diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-25 00:40:13 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-25 00:40:13 +0300 |
| commit | a13de74e476532e32efb06e96acae84c634f0159 (patch) | |
| tree | 2fb1605ea63eccefdcf34ae24b4b096cdf11020f | |
| parent | 8395d932d24a9b4c01ab33ed0b4b2de06328afc2 (diff) | |
| parent | bedd29d793da3312e1350a56245c4971a38d4453 (diff) | |
| download | linux-a13de74e476532e32efb06e96acae84c634f0159.tar.xz | |
Merge tag 'iommu-updates-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
- Consolidate iommu_map/unmap functions.
There have been blocking and atomic variants so far, but that was
problematic as this approach does not scale with required new
variants which just differ in the GFP flags used. So Jason
consolidated this back into single functions that take a GFP
parameter.
- Retire the detach_dev() call-back in iommu_ops
- Arm SMMU updates from Will:
- Device-tree binding updates:
- Cater for three power domains on SM6375
- Document existing compatible strings for Qualcomm SoCs
- Tighten up clocks description for platform-specific
compatible strings
- Enable Qualcomm workarounds for some additional platforms that
need them
- Intel VT-d updates from Lu Baolu:
- Add Intel IOMMU performance monitoring support
- Set No Execute Enable bit in PASID table entry
- Two performance optimizations
- Fix PASID directory pointer coherency
- Fix missed rollbacks in error path
- Cleanups
- Apple t8110 DART support
- Exynos IOMMU:
- Implement better fault handling
- Error handling fixes
- Renesas IPMMU:
- Add device tree bindings for r8a779g0
- AMD IOMMU:
- Various fixes for handling on SNP-enabled systems and
handling of faults with unknown request-ids
- Cleanups and other small fixes
- Various other smaller fixes and cleanups
* tag 'iommu-updates-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (71 commits)
iommu/amd: Skip attach device domain is same as new domain
iommu: Attach device group to old domain in error path
iommu/vt-d: Allow to use flush-queue when first level is default
iommu/vt-d: Fix PASID directory pointer coherency
iommu/vt-d: Avoid superfluous IOTLB tracking in lazy mode
iommu/vt-d: Fix error handling in sva enable/disable paths
iommu/amd: Improve page fault error reporting
iommu/amd: Do not identity map v2 capable device when snp is enabled
iommu: Fix error unwind in iommu_group_alloc()
iommu/of: mark an unused function as __maybe_unused
iommu: dart: DART_T8110_ERROR range should be 0 to 5
iommu/vt-d: Enable IOMMU perfmon support
iommu/vt-d: Add IOMMU perfmon overflow handler support
iommu/vt-d: Support cpumask for IOMMU perfmon
iommu/vt-d: Add IOMMU perfmon support
iommu/vt-d: Support Enhanced Command Interface
iommu/vt-d: Retrieve IOMMU perfmon capability information
iommu/vt-d: Support size of the register set in DRHD
iommu/vt-d: Set No Execute Enable bit in PASID table entry
iommu/vt-d: Remove sva from intel_svm_dev
...
63 files changed, 2493 insertions, 646 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu b/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu new file mode 100644 index 000000000000..d7af4919302e --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu @@ -0,0 +1,37 @@ +What: /sys/bus/event_source/devices/dmar*/format +Date: Jan 2023 +KernelVersion: 6.3 +Contact: Kan Liang <kan.liang@linux.intel.com> +Description: Read-only. Attribute group to describe the magic bits + that go into perf_event_attr.config, + perf_event_attr.config1 or perf_event_attr.config2 for + the IOMMU pmu. (See also + ABI/testing/sysfs-bus-event_source-devices-format). + + Each attribute in this group defines a bit range in + perf_event_attr.config, perf_event_attr.config1, + or perf_event_attr.config2. All supported attributes + are listed below (See the VT-d Spec 4.0 for possible + attribute values):: + + event = "config:0-27" - event ID + event_group = "config:28-31" - event group ID + + filter_requester_en = "config1:0" - Enable Requester ID filter + filter_domain_en = "config1:1" - Enable Domain ID filter + filter_pasid_en = "config1:2" - Enable PASID filter + filter_ats_en = "config1:3" - Enable Address Type filter + filter_page_table_en= "config1:4" - Enable Page Table Level filter + filter_requester_id = "config1:16-31" - Requester ID filter + filter_domain = "config1:32-47" - Domain ID filter + filter_pasid = "config2:0-21" - PASID filter + filter_ats = "config2:24-28" - Address Type filter + filter_page_table = "config2:32-36" - Page Table Level filter + +What: /sys/bus/event_source/devices/dmar*/cpumask +Date: Jan 2023 +KernelVersion: 6.3 +Contact: Kan Liang <kan.liang@linux.intel.com> +Description: Read-only. This file always returns the CPU to which the + IOMMU pmu is bound for access to all IOMMU pmu performance + monitoring events. diff --git a/Documentation/devicetree/bindings/iommu/apple,dart.yaml b/Documentation/devicetree/bindings/iommu/apple,dart.yaml index 06af2bacbe97..903edf85d72e 100644 --- a/Documentation/devicetree/bindings/iommu/apple,dart.yaml +++ b/Documentation/devicetree/bindings/iommu/apple,dart.yaml @@ -24,6 +24,7 @@ properties: compatible: enum: - apple,t8103-dart + - apple,t8110-dart - apple,t6000-dart reg: diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index b28c5c2b0ff2..807cb511fe18 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -36,13 +36,17 @@ properties: - enum: - qcom,qcm2290-smmu-500 - qcom,qdu1000-smmu-500 + - qcom,sa8775p-smmu-500 - qcom,sc7180-smmu-500 - qcom,sc7280-smmu-500 - qcom,sc8180x-smmu-500 - qcom,sc8280xp-smmu-500 - qcom,sdm670-smmu-500 - qcom,sdm845-smmu-500 + - qcom,sdx55-smmu-500 + - qcom,sdx65-smmu-500 - qcom,sm6115-smmu-500 + - qcom,sm6125-smmu-500 - qcom,sm6350-smmu-500 - qcom,sm6375-smmu-500 - qcom,sm8150-smmu-500 @@ -52,14 +56,6 @@ properties: - const: qcom,smmu-500 - const: arm,mmu-500 - - description: Qcom SoCs implementing "arm,mmu-500" (non-qcom implementation) - deprecated: true - items: - - enum: - - qcom,sdx55-smmu-500 - - qcom,sdx65-smmu-500 - - const: arm,mmu-500 - - description: Qcom SoCs implementing "arm,mmu-500" (legacy binding) deprecated: true items: @@ -84,6 +80,7 @@ properties: items: - enum: - qcom,sc7280-smmu-500 + - qcom,sm8150-smmu-500 - qcom,sm8250-smmu-500 - const: qcom,adreno-smmu - const: arm,mmu-500 @@ -201,7 +198,8 @@ properties: maxItems: 7 power-domains: - maxItems: 1 + minItems: 1 + maxItems: 3 nvidia,memory-controller: description: | @@ -366,6 +364,56 @@ allOf: - description: interface clock required to access smmu's registers through the TCU's programming interface. + # Disallow clocks for all other platforms with specific compatibles + - if: + properties: + compatible: + contains: + enum: + - cavium,smmu-v2 + - marvell,ap806-smmu-500 + - nvidia,smmu-500 + - qcom,qcm2290-smmu-500 + - qcom,qdu1000-smmu-500 + - qcom,sa8775p-smmu-500 + - qcom,sc7180-smmu-500 + - qcom,sc8180x-smmu-500 + - qcom,sc8280xp-smmu-500 + - qcom,sdm670-smmu-500 + - qcom,sdm845-smmu-500 + - qcom,sdx55-smmu-500 + - qcom,sdx65-smmu-500 + - qcom,sm6115-smmu-500 + - qcom,sm6125-smmu-500 + - qcom,sm6350-smmu-500 + - qcom,sm6375-smmu-500 + - qcom,sm8350-smmu-500 + - qcom,sm8450-smmu-500 + then: + properties: + clock-names: false + clocks: false + + - if: + properties: + compatible: + contains: + const: qcom,sm6375-smmu-500 + then: + properties: + power-domains: + items: + - description: SNoC MMU TBU RT GDSC + - description: SNoC MMU TBU NRT GDSC + - description: SNoC TURING MMU TBU0 GDSC + + required: + - power-domains + else: + properties: + power-domains: + maxItems: 1 + examples: - |+ /* SMMU with stream matching or stream indexing */ diff --git a/Documentation/devicetree/bindings/iommu/qcom,iommu.txt b/Documentation/devicetree/bindings/iommu/qcom,iommu.txt index 059139abce35..e6cecfd360eb 100644 --- a/Documentation/devicetree/bindings/iommu/qcom,iommu.txt +++ b/Documentation/devicetree/bindings/iommu/qcom,iommu.txt @@ -10,6 +10,7 @@ to non-secure vs secure interrupt line. - compatible : Should be one of: "qcom,msm8916-iommu" + "qcom,msm8953-iommu" Followed by "qcom,msm-iommu-v1". diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml index 26d0a5121f02..72308a4c14e7 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml @@ -49,6 +49,7 @@ properties: - enum: - renesas,ipmmu-r8a779a0 # R-Car V3U - renesas,ipmmu-r8a779f0 # R-Car S4-8 + - renesas,ipmmu-r8a779g0 # R-Car V4H - const: renesas,rcar-gen4-ipmmu-vmsa # R-Car Gen4 reg: diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.yaml b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.yaml index b205215b130d..c680e397cfd2 100644 --- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.yaml +++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.yaml @@ -52,6 +52,30 @@ properties: Address and Length pairs. Specifies regions of memory that are acceptable to allocate from. + iommu-addresses: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: > + A list of phandle and specifier pairs that describe static IO virtual + address space mappings and carveouts associated with a given reserved + memory region. The phandle in the first cell refers to the device for + which the mapping or carveout is to be created. + + The specifier consists of an address/size pair and denotes the IO + virtual address range of the region for the given device. The exact + format depends on the values of the "#address-cells" and "#size-cells" + properties of the device referenced via the phandle. + + When used in combination with a "reg" property, an IOVA mapping is to + be established for this memory region. One example where this can be + useful is to create an identity mapping for physical memory that the + firmware has configured some hardware to access (such as a bootsplash + framebuffer). + + If no "reg" property is specified, the "iommu-addresses" property + defines carveout regions in the IOVA space for the given device. This + can be useful if a certain memory region should not be mapped through + the IOMMU. + no-map: type: boolean description: > @@ -89,12 +113,69 @@ allOf: - no-map oneOf: - - required: - - reg + - oneOf: + - required: + - reg + + - required: + - size + + - oneOf: + # IOMMU reservations + - required: + - iommu-addresses - - required: - - size + # IOMMU mappings + - required: + - reg + - iommu-addresses additionalProperties: true +examples: + - | + / { + compatible = "foo"; + model = "foo"; + + #address-cells = <2>; + #size-cells = <2>; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + adsp_resv: reservation-adsp { + /* + * Restrict IOVA mappings for ADSP buffers to the 512 MiB region + * from 0x40000000 - 0x5fffffff. Anything outside is reserved by + * the ADSP for I/O memory and private memory allocations. + */ + iommu-addresses = <&adsp 0x0 0x00000000 0x00 0x40000000>, + <&adsp 0x0 0x60000000 0xff 0xa0000000>; + }; + + fb: framebuffer@90000000 { + reg = <0x0 0x90000000 0x0 0x00800000>; + iommu-addresses = <&dc0 0x0 0x90000000 0x0 0x00800000>; + }; + }; + + bus@0 { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x0 0x0 0x0 0x40000000>; + + adsp: adsp@2990000 { + reg = <0x2990000 0x2000>; + memory-region = <&adsp_resv>; + }; + + dc0: display@15200000 { + reg = <0x15200000 0x10000>; + memory-region = <&fb>; + }; + }; + }; ... diff --git a/MAINTAINERS b/MAINTAINERS index 02d2d33f507c..88f9a88f4301 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10354,7 +10354,6 @@ L: iommu@lists.linux.dev S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: drivers/iommu/intel/ -F: include/linux/intel-svm.h INTEL IPU3 CSI-2 CIO2 DRIVER M: Yong Zhi <yong.zhi@intel.com> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c135f6e37a00..8bc01071474a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -984,7 +984,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size, len = (j - i) << PAGE_SHIFT; ret = iommu_map(mapping->domain, iova, phys, len, - __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs)); + __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs), + GFP_KERNEL); if (ret < 0) goto fail; iova += len; @@ -1207,7 +1208,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, iova, phys, len, prot); + ret = iommu_map(mapping->domain, iova, phys, len, prot, + GFP_KERNEL); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1379,7 +1381,8 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, + prot, GFP_KERNEL); if (ret < 0) goto fail; @@ -1443,7 +1446,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev, prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO; - ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL); if (ret < 0) goto fail; diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 91e63426bdc5..7119c04c51c5 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -186,9 +186,10 @@ static inline unsigned long *get_st_pto(unsigned long entry) /* Prototypes */ void dma_free_seg_table(unsigned long); -unsigned long *dma_alloc_cpu_table(void); +unsigned long *dma_alloc_cpu_table(gfp_t gfp); void dma_cleanup_tables(unsigned long *); -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr); +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, + gfp_t gfp); void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags); extern const struct dma_map_ops s390_pci_dma_ops; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index ea478d11fbd1..2d9b01d7ca4c 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -27,11 +27,11 @@ static int zpci_refresh_global(struct zpci_dev *zdev) zdev->iommu_pages * PAGE_SIZE); } -unsigned long *dma_alloc_cpu_table(void) +unsigned long *dma_alloc_cpu_table(gfp_t gfp) { unsigned long *table, *entry; - table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC); + table = kmem_cache_alloc(dma_region_table_cache, gfp); if (!table) return NULL; @@ -45,11 +45,11 @@ static void dma_free_cpu_table(void *table) kmem_cache_free(dma_region_table_cache, table); } -static unsigned long *dma_alloc_page_table(void) +static unsigned long *dma_alloc_page_table(gfp_t gfp) { unsigned long *table, *entry; - table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC); + table = kmem_cache_alloc(dma_page_table_cache, gfp); if (!table) return NULL; @@ -63,7 +63,7 @@ static void dma_free_page_table(void *table) kmem_cache_free(dma_page_table_cache, table); } -static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) +static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp) { unsigned long old_rte, rte; unsigned long *sto; @@ -72,7 +72,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) if (reg_entry_isvalid(rte)) { sto = get_rt_sto(rte); } else { - sto = dma_alloc_cpu_table(); + sto = dma_alloc_cpu_table(gfp); if (!sto) return NULL; @@ -90,7 +90,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) return sto; } -static unsigned long *dma_get_page_table_origin(unsigned long *step) +static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp) { unsigned long old_ste, ste; unsigned long *pto; @@ -99,7 +99,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step) if (reg_entry_isvalid(ste)) { pto = get_st_pto(ste); } else { - pto = dma_alloc_page_table(); + pto = dma_alloc_page_table(gfp); if (!pto) return NULL; set_st_pto(&ste, virt_to_phys(pto)); @@ -116,18 +116,19 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step) return pto; } -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, + gfp_t gfp) { unsigned long *sto, *pto; unsigned int rtx, sx, px; rtx = calc_rtx(dma_addr); - sto = dma_get_seg_table_origin(&rto[rtx]); + sto = dma_get_seg_table_origin(&rto[rtx], gfp); if (!sto) return NULL; sx = calc_sx(dma_addr); - pto = dma_get_page_table_origin(&sto[sx]); + pto = dma_get_page_table_origin(&sto[sx], gfp); if (!pto) return NULL; @@ -170,7 +171,8 @@ static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, return -EINVAL; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, + GFP_ATOMIC); if (!entry) { rc = -ENOMEM; goto undo_cpu_trans; @@ -186,7 +188,8 @@ undo_cpu_trans: while (i-- > 0) { page_addr -= PAGE_SIZE; dma_addr -= PAGE_SIZE; - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, + GFP_ATOMIC); if (!entry) break; dma_update_cpu_trans(entry, page_addr, flags); @@ -576,7 +579,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) spin_lock_init(&zdev->iommu_bitmap_lock); - zdev->dma_table = dma_alloc_cpu_table(); + zdev->dma_table = dma_alloc_cpu_table(GFP_KERNEL); if (!zdev->dma_table) { rc = -ENOMEM; goto out; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index 648ecf5a8fbc..a4ac94a2ab57 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -475,7 +475,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, u32 offset = (r->offset + i) << imem->iommu_pgshift; ret = iommu_map(imem->domain, offset, node->dma_addrs[i], - PAGE_SIZE, IOMMU_READ | IOMMU_WRITE); + PAGE_SIZE, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret < 0) { nvkm_error(subdev, "IOMMU mapping failure: %d\n", ret); diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 7bd2e65c2a16..6ca9f396e55b 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1057,7 +1057,7 @@ void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *dma) *dma = iova_dma_addr(&tegra->carveout.domain, alloc); err = iommu_map(tegra->domain, *dma, virt_to_phys(virt), - size, IOMMU_READ | IOMMU_WRITE); + size, IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (err < 0) goto free_iova; diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index bc821b0ed908..d1336e438f4f 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -105,7 +105,7 @@ static int host1x_pushbuffer_init(struct push_buffer *pb) pb->dma = iova_dma_addr(&host1x->iova, alloc); err = iommu_map(host1x->domain, pb->dma, pb->phys, size, - IOMMU_READ); + IOMMU_READ, GFP_KERNEL); if (err) goto iommu_free_iova; } else { diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index a2857accc427..aeeaca65ace9 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -276,8 +276,8 @@ iter_chunk: size = pa_end - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x", va_start, &pa_start, size, flags); - err = iommu_map_atomic(pd->domain, va_start, - pa_start, size, flags); + err = iommu_map(pd->domain, va_start, pa_start, + size, flags, GFP_KERNEL); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); @@ -293,8 +293,8 @@ iter_chunk: size = pa - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n", va_start, &pa_start, size, flags); - err = iommu_map_atomic(pd->domain, va_start, - pa_start, size, flags); + err = iommu_map(pd->domain, va_start, pa_start, + size, flags, GFP_KERNEL); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 79707685d54a..889c7efd050b 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -32,7 +32,8 @@ config IOMMU_IO_PGTABLE config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE - depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARM || ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for cpmxchg64() help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page @@ -70,7 +71,8 @@ config IOMMU_IO_PGTABLE_ARMV7S_SELFTEST config IOMMU_IO_PGTABLE_DART bool "Apple DART Formats" select IOMMU_IO_PGTABLE - depends on ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for cpmxchg64() help Enable support for the Apple DART pagetable formats. These include the t8020 and t6000/t8110 DART formats used in Apple M1/M2 family @@ -284,7 +286,8 @@ config EXYNOS_IOMMU_DEBUG config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" - depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARCH_RENESAS || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU @@ -304,7 +307,8 @@ config SPAPR_TCE_IOMMU config APPLE_DART tristate "Apple DART IOMMU Support" - depends on ARCH_APPLE || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARCH_APPLE || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_DART select IOMMU_API select IOMMU_IO_PGTABLE_DART default ARCH_APPLE @@ -319,7 +323,8 @@ config APPLE_DART # ARM IOMMU support config ARM_SMMU tristate "ARM Ltd. System MMU (SMMU) Support" - depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARM64 || ARM || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU if ARM @@ -466,7 +471,8 @@ config MTK_IOMMU_V1 config QCOM_IOMMU # Note: iommu drivers cannot (yet?) be built as modules bool "Qualcomm IOMMU Support" - depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARCH_QCOM || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE select QCOM_SCM select IOMMU_API select IOMMU_IO_PGTABLE_LPAE diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 467b194975b3..19a46b9f7357 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3475,15 +3475,26 @@ found: return 1; } +#define ACPIID_LEN (ACPIHID_UID_LEN + ACPIHID_HID_LEN) + static int __init parse_ivrs_acpihid(char *str) { u32 seg = 0, bus, dev, fn; char *hid, *uid, *p, *addr; - char acpiid[ACPIHID_UID_LEN + ACPIHID_HID_LEN] = {0}; + char acpiid[ACPIID_LEN] = {0}; int i; addr = strchr(str, '@'); if (!addr) { + addr = strchr(str, '='); + if (!addr) + goto not_found; + + ++addr; + + if (strlen(addr) > ACPIID_LEN) + goto not_found; + if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 || sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) { pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n", @@ -3496,6 +3507,9 @@ static int __init parse_ivrs_acpihid(char *str) /* We have the '@', make it the terminator to get just the acpiid */ *addr++ = 0; + if (strlen(str) > ACPIID_LEN + 1) + goto not_found; + if (sscanf(str, "=%s", acpiid) != 1) goto not_found; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index cbeaab55c0db..c20c41dd9c91 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -558,6 +558,15 @@ static void amd_iommu_report_page_fault(struct amd_iommu *iommu, * prevent logging it. */ if (IS_IOMMU_MEM_TRANSACTION(flags)) { + /* Device not attached to domain properly */ + if (dev_data->domain == NULL) { + pr_err_ratelimited("Event logged [Device not attached to domain properly]\n"); + pr_err_ratelimited(" device=%04x:%02x:%02x.