[PATCH v8 13/25] iommu/arm-smmu-v3-kvm: Add MMIO emulation
From: Mostafa Saleh <smostafa@google.com>
Date: 2026-09-22 13:13:20
Also in:
kvmarm, linux-iommu, lkml
Subsystem:
arm smmu drivers, iommu subsystem, the rest · Maintainers:
Will Deacon, Joerg Roedel, Linus Torvalds
Add data abort handler for the SMMUs, at the moment most registers are just passthrough. In the next patches CMDQ/STE emulation will be added which inserts logic to some register access. Signed-off-by: Mostafa Saleh <smostafa@google.com> --- .../arm/arm-smmu-v3/pkvm/arm-smmu-v3-hyp.h | 14 ++ .../iommu/arm/arm-smmu-v3/pkvm/arm-smmu-v3.c | 159 ++++++++++++++++++ 2 files changed, 173 insertions(+)
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 91177f00fa97..58fa14c239e3 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@@ -4,6 +4,10 @@ #include <asm/kvm_asm.h> +#ifdef __KVM_NVHE_HYPERVISOR__ +#include <nvhe/spinlock.h> +#endif + /* * Parameters from the trusted host: * @mmio_addr base address of the SMMU registers
@@ -14,6 +18,9 @@ * @oas PA size * @pgsize_bitmap Supported page sizes * @sid_bits Max number of SID bits supported + * @lock Lock to protect SMMU emulation + * @hw_lock Lock to protect SMMU HW (as CMDQ) + * Order smmu.lock => host_mmu.lock => smmu.hw_lock */ struct hyp_arm_smmu_v3_device { phys_addr_t mmio_addr;
@@ -24,6 +31,13 @@ struct hyp_arm_smmu_v3_device { unsigned long oas; unsigned long pgsize_bitmap; unsigned int sid_bits; +#ifdef __KVM_NVHE_HYPERVISOR__ + hyp_spinlock_t lock; + hyp_spinlock_t hw_lock; +#else + u32 lock; + u32 hw_lock; +#endif }; 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 f8b7c5406017..7a51cb70205f 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@@ -8,6 +8,7 @@ #include <nvhe/iommu.h> #include <nvhe/mem_protect.h> +#include <nvhe/trap_handler.h> #include "arm-smmu-v3-hyp.h" #include "../arm-smmu-v3.h"
@@ -78,6 +79,9 @@ static int smmu_init_device(struct hyp_arm_smmu_v3_device *smmu) if (!PAGE_ALIGNED(smmu->mmio_addr | smmu->mmio_size)) return -EINVAL; + hyp_spin_lock_init(&smmu->lock); + hyp_spin_lock_init(&smmu->hw_lock); + ret = __pkvm_host_donate_hyp_mmio(hyp_phys_to_pfn(smmu->mmio_addr), smmu->mmio_size >> PAGE_SHIFT, &haddr); if (ret)
@@ -117,6 +121,8 @@ static int smmu_init(void) goto out_reclaim_smmu; } + BUILD_BUG_ON(sizeof(hyp_spinlock_t) != sizeof(u32)); + return 0; out_reclaim_smmu:
@@ -126,6 +132,158 @@ static int smmu_init(void) return ret; } +static bool smmu_dabt_device(struct hyp_arm_smmu_v3_device *smmu, + struct user_pt_regs *regs, + u64 esr, u32 off) +{ + bool is_write = esr & ESR_ELx_WNR; + unsigned int len = BIT((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); + int rd = (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; + const u64 read_write = -1ULL; + const u64 no_access = 0; + u64 mask = no_access; + const u64 read_only = is_write ? no_access : read_write; + bool is_xzr = (rd == 31); + u64 val = is_xzr ? 