FAILED: patch "[PATCH] crypto: octeontx2 - Fix address alignment on CN10K A0/A1 and" failed to apply to 6.6-stable tree

[<gregkh@linuxfoundation.org>]

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 2e13163b43e6bb861182ea999a80dd1d893c0cbf
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2025082142-trend-rind-de4e@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 2e13163b43e6bb861182ea999a80dd1d893c0cbf Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <bbhushan2@marvell.com>
Date: Thu, 22 May 2025 15:36:26 +0530
Subject: [PATCH] crypto: octeontx2 - Fix address alignment on CN10K A0/A1 and
 OcteonTX2

octeontx2 crypto driver allocates memory using kmalloc/kzalloc,
and uses this memory for dma (does dma_map_single()). It assumes
that kmalloc/kzalloc will return 128-byte aligned address. But
kmalloc/kzalloc returns 8-byte aligned address after below changes:
  "9382bc44b5f5 arm64: allow kmalloc() caches aligned to the
   smaller cache_line_size()

Memory allocated are used for following purpose:
 - Input data or scatter list address - 8-Byte alignment
 - Output data or gather list address - 8-Byte alignment
 - Completion address - 32-Byte alignment.

This patch ensures all addresses are aligned as mentioned above.

Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Cc: <stable@vger.kernel.org> # v6.5+
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
index e27e849b01df..98de93851ba1 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 {
@@ -417,10 +420,9 @@ 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 +431,54 @@ 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              |
+	 *  ------------------------------------
+	 */
 
-	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);
+	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;
+
+	/* 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 +494,7 @@ 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 +510,10 @@ 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;