diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-30 13:00:38 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-30 13:00:38 -0700 |
| commit | 58390c8ce1bddb6c623f62e7ed36383e7fa5c02f (patch) | |
| tree | a2abd81e21456b1e2bcbc3bac4dd94650b7a18ec /drivers/iommu | |
| parent | 7acc1372113083fa281ba426021801e2402caca1 (diff) | |
| parent | e51b4198396cd715b140c0e8b259680429ff0cfb (diff) | |
| download | linux-stable-58390c8ce1bddb6c623f62e7ed36383e7fa5c02f.tar.gz | |
Merge tag 'iommu-updates-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
- Convert to platform remove callback returning void
- Extend changing default domain to normal group
- Intel VT-d updates:
- Remove VT-d virtual command interface and IOASID
- Allow the VT-d driver to support non-PRI IOPF
- Remove PASID supervisor request support
- Various small and misc cleanups
- ARM SMMU updates:
- Device-tree binding updates:
* Allow Qualcomm GPU SMMUs to accept relevant clock properties
* Document Qualcomm 8550 SoC as implementing an MMU-500
* Favour new "qcom,smmu-500" binding for Adreno SMMUs
- Fix S2CR quirk detection on non-architectural Qualcomm SMMU
implementations
- Acknowledge SMMUv3 PRI queue overflow when consuming events
- Document (in a comment) why ATS is disabled for bypass streams
- AMD IOMMU updates:
- 5-level page-table support
- NUMA awareness for memory allocations
- Unisoc driver: Support for reattaching an existing domain
- Rockchip driver: Add missing set_platform_dma_ops callback
- Mediatek driver: Adjust the dma-ranges
- Various other small fixes and cleanups
* tag 'iommu-updates-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (82 commits)
iommu: Remove iommu_group_get_by_id()
iommu: Make iommu_release_device() static
iommu/vt-d: Remove BUG_ON in dmar_insert_dev_scope()
iommu/vt-d: Remove a useless BUG_ON(dev->is_virtfn)
iommu/vt-d: Remove BUG_ON in map/unmap()
iommu/vt-d: Remove BUG_ON when domain->pgd is NULL
iommu/vt-d: Remove BUG_ON in handling iotlb cache invalidation
iommu/vt-d: Remove BUG_ON on checking valid pfn range
iommu/vt-d: Make size of operands same in bitwise operations
iommu/vt-d: Remove PASID supervisor request support
iommu/vt-d: Use non-privileged mode for all PASIDs
iommu/vt-d: Remove extern from function prototypes
iommu/vt-d: Do not use GFP_ATOMIC when not needed
iommu/vt-d: Remove unnecessary checks in iopf disabling path
iommu/vt-d: Move PRI handling to IOPF feature path
iommu/vt-d: Move pfsid and ats_qdep calculation to device probe path
iommu/vt-d: Move iopf code from SVA to IOPF enabling path
iommu/vt-d: Allow SVA with device-specific IOPF
dmaengine: idxd: Add enable/disable device IOPF feature
arm64: dts: mt8186: Add dma-ranges for the parent "soc" node
...
Diffstat (limited to 'drivers/iommu')
35 files changed, 673 insertions, 1084 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 889c7efd050b..db98c3f86e8c 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -3,10 +3,6 @@ config IOMMU_IOVA tristate -# The IOASID library may also be used by non-IOMMU_API users -config IOASID - tristate - # IOMMU_API always gets selected by whoever wants it. config IOMMU_API bool @@ -33,7 +29,7 @@ config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE depends on ARM || ARM64 || COMPILE_TEST - depends on !GENERIC_ATOMIC64 # for cpmxchg64() + depends on !GENERIC_ATOMIC64 # for cmpxchg64() help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page @@ -72,7 +68,7 @@ config IOMMU_IO_PGTABLE_DART bool "Apple DART Formats" select IOMMU_IO_PGTABLE depends on ARM64 || COMPILE_TEST - depends on !GENERIC_ATOMIC64 # for cpmxchg64() + depends on !GENERIC_ATOMIC64 # for cmpxchg64() help Enable support for the Apple DART pagetable formats. These include the t8020 and t6000/t8110 DART formats used in Apple M1/M2 family @@ -160,7 +156,6 @@ config IOMMU_DMA # Shared Virtual Addressing config IOMMU_SVA bool - select IOASID config FSL_PAMU bool "Freescale IOMMU support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index f461d0651385..769e43d780ce 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o obj-$(CONFIG_IOMMU_IO_PGTABLE_DART) += io-pgtable-dart.o -obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index c160a332ce33..e98f20a9bdd8 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -34,6 +34,7 @@ extern int amd_iommu_reenable(int); extern int amd_iommu_enable_faulting(void); extern int amd_iommu_guest_ir; extern enum io_pgtable_fmt amd_iommu_pgtable; +extern int amd_iommu_gpt_level; /* IOMMUv2 specific functions */ struct iommu_domain; @@ -122,6 +123,14 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev) return PCI_SEG_DEVID_TO_SBDF(seg, devid); } +static inline void *alloc_pgtable_page(int nid, gfp_t gfp) +{ + struct page *page; + + page = alloc_pages_node(nid, gfp | __GFP_ZERO, 0); + return page ? page_address(page) : NULL; +} + extern bool translation_pre_enabled(struct amd_iommu *iommu); extern bool amd_iommu_is_attach_deferred(struct device *dev); extern int __init add_special_device(u8 type, u8 id, u32 *devid, diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 3d684190b4d5..2ddbda3a4374 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -93,6 +93,8 @@ #define FEATURE_GA (1ULL<<7) #define FEATURE_HE (1ULL<<8) #define FEATURE_PC (1ULL<<9) +#define FEATURE_GATS_SHIFT (12) +#define FEATURE_GATS_MASK (3ULL) #define FEATURE_GAM_VAPIC (1ULL<<21) #define FEATURE_GIOSUP (1ULL<<48) #define FEATURE_EPHSUP (1ULL<<50) @@ -305,6 +307,9 @@ #define PAGE_MODE_6_LEVEL 0x06 #define PAGE_MODE_7_LEVEL 0x07 +#define GUEST_PGTABLE_4_LEVEL 0x00 +#define GUEST_PGTABLE_5_LEVEL 0x01 + #define PM_LEVEL_SHIFT(x) (12 + ((x) * 9)) #define PM_LEVEL_SIZE(x) (((x) < 6) ? \ ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \ @@ -398,6 +403,8 @@ #define DTE_GCR3_SHIFT_B 16 #define DTE_GCR3_SHIFT_C 43 +#define DTE_GPT_LEVEL_SHIFT 54 + #define GCR3_VALID 0x01ULL #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) @@ -549,6 +556,7 @@ struct protection_domain { spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ int glx; /* Number of levels for GCR3 table */ + int nid; /* Node ID */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ unsigned dev_cnt; /* devices assigned to this domain */ @@ -1001,8 +1009,8 @@ struct amd_ir_data { */ struct irq_cfg *cfg; int ga_vector; - int ga_root_ptr; - int ga_tag; + u64 ga_root_ptr; + u32 ga_tag; }; struct amd_irte_ops { diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 19a46b9f7357..329a406cc37d 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -153,6 +153,8 @@ bool amd_iommu_dump; bool amd_iommu_irq_remap __read_mostly; enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1; +/* Guest page table level */ +int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL; int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC; static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; @@ -306,6 +308,11 @@ static bool check_feature_on_all_iommus(u64 mask) return !!(amd_iommu_efr & mask); } +static inline int check_feature_gpt_level(void) +{ + return ((amd_iommu_efr >> FEATURE_GATS_SHIFT) & FEATURE_GATS_MASK); +} + /* * For IVHD type 0x11/0x40, EFR is also available via IVHD. * Default to IVHD EFR since it is available sooner @@ -1941,7 +1948,7 @@ static ssize_t amd_iommu_show_cap(struct device *dev, char *buf) { struct amd_iommu *iommu = dev_to_amd_iommu(dev); - return sprintf(buf, "%x\n", iommu->cap); + return sysfs_emit(buf, "%x\n", iommu->cap); } static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL); @@ -1950,7 +1957,7 @@ static ssize_t amd_iommu_show_features(struct device *dev, char *buf) { struct amd_iommu *iommu = dev_to_amd_iommu(dev); - return sprintf(buf, "%llx:%llx\n", iommu->features2, iommu->features); + return sysfs_emit(buf, "%llx:%llx\n", iommu->features2, iommu->features); } static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL); @@ -2155,8 +2162,10 @@ static void print_iommu_info(void) if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) pr_info("X2APIC enabled\n"); } - if (amd_iommu_pgtable == AMD_IOMMU_V2) - pr_info("V2 page table enabled\n"); + if (amd_iommu_pgtable == AMD_IOMMU_V2) { + pr_info("V2 page table enabled (Paging mode : %d level)\n", + amd_iommu_gpt_level); + } } static int __init amd_iommu_init_pci(void) @@ -2383,6 +2392,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu) struct irq_domain *domain; struct irq_alloc_info info; int irq, ret; + int node = dev_to_node(&iommu->dev->dev); domain = iommu_get_irqdomain(); if (!domain) @@ -2392,7 +2402,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu) info.type = X86_IRQ_ALLOC_TYPE_AMDVI; info.data = iommu; - irq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); + irq = irq_domain_alloc_irqs(domain, 1, node, &info); if (irq < 0) { irq_domain_remove(domain); return irq; @@ -3025,6 +3035,11 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; + /* 5 level guest page table */ + if (cpu_feature_enabled(X86_FEATURE_LA57) && + check_feature_gpt_level() == GUEST_PGTABLE_5_LEVEL) + amd_iommu_gpt_level = PAGE_MODE_5_LEVEL; + /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -3556,6 +3571,11 @@ __setup("ivrs_acpihid", parse_ivrs_acpihid); bool amd_iommu_v2_supported(void) { + /* CPU page table size should match IOMMU guest page table size */ + if (cpu_feature_enabled(X86_FEATURE_LA57) && + amd_iommu_gpt_level != PAGE_MODE_5_LEVEL) + return false; + /* * Since DTE[Mode]=0 is prohibited on SNP-enabled system * (i.e. EFR[SNPSup]=1), IOMMUv2 page table cannot be used without diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index ace0e9b8b913..1b67116882be 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -156,7 +156,7 @@ static bool increase_address_space(struct protection_domain *domain, bool ret = true; u64 *pte; - pte = (void *)get_zeroed_page(gfp); + pte = alloc_pgtable_page(domain->nid, gfp); if (!pte) return false; @@ -250,7 +250,7 @@ static u64 *alloc_pte(struct protection_domain *domain, if (!IOMMU_PTE_PRESENT(__pte) || pte_level == PAGE_MODE_NONE) { - page = (u64 *)get_zeroed_page(gfp); + page = alloc_pgtable_page(domain->nid, gfp); if (!page) return NULL; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index 8638ddf6fb3b..27c3015947e6 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -37,8 +37,7 @@ static inline int get_pgtable_level(void) { - /* 5 level page table is not supported */ - return PAGE_MODE_4_LEVEL; + return amd_iommu_gpt_level; } static inline bool is_large_pte(u64 pte) @@ -46,11 +45,6 @@ static inline bool is_large_pte(u64 pte) return (pte & IOMMU_PAGE_PSE); } -static inline void *alloc_pgtable_page(void) -{ - return (void *)get_zeroed_page(GFP_KERNEL); -} - static inline u64 set_pgtable_attr(u64 *page) { u64 prot; @@ -138,8 +132,8 @@ static void free_pgtable(u64 *pt, int level) } /* Allocate page table */ -static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova, - unsigned long pg_size, bool *updated) +static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova, + unsigned long pg_size, gfp_t gfp, bool *updated) { u64 *pte, *page; int level, end_level; @@ -162,7 +156,7 @@ static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova, } if (!IOMMU_PTE_PRESENT(__pte)) { - page = alloc_pgtable_page(); + page = alloc_pgtable_page(nid, gfp); if (!page) return NULL; @@ -262,7 +256,8 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, while (mapped_size < size) { map_size = get_alloc_page_size(pgsize); - pte = v2_alloc_pte(pdom->iop.pgd, iova, map_size, &updated); + pte = v2_alloc_pte(pdom->nid, pdom->iop.pgd, + iova, map_size, gfp, &updated); if (!pte) { ret = -EINVAL; goto out; @@ -383,8 +378,9 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); struct protection_domain *pdom = (struct protection_domain *)cookie; int ret; + int ias = IOMMU_IN_ADDR_BIT_SIZE; - pgtable->pgd = alloc_pgtable_page(); + pgtable->pgd = alloc_pgtable_page(pdom->nid, GFP_ATOMIC); if (!pgtable->pgd) return NULL; @@ -392,12 +388,15 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (ret) goto err_free_pgd; + if (get_pgtable_level() == PAGE_MODE_5_LEVEL) + ias = 57; + pgtable->iop.ops.map_pages = iommu_v2_map_pages; pgtable->iop.ops.unmap_pages = iommu_v2_unmap_pages; pgtable->iop.ops.iova_to_phys = iommu_v2_iova_to_phys; cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES_V2, - cfg->ias = IOMMU_IN_ADDR_BIT_SIZE, + cfg->ias = ias, cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE, cfg->tlb = &v2_flush_ops; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5a505ba5467e..4a314647d1f7 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1611,6 +1611,11 @@ static void set_dte_entry(struct amd_iommu *iommu, u16 devid, tmp = DTE_GCR3_VAL_C(gcr3) << DTE_GCR3_SHIFT_C; flags |= tmp; + if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) { + dev_table[devid].data[2] |= + ((u64)GUEST_PGTABLE_5_LEVEL << DTE_GPT_LEVEL_SHIFT); + } + if (domain->flags & PD_GIOV_MASK) pte_root |= DTE_FLAG_GIOV; } @@ -1662,14 +1667,14 @@ static void do_attach(struct iommu_dev_data *dev_data, dev_data->domain = domain; list_add(&dev_data->list, &domain->dev_list); + /* Update NUMA Node ID */ + if (domain->nid == NUMA_NO_NODE) + domain->nid = dev_to_node(dev_data->dev); + /* Do reference counting */ domain->dev_iommu[iommu->index] += 1; domain->dev_cnt += 1; - /* Override supported page sizes */ - if (domain->flags & PD_GIOV_MASK) - domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2; - /* Update device table */ set_dte_entry(iommu, dev_data->devid, domain, ats, dev_data->iommu_v2); @@ -2048,6 +2053,8 @@ static int protection_domain_init_v2(struct protection_domain *domain) domain->flags |= PD_GIOV_MASK; + domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2; + if (domain_enable_v2(domain, 1)) { domain_id_free(domain->id); return -ENOMEM; @@ -2097,6 +2104,8 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) if (type == IOMMU_DOMAIN_IDENTITY) return domain; + domain->nid = NUMA_NO_NODE; + pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain); if (!pgtbl_ops) { domain_id_free(domain->id); diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 06169d36eab8..8af64b57f048 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -1150,7 +1150,7 @@ err_clk_disable: return ret; } -static int apple_dart_remove(struct platform_device *pdev) +static void apple_dart_remove(struct platform_device *pdev) { struct apple_dart *dart = platform_get_drvdata(pdev); @@ -1161,8 +1161,6 @@ static int apple_dart_remove(struct platform_device *pdev) iommu_device_sysfs_remove(&dart->iommu); clk_bulk_disable_unprepare(dart->num_clks, dart->clks); - - return 0; } static const struct apple_dart_hw apple_dart_hw_t8103 = { @@ -1296,7 +1294,7 @@ static struct platform_driver apple_dart_driver = { .pm = pm_sleep_ptr(&apple_dart_pm_ops), }, .probe = apple_dart_probe, - .remove = apple_dart_remove, + .remove_new = apple_dart_remove, }; module_platform_driver(apple_dart_driver); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index f2425b0f0cd6..3fd83fb75722 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons); } +static void queue_sync_cons_ovf(struct arm_smmu_queue *q) +{ + struct arm_smmu_ll_queue *llq = &q->llq; + + if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons))) + return; + + llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | + Q_IDX(llq, llq->cons); + queue_sync_cons_out(q); +} + static int queue_sync_prod_in(struct arm_smmu_queue *q) { u32 prod; @@ -1577,8 +1589,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } @@ -1636,9 +1647,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); - queue_sync_cons_out(q); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } @@ -2447,6 +2456,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) master->domain = smmu_domain; + /* + * The SMMU does not support enabling ATS with bypass. When the STE is + * in bypass (STE.Config[2:0] == 0b100), ATS Translation Requests and + * Translated transactions are denied as though ATS is disabled for the + * stream (STE.EATS == 0b00), causing F_BAD_ATS_TREQ and + * F_TRANSL_FORBIDDEN events (IHI0070Ea 5.2 Stream Table Entry). + */ if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS) master->ats_enabled = arm_smmu_ats_supported(master); @@ -3844,7 +3860,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) return 0; } -static int arm_smmu_device_remove(struct platform_device *pdev) +static void arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); @@ -3852,8 +3868,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev) iommu_device_sysfs_remove(&smmu->iommu); arm_smmu_device_disable(smmu); iopf_queue_free(smmu->evtq.iopf); - - return 0; } static void arm_smmu_device_shutdown(struct platform_device *pdev) @@ -3882,7 +3896,7 @@ static struct platform_driver arm_smmu_driver = { .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, - .remove = arm_smmu_device_remove, + .remove_new = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; module_driver(arm_smmu_driver, platform_driver_register, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d1b296b95c86..ae09c627bc84 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -268,13 +268,27 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) { - unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + unsigned int last_s2cr; u32 reg; u32 smr; int i; /* + * Some platforms support more than the Arm SMMU architected maximum of + * 128 stream matching groups. For unknown reasons, the additional + * groups don't exhibit the same behavior as the architected registers, + * so limit the groups to 128 until the behavior is fixed for the other + * groups. + */ + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } + + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + + /* * With some firmware versions writes to S2CR of type FAULT are * ignored, and writing BYPASS will end up written as FAULT in the * register. Perform a write to S2CR to detect if this is the case and diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 2ff7a72cf377..6e0813b26fb6 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -139,7 +139,7 @@ static int arm_smmu_register_legacy_master(struct device *dev, int err; np = dev_get_dev_node(dev); - if (!np || !of_find_property(np, "#stream-id-cells", NULL)) { + if (!np || !of_property_present(np, "#stream-id-cells")) { of_node_put(np); return -ENODEV; } @@ -2195,9 +2195,6 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); - if (!smmu) - return; - if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS)) dev_notice(&pdev->dev, "disabling translation\n"); @@ -2214,19 +2211,14 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) clk_bulk_unprepare(smmu->num_clks, smmu->clks); } -static int arm_smmu_device_remove(struct platform_device *pdev) +static void arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); - if (!smmu) - return -ENODEV; - iommu_device_unregister(&smmu->iommu); iommu_device_sysfs_remove(&smmu->iommu); arm_smmu_device_shutdown(pdev); - - return 0; } static int __maybe_unused arm_smmu_runtime_resume(struct device *dev) @@ -2302,7 +2294,7 @@ static struct platform_driver arm_smmu_driver = { .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, - .remove = arm_smmu_device_remove, + .remove_new = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; module_platform_driver(arm_smmu_driver); diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index c8b70f476cd8..a503ed758ec3 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -682,7 +682,7 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev) return 0; } -static int qcom_iommu_ctx_remove(struct platform_device *pdev) +static void qcom_iommu_ctx_remove(struct platform_device *pdev) { struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(pdev->dev.parent); struct qcom_iommu_ctx *ctx = platform_get_drvdata(pdev); @@ -690,8 +690,6 @@ static int qcom_iommu_ctx_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); qcom_iommu->ctxs[ctx->asid - 1] = NULL; - - return 0; } static const struct of_device_id ctx_of_match[] = { @@ -706,7 +704,7 @@ static struct platform_driver qcom_iommu_ctx_driver = { .of_match_table = ctx_of_match, }, .probe = qcom_iommu_ctx_probe, - .remove = qcom_iommu_ctx_remove, + .remove_new = qcom_iommu_ctx_remove, }; static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu) @@ -824,7 +822,7 @@ err_pm_disable: return ret; } -static int qcom_iommu_device_remove(struct platform_device *pdev) +static void qcom_iommu_device_remove(struct platform_device *pdev) { struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev); @@ -832,8 +830,6 @@ static int qcom_iommu_device_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); iommu_device_sysfs_remove(&qcom_iommu->iommu); iommu_device_unregister(&qcom_iommu->iommu); - - return 0; } static int __maybe_unused qcom_iommu_resume(struct device *dev) @@ -870,7 +866,7 @@ static struct platform_driver qcom_iommu_driver = { .pm = &qcom_iommu_pm_ops, }, .probe = qcom_iommu_device_probe, - .remove = qcom_iommu_device_remove, + .remove_new = qcom_iommu_device_remove, }; static int __init qcom_iommu_init(void) diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 1abd187c6075..c275fe71c4db 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -747,22 +747,16 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) return ret; } - data->clk = devm_clk_get(dev, "sysmmu"); - if (PTR_ERR(data->clk) == -ENOENT) - data->clk = NULL; - else if (IS_ERR(data->clk)) + data->clk = devm_clk_get_optional(dev, "sysmmu"); + if (IS_ERR(data->clk)) return PTR_ERR(data->clk); - data->aclk = devm_clk_get(dev, "aclk"); - if (PTR_ERR(data->aclk) == -ENOENT) - data->aclk = NULL; - else if (IS_ERR(data->aclk)) + data->aclk = devm_clk_get_optional(dev, "aclk"); + if (IS_ERR(data->aclk)) return PTR_ERR(data->aclk); - data->pclk = devm_clk_get(dev, "pclk"); - if (PTR_ERR(data->pclk) == -ENOENT) - data->pclk = NULL; - else if (IS_ERR(data->pclk)) + data->pclk = devm_clk_get_optional(dev, "pclk"); + if (IS_ERR(data->pclk)) return PTR_ERR(data->pclk); if (!data->clk && (!data->aclk || !data->pclk)) { @@ -770,10 +764,8 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) return -ENOSYS; } - data->clk_master = devm_clk_get(dev, "master"); - if (PTR_ERR(data->clk_master) == -ENOENT) - data->clk_master = NULL; - else if (IS_ERR(data->clk_master)) + data->clk_master = devm_clk_get_optional(dev, "master"); + if (IS_ERR(data->clk_master)) return PTR_ERR(data->clk_master); data->sysmmu = dev; diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index 05d820fb1d0b..f37d3b044131 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -178,7 +178,7 @@ int pamu_update_paace_stash(int liodn, u32 value) } /** - * pamu_config_paace() - Sets up PPAACE entry for specified liodn + * pamu_config_ppaace() - Sets up PPAACE entry for specified liodn * * @liodn: Logical IO device number * @omi: Operation mapping index -- if ~omi == 0 then omi not defined @@ -232,7 +232,8 @@ int pamu_config_ppaace(int liodn, u32 omi, u32 stashid, int prot) /** * get_ome_index() - Returns the index in the operation mapping table * for device. - * @*omi_index: pointer for storing the index value + * @omi_index: pointer for storing the index value + * @dev: target device * */ void get_ome_index(u32 *omi_index, struct device *dev) @@ -328,7 +329,7 @@ found_cpu_node: #define QMAN_PORTAL_PAACE 2 #define BMAN_PAACE 3 -/** +/* * Setup operation mapping and stash destinations for QMAN and QMAN portal. * Memory accesses to QMAN and BMAN private memory need not be coherent, so * clear the PAACE entry coherency attribute for them. @@ -357,7 +358,7 @@ static void setup_qbman_paace(struct paace *ppaace, int paace_type) } } -/** +/* * Setup the operation mapping table for various devices. This is a static * table where each table index corresponds to a particular device. PAMU uses * this table to translate device transaction to appropriate corenet diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index 12e1e90fdae1..2e56bd79f589 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -18,7 +18,6 @@ config INTEL_IOMMU select NEED_DMA_MAP_STATE select DMAR_TABLE select SWIOTLB - select IOASID select PCI_ATS select PCI_PRI select PCI_PASID diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c index 806986696841..9862dc20b35e 100644 --- a/drivers/iommu/intel/cap_audit.c +++ b/drivers/iommu/intel/cap_audit.c @@ -54,7 +54,6 @@ static inline void check_dmar_capabilities(struct intel_iommu *a, CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK); @@ -101,7 +100,6 @@ static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 23828d189c2a..a3414afe11b0 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -127,8 +127,6 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) struct