diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 86 | ||||
-rw-r--r-- | drivers/iommu/Makefile | 2 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.c | 33 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_init.c | 12 | ||||
-rw-r--r-- | drivers/iommu/dmar.c | 5 | ||||
-rw-r--r-- | drivers/iommu/exynos-iommu.c | 2 | ||||
-rw-r--r-- | drivers/iommu/intel-iommu.c | 10 | ||||
-rw-r--r-- | drivers/iommu/intel_irq_remapping.c | 48 | ||||
-rw-r--r-- | drivers/iommu/iommu.c | 66 | ||||
-rw-r--r-- | drivers/iommu/irq_remapping.c | 232 | ||||
-rw-r--r-- | drivers/iommu/irq_remapping.h | 1 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu.c | 4 | ||||
-rw-r--r-- | drivers/iommu/shmobile-iommu.c | 395 | ||||
-rw-r--r-- | drivers/iommu/shmobile-ipmmu.c | 136 | ||||
-rw-r--r-- | drivers/iommu/shmobile-ipmmu.h | 34 | ||||
-rw-r--r-- | drivers/iommu/tegra-gart.c | 4 | ||||
-rw-r--r-- | drivers/iommu/tegra-smmu.c | 98 |
17 files changed, 1058 insertions, 110 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e39f9db..c332fb9 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -65,8 +65,8 @@ config AMD_IOMMU_STATS If unsure, say N. config AMD_IOMMU_V2 - tristate "AMD IOMMU Version 2 driver (EXPERIMENTAL)" - depends on AMD_IOMMU && PROFILING && EXPERIMENTAL + tristate "AMD IOMMU Version 2 driver" + depends on AMD_IOMMU && PROFILING select MMU_NOTIFIER ---help--- This option enables support for the AMD IOMMUv2 features of the IOMMU @@ -119,8 +119,8 @@ config INTEL_IOMMU_FLOPPY_WA 16MiB to make floppy (an ISA device) work. config IRQ_REMAP - bool "Support for Interrupt Remapping (EXPERIMENTAL)" - depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL + bool "Support for Interrupt Remapping" + depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI select DMAR_TABLE ---help--- Supports Interrupt remapping for IO-APIC and MSI devices. @@ -130,7 +130,7 @@ config IRQ_REMAP # OMAP IOMMU support config OMAP_IOMMU bool "OMAP IOMMU Support" - depends on ARCH_OMAP + depends on ARCH_OMAP2PLUS select IOMMU_API config OMAP_IOVMM @@ -158,7 +158,7 @@ config TEGRA_IOMMU_GART config TEGRA_IOMMU_SMMU bool "Tegra SMMU IOMMU Support" - depends on ARCH_TEGRA_3x_SOC && TEGRA_AHB + depends on ARCH_TEGRA && TEGRA_AHB select IOMMU_API help Enables support for remapping discontiguous physical memory @@ -187,4 +187,78 @@ config EXYNOS_IOMMU_DEBUG Say N unless you need kernel log message for IOMMU debugging +config SHMOBILE_IPMMU + bool + +config SHMOBILE_IPMMU_TLB + bool + +config SHMOBILE_IOMMU + bool "IOMMU for Renesas IPMMU/IPMMUI" + default n + depends on (ARM && ARCH_SHMOBILE) + select IOMMU_API + select ARM_DMA_USE_IOMMU + select SHMOBILE_IPMMU + select SHMOBILE_IPMMU_TLB + help + Support for Renesas IPMMU/IPMMUI. This option enables + remapping of DMA memory accesses from all of the IP blocks + on the ICB. + + Warning: Drivers (including userspace drivers of UIO + devices) of the IP blocks on the ICB *must* use addresses + allocated from the IPMMU (iova) for DMA with this option + enabled. + + If unsure, say N. + +choice + prompt "IPMMU/IPMMUI address space size" + default SHMOBILE_IOMMU_ADDRSIZE_2048MB + depends on SHMOBILE_IOMMU + help + This option sets IPMMU/IPMMUI address space size by + adjusting the 1st level page table size. The page table size + is calculated as follows: + + page table size = number of page table entries * 4 bytes + number of page table entries = address space size / 1 MiB + + For example, when the address space size is 2048 MiB, the + 1st level page table size is 8192 bytes. + + config SHMOBILE_IOMMU_ADDRSIZE_2048MB + bool "2 GiB" + + config SHMOBILE_IOMMU_ADDRSIZE_1024MB + bool "1 GiB" + + config SHMOBILE_IOMMU_ADDRSIZE_512MB + bool "512 MiB" + + config SHMOBILE_IOMMU_ADDRSIZE_256MB + bool "256 MiB" + + config SHMOBILE_IOMMU_ADDRSIZE_128MB + bool "128 MiB" + + config SHMOBILE_IOMMU_ADDRSIZE_64MB + bool "64 MiB" + + config SHMOBILE_IOMMU_ADDRSIZE_32MB + bool "32 MiB" + +endchoice + +config SHMOBILE_IOMMU_L1SIZE + int + default 8192 if SHMOBILE_IOMMU_ADDRSIZE_2048MB + default 4096 if SHMOBILE_IOMMU_ADDRSIZE_1024MB + default 2048 if SHMOBILE_IOMMU_ADDRSIZE_512MB + default 1024 if SHMOBILE_IOMMU_ADDRSIZE_256MB + default 512 if SHMOBILE_IOMMU_ADDRSIZE_128MB + default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB + default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB + endif # IOMMU_SUPPORT diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index f66b816..ef0e520 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -13,3 +13,5 @@ obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o +obj-$(CONFIG_SHMOBILE_IOMMU) += shmobile-iommu.o +obj-$(CONFIG_SHMOBILE_IPMMU) += shmobile-ipmmu.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index c1c74e0..b287ca3 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2466,18 +2466,16 @@ static int device_change_notifier(struct notifier_block *nb, /* allocate a protection domain if a device is added */ dma_domain = find_protection_domain(devid); - if (dma_domain) - goto out; - dma_domain = dma_ops_domain_alloc(); - if (!dma_domain) - goto out; - dma_domain->target_dev = devid; - - spin_lock_irqsave(&iommu_pd_list_lock, flags); - list_add_tail(&dma_domain->list, &iommu_pd_list); - spin_unlock_irqrestore(&iommu_pd_list_lock, flags); - - dev_data = get_dev_data(dev); + if (!dma_domain) { + dma_domain = dma_ops_domain_alloc(); + if (!dma_domain) + goto out; + dma_domain->target_dev = devid; + + spin_lock_irqsave(&iommu_pd_list_lock, flags); + list_add_tail(&dma_domain->list, &iommu_pd_list); + spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + } dev->archdata.dma_ops = &amd_iommu_dma_ops; @@ -3187,8 +3185,7 @@ int __init amd_iommu_init_dma_ops(void) free_domains: for_each_iommu(iommu) { - if (iommu->default_dom) - dma_ops_domain_free(iommu->default_dom); + dma_ops_domain_free(iommu->default_dom); } return ret; @@ -4017,10 +4014,10 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count) index -= count - 1; + cfg->remapped = 1; irte_info = &cfg->irq_2_iommu; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; goto out; } @@ -4127,9 +4124,9 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, index = attr->ioapic_pin; /* Setup IRQ remapping info */ + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; /* Setup IRTE for IOMMU */ irte.val = 0; @@ -4288,9 +4285,9 @@ static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq, devid = get_device_id(&pdev->dev); irte_info = &cfg->irq_2_iommu; + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index + offset; - irte_info->iommu = (void *)cfg; return 0; } @@ -4314,9 +4311,9 @@ static int setup_hpet_msi(unsigned int irq, unsigned int id) if (index < 0) return index; + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; return 0; } diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index faf10ba..e3c2d74 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -980,7 +980,7 @@ static void __init free_iommu_all(void) * BIOS should disable L2B micellaneous clock gating by setting * L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b */ -static void __init amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) +static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) { u32 value; @@ -1876,11 +1876,6 @@ static int amd_iommu_init_dma(void) struct amd_iommu *iommu; int ret; - init_device_table_dma(); - - for_each_iommu(iommu) - iommu_flush_all_caches(iommu); - if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else @@ -1889,6 +1884,11 @@ static int amd_iommu_init_dma(void) if (ret) return ret; + init_device_table_dma(); + + for_each_iommu(iommu) + iommu_flush_all_caches(iommu); + amd_iommu_init_api(); amd_iommu_init_notifier(); diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 86e2f4a..e5cdaf8 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -41,6 +41,8 @@ #include <asm/irq_remapping.h> #include <asm/iommu_table.h> +#include "irq_remapping.h" + /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of * these units are not supported by the architecture. @@ -1040,7 +1042,7 @@ int dmar_enable_qi(struct intel_iommu *iommu) qi->desc = page_address(desc_page); - qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC); + qi->desc_status = kzalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC); if (!qi->desc_status) { free_page((unsigned long) qi->desc); kfree(qi); @@ -1081,6 +1083,7 @@ static const char *dma_remap_fault_reasons[] = "non-zero reserved fields in RTP", "non-zero reserved fields in CTP", "non-zero reserved fields in PTE", + "PCE for translation request specifies blocking", }; static const char *irq_remap_fault_reasons[] = diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 7fe44f8..238a3ca 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -511,7 +511,7 @@ int exynos_sysmmu_enable(struct device *dev, unsigned long pgtable) return ret; } -bool exynos_sysmmu_disable(struct device *dev) +static bool exynos_sysmmu_disable(struct device *dev) { struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); bool disabled; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index eca2801..0099667 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -46,6 +46,8 @@ #include <asm/cacheflush.h> #include <asm/iommu.h> +#include "irq_remapping.h" + #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE @@ -4253,13 +4255,19 @@ static void quirk_iommu_rwbf(struct pci_dev *dev) { /* * Mobile 4 Series Chipset neglects to set RWBF capability, - * but needs it: + * but needs it. Same seems to hold for the desktop versions. */ printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n"); rwbf_quirk = 1; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_rwbf); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_rwbf); #define GGC 0x52 #define GGC_MEMORY_SIZE_MASK (0xf << 8) diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index af8904d..f3b8f23 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -68,6 +68,7 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) { struct ir_table *table = iommu->ir_table; struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); u16 index, start_index; unsigned int mask = 0; unsigned long flags; @@ -115,6 +116,7 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) for (i = index; i < index + count; i++) table->base[i].present = 1; + cfg->remapped = 1; irq_iommu->iommu = iommu; irq_iommu->irte_index = index; irq_iommu->sub_handle = 0; @@ -155,6 +157,7 @@ static int map_irq_to_irte_handle(int irq, u16 *sub_handle) static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle) { struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; if (!irq_iommu) @@ -162,6 +165,7 @@ static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subha raw_spin_lock_irqsave(&irq_2_ir_lock, flags); + cfg->remapped = 1; irq_iommu->iommu = iommu; irq_iommu->irte_index = index; irq_iommu->sub_handle = subhandle; @@ -425,11 +429,22 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode) /* Enable interrupt-remapping */ iommu->gcmd |= DMA_GCMD_IRE; + iommu->gcmd &= ~DMA_GCMD_CFI; /* Block compatibility-format MSIs */ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_IRES), sts); + /* + * With CFI clear in the Global Command register, we should be + * protected from dangerous (i.e. compatibility) interrupts + * regardless of x2apic status. Check just to be sure. + */ + if (sts & DMA_GSTS_CFIS) + WARN(1, KERN_WARNING + "Compatibility-format IRQs enabled despite intr remapping;\n" + "you are vulnerable to IRQ injection.