[RFC PATCH v4 02/13] iommu/io-pgtable-arm: Add quirk ARM_HD and ARM_BBMLx

[Keqian Zhu <zhukeqian1@huawei.com>]

From: Kunkun Jiang <jiangkunkun@huawei.com>

These features are essential to support dirty log tracking for
SMMU with io-pgtable mapping.

The dirty state information is encoded using the access permission
bits AP[2] (stage 1) or S2AP[1] (stage 2) in conjunction with the
DBM (Dirty Bit Modifier) bit, where DBM means writable and AP[2]/
S2AP[1] means dirty.

When has ARM_HD, we set DBM bit for S1 mapping. As SMMU nested
mode is not upstreamed for now, we just aim to support dirty
log tracking for stage1 with io-pgtable mapping (means not support
SVA).

Co-developed-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
---
 drivers/iommu/io-pgtable-arm.c |  7 ++++++-
 include/linux/io-pgtable.h     | 11 +++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 87def58e79b5..94d790b8ed27 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -72,6 +72,7 @@
 
 #define ARM_LPAE_PTE_NSTABLE		(((arm_lpae_iopte)1) << 63)
 #define ARM_LPAE_PTE_XN			(((arm_lpae_iopte)3) << 53)
+#define ARM_LPAE_PTE_DBM		(((arm_lpae_iopte)1) << 51)
 #define ARM_LPAE_PTE_AF			(((arm_lpae_iopte)1) << 10)
 #define ARM_LPAE_PTE_SH_NS		(((arm_lpae_iopte)0) << 8)
 #define ARM_LPAE_PTE_SH_OS		(((arm_lpae_iopte)2) << 8)
@@ -81,7 +82,7 @@
 
 #define ARM_LPAE_PTE_ATTR_LO_MASK	(((arm_lpae_iopte)0x3ff) << 2)
 /* Ignore the contiguous bit for block splitting */
-#define ARM_LPAE_PTE_ATTR_HI_MASK	(((arm_lpae_iopte)6) << 52)
+#define ARM_LPAE_PTE_ATTR_HI_MASK	(((arm_lpae_iopte)13) << 51)
 #define ARM_LPAE_PTE_ATTR_MASK		(ARM_LPAE_PTE_ATTR_LO_MASK |	\
 					 ARM_LPAE_PTE_ATTR_HI_MASK)
 /* Software bit for solving coherency races */
@@ -379,6 +380,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 					   int prot)
 {
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte pte;
 
 	if (data->iop.fmt == ARM_64_LPAE_S1 ||
@@ -386,6 +388,9 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		pte = ARM_LPAE_PTE_nG;
 		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
 			pte |= ARM_LPAE_PTE_AP_RDONLY;
+		else if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_HD)
+			pte |= ARM_LPAE_PTE_DBM;
+
 		if (!(prot & IOMMU_PRIV))
 			pte |= ARM_LPAE_PTE_AP_UNPRIV;
 	} else {
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 4d40dfa75b55..92274705b772 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -82,6 +82,14 @@ struct io_pgtable_cfg {
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
 	 *	attributes set in the TCR for a non-coherent page-table walker.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_HD: Support hardware management of dirty status.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_BBML1: ARM SMMU supports BBM Level 1 behavior
+	 *	when changing block size.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_BBML2: ARM SMMU supports BBM Level 2 behavior
+	 *	when changing block size.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
@@ -89,6 +97,9 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
 	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA	BIT(6)
+	#define IO_PGTABLE_QUIRK_ARM_HD		BIT(7)
+	#define IO_PGTABLE_QUIRK_ARM_BBML1	BIT(8)
+	#define IO_PGTABLE_QUIRK_ARM_BBML2	BIT(9)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
-- 
2.19.1