pci_dev *tmp; struct dmar_pci_notify_info *info; - BUG_ON(dev->is_virtfn); - /* * Ignore devices that have a domain number higher than what can * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 @@ -264,7 +262,8 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, get_device(dev)); return 1; } - BUG_ON(i >= devices_cnt); + if (WARN_ON(i >= devices_cnt)) + return -EINVAL; } return 0; @@ -993,8 +992,6 @@ static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } - if (ecap_vcs(iommu->ecap)) - iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), @@ -1690,7 +1687,7 @@ static void __dmar_enable_qi(struct intel_iommu *iommu) * is present. */ if (ecap_smts(iommu->ecap)) - val |= (1 << 11) | 1; + val |= BIT_ULL(11) | BIT_ULL(0); raw_spin_lock_irqsave(&iommu->register_lock, flags); @@ -1961,7 +1958,7 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, return 0; } - if (pasid == INVALID_IOASID) + if (pasid == IOMMU_PASID_INVALID) pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), @@ -2042,7 +2039,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) if (!ratelimited) /* Using pasid -1 if pasid is not present */ dmar_fault_do_one(iommu, type, fault_reason, - pasid_present ? pasid : INVALID_IOASID, + pasid_present ? pasid : IOMMU_PASID_INVALID, source_id, guest_addr); fault_index++; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7c2f4bd33582..b871a6afd803 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -876,7 +876,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, return; } /* For request-without-pasid, get the pasid from context entry */ - if (intel_iommu_sm && pasid == INVALID_IOASID) + if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID) pasid = PASID_RID2PASID; dir_index = pasid >> PASID_PDE_SHIFT; @@ -915,8 +915,6 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, int level = agaw_to_level(domain->agaw); int offset; - BUG_ON(!domain->pgd); - if (!domain_pfn_supported(domain, pfn)) /* Address beyond IOMMU's addressing capabilities. */ return NULL; @@ -1005,9 +1003,9 @@ static void dma_pte_clear_range(struct dmar_domain *domain, unsigned int large_page; struct dma_pte *first_pte, *pte; - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ do { @@ -1166,9 +1164,9 @@ next: static void domain_unmap(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn, struct list_head *freelist) { - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ dma_pte_clear_level(domain, agaw_to_level(domain->agaw), @@ -1272,7 +1270,9 @@ static void __iommu_flush_context(struct intel_iommu *iommu, | DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask); break; default: - BUG(); + pr_warn("%s: Unexpected context-cache invalidation type 0x%llx\n", + iommu->name, type); + return; } val |= DMA_CCMD_ICC; @@ -1308,7 +1308,9 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, val_iva = size_order | addr; break; default: - BUG(); + pr_warn("%s: Unexpected iotlb invalidation type 0x%llx\n", + iommu->name, type); + return; } /* Note: set drain read/write */ #if 0 @@ -1406,20 +1408,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) return; pdev = to_pci_dev(info->dev); - /* For IOMMU that supports device IOTLB throttling (DIT), we assign - * PFSID to the invalidation desc of a VF such that IOMMU HW can gauge - * queue depth at PF level. If DIT is not set, PFSID will be treated as - * reserved, which should be set to 0. - */ - if (!ecap_dit(info->iommu->ecap)) - info->pfsid = 0; - else { - struct pci_dev *pf_pdev; - - /* pdev will be returned if device is not a vf */ - pf_pdev = pci_physfn(pdev); - info->pfsid = pci_dev_id(pf_pdev); - } /* The PCIe spec, in its wisdom, declares that the behaviour of the device if you enable PASID support after ATS support is @@ -1429,16 +1417,10 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) if (info->pasid_supported && !pci_enable_pasid(pdev, info->pasid_supported & ~1)) info->pasid_enabled = 1; - if (info->pri_supported && - (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1) && - !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH)) - info->pri_enabled = 1; - if (info->ats_supported && pci_ats_page_aligned(pdev) && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; domain_update_iotlb(info->domain); - info->ats_qdep = pci_ats_queue_depth(pdev); } } @@ -1457,11 +1439,6 @@ static void iommu_disable_pci_caps(struct device_domain_info *info) domain_update_iotlb(info->domain); } - if (info->pri_enabled) { - pci_disable_pri(pdev); - info->pri_enabled = 0; - } - if (info->pasid_enabled) { pci_disable_pasid(pdev); info->pasid_enabled = 0; @@ -1508,7 +1485,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; u16 did = domain_id_iommu(domain, iommu); - BUG_ON(pages == 0); + if (WARN_ON(!pages)) + return; if (ih) ih = 1 << 6; @@ -1722,9 +1700,6 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } - if (vccap_pasid(iommu->vccap)) - ioasid_unregister_allocator(&iommu->pasid_allocator); - #endif } @@ -1895,7 +1870,7 @@ context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) */ static inline void context_set_sm_dte(struct context_entry *context) { - context->lo |= (1 << 2); + context->lo |= BIT_ULL(2); } /* @@ -1904,7 +1879,7 @@ static inline void context_set_sm_dte(struct context_entry *context) */ static inline void context_set_sm_pre(struct context_entry *context) { - context->lo |= (1 << 4); + context->lo |= BIT_ULL(4); } /* Convert value to context PASID directory size field coding. */ @@ -1930,8 +1905,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, pr_debug("Set context mapping for %02x:%02x.%d\n", bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); - BUG_ON(!domain->pgd); - spin_lock(&iommu->lock); ret = -ENOMEM; context = iommu_context_addr(iommu, bus, devfn, 1); @@ -2183,7 +2156,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, phys_addr_t pteval; u64 attr; - BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1)); + if (unlikely(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1))) + return -EINVAL; if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; @@ -2341,8 +2315,6 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level != 4 && level != 5) return -EINVAL; - if (pasid != PASID_RID2PASID) - flags |= PASID_FLAG_SUPERVISOR_MODE; if (level == 5) flags |= PASID_FLAG_FL5LP; @@ -2797,85 +2769,6 @@ out_unmap: return ret; } -#ifdef CONFIG_INTEL_IOMMU_SVM -static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data) -{ - struct intel_iommu *iommu = data; - ioasid_t ioasid; - - if (!iommu) - return INVALID_IOASID; - /* - * VT-d virtual command interface always uses the full 20 bit - * PASID range. Host can partition guest PASID range based on - * policies but it is out of guest's control. - */ - if (min < PASID_MIN || max > intel_pasid_max_id) - return INVALID_IOASID; - - if (vcmd_alloc_pasid(iommu, &ioasid)) - return INVALID_IOASID; - - return ioasid; -} - -static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data) -{ - struct intel_iommu *iommu = data; - - if (!iommu) - return; - /* - * Sanity check the ioasid owner is done at upper layer, e.g. VFIO - * We can only free the PASID when all the devices are unbound. - */ - if (ioasid_find(NULL, ioasid, NULL)) { - pr_alert("Cannot free active IOASID %d\n", ioasid); - return; - } - vcmd_free_pasid(iommu, ioasid); -} - -static void register_pasid_allocator(struct intel_iommu *iommu) -{ - /* - * If we are running in the host, no need for custom allocator - * in that PASIDs are allocated from the host system-wide. - */ - if (!cap_caching_mode(iommu->cap)) - return; - - if (!sm_supported(iommu)) { - pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n"); - return; - } - - /* - * Register a custom PASID allocator if we are running in a guest, - * guest PASID must be obtained via virtual command interface. - * There can be multiple vIOMMUs in each guest but only one allocator - * is active. All vIOMMU allocators will eventually be calling the same - * host allocator. - */ - if (!vccap_pasid(iommu->vccap)) - return; - - pr_info("Register custom PASID allocator\n"); - iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc; - iommu->pasid_allocator.free = intel_vcmd_ioasid_free; - iommu->pasid_allocator.pdata = (void *)iommu; - if (ioasid_register_allocator(&iommu->pasid_allocator)) { - pr_warn("Custom PASID allocator failed, scalable mode disabled\n"); - /* - * Disable scalable mode on this IOMMU if there - * is no custom allocator. Mixing SM capable vIOMMU - * and non-SM vIOMMU are not supported. - */ - intel_iommu_sm = 0; - } -} -#endif - static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; @@ -2964,9 +2857,6 @@ static int __init init_dmars(void) */ for_each_active_iommu(iommu, drhd) { iommu_flush_write_buffer(iommu); -#ifdef CONFIG_INTEL_IOMMU_SVM - register_pasid_allocator(iommu); -#endif iommu_set_root_entry(iommu); } @@ -3760,8 +3650,8 @@ static ssize_t version_show(struct device *dev, { struct intel_iommu *iommu = dev_to_intel_iommu(dev); u32 ver = readl(iommu->reg + DMAR_VER_REG); - return sprintf(buf, "%d:%d\n", - DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); + return sysfs_emit(buf, "%d:%d\n", + DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); } static DEVICE_ATTR_RO(version); @@ -3769,7 +3659,7 @@ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->reg_phys); + return sysfs_emit(buf, "%llx\n", iommu->reg_phys); } static DEVICE_ATTR_RO(address); @@ -3777,7 +3667,7 @@ static ssize_t cap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->cap); + return sysfs_emit(buf, "%llx\n", iommu->cap); } static DEVICE_ATTR_RO(cap); @@ -3785,7 +3675,7 @@ static ssize_t ecap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->ecap); + return sysfs_emit(buf, "%llx\n", iommu->ecap); } static DEVICE_ATTR_RO(ecap); @@ -3793,7 +3683,7 @@ static ssize_t domains_supported_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap)); + return sysfs_emit(buf, "%ld\n", cap_ndoms(iommu->cap)); } static DEVICE_ATTR_RO(domains_supported); @@ -3801,8 +3691,9 @@ static ssize_t domains_used_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids, - cap_ndoms(iommu->cap))); + return sysfs_emit(buf, "%d\n", + bitmap_weight(iommu->domain_ids, + cap_ndoms(iommu->cap))); } static DEVICE_ATTR_RO(domains_used); @@ -4340,8 +4231,9 @@ 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, - GFP_ATOMIC)); + if (unlikely(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, + &level, GFP_ATOMIC))) + return 0; if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); @@ -4521,6 +4413,17 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + + /* + * For IOMMU that supports device IOTLB throttling + * (DIT), we assign PFSID to the invalidation desc + * of a VF such that IOMMU HW can gauge queue depth + * at PF level. If DIT is not set, PFSID will be + * treated as reserved, which should be set to 0. + */ + if (ecap_dit(iommu->ecap)) + info->pfsid = pci_dev_id(pci_physfn(pdev)); + info->ats_qdep = pci_ats_queue_depth(pdev); } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { @@ -4638,7 +4541,6 @@ static int intel_iommu_enable_sva(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; - int ret; if (!info || dmar_disabled) return -EINVAL; @@ -4650,45 +4552,102 @@ static int intel_iommu_enable_sva(struct device *dev) if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE)) return -ENODEV; - if (!info->pasid_enabled || !info->pri_enabled || !info->ats_enabled) + if (!info->pasid_enabled || !info->ats_enabled) return -EINVAL; - ret = iopf_queue_add_device(iommu->iopf_queue, dev); - if (ret) - return ret; + /* + * Devices having device-specific I/O fault handling should not + * support PCI/PRI. The IOMMU side has no means to check the + * capability of device-specific IOPF. Therefore, IOMMU can only + * default that if the device driver enables SVA on a non-PRI + * device, it will handle IOPF in its own way. + */ + if (!info->pri_supported) + return 0; - ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); - if (ret) - iopf_queue_remove_device(iommu->iopf_queue, dev); + /* Devices supporting PRI should have it enabled. */ + if (!info->pri_enabled) + return -EINVAL; - return ret; + return 0; } -static int intel_iommu_disable_sva(struct device *dev) +static int intel_iommu_enable_iopf(struct device *dev) { + struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL; struct