@@ -532,6 +532,7 @@ CONFIG_RTE_LIBRTE_PMD_QAT_SYM=n
#
CONFIG_RTE_PMD_QAT_MAX_PCI_DEVICES=48
CONFIG_RTE_PMD_QAT_COMP_SGL_MAX_SEGMENTS=16
+CONFIG_RTE_PMD_QAT_COMP_IM_BUFFER_SIZE=65536
#
# Compile PMD for virtio crypto devices
@@ -95,6 +95,7 @@
/* Max. number of QuickAssist devices which can be attached */
#define RTE_PMD_QAT_MAX_PCI_DEVICES 48
#define RTE_PMD_QAT_COMP_SGL_MAX_SEGMENTS 16
+#define RTE_PMD_QAT_COMP_IM_BUFFER_SIZE 65536
/* virtio crypto defines */
#define RTE_MAX_VIRTIO_CRYPTO 32
@@ -13,3 +13,4 @@ Adler32 = Y
Crc32 = Y
Adler32&Crc32 = Y
Fixed = Y
+Dynamic = Y
@@ -18,11 +18,7 @@ QAT compression PMD has support for:
Compression/Decompression algorithm:
- * DEFLATE
-
-Huffman code type:
-
- * FIXED
+ * DEFLATE - using Fixed and Dynamic Huffman encoding
Window size support:
@@ -36,7 +32,6 @@ Limitations
-----------
* Compressdev level 0, no compression, is not supported.
-* Dynamic Huffman encoding is not yet supported.
* Queue pairs are not thread-safe (that is, within a single queue pair, RX and TX from different lcores is not supported).
* No BSD support as BSD QAT kernel driver not available.
@@ -166,6 +166,11 @@ New Features
Added the new caam job ring driver for NXP platforms. See the
"NXP CAAM JOB RING (caam_jr)" document for more details on this new driver.
+* **Added support for Dynamic Huffman Encoding to Intel QAT comp PMD.**
+
+ The Intel QuickAssist (QAT) compression PMD has been updated with support
+ for Dynamic Huffman Encoding for the Deflate algorithm.
+
* **Added Event Ethernet Tx Adapter.**
Added event ethernet Tx adapter library that provides configuration and
@@ -7,6 +7,7 @@
#include "qat_device.h"
#include "adf_transport_access_macros.h"
#include "qat_sym_pmd.h"
+#include "qat_comp_pmd.h"
/* Hardware device information per generation */
__extension__
@@ -14,15 +15,18 @@ struct qat_gen_hw_data qat_gen_config[] = {
[QAT_GEN1] = {
.dev_gen = QAT_GEN1,
.qp_hw_data = qat_gen1_qps,
+ .comp_num_im_bufs_required = QAT_NUM_INTERM_BUFS_GEN1
},
[QAT_GEN2] = {
.dev_gen = QAT_GEN2,
.qp_hw_data = qat_gen1_qps,
/* gen2 has same ring layout as gen1 */
+ .comp_num_im_bufs_required = QAT_NUM_INTERM_BUFS_GEN2
},
[QAT_GEN3] = {
.dev_gen = QAT_GEN3,
.qp_hw_data = qat_gen3_qps,
+ .comp_num_im_bufs_required = QAT_NUM_INTERM_BUFS_GEN3
},
};
@@ -16,6 +16,12 @@
#define QAT_DEV_NAME_MAX_LEN 64
+enum qat_comp_num_im_buffers {
+ QAT_NUM_INTERM_BUFS_GEN1 = 12,
+ QAT_NUM_INTERM_BUFS_GEN2 = 20,
+ QAT_NUM_INTERM_BUFS_GEN3 = 20
+};
+
/*
* This struct holds all the data about a QAT pci device
* including data about all services it supports.
