linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Keqian Zhu <zhukeqian1@huawei.com>
To: <linux-kernel@vger.kernel.org>,
	<linux-arm-kernel@lists.infradead.org>,
	<iommu@lists.linux-foundation.org>,
	Robin Murphy <robin.murphy@arm.com>,
	"Will Deacon" <will@kernel.org>, Joerg Roedel <joro@8bytes.org>,
	"Jean-Philippe Brucker" <jean-philippe@linaro.org>,
	Lu Baolu <baolu.lu@linux.intel.com>,
	"Yi Sun" <yi.y.sun@linux.intel.com>,
	Tian Kevin <kevin.tian@intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>,
	Kirti Wankhede <kwankhede@nvidia.com>,
	Cornelia Huck <cohuck@redhat.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	<wanghaibin.wang@huawei.com>, <jiangkunkun@huawei.com>,
	<yuzenghui@huawei.com>, <lushenming@huawei.com>
Subject: [RFC PATCH v4 07/13] iommu/arm-smmu-v3: Add support for Hardware Translation Table Update
Date: Fri, 7 May 2021 18:22:05 +0800	[thread overview]
Message-ID: <20210507102211.8836-8-zhukeqian1@huawei.com> (raw)
In-Reply-To: <20210507102211.8836-1-zhukeqian1@huawei.com>

From: Jean-Philippe Brucker <jean-philippe@linaro.org>

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. Normal DMA with io-pgtables doesn't currently use the access or
dirty flags.

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>
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  2 +
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 41 ++++++++++++++++++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  8 ++++
 3 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index bb251cab61f3..ae075e675892 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -121,10 +121,12 @@ static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 	if (err)
 		goto out_free_asid;
 
+	/* HA and HD will be filtered out later if not supported by the SMMU */
 	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) |
 	      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) {
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 54b2f27b81d4..4ac59a89bc76 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1010,10 +1010,17 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 		 * 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
@@ -1021,7 +1028,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 		 */
 		arm_smmu_sync_cd(smmu_domain, ssid, true);
 
-		val = cd->tcr |
+		val = tcr |
 #ifdef __BIG_ENDIAN
 			CTXDESC_CD_0_ENDI |
 #endif
@@ -3242,6 +3249,28 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	return 0;
 }
 
+static void arm_smmu_get_httu(struct arm_smmu_device *smmu, u32 reg)
+{
+	u32 fw_features = smmu->features & (ARM_SMMU_FEAT_HA | ARM_SMMU_FEAT_HD);
+	u32 features = 0;
+
+	switch (FIELD_GET(IDR0_HTTU, reg)) {
+	case IDR0_HTTU_ACCESS_DIRTY:
+		features |= ARM_SMMU_FEAT_HD;
+		fallthrough;
+	case IDR0_HTTU_ACCESS:
+		features |= ARM_SMMU_FEAT_HA;
+	}
+
+	if (smmu->dev->of_node)
+		smmu->features |= features;
+	else if (features != fw_features)
+		/* ACPI IORT sets the HTTU bits */
+		dev_warn(smmu->dev,
+			 "IDR0.HTTU overridden by FW configuration (0x%x)\n",
+			 fw_features);
+}
+
 static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
@@ -3302,6 +3331,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 			smmu->features |= ARM_SMMU_FEAT_E2H;
 	}
 
+	arm_smmu_get_httu(smmu, reg);
+
 	/*
 	 * The coherency feature as set by FW is used in preference to the ID
 	 * register, but warn on mismatch.
@@ -3487,6 +3518,14 @@ static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
 	if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
 		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
 
+	switch (FIELD_GET(ACPI_IORT_SMMU_V3_HTTU_OVERRIDE, iort_smmu->flags)) {
+	case IDR0_HTTU_ACCESS_DIRTY:
+		smmu->features |= ARM_SMMU_FEAT_HD;
+		fallthrough;
+	case IDR0_HTTU_ACCESS:
+		smmu->features |= ARM_SMMU_FEAT_HA;
+	}
+
 	return 0;
 }
 #else
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 46e8c49214a8..3edcd31b046e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -33,6 +33,9 @@
 #define IDR0_ASID16			(1 << 12)
 #define IDR0_ATS			(1 << 10)
 #define IDR0_HYP			(1 << 9)
+#define IDR0_HTTU			GENMASK(7, 6)
+#define IDR0_HTTU_ACCESS		1
+#define IDR0_HTTU_ACCESS_DIRTY		2
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF			GENMASK(3, 2)
 #define IDR0_TTF_AARCH64		2
@@ -285,6 +288,9 @@
 #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)
@@ -605,6 +611,8 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
 #define ARM_SMMU_FEAT_E2H		(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)
-- 
2.19.1


  parent reply	other threads:[~2021-05-07 10:23 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-07 10:21 [RFC PATCH v4 00/13] iommu/smmuv3: Implement hardware dirty log tracking Keqian Zhu
2021-05-07 10:21 ` [RFC PATCH v4 01/13] iommu: Introduce dirty log tracking framework Keqian Zhu
2021-05-08  3:46   ` Lu Baolu
2021-05-08  7:35     ` Keqian Zhu
2021-05-10  1:08       ` Lu Baolu
2021-05-10 11:07         ` Keqian Zhu
2021-05-11  3:12           ` Lu Baolu
2021-05-11  7:40             ` Keqian Zhu
2021-05-12  3:20               ` Lu Baolu
2021-05-12  8:44                 ` Keqian Zhu
2021-05-12 11:36                   ` Lu Baolu
2021-05-13 10:58                     ` Keqian Zhu
2021-05-13 12:02                       ` Lu Baolu
2021-05-14  2:30                         ` Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 02/13] iommu/io-pgtable-arm: Add quirk ARM_HD and ARM_BBMLx Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 03/13] iommu/io-pgtable-arm: Add and realize split_block ops Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 04/13] iommu/io-pgtable-arm: Add and realize merge_page ops Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 05/13] iommu/io-pgtable-arm: Add and realize sync_dirty_log ops Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 06/13] iommu/io-pgtable-arm: Add and realize clear_dirty_log ops Keqian Zhu
2021-05-07 10:22 ` Keqian Zhu [this message]
2021-05-07 10:22 ` [RFC PATCH v4 08/13] iommu/arm-smmu-v3: Enable HTTU for stage1 with io-pgtable mapping Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 09/13] iommu/arm-smmu-v3: Add feature detection for BBML Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 10/13] iommu/arm-smmu-v3: Realize switch_dirty_log iommu ops Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 11/13] iommu/arm-smmu-v3: Realize sync_dirty_log " Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 12/13] iommu/arm-smmu-v3: Realize clear_dirty_log " Keqian Zhu
2021-05-07 10:22 ` [RFC PATCH v4 13/13] iommu/arm-smmu-v3: Realize support_dirty_log " Keqian Zhu
2021-05-17  8:46 ` [RFC PATCH v4 00/13] iommu/smmuv3: Implement hardware dirty log tracking Keqian Zhu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210507102211.8836-8-zhukeqian1@huawei.com \
    --to=zhukeqian1@huawei.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=alex.williamson@redhat.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=cohuck@redhat.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jean-philippe@linaro.org \
    --cc=jiangkunkun@huawei.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kwankhede@nvidia.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lushenming@huawei.com \
    --cc=robin.murphy@arm.com \
    --cc=wanghaibin.wang@huawei.com \
    --cc=will@kernel.org \
    --cc=yi.y.sun@linux.intel.com \
    --cc=yuzenghui@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).