device_domain_info *info = dev_iommu_priv_get(dev); - struct intel_iommu *iommu = info->iommu; + struct intel_iommu *iommu; int ret; - ret = iommu_unregister_device_fault_handler(dev); + if (!pdev || !info || !info->ats_enabled || !info->pri_supported) + return -ENODEV; + + if (info->pri_enabled) + return -EBUSY; + + iommu = info->iommu; + if (!iommu) + return -EINVAL; + + /* PASID is required in PRG Response Message. */ + if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev)) + return -EINVAL; + + ret = pci_reset_pri(pdev); + if (ret) + return ret; + + ret = iopf_queue_add_device(iommu->iopf_queue, dev); if (ret) return ret; - ret = iopf_queue_remove_device(iommu->iopf_queue, dev); + ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + if (ret) + goto iopf_remove_device; + + ret = pci_enable_pri(pdev, PRQ_DEPTH); if (ret) - iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + goto iopf_unregister_handler; + info->pri_enabled = 1; + + return 0; + +iopf_unregister_handler: + iommu_unregister_device_fault_handler(dev); +iopf_remove_device: + iopf_queue_remove_device(iommu->iopf_queue, dev); return ret; } -static int intel_iommu_enable_iopf(struct device *dev) +static int intel_iommu_disable_iopf(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu = info->iommu; - if (info && info->pri_supported) - return 0; + if (!info->pri_enabled) + return -EINVAL; + + /* + * PCIe spec states that by clearing PRI enable bit, the Page + * Request Interface will not issue new page requests, but has + * outstanding page requests that have been transmitted or are + * queued for transmission. This is supposed to be called after + * the device driver has stopped DMA, all PASIDs have been + * unbound and the outstanding PRQs have been drained. + */ + pci_disable_pri(to_pci_dev(dev)); + info->pri_enabled = 0; - return -ENODEV; + /* + * With PRI disabled and outstanding PRQs drained, unregistering + * fault handler and removing device from iopf queue should never + * fail. + */ + WARN_ON(iommu_unregister_device_fault_handler(dev)); + WARN_ON(iopf_queue_remove_device(iommu->iopf_queue, dev)); + + return 0; } static int @@ -4711,10 +4670,10 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) { switch (feat) { case IOMMU_DEV_FEAT_IOPF: - return 0; + return intel_iommu_disable_iopf(dev); case IOMMU_DEV_FEAT_SVA: - return intel_iommu_disable_sva(dev); + return 0; default: return -ENODEV; diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 694ab9b7d3e9..1c5e1d88862b 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -19,7 +19,6 @@ #include <linux/iommu.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/dmar.h> -#include <linux/ioasid.h> #include <linux/bitfield.h> #include <linux/xarray.h> #include <linux/perf_event.h> @@ -198,7 +197,6 @@ #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_slads(e) (((e) >> 45) & 0x1) -#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) (((e) >> 41) & 0x1) #define ecap_pds(e) (((e) >> 42) & 0x1) @@ -678,7 +676,6 @@ struct intel_iommu { unsigned char prq_name[16]; /* Name for PRQ interrupt */ unsigned long prq_seq_number; struct completion prq_complete; - struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; @@ -798,18 +795,18 @@ static inline bool context_present(struct context_entry *context) return (context->lo & 1); } -extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); +struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev); -extern int dmar_enable_qi(struct intel_iommu *iommu); -extern void dmar_disable_qi(struct intel_iommu *iommu); -extern int dmar_reenable_qi(struct intel_iommu *iommu); -extern void qi_global_iec(struct intel_iommu *iommu); +int dmar_enable_qi(struct intel_iommu *iommu); +void dmar_disable_qi(struct intel_iommu *iommu); +int dmar_reenable_qi(struct intel_iommu *iommu); +void qi_global_iec(struct intel_iommu *iommu); -extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, - u8 fm, u64 type); -extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, - unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, +void qi_flush_context(struct intel_iommu *iommu, u16 did, + u16 sid, u8 fm, u64 type); +void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, + unsigned int size_order, u64 type); +void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, @@ -832,7 +829,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, */ #define QI_OPT_WAIT_DRAIN BIT(0) -extern int dmar_ir_support(void); +int dmar_ir_support(void); void *alloc_pgtable_page(int node, gfp_t gfp); void free_pgtable_page(void *vaddr); @@ -840,9 +837,9 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM -extern void intel_svm_check(struct intel_iommu *iommu); -extern int intel_svm_enable_prq(struct intel_iommu *iommu); -extern int intel_svm_finish_prq(struct intel_iommu *iommu); +void intel_svm_check(struct intel_iommu *iommu); +int intel_svm_enable_prq(struct intel_iommu *iommu); +int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); struct iommu_domain *intel_svm_domain_alloc(void); @@ -889,8 +886,8 @@ extern const struct iommu_ops intel_iommu_ops; #ifdef CONFIG_INTEL_IOMMU 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 iommu_calculate_agaw(struct intel_iommu *iommu); +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) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index df9e261af0b5..a1b987335b31 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -548,7 +548,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) goto out_free_table; } - bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC); + bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_KERNEL); if (bitmap == NULL) { pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id); goto out_free_pages; diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 633e0a4a01e7..c5d479770e12 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -336,15 +336,6 @@ static inline void pasid_set_fault_enable(struct pasid_entry *pe) } /* - * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a - * scalable mode PASID entry. - */ -static inline void pasid_set_sre(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 0, 1); -} - -/* * Setup the WPE(Write Protect Enable) field (Bit 132) of a * scalable mode PASID entry. */ @@ -521,23 +512,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, return -EINVAL; } - if (flags & PASID_FLAG_SUPERVISOR_MODE) { -#ifdef CONFIG_X86 - unsigned long cr0 = read_cr0(); - - /* CR0.WP is normally set but just to be sure */ - if (unlikely(!(cr0 & X86_CR0_WP))) { - pr_err("No CPU write protect!\n"); - return -EINVAL; - } -#endif - if (!ecap_srs(iommu->ecap)) { - pr_err("No supervisor request support on %s\n", - iommu->name); - return -EINVAL; - } - } - if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) { pr_err("No 5-level paging support for first-level on %s\n", iommu->name); @@ -560,10 +534,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, /* Setup the first level page table pointer: */ pasid_set_flptr(pte, (u64)__pa(pgd)); - if (flags & PASID_FLAG_SUPERVISOR_MODE) { - pasid_set_sre(pte); - pasid_set_wpe(pte); - } if (flags & PASID_FLAG_FL5LP) pasid_set_flpm(pte, 1); @@ -658,12 +628,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - /* - * Since it is a second level only translation setup, we should - * set SRE bit as well (addresses are expected to be GPAs). - */ - if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -700,13 +664,6 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - - /* - * We should set SRE bit as well since the addresses are expected - * to be GPAs. - */ - if (ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 20c54e50f533..d6b7d21244b1 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -41,13 +41,6 @@ #define FLPT_DEFAULT_DID 1 #define NUM_RESERVED_DID 2 -/* - * The SUPERVISOR_MODE flag indicates a first level translation which - * can be used for access to kernel addresses. It is valid only for - * access to the kernel's static 1:1 mapping of physical memory — not - * to vmalloc or even module mappings. - */ -#define PASID_FLAG_SUPERVISOR_MODE BIT(0) #define PASID_FLAG_NESTED BIT(1) #define PASID_FLAG_PAGE_SNOOP BIT(2) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7367f56c3bad..e95b339e9cdc 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -16,7 +16,6 @@ #include <linux/interrupt.h> #include <linux/mm_types.h> #include <linux/xarray.h> -#include <linux/ioasid.h> #include <asm/page.h> #include <asm/fpu/api.h> @@ -273,7 +272,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid, if (WARN_ON(!mutex_is_locked(&pasid_mutex))) return -EINVAL; - if (pasid == INVALID_IOASID || pasid >= PASID_MAX) + if (pasid == IOMMU_PASID_INVALID || pasid >= PASID_MAX) return -EINVAL; svm = pasid_private_find(pasid); diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c deleted file mode 100644 index a786c034907c..000000000000 --- a/drivers/iommu/ioasid.c +++ /dev/null @@ -1,422 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * I/O Address Space ID allocator. There is one global IOASID space, split into - * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and - * free IOASIDs with ioasid_alloc() and ioasid_free(). - */ -#include <linux/ioasid.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/xarray.h> - -struct ioasid_data { - ioasid_t id; - struct ioasid_set *set; - void *private; - struct rcu_head rcu; -}; - -/* - * struct ioasid_allocator_data - Internal data structure to hold information - * about an allocator. There are two types of allocators: - * - * - Default allocator always has its own XArray to track the IOASIDs allocated. - * - Custom allocators may share allocation helpers with different private data. - * Custom allocators that share the same helper functions also share the same - * XArray. - * Rules: - * 1. Default allocator is always available, not dynamically registered. This is - * to prevent race conditions with early boot code that want to register - * custom allocators or allocate IOASIDs. - * 2. Custom allocators take precedence over the default allocator. - * 3. When all custom allocators sharing the same helper functions are - * unregistered (e.g. due to hotplug), all outstanding IOASIDs must be - * freed. Otherwise, outstanding IOASIDs will be lost and orphaned. - * 4. When switching between custom allocators sharing the same helper - * functions, outstanding IOASIDs are preserved. - * 5. When switching between custom allocator and default allocator, all IOASIDs - * must be freed to ensure unadulterated space for the new allocator. - * - * @ops: allocator helper functions and its data - * @list: registered custom allocators - * @slist: allocators share the same ops but different data - * @flags: attributes of the allocator - * @xa: xarray holds the IOASID space - * @rcu: used for kfree_rcu when unregistering allocator - */ -struct ioasid_allocator_data { - struct ioasid_allocator_ops *ops; - struct list_head list; - struct list_head slist; -#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */ - unsigned long flags; - struct xarray xa; - struct rcu_head rcu; -}; - -static DEFINE_SPINLOCK(ioasid_allocator_lock); -static LIST_HEAD(allocators_list); - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque); -static void default_free(ioasid_t ioasid, void *opaque); - -static struct ioasid_allocator_ops default_ops = { - .alloc = default_alloc, - .free = default_free, -}; - -static struct ioasid_allocator_data default_allocator = { - .ops = &default_ops, - .flags = 0, - .xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC), -}; - -static struct ioasid_allocator_data *active_allocator = &default_allocator; - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque) -{ - ioasid_t id; - - if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) { - pr_err("Failed to alloc ioasid from %d to %d\n", min, max); - return INVALID_IOASID; - } - - return id; -} - -static void default_free(ioasid_t ioasid, void *opaque) -{ - struct ioasid_data *ioasid_data; - - ioasid_data = xa_erase(&default_allocator.xa, ioasid); - kfree_rcu(ioasid_data, rcu); -} - -/* Allocate and initialize a new custom allocator with its helper functions */ -static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - - ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC); - if (!ia_data) - return