diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 16 | ||||
-rw-r--r-- | drivers/iommu/Makefile | 4 | ||||
-rw-r--r-- | drivers/iommu/amd/amd_iommu.h | 2 | ||||
-rw-r--r-- | drivers/iommu/amd/amd_iommu_types.h | 1 | ||||
-rw-r--r-- | drivers/iommu/amd/init.c | 92 | ||||
-rw-r--r-- | drivers/iommu/amd/iommu.c | 178 | ||||
-rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 5 | ||||
-rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 4 | ||||
-rw-r--r-- | drivers/iommu/exynos-iommu.c | 2 | ||||
-rw-r--r-- | drivers/iommu/intel/dmar.c | 68 | ||||
-rw-r--r-- | drivers/iommu/intel/iommu.c | 88 | ||||
-rw-r--r-- | drivers/iommu/intel/irq_remapping.c | 2 | ||||
-rw-r--r-- | drivers/iommu/intel/pasid.c | 75 | ||||
-rw-r--r-- | drivers/iommu/intel/pasid.h | 6 | ||||
-rw-r--r-- | drivers/iommu/intel/svm.c | 82 | ||||
-rw-r--r-- | drivers/iommu/mtk_iommu.c | 36 | ||||
-rw-r--r-- | drivers/iommu/mtk_iommu_v1.c | 94 | ||||
-rw-r--r-- | drivers/iommu/sprd-iommu.c | 577 | ||||
-rw-r--r-- | drivers/iommu/tegra-smmu.c | 7 |
19 files changed, 967 insertions, 372 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 192ef8f61310..1f111b399bca 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -349,7 +349,7 @@ config S390_AP_IOMMU is not implemented as it is not necessary for VFIO. config MTK_IOMMU - bool "MTK IOMMU Support" + tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST select ARM_DMA_USE_IOMMU select IOMMU_API @@ -364,7 +364,7 @@ config MTK_IOMMU If unsure, say N here. config MTK_IOMMU_V1 - bool "MTK IOMMU Version 1 (M4U gen1) Support" + tristate "MediaTek IOMMU Version 1 (M4U gen1) Support" depends on ARM depends on ARCH_MEDIATEK || COMPILE_TEST select ARM_DMA_USE_IOMMU @@ -408,4 +408,16 @@ config VIRTIO_IOMMU Say Y here if you intend to run this kernel as a guest. +config SPRD_IOMMU + tristate "Unisoc IOMMU Support" + depends on ARCH_SPRD || COMPILE_TEST + select IOMMU_API + help + Support for IOMMU on Unisoc's SoCs, this IOMMU can be used by + Unisoc's multimedia devices, such as display, Image codec(jpeg) + and a few signal processors, including VSP(video), GSP(graphic), + ISP(image), and CPP(camera pixel processor), etc. + + Say Y here if you want to use the multimedia devices listed above. + endif # IOMMU_SUPPORT diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 60fafc23dee6..c0fb0ba88143 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -27,5 +27,5 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o obj-$(CONFIG_S390_IOMMU) += s390-iommu.o obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o -obj-$(CONFIG_IOMMU_SVA_LIB) += iommu-sva-lib.o -obj-$(CONFIG_IOMMU_SVA_LIB) += io-pgfault.o +obj-$(CONFIG_IOMMU_SVA_LIB) += iommu-sva-lib.o io-pgfault.o +obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 026ce7f8d993..55dd38d814d9 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -11,7 +11,6 @@ #include "amd_iommu_types.h" -extern int amd_iommu_get_num_iommus(void); extern int amd_iommu_init_dma_ops(void); extern int amd_iommu_init_passthrough(void); extern irqreturn_t amd_iommu_int_thread(int irq, void *data); @@ -65,7 +64,6 @@ extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid); extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid, unsigned long cr3); extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid); -extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev); #ifdef CONFIG_IRQ_REMAP extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 6937e3674a16..94c1a7a9876d 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -693,7 +693,6 @@ struct iommu_dev_data { } ats; /* ATS state */ bool pri_tlp; /* PASID TLB required for PPR completions */ - u32 errata; /* Bitmap for errata to apply */ bool use_vapic; /* Enable device to use vapic mode */ bool defer_attach; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 9126efcbaf2c..54f6e99528f3 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -12,7 +12,6 @@ #include <linux/acpi.h> #include <linux/list.h> #include <linux/bitmap.h> -#include <linux/delay.h> #include <linux/slab.h> #include <linux/syscore_ops.h> #include <linux/interrupt.h> @@ -208,7 +207,6 @@ u16 *amd_iommu_alias_table; * for a specific device. It is also indexed by the PCI device id. */ struct amd_iommu **amd_iommu_rlookup_table; -EXPORT_SYMBOL(amd_iommu_rlookup_table); /* * This table is used to find the irq remapping table for a given device id @@ -257,8 +255,6 @@ static enum iommu_init_state init_state = IOMMU_START_STATE; static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); -static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, - u8 fxn, u64 *value, bool is_write); static bool amd_iommu_pre_enabled = true; @@ -268,7 +264,6 @@ bool translation_pre_enabled(struct amd_iommu *iommu) { return (iommu->flags & AMD_IOMMU_FLAG_TRANS_PRE_ENABLED); } -EXPORT_SYMBOL(translation_pre_enabled); static void clear_translation_pre_enabled(struct amd_iommu *iommu) { @@ -1717,53 +1712,16 @@ static int __init init_iommu_all(struct acpi_table_header *table) return 0; } -static void __init init_iommu_perf_ctr(struct amd_iommu *iommu) +static void init_iommu_perf_ctr(struct amd_iommu *iommu) { - int retry; + u64 val; struct pci_dev *pdev = iommu->dev; - u64 val = 0xabcd, val2 = 0, save_reg, save_src; if (!iommu_feature(iommu, FEATURE_PC)) return; amd_iommu_pc_present = true; - /* save the value to restore, if writable */ - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false) || - iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, false)) - goto pc_false; - - /* - * Disable power gating by programing the performance counter - * source to 20 (i.e. counts the reads and writes from/to IOMMU - * Reserved Register [MMIO Offset 1FF8h] that are ignored.), - * which never get incremented during this init phase. - * (Note: The event is also deprecated.) - */ - val = 20; - if (iommu_pc_get_set_reg(iommu, 0, 0, 8, &val, true)) - goto pc_false; - - /* Check if the performance counters can be written to */ - val = 0xabcd; - for (retry = 5; retry; retry--) { - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true) || - iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false) || - val2) - break; - - /* Wait about 20 msec for power gating to disable and retry. */ - msleep(20); - } - - /* restore */ - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true) || - iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, true)) - goto pc_false; - - if (val != val2) - goto pc_false; - pci_info(pdev, "IOMMU performance counters supported\n"); val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET); @@ -1771,11 +1729,6 @@ static void __init init_iommu_perf_ctr(struct amd_iommu *iommu) iommu->max_counters = (u8) ((val >> 7) & 0xf); return; - -pc_false: - pci_err(pdev, "Unable to read/write to IOMMU perf counter.\n"); - amd_iommu_pc_present = false; - return; } static ssize_t amd_iommu_show_cap(struct device *dev, @@ -1837,7 +1790,7 @@ static void __init late_iommu_features_init(struct amd_iommu *iommu) * IVHD and MMIO conflict. */ if (features != iommu->features) - pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx\n).", + pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx).\n", features, iommu->features); } @@ -2714,7 +2667,6 @@ static int __init early_amd_iommu_init(void) struct acpi_table_header *ivrs_base; int i, remap_cache_sz, ret; acpi_status status; - u32 pci_id; if (!amd_iommu_detected) return -ENODEV; @@ -2804,16 +2756,6 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; - /* Disable IOMMU if there's Stoney Ridge graphics */ - for (i = 0; i < 32; i++) { - pci_id = read_pci_config(0, i, 0, 0); - if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { - pr_info("Disable IOMMU on Stoney Ridge\n"); - amd_iommu_disabled = true; - break; - } - } - /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -2880,6 +2822,7 @@ static bool detect_ivrs(void) { struct acpi_table_header *ivrs_base; acpi_status status; + int i; status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) @@ -2892,6 +2835,17 @@ static bool detect_ivrs(void) acpi_put_table(ivrs_base); + /* Don't use IOMMU if there is Stoney Ridge graphics */ + for (i = 0; i < 32; i++) { + u32 pci_id; + + pci_id = read_pci_config(0, i, 0, 0); + if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { + pr_info("Disable IOMMU on Stoney Ridge\n"); + return false; + } + } + /* Make sure ACS will be enabled during PCI probe */ pci_request_acs(); @@ -2918,12 +2872,12 @@ static int __init state_next(void) } break; case IOMMU_IVRS_DETECTED: - ret = early_amd_iommu_init(); - init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; - if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) { - pr_info("AMD IOMMU disabled\n"); + if (amd_iommu_disabled) { init_state = IOMMU_CMDLINE_DISABLED; ret = -EINVAL; + } else { + ret = early_amd_iommu_init(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; } break; case IOMMU_ACPI_FINISHED: @@ -3001,8 +2955,11 @@ int __init amd_iommu_prepare(void) amd_iommu_irq_remap = true; ret = iommu_go_to_state(IOMMU_ACPI_FINISHED); - if (ret) + if (ret) { + amd_iommu_irq_remap = false; return ret; + } + return amd_iommu_irq_remap ? 0 : -ENODEV; } @@ -3273,7 +3230,6 @@ struct amd_iommu *get_amd_iommu(unsigned int idx) return iommu; return NULL; } -EXPORT_SYMBOL(get_amd_iommu); /**************************************************************************** * @@ -3355,7 +3311,6 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false); } -EXPORT_SYMBOL(amd_iommu_pc_get_reg); int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value) { @@ -3364,4 +3319,3 @@ int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true); } -EXPORT_SYMBOL(amd_iommu_pc_set_reg); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index ce6393d2224d..80e8e1916dd1 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -290,15 +290,6 @@ static bool pci_iommuv2_capable(struct pci_dev *pdev) return true; } -static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum) -{ - struct iommu_dev_data *dev_data; - - dev_data = dev_iommu_priv_get(&pdev->dev); - - return dev_data->errata & (1 << erratum) ? true : false; -} - /* * This function checks if the driver got a valid device from the caller to * avoid dereferencing invalid pointers. @@ -861,33 +852,58 @@ static void build_inv_dte(struct iommu_cmd *cmd, u16 devid) CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY); } -static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, - size_t size, u16 domid, int pde) +/* + * Builds an invalidation address which is suitable for one page or multiple + * pages. Sets the size bit (S) as needed is more than one page is flushed. + */ +static inline u64 build_inv_address(u64 address, size_t size) { - u64 pages; - bool s; + u64 pages, end, msb_diff; pages = iommu_num_pages(address, size, PAGE_SIZE); - s = false; - if (pages > 1) { + if (pages == 1) + return address & PAGE_MASK; + + end = address + size - 1; + + /* + * msb_diff would hold the index of the most significant bit that + * flipped between the start and end. + */ + msb_diff = fls64(end ^ address) - 1; + + /* + * Bits 63:52 are sign extended. If for some reason bit 51 is different + * between the start and the end, invalidate everything. + */ + if (unlikely(msb_diff > 51)) { + address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; + } else { /* - * If we have to flush more than one page, flush all - * TLB entries for this domain + * The msb-bit must be clear on the address. Just set all the + * lower bits. */ - address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - s = true; + address |= 1ull << (msb_diff - 1); } + /* Clear bits 11:0 */ address &= PAGE_MASK; + /* Set the size bit - we flush more than one 4kb page */ + return address | CMD_INV_IOMMU_PAGES_SIZE_MASK; +} + +static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, + size_t size, u16 domid, int pde) +{ + u64 inv_address = build_inv_address(address, size); + memset(cmd, 0, sizeof(*cmd)); cmd->data[1] |= domid; - cmd->data[2] = lower_32_bits(address); - cmd->data[3] = upper_32_bits(address); + cmd->data[2] = lower_32_bits(inv_address); + cmd->data[3] = upper_32_bits(inv_address); CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); - if (s) /* size bit - we flush more than one 4kb page */ - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; if (pde) /* PDE bit - we want to flush everything, not only the PTEs */ cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; } @@ -895,32 +911,15 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep, u64 address, size_t size) { - u64 pages; - bool s; - - pages = iommu_num_pages(address, size, PAGE_SIZE); - s = false; - - if (pages > 1) { - /* - * If we have to flush more than one page, flush all - * TLB entries for this domain - */ - address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - s = true; - } - - address &= PAGE_MASK; + u64 inv_address = build_inv_address(address, size); memset(cmd, 0, sizeof(*cmd)); cmd->data[0] = devid; cmd->data[0] |= (qdep & 0xff) << 24; cmd->data[1] = devid; - cmd->data[2] = lower_32_bits(address); - cmd->data[3] = upper_32_bits(address); + cmd->data[2] = lower_32_bits(inv_address); + cmd->data[3] = upper_32_bits(inv_address); CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); - if (s) - cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; } static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid, @@ -1531,33 +1530,9 @@ static void pdev_iommuv2_disable(struct pci_dev *pdev) pci_disable_pasid(pdev); } -/* FIXME: Change generic reset-function to do the same */ -static int pri_reset_while_enabled(struct pci_dev *pdev) -{ - u16 control; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) - return -EINVAL; - - pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control); - control |= PCI_PRI_CTRL_RESET; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); - - return 0; -} - static int pdev_iommuv2_enable(struct pci_dev *pdev) { - bool reset_enable; - int reqs, ret; - - /* FIXME: Hardcode number of outstanding requests for now */ - reqs = 32; - if (pdev_pri_erratum(pdev, AMD_PRI_DEV_ERRATUM_LIMIT_REQ_ONE)) - reqs = 1; - reset_enable = pdev_pri_erratum(pdev, AMD_PRI_DEV_ERRATUM_ENABLE_RESET); + int ret; /* Only allow access to user-accessible pages */ ret = pci_enable_pasid(pdev, 0); @@ -1570,16 +1545,11 @@ static int pdev_iommuv2_enable(struct pci_dev *pdev) goto out_err; /* Enable PRI */ - ret = pci_enable_pri(pdev, reqs); + /* FIXME: Hardcode number of outstanding requests for now */ + ret = pci_enable_pri(pdev, 32); if (ret) goto out_err; - if (reset_enable) { - ret = pri_reset_while_enabled(pdev); - if (ret) - goto out_err; - } - ret = pci_enable_ats(pdev, PAGE_SHIFT); if (ret) goto out_err; @@ -1715,9 +1685,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) return ERR_PTR(-ENODEV); devid = get_device_id(dev); - if (devid < 0) - return ERR_PTR(devid); - iommu = amd_iommu_rlookup_table[devid]; if (dev_iommu_priv_get(dev)) @@ -1999,16 +1966,12 @@ static void amd_iommu_detach_device(struct iommu_domain *dom, struct device *dev) { struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); + int devid = get_device_id(dev); struct amd_iommu *iommu; - int devid; if (!check_device(dev)) return; - devid = get_device_id(dev); - if (devid < 0) - return; - if (dev_data->domain != NULL) detach_device(dev); @@ -2289,9 +2252,6 @@ int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids) unsigned long flags; int levels, ret; - if (pasids <= 0 || pasids > (PASID_MASK + 1)) - return -EINVAL; - /* Number of GCR3 table levels required */ for (levels = 0; (pasids - 1) & ~0x1ff; pasids >>= 9) levels += 1; @@ -2542,52 +2502,6 @@ int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid, } EXPORT_SYMBOL(amd_iommu_complete_ppr); -struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev) -{ - struct protection_domain *pdomain; - struct iommu_dev_data *dev_data; - struct device *dev = &pdev->dev; - struct iommu_domain *io_domain; - - if (!check_device(dev)) - return NULL; - - dev_data = dev_iommu_priv_get(&pdev->dev); - pdomain = dev_data->domain; - io_domain = iommu_get_domain_for_dev(dev); - - if (pdomain == NULL && dev_data->defer_attach) { - dev_data->defer_attach = false; - pdomain = to_pdomain(io_domain); - attach_device(dev, pdomain); - } - - if (pdomain == NULL) - return NULL; - - if (io_domain->type != IOMMU_DOMAIN_DMA) - return NULL; - - /* Only return IOMMUv2 domains */ - if (!(pdomain->flags & PD_IOMMUV2_MASK)) - return NULL; - - return &pdomain->domain; -} -EXPORT_SYMBOL(amd_iommu_get_v2_domain); - -void amd_iommu_enable_device_erratum(struct pci_dev *pdev, u32 erratum) -{ - struct iommu_dev_data *dev_data; - - if (!amd_iommu_v2_supported()) - return; - - dev_data = dev_iommu_priv_get(&pdev->dev); - dev_data->errata |= (1 << erratum); -} -EXPORT_SYMBOL(amd_iommu_enable_device_erratum); - int amd_iommu_device_info(struct pci_dev *pdev, struct amd_iommu_device_info *info) { 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 7fe45838298c..6f8ffc86a115 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -245,8 +245,6 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) break; case CMDQ_OP_PREFETCH_CFG: cmd[0] |= FIELD_PREP(CMDQ_PREFETCH_0_SID, ent->prefetch.sid); - cmd[1] |= FIELD_PREP(CMDQ_PREFETCH_1_SIZE, ent->prefetch.size); - cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK; break; case CMDQ_OP_CFGI_CD: cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid); @@ -2328,6 +2326,9 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + if (!gather->pgsize) + return; + arm_smmu_tlb_inv_range_domain(gather->start, gather->end - gather->start + 1, gather->pgsize, true, smmu_domain); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 05cf2bf42d33..46e8c49214a8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -115,7 +115,7 @@ #define GERROR_PRIQ_ABT_ERR (1 << 3) #define GERROR_EVTQ_ABT_ERR (1 << 2) #define GERROR_CMDQ_ERR (1 << 0) -#define GERROR_ERR_MASK 0xfd +#define GERROR_ERR_MASK 0x1fd #define ARM_SMMU_GERRORN 0x64 @@ -410,8 +410,6 @@ struct arm_smmu_cmdq_ent { #define CMDQ_OP_PREFETCH_CFG 0x1 struct { u32 sid; - u8 size; - u64 addr; } prefetch; #define CMDQ_OP_CFGI_STE 0x3 diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index de324b4eedfe..8fa9a591fb96 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -407,7 +407,7 @@ static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id) struct sysmmu_drvdata *data = dev_id; const struct sysmmu_fault_info *finfo; unsigned int i, n, itype; - sysmmu_iova_t fault_addr = -1; + sysmmu_iova_t fault_addr; unsigned short reg_status, reg_clear; int ret = -ENOSYS; diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index d5c51b5c20af..6971397805f3 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1205,6 +1205,63 @@ static inline void reclaim_free_desc(struct q_inval *qi) } } +static const char *qi_type_string(u8 type) +{ + switch (type) { + case QI_CC_TYPE: + return "Context-cache Invalidation"; + case QI_IOTLB_TYPE: + return "IOTLB Invalidation"; + case QI_DIOTLB_TYPE: + return "Device-TLB Invalidation"; + case QI_IEC_TYPE: + return "Interrupt Entry Cache Invalidation"; + case QI_IWD_TYPE: + return "Invalidation Wait"; + case QI_EIOTLB_TYPE: + return "PASID-based IOTLB Invalidation"; + case QI_PC_TYPE: + return "PASID-cache Invalidation"; + case QI_DEIOTLB_TYPE: + return "PASID-based Device-TLB Invalidation"; + case QI_PGRP_RESP_TYPE: + return "Page Group Response"; + default: + return "UNKNOWN"; + } +} + +static void qi_dump_fault(struct intel_iommu *iommu, u32 fault) +{ + unsigned int head = dmar_readl(iommu->reg + DMAR_IQH_REG); + u64 iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG); + struct qi_desc *desc = iommu->qi->desc + head; + + if (fault & DMA_FSTS_IQE) + pr_err("VT-d detected Invalidation Queue Error: Reason %llx", + DMAR_IQER_REG_IQEI(iqe_err)); + if (fault & DMA_FSTS_ITE) + pr_err("VT-d detected Invalidation Time-out Error: SID %llx", + DMAR_IQER_REG_ITESID(iqe_err)); + if (fault & DMA_FSTS_ICE) + pr_err("VT-d detected Invalidation Completion Error: SID %llx", + DMAR_IQER_REG_ICESID(iqe_err)); + + pr_err("QI HEAD: %s qw0 = 0x%llx, qw1 = 0x%llx\n", + qi_type_string(desc->qw0 & 0xf), + (unsigned long long)desc->qw0, + (unsigned long long)desc->qw1); + + head = ((head >> qi_shift(iommu)) + QI_LENGTH - 1) % QI_LENGTH; + head <<= qi_shift(iommu); + desc = iommu->qi->desc + head; + + pr_err("QI PRIOR: %s qw0 = 0x%llx, qw1 = 0x%llx\n", + qi_type_string(desc->qw0 & 0xf), + (unsigned long long)desc->qw0, + (unsigned long long)desc->qw1); +} + static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) { u32 fault; @@ -1216,6 +1273,8 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) return -EAGAIN; fault = readl(iommu->reg + DMAR_FSTS_REG); + if (fault & (DMA_FSTS_IQE | DMA_FSTS_ITE | DMA_FSTS_ICE)) + qi_dump_fault(iommu, fault); /* * If IQE happens, the head points to the descriptor associated @@ -1232,12 +1291,10 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) * used by software as private data. We won't print * out these two qw's for security consideration. */ - pr_err("VT-d detected invalid descriptor: qw0 = %llx, qw1 = %llx\n", - (unsigned long long)desc->qw0, - (unsigned long long)desc->qw1); memcpy(desc, qi->desc + (wait_index << shift), 1 << shift); writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG); + pr_info("Invalidation Queue Error (IQE) cleared\n"); return -EINVAL; } } @@ -1254,6 +1311,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH; writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG); + pr_info("Invalidation Time-out Error (ITE) cleared\n"); do { if (qi->desc_status[head] == QI_IN_USE) @@ -1265,8 +1323,10 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) return -EAGAIN; } - if (fault & DMA_FSTS_ICE) + if (fault & DMA_FSTS_ICE) { writel(DMA_FSTS_ICE, iommu->reg + DMAR_FSTS_REG); + pr_info("Invalidation Completion