[PATCH v7 22/24] iommu/arm-smmu-v3-kvm: Shadow the CPU stage-2 page table

From: Mostafa Saleh

Date: Wed Jul 15 2026 - 08:03:04 EST


Based on the callbacks from the hypervisor, update the SMMUv3
Identity mapped page table.

Signed-off-by: Mostafa Saleh <smostafa@xxxxxxxxxx>
---
.../iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c | 249 +++++++++++++++++-
.../iommu/arm/arm-smmu-v3/pkvm/arm_smmu_v3.h | 2 +
2 files changed, 249 insertions(+), 2 deletions(-)

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 45dbab1b18ad..f30757dd9b11 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
@@ -13,6 +13,9 @@

#include "arm_smmu_v3.h"

+#include <linux/io-pgtable.h>
+#include "../../../io-pgtable-arm.h"
+
size_t __ro_after_init kvm_hyp_arm_smmu_v3_count;
struct hyp_arm_smmu_v3_device *kvm_hyp_arm_smmu_v3_smmus;

@@ -64,6 +67,9 @@ struct hyp_arm_smmu_v3_device *kvm_hyp_arm_smmu_v3_smmus;
__ret; \
})

+/* Protected by host_mmu.lock from core code. */
+static struct io_pgtable *idmap_pgtable;
+
static bool is_cmdq_enabled(struct hyp_arm_smmu_v3_device *smmu)
{
return FIELD_GET(CR0_CMDQEN, smmu->cr0);
@@ -211,7 +217,6 @@ static int smmu_sync_cmd(struct hyp_arm_smmu_v3_device *smmu)
smmu_cmdq_empty(&smmu->cmdq));
}

-__maybe_unused
static int smmu_send_cmd(struct hyp_arm_smmu_v3_device *smmu,
struct arm_smmu_cmd *cmd)
{
@@ -224,6 +229,69 @@ static int smmu_send_cmd(struct hyp_arm_smmu_v3_device *smmu,
return smmu_sync_cmd(smmu);
}

+static void __smmu_add_cmd(void *__opaque, struct arm_smmu_cmdq_batch *unused,
+ struct arm_smmu_cmd *cmd)
+{
+ struct hyp_arm_smmu_v3_device *smmu = (struct hyp_arm_smmu_v3_device *)__opaque;
+
+ WARN_ON(smmu_add_cmd(smmu, cmd));
+}
+
+static int smmu_tlb_inv_range_smmu(struct hyp_arm_smmu_v3_device *smmu,
+ struct arm_smmu_cmd *cmd,
+ unsigned long iova, size_t size, size_t granule,
+ bool leaf)
+{
+ arm_smmu_tlb_inv_build(cmd, iova, size, granule,
+ PAGE_SHIFT, smmu->features & ARM_SMMU_FEAT_RANGE_INV,
+ smmu, leaf, __smmu_add_cmd, NULL);
+ return smmu_sync_cmd(smmu);
+}
+
+static void smmu_tlb_inv_range(unsigned long iova, size_t size, size_t granule,
+ bool leaf)
+{
+ struct arm_smmu_cmd cmd_s1 = arm_smmu_make_cmd_op(CMDQ_OP_TLBI_NH_ALL);
+ struct hyp_arm_smmu_v3_device *smmu;
+
+ for_each_smmu(smmu) {
+ struct arm_smmu_cmd cmd = arm_smmu_make_cmd_op(CMDQ_OP_TLBI_S2_IPA);
+
+ hyp_spin_lock(&smmu->hw_lock);
+ /*
+ * Don't bother if SMMU is disabled, this would be useful for the case
+ * when RPM is supported to avoid touching the SMMU MMIO when disabled.
+ * The hypervisor also asserts CMDQEN is enabled before the SMMU is
+ * enabled. As otherwise the host can prevent the hypervisor from doing
+ * TLB invalidations.
+ * When the SMMU is re-enabled the hypervisor clean the TLBs.
+ */
+ if (smmu->active) {
+ WARN_ON(smmu_tlb_inv_range_smmu(smmu, &cmd, iova, size, granule, leaf));
+ WARN_ON(smmu_send_cmd(smmu, &cmd_s1));
+ }
+ hyp_spin_unlock(&smmu->hw_lock);
+ }
+}
+
+static void smmu_tlb_flush_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+ smmu_tlb_inv_range(iova, size, granule, false);
+}
+
+static void smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule,
+ void *cookie)
+{
+ smmu_tlb_inv_range(iova, granule, granule, true);
+}
+
+static const struct iommu_flush_ops smmu_tlb_ops = {
+ .tlb_flush_walk = smmu_tlb_flush_walk,
+ .tlb_add_page = smmu_tlb_add_page,
+};
+
/* Put the device in a state that can be probed by the host driver. */
static void smmu_deinit_device(struct hyp_arm_smmu_v3_device *smmu)
{
@@ -477,6 +545,38 @@ static int smmu_init_device(struct hyp_arm_smmu_v3_device *smmu)
return ret;
}