NULL; - - xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC); - INIT_LIST_HEAD(&ia_data->slist); - ia_data->flags |= IOASID_ALLOCATOR_CUSTOM; - ia_data->ops = ops; - - /* For tracking custom allocators that share the same ops */ - list_add_tail(&ops->list, &ia_data->slist); - - return ia_data; -} - -static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b) -{ - return (a->free == b->free) && (a->alloc == b->alloc); -} - -/** - * ioasid_register_allocator - register a custom allocator - * @ops: the custom allocator ops to be registered - * - * Custom allocators take precedence over the default xarray based allocator. - * Private data associated with the IOASID allocated by the custom allocators - * are managed by IOASID framework similar to data stored in xa by default - * allocator. - * - * There can be multiple allocators registered but only one is active. In case - * of runtime removal of a custom allocator, the next one is activated based - * on the registration ordering. - * - * Multiple allocators can share the same alloc() function, in this case the - * IOASID space is shared. - */ -int ioasid_register_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - struct ioasid_allocator_data *pallocator; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - - ia_data = ioasid_alloc_allocator(ops); - if (!ia_data) { - ret = -ENOMEM; - goto out_unlock; - } - - /* - * No particular preference, we activate the first one and keep - * the later registered allocators in a list in case the first one gets - * removed due to hotplug. - */ - if (list_empty(&allocators_list)) { - WARN_ON(active_allocator != &default_allocator); - /* Use this new allocator if default is not active */ - if (xa_empty(&active_allocator->xa)) { - rcu_assign_pointer(active_allocator, ia_data); - list_add_tail(&ia_data->list, &allocators_list); - goto out_unlock; - } - pr_warn("Default allocator active with outstanding IOASID\n"); - ret = -EAGAIN; - goto out_free; - } - - /* Check if the allocator is already registered */ - list_for_each_entry(pallocator, &allocators_list, list) { - if (pallocator->ops == ops) { - pr_err("IOASID allocator already registered\n"); - ret = -EEXIST; - goto out_free; - } else if (use_same_ops(pallocator->ops, ops)) { - /* - * If the new allocator shares the same ops, - * then they will share the same IOASID space. - * We should put them under the same xarray. - */ - list_add_tail(&ops->list, &pallocator->slist); - goto out_free; - } - } - list_add_tail(&ia_data->list, &allocators_list); - - spin_unlock(&ioasid_allocator_lock); - return 0; -out_free: - kfree(ia_data); -out_unlock: - spin_unlock(&ioasid_allocator_lock); - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_register_allocator); - -/** - * ioasid_unregister_allocator - Remove a custom IOASID allocator ops - * @ops: the custom allocator to be removed - * - * Remove an allocator from the list, activate the next allocator in - * the order it was registered. Or revert to default allocator if all - * custom allocators are unregistered without outstanding IOASIDs. - */ -void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *pallocator; - struct ioasid_allocator_ops *sops; - - spin_lock(&ioasid_allocator_lock); - if (list_empty(&allocators_list)) { - pr_warn("No custom IOASID allocators active!\n"); - goto exit_unlock; - } - - list_for_each_entry(pallocator, &allocators_list, list) { - if (!use_same_ops(pallocator->ops, ops)) - continue; - - if (list_is_singular(&pallocator->slist)) { - /* No shared helper functions */ - list_del(&pallocator->list); - /* - * All IOASIDs should have been freed before - * the last allocator that shares the same ops - * is unregistered. - */ - WARN_ON(!xa_empty(&pallocator->xa)); - if (list_empty(&allocators_list)) { - pr_info("No custom IOASID allocators, switch to default.\n"); - rcu_assign_pointer(active_allocator, &default_allocator); - } else if (pallocator == active_allocator) { - rcu_assign_pointer(active_allocator, - list_first_entry(&allocators_list, - struct ioasid_allocator_data, list)); - pr_info("IOASID allocator changed"); - } - kfree_rcu(pallocator, rcu); - break; - } - /* - * Find the matching shared ops to delete, - * but keep outstanding IOASIDs - */ - list_for_each_entry(sops, &pallocator->slist, list) { - if (sops == ops) { - list_del(&ops->list); - break; - } - } - break; - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_unregister_allocator); - -/** - * ioasid_set_data - Set private data for an allocated ioasid - * @ioasid: the ID to set data - * @data: the private data - * - * For IOASID that is already allocated, private data can be set - * via this API. Future lookup can be done via ioasid_find. - */ -int ioasid_set_data(ioasid_t ioasid, void *data) -{ - struct ioasid_data *ioasid_data; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (ioasid_data) - rcu_assign_pointer(ioasid_data->private, data); - else - ret = -ENOENT; - spin_unlock(&ioasid_allocator_lock); - - /* - * Wait for readers to stop accessing the old private data, so the - * caller can free it. - */ - if (!ret) - synchronize_rcu(); - - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_set_data); - -/** - * ioasid_alloc - Allocate an IOASID - * @set: the IOASID set - * @min: the minimum ID (inclusive) - * @max: the maximum ID (inclusive) - * @private: data private to the caller - * - * Allocate an ID between @min and @max. The @private pointer is stored - * internally and can be retrieved with ioasid_find(). - * - * Return: the allocated ID on success, or %INVALID_IOASID on failure. - */ -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private) -{ - struct ioasid_data *data; - void *adata; - ioasid_t id; - - data = kzalloc(sizeof(*data), GFP_ATOMIC); - if (!data) - return INVALID_IOASID; - - data->set = set; - data->private = private; - - /* - * Custom allocator needs allocator data to perform platform specific - * operations. - */ - spin_lock(&ioasid_allocator_lock); - adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data; - id = active_allocator->ops->alloc(min, max, adata); - if (id == INVALID_IOASID) { - pr_err("Failed ASID allocation %lu\n", active_allocator->flags); - goto exit_free; - } - - if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) && - xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) { - /* Custom allocator needs framework to store and track allocation results */ - pr_err("Failed to alloc ioasid from %d\n", id); - active_allocator->ops->free(id, active_allocator->ops->pdata); - goto exit_free; - } - data->id = id; - - spin_unlock(&ioasid_allocator_lock); - return id; -exit_free: - spin_unlock(&ioasid_allocator_lock); - kfree(data); - return INVALID_IOASID; -} -EXPORT_SYMBOL_GPL(ioasid_alloc); - -/** - * ioasid_free - Free an ioasid - * @ioasid: the ID to remove - */ -void ioasid_free(ioasid_t ioasid) -{ - struct ioasid_data *ioasid_data; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (!ioasid_data) { - pr_err("Trying to free unknown IOASID %u\n", ioasid); - goto exit_unlock; - } - - active_allocator->ops->free(ioasid, active_allocator->ops->pdata); - /* Custom allocator needs additional steps to free the xa element */ - if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { - ioasid_data = xa_erase(&active_allocator->xa, ioasid); - kfree_rcu(ioasid_data, rcu); - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_free); - -/** - * ioasid_find - Find IOASID data - * @set: the IOASID set - * @ioasid: the IOASID to find - * @getter: function to call on the found object - * - * The optional getter function allows to take a reference to the found object - * under the rcu lock. The function can also check if the object is still valid: - * if @getter returns false, then the object is invalid and NULL is returned. - * - * If the IOASID exists, return the private pointer passed to ioasid_alloc. - * Private data can be NULL if not set. Return an error if the IOASID is not - * found, or if @set is not NULL and the IOASID does not belong to the set. - */ -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - void *priv; - struct ioasid_data *ioasid_data; - struct ioasid_allocator_data *idata; - - rcu_read_lock(); - idata = rcu_dereference(active_allocator); - ioasid_data = xa_load(&idata->xa, ioasid); - if (!ioasid_data) { - priv = ERR_PTR(-ENOENT); - goto unlock; - } - if (set && ioasid_data->set != set) { - /* data found but does not belong to the set */ - priv = ERR_PTR(-EACCES); - goto unlock; - } - /* Now IOASID and its set is verified, we can return the private data */ - priv = rcu_dereference(ioasid_data->private); - if (getter && !getter(priv)) - priv = NULL; -unlock: - rcu_read_unlock(); - - return priv; -} -EXPORT_SYMBOL_GPL(ioasid_find); - -MODULE_AUTHOR("Jean-Philippe Brucker <jean-philippe.brucker@arm.com>"); -MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>"); -MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator"); -MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index dd76a1a09cf7..9821bc44f5ac 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -10,26 +10,15 @@ #include "iommu-sva.h" static DEFINE_MUTEX(iommu_sva_lock); -static DECLARE_IOASID_SET(iommu_sva_pasid); +static DEFINE_IDA(iommu_global_pasid_ida); -/** - * iommu_sva_alloc_pasid - Allocate a PASID for the mm - * @mm: the mm - * @min: minimum PASID value (inclusive) - * @max: maximum PASID value (inclusive) - * - * Try to allocate a PASID for this mm, or take a reference to the existing one - * provided it fits within the [@min, @max] range. On success the PASID is - * available in mm->pasid and will be available for the lifetime of the mm. - * - * Returns 0 on success and < 0 on error. - */ -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) +/* Allocate a PASID for the mm within range (inclusive) */ +static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) { int ret = 0; - ioasid_t pasid; - if (min == INVALID_IOASID || max == INVALID_IOASID || + if (min == IOMMU_PASID_INVALID || + max == IOMMU_PASID_INVALID || min == 0 || max < min) return -EINVAL; @@ -39,41 +28,20 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) mutex_lock(&iommu_sva_lock); /* Is a PASID already associated with this mm? */ if (mm_valid_pasid(mm)) { - if (mm->pasid < min || mm->pasid >= max) + if (mm->pasid < min || mm->pasid > max) ret = -EOVERFLOW; goto out; } - pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); - if (pasid == INVALID_IOASID) - ret = -ENOMEM; - else - mm_pasid_set(mm, pasid); + ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL); + if (ret < min) + goto out; + mm->pasid = ret; + ret = 0; out: mutex_unlock(&iommu_sva_lock); return ret; } -EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); - -/* ioasid_find getter() requires a void * argument */ -static bool __mmget_not_zero(void *mm) -{ - return mmget_not_zero(mm); -} - -/** - * iommu_sva_find() - Find mm associated to the given PASID - * @pasid: Process Address Space ID assigned to the mm - * - * On success a reference to the mm is taken, and must be released with mmput(). - * - * Returns the mm corresponding to this PASID, or an error if not found. - */ -struct mm_struct *iommu_sva_find(ioasid_t pasid) -{ - return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero); -} -EXPORT_SYMBOL_GPL(iommu_sva_find); /** * iommu_sva_bind_device() - Bind a process address space to a device @@ -242,3 +210,11 @@ out_put_mm: return status; } + +void mm_pasid_drop(struct mm_struct *mm) +{ + if (likely(!mm_valid_pasid(mm))) + return; + + ida_free(&iommu_global_pasid_ida, mm->pasid); +} diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h index 7215a761b962..54946b5a7caf 100644 --- a/drivers/iommu/iommu-sva.h +++ b/drivers/iommu/iommu-sva.h @@ -5,12 +5,8 @@ #ifndef _IOMMU_SVA_H #define _IOMMU_SVA_H -#include <linux/ioasid.h> #include <linux/mm_types.h> -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); -struct mm_struct *iommu_sva_find(ioasid_t pasid); - /* I/O Page fault */ struct device; struct iommu_fault; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 807c98de40d4..f1dcfa3f1a1b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -88,6 +88,7 @@ static const char * const iommu_group_resv_type_string[] = { static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data); +static void iommu_release_device(struct device *dev); static int iommu_alloc_default_domain(struct