diff options
Diffstat (limited to 'drivers/iommu')
| -rw-r--r-- | drivers/iommu/Kconfig | 25 | ||||
| -rw-r--r-- | drivers/iommu/Makefile | 3 | ||||
| -rw-r--r-- | drivers/iommu/dmar.c | 11 | ||||
| -rw-r--r-- | drivers/iommu/exynos-iommu.c | 1076 | ||||
| -rw-r--r-- | drivers/iommu/intel-iommu.c | 43 | ||||
| -rw-r--r-- | drivers/iommu/intel_irq_remapping.c (renamed from drivers/iommu/intr_remapping.c) | 359 | ||||
| -rw-r--r-- | drivers/iommu/intr_remapping.h | 17 | ||||
| -rw-r--r-- | drivers/iommu/irq_remapping.c | 166 | ||||
| -rw-r--r-- | drivers/iommu/irq_remapping.h | 90 |
9 files changed, 1683 insertions, 107 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 3bd9fff5c589..340893727538 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -43,7 +43,7 @@ config AMD_IOMMU With this option you can enable support for AMD IOMMU hardware in your system. An IOMMU is a hardware component which provides remapping of DMA memory accesses from devices. With an AMD IOMMU you - can isolate the the DMA memory of different devices and protect the + can isolate the DMA memory of different devices and protect the system from misbehaving device drivers or hardware. You can find out if your system has an AMD IOMMU if you look into @@ -67,7 +67,7 @@ config AMD_IOMMU_V2 ---help--- This option enables support for the AMD IOMMUv2 features of the IOMMU hardware. Select this option if you want to use devices that support - the the PCI PRI and PASID interface. + the PCI PRI and PASID interface. # Intel IOMMU support config DMAR_TABLE @@ -162,4 +162,25 @@ config TEGRA_IOMMU_SMMU space through the SMMU (System Memory Management Unit) hardware included on Tegra SoCs. +config EXYNOS_IOMMU + bool "Exynos IOMMU Support" + depends on ARCH_EXYNOS && EXYNOS_DEV_SYSMMU + select IOMMU_API + help + Support for the IOMMU(System MMU) of Samsung Exynos application + processor family. This enables H/W multimedia accellerators to see + non-linear physical memory chunks as a linear memory in their + address spaces + + If unsure, say N here. + +config EXYNOS_IOMMU_DEBUG + bool "Debugging log for Exynos IOMMU" + depends on EXYNOS_IOMMU + help + Select this to see the detailed log message that shows what + happens in the IOMMU driver + + Say N unless you need kernel log message for IOMMU debugging + endif # IOMMU_SUPPORT diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 7ad7a3bc1242..76e54ef796de 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -4,9 +4,10 @@ obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o -obj-$(CONFIG_IRQ_REMAP) += intr_remapping.o +obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o obj-$(CONFIG_OMAP_IOVMM) += omap-iovmm.o 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 diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 35c1e17fce1d..3a74e4410fc0 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -36,6 +36,7 @@ #include <linux/tboot.h> #include <linux/dmi.h> #include <linux/slab.h> +#include <asm/irq_remapping.h> #include <asm/iommu_table.h> #define PREFIX "DMAR: " @@ -555,7 +556,7 @@ int __init detect_intel_iommu(void) dmar = (struct acpi_table_dmar *) dmar_tbl; - if (ret && intr_remapping_enabled && cpu_has_x2apic && + if (ret && irq_remapping_enabled && cpu_has_x2apic && dmar->flags & 0x1) printk(KERN_INFO "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); @@ -1041,7 +1042,7 @@ static const char *dma_remap_fault_reasons[] = "non-zero reserved fields in PTE", }; -static const char *intr_remap_fault_reasons[] = +static const char *irq_remap_fault_reasons[] = { "Detected reserved fields in the decoded interrupt-remapped request", "Interrupt index exceeded the interrupt-remapping table size", @@ -1056,10 +1057,10 @@ static const char *intr_remap_fault_reasons[] = const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type) { - if (fault_reason >= 0x20 && (fault_reason <= 0x20 + - ARRAY_SIZE(intr_remap_fault_reasons))) { + if (fault_reason >= 0x20 && (fault_reason - 0x20 < + ARRAY_SIZE(irq_remap_fault_reasons))) { *fault_type = INTR_REMAP; - return intr_remap_fault_reasons[fault_reason - 0x20]; + return irq_remap_fault_reasons[fault_reason - 0x20]; } else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) { *fault_type = DMA_REMAP; return dma_remap_fault_reasons[fault_reason]; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c new file mode 100644 index 000000000000..9a114b9ff170 --- /dev/null +++ b/drivers/iommu/exynos-iommu.c @@ -0,0 +1,1076 @@ +/* linux/drivers/iommu/exynos_iommu.c + * + * Copyright (c) 2011 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * 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. + */ + +#ifdef CONFIG_EXYNOS_IOMMU_DEBUG +#define DEBUG +#endif + +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/pm_runtime.h> +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/mm.h> +#include <linux/iommu.h> +#include <linux/errno.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/export.h> + +#include <asm/cacheflush.h> +#include <asm/pgtable.h> + +#include <mach/sysmmu.h> + +/* We does not consider super section mapping (16MB) */ +#define SECT_ORDER 20 +#define LPAGE_ORDER 16 +#define SPAGE_ORDER 12 + +#define SECT_SIZE (1 << SECT_ORDER) +#define LPAGE_SIZE (1 << LPAGE_ORDER) +#define SPAGE_SIZE (1 << SPAGE_ORDER) + +#define SECT_MASK (~(SECT_SIZE - 1)) +#define LPAGE_MASK (~(LPAGE_SIZE - 1)) +#define SPAGE_MASK (~(SPAGE_SIZE - 1)) + +#define lv1ent_fault(sent) (((*(sent) & 3) == 0) || ((*(sent) & 3) == 3)) +#define lv1ent_page(sent) ((*(sent) & 3) == 1) +#define lv1ent_section(sent) ((*(sent) & 3) == 2) + +#define lv2ent_fault(pent) ((*(pent) & 3) == 0) +#define lv2ent_small(pent) ((*(pent) & 2) == 2) +#define lv2ent_large(pent) ((*(pent) & 3) == 1) + +#define section_phys(sent) (*(sent) & SECT_MASK) +#define section_offs(iova) ((iova) & 0xFFFFF) +#define lpage_phys(pent) (*(pent) & LPAGE_MASK) +#define lpage_offs(iova) ((iova) & 0xFFFF) +#define spage_phys(pent) (*(pent) & SPAGE_MASK) +#define spage_offs(iova) ((iova) & 0xFFF) + +#define lv1ent_offset(iova) ((iova) >> SECT_ORDER) +#define lv2ent_offset(iova) (((iova) & 0xFF000) >> SPAGE_ORDER) + +#define NUM_LV1ENTRIES 4096 +#define NUM_LV2ENTRIES 256 + +#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(long)) + +#define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE) + +#define lv2table_base(sent) (*(sent) & 0xFFFFFC00) + +#define mk_lv1ent_sect(pa) ((pa) | 2) +#define mk_lv1ent_page(pa) ((pa) | 1) +#define mk_lv2ent_lpage(pa) ((pa) | 1) +#define mk_lv2ent_spage(pa) ((pa) | 2) + +#define CTRL_ENABLE 0x5 +#define CTRL_BLOCK 0x7 +#define CTRL_DISABLE 0x0 + +#define REG_MMU_CTRL 0x000 +#define REG_MMU_CFG 0x004 +#define REG_MMU_STATUS 0x008 +#define REG_MMU_FLUSH 0x00C +#define REG_MMU_FLUSH_ENTRY 0x010 +#define REG_PT_BASE_ADDR 0x014 +#define REG_INT_STATUS 0x018 +#define REG_INT_CLEAR 0x01C + +#define REG_PAGE_FAULT_ADDR 0x024 +#define REG_AW_FAULT_ADDR 0x028 +#define REG_AR_FAULT_ADDR 0x02C +#define REG_DEFAULT_SLAVE_ADDR 0x030 + +#define REG_MMU_VERSION 0x034 + +#define REG_PB0_SADDR 0x04C +#define REG_PB0_EADDR 0x050 +#define REG_PB1_SADDR 0x054 +#define REG_PB1_EADDR 0x058 + +static unsigned long *section_entry(unsigned long *pgtable, unsigned long iova) +{ + return pgtable + lv1ent_offset(iova); +} + +static unsigned long *page_entry(unsigned long *sent, unsigned long iova) +{ + return (unsigned long *)__va(lv2table_base(sent)) + lv2ent_offset(iova); +} + +enum exynos_sysmmu_inttype { + SYSMMU_PAGEFAULT, + SYSMMU_AR_MULTIHIT, + SYSMMU_AW_MULTIHIT, + SYSMMU_BUSERROR, + SYSMMU_AR_SECURITY, + SYSMMU_AR_ACCESS, + SYSMMU_AW_SECURITY, + SYSMMU_AW_PROTECTION, /* 7 */ + SYSMMU_FAULT_UNKNOWN, + SYSMMU_FAULTS_NUM +}; + +/* + * @itype: type of fault. + * @pgtable_base: the physical address of page table base. This is 0 if @itype + * is SYSMMU_BUSERROR. + * @fault_addr: the device (virtual) address that the System MMU tried to + * translated. This is 0 if @itype is SYSMMU_BUSERROR. + */ +typedef int (*sysmmu_fault_handler_t)(enum exynos_sysmmu_inttype itype, + unsigned long pgtable_base, unsigned long fault_addr); + +static unsigned short fault_reg_offset[SYSMMU_FAULTS_NUM] = { + REG_PAGE_FAULT_ADDR, + REG_AR_FAULT_ADDR, + REG_AW_FAULT_ADDR, + REG_DEFAULT_SLAVE_ADDR, + REG_AR_FAULT_ADDR, + REG_AR_FAULT_ADDR, + REG_AW_FAULT_ADDR, + REG_AW_FAULT_ADDR +}; + +static char *sysmmu_fault_name[SYSMMU_FAULTS_NUM] = { + "PAGE FAULT", + "AR MULTI-HIT FAULT", + "AW MULTI-HIT FAULT", + "BUS ERROR", + "AR SECURITY PROTECTION FAULT", + "AR ACCESS PROTECTION FAULT", + "AW SECURITY PROTECTION FAULT", + "AW ACCESS PROTECTION FAULT", + "UNKNOWN FAULT" +}; + +struct exynos_iommu_domain { + struct list_head clients; /* list of sysmmu_drvdata.node */ + unsigned long *pgtable; /* lv1 page table, 16KB */ + short *lv2entcnt; /* free lv2 entry counter for each section */ + spinlock_t lock; /* lock for this structure */ + spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */ +}; + +struct sysmmu_drvdata { + struct list_head node; /* entry of exynos_iommu_domain.clients */ + struct device *sysmmu; /* System MMU's device descriptor */ + struct device *dev; /* Owner of system MMU */ + char *dbgname; + int nsfrs; + void __iomem **sfrbases; + struct clk *clk[2]; + int activations; + rwlock_t lock; + struct iommu_domain *domain; + sysmmu_fault_handler_t fault_handler; + unsigned long pgtable; +}; + +static bool set_sysmmu_active(struct sysmmu_drvdata *data) +{ + /* return true if the System MMU was not active previously + and it needs to be initialized */ + return ++data->activations == 1; +} + +static bool set_sysmmu_inactive(struct sysmmu_drvdata *data) +{ + /* return true if the System MMU is needed to be disabled */ + BUG_ON(data->activations < 1); + return --data->activations == 0; +} + +static bool is_sysmmu_active(struct sysmmu_drvdata *data) +{ + return data->activations > 0; +} + +static void sysmmu_unblock(void __iomem *sfrbase) +{ + __raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL); +} + +static bool sysmmu_block(void __iomem *sfrbase) +{ + int i = 120; + + __raw_writel(CTRL_BLOCK, sfrbase + REG_MMU_CTRL); + while ((i > 0) && !(__raw_readl(sfrbase + REG_MMU_STATUS) & 1)) + --i; + + if (!(__raw_readl(sfrbase + REG_MMU_STATUS) & 1)) { + sysmmu_unblock(sfrbase); + return false; + } + + return true; +} + +static void __sysmmu_tlb_invalidate(void __iomem *sfrbase) +{ + __raw_writel(0x1, sfrbase + REG_MMU_FLUSH); +} + +static void __sysmmu_tlb_invalidate_entry(void __iomem *sfrbase, + unsigned long iova) +{ + __raw_writel((iova & SPAGE_MASK) | 1, sfrbase + REG_MMU_FLUSH_ENTRY); +} + +static void __sysmmu_set_ptbase(void __iomem *sfrbase, + unsigned long pgd) +{ + __raw_writel(0x1, sfrbase + REG_MMU_CFG); /* 16KB LV1, LRU */ + __raw_writel(pgd, sfrbase + REG_PT_BASE_ADDR); + + __sysmmu_tlb_invalidate(sfrbase); +} + +static void __sysmmu_set_prefbuf(void __iomem *sfrbase, unsigned long base, + unsigned long size, int idx) +{ + __raw_writel(base, sfrbase + REG_PB0_SADDR + idx * 8); + __raw_writel(size - 1 + base, sfrbase + REG_PB0_EADDR + idx * 8); +} + +void exynos_sysmmu_set_prefbuf(struct device *dev, + unsigned long base0, unsigned long size0, + unsigned long base1, unsigned long size1) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + unsigned long flags; + int i; + + BUG_ON((base0 + size0) <= base0); + BUG_ON((size1 > 0) && ((base1 + size1) <= base1)); + + read_lock_irqsave(&data->lock, flags); + if (!is_sysmmu_active(data)) + goto finish; + + for (i = 0; i < data->nsfrs; i++) { + if ((readl(data->sfrbases[i] + REG_MMU_VERSION) >> 28) == 3) { + if (!sysmmu_block(data->sfrbases[i])) + continue; + + if (size1 == 0) { + if (size0 <= SZ_128K) { + base1 = base0; + size1 = size0; + } else { + size1 = size0 - + ALIGN(size0 / 2, SZ_64K); + size0 = size0 - size1; + base1 = base0 + size0; + } + } + + __sysmmu_set_prefbuf( + data->sfrbases[i], base0, size0, 0); + __sysmmu_set_prefbuf( + data->sfrbases[i], base1, size1, 1); + + sysmmu_unblock(data->sfrbases[i]); + } + } +finish: + read_unlock_irqrestore(&data->lock, flags); +} + +static void __set_fault_handler(struct sysmmu_drvdata *data, + sysmmu_fault_handler_t handler) +{ + unsigned long flags; + + write_lock_irqsave(&data->lock, flags); + data->fault_handler = handler; + write_unlock_irqrestore(&data->lock, flags); +} + +void exynos_sysmmu_set_fault_handler(struct device *dev, + sysmmu_fault_handler_t handler) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + + __set_fault_handler(data, handler); +} + +static int default_fault_handler(enum exynos_sysmmu_inttype itype, + unsigned long pgtable_base, unsigned long fault_addr) +{ + unsigned long *ent; + + if ((itype >= SYSMMU_FAULTS_NUM) || (itype < SYSMMU_PAGEFAULT)) + itype = SYSMMU_FAULT_UNKNOWN; + + pr_err("%s occured at 0x%lx(Page table base: 0x%lx)\n", + sysmmu_fault_name[itype], fault_addr, pgtable_base); + + ent = section_entry(__va(pgtable_base), fault_addr); + pr_err("\tLv1 entry: 0x%lx\n", *ent); + + if (lv1ent_page(ent)) { + ent = page_entry(ent, fault_addr); + pr_err("\t Lv2 entry: 0x%lx\n", *ent); + } + + pr_err("Generating Kernel OOPS... because it is unrecoverable.