Certain DSA 3.0 opcodes, such as Gather copy and Gather reduce requires max
SGL configured for workqueues prior to support these opcodes.
Configure the maximum scatter-gather list (SGL) size for workqueues during
setup on the supported HW. Application can then properly handle the SGL
size without explicitly setting it.
Signed-off-by: Yi Sun <yi.sun@intel.com>
Co-developed-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5cf419fe6b46..1c10b030bea7 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -375,6 +375,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
memset(wq->name, 0, WQ_NAME_SIZE);
wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH);
+ idxd_wq_set_init_max_sgl_size(idxd, wq);
if (wq->opcap_bmap)
bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
}
@@ -974,6 +975,8 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
/* bytes 12-15 */
wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size));
+ if (idxd_sgl_supported(idxd))
+ wq->wqcfg->max_sgl_shift = ilog2(wq->max_sgl_size);
/* bytes 32-63 */
if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) {
@@ -1152,6 +1155,8 @@ static int idxd_wq_load_config(struct idxd_wq *wq)
wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift;
idxd_wq_set_max_batch_size(idxd->data->type, wq, 1U << wq->wqcfg->max_batch_shift);
+ if (idxd_sgl_supported(idxd))
+ wq->max_sgl_size = 1U << wq->wqcfg->max_sgl_shift;
for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index cc0a3fe1c957..fe5af50b58a4 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -227,6 +227,7 @@ struct idxd_wq {
char name[WQ_NAME_SIZE + 1];
u64 max_xfer_bytes;
u32 max_batch_size;
+ u32 max_sgl_size;
/* Lock to protect upasid_xa access. */
struct mutex uc_lock;
@@ -348,6 +349,7 @@ struct idxd_device {
u64 max_xfer_bytes;
u32 max_batch_size;
+ u32 max_sgl_size;
int max_groups;
int max_engines;
int max_rdbufs;
@@ -692,6 +694,20 @@ static inline void idxd_wq_set_max_batch_size(int idxd_type, struct idxd_wq *wq,
wq->max_batch_size = max_batch_size;
}
+static bool idxd_sgl_supported(struct idxd_device *idxd)
+{
+ return idxd->hw.dsacap0.sgl_formats &&
+ idxd->data->type == IDXD_TYPE_DSA &&
+ idxd->hw.version >= DEVICE_VERSION_3;
+}
+
+static inline void idxd_wq_set_init_max_sgl_size(struct idxd_device *idxd,
+ struct idxd_wq *wq)
+{
+ if (idxd_sgl_supported(idxd))
+ wq->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift;
+}
+
static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wqcfg,
u32 max_batch_shift)
{
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index cc8203320d40..f37a7d7b537a 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -217,6 +217,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
init_completion(&wq->wq_resurrect);
wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH);
+ idxd_wq_set_init_max_sgl_size(idxd, wq);
wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
if (!wq->wqcfg) {
@@ -585,6 +586,10 @@ static void idxd_read_caps(struct idxd_device *idxd)
idxd->hw.dsacap0.bits = ioread64(idxd->reg_base + IDXD_DSACAP0_OFFSET);
idxd->hw.dsacap1.bits = ioread64(idxd->reg_base + IDXD_DSACAP1_OFFSET);
idxd->hw.dsacap2.bits = ioread64(idxd->reg_base + IDXD_DSACAP2_OFFSET);
+ if (idxd_sgl_supported(idxd)) {
+ idxd->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift;
+ dev_dbg(dev, "max sgl size: %u\n", idxd->max_sgl_size);
+ }
/* read iaa cap */
if (idxd->data->type == IDXD_TYPE_IAX && idxd->hw.version >= DEVICE_VERSION_2)
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 45485ecd7bb6..0401cfc95f27 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -385,7 +385,8 @@ union wqcfg {
/* bytes 12-15 */
u32 max_xfer_shift:5;
u32 max_batch_shift:4;
- u32 rsvd4:23;
+ u32 max_sgl_shift:4;
+ u32 rsvd4:19;
/* bytes 16-19 */
u16 occupancy_inth;
@@ -585,6 +586,15 @@ union evl_status_reg {
#define IDXD_DSACAP0_OFFSET 0x180
union dsacap0_reg {
+ struct {
+ u64 max_sgl_shift:4;
