From: Anatoly Burakov <anatoly.burakov@intel.com>
To: dev@dpdk.org, Chengwen Feng <fengchengwen@huawei.com>,
Kevin Laatz <kevin.laatz@intel.com>,
Bruce Richardson <bruce.richardson@intel.com>
Cc: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Subject: [PATCH v1 2/3] dma/idxd: implement inter-domain operations
Date: Fri, 11 Aug 2023 16:14:45 +0000 [thread overview]
Message-ID: <10660b2852115b92ccc6cc193c5b693183217a80.1691768110.git.anatoly.burakov@intel.com> (raw)
In-Reply-To: <cover.1691768109.git.anatoly.burakov@intel.com>
Implement inter-domain copy and fill operations defined in the newly
added DMA device API.
Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
doc/guides/prog_guide/dmadev.rst | 4 +
drivers/dma/idxd/idxd_bus.c | 35 +++++++++
drivers/dma/idxd/idxd_common.c | 123 +++++++++++++++++++++++++++----
drivers/dma/idxd/idxd_hw_defs.h | 14 +++-
drivers/dma/idxd/idxd_internal.h | 7 ++
5 files changed, 165 insertions(+), 18 deletions(-)
diff --git a/doc/guides/prog_guide/dmadev.rst b/doc/guides/prog_guide/dmadev.rst
index e4e5196416..c2a957e971 100644
--- a/doc/guides/prog_guide/dmadev.rst
+++ b/doc/guides/prog_guide/dmadev.rst
@@ -126,6 +126,10 @@ destination PASID to perform the operation. When `src_handle` value is set,
Currently, source and destination handles are opaque values the user has to get
from private API's of those DMA device drivers that support the operation.
+List of drivers supporting inter-domain operations:
+
+- Intel(R) IDXD driver
+
Querying Device Statistics
~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/drivers/dma/idxd/idxd_bus.c b/drivers/dma/idxd/idxd_bus.c
index 3b2d4c2b65..787bc4e2d7 100644
--- a/drivers/dma/idxd/idxd_bus.c
+++ b/drivers/dma/idxd/idxd_bus.c
@@ -7,6 +7,7 @@
#include <unistd.h>
#include <sys/mman.h>
#include <libgen.h>
+#include <inttypes.h>
#include <bus_driver.h>
#include <dev_driver.h>
@@ -187,6 +188,31 @@ read_wq_int(struct rte_dsa_device *dev, const char *filename,
return ret;
}
+static int
+read_gen_cap(struct rte_dsa_device *dev, uint64_t *gen_cap)
+{
+ char sysfs_node[PATH_MAX];
+ FILE *f;
+
+ snprintf(sysfs_node, sizeof(sysfs_node), "%s/dsa%d/gen_cap",
+ dsa_get_sysfs_path(), dev->addr.device_id);
+ f = fopen(sysfs_node, "r");
+ if (f == NULL) {
+ IDXD_PMD_ERR("%s(): opening file '%s' failed: %s",
+ __func__, sysfs_node, strerror(errno));
+ return -1;
+ }
+
+ if (fscanf(f, "%" PRIx64, gen_cap) != 1) {
+ IDXD_PMD_ERR("%s(): error reading file '%s': %s",
+ __func__, sysfs_node, strerror(errno));
+ return -1;
+ }
+
+ fclose(f);
+ return 0;
+}
+
static int
read_device_int(struct rte_dsa_device *dev, const char *filename,
int *value)
@@ -219,6 +245,7 @@ idxd_probe_dsa(struct rte_dsa_device *dev)
{
struct idxd_dmadev idxd = {0};
int ret = 0;
+ uint64_t gen_cap;
IDXD_PMD_INFO("Probing device %s on numa node %d",
dev->wq_name, dev->device.numa_node);
@@ -232,6 +259,14 @@ idxd_probe_dsa(struct rte_dsa_device *dev)
idxd.u.bus.dsa_id = dev->addr.device_id;
idxd.sva_support = 1;
+ ret = read_gen_cap(dev, &gen_cap);
+ if (ret) {
+ IDXD_PMD_ERR("Failed to read gen_cap for %s", dev->wq_name);
+ return ret;
+ }
+ if (gen_cap & IDXD_INTERDOM_SUPPORT)
+ idxd.inter_dom_support = 1;
+
idxd.portal = idxd_bus_mmap_wq(dev);
if (idxd.portal == NULL) {
IDXD_PMD_ERR("WQ mmap failed");
diff --git a/drivers/dma/idxd/idxd_common.c b/drivers/dma/idxd/idxd_common.c
index 83d53942eb..ffe8614d16 100644
