summaryrefslogtreecommitdiff
path: root/drivers/crypto/marvell
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/crypto/marvell')
-rw-r--r--drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h125
-rw-r--r--drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c35
2 files changed, 116 insertions, 44 deletions
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
index e27e849b01df..90a031421aac 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
@@ -34,6 +34,9 @@
#define SG_COMP_2 2
#define SG_COMP_1 1
+#define OTX2_CPT_DPTR_RPTR_ALIGN 8
+#define OTX2_CPT_RES_ADDR_ALIGN 32
+
union otx2_cpt_opcode {
u16 flags;
struct {
@@ -347,22 +350,48 @@ static inline struct otx2_cpt_inst_info *
cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
gfp_t gfp)
{
- u32 dlen = 0, g_len, sg_len, info_len;
- int align = OTX2_CPT_DMA_MINALIGN;
+ u32 dlen = 0, g_len, s_len, sg_len, info_len;
struct otx2_cpt_inst_info *info;
- u16 g_sz_bytes, s_sz_bytes;
u32 total_mem_len;
int i;
- g_sz_bytes = ((req->in_cnt + 2) / 3) *
- sizeof(struct cn10kb_cpt_sglist_component);
- s_sz_bytes = ((req->out_cnt + 2) / 3) *
- sizeof(struct cn10kb_cpt_sglist_component);
+ /* Allocate memory to meet below alignment requirement:
+ * ------------------------------------
+ * | struct otx2_cpt_inst_info |
+ * | (No alignment required) |
+ * | --------------------------------|
+ * | | padding for ARCH_DMA_MINALIGN |
+ * | | alignment |
+ * |------------------------------------|
+ * | SG List Gather/Input memory |
+ * | Length = multiple of 32Bytes |
+ * | Alignment = 8Byte |
+ * |---------------------------------- |
+ * | SG List Scatter/Output memory |
+ * | Length = multiple of 32Bytes |
+ * | Alignment = 8Byte |
+ * | -------------------------------|
+ * | | padding for 32B alignment |
+ * |------------------------------------|
+ * | Result response memory |
+ * | Alignment = 32Byte |
+ * ------------------------------------
+ */
+
+ info_len = sizeof(*info);
+
+ g_len = ((req->in_cnt + 2) / 3) *
+ sizeof(struct cn10kb_cpt_sglist_component);
+ s_len = ((req->out_cnt + 2) / 3) *
+ sizeof(struct cn10kb_cpt_sglist_component);
+ sg_len = g_len + s_len;
- g_len = ALIGN(g_sz_bytes, align);
- sg_len = ALIGN(g_len + s_sz_bytes, align);
- info_len = ALIGN(sizeof(*info), align);
- total_mem_len = sg_len + info_len + sizeof(union otx2_cpt_res_s);
+ /* Allocate extra memory for SG and response address alignment */
+ total_mem_len = ALIGN(info_len, OTX2_CPT_DPTR_RPTR_ALIGN);
+ total_mem_len += (ARCH_DMA_MINALIGN - 1) &
+ ~(OTX2_CPT_DPTR_RPTR_ALIGN - 1);
+ total_mem_len += ALIGN(sg_len, OTX2_CPT_RES_ADDR_ALIGN);
+ total_mem_len += sizeof(union otx2_cpt_res_s);
info = kzalloc(total_mem_len, gfp);
if (unlikely(!info))
@@ -372,7 +401,8 @@ cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
dlen += req->in[i].size;
info->dlen = dlen;
- info->in_buffer = (u8 *)info + info_len;
+ info->in_buffer = PTR_ALIGN((u8 *)info + info_len, ARCH_DMA_MINALIGN);
+ info->out_buffer = info->in_buffer + g_len;
info->gthr_sz = req->in_cnt;
info->sctr_sz = req->out_cnt;
@@ -384,7 +414,7 @@ cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
}
if (sgv2io_components_setup(pdev, req->out, req->out_cnt,
- &info->in_buffer[g_len])) {
+ info->out_buffer)) {