Error (ICE) cleared\n"); + } return 0; } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1db4d8934526..0e04d450c38a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -657,7 +657,14 @@ static int domain_update_iommu_snooping(struct intel_iommu *skip) rcu_read_lock(); for_each_active_iommu(iommu, drhd) { if (iommu != skip) { - if (!ecap_sc_support(iommu->ecap)) { + /* + * If the hardware is operating in the scalable mode, + * the snooping control is always supported since we + * always set PASID-table-entry.PGSNP bit if the domain + * is managed outside (UNMANAGED). + */ + if (!sm_supported(iommu) && + !ecap_sc_support(iommu->ecap)) { ret = 0; break; } @@ -1339,6 +1346,11 @@ static void iommu_set_root_entry(struct intel_iommu *iommu) readl, (sts & DMA_GSTS_RTPS), sts); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); + + iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); + if (sm_supported(iommu)) + qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0); + iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); } void iommu_flush_write_buffer(struct intel_iommu *iommu) @@ -2288,6 +2300,41 @@ static inline int hardware_largepage_caps(struct dmar_domain *domain, return level; } +/* + * Ensure that old small page tables are removed to make room for superpage(s). + * We're going to add new large pages, so make sure we don't remove their parent + * tables. The IOTLB/devTLBs should be flushed if any PDE/PTEs are cleared. + */ +static void switch_to_super_page(struct dmar_domain *domain, + unsigned long start_pfn, + unsigned long end_pfn, int level) +{ + unsigned long lvl_pages = lvl_to_nr_pages(level); + struct dma_pte *pte = NULL; + int i; + + while (start_pfn <= end_pfn) { + if (!pte) + pte = pfn_to_dma_pte(domain, start_pfn, &level); + + if (dma_pte_present(pte)) { + dma_pte_free_pagetable(domain, start_pfn, + start_pfn + lvl_pages - 1, + level + 1); + + for_each_domain_iommu(i, domain) + iommu_flush_iotlb_psi(g_iommus[i], domain, + start_pfn, lvl_pages, + 0, 0); + } + + pte++; + start_pfn += lvl_pages; + if (first_pte_in_page(pte)) + pte = NULL; + } +} + static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long phys_pfn, unsigned long nr_pages, int prot) @@ -2304,8 +2351,9 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -EINVAL; attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); + attr |= DMA_FL_PTE_PRESENT; if (domain_use_first_level(domain)) { - attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US; + attr |= DMA_FL_PTE_XD | DMA_FL_PTE_US; if (domain->domain.type == IOMMU_DOMAIN_DMA) { attr |= DMA_FL_PTE_ACCESS; @@ -2328,22 +2376,11 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -ENOMEM; /* It is large page*/ if (largepage_lvl > 1) { - unsigned long nr_superpages, end_pfn; + unsigned long end_pfn; pteval |= DMA_PTE_LARGE_PAGE; - lvl_pages = lvl_to_nr_pages(largepage_lvl); - - nr_superpages = nr_pages / lvl_pages; - end_pfn = iov_pfn + nr_superpages * lvl_pages - 1; - - /* - * Ensure that old small page tables are - * removed to make room for superpage(s). - * We're adding new large pages, so make sure - * we don't remove their parent tables. - */ - dma_pte_free_pagetable(domain, iov_pfn, end_pfn, - largepage_lvl + 1); + end_pfn = ((iov_pfn + nr_pages) & level_mask(largepage_lvl)) - 1; + switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl); } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; } @@ -2421,6 +2458,10 @@ static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn (((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); + + if (sm_supported(iommu)) + qi_flush_pasid_cache(iommu, did_old, QI_PC_ALL_PASIDS, 0); + iommu->flush.flush_iotlb(iommu, did_old, 0, @@ -2504,6 +2545,9 @@ static int domain_setup_first_level(struct intel_iommu *iommu, flags |= (level == 5) ? PASID_FLAG_FL5LP : 0; + if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED) + flags |= PASID_FLAG_PAGE_SNOOP; + return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid, domain->iommu_did[iommu->seq_id], flags); @@ -3266,8 +3310,6 @@ static int __init init_dmars(void) register_pasid_allocator(iommu); #endif iommu_set_root_entry(iommu); - iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); - iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); } #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA @@ -3457,12 +3499,7 @@ static int init_iommu_hw(void) } iommu_flush_write_buffer(iommu); - iommu_set_root_entry(iommu); - - iommu->flush.flush_context(iommu, 0, 0, 0, - DMA_CCMD_GLOBAL_INVL); - iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); iommu_enable_translation(iommu); iommu_disable_protect_mem_regions(iommu); } @@ -3845,8 +3882,6 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru) goto disable_iommu; iommu_set_root_entry(iommu); - iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); - iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); iommu_enable_translation(iommu); iommu_disable_protect_mem_regions(iommu); @@ -5365,6 +5400,9 @@ intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) if (!info) return -EINVAL; + if (!info->pasid_enabled || !info->pri_enabled || !info->ats_enabled) + return -EINVAL; + if (info->iommu->flags & VTD_FLAG_SVM_CAPABLE) return 0; } diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 611ef5243cb6..5c16ebe037a1 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -736,7 +736,7 @@ static int __init intel_prepare_irq_remapping(void) return -ENODEV; if (intel_cap_audit(CAP_AUDIT_STATIC_IRQR, NULL)) - goto error; + return -ENODEV; if (!dmar_ir_support()) return -ENODEV; diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index f26cb6195b2c..72646bafc52f 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -24,7 +24,6 @@ /* * Intel IOMMU system wide PASID name space: */ -static DEFINE_SPINLOCK(pasid_lock); u32 intel_pasid_max_id = PASID_MAX; int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid) @@ -231,7 +230,7 @@ struct pasid_table *intel_pasid_get_table(struct device *dev) return info->pasid_table; } -int intel_pasid_get_dev_max_id(struct device *dev) +static int intel_pasid_get_dev_max_id(struct device *dev) { struct device_domain_info *info; @@ -242,7 +241,7 @@ int intel_pasid_get_dev_max_id(struct device *dev) return info->pasid_table->max_pasid; } -struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) +static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) { struct device_domain_info *info; struct pasid_table *pasid_table; @@ -259,19 +258,25 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) dir_index = pasid >> PASID_PDE_SHIFT; index = pasid & PASID_PTE_MASK; - spin_lock(&pasid_lock); +retry: entries = get_pasid_table_from_pde(&dir[dir_index]); if (!entries) { entries = alloc_pgtable_page(info->iommu->node); - if (!entries) { - spin_unlock(&pasid_lock); + if (!entries) return NULL; - } - WRITE_ONCE(dir[dir_index].val, - (u64)virt_to_phys(entries) | PASID_PTE_PRESENT); + /* + * The pasid directory table entry won't be freed after + * allocation. No worry about the race with free and + * clear. However, this entry might be populated by others + * while we are preparing it. Use theirs with a retry. + */ + if (cmpxchg64(&dir[dir_index].val, 0ULL, + (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) { + free_pgtable_page(entries); + goto retry; + } } - spin_unlock(&pasid_lock); return &entries[index]; } @@ -394,6 +399,15 @@ static inline void pasid_set_sre(struct pasid_entry *pe) } /* + * Setup the WPE(Write Protect Enable) field (Bit 132) of a + * scalable mode PASID entry. + */ +static inline void pasid_set_wpe(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4); +} + +/* * Setup the P(Present) field (Bit 0) of a scalable mode PASID * entry. */ @@ -412,6 +426,16 @@ static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value) } /* + * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode + * PASID entry. + */ +static inline void +pasid_set_pgsnp(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24); +} + +/* * Setup the First Level Page table Pointer field (Bit 140~191) * of a scalable mode PASID entry. */ @@ -493,6 +517,9 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, if (WARN_ON(!pte)) return; + if (!