iommu_group *group, struct device *dev); static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus, @@ -457,20 +458,86 @@ err_out: } -void iommu_release_device(struct device *dev) +/* + * Remove a device from a group's device list and return the group device + * if successful. + */ +static struct group_device * +__iommu_group_remove_device(struct iommu_group *group, struct device *dev) { + struct group_device *device; + + lockdep_assert_held(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + if (device->dev == dev) { + list_del(&device->list); + return device; + } + } + + return NULL; +} + +/* + * Release a device from its group and decrements the iommu group reference + * count. + */ +static void __iommu_group_release_device(struct iommu_group *group, + struct group_device *grp_dev) +{ + struct device *dev = grp_dev->dev; + + sysfs_remove_link(group->devices_kobj, grp_dev->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + trace_remove_device_from_group(group->id, dev); + + kfree(grp_dev->name); + kfree(grp_dev); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +} + +static void iommu_release_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + struct group_device *device; const struct iommu_ops *ops; - if (!dev->iommu) + if (!dev->iommu || !group) return; iommu_device_unlink(dev->iommu->iommu_dev, dev); + mutex_lock(&group->mutex); + device = __iommu_group_remove_device(group, dev); + + /* + * If the group has become empty then ownership must have been released, + * and the current domain must be set back to NULL or the default + * domain. + */ + if (list_empty(&group->devices)) + WARN_ON(group->owner_cnt || + group->domain != group->default_domain); + + /* + * release_device() must stop using any attached domain on the device. + * If there are still other devices in the group they are not effected + * by this callback. + * + * The IOMMU driver must set the device to either an identity or + * blocking translation and stop using any domain pointer, as it is + * going to be freed. + */ ops = dev_iommu_ops(dev); if (ops->release_device) ops->release_device(dev); + mutex_unlock(&group->mutex); + + if (device) + __iommu_group_release_device(group, device); - iommu_group_remove_device(dev); module_put(ops->owner); dev_iommu_free(dev); } @@ -554,7 +621,7 @@ static void iommu_group_remove_file(struct iommu_group *group, static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) { - return sprintf(buf, "%s\n", group->name); + return sysfs_emit(buf, "%s\n", group->name); } /** @@ -667,52 +734,51 @@ static ssize_t iommu_group_show_resv_regions(struct iommu_group *group, { struct iommu_resv_region *region, *next; struct list_head group_resv_regions; - char *str = buf; + int offset = 0; INIT_LIST_HEAD(&group_resv_regions); iommu_get_group_resv_regions(group, &group_resv_regions); list_for_each_entry_safe(region, next, &group_resv_regions, list) { - str += sprintf(str, "0x%016llx 0x%016llx %s\n", - (long long int)region->start, - (long long int)(region->start + - region->length - 1), - iommu_group_resv_type_string[region->type]); + offset += sysfs_emit_at(buf, offset, "0x%016llx 0x%016llx %s\n", + (long long)region->start, + (long long)(region->start + + region->length - 1), + iommu_group_resv_type_string[region->type]); kfree(region); } - return (str - buf); + return offset; } static ssize_t iommu_group_show_type(struct iommu_group *group, char *buf) { - char *type = "unknown\n"; + char *type = "unknown"; mutex_lock(&group->mutex); if (group->default_domain) { switch (group->default_domain->type) { case IOMMU_DOMAIN_BLOCKED: - type = "blocked\n"; + type = "blocked"; break; case IOMMU_DOMAIN_IDENTITY: - type = "identity\n"; + type = "identity"; break; case IOMMU_DOMAIN_UNMANAGED: - type = "unmanaged\n"; + type = "unmanaged"; break; case IOMMU_DOMAIN_DMA: - type = "DMA\n"; + type = "DMA"; break; case IOMMU_DOMAIN_DMA_FQ: - type = "DMA-FQ\n"; + type = "DMA-FQ"; break; } } mutex_unlock(&group->mutex); - strcpy(buf, type); - return strlen(type); + return sysfs_emit(buf, "%s\n", type); } static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); @@ -743,7 +809,7 @@ static void iommu_group_release(struct kobject *kobj) kfree(group); } -static struct kobj_type iommu_group_ktype = { +static const struct kobj_type iommu_group_ktype = { .sysfs_ops = &iommu_group_sysfs_ops, .release = iommu_group_release, }; @@ -820,35 +886,6 @@ struct iommu_group *iommu_group_alloc(void) } EXPORT_SYMBOL_GPL(iommu_group_alloc); -struct iommu_group *iommu_group_get_by_id(int id) -{ - struct kobject *group_kobj; - struct iommu_group *group; - const char *name; - - if (!iommu_group_kset) - return NULL; - - name = kasprintf(GFP_KERNEL, "%d", id); - if (!name) - return NULL; - - group_kobj = kset_find_obj(iommu_group_kset, name); - kfree(name); - - if (!group_kobj) - return NULL; - - group = container_of(group_kobj, struct iommu_group, kobj); - BUG_ON(group->id != id); - - kobject_get(group->devices_kobj); - kobject_put(&group->kobj); - - return group; -} -EXPORT_SYMBOL_GPL(iommu_group_get_by_id); - /** * iommu_group_get_iommudata - retrieve iommu_data registered for a group * @group: the group @@ -1072,7 +1109,7 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device); void iommu_group_remove_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; - struct group_device *tmp_device, *device = NULL; + struct group_device *device; if (!group) return; @@ -1080,27 +1117,11 @@ void iommu_group_remove_device(struct device *dev) dev_info(dev, "Removing from iommu group %d\n", group->id); mutex_lock(&group->mutex); - list_for_each_entry(tmp_device, &group->devices, list) { - if (tmp_device->dev == dev) { - device = tmp_device; - list_del(&device->list); - break; - } - } + device = __iommu_group_remove_device(group, dev); mutex_unlock(&group->mutex); - if (!device) - return; - - sysfs_remove_link(group->devices_kobj, device->name); - sysfs_remove_link(&dev->kobj, "iommu_group"); - - trace_remove_device_from_group(group->id, dev); - - kfree(device->name); - kfree(device); - dev->iommu_group = NULL; - kobject_put(group->devices_kobj); + if (device) + __iommu_group_release_device(group, device); } EXPORT_SYMBOL_GPL(iommu_group_remove_device); @@ -1968,8 +1989,13 @@ static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus, return NULL; domain->type = type; - /* Assume all sizes by default; the driver may override this later */ - domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + /* + * If not already set, assume all sizes by default; the driver + * may override this later + */ + if (!domain->pgsize_bitmap) + domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + if (!domain->ops) domain->ops = bus->iommu_ops->default_domain_ops; @@ -2821,11 +2847,10 @@ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); /* - * Changes the default domain of an iommu group that has *only* one device + * Changes the default domain of an iommu group * * @group: The group for which the default domain should be changed - * @prev_dev: The device in the group (this is used to make sure that the device - * hasn't changed after the caller has called this function) + * @dev: The first device in the group * @type: The type of the new default domain that gets associated with the group * * Returns 0 on success and error code on failure @@ -2836,124 +2861,63 @@ EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); * Please take a closer look if intended to use for other purposes. */ static int iommu_change_dev_def_domain(struct iommu_group *group, - struct device *prev_dev, int type) + struct device *dev, int type) { + struct __group_domain_type gtype = {NULL, 0}; struct iommu_domain *prev_dom; - struct group_device *grp_dev; - int ret, dev_def_dom; - struct device *dev; - - mutex_lock(&group->mutex); - - if (group->default_domain != group->domain) { - dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n"); - ret = -EBUSY; - goto out; - } - - /* - * iommu group wasn't locked while acquiring device lock in - * iommu_group_store_type(). So, make sure that the device count hasn't - * changed while acquiring device lock. - * - * Changing default domain of an iommu group with two or more devices - * isn't supported because there could be a potential deadlock. Consider - * the following scenario. T1 is trying to acquire device locks of all - * the devices in the group and before it could acquire all of them, - * there could be another thread T2 (from different sub-system and use - * case) that has already acquired some of the device locks and might be - * waiting for T1 to release other device locks. - */ - if (iommu_group_device_count(group) != 1) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Group has more than one device\n"); - ret = -EINVAL; - goto out; - } + int ret; - /* Since group has only one device */ - grp_dev = list_first_entry(&group->devices, struct group_device, list); - dev = grp_dev->dev; - - if (prev_dev != dev) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Device has been changed\n"); - ret = -EBUSY; - goto out; - } + lockdep_assert_held(&group->mutex); prev_dom = group->default_domain; - if (!prev_dom) { - ret = -EINVAL; - goto out; - } - - dev_def_dom = iommu_get_def_domain_type(dev); + __iommu_group_for_each_dev(group, >ype, + probe_get_default_domain_type); if (!type) { /* * If the user hasn't requested any specific type of domain and * if the device supports both the domains, then default to the * domain the device was booted with */ - type = dev_def_dom ? : iommu_def_domain_type; - } else if (dev_def_dom && type != dev_def_dom) { - dev_err_ratelimited(prev_dev, "Device cannot be in %s domain\n", + type = gtype.type ? : iommu_def_domain_type; + } else if (gtype.type && type != gtype.type) { + dev_err_ratelimited(dev, "Device cannot be in %s domain\n", iommu_domain_type_str(type)); - ret = -EINVAL; - goto out; + return -EINVAL; } /* * Switch to a new domain only if the requested domain type is different * from the existing default domain type */ - if (prev_dom->type == type) { - ret = 0; - goto out; - } + if (prev_dom->type == type) + return 0; - /* We can bring up a flush queue without tearing down the domain */ - if (type == IOMMU_DOMAIN_DMA_FQ && prev_dom->type == IOMMU_DOMAIN_DMA) { - ret = iommu_dma_init_fq(prev_dom); - if (!ret) - prev_dom->type = IOMMU_DOMAIN_DMA_FQ; - goto out; - } + group->default_domain = NULL; + group->domain = NULL; /* Sets group->default_domain to the newly allocated domain */ ret = iommu_group_alloc_default_domain(dev->bus, group, type); if (ret) - goto out; + goto restore_old_domain; - ret = iommu_create_device_direct_mappings(group, dev); + ret = iommu_group_create_direct_mappings(group); if (ret) goto free_new_domain; - ret = __iommu_attach_device(group->default_domain, dev); + ret = __iommu_attach_group(group->default_domain, group); if (ret) goto free_new_domain; - group->domain = group->default_domain; - - /* - * Release the mutex here because ops->probe_finalize() call-back of - * some vendor IOMMU drivers calls arm_iommu_attach_device() which - * in-turn might call back into IOMMU core code, where it tries to take - * group->mutex, resulting in a deadlock. - */ - mutex_unlock(&group->mutex); - - /* Make sure dma_ops is appropriatley set */ - iommu_group_do_probe_finalize(dev, group->default_domain); iommu_domain_free(prev_dom); + return 0; free_new_domain: iommu_domain_free(group->default_domain); +restore_old_domain: group->default_domain = prev_dom; group->domain = prev_dom; -out: - mutex_unlock(&group->mutex); - return ret; } @@ -2963,7 +2927,7 @@ out: * transition. Return failure if this isn't met. * * We need to consider the race between this and the device release path. - * device_lock(dev) is used here to guarantee that the device release path + * group->mutex is used here to guarantee that the device release path * will not be entered at the same time. */ static ssize_t iommu_group_store_type(struct iommu_group *group, @@ -2990,67 +2954,42 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, else return -EINVAL; - /* - * Lock/Unlock the group mutex here before device lock to - * 1. Make sure that the iommu group has only one device (this is a - * prerequisite for step 2) - * 2. Get struct *dev which is needed to lock device - */ mutex_lock(&group->mutex); - if (iommu_group_device_count(group) != 