@@ -72,6 +78,7 @@ struct qat_pci_device {
struct qat_gen_hw_data {
enum qat_device_gen dev_gen;
const struct qat_qp_hw_data (*qp_hw_data)[ADF_MAX_QPS_ON_ANY_SERVICE];
+ enum qat_comp_num_im_buffers comp_num_im_bufs_required;
};
extern struct qat_gen_hw_data qat_gen_config[];
@@ -192,7 +192,7 @@ static void qat_comp_create_req_hdr(struct icp_qat_fw_comn_req_hdr *header,
}
static int qat_comp_create_templates(struct qat_comp_xform *qat_xform,
- const struct rte_memzone *interm_buff_mz __rte_unused,
+ const struct rte_memzone *interm_buff_mz,
const struct rte_comp_xform *xform)
{
struct icp_qat_fw_comp_req *comp_req;
@@ -280,10 +280,20 @@ static int qat_comp_create_templates(struct qat_comp_xform *qat_xform,
ICP_QAT_FW_COMN_CURR_ID_SET(&comp_req->comp_cd_ctrl,
ICP_QAT_FW_SLICE_COMP);
} else if (qat_xform->qat_comp_request_type ==
- QAT_COMP_REQUEST_DYNAMIC_COMP_STATELESS) {
+ QAT_COMP_REQUEST_DYNAMIC_COMP_STATELESS) {
- QAT_LOG(ERR, "Dynamic huffman encoding not supported");
- return -EINVAL;
+ ICP_QAT_FW_COMN_NEXT_ID_SET(&comp_req->comp_cd_ctrl,
+ ICP_QAT_FW_SLICE_XLAT);
+ ICP_QAT_FW_COMN_CURR_ID_SET(&comp_req->comp_cd_ctrl,
+ ICP_QAT_FW_SLICE_COMP);
+
+ ICP_QAT_FW_COMN_NEXT_ID_SET(&comp_req->u2.xlt_cd_ctrl,
+ ICP_QAT_FW_SLICE_DRAM_WR);
+ ICP_QAT_FW_COMN_CURR_ID_SET(&comp_req->u2.xlt_cd_ctrl,
+ ICP_QAT_FW_SLICE_XLAT);
+
+ comp_req->u1.xlt_pars.inter_buff_ptr =
+ interm_buff_mz->phys_addr;
}
#if RTE_LOG_DP_LEVEL >= RTE_LOG_DEBUG
@@ -334,12 +344,6 @@ qat_comp_private_xform_create(struct rte_compressdev *dev,
(struct qat_comp_xform *)*private_xform;
if (xform->type == RTE_COMP_COMPRESS) {
- if (xform->compress.deflate.huffman ==
- RTE_COMP_HUFFMAN_DYNAMIC) {
- QAT_LOG(ERR,
- "QAT device doesn't support dynamic compression");
- return -ENOTSUP;
- }
if (xform->compress.deflate.huffman == RTE_COMP_HUFFMAN_FIXED ||
((xform->compress.deflate.huffman == RTE_COMP_HUFFMAN_DEFAULT)
@@ -347,6 +351,21 @@ qat_comp_private_xform_create(struct rte_compressdev *dev,
qat_xform->qat_comp_request_type =
QAT_COMP_REQUEST_FIXED_COMP_STATELESS;
+ else if ((xform->compress.deflate.huffman ==
+ RTE_COMP_HUFFMAN_DYNAMIC ||
+ xform->compress.deflate.huffman ==
+ RTE_COMP_HUFFMAN_DEFAULT) &&
+ qat->interm_buff_mz != NULL)
+
+ qat_xform->qat_comp_request_type =
+ QAT_COMP_REQUEST_DYNAMIC_COMP_STATELESS;
+
+ else {
+ QAT_LOG(ERR,
+ "IM buffers needed for dynamic deflate. Set size in config file");
+ return -EINVAL;
+ }
+
qat_xform->checksum_type = xform->compress.chksum;
} else {
@@ -15,6 +15,10 @@
#include "icp_qat_fw_comp.h"
#include "icp_qat_fw_la.h"
+#define QAT_64_BYTE_ALIGN_MASK (~0x3f)
+#define QAT_64_BYTE_ALIGN (64)
+#define QAT_NUM_BUFS_IN_IM_SGL 1
+
#define ERR_CODE_QAT_COMP_WRONG_FW -99
enum qat_comp_request_type {
@@ -24,6 +28,15 @@ enum qat_comp_request_type {
REQ_COMP_END
};
+struct array_of_ptrs {
+ phys_addr_t pointer[0];
+};
+
+struct qat_inter_sgl {
+ qat_sgl_hdr;
+ struct qat_flat_buf buffers[QAT_NUM_BUFS_IN_IM_SGL];