(pte->val[0] & PASID_PTE_PRESENT)) + return; + did = pasid_get_domain_id(pte); intel_pasid_clear_entry(dev, pasid, fault_ignore); @@ -522,6 +549,22 @@ static void pasid_flush_caches(struct intel_iommu *iommu, } } +static inline int pasid_enable_wpe(struct pasid_entry *pte) +{ +#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_ratelimited("No CPU write protect!\n"); + return -EINVAL; + } +#endif + pasid_set_wpe(pte); + + return 0; +}; + /* * Set up the scalable mode pasid table entry for first only * translation type. @@ -553,6 +596,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, return -EINVAL; } pasid_set_sre(pte); + if (pasid_enable_wpe(pte)) + return -EINVAL; + } if (flags & PASID_FLAG_FL5LP) { @@ -565,6 +611,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, } } + if (flags & PASID_FLAG_PAGE_SNOOP) + pasid_set_pgsnp(pte); + pasid_set_domain_id(pte, did); pasid_set_address_width(pte, iommu->agaw); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); @@ -643,6 +692,9 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); + if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED) + pasid_set_pgsnp(pte); + /* * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). @@ -706,6 +758,9 @@ intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte, return -EINVAL; } pasid_set_sre(pte); + /* Enable write protect WP if guest requested */ + if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_WPE) + pasid_set_wpe(pte); } if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) { diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 444c0bec221a..5ff61c3d401f 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -48,6 +48,7 @@ */ #define PASID_FLAG_SUPERVISOR_MODE BIT(0) #define PASID_FLAG_NESTED BIT(1) +#define PASID_FLAG_PAGE_SNOOP BIT(2) /* * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first- @@ -99,14 +100,9 @@ static inline bool pasid_pte_is_present(struct pasid_entry *pte) } extern unsigned int intel_pasid_max_id; -int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp); -void intel_pasid_free_id(u32 pasid); -void *intel_pasid_lookup_id(u32 pasid); int intel_pasid_alloc_table(struct device *dev); void intel_pasid_free_table(struct device *dev); struct pasid_table *intel_pasid_get_table(struct device *dev); -int intel_pasid_get_dev_max_id(struct device *dev); -struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid); int intel_pasid_setup_first_level(struct intel_iommu *iommu, struct device *dev, pgd_t *pgd, u32 pasid, u16 did, int flags); diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 574a7e657a9a..5165cea90421 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -462,13 +462,12 @@ static void load_pasid(struct mm_struct *mm, u32 pasid) /* Caller must hold pasid_mutex, mm reference */ static int intel_svm_bind_mm(struct device *dev, unsigned int flags, - struct svm_dev_ops *ops, struct mm_struct *mm, struct intel_svm_dev **sd) { struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); + struct intel_svm *svm = NULL, *t; struct device_domain_info *info; struct intel_svm_dev *sdev; - struct intel_svm *svm = NULL; unsigned long iflags; int pasid_max; int ret; @@ -494,34 +493,26 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags, } } - if (!(flags & SVM_FLAG_PRIVATE_PASID)) { - struct intel_svm *t; - - list_for_each_entry(t, &global_svm_list, list) { - if (t->mm != mm || (t->flags & SVM_FLAG_PRIVATE_PASID)) - continue; - - svm = t; - if (svm->pasid >= pasid_max) { - dev_warn(dev, - "Limited PASID width. Cannot use existing PASID %d\n", - svm->pasid); - ret = -ENOSPC; - goto out; - } + list_for_each_entry(t, &global_svm_list, list) { + if (t->mm != mm) + continue; - /* Find the matching device in svm list */ - for_each_svm_dev(sdev, svm, dev) { - if (sdev->ops != ops) { - ret = -EBUSY; - goto out; - } - sdev->users++; - goto success; - } + svm = t; + if (svm->pasid >= pasid_max) { + dev_warn(dev, + "Limited PASID width. Cannot use existing PASID %d\n", + svm->pasid); + ret = -ENOSPC; + goto out; + } - break; + /* Find the matching device in svm list */ + for_each_svm_dev(sdev, svm, dev) { + sdev->users++; + goto success; } + + break; } sdev = kzalloc(sizeof(*sdev), GFP_KERNEL); @@ -550,7 +541,6 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags, /* Finish the setup now we know we're keeping it */ sdev->users = 1; - sdev->ops = ops; init_rcu_head(&sdev->rcu); if (!svm) { @@ -862,7 +852,7 @@ intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc) /* Fill in event data for device specific processing */ memset(&event, 0, sizeof(struct iommu_fault_event)); event.fault.type = IOMMU_FAULT_PAGE_REQ; - event.fault.prm.addr = desc->addr; + event.fault.prm.addr = (u64)desc->addr << VTD_PAGE_SHIFT; event.fault.prm.pasid = desc->pasid; event.fault.prm.grpid = desc->prg_index; event.fault.prm.perm = prq_to_iommu_prot(desc); @@ -895,6 +885,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_iommu *iommu = d; struct intel_svm *svm = NULL; int head, tail, handled = 0; + unsigned int flags = 0; /* Clear PPR bit before reading head/tail registers, to * ensure that we get a new interrupt if needed. */ @@ -920,7 +911,17 @@ static irqreturn_t prq_event_thread(int irq, void *d) ((unsigned long long *)req)[1]); goto no_pasid; } - + /* We shall not receive page request for supervisor SVM */ + if (req->pm_req && (req->rd_req | req->wr_req)) { + pr_err("Unexpected page request in Privilege Mode"); + /* No need to find the matching sdev as for bad_req */ + goto no_pasid; + } + /* DMA read with exec requeset is not supported. */ + if (req->exe_req && req->rd_req) { + pr_err("Execution request not supported\n"); + goto no_pasid; + } if (!svm || svm->pasid != req->pasid) { rcu_read_lock(); svm = ioasid_find(NULL, req->pasid, NULL); @@ -982,9 +983,11 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (access_error(vma, req)) goto invalid; - ret = handle_mm_fault(vma, address, - req->wr_req ? FAULT_FLAG_WRITE : 0, - NULL); + flags = FAULT_FLAG_USER | FAULT_FLAG_REMOTE; + if (req->wr_req) + flags |= FAULT_FLAG_WRITE; + + ret = handle_mm_fault(vma, address, flags, NULL); if (ret & VM_FAULT_ERROR) goto invalid; @@ -993,13 +996,6 @@ invalid: mmap_read_unlock(svm->mm); mmput(svm->mm); bad_req: - WARN_ON(!sdev); - if (sdev && sdev->ops && sdev->ops->fault_cb) { - int rwxp = (req->rd_req << 3) | (req->wr_req << 2) | - (req->exe_req << 