\n"); + + BUG(); + + return 0; +} + +static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id) +{ + /* SYSMMU is in blocked when interrupt occurred. */ + struct sysmmu_drvdata *data = dev_id; + struct resource *irqres; + struct platform_device *pdev; + enum exynos_sysmmu_inttype itype; + unsigned long addr = -1; + + int i, ret = -ENOSYS; + + read_lock(&data->lock); + + WARN_ON(!is_sysmmu_active(data)); + + pdev = to_platform_device(data->sysmmu); + for (i = 0; i < (pdev->num_resources / 2); i++) { + irqres = platform_get_resource(pdev, IORESOURCE_IRQ, i); + if (irqres && ((int)irqres->start == irq)) + break; + } + + if (i == pdev->num_resources) { + itype = SYSMMU_FAULT_UNKNOWN; + } else { + itype = (enum exynos_sysmmu_inttype) + __ffs(__raw_readl(data->sfrbases[i] + REG_INT_STATUS)); + if (WARN_ON(!((itype >= 0) && (itype < SYSMMU_FAULT_UNKNOWN)))) + itype = SYSMMU_FAULT_UNKNOWN; + else + addr = __raw_readl( + data->sfrbases[i] + fault_reg_offset[itype]); + } + + if (data->domain) + ret = report_iommu_fault(data->domain, data->dev, + addr, itype); + + if ((ret == -ENOSYS) && data->fault_handler) { + unsigned long base = data->pgtable; + if (itype != SYSMMU_FAULT_UNKNOWN) + base = __raw_readl( + data->sfrbases[i] + REG_PT_BASE_ADDR); + ret = data->fault_handler(itype, base, addr); + } + + if (!ret && (itype != SYSMMU_FAULT_UNKNOWN)) + __raw_writel(1 << itype, data->sfrbases[i] + REG_INT_CLEAR); + else + dev_dbg(data->sysmmu, "(%s) %s is not handled.\n", + data->dbgname, sysmmu_fault_name[itype]); + + if (itype != SYSMMU_FAULT_UNKNOWN) + sysmmu_unblock(data->sfrbases[i]); + + read_unlock(&data->lock); + + return IRQ_HANDLED; +} + +static bool __exynos_sysmmu_disable(struct sysmmu_drvdata *data) +{ + unsigned long flags; + bool disabled = false; + int i; + + write_lock_irqsave(&data->lock, flags); + + if (!set_sysmmu_inactive(data)) + goto finish; + + for (i = 0; i < data->nsfrs; i++) + __raw_writel(CTRL_DISABLE, data->sfrbases[i] + REG_MMU_CTRL); + + if (data->clk[1]) + clk_disable(data->clk[1]); + if (data->clk[0]) + clk_disable(data->clk[0]); + + disabled = true; + data->pgtable = 0; + data->domain = NULL; +finish: + write_unlock_irqrestore(&data->lock, flags); + + if (disabled) + dev_dbg(data->sysmmu, "(%s) Disabled\n", data->dbgname); + else + dev_dbg(data->sysmmu, "(%s) %d times left to be disabled\n", + data->dbgname, data->activations); + + return disabled; +} + +/* __exynos_sysmmu_enable: Enables System MMU + * + * returns -error if an error occurred and System MMU is not enabled, + * 0 if the System MMU has been just enabled and 1 if System MMU was already + * enabled before. + */ +static int __exynos_sysmmu_enable(struct sysmmu_drvdata *data, + unsigned long pgtable, struct iommu_domain *domain) +{ + int i, ret = 0; + unsigned long flags; + + write_lock_irqsave(&data->lock, flags); + + if (!set_sysmmu_active(data)) { + if (WARN_ON(pgtable != data->pgtable)) { + ret = -EBUSY; + set_sysmmu_inactive(data); + } else { + ret = 1; + } + + dev_dbg(data->sysmmu, "(%s) Already enabled\n", data->dbgname); + goto finish; + } + + if (data->clk[0]) + clk_enable(data->clk[0]); + if (data->clk[1]) + clk_enable(data->clk[1]); + + data->pgtable = pgtable; + + for (i = 0; i < data->nsfrs; i++) { + __sysmmu_set_ptbase(data->sfrbases[i], pgtable); + + if ((readl(data->sfrbases[i] + REG_MMU_VERSION) >> 28) == 3) { + /* System MMU version is 3.x */ + __raw_writel((1 << 12) | (2 << 28), + data->sfrbases[i] + REG_MMU_CFG); + __sysmmu_set_prefbuf(data->sfrbases[i], 0, -1, 0); + __sysmmu_set_prefbuf(data->sfrbases[i], 0, -1, 1); + } + + __raw_writel(CTRL_ENABLE, data->sfrbases[i] + REG_MMU_CTRL); + } + + data->domain = domain; + + dev_dbg(data->sysmmu, "(%s) Enabled\n", data->dbgname); +finish: + write_unlock_irqrestore(&data->lock, flags); + + return ret; +} + +int exynos_sysmmu_enable(struct device *dev, unsigned long pgtable) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + int ret; + + BUG_ON(!memblock_is_memory(pgtable)); + + ret = pm_runtime_get_sync(data->sysmmu); + if (ret < 0) { + dev_dbg(data->sysmmu, "(%s) Failed to enable\n", data->dbgname); + return ret; + } + + ret = __exynos_sysmmu_enable(data, pgtable, NULL); + if (WARN_ON(ret < 0)) { + pm_runtime_put(data->sysmmu); + dev_err(data->sysmmu, + "(%s) Already enabled with page table %#lx\n", + data->dbgname, data->pgtable); + } else { + data->dev = dev; + } + + return ret; +} + +bool exynos_sysmmu_disable(struct device *dev) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + bool disabled; + + disabled = __exynos_sysmmu_disable(data); + pm_runtime_put(data->sysmmu); + + return disabled; +} + +static void sysmmu_tlb_invalidate_entry(struct device *dev, unsigned long iova) +{ + unsigned long flags; + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + + read_lock_irqsave(&data->lock, flags); + + if (is_sysmmu_active(data)) { + int i; + for (i = 0; i < data->nsfrs; i++) { + if (sysmmu_block(data->sfrbases[i])) { + __sysmmu_tlb_invalidate_entry( + data->sfrbases[i], iova); + sysmmu_unblock(data->sfrbases[i]); + } + } + } else { + dev_dbg(data->sysmmu, + "(%s) Disabled. Skipping invalidating TLB.\n", + data->dbgname); + } + + read_unlock_irqrestore(&data->lock, flags); +} + +void exynos_sysmmu_tlb_invalidate(struct device *dev) +{ + unsigned long flags; + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + + read_lock_irqsave(&data->lock, flags); + + if (is_sysmmu_active(data)) { + int i; + for (i = 0; i < data->nsfrs; i++) { + if (sysmmu_block(data->sfrbases[i])) { + __sysmmu_tlb_invalidate(data->sfrbases[i]); + sysmmu_unblock(data->sfrbases[i]); + } + } + } else { + dev_dbg(data->sysmmu, + "(%s) Disabled. Skipping invalidating TLB.\n", + data->dbgname); + } + + read_unlock_irqrestore(&data->lock, flags); +} + +static int exynos_sysmmu_probe(struct platform_device *pdev) +{ + int i, ret; + struct device *dev; + struct sysmmu_drvdata *data; + + dev = &pdev->dev; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + dev_dbg(dev, "Not enough memory\n"); + ret = -ENOMEM; + goto err_alloc; + } + + ret = dev_set_drvdata(dev, data); + if (ret) { + dev_dbg(dev, "Unabled to initialize driver data\n"); + goto err_init; + } + + data->nsfrs = pdev->num_resources / 2; + data->sfrbases = kmalloc(sizeof(*data->sfrbases) * data->nsfrs, + GFP_KERNEL); + if (data->sfrbases == NULL) { + dev_dbg(dev, "Not enough memory\n"); + ret = -ENOMEM; + goto err_init; + } + + for (i = 0; i < data->nsfrs; i++) { + struct resource *res; + res = platform_get_resource(pdev, IORESOURCE_MEM, i); + if (!res) { + dev_dbg(dev, "Unable to find IOMEM region\n"); + ret = -ENOENT; + goto err_res; + } + + data->sfrbases[i] = ioremap(res->start, resource_size(res)); + if (!data->sfrbases[i]) { + dev_dbg(dev, "Unable to map