diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 25 | ||||
-rw-r--r-- | drivers/iommu/Makefile | 2 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.c | 3 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_v2.c | 8 | ||||
-rw-r--r-- | drivers/iommu/arm-smmu.c | 134 | ||||
-rw-r--r-- | drivers/iommu/exynos-iommu.c | 1 | ||||
-rw-r--r-- | drivers/iommu/intel-iommu.c | 1 | ||||
-rw-r--r-- | drivers/iommu/iommu.c | 60 | ||||
-rw-r--r-- | drivers/iommu/ipmmu-vmsa.c | 3 | ||||
-rw-r--r-- | drivers/iommu/msm_iommu.c | 4 | ||||
-rw-r--r-- | drivers/iommu/msm_iommu_dev.c | 10 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu-debug.c | 242 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu.c | 313 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu.h | 98 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu2.c | 337 | ||||
-rw-r--r-- | drivers/iommu/rockchip-iommu.c | 1038 | ||||
-rw-r--r-- | drivers/iommu/shmobile-iommu.c | 1 | ||||
-rw-r--r-- | drivers/iommu/tegra-smmu.c | 1 |
18 files changed, 1553 insertions, 728 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index dd5112265cc9..22f15f9951e7 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -144,13 +144,26 @@ config OMAP_IOMMU select IOMMU_API config OMAP_IOMMU_DEBUG - tristate "Export OMAP IOMMU internals in DebugFS" - depends on OMAP_IOMMU && DEBUG_FS - help - Select this to see extensive information about - the internal state of OMAP IOMMU in debugfs. + bool "Export OMAP IOMMU internals in DebugFS" + depends on OMAP_IOMMU && DEBUG_FS + ---help--- + Select this to see extensive information about + the internal state of OMAP IOMMU in debugfs. + + Say N unless you know you need this. - Say N unless you know you need this. +config ROCKCHIP_IOMMU + bool "Rockchip IOMMU Support" + depends on ARM + depends on ARCH_ROCKCHIP || COMPILE_TEST + select IOMMU_API + select ARM_DMA_USE_IOMMU + help + Support for IOMMUs found on Rockchip rk32xx SOCs. + These IOMMUs allow virtualization of the address space used by most + cores within the multimedia subsystem. + Say Y here if you are using a Rockchip SoC that includes an IOMMU + device. config TEGRA_IOMMU_GART bool "Tegra GART IOMMU Support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 16edef74b8ee..7b976f294a69 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -11,8 +11,8 @@ obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o -obj-$(CONFIG_OMAP_IOMMU) += omap-iommu2.o obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o +obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 505a9adac2d5..b205f76d7129 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3411,6 +3411,8 @@ static bool amd_iommu_capable(enum iommu_cap cap) return true; case IOMMU_CAP_INTR_REMAP: return (irq_remapping_enabled == 1); + case IOMMU_CAP_NOEXEC: + return false; } return false; @@ -3424,6 +3426,7 @@ static const struct iommu_ops amd_iommu_ops = { .detach_dev = amd_iommu_detach_device, .map = amd_iommu_map, .unmap = amd_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = amd_iommu_iova_to_phys, .pgsize_bitmap = AMD_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 90d734bbf467..a2d87a60c27f 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -279,10 +279,8 @@ static void free_pasid_state(struct pasid_state *pasid_state) static void put_pasid_state(struct pasid_state *pasid_state) { - if (atomic_dec_and_test(&pasid_state->count)) { - put_device_state(pasid_state->device_state); + if (atomic_dec_and_test(&pasid_state->count)) wake_up(&pasid_state->wq); - } } static void put_pasid_state_wait(struct pasid_state *pasid_state) @@ -291,9 +289,7 @@ static void put_pasid_state_wait(struct pasid_state *pasid_state) prepare_to_wait(&pasid_state->wq, &wait, TASK_UNINTERRUPTIBLE); - if (atomic_dec_and_test(&pasid_state->count)) - put_device_state(pasid_state->device_state); - else + if (!atomic_dec_and_test(&pasid_state->count)) schedule(); finish_wait(&pasid_state->wq, &wait); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 60558f794922..b8aac1389a96 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -404,9 +404,16 @@ struct arm_smmu_cfg { #define ARM_SMMU_CB_ASID(cfg) ((cfg)->cbndx) #define ARM_SMMU_CB_VMID(cfg) ((cfg)->cbndx + 1) +enum arm_smmu_domain_stage { + ARM_SMMU_DOMAIN_S1 = 0, + ARM_SMMU_DOMAIN_S2, + ARM_SMMU_DOMAIN_NESTED, +}; + struct arm_smmu_domain { struct arm_smmu_device *smmu; struct arm_smmu_cfg cfg; + enum arm_smmu_domain_stage stage; spinlock_t lock; }; @@ -906,19 +913,46 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, if (smmu_domain->smmu) goto out_unlock; - if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) { + /* + * Mapping the requested stage onto what we support is surprisingly + * complicated, mainly because the spec allows S1+S2 SMMUs without + * support for nested translation. That means we end up with the + * following table: + * + * Requested Supported Actual + * S1 N S1 + * S1 S1+S2 S1 + * S1 S2 S2 + * S1 S1 S1 + * N N N + * N S1+S2 S2 + * N S2 S2 + * N S1 S1 + * + * Note that you can't actually request stage-2 mappings. + */ + if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1)) + smmu_domain->stage = ARM_SMMU_DOMAIN_S2; + if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2)) + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + + switch (smmu_domain->stage) { + case ARM_SMMU_DOMAIN_S1: + cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS; + start = smmu->num_s2_context_banks; + break; + case ARM_SMMU_DOMAIN_NESTED: /* * We will likely want to change this if/when KVM gets * involved. */ - cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS; - start = smmu->num_s2_context_banks; - } else if (smmu->features & ARM_SMMU_FEAT_TRANS_S1) { - cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS; - start = smmu->num_s2_context_banks; - } else { + case ARM_SMMU_DOMAIN_S2: cfg->cbar = CBAR_TYPE_S2_TRANS; start = 0; + break; + default: + ret = -EINVAL; + goto out_unlock; } ret = __arm_smmu_alloc_bitmap(smmu->context_map, start, @@ -1281,7 +1315,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, unsigned long pfn, int prot, int stage) { pte_t *pte, *start; - pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF | ARM_SMMU_PTE_XN; + pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF; if (pmd_none(*pmd)) { /* Allocate a new set of tables */ @@ -1315,10 +1349,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, pteval |= ARM_SMMU_PTE_MEMATTR_NC; } + if (prot & IOMMU_NOEXEC) + pteval |= ARM_SMMU_PTE_XN; + /* If no access, create a faulting entry to avoid TLB fills */ - if (prot & IOMMU_EXEC) - pteval &= ~ARM_SMMU_PTE_XN; - else if (!(prot & (IOMMU_READ | IOMMU_WRITE))) + if (!(prot & (IOMMU_READ | IOMMU_WRITE))) pteval &= ~ARM_SMMU_PTE_PAGE; pteval |= ARM_SMMU_PTE_SH_IS; @@ -1568,6 +1603,8 @@ static bool arm_smmu_capable(enum iommu_cap cap) return true; case IOMMU_CAP_INTR_REMAP: return true; /* MSIs are just memory writes */ + case IOMMU_CAP_NOEXEC: + return true; default: return false; } @@ -1644,20 +1681,57 @@ static void arm_smmu_remove_device(struct device *dev) iommu_group_remove_device(dev); } +static int arm_smmu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + struct arm_smmu_domain *smmu_domain = domain->priv; + + switch (attr) { + case DOMAIN_ATTR_NESTING: + *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED); + return 0; + default: + return -ENODEV; + } +} + +static int arm_smmu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + struct arm_smmu_domain *smmu_domain = domain->priv; + + switch (attr) { + case DOMAIN_ATTR_NESTING: + if (smmu_domain->smmu) + return -EPERM; + if (*(int *)data) + smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; + else + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + + return 0; + default: + return -ENODEV; + } +} + static const struct iommu_ops arm_smmu_ops = { - .capable = arm_smmu_capable, - .domain_init = arm_smmu_domain_init, - .domain_destroy = arm_smmu_domain_destroy, - .attach_dev = arm_smmu_attach_dev, - .detach_dev = arm_smmu_detach_dev, - .map = arm_smmu_map, - .unmap = arm_smmu_unmap, - .iova_to_phys = arm_smmu_iova_to_phys, - .add_device = arm_smmu_add_device, - .remove_device = arm_smmu_remove_device, - .pgsize_bitmap = (SECTION_SIZE | - ARM_SMMU_PTE_CONT_SIZE | - PAGE_SIZE), + .capable = arm_smmu_capable, + .domain_init = arm_smmu_domain_init, + .domain_destroy = arm_smmu_domain_destroy, + .attach_dev = arm_smmu_attach_dev, + .detach_dev = arm_smmu_detach_dev, + .map = arm_smmu_map, + .unmap = arm_smmu_unmap, + .map_sg = default_iommu_map_sg, + .iova_to_phys = arm_smmu_iova_to_phys, + .add_device = arm_smmu_add_device, + .remove_device = arm_smmu_remove_device, + .domain_get_attr = arm_smmu_domain_get_attr, + .domain_set_attr = arm_smmu_domain_set_attr, + .pgsize_bitmap = (SECTION_SIZE | + ARM_SMMU_PTE_CONT_SIZE | + PAGE_SIZE), }; static void arm_smmu_device_reset(struct arm_smmu_device *smmu) @@ -2072,8 +2146,20 @@ static struct platform_driver arm_smmu_driver = { static int __init arm_smmu_init(void) { + struct device_node *np; int ret; + /* + * Play nice with systems that don't have an ARM SMMU by checking that + * an ARM SMMU exists in the system before proceeding with the driver + * and IOMMU bus operation registration. + */ + np = of_find_matching_node(NULL, arm_smmu_of_match); + if (!np) + return 0; + + of_node_put(np); + ret = platform_driver_register(&arm_smmu_driver); if (ret) return ret; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 74233186f6f7..28372b85d8da 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1178,6 +1178,7 @@ static const struct iommu_ops exynos_iommu_ops = { .detach_dev = exynos_iommu_detach_device, .map = exynos_iommu_map, .unmap = exynos_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = exynos_iommu_iova_to_phys, .add_device = exynos_iommu_add_device, .remove_device = exynos_iommu_remove_device, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index fe6830af6cfa..1232336b960e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4628,6 +4628,7 @@ static const struct iommu_ops intel_iommu_ops = { .detach_dev = intel_iommu_detach_device, .map = intel_iommu_map, .unmap = intel_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = intel_iommu_iova_to_phys, .add_device = intel_iommu_add_device, .remove_device = intel_iommu_remove_device, diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index ed8b04867b1f..1bd63352ab17 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -818,7 +818,15 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) kfree(nb); return err; } - return bus_for_each_dev(bus, NULL, &cb, add_iommu_group); + + err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group); + if (err) { + bus_unregister_notifier(bus, nb); + kfree(nb); + return err; + } + + return 0; } /** @@ -836,13 +844,19 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) */ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops) { + int err; + if (bus->iommu_ops != NULL) return -EBUSY; bus->iommu_ops = ops; /* Do IOMMU specific setup for this bus-type */ - return iommu_bus_init(bus, ops); + err = iommu_bus_init(bus, ops); + if (err) + bus->iommu_ops = NULL; + + return err; } EXPORT_SYMBOL_GPL(bus_set_iommu); @@ -1124,6 +1138,48 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) } EXPORT_SYMBOL_GPL(iommu_unmap); +size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + struct scatterlist *s; + size_t mapped = 0; + unsigned int i, min_pagesz; + int ret; + + if (unlikely(domain->ops->pgsize_bitmap == 0UL)) + return 0; + + min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); + + for_each_sg(sg, s, nents, i) { + phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset; + + /* + * We are mapping on IOMMU page boundaries, so offset within + * the page must be 0. However, the IOMMU may support pages + * smaller than PAGE_SIZE, so s->offset may still represent + * an offset of that boundary within the CPU page. + */ + if (!IS_ALIGNED(s->offset, min_pagesz)) + goto out_err; + + ret = iommu_map(domain, iova + mapped, phys, s->length, prot); + if (ret) + goto out_err; + + mapped += s->length; + } + + return mapped; + +out_err: + /* undo mappings already done */ + iommu_unmap(domain, iova, mapped); + + return 0; + +} +EXPORT_SYMBOL_GPL(default_iommu_map_sg); int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 7dab5cbcc775..99effbb17191 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1127,6 +1127,7 @@ static const struct iommu_ops ipmmu_ops = { .detach_dev = ipmmu_detach_device, .map = ipmmu_map, .unmap = ipmmu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = ipmmu_iova_to_phys, .add_device = ipmmu_add_device, .remove_device = ipmmu_remove_device, @@ -1184,7 +1185,7 @@ static int ipmmu_probe(struct platform_device *pdev) dev_name(&pdev->dev), mmu); if (ret < 0) { dev_err(&pdev->dev, "failed to request IRQ %d\n", irq); - return irq; + return ret; } ipmmu_device_reset(mmu); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 6e3dcc289d59..e1b05379ca0e 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -73,8 +73,7 @@ fail: static void __disable_clocks(struct msm_iommu_drvdata *drvdata) { - if (drvdata->clk) - clk_disable(drvdata->clk); + clk_disable(drvdata->clk); clk_disable(drvdata->pclk); } @@ -681,6 +680,7 @@ static const struct iommu_ops msm_iommu_ops = { .detach_dev = msm_iommu_detach_dev, .map = msm_iommu_map, .unmap = msm_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = msm_iommu_iova_to_phys, .pgsize_bitmap = MSM_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c index 61def7cb5263..b6d01f97e537 100644 --- a/drivers/iommu/msm_iommu_dev.c +++ b/drivers/iommu/msm_iommu_dev.c @@ -131,7 +131,7 @@ static int msm_iommu_probe(struct platform_device *pdev) struct clk *iommu_clk; struct clk *iommu_pclk; struct msm_iommu_drvdata *drvdata; - struct msm_iommu_dev *iommu_dev = pdev->dev.platform_data; + struct msm_iommu_dev *iommu_dev = dev_get_platdata(&pdev->dev); void __iomem *regs_base; int ret, irq, par; @@ -224,8 +224,7 @@ static int msm_iommu_probe(struct platform_device *pdev) platform_set_drvdata(pdev, drvdata); - if (iommu_clk) - clk_disable(iommu_clk); + clk_disable(iommu_clk); clk_disable(iommu_pclk); @@ -264,7 +263,7 @@ static int msm_iommu_remove(struct platform_device *pdev) static int msm_iommu_ctx_probe(struct platform_device *pdev) { - struct msm_iommu_ctx_dev *c = pdev->dev.platform_data; + struct msm_iommu_ctx_dev *c = dev_get_platdata(&pdev->dev); struct msm_iommu_drvdata *drvdata; struct msm_iommu_ctx_drvdata *ctx_drvdata; int i, ret; @@ -323,8 +322,7 @@ static int msm_iommu_ctx_probe(struct platform_device *pdev) SET_NSCFG(drvdata->base, mid, 3); } - if (drvdata->clk) - clk_disable(drvdata->clk); + clk_disable(drvdata->clk); clk_disable(drvdata->pclk); dev_info(&pdev->dev, "context %s using bank %d\n", c->name, c->num); diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index 531658d17333..f3d20a2039d2 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -10,45 +10,35 @@ * published by the Free Software Foundation. */ -#include <linux/module.h> #include <linux/err.h> -#include <linux/clk.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/uaccess.h> -#include <linux/platform_device.h> #include <linux/debugfs.h> -#include <linux/omap-iommu.h> #include <linux/platform_data/iommu-omap.h> #include "omap-iopgtable.h" #include "omap-iommu.h" -#define MAXCOLUMN 100 /* for short messages */ - static DEFINE_MUTEX(iommu_debug_lock); static struct dentry *iommu_debug_root; -static ssize_t debug_read_ver(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static inline bool is_omap_iommu_detached(struct omap_iommu *obj) { - u32 ver = omap_iommu_arch_version(); - char buf[MAXCOLUMN], *p = buf; - - p += sprintf(p, "H/W version: %d.%d\n", (ver >> 4) & 0xf , ver & 0xf); - - return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + return !obj->domain; } static ssize_t debug_read_regs(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - struct device *dev = file->private_data; - struct omap_iommu *obj = dev_to_omap_iommu(dev); + struct omap_iommu *obj = file->private_data; char *p, *buf; ssize_t bytes; + if (is_omap_iommu_detached(obj)) + return -EPERM; + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -68,11 +58,13 @@ static ssize_t debug_read_regs(struct file *file, char __user *userbuf, static ssize_t debug_read_tlb(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - struct device *dev = file->private_data; - struct omap_iommu *obj = dev_to_omap_iommu(dev); + struct omap_iommu *obj = file->private_data; char *p, *buf; ssize_t bytes, rest; + if (is_omap_iommu_detached(obj)) + return -EPERM; + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -93,133 +85,69 @@ static ssize_t debug_read_tlb(struct file *file, char __user *userbuf, return bytes; } -static ssize_t debug_write_pagetable(struct file *file, - const char __user *userbuf, size_t count, loff_t *ppos) +static void dump_ioptable(struct seq_file *s) { - struct iotlb_entry e; - struct cr_regs cr; - int err; - struct device *dev = file->private_data; - struct omap_iommu *obj = dev_to_omap_iommu(dev); - char buf[MAXCOLUMN], *p = buf; - - count = min(count, sizeof(buf)); - - mutex_lock(&iommu_debug_lock); - if (copy_from_user(p, userbuf, count)) { - mutex_unlock(&iommu_debug_lock); - return -EFAULT; - } - - sscanf(p, "%x %x", &cr.cam, &cr.ram); - if (!cr.cam || !cr.ram) { - mutex_unlock(&iommu_debug_lock); - return -EINVAL; - } - - omap_iotlb_cr_to_e(&cr, &e); - err = omap_iopgtable_store_entry(obj, &e); - if (err) - dev_err(obj->dev, "%s: fail to store cr\n", __func__); - - mutex_unlock(&iommu_debug_lock); - return count; -} - -#define dump_ioptable_entry_one(lv, da, val) \ - ({ \ - int __err = 0; \ - ssize_t bytes; \ - const int maxcol = 22; \ - const char *str = "%d: %08x %08x\n"; \ - bytes = snprintf(p, maxcol, str, lv, da, val); \ - p += bytes; \ - len -= bytes; \ - if (len < maxcol) \ - __err = -ENOMEM; \ - __err; \ - }) - -static ssize_t dump_ioptable(struct omap_iommu *obj, char *buf, ssize_t len) -{ - int i; - u32 *iopgd; - char *p = buf; + int i, j; + u32 da; + u32 *iopgd, *iopte; + struct omap_iommu *obj = s->private; spin_lock(&obj->page_table_lock); iopgd = iopgd_offset(obj, 0); for (i = 0; i < PTRS_PER_IOPGD; i++, iopgd++) { - int j, err; - u32 *iopte; - u32 da; - if (!*iopgd) continue; if (!(*iopgd & IOPGD_TABLE)) { da = i << IOPGD_SHIFT; - - err = dump_ioptable_entry_one(1, da, *iopgd); - if (err) - goto out; + seq_printf(s, "1: 0x%08x 0x%08x\n", da, *iopgd); continue; } iopte = iopte_offset(iopgd, 0); - for (j = 0; j < PTRS_PER_IOPTE; j++, iopte++) { if (!*iopte) continue; da = (i << IOPGD_SHIFT) + (j << IOPTE_SHIFT); - err = dump_ioptable_entry_one(2, da, *iopgd); - if (err) - goto out; + seq_printf(s, "2: 0x%08x 0x%08x\n", da, *iopte); } } -out: - spin_unlock(&obj->page_table_lock); - return p - buf; + spin_unlock(&obj->page_table_lock); } -static ssize_t debug_read_pagetable(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static int debug_read_pagetable(struct seq_file *s, void *data) { - struct device *dev = file->private_data; - struct omap_iommu *obj = dev_to_omap_iommu(dev); - char *p, *buf; - size_t bytes; + struct omap_iommu *obj = s->private; - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - p += sprintf(p, "L: %8s %8s\n", "da:", "pa:"); - p += sprintf(p, "-----------------------------------------\n"); + if (is_omap_iommu_detached(obj)) + return -EPERM; mutex_lock(&iommu_debug_lock); - bytes = PAGE_SIZE - (p - buf); - p += dump_ioptable(obj, p, bytes); - - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + seq_printf(s, "L: %8s %8s\n", "da:", "pte:"); + seq_puts(s, "--------------------------\n"); + dump_ioptable(s); mutex_unlock(&iommu_debug_lock); - free_page((unsigned long)buf); - return bytes; + return 0; } -#define DEBUG_FOPS(name) \ - static const struct file_operations debug_##name##_fops = { \ - .open = simple_open, \ - .read = debug_read_##name, \ - .write = debug_write_##name, \ - .llseek = generic_file_llseek, \ - }; +#define DEBUG_SEQ_FOPS_RO(name) \ + static int debug_open_##name(struct inode *inode, struct file *file) \ + { \ + return single_open(file, debug_read_##name, inode->i_private); \ + } \ + \ + static const struct file_operations debug_##name##_fops = { \ + .open = debug_open_##name, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + } #define DEBUG_FOPS_RO(name) \ static const struct file_operations debug_##name##_fops = { \ @@ -228,103 +156,63 @@ static ssize_t debug_read_pagetable(struct file *file, char __user *userbuf, .llseek = generic_file_llseek, \ }; -DEBUG_FOPS_RO(ver); DEBUG_FOPS_RO(regs); DEBUG_FOPS_RO(tlb); -DEBUG_FOPS(pagetable); +DEBUG_SEQ_FOPS_RO(pagetable); #define __DEBUG_ADD_FILE(attr, mode) \ { \ struct dentry *dent; \ - dent = debugfs_create_file(#attr, mode, parent, \ - dev, &debug_##attr##_fops); \ + dent = debugfs_create_file(#attr, mode, obj->debug_dir, \ + obj, &debug_##attr##_fops); \ if (!dent) \ - return -ENOMEM; \ + goto err; \ } -#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600) #define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400) -static int iommu_debug_register(struct device *dev, void *data) +void omap_iommu_debugfs_add(struct omap_iommu *obj) { - struct platform_device *pdev = to_platform_device(dev); - struct omap_iommu *obj = platform_get_drvdata(pdev); - struct omap_iommu_arch_data *arch_data; - struct dentry *d, *parent; - - if (!obj || !obj->dev) - return -EINVAL; - - arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL); - if (!arch_data) - return -ENOMEM; - - arch_data->iommu_dev = obj; + struct dentry *d; - dev->archdata.iommu = arch_data; + if (!iommu_debug_root) + return; - d = debugfs_create_dir(obj->name, iommu_debug_root); - if (!d) - goto nomem; - parent = d; + obj->debug_dir = debugfs_create_dir(obj->name, iommu_debug_root); + if (!obj->debug_dir) + return; - d = debugfs_create_u8("nr_tlb_entries", 400, parent, + d = debugfs_create_u8("nr_tlb_entries", 0400, obj->debug_dir, (u8 *)&obj->nr_tlb_entries); if (!d) - goto nomem; + return; - DEBUG_ADD_FILE_RO(ver); DEBUG_ADD_FILE_RO(regs); DEBUG_ADD_FILE_RO(tlb); - DEBUG_ADD_FILE(pagetable); + DEBUG_ADD_FILE_RO(pagetable); - return 0; + return; -nomem: - kfree(arch_data); - return -ENOMEM; +err: + debugfs_remove_recursive(obj->debug_dir); } -static int iommu_debug_unregister(struct device *dev, void *data) +void omap_iommu_debugfs_remove(struct omap_iommu *obj) { - if (!dev->archdata.iommu) - return 0; - - kfree(dev->archdata.iommu); + if (!obj->debug_dir) + return; - dev->archdata.iommu = NULL; - - return 0; + debugfs_remove_recursive(obj->debug_dir); } -static int __init iommu_debug_init(void) +void __init omap_iommu_debugfs_init(void) { - struct dentry *d; - int err; - - d = debugfs_create_dir("iommu", NULL); - if (!d) - return -ENOMEM; - iommu_debug_root = d; - - err = omap_foreach_iommu_device(d, iommu_debug_register); - if (err) - goto err_out; - return 0; - -err_out: - debugfs_remove_recursive(iommu_debug_root); - return err; + iommu_debug_root = debugfs_create_dir("omap_iommu", NULL); + if (!iommu_debug_root) + pr_err("can't create debugfs dir\n"); } -module_init(iommu_debug_init) -static void __exit iommu_debugfs_exit(void) +void __exit omap_iommu_debugfs_exit(void) { - debugfs_remove_recursive(iommu_debug_root); - omap_foreach_iommu_device(NULL, iommu_debug_unregister); + debugfs_remove(iommu_debug_root); } -module_exit(iommu_debugfs_exit) - -MODULE_DESCRIPTION("omap iommu: debugfs interface"); -MODULE_AUTHOR("Hiroshi DOYU <Hiroshi.DOYU@nokia.com>"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 36278870e84a..bbb7dcef02d3 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -76,53 +76,23 @@ struct iotlb_lock { short vict; }; -/* accommodate the difference between omap1 and omap2/3 */ -static const struct iommu_functions *arch_iommu; - static struct platform_driver omap_iommu_driver; static struct kmem_cache *iopte_cachep; /** - * omap_install_iommu_arch - Install archtecure specific iommu functions - * @ops: a pointer to architecture specific iommu functions - * - * There are several kind of iommu algorithm(tlb, pagetable) among - * omap series. This interface installs such an iommu algorighm. - **/ -int omap_install_iommu_arch(const struct iommu_functions *ops) -{ - if (arch_iommu) - return -EBUSY; - - arch_iommu = ops; - return 0; -} -EXPORT_SYMBOL_GPL(omap_install_iommu_arch); - -/** - * omap_uninstall_iommu_arch - Uninstall archtecure specific iommu functions - * @ops: a pointer to architecture specific iommu functions - * - * This interface uninstalls the iommu algorighm installed previously. - **/ -void omap_uninstall_iommu_arch(const struct iommu_functions *ops) -{ - if (arch_iommu != ops) - pr_err("%s: not your arch\n", __func__); - - arch_iommu = NULL; -} -EXPORT_SYMBOL_GPL(omap_uninstall_iommu_arch); - -/** * omap_iommu_save_ctx - Save registers for pm off-mode support * @dev: client device **/ void omap_iommu_save_ctx(struct device *dev) { struct omap_iommu *obj = dev_to_omap_iommu(dev); + u32 *p = obj->ctx; + int i; - arch_iommu->save_ctx(obj); + for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) { + p[i] = iommu_read_reg(obj, i * sizeof(u32)); + dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]); + } } EXPORT_SYMBOL_GPL(omap_iommu_save_ctx); @@ -133,28 +103,74 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx); void omap_iommu_restore_ctx(struct device *dev) { struct omap_iommu *obj = dev_to_omap_iommu(dev); + u32 *p = obj->ctx; + int i; - arch_iommu->restore_ctx(obj); + for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) { + iommu_write_reg(obj, p[i], i * sizeof(u32)); + dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]); + } } EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx); -/** - * omap_iommu_arch_version - Return running iommu arch version - **/ -u32 omap_iommu_arch_version(void) +static void __iommu_set_twl(struct omap_iommu *obj, bool on) { - return arch_iommu->version; + u32 l = iommu_read_reg(obj, MMU_CNTL); + + if (on) + iommu_write_reg(obj, MMU_IRQ_TWL_MASK, MMU_IRQENABLE); + else + iommu_write_reg(obj, MMU_IRQ_TLB_MISS_MASK, MMU_IRQENABLE); + + l &= ~MMU_CNTL_MASK; + if (on) + l |= (MMU_CNTL_MMU_EN | MMU_CNTL_TWL_EN); + else + l |= (MMU_CNTL_MMU_EN); + + iommu_write_reg(obj, l, MMU_CNTL); +} + +static int omap2_iommu_enable(struct omap_iommu *obj) +{ + u32 l, pa; + + if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd, SZ_16K)) + return -EINVAL; + + pa = virt_to_phys(obj->iopgd); + if (!IS_ALIGNED(pa, SZ_16K)) + return -EINVAL; + + l = iommu_read_reg(obj, MMU_REVISION); + dev_info(obj->dev, "%s: version %d.%d\n", obj->name, + (l >> 4) & 0xf, l & 0xf); + + iommu_write_reg(obj, pa, MMU_TTB); + + if (obj->has_bus_err_back) + iommu_write_reg(obj, MMU_GP_REG_BUS_ERR_BACK_EN, MMU_GP_REG); + + __iommu_set_twl(obj, true); + + return 0; +} + +static void omap2_iommu_disable(struct omap_iommu *obj) +{ + u32 l = iommu_read_reg(obj, MMU_CNTL); + + l &= ~MMU_CNTL_MASK; + iommu_write_reg(obj, l, MMU_CNTL); + + dev_dbg(obj->dev, "%s is shutting down\n", obj->name); } -EXPORT_SYMBOL_GPL(omap_iommu_arch_version); static int iommu_enable(struct omap_iommu *obj) { int err; struct platform_device *pdev = to_platform_device(obj->dev); - struct iommu_platform_data *pdata = pdev->dev.platform_data; - - if (!arch_iommu) - return -ENODEV; + struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev); if (pdata && pdata->deassert_reset) { err = pdata->deassert_reset(pdev, pdata->reset_name); @@ -166,7 +182,7 @@ static int iommu_enable(struct omap_iommu *obj) pm_runtime_get_sync(obj->dev); - err = arch_iommu->enable(obj); + err = omap2_iommu_enable(obj); return err; } @@ -174,9 +190,9 @@ static int iommu_enable(struct omap_iommu *obj) static void iommu_disable(struct omap_iommu *obj) { struct platform_device *pdev = to_platform_device(obj->dev); - struct iommu_platform_data *pdata = pdev->dev.platform_data; + struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev); - arch_iommu->disable(obj); + omap2_iommu_disable(obj); pm_runtime_put_sync(obj->dev); @@ -187,44 +203,51 @@ static void iommu_disable(struct omap_iommu *obj) /* * TLB operations */ -void omap_iotlb_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e) -{ - BUG_ON(!cr || !e); - - arch_iommu->cr_to_e(cr, e); -} -EXPORT_SYMBOL_GPL(omap_iotlb_cr_to_e); - static inline int iotlb_cr_valid(struct cr_regs *cr) { if (!cr) return -EINVAL; - return arch_iommu->cr_valid(cr); -} - -static inline struct cr_regs *iotlb_alloc_cr(struct omap_iommu *obj, - struct iotlb_entry *e) -{ - if (!e) - return NULL; - - return arch_iommu->alloc_cr(obj, e); + return cr->cam & MMU_CAM_V; } static u32 iotlb_cr_to_virt(struct cr_regs *cr) { - return arch_iommu->cr_to_virt(cr); + u32 page_size = cr->cam & MMU_CAM_PGSZ_MASK; + u32 mask = get_cam_va_mask(cr->cam & page_size); + + return cr->cam & mask; } static u32 get_iopte_attr(struct iotlb_entry *e) { - return arch_iommu->get_pte_attr(e); + u32 attr; + + attr = e->mixed << 5; + attr |= e->endian; + attr |= e->elsz >> 3; + attr <<= (((e->pgsz == MMU_CAM_PGSZ_4K) || + (e->pgsz == MMU_CAM_PGSZ_64K)) ? 