%x domain=0x%04x\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), + PCI_FUNC(devid), domain_id); + goto out; + } + if (!report_iommu_fault(&dev_data->domain->domain, &pdev->dev, address, IS_WRITE_REQUEST(flags) ? @@ -667,7 +676,14 @@ retry: event[0], event[1], event[2], event[3]); } - memset(__evt, 0, 4 * sizeof(u32)); + /* + * To detect the hardware errata 732 we need to clear the + * entry back to zero. This issue does not exist on SNP + * enabled system. Also this buffer is not writeable on + * SNP enabled system. + */ + if (!amd_iommu_snp_en) + memset(__evt, 0, 4 * sizeof(u32)); } static void iommu_poll_events(struct amd_iommu *iommu) @@ -736,10 +752,13 @@ static void iommu_poll_ppr_log(struct amd_iommu *iommu) entry[1] = raw[1]; /* - * To detect the hardware bug we need to clear the entry - * back to zero. + * To detect the hardware errata 733 we need to clear the + * entry back to zero. This issue does not exist on SNP + * enabled system. Also this buffer is not writeable on + * SNP enabled system. */ - raw[0] = raw[1] = 0UL; + if (!amd_iommu_snp_en) + raw[0] = raw[1] = 0UL; /* Update head pointer of hardware ring-buffer */ head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE; @@ -1702,27 +1721,29 @@ static int pdev_pri_ats_enable(struct pci_dev *pdev) /* Only allow access to user-accessible pages */ ret = pci_enable_pasid(pdev, 0); if (ret) - goto out_err; + return ret; /* First reset the PRI state of the device */ ret = pci_reset_pri(pdev); if (ret) - goto out_err; + goto out_err_pasid; /* Enable PRI */ /* FIXME: Hardcode number of outstanding requests for now */ ret = pci_enable_pri(pdev, 32); if (ret) - goto out_err; + goto out_err_pasid; ret = pci_enable_ats(pdev, PAGE_SHIFT); if (ret) - goto out_err; + goto out_err_pri; return 0; -out_err: +out_err_pri: pci_disable_pri(pdev); + +out_err_pasid: pci_disable_pasid(pdev); return ret; @@ -2072,6 +2093,10 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) if (ret) goto out_err; + /* No need to allocate io pgtable ops in passthrough mode */ + if (type == IOMMU_DOMAIN_IDENTITY) + return domain; + pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain); if (!pgtbl_ops) { domain_id_free(domain->id); @@ -2126,31 +2151,6 @@ static void amd_iommu_domain_free(struct iommu_domain *dom) protection_domain_free(domain); } -static void amd_iommu_detach_device(struct iommu_domain *dom, - struct device *dev) -{ - struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); - struct amd_iommu *iommu; - - if (!check_device(dev)) - return; - - if (dev_data->domain != NULL) - detach_device(dev); - - iommu = rlookup_amd_iommu(dev); - if (!iommu) - return; - -#ifdef CONFIG_IRQ_REMAP - if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) && - (dom->type == IOMMU_DOMAIN_UNMANAGED)) - dev_data->use_vapic = 0; -#endif - - iommu_completion_wait(iommu); -} - static int amd_iommu_attach_device(struct iommu_domain *dom, struct device *dev) { @@ -2159,6 +2159,13 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, struct amd_iommu *iommu = rlookup_amd_iommu(dev); int ret; + /* + * Skip attach device to domain if new domain is same as + * devices current domain + */ + if (dev_data->domain == domain) + return 0; + dev_data->defer_attach = false; if (dev_data->domain) @@ -2387,12 +2394,17 @@ static int amd_iommu_def_domain_type(struct device *dev) return 0; /* - * Do not identity map IOMMUv2 capable devices when memory encryption is - * active, because some of those devices (AMD GPUs) don't have the - * encryption bit in their DMA-mask and require remapping. + * Do not identity map IOMMUv2 capable devices when: + * - memory encryption is active, because some of those devices + * (AMD GPUs) don't have the encryption bit in their DMA-mask + * and require remapping. + * - SNP is enabled, because it prohibits DTE[Mode]=0. */ - if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT) && dev_data->iommu_v2) + if (dev_data->iommu_v2 && + !cc_platform_has(CC_ATTR_MEM_ENCRYPT) && + !amd_iommu_snp_en) { return IOMMU_DOMAIN_IDENTITY; + } return 0; } @@ -2416,7 +2428,6 @@ const struct iommu_ops amd_iommu_ops = { .def_domain_type = amd_iommu_def_domain_type, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = amd_iommu_attach_device, - .detach_dev = amd_iommu_detach_device, .map_pages = amd_iommu_map_pages, .unmap_pages = amd_iommu_unmap_pages, .iotlb_sync_map = amd_iommu_iotlb_sync_map, diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 4f4a323be0d0..06169d36eab8 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -34,57 +34,154 @@ #include "dma-iommu.h" -#define DART_MAX_STREAMS 16 +#define DART_MAX_STREAMS 256 #define DART_MAX_TTBR 4 #define MAX_DARTS_PER_DEVICE 2 -#define DART_STREAM_ALL 0xffff +/* Common registers */ #define DART_PARAMS1 0x00 -#define DART_PARAMS_PAGE_SHIFT GENMASK(27, 24) +#define DART_PARAMS1_PAGE_SHIFT GENMASK(27, 24) #define DART_PARAMS2 0x04 -#define DART_PARAMS_BYPASS_SUPPORT BIT(0) +#define DART_PARAMS2_BYPASS_SUPPORT BIT(0) -#define DART_STREAM_COMMAND 0x20 -#define DART_STREAM_COMMAND_BUSY BIT(2) -#define DART_STREAM_COMMAND_INVALIDATE BIT(20) +/* T8020/T6000 registers */ -#define DART_STREAM_SELECT 0x34 +#define DART_T8020_STREAM_COMMAND 0x20 +#define DART_T8020_STREAM_COMMAND_BUSY BIT(2) +#define DART_T8020_STREAM_COMMAND_INVALIDATE BIT(20) -#define DART_ERROR 0x40 -#define DART_ERROR_STREAM GENMASK(27, 24) -#define DART_ERROR_CODE GENMASK(11, 0) -#define DART_ERROR_FLAG BIT(31) +#define DART_T8020_STREAM_SELECT 0x34 -#define DART_ERROR_READ_FAULT BIT(4) -#define DART_ERROR_WRITE_FAULT BIT(3) -#define DART_ERROR_NO_PTE BIT(2) -#define DART_ERROR_NO_PMD BIT(1) -#define DART_ERROR_NO_TTBR BIT(0) +#define DART_T8020_ERROR 0x40 +#define DART_T8020_ERROR_STREAM GENMASK(27, 24) +#define DART_T8020_ERROR_CODE GENMASK(11, 0) +#define DART_T8020_ERROR_FLAG BIT(31) -#define DART_CONFIG 0x60 -#define DART_CONFIG_LOCK BIT(15) +#define DART_T8020_ERROR_READ_FAULT BIT(4) +#define DART_T8020_ERROR_WRITE_FAULT BIT(3) +#define DART_T8020_ERROR_NO_PTE BIT(2) +#define DART_T8020_ERROR_NO_PMD BIT(1) +#define DART_T8020_ERROR_NO_TTBR BIT(0) -#define DART_STREAM_COMMAND_BUSY_TIMEOUT 100 - -#define DART_ERROR_ADDR_HI 0x54 -#define DART_ERROR_ADDR_LO 0x50 - -#define DART_STREAMS_ENABLE 0xfc +#define DART_T8020_CONFIG 0x60 +#define DART_T8020_CONFIG_LOCK BIT(15) -#define DART_TCR(sid) (0x100 + 4 * (sid)) -#define DART_TCR_TRANSLATE_ENABLE BIT(7) -#define DART_TCR_BYPASS0_ENABLE BIT(8) -#define DART_TCR_BYPASS1_ENABLE BIT(12) +#define DART_STREAM_COMMAND_BUSY_TIMEOUT 100 -#define DART_TTBR(sid, idx) (0x200 + 16 * (sid) + 4 * (idx)) -#define DART_TTBR_VALID BIT(31) -#define DART_TTBR_SHIFT 12 +#define DART_T8020_ERROR_ADDR_HI 0x54 +#define DART_T8020_ERROR_ADDR_LO 0x50 + +#define DART_T8020_STREAMS_ENABLE 0xfc + +#define DART_T8020_TCR 0x100 +#define DART_T8020_TCR_TRANSLATE_ENABLE BIT(7) +#define DART_T8020_TCR_BYPASS_DART BIT(8) +#define DART_T8020_TCR_BYPASS_DAPF BIT(12) + +#define DART_T8020_TTBR 0x200 +#define DART_T8020_TTBR_VALID BIT(31) +#define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0 +#define DART_T8020_TTBR_SHIFT 12 + +/* T8110 registers */ + +#define DART_T8110_PARAMS3 0x08 +#define DART_T8110_PARAMS3_PA_WIDTH GENMASK(29, 24) +#define DART_T8110_PARAMS3_VA_WIDTH GENMASK(21, 16) +#define DART_T8110_PARAMS3_VER_MAJ GENMASK(15, 8) +#define DART_T8110_PARAMS3_VER_MIN GENMASK(7, 0) + +#define DART_T8110_PARAMS4 0x0c +#define DART_T8110_PARAMS4_NUM_CLIENTS GENMASK(24, 16) +#define DART_T8110_PARAMS4_NUM_SIDS GENMASK(8, 0) + +#define DART_T8110_TLB_CMD 0x80 +#define DART_T8110_TLB_CMD_BUSY BIT(31) +#define DART_T8110_TLB_CMD_OP GENMASK(10, 8) +#define DART_T8110_TLB_CMD_OP_FLUSH_ALL 0 +#define DART_T8110_TLB_CMD_OP_FLUSH_SID 1 +#define DART_T8110_TLB_CMD_STREAM GENMASK(7, 0) + +#define DART_T8110_ERROR 0x100 +#define DART_T8110_ERROR_STREAM GENMASK(27, 20) +#define DART_T8110_ERROR_CODE GENMASK(14, 0) +#define DART_T8110_ERROR_FLAG BIT(31) + +#define DART_T8110_ERROR_MASK 0x104 + +#define DART_T8110_ERROR_READ_FAULT BIT(5) +#define DART_T8110_ERROR_WRITE_FAULT BIT(4) +#define DART_T8110_ERROR_NO_PTE BIT(3) +#define DART_T8110_ERROR_NO_PMD BIT(2) +#define DART_T8110_ERROR_NO_PGD BIT(1) +#define DART_T8110_ERROR_NO_TTBR BIT(0) + +#define DART_T8110_ERROR_ADDR_LO 0x170 +#define DART_T8110_ERROR_ADDR_HI 0x174 + +#define DART_T8110_PROTECT 0x200 +#define DART_T8110_UNPROTECT 0x204 +#define DART_T8110_PROTECT_LOCK 0x208 +#define DART_T8110_PROTECT_TTBR_TCR BIT(0) + +#define DART_T8110_ENABLE_STREAMS 0xc00 +#define DART_T8110_DISABLE_STREAMS 0xc20 + +#define DART_T8110_TCR 0x1000 +#define DART_T8110_TCR_REMAP GENMASK(11, 8) +#define DART_T8110_TCR_REMAP_EN BIT(7) +#define DART_T8110_TCR_BYPASS_DAPF BIT(2) +#define DART_T8110_TCR_BYPASS_DART BIT(1) +#define DART_T8110_TCR_TRANSLATE_ENABLE BIT(0) + +#define DART_T8110_TTBR 0x1400 +#define DART_T8110_TTBR_VALID BIT(0) +#define DART_T8110_TTBR_ADDR_FIELD_SHIFT 2 +#define DART_T8110_TTBR_SHIFT 14 + +#define DART_TCR(dart, sid) ((dart)->hw->tcr + ((sid) << 2)) + +#define DART_TTBR(dart, sid, idx) ((dart)->hw->ttbr + \ + (((dart)->hw->ttbr_count * (sid)) << 2) + \ + ((idx) << 2)) + +struct apple_dart_stream_map; + +enum dart_type { + DART_T8020, + DART_T6000, + DART_T8110, +}; struct apple_dart_hw { + enum dart_type type; + irqreturn_t (*irq_handler)(int irq, void *dev); + int (*invalidate_tlb)(struct apple_dart_stream_map *stream_map); + u32 oas; enum io_pgtable_fmt fmt; + + int max_sid_count; + + u64 lock; + u64 lock_bit; + + u64 error; + + u64 enable_streams; + + u64 tcr; + u64 tcr_enabled; + u64 tcr_disabled; + u64 tcr_bypass; + + u64 ttbr; + u64 ttbr_valid; + u64 ttbr_addr_field_shift; + u64 ttbr_shift; + int ttbr_count; }; /* @@ -115,12 +212,18 @@ struct apple_dart { spinlock_t lock; + u32 ias; + u32 oas; u32 pgsize; + u32 num_streams; u32 supports_bypass : 1; u32 force_bypass : 1; struct iommu_group *sid2group[DART_MAX_STREAMS]; struct iommu_device iommu; + + u32 save_tcr[DART_MAX_STREAMS]; + u32 save_ttbr[DART_MAX_STREAMS][DART_MAX_TTBR]; }; /* @@ -140,11 +243,11 @@ struct apple_dart { */ struct apple_dart_stream_map { struct apple_dart *dart; - unsigned long sidmap; + DECLARE_BITMAP(sidmap, DART_MAX_STREAMS); }; struct apple_dart_atomic_stream_map { struct apple_dart *dart; - atomic64_t sidmap; + atomic_long_t sidmap[BITS_TO_LONGS(DART_MAX_STREAMS)]; }; /* @@ -202,50 +305,55 @@ static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom) static void apple_dart_hw_enable_translation(struct apple_dart_stream_map *stream_map) { + struct apple_dart *dart = stream_map->dart; int sid; - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) - writel(DART_TCR_TRANSLATE_ENABLE, - stream_map->dart->regs + DART_TCR(sid)); + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) + writel(dart->hw->tcr_enabled, dart->regs + DART_TCR(dart, sid)); } static void apple_dart_hw_disable_dma(struct apple_dart_stream_map *stream_map) { + struct apple_dart *dart = stream_map->dart; int sid; - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) - writel(0, stream_map->dart->regs + DART_TCR(sid)); + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) + writel(dart->hw->tcr_disabled, dart->regs + DART_TCR(dart, sid)); } static void apple_dart_hw_enable_bypass(struct apple_dart_stream_map *stream_map) { + struct apple_dart *dart = stream_map->dart; int sid; WARN_ON(!stream_map->dart->supports_bypass); - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) - writel(DART_TCR_BYPASS0_ENABLE | DART_TCR_BYPASS1_ENABLE, - stream_map->dart->regs + DART_TCR(sid)); + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) + writel(dart->hw->tcr_bypass, + dart->regs + DART_TCR(dart, sid)); } static void apple_dart_hw_set_ttbr(struct apple_dart_stream_map *stream_map, u8 idx, phys_addr_t paddr) { + struct apple_dart *dart = stream_map->dart; int sid; - WARN_ON(paddr & ((1 << DART_TTBR_SHIFT) - 1)); - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) - writel(DART_TTBR_VALID | (paddr >> DART_TTBR_SHIFT), - stream_map->dart->regs + DART_TTBR(sid, idx)); + WARN_ON(paddr & ((1 << dart->hw->ttbr_shift) - 1)); + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) + writel(dart->hw->ttbr_valid | + (paddr >> dart->hw->ttbr_shift) << dart->hw->ttbr_addr_field_shift, + dart->regs + DART_TTBR(dart, sid, idx)); } static void apple_dart_hw_clear_ttbr(struct apple_dart_stream_map *stream_map, u8 idx) { + struct apple_dart *dart = stream_map->dart; int sid; - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) - writel(0, stream_map->dart->regs + DART_TTBR(sid, idx)); + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) + writel(0, dart->regs + DART_TTBR(dart, sid, idx)); } static void @@ -253,12 +361,12 @@ apple_dart_hw_clear_all_ttbrs(struct apple_dart_stream_map *stream_map) { int i; - for (i = 0; i < DART_MAX_TTBR; ++i) + for (i = 0; i < stream_map->dart->hw->ttbr_count; ++i) apple_dart_hw_clear_ttbr(stream_map, i); } static int -apple_dart_hw_stream_command(struct apple_dart_stream_map *stream_map, +apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map, u32 command) { unsigned long flags; @@ -267,12 +375,12 @@ apple_dart_hw_stream_command(struct apple_dart_stream_map *stream_map, spin_lock_irqsave(&stream_map->dart->lock, flags); - writel(stream_map->sidmap, stream_map->dart->regs + DART_STREAM_SELECT); - writel(command, stream_map->dart->regs + DART_STREAM_COMMAND); + writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT); + writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND); ret = readl_poll_timeout_atomic( - stream_map->dart->regs + DART_STREAM_COMMAND, command_reg, - !(command_reg & DART_STREAM_COMMAND_BUSY), 1, + stream_map->dart->regs + DART_T8020_STREAM_COMMAND, command_reg, + !(command_reg & DART_T8020_STREAM_COMMAND_BUSY), 1, DART_STREAM_COMMAND_BUSY_TIMEOUT); spin_unlock_irqrestore(&stream_map->dart->lock, flags); @@ -280,7 +388,45 @@ apple_dart_hw_stream_command(struct apple_dart_stream_map *stream_map, if (ret) { dev_err(stream_map->dart->dev, "busy bit did not clear after command %x for streams %lx\n", - command, stream_map->sidmap); + command, stream_map->sidmap[0]); + return ret; + } + + return 0; +} + +static int +apple_dart_t8110_hw_tlb_command(struct apple_dart_stream_map *stream_map, + u32 command) +{ + struct apple_dart *dart = stream_map->dart; + unsigned long flags; + int ret = 0; + int sid; + + spin_lock_irqsave(&dart->lock, flags); + + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) { + u32 val = FIELD_PREP(DART_T8110_TLB_CMD_OP, command) | + FIELD_PREP(DART_T8110_TLB_CMD_STREAM, sid); + writel(val, dart->regs + DART_T8110_TLB_CMD); + + ret = readl_poll_timeout_atomic( + dart->regs + DART_T8110_TLB_CMD, val, + !(val & DART_T8110_TLB_CMD_BUSY), 1, + DART_STREAM_COMMAND_BUSY_TIMEOUT); + + if (ret) + break; + + } + + spin_unlock_irqrestore(&dart->lock, flags); + + if (ret) { + dev_err(stream_map->dart->dev, + "busy bit did not clear after command %x for stream %d\n", + command, sid); return ret; } @@ -288,48 +434,64 @@ apple_dart_hw_stream_command(struct apple_dart_stream_map *stream_map, } static int -apple_dart_hw_invalidate_tlb(struct apple_dart_stream_map *stream_map) +apple_dart_t8020_hw_invalidate_tlb(struct apple_dart_stream_map *stream_map) +{ + return apple_dart_t8020_hw_stream_command( + stream_map, DART_T8020_STREAM_COMMAND_INVALIDATE); +} + +static int +apple_dart_t8110_hw_invalidate_tlb(struct apple_dart_stream_map *stream_map) { - return apple_dart_hw_stream_command(stream_map, - DART_STREAM_COMMAND_INVALIDATE); + return apple_dart_t8110_hw_tlb_command( + stream_map, DART_T8110_TLB_CMD_OP_FLUSH_SID); } static int apple_dart_hw_reset(struct apple_dart *dart) { u32 config; struct apple_dart_stream_map stream_map; + int i; - config = readl(dart->regs + DART_CONFIG); - if (config & DART_CONFIG_LOCK) { + config = readl(dart->regs + dart->hw->lock); + if (config & dart->hw->lock_bit) { dev_err(dart->dev, "DART is locked down until reboot: %08x\n", config); return -EINVAL; } stream_map.dart = dart; - stream_map.sidmap = DART_STREAM_ALL; + bitmap_zero(stream_map.sidmap, DART_MAX_STREAMS); + bitmap_set(stream_map.sidmap, 0, dart->num_streams); apple_dart_hw_disable_dma(&stream_map); apple_dart_hw_clear_all_ttbrs(&stream_map); /* enable all streams globally since TCR is used to control isolation */ - writel(DART_STREAM_ALL, dart->regs + DART_STREAMS_ENABLE); + for (i = 0; i < BITS_TO_U32(dart->num_streams); i++) + writel(U32_MAX, dart->regs + dart->hw->enable_streams + 4 * i); /* clear any pending errors before the interrupt is unmasked */ - writel(readl(dart->regs + DART_ERROR), dart->regs + DART_ERROR); + writel(readl(dart->regs + dart->hw->error), dart->regs + dart->hw->error); + + if (dart->hw->type == DART_T8110) + writel(0, dart->regs + DART_T8110_ERROR_MASK); - return apple_dart_hw_invalidate_tlb(&stream_map); + return dart->hw->invalidate_tlb(&stream_map); } static void apple_dart_domain_flush_tlb(struct apple_dart_domain *domain) { - int i; + int i, j; struct apple_dart_atomic_stream_map *domain_stream_map; struct apple_dart_stream_map stream_map; for_each_stream_map(i, domain, domain_stream_map) { stream_map.dart = domain_stream_map->dart; - stream_map.sidmap = atomic64_read(&domain_stream_map->sidmap); - apple_dart_hw_invalidate_tlb(&stream_map); + + for (j = 0; j < BITS_TO_LONGS(stream_map.dart->num_streams); j++) + stream_map.sidmap[j] = atomic_long_read(&domain_stream_map->sidmap[j]); + + stream_map.dart->hw->invalidate_tlb(&stream_map); } } @@ -399,11 +561,11 @@ apple_dart_setup_translation(struct apple_dart_domain *domain, for (i = 0; i < pgtbl_cfg->apple_dart_cfg.n_ttbrs; ++i) apple_dart_hw_set_ttbr(stream_map, i, pgtbl_cfg->apple_dart_cfg.ttbr[i]); - for (; i < DART_MAX_TTBR; ++i) + for (; i < stream_map->dart->hw->ttbr_count; ++i) apple_dart_hw_clear_ttbr(stream_map, i); apple_dart_hw_enable_translation(stream_map); - apple_dart_hw_invalidate_tlb(stream_map); + stream_map->dart->hw->invalidate_tlb(stream_map); } static int apple_dart_finalize_domain(struct iommu_domain *domain, @@ -413,7 +575,7 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, struct apple_dart *dart = cfg->stream_maps[0].dart; struct io_pgtable_cfg pgtbl_cfg; int ret = 0; - int i; + int i, j; mutex_lock(&dart_domain->init_lock); @@ -422,14 +584,15 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { dart_domain->stream_maps[i].dart = cfg->stream_maps[i].dart; - atomic64_set(&dart_domain->stream_maps[i].sidmap, - cfg->stream_maps[i].sidmap); + for (j = 0; j < BITS_TO_LONGS(dart->num_streams); j++) + atomic_long_set(&dart_domain->stream_maps[i].sidmap[j], + cfg->stream_maps[i].sidmap[j]); } pgtbl_cfg = (struct io_pgtable_cfg){ .pgsize_bitmap = dart->pgsize, - .ias = 32, - .oas = dart->hw->oas, + .ias = dart->ias, + .oas = dart->oas, .coherent_walk = 1, .iommu_dev = dart->dev, }; @@ -443,7 +606,7 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; domain->geometry.aperture_start = 0; - domain->geometry.aperture_end = DMA_BIT_MASK(32); + domain->geometry.aperture_end = (dma_addr_t)DMA_BIT_MASK(dart->ias); domain->geometry.force_aperture = true; dart_domain->finalized = true; @@ -458,7 +621,7 @@ apple_dart_mod_streams(struct apple_dart_atomic_stream_map *domain_maps, struct apple_dart_stream_map *master_maps, bool add_streams) { - int i; + int i, j; for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { if (domain_maps[i].dart != master_maps[i].dart) @@ -468,12 +631,14 @@ apple_dart_mod_streams(struct apple_dart_atomic_stream_map *domain_maps, for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { if (!domain_maps[i].dart) break; - if (add_streams) - atomic64_or(master_maps[i].sidmap, - &domain_maps[i].sidmap); - else - atomic64_and(~master_maps[i].sidmap, - &domain_maps[i].sidmap); + for (j = 0; j < BITS_TO_LONGS(domain_maps[i].dart->num_streams); j++) { + if (add_streams) + atomic_long_or(master_maps[i].sidmap[j], + &domain_maps[i].sidmap[j]); + else + atomic_long_and(~master_maps[i].sidmap[j], + &domain_maps[i].sidmap[j]); + } } return 0; @@ -486,13 +651,6 @@ static int apple_dart_domain_add_streams(struct apple_dart_domain *domain, true); } -static int apple_dart_domain_remove_streams(struct apple_dart_domain *domain, - struct apple_dart_master_cfg *cfg) -{ - return apple_dart_mod_streams(domain->stream_maps, cfg->stream_maps, - false); -} - static int apple_dart_attach_dev(struct iommu_domain *domain, struct device *dev) { @@ -535,22 +693,6 @@ static int apple_dart_attach_dev(struct iommu_domain *domain, return ret; } -static void apple_dart_detach_dev(struct iommu_domain *domain, - struct device *dev) -{ - int i; - struct apple_dart_stream_map *stream_map; - struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); - struct apple_dart_domain *dart_domain = to_dart_domain(domain); - - for_each_stream_map(i, cfg, stream_map) - apple_dart_hw_disable_dma(stream_map); - - if (domain->type == IOMMU_DOMAIN_DMA || - domain->type == IOMMU_DOMAIN_UNMANAGED) - apple_dart_domain_remove_streams(dart_domain, cfg); -} - static struct iommu_device *apple_dart_probe_device(struct device *dev) { struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); @@ -637,14 +779,14 @@ static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args) for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { if (cfg->stream_maps[i].dart == dart) { - cfg->stream_maps[i].sidmap |= 1 << sid; + set_bit(sid, cfg->stream_maps[i].sidmap); return 0; } } for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { if (!cfg->stream_maps[i].dart) { cfg->stream_maps[i].dart = dart; - cfg->stream_maps[i].sidmap = 1 << sid; + set_bit(sid, cfg->stream_maps[i].sidmap); return 0; } } @@ -663,13 +805,36 @@ static void apple_dart_release_group(void *iommu_data) mutex_lock(&apple_dart_groups_lock); for_each_stream_map(i, group_master_cfg, stream_map) - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) + for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams) stream_map->dart->sid2group[sid] = NULL; kfree(iommu_data); mutex_unlock(&apple_dart_groups_lock); } +static int apple_dart_merge_master_cfg(struct apple_dart_master_cfg *dst, + struct apple_dart_master_cfg *src) +{ + /* + * We know that this function is only called for groups returned from + * pci_device_group and that all Apple Silicon platforms never spread + * PCIe devices from the same bus across multiple DARTs such that we can + * just assume that both src and dst only have the same single DART. + */ + if (src->stream_maps[1].dart) + return -EINVAL; + if (dst->stream_maps[1].dart) + return -EINVAL; + if (src->stream_maps[0].dart != dst->stream_maps[0].dart) + return -EINVAL; + + bitmap_or(dst->stream_maps[0].sidmap, + dst->stream_maps[0].sidmap, + src->stream_maps[0].sidmap, + dst->stream_maps[0].dart->num_streams); + return 0; +} + static struct iommu_group *apple_dart_device_group(struct device *dev) { int i, sid; @@ -682,7 +847,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) mutex_lock(&apple_dart_groups_lock); for_each_stream_map(i, cfg, stream_map) { - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) { + for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams) { struct iommu_group *stream_group = stream_map->dart->sid2group[sid]; @@ -711,17 +876,31 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) if (!group) goto out; - group_master_cfg = kmemdup(cfg, sizeof(*group_master_cfg), GFP_KERNEL); - if (!group_master_cfg) { - iommu_group_put(group); - goto out; - } + group_master_cfg = iommu_group_get_iommudata(group); + if (group_master_cfg) { + int ret; + + ret = apple_dart_merge_master_cfg(group_master_cfg, cfg); + if (ret) { + dev_err(dev, "Failed to merge DART IOMMU grups.\n"); + iommu_group_put(group); + res = ERR_PTR(ret); + goto out; + } + } else { + group_master_cfg = kmemdup(cfg, sizeof(*group_master_cfg), + GFP_KERNEL); + if (!group_master_cfg) { + iommu_group_put(group); + goto out; + } - iommu_group_set_iommudata(group, group_master_cfg, - apple_dart_release_group); + iommu_group_set_iommudata(group, group_master_cfg, + apple_dart_release_group); + } for_each_stream_map(i, cfg, stream_map) - for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) + for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams) stream_map->dart->sid2group[sid] = group; res = group; @@ -780,7 +959,6 @@ static const struct iommu_ops apple_dart_iommu_ops = { .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = apple_dart_attach_dev, - .detach_dev = apple_dart_detach_dev, .map_pages = apple_dart_map_pages, .unmap_pages = apple_dart_unmap_pages, .flush_iotlb_all = apple_dart_flush_iotlb_all, @@ -791,30 +969,69 @@ static const struct iommu_ops apple_dart_iommu_ops = { } }; -static irqreturn_t apple_dart_irq(int irq, void *dev) +static irqreturn_t apple_dart_t8020_irq(int irq, void *dev) +{ + struct apple_dart *dart = dev; + const char *fault_name = NULL; + u32 error = readl(dart->regs + DART_T8020_ERROR); + u32 error_code = FIELD_GET(DART_T8020_ERROR_CODE, error); + u32 addr_lo = readl(dart->regs + DART_T8020_ERROR_ADDR_LO); + u32 addr_hi = readl(dart->regs + DART_T8020_ERROR_ADDR_HI); + u64 addr = addr_lo | (((u64)addr_hi) << 32); + u8 stream_idx = FIELD_GET(DART_T8020_ERROR_STREAM, error); + + if (!(error & DART_T8020_ERROR_FLAG)) + return IRQ_NONE; + + /* there should only be a single bit set but let's use == to be sure */ + if (error_code == DART_T8020_ERROR_READ_FAULT) + fault_name = "READ FAULT"; + else if (error_code == DART_T8020_ERROR_WRITE_FAULT) + fault_name = "WRITE FAULT"; + else if (error_code == DART_T8020_ERROR_NO_PTE) + fault_name = "NO PTE FOR IOVA"; + else if (error_code == DART_T8020_ERROR_NO_PMD) + fault_name = "NO PMD FOR IOVA"; + else if (error_code == DART_T8020_ERROR_NO_TTBR) + fault_name = "NO TTBR FOR IOVA"; + else + fault_name = "unknown"; + + dev_err_ratelimited( + dart->dev, + "translation fault: status:0x%x stream:%d code:0x%x (%s) at 0x%llx", + error, stream_idx, error_code, fault_name, addr); + + writel(error, dart->regs + DART_T8020_ERROR); + return IRQ_HANDLED; +} + +static irqreturn_t apple_dart_t8110_irq(int irq, void *dev) { struct apple_dart *dart = dev; const char *fault_name = NULL; - u32 error = readl(dart->regs + DART_ERROR); - u32 error_code = FIELD_GET(DART_ERROR_CODE, error); - u32 addr_lo = readl(dart->regs + DART_ERROR_ADDR_LO); - u32 addr_hi = readl(dart->regs + DART_ERROR_ADDR_HI); + u32 error = readl(dart->regs + DART_T8110_ERROR); + u32 error_code = FIELD_GET(DART_T8110_ERROR_CODE, error); + u32 addr_lo = readl(dart->regs + DART_T8110_ERROR_ADDR_LO); + u32 addr_hi = readl(dart->regs + DART_T8110_ERROR_ADDR_HI); u64 addr = addr_lo | (((u64)addr_hi) << 32); - u8 stream_idx = FIELD_GET(DART_ERROR_STREAM, error); + u8 stream_idx = FIELD_GET(DART_T8110_ERROR_STREAM, error); - if (!(error & DART_ERROR_FLAG)) + if (!(error & DART_T8110_ERROR_FLAG)) return IRQ_NONE; /* there should only be a single bit set but let's use == to be sure */ - if (error_code == DART_ERROR_READ_FAULT) + if (error_code == DART_T8110_ERROR_READ_FAULT) fault_name = "READ FAULT"; - else if (error_code == DART_ERROR_WRITE_FAULT) + else if (error_code == DART_T8110_ERROR_WRITE_FAULT) fault_name = "WRITE FAULT"; - else if (error_code == DART_ERROR_NO_PTE) + else if (error_code == DART_T8110_ERROR_NO_PTE) fault_name = "NO PTE FOR IOVA"; - else if (error_code == DART_ERROR_NO_PMD) + else if (error_code == DART_T8110_ERROR_NO_PMD) fault_name = "NO PMD FOR IOVA"; - else if (error_code == DART_ERROR_NO_TTBR) + else if (error_code == DART_T8110_ERROR_NO_PGD) + fault_name = "NO PGD FOR IOVA"; + else if (error_code == DART_T8110_ERROR_NO_TTBR) fault_name = "NO TTBR FOR IOVA"; else fault_name = "unknown"; @@ -824,14 +1041,14 @@ static irqreturn_t apple_dart_irq(int irq, void *dev) "translation fault: status:0x%x stream:%d code:0x%x (%s) at 0x%llx", error, stream_idx, error_code, fault_name, addr); - writel(error, dart->regs + DART_ERROR); + writel(error, dart->regs + DART_T8110_ERROR); return IRQ_HANDLED; } static int apple_dart_probe(struct platform_device *pdev) { int ret; - u32 dart_params[2]; + u32 dart_params[4]; struct resource *res; struct apple_dart *dart; struct device *dev = &pdev->dev; @@ -866,17 +1083,42 @@ static int apple_dart_probe(struct platform_device *pdev) if (ret) return ret; - ret = apple_dart_hw_reset(dart); - if (ret) - goto err_clk_disable; - dart_params[0] = readl(dart->regs + DART_PARAMS1); dart_params[1] = readl(dart->regs + DART_PARAMS2); - dart->pgsize = 1 << FIELD_GET(DART_PARAMS_PAGE_SHIFT, dart_params[0]); - dart->supports_bypass = dart_params[1] & DART_PARAMS_BYPASS_SUPPORT; + dart->pgsize = 1 << FIELD_GET(DART_PARAMS1_PAGE_SHIFT, dart_params[0]); + dart->supports_bypass = dart_params[1] & DART_PARAMS2_BYPASS_SUPPORT; + + switch (dart->hw->type) { + case DART_T8020: + case DART_T6000: + dart->ias = 32; + dart->oas = dart->hw->oas; + dart->num_streams = dart->hw->max_sid_count; + break; + + case DART_T8110: + dart_params[2] = readl(dart->regs + DART_T8110_PARAMS3); + dart_params[3] = readl(dart->regs + DART_T8110_PARAMS4); + dart->ias = FIELD_GET(DART_T8110_PARAMS3_VA_WIDTH, dart_params[2]); + dart->oas = FIELD_GET(DART_T8110_PARAMS3_PA_WIDTH, dart_params[2]); + dart->num_streams = FIELD_GET(DART_T8110_PARAMS4_NUM_SIDS, dart_params[3]); + break; + } + + if (dart->num_streams > DART_MAX_STREAMS) { + dev_err(&pdev->dev, "Too many streams (%d > %d)\n", + dart->num_streams, DART_MAX_STREAMS); + ret = -EINVAL; + goto err_clk_disable; + } + dart->force_bypass = dart->pgsize > PAGE_SIZE; - ret = request_irq(dart->irq, apple_dart_irq, IRQF_SHARED, + ret = apple_dart_hw_reset(dart); + if (ret) + goto err_clk_disable; + + ret = request_irq(dart->irq, dart->hw->irq_handler, IRQF_SHARED, "apple-dart fault handler", dart); if (ret) goto err_clk_disable; @@ -894,8 +1136,8 @@ static int apple_dart_probe(struct platform_device *pdev) dev_info( &pdev->dev, - "DART [pagesize %x, bypass support: %d, bypass forced: %d] initialized\n", - dart->pgsize, dart->supports_bypass, dart->force_bypass); + "DART [pagesize %x, %d streams, bypass support: %d, bypass forced: %d] initialized\n", + dart->pgsize, dart->num_streams, dart->supports_bypass, dart->force_bypass); return 0; err_sysfs_remove: @@ -924,16 +1166,123 @@ static int apple_dart_remove(struct platform_device *pdev) } static const struct apple_dart_hw apple_dart_hw_t8103 = { + .type = DART_T8020, + .irq_handler = apple_dart_t8020_irq, + .invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb, .oas = 36, .fmt = APPLE_DART, + .max_sid_count = 16, + + .enable_streams = DART_T8020_STREAMS_ENABLE, + .lock = DART_T8020_CONFIG, + .lock_bit = DART_T8020_CONFIG_LOCK, + + .error = DART_T8020_ERROR, + + .tcr = DART_T8020_TCR, + .tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE, + .tcr_disabled = 0, + .tcr_bypass = DART_T8020_TCR_BYPASS_DAPF | DART_T8020_TCR_BYPASS_DART, + + .ttbr = DART_T8020_TTBR, + .ttbr_valid = DART_T8020_TTBR_VALID, + .ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT, + .ttbr_shift = DART_T8020_TTBR_SHIFT, + .ttbr_count = 4, }; static const struct apple_dart_hw apple_dart_hw_t6000 = { + .type = DART_T6000, + .irq_handler = apple_dart_t8020_irq, + .invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb, .oas = 42, .fmt = APPLE_DART2, + .max_sid_count = 16, + + .enable_streams = DART_T8020_STREAMS_ENABLE, + .lock = DART_T8020_CONFIG, + .lock_bit = DART_T8020_CONFIG_LOCK, + + .error = DART_T8020_ERROR, + + .tcr = DART_T8020_TCR, + .tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE, + .tcr_disabled = 0, + .tcr_bypass = DART_T8020_TCR_BYPASS_DAPF | DART_T8020_TCR_BYPASS_DART, + + .ttbr = DART_T8020_TTBR, + .ttbr_valid = DART_T8020_TTBR_VALID, + .ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT, + .ttbr_shift = DART_T8020_TTBR_SHIFT, + .ttbr_count = 4, }; +static const struct apple_dart_hw apple_dart_hw_t8110 = { + .type = DART_T8110, + .irq_handler = apple_dart_t8110_irq, + .invalidate_tlb = apple_dart_t8110_hw_invalidate_tlb, + .fmt = APPLE_DART2, + .max_sid_count = 256, + + .enable_streams = DART_T8110_ENABLE_STREAMS, + .lock = DART_T8110_PROTECT, + .lock_bit = DART_T8110_PROTECT_TTBR_TCR, + + .error = DART_T8110_ERROR, + + .tcr = DART_T8110_TCR, + .tcr_enabled = DART_T8110_TCR_TRANSLATE_ENABLE, + .tcr_disabled = 0, + .tcr_bypass = DART_T8110_TCR_BYPASS_DAPF | DART_T8110_TCR_BYPASS_DART, + + .ttbr = DART_T8110_TTBR, + .ttbr_valid = DART_T8110_TTBR_VALID, + .ttbr_addr_field_shift = DART_T8110_TTBR_ADDR_FIELD_SHIFT, + .ttbr_shift = DART_T8110_TTBR_SHIFT, + .ttbr_count = 1, +}; + +static __maybe_unused int apple_dart_suspend(struct device *dev) +{ + struct apple_dart *dart = dev_get_drvdata(dev); + unsigned int sid, idx; + + for (sid = 0; sid < dart->num_streams; sid++) { + dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid)); + for (idx = 0; idx < dart->hw->ttbr_count; idx++) + dart->save_ttbr[sid][idx] = + readl(dart->regs + DART_TTBR(dart, sid, idx)); + } + + return 0; +} + +static __maybe_unused int apple_dart_resume(struct device *dev) +{ + struct apple_dart *dart = dev_get_drvdata(dev); + unsigned int sid, idx; + int ret; + + ret = apple_dart_hw_reset(dart); + if (ret) { + dev_err(dev, "Failed to reset DART on resume\n"); + return ret; + } + + for (sid = 0; sid < dart->num_streams; sid++) { + for (idx = 0; idx < dart->hw->ttbr_count; idx++) + writel(dart->save_ttbr[sid][idx], + dart->regs + DART_TTBR(dart, sid, idx)); + writel(dart->save_tcr[sid], dart->regs + DART_TCR(dart, sid)); + } + + return 0; +} + +DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume); + static const struct of_device_id apple_dart_of_match[] = { { .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 }, + { .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 }, { .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 }, {}, }; @@ -944,6 +1293,7 @@ static struct platform_driver apple_dart_driver = { .name = "apple-dart", .of_match_table = apple_dart_of_match, .suppress_bind_attrs = true, + .pm = pm_sleep_ptr(&apple_dart_pm_ops), }, .probe = apple_dart_probe, .remove = apple_dart_remove, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 91d404deb115..d7ad49aa997e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -250,6 +250,8 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { { .compatible = "qcom,sc7280-mdss" }, { .compatible = "qcom,sc7280-mss-pil" }, { .compatible = "qcom,sc8180x-mdss" }, + { .compatible = "qcom,sc8280xp-mdss" }, + { .compatible = "qcom,sm8150-mdss" }, { .compatible = "qcom,sm8250-mdss" }, { .compatible = "qcom,sdm845-mdss" }, { .compatible = "qcom,sdm845-mss-pil" }, diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 270c3d9128ba..d7be3adee426 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -387,28 +387,6 @@ static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev return 0; } -static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *dev) -{ - struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); - unsigned i; - - if (WARN_ON(!qcom_domain->iommu)) - return; - - pm_runtime_get_sync(qcom_iommu->dev); - for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); - - /* Disable the context bank: */ - iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0); - - ctx->domain = NULL; - } - pm_runtime_put_sync(qcom_iommu->dev); -} - static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) @@ -583,7 +561,6 @@ static const struct iommu_ops qcom_iommu_ops = { .pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = qcom_iommu_attach_dev, - .detach_dev = qcom_iommu_detach_dev, .map_pages = qcom_iommu_map, .unmap_pages = qcom_iommu_unmap, .flush_iotlb_all = qcom_iommu_flush_iotlb_all, diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f798c44e0903..99b2646cb5c7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -23,6 +23,7 @@ #include <linux/memremap.h> #include <linux/mm.h> #include <linux/mutex.h> +#include <linux/of_iommu.h> #include <linux/pci.h> #include <linux/scatterlist.h> #include <linux/spinlock.h> @@ -391,6 +392,8 @@ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) if (!is_of_node(dev_iommu_fwspec_get(dev)->iommu_fwnode)) iort_iommu_get_resv_regions(dev, list); + if (dev->of_node) + of_iommu_get_resv_regions(dev, list); } EXPORT_SYMBOL(iommu_dma_get_resv_regions); @@ -713,7 +716,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, if (!iova) return DMA_MAPPING_ERROR; - if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) { + if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) { iommu_dma_free_iova(cookie, iova, size, NULL); return DMA_MAPPING_ERROR; } @@ -822,7 +825,14 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev, if (!iova) goto out_free_pages; - if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, GFP_KERNEL)) + /* + * Remove the zone/policy flags from the GFP - these are applied to the + * __iommu_dma_alloc_pages() but are not used for the supporting + * internal allocations that follow. + */ + gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM | __GFP_COMP); + + if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, gfp)) goto out_free_iova; if (!