crypto: caam - handle core endianness != caam endianness

There are SoCs like LS1043A where CAAM endianness (BE) does not match
the default endianness of the core (LE).
Moreover, there are requirements for the driver to handle cases like
CPU_BIG_ENDIAN=y on ARM-based SoCs.
This requires for a complete rewrite of the I/O accessors.

PPC-specific accessors - {in,out}_{le,be}XX - are replaced with
generic ones - io{read,write}[be]XX.

Endianness is detected dynamically (at runtime) to allow for
multiplatform kernels, for e.g. running the same kernel image
on LS1043A (BE CAAM) and LS2080A (LE CAAM) armv8-based SoCs.

While here: debugfs entries need to take into consideration the
endianness of the core when displaying data. Add the necessary
glue code so the entries remain the same, but they are properly
read, regardless of the core and/or SEC endianness.

Note: pdb.h fixes only what is currently being used (IPsec).

Reviewed-by: Tudor Ambarus <tudor-dan.ambarus@nxp.com>
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Alex Porosanu <alexandru.porosanu@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 80 insertions, 45 deletions

diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 5ad5f3009ae0..0ec112ee5204 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -15,6 +15,9 @@
 #include "desc_constr.h"
 #include "error.h"
 
+bool caam_little_end;
+EXPORT_SYMBOL(caam_little_end);
+
 /*
  * i.MX targets tend to have clock control subsystems that can
  * enable/disable clocking to our device.
@@ -106,7 +109,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 
 
 	if (ctrlpriv->virt_en == 1) {
-		setbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, 0, DECORSR_JR0);
 
 		while (!(rd_reg32(&ctrl->deco_rsr) & DECORSR_VALID) &&
 		       --timeout)
@@ -115,7 +118,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		timeout = 100000;
 	}
 
-	setbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, 0, DECORR_RQD0ENABLE);
 
 	while (!(rd_reg32(&ctrl->deco_rq) & DECORR_DEN0) &&
 								 --timeout)
@@ -123,12 +126,12 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 
 	if (!timeout) {
 		dev_err(ctrldev, "failed to acquire DECO 0\n");
-		clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+		clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 		return -ENODEV;
 	}
 
 	for (i = 0; i < desc_len(desc); i++)
-		wr_reg32(&deco->descbuf[i], *(desc + i));
+		wr_reg32(&deco->descbuf[i], caam32_to_cpu(*(desc + i)));
 
 	flags = DECO_JQCR_WHL;
 	/*
@@ -139,7 +142,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		flags |= DECO_JQCR_FOUR;
 
 	/* Instruct the DECO to execute it */
-	setbits32(&deco->jr_ctl_hi, flags);
+	clrsetbits_32(&deco->jr_ctl_hi, 0, flags);
 
 	timeout = 10000000;
 	do {
@@ -158,10 +161,10 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		  DECO_OP_STATUS_HI_ERR_MASK;
 
 	if (ctrlpriv->virt_en == 1)
-		clrbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, DECORSR_JR0, 0);
 
 	/* Mark the DECO as free */
-	clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 
 	if (!timeout)
 		return -EAGAIN;
@@ -349,7 +352,7 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	r4tst = &ctrl->r4tst[0];
 
 	/* put RNG4 into program mode */
-	setbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+	clrsetbits_32(&r4tst->rtmctl, 0, RTMCTL_PRGM);
 
 	/*
 	 * Performance-wise, it does not make sense to
@@ -363,7 +366,7 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	      >> RTSDCTL_ENT_DLY_SHIFT;
 	if (ent_delay <= val) {
 		/* put RNG4 into run mode */
-		clrbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+		clrsetbits_32(&r4tst->rtmctl, RTMCTL_PRGM, 0);
 		return;
 	}
 
@@ -381,9 +384,9 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	 * select raw sampling in both entropy shifter
 	 * and statistical checker
 	 */
-	setbits32(&val, RTMCTL_SAMP_MODE_RAW_ES_SC);
+	clrsetbits_32(&val, 0, RTMCTL_SAMP_MODE_RAW_ES_SC);
 	/* put RNG4 into run mode */
-	clrbits32(&val, RTMCTL_PRGM);
+	clrsetbits_32(&val, RTMCTL_PRGM, 0);
 	/* write back the control register */
 	wr_reg32(&r4tst->rtmctl, val);
 }
@@ -406,6 +409,23 @@ int caam_get_era(void)
 }
 EXPORT_SYMBOL(caam_get_era);
 