1) | (req->pm_req); - sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr, - req->priv_data, rwxp, result); - } /* We get here in the error case where the PASID lookup failed, and these can be NULL. Do not use them below this point! */ sdev = NULL; @@ -1021,12 +1017,12 @@ no_pasid: QI_PGRP_RESP_TYPE; resp.qw1 = QI_PGRP_IDX(req->prg_index) | QI_PGRP_LPIG(req->lpig); + resp.qw2 = 0; + resp.qw3 = 0; if (req->priv_data_present) memcpy(&resp.qw2, req->priv_data, sizeof(req->priv_data)); - resp.qw2 = 0; - resp.qw3 = 0; qi_submit_sync(iommu, &resp, 1, 0); } prq_advance: @@ -1074,7 +1070,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata) if (drvdata) flags = *(unsigned int *)drvdata; mutex_lock(&pasid_mutex); - ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev); + ret = intel_svm_bind_mm(dev, flags, mm, &sdev); if (ret) sva = ERR_PTR(ret); else if (sdev) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 6ecc007f07cd..cdda3a85fc08 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -17,6 +17,7 @@ #include <linux/iopoll.h> #include <linux/list.h> #include <linux/mfd/syscon.h> +#include <linux/module.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_irq.h> @@ -683,18 +684,12 @@ static const struct iommu_ops mtk_iommu_ops = { .get_resv_regions = mtk_iommu_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, .pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M, + .owner = THIS_MODULE, }; static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) { u32 regval; - int ret; - - ret = clk_prepare_enable(data->bclk); - if (ret) { - dev_err(data->dev, "Failed to enable iommu bclk(%d)\n", ret); - return ret; - } if (data->plat_data->m4u_plat == M4U_MT8173) { regval = F_MMU_PREFETCH_RT_REPLACE_MOD | @@ -760,7 +755,6 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0, dev_name(data->dev), (void *)data)) { writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR); - clk_disable_unprepare(data->bclk); dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq); return -ENODEV; } @@ -977,14 +971,19 @@ static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev) void __iomem *base = data->base; int ret; - /* Avoid first resume to affect the default value of registers below. */ - if (!m4u_dom) - return 0; ret = clk_prepare_enable(data->bclk); if (ret) { dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret); return ret; } + + /* + * Uppon first resume, only enable the clk and return, since the values of the + * registers are not yet set. + */ + if (!m4u_dom) + return 0; + writel_relaxed(reg->wr_len_ctrl, base + REG_MMU_WR_LEN_CTRL); writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL); writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS); @@ -1079,16 +1078,7 @@ static struct platform_driver mtk_iommu_driver = { .pm = &mtk_iommu_pm_ops, } }; +module_platform_driver(mtk_iommu_driver); -static int __init mtk_iommu_init(void) -{ - int ret; - - ret = platform_driver_register(&mtk_iommu_driver); - if (ret != 0) - pr_err("Failed to register MTK IOMMU driver\n"); - - return ret; -} - -subsys_initcall(mtk_iommu_init) +MODULE_DESCRIPTION("IOMMU API for MediaTek M4U implementations"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 82ddfe9170d4..8ba9a2ec5509 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -20,6 +20,7 @@ #include <linux/iommu.h> #include <linux/iopoll.h> #include <linux/list.h> +#include <linux/module.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_irq.h> @@ -423,23 +424,21 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct of_phandle_args iommu_spec; - struct of_phandle_iterator it; struct mtk_iommu_data *data; - int err; + int err, idx = 0; - of_for_each_phandle(&it, err, dev->of_node, "iommus", - "#iommu-cells", -1) { - int count = of_phandle_iterator_args(&it, iommu_spec.args, - MAX_PHANDLE_ARGS); - iommu_spec.np = of_node_get(it.node); - iommu_spec.args_count = count; + while (!of_parse_phandle_with_args(dev->of_node, "iommus", + "#iommu-cells", + idx, &iommu_spec)) { - mtk_iommu_create_mapping(dev, &iommu_spec); + err = mtk_iommu_create_mapping(dev, &iommu_spec); + of_node_put(iommu_spec.np); + if (err) + return ERR_PTR(err); /* dev->iommu_fwspec might have changed */ fwspec = dev_iommu_fwspec_get(dev); - - of_node_put(iommu_spec.np); + idx++; } if (!fwspec || fwspec->ops != &mtk_iommu_ops) @@ -529,6 +528,7 @@ static const struct iommu_ops mtk_iommu_ops = { .def_domain_type = mtk_iommu_def_domain_type, .device_group = generic_device_group, .pgsize_bitmap = ~0UL << MT2701_IOMMU_PAGE_SHIFT, + .owner = THIS_MODULE, }; static const struct of_device_id mtk_iommu_of_ids[] = { @@ -547,10 +547,8 @@ static int mtk_iommu_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct resource *res; struct component_match *match = NULL; - struct of_phandle_args larb_spec; - struct of_phandle_iterator it; void *protect; - int larb_nr, ret, err; + int larb_nr, ret, i; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) @@ -578,35 +576,33 @@ static int mtk_iommu_probe(struct platform_device *pdev) if (IS_ERR(data->bclk)) return PTR_ERR(data->bclk); - larb_nr = 0; - of_for_each_phandle(&it, err, dev->of_node, - "mediatek,larbs", NULL, 0) { + larb_nr = of_count_phandle_with_args(dev->of_node, + "mediatek,larbs", NULL); + if (larb_nr < 0) + return larb_nr; + + for (i = 0; i < larb_nr; i++) { + struct device_node *larbnode; struct platform_device *plarbdev; - int count = of_phandle_iterator_args(&it, larb_spec.args, - MAX_PHANDLE_ARGS); - if (count) - continue; + larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i); + if (!larbnode) + return -EINVAL; - larb_spec.np = of_node_get(it.node); - if (!of_device_is_available(larb_spec.np)) + if (!of_device_is_available(larbnode)) { + of_node_put(larbnode); continue; + } - plarbdev = of_find_device_by_node(larb_spec.np); + plarbdev = of_find_device_by_node(larbnode); if (!plarbdev) { - plarbdev = of_platform_device_create( - larb_spec.np, NULL, - platform_bus_type.dev_root); - if (!plarbdev) { - of_node_put(larb_spec.np); - return -EPROBE_DEFER; - } + of_node_put(larbnode); + return -EPROBE_DEFER; } + data->larb_imu[i].dev = &plarbdev->dev; - data->larb_imu[larb_nr].dev = &plarbdev->dev; component_match_add_release(dev, &match, release_of, - compare_of, larb_spec.np); - larb_nr++; + compare_of, larbnode); } platform_set_drvdata(pdev, data); @@ -624,12 +620,26 @@ static int mtk_iommu_probe(struct platform_device *pdev) ret = iommu_device_register(&data->iommu); if (ret) - return ret; + goto out_sysfs_remove; - if (!iommu_present(&platform_bus_type)) - bus_set_iommu(&platform_bus_type, &mtk_iommu_ops); + if (!iommu_present(&platform_bus_type)) { + ret = bus_set_iommu(&platform_bus_type, &mtk_iommu_ops); + if (ret) + goto out_dev_unreg; + } + + ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match); + if (ret) + goto out_bus_set_null; + return ret; - return component_master_add_with_match(dev, &mtk_iommu_com_ops, match); +out_bus_set_null: + bus_set_iommu(&platform_bus_type, NULL); +out_dev_unreg: + iommu_device_unregister(&data->iommu); +out_sysfs_remove: + iommu_device_sysfs_remove(&data->iommu); + return ret; } static int mtk_iommu_remove(struct platform_device *pdev) @@ -691,9 +701,7 @@ static struct platform_driver mtk_iommu_driver = { .pm = &mtk_iommu_pm_ops, } }; +module_platform_driver(mtk_iommu_driver); -static int __init m4u_init(void) -{ - return platform_driver_register(&mtk_iommu_driver); -} -subsys_initcall(m4u_init); +MODULE_DESCRIPTION("IOMMU API for MediaTek M4U v1 implementations"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c new file mode 100644 index 000000000000..3811a5085b50 --- /dev/null +++ b/drivers/iommu/sprd-iommu.c @@ -0,0 +1,577 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Unisoc IOMMU driver + * + * Copyright (C) 2020 Unisoc, Inc. + * Author: Chunyan Zhang <chunyan.zhang@unisoc.com> + */ + +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/dma-iommu.h> +#include <linux/dma-mapping.h> +#include <linux/errno.h> +#include <linux/iommu.