diff options
Diffstat (limited to 'drivers/iommu/arm-smmu.c')
| -rw-r--r-- | drivers/iommu/arm-smmu.c | 999 |
1 files changed, 465 insertions, 534 deletions
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 64977c131ee6..16c4b87af42b 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -19,19 +19,15 @@ #include <linux/acpi.h> #include <linux/acpi_iort.h> -#include <linux/atomic.h> +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/dma-iommu.h> #include <linux/dma-mapping.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/io.h> -#include <linux/io-64-nonatomic-hi-lo.h> -#include <linux/io-pgtable.h> -#include <linux/iommu.h> #include <linux/iopoll.h> -#include <linux/init.h> -#include <linux/moduleparam.h> +#include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_device.h> @@ -39,13 +35,13 @@ #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/ratelimit.h> #include <linux/slab.h> -#include <linux/spinlock.h> #include <linux/amba/bus.h> #include <linux/fsl/mc.h> -#include "arm-smmu-regs.h" +#include "arm-smmu.h" /* * Apparently, some Qualcomm arm64 platforms which appear to expose their SMMU @@ -56,54 +52,13 @@ */ #define QCOM_DUMMY_VAL -1 -#define ARM_MMU500_ACTLR_CPRE (1 << 1) - -#define ARM_MMU500_ACR_CACHE_LOCK (1 << 26) -#define ARM_MMU500_ACR_S2CRB_TLBEN (1 << 10) -#define ARM_MMU500_ACR_SMTNMB_TLBEN (1 << 8) - #define TLB_LOOP_TIMEOUT 1000000 /* 1s! */ #define TLB_SPIN_COUNT 10 -/* Maximum number of context banks per SMMU */ -#define ARM_SMMU_MAX_CBS 128 - -/* SMMU global address space */ -#define ARM_SMMU_GR0(smmu) ((smmu)->base) -#define ARM_SMMU_GR1(smmu) ((smmu)->base + (1 << (smmu)->pgshift)) - -/* - * SMMU global address space with conditional offset to access secure - * aliases of non-secure registers (e.g. nsCR0: 0x400, nsGFSR: 0x448, - * nsGFSYNR0: 0x450) - */ -#define ARM_SMMU_GR0_NS(smmu) \ - ((smmu)->base + \ - ((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS) \ - ? 0x400 : 0)) - -/* - * Some 64-bit registers only make sense to write atomically, but in such - * cases all the data relevant to AArch32 formats lies within the lower word, - * therefore this actually makes more sense than it might first appear. - */ -#ifdef CONFIG_64BIT -#define smmu_write_atomic_lq writeq_relaxed -#else -#define smmu_write_atomic_lq writel_relaxed -#endif - -/* Translation context bank */ -#define ARM_SMMU_CB(smmu, n) ((smmu)->cb_base + ((n) << (smmu)->pgshift)) - #define MSI_IOVA_BASE 0x8000000 #define MSI_IOVA_LENGTH 0x100000 static int force_stage; -/* - * not really modular, but the easiest way to keep compat with existing - * bootargs behaviour is to continue using module_param() here. - */ module_param(force_stage, int, S_IRUGO); MODULE_PARM_DESC(force_stage, "Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation."); @@ -113,19 +68,6 @@ module_param(disable_bypass, bool, S_IRUGO); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); -enum arm_smmu_arch_version { - ARM_SMMU_V1, - ARM_SMMU_V1_64K, - ARM_SMMU_V2, -}; - -enum arm_smmu_implementation { - GENERIC_SMMU, - ARM_MMU500, - CAVIUM_SMMUV2, - QCOM_SMMUV2, -}; - struct arm_smmu_s2cr { struct iommu_group *group; int count; @@ -163,117 +105,8 @@ struct arm_smmu_master_cfg { #define for_each_cfg_sme(fw, i, idx) \ for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i) -struct arm_smmu_device { - struct device *dev; - - void __iomem *base; - void __iomem *cb_base; - unsigned long pgshift; - -#define ARM_SMMU_FEAT_COHERENT_WALK (1 << 0) -#define ARM_SMMU_FEAT_STREAM_MATCH (1 << 1) -#define ARM_SMMU_FEAT_TRANS_S1 (1 << 2) -#define ARM_SMMU_FEAT_TRANS_S2 (1 << 3) -#define ARM_SMMU_FEAT_TRANS_NESTED (1 << 4) -#define ARM_SMMU_FEAT_TRANS_OPS (1 << 5) -#define ARM_SMMU_FEAT_VMID16 (1 << 6) -#define ARM_SMMU_FEAT_FMT_AARCH64_4K (1 << 7) -#define ARM_SMMU_FEAT_FMT_AARCH64_16K (1 << 8) -#define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9) -#define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10) -#define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11) -#define ARM_SMMU_FEAT_EXIDS (1 << 12) - u32 features; - -#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0) - u32 options; - enum arm_smmu_arch_version version; - enum arm_smmu_implementation model; - - u32 num_context_banks; - u32 num_s2_context_banks; - DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS); - struct arm_smmu_cb *cbs; - atomic_t irptndx; - - u32 num_mapping_groups; - u16 streamid_mask; - u16 smr_mask_mask; - struct arm_smmu_smr *smrs; - struct arm_smmu_s2cr *s2crs; - struct mutex stream_map_mutex; - - unsigned long va_size; - unsigned long ipa_size; - unsigned long pa_size; - unsigned long pgsize_bitmap; - - u32 num_global_irqs; - u32 num_context_irqs; - unsigned int *irqs; - struct clk_bulk_data *clks; - int num_clks; - - u32 cavium_id_base; /* Specific to Cavium */ - - spinlock_t global_sync_lock; - - /* IOMMU core code handle */ - struct iommu_device iommu; -}; - -enum arm_smmu_context_fmt { - ARM_SMMU_CTX_FMT_NONE, - ARM_SMMU_CTX_FMT_AARCH64, - ARM_SMMU_CTX_FMT_AARCH32_L, - ARM_SMMU_CTX_FMT_AARCH32_S, -}; - -struct arm_smmu_cfg { - u8 cbndx; - u8 irptndx; - union { - u16 asid; - u16 vmid; - }; - u32 cbar; - enum arm_smmu_context_fmt fmt; -}; -#define INVALID_IRPTNDX 0xff - -enum arm_smmu_domain_stage { - ARM_SMMU_DOMAIN_S1 = 0, - ARM_SMMU_DOMAIN_S2, - ARM_SMMU_DOMAIN_NESTED, - ARM_SMMU_DOMAIN_BYPASS, -}; - -struct arm_smmu_domain { - struct arm_smmu_device *smmu; - struct io_pgtable_ops *pgtbl_ops; - const struct iommu_gather_ops *tlb_ops; - struct arm_smmu_cfg cfg; - enum arm_smmu_domain_stage stage; - bool non_strict; - struct mutex init_mutex; /* Protects smmu pointer */ - spinlock_t cb_lock; /* Serialises ATS1* ops and TLB syncs */ - struct iommu_domain domain; -}; - -struct arm_smmu_option_prop { - u32 opt; - const char *prop; -}; - -static atomic_t cavium_smmu_context_count = ATOMIC_INIT(0); - static bool using_legacy_binding, using_generic_binding; -static struct arm_smmu_option_prop arm_smmu_options[] = { - { ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" }, - { 0, NULL}, -}; - static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu) { if (pm_runtime_enabled(smmu->dev)) @@ -285,7 +118,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu) static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu) { if (pm_runtime_enabled(smmu->dev)) - pm_runtime_put(smmu->dev); + pm_runtime_put_autosuspend(smmu->dev); } static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) @@ -293,19 +126,11 @@ static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) return container_of(dom, struct arm_smmu_domain, domain); } -static void parse_driver_options(struct arm_smmu_device *smmu) -{ - int i = 0; +static struct platform_driver arm_smmu_driver; +static struct iommu_ops arm_smmu_ops; - do { - if (of_property_read_bool(smmu->dev->of_node, - arm_smmu_options[i].prop)) { - smmu->options |= arm_smmu_options[i].opt; - dev_notice(smmu->dev, "option %s\n", - arm_smmu_options[i].prop); - } - } while (arm_smmu_options[++i].opt); -} +#ifdef CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS +static int arm_smmu_bus_init(struct iommu_ops *ops); static struct device_node *dev_get_dev_node(struct device *dev) { @@ -333,7 +158,7 @@ static int __find_legacy_master_phandle(struct device *dev, void *data) int err; of_for_each_phandle(it, err, dev->of_node, "mmu-masters", - "#stream-id-cells", 0) + "#stream-id-cells", -1) if (it->node == np) { *(void **)data = dev; return 1; @@ -342,9 +167,6 @@ static int __find_legacy_master_phandle(struct device *dev, void *data) return err == -ENOENT ? 