dev_err(&pdev->dev, "Failed to setup scatter list\n");
goto destroy_info;
}
@@ -401,8 +431,10 @@ cn10k_sgv2_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
* Get buffer for union otx2_cpt_res_s response
* structure and its physical address
*/
- info->completion_addr = info->in_buffer + sg_len;
- info->comp_baddr = info->dptr_baddr + sg_len;
+ info->completion_addr = PTR_ALIGN((info->in_buffer + sg_len),
+ OTX2_CPT_RES_ADDR_ALIGN);
+ info->comp_baddr = ALIGN((info->dptr_baddr + sg_len),
+ OTX2_CPT_RES_ADDR_ALIGN);
return info;
@@ -417,10 +449,9 @@ static inline struct otx2_cpt_inst_info *
otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
gfp_t gfp)
{
- int align = OTX2_CPT_DMA_MINALIGN;
struct otx2_cpt_inst_info *info;
- u32 dlen, align_dlen, info_len;
- u16 g_sz_bytes, s_sz_bytes;
+ u32 dlen, info_len;
+ u16 g_len, s_len;
u32 total_mem_len;
if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT ||
@@ -429,22 +460,54 @@ otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
return NULL;
}
- g_sz_bytes = ((req->in_cnt + 3) / 4) *
- sizeof(struct otx2_cpt_sglist_component);
- s_sz_bytes = ((req->out_cnt + 3) / 4) *
- sizeof(struct otx2_cpt_sglist_component);
+ /* Allocate memory to meet below alignment requirement:
+ * ------------------------------------
+ * | struct otx2_cpt_inst_info |
+ * | (No alignment required) |
+ * | --------------------------------|
+ * | | padding for ARCH_DMA_MINALIGN |
+ * | | alignment |
+ * |------------------------------------|
+ * | SG List Header of 8 Byte |
+ * |------------------------------------|
+ * | SG List Gather/Input memory |
+ * | Length = multiple of 32Bytes |
+ * | Alignment = 8Byte |
+ * |---------------------------------- |
+ * | SG List Scatter/Output memory |
+ * | Length = multiple of 32Bytes |
+ * | Alignment = 8Byte |
+ * | -------------------------------|
+ * | | padding for 32B alignment |
+ * |------------------------------------|
+ * | Result response memory |
+ * | Alignment = 32Byte |
+ * ------------------------------------
+ */
+
+ info_len = sizeof(*info);
+
+ g_len = ((req->in_cnt + 3) / 4) *
+ sizeof(struct otx2_cpt_sglist_component);
+ s_len = ((req->out_cnt + 3) / 4) *
+ sizeof(struct otx2_cpt_sglist_component);
+
+ dlen = g_len + s_len + SG_LIST_HDR_SIZE;
- dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
- align_dlen = ALIGN(dlen, align);
- info_len = ALIGN(sizeof(*info), align);
- total_mem_len = align_dlen + info_len + sizeof(union otx2_cpt_res_s);
+ /* Allocate extra memory for SG and response address alignment */
+ total_mem_len = ALIGN(info_len, OTX2_CPT_DPTR_RPTR_ALIGN);
+ total_mem_len += (ARCH_DMA_MINALIGN - 1) &
+ ~(OTX2_CPT_DPTR_RPTR_ALIGN - 1);
+ total_mem_len += ALIGN(dlen, OTX2_CPT_RES_ADDR_ALIGN);
+ total_mem_len += sizeof(union otx2_cpt_res_s);
info = kzalloc(total_mem_len, gfp);
if (unlikely(!info))
return NULL;
info->dlen = dlen;
- info->in_buffer = (u8 *)info + info_len;
+ info->in_buffer = PTR_ALIGN((u8 *)info + info_len, ARCH_DMA_MINALIGN);
+ info->out_buffer = info->in_buffer + SG_LIST_HDR_SIZE + g_len;
((u16 *)info->in_buffer)[0] = req->out_cnt;
((u16 *)info->in_buffer)[1] = req->in_cnt;
@@ -460,7 +523,7 @@ otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
}
if (setup_sgio_components(pdev, req->out, req->out_cnt,