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/regmap.h> +#include <linux/slab.h> + +#define SPRD_IOMMU_PAGE_SHIFT 12 +#define SPRD_IOMMU_PAGE_SIZE SZ_4K + +#define SPRD_EX_CFG 0x0 +#define SPRD_IOMMU_VAOR_BYPASS BIT(4) +#define SPRD_IOMMU_GATE_EN BIT(1) +#define SPRD_IOMMU_EN BIT(0) +#define SPRD_EX_UPDATE 0x4 +#define SPRD_EX_FIRST_VPN 0x8 +#define SPRD_EX_VPN_RANGE 0xc +#define SPRD_EX_FIRST_PPN 0x10 +#define SPRD_EX_DEFAULT_PPN 0x14 + +#define SPRD_IOMMU_VERSION 0x0 +#define SPRD_VERSION_MASK GENMASK(15, 8) +#define SPRD_VERSION_SHIFT 0x8 +#define SPRD_VAU_CFG 0x4 +#define SPRD_VAU_UPDATE 0x8 +#define SPRD_VAU_AUTH_CFG 0xc +#define SPRD_VAU_FIRST_PPN 0x10 +#define SPRD_VAU_DEFAULT_PPN_RD 0x14 +#define SPRD_VAU_DEFAULT_PPN_WR 0x18 +#define SPRD_VAU_FIRST_VPN 0x1c +#define SPRD_VAU_VPN_RANGE 0x20 + +enum sprd_iommu_version { + SPRD_IOMMU_EX, + SPRD_IOMMU_VAU, +}; + +/* + * struct sprd_iommu_device - high-level sprd IOMMU device representation, + * including hardware information and configuration, also driver data, etc + * + * @ver: sprd IOMMU IP version + * @prot_page_va: protect page base virtual address + * @prot_page_pa: protect page base physical address, data would be + * written to here while translation fault + * @base: mapped base address for accessing registers + * @dev: pointer to basic device structure + * @iommu: IOMMU core representation + * @group: IOMMU group + * @eb: gate clock which controls IOMMU access + */ +struct sprd_iommu_device { + enum sprd_iommu_version ver; + u32 *prot_page_va; + dma_addr_t prot_page_pa; + void __iomem *base; + struct device *dev; + struct iommu_device iommu; + struct iommu_group *group; + struct clk *eb; +}; + +struct sprd_iommu_domain { + spinlock_t pgtlock; /* lock for page table */ + struct iommu_domain domain; + u32 *pgt_va; /* page table virtual address base */ + dma_addr_t pgt_pa; /* page table physical address base */ + struct sprd_iommu_device *sdev; +}; + +static const struct iommu_ops sprd_iommu_ops; + +static struct sprd_iommu_domain *to_sprd_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct sprd_iommu_domain, domain); +} + +static inline void +sprd_iommu_write(struct sprd_iommu_device *sdev, unsigned int reg, u32 val) +{ + writel_relaxed(val, sdev->base + reg); +} + +static inline u32 +sprd_iommu_read(struct sprd_iommu_device *sdev, unsigned int reg) +{ + return readl_relaxed(sdev->base + reg); +} + +static inline void +sprd_iommu_update_bits(struct sprd_iommu_device *sdev, unsigned int reg, + u32 mask, u32 shift, u32 val) +{ + u32 t = sprd_iommu_read(sdev, reg); + + t = (t & (~(mask << shift))) | ((val & mask) << shift); + sprd_iommu_write(sdev, reg, t); +} + +static inline int +sprd_iommu_get_version(struct sprd_iommu_device *sdev) +{ + int ver = (sprd_iommu_read(sdev, SPRD_IOMMU_VERSION) & + SPRD_VERSION_MASK) >> SPRD_VERSION_SHIFT; + + switch (ver) { + case SPRD_IOMMU_EX: + case SPRD_IOMMU_VAU: + return ver; + default: + return -EINVAL; + } +} + +static size_t +sprd_iommu_pgt_size(struct iommu_domain *domain) +{ + return ((domain->geometry.aperture_end - + domain->geometry.aperture_start + 1) >> + SPRD_IOMMU_PAGE_SHIFT) * sizeof(u32); +} + +static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) +{ + struct sprd_iommu_domain *dom; + + if (domain_type != IOMMU_DOMAIN_DMA && domain_type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + dom = kzalloc(sizeof(*dom), GFP_KERNEL); + if (!dom) + return NULL; + + if (iommu_get_dma_cookie(&dom->domain)) { + kfree(dom); + return NULL; + } + + spin_lock_init(&dom->pgtlock); + + dom->domain.geometry.aperture_start = 0; + dom->domain.geometry.aperture_end = SZ_256M - 1; + + return &dom->domain; +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + iommu_put_dma_cookie(domain); + kfree(dom); +} + +static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) +{ + struct sprd_iommu_device *sdev = dom->sdev; + u32 val; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_FIRST_VPN; + else + reg = SPRD_VAU_FIRST_VPN; + + val = dom->domain.geometry.aperture_start >> SPRD_IOMMU_PAGE_SHIFT; + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_vpn_range(struct sprd_iommu_domain *dom) +{ + struct sprd_iommu_device *sdev = dom->sdev; + u32 val; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_VPN_RANGE; + else + reg = SPRD_VAU_VPN_RANGE; + + val = (dom->domain.geometry.aperture_end - + dom->domain.geometry.aperture_start) >> SPRD_IOMMU_PAGE_SHIFT; + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_first_ppn(struct sprd_iommu_domain *dom) +{ + u32 val = dom->pgt_pa >> SPRD_IOMMU_PAGE_SHIFT; + struct sprd_iommu_device *sdev = dom->sdev; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_FIRST_PPN; + else + reg = SPRD_VAU_FIRST_PPN; + + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_default_ppn(struct sprd_iommu_device *sdev) +{ + u32 val = sdev->prot_page_pa >> SPRD_IOMMU_PAGE_SHIFT; + + if (sdev->ver == SPRD_IOMMU_EX) { + sprd_iommu_write(sdev, SPRD_EX_DEFAULT_PPN, val); + } else if (sdev->ver == SPRD_IOMMU_VAU) { + sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_RD, val); + sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_WR, val); + } +} + +static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) +{ + unsigned int reg_cfg; + u32 mask, val; + + if (sdev->ver == SPRD_IOMMU_EX) + reg_cfg = SPRD_EX_CFG; + else + reg_cfg = SPRD_VAU_CFG; + + mask = SPRD_IOMMU_EN | SPRD_IOMMU_GATE_EN; + val = en ? mask : 0; + sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); +} + +static int sprd_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev); + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + size_t pgt_size = sprd_iommu_pgt_size(domain); + + if (dom->sdev) { + pr_err("There's already a device attached to this domain.\n"); + return -EINVAL; + } + + dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); + if (!dom->pgt_va) + return -ENOMEM; + + dom->sdev = sdev; + + sprd_iommu_first_ppn(dom); + sprd_iommu_first_vpn(dom); + sprd_iommu_vpn_range(dom); + sprd_iommu_default_ppn(sdev); + sprd_iommu_hw_en(sdev, true); + + return 0; +} + +static void sprd_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + struct sprd_iommu_device *sdev = dom->sdev; + size_t pgt_size = sprd_iommu_pgt_size(domain); + + if (!sdev) + return; + + dma_free_coherent(sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + sprd_iommu_hw_en(sdev, false); + dom->sdev = NULL; +} + +static int sprd_iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned int page_num = size >> SPRD_IOMMU_PAGE_SHIFT; + unsigned long flags; + unsigned int i; + u32 *pgt_base_iova; + u32 pabase = (u32)paddr; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (!dom->sdev) { + pr_err("No sprd_iommu_device attached to the domain\n"); + return -EINVAL; + } + + if (iova < start || (iova + size) > (end + 1)) { + dev_err(dom->sdev->dev, "(iova(0x%lx) + size(%zx)) are not in the range!