+} __rte_packed __rte_cache_aligned;
+
struct qat_comp_sgl {
qat_sgl_hdr;
struct qat_flat_buf buffers[RTE_PMD_QAT_COMP_SGL_MAX_SEGMENTS];
@@ -14,6 +14,7 @@ static const struct rte_compressdev_capabilities qat_comp_gen_capabilities[] = {
RTE_COMP_FF_CRC32_ADLER32_CHECKSUM |
RTE_COMP_FF_SHAREABLE_PRIV_XFORM |
RTE_COMP_FF_HUFFMAN_FIXED |
+ RTE_COMP_FF_HUFFMAN_DYNAMIC |
RTE_COMP_FF_OOP_SGL_IN_SGL_OUT |
RTE_COMP_FF_OOP_SGL_IN_LB_OUT |
RTE_COMP_FF_OOP_LB_IN_SGL_OUT,
@@ -112,7 +113,7 @@ qat_comp_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
/* store a link to the qp in the qat_pci_device */
qat_private->qat_dev->qps_in_use[QAT_SERVICE_COMPRESSION][qp_id]
- = *qp_addr;
+ = *qp_addr;
qp = (struct qat_qp *)*qp_addr;
@@ -135,6 +136,103 @@ qat_comp_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
return ret;
}
+
+#define QAT_IM_BUFFER_DEBUG 0
+static const struct rte_memzone *
+qat_comp_setup_inter_buffers(struct qat_comp_dev_private *comp_dev,
+ uint32_t buff_size)
+{
+ char inter_buff_mz_name[RTE_MEMZONE_NAMESIZE];
+ const struct rte_memzone *memzone;
+ uint8_t *mz_start = NULL;
+ rte_iova_t mz_start_phys = 0;
+ struct array_of_ptrs *array_of_pointers;
+ int size_of_ptr_array;
+ uint32_t full_size;
+ uint32_t offset_of_sgls, offset_of_flat_buffs = 0;
+ int i;
+ int num_im_sgls = qat_gen_config[
+ comp_dev->qat_dev->qat_dev_gen].comp_num_im_bufs_required;
+
+ QAT_LOG(DEBUG, "QAT COMP device %s needs %d sgls",
+ comp_dev->qat_dev->name, num_im_sgls);
+ snprintf(inter_buff_mz_name, RTE_MEMZONE_NAMESIZE,
+ "%s_inter_buff", comp_dev->qat_dev->name);
+ memzone = rte_memzone_lookup(inter_buff_mz_name);
+ if (memzone != NULL) {
+ QAT_LOG(DEBUG, "QAT COMP im buffer memzone created already");
+ return memzone;
+ }
+
+ /* Create a memzone to hold intermediate buffers and associated
+ * meta-data needed by the firmware. The memzone contains:
+ * - a list of num_im_sgls physical pointers to sgls
+ * - the num_im_sgl sgl structures, each pointing to 2 flat buffers
+ * - the flat buffers: num_im_sgl * 2
+ * where num_im_sgls depends on the hardware generation of the device
+ */
+
+ size_of_ptr_array = num_im_sgls * sizeof(phys_addr_t);
+ offset_of_sgls = (size_of_ptr_array + (~QAT_64_BYTE_ALIGN_MASK))
+ & QAT_64_BYTE_ALIGN_MASK;
+ offset_of_flat_buffs =
+ offset_of_sgls + num_im_sgls * sizeof(struct qat_inter_sgl);
+ full_size = offset_of_flat_buffs +
+ num_im_sgls * buff_size * QAT_NUM_BUFS_IN_IM_SGL;
+
+ memzone = rte_memzone_reserve_aligned(inter_buff_mz_name, full_size,
+ comp_dev->compressdev->data->socket_id,
+ RTE_MEMZONE_2MB, QAT_64_BYTE_ALIGN);
+ if (memzone == NULL) {
+ QAT_LOG(ERR, "Can't allocate intermediate buffers"
+ " for device %s", comp_dev->qat_dev->name);
+ return NULL;
+ }
+
+ mz_start = (uint8_t *)memzone->addr;
+ mz_start_phys = memzone->phys_addr;
+ QAT_LOG(DEBUG, "Memzone %s: addr = %p, phys = 0x%"PRIx64
+ ", size required %d, size created %zu",