(ioprot & IOMMU_CACHE)) { @@ -833,7 +843,8 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev, arch_dma_prep_coherent(sg_page(sg), sg->length); } - ret = iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot); + ret = iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, ioprot, + gfp); if (ret < 0 || ret < size) goto out_free_sg; @@ -1281,7 +1292,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * We'll leave any physical concatenation to the IOMMU driver's * implementation - it knows better than we do. */ - ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot); + ret = iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); if (ret < 0 || ret < iova_len) goto out_free_iova; @@ -1615,7 +1626,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!iova) goto out_free_page; - if (iommu_map(domain, iova, msi_addr, size, prot)) + if (iommu_map(domain, iova, msi_addr, size, prot, GFP_KERNEL)) goto out_free_iova; INIT_LIST_HEAD(&msi_page->list); diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index b0cde2211987..483aaaeb6dae 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -185,38 +185,43 @@ static sysmmu_pte_t *page_entry(sysmmu_pte_t *sent, sysmmu_iova_t iova) lv2table_base(sent)) + lv2ent_offset(iova); } -/* - * IOMMU fault information register - */ -struct sysmmu_fault_info { - unsigned int bit; /* bit number in STATUS register */ - unsigned short addr_reg; /* register to read VA fault address */ +struct sysmmu_fault { + sysmmu_iova_t addr; /* IOVA address that caused fault */ + const char *name; /* human readable fault name */ + unsigned int type; /* fault type for report_iommu_fault() */ +}; + +struct sysmmu_v1_fault_info { + unsigned short addr_reg; /* register to read IOVA fault address */ const char *name; /* human readable fault name */ unsigned int type; /* fault type for report_iommu_fault */ }; -static const struct sysmmu_fault_info sysmmu_faults[] = { - { 0, REG_PAGE_FAULT_ADDR, "PAGE", IOMMU_FAULT_READ }, - { 1, REG_AR_FAULT_ADDR, "AR MULTI-HIT", IOMMU_FAULT_READ }, - { 2, REG_AW_FAULT_ADDR, "AW MULTI-HIT", IOMMU_FAULT_WRITE }, - { 3, REG_DEFAULT_SLAVE_ADDR, "BUS ERROR", IOMMU_FAULT_READ }, - { 4, REG_AR_FAULT_ADDR, "AR SECURITY PROTECTION", IOMMU_FAULT_READ }, - { 5, REG_AR_FAULT_ADDR, "AR ACCESS PROTECTION", IOMMU_FAULT_READ }, - { 6, REG_AW_FAULT_ADDR, "AW SECURITY PROTECTION", IOMMU_FAULT_WRITE }, - { 7, REG_AW_FAULT_ADDR, "AW ACCESS PROTECTION", IOMMU_FAULT_WRITE }, +static const struct sysmmu_v1_fault_info sysmmu_v1_faults[] = { + { REG_PAGE_FAULT_ADDR, "PAGE", IOMMU_FAULT_READ }, + { REG_AR_FAULT_ADDR, "MULTI-HIT", IOMMU_FAULT_READ }, + { REG_AW_FAULT_ADDR, "MULTI-HIT", IOMMU_FAULT_WRITE }, + { REG_DEFAULT_SLAVE_ADDR, "BUS ERROR", IOMMU_FAULT_READ }, + { REG_AR_FAULT_ADDR, "SECURITY PROTECTION", IOMMU_FAULT_READ }, + { REG_AR_FAULT_ADDR, "ACCESS PROTECTION", IOMMU_FAULT_READ }, + { REG_AW_FAULT_ADDR, "SECURITY PROTECTION", IOMMU_FAULT_WRITE }, + { REG_AW_FAULT_ADDR, "ACCESS PROTECTION", IOMMU_FAULT_WRITE }, +}; + +/* SysMMU v5 has the same faults for AR (0..4 bits) and AW (16..20 bits) */ +static const char * const sysmmu_v5_fault_names[] = { + "PTW", + "PAGE", + "MULTI-HIT", + "ACCESS PROTECTION", + "SECURITY PROTECTION" }; -static const struct sysmmu_fault_info sysmmu_v5_faults[] = { - { 0, REG_V5_FAULT_AR_VA, "AR PTW", IOMMU_FAULT_READ }, - { 1, REG_V5_FAULT_AR_VA, "AR PAGE", IOMMU_FAULT_READ }, - { 2, REG_V5_FAULT_AR_VA, "AR MULTI-HIT", IOMMU_FAULT_READ }, - { 3, REG_V5_FAULT_AR_VA, "AR ACCESS PROTECTION", IOMMU_FAULT_READ }, - { 4, REG_V5_FAULT_AR_VA, "AR SECURITY PROTECTION", IOMMU_FAULT_READ }, - { 16, REG_V5_FAULT_AW_VA, "AW PTW", IOMMU_FAULT_WRITE }, - { 17, REG_V5_FAULT_AW_VA, "AW PAGE", IOMMU_FAULT_WRITE }, - { 18, REG_V5_FAULT_AW_VA, "AW MULTI-HIT", IOMMU_FAULT_WRITE }, - { 19, REG_V5_FAULT_AW_VA, "AW ACCESS PROTECTION", IOMMU_FAULT_WRITE }, - { 20, REG_V5_FAULT_AW_VA, "AW SECURITY PROTECTION", IOMMU_FAULT_WRITE }, +static const char * const sysmmu_v7_fault_names[] = { + "PTW", + "PAGE", + "ACCESS PROTECTION", + "RESERVED" }; /* @@ -246,9 +251,12 @@ struct exynos_iommu_domain { struct iommu_domain domain; /* generic domain data structure */ }; +struct sysmmu_drvdata; + /* * SysMMU version specific data. Contains offsets for the registers which can * be found in different SysMMU variants, but have different offset values. + * Also contains version specific callbacks to abstract the hardware. */ struct sysmmu_variant { u32 pt_base; /* page table base address (physical) */ @@ -259,6 +267,11 @@ struct sysmmu_variant { u32 flush_end; /* end address of range invalidation */ u32 int_status; /* interrupt status information */ u32 int_clear; /* clear the interrupt */ + u32 fault_va; /* IOVA address that caused fault */ + u32 fault_info; /* fault transaction info */ + + int (*get_fault_info)(struct sysmmu_drvdata *data, unsigned int itype, + struct sysmmu_fault *fault); }; /* @@ -293,6 +306,59 @@ struct sysmmu_drvdata { #define SYSMMU_REG(data, reg) ((data)->sfrbase + (data)->variant->reg) +static int exynos_sysmmu_v1_get_fault_info(struct sysmmu_drvdata *data, + unsigned int itype, + struct sysmmu_fault *fault) +{ + const struct sysmmu_v1_fault_info *finfo; + + if (itype >= ARRAY_SIZE(sysmmu_v1_faults)) + return -ENXIO; + + finfo = &sysmmu_v1_faults[itype]; + fault->addr = readl(data->sfrbase + finfo->addr_reg); + fault->name = finfo->name; + fault->type = finfo->type; + + return 0; +} + +static int exynos_sysmmu_v5_get_fault_info(struct sysmmu_drvdata *data, + unsigned int itype, + struct sysmmu_fault *fault) +{ + unsigned int addr_reg; + + if (itype < ARRAY_SIZE(sysmmu_v5_fault_names)) { + fault->type = IOMMU_FAULT_READ; + addr_reg = REG_V5_FAULT_AR_VA; + } else if (itype >= 16 && itype <= 20) { + fault->type = IOMMU_FAULT_WRITE; + addr_reg = REG_V5_FAULT_AW_VA; + itype -= 16; + } else { + return -ENXIO; + } + + fault->name = sysmmu_v5_fault_names[itype]; + fault->addr = readl(data->sfrbase + addr_reg); + + return 0; +} + +static int exynos_sysmmu_v7_get_fault_info(struct sysmmu_drvdata *data, + unsigned int itype, + struct sysmmu_fault *fault) +{ + u32 info = readl(SYSMMU_REG(data, fault_info)); + + fault->addr = readl(SYSMMU_REG(data, fault_va)); + fault->name = sysmmu_v7_fault_names[itype % 4]; + fault->type = (info & BIT(20)) ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; + + return 0; +} + /* SysMMU v1..v3 */ static const struct sysmmu_variant sysmmu_v1_variant = { .flush_all = 0x0c, @@ -300,9 +366,11 @@ static const struct sysmmu_variant sysmmu_v1_variant = { .pt_base = 0x14, .int_status = 0x18, .int_clear = 0x1c, + + .get_fault_info = exynos_sysmmu_v1_get_fault_info, }; -/* SysMMU v5 and v7 (non-VM capable) */ +/* SysMMU v5 */ static const struct sysmmu_variant sysmmu_v5_variant = { .pt_base = 0x0c, .flush_all = 0x10, @@ -312,9 +380,27 @@ static const struct sysmmu_variant sysmmu_v5_variant = { .flush_end = 0x24, .int_status = 0x60, .int_clear = 0x64, + + .get_fault_info = exynos_sysmmu_v5_get_fault_info, }; -/* SysMMU v7: VM capable register set */ +/* SysMMU v7: non-VM capable register layout */ +static const struct sysmmu_variant sysmmu_v7_variant = { + .pt_base = 0x0c, + .flush_all = 0x10, + .flush_entry = 0x14, + .flush_range = 0x18, + .flush_start = 0x20, + .flush_end = 0x24, + .int_status = 0x60, + .int_clear = 0x64, + .fault_va = 0x70, + .fault_info = 0x78, + + .get_fault_info = exynos_sysmmu_v7_get_fault_info, +}; + +/* SysMMU v7: VM capable register layout */ static const struct sysmmu_variant sysmmu_v7_vm_variant = { .pt_base = 0x800c, .flush_all = 0x8010, @@ -324,6 +410,10 @@ static const struct sysmmu_variant sysmmu_v7_vm_variant = { .flush_end = 0x8024, .int_status = 0x60, .int_clear = 0x64, + .fault_va = 0x1000, + .fault_info = 0x1004, + + .get_fault_info = exynos_sysmmu_v7_get_fault_info, }; static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom) @@ -446,75 +536,63 @@ static void __sysmmu_get_version(struct sysmmu_drvdata *data) if (data->has_vcr) data->variant = &sysmmu_v7_vm_variant; else - data->variant = &sysmmu_v5_variant; + data->variant = &sysmmu_v7_variant; } __sysmmu_disable_clocks(data); } static void show_fault_information(struct sysmmu_drvdata *data, - const struct sysmmu_fault_info *finfo, - sysmmu_iova_t fault_addr) + const struct sysmmu_fault *fault) { sysmmu_pte_t *ent; - dev_err(data->sysmmu, "%s: %s FAULT occurred at %#x\n", - dev_name(data->master), finfo->name, fault_addr); + dev_err(data->sysmmu, "%s: [%s] %s FAULT occurred at %#x\n", + dev_name(data->master), + fault->type == IOMMU_FAULT_READ ? "READ" : "WRITE", + fault->name, fault->addr); dev_dbg(data->sysmmu, "Page table base: %pa\n", &data->pgtable); - ent = section_entry(phys_to_virt(data->pgtable), fault_addr); + ent = section_entry(phys_to_virt(data->pgtable), fault->addr); dev_dbg(data->sysmmu, "\tLv1 entry: %#x\n", *ent); if (lv1ent_page(ent)) { - ent = page_entry(ent, fault_addr); + ent = page_entry(ent, fault->addr); dev_dbg(data->sysmmu, "\t Lv2 entry: %#x\n", *ent); } } static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id) { - /* SYSMMU is in blocked state when interrupt occurred. */ struct sysmmu_drvdata *data = dev_id; - const struct sysmmu_fault_info *finfo; - unsigned int i, n, itype; - sysmmu_iova_t fault_addr; + unsigned int itype; + struct sysmmu_fault fault; int ret = -ENOSYS; WARN_ON(!data->active); - if (MMU_MAJ_VER(data->version) < 5) { - finfo = sysmmu_faults; - n = ARRAY_SIZE(sysmmu_faults); - } else { - finfo = sysmmu_v5_faults; - n = ARRAY_SIZE(sysmmu_v5_faults); - } - spin_lock(&data->lock); - clk_enable(data->clk_master); itype = __ffs(readl(SYSMMU_REG(data, int_status))); - for (i = 0; i < n; i++, finfo++) - if (finfo->bit == itype) - break; - /* unknown/unsupported fault */ - BUG_ON(i == n); - - /* print debug message */ - fault_addr = readl(data->sfrbase + finfo->addr_reg); - show_fault_information(data, finfo, fault_addr); - - if (data->domain) - ret = report_iommu_fault(&data->domain->domain, - data->master, fault_addr, finfo->type); - /* fault is not recovered by fault handler */ - BUG_ON(ret != 0); + ret = data->variant->get_fault_info(data, itype, &fault); + if (ret) { + dev_err(data->sysmmu, "Unhandled interrupt bit %u\n", itype); + goto out; + } + show_fault_information(data, &fault); + if (data->domain) { + ret = report_iommu_fault(&data->domain->domain, data->master, + fault.addr, fault.type); + } + if (ret) + panic("Unrecoverable System MMU Fault!"); + +out: writel(1 << itype, SYSMMU_REG(data, int_clear)); + /* SysMMU is in blocked state when interrupt occurred */ sysmmu_unblock(data); - clk_disable(data->clk_master); - spin_unlock(&data->lock); return IRQ_HANDLED; @@ -1346,8 +1424,10 @@ static void exynos_iommu_release_device(struct device *dev) struct iommu_group *group = iommu_group_get(dev); if (group) { +#ifndef CONFIG_ARM WARN_ON(owner->domain != iommu_group_default_domain(group)); +#endif exynos_iommu_detach_device(owner->domain, dev); iommu_group_put(group); } @@ -1398,13 +1478,15 @@ static int exynos_iommu_of_xlate(struct device *dev, static const struct iommu_ops exynos_iommu_ops = { .domain_alloc = exynos_iommu_domain_alloc, .device_group = generic_device_group, +#ifdef CONFIG_ARM + .set_platform_dma_ops = exynos_iommu_release_device, +#endif .probe_device = exynos_iommu_probe_device, .release_device = exynos_iommu_release_device, .pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE, .of_xlate = exynos_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = exynos_iommu_attach_device, - .detach_dev = exynos_iommu_detach_device, .map = exynos_iommu_map, .unmap = exynos_iommu_unmap, .iova_to_phys = exynos_iommu_iova_to_phys, @@ -1446,7 +1528,7 @@ static int __init exynos_iommu_init(void) return 0; err_reg_driver: - platform_driver_unregister(&exynos_sysmmu_driver); + kmem_cache_free(lv2table_kmem_cache, zero_lv2_table); err_zero_lv2: kmem_cache_destroy(lv2table_kmem_cache); return ret; diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index 4408ac3c49b6..bce372297099 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -283,9 +283,9 @@ static int fsl_pamu_attach_device(struct iommu_domain *domain, return ret; } -static void fsl_pamu_detach_device(struct iommu_domain *domain, - struct device *dev) +static void fsl_pamu_set_platform_dma(struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); const u32 *prop; int len; @@ -452,9 +452,9 @@ static const struct iommu_ops fsl_pamu_ops = { .domain_alloc = fsl_pamu_domain_alloc, .probe_device = fsl_pamu_probe_device, .device_group = fsl_pamu_device_group, + .set_platform_dma_ops = fsl_pamu_set_platform_dma, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = fsl_pamu_attach_device, - .detach_dev = fsl_pamu_detach_device, .iova_to_phys = fsl_pamu_iova_to_phys, .free = fsl_pamu_domain_free, } diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index b7dff5092fd2..12e1e90fdae1 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -96,4 +96,15 @@ config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON passing intel_iommu=sm_on to the kernel. If not sure, please use the default value. +config INTEL_IOMMU_PERF_EVENTS + def_bool y + bool "Intel IOMMU performance events" + depends on INTEL_IOMMU && PERF_EVENTS + help + Selecting this option will enable the performance monitoring + infrastructure in the Intel IOMMU. It collects information about + key events occurring during operation of the remapping hardware, + to aid performance tuning and debug. These are available on modern + processors which support Intel VT-d 4.0 and later. + endif # INTEL_IOMMU diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index fa0dae16441c..7af3b8a4f2a0 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_DMAR_PERF) += perf.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o +obj-$(CONFIG_INTEL_IOMMU_PERF_EVENTS) += perfmon.o diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b00a0ceb2d13..6acfe879589c 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -34,6 +34,7 @@ #include "../irq_remapping.h" #include "perf.h" #include "trace.h" +#include "perfmon.h" typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *); struct dmar_res_callback { @@ -427,6 +428,8 @@ static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg) memcpy(dmaru->hdr, header, header->length); dmaru->reg_base_addr = drhd->address; dmaru->segment = drhd->segment; + /* The size of the register set is 2 ^ N 4 KB pages. */ + dmaru->reg_size = 1UL << (drhd->size + 12); dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */ dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1), ((void *)drhd) + drhd->header.length, @@ -956,17 +959,18 @@ static void unmap_iommu(struct intel_iommu *iommu) /** * map_iommu: map the iommu's registers * @iommu: the iommu to map - * @phys_addr: the physical address of the base resgister + * @drhd: DMA remapping hardware definition structure * * Memory map the iommu's registers. Start w/ a single page, and * possibly expand if that turns out to be insufficent. */ -static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) +static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd) { + u64 phys_addr = drhd->reg_base_addr; int map_size, err=0; iommu->reg_phys = phys_addr; - iommu->reg_size = VTD_PAGE_SIZE; + iommu->reg_size = drhd->reg_size; if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) { pr_err("Can't reserve memory\n"); @@ -1013,6 +1017,16 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) goto release; } } + + if (cap_ecmds(iommu->cap)) { + int i; + + for (i = 0; i < DMA_MAX_NUM_ECMDCAP; i++) { + iommu->ecmdcap[i] = dmar_readq(iommu->reg + DMAR_ECCAP_REG + + i * DMA_ECMD_REG_STEP); + } + } + err = 0; goto out; @@ -1050,7 +1064,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) } sprintf(iommu->name, "dmar%d", iommu->seq_id); - err = map_iommu(iommu, drhd->reg_base_addr); + err = map_iommu(iommu, drhd); if (err) { pr_err("Failed to map %s\n", iommu->name); goto error_free_seq_id; @@ -1103,6 +1117,9 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) if (sts & DMA_GSTS_QIES) iommu->gcmd |= DMA_GCMD_QIE; + if (alloc_iommu_pmu(iommu)) + pr_debug("Cannot alloc PMU for iommu (seq_id = %d)\n", iommu->seq_id); + raw_spin_lock_init(&iommu->register_lock); /* @@ -1127,6 +1144,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); if (err) goto err_sysfs; + + iommu_pmu_register(iommu); } drhd->iommu = iommu; @@ -1137,6 +1156,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) err_sysfs: iommu_device_sysfs_remove(&iommu->iommu); err_unmap: + free_iommu_pmu(iommu); unmap_iommu(iommu); error_free_seq_id: ida_free(&dmar_seq_ids, iommu->seq_id); @@ -1148,10 +1168,13 @@ error: static void free_iommu(struct intel_iommu *iommu) { if (intel_iommu_enabled && !iommu->drhd->ignored) { + iommu_pmu_unregister(iommu); iommu_device_unregister(&iommu->iommu); iommu_device_sysfs_remove(&iommu->iommu); } + free_iommu_pmu(iommu); + if (iommu->irq) { if (iommu->pr_irq) { free_irq(iommu->pr_irq, iommu); @@ -1859,6 +1882,8 @@ static inline int dmar_msi_reg(struct intel_iommu *iommu, int irq) return DMAR_FECTL_REG; else if (iommu->pr_irq == irq) return DMAR_PECTL_REG; + else if (iommu->perf_irq == irq) + return DMAR_PERFINTRCTL_REG; else BUG(); } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 59df7e42fd53..86ee06ac058b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -16,7 +16,6 @@ #include <linux/crash_dump.h> #include <linux/dma-direct.h> #include <linux/dmi.h> -#include <linux/intel-svm.h> #include <linux/memory.h> #include <linux/pci.h> #include <linux/pci-ats.h> @@ -30,6 +29,7 @@ #include "../iommu-sva.h" #include "pasid.h" #include "cap_audit.h" +#include "perfmon.h" #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE @@ -362,12 +362,12 @@ static int __init intel_iommu_setup(char *str) } __setup("intel_iommu=", intel_iommu_setup); -void *alloc_pgtable_page(int node) +void *alloc_pgtable_page(int node, gfp_t gfp) { struct page *page; void *vaddr = NULL; - page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0); + page = alloc_pages_node(node, gfp | __GFP_ZERO, 0); if (page) vaddr = page_address(page); return vaddr; @@ -612,7 +612,7 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, if (!alloc) return NULL; - context = alloc_pgtable_page(iommu->node); + context = alloc_pgtable_page(iommu->node, GFP_ATOMIC); if (!context) return NULL; @@ -908,7 +908,8 @@ pgtable_walk: #endif static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, - unsigned long pfn, int *target_level) + unsigned long pfn, int *target_level, + gfp_t gfp) { struct dma_pte *parent, *pte; int level = agaw_to_level(domain->agaw); @@ -935,7 +936,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, if (!dma_pte_present(pte)) { uint64_t pteval; - tmp_page = alloc_pgtable_page(domain->nid); + tmp_page = alloc_pgtable_page(domain->nid, gfp); if (!tmp_page) return NULL; @@ -1186,7 +1187,7 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu) { struct root_entry *root; - root = (struct root_entry *)alloc_pgtable_page(iommu->node); + root = (struct root_entry *)alloc_pgtable_page(iommu->node, GFP_ATOMIC); if (!root) { pr_err("Allocating root entry for %s failed\n", iommu->name); @@ -2150,7 +2151,8 @@ static void switch_to_super_page(struct dmar_domain *domain, while (start_pfn <= end_pfn) { if (!pte) - pte = pfn_to_dma_pte(domain, start_pfn, &level); + pte = pfn_to_dma_pte(domain, start_pfn, &level, + GFP_ATOMIC); if (dma_pte_present(pte)) { dma_pte_free_pagetable(domain, start_pfn, @@ -2172,7 +2174,8 @@ static void switch_to_super_page(struct dmar_domain *domain, static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, - unsigned long phys_pfn, unsigned long nr_pages, int prot) + unsigned long phys_pfn, unsigned long nr_pages, int prot, + gfp_t gfp) { struct dma_pte *first_pte = NULL, *pte = NULL; unsigned int largepage_lvl = 0; @@ -2202,7 +2205,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, nr_pages); - pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl); + pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl, + gfp); if (!pte) return -ENOMEM; first_pte = pte; @@ -2368,7 +2372,7 @@ static int iommu_domain_identity_map(struct dmar_domain *domain, return __domain_mapping(domain, first_vpfn, first_vpfn, last_vpfn - first_vpfn + 1, - DMA_PTE_READ|DMA_PTE_WRITE); + DMA_PTE_READ|DMA_PTE_WRITE, GFP_KERNEL); } static int md_domain_init(struct dmar_domain *domain, int guest_width); @@ -2676,7 +2680,7 @@ static int copy_context_table(struct intel_iommu *iommu, if (!old_ce) goto out; - new_ce = alloc_pgtable_page(iommu->node); + new_ce = alloc_pgtable_page(iommu->node, GFP_KERNEL); if (!new_ce) goto out_unmap; @@ -4005,7 +4009,8 @@ int __init intel_iommu_init(void) * is likely to be much lower than the overhead of synchronizing * the virtual and physical IOMMU page-tables. */ - if (cap_caching_mode(iommu->cap)) { + if (cap_caching_mode(iommu->cap) && + !first_level_by_default(IOMMU_DOMAIN_DMA)) { pr_info_once("IOMMU batching disallowed due to