\n"); + raw_spin_unlock_irqrestore(&iommu->register_lock, flags); } @@ -526,20 +541,24 @@ static int __init intel_irq_remapping_supported(void) static int __init intel_enable_irq_remapping(void) { struct dmar_drhd_unit *drhd; + bool x2apic_present; int setup = 0; int eim = 0; + x2apic_present = x2apic_supported(); + if (parse_ioapics_under_ir() != 1) { printk(KERN_INFO "Not enable interrupt remapping\n"); - return -1; + goto error; } - if (x2apic_supported()) { + if (x2apic_present) { eim = !dmar_x2apic_optout(); - WARN(!eim, KERN_WARNING - "Your BIOS is broken and requested that x2apic be disabled\n" - "This will leave your machine vulnerable to irq-injection attacks\n" - "Use 'intremap=no_x2apic_optout' to override BIOS request\n"); + if (!eim) + printk(KERN_WARNING + "Your BIOS is broken and requested that x2apic be disabled.\n" + "This will slightly decrease performance.\n" + "Use 'intremap=no_x2apic_optout' to override BIOS request.\n"); } for_each_drhd_unit(drhd) { @@ -578,7 +597,7 @@ static int __init intel_enable_irq_remapping(void) if (eim && !ecap_eim_support(iommu->ecap)) { printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, " " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap); - return -1; + goto error; } } @@ -594,7 +613,7 @@ static int __init intel_enable_irq_remapping(void) printk(KERN_ERR "DRHD %Lx: failed to enable queued, " " invalidation, ecap %Lx, ret %d\n", drhd->reg_base_addr, iommu->ecap, ret); - return -1; + goto error; } } @@ -617,6 +636,14 @@ static int __init intel_enable_irq_remapping(void) goto error; irq_remapping_enabled = 1; + + /* + * VT-d has a different layout for IO-APIC entries when + * interrupt remapping is enabled. So it needs a special routine + * to print IO-APIC entries for debugging purposes too. + */ + x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries; + pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic"); return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE; @@ -625,6 +652,11 @@ error: /* * handle error condition gracefully here! */ + + if (x2apic_present) + WARN(1, KERN_WARNING + "Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n"); + return -1; } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index ddbdaca..b972d43 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -734,7 +734,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, size_t orig_size = size; int ret = 0; - if (unlikely(domain->ops->map == NULL)) + if (unlikely(domain->ops->unmap == NULL || + domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; /* find out the minimum page size supported */ @@ -808,7 +809,8 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) size_t unmapped_page, unmapped = 0; unsigned int min_pagesz; - if (unlikely(domain->ops->unmap == NULL)) + if (unlikely(domain->ops->unmap == NULL || + domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; /* find out the minimum page size supported */ @@ -850,6 +852,26 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) } EXPORT_SYMBOL_GPL(iommu_unmap); + +int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, + phys_addr_t paddr, u64 size) +{ + if (unlikely(domain->ops->domain_window_enable == NULL)) + return -ENODEV; + + return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size); +} +EXPORT_SYMBOL_GPL(iommu_domain_window_enable); + +void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) +{ + if (unlikely(domain->ops->domain_window_disable == NULL)) + return; + + return domain->ops->domain_window_disable(domain, wnd_nr); +} +EXPORT_SYMBOL_GPL(iommu_domain_window_disable); + static int __init iommu_init(void) { iommu_group_kset = kset_create_and_add("iommu_groups", @@ -861,13 +883,15 @@ static int __init iommu_init(void) return 0; } -subsys_initcall(iommu_init); +arch_initcall(iommu_init); int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { struct iommu_domain_geometry *geometry; + bool *paging; int ret = 0; + u32 *count; switch (attr) { case DOMAIN_ATTR_GEOMETRY: @@ -875,6 +899,19 @@ int iommu_domain_get_attr(struct iommu_domain *domain, *geometry = domain->geometry; break; + case DOMAIN_ATTR_PAGING: + paging = data; + *paging = (domain->ops->pgsize_bitmap != 0UL); + break; + case DOMAIN_ATTR_WINDOWS: + count = data; + + if (domain->ops->domain_get_windows != NULL) + *count = domain->ops->domain_get_windows(domain); + else + ret = -ENODEV; + + break; default: if (!domain->ops->domain_get_attr) return -EINVAL; @@ -889,9 +926,26 @@ EXPORT_SYMBOL_GPL(iommu_domain_get_attr); int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { - if (!domain->ops->domain_set_attr) - return -EINVAL; + int ret = 0; + u32 *count; - return domain->ops->domain_set_attr(domain, attr, data); + switch (attr) { + case DOMAIN_ATTR_WINDOWS: + count = data; + + if (domain->ops->domain_set_windows != NULL) + ret = domain->ops->domain_set_windows(domain, *count); + else + ret = -ENODEV; + + break; + default: + if (domain->ops->domain_set_attr == NULL) + return -EINVAL; + + ret = domain->ops->domain_set_attr(domain, attr, data); + } + + return ret; } EXPORT_SYMBOL_GPL(iommu_domain_set_attr); diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index faf85d6..7c11ff3 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -1,11 +1,17 @@ +#include <linux/seq_file.h> +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/string.h> -#include <linux/cpumask.h> #include <linux/errno.h> #include <linux/msi.h> +#include <linux/irq.h> +#include <linux/pci.h> #include <asm/hw_irq.h> #include <asm/irq_remapping.h> +#include <asm/processor.h> +#include <asm/x86_init.h> +#include <asm/apic.h> #include "irq_remapping.h" @@ -17,6 +23,152 @@ int no_x2apic_optout; static struct irq_remap_ops *remap_ops; +static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec); +static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, + int index, int sub_handle); +static int set_remapped_irq_affinity(struct irq_data *data, + const struct cpumask *mask, + bool force); + +static bool irq_remapped(struct irq_cfg *cfg) +{ + return (cfg->remapped == 1); +} + +static void irq_remapping_disable_io_apic(void) +{ + /* + * With interrupt-remapping, for now we will use virtual wire A + * mode, as virtual wire B is little complex (need to configure + * both IOAPIC RTE as well as interrupt-remapping table entry). + * As this gets called during crash dump, keep this simple for + * now. + */ + if (cpu_has_apic || apic_from_smp_config()) + disconnect_bsp_APIC(0); +} + +static int do_setup_msi_irqs(struct pci_dev *dev, int nvec) +{ + int node, ret, sub_handle, index = 0; + unsigned int irq; + struct msi_desc *msidesc; + + nvec = __roundup_pow_of_two(nvec); + + WARN_ON(!list_is_singular(&dev->msi_list)); + msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + WARN_ON(msidesc->irq); + WARN_ON(msidesc->msi_attrib.multiple); + + node = dev_to_node(&dev->dev); + irq = __create_irqs(get_nr_irqs_gsi(), nvec, node); + if (irq == 0) + return -ENOSPC; + + msidesc->msi_attrib.multiple = ilog2(nvec); + for (sub_handle = 0; sub_handle < nvec; sub_handle++) { + if (!sub_handle) { + index = msi_alloc_remapped_irq(dev, irq, nvec); + if (index < 0) { + ret = index; + goto error; + } + } else { + ret = msi_setup_remapped_irq(dev, irq + sub_handle, + index, sub_handle); + if (ret < 0) + goto error; + } + ret = setup_msi_irq(dev, msidesc, irq, sub_handle); + if (ret < 0) + goto error; + } + return 0; + +error: + destroy_irqs(irq, nvec); + + /* + * Restore altered MSI descriptor fields and prevent just destroyed + * IRQs from tearing down again in default_teardown_msi_irqs() + */ + msidesc->irq = 0; + msidesc->msi_attrib.multiple = 0; + + return ret; +} + +static int do_setup_msix_irqs(struct pci_dev *dev, int nvec) +{ + int node, ret, sub_handle, index = 0; + struct msi_desc *msidesc; + unsigned int irq; + + node = dev_to_node(&dev->dev); + irq = get_nr_irqs_gsi(); + sub_handle = 0; + + list_for_each_entry(msidesc, &dev->msi_list, list) { + + irq = create_irq_nr(irq, node); + if (irq == 0) + return -1; + + if (sub_handle == 0) + ret = index = msi_alloc_remapped_irq(dev, irq, nvec); + else + ret = msi_setup_remapped_irq(dev, irq, index, sub_handle); + + if (ret < 0) + goto error; + + ret = setup_msi_irq(dev, msidesc, irq, 0); + if (ret < 0) + goto error; + + sub_handle += 1; + irq += 1; + } + + return 0; + +error: + destroy_irq(irq); + return ret; +} + +static int irq_remapping_setup_msi_irqs(struct pci_dev *dev, + int nvec, int type) +{ + if (type == PCI_CAP_ID_MSI) + return do_setup_msi_irqs(dev, nvec); + else + return do_setup_msix_irqs(dev, nvec); +} + +void eoi_ioapic_pin_remapped(int apic, int pin, int vector) +{ + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + io_apic_eoi(apic, pin); +} + +static void __init irq_remapping_modify_x86_ops(void) +{ + x86_io_apic_ops.disable = irq_remapping_disable_io_apic; + x86_io_apic_ops.set_affinity = set_remapped_irq_affinity; + x86_io_apic_ops.setup_entry = setup_ioapic_remapped_entry; + x86_io_apic_ops.eoi_ioapic_pin = eoi_ioapic_pin_remapped; + x86_msi.setup_msi_irqs = irq_remapping_setup_msi_irqs; + x86_msi.setup_hpet_msi = setup_hpet_msi_remapped; + x86_msi.compose_msi_msg = compose_remapped_msi_msg; +} + static __init int setup_nointremap(char *str) { disable_irq_remap = 1; @@ -79,15 +231,24 @@ int __init irq_remapping_prepare(void) int __init irq_remapping_enable(void) { + int ret; + if (!remap_ops || !remap_ops->enable) return -ENODEV; - return remap_ops->enable(); + ret = remap_ops->enable(); + + if (irq_remapping_enabled) + irq_remapping_modify_x86_ops(); + + return ret; } void irq_remapping_disable(void) { - if (!remap_ops || !remap_ops->disable) + if (!irq_remapping_enabled || + !remap_ops || + !remap_ops->disable) return; remap_ops->disable(); @@ -95,7 +256,9 @@ void irq_remapping_disable(void) int irq_remapping_reenable(int mode) { - if (!remap_ops || !remap_ops->reenable) + if (!irq_remapping_enabled || + !remap_ops || + !remap_ops->reenable) return 0; return remap_ops->reenable(mode); @@ -103,6 +266,9 @@ int irq_remapping_reenable(int mode) int __init irq_remap_enable_fault_handling(void) { + if (!irq_remapping_enabled) + return 0; + if (!remap_ops || !remap_ops->enable_faulting) return -ENODEV; @@ -133,23 +299,28 @@ int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, void free_remapped_irq(int irq) { + struct irq_cfg *cfg = irq_get_chip_data(irq); + if (!remap_ops || !remap_ops->free_irq) return; - remap_ops->free_irq(irq); + if (irq_remapped(cfg)) + remap_ops->free_irq(irq); } void compose_remapped_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, struct msi_msg *msg, u8 hpet_id) { - if (!remap_ops || !remap_ops->compose_msi_msg) - return; + struct irq_cfg *cfg = irq_get_chip_data(irq); - remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); + if (!irq_remapped(cfg)) + native_compose_msi_msg(pdev, irq, dest, msg, hpet_id); + else if (remap_ops && remap_ops->compose_msi_msg) + remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); } -int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) +static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) { if (!remap_ops || !remap_ops->msi_alloc_irq) return -ENODEV; @@ -157,8 +328,8 @@ int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) return remap_ops->msi_alloc_irq(pdev, irq, nvec); } -int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, - int index, int sub_handle) +static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, + int index, int sub_handle) { if (!remap_ops || !remap_ops->msi_setup_irq) return -ENODEV; @@ -173,3 +344,42 @@ int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) return remap_ops->setup_hpet_msi(irq, id); } + +void panic_if_irq_remap(const char *msg) +{ + if (irq_remapping_enabled) + panic(msg); +} + +static void ir_ack_apic_edge(struct irq_data *data) +{ + ack_APIC_irq(); +} + +static void ir_ack_apic_level(struct irq_data *data) +{ + ack_APIC_irq(); + eoi_ioapic_irq(data->irq, data->chip_data); +} + +static void ir_print_prefix(struct irq_data *data, struct seq_file *p) +{ + seq_printf(p, " IR-%s", data->chip->name); +} + +void irq_remap_modify_chip_defaults(struct irq_chip *chip) +{ + chip->irq_print_chip = ir_print_prefix; + chip->irq_ack = ir_ack_apic_edge; + chip->irq_eoi = ir_ack_apic_level; + chip->irq_set_affinity = x86_io_apic_ops.set_affinity; +} + +bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip) +{ + if (!irq_remapped(cfg)) + return false; + irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); + irq_remap_modify_chip_defaults(chip); + return true; +} diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index 95363ac..ecb6376 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -34,6 +34,7 @@ struct msi_msg; extern int disable_irq_remap; extern int disable_sourceid_checking; extern int no_x2apic_optout; +extern int irq_remapping_enabled; struct irq_remap_ops { /* Check whether Interrupt Remapping is supported */ diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index d33c980..6ac02fa 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -146,7 +146,7 @@ static int iommu_enable(struct omap_iommu *obj) struct platform_device *pdev = to_platform_device(obj->dev); struct iommu_platform_data *pdata = pdev->dev.platform_data; - if (!obj || !pdata) + if (!pdata) return -EINVAL; if (!arch_iommu) @@ -172,7 +172,7 @@ 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; - if (!obj || !pdata) + if (!pdata) return; arch_iommu->disable(obj); diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c new file mode 100644 index 0000000..b6e8b57 --- /dev/null +++ b/drivers/iommu/shmobile-iommu.c @@ -0,0 +1,395 @@ +/* + * IOMMU for IPMMU/IPMMUI + * Copyright (C) 2012 Hideki EIRAKU + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ + +#include <linux/dma-mapping.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/platform_device.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <asm/dma-iommu.h> +#include "shmobile-ipmmu.h" + +#define L1_SIZE CONFIG_SHMOBILE_IOMMU_L1SIZE +#define L1_LEN (L1_SIZE / 4) +#define L1_ALIGN L1_SIZE +#define L2_SIZE SZ_1K +#define L2_LEN (L2_SIZE / 4) +#define L2_ALIGN L2_SIZE + +struct shmobile_iommu_domain_pgtable { + uint32_t *pgtable; + dma_addr_t handle; +}; + +struct shmobile_iommu_archdata { + struct list_head attached_list; + struct dma_iommu_mapping *iommu_mapping; + spinlock_t attach_lock; + struct shmobile_iommu_domain *attached; + int num_attached_devices; + struct shmobile_ipmmu *ipmmu; +}; + +struct shmobile_iommu_domain { + struct shmobile_iommu_domain_pgtable l1, l2[L1_LEN]; + spinlock_t map_lock; + spinlock_t attached_list_lock; + struct list_head attached_list; +}; + +static struct shmobile_iommu_archdata *ipmmu_archdata; +static struct kmem_cache *l1cache, *l2cache; + +static int pgtable_alloc(struct shmobile_iommu_domain_pgtable *pgtable, + struct kmem_cache *cache, size_t size) +{ + pgtable->pgtable = kmem_cache_zalloc(cache, GFP_ATOMIC); + if (!pgtable->pgtable) + return -ENOMEM; + pgtable->handle = dma_map_single(NULL, pgtable->pgtable, size, + DMA_TO_DEVICE); + return 0; +} + +static void pgtable_free(struct shmobile_iommu_domain_pgtable *pgtable, + struct kmem_cache *cache, size_t size) +{ + dma_unmap_single(NULL, pgtable->handle, size, DMA_TO_DEVICE); + kmem_cache_free(cache, pgtable->pgtable); +} + +static uint32_t pgtable_read(struct shmobile_iommu_domain_pgtable *pgtable, + unsigned int index) +{ + return pgtable->pgtable[index]; +} + +static void pgtable_write(struct shmobile_iommu_domain_pgtable *pgtable, + unsigned int index, unsigned int count, uint32_t val) +{ + unsigned int i; + + for (i = 0; i < count; i++) + pgtable->pgtable[index + i] = val; + dma_sync_single_for_device(NULL, pgtable->handle + index * sizeof(val), + sizeof(val) * count, DMA_TO_DEVICE); +} + +static int shmobile_iommu_domain_init(struct iommu_domain *domain) +{ + struct shmobile_iommu_domain *sh_domain; + int i, ret; + + sh_domain = kmalloc(sizeof(*sh_domain), GFP_KERNEL); + if (!sh_domain) + return -ENOMEM; + ret = pgtable_alloc(&sh_domain->l1, l1cache, L1_SIZE); + if (ret < 0) { + kfree(sh_domain); + return ret; + } + for (i = 0; i < L1_LEN; i++) + sh_domain->l2[i].pgtable = NULL; + spin_lock_init(&sh_domain->map_lock); + spin_lock_init(&sh_domain->attached_list_lock); + INIT_LIST_HEAD(&sh_domain->attached_list); + domain->priv = sh_domain; + return 0; +} + +static void shmobile_iommu_domain_destroy(struct iommu_domain *domain) +{ + struct shmobile_iommu_domain *sh_domain = domain->priv; + int i; + + for (i = 0; i < L1_LEN; i++) { + if (sh_domain->l2[i].pgtable) + pgtable_free(&sh_domain->l2[i], l2cache, L2_SIZE); + } + pgtable_free(&sh_domain->l1, l1cache, L1_SIZE); + kfree(sh_domain); + domain->priv = NULL; +} + +static int shmobile_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; + struct shmobile_iommu_domain *sh_domain = domain->priv; + int ret = -EBUSY; + + if (!archdata) + return -ENODEV; + spin_lock(&sh_domain->attached_list_lock); + spin_lock(&archdata->attach_lock); + if (archdata->attached != sh_domain) { + if (archdata->attached) + goto err; + ipmmu_tlb_set(archdata->ipmmu, sh_domain->l1.handle, L1_SIZE, + 0); + ipmmu_tlb_flush(archdata->ipmmu); + archdata->attached = sh_domain; + archdata->num_attached_devices = 0; + list_add(&archdata->attached_list, &sh_domain->attached_list); + } + archdata->num_attached_devices++; + ret = 0; +err: + spin_unlock(&archdata->attach_lock); + spin_unlock(&sh_domain->attached_list_lock); + return ret; +} + +static void shmobile_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; + struct shmobile_iommu_domain *sh_domain = domain->priv; + + if (!archdata) + return; + spin_lock(&sh_domain->attached_list_lock); + spin_lock(&archdata->attach_lock); + archdata->num_attached_devices--; + if (!archdata->num_attached_devices) { + ipmmu_tlb_set(archdata->ipmmu, 0, 0, 0); + ipmmu_tlb_flush(archdata->ipmmu); + archdata->attached = NULL; + list_del(&archdata->attached_list); + } + spin_unlock(&archdata->attach_lock); + spin_unlock(&sh_domain->attached_list_lock); +} + +static void domain_tlb_flush(struct shmobile_iommu_domain *sh_domain) +{ + struct shmobile_iommu_archdata *archdata; + + spin_lock(&sh_domain->attached_list_lock); + list_for_each_entry(archdata, &sh_domain->attached_list, attached_list) + ipmmu_tlb_flush(archdata->ipmmu); + spin_unlock(&sh_domain->attached_list_lock); +} + +static int l2alloc(struct shmobile_iommu_domain *sh_domain, + unsigned int l1index) +{ + int ret; + + if (!sh_domain->l2[l1index].pgtable) { + ret = pgtable_alloc(&sh_domain->l2[l1index], l2cache, L2_SIZE); + if (ret < 0) + return ret; + } + pgtable_write(&sh_domain->l1, l1index, 1, + sh_domain->l2[l1index].handle | 0x1); + return 0; +} + +static void l2realfree(struct shmobile_iommu_domain_pgtable *l2) +{ + if (l2->pgtable) + pgtable_free(l2, l2cache, L2_SIZE); +} + +static void l2free(struct shmobile_iommu_domain *sh_domain, + unsigned int l1index, + struct shmobile_iommu_domain_pgtable *l2) +{ + pgtable_write(&sh_domain->l1, l1index, 1, 0); + if (sh_domain->l2[l1index].pgtable) { + *l2 = sh_domain->l2[l1index]; + sh_domain->l2[l1index].pgtable = NULL; + } +} + +static int shmobile_iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; + struct shmobile_iommu_domain *sh_domain = domain->priv; + unsigned int l1index, l2index; + int ret; + + l1index = iova >> 20; + switch (size) { + case SZ_4K: + l2index = (iova >> 12) & 0xff; + spin_lock(&sh_domain->map_lock); + ret = l2alloc(sh_domain, l1index); + if (!ret) + pgtable_write(&sh_domain->l2[l1index], l2index, 1, + paddr | 0xff2); + spin_unlock(&sh_domain->map_lock); + break; + case SZ_64K: + l2index = (iova >> 12) & 0xf0; + spin_lock(&sh_domain->map_lock); + ret = l2alloc(sh_domain, l1index); + if (!ret) + pgtable_write(&sh_domain->l2[l1index], l2index, 0x10, + paddr | 0xff1); + spin_unlock(&sh_domain->map_lock); + break; + case SZ_1M: + spin_lock(&sh_domain->map_lock); + l2free(sh_domain, l1index, &l2); + pgtable_write(&sh_domain->l1, l1index, 1, paddr | 0xc02); + spin_unlock(&sh_domain->map_lock); + ret = 0; + break; + default: + ret = -EINVAL; + } + if (!ret) + domain_tlb_flush(sh_domain); + l2realfree(&l2); + return ret; +} + +static size_t shmobile_iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; + struct shmobile_iommu_domain *sh_domain = domain->priv; + unsigned int l1index, l2index; + uint32_t l2entry = 0; + size_t ret = 0; + + l1index = iova >> 20; + if (!(iova & 0xfffff) && size >= SZ_1M) { + spin_lock(&sh_domain->map_lock); + l2free(sh_domain, l1index, &l2); + spin_unlock(&sh_domain->map_lock); + ret = SZ_1M; + goto done; + } + l2index = (iova >> 12) & 0xff; + spin_lock(&sh_domain->map_lock); + if (sh_domain->l2[l1index].pgtable) + l2entry = pgtable_read(&sh_domain->l2[l1index], l2index); + switch (l2entry & 3) { + case 1: + if (l2index & 0xf) + break; + pgtable_write(&sh_domain->l2[l1index], l2index, 0x10, 0); + ret = SZ_64K; + break; + case 2: + pgtable_write(&sh_domain->l2[l1index], l2index, 1, 0); + ret = SZ_4K; + break; + } + spin_unlock(&sh_domain->map_lock); +done: + if (ret) + domain_tlb_flush(sh_domain); + l2realfree(&l2); + return ret; +} + +static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain, + unsigned long iova) +{ + struct shmobile_iommu_domain *sh_domain = domain->priv; + uint32_t l1entry = 0, l2entry = 0; + unsigned int l1index, l2index; + + l1index = iova >> 20; + l2index = (iova >> 12) & 0xff; + spin_lock(&sh_domain->map_lock); + if (sh_domain->l2[l1index].pgtable) + l2entry = pgtable_read(&sh_domain->l2[l1index], l2index); + else + l1entry = pgtable_read(&sh_domain->l1, l1index); + spin_unlock(&sh_domain->map_lock); + switch (l2entry & 3) { + case 1: + return (l2entry & ~0xffff) | (iova & 0xffff); + case 2: + return (l2entry & ~0xfff) | (iova & 0xfff); + default: + if ((l1entry & 3) == 2) + return (l1entry & ~0xfffff) | (iova & 0xfffff); + return 0; + } +} + +static int find_dev_name(struct shmobile_ipmmu *ipmmu, const char *dev_name) +{ + unsigned int i, n = ipmmu->num_dev_names; + + for (i = 0; i < n; i++) { + if (strcmp(ipmmu->dev_names[i], dev_name) == 0) + return 1; + } + return 0; +} + +static int shmobile_iommu_add_device(struct device *dev) +{ + struct shmobile_iommu_archdata *archdata = ipmmu_archdata; + struct dma_iommu_mapping *mapping; + + if (!find_dev_name(archdata->ipmmu, dev_name(dev))) + return 0; + mapping = archdata->iommu_mapping; + if (!mapping) { + mapping = arm_iommu_create_mapping(&platform_bus_type, 0, + L1_LEN << 20, 0); + if (IS_ERR(mapping)) + return PTR_ERR(mapping); + archdata->iommu_mapping = mapping; + } + dev->archdata.iommu = archdata; + if (arm_iommu_attach_device(dev, mapping)) + pr_err("arm_iommu_attach_device failed\n"); + return 0; +} + +static struct iommu_ops shmobile_iommu_ops = { + .domain_init = shmobile_iommu_domain_init, + .domain_destroy = shmobile_iommu_domain_destroy, + .attach_dev = shmobile_iommu_attach_device, + .detach_dev = shmobile_iommu_detach_device, + .map = shmobile_iommu_map, + .unmap = shmobile_iommu_unmap, + .iova_to_phys = shmobile_iommu_iova_to_phys, + .add_device = shmobile_iommu_add_device, + .pgsize_bitmap = SZ_1M | SZ_64K | SZ_4K, +}; + +int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu) +{ + static struct shmobile_iommu_archdata *archdata; + + l1cache = kmem_cache_create("shmobile-iommu-pgtable1", L1_SIZE, + L1_ALIGN, SLAB_HWCACHE_ALIGN, NULL); + if (!l1cache) + return -ENOMEM; + l2cache = kmem_cache_create("shmobile-iommu-pgtable2", L2_SIZE, + L2_ALIGN, SLAB_HWCACHE_ALIGN, NULL); + if (!l2cache) { + kmem_cache_destroy(l1cache); + return -ENOMEM; + } + archdata = kmalloc(sizeof(*archdata), GFP_KERNEL); + if (!archdata) { + kmem_cache_destroy(l1cache); + kmem_cache_destroy(l2cache); + return -ENOMEM; + } + spin_lock_init(&archdata->attach_lock); + archdata->attached = NULL; + archdata->ipmmu = ipmmu; + ipmmu_archdata = archdata; + bus_set_iommu(&platform_bus_type, &shmobile_iommu_ops); + return 0; +} diff --git a/drivers/iommu/shmobile-ipmmu.c b/drivers/iommu/shmobile-ipmmu.c new file mode 100644 index 0000000..8321f89 --- /dev/null +++ b/drivers/iommu/shmobile-ipmmu.c @@ -0,0 +1,136 @@ +/* + * IPMMU/IPMMUI + * Copyright (C) 2012 Hideki EIRAKU + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ + +#include <linux/err.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/platform_data/sh_ipmmu.h> +#include "shmobile-ipmmu.h" + +#define IMCTR1 0x000 +#define IMCTR2 0x004 +#define IMASID 0x010 +#define IMTTBR 0x014 +#define IMTTBCR 0x018 + +#define IMCTR1_TLBEN (1 << 0) +#define IMCTR1_FLUSH (1 << 1) + +static void ipmmu_reg_write(struct shmobile_ipmmu *ipmmu, unsigned long reg_off, + unsigned long data) +{ + iowrite32(data, ipmmu->ipmmu_base + reg_off); +} + +void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu) +{ + if (!ipmmu) + return; + + mutex_lock(&ipmmu->flush_lock); + if (ipmmu->tlb_enabled) + ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH | IMCTR1_TLBEN); + else + ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH); + mutex_unlock(&ipmmu->flush_lock); +} + +void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size, + int asid) +{ + if (!ipmmu) + return; + + mutex_lock(&ipmmu->flush_lock); + switch (size) { + default: + ipmmu->tlb_enabled = 0; + break; + case 0x2000: + ipmmu_reg_write(ipmmu, IMTTBCR, 1); + ipmmu->tlb_enabled = 1; + break; + case 0x1000: + ipmmu_reg_write(ipmmu, IMTTBCR, 2); + ipmmu->tlb_enabled = 1; + break; + case 0x800: + ipmmu_reg_write(ipmmu, IMTTBCR, 3); + ipmmu->tlb_enabled = 1; + break; + case 0x400: + ipmmu_reg_write(ipmmu, IMTTBCR, 4); + ipmmu->tlb_enabled = 1; + break; + case 0x200: + ipmmu_reg_write(ipmmu, IMTTBCR, 5); + ipmmu->tlb_enabled = 1; + break; + case 0x100: + ipmmu_reg_write(ipmmu, IMTTBCR, 6); + ipmmu->tlb_enabled = 1; + break; + case 0x80: + ipmmu_reg_write(ipmmu, IMTTBCR, 7); + ipmmu->tlb_enabled = 1; + break; + } + ipmmu_reg_write(ipmmu, IMTTBR, phys); + ipmmu_reg_write(ipmmu, IMASID, asid); + mutex_unlock(&ipmmu->flush_lock); +} + +static int ipmmu_probe(struct platform_device *pdev) +{ + struct shmobile_ipmmu *ipmmu; + struct resource *res; + struct shmobile_ipmmu_platform_data *pdata = pdev->dev.platform_data; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "cannot get platform resources\n"); + return -ENOENT; + } + ipmmu = devm_kzalloc(&pdev->dev, sizeof(*ipmmu), GFP_KERNEL); + if (!ipmmu) { + dev_err(&pdev->dev, "cannot allocate device data\n"); + return -ENOMEM; + } + mutex_init(&ipmmu->flush_lock); + ipmmu->dev = &pdev->dev; + ipmmu->ipmmu_base = devm_ioremap_nocache(&pdev->dev, res->start, + resource_size(res)); + if (!ipmmu->ipmmu_base) { + dev_err(&pdev->dev, "ioremap_nocache failed\n"); + return -ENOMEM; + } + ipmmu->dev_names = pdata->dev_names; + ipmmu->num_dev_names = pdata->num_dev_names; + platform_set_drvdata(pdev, ipmmu); + ipmmu_reg_write(ipmmu, IMCTR1, 0x0); /* disable TLB */ + ipmmu_reg_write(ipmmu, IMCTR2, 0x0); /* disable PMB */ + ipmmu_iommu_init(ipmmu); + return 0; +} + +static struct platform_driver ipmmu_driver = { + .probe = ipmmu_probe, + .driver = { + .owner = THIS_MODULE, + .name = "ipmmu", + }, +}; + +static int __init ipmmu_init(void) +{ + return platform_driver_register(&ipmmu_driver); +} +subsys_initcall(ipmmu_init); diff --git a/drivers/iommu/shmobile-ipmmu.h b/drivers/iommu/shmobile-ipmmu.h new file mode 100644 index 0000000..4d53684 --- /dev/null +++ b/drivers/iommu/shmobile-ipmmu.h @@ -0,0 +1,34 @@ +/* shmobile-ipmmu.h + * + * Copyright (C) 2012 Hideki EIRAKU + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ + +#ifndef __SHMOBILE_IPMMU_H__ +#define __SHMOBILE_IPMMU_H__ + +struct shmobile_ipmmu { + struct device *dev; + void __iomem *ipmmu_base; + int tlb_enabled; + struct mutex flush_lock; + const char * const *dev_names; + unsigned int num_dev_names; +}; + +#ifdef CONFIG_SHMOBILE_IPMMU_TLB +void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu); +void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size, + int asid); +int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu); +#else +static inline int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu) +{ + return -EINVAL; +} +#endif + +#endif /* __SHMOBILE_IPMMU_H__ */ diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 8219f1d..8643757 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -430,13 +430,11 @@ const struct dev_pm_ops tegra_gart_pm_ops = { .resume = tegra_gart_resume, }; -#ifdef CONFIG_OF static struct of_device_id tegra_gart_of_match[] = { { .compatible = "nvidia,tegra20-gart", }, { }, }; MODULE_DEVICE_TABLE(of, tegra_gart_of_match); -#endif static struct platform_driver tegra_gart_driver = { .probe = tegra_gart_probe, @@ -445,7 +443,7 @@ static struct platform_driver tegra_gart_driver = { .owner = THIS_MODULE, .name = "tegra-gart", .pm = &tegra_gart_pm_ops, - .of_match_table = of_match_ptr(tegra_gart_of_match), + .of_match_table = tegra_gart_of_match, }, }; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index fc17889..b34e5fd 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -1,7 +1,7 @@ /* * IOMMU API for SMMU in Tegra30 * - * Copyright (c) 2011-2012, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2011-2013, NVIDIA CORPORATION. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -19,6 +19,7 @@ #define pr_fmt(fmt) "%s(): " fmt, __func__ +#include <linux/err.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/spinlock.h> @@ -293,7 +294,11 @@ struct smmu_debugfs_info { * Per SMMU device - IOMMU device */ struct smmu_device { - void __iomem *regs[NUM_SMMU_REG_BANKS]; + void __iomem *regbase; /* register offset base */ + void __iomem **regs; /* register block start address array */ + void __iomem **rege; /* register block end address array */ + int nregs; /* number of register blocks */ + unsigned long iovmm_base; /* remappable base address */ unsigned long page_count; /* total remappable size */ spinlock_t lock; @@ -323,38 +328,37 @@ static struct smmu_device *smmu_handle; /* unique for a system */ /* * SMMU register accessors */ +static bool inline smmu_valid_reg(struct smmu_device *smmu, + void __iomem *addr) +{ + int i; + + for (i = 0; i < smmu->nregs; i++) { + if (addr < smmu->regs[i]) + break; + if (addr <= smmu->rege[i]) + return true; + } + + return false; +} + static inline u32 smmu_read(struct smmu_device *smmu, size_t offs) { - BUG_ON(offs < 0x10); - if (offs < 0x3c) - return readl(smmu->regs[0] + offs - 0x10); - BUG_ON(offs < 0x1f0); - if (offs < 0x200) - return readl(smmu->regs[1] + offs - 0x1f0); - BUG_ON(offs < 0x228); - if (offs < 0x284) - return readl(smmu->regs[2] + offs - 0x228); - BUG(); + void __iomem *addr = smmu->regbase + offs; + + BUG_ON(!smmu_valid_reg(smmu, addr)); + + return readl(addr); } static inline void smmu_write(struct smmu_device *smmu, u32 val, size_t offs) { - BUG_ON(offs < 0x10); - if (offs < 0x3c) { - writel(val, smmu->regs[0] + offs - 0x10); - return; - } - BUG_ON(offs < 0x1f0); - if (offs < 0x200) { - writel(val, smmu->regs[1] + offs - 0x1f0); - return; - } - BUG_ON(offs < 0x228); - if (offs < 0x284) { - writel(val, smmu->regs[2] + offs - 0x228); - return; - } - BUG(); + void __iomem *addr = smmu->regbase + offs; + + BUG_ON(!smmu_valid_reg(smmu, addr)); + + writel(val, addr); } #define VA_PAGE_TO_PA(va, page) \ @@ -964,7 +968,6 @@ static ssize_t smmu_debugfs_stats_write(struct file *file, { struct smmu_debugfs_info *info; struct smmu_device *smmu; - struct dentry *dent; int i; enum { _OFF = 0, @@ -992,8 +995,7 @@ static ssize_t smmu_debugfs_stats_write(struct file *file, if (i == ARRAY_SIZE(command)) return -EINVAL; - dent = file->f_dentry; - info = dent->d_inode->i_private; + info = file_inode(file)->i_private; smmu = info->smmu; offs = SMMU_CACHE_CONFIG(info->cache); @@ -1028,15 +1030,11 @@ static ssize_t smmu_debugfs_stats_write(struct file *file, static int smmu_debugfs_stats_show(struct seq_file *s, void *v) { - struct smmu_debugfs_info *info; - struct smmu_device *smmu; - struct dentry *dent; + struct smmu_debugfs_info *info = s->private; + struct smmu_device *smmu = info->smmu; int i; const char * const stats[] = { "hit", "miss", }; - dent = d_find_alias(s->private); - info = dent->d_inode->i_private; - smmu = info->smmu; for (i = 0; i < ARRAY_SIZE(stats); i++) { u32 val; @@ -1050,14 +1048,12 @@ static int smmu_debugfs_stats_show(struct seq_file *s, void *v) stats[i], val, offs); } seq_printf(s, "\n"); - dput(dent); - return 0; } static int smmu_debugfs_stats_open(struct inode *inode, struct file *file) { - return single_open(file, smmu_debugfs_stats_show, inode); + return single_open(file, smmu_debugfs_stats_show, inode->i_private); } static const struct file_operations smmu_debugfs_stats_fops = { @@ -1170,16 +1166,25 @@ static int tegra_smmu_probe(struct platform_device *pdev) return -ENOMEM; } - for (i = 0; i < ARRAY_SIZE(smmu->regs); i++) { + smmu->nregs = pdev->num_resources; + smmu->regs = devm_kzalloc(dev, 2 * smmu->nregs * sizeof(*smmu->regs), + GFP_KERNEL); + smmu->rege = smmu->regs + smmu->nregs; + if (!smmu->regs) + return -ENOMEM; + for (i = 0; i < smmu->nregs; i++) { struct resource *res; res = platform_get_resource(pdev, IORESOURCE_MEM, i); if (!res) return -ENODEV; - smmu->regs[i] = devm_request_and_ioremap(&pdev->dev, res); - if (!smmu->regs[i]) - return -EBUSY; + smmu->regs[i] = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(smmu->regs[i])) + return PTR_ERR(smmu->regs[i]); + smmu->rege[i] = smmu->regs[i] + resource_size(res) - 1; } + /* Same as "mc" 1st regiter block start address */ + smmu->regbase = (void __iomem *)((u32)smmu->regs[0] & PAGE_MASK); err = of_get_dma_window(dev->of_node, NULL, 0, NULL, &base, &size); if (err) @@ -1216,6 +1221,7 @@ static int tegra_smmu_probe(struct platform_device *pdev) as->pte_attr = _PTE_ATTR; spin_lock_init(&as->lock); + spin_lock_init(&as->client_lock); INIT_LIST_HEAD(&as->client); } spin_lock_init(&smmu->lock); @@ -1254,13 +1260,11 @@ const struct dev_pm_ops tegra_smmu_pm_ops = { .resume = tegra_smmu_resume, }; -#ifdef CONFIG_OF static struct of_device_id tegra_smmu_of_match[] = { { .compatible = "nvidia,tegra30-smmu", }, { }, }; MODULE_DEVICE_TABLE(of, tegra_smmu_of_match); -#endif static struct platform_driver tegra_smmu_driver = { .probe = tegra_smmu_probe, @@ -1269,7 +1273,7 @@ static struct platform_driver tegra_smmu_driver = { .owner = THIS_MODULE, .name = "tegra-smmu", .pm = &tegra_smmu_pm_ops, - .of_match_table = of_match_ptr(tegra_smmu_of_match), + .of_match_table = tegra_smmu_of_match, }, }; |