0 : err; } -static struct platform_driver arm_smmu_driver; -static struct iommu_ops arm_smmu_ops; - static int arm_smmu_register_legacy_master(struct device *dev, struct arm_smmu_device **smmu) { @@ -396,6 +218,27 @@ static int arm_smmu_register_legacy_master(struct device *dev, return err; } +/* + * With the legacy DT binding in play, we have no guarantees about + * probe order, but then we're also not doing default domains, so we can + * delay setting bus ops until we're sure every possible SMMU is ready, + * and that way ensure that no add_device() calls get missed. + */ +static int arm_smmu_legacy_bus_init(void) +{ + if (using_legacy_binding) + return arm_smmu_bus_init(&arm_smmu_ops); + return 0; +} +device_initcall_sync(arm_smmu_legacy_bus_init); +#else +static int arm_smmu_register_legacy_master(struct device *dev, + struct arm_smmu_device **smmu) +{ + return -ENODEV; +} +#endif /* CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS */ + static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end) { int idx; @@ -415,15 +258,20 @@ static void __arm_smmu_free_bitmap(unsigned long *map, int idx) } /* Wait for any pending TLB invalidations to complete */ -static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, - void __iomem *sync, void __iomem *status) +static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page, + int sync, int status) { unsigned int spin_cnt, delay; + u32 reg; + + if (smmu->impl && unlikely(smmu->impl->tlb_sync)) + return smmu->impl->tlb_sync(smmu, page, sync, status); - writel_relaxed(QCOM_DUMMY_VAL, sync); + arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL); for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) { for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) { - if (!(readl_relaxed(status) & sTLBGSTATUS_GSACTIVE)) + reg = arm_smmu_readl(smmu, page, status); + if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE)) return; cpu_relax(); } @@ -435,134 +283,189 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu) { - void __iomem *base = ARM_SMMU_GR0(smmu); unsigned long flags; spin_lock_irqsave(&smmu->global_sync_lock, flags); - __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_GR0_sTLBGSYNC, - base + ARM_SMMU_GR0_sTLBGSTATUS); + __arm_smmu_tlb_sync(smmu, ARM_SMMU_GR0, ARM_SMMU_GR0_sTLBGSYNC, + ARM_SMMU_GR0_sTLBGSTATUS); spin_unlock_irqrestore(&smmu->global_sync_lock, flags); } -static void arm_smmu_tlb_sync_context(void *cookie) +static void arm_smmu_tlb_sync_context(struct arm_smmu_domain *smmu_domain) { - struct arm_smmu_domain *smmu_domain = cookie; struct arm_smmu_device *smmu = smmu_domain->smmu; - void __iomem *base = ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx); unsigned long flags; spin_lock_irqsave(&smmu_domain->cb_lock, flags); - __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_CB_TLBSYNC, - base + ARM_SMMU_CB_TLBSTATUS); + __arm_smmu_tlb_sync(smmu, ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx), + ARM_SMMU_CB_TLBSYNC, ARM_SMMU_CB_TLBSTATUS); spin_unlock_irqrestore(&smmu_domain->cb_lock, flags); } -static void arm_smmu_tlb_sync_vmid(void *cookie) -{ - struct arm_smmu_domain *smmu_domain = cookie; - - arm_smmu_tlb_sync_global(smmu_domain->smmu); -} - static void arm_smmu_tlb_inv_context_s1(void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; - struct arm_smmu_cfg *cfg = &smmu_domain->cfg; - void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx); - /* - * NOTE: this is not a relaxed write; it needs to guarantee that PTEs - * cleared by the current CPU are visible to the SMMU before the TLBI. + * The TLBI write may be relaxed, so ensure that PTEs cleared by the + * current CPU are visible beforehand. */ - writel(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID); - arm_smmu_tlb_sync_context(cookie); + wmb(); + arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx, + ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid); + arm_smmu_tlb_sync_context(smmu_domain); } static void arm_smmu_tlb_inv_context_s2(void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; struct arm_smmu_device *smmu = smmu_domain->smmu; - void __iomem *base = ARM_SMMU_GR0(smmu); - /* NOTE: see above */ - writel(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); + /* See above */ + wmb(); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid); arm_smmu_tlb_sync_global(smmu); } -static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size, + size_t granule, void *cookie, int reg) { struct arm_smmu_domain *smmu_domain = cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; - bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS; - void __iomem *reg = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx); + int idx = cfg->cbndx; - if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) + if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) wmb(); - if (stage1) { - reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA; - - if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) { - iova &= ~12UL; - iova |= cfg->asid; - do { - writel_relaxed(iova, reg); - iova += granule; - } while (size -= granule); - } else { - iova >>= 12; - iova |= (u64)cfg->asid << 48; - do { - writeq_relaxed(iova, reg); - iova += granule >> 12; - } while (size -= granule); - } + if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) { + iova = (iova >> 12) << 12; + iova |= cfg->asid; + do { + arm_smmu_cb_write(smmu, idx, reg, iova); + iova += granule; + } while (size -= granule); } else { - reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L : - ARM_SMMU_CB_S2_TLBIIPAS2; iova >>= 12; + iova |= (u64)cfg->asid << 48; do { - smmu_write_atomic_lq(iova, reg); + arm_smmu_cb_writeq(smmu, idx, reg, iova); iova += granule >> 12; } while (size -= granule); } } +static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size, + size_t granule, void *cookie, int reg) +{ + struct arm_smmu_domain *smmu_domain = cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; + int idx = smmu_domain->cfg.cbndx; + + if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) + wmb(); + + iova >>= 12; + do { + if (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64) + arm_smmu_cb_writeq(smmu, idx, reg, iova); + else + arm_smmu_cb_write(smmu, idx, reg, iova); + iova += granule >> 12; + } while (size -= granule); +} + +static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ + arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, + ARM_SMMU_CB_S1_TLBIVA); + arm_smmu_tlb_sync_context(cookie); +} + +static void arm_smmu_tlb_inv_leaf_s1(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ + arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, + ARM_SMMU_CB_S1_TLBIVAL); + arm_smmu_tlb_sync_context(cookie); +} + +static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) +{ + arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie, + ARM_SMMU_CB_S1_TLBIVAL); +} + +static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ + arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, + ARM_SMMU_CB_S2_TLBIIPAS2); + arm_smmu_tlb_sync_context(cookie); +} + +static void arm_smmu_tlb_inv_leaf_s2(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ + arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, + ARM_SMMU_CB_S2_TLBIIPAS2L); + arm_smmu_tlb_sync_context(cookie); +} + +static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) +{ + arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie, + ARM_SMMU_CB_S2_TLBIIPAS2L); +} + +static void arm_smmu_tlb_inv_any_s2_v1(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ + arm_smmu_tlb_inv_context_s2(cookie); +} /* * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears * almost negligible, but the benefit of getting the first one in as far ahead * of the sync as possible is significant, hence we don't just make this a - * no-op and set .tlb_sync to arm_smmu_inv_context_s2() as you might think. + * no-op and call arm_smmu_tlb_inv_context_s2() from .iotlb_sync as you might + * think. */ -static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; - void __iomem *base = ARM_SMMU_GR0(smmu_domain->smmu); + struct arm_smmu_device *smmu = smmu_domain->smmu; - if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) + if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) wmb(); - writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid); } -static const struct iommu_gather_ops arm_smmu_s1_tlb_ops = { +static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context_s1, - .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, - .tlb_sync = arm_smmu_tlb_sync_context, + .tlb_flush_walk = arm_smmu_tlb_inv_walk_s1, + .tlb_flush_leaf = arm_smmu_tlb_inv_leaf_s1, + .tlb_add_page = arm_smmu_tlb_add_page_s1, }; -static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v2 = { +static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = { .tlb_flush_all = arm_smmu_tlb_inv_context_s2, - .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, - .tlb_sync = arm_smmu_tlb_sync_context, + .tlb_flush_walk = arm_smmu_tlb_inv_walk_s2, + .tlb_flush_leaf = arm_smmu_tlb_inv_leaf_s2, + .tlb_add_page = arm_smmu_tlb_add_page_s2, }; -static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = { +static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = { .tlb_flush_all = arm_smmu_tlb_inv_context_s2, - .tlb_add_flush = arm_smmu_tlb_inv_vmid_nosync, - .tlb_sync = arm_smmu_tlb_sync_vmid, + .tlb_flush_walk = arm_smmu_tlb_inv_any_s2_v1, + .tlb_flush_leaf = arm_smmu_tlb_inv_any_s2_v1, + .tlb_add_page = arm_smmu_tlb_add_page_s2_v1, }; static irqreturn_t arm_smmu_context_fault(int irq, void *dev) @@ -571,26 +474,22 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct arm_smmu_device *smmu = smmu_domain->smmu; - void __iomem *gr1_base = ARM_SMMU_GR1(smmu); - void __iomem *cb_base; - - cb_base = ARM_SMMU_CB(smmu, cfg->cbndx); - fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR); + int idx = smmu_domain->cfg.cbndx; - if (!(fsr & FSR_FAULT)) + fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR); + if (!(fsr & ARM_SMMU_FSR_FAULT)) return IRQ_NONE; - fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); - iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); - cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx)); + fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0); + iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR); + cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx)); dev_err_ratelimited(smmu->dev, "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n", - fsr, iova, fsynr, cbfrsynra, cfg->cbndx); + fsr, iova, fsynr, cbfrsynra, idx); - writel(fsr, cb_base + ARM_SMMU_CB_FSR); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_FSR, fsr); return IRQ_HANDLED; } @@ -598,23 +497,32 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev) { u32 gfsr, gfsynr0, gfsynr1, gfsynr2; struct arm_smmu_device *smmu = dev; - void __iomem *gr0_base = ARM_SMMU_GR0_NS(smmu); + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); - gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR); - gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0); - gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1); - gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2); + gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR); + gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0); + gfsynr1 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR1); + gfsynr2 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR2); if (!gfsr) return IRQ_NONE; - dev_err_ratelimited(smmu->dev, - "Unexpected global fault, this could be serious\n"); - dev_err_ratelimited(smmu->dev, - "\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n", - gfsr, gfsynr0, gfsynr1, gfsynr2); + if (__ratelimit(&rs)) { + if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) && + (gfsr & ARM_SMMU_sGFSR_USF)) + dev_err(smmu->dev, + "Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n", + (u16)gfsynr1); + else + dev_err(smmu->dev, + "Unexpected global fault, this could be serious\n"); + dev_err(smmu->dev, + "\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n", + gfsr, gfsynr0, gfsynr1, gfsynr2); + } - writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, gfsr); return IRQ_HANDLED; } @@ -627,31 +535,33 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->cfg = cfg; - /* TTBCR */ + /* TCR */ if (stage1) { if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) { cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr; } else { - cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr; - cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32; - cb->tcr[1] |= TTBCR2_SEP_UPSTREAM; + cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg); + cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg); if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) - cb->tcr[1] |= TTBCR2_AS; + cb->tcr[1] |= ARM_SMMU_TCR2_AS; + else + cb->tcr[0] |= ARM_SMMU_TCR_EAE; } } else { - cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr; + cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg); } /* TTBRs */ if (stage1) { if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) { - cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr[0]; - cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1]; + cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr; + cb->ttbr[1] = 0; } else { - cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0]; - cb->ttbr[0] |= (u64)cfg->asid << TTBRn_ASID_SHIFT; - cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1]; - cb->ttbr[1] |= (u64)cfg->asid << TTBRn_ASID_SHIFT; + cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr; + cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID, + cfg->asid); + cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, + cfg->asid); } } else { cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr; @@ -663,8 +573,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr; cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr; } else { - cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair[0]; - cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair[1]; + cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair; + cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32; } } } @@ -675,84 +585,84 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) bool stage1; struct arm_smmu_cb *cb = &smmu->cbs[idx]; struct arm_smmu_cfg *cfg = cb->cfg; - void __iomem *cb_base, *gr1_base; - - cb_base = ARM_SMMU_CB(smmu, idx); /* Unassigned context banks only need disabling */ if (!cfg) { - writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, 0); return; } - gr1_base = ARM_SMMU_GR1(smmu); stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS; /* CBA2R */ if (smmu->version > ARM_SMMU_V1) { if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) - reg = CBA2R_RW64_64BIT; + reg = ARM_SMMU_CBA2R_VA64; else - reg = CBA2R_RW64_32BIT; + reg = 0; /* 16-bit VMIDs live in CBA2R */ if (smmu->features & ARM_SMMU_FEAT_VMID16) - reg |= cfg->vmid << CBA2R_VMID_SHIFT; + reg |= FIELD_PREP(ARM_SMMU_CBA2R_VMID16, cfg->vmid); - writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(idx)); + arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg); } /* CBAR */ - reg = cfg->cbar; + reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, cfg->cbar); if (smmu->version < ARM_SMMU_V2) - reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT; + reg |= FIELD_PREP(ARM_SMMU_CBAR_IRPTNDX, cfg->irptndx); /* * Use the weakest shareability/memory types, so they are * overridden by the ttbcr/pte. */ if (stage1) { - reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) | - (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT); + reg |= FIELD_PREP(ARM_SMMU_CBAR_S1_BPSHCFG, + ARM_SMMU_CBAR_S1_BPSHCFG_NSH) | + FIELD_PREP(ARM_SMMU_CBAR_S1_MEMATTR, + ARM_SMMU_CBAR_S1_MEMATTR_WB); } else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) { /* 8-bit VMIDs live in CBAR */ - reg |= cfg->vmid << CBAR_VMID_SHIFT; + reg |= FIELD_PREP(ARM_SMMU_CBAR_VMID, cfg->vmid); } - writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(idx)); + arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg); /* - * TTBCR + * TCR * We must write this before the TTBRs, since it determines the * access behaviour of some fields (in particular, ASID[15:8]). */ if (stage1 && smmu->version > ARM_SMMU_V1) - writel_relaxed(cb->tcr[1], cb_base + ARM_SMMU_CB_TTBCR2); - writel_relaxed(cb->tcr[0], cb_base + ARM_SMMU_CB_TTBCR); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR2, cb->tcr[1]); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR, cb->tcr[0]); /* TTBRs */ if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) { - writel_relaxed(cfg->asid, cb_base + ARM_SMMU_CB_CONTEXTIDR); - writel_relaxed(cb->ttbr[0], cb_base + ARM_SMMU_CB_TTBR0); - writel_relaxed(cb->ttbr[1], cb_base + ARM_SMMU_CB_TTBR1); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_CONTEXTIDR, cfg->asid); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR1, cb->ttbr[1]); } else { - writeq_relaxed(cb->ttbr[0], cb_base + ARM_SMMU_CB_TTBR0); + arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]); if (stage1) - writeq_relaxed(cb->ttbr[1], cb_base + ARM_SMMU_CB_TTBR1); + arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR1, + cb->ttbr[1]); } /* MAIRs (stage-1 only) */ if (stage1) { - writel_relaxed(cb->mair[0], cb_base + ARM_SMMU_CB_S1_MAIR0); - writel_relaxed(cb->mair[1], cb_base + ARM_SMMU_CB_S1_MAIR1); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR0, cb->mair[0]); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR1, cb->mair[1]); } /* SCTLR */ - reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | SCTLR_M; + reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE | + ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M; if (stage1) - reg |= SCTLR_S1_ASIDPNE; + reg |= ARM_SMMU_SCTLR_S1_ASIDPNE; if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) - reg |= SCTLR_E; + reg |= ARM_SMMU_SCTLR_E; - writel_relaxed(reg, cb_base + ARM_SMMU_CB_SCTLR); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg); } static int arm_smmu_init_domain_context(struct iommu_domain *domain, @@ -842,7 +752,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, ias = min(ias, 32UL); oas = min(oas, 32UL); } - smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops; + smmu_domain->flush_ops = &arm_smmu_s1_tlb_ops; break; case ARM_SMMU_DOMAIN_NESTED: /* @@ -862,9 +772,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, oas = min(oas, 40UL); } if (smmu->version == ARM_SMMU_V2) - smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2; + smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v2; else - smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1; + smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v1; break; default: ret = -EINVAL; @@ -884,23 +794,29 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, } if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2) - cfg->vmid = cfg->cbndx + 1 + smmu->cavium_id_base; + cfg->vmid = cfg->cbndx + 1; else - cfg->asid = cfg->cbndx + smmu->cavium_id_base; + cfg->asid = cfg->cbndx; + + smmu_domain->smmu = smmu; + if (smmu->impl && smmu->impl->init_context) { + ret = smmu->impl->init_context(smmu_domain); + if (ret) + goto out_unlock; + } pgtbl_cfg = (struct io_pgtable_cfg) { .pgsize_bitmap = smmu->pgsize_bitmap, .ias = ias, .oas = oas, .coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK, - .tlb = smmu_domain->tlb_ops, + .tlb = smmu_domain->flush_ops, .iommu_dev = smmu->dev, }; if (smmu_domain->non_strict) pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; - smmu_domain->smmu = smmu; pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops) { ret = -ENOMEM; @@ -926,7 +842,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, if (ret < 0) { dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n", cfg->irptndx, irq); - cfg->irptndx = INVALID_IRPTNDX; + cfg->irptndx = ARM_SMMU_INVALID_IRPTNDX; } mutex_unlock(&smmu_domain->init_mutex); @@ -936,6 +852,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, return 0; out_clear_smmu: + __arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx); smmu_domain->smmu = NULL; out_unlock: mutex_unlock(&smmu_domain->init_mutex); @@ -963,7 +880,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) smmu->cbs[cfg->cbndx].cfg = NULL; arm_smmu_write_context_bank(smmu, cfg->cbndx); - if (cfg->irptndx != INVALID_IRPTNDX) { + if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) { irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx]; devm_free_irq(smmu->dev, irq, domain); } @@ -1019,24 +936,25 @@ static void arm_smmu_domain_free(struct iommu_domain *domain) static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx) { struct arm_smmu_smr *smr = smmu->smrs + idx; - u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT; + u32 reg = FIELD_PREP(ARM_SMMU_SMR_ID, smr->id) | + FIELD_PREP(ARM_SMMU_SMR_MASK, smr->mask); if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid) - reg |= SMR_VALID; - writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx)); + reg |= ARM_SMMU_SMR_VALID; + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg); } static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx) { struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx; - u32 reg = (s2cr->type & S2CR_TYPE_MASK) << S2CR_TYPE_SHIFT | - (s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT | - (s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT; + u32 reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, s2cr->type) | + FIELD_PREP(ARM_SMMU_S2CR_CBNDX, s2cr->cbndx) | + FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg); if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs && smmu->smrs[idx].valid) - reg |= S2CR_EXIDVALID; - writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx)); + reg |= ARM_SMMU_S2CR_EXIDVALID; + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg); } static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx) @@ -1052,26 +970,38 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx) */ static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu) { - void __iomem *gr0_base = ARM_SMMU_GR0(smmu); u32 smr; + int i; if (!smmu->smrs) return; - + /* + * If we've had to accommodate firmware memory regions, we may + * have live SMRs by now; tread carefully... + * + * Somewhat perversely, not having a free SMR for this test implies we + * can get away without it anyway, as we'll only be able to 'allocate' + * these SMRs for the ID/mask values we're already trusting to be OK. + */ + for (i = 0; i < smmu->num_mapping_groups; i++) + if (!smmu->smrs[i].valid) + goto smr_ok; + return; +smr_ok: /* * SMR.ID bits may not be preserved if the corresponding MASK * bits are set, so check each one separately. We can reject * masters later if they try to claim IDs outside these masks. */ - smr = smmu->streamid_mask << SMR_ID_SHIFT; - writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); - smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); - smmu->streamid_mask = smr >> SMR_ID_SHIFT; + smr = FIELD_PREP(ARM_SMMU_SMR_ID, smmu->streamid_mask); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr); + smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i)); + smmu->streamid_mask = FIELD_GET(ARM_SMMU_SMR_ID, smr); - smr = smmu->streamid_mask << SMR_MASK_SHIFT; - writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); - smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); - smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT; + smr = FIELD_PREP(ARM_SMMU_SMR_MASK, smmu->streamid_mask); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr); + smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i)); + smmu->smr_mask_mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr); } static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask) @@ -1140,8 +1070,8 @@ static int arm_smmu_master_alloc_smes(struct device *dev) mutex_lock(&smmu->stream_map_mutex); /* Figure out a viable stream map entry allocation */ for_each_cfg_sme(fwspec, i, idx) { - u16 sid = fwspec->ids[i]; - u16 mask = fwspec->ids[i] >> SMR_MASK_SHIFT; + u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]); + u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]); if (idx != INVALID_SMENDX) { ret = -EEXIST; @@ -1163,8 +1093,6 @@ static int arm_smmu_master_alloc_smes(struct device *dev) } group = iommu_group_get_for_dev(dev); - if (!group) - group = ERR_PTR(-ENOMEM); if (IS_ERR(group)) { ret = PTR_ERR(group); goto out_err; @@ -1278,13 +1206,27 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) /* Looks ok, so add the device to the domain */ ret = arm_smmu_domain_add_master(smmu_domain, fwspec); + /* + * Setup an autosuspend delay to avoid bouncing runpm state. + * Otherwise, if a driver for a suspended consumer device + * unmaps buffers, it will runpm resume/suspend for each one. + * + * For example, when used by a GPU device, when an application + * or game exits, it can trigger unmapping 100s or 1000s of + * buffers. With a runpm cycle for each buffer, that adds up + * to 5-10sec worth of reprogramming the context bank, while + * the system appears to be locked up to the user. + */ + pm_runtime_set_autosuspend_delay(smmu->dev, 20); + pm_runtime_use_autosuspend(smmu->dev); + rpm_put: arm_smmu_rpm_put(smmu); return ret; } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; @@ -1301,7 +1243,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, } static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; @@ -1311,7 +1253,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, return 0; arm_smmu_rpm_get(smmu); - ret = ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size, gather); arm_smmu_rpm_put(smmu); return ret; @@ -1322,23 +1264,29 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; - if (smmu_domain->tlb_ops) { + if (smmu_domain->flush_ops) { arm_smmu_rpm_get(smmu); - smmu_domain->tlb_ops->tlb_flush_all(smmu_domain); + smmu_domain->flush_ops->tlb_flush_all(smmu_domain); arm_smmu_rpm_put(smmu); } } -static void arm_smmu_iotlb_sync(struct iommu_domain *domain) +static void arm_smmu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; - if (smmu_domain->tlb_ops) { - arm_smmu_rpm_get(smmu); - smmu_domain->tlb_ops->tlb_sync(smmu_domain); - arm_smmu_rpm_put(smmu); - } + if (!smmu) + return; + + arm_smmu_rpm_get(smmu); + if (smmu->version == ARM_SMMU_V2 || + smmu_domain->stage == ARM_SMMU_DOMAIN_S1) + arm_smmu_tlb_sync_context(smmu_domain); + else + arm_smmu_tlb_sync_global(smmu); + arm_smmu_rpm_put(smmu); } static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain, @@ -1349,28 +1297,26 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain, struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops; struct device *dev = smmu->dev; - void __iomem *cb_base; + void __iomem *reg; u32 tmp; u64 phys; unsigned long va, flags; - int ret; + int ret, idx = cfg->cbndx; ret = arm_smmu_rpm_get(smmu); if (ret < 0) return 0; - cb_base = ARM_SMMU_CB(smmu, cfg->cbndx); - spin_lock_irqsave(&smmu_domain->cb_lock, flags); - /* ATS1 registers can only be written atomically */ va = iova & ~0xfffUL; - if (smmu->version == ARM_SMMU_V2) - smmu_write_atomic_lq(va, cb_base + ARM_SMMU_CB_ATS1PR); - else /* Register is only 32-bit in v1 */ - writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR); + if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) + arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_ATS1PR, va); + else + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va); - if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp, - !(tmp & ATSR_ACTIVE), 5, 50)) { + reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR; + if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ARM_SMMU_ATSR_ACTIVE), + 5, 50)) { spin_unlock_irqrestore(&smmu_domain->cb_lock, flags); dev_err(dev, "iova to phys timed out on %pad. Falling back to software table walk.\n", @@ -1378,9 +1324,9 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain, return ops->iova_to_phys(ops, iova); } - phys = readq_relaxed(cb_base + ARM_SMMU_CB_PAR); + phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR); spin_unlock_irqrestore(&smmu_domain->cb_lock, flags); - if (phys & CB_PAR_F) { + if (phys & ARM_SMMU_CB_PAR_F) { dev_err(dev, "translation fault!\n"); dev_err(dev, "PAR = 0x%llx\n", phys); return 0; @@ -1426,16 +1372,11 @@ static bool arm_smmu_capable(enum iommu_cap cap) } } -static int arm_smmu_match_node(struct device *dev, const void *data) -{ - return dev->fwnode == data; -} - static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL, - fwnode, arm_smmu_match_node); + struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, + fwnode); put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -1466,8 +1407,8 @@ static int arm_smmu_add_device(struct device *dev) ret = -EINVAL; for (i = 0; i < fwspec->num_ids; i++) { - u16 sid = fwspec->ids[i]; - u16 mask = fwspec->ids[i] >> SMR_MASK_SHIFT; + u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]); + u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]); if (sid & ~smmu->streamid_mask) { dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n", @@ -1648,12 +1589,12 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args) u32 mask, fwid = 0; if (args->args_count > 0) - fwid |= (u16)args->args[0]; + fwid |= FIELD_PREP(ARM_SMMU_SMR_ID, args->args[0]); if (args->args_count > 1) - fwid |= (u16)args->args[1] << SMR_MASK_SHIFT; + fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, args->args[1]); else if (!of_property_read_u32(args->np, "stream-match-mask", &mask)) - fwid |= (u16)mask << SMR_MASK_SHIFT; + fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, mask); return iommu_fwspec_add_ids(dev, &fwid, 1); } @@ -1674,15 +1615,6 @@ static void arm_smmu_get_resv_regions(struct device *dev, iommu_dma_get_resv_regions(dev, head); } -static void arm_smmu_put_resv_regions(struct device *dev, - struct list_head *head) -{ - struct iommu_resv_region *entry, *next; - - list_for_each_entry_safe(entry, next, head, list) - kfree(entry); -} - static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, .domain_alloc = arm_smmu_domain_alloc, @@ -1700,19 +1632,18 @@ static struct iommu_ops arm_smmu_ops = { .domain_set_attr = arm_smmu_domain_set_attr, .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, - .put_resv_regions = arm_smmu_put_resv_regions, + .put_resv_regions = generic_iommu_put_resv_regions, .pgsize_bitmap = -1UL, /* Restricted during device attach */ }; static void arm_smmu_device_reset(struct arm_smmu_device *smmu) { - void __iomem *gr0_base = ARM_SMMU_GR0(smmu); int i; - u32 reg, major; + u32 reg; /* clear global FSR */ - reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR); - writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR); + reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, reg); /* * Reset stream mapping groups: Initial values mark all SMRn as @@ -1721,76 +1652,50 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu) for (i = 0; i < smmu->num_mapping_groups; ++i) arm_smmu_write_sme(smmu, i); - if (smmu->model == ARM_MMU500) { - /* - * Before clearing ARM_MMU500_ACTLR_CPRE, need to - * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK - * bit is only present in MMU-500r2 onwards. - */ - reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7); - major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK; - reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sACR); - if (major >= 2) - reg &= ~ARM_MMU500_ACR_CACHE_LOCK; - /* - * Allow unmatched Stream IDs to allocate bypass - * TLB entries for reduced latency. - */ - reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN; - writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR); - } - /* Make sure all context banks are disabled and clear CB_FSR */ for (i = 0; i < smmu->num_context_banks; ++i) { - void __iomem *cb_base = ARM_SMMU_CB(smmu, i); - arm_smmu_write_context_bank(smmu, i); - writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR); - /* - * Disable MMU-500's not-particularly-beneficial next-page - * prefetcher for the sake of errata #841119 and #826419. - */ - if (smmu->model == ARM_MMU500) { - reg = readl_relaxed(cb_base + ARM_SMMU_CB_ACTLR); - reg &= ~ARM_MMU500_ACTLR_CPRE; - writel_relaxed(reg, cb_base + ARM_SMMU_CB_ACTLR); - } + arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT); } /* Invalidate the TLB, just in case */ - writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLH); - writel_relaxed(QCOM_DUMMY_VAL, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLH, QCOM_DUMMY_VAL); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLNSNH, QCOM_DUMMY_VAL); - reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0); + reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0); /* Enable fault reporting */ - reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE); + reg |= (ARM_SMMU_sCR0_GFRE | ARM_SMMU_sCR0_GFIE | + ARM_SMMU_sCR0_GCFGFRE | ARM_SMMU_sCR0_GCFGFIE); /* Disable TLB broadcasting. */ - reg |= (sCR0_VMIDPNE | sCR0_PTM); + reg |= (ARM_SMMU_sCR0_VMIDPNE | ARM_SMMU_sCR0_PTM); /* Enable client access, handling unmatched streams as appropriate */ - reg &= ~sCR0_CLIENTPD; + reg &= ~ARM_SMMU_sCR0_CLIENTPD; if (disable_bypass) - reg |= sCR0_USFCFG; + reg |= ARM_SMMU_sCR0_USFCFG; else - reg &= ~sCR0_USFCFG; + reg &= ~ARM_SMMU_sCR0_USFCFG; /* Disable forced broadcasting */ - reg &= ~sCR0_FB; + reg &= ~ARM_SMMU_sCR0_FB; /* Don't upgrade barriers */ - reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT); + reg &= ~(ARM_SMMU_sCR0_BSU); if (smmu->features & ARM_SMMU_FEAT_VMID16) - reg |= sCR0_VMID16EN; + reg |= ARM_SMMU_sCR0_VMID16EN; if (smmu->features & ARM_SMMU_FEAT_EXIDS) - reg |= sCR0_EXIDENABLE; + reg |= ARM_SMMU_sCR0_EXIDENABLE; + + if (smmu->impl && smmu->impl->reset) + smmu->impl->reset(smmu); /* Push the button */ arm_smmu_tlb_sync_global(smmu); - writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, reg); } static int arm_smmu_id_size_to_bits(int size) @@ -1814,8 +1719,7 @@ static int arm_smmu_id_size_to_bits(int size) static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) { - unsigned long size; - void __iomem *gr0_base = ARM_SMMU_GR0(smmu); + unsigned int size; u32 id; bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK; int i; @@ -1825,25 +1729,25 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) smmu->version == ARM_SMMU_V2 ? 2 : 1); /* ID0 */ - id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0); + id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID0); /* Restrict available stages based on module parameter */ if (force_stage == 1) - id &= ~(ID0_S2TS | ID0_NTS); + id &= ~(ARM_SMMU_ID0_S2TS | ARM_SMMU_ID0_NTS); else if (force_stage == 2) - id &= ~(ID0_S1TS | ID0_NTS); + id &= ~(ARM_SMMU_ID0_S1TS | ARM_SMMU_ID0_NTS); - if (id & ID0_S1TS) { + if (id & ARM_SMMU_ID0_S1TS) { smmu->features |= ARM_SMMU_FEAT_TRANS_S1; dev_notice(smmu->dev, "\tstage 1 translation\n"); } - if (id & ID0_S2TS) { + if (id & ARM_SMMU_ID0_S2TS) { smmu->features |= ARM_SMMU_FEAT_TRANS_S2; dev_notice(smmu->dev, "\tstage 2 translation\n"); } - if (id & ID0_NTS) { + if (id & ARM_SMMU_ID0_NTS) { smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED; dev_notice(smmu->dev, "\tnested translation\n"); } @@ -1854,8 +1758,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) return -ENODEV; } - if ((id & ID0_S1TS) && - ((smmu->version < ARM_SMMU_V2) || !(id & ID0_ATOSNS))) { + if ((id & ARM_SMMU_ID0_S1TS) && + ((smmu->version < ARM_SMMU_V2) || !(id & ARM_SMMU_ID0_ATOSNS))) { smmu->features |= ARM_SMMU_FEAT_TRANS_OPS; dev_notice(smmu->dev, "\taddress translation ops\n"); } @@ -1866,7 +1770,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) * Fortunately, this also opens up a workaround for systems where the * ID register value has ended up configured incorrectly. */ - cttw_reg = !!(id & ID0_CTTW); + cttw_reg = !!(id & ARM_SMMU_ID0_CTTW); if (cttw_fw || cttw_reg) dev_notice(smmu->dev, "\t%scoherent table walk\n", cttw_fw ? "" : "non-"); @@ -1875,16 +1779,16 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) "\t(IDR0.CTTW overridden by FW configuration)\n"); /* Max. number of entries we have for stream matching/indexing */ - if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) { + if (smmu->version == ARM_SMMU_V2 && id & ARM_SMMU_ID0_EXIDS) { smmu->features |= ARM_SMMU_FEAT_EXIDS; size = 1 << 16; } else { - size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK); + size = 1 << FIELD_GET(ARM_SMMU_ID0_NUMSIDB, id); } smmu->streamid_mask = size - 1; - if (id & ID0_SMS) { + if (id & ARM_SMMU_ID0_SMS) { smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH; - size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK; + size = FIELD_GET(ARM_SMMU_ID0_NUMSMRG, id); if (size == 0) { dev_err(smmu->dev, "stream-matching supported, but no SMRs present!\n"); @@ -1898,7 +1802,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) return -ENOMEM; dev_notice(smmu->dev, - "\tstream matching with %lu register groups", size); + "\tstream matching with %u register groups", size); } /* s2cr->type == 0 means translation, so initialise explicitly */ smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs), @@ -1912,59 +1816,49 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) mutex_init(&smmu->stream_map_mutex); spin_lock_init(&smmu->global_sync_lock); - if (smmu->version < ARM_SMMU_V2 || !(id & ID0_PTFS_NO_AARCH32)) { + if (smmu->version < ARM_SMMU_V2 || + !(id & ARM_SMMU_ID0_PTFS_NO_AARCH32)) { smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L; - if (!(id & ID0_PTFS_NO_AARCH32S)) + if (!(id & ARM_SMMU_ID0_PTFS_NO_AARCH32S)) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_S; } /* ID1 */ - id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1); - smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12; + id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1); + smmu->pgshift = (id & ARM_SMMU_ID1_PAGESIZE) ? 16 : 12; /* Check for size mismatch of SMMU address space from mapped region */ - size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1); - size <<= smmu->pgshift; - if (smmu->cb_base != gr0_base + size) + size = 1 << (FIELD_GET(ARM_SMMU_ID1_NUMPAGENDXB, id) + 1); + if (smmu->numpage != 2 * size << smmu->pgshift) dev_warn(smmu->dev, - "SMMU address space size (0x%lx) differs from mapped region size (0x%tx)!\n", - size * 2, (smmu->cb_base - gr0_base) * 2); + "SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n", + 2 * size << smmu->pgshift, smmu->numpage); + /* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */ + smmu->numpage = size; - smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK; - smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK; + smmu->num_s2_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMS2CB, id); + smmu->num_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMCB, id); if (smmu->num_s2_context_banks > smmu->num_context_banks) { dev_err(smmu->dev, "impossible number of S2 context banks!\n"); return -ENODEV; } dev_notice(smmu->dev, "\t%u context banks (%u stage-2 only)\n", smmu->num_context_banks, smmu->num_s2_context_banks); - /* - * Cavium CN88xx erratum #27704. - * Ensure ASID and VMID allocation is unique across all SMMUs in - * the system. - */ - if (smmu->model == CAVIUM_SMMUV2) { - smmu->cavium_id_base = - atomic_add_return(smmu->num_context_banks, - &cavium_smmu_context_count); - smmu->cavium_id_base -= smmu->num_context_banks; - dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n"); - } smmu->cbs = devm_kcalloc(smmu->dev, smmu->num_context_banks, sizeof(*smmu->cbs), GFP_KERNEL); if (!smmu->cbs) return -ENOMEM; /* ID2 */ - id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2); - size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK); + id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2); + size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_IAS, id)); smmu->ipa_size = size; /* The output mask is also applied for bypass */ - size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK); + size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_OAS, id)); smmu->pa_size = size; - if (id & ID2_VMID16) + if (id & ARM_SMMU_ID2_VMID16) smmu->features |= ARM_SMMU_FEAT_VMID16; /* @@ -1981,13 +1875,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) if (smmu->version == ARM_SMMU_V1_64K) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K; } else { - size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK; + size = FIELD_GET(ARM_SMMU_ID2_UBS, id); smmu->va_size = arm_smmu_id_size_to_bits(size); - if (id & ID2_PTFS_4K) + if (id & ARM_SMMU_ID2_PTFS_4K) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K; - if (id & ID2_PTFS_16K) + if (id & ARM_SMMU_ID2_PTFS_16K) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_16K; - if (id & ID2_PTFS_64K) + if (id & ARM_SMMU_ID2_PTFS_64K) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K; } @@ -2018,6 +1912,9 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n", smmu->ipa_size, smmu->pa_size); + if (smmu->impl && smmu->impl->cfg_probe) + return smmu->impl->cfg_probe(smmu); + return 0; } @@ -2046,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = { { .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 }, { }, }; +MODULE_DEVICE_TABLE(of, arm_smmu_of_match); #ifdef CONFIG_ACPI static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu) @@ -2130,12 +2028,12 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev, smmu->version = data->version; smmu->model = data->model; - parse_driver_options(smmu); - legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL); if (legacy_binding && !using_generic_binding) { - if (!using_legacy_binding) - pr_notice("deprecated \"mmu-masters\" DT property in use; DMA API support unavailable\n"); + if (!using_legacy_binding) { + pr_notice("deprecated \"mmu-masters\" DT property in use; %s support unavailable\n", + IS_ENABLED(CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS) ? "DMA API" : "SMMU"); + } using_legacy_binding = true; } else if (!legacy_binding && !using_legacy_binding) { using_generic_binding = true; @@ -2150,25 +2048,50 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev, return 0; } -static void arm_smmu_bus_init(void) +static int arm_smmu_bus_init(struct iommu_ops *ops) { + int err; + /* Oh, for a proper bus abstraction */ - if (!iommu_present(&platform_bus_type)) - bus_set_iommu(&platform_bus_type, &arm_smmu_ops); + if (!iommu_present(&platform_bus_type)) { + err = bus_set_iommu(&platform_bus_type, ops); + if (err) + return err; + } #ifdef CONFIG_ARM_AMBA - if (!iommu_present(&amba_bustype)) - bus_set_iommu(&amba_bustype, &arm_smmu_ops); + if (!iommu_present(&amba_bustype)) { + err = bus_set_iommu(&amba_bustype, ops); + if (err) + goto err_reset_platform_ops; + } #endif #ifdef CONFIG_PCI if (!iommu_present(&pci_bus_type)) { - pci_request_acs(); - bus_set_iommu(&pci_bus_type, &arm_smmu_ops); + err = bus_set_iommu(&pci_bus_type, ops); + if (err) + goto err_reset_amba_ops; } #endif #ifdef CONFIG_FSL_MC_BUS - if (!iommu_present(&fsl_mc_bus_type)) - bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops); + if (!iommu_present(&fsl_mc_bus_type)) { + err = bus_set_iommu(&fsl_mc_bus_type, ops); + if (err) + goto err_reset_pci_ops; + } +#endif + return 0; + +err_reset_pci_ops: __maybe_unused; +#ifdef CONFIG_PCI + bus_set_iommu(&pci_bus_type, NULL); +#endif +err_reset_amba_ops: __maybe_unused; +#ifdef CONFIG_ARM_AMBA + bus_set_iommu(&amba_bustype, NULL); #endif +err_reset_platform_ops: __maybe_unused; + bus_set_iommu(&platform_bus_type, NULL); + return err; } static int arm_smmu_device_probe(struct platform_device *pdev) @@ -2194,12 +2117,20 @@ static int arm_smmu_device_probe(struct platform_device *pdev) if (err) return err; + smmu = arm_smmu_impl_init(smmu); + if (IS_ERR(smmu)) + return PTR_ERR(smmu); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ioaddr = res->start; smmu->base = devm_ioremap_resource(dev, res); if (IS_ERR(smmu->base)) return PTR_ERR(smmu->base); - smmu->cb_base = smmu->base + resource_size(res) / 2; + /* + * The resource size should effectively match the value of SMMU_TOP; + * stash that temporarily until we know PAGESIZE to validate it with. + */ + smmu->numpage = resource_size(res); num_irqs = 0; while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) { @@ -2224,10 +2155,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev) for (i = 0; i < num_irqs; ++i) { int irq = platform_get_irq(pdev, i); - if (irq < 0) { - dev_err(dev, "failed to get irq index %d\n", i); + if (irq < 0) return -ENODEV; - } smmu->irqs[i] = irq; } @@ -2308,38 +2237,28 @@ static int arm_smmu_device_probe(struct platform_device *pdev) * ready to handle default domain setup as soon as any SMMU exists. */ if (!using_legacy_binding) - arm_smmu_bus_init(); + return arm_smmu_bus_init(&arm_smmu_ops); return 0; } -/* - * With the legacy DT binding in play, though, we have no guarantees about - * probe order, but then we're also not doing default domains, so we can - * delay setting bus ops until we're sure every possible SMMU is ready, - * and that way ensure that no add_device() calls get missed. - */ -static int arm_smmu_legacy_bus_init(void) -{ - if (using_legacy_binding) - arm_smmu_bus_init(); - return 0; -} -device_initcall_sync(arm_smmu_legacy_bus_init); - -static void arm_smmu_device_shutdown(struct platform_device *pdev) +static int arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); if (!smmu) - return; + return -ENODEV; if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS)) dev_err(&pdev->dev, "removing device with active domains!\n"); + arm_smmu_bus_init(NULL); + iommu_device_unregister(&smmu->iommu); + iommu_device_sysfs_remove(&smmu->iommu); + arm_smmu_rpm_get(smmu); /* Turn the thing off */ - writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD); arm_smmu_rpm_put(smmu); if (pm_runtime_enabled(smmu->dev)) @@ -2348,6 +2267,12 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) clk_bulk_disable(smmu->num_clks, smmu->clks); clk_bulk_unprepare(smmu->num_clks, smmu->clks); + return 0; +} + +static void arm_smmu_device_shutdown(struct platform_device *pdev) +{ + arm_smmu_device_remove(pdev); } static int __maybe_unused arm_smmu_runtime_resume(struct device *dev) @@ -2398,11 +2323,17 @@ static const struct dev_pm_ops arm_smmu_pm_ops = { static struct platform_driver arm_smmu_driver = { .driver = { .name = "arm-smmu", - .of_match_table = of_match_ptr(arm_smmu_of_match), + .of_match_table = arm_smmu_of_match, .pm = &arm_smmu_pm_ops, - .suppress_bind_attrs = true, + .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, + .remove = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; -builtin_platform_driver(arm_smmu_driver); +module_platform_driver(arm_smmu_driver); + +MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations"); +MODULE_AUTHOR("Will Deacon <will@kernel.org>"); +MODULE_ALIAS("platform:arm-smmu"); +MODULE_LICENSE("GPL v2"); |
