Merge tag 'v6.17-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "API:
   - Allow hash drivers without fallbacks (e.g., hardware key)

  Algorithms:
   - Add hmac hardware key support (phmac) on s390
   - Re-enable sha384 in FIPS mode
   - Disable sha1 in FIPS mode
   - Convert zstd to acomp

  Drivers:
   - Lower priority of qat skcipher and aead
   - Convert aspeed to partial block API
   - Add iMX8QXP support in caam
   - Add rate limiting support for GEN6 devices in qat
   - Enable telemetry for GEN6 devices in qat
   - Implement full backlog mode for hisilicon/sec2"

* tag 'v6.17-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (116 commits)
  crypto: keembay - Use min() to simplify ocs_create_linked_list_from_sg()
  crypto: hisilicon/hpre - fix dma unmap sequence
  crypto: qat - make adf_dev_autoreset() static
  crypto: ccp - reduce stack usage in ccp_run_aes_gcm_cmd
  crypto: qat - refactor ring-related debug functions
  crypto: qat - fix seq_file position update in adf_ring_next()
  crypto: qat - fix DMA direction for compression on GEN2 devices
  crypto: jitter - replace ARRAY_SIZE definition with header include
  crypto: engine - remove {prepare,unprepare}_crypt_hardware callbacks
  crypto: engine - remove request batching support
  crypto: qat - flush misc workqueue during device shutdown
  crypto: qat - enable rate limiting feature for GEN6 devices
  crypto: qat - add compression slice count for rate limiting
  crypto: qat - add get_svc_slice_cnt() in device data structure
  crypto: qat - add adf_rl_get_num_svc_aes() in rate limiting
  crypto: qat - relocate service related functions
  crypto: qat - consolidate service enums
  crypto: qat - add decompression service for rate limiting
  crypto: qat - validate service in rate limiting sysfs api
  crypto: hisilicon/sec2 - implement full backlog mode for sec
  ...

1 files changed, 35 insertions, 16 deletions

diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
index 7180944ece50..cc47e361089a 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -1493,11 +1493,13 @@ 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
@@ -1520,22 +1522,28 @@ 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;
@@ -1547,27 +1555,38 @@ 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;
 
 		while (lfs->ops->cpt_get_compcode(result) ==
-						OTX2_CPT_COMPLETION_CODE_INIT)
+						OTX2_CPT_COMPLETION_CODE_INIT) {
 			cpu_relax();
+			udelay(1);
+			timeout--;
+			if (!timeout) {
+				ret = -ENODEV;
+				cptpf->is_eng_caps_discovered = false;
+				dev_warn(&pdev->dev, "Timeout on CPT load_fvc completion poll\n");
+				goto error_no_response;
+			}
+		}
 
 		cptpf->eng_caps[etype].u = be64_to_cpup(rptr);
 	}
-	dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
 	cptpf->is_eng_caps_discovered = true;
 
-free_result:
-	kfree(result);
+error_no_response:
+	dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
+free_rptr:
+	kfree(base);
 lf_cleanup:
 	otx2_cptlf_shutdown(lfs);
 delete_grps: