mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mostafa Saleh <smostafa@google.com>
To: linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,  kvmarm@lists.linux.dev,
	iommu@lists.linux.dev
Cc: catalin.marinas@arm.com, will@kernel.org, maz@kernel.org,
	 oliver.upton@linux.dev, joey.gouly@arm.com,
	suzuki.poulose@arm.com,  yuzenghui@huawei.com, joro@8bytes.org,
	jgg@ziepe.ca, mark.rutland@arm.com,  qperret@google.com,
	tabba@google.com, vdonnefort@google.com,
	 sebastianene@google.com, keirf@google.com,
	 Mostafa Saleh <smostafa@google.com>
Subject: [PATCH v8 17/25] iommu/arm-smmu-v3-kvm: Shadow stream table
Date: Tue, 22 Sep 2026 13:12:50 +0000	[thread overview]
Message-ID: <20260922131259.2975334-18-smostafa@google.com> (raw)
In-Reply-To: <20260922131259.2975334-1-smostafa@google.com>

Allocate the shadow stream table per SMMU.
We choose the size of that table to be 1MB which is the
max size used by host in the case of 2 levels.

All the host writes are still passthrough for bisectability, that
is changed next where CFGI commands will be trapped and used to
update the shadow copy that will be used by the HW.

Similar to the command queue, the host stream table is
shared/unshared each time the SMMU is enabled/disabled.

Handling of L2 tables is also done in the next patch when
the shadowing is added.

Signed-off-by: Mostafa Saleh <smostafa@google.com>
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-kvm.c   |  21 ++-
 .../arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h    |  10 ++
 .../iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c  | 122 ++++++++++++++++++
 3 files changed, 152 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-kvm.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-kvm.c
index 28f8b1fba8f7..6b5a93dfbc2b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-kvm.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-kvm.c
@@ -16,6 +16,13 @@
 #include "pkvm/arm-smmu-v3-hyp.h"
 
 #define SMMU_KVM_CMDQ_ORDER		get_order(MAX(SZ_64K, PAGE_SIZE))
+/*
+ * Use the max value of L1 the kernel uses, that also covers the worst case
+ * for linear tables as it is mandatory according to the spec to support 2
+ * lvl tables if SIDSIZE >= 7
+ */
+#define SMMU_KVM_STRTAB_ORDER		(get_order(STRTAB_MAX_L1_ENTRIES * \
+					 sizeof(struct arm_smmu_strtab_l1)))
 
 extern struct pkvm_iommu_ops kvm_nvhe_sym(smmu_ops);
 
@@ -34,6 +41,9 @@ static void kvm_arm_smmu_array_free(void)
 		if (smmu->cmdq.base_dma)
 			free_pages((unsigned long)phys_to_virt(smmu->cmdq.base_dma),
 				   SMMU_KVM_CMDQ_ORDER);
+		if (smmu->strtab_dma)
+			free_pages((unsigned long)phys_to_virt(smmu->strtab_dma),
+				   SMMU_KVM_STRTAB_ORDER);
 	}
 
 	order = get_order(kvm_arm_smmu_count * sizeof(*kvm_arm_smmu_array));
@@ -80,8 +90,8 @@ static int smmuv3_nesting_probe(struct platform_device *pdev)
 {
 	struct hyp_arm_smmu_v3_device *smmu = &kvm_arm_smmu_array[kvm_arm_smmu_cur];
 	struct device *dev = &pdev->dev;
+	void *cmdq_base, *strtab;
 	struct resource *res;
-	void *cmdq_base;
 
 	/* Only device tree, ACPI not supported. */
 	if (!dev->of_node)
@@ -117,6 +127,15 @@ static int smmuv3_nesting_probe(struct platform_device *pdev)
 	smmu->cmdq.base_dma = virt_to_phys(cmdq_base);
 	smmu->cmdq.llq.max_n_shift = SMMU_KVM_CMDQ_ORDER + PAGE_SHIFT - CMDQ_ENT_SZ_SHIFT;
 