+static int smmu_init_pgt(void)
+{
+ /* Default values overridden based on SMMUs common features. */
+ struct io_pgtable_cfg cfg = (struct io_pgtable_cfg) {
+ .tlb = &smmu_tlb_ops,
+ .pgsize_bitmap = -1,
+ .ias = 48,
+ .oas = 48,
+ .coherent_walk = true,
+ .quirks = IO_PGTABLE_QUIRK_NO_WARN,
+ };
+ struct hyp_arm_smmu_v3_device *smmu;
+ struct io_pgtable_ops *ops;
+
+ for_each_smmu(smmu) {
+ cfg.ias = min(cfg.ias, smmu->oas);
+ cfg.oas = min(cfg.oas, smmu->oas);
+ cfg.pgsize_bitmap &= smmu->pgsize_bitmap;
+ cfg.coherent_walk &= !!(smmu->features & ARM_SMMU_FEAT_COHERENCY);
+ }
+
+ /* At least PAGE_SIZE must be supported by all SMMUs*/
+ if ((cfg.pgsize_bitmap & PAGE_SIZE) == 0)
+ return -EINVAL;
+
+ ops = kvm_alloc_io_pgtable_ops(ARM_64_LPAE_S2, &cfg, NULL);
+ if (!ops)
+ return -ENOMEM;
+ idmap_pgtable = io_pgtable_ops_to_pgtable(ops);
+ return 0;
+}
+
/* Called while is the host is still trusted. */
static int smmu_init(void)
{
@@ -502,7 +602,10 @@ static int smmu_init(void)

BUILD_BUG_ON(sizeof(hyp_spinlock_t) != sizeof(u32));

- return 0;
+ ret = smmu_init_pgt();
+ if (ret)
+ goto out_reclaim_smmu;
+ return ret;

out_reclaim_smmu:
while (smmu != kvm_hyp_arm_smmu_v3_smmus)
@@ -646,6 +749,34 @@ static int smmu_update_ste_shadow(struct hyp_arm_smmu_v3_device *smmu, bool enab
return smmu_unshare_pages(strtab_host_base(smmu), strtab_size);
}

+static int smmu_flush_all_tlb(struct hyp_arm_smmu_v3_device *smmu)
+{
+ int ret;
+ u32 cr0;
+ struct arm_smmu_cmd cmd = arm_smmu_make_cmd_op(CMDQ_OP_TLBI_NSNH_ALL);
+
+ hyp_spin_lock(&smmu->hw_lock);
+ /*
+ * This must be called when the SMMU is getting enabled.
+ * First enable the cmdq and then invalidate the TLB.
+ */
+ cr0 = readl_relaxed(smmu->base + ARM_SMMU_CR0);
+ if (!(cr0 & CR0_CMDQEN)) {
+ cr0 |= CR0_CMDQEN;
+ writel_relaxed(cr0, smmu->base + ARM_SMMU_CR0);
+ ret = smmu_wait(false,
+ readl_relaxed(smmu->base + ARM_SMMU_CR0ACK) == cr0);
+ if (ret) {
+ hyp_spin_unlock(&smmu->hw_lock);
+ return ret;
+ }
+ }
+
+ ret = smmu_send_cmd(smmu, &cmd);
+ hyp_spin_unlock(&smmu->hw_lock);
+ return ret;
+}
+
static void smmu_emulate_enable(struct hyp_arm_smmu_v3_device *smmu)
{
/* Enabling SMMU without CMDQ, means TLB invalidation won't work. */
@@ -653,6 +784,8 @@ static void smmu_emulate_enable(struct hyp_arm_smmu_v3_device *smmu)
return;

WARN_ON(smmu_update_ste_shadow(smmu, true));
+ /* Clean the TLBs each time the SMMU is enabled. */
+ WARN_ON(smmu_flush_all_tlb(smmu));
}

static void smmu_emulate_disable(struct hyp_arm_smmu_v3_device *smmu)
@@ -673,6 +806,13 @@ static void smmu_emulate_cmdq_enable(struct hyp_arm_smmu_v3_device *smmu)

static void smmu_emulate_cmdq_disable(struct hyp_arm_smmu_v3_device *smmu)
{
+ /*
+ * We can not enable the SMMU if the CMDQ is enabled and similarly
+ * we can not disable the CMDQ if the SMMU is enabled, as that can
+ * lead to stale TLBs.
+ */
+ WARN_ON(is_smmu_enabled(smmu));
+
WARN_ON(smmu_unshare_pages(smmu->cmdq_host.base_dma,
cmdq_size(&smmu->cmdq_host)));
}
@@ -936,6 +1076,18 @@ static bool smmu_dabt_device(struct hyp_arm_smmu_v3_device *smmu,
else
writel_relaxed(val & mask, smmu->base + off);

