
if (rx_chn->flows_ready < rx_chn->flow_num)
return -EINVAL;
dmaengine: ti: k3-udma-glue: move psi-l pairing in channel en/dis functions The NAVSS UDMA will stuck if target IP module is disabled by PM while PSI-L threads are paired UDMA<->IP and no further transfers is possible. This could be the case for IPs J721E Main CPSW (cpsw9g). Hence, to avoid such situation do PSI-L threads pairing only when UDMA channel is going to be enabled as at this time DMA consumer module expected to be active already. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201030203000.4281-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-10-31 04:30:00 +08:00
ret = xudma_navss_psil_pair(rx_chn->common.udmax,
rx_chn->common.src_thread,
rx_chn->common.dst_thread);
if (ret) {
dev_err(rx_chn->common.dev, "PSI-L request err %d\n", ret);
return ret;
}
rx_chn->psil_paired = true;
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG,
dmaengine: ti: k3-udma-glue: fix channel enable functions Now the K3 UDMA glue layer enable functions perform RMW operation on UDMA RX/TX RT_CTL registers to set EN bit and enable channel, which is incorrect, because only EN bit has to be set in those registers to enable channel (all other bits should be cleared 0). More over, this causes issues when bootloader leaves UDMA channel RX/TX RT_CTL registers in incorrect state - TDOWN bit set, for example. As result, UDMA channel will just perform teardown right after it's enabled. Hence, fix it by writing correct values (EN=1) directly in UDMA channel RX/TX RT_CTL registers in k3_udma_glue_enable_tx/rx_chn() functions. Fixes: d70241913413 ("dmaengine: ti: k3-udma: Add glue layer for non DMAengine users") Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20200916120955.7963-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-09-16 20:09:55 +08:00
UDMA_CHAN_RT_CTL_EN);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_PEER_RT_EN_REG,
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
UDMA_PEER_RT_EN_ENABLE);
k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt en");
return 0;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_enable_rx_chn);
void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
{
k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis1");
xudma_rchanrt_write(rx_chn->udma_rchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG, 0);
xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG, 0);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis2");
dmaengine: ti: k3-udma-glue: move psi-l pairing in channel en/dis functions The NAVSS UDMA will stuck if target IP module is disabled by PM while PSI-L threads are paired UDMA<->IP and no further transfers is possible. This could be the case for IPs J721E Main CPSW (cpsw9g). Hence, to avoid such situation do PSI-L threads pairing only when UDMA channel is going to be enabled as at this time DMA consumer module expected to be active already. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201030203000.4281-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-10-31 04:30:00 +08:00
if (rx_chn->psil_paired) {
xudma_navss_psil_unpair(rx_chn->common.udmax,
rx_chn->common.src_thread,
rx_chn->common.dst_thread);
rx_chn->psil_paired = false;
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
EXPORT_SYMBOL_GPL(k3_udma_glue_disable_rx_chn);
void k3_udma_glue_tdown_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
bool sync)
{
int i = 0;
u32 val;
if (rx_chn->remote)
return;
k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown1");
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_PEER_RT_EN_REG,
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
UDMA_PEER_RT_EN_ENABLE | UDMA_PEER_RT_EN_TEARDOWN);
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
val = xudma_rchanrt_read(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
val = xudma_rchanrt_read(rx_chn->udma_rchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_CTL_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
udelay(1);
if (i > K3_UDMAX_TDOWN_TIMEOUT_US) {
dev_err(rx_chn->common.dev, "RX tdown timeout\n");
break;
}
i++;
}
val = xudma_rchanrt_read(rx_chn->udma_rchanx,
dmaengine: ti: k3-udma: Use common defines for TCHANRT/RCHANRT registers The register offsets and functions are the same among TCHAN and RCHAN. Use generic, common names for them. Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20200707102352.28773-4-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-07 18:23:50 +08:00
UDMA_CHAN_RT_PEER_RT_EN_REG);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
if (sync && (val & UDMA_PEER_RT_EN_ENABLE))
dev_err(rx_chn->common.dev, "TX tdown peer not stopped\n");
k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown2");
}
EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_rx_chn);
void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_num, void *data,
void (*cleanup)(void *data, dma_addr_t desc_dma), bool skip_fdq)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
struct device *dev = rx_chn->common.dev;
dma_addr_t desc_dma;
int occ_rx, i, ret;
/* reset RXCQ as it is not input for udma - expected to be empty */
occ_rx = k3_ringacc_ring_get_occ(flow->ringrx);
dev_dbg(dev, "RX reset flow %u occ_rx %u\n", flow_num, occ_rx);
/* Skip RX FDQ in case one FDQ is used for the set of flows */
if (skip_fdq)
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
goto do_reset;
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
/*
* RX FDQ reset need to be special way as it is input for udma and its
* state cached by udma, so:
* 1) save RX FDQ occ
* 2) clean up RX FDQ and call callback .cleanup() for each desc
* 3) reset RX FDQ in a special way
*/
occ_rx = k3_ringacc_ring_get_occ(flow->ringrxfdq);
dev_dbg(dev, "RX reset flow %u occ_rx_fdq %u\n", flow_num, occ_rx);