+	strtab = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, SMMU_KVM_STRTAB_ORDER);
+	if (!strtab) {
+		free_pages((unsigned long)cmdq_base, SMMU_KVM_CMDQ_ORDER);
+		return -ENOMEM;
+	}
+
+	smmu->strtab_dma = virt_to_phys(strtab);
+	smmu->strtab_size = PAGE_SIZE << SMMU_KVM_STRTAB_ORDER;
+
 	if (of_dma_is_coherent(dev->of_node))
 		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h
index 39afdeffcd63..d4700d3a3c10 100644
--- a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h
+++ b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h
@@ -14,6 +14,8 @@
  * Parameters from the trusted host:
  * @mmio_addr		base address of the SMMU registers
  * @mmio_size		size of the registers resource
+ * @strtab_dma		Phys address of stream table
+ * @strtab_size		Stream table size
  *
  * Other members are filled and used at runtime by the SMMU driver.
  * @base		Virtual address of SMMU registers
@@ -27,6 +29,9 @@
  * @cmdq_host		Host view of the CMDQ, only q_base and llq used.
  * @cmdq_max_shift	Max shift for the CMDQ probed from HW.
  * @cr0			Last value of CR0
+ * @host_ste_cfg	Host stream table config
+ * @host_ste_base	Host stream table base
+ * @strtab_cfg		Stream table as seen by HW
  */
 struct hyp_arm_smmu_v3_device {
 	phys_addr_t		mmio_addr;
@@ -48,6 +53,11 @@ struct hyp_arm_smmu_v3_device {
 	struct arm_smmu_queue	cmdq_host;
 	u32			cmdq_max_shift;
 	u32			cr0;
+	dma_addr_t		strtab_dma;
+	size_t			strtab_size;
+	u64			host_ste_cfg;
+	u64			host_ste_base;
+	struct arm_smmu_strtab_cfg strtab_cfg;
 };
 
 extern size_t kvm_nvhe_sym(kvm_hyp_arm_smmu_v3_count);
diff --git a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c
index 8c67e348f4a3..54049b8b1363 100644
--- a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c
@@ -17,6 +17,14 @@
 size_t __ro_after_init kvm_hyp_arm_smmu_v3_count;
 struct hyp_arm_smmu_v3_device *kvm_hyp_arm_smmu_v3_smmus;
 
+/* strtab accessors */
+#define strtab_log2size(smmu)	(FIELD_GET(STRTAB_BASE_CFG_LOG2SIZE, (smmu)->host_ste_cfg))
+#define strtab_size(smmu)	((1UL << strtab_log2size(smmu)) * STRTAB_STE_DWORDS * 8)
+#define strtab_host_base(smmu)	((smmu)->host_ste_base & STRTAB_BASE_ADDR_MASK)
+#define strtab_split(smmu)	(FIELD_GET(STRTAB_BASE_CFG_SPLIT, (smmu)->host_ste_cfg))
+#define strtab_l1_size(smmu)	((1UL << (strtab_log2size(smmu) - strtab_split(smmu))) * \
+				 (sizeof(struct arm_smmu_strtab_l1)))
+
 #define for_each_smmu(smmu) \
 	for ((smmu) = kvm_hyp_arm_smmu_v3_smmus; \
 	     (smmu) != &kvm_hyp_arm_smmu_v3_smmus[kvm_hyp_arm_smmu_v3_count]; \
@@ -64,6 +72,11 @@ static bool is_cmdq_enabled(struct hyp_arm_smmu_v3_device *smmu)
 	return FIELD_GET(CR0_CMDQEN, smmu->cr0);
 }
 
+static bool is_smmu_enabled(struct hyp_arm_smmu_v3_device *smmu)
+{
+	return FIELD_GET(CR0_SMMUEN, smmu->cr0);
+}
+
 /*
  * CMDQ, STE host copies are accessed by the hypervisor, we share them to
  * - Prevent the host from passing protected VM memory.
@@ -197,6 +210,11 @@ static void smmu_deinit_device(struct hyp_arm_smmu_v3_device *smmu)
 	if (smmu->cmdq.base)
 		WARN_ON(__pkvm_hyp_donate_host(smmu->cmdq.base_dma >> PAGE_SHIFT,
 					       PAGE_ALIGN(cmdq_size(&smmu->cmdq)) >> PAGE_SHIFT));
+
+	if (smmu->strtab_cfg.linear.table ||
+	    smmu->strtab_cfg.l2.l1tab)
+		WARN_ON(__pkvm_hyp_donate_host(hyp_phys_to_pfn(smmu->strtab_dma),
+					       smmu->strtab_size >> PAGE_SHIFT));
 	smmu->base = NULL;
 }
 
@@ -269,6 +287,45 @@ static int smmu_init_cmdq(struct hyp_arm_smmu_v3_device *smmu)
 	return 0;
 }
 