1) { + /* We can bring up a flush queue without tearing down the domain. */ + if (req_type == IOMMU_DOMAIN_DMA_FQ && + group->default_domain->type == IOMMU_DOMAIN_DMA) { + ret = iommu_dma_init_fq(group->default_domain); + if (!ret) + group->default_domain->type = IOMMU_DOMAIN_DMA_FQ; mutex_unlock(&group->mutex); - pr_err_ratelimited("Cannot change default domain: Group has more than one device\n"); - return -EINVAL; + + return ret ?: count; + } + + /* Otherwise, ensure that device exists and no driver is bound. */ + if (list_empty(&group->devices) || group->owner_cnt) { + mutex_unlock(&group->mutex); + return -EPERM; } - /* Since group has only one device */ grp_dev = list_first_entry(&group->devices, struct group_device, list); dev = grp_dev->dev; - get_device(dev); + + ret = iommu_change_dev_def_domain(group, dev, req_type); /* - * Don't hold the group mutex because taking group mutex first and then - * the device lock could potentially cause a deadlock as below. Assume - * two threads T1 and T2. T1 is trying to change default domain of an - * iommu group and T2 is trying to hot unplug a device or release [1] VF - * of a PCIe device which is in the same iommu group. T1 takes group - * mutex and before it could take device lock assume T2 has taken device - * lock and is yet to take group mutex. Now, both the threads will be - * waiting for the other thread to release lock. Below, lock order was - * suggested. - * device_lock(dev); - * mutex_lock(&group->mutex); - * iommu_change_dev_def_domain(); - * mutex_unlock(&group->mutex); - * device_unlock(dev); - * - * [1] Typical device release path - * device_lock() from device/driver core code - * -> bus_notifier() - * -> iommu_bus_notifier() - * -> iommu_release_device() - * -> ops->release_device() vendor driver calls back iommu core code - * -> mutex_lock() from iommu core code + * Release the mutex here because ops->probe_finalize() call-back of + * some vendor IOMMU drivers calls arm_iommu_attach_device() which + * in-turn might call back into IOMMU core code, where it tries to take + * group->mutex, resulting in a deadlock. */ mutex_unlock(&group->mutex); - /* Check if the device in the group still has a driver bound to it */ - device_lock(dev); - if (device_is_bound(dev) && !(req_type == IOMMU_DOMAIN_DMA_FQ && - group->default_domain->type == IOMMU_DOMAIN_DMA)) { - pr_err_ratelimited("Device is still bound to driver\n"); - ret = -EBUSY; - goto out; - } - - ret = iommu_change_dev_def_domain(group, dev, req_type); - ret = ret ?: count; - -out: - device_unlock(dev); - put_device(dev); + /* Make sure dma_ops is appropriatley set */ + if (!ret) + __iommu_group_dma_finalize(group); - return ret; + return ret ?: count; } static bool iommu_is_default_domain(struct iommu_group *group) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index bdf1a4e5eae0..9f64c5c9f5b9 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -30,7 +30,6 @@ #define arm_iommu_create_mapping(...) NULL #define arm_iommu_attach_device(...) -ENODEV #define arm_iommu_release_mapping(...) do {} while (0) -#define arm_iommu_detach_device(...) do {} while (0) #endif #define IPMMU_CTX_MAX 16U @@ -697,7 +696,6 @@ static const struct soc_device_attribute soc_needs_opt_in[] = { static const struct soc_device_attribute soc_denylist[] = { { .soc_id = "r8a774a1", }, - { .soc_id = "r8a7795", .revision = "ES1.*" }, { .soc_id = "r8a7795", .revision = "ES2.*" }, { .soc_id = "r8a7796", }, { /* sentinel */ } @@ -820,7 +818,18 @@ static void ipmmu_probe_finalize(struct device *dev) static void ipmmu_release_device(struct device *dev) { - arm_iommu_detach_device(dev); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct ipmmu_vmsa_device *mmu = to_ipmmu(dev); + unsigned int i; + + for (i = 0; i < fwspec->num_ids; ++i) { + unsigned int utlb = fwspec->ids[i]; + + ipmmu_imuctr_write(mmu, utlb, 0); + mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID; + } + + arm_iommu_release_mapping(mmu->mapping); } static struct iommu_group *ipmmu_find_group(struct device *dev) @@ -1014,7 +1023,7 @@ static int ipmmu_probe(struct platform_device *pdev) * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property. */ if (!mmu->features->has_cache_leaf_nodes || - !of_find_property(pdev->dev.of_node, "renesas,ipmmu-main", NULL)) + !of_property_present(pdev->dev.of_node, "renesas,ipmmu-main")) mmu->root = mmu; else mmu->root = ipmmu_find_root(); @@ -1073,7 +1082,7 @@ static int ipmmu_probe(struct platform_device *pdev) return 0; } -static int ipmmu_remove(struct platform_device *pdev) +static void ipmmu_remove(struct platform_device *pdev) { struct ipmmu_vmsa_device *mmu = platform_get_drvdata(pdev); @@ -1083,8 +1092,6 @@ static int ipmmu_remove(struct platform_device *pdev) arm_iommu_release_mapping(mmu->mapping); ipmmu_device_reset(mmu); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -1131,6 +1138,6 @@ static struct platform_driver ipmmu_driver = { .pm = DEV_PM_OPS, }, .probe = ipmmu_probe, - .remove = ipmmu_remove, + .remove_new = ipmmu_remove, }; builtin_platform_driver(ipmmu_driver); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 454f6331c889..79d89bad5132 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -811,13 +811,12 @@ static const struct of_device_id msm_iommu_dt_match[] = { {} }; -static int msm_iommu_remove(struct platform_device *pdev) +static void msm_iommu_remove(struct platform_device *pdev) { struct msm_iommu_dev *iommu = platform_get_drvdata(pdev); clk_unprepare(iommu->clk); clk_unprepare(iommu->pclk); - return 0; } static struct platform_driver msm_iommu_driver = { @@ -826,6 +825,6 @@ static struct platform_driver msm_iommu_driver = { .of_match_table = msm_iommu_dt_match, }, .probe = msm_iommu_probe, - .remove = msm_iommu_remove, + .remove_new = msm_iommu_remove, }; builtin_platform_driver(msm_iommu_driver); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index d5a4955910ff..aecc7d154f28 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -8,7 +8,6 @@ #include <linux/clk.h> #include <linux/component.h> #include <linux/device.h> -#include <linux/dma-direct.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -197,12 +196,42 @@ struct mtk_iommu_plat_data { char *pericfg_comp_str; struct list_head *hw_list; - unsigned int iova_region_nr; - const struct mtk_iommu_iova_region *iova_region; - u8 banks_num; - bool banks_enable[MTK_IOMMU_BANK_MAX]; - unsigned int banks_portmsk[MTK_IOMMU_BANK_MAX]; + /* + * The IOMMU HW may support 16GB iova. In order to balance the IOVA ranges, + * different masters will be put in different iova ranges, for example vcodec + * is in 4G-8G and cam is in 8G-12G. Meanwhile, some masters may have the + * special IOVA range requirement, like CCU can only support the address + * 0x40000000-0x44000000. + * Here list the iova ranges this SoC supports and which larbs/ports are in + * which region. + * + * 16GB iova all use one pgtable, but each a region is a iommu group. + */ + struct { + unsigned int iova_region_nr; + const struct mtk_iommu_iova_region *iova_region; + /* + * Indicate the correspondance between larbs, ports and regions. + * + * The index is the same as iova_region and larb port numbers are + * described as bit positions. + * For example, storing BIT(0) at index 2,1 means "larb 1, port0 is in region 2". + * [2] = { [1] = BIT(0) } + */ + const u32 (*iova_region_larb_msk)[MTK_LARB_NR_MAX]; + }; + + /* + * The IOMMU HW may have 5 banks. Each bank has a independent pgtable. + * Here list how many banks this SoC supports/enables and which ports are in which bank. + */ + struct { + u8 banks_num; + bool banks_enable[MTK_IOMMU_BANK_MAX]; + unsigned int banks_portmsk[MTK_IOMMU_BANK_MAX]; + }; + unsigned char larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX]; }; @@ -303,16 +332,23 @@ static LIST_HEAD(m4ulist); /* List all the M4U HWs */ #define for_each_m4u(data, head) list_for_each_entry(data, head, list) +#define MTK_IOMMU_IOVA_SZ_4G (SZ_4G - SZ_8M) /* 8M as gap */ + static const struct mtk_iommu_iova_region single_domain[] = { - {.iova_base = 0, .size = SZ_4G}, + {.iova_base = 0, .size = MTK_IOMMU_IOVA_SZ_4G}, }; -static const struct mtk_iommu_iova_region mt8192_multi_dom[] = { - { .iova_base = 0x0, .size = SZ_4G}, /* 0 ~ 4G */ +#define MT8192_MULTI_REGION_NR_MAX 6 + +#define MT8192_MULTI_REGION_NR (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) ? \ + MT8192_MULTI_REGION_NR_MAX : 1) + +static const struct mtk_iommu_iova_region mt8192_multi_dom[MT8192_MULTI_REGION_NR] = { + { .iova_base = 0x0, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 0 ~ 4G, */ #if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) - { .iova_base = SZ_4G, .size = SZ_4G}, /* 4G ~ 8G */ - { .iova_base = SZ_4G * 2, .size = SZ_4G}, /* 8G ~ 12G */ - { .iova_base = SZ_4G * 3, .size = SZ_4G}, /* 12G ~ 16G */ + { .iova_base = SZ_4G, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 4G ~ 8G */ + { .iova_base = SZ_4G * 2, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 8G ~ 12G */ + { .iova_base = SZ_4G * 3, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 12G ~ 16G */ { .iova_base = 0x240000000ULL, .size = 0x4000000}, /* CCU0 */ { .iova_base = 0x244000000ULL, .size = 0x4000000}, /* CCU1 */ @@ -508,30 +544,29 @@ static unsigned int mtk_iommu_get_bank_id(struct device *dev, static int mtk_iommu_get_iova_region_id(struct device *dev, const struct mtk_iommu_plat_data *plat_data) { - const struct mtk_iommu_iova_region *rgn = plat_data->iova_region; - const struct bus_dma_region *dma_rgn = dev->dma_range_map; - int i, candidate = -1; - dma_addr_t dma_end; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + unsigned int portidmsk = 0, larbid; + const u32 *rgn_larb_msk; + int i; - if (!dma_rgn || plat_data->iova_region_nr == 1) + if (plat_data->iova_region_nr == 1) return 0; - dma_end = dma_rgn->dma_start + dma_rgn->size - 1; - for (i = 0; i < plat_data->iova_region_nr; i++, rgn++) { - /* Best fit. */ - if (dma_rgn->dma_start == rgn->iova_base && - dma_end == rgn->iova_base + rgn->size - 1) + larbid = MTK_M4U_TO_LARB(fwspec->ids[0]); + for (i = 0; i < fwspec->num_ids; i++) + portidmsk |= BIT(MTK_M4U_TO_PORT(fwspec->ids[i])); + + for (i = 0; i < plat_data->iova_region_nr; i++) { + rgn_larb_msk = plat_data->iova_region_larb_msk[i]; + if (!rgn_larb_msk) + continue; + + if ((rgn_larb_msk[larbid] & portidmsk) == portidmsk) return i; - /* ok if it is inside this region. */ - if (dma_rgn->dma_start >= rgn->iova_base && - dma_end < rgn->iova_base + rgn->size) - candidate = i; } - if (candidate >= 0) - return candidate; - dev_err(dev, "Can NOT find the iommu domain id(%pad 0x%llx).\n", - &dma_rgn->dma_start, dma_rgn->size); + dev_err(dev, "Can NOT find the region for larb(%d-%x).\n", + larbid, portidmsk); return -EINVAL; } @@ -703,6 +738,14 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, } mutex_unlock(&data->mutex); + if (region_id > 0) { + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(34)); + if (ret) { + dev_err(m4udev, "Failed to set dma_mask for %s(%d).\n", dev_name(dev), ret); + return ret; + } + } + return mtk_iommu_config(data, dev, true, region_id); err_unlock: @@ -1258,6 +1301,14 @@ static int mtk_iommu_probe(struct platform_device *pdev) return PTR_ERR(data->bclk); } + if (MTK_IOMMU_HAS_FLAG(data->plat_data, PGTABLE_PA_35_EN)) { + ret = dma_set_mask(dev, DMA_BIT_MASK(35)); + if (ret) { + dev_err(dev, "Failed to set dma_mask 35.