virtualization\n"); iommu_set_dma_strict(); } @@ -4013,6 +4018,8 @@ int __init intel_iommu_init(void) intel_iommu_groups, "%s", iommu->name); iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); + + iommu_pmu_register(iommu); } up_read(&dmar_global_lock); @@ -4136,7 +4143,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->max_addr = 0; /* always allocate the top pgd */ - domain->pgd = alloc_pgtable_page(domain->nid); + domain->pgd = alloc_pgtable_page(domain->nid, GFP_ATOMIC); if (!domain->pgd) return -ENOMEM; domain_flush_cache(domain, domain->pgd, PAGE_SIZE); @@ -4298,7 +4305,7 @@ static int intel_iommu_map(struct iommu_domain *domain, the low bits of hpa would take us onto the next page */ size = aligned_nrpages(hpa, size); return __domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT, - hpa >> VTD_PAGE_SHIFT, size, prot); + hpa >> VTD_PAGE_SHIFT, size, prot, gfp); } static int intel_iommu_map_pages(struct iommu_domain *domain, @@ -4333,7 +4340,8 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, /* Cope with horrid API which requires us to unmap more than the size argument if it happens to be a large-page mapping. */ - BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level)); + BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level, + GFP_ATOMIC)); if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); @@ -4346,7 +4354,12 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, if (dmar_domain->max_addr == iova + size) dmar_domain->max_addr = iova; - iommu_iotlb_gather_add_page(domain, gather, iova, size); + /* + * We do not use page-selective IOTLB invalidation in flush queue, + * so there is no need to track page and sync iotlb. + */ + if (!iommu_iotlb_gather_queued(gather)) + iommu_iotlb_gather_add_page(domain, gather, iova, size); return size; } @@ -4392,7 +4405,8 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, int level = 0; u64 phys = 0; - pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); + pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level, + GFP_ATOMIC); if (pte && dma_pte_present(pte)) phys = dma_pte_addr(pte) + (iova & (BIT_MASK(level_to_offset_bits(level) + @@ -4642,8 +4656,12 @@ static int intel_iommu_enable_sva(struct device *dev) return -EINVAL; ret = iopf_queue_add_device(iommu->iopf_queue, dev); - if (!ret) - ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + if (ret) + return ret; + + ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + if (ret) + iopf_queue_remove_device(iommu->iopf_queue, dev); return ret; } @@ -4655,8 +4673,12 @@ static int intel_iommu_disable_sva(struct device *dev) int ret; ret = iommu_unregister_device_fault_handler(dev); - if (!ret) - ret = iopf_queue_remove_device(iommu->iopf_queue, dev); + if (ret) + return ret; + + ret = iopf_queue_remove_device(iommu->iopf_queue, dev); + if (ret) + iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); return ret; } @@ -5023,3 +5045,59 @@ void quirk_extra_dev_tlb_flush(struct device_domain_info *info, pasid, qdep, address, mask); } } + +#define ecmd_get_status_code(res) (((res) & 0xff) >> 1) + +/* + * Function to submit a command to the enhanced command interface. The + * valid enhanced command descriptions are defined in Table 47 of the + * VT-d spec. The VT-d hardware implementation may support some but not + * all commands, which can be determined by checking the Enhanced + * Command Capability Register. + * + * Return values: + * - 0: Command successful without any error; + * - Negative: software error value; + * - Nonzero positive: failure status code defined in Table 48. + */ +int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob) +{ + unsigned long flags; + u64 res; + int ret; + + if (!cap_ecmds(iommu->cap)) + return -ENODEV; + + raw_spin_lock_irqsave(&iommu->register_lock, flags); + + res = dmar_readq(iommu->reg + DMAR_ECRSP_REG); + if (res & DMA_ECMD_ECRSP_IP) { + ret = -EBUSY; + goto err; + } + + /* + * Unconditionally write the operand B, because + * - There is no side effect if an ecmd doesn't require an + * operand B, but we set the register to some value. + * - It's not invoked in any critical path. The extra MMIO + * write doesn't bring any performance concerns. + */ + dmar_writeq(iommu->reg + DMAR_ECEO_REG, ob); + dmar_writeq(iommu->reg + DMAR_ECMD_REG, ecmd | (oa << DMA_ECMD_OA_SHIFT)); + + IOMMU_WAIT_OP(iommu, DMAR_ECRSP_REG, dmar_readq, + !(res & DMA_ECMD_ECRSP_IP), res); + + if (res & DMA_ECMD_ECRSP_IP) { + ret = -ETIMEDOUT; + goto err; + } + + ret = ecmd_get_status_code(res); +err: + raw_spin_unlock_irqrestore(&iommu->register_lock, flags); + + return ret; +} diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 06e61e474856..d6df3b865812 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -22,6 +22,7 @@ #include <linux/ioasid.h> #include <linux/bitfield.h> #include <linux/xarray.h> +#include <linux/perf_event.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -125,6 +126,17 @@ #define DMAR_MTRR_PHYSMASK8_REG 0x208 #define DMAR_MTRR_PHYSBASE9_REG 0x210 #define DMAR_MTRR_PHYSMASK9_REG 0x218 +#define DMAR_PERFCAP_REG 0x300 +#define DMAR_PERFCFGOFF_REG 0x310 +#define DMAR_PERFOVFOFF_REG 0x318 +#define DMAR_PERFCNTROFF_REG 0x31c +#define DMAR_PERFINTRSTS_REG 0x324 +#define DMAR_PERFINTRCTL_REG 0x328 +#define DMAR_PERFEVNTCAP_REG 0x380 +#define DMAR_ECMD_REG 0x400 +#define DMAR_ECEO_REG 0x408 +#define DMAR_ECRSP_REG 0x410 +#define DMAR_ECCAP_REG 0x430 #define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ #define DMAR_VCMD_REG 0xe00 /* Virtual command register */ #define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ @@ -148,6 +160,7 @@ */ #define cap_esrtps(c) (((c) >> 63) & 1) #define cap_esirtps(c) (((c) >> 62) & 1) +#define cap_ecmds(c) (((c) >> 61) & 1) #define cap_fl5lp_support(c) (((c) >> 60) & 1) #define cap_pi_support(c) (((c) >> 59) & 1) #define cap_fl1gp_support(c) (((c) >> 56) & 1) @@ -179,7 +192,8 @@ * Extended Capability Register */ -#define ecap_rps(e) (((e) >> 49) & 0x1) +#define ecap_pms(e) (((e) >> 51) & 0x1) +#define ecap_rps(e) (((e) >> 49) & 0x1) #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) @@ -210,6 +224,22 @@ #define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) #define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ +/* + * Decoding Perf Capability Register + */ +#define pcap_num_cntr(p) ((p) & 0xffff) +#define pcap_cntr_width(p) (((p) >> 16) & 0x7f) +#define pcap_num_event_group(p) (((p) >> 24) & 0x1f) +#define pcap_filters_mask(p) (((p) >> 32) & 0x1f) +#define pcap_interrupt(p) (((p) >> 50) & 0x1) +/* The counter stride is calculated as 2 ^ (x+10) bytes */ +#define pcap_cntr_stride(p) (1ULL << ((((p) >> 52) & 0x7) + 10)) + +/* + * Decoding Perf Event Capability Register + */ +#define pecap_es(p) ((p) & 0xfffffff) + /* Virtual command interface capability */ #define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ @@ -281,6 +311,26 @@ #define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16) #define DMA_CCMD_DID(d) ((u64)((d) & 0xffff)) +/* ECMD_REG */ +#define DMA_MAX_NUM_ECMD 256 +#define DMA_MAX_NUM_ECMDCAP (DMA_MAX_NUM_ECMD / 64) +#define DMA_ECMD_REG_STEP 8 +#define DMA_ECMD_ENABLE 0xf0 +#define DMA_ECMD_DISABLE 0xf1 +#define DMA_ECMD_FREEZE 0xf4 +#define DMA_ECMD_UNFREEZE 0xf5 +#define DMA_ECMD_OA_SHIFT 16 +#define DMA_ECMD_ECRSP_IP 0x1 +#define DMA_ECMD_ECCAP3 3 +#define DMA_ECMD_ECCAP3_ECNTS BIT_ULL(48) +#define DMA_ECMD_ECCAP3_DCNTS BIT_ULL(49) +#define DMA_ECMD_ECCAP3_FCNTS BIT_ULL(52) +#define DMA_ECMD_ECCAP3_UFCNTS BIT_ULL(53) +#define DMA_ECMD_ECCAP3_ESSENTIAL (DMA_ECMD_ECCAP3_ECNTS | \ + DMA_ECMD_ECCAP3_DCNTS | \ + DMA_ECMD_ECCAP3_FCNTS | \ + DMA_ECMD_ECCAP3_UFCNTS) + /* FECTL_REG */ #define DMA_FECTL_IM (((u32)1) << 31) @@ -309,6 +359,9 @@ #define DMA_VCS_PAS ((u64)1) +/* PERFINTRSTS_REG */ +#define DMA_PERFINTRSTS_PIS ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ @@ -438,6 +491,11 @@ struct q_inval { int free_cnt; }; +/* Page Request Queue depth */ +#define PRQ_ORDER 4 +#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) +#define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) + struct dmar_pci_notify_info; #ifdef CONFIG_IRQ_REMAP @@ -554,6 +612,40 @@ struct dmar_domain { iommu core */ }; +/* + * In theory, the VT-d 4.0 spec can support up to 2 ^ 16 counters. + * But in practice, there are only 14 counters for the existing + * platform. Setting the max number of counters to 64 should be good + * enough for a long time. Also, supporting more than 64 counters + * requires more extras, e.g., extra freeze and overflow registers, + * which is not necessary for now. + */ +#define IOMMU_PMU_IDX_MAX 64 + +struct iommu_pmu { + struct intel_iommu *iommu; + u32 num_cntr; /* Number of counters */ + u32 num_eg; /* Number of event group */ + u32 cntr_width; /* Counter width */ + u32 cntr_stride; /* Counter Stride */ + u32 filter; /* Bitmask of filter support */ + void __iomem *base; /* the PerfMon base address */ + void __iomem *cfg_reg; /* counter configuration base address */ + void __iomem *cntr_reg; /* counter 0 address*/ + void __iomem *overflow; /* overflow status register */ + + u64 *evcap; /* Indicates all supported events */ + u32 **cntr_evcap; /* Supported events of each counter. */ + + struct pmu pmu; + DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX); + struct perf_event *event_list[IOMMU_PMU_IDX_MAX]; + unsigned char irq_name[16]; +}; + +#define IOMMU_IRQ_ID_OFFSET_PRQ (DMAR_UNITS_SUPPORTED) +#define IOMMU_IRQ_ID_OFFSET_PERF (2 * DMAR_UNITS_SUPPORTED) + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -561,12 +653,13 @@ struct intel_iommu { u64 cap; u64 ecap; u64 vccap; + u64 ecmdcap[DMA_MAX_NUM_ECMDCAP]; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ int msagaw; /* max sagaw of this iommu */ - unsigned int irq, pr_irq; + unsigned int irq, pr_irq, perf_irq; u16 segment; /* PCI segment# */ unsigned char name[13]; /* Device Name */ @@ -600,6 +693,8 @@ struct intel_iommu { struct dmar_drhd_unit *drhd; void *perf_statistic; + + struct iommu_pmu *pmu; }; /* PCI domain-device relationship */ @@ -737,7 +832,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, extern int dmar_ir_support(void); -void *alloc_pgtable_page(int node); +void *alloc_pgtable_page(int node, gfp_t gfp); void free_pgtable_page(void *vaddr); void iommu_flush_write_buffer(struct intel_iommu *iommu); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); @@ -756,19 +851,13 @@ struct intel_svm_dev { struct rcu_head rcu; struct device *dev; struct intel_iommu *iommu; - struct iommu_sva sva; - u32 pasid; - int users; u16 did; - u16 dev_iotlb:1; u16 sid, qdep; }; struct intel_svm { struct mmu_notifier notifier; struct mm_struct *mm; - - unsigned int flags; u32 pasid; struct list_head devs; }; @@ -800,6 +889,14 @@ extern const struct iommu_ops intel_iommu_ops; extern int intel_iommu_sm; extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); +int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob); + +static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu) +{ + return (iommu->ecmdcap[DMA_ECMD_ECCAP3] & DMA_ECMD_ECCAP3_ESSENTIAL) == + DMA_ECMD_ECCAP3_ESSENTIAL; +} + extern int dmar_disabled; extern int intel_iommu_enabled; #else diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index fb3c7020028d..633e0a4a01e7 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -128,6 +128,9 @@ int intel_pasid_alloc_table(struct device *dev) pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3); info->pasid_table = pasid_table; + if (!ecap_coherent(info->iommu->ecap)) + clflush_cache_range(pasid_table->table, size); + return 0; } @@ -200,7 +203,7 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) retry: entries = get_pasid_table_from_pde(&dir[dir_index]); if (!entries) { - entries = alloc_pgtable_page(info->iommu->node); + entries = alloc_pgtable_page(info->iommu->node, GFP_ATOMIC); if (!entries) return NULL; @@ -215,6 +218,10 @@ retry: free_pgtable_page(entries); goto retry; } + if (!ecap_coherent(info->iommu->ecap)) { + clflush_cache_range(entries, VTD_PAGE_SIZE); + clflush_cache_range(&dir[dir_index].val, sizeof(*dir)); + } } return &entries[index]; @@ -365,6 +372,16 @@ static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value) } /* + * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID + * entry. It is required when XD bit of the first level page table + * entry is about to be set. + */ +static inline void pasid_set_nxe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5); +} + +/* * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode * PASID entry. */ @@ -557,6 +574,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, pasid_set_domain_id(pte, did); pasid_set_address_width(pte, iommu->agaw); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); + pasid_set_nxe(pte); /* Setup Present and PASID Granular Transfer Type: */ pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY); diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c new file mode 100644 index 000000000000..e17d9743a0d8 --- /dev/null +++ b/drivers/iommu/intel/perfmon.c @@ -0,0 +1,877 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Support Intel IOMMU PerfMon + * Copyright(c) 2023 Intel Corporation. + */ +#define pr_fmt(fmt) "DMAR: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include <linux/dmar.h> +#include "iommu.h" +#include "perfmon.h" + +PMU_FORMAT_ATTR(event, "config:0-27"); /* ES: Events Select */ +PMU_FORMAT_ATTR(event_group, "config:28-31"); /* EGI: Event Group Index */ + +static struct attribute *iommu_pmu_format_attrs[] = { + &format_attr_event_group.attr, + &format_attr_event.attr, + NULL +}; + +static struct attribute_group iommu_pmu_format_attr_group = { + .name = "format", + .attrs = iommu_pmu_format_attrs, +}; + +/* The available events are added in attr_update later */ +static struct attribute *attrs_empty[] = { + NULL +}; + +static struct attribute_group iommu_pmu_events_attr_group = { + .name = "events", + .attrs = attrs_empty, +}; + +static cpumask_t iommu_pmu_cpu_mask; + +static ssize_t +cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &iommu_pmu_cpu_mask); +} +static DEVICE_ATTR_RO(cpumask); + +static struct attribute *iommu_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static struct attribute_group iommu_pmu_cpumask_attr_group = { + .attrs = iommu_pmu_cpumask_attrs, +}; + +static const struct attribute_group *iommu_pmu_attr_groups[] = { + &iommu_pmu_format_attr_group, + &iommu_pmu_events_attr_group, + &iommu_pmu_cpumask_attr_group, + NULL +}; + +static inline struct iommu_pmu *dev_to_iommu_pmu(struct device *dev) +{ + /* + * The perf_event creates its own dev for each PMU. + * See pmu_dev_alloc() + */ + return container_of(dev_get_drvdata(dev), struct iommu_pmu, pmu); +} + +#define IOMMU_PMU_ATTR(_name, _format, _filter) \ + PMU_FORMAT_ATTR(_name, _format); \ + \ +static struct attribute *_name##_attr[] = { \ + &format_attr_##_name.attr, \ + NULL \ +}; \ + \ +static umode_t \ +_name##_is_visible(struct kobject *kobj, struct attribute *attr, int i) \ +{ \ + struct device *dev = kobj_to_dev(kobj); \ + struct iommu_pmu *iommu_pmu = dev_to_iommu_pmu(dev); \ + \ + if (!iommu_pmu) \ + return 0; \ + return (iommu_pmu->filter & _filter) ? attr->mode : 0; \ +} \ + \ +static struct attribute_group _name = { \ + .name = "format", \ + .attrs = _name##_attr, \ + .is_visible = _name##_is_visible, \ +}; + +IOMMU_PMU_ATTR(filter_requester_id_en, "config1:0", IOMMU_PMU_FILTER_REQUESTER_ID); +IOMMU_PMU_ATTR(filter_domain_en, "config1:1", IOMMU_PMU_FILTER_DOMAIN); +IOMMU_PMU_ATTR(filter_pasid_en, "config1:2", IOMMU_PMU_FILTER_PASID); +IOMMU_PMU_ATTR(filter_ats_en, "config1:3", IOMMU_PMU_FILTER_ATS); +IOMMU_PMU_ATTR(filter_page_table_en, "config1:4", IOMMU_PMU_FILTER_PAGE_TABLE); +IOMMU_PMU_ATTR(filter_requester_id, "config1:16-31", IOMMU_PMU_FILTER_REQUESTER_ID); +IOMMU_PMU_ATTR(filter_domain, "config1:32-47", IOMMU_PMU_FILTER_DOMAIN); +IOMMU_PMU_ATTR(filter_pasid, "config2:0-21", IOMMU_PMU_FILTER_PASID); +IOMMU_PMU_ATTR(filter_ats, "config2:24-28", IOMMU_PMU_FILTER_ATS); +IOMMU_PMU_ATTR(filter_page_table, "config2:32-36", IOMMU_PMU_FILTER_PAGE_TABLE); + +#define iommu_pmu_en_requester_id(e) ((e) & 0x1) +#define iommu_pmu_en_domain(e) (((e) >> 1) & 0x1) +#define iommu_pmu_en_pasid(e) (((e) >> 2) & 0x1) +#define iommu_pmu_en_ats(e) (((e) >> 3) & 0x1) +#define iommu_pmu_en_page_table(e) (((e) >> 4) & 0x1) +#define iommu_pmu_get_requester_id(filter) (((filter) >> 16) & 0xffff) +#define iommu_pmu_get_domain(filter) (((filter) >> 32) & 0xffff) +#define iommu_pmu_get_pasid(filter) ((filter) & 0x3fffff) +#define iommu_pmu_get_ats(filter) (((filter) >> 24) & 0x1f) +#define iommu_pmu_get_page_table(filter) (((filter) >> 32) & 0x1f) + +#define iommu_pmu_set_filter(_name, _config, _filter, _idx, _econfig) \ +{ \ + if ((iommu_pmu->filter & _filter) && iommu_pmu_en_##_name(_econfig)) { \ + dmar_writel(iommu_pmu->cfg_reg + _idx * IOMMU_PMU_CFG_OFFSET + \ + IOMMU_PMU_CFG_SIZE + \ + (ffs(_filter) - 1) * IOMMU_PMU_CFG_FILTERS_OFFSET, \ + iommu_pmu_get_##_name(_config) | IOMMU_PMU_FILTER_EN);\ + } \ +} + +#define iommu_pmu_clear_filter(_filter, _idx) \ +{ \ + if (iommu_pmu->filter & _filter) { \ + dmar_writel(iommu_pmu->cfg_reg + _idx * IOMMU_PMU_CFG_OFFSET + \ + IOMMU_PMU_CFG_SIZE + \ + (ffs(_filter) - 1) * IOMMU_PMU_CFG_FILTERS_OFFSET, \ + 0); \ + } \ +} + +/* + * Define the event attr related functions + * Input: _name: event attr name + * _string: string of the event in sysfs + * _g_idx: event group encoding + * _event: event encoding + */ +#define IOMMU_PMU_EVENT_ATTR(_name, _string, _g_idx, _event) \ + PMU_EVENT_ATTR_STRING(_name, event_attr_##_name, _string) \ + \ +static struct attribute *_name##_attr[] = { \ + &event_attr_##_name.attr.attr, \ + NULL \ +}; \ + \ +static umode_t \ +_name##_is_visible(struct kobject *kobj, struct attribute *attr, int i) \ +{ \ + struct device *dev = kobj_to_dev(kobj); \ + struct iommu_pmu *iommu_pmu = dev_to_iommu_pmu(dev); \ + \ + if (!iommu_pmu) \ + return 0; \ + return (iommu_pmu->evcap[_g_idx] & _event) ? attr->mode : 0; \ +} \ + \ +static struct attribute_group _name = { \ + .name = "events", \ + .attrs = _name##_attr, \ + .is_visible = _name##_is_visible, \ +}; + +IOMMU_PMU_EVENT_ATTR(iommu_clocks, "event_group=0x0,event=0x001", 0x0, 0x001) +IOMMU_PMU_EVENT_ATTR(iommu_requests, "event_group=0x0,event=0x002", 0x0, 0x002) +IOMMU_PMU_EVENT_ATTR(pw_occupancy, "event_group=0x0,event=0x004", 0x0, 0x004) +IOMMU_PMU_EVENT_ATTR(ats_blocked, "event_group=0x0,event=0x008", 0x0, 0x008) +IOMMU_PMU_EVENT_ATTR(iommu_mrds, "event_group=0x1,event=0x001", 0x1, 0x001) +IOMMU_PMU_EVENT_ATTR(iommu_mem_blocked, "event_group=0x1,event=0x020", 0x1, 0x020) +IOMMU_PMU_EVENT_ATTR(pg_req_posted, "event_group=0x1,event=0x040", 0x1, 0x040) +IOMMU_PMU_EVENT_ATTR(ctxt_cache_lookup, "event_group=0x2,event=0x001", 0x2, 0x001) +IOMMU_PMU_EVENT_ATTR(ctxt_cache_hit, "event_group=0x2,event=0x002", 0x2, 0x002) +IOMMU_PMU_EVENT_ATTR(pasid_cache_lookup, "event_group=0x2,event=0x004", 0x2, 0x004) +IOMMU_PMU_EVENT_ATTR(pasid_cache_hit, "event_group=0x2,event=0x008", 0x2, 0x008) +IOMMU_PMU_EVENT_ATTR(ss_nonleaf_lookup, "event_group=0x2,event=0x010", 0x2, 0x010) +IOMMU_PMU_EVENT_ATTR(ss_nonleaf_hit, "event_group=0x2,event=0x020", 0x2, 0x020) +IOMMU_PMU_EVENT_ATTR(fs_nonleaf_lookup, "event_group=0x2,event=0x040", 0x2, 0x040) +IOMMU_PMU_EVENT_ATTR(fs_nonleaf_hit, "event_group=0x2,event=0x080", 0x2, 0x080) +IOMMU_PMU_EVENT_ATTR(hpt_nonleaf_lookup, "event_group=0x2,event=0x100", 0x2, 0x100) +IOMMU_PMU_EVENT_ATTR(hpt_nonleaf_hit, "event_group=0x2,event=0x200", 0x2, 0x200) +IOMMU_PMU_EVENT_ATTR(iotlb_lookup, "event_group=0x3,event=0x001", 0x3, 0x001) +IOMMU_PMU_EVENT_ATTR(iotlb_hit, "event_group=0x3,event=0x002", 0x3, 0x002) +IOMMU_PMU_EVENT_ATTR(hpt_leaf_lookup, "event_group=0x3,event=0x004", 0x3, 0x004) +IOMMU_PMU_EVENT_ATTR(hpt_leaf_hit, "event_group=0x3,event=0x008", 0x3, 0x008) +IOMMU_PMU_EVENT_ATTR(int_cache_lookup, "event_group=0x4,event=0x001", 0x4, 0x001) +IOMMU_PMU_EVENT_ATTR(int_cache_hit_nonposted, "event_group=0x4,event=0x002", 0x4, 0x002) +IOMMU_PMU_EVENT_ATTR(int_cache_hit_posted, "event_group=0x4,event=0x004", 0x4, 0x004) + +static const struct attribute_group *iommu_pmu_attr_update[] = { + &filter_requester_id_en, + &filter_domain_en, + &filter_pasid_en, + &filter_ats_en, + &filter_page_table_en, + &filter_requester_id, + &filter_domain, + &filter_pasid, + &filter_ats, + &filter_page_table, + &iommu_clocks, + &iommu_requests, + &pw_occupancy, + &ats_blocked, + &iommu_mrds, + &iommu_mem_blocked, + &pg_req_posted, + &ctxt_cache_lookup, + &ctxt_cache_hit, + &pasid_cache_lookup, + &pasid_cache_hit, + &ss_nonleaf_lookup, + &ss_nonleaf_hit, + &fs_nonleaf_lookup, + &fs_nonleaf_hit, + &hpt_nonleaf_lookup, + &hpt_nonleaf_hit, + &iotlb_lookup, + &iotlb_hit, + &hpt_leaf_lookup, + &hpt_leaf_hit, + &int_cache_lookup, + &int_cache_hit_nonposted, + &int_cache_hit_posted, + NULL +}; + +static inline void __iomem * +iommu_event_base(struct iommu_pmu *iommu_pmu, int idx) +{ + return iommu_pmu->cntr_reg + idx * iommu_pmu->cntr_stride; +} + +static inline void __iomem * +iommu_config_base(struct iommu_pmu *iommu_pmu, int idx) +{ + return iommu_pmu->cfg_reg + idx * IOMMU_PMU_CFG_OFFSET; +} + +static inline struct iommu_pmu *iommu_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct iommu_pmu, pmu); +} + +static inline u64 iommu_event_config(struct perf_event *event) +{ + u64 config = event->attr.config; + + return (iommu_event_select(config) << IOMMU_EVENT_CFG_ES_SHIFT) | + (iommu_event_group(config) << IOMMU_EVENT_CFG_EGI_SHIFT) | + IOMMU_EVENT_CFG_INT; +} + +static inline bool is_iommu_pmu_event(struct iommu_pmu *iommu_pmu, + struct perf_event *event) +{ + return event->pmu == &iommu_pmu->pmu; +} + +static int iommu_pmu_validate_event(struct perf_event *event) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + u32 event_group = iommu_event_group(event->attr.config); + + if (event_group >= iommu_pmu->num_eg) + return -EINVAL; + + return 0; +} + +static int iommu_pmu_validate_group(struct perf_event *event) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + struct perf_event *sibling; + int nr = 0; + + /* + * All events in a group must be scheduled simultaneously. + * Check whether there is enough counters for all the events. + */ + for_each_sibling_event(sibling, event->group_leader) { + if (!is_iommu_pmu_event(iommu_pmu, sibling) || + sibling->state <= PERF_EVENT_STATE_OFF) + continue; + + if (++nr > iommu_pmu->num_cntr) + return -EINVAL; + } + + return 0; +} + +static int iommu_pmu_event_init(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* sampling not supported */ + if (event->attr.sample_period) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + if (iommu_pmu_validate_event(event)) + return -EINVAL; + + hwc->config = iommu_event_config(event); + + return iommu_pmu_validate_group(event); +} + +static void iommu_pmu_event_update(struct perf_event *event) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + struct hw_perf_event *hwc = &event->hw; + u64 prev_count, new_count, delta; + int shift = 64 - iommu_pmu->cntr_width; + +again: + prev_count = local64_read(&hwc->prev_count); + new_count = dmar_readq(iommu_event_base(iommu_pmu, hwc->idx)); + if (local64_xchg(&hwc->prev_count, new_count) != prev_count) + goto again; + + /* + * The counter width is enumerated. Always shift the counter + * before using it. + */ + delta = (new_count << shift) - (prev_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); +} + +static void iommu_pmu_start(struct perf_event *event, int flags) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + struct intel_iommu *iommu = iommu_pmu->iommu; + struct hw_perf_event *hwc = &event->hw; + u64 count; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + if (WARN_ON_ONCE(hwc->idx < 0 || hwc->idx >= IOMMU_PMU_IDX_MAX)) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + hwc->state = 0; + + /* Always reprogram the period */ + count = dmar_readq(iommu_event_base(iommu_pmu, hwc->idx)); + local64_set((&hwc->prev_count), count); + + /* + * The error of ecmd will be ignored. + * - The existing perf_event subsystem doesn't handle the error. + * Only IOMMU PMU returns runtime HW error. We don't want to + * change the existing generic interfaces for the specific case. + * - It's a corner case caused by HW, which is very unlikely to + * happen. There is nothing SW can do. + * - The worst case is that the user will get <not count> with + * perf command, which can give the user some hints. + */ + ecmd_submit_sync(iommu, DMA_ECMD_ENABLE, hwc->idx, 0); + + perf_event_update_userpage(event); +} + +static void iommu_pmu_stop(struct perf_event *event, int flags) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + struct intel_iommu *iommu = iommu_pmu->iommu; + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + ecmd_submit_sync(iommu, DMA_ECMD_DISABLE, hwc->idx, 0); + + iommu_pmu_event_update(event); + + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + } +} + +static inline int +iommu_pmu_validate_per_cntr_event(struct iommu_pmu *iommu_pmu, + int idx, struct perf_event *event) +{ + u32 event_group = iommu_event_group(event->attr.config); + u32 select = iommu_event_select(event->attr.config); + + if (!(iommu_pmu->cntr_evcap[idx][event_group] & select)) + return -EINVAL; + + return 0; +} + +static int iommu_pmu_assign_event(struct iommu_pmu *iommu_pmu, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx; + + /* + * The counters which support limited events are usually at the end. + * Schedule them first to accommodate more events. + */ + for (idx = iommu_pmu->num_cntr - 1; idx >= 0; idx--) { + if (test_and_set_bit(idx, iommu_pmu->used_mask)) + continue; + /* Check per-counter event capabilities */ + if (!iommu_pmu_validate_per_cntr_event(iommu_pmu, idx, event)) + break; + clear_bit(idx, iommu_pmu->used_mask); + } + if (idx < 0) + return -EINVAL; + + iommu_pmu->event_list[idx] = event; + hwc->idx = idx; + + /* config events */ + dmar_writeq(iommu_config_base(iommu_pmu, idx), hwc->config); + + iommu_pmu_set_filter(requester_id, event->attr.config1, + IOMMU_PMU_FILTER_REQUESTER_ID, idx, + event->attr.config1); + iommu_pmu_set_filter(domain, event->attr.config1, + IOMMU_PMU_FILTER_DOMAIN, idx, + event->attr.config1); + iommu_pmu_set_filter(pasid, event->attr.config1, + IOMMU_PMU_FILTER_PASID, idx, + event->attr.config1); + iommu_pmu_set_filter(ats, event->attr.config2, + IOMMU_PMU_FILTER_ATS, idx, + event->attr.config1); + iommu_pmu_set_filter(page_table, event->attr.config2, + IOMMU_PMU_FILTER_PAGE_TABLE, idx, + event->attr.config1); + + return 0; +} + +static int iommu_pmu_add(struct perf_event *event, int flags) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + struct hw_perf_event *hwc = &event->hw; + int ret; + + ret = iommu_pmu_assign_event(iommu_pmu, event); + if (ret < 0) + return ret; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (flags & PERF_EF_START) + iommu_pmu_start(event, 0); + + return 0; +} + +static void iommu_pmu_del(struct perf_event *event, int flags) +{ + struct iommu_pmu *iommu_pmu = iommu_event_to_pmu(event); + int idx = event->hw.idx; + + iommu_pmu_stop(event, PERF_EF_UPDATE); + + iommu_pmu_clear_filter(IOMMU_PMU_FILTER_REQUESTER_ID, idx); + iommu_pmu_clear_filter(IOMMU_PMU_FILTER_DOMAIN, idx); + iommu_pmu_clear_filter(IOMMU_PMU_FILTER_PASID, idx); + iommu_pmu_clear_filter(IOMMU_PMU_FILTER_ATS, idx); + iommu_pmu_clear_filter(IOMMU_PMU_FILTER_PAGE_TABLE, idx); + + iommu_pmu->event_list[idx] = NULL; + event->hw.idx = -1; + clear_bit(idx, iommu_pmu->used_mask); + + perf_event_update_userpage(event); +} + +static void iommu_pmu_enable(struct pmu *pmu) +{ + struct iommu_pmu *iommu_pmu = container_of(pmu, struct iommu_pmu, pmu); + struct intel_iommu *iommu = iommu_pmu->iommu; + + ecmd_submit_sync(iommu, DMA_ECMD_UNFREEZE, 0, 0); +} + +static void iommu_pmu_disable(struct pmu *pmu) +{ + struct iommu_pmu *iommu_pmu = container_of(pmu, struct iommu_pmu, pmu); + struct intel_iommu *iommu = iommu_pmu->iommu; + + ecmd_submit_sync(iommu, DMA_ECMD_FREEZE, 0, 0); +} + +static void iommu_pmu_counter_overflow(struct iommu_pmu *iommu_pmu) +{ + struct perf_event *event; + u64 status; + int i; + + /* + * Two counters may be overflowed very close. Always check + * whether there are more to handle. + */ + while ((status = dmar_readq(iommu_pmu->overflow))) { + for_each_set_bit(i, (unsigned long *)&status, iommu_pmu->num_cntr) { + /* + * Find the assigned event of the counter. + * Accumulate the value into the event->count. + */ + event = iommu_pmu->event_list[i]; + if (!event) { + pr_warn_once("Cannot find the assigned event for counter %d\n", i); + continue; + } + iommu_pmu_event_update(event); + } + + dmar_writeq(iommu_pmu->overflow, status); + } +} + +static irqreturn_t iommu_pmu_irq_handler(int irq, void *dev_id) +{ + struct intel_iommu *iommu = dev_id; + + if (!dmar_readl(iommu->reg + DMAR_PERFINTRSTS_REG)) + return IRQ_NONE; + + iommu_pmu_counter_overflow(iommu->pmu); + + /* Clear the status bit */ + dmar_writel(iommu->reg + DMAR_PERFINTRSTS_REG, DMA_PERFINTRSTS_PIS); + + return IRQ_HANDLED; +} + +static int __iommu_pmu_register(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + + iommu_pmu->pmu.name = iommu->name; + iommu_pmu->pmu.task_ctx_nr = perf_invalid_context; + iommu_pmu->pmu.event_init = iommu_pmu_event_init; + iommu_pmu->pmu.pmu_enable = iommu_pmu_enable; + iommu_pmu->pmu.pmu_disable = iommu_pmu_disable; + iommu_pmu->pmu.add = iommu_pmu_add; + iommu_pmu->pmu.del = iommu_pmu_del; + iommu_pmu->pmu.start = iommu_pmu_start; + iommu_pmu->pmu.stop = iommu_pmu_stop; + iommu_pmu->pmu.read = iommu_pmu_event_update; + iommu_pmu->pmu.attr_groups = iommu_pmu_attr_groups; + iommu_pmu->pmu.attr_update = iommu_pmu_attr_update; + iommu_pmu->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; + iommu_pmu->pmu.module = THIS_MODULE; + + return perf_pmu_register(&iommu_pmu->pmu, iommu_pmu->pmu.name, -1); +} + +static inline void __iomem * +get_perf_reg_address(struct intel_iommu *iommu, u32 offset) +{ + u32 off = dmar_readl(iommu->reg + offset); + + return iommu->reg + off; +} + +int alloc_iommu_pmu(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu; + int i, j, ret; + u64 perfcap; + u32 cap; + + if (!ecap_pms(iommu->ecap)) + return 0; + + /* The IOMMU PMU requires the ECMD support as well */ + if (!cap_ecmds(iommu->cap)) + return -ENODEV; + + perfcap = dmar_readq(iommu->reg + DMAR_PERFCAP_REG); + /* The performance monitoring is not supported. */ + if (!perfcap) + return -ENODEV; + + /* Sanity check for the number of the counters and event groups */ + if (!pcap_num_cntr(perfcap) || !pcap_num_event_group(perfcap)) + return -ENODEV; + + /* The interrupt on overflow is required */ + if (!pcap_interrupt(perfcap)) + return -ENODEV; + + /* Check required Enhanced Command Capability */ + if (!ecmd_has_pmu_essential(iommu)) + return -ENODEV; + + iommu_pmu = kzalloc(sizeof(*iommu_pmu), GFP_KERNEL); + if (!iommu_pmu) + return -ENOMEM; + + iommu_pmu->num_cntr = pcap_num_cntr(perfcap); + if (iommu_pmu->num_cntr > IOMMU_PMU_IDX_MAX) { + pr_warn_once("The number of IOMMU counters %d > max(%d), clipping!", + iommu_pmu->num_cntr, IOMMU_PMU_IDX_MAX); + iommu_pmu->num_cntr = IOMMU_PMU_IDX_MAX; + } + + iommu_pmu->cntr_width = pcap_cntr_width(perfcap); + iommu_pmu->filter = pcap_filters_mask(perfcap); + iommu_pmu->cntr_stride = pcap_cntr_stride(perfcap); + iommu_pmu->num_eg = pcap_num_event_group(perfcap); + + iommu_pmu->evcap = kcalloc(iommu_pmu->num_eg, sizeof(u64), GFP_KERNEL); + if (!iommu_pmu->evcap) { + ret = -ENOMEM; + goto free_pmu; + } + + /* Parse event group capabilities */ + for (i = 0; i < iommu_pmu->num_eg; i++) { + u64 pcap; + + pcap = dmar_readq(iommu->reg + DMAR_PERFEVNTCAP_REG + + i * IOMMU_PMU_CAP_REGS_STEP); + iommu_pmu->evcap[i] = pecap_es(pcap); + } + + iommu_pmu->cntr_evcap = kcalloc(iommu_pmu->num_cntr, sizeof(u32 *), GFP_KERNEL); + if (!iommu_pmu->cntr_evcap) { + ret = -ENOMEM; + goto free_pmu_evcap; + } + for (i = 0; i < iommu_pmu->num_cntr; i++) { + iommu_pmu->cntr_evcap[i] = kcalloc(iommu_pmu->num_eg, sizeof(u32), GFP_KERNEL); + if (!iommu_pmu->cntr_evcap[i]) { + ret = -ENOMEM; + goto free_pmu_cntr_evcap; + } + /* + * Set to the global capabilities, will adjust according + * to per-counter capabilities later. + */ + for (j = 0; j < iommu_pmu->num_eg; j++) + iommu_pmu->cntr_evcap[i][j] = (u32)iommu_pmu->evcap[j]; + } + + iommu_pmu->cfg_reg = get_perf_reg_address(iommu, DMAR_PERFCFGOFF_REG); + iommu_pmu->cntr_reg = get_perf_reg_address(iommu, DMAR_PERFCNTROFF_REG); + iommu_pmu->overflow = get_perf_reg_address(iommu, DMAR_PERFOVFOFF_REG); + + /* + * Check per-counter capabilities. All counters should have the + * same capabilities on Interrupt on Overflow Support and Counter + * Width. + */ + for (i = 0; i < iommu_pmu->num_cntr; i++) { + cap = dmar_readl(iommu_pmu->cfg_reg + + i * IOMMU_PMU_CFG_OFFSET + + IOMMU_PMU_CFG_CNTRCAP_OFFSET); + if (!iommu_cntrcap_pcc(cap)) + continue; + + /* + * It's possible that some counters have a different + * capability because of e.g., HW bug. Check the corner + * case here and simply drop those counters. + */ + if ((iommu_cntrcap_cw(cap) != iommu_pmu->cntr_width) || + !iommu_cntrcap_ios(cap)) { + iommu_pmu->num_cntr = i; + pr_warn("PMU counter capability inconsistent, counter number reduced to %d\n", + iommu_pmu->num_cntr); + } + + /* Clear the pre-defined events group */ + for (j = 0; j < iommu_pmu->num_eg; j++) + iommu_pmu->cntr_evcap[i][j] = 0; + + /* Override with per-counter event capabilities */ + for (j = 0; j < iommu_cntrcap_egcnt(cap); j++) { + cap = dmar_readl(iommu_pmu->cfg_reg + i * IOMMU_PMU_CFG_OFFSET + + IOMMU_PMU_CFG_CNTREVCAP_OFFSET + + (j * IOMMU_PMU_OFF_REGS_STEP)); + iommu_pmu->cntr_evcap[i][iommu_event_group(cap)] = iommu_event_select(cap); + /* + * Some events may only be supported by a specific counter. + * Track them in the evcap as well. + */ + iommu_pmu->evcap[iommu_event_group(cap)] |= iommu_event_select(cap); + } + } + + iommu_pmu->iommu = iommu; + iommu->pmu = iommu_pmu; + + return 0; + +free_pmu_cntr_evcap: + for (i = 0; i < iommu_pmu->num_cntr; i++) + kfree(iommu_pmu->cntr_evcap[i]); + kfree(iommu_pmu->cntr_evcap); +free_pmu_evcap: + kfree(iommu_pmu->evcap); +free_pmu: + kfree(iommu_pmu); + + return ret; +} + +void free_iommu_pmu(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) + return; + + if (iommu_pmu->evcap) { + int i; + + for (i = 0; i < iommu_pmu->num_cntr; i++) + kfree(iommu_pmu->cntr_evcap[i]); + kfree(iommu_pmu->cntr_evcap); + } + kfree(iommu_pmu->evcap); + kfree(iommu_pmu); + iommu->pmu = NULL; +} + +static int iommu_pmu_set_interrupt(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + int irq, ret; + + irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PERF + iommu->seq_id, iommu->node, iommu); + if (irq <= 0) + return -EINVAL; + + snprintf(iommu_pmu->irq_name, sizeof(iommu_pmu->irq_name), "dmar%d-perf", iommu->seq_id); + + iommu->perf_irq = irq; + ret = request_threaded_irq(irq, NULL, iommu_pmu_irq_handler, + IRQF_ONESHOT, iommu_pmu->irq_name, iommu); + if (ret) { + dmar_free_hwirq(irq); + iommu->perf_irq = 0; + return ret; + } + return 0; +} + +static void iommu_pmu_unset_interrupt(struct intel_iommu *iommu) +{ + if (!iommu->perf_irq) + return; + + free_irq(iommu->perf_irq, iommu); + dmar_free_hwirq(iommu->perf_irq); + iommu->perf_irq = 0; +} + +static int iommu_pmu_cpu_online(unsigned int cpu) +{ + if (cpumask_empty(&iommu_pmu_cpu_mask)) + cpumask_set_cpu(cpu, &iommu_pmu_cpu_mask); + + return 0; +} + +static int iommu_pmu_cpu_offline(unsigned int cpu) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + int target; + + if (!cpumask_test_and_clear_cpu(cpu, &iommu_pmu_cpu_mask)) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &iommu_pmu_cpu_mask); + else + target = -1; + + rcu_read_lock(); + + for_each_iommu(iommu, drhd) { + if (!iommu->pmu) + continue; + perf_pmu_migrate_context(&iommu->pmu->pmu, cpu, target); + } + rcu_read_unlock(); + + return 0; +} + +static int nr_iommu_pmu; + +static int iommu_pmu_cpuhp_setup(struct iommu_pmu *iommu_pmu) +{ + int ret; + + if (nr_iommu_pmu++) + return 0; + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, + "driver/iommu/intel/perfmon:online", + iommu_pmu_cpu_online, + iommu_pmu_cpu_offline); + if (ret) + nr_iommu_pmu = 0; + + return ret; +} + +static void iommu_pmu_cpuhp_free(struct iommu_pmu *iommu_pmu) +{ + if (--nr_iommu_pmu) + return; + + cpuhp_remove_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE); +} + +void iommu_pmu_register(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) + return; + + if (__iommu_pmu_register(iommu)) + goto err; + + if (iommu_pmu_cpuhp_setup(iommu_pmu)) + goto unregister; + + /* Set interrupt for overflow */ + if (iommu_pmu_set_interrupt(iommu)) + goto cpuhp_free; + + return; + +cpuhp_free: + iommu_pmu_cpuhp_free(iommu_pmu); +unregister: + perf_pmu_unregister(&iommu_pmu->pmu); +err: + pr_err("Failed to register PMU for iommu (seq_id = %d)\n", iommu->seq_id); + free_iommu_pmu(iommu); +} + +void iommu_pmu_unregister(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) + return; + + iommu_pmu_unset_interrupt(iommu); + iommu_pmu_cpuhp_free(iommu_pmu); + perf_pmu_unregister(&iommu_pmu->pmu); +} diff --git a/drivers/iommu/intel/perfmon.h b/drivers/iommu/intel/perfmon.h new file mode 100644 index 000000000000..58606af9a2b9 --- /dev/null +++ b/drivers/iommu/intel/perfmon.