- &info->in_buffer[8 + g_sz_bytes])) {
+ info->out_buffer)) {
dev_err(&pdev->dev, "Failed to setup scatter list\n");
goto destroy_info;
}
@@ -476,8 +539,10 @@ otx2_sg_info_create(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
* Get buffer for union otx2_cpt_res_s response
* structure and its physical address
*/
- info->completion_addr = info->in_buffer + align_dlen;
- info->comp_baddr = info->dptr_baddr + align_dlen;
+ info->completion_addr = PTR_ALIGN((info->in_buffer + dlen),
+ OTX2_CPT_RES_ADDR_ALIGN);
+ info->comp_baddr = ALIGN((info->dptr_baddr + dlen),
+ OTX2_CPT_RES_ADDR_ALIGN);
return info;
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
index 9095dea2748d..56645b3eb717 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -1491,12 +1491,13 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
union otx2_cpt_opcode opcode;
union otx2_cpt_res_s *result;
union otx2_cpt_inst_s inst;
+ dma_addr_t result_baddr;
dma_addr_t rptr_baddr;
struct pci_dev *pdev;
- u32 len, compl_rlen;
int timeout = 10000;
+ void *base, *rptr;
int ret, etype;
- void *rptr;
+ u32 len;
/*
* We don't get capabilities if it was already done
@@ -1519,22 +1520,28 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
if (ret)
goto delete_grps;
- compl_rlen = ALIGN(sizeof(union otx2_cpt_res_s), OTX2_CPT_DMA_MINALIGN);
- len = compl_rlen + LOADFVC_RLEN;
+ /* Allocate extra memory for "rptr" and "result" pointer alignment */
+ len = LOADFVC_RLEN + ARCH_DMA_MINALIGN +
+ sizeof(union otx2_cpt_res_s) + OTX2_CPT_RES_ADDR_ALIGN;
- result = kzalloc(len, GFP_KERNEL);
- if (!result) {
+ base = kzalloc(len, GFP_KERNEL);
+ if (!base) {
ret = -ENOMEM;
goto lf_cleanup;
}
- rptr_baddr = dma_map_single(&pdev->dev, (void *)result, len,
- DMA_BIDIRECTIONAL);
+
+ rptr = PTR_ALIGN(base, ARCH_DMA_MINALIGN);
+ rptr_baddr = dma_map_single(&pdev->dev, rptr, len, DMA_BIDIRECTIONAL);
if (dma_mapping_error(&pdev->dev, rptr_baddr)) {
dev_err(&pdev->dev, "DMA mapping failed\n");
ret = -EFAULT;
- goto free_result;
+ goto free_rptr;
}
- rptr = (u8 *)result + compl_rlen;
+
+ result = (union otx2_cpt_res_s *)PTR_ALIGN(rptr + LOADFVC_RLEN,
+ OTX2_CPT_RES_ADDR_ALIGN);
+ result_baddr = ALIGN(rptr_baddr + LOADFVC_RLEN,
+ OTX2_CPT_RES_ADDR_ALIGN);
/* Fill in the command */
opcode.s.major = LOADFVC_MAJOR_OP;
@@ -1546,14 +1553,14 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
/* 64-bit swap for microcode data reads, not needed for addresses */
cpu_to_be64s(&iq_cmd.cmd.u);
iq_cmd.dptr = 0;
- iq_cmd.rptr = rptr_baddr + compl_rlen;
+ iq_cmd.rptr = rptr_baddr;
iq_cmd.cptr.u = 0;
for (etype = 1; etype < OTX2_CPT_MAX_ENG_TYPES; etype++) {
result->s.compcode = OTX2_CPT_COMPLETION_CODE_INIT;
iq_cmd.cptr.s.grp = otx2_cpt_get_eng_grp(&cptpf->eng_grps,
etype);
- otx2_cpt_fill_inst(&inst, &iq_cmd, rptr_baddr);
+ otx2_cpt_fill_inst(&inst, &iq_cmd, result_baddr);
lfs->ops->send_cmd(&inst, 1, &cptpf->lfs.lf[0]);
timeout = 10000;
@@ -1576,8 +1583,8 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
error_no_response:
dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
-free_result:
- kfree(result);
+free_rptr:
+ kfree(base);
lf_cleanup:
otx2_cptlf_shutdown(lfs);
delete_grps:
generated by cgit v1.2.3 (git 2.39.0) at 2025-09-02 21:03:31 +0300