0 : 6); + return attr; } static u32 iommu_report_fault(struct omap_iommu *obj, u32 *da) { - return arch_iommu->fault_isr(obj, da); + u32 status, fault_addr; + + status = iommu_read_reg(obj, MMU_IRQSTATUS); + status &= MMU_IRQ_MASK; + if (!status) { + *da = 0; + return 0; + } + + fault_addr = iommu_read_reg(obj, MMU_FAULT_AD); + *da = fault_addr; + + iommu_write_reg(obj, status, MMU_IRQSTATUS); + + return status; } static void iotlb_lock_get(struct omap_iommu *obj, struct iotlb_lock *l) @@ -250,31 +273,19 @@ static void iotlb_lock_set(struct omap_iommu *obj, struct iotlb_lock *l) static void iotlb_read_cr(struct omap_iommu *obj, struct cr_regs *cr) { - arch_iommu->tlb_read_cr(obj, cr); + cr->cam = iommu_read_reg(obj, MMU_READ_CAM); + cr->ram = iommu_read_reg(obj, MMU_READ_RAM); } static void iotlb_load_cr(struct omap_iommu *obj, struct cr_regs *cr) { - arch_iommu->tlb_load_cr(obj, cr); + iommu_write_reg(obj, cr->cam | MMU_CAM_V, MMU_CAM); + iommu_write_reg(obj, cr->ram, MMU_RAM); iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); iommu_write_reg(obj, 1, MMU_LD_TLB); } -/** - * iotlb_dump_cr - Dump an iommu tlb entry into buf - * @obj: target iommu - * @cr: contents of cam and ram register - * @buf: output buffer - **/ -static inline ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr, - char *buf) -{ - BUG_ON(!cr || !buf); - - return arch_iommu->dump_cr(obj, cr, buf); -} - /* only used in iotlb iteration for-loop */ static struct cr_regs __iotlb_read_cr(struct omap_iommu *obj, int n) { @@ -289,12 +300,36 @@ static struct cr_regs __iotlb_read_cr(struct omap_iommu *obj, int n) return cr; } +#ifdef PREFETCH_IOTLB +static struct cr_regs *iotlb_alloc_cr(struct omap_iommu *obj, + struct iotlb_entry *e) +{ + struct cr_regs *cr; + + if (!e) + return NULL; + + if (e->da & ~(get_cam_va_mask(e->pgsz))) { + dev_err(obj->dev, "%s:\twrong alignment: %08x\n", __func__, + e->da); + return ERR_PTR(-EINVAL); + } + + cr = kmalloc(sizeof(*cr), GFP_KERNEL); + if (!cr) + return ERR_PTR(-ENOMEM); + + cr->cam = (e->da & MMU_CAM_VATAG_MASK) | e->prsvd | e->pgsz | e->valid; + cr->ram = e->pa | e->endian | e->elsz | e->mixed; + + return cr; +} + /** * load_iotlb_entry - Set an iommu tlb entry * @obj: target iommu * @e: an iommu tlb entry info **/ -#ifdef PREFETCH_IOTLB static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e) { int err = 0; @@ -423,7 +458,45 @@ static void flush_iotlb_all(struct omap_iommu *obj) pm_runtime_put_sync(obj->dev); } -#if defined(CONFIG_OMAP_IOMMU_DEBUG) || defined(CONFIG_OMAP_IOMMU_DEBUG_MODULE) +#ifdef CONFIG_OMAP_IOMMU_DEBUG + +#define pr_reg(name) \ + do { \ + ssize_t bytes; \ + const char *str = "%20s: %08x\n"; \ + const int maxcol = 32; \ + bytes = snprintf(p, maxcol, str, __stringify(name), \ + iommu_read_reg(obj, MMU_##name)); \ + p += bytes; \ + len -= bytes; \ + if (len < maxcol) \ + goto out; \ + } while (0) + +static ssize_t +omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len) +{ + char *p = buf; + + pr_reg(REVISION); + pr_reg(IRQSTATUS); + pr_reg(IRQENABLE); + pr_reg(WALKING_ST); + pr_reg(CNTL); + pr_reg(FAULT_AD); + pr_reg(TTB); + pr_reg(LOCK); + pr_reg(LD_TLB); + pr_reg(CAM); + pr_reg(RAM); + pr_reg(GFLUSH); + pr_reg(FLUSH_ENTRY); + pr_reg(READ_CAM); + pr_reg(READ_RAM); + pr_reg(EMU_FAULT_AD); +out: + return p - buf; +} ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes) { @@ -432,13 +505,12 @@ ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes) pm_runtime_get_sync(obj->dev); - bytes = arch_iommu->dump_ctx(obj, buf, bytes); + bytes = omap2_iommu_dump_ctx(obj, buf, bytes); pm_runtime_put_sync(obj->dev); return bytes; } -EXPORT_SYMBOL_GPL(omap_iommu_dump_ctx); static int __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num) @@ -464,6 +536,24 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num) } /** + * iotlb_dump_cr - Dump an iommu tlb entry into buf + * @obj: target iommu + * @cr: contents of cam and ram register + * @buf: output buffer + **/ +static ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr, + char *buf) +{ + char *p = buf; + + /* FIXME: Need more detail analysis of cam/ram */ + p += sprintf(p, "%08x %08x %01x\n", cr->cam, cr->ram, + (cr->cam & MMU_CAM_P) ? 1 : 0); + + return p - buf; +} + +/** * omap_dump_tlb_entries - dump cr arrays to given buffer * @obj: target iommu * @buf: output buffer @@ -488,16 +578,8 @@ size_t omap_dump_tlb_entries(struct omap_iommu *obj, char *buf, ssize_t bytes) return p - buf; } -EXPORT_SYMBOL_GPL(omap_dump_tlb_entries); - -int omap_foreach_iommu_device(void *data, int (*fn)(struct device *, void *)) -{ - return driver_for_each_device(&omap_iommu_driver.driver, - NULL, data, fn); -} -EXPORT_SYMBOL_GPL(omap_foreach_iommu_device); -#endif /* CONFIG_OMAP_IOMMU_DEBUG_MODULE */ +#endif /* CONFIG_OMAP_IOMMU_DEBUG */ /* * H/W pagetable operations @@ -680,7 +762,8 @@ iopgtable_store_entry_core(struct omap_iommu *obj, struct iotlb_entry *e) * @obj: target iommu * @e: an iommu tlb entry info **/ -int omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e) +static int +omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e) { int err; @@ -690,7 +773,6 @@ int omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e) prefetch_iotlb_entry(obj, e); return err; } -EXPORT_SYMBOL_GPL(omap_iopgtable_store_entry); /** * iopgtable_lookup_entry - Lookup an iommu pte entry @@ -819,8 +901,9 @@ static irqreturn_t iommu_fault_handler(int irq, void *data) u32 *iopgd, *iopte; struct omap_iommu *obj = data; struct iommu_domain *domain = obj->domain; + struct omap_iommu_domain *omap_domain = domain->priv; - if (!obj->refcount) + if (!omap_domain->iommu_dev) return IRQ_NONE; errs = iommu_report_fault(obj, &da); @@ -880,13 +963,6 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd) spin_lock(&obj->iommu_lock); - /* an iommu device can only be attached once */ - if (++obj->refcount > 1) { - dev_err(dev, "%s: already attached!\n", obj->name); - err = -EBUSY; - goto err_enable; - } - obj->iopgd = iopgd; err = iommu_enable(obj); if (err) @@ -899,7 +975,6 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd) return obj; err_enable: - obj->refcount--; spin_unlock(&obj->iommu_lock); return ERR_PTR(err); } @@ -915,9 +990,7 @@ static void omap_iommu_detach(struct omap_iommu *obj) spin_lock(&obj->iommu_lock); - if (--obj->refcount == 0) - iommu_disable(obj); - + iommu_disable(obj); obj->iopgd = NULL; spin_unlock(&obj->iommu_lock); @@ -934,7 +1007,7 @@ static int omap_iommu_probe(struct platform_device *pdev) int irq; struct omap_iommu *obj; struct resource *res; - struct iommu_platform_data *pdata = pdev->dev.platform_data; + struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev); struct device_node *of = pdev->dev.of_node; obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL); @@ -981,6 +1054,8 @@ static int omap_iommu_probe(struct platform_device *pdev) pm_runtime_irq_safe(obj->dev); pm_runtime_enable(obj->dev); + omap_iommu_debugfs_add(obj); + dev_info(&pdev->dev, "%s registered\n", obj->name); return 0; } @@ -990,6 +1065,7 @@ static int omap_iommu_remove(struct platform_device *pdev) struct omap_iommu *obj = platform_get_drvdata(pdev); iopgtable_clear_entry_all(obj); + omap_iommu_debugfs_remove(obj); pm_runtime_disable(obj->dev); @@ -1026,7 +1102,6 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz) e->da = da; e->pa = pa; e->valid = MMU_CAM_V; - /* FIXME: add OMAP1 support */ e->pgsz = pgsz; e->endian = MMU_RAM_ENDIAN_LITTLE; e->elsz = MMU_RAM_ELSZ_8; @@ -1131,6 +1206,7 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain, omap_domain->iommu_dev = arch_data->iommu_dev = NULL; omap_domain->dev = NULL; + oiommu->domain = NULL; } static void omap_iommu_detach_dev(struct iommu_domain *domain, @@ -1288,6 +1364,7 @@ static const struct iommu_ops omap_iommu_ops = { .detach_dev = omap_iommu_detach_dev, .map = omap_iommu_map, .unmap = omap_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = omap_iommu_iova_to_phys, .add_device = omap_iommu_add_device, .remove_device = omap_iommu_remove_device, @@ -1308,6 +1385,8 @@ static int __init omap_iommu_init(void) bus_set_iommu(&platform_bus_type, &omap_iommu_ops); + omap_iommu_debugfs_init(); + return platform_driver_register(&omap_iommu_driver); } /* must be ready before omap3isp is probed */ @@ -1318,6 +1397,8 @@ static void __exit omap_iommu_exit(void) kmem_cache_destroy(iopte_cachep); platform_driver_unregister(&omap_iommu_driver); + + omap_iommu_debugfs_exit(); } module_exit(omap_iommu_exit); diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h index 4f1b68c08c15..d736630df3c8 100644 --- a/drivers/iommu/omap-iommu.h +++ b/drivers/iommu/omap-iommu.h @@ -10,9 +10,8 @@ * published by the Free Software Foundation. */ -#if defined(CONFIG_ARCH_OMAP1) -#error "iommu for this processor not implemented yet" -#endif +#ifndef _OMAP_IOMMU_H +#define _OMAP_IOMMU_H struct iotlb_entry { u32 da; @@ -30,10 +29,9 @@ struct omap_iommu { const char *name; void __iomem *regbase; struct device *dev; - void *isr_priv; struct iommu_domain *domain; + struct dentry *debug_dir; - unsigned int refcount; spinlock_t iommu_lock; /* global for this whole object */ /* @@ -67,34 +65,6 @@ struct cr_regs { }; }; -/* architecture specific functions */ -struct iommu_functions { - unsigned long version; - - int (*enable)(struct omap_iommu *obj); - void (*disable)(struct omap_iommu *obj); - void (*set_twl)(struct omap_iommu *obj, bool on); - u32 (*fault_isr)(struct omap_iommu *obj, u32 *ra); - - void (*tlb_read_cr)(struct omap_iommu *obj, struct cr_regs *cr); - void (*tlb_load_cr)(struct omap_iommu *obj, struct cr_regs *cr); - - struct cr_regs *(*alloc_cr)(struct omap_iommu *obj, - struct iotlb_entry *e); - int (*cr_valid)(struct cr_regs *cr); - u32 (*cr_to_virt)(struct cr_regs *cr); - void (*cr_to_e)(struct cr_regs *cr, struct iotlb_entry *e); - ssize_t (*dump_cr)(struct omap_iommu *obj, struct cr_regs *cr, - char *buf); - - u32 (*get_pte_attr)(struct iotlb_entry *e); - - void (*save_ctx)(struct omap_iommu *obj); - void (*restore_ctx)(struct omap_iommu *obj); - ssize_t (*dump_ctx)(struct omap_iommu *obj, char *buf, ssize_t len); -}; - -#ifdef CONFIG_IOMMU_API /** * dev_to_omap_iommu() - retrieves an omap iommu object from a user device * @dev: iommu client device @@ -105,7 +75,6 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) return arch_data->iommu_dev; } -#endif /* * MMU Register offsets @@ -133,6 +102,28 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) /* * MMU Register bit definitions */ +/* IRQSTATUS & IRQENABLE */ +#define MMU_IRQ_MULTIHITFAULT (1 << 4) +#define MMU_IRQ_TABLEWALKFAULT (1 << 3) +#define MMU_IRQ_EMUMISS (1 << 2) +#define MMU_IRQ_TRANSLATIONFAULT (1 << 1) +#define MMU_IRQ_TLBMISS (1 << 0) + +#define __MMU_IRQ_FAULT \ + (MMU_IRQ_MULTIHITFAULT | MMU_IRQ_EMUMISS | MMU_IRQ_TRANSLATIONFAULT) +#define MMU_IRQ_MASK \ + (__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT | MMU_IRQ_TLBMISS) +#define MMU_IRQ_TWL_MASK (__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT) +#define MMU_IRQ_TLB_MISS_MASK (__MMU_IRQ_FAULT | MMU_IRQ_TLBMISS) + +/* MMU_CNTL */ +#define MMU_CNTL_SHIFT 1 +#define MMU_CNTL_MASK (7 << MMU_CNTL_SHIFT) +#define MMU_CNTL_EML_TLB (1 << 3) +#define MMU_CNTL_TWL_EN (1 << 2) +#define MMU_CNTL_MMU_EN (1 << 1) + +/* CAM */ #define MMU_CAM_VATAG_SHIFT 12 #define MMU_CAM_VATAG_MASK \ ((~0UL >> MMU_CAM_VATAG_SHIFT) << MMU_CAM_VATAG_SHIFT) @@ -144,6 +135,7 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) #define MMU_CAM_PGSZ_4K (2 << 0) #define MMU_CAM_PGSZ_16M (3 << 0) +/* RAM */ #define MMU_RAM_PADDR_SHIFT 12 #define MMU_RAM_PADDR_MASK \ ((~0UL >> MMU_RAM_PADDR_SHIFT) << MMU_RAM_PADDR_SHIFT) @@ -165,6 +157,12 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) #define MMU_GP_REG_BUS_ERR_BACK_EN 0x1 +#define get_cam_va_mask(pgsz) \ + (((pgsz) == MMU_CAM_PGSZ_16M) ? 0xff000000 : \ + ((pgsz) == MMU_CAM_PGSZ_1M) ? 0xfff00000 : \ + ((pgsz) == MMU_CAM_PGSZ_64K) ? 0xffff0000 : \ + ((pgsz) == MMU_CAM_PGSZ_4K) ? 0xfffff000 : 0) + /* * utilities for super page(16MB, 1MB, 64KB and 4KB) */ @@ -192,27 +190,25 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) /* * global functions */ -extern u32 omap_iommu_arch_version(void); - -extern void omap_iotlb_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e); - -extern int -omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e); - -extern void omap_iommu_save_ctx(struct device *dev); -extern void omap_iommu_restore_ctx(struct device *dev); - -extern int omap_foreach_iommu_device(void *data, - int (*fn)(struct device *, void *)); - -extern int omap_install_iommu_arch(const struct iommu_functions *ops); -extern void omap_uninstall_iommu_arch(const struct iommu_functions *ops); - +#ifdef CONFIG_OMAP_IOMMU_DEBUG extern ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len); extern size_t omap_dump_tlb_entries(struct omap_iommu *obj, char *buf, ssize_t len); +void omap_iommu_debugfs_init(void); +void omap_iommu_debugfs_exit(void); + +void omap_iommu_debugfs_add(struct omap_iommu *obj); +void omap_iommu_debugfs_remove(struct omap_iommu *obj); +#else +static inline void omap_iommu_debugfs_init(void) { } +static inline void omap_iommu_debugfs_exit(void) { } + +static inline void omap_iommu_debugfs_add(struct omap_iommu *obj) { } +static inline void omap_iommu_debugfs_remove(struct omap_iommu *obj) { } +#endif + /* * register accessors */ @@ -225,3 +221,5 @@ static inline void iommu_write_reg(struct omap_iommu *obj, u32 val, size_t offs) { __raw_writel(val, obj->regbase + offs); } + +#endif /* _OMAP_IOMMU_H */ diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c deleted file mode 100644 index 5e1ea3b0bf16..000000000000 --- a/drivers/iommu/omap-iommu2.c +++ /dev/null @@ -1,337 +0,0 @@ -/* - * omap iommu: omap2/3 architecture specific functions - * - * Copyright (C) 2008-2009 Nokia Corporation - * - * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>, - * Paul Mundt and Toshihiro Kobayashi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/err.h> -#include <linux/device.h> -#include <linux/io.h> -#include <linux/jiffies.h> -#include <linux/module.h> -#include <linux/omap-iommu.h> -#include <linux/slab.h> -#include <linux/stringify.h> -#include <linux/platform_data/iommu-omap.h> - -#include "omap-iommu.h" - -/* - * omap2 architecture specific register bit definitions - */ -#define IOMMU_ARCH_VERSION 0x00000011 - -/* IRQSTATUS & IRQENABLE */ -#define MMU_IRQ_MULTIHITFAULT (1 << 4) -#define MMU_IRQ_TABLEWALKFAULT (1 << 3) -#define MMU_IRQ_EMUMISS (1 << 2) -#define MMU_IRQ_TRANSLATIONFAULT (1 << 1) -#define MMU_IRQ_TLBMISS (1 << 0) - -#define __MMU_IRQ_FAULT \ - (MMU_IRQ_MULTIHITFAULT | MMU_IRQ_EMUMISS | MMU_IRQ_TRANSLATIONFAULT) -#define MMU_IRQ_MASK \ - (__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT | MMU_IRQ_TLBMISS) -#define MMU_IRQ_TWL_MASK (__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT) -#define MMU_IRQ_TLB_MISS_MASK (__MMU_IRQ_FAULT | MMU_IRQ_TLBMISS) - -/* MMU_CNTL */ -#define MMU_CNTL_SHIFT 1 -#define MMU_CNTL_MASK (7 << MMU_CNTL_SHIFT) -#define MMU_CNTL_EML_TLB (1 << 3) -#define MMU_CNTL_TWL_EN (1 << 2) -#define MMU_CNTL_MMU_EN (1 << 1) - -#define get_cam_va_mask(pgsz) \ - (((pgsz) == MMU_CAM_PGSZ_16M) ? 0xff000000 : \ - ((pgsz) == MMU_CAM_PGSZ_1M) ? 0xfff00000 : \ - ((pgsz) == MMU_CAM_PGSZ_64K) ? 0xffff0000 : \ - ((pgsz) == MMU_CAM_PGSZ_4K) ? 0xfffff000 : 0) - -/* IOMMU errors */ -#define OMAP_IOMMU_ERR_TLB_MISS (1 << 0) -#define OMAP_IOMMU_ERR_TRANS_FAULT (1 << 1) -#define OMAP_IOMMU_ERR_EMU_MISS (1 << 2) -#define OMAP_IOMMU_ERR_TBLWALK_FAULT (1 << 3) -#define OMAP_IOMMU_ERR_MULTIHIT_FAULT (1 << 4) - -static void __iommu_set_twl(struct omap_iommu *obj, bool on) -{ - u32 l = iommu_read_reg(obj, MMU_CNTL); - - if (on) - iommu_write_reg(obj, MMU_IRQ_TWL_MASK, MMU_IRQENABLE); - else - iommu_write_reg(obj, MMU_IRQ_TLB_MISS_MASK, MMU_IRQENABLE); - - l &= ~MMU_CNTL_MASK; - if (on) - l |= (MMU_CNTL_MMU_EN | MMU_CNTL_TWL_EN); - else - l |= (MMU_CNTL_MMU_EN); - - iommu_write_reg(obj, l, MMU_CNTL); -} - - -static int omap2_iommu_enable(struct omap_iommu *obj) -{ - u32 l, pa; - - if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd, SZ_16K)) - return -EINVAL; - - pa = virt_to_phys(obj->iopgd); - if (!IS_ALIGNED(pa, SZ_16K)) - return -EINVAL; - - l = iommu_read_reg(obj, MMU_REVISION); - dev_info(obj->dev, "%s: version %d.%d\n", obj->name, - (l >> 4) & 0xf, l & 0xf); - - iommu_write_reg(obj, pa, MMU_TTB); - - if (obj->has_bus_err_back) - iommu_write_reg(obj, MMU_GP_REG_BUS_ERR_BACK_EN, MMU_GP_REG); - - __iommu_set_twl(obj, true); - - return 0; -} - -static void omap2_iommu_disable(struct omap_iommu *obj) -{ - u32 l = iommu_read_reg(obj, MMU_CNTL); - - l &= ~MMU_CNTL_MASK; - iommu_write_reg(obj, l, MMU_CNTL); - - dev_dbg(obj->dev, "%s is shutting down\n", obj->name); -} - -static void omap2_iommu_set_twl(struct omap_iommu *obj, bool on) -{ - __iommu_set_twl(obj, false); -} - -static u32 omap2_iommu_fault_isr(struct omap_iommu *obj, u32 *ra) -{ - u32 stat, da; - u32 errs = 0; - - stat = iommu_read_reg(obj, MMU_IRQSTATUS); - stat &= MMU_IRQ_MASK; - if (!stat) { - *ra = 0; - return 0; - } - - da = iommu_read_reg(obj, MMU_FAULT_AD); - *ra = da; - - if (stat & MMU_IRQ_TLBMISS) - errs |= OMAP_IOMMU_ERR_TLB_MISS; - if (stat & MMU_IRQ_TRANSLATIONFAULT) - errs |= OMAP_IOMMU_ERR_TRANS_FAULT; - if (stat & MMU_IRQ_EMUMISS) - errs |= OMAP_IOMMU_ERR_EMU_MISS; - if (stat & MMU_IRQ_TABLEWALKFAULT) - errs |= OMAP_IOMMU_ERR_TBLWALK_FAULT; - if (stat & MMU_IRQ_MULTIHITFAULT) - errs |= OMAP_IOMMU_ERR_MULTIHIT_FAULT; - iommu_write_reg(obj, stat, MMU_IRQSTATUS); - - return errs; -} - -static void omap2_tlb_read_cr(struct omap_iommu *obj, struct cr_regs *cr) -{ - cr->cam = iommu_read_reg(obj, MMU_READ_CAM); - cr->ram = iommu_read_reg(obj, MMU_READ_RAM); -} - -static void omap2_tlb_load_cr(struct omap_iommu *obj, struct cr_regs *cr) -{ - iommu_write_reg(obj, cr->cam | MMU_CAM_V, MMU_CAM); - iommu_write_reg(obj, cr->ram, MMU_RAM); -} - -static u32 omap2_cr_to_virt(struct cr_regs *cr) -{ - u32 page_size = cr->cam & MMU_CAM_PGSZ_MASK; - u32 mask = get_cam_va_mask(cr->cam & page_size); - - return cr->cam & mask; -} - -static struct cr_regs *omap2_alloc_cr(struct omap_iommu *obj, - struct iotlb_entry *e) -{ - struct cr_regs *cr; - - if (e->da & ~(get_cam_va_mask(e->pgsz))) { - dev_err(obj->dev, "%s:\twrong alignment: %08x\n", __func__, - e->da); - return ERR_PTR(-EINVAL); - } - - cr = kmalloc(sizeof(*cr), GFP_KERNEL); - if (!cr) - return ERR_PTR(-ENOMEM); - - cr->cam = (e->da & MMU_CAM_VATAG_MASK) | e->prsvd | e->pgsz | e->valid; - cr->ram = e->pa | e->endian | e->elsz | e->mixed; - - return cr; -} - -static inline int omap2_cr_valid(struct cr_regs *cr) -{ - return cr->cam & MMU_CAM_V; -} - -static u32 omap2_get_pte_attr(struct iotlb_entry *e) -{ - u32 attr; - - attr = e->mixed << 5; - attr |= e->endian; - attr |= e->elsz >> 3; - attr <<= (((e->pgsz == MMU_CAM_PGSZ_4K) || - (e->pgsz == MMU_CAM_PGSZ_64K)) ? 0 : 6); - return attr; -} - -static ssize_t -omap2_dump_cr(struct omap_iommu *obj, struct cr_regs *cr, char *buf) -{ - char *p = buf; - - /* FIXME: Need more detail analysis of cam/ram */ - p += sprintf(p, "%08x %08x %01x\n", cr->cam, cr->ram, - (cr->cam & MMU_CAM_P) ? 