--- a/drivers/dma/idxd/idxd_common.c
+++ b/drivers/dma/idxd/idxd_common.c
@@ -41,7 +41,57 @@ __idxd_movdir64b(volatile void *dst, const struct idxd_hw_desc *src)
__use_avx2
static __rte_always_inline void
-__submit(struct idxd_dmadev *idxd)
+__idxd_enqcmd(volatile void *dst, const struct idxd_hw_desc *src)
+{
+ asm volatile (".byte 0xf2, 0x0f, 0x38, 0xf8, 0x02"
+ :
+ : "a" (dst), "d" (src)
+ : "memory");
+}
+
+static inline uint32_t
+__idxd_get_inter_dom_flags(const enum rte_idxd_ops op)
+{
+ switch (op) {
+ case idxd_op_memmove:
+ return IDXD_FLAG_SRC_ALT_PASID | IDXD_FLAG_DST_ALT_PASID;
+ case idxd_op_fill:
+ return IDXD_FLAG_DST_ALT_PASID;
+ default:
+ /* no flags needed */
+ return 0;
+ }
+}
+
+static inline uint32_t
+__idxd_get_op_flags(enum rte_idxd_ops op, uint64_t flags, bool inter_dom)
+{
+ uint32_t op_flags = op;
+ uint32_t flag_mask = IDXD_FLAG_FENCE;
+ if (inter_dom) {
+ flag_mask |= __idxd_get_inter_dom_flags(op);
+ op_flags |= idxd_op_inter_dom;
+ }
+ op_flags = op_flags << IDXD_CMD_OP_SHIFT;
+ return op_flags | (flags & flag_mask) | IDXD_FLAG_CACHE_CONTROL;
+}
+
+static inline uint64_t
+__idxd_get_alt_pasid(uint64_t flags, uint64_t src_idpte_id,
+ uint64_t dst_idpte_id)
+{
+ /* hardware is intolerant to inactive fields being non-zero */
+ if (!(flags & RTE_DMA_OP_FLAG_SRC_HANDLE))
+ src_idpte_id = 0;
+ if (!(flags & RTE_DMA_OP_FLAG_DST_HANDLE))
+ dst_idpte_id = 0;
+ return (src_idpte_id << IDXD_CMD_DST_IDPTE_IDX_SHIFT) |
+ (dst_idpte_id << IDXD_CMD_DST_IDPTE_IDX_SHIFT);
+}
+
+__use_avx2
+static __rte_always_inline void
+__submit(struct idxd_dmadev *idxd, const bool use_enqcmd)
{
rte_prefetch1(&idxd->batch_comp_ring[idxd->batch_idx_read]);
@@ -59,7 +109,10 @@ __submit(struct idxd_dmadev *idxd)
desc.completion = comp_addr;
desc.op_flags |= IDXD_FLAG_REQUEST_COMPLETION;
_mm_sfence(); /* fence before writing desc to device */
- __idxd_movdir64b(idxd->portal, &desc);
+ if (use_enqcmd)
+ __idxd_enqcmd(idxd->portal, &desc);
+ else
+ __idxd_movdir64b(idxd->portal, &desc);
} else {
const struct idxd_hw_desc batch_desc = {
.op_flags = (idxd_op_batch << IDXD_CMD_OP_SHIFT) |
@@ -71,7 +124,10 @@ __submit(struct idxd_dmadev *idxd)
.size = idxd->batch_size,
};
_mm_sfence(); /* fence before writing desc to device */
- __idxd_movdir64b(idxd->portal, &batch_desc);
+ if (use_enqcmd)
+ __idxd_enqcmd(idxd->portal, &batch_desc);
+ else
+ __idxd_movdir64b(idxd->portal, &batch_desc);
}
if (++idxd->batch_idx_write > idxd->max_batches)
@@ -93,7 +149,9 @@ __idxd_write_desc(struct idxd_dmadev *idxd,
const rte_iova_t src,
const rte_iova_t dst,
const uint32_t size,
- const uint32_t flags)
+ const uint32_t flags,
+ const uint64_t alt_pasid,
+ const bool use_enqcmd)
{
uint16_t mask = idxd->desc_ring_mask;
uint16_t job_id = idxd->batch_start + idxd->batch_size;
@@ -113,14 +171,14 @@ __idxd_write_desc(struct idxd_dmadev *idxd,
_mm256_store_si256((void *)&idxd->desc_ring[write_idx],
_mm256_set_epi64x(dst, src, comp_addr, op_flags64));
_mm256_store_si256((void *)&idxd->desc_ring[write_idx].size,
- _mm256_set_epi64x(0, 0, 0, size));
+ _mm256_set_epi64x(alt_pasid, 0, 0, size));
idxd->batch_size++;
rte_prefetch0_write(&idxd->desc_ring[write_idx + 1]);
if (flags & RTE_DMA_OP_FLAG_SUBMIT)
- __submit(idxd);
+ __submit(idxd, use_enqcmd);
return job_id;
}
@@ -134,10 +192,26 @@ idxd_enqueue_copy(void *dev_private, uint16_t qid __rte_unused, rte_iova_t src,
* but check it at compile time to be sure.
