crypto: octeontx2 - Fix address alignment issue on ucode loading

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()"

Completion address should be 32-Byte alignment when loading
microcode.

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>

Author: Bharat Bhushan

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: