From 2c3c1048746a4622d8c89a29670120dc8fab93c4 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 20:49:45 +0200 Subject: Adding upstream version 6.1.76. Signed-off-by: Daniel Baumann --- drivers/iommu/amd/Kconfig | 44 + drivers/iommu/amd/Makefile | 4 + drivers/iommu/amd/amd_iommu.h | 142 ++ drivers/iommu/amd/amd_iommu_types.h | 1029 ++++++++++ drivers/iommu/amd/debugfs.c | 32 + drivers/iommu/amd/init.c | 3764 +++++++++++++++++++++++++++++++++++ drivers/iommu/amd/io_pgtable.c | 537 +++++ drivers/iommu/amd/io_pgtable_v2.c | 415 ++++ drivers/iommu/amd/iommu.c | 3750 ++++++++++++++++++++++++++++++++++ drivers/iommu/amd/iommu_v2.c | 991 +++++++++ drivers/iommu/amd/quirks.c | 105 + 11 files changed, 10813 insertions(+) create mode 100644 drivers/iommu/amd/Kconfig create mode 100644 drivers/iommu/amd/Makefile create mode 100644 drivers/iommu/amd/amd_iommu.h create mode 100644 drivers/iommu/amd/amd_iommu_types.h create mode 100644 drivers/iommu/amd/debugfs.c create mode 100644 drivers/iommu/amd/init.c create mode 100644 drivers/iommu/amd/io_pgtable.c create mode 100644 drivers/iommu/amd/io_pgtable_v2.c create mode 100644 drivers/iommu/amd/iommu.c create mode 100644 drivers/iommu/amd/iommu_v2.c create mode 100644 drivers/iommu/amd/quirks.c (limited to 'drivers/iommu/amd') diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig new file mode 100644 index 000000000..9b5fc3356 --- /dev/null +++ b/drivers/iommu/amd/Kconfig @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: GPL-2.0-only +# AMD IOMMU support +config AMD_IOMMU + bool "AMD IOMMU support" + select SWIOTLB + select PCI_MSI + select PCI_ATS + select PCI_PRI + select PCI_PASID + select IOMMU_API + select IOMMU_IOVA + select IOMMU_IO_PGTABLE + depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE + help + 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 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 + your BIOS for an option to enable it or if you have an IVRS ACPI + table. + +config AMD_IOMMU_V2 + tristate "AMD IOMMU Version 2 driver" + depends on AMD_IOMMU + select MMU_NOTIFIER + 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 PCI PRI and PASID interface. + +config AMD_IOMMU_DEBUGFS + bool "Enable AMD IOMMU internals in DebugFS" + depends on AMD_IOMMU && IOMMU_DEBUGFS + help + !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!! + Exposes AMD IOMMU device internals in DebugFS. + + This option is -NOT- intended for production environments, and should + not generally be enabled. diff --git a/drivers/iommu/amd/Makefile b/drivers/iommu/amd/Makefile new file mode 100644 index 000000000..773d8aa00 --- /dev/null +++ b/drivers/iommu/amd/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o +obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o +obj-$(CONFIG_AMD_IOMMU_V2) += iommu_v2.o diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h new file mode 100644 index 000000000..471f40351 --- /dev/null +++ b/drivers/iommu/amd/amd_iommu.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009-2010 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + */ + +#ifndef AMD_IOMMU_H +#define AMD_IOMMU_H + +#include + +#include "amd_iommu_types.h" + +extern irqreturn_t amd_iommu_int_thread(int irq, void *data); +extern irqreturn_t amd_iommu_int_handler(int irq, void *data); +extern void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid); +extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu); +extern void amd_iommu_restart_ga_log(struct amd_iommu *iommu); +extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid); + +#ifdef CONFIG_AMD_IOMMU_DEBUGFS +void amd_iommu_debugfs_setup(struct amd_iommu *iommu); +#else +static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {} +#endif + +/* Needed for interrupt remapping */ +extern int amd_iommu_prepare(void); +extern int amd_iommu_enable(void); +extern void amd_iommu_disable(void); +extern int amd_iommu_reenable(int); +extern int amd_iommu_enable_faulting(void); +extern int amd_iommu_guest_ir; +extern enum io_pgtable_fmt amd_iommu_pgtable; + +/* IOMMUv2 specific functions */ +struct iommu_domain; + +extern bool amd_iommu_v2_supported(void); +extern struct amd_iommu *get_amd_iommu(unsigned int idx); +extern u8 amd_iommu_pc_get_max_banks(unsigned int idx); +extern bool amd_iommu_pc_supported(void); +extern u8 amd_iommu_pc_get_max_counters(unsigned int idx); +extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); +extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); + +extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb); +extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb); +extern void amd_iommu_domain_direct_map(struct iommu_domain *dom); +extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids); +extern int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, + u64 address); +extern void amd_iommu_update_and_flush_device_table(struct protection_domain *domain); +extern void amd_iommu_domain_update(struct protection_domain *domain); +extern void amd_iommu_domain_flush_complete(struct protection_domain *domain); +extern void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain); +extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid); +extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid, + unsigned long cr3); +extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid); + +#ifdef CONFIG_IRQ_REMAP +extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu); +#else +static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu) +{ + return 0; +} +#endif + +#define PPR_SUCCESS 0x0 +#define PPR_INVALID 0x1 +#define PPR_FAILURE 0xf + +extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid, + int status, int tag); + +static inline bool is_rd890_iommu(struct pci_dev *pdev) +{ + return (pdev->vendor == PCI_VENDOR_ID_ATI) && + (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); +} + +static inline bool iommu_feature(struct amd_iommu *iommu, u64 mask) +{ + return !!(iommu->features & mask); +} + +static inline u64 iommu_virt_to_phys(void *vaddr) +{ + return (u64)__sme_set(virt_to_phys(vaddr)); +} + +static inline void *iommu_phys_to_virt(unsigned long paddr) +{ + return phys_to_virt(__sme_clr(paddr)); +} + +static inline +void amd_iommu_domain_set_pt_root(struct protection_domain *domain, u64 root) +{ + atomic64_set(&domain->iop.pt_root, root); + domain->iop.root = (u64 *)(root & PAGE_MASK); + domain->iop.mode = root & 7; /* lowest 3 bits encode pgtable mode */ +} + +static inline +void amd_iommu_domain_clr_pt_root(struct protection_domain *domain) +{ + amd_iommu_domain_set_pt_root(domain, 0); +} + +static inline int get_pci_sbdf_id(struct pci_dev *pdev) +{ + int seg = pci_domain_nr(pdev->bus); + u16 devid = pci_dev_id(pdev); + + return PCI_SEG_DEVID_TO_SBDF(seg, devid); +} + +extern bool translation_pre_enabled(struct amd_iommu *iommu); +extern bool amd_iommu_is_attach_deferred(struct device *dev); +extern int __init add_special_device(u8 type, u8 id, u32 *devid, + bool cmd_line); + +#ifdef CONFIG_DMI +void amd_iommu_apply_ivrs_quirks(void); +#else +static inline void amd_iommu_apply_ivrs_quirks(void) { } +#endif + +extern void amd_iommu_domain_set_pgtable(struct protection_domain *domain, + u64 *root, int mode); +extern struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); + +extern u64 amd_iommu_efr; +extern u64 amd_iommu_efr2; + +extern bool amd_iommu_snp_en; +#endif diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h new file mode 100644 index 000000000..f5e9377b5 --- /dev/null +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -0,0 +1,1029 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + * Leo Duran + */ + +#ifndef _ASM_X86_AMD_IOMMU_TYPES_H +#define _ASM_X86_AMD_IOMMU_TYPES_H + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Maximum number of IOMMUs supported + */ +#define MAX_IOMMUS 32 + +/* + * some size calculation constants + */ +#define DEV_TABLE_ENTRY_SIZE 32 +#define ALIAS_TABLE_ENTRY_SIZE 2 +#define RLOOKUP_TABLE_ENTRY_SIZE (sizeof(void *)) + +/* Capability offsets used by the driver */ +#define MMIO_CAP_HDR_OFFSET 0x00 +#define MMIO_RANGE_OFFSET 0x0c +#define MMIO_MISC_OFFSET 0x10 + +/* Masks, shifts and macros to parse the device range capability */ +#define MMIO_RANGE_LD_MASK 0xff000000 +#define MMIO_RANGE_FD_MASK 0x00ff0000 +#define MMIO_RANGE_BUS_MASK 0x0000ff00 +#define MMIO_RANGE_LD_SHIFT 24 +#define MMIO_RANGE_FD_SHIFT 16 +#define MMIO_RANGE_BUS_SHIFT 8 +#define MMIO_GET_LD(x) (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT) +#define MMIO_GET_FD(x) (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT) +#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT) +#define MMIO_MSI_NUM(x) ((x) & 0x1f) + +/* Flag masks for the AMD IOMMU exclusion range */ +#define MMIO_EXCL_ENABLE_MASK 0x01ULL +#define MMIO_EXCL_ALLOW_MASK 0x02ULL + +/* Used offsets into the MMIO space */ +#define MMIO_DEV_TABLE_OFFSET 0x0000 +#define MMIO_CMD_BUF_OFFSET 0x0008 +#define MMIO_EVT_BUF_OFFSET 0x0010 +#define MMIO_CONTROL_OFFSET 0x0018 +#define MMIO_EXCL_BASE_OFFSET 0x0020 +#define MMIO_EXCL_LIMIT_OFFSET 0x0028 +#define MMIO_EXT_FEATURES 0x0030 +#define MMIO_PPR_LOG_OFFSET 0x0038 +#define MMIO_GA_LOG_BASE_OFFSET 0x00e0 +#define MMIO_GA_LOG_TAIL_OFFSET 0x00e8 +#define MMIO_MSI_ADDR_LO_OFFSET 0x015C +#define MMIO_MSI_ADDR_HI_OFFSET 0x0160 +#define MMIO_MSI_DATA_OFFSET 0x0164 +#define MMIO_INTCAPXT_EVT_OFFSET 0x0170 +#define MMIO_INTCAPXT_PPR_OFFSET 0x0178 +#define MMIO_INTCAPXT_GALOG_OFFSET 0x0180 +#define MMIO_EXT_FEATURES2 0x01A0 +#define MMIO_CMD_HEAD_OFFSET 0x2000 +#define MMIO_CMD_TAIL_OFFSET 0x2008 +#define MMIO_EVT_HEAD_OFFSET 0x2010 +#define MMIO_EVT_TAIL_OFFSET 0x2018 +#define MMIO_STATUS_OFFSET 0x2020 +#define MMIO_PPR_HEAD_OFFSET 0x2030 +#define MMIO_PPR_TAIL_OFFSET 0x2038 +#define MMIO_GA_HEAD_OFFSET 0x2040 +#define MMIO_GA_TAIL_OFFSET 0x2048 +#define MMIO_CNTR_CONF_OFFSET 0x4000 +#define MMIO_CNTR_REG_OFFSET 0x40000 +#define MMIO_REG_END_OFFSET 0x80000 + + + +/* Extended Feature Bits */ +#define FEATURE_PREFETCH (1ULL<<0) +#define FEATURE_PPR (1ULL<<1) +#define FEATURE_X2APIC (1ULL<<2) +#define FEATURE_NX (1ULL<<3) +#define FEATURE_GT (1ULL<<4) +#define FEATURE_IA (1ULL<<6) +#define FEATURE_GA (1ULL<<7) +#define FEATURE_HE (1ULL<<8) +#define FEATURE_PC (1ULL<<9) +#define FEATURE_GAM_VAPIC (1ULL<<21) +#define FEATURE_GIOSUP (1ULL<<48) +#define FEATURE_EPHSUP (1ULL<<50) +#define FEATURE_SNP (1ULL<<63) + +#define FEATURE_PASID_SHIFT 32 +#define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT) + +#define FEATURE_GLXVAL_SHIFT 14 +#define FEATURE_GLXVAL_MASK (0x03ULL << FEATURE_GLXVAL_SHIFT) + +/* Extended Feature 2 Bits */ +#define FEATURE_SNPAVICSUP_SHIFT 5 +#define FEATURE_SNPAVICSUP_MASK (0x07ULL << FEATURE_SNPAVICSUP_SHIFT) +#define FEATURE_SNPAVICSUP_GAM(x) \ + ((x & FEATURE_SNPAVICSUP_MASK) >> FEATURE_SNPAVICSUP_SHIFT == 0x1) + +/* Note: + * The current driver only support 16-bit PASID. + * Currently, hardware only implement upto 16-bit PASID + * even though the spec says it could have upto 20 bits. + */ +#define PASID_MASK 0x0000ffff + +/* MMIO status bits */ +#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK (1 << 0) +#define MMIO_STATUS_EVT_INT_MASK (1 << 1) +#define MMIO_STATUS_COM_WAIT_INT_MASK (1 << 2) +#define MMIO_STATUS_PPR_INT_MASK (1 << 6) +#define MMIO_STATUS_GALOG_RUN_MASK (1 << 8) +#define MMIO_STATUS_GALOG_OVERFLOW_MASK (1 << 9) +#define MMIO_STATUS_GALOG_INT_MASK (1 << 10) + +/* event logging constants */ +#define EVENT_ENTRY_SIZE 0x10 +#define EVENT_TYPE_SHIFT 28 +#define EVENT_TYPE_MASK 0xf +#define EVENT_TYPE_ILL_DEV 0x1 +#define EVENT_TYPE_IO_FAULT 0x2 +#define EVENT_TYPE_DEV_TAB_ERR 0x3 +#define EVENT_TYPE_PAGE_TAB_ERR 0x4 +#define EVENT_TYPE_ILL_CMD 0x5 +#define EVENT_TYPE_CMD_HARD_ERR 0x6 +#define EVENT_TYPE_IOTLB_INV_TO 0x7 +#define EVENT_TYPE_INV_DEV_REQ 0x8 +#define EVENT_TYPE_INV_PPR_REQ 0x9 +#define EVENT_TYPE_RMP_FAULT 0xd +#define EVENT_TYPE_RMP_HW_ERR 0xe +#define EVENT_DEVID_MASK 0xffff +#define EVENT_DEVID_SHIFT 0 +#define EVENT_DOMID_MASK_LO 0xffff +#define EVENT_DOMID_MASK_HI 0xf0000 +#define EVENT_FLAGS_MASK 0xfff +#define EVENT_FLAGS_SHIFT 0x10 +#define EVENT_FLAG_RW 0x020 +#define EVENT_FLAG_I 0x008 + +/* feature control bits */ +#define CONTROL_IOMMU_EN 0 +#define CONTROL_HT_TUN_EN 1 +#define CONTROL_EVT_LOG_EN 2 +#define CONTROL_EVT_INT_EN 3 +#define CONTROL_COMWAIT_EN 4 +#define CONTROL_INV_TIMEOUT 5 +#define CONTROL_PASSPW_EN 8 +#define CONTROL_RESPASSPW_EN 9 +#define CONTROL_COHERENT_EN 10 +#define CONTROL_ISOC_EN 11 +#define CONTROL_CMDBUF_EN 12 +#define CONTROL_PPRLOG_EN 13 +#define CONTROL_PPRINT_EN 14 +#define CONTROL_PPR_EN 15 +#define CONTROL_GT_EN 16 +#define CONTROL_GA_EN 17 +#define CONTROL_GAM_EN 25 +#define CONTROL_GALOG_EN 28 +#define CONTROL_GAINT_EN 29 +#define CONTROL_XT_EN 50 +#define CONTROL_INTCAPXT_EN 51 +#define CONTROL_IRTCACHEDIS 59 +#define CONTROL_SNPAVIC_EN 61 + +#define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) +#define CTRL_INV_TO_NONE 0 +#define CTRL_INV_TO_1MS 1 +#define CTRL_INV_TO_10MS 2 +#define CTRL_INV_TO_100MS 3 +#define CTRL_INV_TO_1S 4 +#define CTRL_INV_TO_10S 5 +#define CTRL_INV_TO_100S 6 + +/* command specific defines */ +#define CMD_COMPL_WAIT 0x01 +#define CMD_INV_DEV_ENTRY 0x02 +#define CMD_INV_IOMMU_PAGES 0x03 +#define CMD_INV_IOTLB_PAGES 0x04 +#define CMD_INV_IRT 0x05 +#define CMD_COMPLETE_PPR 0x07 +#define CMD_INV_ALL 0x08 + +#define CMD_COMPL_WAIT_STORE_MASK 0x01 +#define CMD_COMPL_WAIT_INT_MASK 0x02 +#define CMD_INV_IOMMU_PAGES_SIZE_MASK 0x01 +#define CMD_INV_IOMMU_PAGES_PDE_MASK 0x02 +#define CMD_INV_IOMMU_PAGES_GN_MASK 0x04 + +#define PPR_STATUS_MASK 0xf +#define PPR_STATUS_SHIFT 12 + +#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS 0x7fffffffffffffffULL + +/* macros and definitions for device table entries */ +#define DEV_ENTRY_VALID 0x00 +#define DEV_ENTRY_TRANSLATION 0x01 +#define DEV_ENTRY_PPR 0x34 +#define DEV_ENTRY_IR 0x3d +#define DEV_ENTRY_IW 0x3e +#define DEV_ENTRY_NO_PAGE_FAULT 0x62 +#define DEV_ENTRY_EX 0x67 +#define DEV_ENTRY_SYSMGT1 0x68 +#define DEV_ENTRY_SYSMGT2 0x69 +#define DEV_ENTRY_IRQ_TBL_EN 0x80 +#define DEV_ENTRY_INIT_PASS 0xb8 +#define DEV_ENTRY_EINT_PASS 0xb9 +#define DEV_ENTRY_NMI_PASS 0xba +#define DEV_ENTRY_LINT0_PASS 0xbe +#define DEV_ENTRY_LINT1_PASS 0xbf +#define DEV_ENTRY_MODE_MASK 0x07 +#define DEV_ENTRY_MODE_SHIFT 0x09 + +#define MAX_DEV_TABLE_ENTRIES 0xffff + +/* constants to configure the command buffer */ +#define CMD_BUFFER_SIZE 8192 +#define CMD_BUFFER_UNINITIALIZED 1 +#define CMD_BUFFER_ENTRIES 512 +#define MMIO_CMD_SIZE_SHIFT 56 +#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) + +/* constants for event buffer handling */ +#define EVT_BUFFER_SIZE 8192 /* 512 entries */ +#define EVT_LEN_MASK (0x9ULL << 56) + +/* Constants for PPR Log handling */ +#define PPR_LOG_ENTRIES 512 +#define PPR_LOG_SIZE_SHIFT 56 +#define PPR_LOG_SIZE_512 (0x9ULL << PPR_LOG_SIZE_SHIFT) +#define PPR_ENTRY_SIZE 16 +#define PPR_LOG_SIZE (PPR_ENTRY_SIZE * PPR_LOG_ENTRIES) + +#define PPR_REQ_TYPE(x) (((x) >> 60) & 0xfULL) +#define PPR_FLAGS(x) (((x) >> 48) & 0xfffULL) +#define PPR_DEVID(x) ((x) & 0xffffULL) +#define PPR_TAG(x) (((x) >> 32) & 0x3ffULL) +#define PPR_PASID1(x) (((x) >> 16) & 0xffffULL) +#define PPR_PASID2(x) (((x) >> 42) & 0xfULL) +#define PPR_PASID(x) ((PPR_PASID2(x) << 16) | PPR_PASID1(x)) + +#define PPR_REQ_FAULT 0x01 + +/* Constants for GA Log handling */ +#define GA_LOG_ENTRIES 512 +#define GA_LOG_SIZE_SHIFT 56 +#define GA_LOG_SIZE_512 (0x8ULL << GA_LOG_SIZE_SHIFT) +#define GA_ENTRY_SIZE 8 +#define GA_LOG_SIZE (GA_ENTRY_SIZE * GA_LOG_ENTRIES) + +#define GA_TAG(x) (u32)(x & 0xffffffffULL) +#define GA_DEVID(x) (u16)(((x) >> 32) & 0xffffULL) +#define GA_REQ_TYPE(x) (((x) >> 60) & 0xfULL) + +#define GA_GUEST_NR 0x1 + +#define IOMMU_IN_ADDR_BIT_SIZE 52 +#define IOMMU_OUT_ADDR_BIT_SIZE 52 + +/* + * This bitmap is used to advertise the page sizes our hardware support + * to the IOMMU core, which will then use this information to split + * physically contiguous memory regions it is mapping into page sizes + * that we support. + * + * 512GB Pages are not supported due to a hardware bug + */ +#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38)) +/* 4K, 2MB, 1G page sizes are supported */ +#define AMD_IOMMU_PGSIZES_V2 (PAGE_SIZE | (1ULL << 21) | (1ULL << 30)) + +/* Bit value definition for dte irq remapping fields*/ +#define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6) +#define DTE_IRQ_REMAP_INTCTL_MASK (0x3ULL << 60) +#define DTE_IRQ_REMAP_INTCTL (2ULL << 60) +#define DTE_IRQ_REMAP_ENABLE 1ULL + +/* + * AMD IOMMU hardware only support 512 IRTEs despite + * the architectural limitation of 2048 entries. + */ +#define DTE_INTTAB_ALIGNMENT 128 +#define DTE_INTTABLEN_VALUE 9ULL +#define DTE_INTTABLEN (DTE_INTTABLEN_VALUE << 1) +#define DTE_INTTABLEN_MASK (0xfULL << 1) +#define MAX_IRQS_PER_TABLE (1 << DTE_INTTABLEN_VALUE) + +#define PAGE_MODE_NONE 0x00 +#define PAGE_MODE_1_LEVEL 0x01 +#define PAGE_MODE_2_LEVEL 0x02 +#define PAGE_MODE_3_LEVEL 0x03 +#define PAGE_MODE_4_LEVEL 0x04 +#define PAGE_MODE_5_LEVEL 0x05 +#define PAGE_MODE_6_LEVEL 0x06 +#define PAGE_MODE_7_LEVEL 0x07 + +#define PM_LEVEL_SHIFT(x) (12 + ((x) * 9)) +#define PM_LEVEL_SIZE(x) (((x) < 6) ? \ + ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \ + (0xffffffffffffffffULL)) +#define PM_LEVEL_INDEX(x, a) (((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL) +#define PM_LEVEL_ENC(x) (((x) << 9) & 0xe00ULL) +#define PM_LEVEL_PDE(x, a) ((a) | PM_LEVEL_ENC((x)) | \ + IOMMU_PTE_PR | IOMMU_PTE_IR | IOMMU_PTE_IW) +#define PM_PTE_LEVEL(pte) (((pte) >> 9) & 0x7ULL) + +#define PM_MAP_4k 0 +#define PM_ADDR_MASK 0x000ffffffffff000ULL +#define PM_MAP_MASK(lvl) (PM_ADDR_MASK & \ + (~((1ULL << (12 + ((lvl) * 9))) - 1))) +#define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr)) + +/* + * Returns the page table level to use for a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_LEVEL(pagesize) \ + ((__ffs(pagesize) - 12) / 9) +/* + * Returns the number of ptes to use for a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_PTE_COUNT(pagesize) \ + (1ULL << ((__ffs(pagesize) - 12) % 9)) + +/* + * Aligns a given io-virtual address to a given page size + * Pagesize is expected to be a power-of-two + */ +#define PAGE_SIZE_ALIGN(address, pagesize) \ + ((address) & ~((pagesize) - 1)) +/* + * Creates an IOMMU PTE for an address and a given pagesize + * The PTE has no permission bits set + * Pagesize is expected to be a power-of-two larger than 4096 + */ +#define PAGE_SIZE_PTE(address, pagesize) \ + (((address) | ((pagesize) - 1)) & \ + (~(pagesize >> 1)) & PM_ADDR_MASK) + +/* + * Takes a PTE value with mode=0x07 and returns the page size it maps + */ +#define PTE_PAGE_SIZE(pte) \ + (1ULL << (1 + ffz(((pte) | 0xfffULL)))) + +/* + * Takes a page-table level and returns the default page-size for this level + */ +#define PTE_LEVEL_PAGE_SIZE(level) \ + (1ULL << (12 + (9 * (level)))) + +/* + * Bit value definition for I/O PTE fields + */ +#define IOMMU_PTE_PR (1ULL << 0) +#define IOMMU_PTE_U (1ULL << 59) +#define IOMMU_PTE_FC (1ULL << 60) +#define IOMMU_PTE_IR (1ULL << 61) +#define IOMMU_PTE_IW (1ULL << 62) + +/* + * Bit value definition for DTE fields + */ +#define DTE_FLAG_V (1ULL << 0) +#define DTE_FLAG_TV (1ULL << 1) +#define DTE_FLAG_IR (1ULL << 61) +#define DTE_FLAG_IW (1ULL << 62) + +#define DTE_FLAG_IOTLB (1ULL << 32) +#define DTE_FLAG_GIOV (1ULL << 54) +#define DTE_FLAG_GV (1ULL << 55) +#define DTE_FLAG_MASK (0x3ffULL << 32) +#define DTE_GLX_SHIFT (56) +#define DTE_GLX_MASK (3) +#define DEV_DOMID_MASK 0xffffULL + +#define DTE_GCR3_VAL_A(x) (((x) >> 12) & 0x00007ULL) +#define DTE_GCR3_VAL_B(x) (((x) >> 15) & 0x0ffffULL) +#define DTE_GCR3_VAL_C(x) (((x) >> 31) & 0x1fffffULL) + +#define DTE_GCR3_INDEX_A 0 +#define DTE_GCR3_INDEX_B 1 +#define DTE_GCR3_INDEX_C 1 + +#define DTE_GCR3_SHIFT_A 58 +#define DTE_GCR3_SHIFT_B 16 +#define DTE_GCR3_SHIFT_C 43 + +#define GCR3_VALID 0x01ULL + +#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) +#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_PR) +#define IOMMU_PTE_PAGE(pte) (iommu_phys_to_virt((pte) & IOMMU_PAGE_MASK)) +#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07) + +#define IOMMU_PROT_MASK 0x03 +#define IOMMU_PROT_IR 0x01 +#define IOMMU_PROT_IW 0x02 + +#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE (1 << 2) + +/* IOMMU capabilities */ +#define IOMMU_CAP_IOTLB 24 +#define IOMMU_CAP_NPCACHE 26 +#define IOMMU_CAP_EFR 27 + +/* IOMMU IVINFO */ +#define IOMMU_IVINFO_OFFSET 36 +#define IOMMU_IVINFO_EFRSUP BIT(0) +#define IOMMU_IVINFO_DMA_REMAP BIT(1) + +/* IOMMU Feature Reporting Field (for IVHD type 10h */ +#define IOMMU_FEAT_GASUP_SHIFT 6 + +/* IOMMU Extended Feature Register (EFR) */ +#define IOMMU_EFR_XTSUP_SHIFT 2 +#define IOMMU_EFR_GASUP_SHIFT 7 +#define IOMMU_EFR_MSICAPMMIOSUP_SHIFT 46 + +#define MAX_DOMAIN_ID 65536 + +/* Protection domain flags */ +#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */ +#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops + domain for an IOMMU */ +#define PD_PASSTHROUGH_MASK (1UL << 2) /* domain has no page + translation */ +#define PD_IOMMUV2_MASK (1UL << 3) /* domain has gcr3 table */ +#define PD_GIOV_MASK (1UL << 4) /* domain enable GIOV support */ + +extern bool amd_iommu_dump; +#define DUMP_printk(format, arg...) \ + do { \ + if (amd_iommu_dump) \ + pr_info("AMD-Vi: " format, ## arg); \ + } while(0); + +/* global flag if IOMMUs cache non-present entries */ +extern bool amd_iommu_np_cache; +/* Only true if all IOMMUs support device IOTLBs */ +extern bool amd_iommu_iotlb_sup; + +struct irq_remap_table { + raw_spinlock_t lock; + unsigned min_index; + u32 *table; +}; + +/* Interrupt remapping feature used? */ +extern bool amd_iommu_irq_remap; + +extern const struct iommu_ops amd_iommu_ops; + +/* IVRS indicates that pre-boot remapping was enabled */ +extern bool amdr_ivrs_remap_support; + +/* kmem_cache to get tables with 128 byte alignement */ +extern struct kmem_cache *amd_iommu_irq_cache; + +#define PCI_SBDF_TO_SEGID(sbdf) (((sbdf) >> 16) & 0xffff) +#define PCI_SBDF_TO_DEVID(sbdf) ((sbdf) & 0xffff) +#define PCI_SEG_DEVID_TO_SBDF(seg, devid) ((((u32)(seg) & 0xffff) << 16) | \ + ((devid) & 0xffff)) + +/* Make iterating over all pci segment easier */ +#define for_each_pci_segment(pci_seg) \ + list_for_each_entry((pci_seg), &amd_iommu_pci_seg_list, list) +#define for_each_pci_segment_safe(pci_seg, next) \ + list_for_each_entry_safe((pci_seg), (next), &amd_iommu_pci_seg_list, list) +/* + * Make iterating over all IOMMUs easier + */ +#define for_each_iommu(iommu) \ + list_for_each_entry((iommu), &amd_iommu_list, list) +#define for_each_iommu_safe(iommu, next) \ + list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list) + +#define APERTURE_RANGE_SHIFT 27 /* 128 MB */ +#define APERTURE_RANGE_SIZE (1ULL << APERTURE_RANGE_SHIFT) +#define APERTURE_RANGE_PAGES (APERTURE_RANGE_SIZE >> PAGE_SHIFT) +#define APERTURE_MAX_RANGES 32 /* allows 4GB of DMA address space */ +#define APERTURE_RANGE_INDEX(a) ((a) >> APERTURE_RANGE_SHIFT) +#define APERTURE_PAGE_INDEX(a) (((a) >> 21) & 0x3fULL) + +/* + * This struct is used to pass information about + * incoming PPR faults around. + */ +struct amd_iommu_fault { + u64 address; /* IO virtual address of the fault*/ + u32 pasid; /* Address space identifier */ + u32 sbdf; /* Originating PCI device id */ + u16 tag; /* PPR tag */ + u16 flags; /* Fault flags */ + +}; + + +struct amd_iommu; +struct iommu_domain; +struct irq_domain; +struct amd_irte_ops; + +#define AMD_IOMMU_FLAG_TRANS_PRE_ENABLED (1 << 0) + +#define io_pgtable_to_data(x) \ + container_of((x), struct amd_io_pgtable, iop) + +#define io_pgtable_ops_to_data(x) \ + io_pgtable_to_data(io_pgtable_ops_to_pgtable(x)) + +#define io_pgtable_ops_to_domain(x) \ + container_of(io_pgtable_ops_to_data(x), \ + struct protection_domain, iop) + +#define io_pgtable_cfg_to_data(x) \ + container_of((x), struct amd_io_pgtable, pgtbl_cfg) + +struct amd_io_pgtable { + struct io_pgtable_cfg pgtbl_cfg; + struct io_pgtable iop; + int mode; + u64 *root; + atomic64_t pt_root; /* pgtable root and pgtable mode */ + u64 *pgd; /* v2 pgtable pgd pointer */ +}; + +/* + * This structure contains generic data for IOMMU protection domains + * independent of their use. + */ +struct protection_domain { + struct list_head dev_list; /* List of all devices in this domain */ + struct iommu_domain domain; /* generic domain handle used by + iommu core code */ + struct amd_io_pgtable iop; + spinlock_t lock; /* mostly used to lock the page table*/ + u16 id; /* the domain id written to the device table */ + int glx; /* Number of levels for GCR3 table */ + u64 *gcr3_tbl; /* Guest CR3 table */ + unsigned long flags; /* flags to find out type of domain */ + unsigned dev_cnt; /* devices assigned to this domain */ + unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ +}; + +/* + * This structure contains information about one PCI segment in the system. + */ +struct amd_iommu_pci_seg { + /* List with all PCI segments in the system */ + struct list_head list; + + /* List of all available dev_data structures */ + struct llist_head dev_data_list; + + /* PCI segment number */ + u16 id; + + /* Largest PCI device id we expect translation requests for */ + u16 last_bdf; + + /* Size of the device table */ + u32 dev_table_size; + + /* Size of the alias table */ + u32 alias_table_size; + + /* Size of the rlookup table */ + u32 rlookup_table_size; + + /* + * device table virtual address + * + * Pointer to the per PCI segment device table. + * It is indexed by the PCI device id or the HT unit id and contains + * information about the domain the device belongs to as well as the + * page table root pointer. + */ + struct dev_table_entry *dev_table; + + /* + * The rlookup iommu table is used to find the IOMMU which is + * responsible for a specific device. It is indexed by the PCI + * device id. + */ + struct amd_iommu **rlookup_table; + + /* + * This table is used to find the irq remapping table for a given + * device id quickly. + */ + struct irq_remap_table **irq_lookup_table; + + /* + * Pointer to a device table which the content of old device table + * will be copied to. It's only be used in kdump kernel. + */ + struct dev_table_entry *old_dev_tbl_cpy; + + /* + * The alias table is a driver specific data structure which contains the + * mappings of the PCI device ids to the actual requestor ids on the IOMMU. + * More than one device can share the same requestor id. + */ + u16 *alias_table; + + /* + * A list of required unity mappings we find in ACPI. It is not locked + * because as runtime it is only read. It is created at ACPI table + * parsing time. + */ + struct list_head unity_map; +}; + +/* + * Structure where we save information about one hardware AMD IOMMU in the + * system. + */ +struct amd_iommu { + struct list_head list; + + /* Index within the IOMMU array */ + int index; + + /* locks the accesses to the hardware */ + raw_spinlock_t lock; + + /* Pointer to PCI device of this IOMMU */ + struct pci_dev *dev; + + /* Cache pdev to root device for resume quirks */ + struct pci_dev *root_pdev; + + /* physical address of MMIO space */ + u64 mmio_phys; + + /* physical end address of MMIO space */ + u64 mmio_phys_end; + + /* virtual address of MMIO space */ + u8 __iomem *mmio_base; + + /* capabilities of that IOMMU read from ACPI */ + u32 cap; + + /* flags read from acpi table */ + u8 acpi_flags; + + /* Extended features */ + u64 features; + + /* Extended features 2 */ + u64 features2; + + /* IOMMUv2 */ + bool is_iommu_v2; + + /* PCI device id of the IOMMU device */ + u16 devid; + + /* + * Capability pointer. There could be more than one IOMMU per PCI + * device function if there are more than one AMD IOMMU capability + * pointers. + */ + u16 cap_ptr; + + /* pci domain of this IOMMU */ + struct amd_iommu_pci_seg *pci_seg; + + /* start of exclusion range of that IOMMU */ + u64 exclusion_start; + /* length of exclusion range of that IOMMU */ + u64 exclusion_length; + + /* command buffer virtual address */ + u8 *cmd_buf; + u32 cmd_buf_head; + u32 cmd_buf_tail; + + /* event buffer virtual address */ + u8 *evt_buf; + + /* Base of the PPR log, if present */ + u8 *ppr_log; + + /* Base of the GA log, if present */ + u8 *ga_log; + + /* Tail of the GA log, if present */ + u8 *ga_log_tail; + + /* true if interrupts for this IOMMU are already enabled */ + bool int_enabled; + + /* if one, we need to send a completion wait command */ + bool need_sync; + + /* true if disable irte caching */ + bool irtcachedis_enabled; + + /* Handle for IOMMU core code */ + struct iommu_device iommu; + + /* + * We can't rely on the BIOS to restore all values on reinit, so we + * need to stash them + */ + + /* The iommu BAR */ + u32 stored_addr_lo; + u32 stored_addr_hi; + + /* + * Each iommu has 6 l1s, each of which is documented as having 0x12 + * registers + */ + u32 stored_l1[6][0x12]; + + /* The l2 indirect registers */ + u32 stored_l2[0x83]; + + /* The maximum PC banks and counters/bank (PCSup=1) */ + u8 max_banks; + u8 max_counters; +#ifdef CONFIG_IRQ_REMAP + struct irq_domain *ir_domain; + struct irq_domain *msi_domain; + + struct amd_irte_ops *irte_ops; +#endif + + u32 flags; + volatile u64 *cmd_sem; + u64 cmd_sem_val; + +#ifdef CONFIG_AMD_IOMMU_DEBUGFS + /* DebugFS Info */ + struct dentry *debugfs; +#endif +}; + +static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) +{ + struct iommu_device *iommu = dev_to_iommu_device(dev); + + return container_of(iommu, struct amd_iommu, iommu); +} + +#define ACPIHID_UID_LEN 256 +#define ACPIHID_HID_LEN 9 + +struct acpihid_map_entry { + struct list_head list; + u8 uid[ACPIHID_UID_LEN]; + u8 hid[ACPIHID_HID_LEN]; + u32 devid; + u32 root_devid; + bool cmd_line; + struct iommu_group *group; +}; + +struct devid_map { + struct list_head list; + u8 id; + u32 devid; + bool cmd_line; +}; + +/* + * This struct contains device specific data for the IOMMU + */ +struct iommu_dev_data { + /*Protect against attach/detach races */ + spinlock_t lock; + + struct list_head list; /* For domain->dev_list */ + struct llist_node dev_data_list; /* For global dev_data_list */ + struct protection_domain *domain; /* Domain the device is bound to */ + struct device *dev; + u16 devid; /* PCI Device ID */ + bool iommu_v2; /* Device can make use of IOMMUv2 */ + struct { + bool enabled; + int qdep; + } ats; /* ATS state */ + bool pri_tlp; /* PASID TLB required for + PPR completions */ + bool use_vapic; /* Enable device to use vapic mode */ + bool defer_attach; + + struct ratelimit_state rs; /* Ratelimit IOPF messages */ +}; + +/* Map HPET and IOAPIC ids to the devid used by the IOMMU */ +extern struct list_head ioapic_map; +extern struct list_head hpet_map; +extern struct list_head acpihid_map; + +/* + * List with all PCI segments in the system. This list is not locked because + * it is only written at driver initialization time + */ +extern struct list_head amd_iommu_pci_seg_list; + +/* + * List with all IOMMUs in the system. This list is not locked because it is + * only written and read at driver initialization or suspend time + */ +extern struct list_head amd_iommu_list; + +/* + * Array with pointers to each IOMMU struct + * The indices are referenced in the protection domains + */ +extern struct amd_iommu *amd_iommus[MAX_IOMMUS]; + +/* + * Structure defining one entry in the device table + */ +struct dev_table_entry { + u64 data[4]; +}; + +/* + * One entry for unity mappings parsed out of the ACPI table. + */ +struct unity_map_entry { + struct list_head list; + + /* starting device id this entry is used for (including) */ + u16 devid_start; + /* end device id this entry is used for (including) */ + u16 devid_end; + + /* start address to unity map (including) */ + u64 address_start; + /* end address to unity map (including) */ + u64 address_end; + + /* required protection */ + int prot; +}; + +/* + * Data structures for device handling + */ + +/* size of the dma_ops aperture as power of 2 */ +extern unsigned amd_iommu_aperture_order; + +/* allocation bitmap for domain ids */ +extern unsigned long *amd_iommu_pd_alloc_bitmap; + +/* Smallest max PASID supported by any IOMMU in the system */ +extern u32 amd_iommu_max_pasid; + +extern bool amd_iommu_v2_present; + +extern bool amd_iommu_force_isolation; + +/* Max levels of glxval supported */ +extern int amd_iommu_max_glx_val; + +/* + * This function flushes all internal caches of + * the IOMMU used by this driver. + */ +extern void iommu_flush_all_caches(struct amd_iommu *iommu); + +static inline int get_ioapic_devid(int id) +{ + struct devid_map *entry; + + list_for_each_entry(entry, &ioapic_map, list) { + if (entry->id == id) + return entry->devid; + } + + return -EINVAL; +} + +static inline int get_hpet_devid(int id) +{ + struct devid_map *entry; + + list_for_each_entry(entry, &hpet_map, list) { + if (entry->id == id) + return entry->devid; + } + + return -EINVAL; +} + +enum amd_iommu_intr_mode_type { + AMD_IOMMU_GUEST_IR_LEGACY, + + /* This mode is not visible to users. It is used when + * we cannot fully enable vAPIC and fallback to only support + * legacy interrupt remapping via 128-bit IRTE. + */ + AMD_IOMMU_GUEST_IR_LEGACY_GA, + AMD_IOMMU_GUEST_IR_VAPIC, +}; + +#define AMD_IOMMU_GUEST_IR_GA(x) (x == AMD_IOMMU_GUEST_IR_VAPIC || \ + x == AMD_IOMMU_GUEST_IR_LEGACY_GA) + +#define AMD_IOMMU_GUEST_IR_VAPIC(x) (x == AMD_IOMMU_GUEST_IR_VAPIC) + +union irte { + u32 val; + struct { + u32 valid : 1, + no_fault : 1, + int_type : 3, + rq_eoi : 1, + dm : 1, + rsvd_1 : 1, + destination : 8, + vector : 8, + rsvd_2 : 8; + } fields; +}; + +#define APICID_TO_IRTE_DEST_LO(x) (x & 0xffffff) +#define APICID_TO_IRTE_DEST_HI(x) ((x >> 24) & 0xff) + +union irte_ga_lo { + u64 val; + + /* For int remapping */ + struct { + u64 valid : 1, + no_fault : 1, + /* ------ */ + int_type : 3, + rq_eoi : 1, + dm : 1, + /* ------ */ + guest_mode : 1, + destination : 24, + ga_tag : 32; + } fields_remap; + + /* For guest vAPIC */ + struct { + u64 valid : 1, + no_fault : 1, + /* ------ */ + ga_log_intr : 1, + rsvd1 : 3, + is_run : 1, + /* ------ */ + guest_mode : 1, + destination : 24, + ga_tag : 32; + } fields_vapic; +}; + +union irte_ga_hi { + u64 val; + struct { + u64 vector : 8, + rsvd_1 : 4, + ga_root_ptr : 40, + rsvd_2 : 4, + destination : 8; + } fields; +}; + +struct irte_ga { + union irte_ga_lo lo; + union irte_ga_hi hi; +}; + +struct irq_2_irte { + u16 devid; /* Device ID for IRTE table */ + u16 index; /* Index into IRTE table*/ +}; + +struct amd_ir_data { + u32 cached_ga_tag; + struct amd_iommu *iommu; + struct irq_2_irte irq_2_irte; + struct msi_msg msi_entry; + void *entry; /* Pointer to union irte or struct irte_ga */ + void *ref; /* Pointer to the actual irte */ + + /** + * Store information for activate/de-activate + * Guest virtual APIC mode during runtime. + */ + struct irq_cfg *cfg; + int ga_vector; + u64 ga_root_ptr; + u32 ga_tag; +}; + +struct amd_irte_ops { + void (*prepare)(void *, u32, bool, u8, u32, int); + void (*activate)(struct amd_iommu *iommu, void *, u16, u16); + void (*deactivate)(struct amd_iommu *iommu, void *, u16, u16); + void (*set_affinity)(struct amd_iommu *iommu, void *, u16, u16, u8, u32); + void *(*get)(struct irq_remap_table *, int); + void (*set_allocated)(struct irq_remap_table *, int); + bool (*is_allocated)(struct irq_remap_table *, int); + void (*clear_allocated)(struct irq_remap_table *, int); +}; + +#ifdef CONFIG_IRQ_REMAP +extern struct amd_irte_ops irte_32_ops; +extern struct amd_irte_ops irte_128_ops; +#endif + +#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */ diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c new file mode 100644 index 000000000..545372fcc --- /dev/null +++ b/drivers/iommu/amd/debugfs.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD IOMMU driver + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * + * Author: Gary R Hook + */ + +#include +#include + +#include "amd_iommu.h" + +static struct dentry *amd_iommu_debugfs; +static DEFINE_MUTEX(amd_iommu_debugfs_lock); + +#define MAX_NAME_LEN 20 + +void amd_iommu_debugfs_setup(struct amd_iommu *iommu) +{ + char name[MAX_NAME_LEN + 1]; + + mutex_lock(&amd_iommu_debugfs_lock); + if (!amd_iommu_debugfs) + amd_iommu_debugfs = debugfs_create_dir("amd", + iommu_debugfs_dir); + mutex_unlock(&amd_iommu_debugfs_lock); + + snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index); + iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs); +} diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c new file mode 100644 index 000000000..f6e64c985 --- /dev/null +++ b/drivers/iommu/amd/init.c @@ -0,0 +1,3764 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + * Leo Duran + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "amd_iommu.h" +#include "../irq_remapping.h" + +/* + * definitions for the ACPI scanning code + */ +#define IVRS_HEADER_LENGTH 48 + +#define ACPI_IVHD_TYPE_MAX_SUPPORTED 0x40 +#define ACPI_IVMD_TYPE_ALL 0x20 +#define ACPI_IVMD_TYPE 0x21 +#define ACPI_IVMD_TYPE_RANGE 0x22 + +#define IVHD_DEV_ALL 0x01 +#define IVHD_DEV_SELECT 0x02 +#define IVHD_DEV_SELECT_RANGE_START 0x03 +#define IVHD_DEV_RANGE_END 0x04 +#define IVHD_DEV_ALIAS 0x42 +#define IVHD_DEV_ALIAS_RANGE 0x43 +#define IVHD_DEV_EXT_SELECT 0x46 +#define IVHD_DEV_EXT_SELECT_RANGE 0x47 +#define IVHD_DEV_SPECIAL 0x48 +#define IVHD_DEV_ACPI_HID 0xf0 + +#define UID_NOT_PRESENT 0 +#define UID_IS_INTEGER 1 +#define UID_IS_CHARACTER 2 + +#define IVHD_SPECIAL_IOAPIC 1 +#define IVHD_SPECIAL_HPET 2 + +#define IVHD_FLAG_HT_TUN_EN_MASK 0x01 +#define IVHD_FLAG_PASSPW_EN_MASK 0x02 +#define IVHD_FLAG_RESPASSPW_EN_MASK 0x04 +#define IVHD_FLAG_ISOC_EN_MASK 0x08 + +#define IVMD_FLAG_EXCL_RANGE 0x08 +#define IVMD_FLAG_IW 0x04 +#define IVMD_FLAG_IR 0x02 +#define IVMD_FLAG_UNITY_MAP 0x01 + +#define ACPI_DEVFLAG_INITPASS 0x01 +#define ACPI_DEVFLAG_EXTINT 0x02 +#define ACPI_DEVFLAG_NMI 0x04 +#define ACPI_DEVFLAG_SYSMGT1 0x10 +#define ACPI_DEVFLAG_SYSMGT2 0x20 +#define ACPI_DEVFLAG_LINT0 0x40 +#define ACPI_DEVFLAG_LINT1 0x80 +#define ACPI_DEVFLAG_ATSDIS 0x10000000 + +#define LOOP_TIMEOUT 2000000 + +#define IVRS_GET_SBDF_ID(seg, bus, dev, fd) (((seg & 0xffff) << 16) | ((bus & 0xff) << 8) \ + | ((dev & 0x1f) << 3) | (fn & 0x7)) + +/* + * ACPI table definitions + * + * These data structures are laid over the table to parse the important values + * out of it. + */ + +/* + * structure describing one IOMMU in the ACPI table. Typically followed by one + * or more ivhd_entrys. + */ +struct ivhd_header { + u8 type; + u8 flags; + u16 length; + u16 devid; + u16 cap_ptr; + u64 mmio_phys; + u16 pci_seg; + u16 info; + u32 efr_attr; + + /* Following only valid on IVHD type 11h and 40h */ + u64 efr_reg; /* Exact copy of MMIO_EXT_FEATURES */ + u64 efr_reg2; +} __attribute__((packed)); + +/* + * A device entry describing which devices a specific IOMMU translates and + * which requestor ids they use. + */ +struct ivhd_entry { + u8 type; + u16 devid; + u8 flags; + struct_group(ext_hid, + u32 ext; + u32 hidh; + ); + u64 cid; + u8 uidf; + u8 uidl; + u8 uid; +} __attribute__((packed)); + +/* + * An AMD IOMMU memory definition structure. It defines things like exclusion + * ranges for devices and regions that should be unity mapped. + */ +struct ivmd_header { + u8 type; + u8 flags; + u16 length; + u16 devid; + u16 aux; + u16 pci_seg; + u8 resv[6]; + u64 range_start; + u64 range_length; +} __attribute__((packed)); + +bool amd_iommu_dump; +bool amd_iommu_irq_remap __read_mostly; + +enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1; + +int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC; +static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; + +static bool amd_iommu_detected; +static bool amd_iommu_disabled __initdata; +static bool amd_iommu_force_enable __initdata; +static bool amd_iommu_irtcachedis; +static int amd_iommu_target_ivhd_type; + +/* Global EFR and EFR2 registers */ +u64 amd_iommu_efr; +u64 amd_iommu_efr2; + +/* SNP is enabled on the system? */ +bool amd_iommu_snp_en; +EXPORT_SYMBOL(amd_iommu_snp_en); + +LIST_HEAD(amd_iommu_pci_seg_list); /* list of all PCI segments */ +LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the + system */ + +/* Array to assign indices to IOMMUs*/ +struct amd_iommu *amd_iommus[MAX_IOMMUS]; + +/* Number of IOMMUs present in the system */ +static int amd_iommus_present; + +/* IOMMUs have a non-present cache? */ +bool amd_iommu_np_cache __read_mostly; +bool amd_iommu_iotlb_sup __read_mostly = true; + +u32 amd_iommu_max_pasid __read_mostly = ~0; + +bool amd_iommu_v2_present __read_mostly; +static bool amd_iommu_pc_present __read_mostly; +bool amdr_ivrs_remap_support __read_mostly; + +bool amd_iommu_force_isolation __read_mostly; + +/* + * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap + * to know which ones are already in use. + */ +unsigned long *amd_iommu_pd_alloc_bitmap; + +enum iommu_init_state { + IOMMU_START_STATE, + IOMMU_IVRS_DETECTED, + IOMMU_ACPI_FINISHED, + IOMMU_ENABLED, + IOMMU_PCI_INIT, + IOMMU_INTERRUPTS_EN, + IOMMU_INITIALIZED, + IOMMU_NOT_FOUND, + IOMMU_INIT_ERROR, + IOMMU_CMDLINE_DISABLED, +}; + +/* Early ioapic and hpet maps from kernel command line */ +#define EARLY_MAP_SIZE 4 +static struct devid_map __initdata early_ioapic_map[EARLY_MAP_SIZE]; +static struct devid_map __initdata early_hpet_map[EARLY_MAP_SIZE]; +static struct acpihid_map_entry __initdata early_acpihid_map[EARLY_MAP_SIZE]; + +static int __initdata early_ioapic_map_size; +static int __initdata early_hpet_map_size; +static int __initdata early_acpihid_map_size; + +static bool __initdata cmdline_maps; + +static enum iommu_init_state init_state = IOMMU_START_STATE; + +static int amd_iommu_enable_interrupts(void); +static int __init iommu_go_to_state(enum iommu_init_state state); +static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg); + +static bool amd_iommu_pre_enabled = true; + +static u32 amd_iommu_ivinfo __initdata; + +bool translation_pre_enabled(struct amd_iommu *iommu) +{ + return (iommu->flags & AMD_IOMMU_FLAG_TRANS_PRE_ENABLED); +} + +static void clear_translation_pre_enabled(struct amd_iommu *iommu) +{ + iommu->flags &= ~AMD_IOMMU_FLAG_TRANS_PRE_ENABLED; +} + +static void init_translation_status(struct amd_iommu *iommu) +{ + u64 ctrl; + + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + if (ctrl & (1<flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED; +} + +static inline unsigned long tbl_size(int entry_size, int last_bdf) +{ + unsigned shift = PAGE_SHIFT + + get_order((last_bdf + 1) * entry_size); + + return 1UL << shift; +} + +int amd_iommu_get_num_iommus(void) +{ + return amd_iommus_present; +} + +/* + * Iterate through all the IOMMUs to get common EFR + * masks among all IOMMUs and warn if found inconsistency. + */ +static void get_global_efr(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + u64 tmp = iommu->features; + u64 tmp2 = iommu->features2; + + if (list_is_first(&iommu->list, &amd_iommu_list)) { + amd_iommu_efr = tmp; + amd_iommu_efr2 = tmp2; + continue; + } + + if (amd_iommu_efr == tmp && + amd_iommu_efr2 == tmp2) + continue; + + pr_err(FW_BUG + "Found inconsistent EFR/EFR2 %#llx,%#llx (global %#llx,%#llx) on iommu%d (%04x:%02x:%02x.%01x).\n", + tmp, tmp2, amd_iommu_efr, amd_iommu_efr2, + iommu->index, iommu->pci_seg->id, + PCI_BUS_NUM(iommu->devid), PCI_SLOT(iommu->devid), + PCI_FUNC(iommu->devid)); + + amd_iommu_efr &= tmp; + amd_iommu_efr2 &= tmp2; + } + + pr_info("Using global IVHD EFR:%#llx, EFR2:%#llx\n", amd_iommu_efr, amd_iommu_efr2); +} + +static bool check_feature_on_all_iommus(u64 mask) +{ + return !!(amd_iommu_efr & mask); +} + +/* + * For IVHD type 0x11/0x40, EFR is also available via IVHD. + * Default to IVHD EFR since it is available sooner + * (i.e. before PCI init). + */ +static void __init early_iommu_features_init(struct amd_iommu *iommu, + struct ivhd_header *h) +{ + if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP) { + iommu->features = h->efr_reg; + iommu->features2 = h->efr_reg2; + } + if (amd_iommu_ivinfo & IOMMU_IVINFO_DMA_REMAP) + amdr_ivrs_remap_support = true; +} + +/* Access to l1 and l2 indexed register spaces */ + +static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address) +{ + u32 val; + + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); + pci_read_config_dword(iommu->dev, 0xfc, &val); + return val; +} + +static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val) +{ + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31)); + pci_write_config_dword(iommu->dev, 0xfc, val); + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); +} + +static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address) +{ + u32 val; + + pci_write_config_dword(iommu->dev, 0xf0, address); + pci_read_config_dword(iommu->dev, 0xf4, &val); + return val; +} + +static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val) +{ + pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8)); + pci_write_config_dword(iommu->dev, 0xf4, val); +} + +/**************************************************************************** + * + * AMD IOMMU MMIO register space handling functions + * + * These functions are used to program the IOMMU device registers in + * MMIO space required for that driver. + * + ****************************************************************************/ + +/* + * This function set the exclusion range in the IOMMU. DMA accesses to the + * exclusion range are passed through untranslated + */ +static void iommu_set_exclusion_range(struct amd_iommu *iommu) +{ + u64 start = iommu->exclusion_start & PAGE_MASK; + u64 limit = (start + iommu->exclusion_length - 1) & PAGE_MASK; + u64 entry; + + if (!iommu->exclusion_start) + return; + + entry = start | MMIO_EXCL_ENABLE_MASK; + memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET, + &entry, sizeof(entry)); + + entry = limit; + memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET, + &entry, sizeof(entry)); +} + +static void iommu_set_cwwb_range(struct amd_iommu *iommu) +{ + u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem); + u64 entry = start & PM_ADDR_MASK; + + if (!check_feature_on_all_iommus(FEATURE_SNP)) + return; + + /* Note: + * Re-purpose Exclusion base/limit registers for Completion wait + * write-back base/limit. + */ + memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET, + &entry, sizeof(entry)); + + /* Note: + * Default to 4 Kbytes, which can be specified by setting base + * address equal to the limit address. + */ + memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET, + &entry, sizeof(entry)); +} + +/* Programs the physical address of the device table into the IOMMU hardware */ +static void iommu_set_device_table(struct amd_iommu *iommu) +{ + u64 entry; + u32 dev_table_size = iommu->pci_seg->dev_table_size; + void *dev_table = (void *)get_dev_table(iommu); + + BUG_ON(iommu->mmio_base == NULL); + + entry = iommu_virt_to_phys(dev_table); + entry |= (dev_table_size >> 12) - 1; + memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET, + &entry, sizeof(entry)); +} + +/* Generic functions to enable/disable certain features of the IOMMU. */ +static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit) +{ + u64 ctrl; + + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl |= (1ULL << bit); + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); +} + +static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit) +{ + u64 ctrl; + + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= ~(1ULL << bit); + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); +} + +static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout) +{ + u64 ctrl; + + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= ~CTRL_INV_TO_MASK; + ctrl |= (timeout << CONTROL_INV_TIMEOUT) & CTRL_INV_TO_MASK; + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); +} + +/* Function to enable the hardware */ +static void iommu_enable(struct amd_iommu *iommu) +{ + iommu_feature_enable(iommu, CONTROL_IOMMU_EN); +} + +static void iommu_disable(struct amd_iommu *iommu) +{ + if (!iommu->mmio_base) + return; + + /* Disable command buffer */ + iommu_feature_disable(iommu, CONTROL_CMDBUF_EN); + + /* Disable event logging and event interrupts */ + iommu_feature_disable(iommu, CONTROL_EVT_INT_EN); + iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); + + /* Disable IOMMU GA_LOG */ + iommu_feature_disable(iommu, CONTROL_GALOG_EN); + iommu_feature_disable(iommu, CONTROL_GAINT_EN); + + /* Disable IOMMU hardware itself */ + iommu_feature_disable(iommu, CONTROL_IOMMU_EN); + + /* Clear IRTE cache disabling bit */ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); +} + +/* + * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in + * the system has one. + */ +static u8 __iomem * __init iommu_map_mmio_space(u64 address, u64 end) +{ + if (!request_mem_region(address, end, "amd_iommu")) { + pr_err("Can not reserve memory region %llx-%llx for mmio\n", + address, end); + pr_err("This is a BIOS bug. Please contact your hardware vendor\n"); + return NULL; + } + + return (u8 __iomem *)ioremap(address, end); +} + +static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu) +{ + if (iommu->mmio_base) + iounmap(iommu->mmio_base); + release_mem_region(iommu->mmio_phys, iommu->mmio_phys_end); +} + +static inline u32 get_ivhd_header_size(struct ivhd_header *h) +{ + u32 size = 0; + + switch (h->type) { + case 0x10: + size = 24; + break; + case 0x11: + case 0x40: + size = 40; + break; + } + return size; +} + +/**************************************************************************** + * + * The functions below belong to the first pass of AMD IOMMU ACPI table + * parsing. In this pass we try to find out the highest device id this + * code has to handle. Upon this information the size of the shared data + * structures is determined later. + * + ****************************************************************************/ + +/* + * This function calculates the length of a given IVHD entry + */ +static inline int ivhd_entry_length(u8 *ivhd) +{ + u32 type = ((struct ivhd_entry *)ivhd)->type; + + if (type < 0x80) { + return 0x04 << (*ivhd >> 6); + } else if (type == IVHD_DEV_ACPI_HID) { + /* For ACPI_HID, offset 21 is uid len */ + return *((u8 *)ivhd + 21) + 22; + } + return 0; +} + +/* + * After reading the highest device id from the IOMMU PCI capability header + * this function looks if there is a higher device id defined in the ACPI table + */ +static int __init find_last_devid_from_ivhd(struct ivhd_header *h) +{ + u8 *p = (void *)h, *end = (void *)h; + struct ivhd_entry *dev; + int last_devid = -EINVAL; + + u32 ivhd_size = get_ivhd_header_size(h); + + if (!ivhd_size) { + pr_err("Unsupported IVHD type %#x\n", h->type); + return -EINVAL; + } + + p += ivhd_size; + end += h->length; + + while (p < end) { + dev = (struct ivhd_entry *)p; + switch (dev->type) { + case IVHD_DEV_ALL: + /* Use maximum BDF value for DEV_ALL */ + return 0xffff; + case IVHD_DEV_SELECT: + case IVHD_DEV_RANGE_END: + case IVHD_DEV_ALIAS: + case IVHD_DEV_EXT_SELECT: + /* all the above subfield types refer to device ids */ + if (dev->devid > last_devid) + last_devid = dev->devid; + break; + default: + break; + } + p += ivhd_entry_length(p); + } + + WARN_ON(p != end); + + return last_devid; +} + +static int __init check_ivrs_checksum(struct acpi_table_header *table) +{ + int i; + u8 checksum = 0, *p = (u8 *)table; + + for (i = 0; i < table->length; ++i) + checksum += p[i]; + if (checksum != 0) { + /* ACPI table corrupt */ + pr_err(FW_BUG "IVRS invalid checksum\n"); + return -ENODEV; + } + + return 0; +} + +/* + * Iterate over all IVHD entries in the ACPI table and find the highest device + * id which we need to handle. This is the first of three functions which parse + * the ACPI table. So we check the checksum here. + */ +static int __init find_last_devid_acpi(struct acpi_table_header *table, u16 pci_seg) +{ + u8 *p = (u8 *)table, *end = (u8 *)table; + struct ivhd_header *h; + int last_devid, last_bdf = 0; + + p += IVRS_HEADER_LENGTH; + + end += table->length; + while (p < end) { + h = (struct ivhd_header *)p; + if (h->pci_seg == pci_seg && + h->type == amd_iommu_target_ivhd_type) { + last_devid = find_last_devid_from_ivhd(h); + + if (last_devid < 0) + return -EINVAL; + if (last_devid > last_bdf) + last_bdf = last_devid; + } + p += h->length; + } + WARN_ON(p != end); + + return last_bdf; +} + +/**************************************************************************** + * + * The following functions belong to the code path which parses the ACPI table + * the second time. In this ACPI parsing iteration we allocate IOMMU specific + * data structures, initialize the per PCI segment device/alias/rlookup table + * and also basically initialize the hardware. + * + ****************************************************************************/ + +/* Allocate per PCI segment device table */ +static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg) +{ + pci_seg->dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, + get_order(pci_seg->dev_table_size)); + if (!pci_seg->dev_table) + return -ENOMEM; + + return 0; +} + +static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg) +{ + free_pages((unsigned long)pci_seg->dev_table, + get_order(pci_seg->dev_table_size)); + pci_seg->dev_table = NULL; +} + +/* Allocate per PCI segment IOMMU rlookup table. */ +static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg) +{ + pci_seg->rlookup_table = (void *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, + get_order(pci_seg->rlookup_table_size)); + if (pci_seg->rlookup_table == NULL) + return -ENOMEM; + + return 0; +} + +static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg) +{ + free_pages((unsigned long)pci_seg->rlookup_table, + get_order(pci_seg->rlookup_table_size)); + pci_seg->rlookup_table = NULL; +} + +static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg) +{ + pci_seg->irq_lookup_table = (void *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, + get_order(pci_seg->rlookup_table_size)); + kmemleak_alloc(pci_seg->irq_lookup_table, + pci_seg->rlookup_table_size, 1, GFP_KERNEL); + if (pci_seg->irq_lookup_table == NULL) + return -ENOMEM; + + return 0; +} + +static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg) +{ + kmemleak_free(pci_seg->irq_lookup_table); + free_pages((unsigned long)pci_seg->irq_lookup_table, + get_order(pci_seg->rlookup_table_size)); + pci_seg->irq_lookup_table = NULL; +} + +static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg) +{ + int i; + + pci_seg->alias_table = (void *)__get_free_pages(GFP_KERNEL, + get_order(pci_seg->alias_table_size)); + if (!pci_seg->alias_table) + return -ENOMEM; + + /* + * let all alias entries point to itself + */ + for (i = 0; i <= pci_seg->last_bdf; ++i) + pci_seg->alias_table[i] = i; + + return 0; +} + +static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg) +{ + free_pages((unsigned long)pci_seg->alias_table, + get_order(pci_seg->alias_table_size)); + pci_seg->alias_table = NULL; +} + +/* + * Allocates the command buffer. This buffer is per AMD IOMMU. We can + * write commands to that buffer later and the IOMMU will execute them + * asynchronously + */ +static int __init alloc_command_buffer(struct amd_iommu *iommu) +{ + iommu->cmd_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(CMD_BUFFER_SIZE)); + + return iommu->cmd_buf ? 0 : -ENOMEM; +} + +/* + * This function restarts event logging in case the IOMMU experienced + * an event log buffer overflow. + */ +void amd_iommu_restart_event_logging(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); +} + +/* + * This function restarts event logging in case the IOMMU experienced + * an GA log overflow. + */ +void amd_iommu_restart_ga_log(struct amd_iommu *iommu) +{ + u32 status; + + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (status & MMIO_STATUS_GALOG_RUN_MASK) + return; + + pr_info_ratelimited("IOMMU GA Log restarting\n"); + + iommu_feature_disable(iommu, CONTROL_GALOG_EN); + iommu_feature_disable(iommu, CONTROL_GAINT_EN); + + writel(MMIO_STATUS_GALOG_OVERFLOW_MASK, + iommu->mmio_base + MMIO_STATUS_OFFSET); + + iommu_feature_enable(iommu, CONTROL_GAINT_EN); + iommu_feature_enable(iommu, CONTROL_GALOG_EN); +} + +/* + * This function resets the command buffer if the IOMMU stopped fetching + * commands from it. + */ +static void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_CMDBUF_EN); + + writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); + iommu->cmd_buf_head = 0; + iommu->cmd_buf_tail = 0; + + iommu_feature_enable(iommu, CONTROL_CMDBUF_EN); +} + +/* + * This function writes the command buffer address to the hardware and + * enables it. + */ +static void iommu_enable_command_buffer(struct amd_iommu *iommu) +{ + u64 entry; + + BUG_ON(iommu->cmd_buf == NULL); + + entry = iommu_virt_to_phys(iommu->cmd_buf); + entry |= MMIO_CMD_SIZE_512; + + memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET, + &entry, sizeof(entry)); + + amd_iommu_reset_cmd_buffer(iommu); +} + +/* + * This function disables the command buffer + */ +static void iommu_disable_command_buffer(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_CMDBUF_EN); +} + +static void __init free_command_buffer(struct amd_iommu *iommu) +{ + free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE)); +} + +static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, + gfp_t gfp, size_t size) +{ + int order = get_order(size); + void *buf = (void *)__get_free_pages(gfp, order); + + if (buf && + check_feature_on_all_iommus(FEATURE_SNP) && + set_memory_4k((unsigned long)buf, (1 << order))) { + free_pages((unsigned long)buf, order); + buf = NULL; + } + + return buf; +} + +/* allocates the memory where the IOMMU will log its events to */ +static int __init alloc_event_buffer(struct amd_iommu *iommu) +{ + iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + EVT_BUFFER_SIZE); + + return iommu->evt_buf ? 0 : -ENOMEM; +} + +static void iommu_enable_event_buffer(struct amd_iommu *iommu) +{ + u64 entry; + + BUG_ON(iommu->evt_buf == NULL); + + entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK; + + memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, + &entry, sizeof(entry)); + + /* set head and tail to zero manually */ + writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); +} + +/* + * This function disables the event log buffer + */ +static void iommu_disable_event_buffer(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); +} + +static void __init free_event_buffer(struct amd_iommu *iommu) +{ + free_pages((unsigned long)iommu->evt_buf, get_order(EVT_BUFFER_SIZE)); +} + +/* allocates the memory where the IOMMU will log its events to */ +static int __init alloc_ppr_log(struct amd_iommu *iommu) +{ + iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + PPR_LOG_SIZE); + + return iommu->ppr_log ? 0 : -ENOMEM; +} + +static void iommu_enable_ppr_log(struct amd_iommu *iommu) +{ + u64 entry; + + if (iommu->ppr_log == NULL) + return; + + entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512; + + memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET, + &entry, sizeof(entry)); + + /* set head and tail to zero manually */ + writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET); + + iommu_feature_enable(iommu, CONTROL_PPRLOG_EN); + iommu_feature_enable(iommu, CONTROL_PPR_EN); +} + +static void __init free_ppr_log(struct amd_iommu *iommu) +{ + free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE)); +} + +static void free_ga_log(struct amd_iommu *iommu) +{ +#ifdef CONFIG_IRQ_REMAP + free_pages((unsigned long)iommu->ga_log, get_order(GA_LOG_SIZE)); + free_pages((unsigned long)iommu->ga_log_tail, get_order(8)); +#endif +} + +#ifdef CONFIG_IRQ_REMAP +static int iommu_ga_log_enable(struct amd_iommu *iommu) +{ + u32 status, i; + u64 entry; + + if (!iommu->ga_log) + return -EINVAL; + + entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512; + memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET, + &entry, sizeof(entry)); + entry = (iommu_virt_to_phys(iommu->ga_log_tail) & + (BIT_ULL(52)-1)) & ~7ULL; + memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET, + &entry, sizeof(entry)); + writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_GA_TAIL_OFFSET); + + + iommu_feature_enable(iommu, CONTROL_GAINT_EN); + iommu_feature_enable(iommu, CONTROL_GALOG_EN); + + for (i = 0; i < LOOP_TIMEOUT; ++i) { + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (status & (MMIO_STATUS_GALOG_RUN_MASK)) + break; + udelay(10); + } + + if (WARN_ON(i >= LOOP_TIMEOUT)) + return -EINVAL; + + return 0; +} + +static int iommu_init_ga_log(struct amd_iommu *iommu) +{ + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) + return 0; + + iommu->ga_log = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(GA_LOG_SIZE)); + if (!iommu->ga_log) + goto err_out; + + iommu->ga_log_tail = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(8)); + if (!iommu->ga_log_tail) + goto err_out; + + return 0; +err_out: + free_ga_log(iommu); + return -EINVAL; +} +#endif /* CONFIG_IRQ_REMAP */ + +static int __init alloc_cwwb_sem(struct amd_iommu *iommu) +{ + iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1); + + return iommu->cmd_sem ? 0 : -ENOMEM; +} + +static void __init free_cwwb_sem(struct amd_iommu *iommu) +{ + if (iommu->cmd_sem) + free_page((unsigned long)iommu->cmd_sem); +} + +static void iommu_enable_xt(struct amd_iommu *iommu) +{ +#ifdef CONFIG_IRQ_REMAP + /* + * XT mode (32-bit APIC destination ID) requires + * GA mode (128-bit IRTE support) as a prerequisite. + */ + if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir) && + amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + iommu_feature_enable(iommu, CONTROL_XT_EN); +#endif /* CONFIG_IRQ_REMAP */ +} + +static void iommu_enable_gt(struct amd_iommu *iommu) +{ + if (!iommu_feature(iommu, FEATURE_GT)) + return; + + iommu_feature_enable(iommu, CONTROL_GT_EN); +} + +/* sets a specific bit in the device table entry. */ +static void __set_dev_entry_bit(struct dev_table_entry *dev_table, + u16 devid, u8 bit) +{ + int i = (bit >> 6) & 0x03; + int _bit = bit & 0x3f; + + dev_table[devid].data[i] |= (1UL << _bit); +} + +static void set_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit) +{ + struct dev_table_entry *dev_table = get_dev_table(iommu); + + return __set_dev_entry_bit(dev_table, devid, bit); +} + +static int __get_dev_entry_bit(struct dev_table_entry *dev_table, + u16 devid, u8 bit) +{ + int i = (bit >> 6) & 0x03; + int _bit = bit & 0x3f; + + return (dev_table[devid].data[i] & (1UL << _bit)) >> _bit; +} + +static int get_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit) +{ + struct dev_table_entry *dev_table = get_dev_table(iommu); + + return __get_dev_entry_bit(dev_table, devid, bit); +} + +static bool __copy_device_table(struct amd_iommu *iommu) +{ + u64 int_ctl, int_tab_len, entry = 0; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + struct dev_table_entry *old_devtb = NULL; + u32 lo, hi, devid, old_devtb_size; + phys_addr_t old_devtb_phys; + u16 dom_id, dte_v, irq_v; + gfp_t gfp_flag; + u64 tmp; + + /* Each IOMMU use separate device table with the same size */ + lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET); + hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4); + entry = (((u64) hi) << 32) + lo; + + old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12; + if (old_devtb_size != pci_seg->dev_table_size) { + pr_err("The device table size of IOMMU:%d is not expected!\n", + iommu->index); + return false; + } + + /* + * When SME is enabled in the first kernel, the entry includes the + * memory encryption mask(sme_me_mask), we must remove the memory + * encryption mask to obtain the true physical address in kdump kernel. + */ + old_devtb_phys = __sme_clr(entry) & PAGE_MASK; + + if (old_devtb_phys >= 0x100000000ULL) { + pr_err("The address of old device table is above 4G, not trustworthy!\n"); + return false; + } + old_devtb = (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) && is_kdump_kernel()) + ? (__force void *)ioremap_encrypted(old_devtb_phys, + pci_seg->dev_table_size) + : memremap(old_devtb_phys, pci_seg->dev_table_size, MEMREMAP_WB); + + if (!old_devtb) + return false; + + gfp_flag = GFP_KERNEL | __GFP_ZERO | GFP_DMA32; + pci_seg->old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag, + get_order(pci_seg->dev_table_size)); + if (pci_seg->old_dev_tbl_cpy == NULL) { + pr_err("Failed to allocate memory for copying old device table!\n"); + memunmap(old_devtb); + return false; + } + + for (devid = 0; devid <= pci_seg->last_bdf; ++devid) { + pci_seg->old_dev_tbl_cpy[devid] = old_devtb[devid]; + dom_id = old_devtb[devid].data[1] & DEV_DOMID_MASK; + dte_v = old_devtb[devid].data[0] & DTE_FLAG_V; + + if (dte_v && dom_id) { + pci_seg->old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0]; + pci_seg->old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1]; + __set_bit(dom_id, amd_iommu_pd_alloc_bitmap); + /* If gcr3 table existed, mask it out */ + if (old_devtb[devid].data[0] & DTE_FLAG_GV) { + tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B; + tmp |= DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C; + pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp; + tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A; + tmp |= DTE_FLAG_GV; + pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp; + } + } + + irq_v = old_devtb[devid].data[2] & DTE_IRQ_REMAP_ENABLE; + int_ctl = old_devtb[devid].data[2] & DTE_IRQ_REMAP_INTCTL_MASK; + int_tab_len = old_devtb[devid].data[2] & DTE_INTTABLEN_MASK; + if (irq_v && (int_ctl || int_tab_len)) { + if ((int_ctl != DTE_IRQ_REMAP_INTCTL) || + (int_tab_len != DTE_INTTABLEN)) { + pr_err("Wrong old irq remapping flag: %#x\n", devid); + memunmap(old_devtb); + return false; + } + + pci_seg->old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2]; + } + } + memunmap(old_devtb); + + return true; +} + +static bool copy_device_table(void) +{ + struct amd_iommu *iommu; + struct amd_iommu_pci_seg *pci_seg; + + if (!amd_iommu_pre_enabled) + return false; + + pr_warn("Translation is already enabled - trying to copy translation structures\n"); + + /* + * All IOMMUs within PCI segment shares common device table. + * Hence copy device table only once per PCI segment. + */ + for_each_pci_segment(pci_seg) { + for_each_iommu(iommu) { + if (pci_seg->id != iommu->pci_seg->id) + continue; + if (!__copy_device_table(iommu)) + return false; + break; + } + } + + return true; +} + +void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid) +{ + int sysmgt; + + sysmgt = get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1) | + (get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2) << 1); + + if (sysmgt == 0x01) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_IW); +} + +/* + * This function takes the device specific flags read from the ACPI + * table and sets up the device table entry with that information + */ +static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu, + u16 devid, u32 flags, u32 ext_flags) +{ + if (flags & ACPI_DEVFLAG_INITPASS) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_INIT_PASS); + if (flags & ACPI_DEVFLAG_EXTINT) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_EINT_PASS); + if (flags & ACPI_DEVFLAG_NMI) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_NMI_PASS); + if (flags & ACPI_DEVFLAG_SYSMGT1) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1); + if (flags & ACPI_DEVFLAG_SYSMGT2) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2); + if (flags & ACPI_DEVFLAG_LINT0) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT0_PASS); + if (flags & ACPI_DEVFLAG_LINT1) + set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT1_PASS); + + amd_iommu_apply_erratum_63(iommu, devid); + + amd_iommu_set_rlookup_table(iommu, devid); +} + +int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line) +{ + struct devid_map *entry; + struct list_head *list; + + if (type == IVHD_SPECIAL_IOAPIC) + list = &ioapic_map; + else if (type == IVHD_SPECIAL_HPET) + list = &hpet_map; + else + return -EINVAL; + + list_for_each_entry(entry, list, list) { + if (!(entry->id == id && entry->cmd_line)) + continue; + + pr_info("Command-line override present for %s id %d - ignoring\n", + type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id); + + *devid = entry->devid; + + return 0; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->id = id; + entry->devid = *devid; + entry->cmd_line = cmd_line; + + list_add_tail(&entry->list, list); + + return 0; +} + +static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u32 *devid, + bool cmd_line) +{ + struct acpihid_map_entry *entry; + struct list_head *list = &acpihid_map; + + list_for_each_entry(entry, list, list) { + if (strcmp(entry->hid, hid) || + (*uid && *entry->uid && strcmp(entry->uid, uid)) || + !entry->cmd_line) + continue; + + pr_info("Command-line override for hid:%s uid:%s\n", + hid, uid); + *devid = entry->devid; + return 0; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + memcpy(entry->uid, uid, strlen(uid)); + memcpy(entry->hid, hid, strlen(hid)); + entry->devid = *devid; + entry->cmd_line = cmd_line; + entry->root_devid = (entry->devid & (~0x7)); + + pr_info("%s, add hid:%s, uid:%s, rdevid:%d\n", + entry->cmd_line ? "cmd" : "ivrs", + entry->hid, entry->uid, entry->root_devid); + + list_add_tail(&entry->list, list); + return 0; +} + +static int __init add_early_maps(void) +{ + int i, ret; + + for (i = 0; i < early_ioapic_map_size; ++i) { + ret = add_special_device(IVHD_SPECIAL_IOAPIC, + early_ioapic_map[i].id, + &early_ioapic_map[i].devid, + early_ioapic_map[i].cmd_line); + if (ret) + return ret; + } + + for (i = 0; i < early_hpet_map_size; ++i) { + ret = add_special_device(IVHD_SPECIAL_HPET, + early_hpet_map[i].id, + &early_hpet_map[i].devid, + early_hpet_map[i].cmd_line); + if (ret) + return ret; + } + + for (i = 0; i < early_acpihid_map_size; ++i) { + ret = add_acpi_hid_device(early_acpihid_map[i].hid, + early_acpihid_map[i].uid, + &early_acpihid_map[i].devid, + early_acpihid_map[i].cmd_line); + if (ret) + return ret; + } + + return 0; +} + +/* + * Takes a pointer to an AMD IOMMU entry in the ACPI table and + * initializes the hardware and our data structures with it. + */ +static int __init init_iommu_from_acpi(struct amd_iommu *iommu, + struct ivhd_header *h) +{ + u8 *p = (u8 *)h; + u8 *end = p, flags = 0; + u16 devid = 0, devid_start = 0, devid_to = 0, seg_id; + u32 dev_i, ext_flags = 0; + bool alias = false; + struct ivhd_entry *e; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + u32 ivhd_size; + int ret; + + + ret = add_early_maps(); + if (ret) + return ret; + + amd_iommu_apply_ivrs_quirks(); + + /* + * First save the recommended feature enable bits from ACPI + */ + iommu->acpi_flags = h->flags; + + /* + * Done. Now parse the device entries + */ + ivhd_size = get_ivhd_header_size(h); + if (!ivhd_size) { + pr_err("Unsupported IVHD type %#x\n", h->type); + return -EINVAL; + } + + p += ivhd_size; + + end += h->length; + + + while (p < end) { + e = (struct ivhd_entry *)p; + seg_id = pci_seg->id; + + switch (e->type) { + case IVHD_DEV_ALL: + + DUMP_printk(" DEV_ALL\t\t\tflags: %02x\n", e->flags); + + for (dev_i = 0; dev_i <= pci_seg->last_bdf; ++dev_i) + set_dev_entry_from_acpi(iommu, dev_i, e->flags, 0); + break; + case IVHD_DEV_SELECT: + + DUMP_printk(" DEV_SELECT\t\t\t devid: %04x:%02x:%02x.%x " + "flags: %02x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags); + + devid = e->devid; + set_dev_entry_from_acpi(iommu, devid, e->flags, 0); + break; + case IVHD_DEV_SELECT_RANGE_START: + + DUMP_printk(" DEV_SELECT_RANGE_START\t " + "devid: %04x:%02x:%02x.%x flags: %02x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags); + + devid_start = e->devid; + flags = e->flags; + ext_flags = 0; + alias = false; + break; + case IVHD_DEV_ALIAS: + + DUMP_printk(" DEV_ALIAS\t\t\t devid: %04x:%02x:%02x.%x " + "flags: %02x devid_to: %02x:%02x.%x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags, + PCI_BUS_NUM(e->ext >> 8), + PCI_SLOT(e->ext >> 8), + PCI_FUNC(e->ext >> 8)); + + devid = e->devid; + devid_to = e->ext >> 8; + set_dev_entry_from_acpi(iommu, devid , e->flags, 0); + set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0); + pci_seg->alias_table[devid] = devid_to; + break; + case IVHD_DEV_ALIAS_RANGE: + + DUMP_printk(" DEV_ALIAS_RANGE\t\t " + "devid: %04x:%02x:%02x.%x flags: %02x " + "devid_to: %04x:%02x:%02x.%x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags, + seg_id, PCI_BUS_NUM(e->ext >> 8), + PCI_SLOT(e->ext >> 8), + PCI_FUNC(e->ext >> 8)); + + devid_start = e->devid; + flags = e->flags; + devid_to = e->ext >> 8; + ext_flags = 0; + alias = true; + break; + case IVHD_DEV_EXT_SELECT: + + DUMP_printk(" DEV_EXT_SELECT\t\t devid: %04x:%02x:%02x.%x " + "flags: %02x ext: %08x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags, e->ext); + + devid = e->devid; + set_dev_entry_from_acpi(iommu, devid, e->flags, + e->ext); + break; + case IVHD_DEV_EXT_SELECT_RANGE: + + DUMP_printk(" DEV_EXT_SELECT_RANGE\t devid: " + "%04x:%02x:%02x.%x flags: %02x ext: %08x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid), + e->flags, e->ext); + + devid_start = e->devid; + flags = e->flags; + ext_flags = e->ext; + alias = false; + break; + case IVHD_DEV_RANGE_END: + + DUMP_printk(" DEV_RANGE_END\t\t devid: %04x:%02x:%02x.%x\n", + seg_id, PCI_BUS_NUM(e->devid), + PCI_SLOT(e->devid), + PCI_FUNC(e->devid)); + + devid = e->devid; + for (dev_i = devid_start; dev_i <= devid; ++dev_i) { + if (alias) { + pci_seg->alias_table[dev_i] = devid_to; + set_dev_entry_from_acpi(iommu, + devid_to, flags, ext_flags); + } + set_dev_entry_from_acpi(iommu, dev_i, + flags, ext_flags); + } + break; + case IVHD_DEV_SPECIAL: { + u8 handle, type; + const char *var; + u32 devid; + int ret; + + handle = e->ext & 0xff; + devid = PCI_SEG_DEVID_TO_SBDF(seg_id, (e->ext >> 8)); + type = (e->ext >> 24) & 0xff; + + if (type == IVHD_SPECIAL_IOAPIC) + var = "IOAPIC"; + else if (type == IVHD_SPECIAL_HPET) + var = "HPET"; + else + var = "UNKNOWN"; + + DUMP_printk(" DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x\n", + var, (int)handle, + seg_id, PCI_BUS_NUM(devid), + PCI_SLOT(devid), + PCI_FUNC(devid)); + + ret = add_special_device(type, handle, &devid, false); + if (ret) + return ret; + + /* + * add_special_device might update the devid in case a + * command-line override is present. So call + * set_dev_entry_from_acpi after add_special_device. + */ + set_dev_entry_from_acpi(iommu, devid, e->flags, 0); + + break; + } + case IVHD_DEV_ACPI_HID: { + u32 devid; + u8 hid[ACPIHID_HID_LEN]; + u8 uid[ACPIHID_UID_LEN]; + int ret; + + if (h->type != 0x40) { + pr_err(FW_BUG "Invalid IVHD device type %#x\n", + e->type); + break; + } + + BUILD_BUG_ON(sizeof(e->ext_hid) != ACPIHID_HID_LEN - 1); + memcpy(hid, &e->ext_hid, ACPIHID_HID_LEN - 1); + hid[ACPIHID_HID_LEN - 1] = '\0'; + + if (!(*hid)) { + pr_err(FW_BUG "Invalid HID.\n"); + break; + } + + uid[0] = '\0'; + switch (e->uidf) { + case UID_NOT_PRESENT: + + if (e->uidl != 0) + pr_warn(FW_BUG "Invalid UID length.\n"); + + break; + case UID_IS_INTEGER: + + sprintf(uid, "%d", e->uid); + + break; + case UID_IS_CHARACTER: + + memcpy(uid, &e->uid, e->uidl); + uid[e->uidl] = '\0'; + + break; + default: + break; + } + + devid = PCI_SEG_DEVID_TO_SBDF(seg_id, e->devid); + DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x\n", + hid, uid, seg_id, + PCI_BUS_NUM(devid), + PCI_SLOT(devid), + PCI_FUNC(devid)); + + flags = e->flags; + + ret = add_acpi_hid_device(hid, uid, &devid, false); + if (ret) + return ret; + + /* + * add_special_device might update the devid in case a + * command-line override is present. So call + * set_dev_entry_from_acpi after add_special_device. + */ + set_dev_entry_from_acpi(iommu, devid, e->flags, 0); + + break; + } + default: + break; + } + + p += ivhd_entry_length(p); + } + + return 0; +} + +/* Allocate PCI segment data structure */ +static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id, + struct acpi_table_header *ivrs_base) +{ + struct amd_iommu_pci_seg *pci_seg; + int last_bdf; + + /* + * First parse ACPI tables to find the largest Bus/Dev/Func we need to + * handle in this PCI segment. Upon this information the shared data + * structures for the PCI segments in the system will be allocated. + */ + last_bdf = find_last_devid_acpi(ivrs_base, id); + if (last_bdf < 0) + return NULL; + + pci_seg = kzalloc(sizeof(struct amd_iommu_pci_seg), GFP_KERNEL); + if (pci_seg == NULL) + return NULL; + + pci_seg->last_bdf = last_bdf; + DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf); + pci_seg->dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf); + pci_seg->alias_table_size = tbl_size(ALIAS_TABLE_ENTRY_SIZE, last_bdf); + pci_seg->rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE, last_bdf); + + pci_seg->id = id; + init_llist_head(&pci_seg->dev_data_list); + INIT_LIST_HEAD(&pci_seg->unity_map); + list_add_tail(&pci_seg->list, &amd_iommu_pci_seg_list); + + if (alloc_dev_table(pci_seg)) + return NULL; + if (alloc_alias_table(pci_seg)) + return NULL; + if (alloc_rlookup_table(pci_seg)) + return NULL; + + return pci_seg; +} + +static struct amd_iommu_pci_seg *__init get_pci_segment(u16 id, + struct acpi_table_header *ivrs_base) +{ + struct amd_iommu_pci_seg *pci_seg; + + for_each_pci_segment(pci_seg) { + if (pci_seg->id == id) + return pci_seg; + } + + return alloc_pci_segment(id, ivrs_base); +} + +static void __init free_pci_segments(void) +{ + struct amd_iommu_pci_seg *pci_seg, *next; + + for_each_pci_segment_safe(pci_seg, next) { + list_del(&pci_seg->list); + free_irq_lookup_table(pci_seg); + free_rlookup_table(pci_seg); + free_alias_table(pci_seg); + free_dev_table(pci_seg); + kfree(pci_seg); + } +} + +static void __init free_iommu_one(struct amd_iommu *iommu) +{ + free_cwwb_sem(iommu); + free_command_buffer(iommu); + free_event_buffer(iommu); + free_ppr_log(iommu); + free_ga_log(iommu); + iommu_unmap_mmio_space(iommu); +} + +static void __init free_iommu_all(void) +{ + struct amd_iommu *iommu, *next; + + for_each_iommu_safe(iommu, next) { + list_del(&iommu->list); + free_iommu_one(iommu); + kfree(iommu); + } +} + +/* + * Family15h Model 10h-1fh erratum 746 (IOMMU Logging May Stall Translations) + * Workaround: + * BIOS should disable L2B micellaneous clock gating by setting + * L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b + */ +static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x10) || + (boot_cpu_data.x86_model > 0x1f)) + return; + + pci_write_config_dword(iommu->dev, 0xf0, 0x90); + pci_read_config_dword(iommu->dev, 0xf4, &value); + + if (value & BIT(2)) + return; + + /* Select NB indirect register 0x90 and enable writing */ + pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8)); + + pci_write_config_dword(iommu->dev, 0xf4, value | 0x4); + pci_info(iommu->dev, "Applying erratum 746 workaround\n"); + + /* Clear the enable writing bit */ + pci_write_config_dword(iommu->dev, 0xf0, 0x90); +} + +/* + * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission) + * Workaround: + * BIOS should enable ATS write permission check by setting + * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b + */ +static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x30) || + (boot_cpu_data.x86_model > 0x3f)) + return; + + /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */ + value = iommu_read_l2(iommu, 0x47); + + if (value & BIT(0)) + return; + + /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */ + iommu_write_l2(iommu, 0x47, value | BIT(0)); + + pci_info(iommu->dev, "Applying ATS write check workaround\n"); +} + +/* + * This function glues the initialization function for one IOMMU + * together and also allocates the command buffer and programs the + * hardware. It does NOT enable the IOMMU. This is done afterwards. + */ +static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, + struct acpi_table_header *ivrs_base) +{ + struct amd_iommu_pci_seg *pci_seg; + + pci_seg = get_pci_segment(h->pci_seg, ivrs_base); + if (pci_seg == NULL) + return -ENOMEM; + iommu->pci_seg = pci_seg; + + raw_spin_lock_init(&iommu->lock); + iommu->cmd_sem_val = 0; + + /* Add IOMMU to internal data structures */ + list_add_tail(&iommu->list, &amd_iommu_list); + iommu->index = amd_iommus_present++; + + if (unlikely(iommu->index >= MAX_IOMMUS)) { + WARN(1, "System has more IOMMUs than supported by this driver\n"); + return -ENOSYS; + } + + /* Index is fine - add IOMMU to the array */ + amd_iommus[iommu->index] = iommu; + + /* + * Copy data from ACPI table entry to the iommu struct + */ + iommu->devid = h->devid; + iommu->cap_ptr = h->cap_ptr; + iommu->mmio_phys = h->mmio_phys; + + switch (h->type) { + case 0x10: + /* Check if IVHD EFR contains proper max banks/counters */ + if ((h->efr_attr != 0) && + ((h->efr_attr & (0xF << 13)) != 0) && + ((h->efr_attr & (0x3F << 17)) != 0)) + iommu->mmio_phys_end = MMIO_REG_END_OFFSET; + else + iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; + + /* + * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports. + * GAM also requires GA mode. Therefore, we need to + * check cmpxchg16b support before enabling it. + */ + if (!boot_cpu_has(X86_FEATURE_CX16) || + ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0)) + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + break; + case 0x11: + case 0x40: + if (h->efr_reg & (1 << 9)) + iommu->mmio_phys_end = MMIO_REG_END_OFFSET; + else + iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; + + /* + * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports. + * XT, GAM also requires GA mode. Therefore, we need to + * check cmpxchg16b support before enabling them. + */ + if (!boot_cpu_has(X86_FEATURE_CX16) || + ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) { + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + break; + } + + if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) + amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; + + early_iommu_features_init(iommu, h); + + break; + default: + return -EINVAL; + } + + iommu->mmio_base = iommu_map_mmio_space(iommu->mmio_phys, + iommu->mmio_phys_end); + if (!iommu->mmio_base) + return -ENOMEM; + + return init_iommu_from_acpi(iommu, h); +} + +static int __init init_iommu_one_late(struct amd_iommu *iommu) +{ + int ret; + + if (alloc_cwwb_sem(iommu)) + return -ENOMEM; + + if (alloc_command_buffer(iommu)) + return -ENOMEM; + + if (alloc_event_buffer(iommu)) + return -ENOMEM; + + iommu->int_enabled = false; + + init_translation_status(iommu); + if (translation_pre_enabled(iommu) && !is_kdump_kernel()) { + iommu_disable(iommu); + clear_translation_pre_enabled(iommu); + pr_warn("Translation was enabled for IOMMU:%d but we are not in kdump mode\n", + iommu->index); + } + if (amd_iommu_pre_enabled) + amd_iommu_pre_enabled = translation_pre_enabled(iommu); + + if (amd_iommu_irq_remap) { + ret = amd_iommu_create_irq_domain(iommu); + if (ret) + return ret; + } + + /* + * Make sure IOMMU is not considered to translate itself. The IVRS + * table tells us so, but this is a lie! + */ + iommu->pci_seg->rlookup_table[iommu->devid] = NULL; + + return 0; +} + +/** + * get_highest_supported_ivhd_type - Look up the appropriate IVHD type + * @ivrs: Pointer to the IVRS header + * + * This function search through all IVDB of the maximum supported IVHD + */ +static u8 get_highest_supported_ivhd_type(struct acpi_table_header *ivrs) +{ + u8 *base = (u8 *)ivrs; + struct ivhd_header *ivhd = (struct ivhd_header *) + (base + IVRS_HEADER_LENGTH); + u8 last_type = ivhd->type; + u16 devid = ivhd->devid; + + while (((u8 *)ivhd - base < ivrs->length) && + (ivhd->type <= ACPI_IVHD_TYPE_MAX_SUPPORTED)) { + u8 *p = (u8 *) ivhd; + + if (ivhd->devid == devid) + last_type = ivhd->type; + ivhd = (struct ivhd_header *)(p + ivhd->length); + } + + return last_type; +} + +/* + * Iterates over all IOMMU entries in the ACPI table, allocates the + * IOMMU structure and initializes it with init_iommu_one() + */ +static int __init init_iommu_all(struct acpi_table_header *table) +{ + u8 *p = (u8 *)table, *end = (u8 *)table; + struct ivhd_header *h; + struct amd_iommu *iommu; + int ret; + + end += table->length; + p += IVRS_HEADER_LENGTH; + + /* Phase 1: Process all IVHD blocks */ + while (p < end) { + h = (struct ivhd_header *)p; + if (*p == amd_iommu_target_ivhd_type) { + + DUMP_printk("device: %04x:%02x:%02x.%01x cap: %04x " + "flags: %01x info %04x\n", + h->pci_seg, PCI_BUS_NUM(h->devid), + PCI_SLOT(h->devid), PCI_FUNC(h->devid), + h->cap_ptr, h->flags, h->info); + DUMP_printk(" mmio-addr: %016llx\n", + h->mmio_phys); + + iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); + if (iommu == NULL) + return -ENOMEM; + + ret = init_iommu_one(iommu, h, table); + if (ret) + return ret; + } + p += h->length; + + } + WARN_ON(p != end); + + /* Phase 2 : Early feature support check */ + get_global_efr(); + + /* Phase 3 : Enabling IOMMU features */ + for_each_iommu(iommu) { + ret = init_iommu_one_late(iommu); + if (ret) + return ret; + } + + return 0; +} + +static void init_iommu_perf_ctr(struct amd_iommu *iommu) +{ + u64 val; + struct pci_dev *pdev = iommu->dev; + + if (!iommu_feature(iommu, FEATURE_PC)) + return; + + amd_iommu_pc_present = true; + + pci_info(pdev, "IOMMU performance counters supported\n"); + + val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET); + iommu->max_banks = (u8) ((val >> 12) & 0x3f); + iommu->max_counters = (u8) ((val >> 7) & 0xf); + + return; +} + +static ssize_t amd_iommu_show_cap(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct amd_iommu *iommu = dev_to_amd_iommu(dev); + return sprintf(buf, "%x\n", iommu->cap); +} +static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL); + +static ssize_t amd_iommu_show_features(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct amd_iommu *iommu = dev_to_amd_iommu(dev); + return sprintf(buf, "%llx:%llx\n", iommu->features2, iommu->features); +} +static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL); + +static struct attribute *amd_iommu_attrs[] = { + &dev_attr_cap.attr, + &dev_attr_features.attr, + NULL, +}; + +static struct attribute_group amd_iommu_group = { + .name = "amd-iommu", + .attrs = amd_iommu_attrs, +}; + +static const struct attribute_group *amd_iommu_groups[] = { + &amd_iommu_group, + NULL, +}; + +/* + * Note: IVHD 0x11 and 0x40 also contains exact copy + * of the IOMMU Extended Feature Register [MMIO Offset 0030h]. + * Default to EFR in IVHD since it is available sooner (i.e. before PCI init). + */ +static void __init late_iommu_features_init(struct amd_iommu *iommu) +{ + u64 features, features2; + + if (!(iommu->cap & (1 << IOMMU_CAP_EFR))) + return; + + /* read extended feature bits */ + features = readq(iommu->mmio_base + MMIO_EXT_FEATURES); + features2 = readq(iommu->mmio_base + MMIO_EXT_FEATURES2); + + if (!iommu->features) { + iommu->features = features; + iommu->features2 = features2; + return; + } + + /* + * Sanity check and warn if EFR values from + * IVHD and MMIO conflict. + */ + if (features != iommu->features || + features2 != iommu->features2) { + pr_warn(FW_WARN + "EFR mismatch. Use IVHD EFR (%#llx : %#llx), EFR2 (%#llx : %#llx).\n", + features, iommu->features, + features2, iommu->features2); + } +} + +static int __init iommu_init_pci(struct amd_iommu *iommu) +{ + int cap_ptr = iommu->cap_ptr; + int ret; + + iommu->dev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, + PCI_BUS_NUM(iommu->devid), + iommu->devid & 0xff); + if (!iommu->dev) + return -ENODEV; + + /* Prevent binding other PCI device drivers to IOMMU devices */ + iommu->dev->match_driver = false; + + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, + &iommu->cap); + + if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) + amd_iommu_iotlb_sup = false; + + late_iommu_features_init(iommu); + + if (iommu_feature(iommu, FEATURE_GT)) { + int glxval; + u32 max_pasid; + u64 pasmax; + + pasmax = iommu->features & FEATURE_PASID_MASK; + pasmax >>= FEATURE_PASID_SHIFT; + max_pasid = (1 << (pasmax + 1)) - 1; + + amd_iommu_max_pasid = min(amd_iommu_max_pasid, max_pasid); + + BUG_ON(amd_iommu_max_pasid & ~PASID_MASK); + + glxval = iommu->features & FEATURE_GLXVAL_MASK; + glxval >>= FEATURE_GLXVAL_SHIFT; + + if (amd_iommu_max_glx_val == -1) + amd_iommu_max_glx_val = glxval; + else + amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); + } + + if (iommu_feature(iommu, FEATURE_GT) && + iommu_feature(iommu, FEATURE_PPR)) { + iommu->is_iommu_v2 = true; + amd_iommu_v2_present = true; + } + + if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu)) + return -ENOMEM; + + if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) { + pr_info("Using strict mode due to virtualization\n"); + iommu_set_dma_strict(); + amd_iommu_np_cache = true; + } + + init_iommu_perf_ctr(iommu); + + if (amd_iommu_pgtable == AMD_IOMMU_V2) { + if (!iommu_feature(iommu, FEATURE_GIOSUP) || + !iommu_feature(iommu, FEATURE_GT)) { + pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n"); + amd_iommu_pgtable = AMD_IOMMU_V1; + } else if (iommu_default_passthrough()) { + pr_warn("V2 page table doesn't support passthrough mode. Fallback to v1.\n"); + amd_iommu_pgtable = AMD_IOMMU_V1; + } + } + + if (is_rd890_iommu(iommu->dev)) { + int i, j; + + iommu->root_pdev = + pci_get_domain_bus_and_slot(iommu->pci_seg->id, + iommu->dev->bus->number, + PCI_DEVFN(0, 0)); + + /* + * Some rd890 systems may not be fully reconfigured by the + * BIOS, so it's necessary for us to store this information so + * it can be reprogrammed on resume + */ + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, + &iommu->stored_addr_lo); + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, + &iommu->stored_addr_hi); + + /* Low bit locks writes to configuration space */ + iommu->stored_addr_lo &= ~1; + + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); + + for (i = 0; i < 0x83; i++) + iommu->stored_l2[i] = iommu_read_l2(iommu, i); + } + + amd_iommu_erratum_746_workaround(iommu); + amd_iommu_ats_write_check_workaround(iommu); + + ret = iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev, + amd_iommu_groups, "ivhd%d", iommu->index); + if (ret) + return ret; + + iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL); + + return pci_enable_device(iommu->dev); +} + +static void print_iommu_info(void) +{ + static const char * const feat_str[] = { + "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", + "IA", "GA", "HE", "PC" + }; + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + struct pci_dev *pdev = iommu->dev; + int i; + + pci_info(pdev, "Found IOMMU cap 0x%x\n", iommu->cap_ptr); + + if (iommu->cap & (1 << IOMMU_CAP_EFR)) { + pr_info("Extended features (%#llx, %#llx):", iommu->features, iommu->features2); + + for (i = 0; i < ARRAY_SIZE(feat_str); ++i) { + if (iommu_feature(iommu, (1ULL << i))) + pr_cont(" %s", feat_str[i]); + } + + if (iommu->features & FEATURE_GAM_VAPIC) + pr_cont(" GA_vAPIC"); + + if (iommu->features & FEATURE_SNP) + pr_cont(" SNP"); + + pr_cont("\n"); + } + } + if (irq_remapping_enabled) { + pr_info("Interrupt remapping enabled\n"); + if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + pr_info("X2APIC enabled\n"); + } + if (amd_iommu_pgtable == AMD_IOMMU_V2) + pr_info("V2 page table enabled\n"); +} + +static int __init amd_iommu_init_pci(void) +{ + struct amd_iommu *iommu; + struct amd_iommu_pci_seg *pci_seg; + int ret; + + for_each_iommu(iommu) { + ret = iommu_init_pci(iommu); + if (ret) { + pr_err("IOMMU%d: Failed to initialize IOMMU Hardware (error=%d)!\n", + iommu->index, ret); + goto out; + } + /* Need to setup range after PCI init */ + iommu_set_cwwb_range(iommu); + } + + /* + * Order is important here to make sure any unity map requirements are + * fulfilled. The unity mappings are created and written to the device + * table during the iommu_init_pci() call. + * + * After that we call init_device_table_dma() to make sure any + * uninitialized DTE will block DMA, and in the end we flush the caches + * of all IOMMUs to make sure the changes to the device table are + * active. + */ + for_each_pci_segment(pci_seg) + init_device_table_dma(pci_seg); + + for_each_iommu(iommu) + iommu_flush_all_caches(iommu); + + print_iommu_info(); + +out: + return ret; +} + +/**************************************************************************** + * + * The following functions initialize the MSI interrupts for all IOMMUs + * in the system. It's a bit challenging because there could be multiple + * IOMMUs per PCI BDF but we can call pci_enable_msi(x) only once per + * pci_dev. + * + ****************************************************************************/ + +static int iommu_setup_msi(struct amd_iommu *iommu) +{ + int r; + + r = pci_enable_msi(iommu->dev); + if (r) + return r; + + r = request_threaded_irq(iommu->dev->irq, + amd_iommu_int_handler, + amd_iommu_int_thread, + 0, "AMD-Vi", + iommu); + + if (r) { + pci_disable_msi(iommu->dev); + return r; + } + + return 0; +} + +union intcapxt { + u64 capxt; + struct { + u64 reserved_0 : 2, + dest_mode_logical : 1, + reserved_1 : 5, + destid_0_23 : 24, + vector : 8, + reserved_2 : 16, + destid_24_31 : 8; + }; +} __attribute__ ((packed)); + + +static struct irq_chip intcapxt_controller; + +static int intcapxt_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irqd, bool reserve) +{ + return 0; +} + +static void intcapxt_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irqd) +{ +} + + +static int intcapxt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + int i, ret; + + if (!info || info->type != X86_IRQ_ALLOC_TYPE_AMDVI) + return -EINVAL; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + for (i = virq; i < virq + nr_irqs; i++) { + struct irq_data *irqd = irq_domain_get_irq_data(domain, i); + + irqd->chip = &intcapxt_controller; + irqd->chip_data = info->data; + __irq_set_handler(i, handle_edge_irq, 0, "edge"); + } + + return ret; +} + +static void intcapxt_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} + + +static void intcapxt_unmask_irq(struct irq_data *irqd) +{ + struct amd_iommu *iommu = irqd->chip_data; + struct irq_cfg *cfg = irqd_cfg(irqd); + union intcapxt xt; + + xt.capxt = 0ULL; + xt.dest_mode_logical = apic->dest_mode_logical; + xt.vector = cfg->vector; + xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0); + xt.destid_24_31 = cfg->dest_apicid >> 24; + + /** + * Current IOMMU implementation uses the same IRQ for all + * 3 IOMMU interrupts. + */ + writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET); + writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET); + writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET); +} + +static void intcapxt_mask_irq(struct irq_data *irqd) +{ + struct amd_iommu *iommu = irqd->chip_data; + + writeq(0, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET); + writeq(0, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET); + writeq(0, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET); +} + + +static int intcapxt_set_affinity(struct irq_data *irqd, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irqd->parent_data; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + return 0; +} + +static int intcapxt_set_wake(struct irq_data *irqd, unsigned int on) +{ + return on ? -EOPNOTSUPP : 0; +} + +static struct irq_chip intcapxt_controller = { + .name = "IOMMU-MSI", + .irq_unmask = intcapxt_unmask_irq, + .irq_mask = intcapxt_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_affinity = intcapxt_set_affinity, + .irq_set_wake = intcapxt_set_wake, + .flags = IRQCHIP_MASK_ON_SUSPEND, +}; + +static const struct irq_domain_ops intcapxt_domain_ops = { + .alloc = intcapxt_irqdomain_alloc, + .free = intcapxt_irqdomain_free, + .activate = intcapxt_irqdomain_activate, + .deactivate = intcapxt_irqdomain_deactivate, +}; + + +static struct irq_domain *iommu_irqdomain; + +static struct irq_domain *iommu_get_irqdomain(void) +{ + struct fwnode_handle *fn; + + /* No need for locking here (yet) as the init is single-threaded */ + if (iommu_irqdomain) + return iommu_irqdomain; + + fn = irq_domain_alloc_named_fwnode("AMD-Vi-MSI"); + if (!fn) + return NULL; + + iommu_irqdomain = irq_domain_create_hierarchy(x86_vector_domain, 0, 0, + fn, &intcapxt_domain_ops, + NULL); + if (!iommu_irqdomain) + irq_domain_free_fwnode(fn); + + return iommu_irqdomain; +} + +static int iommu_setup_intcapxt(struct amd_iommu *iommu) +{ + struct irq_domain *domain; + struct irq_alloc_info info; + int irq, ret; + + domain = iommu_get_irqdomain(); + if (!domain) + return -ENXIO; + + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_AMDVI; + info.data = iommu; + + irq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); + if (irq < 0) { + irq_domain_remove(domain); + return irq; + } + + ret = request_threaded_irq(irq, amd_iommu_int_handler, + amd_iommu_int_thread, 0, "AMD-Vi", iommu); + if (ret) { + irq_domain_free_irqs(irq, 1); + irq_domain_remove(domain); + return ret; + } + + return 0; +} + +static int iommu_init_irq(struct amd_iommu *iommu) +{ + int ret; + + if (iommu->int_enabled) + goto enable_faults; + + if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + ret = iommu_setup_intcapxt(iommu); + else if (iommu->dev->msi_cap) + ret = iommu_setup_msi(iommu); + else + ret = -ENODEV; + + if (ret) + return ret; + + iommu->int_enabled = true; +enable_faults: + + if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN); + + iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); + + if (iommu->ppr_log != NULL) + iommu_feature_enable(iommu, CONTROL_PPRINT_EN); + return 0; +} + +/**************************************************************************** + * + * The next functions belong to the third pass of parsing the ACPI + * table. In this last pass the memory mapping requirements are + * gathered (like exclusion and unity mapping ranges). + * + ****************************************************************************/ + +static void __init free_unity_maps(void) +{ + struct unity_map_entry *entry, *next; + struct amd_iommu_pci_seg *p, *pci_seg; + + for_each_pci_segment_safe(pci_seg, p) { + list_for_each_entry_safe(entry, next, &pci_seg->unity_map, list) { + list_del(&entry->list); + kfree(entry); + } + } +} + +/* called for unity map ACPI definition */ +static int __init init_unity_map_range(struct ivmd_header *m, + struct acpi_table_header *ivrs_base) +{ + struct unity_map_entry *e = NULL; + struct amd_iommu_pci_seg *pci_seg; + char *s; + + pci_seg = get_pci_segment(m->pci_seg, ivrs_base); + if (pci_seg == NULL) + return -ENOMEM; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (e == NULL) + return -ENOMEM; + + switch (m->type) { + default: + kfree(e); + return 0; + case ACPI_IVMD_TYPE: + s = "IVMD_TYPEi\t\t\t"; + e->devid_start = e->devid_end = m->devid; + break; + case ACPI_IVMD_TYPE_ALL: + s = "IVMD_TYPE_ALL\t\t"; + e->devid_start = 0; + e->devid_end = pci_seg->last_bdf; + break; + case ACPI_IVMD_TYPE_RANGE: + s = "IVMD_TYPE_RANGE\t\t"; + e->devid_start = m->devid; + e->devid_end = m->aux; + break; + } + e->address_start = PAGE_ALIGN(m->range_start); + e->address_end = e->address_start + PAGE_ALIGN(m->range_length); + e->prot = m->flags >> 1; + + /* + * Treat per-device exclusion ranges as r/w unity-mapped regions + * since some buggy BIOSes might lead to the overwritten exclusion + * range (exclusion_start and exclusion_length members). This + * happens when there are multiple exclusion ranges (IVMD entries) + * defined in ACPI table. + */ + if (m->flags & IVMD_FLAG_EXCL_RANGE) + e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1; + + DUMP_printk("%s devid_start: %04x:%02x:%02x.%x devid_end: " + "%04x:%02x:%02x.%x range_start: %016llx range_end: %016llx" + " flags: %x\n", s, m->pci_seg, + PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start), + PCI_FUNC(e->devid_start), m->pci_seg, + PCI_BUS_NUM(e->devid_end), + PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end), + e->address_start, e->address_end, m->flags); + + list_add_tail(&e->list, &pci_seg->unity_map); + + return 0; +} + +/* iterates over all memory definitions we find in the ACPI table */ +static int __init init_memory_definitions(struct acpi_table_header *table) +{ + u8 *p = (u8 *)table, *end = (u8 *)table; + struct ivmd_header *m; + + end += table->length; + p += IVRS_HEADER_LENGTH; + + while (p < end) { + m = (struct ivmd_header *)p; + if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE)) + init_unity_map_range(m, table); + + p += m->length; + } + + return 0; +} + +/* + * Init the device table to not allow DMA access for devices + */ +static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg) +{ + u32 devid; + struct dev_table_entry *dev_table = pci_seg->dev_table; + + if (dev_table == NULL) + return; + + for (devid = 0; devid <= pci_seg->last_bdf; ++devid) { + __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_VALID); + if (!amd_iommu_snp_en) + __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_TRANSLATION); + } +} + +static void __init uninit_device_table_dma(struct amd_iommu_pci_seg *pci_seg) +{ + u32 devid; + struct dev_table_entry *dev_table = pci_seg->dev_table; + + if (dev_table == NULL) + return; + + for (devid = 0; devid <= pci_seg->last_bdf; ++devid) { + dev_table[devid].data[0] = 0ULL; + dev_table[devid].data[1] = 0ULL; + } +} + +static void init_device_table(void) +{ + struct amd_iommu_pci_seg *pci_seg; + u32 devid; + + if (!amd_iommu_irq_remap) + return; + + for_each_pci_segment(pci_seg) { + for (devid = 0; devid <= pci_seg->last_bdf; ++devid) + __set_dev_entry_bit(pci_seg->dev_table, + devid, DEV_ENTRY_IRQ_TBL_EN); + } +} + +static void iommu_init_flags(struct amd_iommu *iommu) +{ + iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + + /* Set IOTLB invalidation timeout to 1s */ + iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S); +} + +static void iommu_apply_resume_quirks(struct amd_iommu *iommu) +{ + int i, j; + u32 ioc_feature_control; + struct pci_dev *pdev = iommu->root_pdev; + + /* RD890 BIOSes may not have completely reconfigured the iommu */ + if (!is_rd890_iommu(iommu->dev) || !pdev) + return; + + /* + * First, we need to ensure that the iommu is enabled. This is + * controlled by a register in the northbridge + */ + + /* Select Northbridge indirect register 0x75 and enable writing */ + pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7)); + pci_read_config_dword(pdev, 0x64, &ioc_feature_control); + + /* Enable the iommu */ + if (!(ioc_feature_control & 0x1)) + pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1); + + /* Restore the iommu BAR */ + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, + iommu->stored_addr_lo); + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8, + iommu->stored_addr_hi); + + /* Restore the l1 indirect regs for each of the 6 l1s */ + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]); + + /* Restore the l2 indirect regs */ + for (i = 0; i < 0x83; i++) + iommu_write_l2(iommu, i, iommu->stored_l2[i]); + + /* Lock PCI setup registers */ + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, + iommu->stored_addr_lo | 1); +} + +static void iommu_enable_ga(struct amd_iommu *iommu) +{ +#ifdef CONFIG_IRQ_REMAP + switch (amd_iommu_guest_ir) { + case AMD_IOMMU_GUEST_IR_VAPIC: + case AMD_IOMMU_GUEST_IR_LEGACY_GA: + iommu_feature_enable(iommu, CONTROL_GA_EN); + iommu->irte_ops = &irte_128_ops; + break; + default: + iommu->irte_ops = &irte_32_ops; + break; + } +#endif +} + +static void iommu_disable_irtcachedis(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); +} + +static void iommu_enable_irtcachedis(struct amd_iommu *iommu) +{ + u64 ctrl; + + if (!amd_iommu_irtcachedis) + return; + + /* + * Note: + * The support for IRTCacheDis feature is dertermined by + * checking if the bit is writable. + */ + iommu_feature_enable(iommu, CONTROL_IRTCACHEDIS); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= (1ULL << CONTROL_IRTCACHEDIS); + if (ctrl) + iommu->irtcachedis_enabled = true; + pr_info("iommu%d (%#06x) : IRT cache is %s\n", + iommu->index, iommu->devid, + iommu->irtcachedis_enabled ? "disabled" : "enabled"); +} + +static void early_enable_iommu(struct amd_iommu *iommu) +{ + iommu_disable(iommu); + iommu_init_flags(iommu); + iommu_set_device_table(iommu); + iommu_enable_command_buffer(iommu); + iommu_enable_event_buffer(iommu); + iommu_set_exclusion_range(iommu); + iommu_enable_ga(iommu); + iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); + iommu_enable(iommu); + iommu_flush_all_caches(iommu); +} + +/* + * This function finally enables all IOMMUs found in the system after + * they have been initialized. + * + * Or if in kdump kernel and IOMMUs are all pre-enabled, try to copy + * the old content of device table entries. Not this case or copy failed, + * just continue as normal kernel does. + */ +static void early_enable_iommus(void) +{ + struct amd_iommu *iommu; + struct amd_iommu_pci_seg *pci_seg; + + if (!copy_device_table()) { + /* + * If come here because of failure in copying device table from old + * kernel with all IOMMUs enabled, print error message and try to + * free allocated old_dev_tbl_cpy. + */ + if (amd_iommu_pre_enabled) + pr_err("Failed to copy DEV table from previous kernel.\n"); + + for_each_pci_segment(pci_seg) { + if (pci_seg->old_dev_tbl_cpy != NULL) { + free_pages((unsigned long)pci_seg->old_dev_tbl_cpy, + get_order(pci_seg->dev_table_size)); + pci_seg->old_dev_tbl_cpy = NULL; + } + } + + for_each_iommu(iommu) { + clear_translation_pre_enabled(iommu); + early_enable_iommu(iommu); + } + } else { + pr_info("Copied DEV table from previous kernel.\n"); + + for_each_pci_segment(pci_seg) { + free_pages((unsigned long)pci_seg->dev_table, + get_order(pci_seg->dev_table_size)); + pci_seg->dev_table = pci_seg->old_dev_tbl_cpy; + } + + for_each_iommu(iommu) { + iommu_disable_command_buffer(iommu); + iommu_disable_event_buffer(iommu); + iommu_disable_irtcachedis(iommu); + iommu_enable_command_buffer(iommu); + iommu_enable_event_buffer(iommu); + iommu_enable_ga(iommu); + iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); + iommu_set_device_table(iommu); + iommu_flush_all_caches(iommu); + } + } +} + +static void enable_iommus_v2(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + iommu_enable_ppr_log(iommu); + iommu_enable_gt(iommu); + } +} + +static void enable_iommus_vapic(void) +{ +#ifdef CONFIG_IRQ_REMAP + u32 status, i; + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + /* + * Disable GALog if already running. It could have been enabled + * in the previous boot before kdump. + */ + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (!(status & MMIO_STATUS_GALOG_RUN_MASK)) + continue; + + iommu_feature_disable(iommu, CONTROL_GALOG_EN); + iommu_feature_disable(iommu, CONTROL_GAINT_EN); + + /* + * Need to set and poll check the GALOGRun bit to zero before + * we can set/ modify GA Log registers safely. + */ + for (i = 0; i < LOOP_TIMEOUT; ++i) { + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (!(status & MMIO_STATUS_GALOG_RUN_MASK)) + break; + udelay(10); + } + + if (WARN_ON(i >= LOOP_TIMEOUT)) + return; + } + + if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) && + !check_feature_on_all_iommus(FEATURE_GAM_VAPIC)) { + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA; + return; + } + + if (amd_iommu_snp_en && + !FEATURE_SNPAVICSUP_GAM(amd_iommu_efr2)) { + pr_warn("Force to disable Virtual APIC due to SNP\n"); + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA; + return; + } + + /* Enabling GAM and SNPAVIC support */ + for_each_iommu(iommu) { + if (iommu_init_ga_log(iommu) || + iommu_ga_log_enable(iommu)) + return; + + iommu_feature_enable(iommu, CONTROL_GAM_EN); + if (amd_iommu_snp_en) + iommu_feature_enable(iommu, CONTROL_SNPAVIC_EN); + } + + amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP); + pr_info("Virtual APIC enabled\n"); +#endif +} + +static void enable_iommus(void) +{ + early_enable_iommus(); + enable_iommus_vapic(); + enable_iommus_v2(); +} + +static void disable_iommus(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) + iommu_disable(iommu); + +#ifdef CONFIG_IRQ_REMAP + if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) + amd_iommu_irq_ops.capability &= ~(1 << IRQ_POSTING_CAP); +#endif +} + +/* + * Suspend/Resume support + * disable suspend until real resume implemented + */ + +static void amd_iommu_resume(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) + iommu_apply_resume_quirks(iommu); + + /* re-load the hardware */ + enable_iommus(); + + amd_iommu_enable_interrupts(); +} + +static int amd_iommu_suspend(void) +{ + /* disable IOMMUs to go out of the way for BIOS */ + disable_iommus(); + + return 0; +} + +static struct syscore_ops amd_iommu_syscore_ops = { + .suspend = amd_iommu_suspend, + .resume = amd_iommu_resume, +}; + +static void __init free_iommu_resources(void) +{ + kmem_cache_destroy(amd_iommu_irq_cache); + amd_iommu_irq_cache = NULL; + + free_iommu_all(); + free_pci_segments(); +} + +/* SB IOAPIC is always on this device in AMD systems */ +#define IOAPIC_SB_DEVID ((0x00 << 8) | PCI_DEVFN(0x14, 0)) + +static bool __init check_ioapic_information(void) +{ + const char *fw_bug = FW_BUG; + bool ret, has_sb_ioapic; + int idx; + + has_sb_ioapic = false; + ret = false; + + /* + * If we have map overrides on the kernel command line the + * messages in this function might not describe firmware bugs + * anymore - so be careful + */ + if (cmdline_maps) + fw_bug = ""; + + for (idx = 0; idx < nr_ioapics; idx++) { + int devid, id = mpc_ioapic_id(idx); + + devid = get_ioapic_devid(id); + if (devid < 0) { + pr_err("%s: IOAPIC[%d] not in IVRS table\n", + fw_bug, id); + ret = false; + } else if (devid == IOAPIC_SB_DEVID) { + has_sb_ioapic = true; + ret = true; + } + } + + if (!has_sb_ioapic) { + /* + * We expect the SB IOAPIC to be listed in the IVRS + * table. The system timer is connected to the SB IOAPIC + * and if we don't have it in the list the system will + * panic at boot time. This situation usually happens + * when the BIOS is buggy and provides us the wrong + * device id for the IOAPIC in the system. + */ + pr_err("%s: No southbridge IOAPIC found\n", fw_bug); + } + + if (!ret) + pr_err("Disabling interrupt remapping\n"); + + return ret; +} + +static void __init free_dma_resources(void) +{ + free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, + get_order(MAX_DOMAIN_ID/8)); + amd_iommu_pd_alloc_bitmap = NULL; + + free_unity_maps(); +} + +static void __init ivinfo_init(void *ivrs) +{ + amd_iommu_ivinfo = *((u32 *)(ivrs + IOMMU_IVINFO_OFFSET)); +} + +/* + * This is the hardware init function for AMD IOMMU in the system. + * This function is called either from amd_iommu_init or from the interrupt + * remapping setup code. + * + * This function basically parses the ACPI table for AMD IOMMU (IVRS) + * four times: + * + * 1 pass) Discover the most comprehensive IVHD type to use. + * + * 2 pass) Find the highest PCI device id the driver has to handle. + * Upon this information the size of the data structures is + * determined that needs to be allocated. + * + * 3 pass) Initialize the data structures just allocated with the + * information in the ACPI table about available AMD IOMMUs + * in the system. It also maps the PCI devices in the + * system to specific IOMMUs + * + * 4 pass) After the basic data structures are allocated and + * initialized we update them with information about memory + * remapping requirements parsed out of the ACPI table in + * this last pass. + * + * After everything is set up the IOMMUs are enabled and the necessary + * hotplug and suspend notifiers are registered. + */ +static int __init early_amd_iommu_init(void) +{ + struct acpi_table_header *ivrs_base; + int remap_cache_sz, ret; + acpi_status status; + + if (!amd_iommu_detected) + return -ENODEV; + + status = acpi_get_table("IVRS", 0, &ivrs_base); + if (status == AE_NOT_FOUND) + return -ENODEV; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("IVRS table error: %s\n", err); + return -EINVAL; + } + + /* + * Validate checksum here so we don't need to do it when + * we actually parse the table + */ + ret = check_ivrs_checksum(ivrs_base); + if (ret) + goto out; + + ivinfo_init(ivrs_base); + + amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base); + DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type); + + /* Device table - directly used by all IOMMUs */ + ret = -ENOMEM; + + amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, + get_order(MAX_DOMAIN_ID/8)); + if (amd_iommu_pd_alloc_bitmap == NULL) + goto out; + + /* + * never allocate domain 0 because its used as the non-allocated and + * error value placeholder + */ + __set_bit(0, amd_iommu_pd_alloc_bitmap); + + /* + * now the data structures are allocated and basically initialized + * start the real acpi table scan + */ + ret = init_iommu_all(ivrs_base); + if (ret) + goto out; + + /* Disable any previously enabled IOMMUs */ + if (!is_kdump_kernel() || amd_iommu_disabled) + disable_iommus(); + + if (amd_iommu_irq_remap) + amd_iommu_irq_remap = check_ioapic_information(); + + if (amd_iommu_irq_remap) { + struct amd_iommu_pci_seg *pci_seg; + /* + * Interrupt remapping enabled, create kmem_cache for the + * remapping tables. + */ + ret = -ENOMEM; + if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + remap_cache_sz = MAX_IRQS_PER_TABLE * sizeof(u32); + else + remap_cache_sz = MAX_IRQS_PER_TABLE * (sizeof(u64) * 2); + amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache", + remap_cache_sz, + DTE_INTTAB_ALIGNMENT, + 0, NULL); + if (!amd_iommu_irq_cache) + goto out; + + for_each_pci_segment(pci_seg) { + if (alloc_irq_lookup_table(pci_seg)) + goto out; + } + } + + ret = init_memory_definitions(ivrs_base); + if (ret) + goto out; + + /* init the device table */ + init_device_table(); + +out: + /* Don't leak any ACPI memory */ + acpi_put_table(ivrs_base); + + return ret; +} + +static int amd_iommu_enable_interrupts(void) +{ + struct amd_iommu *iommu; + int ret = 0; + + for_each_iommu(iommu) { + ret = iommu_init_irq(iommu); + if (ret) + goto out; + } + +out: + return ret; +} + +static bool __init detect_ivrs(void) +{ + struct acpi_table_header *ivrs_base; + acpi_status status; + int i; + + status = acpi_get_table("IVRS", 0, &ivrs_base); + if (status == AE_NOT_FOUND) + return false; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("IVRS table error: %s\n", err); + return false; + } + + acpi_put_table(ivrs_base); + + if (amd_iommu_force_enable) + goto out; + + /* Don't use IOMMU if there is Stoney Ridge graphics */ + for (i = 0; i < 32; i++) { + u32 pci_id; + + pci_id = read_pci_config(0, i, 0, 0); + if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { + pr_info("Disable IOMMU on Stoney Ridge\n"); + return false; + } + } + +out: + /* Make sure ACS will be enabled during PCI probe */ + pci_request_acs(); + + return true; +} + +/**************************************************************************** + * + * AMD IOMMU Initialization State Machine + * + ****************************************************************************/ + +static int __init state_next(void) +{ + int ret = 0; + + switch (init_state) { + case IOMMU_START_STATE: + if (!detect_ivrs()) { + init_state = IOMMU_NOT_FOUND; + ret = -ENODEV; + } else { + init_state = IOMMU_IVRS_DETECTED; + } + break; + case IOMMU_IVRS_DETECTED: + if (amd_iommu_disabled) { + init_state = IOMMU_CMDLINE_DISABLED; + ret = -EINVAL; + } else { + ret = early_amd_iommu_init(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; + } + break; + case IOMMU_ACPI_FINISHED: + early_enable_iommus(); + x86_platform.iommu_shutdown = disable_iommus; + init_state = IOMMU_ENABLED; + break; + case IOMMU_ENABLED: + register_syscore_ops(&amd_iommu_syscore_ops); + ret = amd_iommu_init_pci(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; + enable_iommus_vapic(); + enable_iommus_v2(); + break; + case IOMMU_PCI_INIT: + ret = amd_iommu_enable_interrupts(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN; + break; + case IOMMU_INTERRUPTS_EN: + init_state = IOMMU_INITIALIZED; + break; + case IOMMU_INITIALIZED: + /* Nothing to do */ + break; + case IOMMU_NOT_FOUND: + case IOMMU_INIT_ERROR: + case IOMMU_CMDLINE_DISABLED: + /* Error states => do nothing */ + ret = -EINVAL; + break; + default: + /* Unknown state */ + BUG(); + } + + if (ret) { + free_dma_resources(); + if (!irq_remapping_enabled) { + disable_iommus(); + free_iommu_resources(); + } else { + struct amd_iommu *iommu; + struct amd_iommu_pci_seg *pci_seg; + + for_each_pci_segment(pci_seg) + uninit_device_table_dma(pci_seg); + + for_each_iommu(iommu) + iommu_flush_all_caches(iommu); + } + } + return ret; +} + +static int __init iommu_go_to_state(enum iommu_init_state state) +{ + int ret = -EINVAL; + + while (init_state != state) { + if (init_state == IOMMU_NOT_FOUND || + init_state == IOMMU_INIT_ERROR || + init_state == IOMMU_CMDLINE_DISABLED) + break; + ret = state_next(); + } + + return ret; +} + +#ifdef CONFIG_IRQ_REMAP +int __init amd_iommu_prepare(void) +{ + int ret; + + amd_iommu_irq_remap = true; + + ret = iommu_go_to_state(IOMMU_ACPI_FINISHED); + if (ret) { + amd_iommu_irq_remap = false; + return ret; + } + + return amd_iommu_irq_remap ? 0 : -ENODEV; +} + +int __init amd_iommu_enable(void) +{ + int ret; + + ret = iommu_go_to_state(IOMMU_ENABLED); + if (ret) + return ret; + + irq_remapping_enabled = 1; + return amd_iommu_xt_mode; +} + +void amd_iommu_disable(void) +{ + amd_iommu_suspend(); +} + +int amd_iommu_reenable(int mode) +{ + amd_iommu_resume(); + + return 0; +} + +int __init amd_iommu_enable_faulting(void) +{ + /* We enable MSI later when PCI is initialized */ + return 0; +} +#endif + +/* + * This is the core init function for AMD IOMMU hardware in the system. + * This function is called from the generic x86 DMA layer initialization + * code. + */ +static int __init amd_iommu_init(void) +{ + struct amd_iommu *iommu; + int ret; + + ret = iommu_go_to_state(IOMMU_INITIALIZED); +#ifdef CONFIG_GART_IOMMU + if (ret && list_empty(&amd_iommu_list)) { + /* + * We failed to initialize the AMD IOMMU - try fallback + * to GART if possible. + */ + gart_iommu_init(); + } +#endif + + for_each_iommu(iommu) + amd_iommu_debugfs_setup(iommu); + + return ret; +} + +static bool amd_iommu_sme_check(void) +{ + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) || + (boot_cpu_data.x86 != 0x17)) + return true; + + /* For Fam17h, a specific level of support is required */ + if (boot_cpu_data.microcode >= 0x08001205) + return true; + + if ((boot_cpu_data.microcode >= 0x08001126) && + (boot_cpu_data.microcode <= 0x080011ff)) + return true; + + pr_notice("IOMMU not currently supported when SME is active\n"); + + return false; +} + +/**************************************************************************** + * + * Early detect code. This code runs at IOMMU detection time in the DMA + * layer. It just looks if there is an IVRS ACPI table to detect AMD + * IOMMUs + * + ****************************************************************************/ +int __init amd_iommu_detect(void) +{ + int ret; + + if (no_iommu || (iommu_detected && !gart_iommu_aperture)) + return -ENODEV; + + if (!amd_iommu_sme_check()) + return -ENODEV; + + ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); + if (ret) + return ret; + + amd_iommu_detected = true; + iommu_detected = 1; + x86_init.iommu.iommu_init = amd_iommu_init; + + return 1; +} + +/**************************************************************************** + * + * Parsing functions for the AMD IOMMU specific kernel command line + * options. + * + ****************************************************************************/ + +static int __init parse_amd_iommu_dump(char *str) +{ + amd_iommu_dump = true; + + return 1; +} + +static int __init parse_amd_iommu_intr(char *str) +{ + for (; *str; ++str) { + if (strncmp(str, "legacy", 6) == 0) { + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA; + break; + } + if (strncmp(str, "vapic", 5) == 0) { + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC; + break; + } + } + return 1; +} + +static int __init parse_amd_iommu_options(char *str) +{ + if (!str) + return -EINVAL; + + while (*str) { + if (strncmp(str, "fullflush", 9) == 0) { + pr_warn("amd_iommu=fullflush deprecated; use iommu.strict=1 instead\n"); + iommu_set_dma_strict(); + } else if (strncmp(str, "force_enable", 12) == 0) { + amd_iommu_force_enable = true; + } else if (strncmp(str, "off", 3) == 0) { + amd_iommu_disabled = true; + } else if (strncmp(str, "force_isolation", 15) == 0) { + amd_iommu_force_isolation = true; + } else if (strncmp(str, "pgtbl_v1", 8) == 0) { + amd_iommu_pgtable = AMD_IOMMU_V1; + } else if (strncmp(str, "pgtbl_v2", 8) == 0) { + amd_iommu_pgtable = AMD_IOMMU_V2; + } else if (strncmp(str, "irtcachedis", 11) == 0) { + amd_iommu_irtcachedis = true; + } else { + pr_notice("Unknown option - '%s'\n", str); + } + + str += strcspn(str, ","); + while (*str == ',') + str++; + } + + return 1; +} + +static int __init parse_ivrs_ioapic(char *str) +{ + u32 seg = 0, bus, dev, fn; + int id, i; + u32 devid; + + if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) + goto found; + + if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) { + pr_warn("ivrs_ioapic%s option format deprecated; use ivrs_ioapic=%d@%04x:%02x:%02x.%d instead\n", + str, id, seg, bus, dev, fn); + goto found; + } + + pr_err("Invalid command line: ivrs_ioapic%s\n", str); + return 1; + +found: + if (early_ioapic_map_size == EARLY_MAP_SIZE) { + pr_err("Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n", + str); + return 1; + } + + devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); + + cmdline_maps = true; + i = early_ioapic_map_size++; + early_ioapic_map[i].id = id; + early_ioapic_map[i].devid = devid; + early_ioapic_map[i].cmd_line = true; + + return 1; +} + +static int __init parse_ivrs_hpet(char *str) +{ + u32 seg = 0, bus, dev, fn; + int id, i; + u32 devid; + + if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) + goto found; + + if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) { + pr_warn("ivrs_hpet%s option format deprecated; use ivrs_hpet=%d@%04x:%02x:%02x.%d instead\n", + str, id, seg, bus, dev, fn); + goto found; + } + + pr_err("Invalid command line: ivrs_hpet%s\n", str); + return 1; + +found: + if (early_hpet_map_size == EARLY_MAP_SIZE) { + pr_err("Early HPET map overflow - ignoring ivrs_hpet%s\n", + str); + return 1; + } + + devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); + + cmdline_maps = true; + i = early_hpet_map_size++; + early_hpet_map[i].id = id; + early_hpet_map[i].devid = devid; + early_hpet_map[i].cmd_line = true; + + return 1; +} + +#define ACPIID_LEN (ACPIHID_UID_LEN + ACPIHID_HID_LEN) + +static int __init parse_ivrs_acpihid(char *str) +{ + u32 seg = 0, bus, dev, fn; + char *hid, *uid, *p, *addr; + char acpiid[ACPIID_LEN] = {0}; + int i; + + addr = strchr(str, '@'); + if (!addr) { + addr = strchr(str, '='); + if (!addr) + goto not_found; + + ++addr; + + if (strlen(addr) > ACPIID_LEN) + goto not_found; + + if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 || + sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) { + pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n", + str, acpiid, seg, bus, dev, fn); + goto found; + } + goto not_found; + } + + /* We have the '@', make it the terminator to get just the acpiid */ + *addr++ = 0; + + if (strlen(str) > ACPIID_LEN + 1) + goto not_found; + + if (sscanf(str, "=%s", acpiid) != 1) + goto not_found; + + if (sscanf(addr, "%x:%x.%x", &bus, &dev, &fn) == 3 || + sscanf(addr, "%x:%x:%x.%x", &seg, &bus, &dev, &fn) == 4) + goto found; + +not_found: + pr_err("Invalid command line: ivrs_acpihid%s\n", str); + return 1; + +found: + p = acpiid; + hid = strsep(&p, ":"); + uid = p; + + if (!hid || !(*hid) || !uid) { + pr_err("Invalid command line: hid or uid\n"); + return 1; + } + + /* + * Ignore leading zeroes after ':', so e.g., AMDI0095:00 + * will match AMDI0095:0 in the second strcmp in acpi_dev_hid_uid_match + */ + while (*uid == '0' && *(uid + 1)) + uid++; + + i = early_acpihid_map_size++; + memcpy(early_acpihid_map[i].hid, hid, strlen(hid)); + memcpy(early_acpihid_map[i].uid, uid, strlen(uid)); + early_acpihid_map[i].devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); + early_acpihid_map[i].cmd_line = true; + + return 1; +} + +__setup("amd_iommu_dump", parse_amd_iommu_dump); +__setup("amd_iommu=", parse_amd_iommu_options); +__setup("amd_iommu_intr=", parse_amd_iommu_intr); +__setup("ivrs_ioapic", parse_ivrs_ioapic); +__setup("ivrs_hpet", parse_ivrs_hpet); +__setup("ivrs_acpihid", parse_ivrs_acpihid); + +bool amd_iommu_v2_supported(void) +{ + /* + * Since DTE[Mode]=0 is prohibited on SNP-enabled system + * (i.e. EFR[SNPSup]=1), IOMMUv2 page table cannot be used without + * setting up IOMMUv1 page table. + */ + return amd_iommu_v2_present && !amd_iommu_snp_en; +} +EXPORT_SYMBOL(amd_iommu_v2_supported); + +struct amd_iommu *get_amd_iommu(unsigned int idx) +{ + unsigned int i = 0; + struct amd_iommu *iommu; + + for_each_iommu(iommu) + if (i++ == idx) + return iommu; + return NULL; +} + +/**************************************************************************** + * + * IOMMU EFR Performance Counter support functionality. This code allows + * access to the IOMMU PC functionality. + * + ****************************************************************************/ + +u8 amd_iommu_pc_get_max_banks(unsigned int idx) +{ + struct amd_iommu *iommu = get_amd_iommu(idx); + + if (iommu) + return iommu->max_banks; + + return 0; +} +EXPORT_SYMBOL(amd_iommu_pc_get_max_banks); + +bool amd_iommu_pc_supported(void) +{ + return amd_iommu_pc_present; +} +EXPORT_SYMBOL(amd_iommu_pc_supported); + +u8 amd_iommu_pc_get_max_counters(unsigned int idx) +{ + struct amd_iommu *iommu = get_amd_iommu(idx); + + if (iommu) + return iommu->max_counters; + + return 0; +} +EXPORT_SYMBOL(amd_iommu_pc_get_max_counters); + +static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value, bool is_write) +{ + u32 offset; + u32 max_offset_lim; + + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_present) + return -ENODEV; + + /* Check for valid iommu and pc register indexing */ + if (WARN_ON(!iommu || (fxn > 0x28) || (fxn & 7))) + return -ENODEV; + + offset = (u32)(((0x40 | bank) << 12) | (cntr << 8) | fxn); + + /* Limit the offset to the hw defined mmio region aperture */ + max_offset_lim = (u32)(((0x40 | iommu->max_banks) << 12) | + (iommu->max_counters << 8) | 0x28); + if ((offset < MMIO_CNTR_REG_OFFSET) || + (offset > max_offset_lim)) + return -EINVAL; + + if (is_write) { + u64 val = *value & GENMASK_ULL(47, 0); + + writel((u32)val, iommu->mmio_base + offset); + writel((val >> 32), iommu->mmio_base + offset + 4); + } else { + *value = readl(iommu->mmio_base + offset + 4); + *value <<= 32; + *value |= readl(iommu->mmio_base + offset); + *value &= GENMASK_ULL(47, 0); + } + + return 0; +} + +int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value) +{ + if (!iommu) + return -EINVAL; + + return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false); +} + +int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value) +{ + if (!iommu) + return -EINVAL; + + return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true); +} + +#ifdef CONFIG_AMD_MEM_ENCRYPT +int amd_iommu_snp_enable(void) +{ + /* + * The SNP support requires that IOMMU must be enabled, and is + * not configured in the passthrough mode. + */ + if (no_iommu || iommu_default_passthrough()) { + pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported"); + return -EINVAL; + } + + /* + * Prevent enabling SNP after IOMMU_ENABLED state because this process + * affect how IOMMU driver sets up data structures and configures + * IOMMU hardware. + */ + if (init_state > IOMMU_ENABLED) { + pr_err("SNP: Too late to enable SNP for IOMMU.\n"); + return -EINVAL; + } + + amd_iommu_snp_en = check_feature_on_all_iommus(FEATURE_SNP); + if (!amd_iommu_snp_en) + return -EINVAL; + + pr_info("SNP enabled\n"); + + /* Enforce IOMMU v1 pagetable when SNP is enabled. */ + if (amd_iommu_pgtable != AMD_IOMMU_V1) { + pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n"); + amd_iommu_pgtable = AMD_IOMMU_V1; + } + + return 0; +} +#endif diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c new file mode 100644 index 000000000..ace0e9b8b --- /dev/null +++ b/drivers/iommu/amd/io_pgtable.c @@ -0,0 +1,537 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CPU-agnostic AMD IO page table allocator. + * + * Copyright (C) 2020 Advanced Micro Devices, Inc. + * Author: Suravee Suthikulpanit + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "amd_iommu_types.h" +#include "amd_iommu.h" + +static void v1_tlb_flush_all(void *cookie) +{ +} + +static void v1_tlb_flush_walk(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ +} + +static void v1_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) +{ +} + +static const struct iommu_flush_ops v1_flush_ops = { + .tlb_flush_all = v1_tlb_flush_all, + .tlb_flush_walk = v1_tlb_flush_walk, + .tlb_add_page = v1_tlb_add_page, +}; + +/* + * Helper function to get the first pte of a large mapping + */ +static u64 *first_pte_l7(u64 *pte, unsigned long *page_size, + unsigned long *count) +{ + unsigned long pte_mask, pg_size, cnt; + u64 *fpte; + + pg_size = PTE_PAGE_SIZE(*pte); + cnt = PAGE_SIZE_PTE_COUNT(pg_size); + pte_mask = ~((cnt << 3) - 1); + fpte = (u64 *)(((unsigned long)pte) & pte_mask); + + if (page_size) + *page_size = pg_size; + + if (count) + *count = cnt; + + return fpte; +} + +/**************************************************************************** + * + * The functions below are used the create the page table mappings for + * unity mapped regions. + * + ****************************************************************************/ + +static void free_pt_page(u64 *pt, struct list_head *freelist) +{ + struct page *p = virt_to_page(pt); + + list_add_tail(&p->lru, freelist); +} + +static void free_pt_lvl(u64 *pt, struct list_head *freelist, int lvl) +{ + u64 *p; + int i; + + for (i = 0; i < 512; ++i) { + /* PTE present? */ + if (!IOMMU_PTE_PRESENT(pt[i])) + continue; + + /* Large PTE? */ + if (PM_PTE_LEVEL(pt[i]) == 0 || + PM_PTE_LEVEL(pt[i]) == 7) + continue; + + /* + * Free the next level. No need to look at l1 tables here since + * they can only contain leaf PTEs; just free them directly. + */ + p = IOMMU_PTE_PAGE(pt[i]); + if (lvl > 2) + free_pt_lvl(p, freelist, lvl - 1); + else + free_pt_page(p, freelist); + } + + free_pt_page(pt, freelist); +} + +static void free_sub_pt(u64 *root, int mode, struct list_head *freelist) +{ + switch (mode) { + case PAGE_MODE_NONE: + case PAGE_MODE_7_LEVEL: + break; + case PAGE_MODE_1_LEVEL: + free_pt_page(root, freelist); + break; + case PAGE_MODE_2_LEVEL: + case PAGE_MODE_3_LEVEL: + case PAGE_MODE_4_LEVEL: + case PAGE_MODE_5_LEVEL: + case PAGE_MODE_6_LEVEL: + free_pt_lvl(root, freelist, mode); + break; + default: + BUG(); + } +} + +void amd_iommu_domain_set_pgtable(struct protection_domain *domain, + u64 *root, int mode) +{ + u64 pt_root; + + /* lowest 3 bits encode pgtable mode */ + pt_root = mode & 7; + pt_root |= (u64)root; + + amd_iommu_domain_set_pt_root(domain, pt_root); +} + +/* + * This function is used to add another level to an IO page table. Adding + * another level increases the size of the address space by 9 bits to a size up + * to 64 bits. + */ +static bool increase_address_space(struct protection_domain *domain, + unsigned long address, + gfp_t gfp) +{ + unsigned long flags; + bool ret = true; + u64 *pte; + + pte = (void *)get_zeroed_page(gfp); + if (!pte) + return false; + + spin_lock_irqsave(&domain->lock, flags); + + if (address <= PM_LEVEL_SIZE(domain->iop.mode)) + goto out; + + ret = false; + if (WARN_ON_ONCE(domain->iop.mode == PAGE_MODE_6_LEVEL)) + goto out; + + *pte = PM_LEVEL_PDE(domain->iop.mode, iommu_virt_to_phys(domain->iop.root)); + + domain->iop.root = pte; + domain->iop.mode += 1; + amd_iommu_update_and_flush_device_table(domain); + amd_iommu_domain_flush_complete(domain); + + /* + * Device Table needs to be updated and flushed before the new root can + * be published. + */ + amd_iommu_domain_set_pgtable(domain, pte, domain->iop.mode); + + pte = NULL; + ret = true; + +out: + spin_unlock_irqrestore(&domain->lock, flags); + free_page((unsigned long)pte); + + return ret; +} + +static u64 *alloc_pte(struct protection_domain *domain, + unsigned long address, + unsigned long page_size, + u64 **pte_page, + gfp_t gfp, + bool *updated) +{ + int level, end_lvl; + u64 *pte, *page; + + BUG_ON(!is_power_of_2(page_size)); + + while (address > PM_LEVEL_SIZE(domain->iop.mode)) { + /* + * Return an error if there is no memory to update the + * page-table. + */ + if (!increase_address_space(domain, address, gfp)) + return NULL; + } + + + level = domain->iop.mode - 1; + pte = &domain->iop.root[PM_LEVEL_INDEX(level, address)]; + address = PAGE_SIZE_ALIGN(address, page_size); + end_lvl = PAGE_SIZE_LEVEL(page_size); + + while (level > end_lvl) { + u64 __pte, __npte; + int pte_level; + + __pte = *pte; + pte_level = PM_PTE_LEVEL(__pte); + + /* + * If we replace a series of large PTEs, we need + * to tear down all of them. + */ + if (IOMMU_PTE_PRESENT(__pte) && + pte_level == PAGE_MODE_7_LEVEL) { + unsigned long count, i; + u64 *lpte; + + lpte = first_pte_l7(pte, NULL, &count); + + /* + * Unmap the replicated PTEs that still match the + * original large mapping + */ + for (i = 0; i < count; ++i) + cmpxchg64(&lpte[i], __pte, 0ULL); + + *updated = true; + continue; + } + + if (!IOMMU_PTE_PRESENT(__pte) || + pte_level == PAGE_MODE_NONE) { + page = (u64 *)get_zeroed_page(gfp); + + if (!page) + return NULL; + + __npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page)); + + /* pte could have been changed somewhere. */ + if (!try_cmpxchg64(pte, &__pte, __npte)) + free_page((unsigned long)page); + else if (IOMMU_PTE_PRESENT(__pte)) + *updated = true; + + continue; + } + + /* No level skipping support yet */ + if (pte_level != level) + return NULL; + + level -= 1; + + pte = IOMMU_PTE_PAGE(__pte); + + if (pte_page && level == end_lvl) + *pte_page = pte; + + pte = &pte[PM_LEVEL_INDEX(level, address)]; + } + + return pte; +} + +/* + * This function checks if there is a PTE for a given dma address. If + * there is one, it returns the pointer to it. + */ +static u64 *fetch_pte(struct amd_io_pgtable *pgtable, + unsigned long address, + unsigned long *page_size) +{ + int level; + u64 *pte; + + *page_size = 0; + + if (address > PM_LEVEL_SIZE(pgtable->mode)) + return NULL; + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + *page_size = PTE_LEVEL_PAGE_SIZE(level); + + while (level > 0) { + + /* Not Present */ + if (!IOMMU_PTE_PRESENT(*pte)) + return NULL; + + /* Large PTE */ + if (PM_PTE_LEVEL(*pte) == 7 || + PM_PTE_LEVEL(*pte) == 0) + break; + + /* No level skipping support yet */ + if (PM_PTE_LEVEL(*pte) != level) + return NULL; + + level -= 1; + + /* Walk to the next level */ + pte = IOMMU_PTE_PAGE(*pte); + pte = &pte[PM_LEVEL_INDEX(level, address)]; + *page_size = PTE_LEVEL_PAGE_SIZE(level); + } + + /* + * If we have a series of large PTEs, make + * sure to return a pointer to the first one. + */ + if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL) + pte = first_pte_l7(pte, page_size, NULL); + + return pte; +} + +static void free_clear_pte(u64 *pte, u64 pteval, struct list_head *freelist) +{ + u64 *pt; + int mode; + + while (!try_cmpxchg64(pte, &pteval, 0)) + pr_warn("AMD-Vi: IOMMU pte changed since we read it\n"); + + if (!IOMMU_PTE_PRESENT(pteval)) + return; + + pt = IOMMU_PTE_PAGE(pteval); + mode = IOMMU_PTE_MODE(pteval); + + free_sub_pt(pt, mode, freelist); +} + +/* + * Generic mapping functions. It maps a physical address into a DMA + * address space. It allocates the page table pages if necessary. + * In the future it can be extended to a generic mapping function + * supporting all features of AMD IOMMU page tables like level skipping + * and full 64 bit address spaces. + */ +static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) +{ + struct protection_domain *dom = io_pgtable_ops_to_domain(ops); + LIST_HEAD(freelist); + bool updated = false; + u64 __pte, *pte; + int ret, i, count; + + BUG_ON(!IS_ALIGNED(iova, pgsize)); + BUG_ON(!IS_ALIGNED(paddr, pgsize)); + + ret = -EINVAL; + if (!(prot & IOMMU_PROT_MASK)) + goto out; + + while (pgcount > 0) { + count = PAGE_SIZE_PTE_COUNT(pgsize); + pte = alloc_pte(dom, iova, pgsize, NULL, gfp, &updated); + + ret = -ENOMEM; + if (!pte) + goto out; + + for (i = 0; i < count; ++i) + free_clear_pte(&pte[i], pte[i], &freelist); + + if (!list_empty(&freelist)) + updated = true; + + if (count > 1) { + __pte = PAGE_SIZE_PTE(__sme_set(paddr), pgsize); + __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_PR | IOMMU_PTE_FC; + } else + __pte = __sme_set(paddr) | IOMMU_PTE_PR | IOMMU_PTE_FC; + + if (prot & IOMMU_PROT_IR) + __pte |= IOMMU_PTE_IR; + if (prot & IOMMU_PROT_IW) + __pte |= IOMMU_PTE_IW; + + for (i = 0; i < count; ++i) + pte[i] = __pte; + + iova += pgsize; + paddr += pgsize; + pgcount--; + if (mapped) + *mapped += pgsize; + } + + ret = 0; + +out: + if (updated) { + unsigned long flags; + + spin_lock_irqsave(&dom->lock, flags); + /* + * Flush domain TLB(s) and wait for completion. Any Device-Table + * Updates and flushing already happened in + * increase_address_space(). + */ + amd_iommu_domain_flush_tlb_pde(dom); + amd_iommu_domain_flush_complete(dom); + spin_unlock_irqrestore(&dom->lock, flags); + } + + /* Everything flushed out, free pages now */ + put_pages_list(&freelist); + + return ret; +} + +static unsigned long iommu_v1_unmap_pages(struct io_pgtable_ops *ops, + unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) +{ + struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); + unsigned long long unmapped; + unsigned long unmap_size; + u64 *pte; + size_t size = pgcount << __ffs(pgsize); + + BUG_ON(!is_power_of_2(pgsize)); + + unmapped = 0; + + while (unmapped < size) { + pte = fetch_pte(pgtable, iova, &unmap_size); + if (pte) { + int i, count; + + count = PAGE_SIZE_PTE_COUNT(unmap_size); + for (i = 0; i < count; i++) + pte[i] = 0ULL; + } else { + return unmapped; + } + + iova = (iova & ~(unmap_size - 1)) + unmap_size; + unmapped += unmap_size; + } + + return unmapped; +} + +static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned long iova) +{ + struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); + unsigned long offset_mask, pte_pgsize; + u64 *pte, __pte; + + pte = fetch_pte(pgtable, iova, &pte_pgsize); + + if (!pte || !IOMMU_PTE_PRESENT(*pte)) + return 0; + + offset_mask = pte_pgsize - 1; + __pte = __sme_clr(*pte & PM_ADDR_MASK); + + return (__pte & ~offset_mask) | (iova & offset_mask); +} + +/* + * ---------------------------------------------------- + */ +static void v1_free_pgtable(struct io_pgtable *iop) +{ + struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop); + struct protection_domain *dom; + LIST_HEAD(freelist); + + if (pgtable->mode == PAGE_MODE_NONE) + return; + + dom = container_of(pgtable, struct protection_domain, iop); + + /* Page-table is not visible to IOMMU anymore, so free it */ + BUG_ON(pgtable->mode < PAGE_MODE_NONE || + pgtable->mode > PAGE_MODE_6_LEVEL); + + free_sub_pt(pgtable->root, pgtable->mode, &freelist); + + /* Update data structure */ + amd_iommu_domain_clr_pt_root(dom); + + /* Make changes visible to IOMMUs */ + amd_iommu_domain_update(dom); + + put_pages_list(&freelist); +} + +static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); + + cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES, + cfg->ias = IOMMU_IN_ADDR_BIT_SIZE, + cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE, + cfg->tlb = &v1_flush_ops; + + pgtable->iop.ops.map_pages = iommu_v1_map_pages; + pgtable->iop.ops.unmap_pages = iommu_v1_unmap_pages; + pgtable->iop.ops.iova_to_phys = iommu_v1_iova_to_phys; + + return &pgtable->iop; +} + +struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns = { + .alloc = v1_alloc_pgtable, + .free = v1_free_pgtable, +}; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c new file mode 100644 index 000000000..8638ddf6f --- /dev/null +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -0,0 +1,415 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CPU-agnostic AMD IO page table v2 allocator. + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Author: Suravee Suthikulpanit + * Author: Vasant Hegde + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include +#include + +#include + +#include "amd_iommu_types.h" +#include "amd_iommu.h" + +#define IOMMU_PAGE_PRESENT BIT_ULL(0) /* Is present */ +#define IOMMU_PAGE_RW BIT_ULL(1) /* Writeable */ +#define IOMMU_PAGE_USER BIT_ULL(2) /* Userspace addressable */ +#define IOMMU_PAGE_PWT BIT_ULL(3) /* Page write through */ +#define IOMMU_PAGE_PCD BIT_ULL(4) /* Page cache disabled */ +#define IOMMU_PAGE_ACCESS BIT_ULL(5) /* Was accessed (updated by IOMMU) */ +#define IOMMU_PAGE_DIRTY BIT_ULL(6) /* Was written to (updated by IOMMU) */ +#define IOMMU_PAGE_PSE BIT_ULL(7) /* Page Size Extensions */ +#define IOMMU_PAGE_NX BIT_ULL(63) /* No execute */ + +#define MAX_PTRS_PER_PAGE 512 + +#define IOMMU_PAGE_SIZE_2M BIT_ULL(21) +#define IOMMU_PAGE_SIZE_1G BIT_ULL(30) + + +static inline int get_pgtable_level(void) +{ + /* 5 level page table is not supported */ + return PAGE_MODE_4_LEVEL; +} + +static inline bool is_large_pte(u64 pte) +{ + return (pte & IOMMU_PAGE_PSE); +} + +static inline void *alloc_pgtable_page(void) +{ + return (void *)get_zeroed_page(GFP_KERNEL); +} + +static inline u64 set_pgtable_attr(u64 *page) +{ + u64 prot; + + prot = IOMMU_PAGE_PRESENT | IOMMU_PAGE_RW | IOMMU_PAGE_USER; + prot |= IOMMU_PAGE_ACCESS | IOMMU_PAGE_DIRTY; + + return (iommu_virt_to_phys(page) | prot); +} + +static inline void *get_pgtable_pte(u64 pte) +{ + return iommu_phys_to_virt(pte & PM_ADDR_MASK); +} + +static u64 set_pte_attr(u64 paddr, u64 pg_size, int prot) +{ + u64 pte; + + pte = __sme_set(paddr & PM_ADDR_MASK); + pte |= IOMMU_PAGE_PRESENT | IOMMU_PAGE_USER; + pte |= IOMMU_PAGE_ACCESS | IOMMU_PAGE_DIRTY; + + if (prot & IOMMU_PROT_IW) + pte |= IOMMU_PAGE_RW; + + /* Large page */ + if (pg_size == IOMMU_PAGE_SIZE_1G || pg_size == IOMMU_PAGE_SIZE_2M) + pte |= IOMMU_PAGE_PSE; + + return pte; +} + +static inline u64 get_alloc_page_size(u64 size) +{ + if (size >= IOMMU_PAGE_SIZE_1G) + return IOMMU_PAGE_SIZE_1G; + + if (size >= IOMMU_PAGE_SIZE_2M) + return IOMMU_PAGE_SIZE_2M; + + return PAGE_SIZE; +} + +static inline int page_size_to_level(u64 pg_size) +{ + if (pg_size == IOMMU_PAGE_SIZE_1G) + return PAGE_MODE_3_LEVEL; + if (pg_size == IOMMU_PAGE_SIZE_2M) + return PAGE_MODE_2_LEVEL; + + return PAGE_MODE_1_LEVEL; +} + +static inline void free_pgtable_page(u64 *pt) +{ + free_page((unsigned long)pt); +} + +static void free_pgtable(u64 *pt, int level) +{ + u64 *p; + int i; + + for (i = 0; i < MAX_PTRS_PER_PAGE; i++) { + /* PTE present? */ + if (!IOMMU_PTE_PRESENT(pt[i])) + continue; + + if (is_large_pte(pt[i])) + continue; + + /* + * Free the next level. No need to look at l1 tables here since + * they can only contain leaf PTEs; just free them directly. + */ + p = get_pgtable_pte(pt[i]); + if (level > 2) + free_pgtable(p, level - 1); + else + free_pgtable_page(p); + } + + free_pgtable_page(pt); +} + +/* Allocate page table */ +static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova, + unsigned long pg_size, bool *updated) +{ + u64 *pte, *page; + int level, end_level; + + level = get_pgtable_level() - 1; + end_level = page_size_to_level(pg_size); + pte = &pgd[PM_LEVEL_INDEX(level, iova)]; + iova = PAGE_SIZE_ALIGN(iova, PAGE_SIZE); + + while (level >= end_level) { + u64 __pte, __npte; + + __pte = *pte; + + if (IOMMU_PTE_PRESENT(__pte) && is_large_pte(__pte)) { + /* Unmap large pte */ + cmpxchg64(pte, *pte, 0ULL); + *updated = true; + continue; + } + + if (!IOMMU_PTE_PRESENT(__pte)) { + page = alloc_pgtable_page(); + if (!page) + return NULL; + + __npte = set_pgtable_attr(page); + /* pte could have been changed somewhere. */ + if (cmpxchg64(pte, __pte, __npte) != __pte) + free_pgtable_page(page); + else if (IOMMU_PTE_PRESENT(__pte)) + *updated = true; + + continue; + } + + level -= 1; + pte = get_pgtable_pte(__pte); + pte = &pte[PM_LEVEL_INDEX(level, iova)]; + } + + /* Tear down existing pte entries */ + if (IOMMU_PTE_PRESENT(*pte)) { + u64 *__pte; + + *updated = true; + __pte = get_pgtable_pte(*pte); + cmpxchg64(pte, *pte, 0ULL); + if (pg_size == IOMMU_PAGE_SIZE_1G) + free_pgtable(__pte, end_level - 1); + else if (pg_size == IOMMU_PAGE_SIZE_2M) + free_pgtable_page(__pte); + } + + return pte; +} + +/* + * This function checks if there is a PTE for a given dma address. + * If there is one, it returns the pointer to it. + */ +static u64 *fetch_pte(struct amd_io_pgtable *pgtable, + unsigned long iova, unsigned long *page_size) +{ + u64 *pte; + int level; + + level = get_pgtable_level() - 1; + pte = &pgtable->pgd[PM_LEVEL_INDEX(level, iova)]; + /* Default page size is 4K */ + *page_size = PAGE_SIZE; + + while (level) { + /* Not present */ + if (!IOMMU_PTE_PRESENT(*pte)) + return NULL; + + /* Walk to the next level */ + pte = get_pgtable_pte(*pte); + pte = &pte[PM_LEVEL_INDEX(level - 1, iova)]; + + /* Large page */ + if (is_large_pte(*pte)) { + if (level == PAGE_MODE_3_LEVEL) + *page_size = IOMMU_PAGE_SIZE_1G; + else if (level == PAGE_MODE_2_LEVEL) + *page_size = IOMMU_PAGE_SIZE_2M; + else + return NULL; /* Wrongly set PSE bit in PTE */ + + break; + } + + level -= 1; + } + + return pte; +} + +static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) +{ + struct protection_domain *pdom = io_pgtable_ops_to_domain(ops); + struct io_pgtable_cfg *cfg = &pdom->iop.iop.cfg; + u64 *pte; + unsigned long map_size; + unsigned long mapped_size = 0; + unsigned long o_iova = iova; + size_t size = pgcount << __ffs(pgsize); + int count = 0; + int ret = 0; + bool updated = false; + + if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize) || !pgcount) + return -EINVAL; + + if (!(prot & IOMMU_PROT_MASK)) + return -EINVAL; + + while (mapped_size < size) { + map_size = get_alloc_page_size(pgsize); + pte = v2_alloc_pte(pdom->iop.pgd, iova, map_size, &updated); + if (!pte) { + ret = -EINVAL; + goto out; + } + + *pte = set_pte_attr(paddr, map_size, prot); + + count++; + iova += map_size; + paddr += map_size; + mapped_size += map_size; + } + +out: + if (updated) { + if (count > 1) + amd_iommu_flush_tlb(&pdom->domain, 0); + else + amd_iommu_flush_page(&pdom->domain, 0, o_iova); + } + + if (mapped) + *mapped += mapped_size; + + return ret; +} + +static unsigned long iommu_v2_unmap_pages(struct io_pgtable_ops *ops, + unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) +{ + struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); + struct io_pgtable_cfg *cfg = &pgtable->iop.cfg; + unsigned long unmap_size; + unsigned long unmapped = 0; + size_t size = pgcount << __ffs(pgsize); + u64 *pte; + + if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize || !pgcount)) + return 0; + + while (unmapped < size) { + pte = fetch_pte(pgtable, iova, &unmap_size); + if (!pte) + return unmapped; + + *pte = 0ULL; + + iova = (iova & ~(unmap_size - 1)) + unmap_size; + unmapped += unmap_size; + } + + return unmapped; +} + +static phys_addr_t iommu_v2_iova_to_phys(struct io_pgtable_ops *ops, unsigned long iova) +{ + struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); + unsigned long offset_mask, pte_pgsize; + u64 *pte, __pte; + + pte = fetch_pte(pgtable, iova, &pte_pgsize); + if (!pte || !IOMMU_PTE_PRESENT(*pte)) + return 0; + + offset_mask = pte_pgsize - 1; + __pte = __sme_clr(*pte & PM_ADDR_MASK); + + return (__pte & ~offset_mask) | (iova & offset_mask); +} + +/* + * ---------------------------------------------------- + */ +static void v2_tlb_flush_all(void *cookie) +{ +} + +static void v2_tlb_flush_walk(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ +} + +static void v2_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) +{ +} + +static const struct iommu_flush_ops v2_flush_ops = { + .tlb_flush_all = v2_tlb_flush_all, + .tlb_flush_walk = v2_tlb_flush_walk, + .tlb_add_page = v2_tlb_add_page, +}; + +static void v2_free_pgtable(struct io_pgtable *iop) +{ + struct protection_domain *pdom; + struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop); + + pdom = container_of(pgtable, struct protection_domain, iop); + if (!(pdom->flags & PD_IOMMUV2_MASK)) + return; + + /* + * Make changes visible to IOMMUs. No need to clear gcr3 entry + * as gcr3 table is already freed. + */ + amd_iommu_domain_update(pdom); + + /* Free page table */ + free_pgtable(pgtable->pgd, get_pgtable_level()); +} + +static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); + struct protection_domain *pdom = (struct protection_domain *)cookie; + int ret; + + pgtable->pgd = alloc_pgtable_page(); + if (!pgtable->pgd) + return NULL; + + ret = amd_iommu_domain_set_gcr3(&pdom->domain, 0, iommu_virt_to_phys(pgtable->pgd)); + if (ret) + goto err_free_pgd; + + pgtable->iop.ops.map_pages = iommu_v2_map_pages; + pgtable->iop.ops.unmap_pages = iommu_v2_unmap_pages; + pgtable->iop.ops.iova_to_phys = iommu_v2_iova_to_phys; + + cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES_V2, + cfg->ias = IOMMU_IN_ADDR_BIT_SIZE, + cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE, + cfg->tlb = &v2_flush_ops; + + return &pgtable->iop; + +err_free_pgd: + free_pgtable_page(pgtable->pgd); + + return NULL; +} + +struct io_pgtable_init_fns io_pgtable_amd_iommu_v2_init_fns = { + .alloc = v2_alloc_pgtable, + .free = v2_free_pgtable, +}; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c new file mode 100644 index 000000000..5d34416b3 --- /dev/null +++ b/drivers/iommu/amd/iommu.c @@ -0,0 +1,3750 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + * Leo Duran + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "amd_iommu.h" +#include "../dma-iommu.h" +#include "../irq_remapping.h" + +#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28)) + +#define LOOP_TIMEOUT 100000 + +/* IO virtual address start page frame number */ +#define IOVA_START_PFN (1) +#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT) + +/* Reserved IOVA ranges */ +#define MSI_RANGE_START (0xfee00000) +#define MSI_RANGE_END (0xfeefffff) +#define HT_RANGE_START (0xfd00000000ULL) +#define HT_RANGE_END (0xffffffffffULL) + +#define DEFAULT_PGTABLE_LEVEL PAGE_MODE_3_LEVEL + +static DEFINE_SPINLOCK(pd_bitmap_lock); + +LIST_HEAD(ioapic_map); +LIST_HEAD(hpet_map); +LIST_HEAD(acpihid_map); + +const struct iommu_ops amd_iommu_ops; + +static ATOMIC_NOTIFIER_HEAD(ppr_notifier); +int amd_iommu_max_glx_val = -1; + +/* + * general struct to manage commands send to an IOMMU + */ +struct iommu_cmd { + u32 data[4]; +}; + +struct kmem_cache *amd_iommu_irq_cache; + +static void detach_device(struct device *dev); +static int domain_enable_v2(struct protection_domain *domain, int pasids); + +/**************************************************************************** + * + * Helper functions + * + ****************************************************************************/ + +static inline int get_acpihid_device_id(struct device *dev, + struct acpihid_map_entry **entry) +{ + struct acpi_device *adev = ACPI_COMPANION(dev); + struct acpihid_map_entry *p; + + if (!adev) + return -ENODEV; + + list_for_each_entry(p, &acpihid_map, list) { + if (acpi_dev_hid_uid_match(adev, p->hid, + p->uid[0] ? p->uid : NULL)) { + if (entry) + *entry = p; + return p->devid; + } + } + return -EINVAL; +} + +static inline int get_device_sbdf_id(struct device *dev) +{ + int sbdf; + + if (dev_is_pci(dev)) + sbdf = get_pci_sbdf_id(to_pci_dev(dev)); + else + sbdf = get_acpihid_device_id(dev, NULL); + + return sbdf; +} + +struct dev_table_entry *get_dev_table(struct amd_iommu *iommu) +{ + struct dev_table_entry *dev_table; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + BUG_ON(pci_seg == NULL); + dev_table = pci_seg->dev_table; + BUG_ON(dev_table == NULL); + + return dev_table; +} + +static inline u16 get_device_segment(struct device *dev) +{ + u16 seg; + + if (dev_is_pci(dev)) { + struct pci_dev *pdev = to_pci_dev(dev); + + seg = pci_domain_nr(pdev->bus); + } else { + u32 devid = get_acpihid_device_id(dev, NULL); + + seg = PCI_SBDF_TO_SEGID(devid); + } + + return seg; +} + +/* Writes the specific IOMMU for a device into the PCI segment rlookup table */ +void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid) +{ + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + pci_seg->rlookup_table[devid] = iommu; +} + +static struct amd_iommu *__rlookup_amd_iommu(u16 seg, u16 devid) +{ + struct amd_iommu_pci_seg *pci_seg; + + for_each_pci_segment(pci_seg) { + if (pci_seg->id == seg) + return pci_seg->rlookup_table[devid]; + } + return NULL; +} + +static struct amd_iommu *rlookup_amd_iommu(struct device *dev) +{ + u16 seg = get_device_segment(dev); + int devid = get_device_sbdf_id(dev); + + if (devid < 0) + return NULL; + return __rlookup_amd_iommu(seg, PCI_SBDF_TO_DEVID(devid)); +} + +static struct protection_domain *to_pdomain(struct iommu_domain *dom) +{ + return container_of(dom, struct protection_domain, domain); +} + +static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid) +{ + struct iommu_dev_data *dev_data; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL); + if (!dev_data) + return NULL; + + spin_lock_init(&dev_data->lock); + dev_data->devid = devid; + ratelimit_default_init(&dev_data->rs); + + llist_add(&dev_data->dev_data_list, &pci_seg->dev_data_list); + return dev_data; +} + +static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) +{ + struct iommu_dev_data *dev_data; + struct llist_node *node; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + if (llist_empty(&pci_seg->dev_data_list)) + return NULL; + + node = pci_seg->dev_data_list.first; + llist_for_each_entry(dev_data, node, dev_data_list) { + if (dev_data->devid == devid) + return dev_data; + } + + return NULL; +} + +static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) +{ + struct amd_iommu *iommu; + struct dev_table_entry *dev_table; + u16 devid = pci_dev_id(pdev); + + if (devid == alias) + return 0; + + iommu = rlookup_amd_iommu(&pdev->dev); + if (!iommu) + return 0; + + amd_iommu_set_rlookup_table(iommu, alias); + dev_table = get_dev_table(iommu); + memcpy(dev_table[alias].data, + dev_table[devid].data, + sizeof(dev_table[alias].data)); + + return 0; +} + +static void clone_aliases(struct amd_iommu *iommu, struct device *dev) +{ + struct pci_dev *pdev; + + if (!dev_is_pci(dev)) + return; + pdev = to_pci_dev(dev); + + /* + * The IVRS alias stored in the alias table may not be + * part of the PCI DMA aliases if it's bus differs + * from the original device. + */ + clone_alias(pdev, iommu->pci_seg->alias_table[pci_dev_id(pdev)], NULL); + + pci_for_each_dma_alias(pdev, clone_alias, NULL); +} + +static void setup_aliases(struct amd_iommu *iommu, struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + u16 ivrs_alias; + + /* For ACPI HID devices, there are no aliases */ + if (!dev_is_pci(dev)) + return; + + /* + * Add the IVRS alias to the pci aliases if it is on the same + * bus. The IVRS table may know about a quirk that we don't. + */ + ivrs_alias = pci_seg->alias_table[pci_dev_id(pdev)]; + if (ivrs_alias != pci_dev_id(pdev) && + PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) + pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1); + + clone_aliases(iommu, dev); +} + +static struct iommu_dev_data *find_dev_data(struct amd_iommu *iommu, u16 devid) +{ + struct iommu_dev_data *dev_data; + + dev_data = search_dev_data(iommu, devid); + + if (dev_data == NULL) { + dev_data = alloc_dev_data(iommu, devid); + if (!dev_data) + return NULL; + + if (translation_pre_enabled(iommu)) + dev_data->defer_attach = true; + } + + return dev_data; +} + +/* +* Find or create an IOMMU group for a acpihid device. +*/ +static struct iommu_group *acpihid_device_group(struct device *dev) +{ + struct acpihid_map_entry *p, *entry = NULL; + int devid; + + devid = get_acpihid_device_id(dev, &entry); + if (devid < 0) + return ERR_PTR(devid); + + list_for_each_entry(p, &acpihid_map, list) { + if ((devid == p->devid) && p->group) + entry->group = p->group; + } + + if (!entry->group) + entry->group = generic_device_group(dev); + else + iommu_group_ref_get(entry->group); + + return entry->group; +} + +static bool pci_iommuv2_capable(struct pci_dev *pdev) +{ + static const int caps[] = { + PCI_EXT_CAP_ID_PRI, + PCI_EXT_CAP_ID_PASID, + }; + int i, pos; + + if (!pci_ats_supported(pdev)) + return false; + + for (i = 0; i < 2; ++i) { + pos = pci_find_ext_capability(pdev, caps[i]); + if (pos == 0) + return false; + } + + return true; +} + +/* + * This function checks if the driver got a valid device from the caller to + * avoid dereferencing invalid pointers. + */ +static bool check_device(struct device *dev) +{ + struct amd_iommu_pci_seg *pci_seg; + struct amd_iommu *iommu; + int devid, sbdf; + + if (!dev) + return false; + + sbdf = get_device_sbdf_id(dev); + if (sbdf < 0) + return false; + devid = PCI_SBDF_TO_DEVID(sbdf); + + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return false; + + /* Out of our scope? */ + pci_seg = iommu->pci_seg; + if (devid > pci_seg->last_bdf) + return false; + + return true; +} + +static int iommu_init_device(struct amd_iommu *iommu, struct device *dev) +{ + struct iommu_dev_data *dev_data; + int devid, sbdf; + + if (dev_iommu_priv_get(dev)) + return 0; + + sbdf = get_device_sbdf_id(dev); + if (sbdf < 0) + return sbdf; + + devid = PCI_SBDF_TO_DEVID(sbdf); + dev_data = find_dev_data(iommu, devid); + if (!dev_data) + return -ENOMEM; + + dev_data->dev = dev; + setup_aliases(iommu, dev); + + /* + * By default we use passthrough mode for IOMMUv2 capable device. + * But if amd_iommu=force_isolation is set (e.g. to debug DMA to + * invalid address), we ignore the capability for the device so + * it'll be forced to go into translation mode. + */ + if ((iommu_default_passthrough() || !amd_iommu_force_isolation) && + dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) { + dev_data->iommu_v2 = iommu->is_iommu_v2; + } + + dev_iommu_priv_set(dev, dev_data); + + return 0; +} + +static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev) +{ + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + struct dev_table_entry *dev_table = get_dev_table(iommu); + int devid, sbdf; + + sbdf = get_device_sbdf_id(dev); + if (sbdf < 0) + return; + + devid = PCI_SBDF_TO_DEVID(sbdf); + pci_seg->rlookup_table[devid] = NULL; + memset(&dev_table[devid], 0, sizeof(struct dev_table_entry)); + + setup_aliases(iommu, dev); +} + +static void amd_iommu_uninit_device(struct device *dev) +{ + struct iommu_dev_data *dev_data; + + dev_data = dev_iommu_priv_get(dev); + if (!dev_data) + return; + + if (dev_data->domain) + detach_device(dev); + + dev_iommu_priv_set(dev, NULL); + + /* + * We keep dev_data around for unplugged devices and reuse it when the + * device is re-plugged - not doing so would introduce a ton of races. + */ +} + +/**************************************************************************** + * + * Interrupt handling functions + * + ****************************************************************************/ + +static void dump_dte_entry(struct amd_iommu *iommu, u16 devid) +{ + int i; + struct dev_table_entry *dev_table = get_dev_table(iommu); + + for (i = 0; i < 4; ++i) + pr_err("DTE[%d]: %016llx\n", i, dev_table[devid].data[i]); +} + +static void dump_command(unsigned long phys_addr) +{ + struct iommu_cmd *cmd = iommu_phys_to_virt(phys_addr); + int i; + + for (i = 0; i < 4; ++i) + pr_err("CMD[%d]: %08x\n", i, cmd->data[i]); +} + +static void amd_iommu_report_rmp_hw_error(struct amd_iommu *iommu, volatile u32 *event) +{ + struct iommu_dev_data *dev_data = NULL; + int devid, vmg_tag, flags; + struct pci_dev *pdev; + u64 spa; + + devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; + vmg_tag = (event[1]) & 0xFFFF; + flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; + spa = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8); + + pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid), + devid & 0xff); + if (pdev) + dev_data = dev_iommu_priv_get(&pdev->dev); + + if (dev_data) { + if (__ratelimit(&dev_data->rs)) { + pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n", + vmg_tag, spa, flags); + } + } else { + pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + vmg_tag, spa, flags); + } + + if (pdev) + pci_dev_put(pdev); +} + +static void amd_iommu_report_rmp_fault(struct amd_iommu *iommu, volatile u32 *event) +{ + struct iommu_dev_data *dev_data = NULL; + int devid, flags_rmp, vmg_tag, flags; + struct pci_dev *pdev; + u64 gpa; + + devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; + flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF; + vmg_tag = (event[1]) & 0xFFFF; + flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; + gpa = ((u64)event[3] << 32) | event[2]; + + pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid), + devid & 0xff); + if (pdev) + dev_data = dev_iommu_priv_get(&pdev->dev); + + if (dev_data) { + if (__ratelimit(&dev_data->rs)) { + pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n", + vmg_tag, gpa, flags_rmp, flags); + } + } else { + pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + vmg_tag, gpa, flags_rmp, flags); + } + + if (pdev) + pci_dev_put(pdev); +} + +#define IS_IOMMU_MEM_TRANSACTION(flags) \ + (((flags) & EVENT_FLAG_I) == 0) + +#define IS_WRITE_REQUEST(flags) \ + ((flags) & EVENT_FLAG_RW) + +static void amd_iommu_report_page_fault(struct amd_iommu *iommu, + u16 devid, u16 domain_id, + u64 address, int flags) +{ + struct iommu_dev_data *dev_data = NULL; + struct pci_dev *pdev; + + pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid), + devid & 0xff); + if (pdev) + dev_data = dev_iommu_priv_get(&pdev->dev); + + if (dev_data) { + /* + * If this is a DMA fault (for which the I(nterrupt) + * bit will be unset), allow report_iommu_fault() to + * prevent logging it. + */ + if (IS_IOMMU_MEM_TRANSACTION(flags)) { + /* Device not attached to domain properly */ + if (dev_data->domain == NULL) { + pr_err_ratelimited("Event logged [Device not attached to domain properly]\n"); + pr_err_ratelimited(" device=%04x:%02x:%02x.%x domain=0x%04x\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), + PCI_FUNC(devid), domain_id); + goto out; + } + + if (!report_iommu_fault(&dev_data->domain->domain, + &pdev->dev, address, + IS_WRITE_REQUEST(flags) ? + IOMMU_FAULT_WRITE : + IOMMU_FAULT_READ)) + goto out; + } + + if (__ratelimit(&dev_data->rs)) { + pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n", + domain_id, address, flags); + } + } else { + pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%04x:%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + domain_id, address, flags); + } + +out: + if (pdev) + pci_dev_put(pdev); +} + +static void iommu_print_event(struct amd_iommu *iommu, void *__evt) +{ + struct device *dev = iommu->iommu.dev; + int type, devid, flags, tag; + volatile u32 *event = __evt; + int count = 0; + u64 address; + u32 pasid; + +retry: + type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK; + devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; + pasid = (event[0] & EVENT_DOMID_MASK_HI) | + (event[1] & EVENT_DOMID_MASK_LO); + flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; + address = (u64)(((u64)event[3]) << 32) | event[2]; + + if (type == 0) { + /* Did we hit the erratum? */ + if (++count == LOOP_TIMEOUT) { + pr_err("No event written to event log\n"); + return; + } + udelay(1); + goto retry; + } + + if (type == EVENT_TYPE_IO_FAULT) { + amd_iommu_report_page_fault(iommu, devid, pasid, address, flags); + return; + } + + switch (type) { + case EVENT_TYPE_ILL_DEV: + dev_err(dev, "Event logged [ILLEGAL_DEV_TABLE_ENTRY device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + pasid, address, flags); + dump_dte_entry(iommu, devid); + break; + case EVENT_TYPE_DEV_TAB_ERR: + dev_err(dev, "Event logged [DEV_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x " + "address=0x%llx flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address, flags); + break; + case EVENT_TYPE_PAGE_TAB_ERR: + dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + pasid, address, flags); + break; + case EVENT_TYPE_ILL_CMD: + dev_err(dev, "Event logged [ILLEGAL_COMMAND_ERROR address=0x%llx]\n", address); + dump_command(address); + break; + case EVENT_TYPE_CMD_HARD_ERR: + dev_err(dev, "Event logged [COMMAND_HARDWARE_ERROR address=0x%llx flags=0x%04x]\n", + address, flags); + break; + case EVENT_TYPE_IOTLB_INV_TO: + dev_err(dev, "Event logged [IOTLB_INV_TIMEOUT device=%04x:%02x:%02x.%x address=0x%llx]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address); + break; + case EVENT_TYPE_INV_DEV_REQ: + dev_err(dev, "Event logged [INVALID_DEVICE_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + pasid, address, flags); + break; + case EVENT_TYPE_RMP_FAULT: + amd_iommu_report_rmp_fault(iommu, event); + break; + case EVENT_TYPE_RMP_HW_ERR: + amd_iommu_report_rmp_hw_error(iommu, event); + break; + case EVENT_TYPE_INV_PPR_REQ: + pasid = PPR_PASID(*((u64 *)__evt)); + tag = event[1] & 0x03FF; + dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n", + iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + pasid, address, flags, tag); + break; + default: + dev_err(dev, "Event logged [UNKNOWN event[0]=0x%08x event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n", + event[0], event[1], event[2], event[3]); + } + + memset(__evt, 0, 4 * sizeof(u32)); +} + +static void iommu_poll_events(struct amd_iommu *iommu) +{ + u32 head, tail; + + head = readl(iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); + tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + + while (head != tail) { + iommu_print_event(iommu, iommu->evt_buf + head); + head = (head + EVENT_ENTRY_SIZE) % EVT_BUFFER_SIZE; + } + + writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); +} + +static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw) +{ + struct amd_iommu_fault fault; + + if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) { + pr_err_ratelimited("Unknown PPR request received\n"); + return; + } + + fault.address = raw[1]; + fault.pasid = PPR_PASID(raw[0]); + fault.sbdf = PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->id, PPR_DEVID(raw[0])); + fault.tag = PPR_TAG(raw[0]); + fault.flags = PPR_FLAGS(raw[0]); + + atomic_notifier_call_chain(&ppr_notifier, 0, &fault); +} + +static void iommu_poll_ppr_log(struct amd_iommu *iommu) +{ + u32 head, tail; + + if (iommu->ppr_log == NULL) + return; + + head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); + tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET); + + while (head != tail) { + volatile u64 *raw; + u64 entry[2]; + int i; + + raw = (u64 *)(iommu->ppr_log + head); + + /* + * Hardware bug: Interrupt may arrive before the entry is + * written to memory. If this happens we need to wait for the + * entry to arrive. + */ + for (i = 0; i < LOOP_TIMEOUT; ++i) { + if (PPR_REQ_TYPE(raw[0]) != 0) + break; + udelay(1); + } + + /* Avoid memcpy function-call overhead */ + entry[0] = raw[0]; + entry[1] = raw[1]; + + /* + * To detect the hardware bug we need to clear the entry + * back to zero. + */ + raw[0] = raw[1] = 0UL; + + /* Update head pointer of hardware ring-buffer */ + head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE; + writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); + + /* Handle PPR entry */ + iommu_handle_ppr_entry(iommu, entry); + + /* Refresh ring-buffer information */ + head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); + tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET); + } +} + +#ifdef CONFIG_IRQ_REMAP +static int (*iommu_ga_log_notifier)(u32); + +int amd_iommu_register_ga_log_notifier(int (*notifier)(u32)) +{ + iommu_ga_log_notifier = notifier; + + return 0; +} +EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier); + +static void iommu_poll_ga_log(struct amd_iommu *iommu) +{ + u32 head, tail, cnt = 0; + + if (iommu->ga_log == NULL) + return; + + head = readl(iommu->mmio_base + MMIO_GA_HEAD_OFFSET); + tail = readl(iommu->mmio_base + MMIO_GA_TAIL_OFFSET); + + while (head != tail) { + volatile u64 *raw; + u64 log_entry; + + raw = (u64 *)(iommu->ga_log + head); + cnt++; + + /* Avoid memcpy function-call overhead */ + log_entry = *raw; + + /* Update head pointer of hardware ring-buffer */ + head = (head + GA_ENTRY_SIZE) % GA_LOG_SIZE; + writel(head, iommu->mmio_base + MMIO_GA_HEAD_OFFSET); + + /* Handle GA entry */ + switch (GA_REQ_TYPE(log_entry)) { + case GA_GUEST_NR: + if (!iommu_ga_log_notifier) + break; + + pr_debug("%s: devid=%#x, ga_tag=%#x\n", + __func__, GA_DEVID(log_entry), + GA_TAG(log_entry)); + + if (iommu_ga_log_notifier(GA_TAG(log_entry)) != 0) + pr_err("GA log notifier failed.\n"); + break; + default: + break; + } + } +} + +static void +amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) +{ + if (!irq_remapping_enabled || !dev_is_pci(dev) || + pci_dev_has_special_msi_domain(to_pci_dev(dev))) + return; + + dev_set_msi_domain(dev, iommu->msi_domain); +} + +#else /* CONFIG_IRQ_REMAP */ +static inline void +amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { } +#endif /* !CONFIG_IRQ_REMAP */ + +#define AMD_IOMMU_INT_MASK \ + (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \ + MMIO_STATUS_EVT_INT_MASK | \ + MMIO_STATUS_PPR_INT_MASK | \ + MMIO_STATUS_GALOG_OVERFLOW_MASK | \ + MMIO_STATUS_GALOG_INT_MASK) + +irqreturn_t amd_iommu_int_thread(int irq, void *data) +{ + struct amd_iommu *iommu = (struct amd_iommu *) data; + u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + + while (status & AMD_IOMMU_INT_MASK) { + /* Enable interrupt sources again */ + writel(AMD_IOMMU_INT_MASK, + iommu->mmio_base + MMIO_STATUS_OFFSET); + + if (status & MMIO_STATUS_EVT_INT_MASK) { + pr_devel("Processing IOMMU Event Log\n"); + iommu_poll_events(iommu); + } + + if (status & MMIO_STATUS_PPR_INT_MASK) { + pr_devel("Processing IOMMU PPR Log\n"); + iommu_poll_ppr_log(iommu); + } + +#ifdef CONFIG_IRQ_REMAP + if (status & (MMIO_STATUS_GALOG_INT_MASK | + MMIO_STATUS_GALOG_OVERFLOW_MASK)) { + pr_devel("Processing IOMMU GA Log\n"); + iommu_poll_ga_log(iommu); + } + + if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) { + pr_info_ratelimited("IOMMU GA Log overflow\n"); + amd_iommu_restart_ga_log(iommu); + } +#endif + + if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) { + pr_info_ratelimited("IOMMU event log overflow\n"); + amd_iommu_restart_event_logging(iommu); + } + + /* + * Hardware bug: ERBT1312 + * When re-enabling interrupt (by writing 1 + * to clear the bit), the hardware might also try to set + * the interrupt bit in the event status register. + * In this scenario, the bit will be set, and disable + * subsequent interrupts. + * + * Workaround: The IOMMU driver should read back the + * status register and check if the interrupt bits are cleared. + * If not, driver will need to go through the interrupt handler + * again and re-clear the bits + */ + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + } + return IRQ_HANDLED; +} + +irqreturn_t amd_iommu_int_handler(int irq, void *data) +{ + return IRQ_WAKE_THREAD; +} + +/**************************************************************************** + * + * IOMMU command queuing functions + * + ****************************************************************************/ + +static int wait_on_sem(struct amd_iommu *iommu, u64 data) +{ + int i = 0; + + while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) { + udelay(1); + i += 1; + } + + if (i == LOOP_TIMEOUT) { + pr_alert("Completion-Wait loop timed out\n"); + return -EIO; + } + + return 0; +} + +static void copy_cmd_to_buffer(struct amd_iommu *iommu, + struct iommu_cmd *cmd) +{ + u8 *target; + u32 tail; + + /* Copy command to buffer */ + tail = iommu->cmd_buf_tail; + target = iommu->cmd_buf + tail; + memcpy(target, cmd, sizeof(*cmd)); + + tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE; + iommu->cmd_buf_tail = tail; + + /* Tell the IOMMU about it */ + writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); +} + +static void build_completion_wait(struct iommu_cmd *cmd, + struct amd_iommu *iommu, + u64 data) +{ + u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem); + + memset(cmd, 0, sizeof(*cmd)); + cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK; + cmd->data[1] = upper_32_bits(paddr); + cmd->data[2] = lower_32_bits(data); + cmd->data[3] = upper_32_bits(data); + CMD_SET_TYPE(cmd, CMD_COMPL_WAIT); +} + +static void build_inv_dte(struct iommu_cmd *cmd, u16 devid) +{ + memset(cmd, 0, sizeof(*cmd)); + cmd->data[0] = devid; + CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY); +} + +/* + * Builds an invalidation address which is suitable for one page or multiple + * pages. Sets the size bit (S) as needed is more than one page is flushed. + */ +static inline u64 build_inv_address(u64 address, size_t size) +{ + u64 pages, end, msb_diff; + + pages = iommu_num_pages(address, size, PAGE_SIZE); + + if (pages == 1) + return address & PAGE_MASK; + + end = address + size - 1; + + /* + * msb_diff would hold the index of the most significant bit that + * flipped between the start and end. + */ + msb_diff = fls64(end ^ address) - 1; + + /* + * Bits 63:52 are sign extended. If for some reason bit 51 is different + * between the start and the end, invalidate everything. + */ + if (unlikely(msb_diff > 51)) { + address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; + } else { + /* + * The msb-bit must be clear on the address. Just set all the + * lower bits. + */ + address |= (1ull << msb_diff) - 1; + } + + /* Clear bits 11:0 */ + address &= PAGE_MASK; + + /* Set the size bit - we flush more than one 4kb page */ + return address | CMD_INV_IOMMU_PAGES_SIZE_MASK; +} + +static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, + size_t size, u16 domid, int pde) +{ + u64 inv_address = build_inv_address(address, size); + + memset(cmd, 0, sizeof(*cmd)); + cmd->data[1] |= domid; + cmd->data[2] = lower_32_bits(inv_address); + cmd->data[3] = upper_32_bits(inv_address); + CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); + if (pde) /* PDE bit - we want to flush everything, not only the PTEs */ + cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; +} + +static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep, + u64 address, size_t size) +{ + u64 inv_address = build_inv_address(address, size); + + memset(cmd, 0, sizeof(*cmd)); + cmd->data[0] = devid; + cmd->data[0] |= (qdep & 0xff) << 24; + cmd->data[1] = devid; + cmd->data[2] = lower_32_bits(inv_address); + cmd->data[3] = upper_32_bits(inv_address); + CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); +} + +static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid, + u64 address, bool size) +{ + memset(cmd, 0, sizeof(*cmd)); + + address &= ~(0xfffULL); + + cmd->data[0] = pasid; + cmd->data[1] = domid; + cmd->data[2] = lower_32_bits(address); + cmd->data[3] = upper_32_bits(address); + cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; + cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; + if (size) + cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; + CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES); +} + +static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid, + int qdep, u64 address, bool size) +{ + memset(cmd, 0, sizeof(*cmd)); + + address &= ~(0xfffULL); + + cmd->data[0] = devid; + cmd->data[0] |= ((pasid >> 8) & 0xff) << 16; + cmd->data[0] |= (qdep & 0xff) << 24; + cmd->data[1] = devid; + cmd->data[1] |= (pasid & 0xff) << 16; + cmd->data[2] = lower_32_bits(address); + cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK; + cmd->data[3] = upper_32_bits(address); + if (size) + cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; + CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES); +} + +static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, u32 pasid, + int status, int tag, bool gn) +{ + memset(cmd, 0, sizeof(*cmd)); + + cmd->data[0] = devid; + if (gn) { + cmd->data[1] = pasid; + cmd->data[2] = CMD_INV_IOMMU_PAGES_GN_MASK; + } + cmd->data[3] = tag & 0x1ff; + cmd->data[3] |= (status & PPR_STATUS_MASK) << PPR_STATUS_SHIFT; + + CMD_SET_TYPE(cmd, CMD_COMPLETE_PPR); +} + +static void build_inv_all(struct iommu_cmd *cmd) +{ + memset(cmd, 0, sizeof(*cmd)); + CMD_SET_TYPE(cmd, CMD_INV_ALL); +} + +static void build_inv_irt(struct iommu_cmd *cmd, u16 devid) +{ + memset(cmd, 0, sizeof(*cmd)); + cmd->data[0] = devid; + CMD_SET_TYPE(cmd, CMD_INV_IRT); +} + +/* + * Writes the command to the IOMMUs command buffer and informs the + * hardware about the new command. + */ +static int __iommu_queue_command_sync(struct amd_iommu *iommu, + struct iommu_cmd *cmd, + bool sync) +{ + unsigned int count = 0; + u32 left, next_tail; + + next_tail = (iommu->cmd_buf_tail + sizeof(*cmd)) % CMD_BUFFER_SIZE; +again: + left = (iommu->cmd_buf_head - next_tail) % CMD_BUFFER_SIZE; + + if (left <= 0x20) { + /* Skip udelay() the first time around */ + if (count++) { + if (count == LOOP_TIMEOUT) { + pr_err("Command buffer timeout\n"); + return -EIO; + } + + udelay(1); + } + + /* Update head and recheck remaining space */ + iommu->cmd_buf_head = readl(iommu->mmio_base + + MMIO_CMD_HEAD_OFFSET); + + goto again; + } + + copy_cmd_to_buffer(iommu, cmd); + + /* Do we need to make sure all commands are processed? */ + iommu->need_sync = sync; + + return 0; +} + +static int iommu_queue_command_sync(struct amd_iommu *iommu, + struct iommu_cmd *cmd, + bool sync) +{ + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&iommu->lock, flags); + ret = __iommu_queue_command_sync(iommu, cmd, sync); + raw_spin_unlock_irqrestore(&iommu->lock, flags); + + return ret; +} + +static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) +{ + return iommu_queue_command_sync(iommu, cmd, true); +} + +/* + * This function queues a completion wait command into the command + * buffer of an IOMMU + */ +static int iommu_completion_wait(struct amd_iommu *iommu) +{ + struct iommu_cmd cmd; + unsigned long flags; + int ret; + u64 data; + + if (!iommu->need_sync) + return 0; + + raw_spin_lock_irqsave(&iommu->lock, flags); + + data = ++iommu->cmd_sem_val; + build_completion_wait(&cmd, iommu, data); + + ret = __iommu_queue_command_sync(iommu, &cmd, false); + if (ret) + goto out_unlock; + + ret = wait_on_sem(iommu, data); + +out_unlock: + raw_spin_unlock_irqrestore(&iommu->lock, flags); + + return ret; +} + +static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid) +{ + struct iommu_cmd cmd; + + build_inv_dte(&cmd, devid); + + return iommu_queue_command(iommu, &cmd); +} + +static void amd_iommu_flush_dte_all(struct amd_iommu *iommu) +{ + u32 devid; + u16 last_bdf = iommu->pci_seg->last_bdf; + + for (devid = 0; devid <= last_bdf; ++devid) + iommu_flush_dte(iommu, devid); + + iommu_completion_wait(iommu); +} + +/* + * This function uses heavy locking and may disable irqs for some time. But + * this is no issue because it is only called during resume. + */ +static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu) +{ + u32 dom_id; + u16 last_bdf = iommu->pci_seg->last_bdf; + + for (dom_id = 0; dom_id <= last_bdf; ++dom_id) { + struct iommu_cmd cmd; + build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, + dom_id, 1); + iommu_queue_command(iommu, &cmd); + } + + iommu_completion_wait(iommu); +} + +static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id) +{ + struct iommu_cmd cmd; + + build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, + dom_id, 1); + iommu_queue_command(iommu, &cmd); + + iommu_completion_wait(iommu); +} + +static void amd_iommu_flush_all(struct amd_iommu *iommu) +{ + struct iommu_cmd cmd; + + build_inv_all(&cmd); + + iommu_queue_command(iommu, &cmd); + iommu_completion_wait(iommu); +} + +static void iommu_flush_irt(struct amd_iommu *iommu, u16 devid) +{ + struct iommu_cmd cmd; + + build_inv_irt(&cmd, devid); + + iommu_queue_command(iommu, &cmd); +} + +static void amd_iommu_flush_irt_all(struct amd_iommu *iommu) +{ + u32 devid; + u16 last_bdf = iommu->pci_seg->last_bdf; + + for (devid = 0; devid <= last_bdf; devid++) + iommu_flush_irt(iommu, devid); + + iommu_completion_wait(iommu); +} + +void iommu_flush_all_caches(struct amd_iommu *iommu) +{ + if (iommu_feature(iommu, FEATURE_IA)) { + amd_iommu_flush_all(iommu); + } else { + amd_iommu_flush_dte_all(iommu); + amd_iommu_flush_irt_all(iommu); + amd_iommu_flush_tlb_all(iommu); + } +} + +/* + * Command send function for flushing on-device TLB + */ +static int device_flush_iotlb(struct iommu_dev_data *dev_data, + u64 address, size_t size) +{ + struct amd_iommu *iommu; + struct iommu_cmd cmd; + int qdep; + + qdep = dev_data->ats.qdep; + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + return -EINVAL; + + build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size); + + return iommu_queue_command(iommu, &cmd); +} + +static int device_flush_dte_alias(struct pci_dev *pdev, u16 alias, void *data) +{ + struct amd_iommu *iommu = data; + + return iommu_flush_dte(iommu, alias); +} + +/* + * Command send function for invalidating a device table entry + */ +static int device_flush_dte(struct iommu_dev_data *dev_data) +{ + struct amd_iommu *iommu; + struct pci_dev *pdev = NULL; + struct amd_iommu_pci_seg *pci_seg; + u16 alias; + int ret; + + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + return -EINVAL; + + if (dev_is_pci(dev_data->dev)) + pdev = to_pci_dev(dev_data->dev); + + if (pdev) + ret = pci_for_each_dma_alias(pdev, + device_flush_dte_alias, iommu); + else + ret = iommu_flush_dte(iommu, dev_data->devid); + if (ret) + return ret; + + pci_seg = iommu->pci_seg; + alias = pci_seg->alias_table[dev_data->devid]; + if (alias != dev_data->devid) { + ret = iommu_flush_dte(iommu, alias); + if (ret) + return ret; + } + + if (dev_data->ats.enabled) + ret = device_flush_iotlb(dev_data, 0, ~0UL); + + return ret; +} + +/* + * TLB invalidation function which is called from the mapping functions. + * It invalidates a single PTE if the range to flush is within a single + * page. Otherwise it flushes the whole TLB of the IOMMU. + */ +static void __domain_flush_pages(struct protection_domain *domain, + u64 address, size_t size, int pde) +{ + struct iommu_dev_data *dev_data; + struct iommu_cmd cmd; + int ret = 0, i; + + build_inv_iommu_pages(&cmd, address, size, domain->id, pde); + + for (i = 0; i < amd_iommu_get_num_iommus(); ++i) { + if (!domain->dev_iommu[i]) + continue; + + /* + * Devices of this domain are behind this IOMMU + * We need a TLB flush + */ + ret |= iommu_queue_command(amd_iommus[i], &cmd); + } + + list_for_each_entry(dev_data, &domain->dev_list, list) { + + if (!dev_data->ats.enabled) + continue; + + ret |= device_flush_iotlb(dev_data, address, size); + } + + WARN_ON(ret); +} + +static void domain_flush_pages(struct protection_domain *domain, + u64 address, size_t size, int pde) +{ + if (likely(!amd_iommu_np_cache)) { + __domain_flush_pages(domain, address, size, pde); + return; + } + + /* + * When NpCache is on, we infer that we run in a VM and use a vIOMMU. + * In such setups it is best to avoid flushes of ranges which are not + * naturally aligned, since it would lead to flushes of unmodified + * PTEs. Such flushes would require the hypervisor to do more work than + * necessary. Therefore, perform repeated flushes of aligned ranges + * until you cover the range. Each iteration flushes the smaller + * between the natural alignment of the address that we flush and the + * greatest naturally aligned region that fits in the range. + */ + while (size != 0) { + int addr_alignment = __ffs(address); + int size_alignment = __fls(size); + int min_alignment; + size_t flush_size; + + /* + * size is always non-zero, but address might be zero, causing + * addr_alignment to be negative. As the casting of the + * argument in __ffs(address) to long might trim the high bits + * of the address on x86-32, cast to long when doing the check. + */ + if (likely((unsigned long)address != 0)) + min_alignment = min(addr_alignment, size_alignment); + else + min_alignment = size_alignment; + + flush_size = 1ul << min_alignment; + + __domain_flush_pages(domain, address, flush_size, pde); + address += flush_size; + size -= flush_size; + } +} + +/* Flush the whole IO/TLB for a given protection domain - including PDE */ +void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain) +{ + domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1); +} + +void amd_iommu_domain_flush_complete(struct protection_domain *domain) +{ + int i; + + for (i = 0; i < amd_iommu_get_num_iommus(); ++i) { + if (domain && !domain->dev_iommu[i]) + continue; + + /* + * Devices of this domain are behind this IOMMU + * We need to wait for completion of all commands. + */ + iommu_completion_wait(amd_iommus[i]); + } +} + +/* Flush the not present cache if it exists */ +static void domain_flush_np_cache(struct protection_domain *domain, + dma_addr_t iova, size_t size) +{ + if (unlikely(amd_iommu_np_cache)) { + unsigned long flags; + + spin_lock_irqsave(&domain->lock, flags); + domain_flush_pages(domain, iova, size, 1); + amd_iommu_domain_flush_complete(domain); + spin_unlock_irqrestore(&domain->lock, flags); + } +} + + +/* + * This function flushes the DTEs for all devices in domain + */ +static void domain_flush_devices(struct protection_domain *domain) +{ + struct iommu_dev_data *dev_data; + + list_for_each_entry(dev_data, &domain->dev_list, list) + device_flush_dte(dev_data); +} + +/**************************************************************************** + * + * The next functions belong to the domain allocation. A domain is + * allocated for every IOMMU as the default domain. If device isolation + * is enabled, every device get its own domain. The most important thing + * about domains is the page table mapping the DMA address space they + * contain. + * + ****************************************************************************/ + +static u16 domain_id_alloc(void) +{ + int id; + + spin_lock(&pd_bitmap_lock); + id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); + BUG_ON(id == 0); + if (id > 0 && id < MAX_DOMAIN_ID) + __set_bit(id, amd_iommu_pd_alloc_bitmap); + else + id = 0; + spin_unlock(&pd_bitmap_lock); + + return id; +} + +static void domain_id_free(int id) +{ + spin_lock(&pd_bitmap_lock); + if (id > 0 && id < MAX_DOMAIN_ID) + __clear_bit(id, amd_iommu_pd_alloc_bitmap); + spin_unlock(&pd_bitmap_lock); +} + +static void free_gcr3_tbl_level1(u64 *tbl) +{ + u64 *ptr; + int i; + + for (i = 0; i < 512; ++i) { + if (!(tbl[i] & GCR3_VALID)) + continue; + + ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK); + + free_page((unsigned long)ptr); + } +} + +static void free_gcr3_tbl_level2(u64 *tbl) +{ + u64 *ptr; + int i; + + for (i = 0; i < 512; ++i) { + if (!(tbl[i] & GCR3_VALID)) + continue; + + ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK); + + free_gcr3_tbl_level1(ptr); + } +} + +static void free_gcr3_table(struct protection_domain *domain) +{ + if (domain->glx == 2) + free_gcr3_tbl_level2(domain->gcr3_tbl); + else if (domain->glx == 1) + free_gcr3_tbl_level1(domain->gcr3_tbl); + else + BUG_ON(domain->glx != 0); + + free_page((unsigned long)domain->gcr3_tbl); +} + +static void set_dte_entry(struct amd_iommu *iommu, u16 devid, + struct protection_domain *domain, bool ats, bool ppr) +{ + u64 pte_root = 0; + u64 flags = 0; + u32 old_domid; + struct dev_table_entry *dev_table = get_dev_table(iommu); + + if (domain->iop.mode != PAGE_MODE_NONE) + pte_root = iommu_virt_to_phys(domain->iop.root); + + pte_root |= (domain->iop.mode & DEV_ENTRY_MODE_MASK) + << DEV_ENTRY_MODE_SHIFT; + + pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V; + + /* + * When SNP is enabled, Only set TV bit when IOMMU + * page translation is in use. + */ + if (!amd_iommu_snp_en || (domain->id != 0)) + pte_root |= DTE_FLAG_TV; + + flags = dev_table[devid].data[1]; + + if (ats) + flags |= DTE_FLAG_IOTLB; + + if (ppr) { + if (iommu_feature(iommu, FEATURE_EPHSUP)) + pte_root |= 1ULL << DEV_ENTRY_PPR; + } + + if (domain->flags & PD_IOMMUV2_MASK) { + u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl); + u64 glx = domain->glx; + u64 tmp; + + pte_root |= DTE_FLAG_GV; + pte_root |= (glx & DTE_GLX_MASK) << DTE_GLX_SHIFT; + + /* First mask out possible old values for GCR3 table */ + tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B; + flags &= ~tmp; + + tmp = DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C; + flags &= ~tmp; + + /* Encode GCR3 table into DTE */ + tmp = DTE_GCR3_VAL_A(gcr3) << DTE_GCR3_SHIFT_A; + pte_root |= tmp; + + tmp = DTE_GCR3_VAL_B(gcr3) << DTE_GCR3_SHIFT_B; + flags |= tmp; + + tmp = DTE_GCR3_VAL_C(gcr3) << DTE_GCR3_SHIFT_C; + flags |= tmp; + + if (domain->flags & PD_GIOV_MASK) + pte_root |= DTE_FLAG_GIOV; + } + + flags &= ~DEV_DOMID_MASK; + flags |= domain->id; + + old_domid = dev_table[devid].data[1] & DEV_DOMID_MASK; + dev_table[devid].data[1] = flags; + dev_table[devid].data[0] = pte_root; + + /* + * A kdump kernel might be replacing a domain ID that was copied from + * the previous kernel--if so, it needs to flush the translation cache + * entries for the old domain ID that is being overwritten + */ + if (old_domid) { + amd_iommu_flush_tlb_domid(iommu, old_domid); + } +} + +static void clear_dte_entry(struct amd_iommu *iommu, u16 devid) +{ + struct dev_table_entry *dev_table = get_dev_table(iommu); + + /* remove entry from the device table seen by the hardware */ + dev_table[devid].data[0] = DTE_FLAG_V; + + if (!amd_iommu_snp_en) + dev_table[devid].data[0] |= DTE_FLAG_TV; + + dev_table[devid].data[1] &= DTE_FLAG_MASK; + + amd_iommu_apply_erratum_63(iommu, devid); +} + +static void do_attach(struct iommu_dev_data *dev_data, + struct protection_domain *domain) +{ + struct amd_iommu *iommu; + bool ats; + + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + return; + ats = dev_data->ats.enabled; + + /* Update data structures */ + dev_data->domain = domain; + list_add(&dev_data->list, &domain->dev_list); + + /* Do reference counting */ + domain->dev_iommu[iommu->index] += 1; + domain->dev_cnt += 1; + + /* Update device table */ + set_dte_entry(iommu, dev_data->devid, domain, + ats, dev_data->iommu_v2); + clone_aliases(iommu, dev_data->dev); + + device_flush_dte(dev_data); +} + +static void do_detach(struct iommu_dev_data *dev_data) +{ + struct protection_domain *domain = dev_data->domain; + struct amd_iommu *iommu; + + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + return; + + /* Update data structures */ + dev_data->domain = NULL; + list_del(&dev_data->list); + clear_dte_entry(iommu, dev_data->devid); + clone_aliases(iommu, dev_data->dev); + + /* Flush the DTE entry */ + device_flush_dte(dev_data); + + /* Flush IOTLB */ + amd_iommu_domain_flush_tlb_pde(domain); + + /* Wait for the flushes to finish */ + amd_iommu_domain_flush_complete(domain); + + /* decrease reference counters - needs to happen after the flushes */ + domain->dev_iommu[iommu->index] -= 1; + domain->dev_cnt -= 1; +} + +static void pdev_iommuv2_disable(struct pci_dev *pdev) +{ + pci_disable_ats(pdev); + pci_disable_pri(pdev); + pci_disable_pasid(pdev); +} + +static int pdev_pri_ats_enable(struct pci_dev *pdev) +{ + int ret; + + /* Only allow access to user-accessible pages */ + ret = pci_enable_pasid(pdev, 0); + if (ret) + return ret; + + /* First reset the PRI state of the device */ + ret = pci_reset_pri(pdev); + if (ret) + goto out_err_pasid; + + /* Enable PRI */ + /* FIXME: Hardcode number of outstanding requests for now */ + ret = pci_enable_pri(pdev, 32); + if (ret) + goto out_err_pasid; + + ret = pci_enable_ats(pdev, PAGE_SHIFT); + if (ret) + goto out_err_pri; + + return 0; + +out_err_pri: + pci_disable_pri(pdev); + +out_err_pasid: + pci_disable_pasid(pdev); + + return ret; +} + +/* + * If a device is not yet associated with a domain, this function makes the + * device visible in the domain + */ +static int attach_device(struct device *dev, + struct protection_domain *domain) +{ + struct iommu_dev_data *dev_data; + struct pci_dev *pdev; + unsigned long flags; + int ret; + + spin_lock_irqsave(&domain->lock, flags); + + dev_data = dev_iommu_priv_get(dev); + + spin_lock(&dev_data->lock); + + ret = -EBUSY; + if (dev_data->domain != NULL) + goto out; + + if (!dev_is_pci(dev)) + goto skip_ats_check; + + pdev = to_pci_dev(dev); + if (domain->flags & PD_IOMMUV2_MASK) { + struct iommu_domain *def_domain = iommu_get_dma_domain(dev); + + ret = -EINVAL; + + /* + * In case of using AMD_IOMMU_V1 page table mode and the device + * is enabling for PPR/ATS support (using v2 table), + * we need to make sure that the domain type is identity map. + */ + if ((amd_iommu_pgtable == AMD_IOMMU_V1) && + def_domain->type != IOMMU_DOMAIN_IDENTITY) { + goto out; + } + + if (dev_data->iommu_v2) { + if (pdev_pri_ats_enable(pdev) != 0) + goto out; + + dev_data->ats.enabled = true; + dev_data->ats.qdep = pci_ats_queue_depth(pdev); + dev_data->pri_tlp = pci_prg_resp_pasid_required(pdev); + } + } else if (amd_iommu_iotlb_sup && + pci_enable_ats(pdev, PAGE_SHIFT) == 0) { + dev_data->ats.enabled = true; + dev_data->ats.qdep = pci_ats_queue_depth(pdev); + } + +skip_ats_check: + ret = 0; + + do_attach(dev_data, domain); + + /* + * We might boot into a crash-kernel here. The crashed kernel + * left the caches in the IOMMU dirty. So we have to flush + * here to evict all dirty stuff. + */ + amd_iommu_domain_flush_tlb_pde(domain); + + amd_iommu_domain_flush_complete(domain); + +out: + spin_unlock(&dev_data->lock); + + spin_unlock_irqrestore(&domain->lock, flags); + + return ret; +} + +/* + * Removes a device from a protection domain (with devtable_lock held) + */ +static void detach_device(struct device *dev) +{ + struct protection_domain *domain; + struct iommu_dev_data *dev_data; + unsigned long flags; + + dev_data = dev_iommu_priv_get(dev); + domain = dev_data->domain; + + spin_lock_irqsave(&domain->lock, flags); + + spin_lock(&dev_data->lock); + + /* + * First check if the device is still attached. It might already + * be detached from its domain because the generic + * iommu_detach_group code detached it and we try again here in + * our alias handling. + */ + if (WARN_ON(!dev_data->domain)) + goto out; + + do_detach(dev_data); + + if (!dev_is_pci(dev)) + goto out; + + if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2) + pdev_iommuv2_disable(to_pci_dev(dev)); + else if (dev_data->ats.enabled) + pci_disable_ats(to_pci_dev(dev)); + + dev_data->ats.enabled = false; + +out: + spin_unlock(&dev_data->lock); + + spin_unlock_irqrestore(&domain->lock, flags); +} + +static struct iommu_device *amd_iommu_probe_device(struct device *dev) +{ + struct iommu_device *iommu_dev; + struct amd_iommu *iommu; + int ret; + + if (!check_device(dev)) + return ERR_PTR(-ENODEV); + + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return ERR_PTR(-ENODEV); + + /* Not registered yet? */ + if (!iommu->iommu.ops) + return ERR_PTR(-ENODEV); + + if (dev_iommu_priv_get(dev)) + return &iommu->iommu; + + ret = iommu_init_device(iommu, dev); + if (ret) { + if (ret != -ENOTSUPP) + dev_err(dev, "Failed to initialize - trying to proceed anyway\n"); + iommu_dev = ERR_PTR(ret); + iommu_ignore_device(iommu, dev); + } else { + amd_iommu_set_pci_msi_domain(dev, iommu); + iommu_dev = &iommu->iommu; + } + + iommu_completion_wait(iommu); + + return iommu_dev; +} + +static void amd_iommu_probe_finalize(struct device *dev) +{ + /* Domains are initialized for this device - have a look what we ended up with */ + set_dma_ops(dev, NULL); + iommu_setup_dma_ops(dev, 0, U64_MAX); +} + +static void amd_iommu_release_device(struct device *dev) +{ + struct amd_iommu *iommu; + + if (!check_device(dev)) + return; + + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return; + + amd_iommu_uninit_device(dev); + iommu_completion_wait(iommu); +} + +static struct iommu_group *amd_iommu_device_group(struct device *dev) +{ + if (dev_is_pci(dev)) + return pci_device_group(dev); + + return acpihid_device_group(dev); +} + +/***************************************************************************** + * + * The next functions belong to the dma_ops mapping/unmapping code. + * + *****************************************************************************/ + +static void update_device_table(struct protection_domain *domain) +{ + struct iommu_dev_data *dev_data; + + list_for_each_entry(dev_data, &domain->dev_list, list) { + struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev); + + if (!iommu) + continue; + set_dte_entry(iommu, dev_data->devid, domain, + dev_data->ats.enabled, dev_data->iommu_v2); + clone_aliases(iommu, dev_data->dev); + } +} + +void amd_iommu_update_and_flush_device_table(struct protection_domain *domain) +{ + update_device_table(domain); + domain_flush_devices(domain); +} + +void amd_iommu_domain_update(struct protection_domain *domain) +{ + /* Update device table */ + amd_iommu_update_and_flush_device_table(domain); + + /* Flush domain TLB(s) and wait for completion */ + amd_iommu_domain_flush_tlb_pde(domain); + amd_iommu_domain_flush_complete(domain); +} + +/***************************************************************************** + * + * The following functions belong to the exported interface of AMD IOMMU + * + * This interface allows access to lower level functions of the IOMMU + * like protection domain handling and assignement of devices to domains + * which is not possible with the dma_ops interface. + * + *****************************************************************************/ + +static void cleanup_domain(struct protection_domain *domain) +{ + struct iommu_dev_data *entry; + unsigned long flags; + + spin_lock_irqsave(&domain->lock, flags); + + while (!list_empty(&domain->dev_list)) { + entry = list_first_entry(&domain->dev_list, + struct iommu_dev_data, list); + BUG_ON(!entry->domain); + do_detach(entry); + } + + spin_unlock_irqrestore(&domain->lock, flags); +} + +static void protection_domain_free(struct protection_domain *domain) +{ + if (!domain) + return; + + if (domain->iop.pgtbl_cfg.tlb) + free_io_pgtable_ops(&domain->iop.iop.ops); + + if (domain->id) + domain_id_free(domain->id); + + kfree(domain); +} + +static int protection_domain_init_v1(struct protection_domain *domain, int mode) +{ + u64 *pt_root = NULL; + + BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL); + + spin_lock_init(&domain->lock); + domain->id = domain_id_alloc(); + if (!domain->id) + return -ENOMEM; + INIT_LIST_HEAD(&domain->dev_list); + + if (mode != PAGE_MODE_NONE) { + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) { + domain_id_free(domain->id); + return -ENOMEM; + } + } + + amd_iommu_domain_set_pgtable(domain, pt_root, mode); + + return 0; +} + +static int protection_domain_init_v2(struct protection_domain *domain) +{ + spin_lock_init(&domain->lock); + domain->id = domain_id_alloc(); + if (!domain->id) + return -ENOMEM; + INIT_LIST_HEAD(&domain->dev_list); + + domain->flags |= PD_GIOV_MASK; + + domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2; + + if (domain_enable_v2(domain, 1)) { + domain_id_free(domain->id); + return -ENOMEM; + } + + return 0; +} + +static struct protection_domain *protection_domain_alloc(unsigned int type) +{ + struct io_pgtable_ops *pgtbl_ops; + struct protection_domain *domain; + int pgtable = amd_iommu_pgtable; + int mode = DEFAULT_PGTABLE_LEVEL; + int ret; + + domain = kzalloc(sizeof(*domain), GFP_KERNEL); + if (!domain) + return NULL; + + /* + * Force IOMMU v1 page table when iommu=pt and + * when allocating domain for pass-through devices. + */ + if (type == IOMMU_DOMAIN_IDENTITY) { + pgtable = AMD_IOMMU_V1; + mode = PAGE_MODE_NONE; + } else if (type == IOMMU_DOMAIN_UNMANAGED) { + pgtable = AMD_IOMMU_V1; + } + + switch (pgtable) { + case AMD_IOMMU_V1: + ret = protection_domain_init_v1(domain, mode); + break; + case AMD_IOMMU_V2: + ret = protection_domain_init_v2(domain); + break; + default: + ret = -EINVAL; + } + + if (ret) + goto out_err; + + pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain); + if (!pgtbl_ops) { + domain_id_free(domain->id); + goto out_err; + } + + return domain; +out_err: + kfree(domain); + return NULL; +} + +static inline u64 dma_max_address(void) +{ + if (amd_iommu_pgtable == AMD_IOMMU_V1) + return ~0ULL; + + /* V2 with 4 level page table */ + return ((1ULL << PM_LEVEL_SHIFT(PAGE_MODE_4_LEVEL)) - 1); +} + +static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) +{ + struct protection_domain *domain; + + /* + * Since DTE[Mode]=0 is prohibited on SNP-enabled system, + * default to use IOMMU_DOMAIN_DMA[_FQ]. + */ + if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY)) + return NULL; + + domain = protection_domain_alloc(type); + if (!domain) + return NULL; + + domain->domain.geometry.aperture_start = 0; + domain->domain.geometry.aperture_end = dma_max_address(); + domain->domain.geometry.force_aperture = true; + + return &domain->domain; +} + +static void amd_iommu_domain_free(struct iommu_domain *dom) +{ + struct protection_domain *domain; + + domain = to_pdomain(dom); + + if (domain->dev_cnt > 0) + cleanup_domain(domain); + + BUG_ON(domain->dev_cnt != 0); + + if (!dom) + return; + + if (domain->flags & PD_IOMMUV2_MASK) + free_gcr3_table(domain); + + protection_domain_free(domain); +} + +static void amd_iommu_detach_device(struct iommu_domain *dom, + struct device *dev) +{ + struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); + struct amd_iommu *iommu; + + if (!check_device(dev)) + return; + + if (dev_data->domain != NULL) + detach_device(dev); + + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return; + +#ifdef CONFIG_IRQ_REMAP + if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) && + (dom->type == IOMMU_DOMAIN_UNMANAGED)) + dev_data->use_vapic = 0; +#endif + + iommu_completion_wait(iommu); +} + +static int amd_iommu_attach_device(struct iommu_domain *dom, + struct device *dev) +{ + struct protection_domain *domain = to_pdomain(dom); + struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; + int ret; + + if (!check_device(dev)) + return -EINVAL; + + dev_data = dev_iommu_priv_get(dev); + dev_data->defer_attach = false; + + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return -EINVAL; + + if (dev_data->domain) + detach_device(dev); + + ret = attach_device(dev, domain); + +#ifdef CONFIG_IRQ_REMAP + if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) { + if (dom->type == IOMMU_DOMAIN_UNMANAGED) + dev_data->use_vapic = 1; + else + dev_data->use_vapic = 0; + } +#endif + + iommu_completion_wait(iommu); + + return ret; +} + +static void amd_iommu_iotlb_sync_map(struct iommu_domain *dom, + unsigned long iova, size_t size) +{ + struct protection_domain *domain = to_pdomain(dom); + struct io_pgtable_ops *ops = &domain->iop.iop.ops; + + if (ops->map_pages) + domain_flush_np_cache(domain, iova, size); +} + +static int amd_iommu_map_pages(struct iommu_domain *dom, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int iommu_prot, gfp_t gfp, size_t *mapped) +{ + struct protection_domain *domain = to_pdomain(dom); + struct io_pgtable_ops *ops = &domain->iop.iop.ops; + int prot = 0; + int ret = -EINVAL; + + if ((amd_iommu_pgtable == AMD_IOMMU_V1) && + (domain->iop.mode == PAGE_MODE_NONE)) + return -EINVAL; + + if (iommu_prot & IOMMU_READ) + prot |= IOMMU_PROT_IR; + if (iommu_prot & IOMMU_WRITE) + prot |= IOMMU_PROT_IW; + + if (ops->map_pages) { + ret = ops->map_pages(ops, iova, paddr, pgsize, + pgcount, prot, gfp, mapped); + } + + return ret; +} + +static void amd_iommu_iotlb_gather_add_page(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ + /* + * AMD's IOMMU can flush as many pages as necessary in a single flush. + * Unless we run in a virtual machine, which can be inferred according + * to whether "non-present cache" is on, it is probably best to prefer + * (potentially) too extensive TLB flushing (i.e., more misses) over + * mutliple TLB flushes (i.e., more flushes). For virtual machines the + * hypervisor needs to synchronize the host IOMMU PTEs with those of + * the guest, and the trade-off is different: unnecessary TLB flushes + * should be avoided. + */ + if (amd_iommu_np_cache && + iommu_iotlb_gather_is_disjoint(gather, iova, size)) + iommu_iotlb_sync(domain, gather); + + iommu_iotlb_gather_add_range(gather, iova, size); +} + +static size_t amd_iommu_unmap_pages(struct iommu_domain *dom, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) +{ + struct protection_domain *domain = to_pdomain(dom); + struct io_pgtable_ops *ops = &domain->iop.iop.ops; + size_t r; + + if ((amd_iommu_pgtable == AMD_IOMMU_V1) && + (domain->iop.mode == PAGE_MODE_NONE)) + return 0; + + r = (ops->unmap_pages) ? ops->unmap_pages(ops, iova, pgsize, pgcount, NULL) : 0; + + if (r) + amd_iommu_iotlb_gather_add_page(dom, gather, iova, r); + + return r; +} + +static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, + dma_addr_t iova) +{ + struct protection_domain *domain = to_pdomain(dom); + struct io_pgtable_ops *ops = &domain->iop.iop.ops; + + return ops->iova_to_phys(ops, iova); +} + +static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap) +{ + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return true; + case IOMMU_CAP_INTR_REMAP: + return (irq_remapping_enabled == 1); + case IOMMU_CAP_NOEXEC: + return false; + case IOMMU_CAP_PRE_BOOT_PROTECTION: + return amdr_ivrs_remap_support; + default: + break; + } + + return false; +} + +static void amd_iommu_get_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *region; + struct unity_map_entry *entry; + struct amd_iommu *iommu; + struct amd_iommu_pci_seg *pci_seg; + int devid, sbdf; + + sbdf = get_device_sbdf_id(dev); + if (sbdf < 0) + return; + + devid = PCI_SBDF_TO_DEVID(sbdf); + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return; + pci_seg = iommu->pci_seg; + + list_for_each_entry(entry, &pci_seg->unity_map, list) { + int type, prot = 0; + size_t length; + + if (devid < entry->devid_start || devid > entry->devid_end) + continue; + + type = IOMMU_RESV_DIRECT; + length = entry->address_end - entry->address_start; + if (entry->prot & IOMMU_PROT_IR) + prot |= IOMMU_READ; + if (entry->prot & IOMMU_PROT_IW) + prot |= IOMMU_WRITE; + if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE) + /* Exclusion range */ + type = IOMMU_RESV_RESERVED; + + region = iommu_alloc_resv_region(entry->address_start, + length, prot, type, + GFP_KERNEL); + if (!region) { + dev_err(dev, "Out of memory allocating dm-regions\n"); + return; + } + list_add_tail(®ion->list, head); + } + + region = iommu_alloc_resv_region(MSI_RANGE_START, + MSI_RANGE_END - MSI_RANGE_START + 1, + 0, IOMMU_RESV_MSI, GFP_KERNEL); + if (!region) + return; + list_add_tail(®ion->list, head); + + region = iommu_alloc_resv_region(HT_RANGE_START, + HT_RANGE_END - HT_RANGE_START + 1, + 0, IOMMU_RESV_RESERVED, GFP_KERNEL); + if (!region) + return; + list_add_tail(®ion->list, head); +} + +bool amd_iommu_is_attach_deferred(struct device *dev) +{ + struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); + + return dev_data->defer_attach; +} +EXPORT_SYMBOL_GPL(amd_iommu_is_attach_deferred); + +static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct protection_domain *dom = to_pdomain(domain); + unsigned long flags; + + spin_lock_irqsave(&dom->lock, flags); + amd_iommu_domain_flush_tlb_pde(dom); + amd_iommu_domain_flush_complete(dom); + spin_unlock_irqrestore(&dom->lock, flags); +} + +static void amd_iommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) +{ + struct protection_domain *dom = to_pdomain(domain); + unsigned long flags; + + spin_lock_irqsave(&dom->lock, flags); + domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1); + amd_iommu_domain_flush_complete(dom); + spin_unlock_irqrestore(&dom->lock, flags); +} + +static int amd_iommu_def_domain_type(struct device *dev) +{ + struct iommu_dev_data *dev_data; + + dev_data = dev_iommu_priv_get(dev); + if (!dev_data) + return 0; + + /* + * Do not identity map IOMMUv2 capable devices when: + * - memory encryption is active, because some of those devices + * (AMD GPUs) don't have the encryption bit in their DMA-mask + * and require remapping. + * - SNP is enabled, because it prohibits DTE[Mode]=0. + */ + if (dev_data->iommu_v2 && + !cc_platform_has(CC_ATTR_MEM_ENCRYPT) && + !amd_iommu_snp_en) { + return IOMMU_DOMAIN_IDENTITY; + } + + return 0; +} + +static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain) +{ + /* IOMMU_PTE_FC is always set */ + return true; +} + +const struct iommu_ops amd_iommu_ops = { + .capable = amd_iommu_capable, + .domain_alloc = amd_iommu_domain_alloc, + .probe_device = amd_iommu_probe_device, + .release_device = amd_iommu_release_device, + .probe_finalize = amd_iommu_probe_finalize, + .device_group = amd_iommu_device_group, + .get_resv_regions = amd_iommu_get_resv_regions, + .is_attach_deferred = amd_iommu_is_attach_deferred, + .pgsize_bitmap = AMD_IOMMU_PGSIZES, + .def_domain_type = amd_iommu_def_domain_type, + .default_domain_ops = &(const struct iommu_domain_ops) { + .attach_dev = amd_iommu_attach_device, + .detach_dev = amd_iommu_detach_device, + .map_pages = amd_iommu_map_pages, + .unmap_pages = amd_iommu_unmap_pages, + .iotlb_sync_map = amd_iommu_iotlb_sync_map, + .iova_to_phys = amd_iommu_iova_to_phys, + .flush_iotlb_all = amd_iommu_flush_iotlb_all, + .iotlb_sync = amd_iommu_iotlb_sync, + .free = amd_iommu_domain_free, + .enforce_cache_coherency = amd_iommu_enforce_cache_coherency, + } +}; + +/***************************************************************************** + * + * The next functions do a basic initialization of IOMMU for pass through + * mode + * + * In passthrough mode the IOMMU is initialized and enabled but not used for + * DMA-API translation. + * + *****************************************************************************/ + +/* IOMMUv2 specific functions */ +int amd_iommu_register_ppr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&ppr_notifier, nb); +} +EXPORT_SYMBOL(amd_iommu_register_ppr_notifier); + +int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&ppr_notifier, nb); +} +EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); + +void amd_iommu_domain_direct_map(struct iommu_domain *dom) +{ + struct protection_domain *domain = to_pdomain(dom); + unsigned long flags; + + spin_lock_irqsave(&domain->lock, flags); + + if (domain->iop.pgtbl_cfg.tlb) + free_io_pgtable_ops(&domain->iop.iop.ops); + + spin_unlock_irqrestore(&domain->lock, flags); +} +EXPORT_SYMBOL(amd_iommu_domain_direct_map); + +/* Note: This function expects iommu_domain->lock to be held prior calling the function. */ +static int domain_enable_v2(struct protection_domain *domain, int pasids) +{ + int levels; + + /* Number of GCR3 table levels required */ + for (levels = 0; (pasids - 1) & ~0x1ff; pasids >>= 9) + levels += 1; + + if (levels > amd_iommu_max_glx_val) + return -EINVAL; + + domain->gcr3_tbl = (void *)get_zeroed_page(GFP_ATOMIC); + if (domain->gcr3_tbl == NULL) + return -ENOMEM; + + domain->glx = levels; + domain->flags |= PD_IOMMUV2_MASK; + + amd_iommu_domain_update(domain); + + return 0; +} + +int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids) +{ + struct protection_domain *pdom = to_pdomain(dom); + unsigned long flags; + int ret; + + spin_lock_irqsave(&pdom->lock, flags); + + /* + * Save us all sanity checks whether devices already in the + * domain support IOMMUv2. Just force that the domain has no + * devices attached when it is switched into IOMMUv2 mode. + */ + ret = -EBUSY; + if (pdom->dev_cnt > 0 || pdom->flags & PD_IOMMUV2_MASK) + goto out; + + if (!pdom->gcr3_tbl) + ret = domain_enable_v2(pdom, pasids); + +out: + spin_unlock_irqrestore(&pdom->lock, flags); + return ret; +} +EXPORT_SYMBOL(amd_iommu_domain_enable_v2); + +static int __flush_pasid(struct protection_domain *domain, u32 pasid, + u64 address, bool size) +{ + struct iommu_dev_data *dev_data; + struct iommu_cmd cmd; + int i, ret; + + if (!(domain->flags & PD_IOMMUV2_MASK)) + return -EINVAL; + + build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size); + + /* + * IOMMU TLB needs to be flushed before Device TLB to + * prevent device TLB refill from IOMMU TLB + */ + for (i = 0; i < amd_iommu_get_num_iommus(); ++i) { + if (domain->dev_iommu[i] == 0) + continue; + + ret = iommu_queue_command(amd_iommus[i], &cmd); + if (ret != 0) + goto out; + } + + /* Wait until IOMMU TLB flushes are complete */ + amd_iommu_domain_flush_complete(domain); + + /* Now flush device TLBs */ + list_for_each_entry(dev_data, &domain->dev_list, list) { + struct amd_iommu *iommu; + int qdep; + + /* + There might be non-IOMMUv2 capable devices in an IOMMUv2 + * domain. + */ + if (!dev_data->ats.enabled) + continue; + + qdep = dev_data->ats.qdep; + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + continue; + build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid, + qdep, address, size); + + ret = iommu_queue_command(iommu, &cmd); + if (ret != 0) + goto out; + } + + /* Wait until all device TLBs are flushed */ + amd_iommu_domain_flush_complete(domain); + + ret = 0; + +out: + + return ret; +} + +static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid, + u64 address) +{ + return __flush_pasid(domain, pasid, address, false); +} + +int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, + u64 address) +{ + struct protection_domain *domain = to_pdomain(dom); + unsigned long flags; + int ret; + + spin_lock_irqsave(&domain->lock, flags); + ret = __amd_iommu_flush_page(domain, pasid, address); + spin_unlock_irqrestore(&domain->lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_flush_page); + +static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid) +{ + return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, + true); +} + +int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid) +{ + struct protection_domain *domain = to_pdomain(dom); + unsigned long flags; + int ret; + + spin_lock_irqsave(&domain->lock, flags); + ret = __amd_iommu_flush_tlb(domain, pasid); + spin_unlock_irqrestore(&domain->lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_flush_tlb); + +static u64 *__get_gcr3_pte(u64 *root, int level, u32 pasid, bool alloc) +{ + int index; + u64 *pte; + + while (true) { + + index = (pasid >> (9 * level)) & 0x1ff; + pte = &root[index]; + + if (level == 0) + break; + + if (!(*pte & GCR3_VALID)) { + if (!alloc) + return NULL; + + root = (void *)get_zeroed_page(GFP_ATOMIC); + if (root == NULL) + return NULL; + + *pte = iommu_virt_to_phys(root) | GCR3_VALID; + } + + root = iommu_phys_to_virt(*pte & PAGE_MASK); + + level -= 1; + } + + return pte; +} + +static int __set_gcr3(struct protection_domain *domain, u32 pasid, + unsigned long cr3) +{ + u64 *pte; + + if (domain->iop.mode != PAGE_MODE_NONE) + return -EINVAL; + + pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true); + if (pte == NULL) + return -ENOMEM; + + *pte = (cr3 & PAGE_MASK) | GCR3_VALID; + + return __amd_iommu_flush_tlb(domain, pasid); +} + +static int __clear_gcr3(struct protection_domain *domain, u32 pasid) +{ + u64 *pte; + + if (domain->iop.mode != PAGE_MODE_NONE) + return -EINVAL; + + pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false); + if (pte == NULL) + return 0; + + *pte = 0; + + return __amd_iommu_flush_tlb(domain, pasid); +} + +int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid, + unsigned long cr3) +{ + struct protection_domain *domain = to_pdomain(dom); + unsigned long flags; + int ret; + + spin_lock_irqsave(&domain->lock, flags); + ret = __set_gcr3(domain, pasid, cr3); + spin_unlock_irqrestore(&domain->lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_domain_set_gcr3); + +int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid) +{ + struct protection_domain *domain = to_pdomain(dom); + unsigned long flags; + int ret; + + spin_lock_irqsave(&domain->lock, flags); + ret = __clear_gcr3(domain, pasid); + spin_unlock_irqrestore(&domain->lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3); + +int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid, + int status, int tag) +{ + struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; + struct iommu_cmd cmd; + + dev_data = dev_iommu_priv_get(&pdev->dev); + iommu = rlookup_amd_iommu(&pdev->dev); + if (!iommu) + return -ENODEV; + + build_complete_ppr(&cmd, dev_data->devid, pasid, status, + tag, dev_data->pri_tlp); + + return iommu_queue_command(iommu, &cmd); +} +EXPORT_SYMBOL(amd_iommu_complete_ppr); + +int amd_iommu_device_info(struct pci_dev *pdev, + struct amd_iommu_device_info *info) +{ + int max_pasids; + int pos; + + if (pdev == NULL || info == NULL) + return -EINVAL; + + if (!amd_iommu_v2_supported()) + return -EINVAL; + + memset(info, 0, sizeof(*info)); + + if (pci_ats_supported(pdev)) + info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + if (pos) + info->flags |= AMD_IOMMU_DEVICE_FLAG_PRI_SUP; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); + if (pos) { + int features; + + max_pasids = 1 << (9 * (amd_iommu_max_glx_val + 1)); + max_pasids = min(max_pasids, (1 << 20)); + + info->flags |= AMD_IOMMU_DEVICE_FLAG_PASID_SUP; + info->max_pasids = min(pci_max_pasids(pdev), max_pasids); + + features = pci_pasid_features(pdev); + if (features & PCI_PASID_CAP_EXEC) + info->flags |= AMD_IOMMU_DEVICE_FLAG_EXEC_SUP; + if (features & PCI_PASID_CAP_PRIV) + info->flags |= AMD_IOMMU_DEVICE_FLAG_PRIV_SUP; + } + + return 0; +} +EXPORT_SYMBOL(amd_iommu_device_info); + +#ifdef CONFIG_IRQ_REMAP + +/***************************************************************************** + * + * Interrupt Remapping Implementation + * + *****************************************************************************/ + +static struct irq_chip amd_ir_chip; +static DEFINE_SPINLOCK(iommu_table_lock); + +static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid, + struct irq_remap_table *table) +{ + u64 dte; + struct dev_table_entry *dev_table = get_dev_table(iommu); + + dte = dev_table[devid].data[2]; + dte &= ~DTE_IRQ_PHYS_ADDR_MASK; + dte |= iommu_virt_to_phys(table->table); + dte |= DTE_IRQ_REMAP_INTCTL; + dte |= DTE_INTTABLEN; + dte |= DTE_IRQ_REMAP_ENABLE; + + dev_table[devid].data[2] = dte; +} + +static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid) +{ + struct irq_remap_table *table; + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + if (WARN_ONCE(!pci_seg->rlookup_table[devid], + "%s: no iommu for devid %x:%x\n", + __func__, pci_seg->id, devid)) + return NULL; + + table = pci_seg->irq_lookup_table[devid]; + if (WARN_ONCE(!table, "%s: no table for devid %x:%x\n", + __func__, pci_seg->id, devid)) + return NULL; + + return table; +} + +static struct irq_remap_table *__alloc_irq_table(void) +{ + struct irq_remap_table *table; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return NULL; + + table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL); + if (!table->table) { + kfree(table); + return NULL; + } + raw_spin_lock_init(&table->lock); + + if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + memset(table->table, 0, + MAX_IRQS_PER_TABLE * sizeof(u32)); + else + memset(table->table, 0, + (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2))); + return table; +} + +static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid, + struct irq_remap_table *table) +{ + struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; + + pci_seg->irq_lookup_table[devid] = table; + set_dte_irq_entry(iommu, devid, table); + iommu_flush_dte(iommu, devid); +} + +static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias, + void *data) +{ + struct irq_remap_table *table = data; + struct amd_iommu_pci_seg *pci_seg; + struct amd_iommu *iommu = rlookup_amd_iommu(&pdev->dev); + + if (!iommu) + return -EINVAL; + + pci_seg = iommu->pci_seg; + pci_seg->irq_lookup_table[alias] = table; + set_dte_irq_entry(iommu, alias, table); + iommu_flush_dte(pci_seg->rlookup_table[alias], alias); + + return 0; +} + +static struct irq_remap_table *alloc_irq_table(struct amd_iommu *iommu, + u16 devid, struct pci_dev *pdev) +{ + struct irq_remap_table *table = NULL; + struct irq_remap_table *new_table = NULL; + struct amd_iommu_pci_seg *pci_seg; + unsigned long flags; + u16 alias; + + spin_lock_irqsave(&iommu_table_lock, flags); + + pci_seg = iommu->pci_seg; + table = pci_seg->irq_lookup_table[devid]; + if (table) + goto out_unlock; + + alias = pci_seg->alias_table[devid]; + table = pci_seg->irq_lookup_table[alias]; + if (table) { + set_remap_table_entry(iommu, devid, table); + goto out_wait; + } + spin_unlock_irqrestore(&iommu_table_lock, flags); + + /* Nothing there yet, allocate new irq remapping table */ + new_table = __alloc_irq_table(); + if (!new_table) + return NULL; + + spin_lock_irqsave(&iommu_table_lock, flags); + + table = pci_seg->irq_lookup_table[devid]; + if (table) + goto out_unlock; + + table = pci_seg->irq_lookup_table[alias]; + if (table) { + set_remap_table_entry(iommu, devid, table); + goto out_wait; + } + + table = new_table; + new_table = NULL; + + if (pdev) + pci_for_each_dma_alias(pdev, set_remap_table_entry_alias, + table); + else + set_remap_table_entry(iommu, devid, table); + + if (devid != alias) + set_remap_table_entry(iommu, alias, table); + +out_wait: + iommu_completion_wait(iommu); + +out_unlock: + spin_unlock_irqrestore(&iommu_table_lock, flags); + + if (new_table) { + kmem_cache_free(amd_iommu_irq_cache, new_table->table); + kfree(new_table); + } + return table; +} + +static int alloc_irq_index(struct amd_iommu *iommu, u16 devid, int count, + bool align, struct pci_dev *pdev) +{ + struct irq_remap_table *table; + int index, c, alignment = 1; + unsigned long flags; + + table = alloc_irq_table(iommu, devid, pdev); + if (!table) + return -ENODEV; + + if (align) + alignment = roundup_pow_of_two(count); + + raw_spin_lock_irqsave(&table->lock, flags); + + /* Scan table for free entries */ + for (index = ALIGN(table->min_index, alignment), c = 0; + index < MAX_IRQS_PER_TABLE;) { + if (!iommu->irte_ops->is_allocated(table, index)) { + c += 1; + } else { + c = 0; + index = ALIGN(index + 1, alignment); + continue; + } + + if (c == count) { + for (; c != 0; --c) + iommu->irte_ops->set_allocated(table, index - c + 1); + + index -= count - 1; + goto out; + } + + index++; + } + + index = -ENOSPC; + +out: + raw_spin_unlock_irqrestore(&table->lock, flags); + + return index; +} + +static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, + struct irte_ga *irte, struct amd_ir_data *data) +{ + bool ret; + struct irq_remap_table *table; + unsigned long flags; + struct irte_ga *entry; + + table = get_irq_table(iommu, devid); + if (!table) + return -ENOMEM; + + raw_spin_lock_irqsave(&table->lock, flags); + + entry = (struct irte_ga *)table->table; + entry = &entry[index]; + + ret = cmpxchg_double(&entry->lo.val, &entry->hi.val, + entry->lo.val, entry->hi.val, + irte->lo.val, irte->hi.val); + /* + * We use cmpxchg16 to atomically update the 128-bit IRTE, + * and it cannot be updated by the hardware or other processors + * behind us, so the return value of cmpxchg16 should be the + * same as the old value. + */ + WARN_ON(!ret); + + if (data) + data->ref = entry; + + raw_spin_unlock_irqrestore(&table->lock, flags); + + iommu_flush_irt(iommu, devid); + iommu_completion_wait(iommu); + + return 0; +} + +static int modify_irte(struct amd_iommu *iommu, + u16 devid, int index, union irte *irte) +{ + struct irq_remap_table *table; + unsigned long flags; + + table = get_irq_table(iommu, devid); + if (!table) + return -ENOMEM; + + raw_spin_lock_irqsave(&table->lock, flags); + table->table[index] = irte->val; + raw_spin_unlock_irqrestore(&table->lock, flags); + + iommu_flush_irt(iommu, devid); + iommu_completion_wait(iommu); + + return 0; +} + +static void free_irte(struct amd_iommu *iommu, u16 devid, int index) +{ + struct irq_remap_table *table; + unsigned long flags; + + table = get_irq_table(iommu, devid); + if (!table) + return; + + raw_spin_lock_irqsave(&table->lock, flags); + iommu->irte_ops->clear_allocated(table, index); + raw_spin_unlock_irqrestore(&table->lock, flags); + + iommu_flush_irt(iommu, devid); + iommu_completion_wait(iommu); +} + +static void irte_prepare(void *entry, + u32 delivery_mode, bool dest_mode, + u8 vector, u32 dest_apicid, int devid) +{ + union irte *irte = (union irte *) entry; + + irte->val = 0; + irte->fields.vector = vector; + irte->fields.int_type = delivery_mode; + irte->fields.destination = dest_apicid; + irte->fields.dm = dest_mode; + irte->fields.valid = 1; +} + +static void irte_ga_prepare(void *entry, + u32 delivery_mode, bool dest_mode, + u8 vector, u32 dest_apicid, int devid) +{ + struct irte_ga *irte = (struct irte_ga *) entry; + + irte->lo.val = 0; + irte->hi.val = 0; + irte->lo.fields_remap.int_type = delivery_mode; + irte->lo.fields_remap.dm = dest_mode; + irte->hi.fields.vector = vector; + irte->lo.fields_remap.destination = APICID_TO_IRTE_DEST_LO(dest_apicid); + irte->hi.fields.destination = APICID_TO_IRTE_DEST_HI(dest_apicid); + irte->lo.fields_remap.valid = 1; +} + +static void irte_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index) +{ + union irte *irte = (union irte *) entry; + + irte->fields.valid = 1; + modify_irte(iommu, devid, index, irte); +} + +static void irte_ga_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index) +{ + struct irte_ga *irte = (struct irte_ga *) entry; + + irte->lo.fields_remap.valid = 1; + modify_irte_ga(iommu, devid, index, irte, NULL); +} + +static void irte_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index) +{ + union irte *irte = (union irte *) entry; + + irte->fields.valid = 0; + modify_irte(iommu, devid, index, irte); +} + +static void irte_ga_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index) +{ + struct irte_ga *irte = (struct irte_ga *) entry; + + irte->lo.fields_remap.valid = 0; + modify_irte_ga(iommu, devid, index, irte, NULL); +} + +static void irte_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index, + u8 vector, u32 dest_apicid) +{ + union irte *irte = (union irte *) entry; + + irte->fields.vector = vector; + irte->fields.destination = dest_apicid; + modify_irte(iommu, devid, index, irte); +} + +static void irte_ga_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index, + u8 vector, u32 dest_apicid) +{ + struct irte_ga *irte = (struct irte_ga *) entry; + + if (!irte->lo.fields_remap.guest_mode) { + irte->hi.fields.vector = vector; + irte->lo.fields_remap.destination = + APICID_TO_IRTE_DEST_LO(dest_apicid); + irte->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(dest_apicid); + modify_irte_ga(iommu, devid, index, irte, NULL); + } +} + +#define IRTE_ALLOCATED (~1U) +static void irte_set_allocated(struct irq_remap_table *table, int index) +{ + table->table[index] = IRTE_ALLOCATED; +} + +static void irte_ga_set_allocated(struct irq_remap_table *table, int index) +{ + struct irte_ga *ptr = (struct irte_ga *)table->table; + struct irte_ga *irte = &ptr[index]; + + memset(&irte->lo.val, 0, sizeof(u64)); + memset(&irte->hi.val, 0, sizeof(u64)); + irte->hi.fields.vector = 0xff; +} + +static bool irte_is_allocated(struct irq_remap_table *table, int index) +{ + union irte *ptr = (union irte *)table->table; + union irte *irte = &ptr[index]; + + return irte->val != 0; +} + +static bool irte_ga_is_allocated(struct irq_remap_table *table, int index) +{ + struct irte_ga *ptr = (struct irte_ga *)table->table; + struct irte_ga *irte = &ptr[index]; + + return irte->hi.fields.vector != 0; +} + +static void irte_clear_allocated(struct irq_remap_table *table, int index) +{ + table->table[index] = 0; +} + +static void irte_ga_clear_allocated(struct irq_remap_table *table, int index) +{ + struct irte_ga *ptr = (struct irte_ga *)table->table; + struct irte_ga *irte = &ptr[index]; + + memset(&irte->lo.val, 0, sizeof(u64)); + memset(&irte->hi.val, 0, sizeof(u64)); +} + +static int get_devid(struct irq_alloc_info *info) +{ + switch (info->type) { + case X86_IRQ_ALLOC_TYPE_IOAPIC: + return get_ioapic_devid(info->devid); + case X86_IRQ_ALLOC_TYPE_HPET: + return get_hpet_devid(info->devid); + case X86_IRQ_ALLOC_TYPE_PCI_MSI: + case X86_IRQ_ALLOC_TYPE_PCI_MSIX: + return get_device_sbdf_id(msi_desc_to_dev(info->desc)); + default: + WARN_ON_ONCE(1); + return -1; + } +} + +struct irq_remap_ops amd_iommu_irq_ops = { + .prepare = amd_iommu_prepare, + .enable = amd_iommu_enable, + .disable = amd_iommu_disable, + .reenable = amd_iommu_reenable, + .enable_faulting = amd_iommu_enable_faulting, +}; + +static void fill_msi_msg(struct msi_msg *msg, u32 index) +{ + msg->data = index; + msg->address_lo = 0; + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; +} + +static void irq_remapping_prepare_irte(struct amd_ir_data *data, + struct irq_cfg *irq_cfg, + struct irq_alloc_info *info, + int devid, int index, int sub_handle) +{ + struct irq_2_irte *irte_info = &data->irq_2_irte; + struct amd_iommu *iommu = data->iommu; + + if (!iommu) + return; + + data->irq_2_irte.devid = devid; + data->irq_2_irte.index = index + sub_handle; + iommu->irte_ops->prepare(data->entry, apic->delivery_mode, + apic->dest_mode_logical, irq_cfg->vector, + irq_cfg->dest_apicid, devid); + + switch (info->type) { + case X86_IRQ_ALLOC_TYPE_IOAPIC: + case X86_IRQ_ALLOC_TYPE_HPET: + case X86_IRQ_ALLOC_TYPE_PCI_MSI: + case X86_IRQ_ALLOC_TYPE_PCI_MSIX: + fill_msi_msg(&data->msi_entry, irte_info->index); + break; + + default: + BUG_ON(1); + break; + } +} + +struct amd_irte_ops irte_32_ops = { + .prepare = irte_prepare, + .activate = irte_activate, + .deactivate = irte_deactivate, + .set_affinity = irte_set_affinity, + .set_allocated = irte_set_allocated, + .is_allocated = irte_is_allocated, + .clear_allocated = irte_clear_allocated, +}; + +struct amd_irte_ops irte_128_ops = { + .prepare = irte_ga_prepare, + .activate = irte_ga_activate, + .deactivate = irte_ga_deactivate, + .set_affinity = irte_ga_set_affinity, + .set_allocated = irte_ga_set_allocated, + .is_allocated = irte_ga_is_allocated, + .clear_allocated = irte_ga_clear_allocated, +}; + +static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct irq_data *irq_data; + struct amd_ir_data *data = NULL; + struct amd_iommu *iommu; + struct irq_cfg *cfg; + int i, ret, devid, seg, sbdf; + int index; + + if (!info) + return -EINVAL; + if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI && + info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX) + return -EINVAL; + + /* + * With IRQ remapping enabled, don't need contiguous CPU vectors + * to support multiple MSI interrupts. + */ + if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) + info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + + sbdf = get_devid(info); + if (sbdf < 0) + return -EINVAL; + + seg = PCI_SBDF_TO_SEGID(sbdf); + devid = PCI_SBDF_TO_DEVID(sbdf); + iommu = __rlookup_amd_iommu(seg, devid); + if (!iommu) + return -EINVAL; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) { + struct irq_remap_table *table; + + table = alloc_irq_table(iommu, devid, NULL); + if (table) { + if (!table->min_index) { + /* + * Keep the first 32 indexes free for IOAPIC + * interrupts. + */ + table->min_index = 32; + for (i = 0; i < 32; ++i) + iommu->irte_ops->set_allocated(table, i); + } + WARN_ON(table->min_index != 32); + index = info->ioapic.pin; + } else { + index = -ENOMEM; + } + } else if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI || + info->type == X86_IRQ_ALLOC_TYPE_PCI_MSIX) { + bool align = (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI); + + index = alloc_irq_index(iommu, devid, nr_irqs, align, + msi_desc_to_pci_dev(info->desc)); + } else { + index = alloc_irq_index(iommu, devid, nr_irqs, false, NULL); + } + + if (index < 0) { + pr_warn("Failed to allocate IRTE\n"); + ret = index; + goto out_free_parent; + } + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + cfg = irq_data ? irqd_cfg(irq_data) : NULL; + if (!cfg) { + ret = -EINVAL; + goto out_free_data; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out_free_data; + + if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + data->entry = kzalloc(sizeof(union irte), GFP_KERNEL); + else + data->entry = kzalloc(sizeof(struct irte_ga), + GFP_KERNEL); + if (!data->entry) { + kfree(data); + goto out_free_data; + } + + data->iommu = iommu; + irq_data->hwirq = (devid << 16) + i; + irq_data->chip_data = data; + irq_data->chip = &amd_ir_chip; + irq_remapping_prepare_irte(data, cfg, info, devid, index, i); + irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT); + } + + return 0; + +out_free_data: + for (i--; i >= 0; i--) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data) + kfree(irq_data->chip_data); + } + for (i = 0; i < nr_irqs; i++) + free_irte(iommu, devid, index + i); +out_free_parent: + irq_domain_free_irqs_common(domain, virq, nr_irqs); + return ret; +} + +static void irq_remapping_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_2_irte *irte_info; + struct irq_data *irq_data; + struct amd_ir_data *data; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + irte_info = &data->irq_2_irte; + free_irte(data->iommu, irte_info->devid, irte_info->index); + kfree(data->entry); + kfree(data); + } + } + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu, + struct amd_ir_data *ir_data, + struct irq_2_irte *irte_info, + struct irq_cfg *cfg); + +static int irq_remapping_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool reserve) +{ + struct amd_ir_data *data = irq_data->chip_data; + struct irq_2_irte *irte_info = &data->irq_2_irte; + struct amd_iommu *iommu = data->iommu; + struct irq_cfg *cfg = irqd_cfg(irq_data); + + if (!iommu) + return 0; + + iommu->irte_ops->activate(iommu, data->entry, irte_info->devid, + irte_info->index); + amd_ir_update_irte(irq_data, iommu, data, irte_info, cfg); + return 0; +} + +static void irq_remapping_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct amd_ir_data *data = irq_data->chip_data; + struct irq_2_irte *irte_info = &data->irq_2_irte; + struct amd_iommu *iommu = data->iommu; + + if (iommu) + iommu->irte_ops->deactivate(iommu, data->entry, irte_info->devid, + irte_info->index); +} + +static int irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + struct amd_iommu *iommu; + int devid = -1; + + if (!amd_iommu_irq_remap) + return 0; + + if (x86_fwspec_is_ioapic(fwspec)) + devid = get_ioapic_devid(fwspec->param[0]); + else if (x86_fwspec_is_hpet(fwspec)) + devid = get_hpet_devid(fwspec->param[0]); + + if (devid < 0) + return 0; + iommu = __rlookup_amd_iommu((devid >> 16), (devid & 0xffff)); + + return iommu && iommu->ir_domain == d; +} + +static const struct irq_domain_ops amd_ir_domain_ops = { + .select = irq_remapping_select, + .alloc = irq_remapping_alloc, + .free = irq_remapping_free, + .activate = irq_remapping_activate, + .deactivate = irq_remapping_deactivate, +}; + +int amd_iommu_activate_guest_mode(void *data) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + u64 valid; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry) + return 0; + + valid = entry->lo.fields_vapic.valid; + + entry->lo.val = 0; + entry->hi.val = 0; + + entry->lo.fields_vapic.valid = valid; + entry->lo.fields_vapic.guest_mode = 1; + entry->lo.fields_vapic.ga_log_intr = 1; + entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr; + entry->hi.fields.vector = ir_data->ga_vector; + entry->lo.fields_vapic.ga_tag = ir_data->ga_tag; + + return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry, ir_data); +} +EXPORT_SYMBOL(amd_iommu_activate_guest_mode); + +int amd_iommu_deactivate_guest_mode(void *data) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + struct irq_cfg *cfg = ir_data->cfg; + u64 valid; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || + !entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + valid = entry->lo.fields_remap.valid; + + entry->lo.val = 0; + entry->hi.val = 0; + + entry->lo.fields_remap.valid = valid; + entry->lo.fields_remap.dm = apic->dest_mode_logical; + entry->lo.fields_remap.int_type = apic->delivery_mode; + entry->hi.fields.vector = cfg->vector; + entry->lo.fields_remap.destination = + APICID_TO_IRTE_DEST_LO(cfg->dest_apicid); + entry->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); + + return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry, ir_data); +} +EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); + +static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) +{ + int ret; + struct amd_iommu_pi_data *pi_data = vcpu_info; + struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data; + struct amd_ir_data *ir_data = data->chip_data; + struct irq_2_irte *irte_info = &ir_data->irq_2_irte; + struct iommu_dev_data *dev_data; + + if (ir_data->iommu == NULL) + return -EINVAL; + + dev_data = search_dev_data(ir_data->iommu, irte_info->devid); + + /* Note: + * This device has never been set up for guest mode. + * we should not modify the IRTE + */ + if (!dev_data || !dev_data->use_vapic) + return 0; + + ir_data->cfg = irqd_cfg(data); + pi_data->ir_data = ir_data; + + /* Note: + * SVM tries to set up for VAPIC mode, but we are in + * legacy mode. So, we force legacy mode instead. + */ + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) { + pr_debug("%s: Fall back to using intr legacy remap\n", + __func__); + pi_data->is_guest_mode = false; + } + + pi_data->prev_ga_tag = ir_data->cached_ga_tag; + if (pi_data->is_guest_mode) { + ir_data->ga_root_ptr = (pi_data->base >> 12); + ir_data->ga_vector = vcpu_pi_info->vector; + ir_data->ga_tag = pi_data->ga_tag; + ret = amd_iommu_activate_guest_mode(ir_data); + if (!ret) + ir_data->cached_ga_tag = pi_data->ga_tag; + } else { + ret = amd_iommu_deactivate_guest_mode(ir_data); + + /* + * This communicates the ga_tag back to the caller + * so that it can do all the necessary clean up. + */ + if (!ret) + ir_data->cached_ga_tag = 0; + } + + return ret; +} + + +static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu, + struct amd_ir_data *ir_data, + struct irq_2_irte *irte_info, + struct irq_cfg *cfg) +{ + + /* + * Atomically updates the IRTE with the new destination, vector + * and flushes the interrupt entry cache. + */ + iommu->irte_ops->set_affinity(iommu, ir_data->entry, irte_info->devid, + irte_info->index, cfg->vector, + cfg->dest_apicid); +} + +static int amd_ir_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct amd_ir_data *ir_data = data->chip_data; + struct irq_2_irte *irte_info = &ir_data->irq_2_irte; + struct irq_cfg *cfg = irqd_cfg(data); + struct irq_data *parent = data->parent_data; + struct amd_iommu *iommu = ir_data->iommu; + int ret; + + if (!iommu) + return -ENODEV; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + amd_ir_update_irte(data, iommu, ir_data, irte_info, cfg); + /* + * After this point, all the interrupts will start arriving + * at the new destination. So, time to cleanup the previous + * vector allocation. + */ + send_cleanup_vector(cfg); + + return IRQ_SET_MASK_OK_DONE; +} + +static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) +{ + struct amd_ir_data *ir_data = irq_data->chip_data; + + *msg = ir_data->msi_entry; +} + +static struct irq_chip amd_ir_chip = { + .name = "AMD-IR", + .irq_ack = apic_ack_irq, + .irq_set_affinity = amd_ir_set_affinity, + .irq_set_vcpu_affinity = amd_ir_set_vcpu_affinity, + .irq_compose_msi_msg = ir_compose_msi_msg, +}; + +int amd_iommu_create_irq_domain(struct amd_iommu *iommu) +{ + struct fwnode_handle *fn; + + fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index); + if (!fn) + return -ENOMEM; + iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu); + if (!iommu->ir_domain) { + irq_domain_free_fwnode(fn); + return -ENOMEM; + } + + iommu->ir_domain->parent = arch_get_ir_parent_domain(); + iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain, + "AMD-IR-MSI", + iommu->index); + return 0; +} + +int amd_iommu_update_ga(int cpu, bool is_run, void *data) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct irq_remap_table *table; + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + int devid = ir_data->irq_2_irte.devid; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + struct irte_ga *ref = (struct irte_ga *) ir_data->ref; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || + !ref || !entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + iommu = ir_data->iommu; + if (!iommu) + return -ENODEV; + + table = get_irq_table(iommu, devid); + if (!table) + return -ENODEV; + + raw_spin_lock_irqsave(&table->lock, flags); + + if (ref->lo.fields_vapic.guest_mode) { + if (cpu >= 0) { + ref->lo.fields_vapic.destination = + APICID_TO_IRTE_DEST_LO(cpu); + ref->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cpu); + } + ref->lo.fields_vapic.is_run = is_run; + barrier(); + } + + raw_spin_unlock_irqrestore(&table->lock, flags); + + iommu_flush_irt(iommu, devid); + iommu_completion_wait(iommu); + return 0; +} +EXPORT_SYMBOL(amd_iommu_update_ga); +#endif diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c new file mode 100644 index 000000000..4caa02304 --- /dev/null +++ b/drivers/iommu/amd/iommu_v2.c @@ -0,0 +1,991 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2010-2012 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "amd_iommu.h" + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Joerg Roedel "); + +#define PRI_QUEUE_SIZE 512 + +struct pri_queue { + atomic_t inflight; + bool finish; + int status; +}; + +struct pasid_state { + struct list_head list; /* For global state-list */ + refcount_t count; /* Reference count */ + unsigned mmu_notifier_count; /* Counting nested mmu_notifier + calls */ + struct mm_struct *mm; /* mm_struct for the faults */ + struct mmu_notifier mn; /* mmu_notifier handle */ + struct pri_queue pri[PRI_QUEUE_SIZE]; /* PRI tag states */ + struct device_state *device_state; /* Link to our device_state */ + u32 pasid; /* PASID index */ + bool invalid; /* Used during setup and + teardown of the pasid */ + spinlock_t lock; /* Protect pri_queues and + mmu_notifer_count */ + wait_queue_head_t wq; /* To wait for count == 0 */ +}; + +struct device_state { + struct list_head list; + u32 sbdf; + atomic_t count; + struct pci_dev *pdev; + struct pasid_state **states; + struct iommu_domain *domain; + int pasid_levels; + int max_pasids; + amd_iommu_invalid_ppr_cb inv_ppr_cb; + amd_iommu_invalidate_ctx inv_ctx_cb; + spinlock_t lock; + wait_queue_head_t wq; +}; + +struct fault { + struct work_struct work; + struct device_state *dev_state; + struct pasid_state *state; + struct mm_struct *mm; + u64 address; + u32 pasid; + u16 tag; + u16 finish; + u16 flags; +}; + +static LIST_HEAD(state_list); +static DEFINE_SPINLOCK(state_lock); + +static struct workqueue_struct *iommu_wq; + +static void free_pasid_states(struct device_state *dev_state); + +static struct device_state *__get_device_state(u32 sbdf) +{ + struct device_state *dev_state; + + list_for_each_entry(dev_state, &state_list, list) { + if (dev_state->sbdf == sbdf) + return dev_state; + } + + return NULL; +} + +static struct device_state *get_device_state(u32 sbdf) +{ + struct device_state *dev_state; + unsigned long flags; + + spin_lock_irqsave(&state_lock, flags); + dev_state = __get_device_state(sbdf); + if (dev_state != NULL) + atomic_inc(&dev_state->count); + spin_unlock_irqrestore(&state_lock, flags); + + return dev_state; +} + +static void free_device_state(struct device_state *dev_state) +{ + struct iommu_group *group; + + /* Get rid of any remaining pasid states */ + free_pasid_states(dev_state); + + /* + * Wait until the last reference is dropped before freeing + * the device state. + */ + wait_event(dev_state->wq, !atomic_read(&dev_state->count)); + + /* + * First detach device from domain - No more PRI requests will arrive + * from that device after it is unbound from the IOMMUv2 domain. + */ + group = iommu_group_get(&dev_state->pdev->dev); + if (WARN_ON(!group)) + return; + + iommu_detach_group(dev_state->domain, group); + + iommu_group_put(group); + + /* Everything is down now, free the IOMMUv2 domain */ + iommu_domain_free(dev_state->domain); + + /* Finally get rid of the device-state */ + kfree(dev_state); +} + +static void put_device_state(struct device_state *dev_state) +{ + if (atomic_dec_and_test(&dev_state->count)) + wake_up(&dev_state->wq); +} + +/* Must be called under dev_state->lock */ +static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state, + u32 pasid, bool alloc) +{ + struct pasid_state **root, **ptr; + int level, index; + + level = dev_state->pasid_levels; + root = dev_state->states; + + while (true) { + + index = (pasid >> (9 * level)) & 0x1ff; + ptr = &root[index]; + + if (level == 0) + break; + + if (*ptr == NULL) { + if (!alloc) + return NULL; + + *ptr = (void *)get_zeroed_page(GFP_ATOMIC); + if (*ptr == NULL) + return NULL; + } + + root = (struct pasid_state **)*ptr; + level -= 1; + } + + return ptr; +} + +static int set_pasid_state(struct device_state *dev_state, + struct pasid_state *pasid_state, + u32 pasid) +{ + struct pasid_state **ptr; + unsigned long flags; + int ret; + + spin_lock_irqsave(&dev_state->lock, flags); + ptr = __get_pasid_state_ptr(dev_state, pasid, true); + + ret = -ENOMEM; + if (ptr == NULL) + goto out_unlock; + + ret = -ENOMEM; + if (*ptr != NULL) + goto out_unlock; + + *ptr = pasid_state; + + ret = 0; + +out_unlock: + spin_unlock_irqrestore(&dev_state->lock, flags); + + return ret; +} + +static void clear_pasid_state(struct device_state *dev_state, u32 pasid) +{ + struct pasid_state **ptr; + unsigned long flags; + + spin_lock_irqsave(&dev_state->lock, flags); + ptr = __get_pasid_state_ptr(dev_state, pasid, true); + + if (ptr == NULL) + goto out_unlock; + + *ptr = NULL; + +out_unlock: + spin_unlock_irqrestore(&dev_state->lock, flags); +} + +static struct pasid_state *get_pasid_state(struct device_state *dev_state, + u32 pasid) +{ + struct pasid_state **ptr, *ret = NULL; + unsigned long flags; + + spin_lock_irqsave(&dev_state->lock, flags); + ptr = __get_pasid_state_ptr(dev_state, pasid, false); + + if (ptr == NULL) + goto out_unlock; + + ret = *ptr; + if (ret) + refcount_inc(&ret->count); + +out_unlock: + spin_unlock_irqrestore(&dev_state->lock, flags); + + return ret; +} + +static void free_pasid_state(struct pasid_state *pasid_state) +{ + kfree(pasid_state); +} + +static void put_pasid_state(struct pasid_state *pasid_state) +{ + if (refcount_dec_and_test(&pasid_state->count)) + wake_up(&pasid_state->wq); +} + +static void put_pasid_state_wait(struct pasid_state *pasid_state) +{ + if (!refcount_dec_and_test(&pasid_state->count)) + wait_event(pasid_state->wq, !refcount_read(&pasid_state->count)); + free_pasid_state(pasid_state); +} + +static void unbind_pasid(struct pasid_state *pasid_state) +{ + struct iommu_domain *domain; + + domain = pasid_state->device_state->domain; + + /* + * Mark pasid_state as invalid, no more faults will we added to the + * work queue after this is visible everywhere. + */ + pasid_state->invalid = true; + + /* Make sure this is visible */ + smp_wmb(); + + /* After this the device/pasid can't access the mm anymore */ + amd_iommu_domain_clear_gcr3(domain, pasid_state->pasid); + + /* Make sure no more pending faults are in the queue */ + flush_workqueue(iommu_wq); +} + +static void free_pasid_states_level1(struct pasid_state **tbl) +{ + int i; + + for (i = 0; i < 512; ++i) { + if (tbl[i] == NULL) + continue; + + free_page((unsigned long)tbl[i]); + } +} + +static void free_pasid_states_level2(struct pasid_state **tbl) +{ + struct pasid_state **ptr; + int i; + + for (i = 0; i < 512; ++i) { + if (tbl[i] == NULL) + continue; + + ptr = (struct pasid_state **)tbl[i]; + free_pasid_states_level1(ptr); + } +} + +static void free_pasid_states(struct device_state *dev_state) +{ + struct pasid_state *pasid_state; + int i; + + for (i = 0; i < dev_state->max_pasids; ++i) { + pasid_state = get_pasid_state(dev_state, i); + if (pasid_state == NULL) + continue; + + put_pasid_state(pasid_state); + + /* + * This will call the mn_release function and + * unbind the PASID + */ + mmu_notifier_unregister(&pasid_state->mn, pasid_state->mm); + + put_pasid_state_wait(pasid_state); /* Reference taken in + amd_iommu_bind_pasid */ + + /* Drop reference taken in amd_iommu_bind_pasid */ + put_device_state(dev_state); + } + + if (dev_state->pasid_levels == 2) + free_pasid_states_level2(dev_state->states); + else if (dev_state->pasid_levels == 1) + free_pasid_states_level1(dev_state->states); + else + BUG_ON(dev_state->pasid_levels != 0); + + free_page((unsigned long)dev_state->states); +} + +static struct pasid_state *mn_to_state(struct mmu_notifier *mn) +{ + return container_of(mn, struct pasid_state, mn); +} + +static void mn_invalidate_range(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct pasid_state *pasid_state; + struct device_state *dev_state; + + pasid_state = mn_to_state(mn); + dev_state = pasid_state->device_state; + + if ((start ^ (end - 1)) < PAGE_SIZE) + amd_iommu_flush_page(dev_state->domain, pasid_state->pasid, + start); + else + amd_iommu_flush_tlb(dev_state->domain, pasid_state->pasid); +} + +static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) +{ + struct pasid_state *pasid_state; + struct device_state *dev_state; + bool run_inv_ctx_cb; + + might_sleep(); + + pasid_state = mn_to_state(mn); + dev_state = pasid_state->device_state; + run_inv_ctx_cb = !pasid_state->invalid; + + if (run_inv_ctx_cb && dev_state->inv_ctx_cb) + dev_state->inv_ctx_cb(dev_state->pdev, pasid_state->pasid); + + unbind_pasid(pasid_state); +} + +static const struct mmu_notifier_ops iommu_mn = { + .release = mn_release, + .invalidate_range = mn_invalidate_range, +}; + +static void set_pri_tag_status(struct pasid_state *pasid_state, + u16 tag, int status) +{ + unsigned long flags; + + spin_lock_irqsave(&pasid_state->lock, flags); + pasid_state->pri[tag].status = status; + spin_unlock_irqrestore(&pasid_state->lock, flags); +} + +static void finish_pri_tag(struct device_state *dev_state, + struct pasid_state *pasid_state, + u16 tag) +{ + unsigned long flags; + + spin_lock_irqsave(&pasid_state->lock, flags); + if (atomic_dec_and_test(&pasid_state->pri[tag].inflight) && + pasid_state->pri[tag].finish) { + amd_iommu_complete_ppr(dev_state->pdev, pasid_state->pasid, + pasid_state->pri[tag].status, tag); + pasid_state->pri[tag].finish = false; + pasid_state->pri[tag].status = PPR_SUCCESS; + } + spin_unlock_irqrestore(&pasid_state->lock, flags); +} + +static void handle_fault_error(struct fault *fault) +{ + int status; + + if (!fault->dev_state->inv_ppr_cb) { + set_pri_tag_status(fault->state, fault->tag, PPR_INVALID); + return; + } + + status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev, + fault->pasid, + fault->address, + fault->flags); + switch (status) { + case AMD_IOMMU_INV_PRI_RSP_SUCCESS: + set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS); + break; + case AMD_IOMMU_INV_PRI_RSP_INVALID: + set_pri_tag_status(fault->state, fault->tag, PPR_INVALID); + break; + case AMD_IOMMU_INV_PRI_RSP_FAIL: + set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE); + break; + default: + BUG(); + } +} + +static bool access_error(struct vm_area_struct *vma, struct fault *fault) +{ + unsigned long requested = 0; + + if (fault->flags & PPR_FAULT_EXEC) + requested |= VM_EXEC; + + if (fault->flags & PPR_FAULT_READ) + requested |= VM_READ; + + if (fault->flags & PPR_FAULT_WRITE) + requested |= VM_WRITE; + + return (requested & ~vma->vm_flags) != 0; +} + +static void do_fault(struct work_struct *work) +{ + struct fault *fault = container_of(work, struct fault, work); + struct vm_area_struct *vma; + vm_fault_t ret = VM_FAULT_ERROR; + unsigned int flags = 0; + struct mm_struct *mm; + u64 address; + + mm = fault->state->mm; + address = fault->address; + + if (fault->flags & PPR_FAULT_USER) + flags |= FAULT_FLAG_USER; + if (fault->flags & PPR_FAULT_WRITE) + flags |= FAULT_FLAG_WRITE; + flags |= FAULT_FLAG_REMOTE; + + mmap_read_lock(mm); + vma = vma_lookup(mm, address); + if (!vma) + /* failed to get a vma in the right range */ + goto out; + + /* Check if we have the right permissions on the vma */ + if (access_error(vma, fault)) + goto out; + + ret = handle_mm_fault(vma, address, flags, NULL); +out: + mmap_read_unlock(mm); + + if (ret & VM_FAULT_ERROR) + /* failed to service fault */ + handle_fault_error(fault); + + finish_pri_tag(fault->dev_state, fault->state, fault->tag); + + put_pasid_state(fault->state); + + kfree(fault); +} + +static int ppr_notifier(struct notifier_block *nb, unsigned long e, void *data) +{ + struct amd_iommu_fault *iommu_fault; + struct pasid_state *pasid_state; + struct device_state *dev_state; + struct pci_dev *pdev = NULL; + unsigned long flags; + struct fault *fault; + bool finish; + u16 tag, devid, seg_id; + int ret; + + iommu_fault = data; + tag = iommu_fault->tag & 0x1ff; + finish = (iommu_fault->tag >> 9) & 1; + + seg_id = PCI_SBDF_TO_SEGID(iommu_fault->sbdf); + devid = PCI_SBDF_TO_DEVID(iommu_fault->sbdf); + pdev = pci_get_domain_bus_and_slot(seg_id, PCI_BUS_NUM(devid), + devid & 0xff); + if (!pdev) + return -ENODEV; + + ret = NOTIFY_DONE; + + /* In kdump kernel pci dev is not initialized yet -> send INVALID */ + if (amd_iommu_is_attach_deferred(&pdev->dev)) { + amd_iommu_complete_ppr(pdev, iommu_fault->pasid, + PPR_INVALID, tag); + goto out; + } + + dev_state = get_device_state(iommu_fault->sbdf); + if (dev_state == NULL) + goto out; + + pasid_state = get_pasid_state(dev_state, iommu_fault->pasid); + if (pasid_state == NULL || pasid_state->invalid) { + /* We know the device but not the PASID -> send INVALID */ + amd_iommu_complete_ppr(dev_state->pdev, iommu_fault->pasid, + PPR_INVALID, tag); + goto out_drop_state; + } + + spin_lock_irqsave(&pasid_state->lock, flags); + atomic_inc(&pasid_state->pri[tag].inflight); + if (finish) + pasid_state->pri[tag].finish = true; + spin_unlock_irqrestore(&pasid_state->lock, flags); + + fault = kzalloc(sizeof(*fault), GFP_ATOMIC); + if (fault == NULL) { + /* We are OOM - send success and let the device re-fault */ + finish_pri_tag(dev_state, pasid_state, tag); + goto out_drop_state; + } + + fault->dev_state = dev_state; + fault->address = iommu_fault->address; + fault->state = pasid_state; + fault->tag = tag; + fault->finish = finish; + fault->pasid = iommu_fault->pasid; + fault->flags = iommu_fault->flags; + INIT_WORK(&fault->work, do_fault); + + queue_work(iommu_wq, &fault->work); + + ret = NOTIFY_OK; + +out_drop_state: + + if (ret != NOTIFY_OK && pasid_state) + put_pasid_state(pasid_state); + + put_device_state(dev_state); + +out: + pci_dev_put(pdev); + return ret; +} + +static struct notifier_block ppr_nb = { + .notifier_call = ppr_notifier, +}; + +int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid, + struct task_struct *task) +{ + struct pasid_state *pasid_state; + struct device_state *dev_state; + struct mm_struct *mm; + u32 sbdf; + int ret; + + might_sleep(); + + if (!amd_iommu_v2_supported()) + return -ENODEV; + + sbdf = get_pci_sbdf_id(pdev); + dev_state = get_device_state(sbdf); + + if (dev_state == NULL) + return -EINVAL; + + ret = -EINVAL; + if (pasid >= dev_state->max_pasids) + goto out; + + ret = -ENOMEM; + pasid_state = kzalloc(sizeof(*pasid_state), GFP_KERNEL); + if (pasid_state == NULL) + goto out; + + + refcount_set(&pasid_state->count, 1); + init_waitqueue_head(&pasid_state->wq); + spin_lock_init(&pasid_state->lock); + + mm = get_task_mm(task); + pasid_state->mm = mm; + pasid_state->device_state = dev_state; + pasid_state->pasid = pasid; + pasid_state->invalid = true; /* Mark as valid only if we are + done with setting up the pasid */ + pasid_state->mn.ops = &iommu_mn; + + if (pasid_state->mm == NULL) + goto out_free; + + mmu_notifier_register(&pasid_state->mn, mm); + + ret = set_pasid_state(dev_state, pasid_state, pasid); + if (ret) + goto out_unregister; + + ret = amd_iommu_domain_set_gcr3(dev_state->domain, pasid, + __pa(pasid_state->mm->pgd)); + if (ret) + goto out_clear_state; + + /* Now we are ready to handle faults */ + pasid_state->invalid = false; + + /* + * Drop the reference to the mm_struct here. We rely on the + * mmu_notifier release call-back to inform us when the mm + * is going away. + */ + mmput(mm); + + return 0; + +out_clear_state: + clear_pasid_state(dev_state, pasid); + +out_unregister: + mmu_notifier_unregister(&pasid_state->mn, mm); + mmput(mm); + +out_free: + free_pasid_state(pasid_state); + +out: + put_device_state(dev_state); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_bind_pasid); + +void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid) +{ + struct pasid_state *pasid_state; + struct device_state *dev_state; + u32 sbdf; + + might_sleep(); + + if (!amd_iommu_v2_supported()) + return; + + sbdf = get_pci_sbdf_id(pdev); + dev_state = get_device_state(sbdf); + if (dev_state == NULL) + return; + + if (pasid >= dev_state->max_pasids) + goto out; + + pasid_state = get_pasid_state(dev_state, pasid); + if (pasid_state == NULL) + goto out; + /* + * Drop reference taken here. We are safe because we still hold + * the reference taken in the amd_iommu_bind_pasid function. + */ + put_pasid_state(pasid_state); + + /* Clear the pasid state so that the pasid can be re-used */ + clear_pasid_state(dev_state, pasid_state->pasid); + + /* + * Call mmu_notifier_unregister to drop our reference + * to pasid_state->mm + */ + mmu_notifier_unregister(&pasid_state->mn, pasid_state->mm); + + put_pasid_state_wait(pasid_state); /* Reference taken in + amd_iommu_bind_pasid */ +out: + /* Drop reference taken in this function */ + put_device_state(dev_state); + + /* Drop reference taken in amd_iommu_bind_pasid */ + put_device_state(dev_state); +} +EXPORT_SYMBOL(amd_iommu_unbind_pasid); + +int amd_iommu_init_device(struct pci_dev *pdev, int pasids) +{ + struct device_state *dev_state; + struct iommu_group *group; + unsigned long flags; + int ret, tmp; + u32 sbdf; + + might_sleep(); + + /* + * When memory encryption is active the device is likely not in a + * direct-mapped domain. Forbid using IOMMUv2 functionality for now. + */ + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) + return -ENODEV; + + if (!amd_iommu_v2_supported()) + return -ENODEV; + + if (pasids <= 0 || pasids > (PASID_MASK + 1)) + return -EINVAL; + + sbdf = get_pci_sbdf_id(pdev); + + dev_state = kzalloc(sizeof(*dev_state), GFP_KERNEL); + if (dev_state == NULL) + return -ENOMEM; + + spin_lock_init(&dev_state->lock); + init_waitqueue_head(&dev_state->wq); + dev_state->pdev = pdev; + dev_state->sbdf = sbdf; + + tmp = pasids; + for (dev_state->pasid_levels = 0; (tmp - 1) & ~0x1ff; tmp >>= 9) + dev_state->pasid_levels += 1; + + atomic_set(&dev_state->count, 1); + dev_state->max_pasids = pasids; + + ret = -ENOMEM; + dev_state->states = (void *)get_zeroed_page(GFP_KERNEL); + if (dev_state->states == NULL) + goto out_free_dev_state; + + dev_state->domain = iommu_domain_alloc(&pci_bus_type); + if (dev_state->domain == NULL) + goto out_free_states; + + /* See iommu_is_default_domain() */ + dev_state->domain->type = IOMMU_DOMAIN_IDENTITY; + amd_iommu_domain_direct_map(dev_state->domain); + + ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids); + if (ret) + goto out_free_domain; + + group = iommu_group_get(&pdev->dev); + if (!group) { + ret = -EINVAL; + goto out_free_domain; + } + + ret = iommu_attach_group(dev_state->domain, group); + if (ret != 0) + goto out_drop_group; + + iommu_group_put(group); + + spin_lock_irqsave(&state_lock, flags); + + if (__get_device_state(sbdf) != NULL) { + spin_unlock_irqrestore(&state_lock, flags); + ret = -EBUSY; + goto out_free_domain; + } + + list_add_tail(&dev_state->list, &state_list); + + spin_unlock_irqrestore(&state_lock, flags); + + return 0; + +out_drop_group: + iommu_group_put(group); + +out_free_domain: + iommu_domain_free(dev_state->domain); + +out_free_states: + free_page((unsigned long)dev_state->states); + +out_free_dev_state: + kfree(dev_state); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_init_device); + +void amd_iommu_free_device(struct pci_dev *pdev) +{ + struct device_state *dev_state; + unsigned long flags; + u32 sbdf; + + if (!amd_iommu_v2_supported()) + return; + + sbdf = get_pci_sbdf_id(pdev); + + spin_lock_irqsave(&state_lock, flags); + + dev_state = __get_device_state(sbdf); + if (dev_state == NULL) { + spin_unlock_irqrestore(&state_lock, flags); + return; + } + + list_del(&dev_state->list); + + spin_unlock_irqrestore(&state_lock, flags); + + put_device_state(dev_state); + free_device_state(dev_state); +} +EXPORT_SYMBOL(amd_iommu_free_device); + +int amd_iommu_set_invalid_ppr_cb(struct pci_dev *pdev, + amd_iommu_invalid_ppr_cb cb) +{ + struct device_state *dev_state; + unsigned long flags; + u32 sbdf; + int ret; + + if (!amd_iommu_v2_supported()) + return -ENODEV; + + sbdf = get_pci_sbdf_id(pdev); + + spin_lock_irqsave(&state_lock, flags); + + ret = -EINVAL; + dev_state = __get_device_state(sbdf); + if (dev_state == NULL) + goto out_unlock; + + dev_state->inv_ppr_cb = cb; + + ret = 0; + +out_unlock: + spin_unlock_irqrestore(&state_lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_set_invalid_ppr_cb); + +int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev, + amd_iommu_invalidate_ctx cb) +{ + struct device_state *dev_state; + unsigned long flags; + u32 sbdf; + int ret; + + if (!amd_iommu_v2_supported()) + return -ENODEV; + + sbdf = get_pci_sbdf_id(pdev); + + spin_lock_irqsave(&state_lock, flags); + + ret = -EINVAL; + dev_state = __get_device_state(sbdf); + if (dev_state == NULL) + goto out_unlock; + + dev_state->inv_ctx_cb = cb; + + ret = 0; + +out_unlock: + spin_unlock_irqrestore(&state_lock, flags); + + return ret; +} +EXPORT_SYMBOL(amd_iommu_set_invalidate_ctx_cb); + +static int __init amd_iommu_v2_init(void) +{ + int ret; + + if (!amd_iommu_v2_supported()) { + pr_info("AMD IOMMUv2 functionality not available on this system - This is not a bug.\n"); + /* + * Load anyway to provide the symbols to other modules + * which may use AMD IOMMUv2 optionally. + */ + return 0; + } + + ret = -ENOMEM; + iommu_wq = alloc_workqueue("amd_iommu_v2", WQ_MEM_RECLAIM, 0); + if (iommu_wq == NULL) + goto out; + + amd_iommu_register_ppr_notifier(&ppr_nb); + + pr_info("AMD IOMMUv2 loaded and initialized\n"); + + return 0; + +out: + return ret; +} + +static void __exit amd_iommu_v2_exit(void) +{ + struct device_state *dev_state, *next; + unsigned long flags; + LIST_HEAD(freelist); + + if (!amd_iommu_v2_supported()) + return; + + amd_iommu_unregister_ppr_notifier(&ppr_nb); + + flush_workqueue(iommu_wq); + + /* + * The loop below might call flush_workqueue(), so call + * destroy_workqueue() after it + */ + spin_lock_irqsave(&state_lock, flags); + + list_for_each_entry_safe(dev_state, next, &state_list, list) { + WARN_ON_ONCE(1); + + put_device_state(dev_state); + list_del(&dev_state->list); + list_add_tail(&dev_state->list, &freelist); + } + + spin_unlock_irqrestore(&state_lock, flags); + + /* + * Since free_device_state waits on the count to be zero, + * we need to free dev_state outside the spinlock. + */ + list_for_each_entry_safe(dev_state, next, &freelist, list) { + list_del(&dev_state->list); + free_device_state(dev_state); + } + + destroy_workqueue(iommu_wq); +} + +module_init(amd_iommu_v2_init); +module_exit(amd_iommu_v2_exit); diff --git a/drivers/iommu/amd/quirks.c b/drivers/iommu/amd/quirks.c new file mode 100644 index 000000000..79dbb8f33 --- /dev/null +++ b/drivers/iommu/amd/quirks.c @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Quirks for AMD IOMMU + * + * Copyright (C) 2019 Kai-Heng Feng + */ + +#ifdef CONFIG_DMI +#include + +#include "amd_iommu.h" + +#define IVHD_SPECIAL_IOAPIC 1 + +struct ivrs_quirk_entry { + u8 id; + u32 devid; +}; + +enum { + DELL_INSPIRON_7375 = 0, + DELL_LATITUDE_5495, + LENOVO_IDEAPAD_330S_15ARR, +}; + +static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = { + /* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */ + [DELL_INSPIRON_7375] = { + { .id = 4, .devid = 0xa0 }, + { .id = 5, .devid = 0x2 }, + {} + }, + /* ivrs_ioapic[4]=00:14.0 */ + [DELL_LATITUDE_5495] = { + { .id = 4, .devid = 0xa0 }, + {} + }, + /* ivrs_ioapic[32]=00:14.0 */ + [LENOVO_IDEAPAD_330S_15ARR] = { + { .id = 32, .devid = 0xa0 }, + {} + }, + {} +}; + +static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d) +{ + const struct ivrs_quirk_entry *i; + + for (i = d->driver_data; i->id != 0 && i->devid != 0; i++) + add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u32 *)&i->devid, 0); + + return 0; +} + +static const struct dmi_system_id ivrs_quirks[] __initconst = { + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Dell Inspiron 7375", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375], + }, + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Dell Latitude 5495", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495], + }, + { + /* + * Acer Aspire A315-41 requires the very same workaround as + * Dell Latitude 5495 + */ + .callback = ivrs_ioapic_quirk_cb, + .ident = "Acer Aspire A315-41", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495], + }, + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Lenovo ideapad 330S-15ARR", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "81FB"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR], + }, + {} +}; + +void __init amd_iommu_apply_ivrs_quirks(void) +{ + dmi_check_system(ivrs_quirks); +} +#endif -- cgit v1.2.3