IOMEM @ PA:%#x\n", + res->start); + ret = -ENOENT; + goto err_res; + } + } + + for (i = 0; i < data->nsfrs; i++) { + ret = platform_get_irq(pdev, i); + if (ret <= 0) { + dev_dbg(dev, "Unable to find IRQ resource\n"); + goto err_irq; + } + + ret = request_irq(ret, exynos_sysmmu_irq, 0, + dev_name(dev), data); + if (ret) { + dev_dbg(dev, "Unabled to register interrupt handler\n"); + goto err_irq; + } + } + + if (dev_get_platdata(dev)) { + char *deli, *beg; + struct sysmmu_platform_data *platdata = dev_get_platdata(dev); + + beg = platdata->clockname; + + for (deli = beg; (*deli != '\0') && (*deli != ','); deli++) + /* NOTHING */; + + if (*deli == '\0') + deli = NULL; + else + *deli = '\0'; + + data->clk[0] = clk_get(dev, beg); + if (IS_ERR(data->clk[0])) { + data->clk[0] = NULL; + dev_dbg(dev, "No clock descriptor registered\n"); + } + + if (data->clk[0] && deli) { + *deli = ','; + data->clk[1] = clk_get(dev, deli + 1); + if (IS_ERR(data->clk[1])) + data->clk[1] = NULL; + } + + data->dbgname = platdata->dbgname; + } + + data->sysmmu = dev; + rwlock_init(&data->lock); + INIT_LIST_HEAD(&data->node); + + __set_fault_handler(data, &default_fault_handler); + + if (dev->parent) + pm_runtime_enable(dev); + + dev_dbg(dev, "(%s) Initialized\n", data->dbgname); + return 0; +err_irq: + while (i-- > 0) { + int irq; + + irq = platform_get_irq(pdev, i); + free_irq(irq, data); + } +err_res: + while (data->nsfrs-- > 0) + iounmap(data->sfrbases[data->nsfrs]); + kfree(data->sfrbases); +err_init: + kfree(data); +err_alloc: + dev_err(dev, "Failed to initialize\n"); + return ret; +} + +static struct platform_driver exynos_sysmmu_driver = { + .probe = exynos_sysmmu_probe, + .driver = { + .owner = THIS_MODULE, + .name = "exynos-sysmmu", + } +}; + +static inline void pgtable_flush(void *vastart, void *vaend) +{ + dmac_flush_range(vastart, vaend); + outer_flush_range(virt_to_phys(vastart), + virt_to_phys(vaend)); +} + +static int exynos_iommu_domain_init(struct iommu_domain *domain) +{ + struct exynos_iommu_domain *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->pgtable = (unsigned long *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, 2); + if (!priv->pgtable) + goto err_pgtable; + + priv->lv2entcnt = (short *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, 1); + if (!priv->lv2entcnt) + goto err_counter; + + pgtable_flush(priv->pgtable, priv->pgtable + NUM_LV1ENTRIES); + + spin_lock_init(&priv->lock); + spin_lock_init(&priv->pgtablelock); + INIT_LIST_HEAD(&priv->clients); + + domain->priv = priv; + return 0; + +err_counter: + free_pages((unsigned long)priv->pgtable, 2); +err_pgtable: + kfree(priv); + return -ENOMEM; +} + +static void exynos_iommu_domain_destroy(struct iommu_domain *domain) +{ + struct exynos_iommu_domain *priv = domain->priv; + struct sysmmu_drvdata *data; + unsigned long flags; + int i; + + WARN_ON(!list_empty(&priv->clients)); + + spin_lock_irqsave(&priv->lock, flags); + + list_for_each_entry(data, &priv->clients, node) { + while (!exynos_sysmmu_disable(data->dev)) + ; /* until System MMU is actually disabled */ + } + + spin_unlock_irqrestore(&priv->lock, flags); + + for (i = 0; i < NUM_LV1ENTRIES; i++) + if (lv1ent_page(priv->pgtable + i)) + kfree(__va(lv2table_base(priv->pgtable + i))); + + free_pages((unsigned long)priv->pgtable, 2); + free_pages((unsigned long)priv->lv2entcnt, 1); + kfree(domain->priv); + domain->priv = NULL; +} + +static int exynos_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + struct exynos_iommu_domain *priv = domain->priv; + unsigned long flags; + int ret; + + ret = pm_runtime_get_sync(data->sysmmu); + if (ret < 0) + return ret; + + ret = 0; + + spin_lock_irqsave(&priv->lock, flags); + + ret = __exynos_sysmmu_enable(data, __pa(priv->pgtable), domain); + + if (ret == 0) { + /* 'data->node' must not be appeared in priv->clients */ + BUG_ON(!list_empty(&data->node)); + data->dev = dev; + list_add_tail(&data->node, &priv->clients); + } + + spin_unlock_irqrestore(&priv->lock, flags); + + if (ret < 0) { + dev_err(dev, "%s: Failed to attach IOMMU with pgtable %#lx\n", + __func__, __pa(priv->pgtable)); + pm_runtime_put(data->sysmmu); + } else if (ret > 0) { + dev_dbg(dev, "%s: IOMMU with pgtable 0x%lx already attached\n", + __func__, __pa(priv->pgtable)); + } else { + dev_dbg(dev, "%s: Attached new IOMMU with pgtable 0x%lx\n", + __func__, __pa(priv->pgtable)); + } + + return ret; +} + +static void exynos_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu); + struct exynos_iommu_domain *priv = domain->priv; + struct list_head *pos; + unsigned long flags; + bool found = false; + + spin_lock_irqsave(&priv->lock, flags); + + list_for_each(pos, &priv->clients) { + if (list_entry(pos, struct sysmmu_drvdata, node) == data) { + found = true; + break; + } + } + + if (!found) + goto finish; + + if (__exynos_sysmmu_disable(data)) { + dev_dbg(dev, "%s: Detached IOMMU with pgtable %#lx\n", + __func__, __pa(priv->pgtable)); + list_del(&data->node); + INIT_LIST_HEAD(&data->node); + + } else { + dev_dbg(dev, "%s: Detaching IOMMU with pgtable %#lx delayed", + __func__, __pa(priv->pgtable)); + } + +finish: + spin_unlock_irqrestore(&priv->lock, flags); + + if (found) + pm_runtime_put(data->sysmmu); +} + +static unsigned long *alloc_lv2entry(unsigned long *sent, unsigned long iova, + short *pgcounter) +{ + if (lv1ent_fault(sent)) { + unsigned long *pent; + + pent = kzalloc(LV2TABLE_SIZE, GFP_ATOMIC); + BUG_ON((unsigned long)pent & (LV2TABLE_SIZE - 1)); + if (!pent) + return NULL; + + *sent = mk_lv1ent_page(__pa(pent)); + *pgcounter = NUM_LV2ENTRIES; + pgtable_flush(pent, pent + NUM_LV2ENTRIES); + pgtable_flush(sent, sent + 1); + } + + return page_entry(sent, iova); +} + +static int lv1set_section(unsigned long *sent, phys_addr_t paddr, short *pgcnt) +{ + if (lv1ent_section(sent)) + return -EADDRINUSE; + + if (lv1ent_page(sent)) { + if (*pgcnt != NUM_LV2ENTRIES) + return -EADDRINUSE; + + kfree(page_entry(sent, 0)); + + *pgcnt = 0; + } + + *sent = mk_lv1ent_sect(paddr); + + pgtable_flush(sent, sent + 1); + + return 0; +} + +static int lv2set_page(unsigned long *pent, phys_addr_t paddr, size_t size, + short *pgcnt) +{ + if (size == SPAGE_SIZE) { + if (!lv2ent_fault(pent)) + return -EADDRINUSE; + + *pent = mk_lv2ent_spage(paddr); + pgtable_flush(pent, pent + 1); + *pgcnt -= 1; + } else { /* size == LPAGE_SIZE */ + int i; + for (i = 0; i < SPAGES_PER_LPAGE; i++, pent++) { + if (!lv2ent_fault(pent)) { + memset(pent, 0, sizeof(*pent) * i); + return -EADDRINUSE; + } + + *pent = mk_lv2ent_lpage(paddr); + } + pgtable_flush(pent - SPAGES_PER_LPAGE, pent); + *pgcnt -= SPAGES_PER_LPAGE; + } + + return 