*/
RTE_BUILD_BUG_ON(RTE_DMA_OP_FLAG_FENCE != IDXD_FLAG_FENCE);
- uint32_t memmove = (idxd_op_memmove << IDXD_CMD_OP_SHIFT) |
- IDXD_FLAG_CACHE_CONTROL | (flags & IDXD_FLAG_FENCE);
- return __idxd_write_desc(dev_private, memmove, src, dst, length,
- flags);
+ uint32_t op_flags = __idxd_get_op_flags(idxd_op_memmove, flags, false);
+ return __idxd_write_desc(dev_private, op_flags, src, dst, length,
+ flags, 0, false);
+}
+
+__use_avx2
+int
+idxd_enqueue_copy_inter_dom(void *dev_private, uint16_t qid __rte_unused, rte_iova_t src,
+ rte_iova_t dst, unsigned int length,
+ uint16_t src_idpte_id, uint16_t dst_idpte_id, uint64_t flags)
+{
+ /* we can take advantage of the fact that the fence flag in dmadev and
+ * DSA are the same, but check it at compile time to be sure.
+ */
+ RTE_BUILD_BUG_ON(RTE_DMA_OP_FLAG_FENCE != IDXD_FLAG_FENCE);
+ uint32_t op_flags = __idxd_get_op_flags(idxd_op_memmove, flags, true);
+ uint64_t alt_pasid = __idxd_get_alt_pasid(flags, src_idpte_id, dst_idpte_id);
+ /* currently, we require inter-domain copies to use enqcmd */
+ return __idxd_write_desc(dev_private, op_flags, src, dst, length,
+ flags, alt_pasid, true);
}
__use_avx2
@@ -145,17 +219,28 @@ int
idxd_enqueue_fill(void *dev_private, uint16_t qid __rte_unused, uint64_t pattern,
rte_iova_t dst, unsigned int length, uint64_t flags)
{
- uint32_t fill = (idxd_op_fill << IDXD_CMD_OP_SHIFT) |
- IDXD_FLAG_CACHE_CONTROL | (flags & IDXD_FLAG_FENCE);
- return __idxd_write_desc(dev_private, fill, pattern, dst, length,
- flags);
+ uint32_t op_flags = __idxd_get_op_flags(idxd_op_fill, flags, false);
+ return __idxd_write_desc(dev_private, op_flags, pattern, dst, length,
+ flags, 0, false);
+}
+
+__use_avx2
+int
+idxd_enqueue_fill_inter_dom(void *dev_private, uint16_t qid __rte_unused,
+ uint64_t pattern, rte_iova_t dst, unsigned int length,
+ uint16_t dst_idpte_id, uint64_t flags)
+{
+ uint32_t op_flags = __idxd_get_op_flags(idxd_op_fill, flags, true);
+ uint64_t alt_pasid = __idxd_get_alt_pasid(flags, 0, dst_idpte_id);
+ return __idxd_write_desc(dev_private, op_flags, pattern, dst, length,
+ flags, alt_pasid, true);
}
__use_avx2
int
idxd_submit(void *dev_private, uint16_t qid __rte_unused)
{
- __submit(dev_private);
+ __submit(dev_private, false);
return 0;
}
@@ -490,6 +575,12 @@ idxd_info_get(const struct rte_dma_dev *dev, struct rte_dma_info *info, uint32_t
};
if (idxd->sva_support)
info->dev_capa |= RTE_DMA_CAPA_SVA;
+
+ if (idxd->inter_dom_support) {
+ info->dev_capa |= RTE_DMA_CAPA_OPS_INTER_DOM;
+ info->controller_id = idxd->u.bus.dsa_id;
+ }
+
return 0;
}
@@ -600,6 +691,8 @@ idxd_dmadev_create(const char *name, struct rte_device *dev,
dmadev->fp_obj->completed_status = idxd_completed_status;
dmadev->fp_obj->burst_capacity = idxd_burst_capacity;
dmadev->fp_obj->dev_private = dmadev->data->dev_private;
+ dmadev->fp_obj->copy_inter_dom = idxd_enqueue_copy_inter_dom;
+ dmadev->fp_obj->fill_inter_dom = idxd_enqueue_fill_inter_dom;
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return 0;
diff --git a/drivers/dma/idxd/idxd_hw_defs.h b/drivers/dma/idxd/idxd_hw_defs.h
index a38540f283..441e9d29a4 100644
--- a/drivers/dma/idxd/idxd_hw_defs.h
+++ b/drivers/dma/idxd/idxd_hw_defs.h
@@ -9,18 +9,24 @@
* Defines used in the data path for interacting with IDXD hardware.
