From 8f23f5dba6b4693448144bde4dd6f537543442c2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 27 Oct 2023 08:05:20 +0800 Subject: iommu: Change kconfig around IOMMU_SVA Linus suggested that the kconfig here is confusing: https://lore.kernel.org/all/CAHk-=wgUiAtiszwseM1p2fCJ+sC4XWQ+YN4TanFhUgvUqjr9Xw@mail.gmail.com/ Let's break it into three kconfigs controlling distinct things: - CONFIG_IOMMU_MM_DATA controls if the mm_struct has the additional fields for the IOMMU. Currently only PASID, but later patches store a struct iommu_mm_data * - CONFIG_ARCH_HAS_CPU_PASID controls if the arch needs the scheduling bit for keeping track of the ENQCMD instruction. x86 will select this if IOMMU_SVA is enabled - IOMMU_SVA controls if the IOMMU core compiles in the SVA support code for iommu driver use and the IOMMU exported API This way ARM will not enable CONFIG_ARCH_HAS_CPU_PASID Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20231027000525.1278806-2-tina.zhang@intel.com Signed-off-by: Joerg Roedel --- arch/Kconfig | 5 +++++ arch/x86/Kconfig | 1 + arch/x86/kernel/traps.c | 2 +- 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index f4b210ab0612..3e49f862670e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED config ARCH_HAS_CPU_FINALIZE_INIT bool +# The architecture has a per-task state that includes the mm's PASID +config ARCH_HAS_CPU_PASID + bool + select IOMMU_MM_DATA + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3762f41bb092..68a2ec36a46e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -71,6 +71,7 @@ config X86 select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CPU_PASID if IOMMU_SVA select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c876f1d36a81..2b62dbb3396a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -565,7 +565,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs) */ static bool try_fixup_enqcmd_gp(void) { -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID u32 pasid; /* -- cgit v1.2.3-58-ga151 From 2396046d75d3c0b2cfead852a77efd023f8539dc Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Fri, 27 Oct 2023 08:05:22 +0800 Subject: iommu: Add mm_get_enqcmd_pasid() helper function mm_get_enqcmd_pasid() should be used by architecture code and closely related to learn the PASID value that the x86 ENQCMD operation should use for the mm. For the moment SMMUv3 uses this without any connection to ENQCMD, it will be cleaned up similar to how the prior patch made VT-d use the PASID argument of set_dev_pasid(). The motivation is to replace mm->pasid with an iommu private data structure that is introduced in a later patch. Reviewed-by: Lu Baolu Reviewed-by: Jason Gunthorpe Tested-by: Nicolin Chen Signed-off-by: Tina Zhang Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20231027000525.1278806-4-tina.zhang@intel.com Signed-off-by: Joerg Roedel --- arch/x86/kernel/traps.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 23 +++++++++++++++-------- drivers/iommu/iommu-sva.c | 2 +- include/linux/iommu.h | 12 ++++++++++++ 4 files changed, 29 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2b62dbb3396a..5944d759afe7 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -591,7 +591,7 @@ static bool try_fixup_enqcmd_gp(void) if (!mm_valid_pasid(current->mm)) return false; - pasid = current->mm->pasid; + pasid = mm_get_enqcmd_pasid(current->mm); /* * Did this thread already have its PASID activated? 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 353248ab18e7..05722121f00e 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 @@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, smmu_domain); } - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start, + size); } static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) @@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events, * but disable translation. */ - arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd); + arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm), + &quiet_cd); arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid); - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0); smmu_mn->cleared = true; mutex_unlock(&sva_lock); @@ -325,10 +327,13 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain, spin_lock_irqsave(&smmu_domain->devices_lock, flags); list_for_each_entry(master, &smmu_domain->devices, domain_head) { - ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd); + ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm), + cd); if (ret) { - list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head) - arm_smmu_write_ctx_desc(master, mm->pasid, NULL); + list_for_each_entry_from_reverse( + master, &smmu_domain->devices, domain_head) + arm_smmu_write_ctx_desc( + master, mm_get_enqcmd_pasid(mm), NULL); break; } } @@ -358,7 +363,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn) list_del(&smmu_mn->list); - arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL); + arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm), + NULL); /* * If we went through clear(), we've already invalidated, and no @@ -366,7 +372,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn) */ if (!smmu_mn->cleared) { arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid); - arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, + 0); } /* Frees smmu_mn */ diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index b78671a8a914..4a2f5699747f 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -141,7 +141,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle) { struct iommu_domain *domain = handle->domain; - return domain->mm->pasid; + return mm_get_enqcmd_pasid(domain->mm); } EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index cd3f398095bf..4fb239c6ca8d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1346,6 +1346,12 @@ static inline bool mm_valid_pasid(struct mm_struct *mm) { return mm->pasid != IOMMU_PASID_INVALID; } + +static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) +{ + return mm->pasid; +} + void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); @@ -1368,6 +1374,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) } static inline void mm_pasid_init(struct mm_struct *mm) {} static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } + +static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) +{ + return IOMMU_PASID_INVALID; +} + static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ -- cgit v1.2.3-58-ga151 From 4720287c7bf76e59d19d4dfbdc3f54eeea6fd46b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 7 Dec 2023 14:03:08 -0400 Subject: iommu: Remove struct iommu_ops *iommu from arch_setup_dma_ops() This is not being used to pass ops, it is just a way to tell if an iommu driver was probed. These days this can be detected directly via device_iommu_mapped(). Call device_iommu_mapped() in the two places that need to check it and remove the iommu parameter everywhere. Reviewed-by: Jerry Snitselaar Reviewed-by: Lu Baolu Reviewed-by: Moritz Fischer Acked-by: Christoph Hellwig Acked-by: Rob Herring Tested-by: Hector Martin Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com Signed-off-by: Joerg Roedel --- arch/arc/mm/dma.c | 2 +- arch/arm/mm/dma-mapping-nommu.c | 2 +- arch/arm/mm/dma-mapping.c | 10 +++++----- arch/arm64/mm/dma-mapping.c | 4 ++-- arch/mips/mm/dma-noncoherent.c | 2 +- arch/riscv/mm/dma-noncoherent.c | 2 +- drivers/acpi/scan.c | 3 +-- drivers/hv/hv_common.c | 2 +- drivers/of/device.c | 2 +- include/linux/dma-map-ops.h | 4 ++-- 10 files changed, 16 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 2a7fbbb83b70..197707bc7658 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, * Plug in direct dma map ops. */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { /* * IOC hardware snoops all DMA traffic keeping the caches consistent diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index cfd9c933d2f0..b94850b57995 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { if (IS_ENABLED(CONFIG_CPU_V7M)) { /* diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 5409225b4abc..6c359a3af8d9 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1713,7 +1713,7 @@ void arm_iommu_detach_device(struct device *dev) EXPORT_SYMBOL_GPL(arm_iommu_detach_device); static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { struct dma_iommu_mapping *mapping; @@ -1748,7 +1748,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) #else static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { } @@ -1757,7 +1757,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { } #endif /* CONFIG_ARM_DMA_USE_IOMMU */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { /* * Due to legacy code that sets the ->dma_coherent flag from a bus @@ -1776,8 +1776,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, if (dev->dma_ops) return; - if (iommu) - arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent); + if (device_iommu_mapped(dev)) + arm_setup_iommu_dma_ops(dev, dma_base, size, coherent); xen_setup_dma_ops(dev); dev->archdata.dma_ops_setup = true; diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..61886e43e3a1 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev) #endif void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { int cls = cache_line_size_of_cpu(); @@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, ARCH_DMA_MINALIGN, cls); dev->dma_coherent = coherent; - if (iommu) + if (device_iommu_mapped(dev)) iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1); xen_setup_dma_ops(dev); diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index 3c4fc97b9f39..0f3cec663a12 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { dev->dma_coherent = coherent; } diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index 4e4e469b8dd6..843107f834b2 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size) } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN, TAINT_CPU_OUT_OF_SPEC, diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 02bb2cce423f..444a0b3c72f2 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1641,8 +1641,7 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; - arch_setup_dma_ops(dev, 0, U64_MAX, - iommu, attr == DEV_DMA_COHERENT); + arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT); return 0; } diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 4372f5d146ab..0285a74363b3 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent) * Hyper-V does not offer a vIOMMU in the guest * VM, so pass 0/NULL for the IOMMU settings */ - arch_setup_dma_ops(dev, 0, 0, NULL, coherent); + arch_setup_dma_ops(dev, 0, 0, coherent); } EXPORT_SYMBOL_GPL(hv_setup_dma_ops); diff --git a/drivers/of/device.c b/drivers/of/device.c index 1ca42ad9dd15..65c71be71a8d 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -193,7 +193,7 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, dev_dbg(dev, "device is%sbehind an iommu\n", iommu ? " " : " not "); - arch_setup_dma_ops(dev, dma_start, size, iommu, coherent); + arch_setup_dma_ops(dev, dma_start, size, coherent); if (!iommu) of_dma_set_restricted_buffer(dev, np); diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index a52e508d1869..e9cc317e9d7d 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -427,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent); + bool coherent); #else static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, const struct iommu_ops *iommu, bool coherent) + u64 size, bool coherent) { } #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ -- cgit v1.2.3-58-ga151