0 : regs->regs[rd]; + + switch (off) { + case ARM_SMMU_IDR0: + if (len != sizeof(u32)) + break; + /* + * Clear stage-2 support, hide MSI to avoid write back to cmdq, + * and hide ATS as it is not emulated or handled in TLB invalidation. + */ + mask = read_only & ~(IDR0_S2P | IDR0_VMID16 | IDR0_MSI | IDR0_HYP | IDR0_ATS); + break; + /* Passthrough the register access for bisectability, handled later */ + case ARM_SMMU_CMDQ_BASE: + case ARM_SMMU_CMDQ_PROD: + case ARM_SMMU_CMDQ_CONS: + case ARM_SMMU_STRTAB_BASE: + case ARM_SMMU_STRTAB_BASE_CFG: + case ARM_SMMU_GBPA: + mask = read_write; + break; + case ARM_SMMU_CR0: + if (len != sizeof(u32)) + break; + mask = read_write; + break; + case ARM_SMMU_CR1: + if (len != sizeof(u32)) + break; + /* Don't mess with shareability/cacheability. */ + if (is_write && + (val != (FIELD_PREP(CR1_TABLE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_TABLE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_TABLE_IC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_QUEUE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_IC, CR1_CACHE_WB)))) + break; + + mask = read_write; + break; + /* Allowed 32 bit registers. */ + case ARM_SMMU_EVTQ_IRQ_CFG1: + case ARM_SMMU_EVTQ_IRQ_CFG2: + case ARM_SMMU_GERROR_IRQ_CFG1: + case ARM_SMMU_GERROR_IRQ_CFG2: + case ARM_SMMU_PRIQ_IRQ_CFG1: + case ARM_SMMU_PRIQ_IRQ_CFG2: + /* These are RES0 as MSI support is hidden. */ + val = 0; + if (!is_write) + goto out_update_regs; + fallthrough; + case ARM_SMMU_EVTQ_PROD + SZ_64K: + case ARM_SMMU_EVTQ_CONS + SZ_64K: + case ARM_SMMU_PRIQ_PROD + SZ_64K: + case ARM_SMMU_PRIQ_CONS + SZ_64K: + case ARM_SMMU_GERRORN: + case ARM_SMMU_IRQ_CTRLACK: + case ARM_SMMU_IRQ_CTRL: + case ARM_SMMU_CR0ACK: + case ARM_SMMU_CR2: + if (len != sizeof(u32)) + break; + mask = read_write; + break; + /* Allowed 64 bit registers. */ + case ARM_SMMU_EVTQ_IRQ_CFG0: + case ARM_SMMU_PRIQ_IRQ_CFG0: + case ARM_SMMU_GERROR_IRQ_CFG0: + /* These are RES0 as MSI support is hidden. */ + val = 0; + if (!is_write) + goto out_update_regs; + fallthrough; + case ARM_SMMU_EVTQ_BASE: + case ARM_SMMU_PRIQ_BASE: + if (len != sizeof(u64)) + break; + mask = read_write; + break; + /* Allowed RO 32 bit registers. */ + case ARM_SMMU_IIDR: + case ARM_SMMU_IDR5: + case ARM_SMMU_IDR3: + case ARM_SMMU_IDR1: + case ARM_SMMU_GERROR: + if (len != sizeof(u32)) + break; + mask = read_only; + break; + } + + if (WARN_ON(!mask)) + goto out_ret; + + hyp_spin_lock(&smmu->hw_lock); + if (is_write) { + if (len == sizeof(u64)) + writeq_relaxed(val & mask, smmu->base + off); + else + writel_relaxed(val & mask, smmu->base + off); + + hyp_spin_unlock(&smmu->hw_lock); + return true; + } + + if (len == sizeof(u64)) + val = readq_relaxed(smmu->base + off) & mask; + else + val = readl_relaxed(smmu->base + off) & mask; + hyp_spin_unlock(&smmu->hw_lock); +out_update_regs: + /* + * Device might be read sensitive, so do it but ignore writing + * back for xzr. + */ + if (!is_xzr) + regs->regs[rd] = val; + +out_ret: + return true; +} + +static bool smmu_dabt_handler(struct user_pt_regs *regs, u64 esr, u64 addr) +{ + struct hyp_arm_smmu_v3_device *smmu; + bool ret; + + for_each_smmu(smmu) { + if (addr < smmu->mmio_addr || addr >= smmu->mmio_addr + smmu->mmio_size) + continue; + hyp_spin_lock(&smmu->lock); + ret = smmu_dabt_device(smmu, regs, esr, addr - smmu->mmio_addr); + hyp_spin_unlock(&smmu->lock); + return ret; + } + return false; +} + static int smmu_host_stage2_idmap(phys_addr_t start, phys_addr_t end, int prot) { return 0;
@@ -135,4 +293,5 @@ static int smmu_host_stage2_idmap(phys_addr_t start, phys_addr_t end, int prot) struct pkvm_iommu_ops smmu_ops = { .init = smmu_init, .host_stage2_idmap = smmu_host_stage2_idmap, + .dabt_handler = smmu_dabt_handler, };
--
2.55.0.1082.g2b9226bbc0-goog