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * PERFCFGOFF_REG, PERFFRZOFF_REG + * PERFOVFOFF_REG, PERFCNTROFF_REG + */ +#define IOMMU_PMU_NUM_OFF_REGS 4 +#define IOMMU_PMU_OFF_REGS_STEP 4 + +#define IOMMU_PMU_FILTER_REQUESTER_ID 0x01 +#define IOMMU_PMU_FILTER_DOMAIN 0x02 +#define IOMMU_PMU_FILTER_PASID 0x04 +#define IOMMU_PMU_FILTER_ATS 0x08 +#define IOMMU_PMU_FILTER_PAGE_TABLE 0x10 + +#define IOMMU_PMU_FILTER_EN BIT(31) + +#define IOMMU_PMU_CFG_OFFSET 0x100 +#define IOMMU_PMU_CFG_CNTRCAP_OFFSET 0x80 +#define IOMMU_PMU_CFG_CNTREVCAP_OFFSET 0x84 +#define IOMMU_PMU_CFG_SIZE 0x8 +#define IOMMU_PMU_CFG_FILTERS_OFFSET 0x4 + +#define IOMMU_PMU_CAP_REGS_STEP 8 + +#define iommu_cntrcap_pcc(p) ((p) & 0x1) +#define iommu_cntrcap_cw(p) (((p) >> 8) & 0xff) +#define iommu_cntrcap_ios(p) (((p) >> 16) & 0x1) +#define iommu_cntrcap_egcnt(p) (((p) >> 28) & 0xf) + +#define IOMMU_EVENT_CFG_EGI_SHIFT 8 +#define IOMMU_EVENT_CFG_ES_SHIFT 32 +#define IOMMU_EVENT_CFG_INT BIT_ULL(1) + +#define iommu_event_select(p) ((p) & 0xfffffff) +#define iommu_event_group(p) (((p) >> 28) & 0xf) + +#ifdef CONFIG_INTEL_IOMMU_PERF_EVENTS +int alloc_iommu_pmu(struct intel_iommu *iommu); +void free_iommu_pmu(struct intel_iommu *iommu); +void iommu_pmu_register(struct intel_iommu *iommu); +void iommu_pmu_unregister(struct intel_iommu *iommu); +#else +static inline int +alloc_iommu_pmu(struct intel_iommu *iommu) +{ + return 0; +} + +static inline void +free_iommu_pmu(struct intel_iommu *iommu) +{ +} + +static inline void +iommu_pmu_register(struct intel_iommu *iommu) +{ +} + +static inline void +iommu_pmu_unregister(struct intel_iommu *iommu) +{ +} +#endif /* CONFIG_INTEL_IOMMU_PERF_EVENTS */ diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index c76b66263467..7367f56c3bad 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -9,7 +9,6 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/slab.h> -#include <linux/intel-svm.h> #include <linux/rculist.h> #include <linux/pci.h> #include <linux/pci-ats.h> @@ -79,7 +78,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) } iommu->prq = page_address(pages); - irq = dmar_alloc_hwirq(DMAR_UNITS_SUPPORTED + iommu->seq_id, iommu->node, iommu); + irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PRQ + iommu->seq_id, iommu->node, iommu); if (irq <= 0) { pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n", iommu->name); @@ -299,9 +298,8 @@ out: return 0; } -static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, - struct device *dev, - struct mm_struct *mm) +static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev, + struct mm_struct *mm) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_svm_dev *sdev; @@ -313,7 +311,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, if (!svm) { svm = kzalloc(sizeof(*svm), GFP_KERNEL); if (!svm) - return ERR_PTR(-ENOMEM); + return -ENOMEM; svm->pasid = mm->pasid; svm->mm = mm; @@ -323,24 +321,17 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, ret = mmu_notifier_register(&svm->notifier, mm); if (ret) { kfree(svm); - return ERR_PTR(ret); + return ret; } ret = pasid_private_add(svm->pasid, svm); if (ret) { mmu_notifier_unregister(&svm->notifier, mm); kfree(svm); - return ERR_PTR(ret); + return ret; } } - /* Find the matching device in svm list */ - sdev = svm_lookup_device_by_dev(svm, dev); - if (sdev) { - sdev->users++; - goto success; - } - sdev = kzalloc(sizeof(*sdev), GFP_KERNEL); if (!sdev) { ret = -ENOMEM; @@ -351,12 +342,8 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, sdev->iommu = iommu; sdev->did = FLPT_DEFAULT_DID; sdev->sid = PCI_DEVID(info->bus, info->devfn); - sdev->users = 1; - sdev->pasid = svm->pasid; - sdev->sva.dev = dev; init_rcu_head(&sdev->rcu); if (info->ats_enabled) { - sdev->dev_iotlb = 1; sdev->qdep = info->ats_qdep; if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS) sdev->qdep = 0; @@ -370,8 +357,8 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, goto free_sdev; list_add_rcu(&sdev->list, &svm->devs); -success: - return &sdev->sva; + + return 0; free_sdev: kfree(sdev); @@ -382,7 +369,7 @@ free_svm: kfree(svm); } - return ERR_PTR(ret); + return ret; } /* Caller must hold pasid_mutex */ @@ -404,32 +391,32 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid) mm = svm->mm; if (sdev) { - sdev->users--; - if (!sdev->users) { - list_del_rcu(&sdev->list); - /* Flush the PASID cache and IOTLB for this device. - * Note that we do depend on the hardware *not* using - * the PASID any more. Just as we depend on other - * devices never using PASIDs that they have no right - * to use. We have a *shared* PASID table, because it's - * large and has to be physically contiguous. So it's - * hard to be as defensive as we might like. */ - intel_pasid_tear_down_entry(iommu, dev, - svm->pasid, false); - intel_svm_drain_prq(dev, svm->pasid); - kfree_rcu(sdev, rcu); - - if (list_empty(&svm->devs)) { - if (svm->notifier.ops) - mmu_notifier_unregister(&svm->notifier, mm); - pasid_private_remove(svm->pasid); - /* We mandate that no page faults may be outstanding - * for the PASID when intel_svm_unbind_mm() is called. - * If that is not obeyed, subtle errors will happen. - * Let's make them less subtle... */ - memset(svm, 0x6b, sizeof(*svm)); - kfree(svm); - } + list_del_rcu(&sdev->list); + /* + * Flush the PASID cache and IOTLB for this device. + * Note that we do depend on the hardware *not* using + * the PASID any more. Just as we depend on other + * devices never using PASIDs that they have no right + * to use. We have a *shared* PASID table, because it's + * large and has to be physically contiguous. So it's + * hard to be as defensive as we might like. + */ + intel_pasid_tear_down_entry(iommu, dev, svm->pasid, false); + intel_svm_drain_prq(dev, svm->pasid); + kfree_rcu(sdev, rcu); + + if (list_empty(&svm->devs)) { + if (svm->notifier.ops) + mmu_notifier_unregister(&svm->notifier, mm); + pasid_private_remove(svm->pasid); + /* + * We mandate that no page faults may be outstanding + * for the PASID when intel_svm_unbind_mm() is called. + * If that is not obeyed, subtle errors will happen. + * Let's make them less subtle... + */ + memset(svm, 0x6b, sizeof(*svm)); + kfree(svm); } } out: @@ -854,13 +841,10 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain, struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; struct mm_struct *mm = domain->mm; - struct iommu_sva *sva; - int ret = 0; + int ret; mutex_lock(&pasid_mutex); - sva = intel_svm_bind_mm(iommu, dev, mm); - if (IS_ERR(sva)) - ret = PTR_ERR(sva); + ret = intel_svm_bind_mm(iommu, dev, mm); mutex_unlock(&pasid_mutex); return ret; diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c index 1e9ca7789de1..23416bf76df9 100644 --- a/drivers/iommu/iommu-traces.c +++ b/drivers/iommu/iommu-traces.c @@ -18,7 +18,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(remove_device_from_group); /* iommu_device_event */ EXPORT_TRACEPOINT_SYMBOL_GPL(attach_device_to_domain); -EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain); /* iommu_map_unmap */ EXPORT_TRACEPOINT_SYMBOL_GPL(map); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 5f6a85aea501..b3f847b25b4f 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -371,6 +371,30 @@ err_unlock: return ret; } +static bool iommu_is_attach_deferred(struct device *dev) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (ops->is_attach_deferred) + return ops->is_attach_deferred(dev); + + return false; +} + +static int iommu_group_do_dma_first_attach(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + lockdep_assert_held(&dev->iommu_group->mutex); + + if (iommu_is_attach_deferred(dev)) { + dev->iommu->attach_deferred = 1; + return 0; + } + + return __iommu_attach_device(domain, dev); +} + int iommu_probe_device(struct device *dev) { const struct iommu_ops *ops; @@ -401,7 +425,7 @@ int iommu_probe_device(struct device *dev) * attach the default domain. */ if (group->default_domain && !group->owner) { - ret = __iommu_attach_device(group->default_domain, dev); + ret = iommu_group_do_dma_first_attach(dev, group->default_domain); if (ret) { mutex_unlock(&group->mutex); iommu_group_put(group); @@ -774,12 +798,16 @@ struct iommu_group *iommu_group_alloc(void) ret = iommu_group_create_file(group, &iommu_group_attr_reserved_regions); - if (ret) + if (ret) { + kobject_put(group->devices_kobj); return ERR_PTR(ret); + } ret = iommu_group_create_file(group, &iommu_group_attr_type); - if (ret) + if (ret) { + kobject_put(group->devices_kobj); return ERR_PTR(ret); + } pr_debug("Allocated group %d\n", group->id); @@ -930,7 +958,7 @@ map_end: if (map_size) { ret = iommu_map(domain, addr - map_size, addr - map_size, map_size, - entry->prot); + entry->prot, GFP_KERNEL); if (ret) goto out; map_size = 0; @@ -947,16 +975,6 @@ out: return ret; } -static bool iommu_is_attach_deferred(struct device *dev) -{ - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (ops->is_attach_deferred) - return ops->is_attach_deferred(dev); - - return false; -} - /** * iommu_group_add_device - add a device to an iommu group * @group: the group into which to add the device (reference should be held) @@ -1009,8 +1027,8 @@ rename: mutex_lock(&group->mutex); list_add_tail(&device->list, &group->devices); - if (group->domain && !iommu_is_attach_deferred(dev)) - ret = __iommu_attach_device(group->domain, dev); + if (group->domain) + ret = iommu_group_do_dma_first_attach(dev, group->domain); mutex_unlock(&group->mutex); if (ret) goto err_put_group; @@ -1776,21 +1794,10 @@ static void probe_alloc_default_domain(struct bus_type *bus, } -static int iommu_group_do_dma_attach(struct device *dev, void *data) -{ - struct iommu_domain *domain = data; - int ret = 0; - - if (!iommu_is_attach_deferred(dev)) - ret = __iommu_attach_device(domain, dev); - - return ret; -} - -static int __iommu_group_dma_attach(struct iommu_group *group) +static int __iommu_group_dma_first_attach(struct iommu_group *group) { return __iommu_group_for_each_dev(group, group->default_domain, - iommu_group_do_dma_attach); + iommu_group_do_dma_first_attach); } static int iommu_group_do_probe_finalize(struct device *dev, void *data) @@ -1855,7 +1862,7 @@ int bus_iommu_probe(struct bus_type *bus) iommu_group_create_direct_mappings(group); - ret = __iommu_group_dma_attach(group); + ret = __iommu_group_dma_first_attach(group); mutex_unlock(&group->mutex); @@ -1987,9 +1994,11 @@ static int __iommu_attach_device(struct iommu_domain *domain, return -ENODEV; ret = domain->ops->attach_dev(domain, dev); - if (!ret) - trace_attach_device_to_domain(dev); - return ret; + if (ret) + return ret; + dev->iommu->attach_deferred = 0; + trace_attach_device_to_domain(dev); + return 0; } /** @@ -2034,22 +2043,12 @@ EXPORT_SYMBOL_GPL(iommu_attach_device); int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) { - if (iommu_is_attach_deferred(dev)) + if (dev->iommu && dev->iommu->attach_deferred) return __iommu_attach_device(domain, dev); return 0; } -static void __iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - if (iommu_is_attach_deferred(dev)) - return; - - domain->ops->detach_dev(domain, dev); - trace_detach_device_from_domain(dev); -} - void iommu_detach_device(struct iommu_domain *domain, struct device *dev) { struct iommu_group *group; @@ -2124,8 +2123,22 @@ static int __iommu_attach_group(struct iommu_domain *domain, ret = __iommu_group_for_each_dev(group, domain, iommu_group_do_attach_device); - if (ret == 0) + if (ret == 0) { group->domain = domain; + } else { + /* + * To recover from the case when certain device within the + * group fails to attach to the new domain, we need force + * attaching all devices back to the old domain. The old + * domain is compatible for all devices in the group, + * hence the iommu driver should always return success. + */ + struct iommu_domain *old_domain = group->domain; + + group->domain = NULL; + WARN(__iommu_group_set_domain(group, old_domain), + "iommu driver failed to attach a compatible domain"); + } return ret; } @@ -2154,11 +2167,12 @@ int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) } EXPORT_SYMBOL_GPL(iommu_attach_group); -static int iommu_group_do_detach_device(struct device *dev, void *data) +static int iommu_group_do_set_platform_dma(struct device *dev, void *data) { - struct iommu_domain *domain = data; + const struct iommu_ops *ops = dev_iommu_ops(dev); - __iommu_detach_device(domain, dev); + if (!WARN_ON(!ops->set_platform_dma_ops)) + ops->set_platform_dma_ops(dev); return 0; } @@ -2172,15 +2186,13 @@ static int __iommu_group_set_domain(struct iommu_group *group, return 0; /* - * New drivers should support default domains and so the detach_dev() op - * will never be called. Otherwise the NULL domain represents some + * New drivers should support default domains, so set_platform_dma() + * op will never be called. Otherwise the NULL domain represents some * platform specific behavior. */ if (!new_domain) { - if (WARN_ON(!group->domain->ops->detach_dev)) - return -EINVAL; - __iommu_group_for_each_dev(group, group->domain, - iommu_group_do_detach_device); + __iommu_group_for_each_dev(group, NULL, + iommu_group_do_set_platform_dma); group->domain = NULL; return 0; } @@ -2360,34 +2372,27 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } -static int _iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_domain_ops *ops = domain->ops; int ret; + might_sleep_if(gfpflags_allow_blocking(gfp)); + + /* Discourage passing strange GFP flags */ + if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM))) + return -EINVAL; + ret = __iommu_map(domain, iova, paddr, size, prot, gfp); if (ret == 0 && ops->iotlb_sync_map) ops->iotlb_sync_map(domain, iova, size); return ret; } - -int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - might_sleep(); - return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); -} EXPORT_SYMBOL_GPL(iommu_map); -int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); -} -EXPORT_SYMBOL_GPL(iommu_map_atomic); - static size_t __iommu_unmap_pages(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -2477,9 +2482,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot, - gfp_t gfp) +ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { const struct iommu_domain_ops *ops = domain->ops; size_t len = 0, mapped = 0; @@ -2487,6 +2492,13 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, unsigned int i = 0; int ret; + might_sleep_if(gfpflags_allow_blocking(gfp)); + + /* Discourage passing strange GFP flags */ + if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM))) + return -EINVAL; + while (i <= nents) { phys_addr_t s_phys = sg_phys(sg); @@ -2526,21 +2538,8 @@ out_err: return ret; } - -ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - might_sleep(); - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); -} EXPORT_SYMBOL_GPL(iommu_map_sg); -ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); -} - /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 1e1d3509efae..f8d92c9bb65b 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -456,7 +456,8 @@ static int batch_iommu_map_small(struct iommu_domain *domain, size % PAGE_SIZE); while (size) { - rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot); + rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot, + GFP_KERNEL_ACCOUNT); if (rc) goto err_unmap; iova += PAGE_SIZE; @@ -500,7 +501,8 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain, else rc = iommu_map(domain, iova, PFN_PHYS(batch->pfns[cur]) + page_offset, - next_iova - iova, area->iommu_prot); + next_iova - iova, area->iommu_prot, + GFP_KERNEL_ACCOUNT); if (rc) goto err_unmap; iova = next_iova; diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index a003bd5fc65c..bdf1a4e5eae0 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -299,18 +299,6 @@ static void ipmmu_utlb_enable(struct ipmmu_vmsa_domain *domain, mmu->utlb_ctx[utlb] = domain->context_id; } -/* - * Disable MMU translation for the microTLB. - */ -static void ipmmu_utlb_disable(struct ipmmu_vmsa_domain *domain, - unsigned int utlb) -{ - struct ipmmu_vmsa_device *mmu = domain->mmu; - - ipmmu_imuctr_write(mmu, utlb, 0); - mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID; -} - static void ipmmu_tlb_flush_all(void *cookie) { struct ipmmu_vmsa_domain *domain = cookie; @@ -643,21 +631,6 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain, return 0; } -static void ipmmu_detach_device(struct iommu_domain *io_domain, - struct device *dev) -{ - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); - unsigned int i; - - for (i = 0; i < fwspec->num_ids; ++i) - ipmmu_utlb_disable(domain, fwspec->ids[i]); - - /* - * TODO: Optimize by disabling the context when no device is attached. - */ -} - static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) @@ -876,7 +849,6 @@ static const struct iommu_ops ipmmu_ops = { .of_xlate = ipmmu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = ipmmu_attach_device, - .detach_dev = ipmmu_detach_device, .map_pages = ipmmu_map, .unmap_pages = ipmmu_unmap, .flush_iotlb_all = ipmmu_flush_iotlb_all, diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index c60624910872..454f6331c889 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -443,9 +443,9 @@ fail: return ret; } -static void msm_iommu_detach_dev(struct iommu_domain *domain, - struct device *dev) +static void msm_iommu_set_platform_dma(struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct msm_priv *priv = to_msm_priv(domain); unsigned long flags; struct msm_iommu_dev *iommu; @@ -678,11 +678,11 @@ static struct iommu_ops msm_iommu_ops = { .domain_alloc = msm_iommu_domain_alloc, .probe_device = msm_iommu_probe_device, .device_group = generic_device_group, + .set_platform_dma_ops = msm_iommu_set_platform_dma, .pgsize_bitmap = MSM_IOMMU_PGSIZES, .of_xlate = qcom_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = msm_iommu_attach_dev, - .detach_dev = msm_iommu_detach_dev, .map_pages = msm_iommu_map, .unmap_pages = msm_iommu_unmap, /* diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 2badd6acfb23..d5a4955910ff 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -710,14 +710,6 @@ err_unlock: return ret; } -static void mtk_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - struct mtk_iommu_data *data = dev_iommu_priv_get(dev); - - mtk_iommu_config(data, dev, false, 0); -} - static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) @@ -946,7 +938,6 @@ static const struct iommu_ops mtk_iommu_ops = { .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = mtk_iommu_attach_device, - .detach_dev = mtk_iommu_detach_device, .map_pages = mtk_iommu_map, .unmap_pages = mtk_iommu_unmap, .flush_iotlb_all = mtk_iommu_flush_iotlb_all, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index ca581ff1c769..43e4c8f89e23 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -319,7 +319,7 @@ static int mtk_iommu_v1_attach_device(struct iommu_domain *domain, struct device return 0; } -static void mtk_iommu_v1_detach_device(struct iommu_domain *domain, struct device *dev) +static void mtk_iommu_v1_set_platform_dma(struct device *dev) { struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev); @@ -585,10 +585,10 @@ static const struct iommu_ops mtk_iommu_v1_ops = { .def_domain_type = mtk_iommu_v1_def_domain_type, .device_group = generic_device_group, .pgsize_bitmap = MT2701_IOMMU_PAGE_SIZE, + .set_platform_dma_ops = mtk_iommu_v1_set_platform_dma, .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = mtk_iommu_v1_attach_device, - .detach_dev = mtk_iommu_v1_detach_device, .map_pages = mtk_iommu_v1_map, .unmap_pages = mtk_iommu_v1_unmap, .iova_to_phys = mtk_iommu_v1_iova_to_phys, diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 00d98f08732f..40f57d293a79 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -10,6 +10,7 @@ #include <linux/limits.