diff mbox series

[v6,19/25] iommu/arm-smmu-v3: Add support for Hardware Translation Table Update

Message ID 20200430143424.2787566-20-jean-philippe@linaro.org (mailing list archive)
State Superseded, archived
Headers show
Series iommu: Shared Virtual Addressing for SMMUv3 | expand

Commit Message

Jean-Philippe Brucker April 30, 2020, 2:34 p.m. UTC
If the SMMU supports it and the kernel was built with HTTU support, enable
hardware update of access and dirty flags. This is essential for shared
page tables, to reduce the number of access faults on the fault queue.

We can enable HTTU even if CPUs don't support it, because the kernel
always checks for HW dirty bit and updates the PTE flags atomically.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

Comments

Prabhakar Kushwaha May 4, 2020, 2:24 p.m. UTC | #1
Dear Jean,

On Thu, Apr 30, 2020 at 8:11 PM Jean-Philippe Brucker
<jean-philippe@linaro.org> wrote:
>
> If the SMMU supports it and the kernel was built with HTTU support, enable

is there any framework/config for HTTU which must be enabled to use this patch?


> We can enable HTTU even if CPUs don't support it, because the kernel
> always checks for HW dirty bit and updates the PTE flags atomically.
>
I believe, this statement is valid in context of this patch-set only.

One cannot use code snipped to test HTTU because exiting
io-pgtable-arm.c driver doesn't have framework to leverage HTTU
benfits. It by-default sets AF=1 and does not set DBM.

Thanks

--pk
Jean-Philippe Brucker May 4, 2020, 4:35 p.m. UTC | #2
Hi,

On Mon, May 04, 2020 at 07:54:03PM +0530, Prabhakar Kushwaha wrote:
> Dear Jean,
> 
> On Thu, Apr 30, 2020 at 8:11 PM Jean-Philippe Brucker
> <jean-philippe@linaro.org> wrote:
> >
> > If the SMMU supports it and the kernel was built with HTTU support, enable
> 
> is there any framework/config for HTTU which must be enabled to use this patch?
> 
> 
> > We can enable HTTU even if CPUs don't support it, because the kernel
> > always checks for HW dirty bit and updates the PTE flags atomically.
> >
> I believe, this statement is valid in context of this patch-set only.
> 
> One cannot use code snipped to test HTTU because exiting
> io-pgtable-arm.c driver doesn't have framework to leverage HTTU
> benfits. It by-default sets AF=1 and does not set DBM.

Right, this patch only sets the hardware access and dirty flags for SVA
(page tables shared with the CPU through iommu_bind*()), it doesn't enable
anything for iommu_map/unmap(). Although I remember discussing it for VM
migration, I don't know of any effort to use hardware access/dirty bits
outside of SVA.

Thanks,
Jean
diff mbox series

Patch

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index c65937d953b5f..240cd0bc00e62 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -58,6 +58,8 @@ 
 #define IDR0_ASID16			(1 << 12)
 #define IDR0_ATS			(1 << 10)
 #define IDR0_HYP			(1 << 9)
+#define IDR0_HD				(1 << 7)
+#define IDR0_HA				(1 << 6)
 #define IDR0_BTM			(1 << 5)
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF			GENMASK(3, 2)
@@ -309,6 +311,9 @@ 
 #define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
 #define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
 
+#define CTXDESC_CD_0_TCR_HA		(1UL << 43)
+#define CTXDESC_CD_0_TCR_HD		(1UL << 42)
+
 #define CTXDESC_CD_0_AA64		(1UL << 41)
 #define CTXDESC_CD_0_S			(1UL << 44)
 #define CTXDESC_CD_0_R			(1UL << 45)
@@ -660,6 +665,8 @@  struct arm_smmu_device {
 #define ARM_SMMU_FEAT_E2H		(1 << 16)
 #define ARM_SMMU_FEAT_BTM		(1 << 17)
 #define ARM_SMMU_FEAT_SVA		(1 << 18)
+#define ARM_SMMU_FEAT_HA		(1 << 19)
+#define ARM_SMMU_FEAT_HD		(1 << 20)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
@@ -1715,10 +1722,17 @@  static int __arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
 		 * this substream's traffic
 		 */
 	} else { /* (1) and (2) */
+		u64 tcr = cd->tcr;
+
 		cdptr[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
 		cdptr[2] = 0;
 		cdptr[3] = cpu_to_le64(cd->mair);
 
+		if (!(smmu->features & ARM_SMMU_FEAT_HD))
+			tcr &= ~CTXDESC_CD_0_TCR_HD;
+		if (!(smmu->features & ARM_SMMU_FEAT_HA))
+			tcr &= ~CTXDESC_CD_0_TCR_HA;
+
 		/*
 		 * STE is live, and the SMMU might read dwords of this CD in any
 		 * order. Ensure that it observes valid values before reading
@@ -1726,7 +1740,7 @@  static int __arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
 		 */
 		arm_smmu_sync_cd(smmu_domain, ssid, true);
 
-		val = cd->tcr |
+		val = tcr |
 #ifdef __BIG_ENDIAN
 			CTXDESC_CD_0_ENDI |
 #endif
@@ -1965,10 +1979,12 @@  static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 		return old_cd;
 	}
 
+	/* HA and HD will be filtered out later if not supported by the SMMU */
 	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - VA_BITS) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) |
+	      CTXDESC_CD_0_TCR_HA | CTXDESC_CD_0_TCR_HD |
 	      CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
 
 	switch (PAGE_SIZE) {
@@ -4461,6 +4477,12 @@  static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 			smmu->features |= ARM_SMMU_FEAT_E2H;
 	}
 
+	if (reg & (IDR0_HA | IDR0_HD)) {
+		smmu->features |= ARM_SMMU_FEAT_HA;
+		if (reg & IDR0_HD)
+			smmu->features |= ARM_SMMU_FEAT_HD;
+	}
+
 	/*
 	 * If the CPU is using VHE, but the SMMU doesn't support it, the SMMU
 	 * will create TLB entries for NH-EL1 world and will miss the