*/
#define IDXD_CMD_OP_SHIFT 24
+#define IDXD_CMD_SRC_IDPTE_IDX_SHIFT 32
+#define IDXD_CMD_DST_IDPTE_IDX_SHIFT 48
enum rte_idxd_ops {
idxd_op_nop = 0,
idxd_op_batch,
idxd_op_drain,
idxd_op_memmove,
- idxd_op_fill
+ idxd_op_fill,
+ idxd_op_inter_dom = 0x20
};
#define IDXD_FLAG_FENCE (1 << 0)
#define IDXD_FLAG_COMPLETION_ADDR_VALID (1 << 2)
#define IDXD_FLAG_REQUEST_COMPLETION (1 << 3)
+#define IDXD_INTERDOM_SUPPORT (1 << 6)
#define IDXD_FLAG_CACHE_CONTROL (1 << 8)
+#define IDXD_FLAG_SRC_ALT_PASID (1 << 16)
+#define IDXD_FLAG_DST_ALT_PASID (1 << 17)
/**
* Hardware descriptor used by DSA hardware, for both bursts and
@@ -42,8 +48,10 @@ struct idxd_hw_desc {
uint16_t intr_handle; /* completion interrupt handle */
- /* remaining 26 bytes are reserved */
- uint16_t reserved[13];
+ /* next 22 bytes are reserved */
+ uint16_t reserved[11];
+ uint16_t src_pasid_hndl; /* pasid handle for source */
+ uint16_t dest_pasid_hndl; /* pasid handle for destination */
} __rte_aligned(64);
#define IDXD_COMP_STATUS_INCOMPLETE 0
diff --git a/drivers/dma/idxd/idxd_internal.h b/drivers/dma/idxd/idxd_internal.h
index cd4177721d..fb999d29f7 100644
--- a/drivers/dma/idxd/idxd_internal.h
+++ b/drivers/dma/idxd/idxd_internal.h
@@ -70,6 +70,7 @@ struct idxd_dmadev {
struct rte_dma_dev *dmadev;
struct rte_dma_vchan_conf qcfg;
uint8_t sva_support;
+ uint8_t inter_dom_support;
uint8_t qid;
union {
@@ -92,8 +93,14 @@ int idxd_info_get(const struct rte_dma_dev *dev, struct rte_dma_info *dev_info,
uint32_t size);
int idxd_enqueue_copy(void *dev_private, uint16_t qid, rte_iova_t src,
rte_iova_t dst, unsigned int length, uint64_t flags);
+int idxd_enqueue_copy_inter_dom(void *dev_private, uint16_t qid, rte_iova_t src,
+ rte_iova_t dst, unsigned int length,
+ uint16_t src_idpte_id, uint16_t dst_idpte_id, uint64_t flags);
int idxd_enqueue_fill(void *dev_private, uint16_t qid, uint64_t pattern,
rte_iova_t dst, unsigned int length, uint64_t flags);
+int idxd_enqueue_fill_inter_dom(void *dev_private, uint16_t qid, uint64_t pattern,
+ rte_iova_t dst, unsigned int length, uint16_t dst_idpte_id,
+ uint64_t flags);
int idxd_submit(void *dev_private, uint16_t qid);
uint16_t idxd_completed(void *dev_private, uint16_t qid, uint16_t max_ops,
uint16_t *last_idx, bool *has_error);
--
2.37.2
next prev parent reply other threads:[~2023-08-11 16:15 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-11 16:14 [PATCH v1 0/3] Add support for inter-domain DMA operations Anatoly Burakov
2023-08-11 16:14 ` [PATCH v1 1/3] dmadev: add inter-domain operations Anatoly Burakov
2023-08-18 8:08 ` [EXT] " Anoob Joseph
2023-10-08 2:33 ` fengchengwen
2023-10-09 5:05 ` Jerin Jacob
2023-10-27 13:46 ` Medvedkin, Vladimir
2023-11-23 5:24 ` Jerin Jacob
2023-08-11 16:14 ` Anatoly Burakov [this message]
2023-08-11 16:14 ` [PATCH v1 3/3] dma/idxd: add API to create and attach to window Anatoly Burakov
2023-08-14 4:39 ` Jerin Jacob
2023-08-14 9:55 ` Burakov, Anatoly
2023-08-15 19:20 ` [EXT] [PATCH v1 0/3] Add support for inter-domain DMA operations Satananda Burla
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=10660b2852115b92ccc6cc193c5b693183217a80.1691768110.git.anatoly.burakov@intel.com \
--to=anatoly.burakov@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=fengchengwen@huawei.com \
--cc=kevin.laatz@intel.com \
--cc=vladimir.medvedkin@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).