\n", + iova, size); + return -EINVAL; + } + + pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT); + + spin_lock_irqsave(&dom->pgtlock, flags); + for (i = 0; i < page_num; i++) { + pgt_base_iova[i] = pabase >> SPRD_IOMMU_PAGE_SHIFT; + pabase += SPRD_IOMMU_PAGE_SIZE; + } + spin_unlock_irqrestore(&dom->pgtlock, flags); + + return 0; +} + +static size_t sprd_iommu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *iotlb_gather) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned long flags; + u32 *pgt_base_iova; + unsigned int page_num = size >> SPRD_IOMMU_PAGE_SHIFT; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (iova < start || (iova + size) > (end + 1)) + return -EINVAL; + + pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT); + + spin_lock_irqsave(&dom->pgtlock, flags); + memset(pgt_base_iova, 0, page_num * sizeof(u32)); + spin_unlock_irqrestore(&dom->pgtlock, flags); + + return 0; +} + +static void sprd_iommu_sync_map(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned int reg; + + if (dom->sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_UPDATE; + else + reg = SPRD_VAU_UPDATE; + + /* clear IOMMU TLB buffer after page table updated */ + sprd_iommu_write(dom->sdev, reg, 0xffffffff); +} + +static void sprd_iommu_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather) +{ + sprd_iommu_sync_map(domain, 0, 0); +} + +static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned long flags; + phys_addr_t pa; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (WARN_ON(iova < start || iova > end)) + return 0; + + spin_lock_irqsave(&dom->pgtlock, flags); + pa = *(dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT)); + pa = (pa << SPRD_IOMMU_PAGE_SHIFT) + ((iova - start) & (SPRD_IOMMU_PAGE_SIZE - 1)); + spin_unlock_irqrestore(&dom->pgtlock, flags); + + return pa; +} + +static struct iommu_device *sprd_iommu_probe_device(struct device *dev) +{ + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct sprd_iommu_device *sdev; + + if (!fwspec || fwspec->ops != &sprd_iommu_ops) + return ERR_PTR(-ENODEV); + + sdev = dev_iommu_priv_get(dev); + + return &sdev->iommu; +} + +static void sprd_iommu_release_device(struct device *dev) +{ + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + + if (!fwspec || fwspec->ops != &sprd_iommu_ops) + return; + + iommu_fwspec_free(dev); +} + +static struct iommu_group *sprd_iommu_device_group(struct device *dev) +{ + struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev); + + return iommu_group_ref_get(sdev->group); +} + +static int sprd_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) +{ + struct platform_device *pdev; + + if (!dev_iommu_priv_get(dev)) { + pdev = of_find_device_by_node(args->np); + dev_iommu_priv_set(dev, platform_get_drvdata(pdev)); + platform_device_put(pdev); + } + + return 0; +} + + +static const struct iommu_ops sprd_iommu_ops = { + .domain_alloc = sprd_iommu_domain_alloc, + .domain_free = sprd_iommu_domain_free, + .attach_dev = sprd_iommu_attach_device, + .detach_dev = sprd_iommu_detach_device, + .map = sprd_iommu_map, + .unmap = sprd_iommu_unmap, + .iotlb_sync_map = sprd_iommu_sync_map, + .iotlb_sync = sprd_iommu_sync, + .iova_to_phys = sprd_iommu_iova_to_phys, + .probe_device = sprd_iommu_probe_device, + .release_device = sprd_iommu_release_device, + .device_group = sprd_iommu_device_group, + .of_xlate = sprd_iommu_of_xlate, + .pgsize_bitmap = ~0UL << SPRD_IOMMU_PAGE_SHIFT, +}; + +static const struct of_device_id sprd_iommu_of_match[] = { + { .compatible = "sprd,iommu-v1" }, + { }, +}; +MODULE_DEVICE_TABLE(of, sprd_iommu_of_match); + +/* + * Clock is not required, access to some of IOMMUs is controlled by gate + * clk, enabled clocks for that kind of IOMMUs before accessing. + * Return 0 for success or no clocks found. + */ +static int sprd_iommu_clk_enable(struct sprd_iommu_device *sdev) +{ + struct clk *eb; + + eb = devm_clk_get_optional(sdev->dev, NULL); + if (!eb) + return 0; + + if (IS_ERR(eb)) + return PTR_ERR(eb); + + sdev->eb = eb; + return clk_prepare_enable(eb); +} + +static void sprd_iommu_clk_disable(struct sprd_iommu_device *sdev) +{ + if (sdev->eb) + clk_disable_unprepare(sdev->eb); +} + +static int sprd_iommu_probe(struct platform_device *pdev) +{ + struct sprd_iommu_device *sdev; + struct device *dev = &pdev->dev; + void __iomem *base; + int ret; + + sdev = devm_kzalloc(dev, sizeof(*sdev), GFP_KERNEL); + if (!sdev) + return -ENOMEM; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) { + dev_err(dev, "Failed to get ioremap resource.\n"); + return PTR_ERR(base); + } + sdev->base = base; + + sdev->prot_page_va = dma_alloc_coherent(dev, SPRD_IOMMU_PAGE_SIZE, + &sdev->prot_page_pa, GFP_KERNEL); + if (!sdev->prot_page_va) + return -ENOMEM; + + platform_set_drvdata(pdev, sdev); + sdev->dev = dev; + + /* All the client devices are in the same iommu-group */ + sdev->group = iommu_group_alloc(); + if (IS_ERR(sdev->group)) { + ret = PTR_ERR(sdev->group); + goto free_page; + } + + ret = iommu_device_sysfs_add(&sdev->iommu, dev, NULL, dev_name(dev)); + if (ret) + goto put_group; + + iommu_device_set_ops(&sdev->iommu, &sprd_iommu_ops); + iommu_device_set_fwnode(&sdev->iommu, &dev->of_node->fwnode); + + ret = iommu_device_register(&sdev->iommu); + if (ret) + goto remove_sysfs; + + if (!iommu_present(&platform_bus_type)) + bus_set_iommu(&platform_bus_type, &sprd_iommu_ops); + + ret = sprd_iommu_clk_enable(sdev); + if (ret) + goto unregister_iommu; + + ret = sprd_iommu_get_version(sdev); + if (ret < 0) { + dev_err(dev, "IOMMU version(%d) is invalid.\n", ret); + goto disable_clk; + } + sdev->ver = ret; + + return 0; + +disable_clk: + sprd_iommu_clk_disable(sdev); +unregister_iommu: + iommu_device_unregister(&sdev->iommu); +remove_sysfs: + iommu_device_sysfs_remove(&sdev->iommu); +put_group: + iommu_group_put(sdev->group); +free_page: + dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa); + return ret; +} + +static int sprd_iommu_remove(struct platform_device *pdev) +{ + struct sprd_iommu_device *sdev = platform_get_drvdata(pdev); + + dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa); + + iommu_group_put(sdev->group); + sdev->group = NULL; + + bus_set_iommu(&platform_bus_type, NULL); + + 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 = { + .driver = { + .name = "sprd-iommu", + .of_match_table = sprd_iommu_of_match, + .suppress_bind_attrs = true, + }, + .probe = sprd_iommu_probe, + .remove = sprd_iommu_remove, +}; +module_platform_driver(sprd_iommu_driver); + +MODULE_DESCRIPTION("IOMMU driver for Unisoc SoCs"); +MODULE_ALIAS("platform:sprd-iommu"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 97eb62f667d2..602aab98c079 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -849,12 +849,11 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) smmu = tegra_smmu_find(args.np); if (smmu) { err = tegra_smmu_configure(smmu, dev, &args); - of_node_put(args.np); - if (err < 0) + if (err < 0) { + of_node_put(args.np); return ERR_PTR(err); - - break; + } } of_node_put(args.np); |