0; +} + +static int exynos_iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + struct exynos_iommu_domain *priv = domain->priv; + unsigned long *entry; + unsigned long flags; + int ret = -ENOMEM; + + BUG_ON(priv->pgtable == NULL); + + spin_lock_irqsave(&priv->pgtablelock, flags); + + entry = section_entry(priv->pgtable, iova); + + if (size == SECT_SIZE) { + ret = lv1set_section(entry, paddr, + &priv->lv2entcnt[lv1ent_offset(iova)]); + } else { + unsigned long *pent; + + pent = alloc_lv2entry(entry, iova, + &priv->lv2entcnt[lv1ent_offset(iova)]); + + if (!pent) + ret = -ENOMEM; + else + ret = lv2set_page(pent, paddr, size, + &priv->lv2entcnt[lv1ent_offset(iova)]); + } + + if (ret) { + pr_debug("%s: Failed to map iova 0x%lx/0x%x bytes\n", + __func__, iova, size); + } + + spin_unlock_irqrestore(&priv->pgtablelock, flags); + + return ret; +} + +static size_t exynos_iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct exynos_iommu_domain *priv = domain->priv; + struct sysmmu_drvdata *data; + unsigned long flags; + unsigned long *ent; + + BUG_ON(priv->pgtable == NULL); + + spin_lock_irqsave(&priv->pgtablelock, flags); + + ent = section_entry(priv->pgtable, iova); + + if (lv1ent_section(ent)) { + BUG_ON(size < SECT_SIZE); + + *ent = 0; + pgtable_flush(ent, ent + 1); + size = SECT_SIZE; + goto done; + } + + if (unlikely(lv1ent_fault(ent))) { + if (size > SECT_SIZE) + size = SECT_SIZE; + goto done; + } + + /* lv1ent_page(sent) == true here */ + + ent = page_entry(ent, iova); + + if (unlikely(lv2ent_fault(ent))) { + size = SPAGE_SIZE; + goto done; + } + + if (lv2ent_small(ent)) { + *ent = 0; + size = SPAGE_SIZE; + priv->lv2entcnt[lv1ent_offset(iova)] += 1; + goto done; + } + + /* lv1ent_large(ent) == true here */ + BUG_ON(size < LPAGE_SIZE); + + memset(ent, 0, sizeof(*ent) * SPAGES_PER_LPAGE); + + size = LPAGE_SIZE; + priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE; +done: + spin_unlock_irqrestore(&priv->pgtablelock, flags); + + spin_lock_irqsave(&priv->lock, flags); + list_for_each_entry(data, &priv->clients, node) + sysmmu_tlb_invalidate_entry(data->dev, iova); + spin_unlock_irqrestore(&priv->lock, flags); + + + return size; +} + +static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain, + unsigned long iova) +{ + struct exynos_iommu_domain *priv = domain->priv; + unsigned long *entry; + unsigned long flags; + phys_addr_t phys = 0; + + spin_lock_irqsave(&priv->pgtablelock, flags); + + entry = section_entry(priv->pgtable, iova); + + if (lv1ent_section(entry)) { + phys = section_phys(entry) + section_offs(iova); + } else if (lv1ent_page(entry)) { + entry = page_entry(entry, iova); + + if (lv2ent_large(entry)) + phys = lpage_phys(entry) + lpage_offs(iova); + else if (lv2ent_small(entry)) + phys = spage_phys(entry) + spage_offs(iova); + } + + spin_unlock_irqrestore(&priv->pgtablelock, flags); + + return phys; +} + +static struct iommu_ops exynos_iommu_ops = { + .domain_init = &exynos_iommu_domain_init, + .domain_destroy = &exynos_iommu_domain_destroy, + .attach_dev = &exynos_iommu_attach_device, + .detach_dev = &exynos_iommu_detach_device, + .map = &exynos_iommu_map, + .unmap = &exynos_iommu_unmap, + .iova_to_phys = &exynos_iommu_iova_to_phys, + .pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE, +}; + +static int __init exynos_iommu_init(void) +{ + int ret; + + ret = platform_driver_register(&exynos_sysmmu_driver); + + if (ret == 0) + bus_set_iommu(&platform_bus_type, &exynos_iommu_ops); + + return ret; +} +subsys_initcall(exynos_iommu_init); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f93d5ac8f81c..b12af2ff8c54 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -42,6 +42,7 @@ #include <linux/dmi.h> #include <linux/pci-ats.h> #include <linux/memblock.h> +#include <asm/irq_remapping.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -1906,6 +1907,15 @@ static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn) iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); } +static inline void unlink_domain_info(struct device_domain_info *info) +{ + assert_spin_locked(&device_domain_lock); + list_del(&info->link); + list_del(&info->global); + if (info->dev) + info->dev->dev.archdata.iommu = NULL; +} + static void domain_remove_dev_info(struct dmar_domain *domain) { struct device_domain_info *info; @@ -1916,10 +1926,7 @@ static void domain_remove_dev_info(struct dmar_domain *domain) while (!list_empty(&domain->devices)) { info = list_entry(domain->devices.next, struct device_domain_info, link); - list_del(&info->link); - list_del(&info->global); - if (info->dev) - info->dev->dev.archdata.iommu = NULL; + unlink_domain_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); iommu_disable_dev_iotlb(info); @@ -2286,12 +2293,6 @@ static int domain_add_dev_info(struct dmar_domain *domain, if (!info) return -ENOMEM; - ret = domain_context_mapping(domain, pdev, translation); - if (ret) { - free_devinfo_mem(info); - return ret; - } - info->segment = pci_domain_nr(pdev->bus); info->bus = pdev->bus->number; info->devfn = pdev->devfn; @@ -2304,6 +2305,15 @@ static int domain_add_dev_info(struct dmar_domain *domain, pdev->dev.archdata.iommu = info; spin_unlock_irqrestore(&device_domain_lock, flags); + ret = domain_context_mapping(domain, pdev, translation); + if (ret) { + spin_lock_irqsave(&device_domain_lock, flags); + unlink_domain_info(info); + spin_unlock_irqrestore(&device_domain_lock, flags); + free_devinfo_mem(info); + return ret; + } + return 0; } @@ -3727,10 +3737,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, if (info->segment == pci_domain_nr(pdev->bus) && info->bus == pdev->bus->number && info->devfn == pdev->devfn) { - list_del(&info->link); - list_del(&info->global); - if (info->dev) - info->dev->dev.archdata.iommu = NULL; + unlink_domain_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); iommu_disable_dev_iotlb(info); @@ -3785,11 +3792,7 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain) while (!list_empty(&domain->devices)) { info = list_entry(domain->devices.next, struct device_domain_info, link); - list_del(&info->link); - list_del(&info->global); - if (info->dev) - info->dev->dev.archdata.iommu = NULL; - + unlink_domain_info(info); spin_unlock_irqrestore(&device_domain_lock, flags1); iommu_disable_dev_iotlb(info); @@ -4082,7 +4085,7 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, if (cap == IOMMU_CAP_CACHE_COHERENCY) return dmar_domain->iommu_snooping; if (cap == IOMMU_CAP_INTR_REMAP) - return intr_remapping_enabled; + return irq_remapping_enabled; return 0; } diff --git a/drivers/iommu/intr_remapping.c b/drivers/iommu/intel_irq_remapping.c index 6777ca049471..6d347064b8b0 100644 --- a/drivers/iommu/intr_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -10,49 +10,33 @@ #include <asm/smp.h> #include <asm/cpu.h> #include <linux/intel-iommu.h> -#include "intr_remapping.h" #include <acpi/acpi.h> +#include <asm/irq_remapping.h> #include <asm/pci-direct.h> +#include <asm/msidef.h> -static struct ioapic_scope ir_ioapic[MAX_IO_APICS]; -static struct hpet_scope ir_hpet[MAX_HPET_TBS]; -static int ir_ioapic_num, ir_hpet_num; -int intr_remapping_enabled; - -static int disable_intremap; -static int disable_sourceid_checking; -static int no_x2apic_optout; +#include "irq_remapping.h" -static __init int setup_nointremap(char *str) -{ - disable_intremap = 1; - return 0; -} -early_param("nointremap", setup_nointremap); +struct ioapic_scope { + struct intel_iommu *iommu; + unsigned int id; + unsigned int bus; /* PCI bus number */ + unsigned int devfn; /* PCI devfn number */ +}; -static __init int setup_intremap(char *str) -{ - if (!str) - return -EINVAL; +struct hpet_scope { + struct intel_iommu *iommu; + u8 id; + unsigned int bus; + unsigned int devfn; +}; - while (*str) { - if (!strncmp(str, "on", 2)) - disable_intremap = 0; - else if (!strncmp(str, "off", 3)) - disable_intremap = 1; - else if (!strncmp(str, "nosid", 5)) - disable_sourceid_checking = 1; - else if (!strncmp(str, "no_x2apic_optout", 16)) - no_x2apic_optout = 1; - - str += strcspn(str, ","); - while (*str == ',') - str++; - } +#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0) +#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8) - return 0; -} -early_param("intremap", setup_intremap); +static struct ioapic_scope ir_ioapic[MAX_IO_APICS]; +static struct hpet_scope ir_hpet[MAX_HPET_TBS]; +static int ir_ioapic_num, ir_hpet_num; static DEFINE_RAW_SPINLOCK(irq_2_ir_lock); @@ -80,7 +64,7 @@ int get_irte(int irq, struct irte *entry) return 0; } -int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) +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); @@ -152,7 +136,7 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask) return qi_submit_sync(&desc, iommu); } -int map_irq_to_irte_handle(int irq, u16 *sub_handle) +static int map_irq_to_irte_handle(int irq, u16 *sub_handle) { struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); unsigned long flags; @@ -168,7 +152,7 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle) return index; } -int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle) +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); unsigned long flags; @@ -188,7 +172,7 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle) return 0; } -int modify_irte(int irq, struct irte *irte_modified) +static int modify_irte(int irq, struct irte *irte_modified) { struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); struct intel_iommu *iommu; @@ -216,7 +200,7 @@ int modify_irte(int irq, struct irte *irte_modified) return rc; } -struct intel_iommu *map_hpet_to_ir(u8 hpet_id) +static struct intel_iommu *map_hpet_to_ir(u8 hpet_id) { int i; @@ -226,7 +210,7 @@ struct intel_iommu *map_hpet_to_ir(u8 hpet_id) return NULL; } -struct intel_iommu *map_ioapic_to_ir(int apic) +static struct intel_iommu *map_ioapic_to_ir(int apic) { int i; @@ -236,7 +220,7 @@ struct intel_iommu *map_ioapic_to_ir(int apic) return NULL; } -struct intel_iommu *map_dev_to_ir(struct pci_dev *dev) +static struct intel_iommu *map_dev_to_ir(struct pci_dev *dev) { struct dmar_drhd_unit *drhd; @@ -270,7 +254,7 @@ static int clear_entries(struct irq_2_iommu *irq_iommu) return qi_flush_iec(iommu, index, irq_iommu->irte_mask); } -int free_irte(int irq) +static int free_irte(int irq) { struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); unsigned long flags; @@ -328,7 +312,7 @@ static void set_irte_sid(struct irte *irte, unsigned int svt, irte->sid = sid; } -int set_ioapic_sid(struct irte *irte, int apic) +static int set_ioapic_sid(struct irte *irte, int apic) { int i; u16 sid = 0; @@ -353,7 +337,7 @@ int set_ioapic_sid(struct irte *irte, int apic) return 0; } -int set_hpet_sid(struct irte *irte, u8 id) +static int set_hpet_sid(struct irte *irte, u8 id) { int i; u16 sid = 0; @@ -383,7 +367,7 @@ int set_hpet_sid(struct irte *irte, u8 id) return 0; } -int set_msi_sid(struct irte *irte, struct pci_dev *dev) +static int set_msi_sid(struct irte *irte, struct pci_dev *dev) { struct pci_dev *bridge; @@ -410,7 +394,7 @@ int set_msi_sid(struct irte *irte, struct pci_dev *dev) return 0; } -static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode) +static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode) { u64 addr; u32 sts; @@ -450,7 +434,7 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode) } -static int setup_intr_remapping(struct intel_iommu *iommu, int mode) +static int intel_setup_irq_remapping(struct intel_iommu *iommu, int mode) { struct ir_table *ir_table; struct page *pages; @@ -473,14 +457,14 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode) ir_table->base = page_address(pages); - iommu_set_intr_remapping(iommu, mode); + iommu_set_irq_remapping(iommu, mode); return 0; } /* * Disable Interrupt Remapping. */ -static void iommu_disable_intr_remapping(struct intel_iommu *iommu) +static void iommu_disable_irq_remapping(struct intel_iommu *iommu) { unsigned long flags; u32 sts; @@ -519,11 +503,11 @@ static int __init dmar_x2apic_optout(void) return dmar->flags & DMAR_X2APIC_OPT_OUT; } -int __init intr_remapping_supported(void) +static int __init intel_irq_remapping_supported(void) { struct dmar_drhd_unit *drhd; - if (disable_intremap) + if (disable_irq_remap) return 0; if (!dmar_ir_support()) @@ -539,7 +523,7 @@ int __init intr_remapping_supported(void) return 1; } -int __init enable_intr_remapping(void) +static int __init intel_enable_irq_remapping(void) { struct dmar_drhd_unit *drhd; int setup = 0; @@ -577,7 +561,7 @@ int __init enable_intr_remapping(void) * Disable intr remapping and queued invalidation, if already * enabled prior to OS handover. */ - iommu_disable_intr_remapping(iommu); + iommu_disable_irq_remapping(iommu); dmar_disable_qi(iommu); } @@ -623,7 +607,7 @@ int __init enable_intr_remapping(void) if (!ecap_ir_support(iommu->ecap)) continue; - if (setup_intr_remapping(iommu, eim)) + if (intel_setup_irq_remapping(iommu, eim)) goto error; setup = 1; @@ -632,7 +616,7 @@ int __init enable_intr_remapping(void) if (!setup) goto error; - intr_remapping_enabled = 1; + irq_remapping_enabled = 1; pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic"); return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE; @@ -775,14 +759,14 @@ int __init parse_ioapics_under_ir(void) int __init ir_dev_scope_init(void) { - if (!intr_remapping_enabled) + if (!irq_remapping_enabled) return 0; return dmar_dev_scope_init(); } rootfs_initcall(ir_dev_scope_init); -void disable_intr_remapping(void) +static void disable_irq_remapping(void) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu = NULL; @@ -794,11 +778,11 @@ void disable_intr_remapping(void) if (!ecap_ir_support(iommu->ecap)) continue; - iommu_disable_intr_remapping(iommu); + iommu_disable_irq_remapping(iommu); } } -int reenable_intr_remapping(int eim) +static int reenable_irq_remapping(int eim) { struct dmar_drhd_unit *drhd; int setup = 0; @@ -816,7 +800,7 @@ int reenable_intr_remapping(int eim) continue; /* Set up interrupt remapping for iommu.