+static int smmu_init_strtab(struct hyp_arm_smmu_v3_device *smmu)
+{
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	int ret;
+	u32 reg;
+
+	ret = __pkvm_host_donate_hyp(hyp_phys_to_pfn(smmu->strtab_dma),
+				     smmu->strtab_size >> PAGE_SHIFT);
+	if (ret)
+		return ret;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		unsigned int last_sid_idx =
+			arm_smmu_strtab_l1_idx((1ULL << smmu->sid_bits) - 1);
+
+		cfg->l2.l1tab = hyp_phys_to_virt(smmu->strtab_dma);
+		cfg->l2.l1_dma = smmu->strtab_dma;
+		cfg->l2.num_l1_ents = min(last_sid_idx + 1, STRTAB_MAX_L1_ENTRIES);
+
+		reg = FIELD_PREP(STRTAB_BASE_CFG_FMT,
+				 STRTAB_BASE_CFG_FMT_2LVL) |
+		      FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE,
+				 ilog2(cfg->l2.num_l1_ents) + STRTAB_SPLIT) |
+		      FIELD_PREP(STRTAB_BASE_CFG_SPLIT, STRTAB_SPLIT);
+	} else {
+		cfg->linear.table = hyp_phys_to_virt(smmu->strtab_dma);
+		cfg->linear.ste_dma = smmu->strtab_dma;
+		cfg->linear.num_ents = 1UL << smmu->sid_bits;
+		reg = FIELD_PREP(STRTAB_BASE_CFG_FMT,
+				 STRTAB_BASE_CFG_FMT_LINEAR) |
+		      FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits);
+	}
+
+	writeq_relaxed((smmu->strtab_dma & STRTAB_BASE_ADDR_MASK) | STRTAB_BASE_RA,
+		       smmu->base + ARM_SMMU_STRTAB_BASE);
+	writel_relaxed(reg, smmu->base + ARM_SMMU_STRTAB_BASE_CFG);
+	return 0;
+}
+
 static int smmu_init_device(struct hyp_arm_smmu_v3_device *smmu)
 {
 	unsigned long haddr;
@@ -294,6 +351,10 @@ static int smmu_init_device(struct hyp_arm_smmu_v3_device *smmu)
 	if (ret)
 		goto out_ret;
 
+	ret = smmu_init_strtab(smmu);
+	if (ret)
+		goto out_ret;
+
 	return 0;
 
 out_ret:
@@ -438,6 +499,46 @@ static int smmu_emulate_cmdq_insert(struct hyp_arm_smmu_v3_device *smmu)
 	return ret;
 }
 
+static int smmu_update_ste_shadow(struct hyp_arm_smmu_v3_device *smmu, bool enabled)
+{
+	size_t size;
+	u32 fmt = FIELD_GET(STRTAB_BASE_CFG_FMT, smmu->host_ste_cfg);
+
+	/* Linux doesn't change the fmt nor size of the strtab in the run time. */
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		if ((fmt != STRTAB_BASE_CFG_FMT_2LVL) ||
+		    (strtab_split(smmu) != STRTAB_SPLIT) ||
+		    (strtab_log2size(smmu) > (ilog2(STRTAB_MAX_L1_ENTRIES) + STRTAB_SPLIT)) ||
+		    (strtab_split(smmu) >= strtab_log2size(smmu)))
+			return -EINVAL;
+		size = strtab_l1_size(smmu);
+	} else {
+		if ((fmt != STRTAB_BASE_CFG_FMT_LINEAR) ||
+		    (strtab_log2size(smmu) > smmu->sid_bits))
+			return -EINVAL;
+		size = strtab_size(smmu);
+	}
+
+	if (enabled)
+		return smmu_share_pages(strtab_host_base(smmu), size);
+
+	return smmu_unshare_pages(strtab_host_base(smmu), size);
+}
+
+static void smmu_emulate_enable(struct hyp_arm_smmu_v3_device *smmu)
+{
+	/* Enabling SMMU without CMDQ, means TLB invalidation won't work. */
+	if (WARN_ON(!is_cmdq_enabled(smmu)))
+		return;
+
+	WARN_ON(smmu_update_ste_shadow(smmu, true));
+}
+
+static void smmu_emulate_disable(struct hyp_arm_smmu_v3_device *smmu)
+{
+	WARN_ON(smmu_update_ste_shadow(smmu, false));
+}
+
 static void smmu_emulate_cmdq_enable(struct hyp_arm_smmu_v3_device *smmu)
 {
 	u32 shift = smmu->cmdq_host.q_base & Q_BASE_LOG2SIZE;
@@ -525,7 +626,23 @@ static bool smmu_dabt_device(struct hyp_arm_smmu_v3_device *smmu,
 		}
 	/* Passthrough the register access for bisectability, handled later */
 	case ARM_SMMU_STRTAB_BASE:
+		if (is_write) {
+			/* Must only be written when SMMU_CR0.SMMUEN == 0.*/
+			if (is_smmu_enabled(smmu))
+				break;
+			smmu->host_ste_base = val;
+		}
+		mask = read_write;
+		break;
 	case ARM_SMMU_STRTAB_BASE_CFG:
+		if (is_write) {
+			/* Must only be written when SMMU_CR0.SMMUEN == 0.*/
+			if (is_smmu_enabled(smmu))
+				break;
+			smmu->host_ste_cfg = val;
+		}
+		mask = read_write;
+		break;
 	case ARM_SMMU_GBPA:
 		mask = read_write;
 		break;
@@ -534,12 +651,17 @@ static bool smmu_dabt_device(struct hyp_arm_smmu_v3_device *smmu,
 			break;
 		if (is_write) {
 			bool last_cmdq_en = is_cmdq_enabled(smmu);
+			bool last_smmu_en = is_smmu_enabled(smmu);
 