1 : 0); - - return p - buf; -} - -#define pr_reg(name) \ - do { \ - ssize_t bytes; \ - const char *str = "%20s: %08x\n"; \ - const int maxcol = 32; \ - bytes = snprintf(p, maxcol, str, __stringify(name), \ - iommu_read_reg(obj, MMU_##name)); \ - p += bytes; \ - len -= bytes; \ - if (len < maxcol) \ - goto out; \ - } while (0) - -static ssize_t -omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len) -{ - char *p = buf; - - pr_reg(REVISION); - pr_reg(IRQSTATUS); - pr_reg(IRQENABLE); - pr_reg(WALKING_ST); - pr_reg(CNTL); - pr_reg(FAULT_AD); - pr_reg(TTB); - pr_reg(LOCK); - pr_reg(LD_TLB); - pr_reg(CAM); - pr_reg(RAM); - pr_reg(GFLUSH); - pr_reg(FLUSH_ENTRY); - pr_reg(READ_CAM); - pr_reg(READ_RAM); - pr_reg(EMU_FAULT_AD); -out: - return p - buf; -} - -static void omap2_iommu_save_ctx(struct omap_iommu *obj) -{ - int i; - u32 *p = obj->ctx; - - for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) { - p[i] = iommu_read_reg(obj, i * sizeof(u32)); - dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]); - } - - BUG_ON(p[0] != IOMMU_ARCH_VERSION); -} - -static void omap2_iommu_restore_ctx(struct omap_iommu *obj) -{ - int i; - u32 *p = obj->ctx; - - for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) { - iommu_write_reg(obj, p[i], i * sizeof(u32)); - dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]); - } - - BUG_ON(p[0] != IOMMU_ARCH_VERSION); -} - -static void omap2_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e) -{ - e->da = cr->cam & MMU_CAM_VATAG_MASK; - e->pa = cr->ram & MMU_RAM_PADDR_MASK; - e->valid = cr->cam & MMU_CAM_V; - e->pgsz = cr->cam & MMU_CAM_PGSZ_MASK; - e->endian = cr->ram & MMU_RAM_ENDIAN_MASK; - e->elsz = cr->ram & MMU_RAM_ELSZ_MASK; - e->mixed = cr->ram & MMU_RAM_MIXED; -} - -static const struct iommu_functions omap2_iommu_ops = { - .version = IOMMU_ARCH_VERSION, - - .enable = omap2_iommu_enable, - .disable = omap2_iommu_disable, - .set_twl = omap2_iommu_set_twl, - .fault_isr = omap2_iommu_fault_isr, - - .tlb_read_cr = omap2_tlb_read_cr, - .tlb_load_cr = omap2_tlb_load_cr, - - .cr_to_e = omap2_cr_to_e, - .cr_to_virt = omap2_cr_to_virt, - .alloc_cr = omap2_alloc_cr, - .cr_valid = omap2_cr_valid, - .dump_cr = omap2_dump_cr, - - .get_pte_attr = omap2_get_pte_attr, - - .save_ctx = omap2_iommu_save_ctx, - .restore_ctx = omap2_iommu_restore_ctx, - .dump_ctx = omap2_iommu_dump_ctx, -}; - -static int __init omap2_iommu_init(void) -{ - return omap_install_iommu_arch(&omap2_iommu_ops); -} -module_init(omap2_iommu_init); - -static void __exit omap2_iommu_exit(void) -{ - omap_uninstall_iommu_arch(&omap2_iommu_ops); -} -module_exit(omap2_iommu_exit); - -MODULE_AUTHOR("Hiroshi DOYU, Paul Mundt and Toshihiro Kobayashi"); -MODULE_DESCRIPTION("omap iommu: omap2/3 architecture specific functions"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c new file mode 100644 index 000000000000..b2023af384b9 --- /dev/null +++ b/drivers/iommu/rockchip-iommu.c @@ -0,0 +1,1038 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/cacheflush.h> +#include <asm/pgtable.h> +#include <linux/compiler.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/jiffies.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +/** MMU register offsets */ +#define RK_MMU_DTE_ADDR 0x00 /* Directory table address */ +#define RK_MMU_STATUS 0x04 +#define RK_MMU_COMMAND 0x08 +#define RK_MMU_PAGE_FAULT_ADDR 0x0C /* IOVA of last page fault */ +#define RK_MMU_ZAP_ONE_LINE 0x10 /* Shootdown one IOTLB entry */ +#define RK_MMU_INT_RAWSTAT 0x14 /* IRQ status ignoring mask */ +#define RK_MMU_INT_CLEAR 0x18 /* Acknowledge and re-arm irq */ +#define RK_MMU_INT_MASK 0x1C /* IRQ enable */ +#define RK_MMU_INT_STATUS 0x20 /* IRQ status after masking */ +#define RK_MMU_AUTO_GATING 0x24 + +#define DTE_ADDR_DUMMY 0xCAFEBABE +#define FORCE_RESET_TIMEOUT 100 /* ms */ + +/* RK_MMU_STATUS fields */ +#define RK_MMU_STATUS_PAGING_ENABLED BIT(0) +#define RK_MMU_STATUS_PAGE_FAULT_ACTIVE BIT(1) +#define RK_MMU_STATUS_STALL_ACTIVE BIT(2) +#define RK_MMU_STATUS_IDLE BIT(3) +#define RK_MMU_STATUS_REPLAY_BUFFER_EMPTY BIT(4) +#define RK_MMU_STATUS_PAGE_FAULT_IS_WRITE BIT(5) +#define RK_MMU_STATUS_STALL_NOT_ACTIVE BIT(31) + +/* RK_MMU_COMMAND command values */ +#define RK_MMU_CMD_ENABLE_PAGING 0 /* Enable memory translation */ +#define RK_MMU_CMD_DISABLE_PAGING 1 /* Disable memory translation */ +#define RK_MMU_CMD_ENABLE_STALL 2 /* Stall paging to allow other cmds */ +#define RK_MMU_CMD_DISABLE_STALL 3 /* Stop stall re-enables paging */ +#define RK_MMU_CMD_ZAP_CACHE 4 /* Shoot down entire IOTLB */ +#define RK_MMU_CMD_PAGE_FAULT_DONE 5 /* Clear page fault */ +#define RK_MMU_CMD_FORCE_RESET 6 /* Reset all registers */ + +/* RK_MMU_INT_* register fields */ +#define RK_MMU_IRQ_PAGE_FAULT 0x01 /* page fault */ +#define RK_MMU_IRQ_BUS_ERROR 0x02 /* bus read error */ +#define RK_MMU_IRQ_MASK (RK_MMU_IRQ_PAGE_FAULT | RK_MMU_IRQ_BUS_ERROR) + +#define NUM_DT_ENTRIES 1024 +#define NUM_PT_ENTRIES 1024 + +#define SPAGE_ORDER 12 +#define SPAGE_SIZE (1 << SPAGE_ORDER) + + /* + * Support mapping any size that fits in one page table: + * 4 KiB to 4 MiB + */ +#define RK_IOMMU_PGSIZE_BITMAP 0x007ff000 + +#define IOMMU_REG_POLL_COUNT_FAST 1000 + +struct rk_iommu_domain { + struct list_head iommus; + u32 *dt; /* page directory table */ + spinlock_t iommus_lock; /* lock for iommus list */ + spinlock_t dt_lock; /* lock for modifying page directory table */ +}; + +struct rk_iommu { + struct device *dev; + void __iomem *base; + int irq; + struct list_head node; /* entry in rk_iommu_domain.iommus */ + struct iommu_domain *domain; /* domain to which iommu is attached */ +}; + +static inline void rk_table_flush(u32 *va, unsigned int count) +{ + phys_addr_t pa_start = virt_to_phys(va); + phys_addr_t pa_end = virt_to_phys(va + count); + size_t size = pa_end - pa_start; + + __cpuc_flush_dcache_area(va, size); + outer_flush_range(pa_start, pa_end); +} + +/** + * Inspired by _wait_for in intel_drv.h + * This is NOT safe for use in interrupt context. + * + * Note that it's important that we check the condition again after having + * timed out, since the timeout could be due to preemption or similar and + * we've never had a chance to check the condition before the timeout. + */ +#define rk_wait_for(COND, MS) ({ \ + unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1; \ + int ret__ = 0; \ + while (!(COND)) { \ + if (time_after(jiffies, timeout__)) { \ + ret__ = (COND) ? 0 : -ETIMEDOUT; \ + break; \ + } \ + usleep_range(50, 100); \ + } \ + ret__; \ +}) + +/* + * The Rockchip rk3288 iommu uses a 2-level page table. + * The first level is the "Directory Table" (DT). + * The DT consists of 1024 4-byte Directory Table Entries (DTEs), each pointing + * to a "Page Table". + * The second level is the 1024 Page Tables (PT). + * Each PT consists of 1024 4-byte Page Table Entries (PTEs), each pointing to + * a 4 KB page of physical memory. + * + * The DT and each PT fits in a single 4 KB page (4-bytes * 1024 entries). + * Each iommu device has a MMU_DTE_ADDR register that contains the physical + * address of the start of the DT page. + * + * The structure of the page table is as follows: + * + * DT + * MMU_DTE_ADDR -> +-----+ + * | | + * +-----+ PT + * | DTE | -> +-----+ + * +-----+ | | Memory + * | | +-----+ Page + * | | | PTE | -> +-----+ + * +-----+ +-----+ | | + * | | | | + * | | | | + * +-----+ | | + * | | + * | | + * +-----+ + */ + +/* + * Each DTE has a PT address and a valid bit: + * +---------------------+-----------+-+ + * | PT address | Reserved |V| + * +---------------------+-----------+-+ + * 31:12 - PT address (PTs always starts on a 4 KB boundary) + * 11: 1 - Reserved + * 0 - 1 if PT @ PT address is valid + */ +#define RK_DTE_PT_ADDRESS_MASK 0xfffff000 +#define RK_DTE_PT_VALID BIT(0) + +static inline phys_addr_t rk_dte_pt_address(u32 dte) +{ + return (phys_addr_t)dte & RK_DTE_PT_ADDRESS_MASK; +} + +static inline bool rk_dte_is_pt_valid(u32 dte) +{ + return dte & RK_DTE_PT_VALID; +} + +static u32 rk_mk_dte(u32 *pt) +{ + phys_addr_t pt_phys = virt_to_phys(pt); + return (pt_phys & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID; +} + +/* + * Each PTE has a Page address, some flags and a valid bit: + * +---------------------+---+-------+-+ + * | Page address |Rsv| Flags |V| + * +---------------------+---+-------+-+ + * 31:12 - Page address (Pages always start on a 4 KB boundary) + * 11: 9 - Reserved + * 8: 1 - Flags + * 8 - Read allocate - allocate cache space on read misses + * 7 - Read cache - enable cache & prefetch of data + * 6 - Write buffer - enable delaying writes on their way to memory + * 5 - Write allocate - allocate cache space on write misses + * 4 - Write cache - different writes can be merged together + * 3 - Override cache attributes + * if 1, bits 4-8 control cache attributes + * if 0, the system bus defaults are used + * 2 - Writable + * 1 - Readable + * 0 - 1 if Page @ Page address is valid + */ +#define RK_PTE_PAGE_ADDRESS_MASK 0xfffff000 +#define RK_PTE_PAGE_FLAGS_MASK 0x000001fe +#define RK_PTE_PAGE_WRITABLE BIT(2) +#define RK_PTE_PAGE_READABLE BIT(1) +#define RK_PTE_PAGE_VALID BIT(0) + +static inline phys_addr_t rk_pte_page_address(u32 pte) +{ + return (phys_addr_t)pte & RK_PTE_PAGE_ADDRESS_MASK; +} + +static inline bool rk_pte_is_page_valid(u32 pte) +{ + return pte & RK_PTE_PAGE_VALID; +} + +/* TODO: set cache flags per prot IOMMU_CACHE */ +static u32 rk_mk_pte(phys_addr_t page, int prot) +{ + u32 flags = 0; + flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE : 0; + flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE : 0; + page &= RK_PTE_PAGE_ADDRESS_MASK; + return page | flags | RK_PTE_PAGE_VALID; +} + +static u32 rk_mk_pte_invalid(u32 pte) +{ + return pte & ~RK_PTE_PAGE_VALID; +} + +/* + * rk3288 iova (IOMMU Virtual Address) format + * 31 22.21 12.11 0 + * +-----------+-----------+-------------+ + * | DTE index | PTE index | Page offset | + * +-----------+-----------+-------------+ + * 31:22 - DTE index - index of DTE in DT + * 21:12 - PTE index - index of PTE in PT @ DTE.pt_address + * 11: 0 - Page offset - offset into page @ PTE.page_address + */ +#define RK_IOVA_DTE_MASK 0xffc00000 +#define RK_IOVA_DTE_SHIFT 22 +#define RK_IOVA_PTE_MASK 0x003ff000 +#define RK_IOVA_PTE_SHIFT 12 +#define RK_IOVA_PAGE_MASK 0x00000fff +#define RK_IOVA_PAGE_SHIFT 0 + +static u32 rk_iova_dte_index(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_DTE_MASK) >> RK_IOVA_DTE_SHIFT; +} + +static u32 rk_iova_pte_index(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_PTE_MASK) >> RK_IOVA_PTE_SHIFT; +} + +static u32 rk_iova_page_offset(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_PAGE_MASK) >> RK_IOVA_PAGE_SHIFT; +} + +static u32 