+#ifdef CONFIG_DEBUG_FS
+static int caam_debugfs_u64_get(void *data, u64 *val)
+{
+	*val = caam64_to_cpu(*(u64 *)data);
+	return 0;
+}
+
+static int caam_debugfs_u32_get(void *data, u64 *val)
+{
+	*val = caam32_to_cpu(*(u32 *)data);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
+#endif
+
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
@@ -504,6 +524,10 @@ static int caam_probe(struct platform_device *pdev)
 		ret = -ENOMEM;
 		goto disable_caam_emi_slow;
 	}
+
+	caam_little_end = !(bool)(rd_reg32(&ctrl->perfmon.status) &
+				  (CSTA_PLEND | CSTA_ALT_PLEND));
+
 	/* Finding the page size for using the CTPR_MS register */
 	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ms);
 	pg_size = (comp_params & CTPR_MS_PG_SZ_MASK) >> CTPR_MS_PG_SZ_SHIFT;
@@ -559,9 +583,9 @@ static int caam_probe(struct platform_device *pdev)
 	}
 
 	if (ctrlpriv->virt_en == 1)
-		setbits32(&ctrl->jrstart, JRSTART_JR0_START |
-			  JRSTART_JR1_START | JRSTART_JR2_START |
-			  JRSTART_JR3_START);
+		clrsetbits_32(&ctrl->jrstart, 0, JRSTART_JR0_START |
+			      JRSTART_JR1_START | JRSTART_JR2_START |
+			      JRSTART_JR3_START);
 
 	if (sizeof(dma_addr_t) == sizeof(u64))
 		if (of_device_is_compatible(nprop, "fsl,sec-v5.0"))
@@ -693,7 +717,7 @@ static int caam_probe(struct platform_device *pdev)
 		ctrlpriv->rng4_sh_init = ~ctrlpriv->rng4_sh_init & RDSTA_IFMASK;
 
 		/* Enable RDB bit so that RNG works faster */
-		setbits32(&ctrl->scfgr, SCFGR_RDBENABLE);
+		clrsetbits_32(&ctrl->scfgr, 0, SCFGR_RDBENABLE);
 	}
 
 	/* NOTE: RTIC detection ought to go here, around Si time */
@@ -719,48 +743,59 @@ static int caam_probe(struct platform_device *pdev)
 	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
 
 	/* Controller-level - performance monitor counters */
+
 	ctrlpriv->ctl_rq_dequeued =
-		debugfs_create_u64("rq_dequeued",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->req_dequeued);
+		debugfs_create_file("rq_dequeued",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->req_dequeued,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_req =
-		debugfs_create_u64("ob_rq_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_req);
+		debugfs_create_file("ob_rq_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_req =
-		debugfs_create_u64("ib_rq_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_req);
+		debugfs_create_file("ib_rq_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_bytes =
-		debugfs_create_u64("ob_bytes_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_bytes);
+		debugfs_create_file("ob_bytes_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_prot_bytes =
-		debugfs_create_u64("ob_bytes_protected",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_prot_bytes);
+		debugfs_create_file("ob_bytes_protected",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_prot_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_bytes =
-		debugfs_create_u64("ib_bytes_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_bytes);
+		debugfs_create_file("ib_bytes_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_valid_bytes =
-		debugfs_create_u64("ib_bytes_validated",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_valid_bytes);
+		debugfs_create_file("ib_bytes_validated",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_valid_bytes,
+				    &caam_fops_u64_ro);
 
 	/* Controller level - global status values */
 	ctrlpriv->ctl_faultaddr =
-		debugfs_create_u64("fault_addr",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultaddr);
+		debugfs_create_file("fault_addr",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultaddr,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultdetail =
-		debugfs_create_u32("fault_detail",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultdetail);
+		debugfs_create_file("fault_detail",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultdetail,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultstatus =
-		debugfs_create_u32("fault_status",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->status);
+		debugfs_create_file("fault_status",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->status,
+				    &caam_fops_u32_ro);
 
 	/* Internal covering keys (useful in non-secure mode only) */
 	ctrlpriv->ctl_kek_wrap.data = &ctrlpriv->ctrl->kek[0];