+ u64 max_gr_block_shift:4;
+ u64 ops_inter_domain:7;
+ u64 rsvd1:17;
+ u64 sgl_formats:16;
+ u64 max_sg_process:8;
+ u64 rsvd2:8;
+ };
u64 bits;
};
--
2.43.0
Hi, Yi, On 6/13/25 09:18, Yi Sun wrote: > Certain DSA 3.0 opcodes, such as Gather copy and Gather reduce requires max s/reduce requires/reduce, require/ > SGL configured for workqueues prior to support these opcodes. s/prior to support/prior to supporting/ > > Configure the maximum scatter-gather list (SGL) size for workqueues during > setup on the supported HW. Application can then properly handle the SGL > size without explicitly setting it. > > Signed-off-by: Yi Sun <yi.sun@intel.com> > Co-developed-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> > Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> > > diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c > index 5cf419fe6b46..1c10b030bea7 100644 > --- a/drivers/dma/idxd/device.c > +++ b/drivers/dma/idxd/device.c > @@ -375,6 +375,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq) > memset(wq->name, 0, WQ_NAME_SIZE); > wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; > idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH); > + idxd_wq_set_init_max_sgl_size(idxd, wq); > if (wq->opcap_bmap) > bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); > } > @@ -974,6 +975,8 @@ static int idxd_wq_config_write(struct idxd_wq *wq) > /* bytes 12-15 */ > wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); > idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size)); > + if (idxd_sgl_supported(idxd)) > + wq->wqcfg->max_sgl_shift = ilog2(wq->max_sgl_size); > > /* bytes 32-63 */ > if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) { > @@ -1152,6 +1155,8 @@ static int idxd_wq_load_config(struct idxd_wq *wq) > > wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift; > idxd_wq_set_max_batch_size(idxd->data->type, wq, 1U << wq->wqcfg->max_batch_shift); > + if (idxd_sgl_supported(idxd)) > + wq->max_sgl_size = 1U << wq->wqcfg->max_sgl_shift; > > for (i = 0; i < WQCFG_STRIDES(idxd); i++) { > wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i); > diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h > index cc0a3fe1c957..fe5af50b58a4 100644 > --- a/drivers/dma/idxd/idxd.h > +++ b/drivers/dma/idxd/idxd.h > @@ -227,6 +227,7 @@ struct idxd_wq { > char name[WQ_NAME_SIZE + 1]; > u64 max_xfer_bytes; > u32 max_batch_size; > + u32 max_sgl_size; > > /* Lock to protect upasid_xa access. */ > struct mutex uc_lock; > @@ -348,6 +349,7 @@ struct idxd_device { > > u64 max_xfer_bytes; > u32 max_batch_size; > + u32 max_sgl_size; > int max_groups; > int max_engines; > int max_rdbufs; > @@ -692,6 +694,20 @@ static inline void idxd_wq_set_max_batch_size(int idxd_type, struct idxd_wq *wq, > wq->max_batch_size = max_batch_size; > } > > +static bool idxd_sgl_supported(struct idxd_device *idxd) > +{ > + return idxd->hw.dsacap0.sgl_formats && > + idxd->data->type == IDXD_TYPE_DSA && > + idxd->hw.version >= DEVICE_VERSION_3; > +} This is not safe on DSA 1 or 2 because the first check idxd->hw.dsacap0.sgl_format is an invalid value on DSA 1 and 2. You need to change the order to this for safety: + return idxd->data->type == IDXD_TYPE_DSA && + idxd->hw.version >= DEVICE_VERSION_3 && + idxd->hw.dsacap0.sgl_formats; > + > +static inline void idxd_wq_set_init_max_sgl_size(struct idxd_device *idxd, > + struct idxd_wq *wq) > +{ > + if (idxd_sgl_supported(idxd)) > + wq->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift; > +} > + > static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wqcfg, > u32 max_batch_shift) > { > diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c > index cc8203320d40..f37a7d7b537a 100644 > --- a/drivers/dma/idxd/init.c > +++ b/drivers/dma/idxd/init.c > @@ -217,6 +217,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd) > init_completion(&wq->wq_resurrect); > wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; > idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH); > + idxd_wq_set_init_max_sgl_size(idxd, wq); > wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; > wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); > if (!wq->wqcfg) { > @@ -585,6 +586,10 @@ static void idxd_read_caps(struct idxd_device *idxd) > idxd->hw.dsacap0.bits = ioread64(idxd->reg_base + IDXD_DSACAP0_OFFSET); > idxd->hw.dsacap1.bits = ioread64(idxd->reg_base + IDXD_DSACAP1_OFFSET); > idxd->hw.dsacap2.bits = ioread64(idxd->reg_base + IDXD_DSACAP2_OFFSET); > + if (idxd_sgl_supported(idxd)) { > + idxd->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift; > + dev_dbg(dev, "max sgl size: %u\n", idxd->max_sgl_size); > + } > > /* read iaa cap */ > if (idxd->data->type == IDXD_TYPE_IAX && idxd->hw.version >= DEVICE_VERSION_2) > diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h > index 45485ecd7bb6..0401cfc95f27 100644 > --- a/drivers/dma/idxd/registers.h > +++ b/drivers/dma/idxd/registers.h > @@ -385,7 +385,8 @@ union wqcfg { > /* bytes 12-15 */ > u32 max_xfer_shift:5; > u32 max_batch_shift:4; > - u32 rsvd4:23; > + u32 max_sgl_shift:4; > + u32 rsvd4:19; > > /* bytes 16-19 */ > u16 occupancy_inth; > @@ -585,6 +586,15 @@ union evl_status_reg { > > #define IDXD_DSACAP0_OFFSET 0x180 > union dsacap0_reg { > + struct { > + u64 max_sgl_shift:4; > + u64 max_gr_block_shift:4; > + u64 ops_inter_domain:7; > + u64 rsvd1:17; > + u64 sgl_formats:16; > + u64 max_sg_process:8; > + u64 rsvd2:8; > + }; Ah. The fields are defined here. I would suggest the fields are defined in patch 1 because: 1. Reviewer (like me) may get confused when reviewing patch 1 where dsacap0 doesn't have any field but is defined a union. 2. There are fields that not max_sgl_shift. So those fields are irrelevant to this patch and had better to be define in patch 1. > u64 bits; > }; > Thanks. -Fenghua
On 13.06.2025 15:03, Fenghua Yu wrote: >Hi, Yi, > >On 6/13/25 09:18, Yi Sun wrote: >>Certain DSA 3.0 opcodes, such as Gather copy and Gather reduce requires max >s/reduce requires/reduce, require/ >>SGL configured for workqueues prior to support these opcodes. >s/prior to support/prior to supporting/ >> Get it. ... ... >> #define IDXD_DSACAP0_OFFSET 0x180 >> union dsacap0_reg { >>+ struct { >>+ u64 max_sgl_shift:4; >>+ u64 max_gr_block_shift:4; >>+ u64 ops_inter_domain:7; >>+ u64 rsvd1:17; >>+ u64 sgl_formats:16; >>+ u64 max_sg_process:8; >>+ u64 rsvd2:8; >>+ }; > >Ah. The fields are defined here. I would suggest the fields are >defined in patch 1 because: > >1. Reviewer (like me) may get confused when reviewing patch 1 where >dsacap0 doesn't have any field but is defined a union. > >2. There are fields that not max_sgl_shift. So those fields are >irrelevant to this patch and had better to be define in patch 1. > >> u64 bits; >> }; > OK, I see. I'll move this definition to patch 1. Thanks --Sun, Yi
On 6/13/25 9:18 AM, Yi Sun wrote: > Certain DSA 3.0 opcodes, such as Gather copy and Gather reduce requires max > SGL configured for workqueues prior to support these opcodes. > > Configure the maximum scatter-gather list (SGL) size for workqueues during > setup on the supported HW. Application can then properly handle the SGL > size without explicitly setting it. > > Signed-off-by: Yi Sun <yi.sun@intel.com> > Co-developed-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> > Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> > > diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c > index 5cf419fe6b46..1c10b030bea7 100644 > --- a/drivers/dma/idxd/device.c > +++ b/drivers/dma/idxd/device.c > @@ -375,6 +375,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq) > memset(wq->name, 0, WQ_NAME_SIZE); > wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; > idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH); > + idxd_wq_set_init_max_sgl_size(idxd, wq); > if (wq->opcap_bmap) > bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); > } > @@ -974,6 +975,8 @@ static int idxd_wq_config_write(struct idxd_wq *wq) > /* bytes 12-15 */ > wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); > idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size)); > + if (idxd_sgl_supported(idxd)) > + wq->wqcfg->max_sgl_shift = ilog2(wq->max_sgl_size); > > /* bytes 32-63 */ > if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) { > @@ -1152,6 +1155,8 @@ static int idxd_wq_load_config(struct idxd_wq *wq) > > wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift; > idxd_wq_set_max_batch_size(idxd->data->type, wq, 1U << wq->wqcfg->max_batch_shift); > + if (idxd_sgl_supported(idxd)) > + wq->max_sgl_size = 1U << wq->wqcfg->max_sgl_shift; > > for (i = 0; i < WQCFG_STRIDES(idxd); i++) { > wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i); > diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h > index cc0a3fe1c957..fe5af50b58a4 100644 > --- a/drivers/dma/idxd/idxd.h > +++ b/drivers/dma/idxd/idxd.h > @@ -227,6 +227,7 @@ struct idxd_wq { > char name[WQ_NAME_SIZE + 1]; > u64 max_xfer_bytes; > u32 max_batch_size; > + u32 max_sgl_size; > > /* Lock to protect upasid_xa access. */ > struct mutex uc_lock; > @@ -348,6 +349,7 @@ struct idxd_device { > > u64 max_xfer_bytes; > u32 max_batch_size; > + u32 max_sgl_size; > int max_groups; > int max_engines; > int max_rdbufs; > @@ -692,6 +694,20 @@ static inline void idxd_wq_set_max_batch_size(int idxd_type, struct idxd_wq *wq, > wq->max_batch_size = max_batch_size; > } > > +static bool idxd_sgl_supported(struct idxd_device *idxd) > +{ > + return idxd->hw.dsacap0.sgl_formats && > + idxd->data->type == IDXD_TYPE_DSA && > + idxd->hw.version >= DEVICE_VERSION_3; > +} > + > +static inline void idxd_wq_set_init_max_sgl_size(struct idxd_device *idxd, > + struct idxd_wq *wq) > +{ > + if (idxd_sgl_supported(idxd)) > + wq->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift; > +} > + > static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wqcfg, > u32 max_batch_shift) > { > diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c > index cc8203320d40..f37a7d7b537a 100644 > --- a/drivers/dma/idxd/init.c > +++ b/drivers/dma/idxd/init.c > @@ -217,6 +217,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd) > init_completion(&wq->wq_resurrect); > wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; > idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH); > + idxd_wq_set_init_max_sgl_size(idxd, wq); > wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; > wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); > if (!wq->wqcfg) { > @@ -585,6 +586,10 @@ static void idxd_read_caps(struct idxd_device *idxd) > idxd->hw.dsacap0.bits = ioread64(idxd->reg_base + IDXD_DSACAP0_OFFSET); > idxd->hw.dsacap1.bits = ioread64(idxd->reg_base + IDXD_DSACAP1_OFFSET); > idxd->hw.dsacap2.bits = ioread64(idxd->reg_base + IDXD_DSACAP2_OFFSET); > + if (idxd_sgl_supported(idxd)) { > + idxd->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift; > + dev_dbg(dev, "max sgl size: %u\n", idxd->max_sgl_size); > + } > > /* read iaa cap */ > if (idxd->data->type == IDXD_TYPE_IAX && idxd->hw.version >= DEVICE_VERSION_2) > diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h > index 45485ecd7bb6..0401cfc95f27 100644 > --- a/drivers/dma/idxd/registers.h > +++ b/drivers/dma/idxd/registers.h > @@ -385,7 +385,8 @@ union wqcfg { > /* bytes 12-15 */ > u32 max_xfer_shift:5; > u32 max_batch_shift:4; > - u32 rsvd4:23; > + u32 max_sgl_shift:4; > + u32 rsvd4:19; > > /* bytes 16-19 */ > u16 occupancy_inth; > @@ -585,6 +586,15 @@ union evl_status_reg { > > #define IDXD_DSACAP0_OFFSET 0x180 > union dsacap0_reg { > + struct { > + u64 max_sgl_shift:4; > + u64 max_gr_block_shift:4; > + u64 ops_inter_domain:7; > + u64 rsvd1:17; > + u64 sgl_formats:16; > + u64 max_sg_process:8; > + u64 rsvd2:8; > + }; > u64 bits; > }; >
© 2016 - 2025 Red Hat, Inc.