rk_iommu_read(struct rk_iommu *iommu, u32 offset) +{ + return readl(iommu->base + offset); +} + +static void rk_iommu_write(struct rk_iommu *iommu, u32 offset, u32 value) +{ + writel(value, iommu->base + offset); +} + +static void rk_iommu_command(struct rk_iommu *iommu, u32 command) +{ + writel(command, iommu->base + RK_MMU_COMMAND); +} + +static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova, + size_t size) +{ + dma_addr_t iova_end = iova + size; + /* + * TODO(djkurtz): Figure out when it is more efficient to shootdown the + * entire iotlb rather than iterate over individual iovas. + */ + for (; iova < iova_end; iova += SPAGE_SIZE) + rk_iommu_write(iommu, RK_MMU_ZAP_ONE_LINE, iova); +} + +static bool rk_iommu_is_stall_active(struct rk_iommu *iommu) +{ + return rk_iommu_read(iommu, RK_MMU_STATUS) & RK_MMU_STATUS_STALL_ACTIVE; +} + +static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu) +{ + return rk_iommu_read(iommu, RK_MMU_STATUS) & + RK_MMU_STATUS_PAGING_ENABLED; +} + +static int rk_iommu_enable_stall(struct rk_iommu *iommu) +{ + int ret; + + if (rk_iommu_is_stall_active(iommu)) + return 0; + + /* Stall can only be enabled if paging is enabled */ + if (!rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL); + + ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1); + if (ret) + dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_disable_stall(struct rk_iommu *iommu) +{ + int ret; + + if (!rk_iommu_is_stall_active(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL); + + ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1); + if (ret) + dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_enable_paging(struct rk_iommu *iommu) +{ + int ret; + + if (rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING); + + ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1); + if (ret) + dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_disable_paging(struct rk_iommu *iommu) +{ + int ret; + + if (!rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING); + + ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1); + if (ret) + dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_force_reset(struct rk_iommu *iommu) +{ + int ret; + u32 dte_addr; + + /* + * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY + * and verifying that upper 5 nybbles are read back. + */ + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, DTE_ADDR_DUMMY); + + dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR); + if (dte_addr != (DTE_ADDR_DUMMY & RK_DTE_PT_ADDRESS_MASK)) { + dev_err(iommu->dev, "Error during raw reset. MMU_DTE_ADDR is not functioning\n"); + return -EFAULT; + } + + rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET); + + ret = rk_wait_for(rk_iommu_read(iommu, RK_MMU_DTE_ADDR) == 0x00000000, + FORCE_RESET_TIMEOUT); + if (ret) + dev_err(iommu->dev, "FORCE_RESET command timed out\n"); + + return ret; +} + +static void log_iova(struct rk_iommu *iommu, dma_addr_t iova) +{ + u32 dte_index, pte_index, page_offset; + u32 mmu_dte_addr; + phys_addr_t mmu_dte_addr_phys, dte_addr_phys; + u32 *dte_addr; + u32 dte; + phys_addr_t pte_addr_phys = 0; + u32 *pte_addr = NULL; + u32 pte = 0; + phys_addr_t page_addr_phys = 0; + u32 page_flags = 0; + + dte_index = rk_iova_dte_index(iova); + pte_index = rk_iova_pte_index(iova); + page_offset = rk_iova_page_offset(iova); + + mmu_dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR); + mmu_dte_addr_phys = (phys_addr_t)mmu_dte_addr; + + dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index); + dte_addr = phys_to_virt(dte_addr_phys); + dte = *dte_addr; + + if (!rk_dte_is_pt_valid(dte)) + goto print_it; + + pte_addr_phys = rk_dte_pt_address(dte) + (pte_index * 4); + pte_addr = phys_to_virt(pte_addr_phys); + pte = *pte_addr; + + if (!rk_pte_is_page_valid(pte)) + goto print_it; + + page_addr_phys = rk_pte_page_address(pte) + page_offset; + page_flags = pte & RK_PTE_PAGE_FLAGS_MASK; + +print_it: + dev_err(iommu->dev, "iova = %pad: dte_index: %#03x pte_index: %#03x page_offset: %#03x\n", + &iova, dte_index, pte_index, page_offset); + dev_err(iommu->dev, "mmu_dte_addr: %pa dte@%pa: %#08x valid: %u pte@%pa: %#08x valid: %u page@%pa flags: %#03x\n", + &mmu_dte_addr_phys, &dte_addr_phys, dte, + rk_dte_is_pt_valid(dte), &pte_addr_phys, pte, + rk_pte_is_page_valid(pte), &page_addr_phys, page_flags); +} + +static irqreturn_t rk_iommu_irq(int irq, void *dev_id) +{ + struct rk_iommu *iommu = dev_id; + u32 status; + u32 int_status; + dma_addr_t iova; + + int_status = rk_iommu_read(iommu, RK_MMU_INT_STATUS); + if (int_status == 0) + return IRQ_NONE; + + iova = rk_iommu_read(iommu, RK_MMU_PAGE_FAULT_ADDR); + + if (int_status & RK_MMU_IRQ_PAGE_FAULT) { + int flags; + + status = rk_iommu_read(iommu, RK_MMU_STATUS); + flags = (status & RK_MMU_STATUS_PAGE_FAULT_IS_WRITE) ? + IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; + + dev_err(iommu->dev, "Page fault at %pad of type %s\n", + &iova, + (flags == IOMMU_FAULT_WRITE) ? "write" : "read"); + + log_iova(iommu, iova); + + /* + * Report page fault to any installed handlers. + * Ignore the return code, though, since we always zap cache + * and clear the page fault anyway. + */ + if (iommu->domain) + report_iommu_fault(iommu->domain, iommu->dev, iova, + flags); + else + dev_err(iommu->dev, "Page fault while iommu not attached to domain?\n"); + + rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE); + rk_iommu_command(iommu, RK_MMU_CMD_PAGE_FAULT_DONE); + } + + if (int_status & RK_MMU_IRQ_BUS_ERROR) + dev_err(iommu->dev, "BUS_ERROR occurred at %pad\n", &iova); + + if (int_status & ~RK_MMU_IRQ_MASK) + dev_err(iommu->dev, "unexpected int_status: %#08x\n", + int_status); + + rk_iommu_write(iommu, RK_MMU_INT_CLEAR, int_status); + + return IRQ_HANDLED; +} + +static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + phys_addr_t pt_phys, phys = 0; + u32 dte, pte; + u32 *page_table; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + dte = rk_domain->dt[rk_iova_dte_index(iova)]; + if (!rk_dte_is_pt_valid(dte)) + goto out; + + pt_phys = rk_dte_pt_address(dte); + page_table = (u32 *)phys_to_virt(pt_phys); + pte = page_table[rk_iova_pte_index(iova)]; + if (!rk_pte_is_page_valid(pte)) + goto out; + + phys = rk_pte_page_address(pte) + rk_iova_page_offset(iova); +out: + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + return phys; +} + +static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain, + dma_addr_t iova, size_t size) +{ + struct list_head *pos; + unsigned long flags; + + /* shootdown these iova from all iommus using this domain */ + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_for_each(pos, &rk_domain->iommus) { + struct rk_iommu *iommu; + iommu = list_entry(pos, struct rk_iommu, node); + rk_iommu_zap_lines(iommu, iova, size); + } + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); +} + +static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, + dma_addr_t iova) +{ + u32 *page_table, *dte_addr; + u32 dte; + phys_addr_t pt_phys; + + assert_spin_locked(&rk_domain->dt_lock); + + dte_addr = &rk_domain->dt[rk_iova_dte_index(iova)]; + dte = *dte_addr; + if (rk_dte_is_pt_valid(dte)) + goto done; + + page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | GFP_DMA32); + if (!page_table) + return ERR_PTR(-ENOMEM); + + dte = rk_mk_dte(page_table); + *dte_addr = dte; + + rk_table_flush(page_table, NUM_PT_ENTRIES); + rk_table_flush(dte_addr, 1); + + /* + * Zap the first iova of newly allocated page table so iommu evicts + * old cached value of new dte from the iotlb. + */ + rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE); + +done: + pt_phys = rk_dte_pt_address(dte); + return (u32 *)phys_to_virt(pt_phys); +} + +static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain, + u32 *pte_addr, dma_addr_t iova, size_t size) +{ + unsigned int pte_count; + unsigned int pte_total = size / SPAGE_SIZE; + + assert_spin_locked(&rk_domain->dt_lock); + + for (pte_count = 0; pte_count < pte_total; pte_count++) { + u32 pte = pte_addr[pte_count]; + if (!rk_pte_is_page_valid(pte)) + break; + + pte_addr[pte_count] = rk_mk_pte_invalid(pte); + } + + rk_table_flush(pte_addr, pte_count); + + return pte_count * SPAGE_SIZE; +} + +static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr, + dma_addr_t iova, phys_addr_t paddr, size_t size, + int prot) +{ + unsigned int pte_count; + unsigned int pte_total = size / SPAGE_SIZE; + phys_addr_t page_phys; + + assert_spin_locked(&rk_domain->dt_lock); + + for (pte_count = 0; pte_count < pte_total; pte_count++) { + u32 pte = pte_addr[pte_count]; + + if (rk_pte_is_page_valid(pte)) + goto unwind; + + pte_addr[pte_count] = rk_mk_pte(paddr, prot); + + paddr += SPAGE_SIZE; + } + + rk_table_flush(pte_addr, pte_count); + + return 0; +unwind: + /* Unmap the range of iovas that we just mapped */ + rk_iommu_unmap_iova(rk_domain, pte_addr, iova, pte_count * SPAGE_SIZE); + + iova += pte_count * SPAGE_SIZE; + page_phys = rk_pte_page_address(pte_addr[pte_count]); + pr_err("iova: %pad already mapped to %pa cannot remap to phys: %pa prot: %#x\n", + &iova, &page_phys, &paddr, prot); + + return -EADDRINUSE; +} + +static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, + phys_addr_t paddr, size_t size, int prot) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + dma_addr_t iova = (dma_addr_t)_iova; + u32 *page_table, *pte_addr; + int ret; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + /* + * pgsize_bitmap specifies iova sizes that fit in one page table + * (1024 4-KiB pages = 4 MiB). + * So, size will always be 4096 <= size <= 4194304. + * Since iommu_map() guarantees that both iova and size will be + * aligned, we will always only be mapping from a single dte here. + */ + page_table = rk_dte_get_page_table(rk_domain, iova); + if (IS_ERR(page_table)) { + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + return PTR_ERR(page_table); + } + + pte_addr = &page_table[rk_iova_pte_index(iova)]; + ret = rk_iommu_map_iova(rk_domain, pte_addr, iova, paddr, size, prot); + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + return ret; +} + +static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, + size_t size) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + dma_addr_t iova = (dma_addr_t)_iova; + phys_addr_t pt_phys; + u32 dte; + u32 *pte_addr; + size_t unmap_size; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + /* + * pgsize_bitmap specifies iova sizes that fit in one page table + * (1024 4-KiB pages = 4 MiB). + * So, size will always be 4096 <= size <= 4194304. + * Since iommu_unmap() guarantees that both iova and size will be + * aligned, we will always only be unmapping from a single dte here. + */ + dte = rk_domain->dt[rk_iova_dte_index(iova)]; + /* Just return 0 if iova is unmapped */ + if (!rk_dte_is_pt_valid(dte)) { + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + return 0; + } + + pt_phys = rk_dte_pt_address(dte); + pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova); + unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, iova, size); + + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + /* Shootdown iotlb entries for iova range that was just unmapped */ + rk_iommu_zap_iova(rk_domain, iova, unmap_size); + + return unmap_size; +} + +static struct rk_iommu *rk_iommu_from_dev(struct device *dev) +{ + struct iommu_group *group; + struct device *iommu_dev; + struct rk_iommu *rk_iommu; + + group = iommu_group_get(dev); + if (!group) + return NULL; + iommu_dev = iommu_group_get_iommudata(group); + rk_iommu = dev_get_drvdata(iommu_dev); + iommu_group_put(group); + + return rk_iommu; +} + +static int rk_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + int ret; + phys_addr_t dte_addr; + + /* + * Allow 'virtual devices' (e.g., drm) to attach to domain. + * Such a device does not belong to an iommu group. + */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return 0; + + ret = rk_iommu_enable_stall(iommu); + if (ret) + return ret; + + ret = rk_iommu_force_reset(iommu); + if (ret) + return ret; + + iommu->domain = domain; + + ret = devm_request_irq(dev, iommu->irq, rk_iommu_irq, + IRQF_SHARED, dev_name(dev), iommu); + if (ret) + return ret; + + dte_addr = virt_to_phys(rk_domain->dt); + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, dte_addr); + rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE); + rk_iommu_write(iommu, RK_MMU_INT_MASK, RK_MMU_IRQ_MASK); + + ret = rk_iommu_enable_paging(iommu); + if (ret) + return ret; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_add_tail(&iommu->node, &rk_domain->iommus); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + dev_info(dev, "Attached to iommu domain\n"); + + rk_iommu_disable_stall(iommu); + + return 0; +} + +static void rk_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + + /* Allow 'virtual devices' (eg drm) to detach from domain */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_del_init(&iommu->node); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + /* Ignore error while disabling, just keep going */ + rk_iommu_enable_stall(iommu); + rk_iommu_disable_paging(iommu); + rk_iommu_write(iommu, RK_MMU_INT_MASK, 0); + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, 0); + rk_iommu_disable_stall(iommu); + + devm_free_irq(dev, iommu->irq, iommu); + + iommu->domain = NULL; + + dev_info(dev, "Detached from iommu domain\n"); +} + +static int rk_iommu_domain_init(struct iommu_domain *domain) +{ + struct rk_iommu_domain *rk_domain; + + rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL); + if (!rk_domain) + return -ENOMEM; + + /* + * rk32xx iommus use a 2 level pagetable. + * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries. + * Allocate one 4 KiB page for each table. + */ + rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32); + if (!rk_domain->dt) + goto err_dt; + + rk_table_flush(rk_domain->dt, NUM_DT_ENTRIES); + + spin_lock_init(&rk_domain->iommus_lock); + spin_lock_init(&rk_domain->dt_lock); + INIT_LIST_HEAD(&rk_domain->iommus); + + domain->priv = rk_domain; + + return 0; +err_dt: + kfree(rk_domain); + return -ENOMEM; +} + +static void rk_iommu_domain_destroy(struct iommu_domain *domain) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + int i; + + WARN_ON(!list_empty(&rk_domain->iommus)); + + for (i = 0; i < NUM_DT_ENTRIES; i++) { + u32 dte = rk_domain->dt[i]; + if (rk_dte_is_pt_valid(dte)) { + phys_addr_t pt_phys = rk_dte_pt_address(dte); + u32 *page_table = phys_to_virt(pt_phys); + free_page((unsigned long)page_table); + } + } + + free_page((unsigned long)rk_domain->dt); + kfree(domain->priv); + domain->priv = NULL; +} + +static bool rk_iommu_is_dev_iommu_master(struct device *dev) +{ + struct device_node *np = dev->of_node; + int ret; + + /* + * An iommu master has an iommus property containing a list of phandles + * to iommu nodes, each with an #iommu-cells property with value 0. + */ + ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells"); + return (ret > 0); +} + +static int rk_iommu_group_set_iommudata(struct iommu_group *group, + struct device *dev) +{ + struct device_node *np = dev->of_node; + struct platform_device *pd; + int ret; + struct of_phandle_args args; + + /* + * An iommu master has an iommus property containing a list of phandles + * to iommu nodes, each with an #iommu-cells property with value 0. + */ + ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0, + &args); + if (ret) { + dev_err(dev, "of_parse_phandle_with_args(%s) => %d\n", + np->full_name, ret); + return ret; + } + if (args.args_count != 0) { + dev_err(dev, "incorrect number of iommu params found for %s (found %d, expected 0)\n", + args.np->full_name, args.args_count); + return -EINVAL; + } + + pd = of_find_device_by_node(args.np); + of_node_put(args.np); + if (!pd) { + dev_err(dev, "iommu %s not found\n", args.np->full_name); + return -EPROBE_DEFER; + } + + /* TODO(djkurtz): handle multiple slave iommus for a single master */ + iommu_group_set_iommudata(group, &pd->dev, NULL); + + return 0; +} + +static int rk_iommu_add_device(struct device *dev) +{ + struct iommu_group *group; + int ret; + + if (!rk_iommu_is_dev_iommu_master(dev)) + return -ENODEV; + + group = iommu_group_get(dev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) { + dev_err(dev, "Failed to allocate IOMMU group\n"); + return PTR_ERR(group); + } + } + + ret = iommu_group_add_device(group, dev); + if (ret) + goto err_put_group; + + ret = rk_iommu_group_set_iommudata(group, dev); + if (ret) + goto err_remove_device; + + iommu_group_put(group); + + return 0; + +err_remove_device: + iommu_group_remove_device(dev); +err_put_group: + iommu_group_put(group); + return ret; +} + +static void rk_iommu_remove_device(struct device *dev) +{ + if (!rk_iommu_is_dev_iommu_master(dev)) + return; + + iommu_group_remove_device(dev); +} + +static const struct iommu_ops rk_iommu_ops = { + .domain_init = rk_iommu_domain_init, + .domain_destroy = rk_iommu_domain_destroy, + .attach_dev = rk_iommu_attach_device, + .detach_dev = rk_iommu_detach_device, + .map = rk_iommu_map, + .unmap = rk_iommu_unmap, + .add_device = rk_iommu_add_device, + .remove_device = rk_iommu_remove_device, + .iova_to_phys = rk_iommu_iova_to_phys, + .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, +}; + +static int rk_iommu_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rk_iommu *iommu; + struct resource *res; + + iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); + if (!iommu) + return -ENOMEM; + + platform_set_drvdata(pdev, iommu); + iommu->dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + iommu->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(iommu->base)) + return PTR_ERR(iommu->base); + + iommu->irq = platform_get_irq(pdev, 0); + if (iommu->irq < 0) { + dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq); + return -ENXIO; + } + + return 0; +} + +static int rk_iommu_remove(struct platform_device *pdev) +{ + return 0; +} + +#ifdef CONFIG_OF +static const struct of_device_id rk_iommu_dt_ids[] = { + { .compatible = "rockchip,iommu" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids); +#endif + +static struct platform_driver rk_iommu_driver = { + .probe = rk_iommu_probe, + .remove = rk_iommu_remove, + .driver = { + .name = "rk_iommu", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(rk_iommu_dt_ids), + }, +}; + +static int __init rk_iommu_init(void) +{ + int ret; + + ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops); + if (ret) + return ret; + + return platform_driver_register(&rk_iommu_driver); +} +static void __exit rk_iommu_exit(void) +{ + platform_driver_unregister(&rk_iommu_driver); +} + +subsys_initcall(rk_iommu_init); +module_exit(rk_iommu_exit); + +MODULE_DESCRIPTION("IOMMU API for Rockchip"); +MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>"); +MODULE_ALIAS("platform:rockchip-iommu"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c index 1333e6fb3405..f1b00774e4de 100644 --- a/drivers/iommu/shmobile-iommu.c +++ b/drivers/iommu/shmobile-iommu.c @@ -361,6 +361,7 @@ static const struct iommu_ops shmobile_iommu_ops = { .detach_dev = shmobile_iommu_detach_device, .map = shmobile_iommu_map, .unmap = shmobile_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = shmobile_iommu_iova_to_phys, .add_device = shmobile_iommu_add_device, .pgsize_bitmap = SZ_1M | SZ_64K | SZ_4K, diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 3afdf43f732a..73e845a66925 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -955,6 +955,7 @@ static const struct iommu_ops smmu_iommu_ops = { .detach_dev = smmu_iommu_detach_dev, .map = smmu_iommu_map, .unmap = smmu_iommu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = smmu_iommu_iova_to_phys, .pgsize_bitmap = SMMU_IOMMU_PGSIZES, }; |