for (i = 0; i < occ_rx; i++) {
ret = k3_ringacc_ring_pop(flow->ringrxfdq, &desc_dma);
if (ret) {
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (ret != -ENODATA)
dev_err(dev, "RX reset pop %d\n", ret);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
break;
}
cleanup(data, desc_dma);
}
k3_ringacc_ring_reset_dma(flow->ringrxfdq, occ_rx);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
do_reset:
k3_ringacc_ring_reset(flow->ringrx);
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
}
EXPORT_SYMBOL_GPL(k3_udma_glue_reset_rx_chn);
int k3_udma_glue_push_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_num, struct cppi5_host_desc_t *desc_rx,
dma_addr_t desc_dma)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
return k3_ringacc_ring_push(flow->ringrxfdq, &desc_dma);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_push_rx_chn);
int k3_udma_glue_pop_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_num, dma_addr_t *desc_dma)
{
struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
return k3_ringacc_ring_pop(flow->ringrx, desc_dma);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_pop_rx_chn);
int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
u32 flow_num)
{
struct k3_udma_glue_rx_flow *flow;
flow = &rx_chn->flows[flow_num];
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(rx_chn->common.udmax)) {
flow->virq = xudma_pktdma_rflow_get_irq(rx_chn->common.udmax,
flow->udma_rflow_id);
} else {
flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
}
dmaengine: ti: k3-udma: Add glue layer for non DMAengine users Certain users can not use right now the DMAengine API due to missing features in the core. Prime example is Networking. These users can use the glue layer interface to avoid misuse of DMAengine API and when the core gains the needed features they can be converted to use generic API. The most prominent features the glue layer clients are depending on: - most PSI-L native peripheral use extra rflow ranges on a receive channel and depending on the peripheral's configuration packets from a single free descriptor ring is going to be received to different receive ring - it is also possible to have different free descriptor rings per rflow and an rflow can also support 4 additional free descriptor ring based on the size of the incoming packet - out of order completion of descriptors on a channel - when we have several queues to handle different priority packets the descriptors will be completed 'out-of-order' - the notion of prep_slave_sg is not matching with what the streaming type of operation is demanding for networking - Streaming type of operation - Ability to fill the free descriptor ring with descriptors in anticipation of incoming traffic and when a packet arrives UDMAP will form a packet and gives it to the client driver - the descriptors are not backed with exact size data buffers as we don't know the size of the packet we will receive, but as a generic pool of buffers to be used by the receive channel - NAPI type of operation (polling instead of interrupt driven transfer) - without this we can not sustain gigabit speeds and we need to support NAPI - not to limit this to networking, but other high performance operations Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Tested-by: Keerthy <j-keerthy@ti.com> Link: https://lore.kernel.org/r/20191223110458.30766-12-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2019-12-23 19:04:51 +08:00
return flow->virq;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
dmaengine: ti: k3-udma-glue: Add function to get device pointer for DMA API Glue layer users should use the device of the DMA for DMA mapping and allocations as it is the DMA which accesses to descriptors and buffers, not the clients Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-5-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:24 +08:00
struct device *
k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn)
{
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
if (xudma_is_pktdma(rx_chn->common.udmax) &&
(rx_chn->common.atype_asel == 14 || rx_chn->common.atype_asel == 15))
return &rx_chn->common.chan_dev;
dmaengine: ti: k3-udma-glue: Add function to get device pointer for DMA API Glue layer users should use the device of the DMA for DMA mapping and allocations as it is the DMA which accesses to descriptors and buffers, not the clients Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-5-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:24 +08:00
return xudma_get_device(rx_chn->common.udmax);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_dma_device);
dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA This commit adds support for PKTDMA in k3-udma glue driver. Use new psil_endpoint_config struct to get static data for a given channel or a flow during setup. Make sure that the RX flows being mapped to a RX channel is within the range of flows that is been allocated to that RX channel. Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-12-08 17:04:40 +08:00
void k3_udma_glue_rx_dma_to_cppi5_addr(struct k3_udma_glue_rx_channel *rx_chn,
dma_addr_t *addr)
{
if (!xudma_is_pktdma(rx_chn->common.udmax) ||
!rx_chn->common.atype_asel)
return;
*addr |= (u64)rx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_dma_to_cppi5_addr);
void k3_udma_glue_rx_cppi5_to_dma_addr(struct k3_udma_glue_rx_channel *rx_chn,
dma_addr_t *addr)
{
if (!xudma_is_pktdma(rx_chn->common.udmax) ||
!rx_chn->common.atype_asel)
return;
*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
}
EXPORT_SYMBOL_GPL(k3_udma_glue_rx_cppi5_to_dma_addr);
static int __init k3_udma_glue_class_init(void)
{
return class_register(&k3_udma_glue_devclass);
}
arch_initcall(k3_udma_glue_class_init);