*/ - iommu_set_intr_remapping(iommu, eim); + iommu_set_irq_remapping(iommu, eim); setup = 1; } @@ -832,3 +816,254 @@ error: return -1; } +static void prepare_irte(struct irte *irte, int vector, + unsigned int dest) +{ + memset(irte, 0, sizeof(*irte)); + + irte->present = 1; + irte->dst_mode = apic->irq_dest_mode; + /* + * Trigger mode in the IRTE will always be edge, and for IO-APIC, the + * actual level or edge trigger will be setup in the IO-APIC + * RTE. This will help simplify level triggered irq migration. + * For more details, see the comments (in io_apic.c) explainig IO-APIC + * irq migration in the presence of interrupt-remapping. + */ + irte->trigger_mode = 0; + irte->dlvry_mode = apic->irq_delivery_mode; + irte->vector = vector; + irte->dest_id = IRTE_DEST(dest); + irte->redir_hint = 1; +} + +static int intel_setup_ioapic_entry(int irq, + struct IO_APIC_route_entry *route_entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) +{ + int ioapic_id = mpc_ioapic_id(attr->ioapic); + struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id); + struct IR_IO_APIC_route_entry *entry; + struct irte irte; + int index; + + if (!iommu) { + pr_warn("No mapping iommu for ioapic %d\n", ioapic_id); + return -ENODEV; + } + + entry = (struct IR_IO_APIC_route_entry *)route_entry; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) { + pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id); + return -ENOMEM; + } + + prepare_irte(&irte, vector, destination); + + /* Set source-id of interrupt request */ + set_ioapic_sid(&irte, ioapic_id); + + modify_irte(irq, &irte); + + apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: " + "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d " + "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X " + "Avail:%X Vector:%02X Dest:%08X " + "SID:%04X SQ:%X SVT:%X)\n", + attr->ioapic, irte.present, irte.fpd, irte.dst_mode, + irte.redir_hint, irte.trigger_mode, irte.dlvry_mode, + irte.avail, irte.vector, irte.dest_id, + irte.sid, irte.sq, irte.svt); + + memset(entry, 0, sizeof(*entry)); + + entry->index2 = (index >> 15) & 0x1; + entry->zero = 0; + entry->format = 1; + entry->index = (index & 0x7fff); + /* + * IO-APIC RTE will be configured with virtual vector. + * irq handler will do the explicit EOI to the io-apic. + */ + entry->vector = attr->ioapic_pin; + entry->mask = 0; /* enable IRQ */ + entry->trigger = attr->trigger; + entry->polarity = attr->polarity; + + /* Mask level triggered irqs. + * Use IRQ_DELAYED_DISABLE for edge triggered irqs. + */ + if (attr->trigger) + entry->mask = 1; + + return 0; +} + +#ifdef CONFIG_SMP +/* + * Migrate the IO-APIC irq in the presence of intr-remapping. + * + * For both level and edge triggered, irq migration is a simple atomic + * update(of vector and cpu destination) of IRTE and flush the hardware cache. + * + * For level triggered, we eliminate the io-apic RTE modification (with the + * updated vector information), by using a virtual vector (io-apic pin number). + * Real vector that is used for interrupting cpu will be coming from + * the interrupt-remapping table entry. + * + * As the migration is a simple atomic update of IRTE, the same mechanism + * is used to migrate MSI irq's in the presence of interrupt-remapping. + */ +static int +intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_cfg *cfg = data->chip_data; + unsigned int dest, irq = data->irq; + struct irte irte; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + if (get_irte(irq, &irte)) + return -EBUSY; + + if (assign_irq_vector(irq, cfg, mask)) + return -EBUSY; + + dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); + + irte.vector = cfg->vector; + irte.dest_id = IRTE_DEST(dest); + + /* + * Atomically updates the IRTE with the new destination, vector + * and flushes the interrupt entry cache. + */ + modify_irte(irq, &irte); + + /* + * After this point, all the interrupts will start arriving + * at the new destination. So, time to cleanup the previous + * vector allocation. + */ + if (cfg->move_in_progress) + send_cleanup_vector(cfg); + + cpumask_copy(data->affinity, mask); + return 0; +} +#endif + +static void intel_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg; + struct irte irte; + u16 sub_handle = 0; + int ir_index; + + cfg = irq_get_chip_data(irq); + + ir_index = map_irq_to_irte_handle(irq, &sub_handle); + BUG_ON(ir_index == -1); + + prepare_irte(&irte, cfg->vector, dest); + + /* Set source-id of interrupt request */ + if (pdev) + set_msi_sid(&irte, pdev); + else + set_hpet_sid(&irte, hpet_id); + + modify_irte(irq, &irte); + + msg->address_hi = MSI_ADDR_BASE_HI; + msg->data = sub_handle; + msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT | + MSI_ADDR_IR_SHV | + MSI_ADDR_IR_INDEX1(ir_index) | + MSI_ADDR_IR_INDEX2(ir_index); +} + +/* + * Map the PCI dev to the corresponding remapping hardware unit + * and allocate 'nvec' consecutive interrupt-remapping table entries + * in it. + */ +static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec) +{ + struct intel_iommu *iommu; + int index; + + iommu = map_dev_to_ir(dev); + if (!iommu) { + printk(KERN_ERR + "Unable to map PCI %s to iommu\n", pci_name(dev)); + return -ENOENT; + } + + index = alloc_irte(iommu, irq, nvec); + if (index < 0) { + printk(KERN_ERR + "Unable to allocate %d IRTE for PCI %s\n", nvec, + pci_name(dev)); + return -ENOSPC; + } + return index; +} + +static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq, + int index, int sub_handle) +{ + struct intel_iommu *iommu; + + iommu = map_dev_to_ir(pdev); + if (!iommu) + return -ENOENT; + /* + * setup the mapping between the irq and the IRTE + * base index, the sub_handle pointing to the + * appropriate interrupt remap table entry. + */ + set_irte_irq(irq, iommu, index, sub_handle); + + return 0; +} + +static int intel_setup_hpet_msi(unsigned int irq, unsigned int id) +{ + struct intel_iommu *iommu = map_hpet_to_ir(id); + int index; + + if (!iommu) + return -1; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) + return -1; + + return 0; +} + +struct irq_remap_ops intel_irq_remap_ops = { + .supported = intel_irq_remapping_supported, + .prepare = dmar_table_init, + .enable = intel_enable_irq_remapping, + .disable = disable_irq_remapping, + .reenable = reenable_irq_remapping, + .enable_faulting = enable_drhd_fault_handling, + .setup_ioapic_entry = intel_setup_ioapic_entry, +#ifdef CONFIG_SMP + .set_affinity = intel_ioapic_set_affinity, +#endif + .free_irq = free_irte, + .compose_msi_msg = intel_compose_msi_msg, + .msi_alloc_irq = intel_msi_alloc_irq, + .msi_setup_irq = intel_msi_setup_irq, + .setup_hpet_msi = intel_setup_hpet_msi, +}; diff --git a/drivers/iommu/intr_remapping.h b/drivers/iommu/intr_remapping.h deleted file mode 100644 index 5662fecfee60..000000000000 --- a/drivers/iommu/intr_remapping.h +++ /dev/null @@ -1,17 +0,0 @@ -#include <linux/intel-iommu.h> - -struct ioapic_scope { - struct intel_iommu *iommu; - unsigned int id; - unsigned int bus; /* PCI bus number */ - unsigned int devfn; /* PCI devfn number */ -}; - -struct hpet_scope { - struct intel_iommu *iommu; - u8 id; - unsigned int bus; - unsigned int devfn; -}; - -#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0) diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c new file mode 100644 index 000000000000..40cda8e98d87 --- /dev/null +++ b/drivers/iommu/irq_remapping.c @@ -0,0 +1,166 @@ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> + +#include "irq_remapping.h" + +int irq_remapping_enabled; + +int disable_irq_remap; +int disable_sourceid_checking; +int no_x2apic_optout; + +static struct irq_remap_ops *remap_ops; + +static __init int setup_nointremap(char *str) +{ + disable_irq_remap = 1; + return 0; +} +early_param("nointremap", setup_nointremap); + +static __init int setup_irqremap(char *str) +{ + if (!str) + return -EINVAL; + + while (*str) { + if (!strncmp(str, "on", 2)) + disable_irq_remap = 0; + else if (!strncmp(str, "off", 3)) + disable_irq_remap = 1; + else if (!strncmp(str, "nosid", 5)) + disable_sourceid_checking = 1; + else if (!strncmp(str, "no_x2apic_optout", 16)) + no_x2apic_optout = 1; + + str += strcspn(str, ","); + while (*str == ',') + str++; + } + + return 0; +} +early_param("intremap", setup_irqremap); + +void __init setup_irq_remapping_ops(void) +{ + remap_ops = &intel_irq_remap_ops; +} + +int irq_remapping_supported(void) +{ + if (disable_irq_remap) + return 0; + + if (!remap_ops || !remap_ops->supported) + return 0; + + return remap_ops->supported(); +} + +int __init irq_remapping_prepare(void) +{ + if (!remap_ops || !remap_ops->prepare) + return -ENODEV; + + return remap_ops->prepare(); +} + +int __init irq_remapping_enable(void) +{ + if (!remap_ops || !remap_ops->enable) + return -ENODEV; + + return remap_ops->enable(); +} + +void irq_remapping_disable(void) +{ + if (!remap_ops || !remap_ops->disable) + return; + + remap_ops->disable(); +} + +int irq_remapping_reenable(int mode) +{ + if (!remap_ops || !remap_ops->reenable) + return 0; + + return remap_ops->reenable(mode); +} + +int __init irq_remap_enable_fault_handling(void) +{ + if (!remap_ops || !remap_ops->enable_faulting) + return -ENODEV; + + return remap_ops->enable_faulting(); +} + +int setup_ioapic_remapped_entry(int irq, + struct IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) +{ + if (!remap_ops || !remap_ops->setup_ioapic_entry) + return -ENODEV; + + return remap_ops->setup_ioapic_entry(irq, entry, destination, + vector, attr); +} + +#ifdef CONFIG_SMP +int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + if (!remap_ops || !remap_ops->set_affinity) + return 0; + + return remap_ops->set_affinity(data, mask, force); +} +#endif + +void free_remapped_irq(int irq) +{ + if (!remap_ops || !remap_ops->free_irq) + return; + + 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; + + remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); +} + +int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) +{ + if (!remap_ops || !remap_ops->msi_alloc_irq) + return -ENODEV; + + 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) +{ + if (!remap_ops || !remap_ops->msi_setup_irq) + return -ENODEV; + + return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle); +} + +int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) +{ + if (!remap_ops || !remap_ops->setup_hpet_msi) + return -ENODEV; + + return remap_ops->setup_hpet_msi(irq, id); +} diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h new file mode 100644 index 000000000000..be9d72950c51 --- /dev/null +++ b/drivers/iommu/irq_remapping.h @@ -0,0 +1,90 @@ +/* + * Copyright (C) 2012 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This header file contains stuff that is shared between different interrupt + * remapping drivers but with no need to be visible outside of the IOMMU layer. + */ + +#ifndef __IRQ_REMAPPING_H +#define __IRQ_REMAPPING_H + +#ifdef CONFIG_IRQ_REMAP + +struct IO_APIC_route_entry; +struct io_apic_irq_attr; +struct irq_data; +struct cpumask; +struct pci_dev; +struct msi_msg; + +extern int disable_irq_remap; +extern int disable_sourceid_checking; +extern int no_x2apic_optout; + +struct irq_remap_ops { + /* Check whether Interrupt Remapping is supported */ + int (*supported)(void); + + /* Initializes hardware and makes it ready for remapping interrupts */ + int (*prepare)(void); + + /* Enables the remapping hardware */ + int (*enable)(void); + + /* Disables the remapping hardware */ + void (*disable)(void); + + /* Reenables the remapping hardware */ + int (*reenable)(int); + + /* Enable fault handling */ + int (*enable_faulting)(void); + + /* IO-APIC setup routine */ + int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *, + unsigned int, int, + struct io_apic_irq_attr *); + +#ifdef CONFIG_SMP + /* Set the CPU affinity of a remapped interrupt */ + int (*set_affinity)(struct irq_data *data, const struct cpumask *mask, + bool force); +#endif + + /* Free an IRQ */ + int (*free_irq)(int); + + /* Create MSI msg to use for interrupt remapping */ + void (*compose_msi_msg)(struct pci_dev *, + unsigned int, unsigned int, + struct msi_msg *, u8); + + /* Allocate remapping resources for MSI */ + int (*msi_alloc_irq)(struct pci_dev *, int, int); + + /* Setup the remapped MSI irq */ + int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int); + + /* Setup interrupt remapping for an HPET MSI */ + int (*setup_hpet_msi)(unsigned int, unsigned int); +}; + +extern struct irq_remap_ops intel_irq_remap_ops; + +#endif /* CONFIG_IRQ_REMAP */ + +#endif /* __IRQ_REMAPPING_H */ |