iommu/io-pgtable-arm: Rationalise TCR handling

Although it's conceptually nice for the io_pgtable_cfg to provide a
standard VMSA TCR value, the reality is that no VMSA-compliant IOMMU
looks exactly like an Arm CPU, and they all have various other TCR
controls which io-pgtable can't be expected to understand. Thus since
there is an expectation that drivers will have to add to the given TCR
value anyway, let's strip it down to just the essentials that are
directly relevant to io-pgtable's inner workings - namely the various
sizes and the walk attributes.

Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: Add missing include of bitfield.h]
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 40 insertions, 58 deletions

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 1c0ec16effbb..a868ce594871 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,40 +100,32 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_32_LPAE_TCR_EAE		(1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1		(1U << 31)
+#define ARM_64_LPAE_VTCR_RES1		(1U << 31)
 
-#define ARM_LPAE_TCR_EPD1		(1 << 23)
-
-#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
-#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
-#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
+#define ARM_LPAE_VTCR_TG0_SHIFT		14
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
 
 #define ARM_LPAE_TCR_SH0_SHIFT		12
-#define ARM_LPAE_TCR_SH0_MASK		0x3
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
 
 #define ARM_LPAE_TCR_ORGN0_SHIFT	10
 #define ARM_LPAE_TCR_IRGN0_SHIFT	8
-#define ARM_LPAE_TCR_RGN_MASK		0x3
 #define ARM_LPAE_TCR_RGN_NC		0
 #define ARM_LPAE_TCR_RGN_WBWA		1
 #define ARM_LPAE_TCR_RGN_WT		2
 #define ARM_LPAE_TCR_RGN_WB		3
 
-#define ARM_LPAE_TCR_SL0_SHIFT		6
-#define ARM_LPAE_TCR_SL0_MASK		0x3
+#define ARM_LPAE_VTCR_SL0_SHIFT		6
+#define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
-#define ARM_LPAE_TCR_SZ_MASK		0xf
-
-#define ARM_LPAE_TCR_PS_SHIFT		16
-#define ARM_LPAE_TCR_PS_MASK		0x7
 
-#define ARM_LPAE_TCR_IPS_SHIFT		32
-#define ARM_LPAE_TCR_IPS_MASK		0x7
+#define ARM_LPAE_VTCR_PS_SHIFT		16
+#define ARM_LPAE_VTCR_PS_MASK		0x7
 
 #define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
 #define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
@@ -792,6 +784,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
@@ -803,58 +796,54 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* TCR */
 	if (cfg->coherent_walk) {
-		reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_IS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
-		reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-
-	/* Disable speculative walks through TTBR1 */
-	reg |= ARM_LPAE_TCR_EPD1;
-	cfg->arm_lpae_s1_cfg.tcr = reg;
+	tcr->tsz = 64ULL - cfg->ias;
 
 	/* MAIRs */
 	reg = (ARM_LPAE_MAIR_ATTR_NC
@@ -915,7 +904,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	/* VTCR */
-	reg = ARM_64_LPAE_S2_TCR_RES1;
+	reg = ARM_64_LPAE_VTCR_RES1;
 	if (cfg->coherent_walk) {
 		reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
 		       (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
@@ -930,45 +919,45 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		reg |= (ARM_LPAE_TCR_TG0_4K << ARM_LPAE_VTCR_TG0_SHIFT);
 		sl++; /* SL0 format is different for 4K granule size */
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		reg |= (ARM_LPAE_TCR_TG0_16K << ARM_LPAE_VTCR_TG0_SHIFT);
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		reg |= (ARM_LPAE_TCR_TG0_64K << ARM_LPAE_VTCR_TG0_SHIFT);
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_VTCR_PS_SHIFT);
 		break;
 	default:
 		goto out_free_data;
 	}
 
 	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
+	reg |= (~sl & ARM_LPAE_VTCR_SL0_MASK) << ARM_LPAE_VTCR_SL0_SHIFT;
 	cfg->arm_lpae_s2_cfg.vtcr = reg;
 
 	/* Allocate pgd pages */
@@ -992,19 +981,12 @@ out_free_data:
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 32 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
-		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
-	}
 
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
 }
 
 static struct io_pgtable *