+ inter_buff_mz_name, mz_start, mz_start_phys,
+ full_size, memzone->len);
+
+ array_of_pointers = (struct array_of_ptrs *)mz_start;
+ for (i = 0; i < num_im_sgls; i++) {
+ uint32_t curr_sgl_offset =
+ offset_of_sgls + i * sizeof(struct qat_inter_sgl);
+ struct qat_inter_sgl *sgl =
+ (struct qat_inter_sgl *)(mz_start + curr_sgl_offset);
+ array_of_pointers->pointer[i] = mz_start_phys + curr_sgl_offset;
+
+ sgl->num_bufs = QAT_NUM_BUFS_IN_IM_SGL;
+ sgl->num_mapped_bufs = 0;
+ sgl->resrvd = 0;
+ sgl->buffers[0].addr = mz_start_phys + offset_of_flat_buffs +
+ ((i * QAT_NUM_BUFS_IN_IM_SGL) * buff_size);
+ sgl->buffers[0].len = buff_size;
+ sgl->buffers[0].resrvd = 0;
+ sgl->buffers[1].addr = mz_start_phys + offset_of_flat_buffs +
+ (((i * QAT_NUM_BUFS_IN_IM_SGL) + 1) * buff_size);
+ sgl->buffers[1].len = buff_size;
+ sgl->buffers[1].resrvd = 0;
+
+#if QAT_IM_BUFFER_DEBUG
+ QAT_LOG(DEBUG, " : phys addr of sgl[%i] in array_of_pointers"
+ "= 0x%"PRIx64, i, array_of_pointers->pointer[i]);
+ QAT_LOG(DEBUG, " : virt address of sgl[%i] = %p", i, sgl);
+ QAT_LOG(DEBUG, " : sgl->buffers[0].addr = 0x%"PRIx64", len=%d",
+ sgl->buffers[0].addr, sgl->buffers[0].len);
+ QAT_LOG(DEBUG, " : sgl->buffers[1].addr = 0x%"PRIx64", len=%d",
+ sgl->buffers[1].addr, sgl->buffers[1].len);
+#endif
+ }
+#if QAT_IM_BUFFER_DEBUG
+ QAT_DP_HEXDUMP_LOG(DEBUG, "IM buffer memzone start:",
+ mz_start, offset_of_flat_buffs + 32);
+#endif
+ return memzone;
+}
+
static struct rte_mempool *
qat_comp_create_xform_pool(struct qat_comp_dev_private *comp_dev,
uint32_t num_elements)
@@ -176,6 +274,12 @@ qat_comp_create_xform_pool(struct qat_comp_dev_private *comp_dev,
static void
_qat_comp_dev_config_clear(struct qat_comp_dev_private *comp_dev)
{
+ /* Free intermediate buffers */
+ if (comp_dev->interm_buff_mz) {
+ rte_memzone_free(comp_dev->interm_buff_mz);
+ comp_dev->interm_buff_mz = NULL;
+ }
+
/* Free private_xform pool */
if (comp_dev->xformpool) {
/* Free internal mempool for private xforms */
@@ -197,6 +301,21 @@ qat_comp_dev_config(struct rte_compressdev *dev,
return -EINVAL;
}
+ if (RTE_PMD_QAT_COMP_IM_BUFFER_SIZE == 0) {
+ QAT_LOG(WARNING,
+ "RTE_PMD_QAT_COMP_IM_BUFFER_SIZE = 0 in config file, so"
+ " QAT device can't be used for Dynamic Deflate. "
+ "Did you really intend to do this?");
+ } else {
+ comp_dev->interm_buff_mz =
+ qat_comp_setup_inter_buffers(comp_dev,
+ RTE_PMD_QAT_COMP_IM_BUFFER_SIZE);
+ if (comp_dev->interm_buff_mz == NULL) {
+ ret = -ENOMEM;
+ goto error_out;
+ }
+ }
+
comp_dev->xformpool = qat_comp_create_xform_pool(comp_dev,
config->max_nb_priv_xforms);
if (comp_dev->xformpool == NULL) {
@@ -365,6 +484,10 @@ qat_comp_dev_create(struct qat_pci_device *qat_pci_dev)
QAT_LOG(ERR, "Compression PMD not supported on QAT dh895xcc");
return 0;
}
+ if (qat_pci_dev->qat_dev_gen == QAT_GEN3) {
+ QAT_LOG(ERR, "Compression PMD not supported on QAT c4xxx");
+ return 0;
+ }
struct rte_compressdev_pmd_init_params init_params = {
.name = "",