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_pci.h> #include <linux/pci.h> @@ -171,3 +172,98 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, return ops; } + +static enum iommu_resv_type __maybe_unused +iommu_resv_region_get_type(struct device *dev, + struct resource *phys, + phys_addr_t start, size_t length) +{ + phys_addr_t end = start + length - 1; + + /* + * IOMMU regions without an associated physical region cannot be + * mapped and are simply reservations. + */ + if (phys->start >= phys->end) + return IOMMU_RESV_RESERVED; + + /* may be IOMMU_RESV_DIRECT_RELAXABLE for certain cases */ + if (start == phys->start && end == phys->end) + return IOMMU_RESV_DIRECT; + + dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys, + &start, &end); + return IOMMU_RESV_RESERVED; +} + +/** + * of_iommu_get_resv_regions - reserved region driver helper for device tree + * @dev: device for which to get reserved regions + * @list: reserved region list + * + * IOMMU drivers can use this to implement their .get_resv_regions() callback + * for memory regions attached to a device tree node. See the reserved-memory + * device tree bindings on how to use these: + * + * Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt + */ +void of_iommu_get_resv_regions(struct device *dev, struct list_head *list) +{ +#if IS_ENABLED(CONFIG_OF_ADDRESS) + struct of_phandle_iterator it; + int err; + + of_for_each_phandle(&it, err, dev->of_node, "memory-region", NULL, 0) { + const __be32 *maps, *end; + struct resource phys; + int size; + + memset(&phys, 0, sizeof(phys)); + + /* + * The "reg" property is optional and can be omitted by reserved-memory regions + * that represent reservations in the IOVA space, which are regions that should + * not be mapped. + */ + if (of_find_property(it.node, "reg", NULL)) { + err = of_address_to_resource(it.node, 0, &phys); + if (err < 0) { + dev_err(dev, "failed to parse memory region %pOF: %d\n", + it.node, err); + continue; + } + } + + maps = of_get_property(it.node, "iommu-addresses", &size); + if (!maps) + continue; + + end = maps + size / sizeof(__be32); + + while (maps < end) { + struct device_node *np; + u32 phandle; + + phandle = be32_to_cpup(maps++); + np = of_find_node_by_phandle(phandle); + + if (np == dev->of_node) { + int prot = IOMMU_READ | IOMMU_WRITE; + struct iommu_resv_region *region; + enum iommu_resv_type type; + phys_addr_t iova; + size_t length; + + maps = of_translate_dma_region(np, maps, &iova, &length); + type = iommu_resv_region_get_type(dev, &phys, iova, length); + + region = iommu_alloc_resv_region(iova, length, prot, type, + GFP_KERNEL); + if (region) + list_add_tail(®ion->list, list); + } + } + } +#endif +} +EXPORT_SYMBOL(of_iommu_get_resv_regions); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 2fd7702c6709..3ab078112a7c 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1556,9 +1556,9 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain, omap_domain->dev = NULL; } -static void omap_iommu_detach_dev(struct iommu_domain *domain, - struct device *dev) +static void omap_iommu_set_platform_dma(struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct omap_iommu_domain *omap_domain = to_omap_domain(domain); spin_lock(&omap_domain->lock); @@ -1737,10 +1737,10 @@ static const struct iommu_ops omap_iommu_ops = { .probe_device = omap_iommu_probe_device, .release_device = omap_iommu_release_device, .device_group = omap_iommu_device_group, + .set_platform_dma_ops = omap_iommu_set_platform_dma, .pgsize_bitmap = OMAP_IOMMU_PGSIZES, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = omap_iommu_attach_dev, - .detach_dev = omap_iommu_detach_dev, .map = omap_iommu_map, .unmap = omap_iommu_unmap, .iova_to_phys = omap_iommu_iova_to_phys, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index a68eadd64f38..f30db22ea5d7 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1192,7 +1192,6 @@ static const struct iommu_ops rk_iommu_ops = { .of_xlate = rk_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = rk_iommu_attach_device, - .detach_dev = rk_iommu_detach_device, .map = rk_iommu_map, .unmap = rk_iommu_unmap, .iova_to_phys = rk_iommu_iova_to_phys, diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index ed33c6cce083..6849644e2892 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -52,7 +52,7 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type) if (!s390_domain) return NULL; - s390_domain->dma_table = dma_alloc_cpu_table(); + s390_domain->dma_table = dma_alloc_cpu_table(GFP_KERNEL); if (!s390_domain->dma_table) { kfree(s390_domain); return NULL; @@ -144,13 +144,10 @@ static int s390_iommu_attach_device(struct iommu_domain *domain, return 0; } -static void s390_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) +static void s390_iommu_set_platform_dma(struct device *dev) { struct zpci_dev *zdev = to_zpci_dev(dev); - WARN_ON(zdev->s390_domain != to_s390_domain(domain)); - __s390_iommu_detach_device(zdev); zpci_dma_init_device(zdev); } @@ -260,7 +257,8 @@ static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain, static int s390_iommu_validate_trans(struct s390_domain *s390_domain, phys_addr_t pa, dma_addr_t dma_addr, - unsigned long nr_pages, int flags) + unsigned long nr_pages, int flags, + gfp_t gfp) { phys_addr_t page_addr = pa & PAGE_MASK; unsigned long *entry; @@ -268,7 +266,8 @@ static int s390_iommu_validate_trans(struct s390_domain *s390_domain, int rc; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + gfp); if (unlikely(!entry)) { rc = -ENOMEM; goto undo_cpu_trans; @@ -284,7 +283,7 @@ undo_cpu_trans: while (i-- > 0) { dma_addr -= PAGE_SIZE; entry = dma_walk_cpu_trans(s390_domain->dma_table, - dma_addr); + dma_addr, gfp); if (!entry) break; dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID); @@ -301,7 +300,8 @@ static int s390_iommu_invalidate_trans(struct s390_domain *s390_domain, int rc = 0; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + GFP_ATOMIC); if (unlikely(!entry)) { rc = -EINVAL; break; @@ -339,7 +339,7 @@ static int s390_iommu_map_pages(struct iommu_domain *domain, flags |= ZPCI_TABLE_PROTECTED; rc = s390_iommu_validate_trans(s390_domain, paddr, iova, - pgcount, flags); + pgcount, flags, gfp); if (!rc) *mapped = size; @@ -435,11 +435,11 @@ static const struct iommu_ops s390_iommu_ops = { .probe_device = s390_iommu_probe_device, .release_device = s390_iommu_release_device, .device_group = generic_device_group, + .set_platform_dma_ops = s390_iommu_set_platform_dma, .pgsize_bitmap = SZ_4K, .get_resv_regions = s390_iommu_get_resv_regions, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = s390_iommu_attach_device, - .detach_dev = s390_iommu_detach_device, .map_pages = s390_iommu_map_pages, .unmap_pages = s390_iommu_unmap_pages, .flush_iotlb_all = s390_iommu_flush_iotlb_all, diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index 219bfa11f7f4..ae94d74b73f4 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -255,21 +255,6 @@ static int sprd_iommu_attach_device(struct iommu_domain *domain, return 0; } -static void sprd_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - struct sprd_iommu_domain *dom = to_sprd_domain(domain); - struct sprd_iommu_device *sdev = dom->sdev; - size_t pgt_size = sprd_iommu_pgt_size(domain); - - if (!sdev) - return; - - dma_free_coherent(sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); - sprd_iommu_hw_en(sdev, false); - dom->sdev = NULL; -} - static int sprd_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) @@ -414,7 +399,6 @@ static const struct iommu_ops sprd_iommu_ops = { .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = sprd_iommu_attach_device, - .detach_dev = sprd_iommu_detach_device, .map_pages = sprd_iommu_map, .unmap_pages = sprd_iommu_unmap, .iotlb_sync_map = sprd_iommu_sync_map, diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 5b585eace3d4..2d993d0cea7d 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -834,7 +834,6 @@ static const struct iommu_ops sun50i_iommu_ops = { .probe_device = sun50i_iommu_probe_device, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = sun50i_iommu_attach_device, - .detach_dev = sun50i_iommu_detach_device, .flush_iotlb_all = sun50i_iommu_flush_iotlb_all, .iotlb_sync_map = sun50i_iommu_iotlb_sync_map, .iotlb_sync = sun50i_iommu_iotlb_sync, diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index ed53279d1106..a482ff838b53 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -124,9 +124,9 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain, return ret; } -static void gart_iommu_detach_dev(struct iommu_domain *domain, - struct device *dev) +static void gart_iommu_set_platform_dma(struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct gart_device *gart = gart_handle; spin_lock(&gart->dom_lock); @@ -270,11 +270,11 @@ static const struct iommu_ops gart_iommu_ops = { .domain_alloc = gart_iommu_domain_alloc, .probe_device = gart_iommu_probe_device, .device_group = generic_device_group, + .set_platform_dma_ops = gart_iommu_set_platform_dma, .pgsize_bitmap = GART_IOMMU_PGSIZES, .of_xlate = gart_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = gart_iommu_attach_dev, - .detach_dev = gart_iommu_detach_dev, .map = gart_iommu_map, .unmap = gart_iommu_unmap, .iova_to_phys = gart_iommu_iova_to_phys, diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index af8d0e685260..1cbf063ccf14 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -511,8 +511,9 @@ disable: return err; } -static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev) +static void tegra_smmu_set_platform_dma(struct device *dev) { + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct tegra_smmu_as *as = to_smmu_as(domain); struct tegra_smmu *smmu = as->smmu; @@ -965,11 +966,11 @@ static const struct iommu_ops tegra_smmu_ops = { .domain_alloc = tegra_smmu_domain_alloc, .probe_device = tegra_smmu_probe_device, .device_group = tegra_smmu_device_group, + .set_platform_dma_ops = tegra_smmu_set_platform_dma, .of_xlate = tegra_smmu_of_xlate, .pgsize_bitmap = SZ_4K, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = tegra_smmu_attach_dev, - .detach_dev = tegra_smmu_detach_dev, .map = tegra_smmu_map, .unmap = tegra_smmu_unmap, .iova_to_phys = tegra_smmu_iova_to_phys, diff --git a/drivers/media/platform/qcom/venus/firmware.c b/drivers/media/platform/qcom/venus/firmware.c index 142d4c74017c..07d4dceb5e72 100644 --- a/drivers/media/platform/qcom/venus/firmware.c +++ b/drivers/media/platform/qcom/venus/firmware.c @@ -158,7 +158,7 @@ static int venus_boot_no_tz(struct venus_core *core, phys_addr_t mem_phys, core->fw.mapped_mem_size = mem_size; ret = iommu_map(iommu, VENUS_FW_START_ADDR, mem_phys, mem_size, - IOMMU_READ | IOMMU_WRITE | IOMMU_PRIV); + IOMMU_READ | IOMMU_WRITE | IOMMU_PRIV, GFP_KERNEL); if (ret) { dev_err(dev, "could not map video firmware region\n"); return ret; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 85096d1efe5b..db6ada2343af 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -472,7 +472,8 @@ static int ipa_imem_init(struct ipa *ipa, unsigned long addr, size_t size) size = PAGE_ALIGN(size + addr - phys); iova = phys; /* We just want a direct mapping */ - ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE); + ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret) return ret; @@ -580,7 +581,8 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) size = PAGE_ALIGN(size + addr - phys); iova = phys; /* We just want a direct mapping */ - ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE); + ret = iommu_map(domain, iova, phys, size, IOMMU_READ | IOMMU_WRITE, + GFP_KERNEL); if (ret) return ret; diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index cfcb759a87de..9a82f0336d95 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -1639,7 +1639,7 @@ static int ath10k_fw_init(struct ath10k *ar) ret = iommu_map(iommu_dom, ar_snoc->fw.fw_start_addr, ar->msa.paddr, ar->msa.mem_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath10k_err(ar, "failed to map firmware region: %d\n", ret); goto err_iommu_detach; diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index cd48eca494ed..920abce9053a 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -1036,7 +1036,7 @@ static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab) ret = iommu_map(iommu_dom, ab_ahb->fw.msa_paddr, ab_ahb->fw.msa_paddr, ab_ahb->fw.msa_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath11k_err(ab, "failed to map firmware region: %d\n", ret); goto err_iommu_detach; @@ -1044,7 +1044,7 @@ static int ath11k_ahb_fw_resources_init(struct ath11k_base *ab) ret = iommu_map(iommu_dom, ab_ahb->fw.ce_paddr, ab_ahb->fw.ce_paddr, ab_ahb->fw.ce_size, - IOMMU_READ | IOMMU_WRITE); + IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) { ath11k_err(ab, "failed to map firmware CE region: %d\n", ret); goto err_iommu_unmap; diff --git a/drivers/of/address.c b/drivers/of/address.c index 67763e5b8c0e..4c0b169ef9bf 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -626,6 +626,47 @@ u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr) } EXPORT_SYMBOL(of_translate_dma_address); +/** + * of_translate_dma_region - Translate device tree address and size tuple + * @dev: device tree node for which to translate + * @prop: pointer into array of cells + * @start: return value for the start of the DMA range + * @length: return value for the length of the DMA range + * + * Returns a pointer to the cell immediately following the translated DMA region. + */ +const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *prop, + phys_addr_t *start, size_t *length) +{ + struct device_node *parent; + u64 address, size; + int na, ns; + + parent = __of_get_dma_parent(dev); + if (!parent) + return NULL; + + na = of_bus_n_addr_cells(parent); + ns = of_bus_n_size_cells(parent); + + of_node_put(parent); + + address = of_translate_dma_address(dev, prop); + if (address == OF_BAD_ADDR) + return NULL; + + size = of_read_number(prop + na, ns); + + if (start) + *start = address; + + if (length) + *length = size; + + return prop + na + ns; +} +EXPORT_SYMBOL(of_translate_dma_region); + const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, u64 *size, unsigned int *flags) { diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 1cd4815a6dd1..80072b6b6283 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -643,7 +643,8 @@ static int rproc_handle_devmem(struct rproc *rproc, void *ptr, if (!mapping) return -ENOMEM; - ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags); + ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags, + GFP_KERNEL); if (ret) { dev_err(dev, "failed to map devmem: %d\n", ret); goto out; @@ -737,7 +738,7 @@ static int rproc_alloc_carveout(struct rproc *rproc, } ret = iommu_map(rproc->domain, mem->da, dma, mem->len, - mem->flags); + mem->flags, GFP_KERNEL); if (ret) { dev_err(dev, "iommu_map failed: %d\n", ret); goto free_mapping; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 2209372f236d..5600eb67ca30 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1480,7 +1480,8 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova, list_for_each_entry(d, &iommu->domain_list, next) { ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT, - npage << PAGE_SHIFT, prot | IOMMU_CACHE); + npage << PAGE_SHIFT, prot | IOMMU_CACHE, + GFP_KERNEL); if (ret) goto unwind; @@ -1777,8 +1778,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, size = npage << PAGE_SHIFT; } - ret = iommu_map(domain->domain, iova, phys, - size, dma->prot | IOMMU_CACHE); + ret = iommu_map(domain->domain, iova, phys, size, + dma->prot | IOMMU_CACHE, GFP_KERNEL); if (ret) { if (!dma->iommu_mapped) { vfio_unpin_pages_remote(dma, iova, @@ -1873,7 +1874,7 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head * continue; ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2, - IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL); if (!ret) { size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 9c5010ee20da..315f9ba47ff2 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -792,7 +792,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, r = ops->set_map(vdpa, asid, iotlb); } else { r = iommu_map(v->domain, iova, pa, size, - perm_to_iommu_flags(perm)); + perm_to_iommu_flags(perm), GFP_KERNEL); } if (r) { vhost_iotlb_del_range(iotlb, iova, iova + size - 1); diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index cdedccccc4f3..81b9e794424d 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -804,7 +804,7 @@ struct acpi_dmar_pci_path { struct acpi_dmar_hardware_unit { struct acpi_dmar_header header; u8 flags; - u8 reserved; + u8 size; /* Size of the register set */ u16 segment; u64 address; /* Register Base Address */ }; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6c6859bfc454..f2ea348ce3b0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -221,6 +221,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, + CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d81a51978d01..725d5e6acec0 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -39,6 +39,7 @@ struct dmar_drhd_unit { struct list_head list; /* list of drhd units */ struct acpi_dmar_header *hdr; /* ACPI header */ u64 reg_base_addr; /* register base address*/ + unsigned long reg_size; /* size of register set */ struct dmar_dev_scope *devices;/* target device array */ int devices_cnt; /* target device count */ u16 segment; /* PCI domain */ diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h deleted file mode 100644 index f9a0d44f6fdb..000000000000 --- a/include/linux/intel-svm.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright © 2015 Intel Corporation. - * - * Authors: David Woodhouse <David.Woodhouse@intel.com> - */ - -#ifndef __INTEL_SVM_H__ -#define __INTEL_SVM_H__ - -/* Page Request Queue depth */ -#define PRQ_ORDER 4 -#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) -#define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) - -#endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 46e1347bfa22..3589d1b8f922 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -228,6 +228,9 @@ struct iommu_iotlb_gather { * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain + * @set_platform_dma_ops: Returning control back to the platform DMA ops. This op + * is to support old IOMMU drivers, new drivers should use + * default domains, and the common IOMMU DMA ops. * @device_group: find iommu group for a particular device * @get_resv_regions: Request list of reserved regions for a device * @of_xlate: add OF master IDs to iommu grouping @@ -256,6 +259,7 @@ struct iommu_ops { struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); + void (*set_platform_dma_ops)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); /* Request/Free a list of reserved regions for a device */ @@ -295,7 +299,6 @@ struct iommu_ops { * * EBUSY - device is attached to a domain and cannot be changed * * ENODEV - device specific errors, not able to be attached * * <others> - treated as ENODEV by the caller. Use is discouraged - * @detach_dev: detach an iommu domain from a device * @set_dev_pasid: set an iommu domain to a pasid of device * @map: map a physically contiguous memory region to an iommu domain * @map_pages: map a physically contiguous set of pages of the same size to @@ -316,7 +319,6 @@ struct iommu_ops { */ struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); @@ -401,6 +403,7 @@ struct iommu_fault_param { * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data * @max_pasids: number of PASIDs this device can consume + * @attach_deferred: the dma domain attachment is deferred * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. * struct iommu_group *iommu_group; @@ -413,6 +416,7 @@ struct dev_iommu { struct iommu_device *iommu_dev; void *priv; u32 max_pasids; + u32 attach_deferred:1; }; int iommu_device_register(struct iommu_device *iommu, @@ -467,19 +471,15 @@ extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); -extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); extern ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot); -extern ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot); + struct scatterlist *sg, unsigned int nents, + int prot, gfp_t gfp); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -773,14 +773,7 @@ static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) } static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - return -ENODEV; -} - -static inline int iommu_map_atomic(struct iommu_domain *domain, - unsigned long iova, phys_addr_t paddr, - size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { return -ENODEV; } @@ -800,14 +793,7 @@ static inline size_t iommu_unmap_fast(struct iommu_domain *domain, static inline ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) -{ - return -ENODEV; -} - -static inline ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) + unsigned int nents, int prot, gfp_t gfp) { return -ENODEV; } @@ -1118,7 +1104,8 @@ iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, static inline size_t iommu_map_sgtable(struct iommu_domain *domain, unsigned long iova, struct sg_table *sgt, int prot) { - return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot, + GFP_KERNEL); } #ifdef CONFIG_IOMMU_DEBUGFS diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 265f26eeaf6b..376671594746 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -38,6 +38,8 @@ struct of_pci_range { /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr); +extern const __be32 *of_translate_dma_region(struct device_node *dev, const __be32 *addr, + phys_addr_t *start, size_t *length); #ifdef CONFIG_OF_ADDRESS extern u64 of_translate_address(struct device_node *np, const __be32 *addr); diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 55c1eb300a86..9a5e6b410dd2 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -12,6 +12,9 @@ extern const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np, const u32 *id); +extern void of_iommu_get_resv_regions(struct device *dev, + struct list_head *list); + #else static inline const struct iommu_ops *of_iommu_configure(struct device *dev, @@ -21,6 +24,11 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, return NULL; } +static inline void of_iommu_get_resv_regions(struct device *dev, + struct list_head *list) +{ +} + #endif /* CONFIG_OF_IOMMU */ #endif /* __OF_IOMMU_H */ diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h index 29096fe12623..70743db1fb75 100644 --- a/include/trace/events/iommu.h +++ b/include/trace/events/iommu.h @@ -76,13 +76,6 @@ DEFINE_EVENT(iommu_device_event, attach_device_to_domain, TP_ARGS(dev) ); -DEFINE_EVENT(iommu_device_event, detach_device_from_domain, - - TP_PROTO(struct device *dev), - - TP_ARGS(dev) -); - TRACE_EVENT(map, TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size), |