\n"); + return ret; + } + } + pm_runtime_enable(dev); if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) { @@ -1316,7 +1367,7 @@ out_runtime_disable: return ret; } -static int mtk_iommu_remove(struct platform_device *pdev) +static void mtk_iommu_remove(struct platform_device *pdev) { struct mtk_iommu_data *data = platform_get_drvdata(pdev); struct mtk_iommu_bank_data *bank; @@ -1338,7 +1389,6 @@ static int mtk_iommu_remove(struct platform_device *pdev) continue; devm_free_irq(&pdev->dev, bank->irq, bank); } - return 0; } static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev) @@ -1492,6 +1542,18 @@ static const struct mtk_iommu_plat_data mt8183_data = { .larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}}, }; +static const unsigned int mt8186_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0, ~0}, /* Region0: all ports for larb0/1/2 */ + [1] = {0, 0, 0, 0, ~0, 0, 0, ~0}, /* Region1: larb4/7 */ + [2] = {0, 0, 0, 0, 0, 0, 0, 0, /* Region2: larb8/9/11/13/16/17/19/20 */ + ~0, ~0, 0, ~0, 0, ~(u32)(BIT(9) | BIT(10)), 0, 0, + /* larb13: the other ports except port9/10 */ + ~0, ~0, 0, ~0, ~0}, + [3] = {0}, + [4] = {[13] = BIT(9) | BIT(10)}, /* larb13 port9/10 */ + [5] = {[14] = ~0}, /* larb14 */ +}; + static const struct mtk_iommu_plat_data mt8186_data_mm = { .m4u_plat = M4U_MT8186, .flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | @@ -1504,6 +1566,18 @@ static const struct mtk_iommu_plat_data mt8186_data_mm = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8186_larb_region_msk, +}; + +static const unsigned int mt8192_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0}, /* Region0: larb0/1 */ + [1] = {0, 0, 0, 0, ~0, ~0, 0, ~0}, /* Region1: larb4/5/7 */ + [2] = {0, 0, ~0, 0, 0, 0, 0, 0, /* Region2: larb2/9/11/13/14/16/17/18/19/20 */ + 0, ~0, 0, ~0, 0, ~(u32)(BIT(9) | BIT(10)), ~(u32)(BIT(4) | BIT(5)), 0, + ~0, ~0, ~0, ~0, ~0}, + [3] = {0}, + [4] = {[13] = BIT(9) | BIT(10)}, /* larb13 port9/10 */ + [5] = {[14] = BIT(4) | BIT(5)}, /* larb14 port4/5 */ }; static const struct mtk_iommu_plat_data mt8192_data = { @@ -1515,6 +1589,7 @@ static const struct mtk_iommu_plat_data mt8192_data = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8192_larb_region_msk, .larbid_remap = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20}, {0, 14, 16}, {0, 13, 18, 17}}, }; @@ -1534,6 +1609,21 @@ static const struct mtk_iommu_plat_data mt8195_data_infra = { .iova_region_nr = ARRAY_SIZE(single_domain), }; +static const unsigned int mt8195_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0, ~0, ~0}, /* Region0: all ports for larb0/1/2/3 */ + [1] = {0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, ~0, ~0, ~0, ~0, ~0, /* Region1: larb19/20/21/22/23/24 */ + ~0}, + [2] = {0, 0, 0, 0, ~0, ~0, ~0, ~0, /* Region2: the other larbs. */ + ~0, ~0, ~0, ~0, ~0, ~0, ~0, ~0, + ~0, ~0, 0, 0, 0, 0, 0, 0, + 0, ~0, ~0, ~0, ~0}, + [3] = {0}, + [4] = {[18] = BIT(0) | BIT(1)}, /* Only larb18 port0/1 */ + [5] = {[18] = BIT(2) | BIT(3)}, /* Only larb18 port2/3 */ +}; + static const struct mtk_iommu_plat_data mt8195_data_vdo = { .m4u_plat = M4U_MT8195, .flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | @@ -1544,6 +1634,7 @@ static const struct mtk_iommu_plat_data mt8195_data_vdo = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8195_larb_region_msk, .larbid_remap = {{2, 0}, {21}, {24}, {7}, {19}, {9, 10, 11}, {13, 17, 15/* 17b */, 25}, {5}}, }; @@ -1558,6 +1649,7 @@ static const struct mtk_iommu_plat_data mt8195_data_vpp = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8195_larb_region_msk, .larbid_remap = {{1}, {3}, {22, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 23}, {8}, {20}, {12}, @@ -1595,7 +1687,7 @@ static const struct of_device_id mtk_iommu_of_ids[] = { static struct platform_driver mtk_iommu_driver = { .probe = mtk_iommu_probe, - .remove = mtk_iommu_remove, + .remove_new = mtk_iommu_remove, .driver = { .name = "mtk-iommu", .of_match_table = mtk_iommu_of_ids, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 43e4c8f89e23..8a0a5e5d049f 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -703,7 +703,7 @@ out_clk_unprepare: return ret; } -static int mtk_iommu_v1_remove(struct platform_device *pdev) +static void mtk_iommu_v1_remove(struct platform_device *pdev) { struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev); @@ -713,7 +713,6 @@ static int mtk_iommu_v1_remove(struct platform_device *pdev) clk_disable_unprepare(data->bclk); devm_free_irq(&pdev->dev, data->irq, data); component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops); - return 0; } static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev) @@ -752,7 +751,7 @@ static const struct dev_pm_ops mtk_iommu_v1_pm_ops = { static struct platform_driver mtk_iommu_v1_driver = { .probe = mtk_iommu_v1_probe, - .remove = mtk_iommu_v1_remove, + .remove_new = mtk_iommu_v1_remove, .driver = { .name = "mtk-iommu-v1", .of_match_table = mtk_iommu_v1_of_ids, diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 3ab078112a7c..537e402f9bba 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1191,7 +1191,7 @@ static int omap_iommu_probe(struct platform_device *pdev) return err; if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8) return -EINVAL; - if (of_find_property(of, "ti,iommu-bus-err-back", NULL)) + if (of_property_read_bool(of, "ti,iommu-bus-err-back")) obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN; obj->dev = &pdev->dev; @@ -1257,7 +1257,7 @@ out_group: return err; } -static int omap_iommu_remove(struct platform_device *pdev) +static void omap_iommu_remove(struct platform_device *pdev) { struct omap_iommu *obj = platform_get_drvdata(pdev); @@ -1274,7 +1274,6 @@ static int omap_iommu_remove(struct platform_device *pdev) pm_runtime_disable(obj->dev); dev_info(&pdev->dev, "%s removed\n", obj->name); - return 0; } static const struct dev_pm_ops omap_iommu_pm_ops = { @@ -1295,7 +1294,7 @@ static const struct of_device_id omap_iommu_of_match[] = { static struct platform_driver omap_iommu_driver = { .probe = omap_iommu_probe, - .remove = omap_iommu_remove, + .remove_new = omap_iommu_remove, .driver = { .name = "omap-iommu", .pm = &omap_iommu_pm_ops, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index f30db22ea5d7..ea5a3088bb7e 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -124,6 +124,7 @@ struct rk_iommudata { static struct device *dma_dev; static const struct rk_iommu_ops *rk_ops; +static struct iommu_domain rk_identity_domain; static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma, unsigned int count) @@ -646,7 +647,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) * Ignore the return code, though, since we always zap cache * and clear the page fault anyway. */ - if (iommu->domain) + if (iommu->domain != &rk_identity_domain) report_iommu_fault(iommu->domain, iommu->dev, iova, flags); else @@ -980,26 +981,27 @@ out_disable_clocks: return ret; } -static void rk_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) +static int rk_iommu_identity_attach(struct iommu_domain *identity_domain, + struct device *dev) { struct rk_iommu *iommu; - struct rk_iommu_domain *rk_domain = to_rk_domain(domain); + struct rk_iommu_domain *rk_domain; unsigned long flags; int ret; /* Allow 'virtual devices' (eg drm) to detach from domain */ iommu = rk_iommu_from_dev(dev); if (!iommu) - return; + return -ENODEV; + + rk_domain = to_rk_domain(iommu->domain); dev_dbg(dev, "Detaching from iommu domain\n"); - /* iommu already detached */ - if (iommu->domain != domain) - return; + if (iommu->domain == identity_domain) + return 0; - iommu->domain = NULL; + iommu->domain = identity_domain; spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_del_init(&iommu->node); @@ -1011,8 +1013,31 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, rk_iommu_disable(iommu); pm_runtime_put(iommu->dev); } + + return 0; } +static void rk_iommu_identity_free(struct iommu_domain *domain) +{ +} + +static struct iommu_domain_ops rk_identity_ops = { + .attach_dev = rk_iommu_identity_attach, + .free = rk_iommu_identity_free, +}; + +static struct iommu_domain rk_identity_domain = { + .type = IOMMU_DOMAIN_IDENTITY, + .ops = &rk_identity_ops, +}; + +#ifdef CONFIG_ARM +static void rk_iommu_set_platform_dma(struct device *dev) +{ + WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev)); +} +#endif + static int rk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { @@ -1035,8 +1060,9 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, if (iommu->domain == domain) return 0; - if (iommu->domain) - rk_iommu_detach_device(iommu->domain, dev); + ret = rk_iommu_identity_attach(&rk_identity_domain, dev); + if (ret) + return ret; iommu->domain = domain; @@ -1050,7 +1076,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, ret = rk_iommu_enable(iommu); if (ret) - rk_iommu_detach_device(iommu->domain, dev); + WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev)); pm_runtime_put(iommu->dev); @@ -1061,6 +1087,9 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) { struct rk_iommu_domain *rk_domain; + if (type == IOMMU_DOMAIN_IDENTITY) + return &rk_identity_domain; + if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA) return NULL; @@ -1176,6 +1205,7 @@ static int rk_iommu_of_xlate(struct device *dev, iommu_dev = of_find_device_by_node(args->np); data->iommu = platform_get_drvdata(iommu_dev); + data->iommu->domain = &rk_identity_domain; dev_iommu_priv_set(dev, data); platform_device_put(iommu_dev); @@ -1188,6 +1218,9 @@ static const struct iommu_ops rk_iommu_ops = { .probe_device = rk_iommu_probe_device, .release_device = rk_iommu_release_device, .device_group = rk_iommu_device_group, +#ifdef CONFIG_ARM + .set_platform_dma_ops = rk_iommu_set_platform_dma, +#endif .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, .of_xlate = rk_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { @@ -1343,7 +1376,7 @@ static int __maybe_unused rk_iommu_suspend(struct device *dev) { struct rk_iommu *iommu = dev_get_drvdata(dev); - if (!iommu->domain) + if (iommu->domain == &rk_identity_domain) return 0; rk_iommu_disable(iommu); @@ -1354,7 +1387,7 @@ static int __maybe_unused rk_iommu_resume(struct device *dev) { struct rk_iommu *iommu = dev_get_drvdata(dev); - if (!iommu->domain) + if (iommu->domain == &rk_identity_domain) return 0; return rk_iommu_enable(iommu); diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index ae94d74b73f4..39e34fdeccda 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -62,6 +62,7 @@ enum sprd_iommu_version { * @eb: gate clock which controls IOMMU access */ struct sprd_iommu_device { + struct sprd_iommu_domain *dom; enum sprd_iommu_version ver; u32 *prot_page_va; dma_addr_t prot_page_pa; @@ -151,13 +152,6 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) return &dom->domain; } -static void sprd_iommu_domain_free(struct iommu_domain *domain) -{ - struct sprd_iommu_domain *dom = to_sprd_domain(domain); - - kfree(dom); -} - static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) { struct sprd_iommu_device *sdev = dom->sdev; @@ -230,6 +224,28 @@ static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); } +static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom) +{ + size_t pgt_size; + + /* Nothing need to do if the domain hasn't been attached */ + if (!dom->sdev) + return; + + pgt_size = sprd_iommu_pgt_size(&dom->domain); + dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + dom->sdev = NULL; + sprd_iommu_hw_en(dom->sdev, false); +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + sprd_iommu_cleanup(dom); + kfree(dom); +} + static int sprd_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { @@ -237,15 +253,27 @@ static int sprd_iommu_attach_device(struct iommu_domain *domain, struct sprd_iommu_domain *dom = to_sprd_domain(domain); size_t pgt_size = sprd_iommu_pgt_size(domain); - if (dom->sdev) - return -EINVAL; + /* The device is attached to this domain */ + if (sdev->dom == dom) + return 0; - dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); - if (!dom->pgt_va) - return -ENOMEM; + /* The first time that domain is attaching to a device */ + if (!dom->pgt_va) { + dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); + if (!dom->pgt_va) + return -ENOMEM; + + dom->sdev = sdev; + } - dom->sdev = sdev; + sdev->dom = dom; + /* + * One sprd IOMMU serves one client device only, disabled it before + * configure mapping table to avoid access conflict in case other + * mapping table is stored in. + */ + sprd_iommu_hw_en(sdev, false); sprd_iommu_first_ppn(dom); sprd_iommu_first_vpn(dom); sprd_iommu_vpn_range(dom); @@ -507,7 +535,7 @@ free_page: return ret; } -static int sprd_iommu_remove(struct platform_device *pdev) +static void sprd_iommu_remove(struct platform_device *pdev) { struct sprd_iommu_device *sdev = platform_get_drvdata(pdev); @@ -519,8 +547,6 @@ static int sprd_iommu_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); iommu_device_sysfs_remove(&sdev->iommu); iommu_device_unregister(&sdev->iommu); - - return 0; } static struct platform_driver sprd_iommu_driver = { @@ -530,7 +556,7 @@ static struct platform_driver sprd_iommu_driver = { .suppress_bind_attrs = true, }, .probe = sprd_iommu_probe, - .remove = sprd_iommu_remove, + .remove_new = sprd_iommu_remove, }; module_platform_driver(sprd_iommu_driver); |