 			smmu->cr0 = val;
 			if (!last_cmdq_en && is_cmdq_enabled(smmu))
 				smmu_emulate_cmdq_enable(smmu);
 			else if (last_cmdq_en && !is_cmdq_enabled(smmu))
 				smmu_emulate_cmdq_disable(smmu);
+			if (!last_smmu_en && is_smmu_enabled(smmu))
+				smmu_emulate_enable(smmu);
+			else if (last_smmu_en && !is_smmu_enabled(smmu))
+				smmu_emulate_disable(smmu);
 		}
 		mask = read_write;
 		break;
-- 
2.55.0.1082.g2b9226bbc0-goog


  parent reply	other threads:[~2026-09-22 13:13 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-22 13:12 [PATCH v8 00/25] KVM: arm64: SMMUv3 driver for pKVM (trap and emulate) Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 01/25] KVM: arm64: Donate MMIO to the hypervisor Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 02/25] iommu/arm-smmu-v3: Move Queue and STE functions to header Mostafa Saleh
2026-09-22 18:23   ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 03/25] iommu/arm-smmu-v3: Introduce RangeInval encoding helpers Mostafa Saleh
2026-09-22 18:45   ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 04/25] iommu/arm-smmu-v3: Move IDR parsing to common functions Mostafa Saleh
2026-09-22 19:45   ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 05/25] iommu/arm-smmu-v3: Move hitless machinery to common code Mostafa Saleh
2026-09-22 19:59   ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 06/25] KVM: arm64: iommu: Introduce IOMMU driver infrastructure Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 07/25] KVM: arm64: iommu: Shadow host stage-2 page table Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 08/25] KVM: arm64: iommu: Add memory pool Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 09/25] KVM: arm64: iommu: Support DABT for IOMMU Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 10/25] iommu/arm-smmu-v3-kvm: Add SMMUv3 driver Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 11/25] iommu/arm-smmu-v3-kvm: Add the kernel driver Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 12/25] iommu/arm-smmu-v3-kvm: Probe SMMU HW Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 13/25] iommu/arm-smmu-v3-kvm: Add MMIO emulation Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 14/25] iommu/arm-smmu-v3-kvm: Shadow the command queue Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 15/25] iommu/arm-smmu-v3-kvm: Add CMDQ functions Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 16/25] iommu/arm-smmu-v3-kvm: Emulate CMDQ for host Mostafa Saleh
2026-09-22 13:12 ` Mostafa Saleh [this message]
2026-09-22 13:12 ` [PATCH v8 18/25] iommu/arm-smmu-v3-kvm: Shadow STEs Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 19/25] iommu/arm-smmu-v3-kvm: Share other queues Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 20/25] iommu/arm-smmu-v3-kvm: Emulate GBPA Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 21/25] iommu/io-pgtable-arm: Support io-pgtable-arm in the hypervisor Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 22/25] iommu/arm-smmu-v3-kvm: Shadow the CPU stage-2 page table Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 23/25] iommu/arm-smmu-v3-kvm: Invalidate the SMMU TLBs Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 24/25] iommu/arm-smmu-v3-kvm: Enable nesting Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 25/25] KVM: arm64: Add documentation for pKVM DMA isolation Mostafa Saleh
2026-09-22 18:07 ` [PATCH v8 00/25] KVM: arm64: SMMUv3 driver for pKVM (trap and emulate) Nicolin Chen

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=20260922131259.2975334-18-smostafa@google.com \
    --to=smostafa@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@ziepe.ca \
    --cc=joey.gouly@arm.com \
    --cc=joro@8bytes.org \
    --cc=keirf@google.com \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=oliver.upton@linux.dev \
    --cc=qperret@google.com \
    --cc=sebastianene@google.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tabba@google.com \
    --cc=vdonnefort@google.com \
    --cc=will@kernel.org \
    --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

all inboxes | Powered by JetHome®