+ /*
+ * Make sure writes to CR0 are immediately observed, that is important
+ * when synchronizing with TLB invalidation as reading CR0 is enough
+ * to deduce the SMMU state, and we have to enforce the ack with the
+ * hw_lock aquired.
+ */
+ if (off == ARM_SMMU_CR0) {
+ WARN_ON(smmu_wait(false,
+ readl_relaxed(smmu->base + ARM_SMMU_CR0ACK) == (val & mask)));
+ smmu->active = !!(val & CR0_CMDQEN);
+ }
+
hyp_spin_unlock(&smmu->hw_lock);
return true;
}
@@ -973,8 +1125,101 @@ static bool smmu_dabt_handler(struct user_pt_regs *regs, u64 esr, u64 addr)
return false;
}

+static size_t smmu_pgsize_idmap(size_t size, u64 paddr, size_t pgsize_bitmap)
+{
+ size_t pgsizes;
+
+ /* Remove page sizes that are larger than the current size */
+ pgsizes = pgsize_bitmap & GENMASK_ULL(__fls(size), 0);
+
+ /* Remove page sizes that the address is not aligned to. */
+ if (likely(paddr))
+ pgsizes &= GENMASK_ULL(__ffs(paddr), 0);
+
+ WARN_ON(!pgsizes);
+
+ /* Return the largest page size that fits. */
+ return BIT(__fls(pgsizes));
+}
+
static int smmu_host_stage2_idmap(phys_addr_t start, phys_addr_t end, int prot)
{
+ size_t pgsize = PAGE_SIZE, pgcount, size;
+ struct io_pgtable *pgtable = idmap_pgtable;
+ int ret = 0;
+
+ end = min(end, BIT(pgtable->cfg.oas));
+ if (start >= end)
+ return 0;
+
+ size = end - start;
+ if (prot) {
+ size_t mapped;
+
+ if (!(prot & IOMMU_MMIO))
+ prot |= IOMMU_CACHE;
+
+ while (size) {
+ mapped = 0;
+ /*
+ * We handle pages size for memory and MMIO differently:
+ * - memory: Map everything with PAGE_SIZE, that is guaranteed to
+ * find memory as we allocated enough pages to cover the entire
+ * memory, we do that as io-pgtable-arm doesn't support
+ * split_blk_unmap logic any more, so we can't break blocks once
+ * mapped to tables.
+ * - MMIO: Unlike memory, pKVM allocate 1G to for all MMIO, while
+ * the MMIO space can be large, as it is assumed to cover the
+ * whole IAS that is not memory, we have to use block mappings,
+ * that is fine for MMIO as it is never donated at the moment,
+ * so we never need to unmap MMIO at the run time triggereing
+ * split block logic.
+ */
+ if (prot & IOMMU_MMIO)
+ pgsize = smmu_pgsize_idmap(size, start, pgtable->cfg.pgsize_bitmap);
+
+ pgcount = size / pgsize;
+ ret = pgtable->ops.map_pages(&pgtable->ops, start, start,
+ pgsize, pgcount, prot, 0, &mapped);
+ size -= mapped;
+ start += mapped;
+
+ if (ret == -EEXIST) {
+ /*
+ * It is possible to get EEXIST when a VM dies with pages
+ * in a shared state.
+ */
+ ret = 0;
+ size -= pgsize;
+ start += pgsize;
+ continue;
+ }
+ /* Map failures doesn't impact security, tolerate it. */
+ if (!mapped || ret)
+ break;
+ }
+ } else {
+ struct iommu_iotlb_gather gather;
+ size_t unmapped;
+
+ while (size) {
+ pgcount = size / pgsize;
+ iommu_iotlb_gather_init(&gather);
+ unmapped = pgtable->ops.unmap_pages(&pgtable->ops, start,
+ pgsize, pgcount, &gather);
+ size -= unmapped;
+ start += unmapped;
+ if (!unmapped)
+ break;
+ }
+ }
+
+ if (ret)
+ return ret;
+
+ if (WARN_ON(size))
+ return -EINVAL;
+
return 0;
}

diff --git a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm_smmu_v3.h b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm_smmu_v3.h
index d96801e433ef..9599809b46fc 100644
--- a/drivers/iommu/arm/arm-smmu-v3/pkvm/arm_smmu_v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/pkvm/arm_smmu_v3.h
@@ -29,6 +29,7 @@
* @cmdq CMDQ as observed by HW
* @cmdq_host Host view of the CMDQ, only q_base and llq used.
* @cr0 Last value of CR0
+ * @active Is SMMU HW cmdq usable, protected by hw_lock
* @host_ste_cfg Host stream table config
* @host_ste_base Host stream table base
* @strtab_cfg Stream table as seen by HW
@@ -55,6 +56,7 @@ struct hyp_arm_smmu_v3_device {
struct arm_smmu_queue cmdq;
struct arm_smmu_queue cmdq_host;
u32 cr0;
+ bool active;
dma_addr_t strtab_dma;
size_t strtab_size;
u64 host_ste_cfg;
--
2.55.0.141.g00534a21ce-goog