diff options
Diffstat (limited to 'drivers/iommu/amd')
| -rw-r--r-- | drivers/iommu/amd/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/iommu/amd/Makefile | 2 | ||||
| -rw-r--r-- | drivers/iommu/amd/amd_iommu.h | 19 | ||||
| -rw-r--r-- | drivers/iommu/amd/amd_iommu_types.h | 97 | ||||
| -rw-r--r-- | drivers/iommu/amd/debugfs.c | 378 | ||||
| -rw-r--r-- | drivers/iommu/amd/init.c | 511 | ||||
| -rw-r--r-- | drivers/iommu/amd/io_pgtable.c | 49 | ||||
| -rw-r--r-- | drivers/iommu/amd/io_pgtable_v2.c | 14 | ||||
| -rw-r--r-- | drivers/iommu/amd/iommu.c | 921 | ||||
| -rw-r--r-- | drivers/iommu/amd/pasid.c | 5 | ||||
| -rw-r--r-- | drivers/iommu/amd/ppr.c | 2 |
11 files changed, 1335 insertions, 664 deletions
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig index 994063e5586f..ecef69c11144 100644 --- a/drivers/iommu/amd/Kconfig +++ b/drivers/iommu/amd/Kconfig @@ -7,6 +7,7 @@ config AMD_IOMMU select PCI_ATS select PCI_PRI select PCI_PASID + select IRQ_MSI_LIB select MMU_NOTIFIER select IOMMU_API select IOMMU_IOVA diff --git a/drivers/iommu/amd/Makefile b/drivers/iommu/amd/Makefile index 9de33b2d42f5..59c04a67f398 100644 --- a/drivers/iommu/amd/Makefile +++ b/drivers/iommu/amd/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o ppr.o pasid.o +obj-y += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o ppr.o pasid.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 1bef5d55b2f9..9b4b589a54b5 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -16,7 +16,6 @@ irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_galog(int irq, void *data); irqreturn_t amd_iommu_int_handler(int irq, void *data); -void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid); void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type, u8 cntrl_intr, u8 cntrl_log, u32 status_run_mask, u32 status_overflow_mask); @@ -29,9 +28,9 @@ void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp, size_t size); #ifdef CONFIG_AMD_IOMMU_DEBUGFS -void amd_iommu_debugfs_setup(struct amd_iommu *iommu); +void amd_iommu_debugfs_setup(void); #else -static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {} +static inline void amd_iommu_debugfs_setup(void) {} #endif /* Needed for interrupt remapping */ @@ -41,14 +40,15 @@ void amd_iommu_disable(void); int amd_iommu_reenable(int mode); int amd_iommu_enable_faulting(unsigned int cpu); extern int amd_iommu_guest_ir; -extern enum io_pgtable_fmt amd_iommu_pgtable; +extern enum protection_domain_mode amd_iommu_pgtable; extern int amd_iommu_gpt_level; +extern u8 amd_iommu_hpt_level; extern unsigned long amd_iommu_pgsize_bitmap; +extern bool amd_iommu_hatdis; /* Protection domain ops */ void amd_iommu_init_identity_domain(void); -struct protection_domain *protection_domain_alloc(unsigned int type, int nid); -void protection_domain_free(struct protection_domain *domain); +struct protection_domain *protection_domain_alloc(void); struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct mm_struct *mm); void amd_iommu_domain_free(struct iommu_domain *dom); @@ -89,7 +89,6 @@ int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag); */ void amd_iommu_flush_all_caches(struct amd_iommu *iommu); void amd_iommu_update_and_flush_device_table(struct protection_domain *domain); -void amd_iommu_domain_update(struct protection_domain *domain); void amd_iommu_domain_flush_pages(struct protection_domain *domain, u64 address, size_t size); void amd_iommu_dev_flush_pasid_pages(struct iommu_dev_data *dev_data, @@ -150,6 +149,8 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev) return PCI_SEG_DEVID_TO_SBDF(seg, devid); } +bool amd_iommu_ht_range_ignore(void); + /* * This must be called after device probe completes. During probe * use rlookup_amd_iommu() get the iommu. @@ -178,9 +179,11 @@ void amd_iommu_apply_ivrs_quirks(void); #else static inline void amd_iommu_apply_ivrs_quirks(void) { } #endif +struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid); void amd_iommu_domain_set_pgtable(struct protection_domain *domain, u64 *root, int mode); struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); +struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid); -#endif +#endif /* AMD_IOMMU_H */ diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index fdb0357e0bb9..5219d7ddfdaa 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -29,8 +29,6 @@ * 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 @@ -96,6 +94,7 @@ #define FEATURE_GA BIT_ULL(7) #define FEATURE_HE BIT_ULL(8) #define FEATURE_PC BIT_ULL(9) +#define FEATURE_HATS GENMASK_ULL(11, 10) #define FEATURE_GATS GENMASK_ULL(13, 12) #define FEATURE_GLX GENMASK_ULL(15, 14) #define FEATURE_GAM_VAPIC BIT_ULL(21) @@ -111,6 +110,11 @@ #define FEATURE_SNPAVICSUP GENMASK_ULL(7, 5) #define FEATURE_SNPAVICSUP_GAM(x) \ (FIELD_GET(FEATURE_SNPAVICSUP, x) == 0x1) +#define FEATURE_HT_RANGE_IGNORE BIT_ULL(11) + +#define FEATURE_NUM_INT_REMAP_SUP GENMASK_ULL(9, 8) +#define FEATURE_NUM_INT_REMAP_SUP_2K(x) \ + (FIELD_GET(FEATURE_NUM_INT_REMAP_SUP, x) == 0x1) /* Note: * The current driver only support 16-bit PASID. @@ -175,12 +179,16 @@ #define CONTROL_GAM_EN 25 #define CONTROL_GALOG_EN 28 #define CONTROL_GAINT_EN 29 +#define CONTROL_NUM_INT_REMAP_MODE 43 +#define CONTROL_NUM_INT_REMAP_MODE_MASK 0x03 +#define CONTROL_NUM_INT_REMAP_MODE_2K 0x01 +#define CONTROL_EPH_EN 45 #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_MASK 7 #define CTRL_INV_TO_NONE 0 #define CTRL_INV_TO_1MS 1 #define CTRL_INV_TO_10MS 2 @@ -220,6 +228,8 @@ #define DEV_ENTRY_EX 0x67 #define DEV_ENTRY_SYSMGT1 0x68 #define DEV_ENTRY_SYSMGT2 0x69 +#define DTE_DATA1_SYSMGT_MASK GENMASK_ULL(41, 40) + #define DEV_ENTRY_IRQ_TBL_EN 0x80 #define DEV_ENTRY_INIT_PASS 0xb8 #define DEV_ENTRY_EINT_PASS 0xb9 @@ -306,15 +316,14 @@ #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 DTE_INTTABLEN_VALUE_512 9ULL +#define DTE_INTTABLEN_512 (DTE_INTTABLEN_VALUE_512 << 1) +#define MAX_IRQS_PER_TABLE_512 BIT(DTE_INTTABLEN_VALUE_512) +#define DTE_INTTABLEN_VALUE_2K 11ULL +#define DTE_INTTABLEN_2K (DTE_INTTABLEN_VALUE_2K << 1) +#define MAX_IRQS_PER_TABLE_2K BIT(DTE_INTTABLEN_VALUE_2K) #define PAGE_MODE_NONE 0x00 #define PAGE_MODE_1_LEVEL 0x01 @@ -407,8 +416,7 @@ #define DTE_FLAG_HAD (3ULL << 7) #define DTE_FLAG_GIOV BIT_ULL(54) #define DTE_FLAG_GV BIT_ULL(55) -#define DTE_GLX_SHIFT (56) -#define DTE_GLX_MASK (3) +#define DTE_GLX GENMASK_ULL(57, 56) #define DTE_FLAG_IR BIT_ULL(61) #define DTE_FLAG_IW BIT_ULL(62) @@ -416,18 +424,18 @@ #define DTE_FLAG_MASK (0x3ffULL << 32) #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_SHIFT_A 58 -#define DTE_GCR3_SHIFT_B 16 -#define DTE_GCR3_SHIFT_C 43 +#define DTE_GCR3_14_12 GENMASK_ULL(60, 58) +#define DTE_GCR3_30_15 GENMASK_ULL(31, 16) +#define DTE_GCR3_51_31 GENMASK_ULL(63, 43) #define DTE_GPT_LEVEL_SHIFT 54 +#define DTE_GPT_LEVEL_MASK GENMASK_ULL(55, 54) #define GCR3_VALID 0x01ULL +/* DTE[128:179] | DTE[184:191] */ +#define DTE_DATA2_INTR_MASK ~GENMASK_ULL(55, 52) + #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_PR) #define IOMMU_PTE_DIRTY(pte) ((pte) & IOMMU_PTE_HD) @@ -453,6 +461,9 @@ /* IOMMU Feature Reporting Field (for IVHD type 10h */ #define IOMMU_FEAT_GASUP_SHIFT 6 +/* IOMMU HATDIS for IVHD type 11h and 40h */ +#define IOMMU_IVHD_ATTR_HATDIS_SHIFT 0 + /* IOMMU Extended Feature Register (EFR) */ #define IOMMU_EFR_XTSUP_SHIFT 2 #define IOMMU_EFR_GASUP_SHIFT 7 @@ -468,7 +479,7 @@ extern bool amd_iommu_dump; #define DUMP_printk(format, arg...) \ do { \ if (amd_iommu_dump) \ - pr_info("AMD-Vi: " format, ## arg); \ + pr_info(format, ## arg); \ } while(0); /* global flag if IOMMUs cache non-present entries */ @@ -490,9 +501,6 @@ 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) | \ @@ -516,6 +524,9 @@ extern struct kmem_cache *amd_iommu_irq_cache; #define for_each_pdom_dev_data_safe(pdom_dev_data, next, pdom) \ list_for_each_entry_safe((pdom_dev_data), (next), &pdom->dev_data_list, list) +#define for_each_ivhd_dte_flags(entry) \ + list_for_each_entry((entry), &amd_ivhd_dev_flags_list, list) + struct amd_iommu; struct iommu_domain; struct irq_domain; @@ -551,7 +562,8 @@ struct amd_io_pgtable { }; enum protection_domain_mode { - PD_MODE_V1 = 1, + PD_MODE_NONE, + PD_MODE_V1, PD_MODE_V2, }; @@ -609,12 +621,6 @@ struct amd_iommu_pci_seg { /* 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 * @@ -789,6 +795,8 @@ struct amd_iommu { #ifdef CONFIG_AMD_IOMMU_DEBUGFS /* DebugFS Info */ struct dentry *debugfs; + int dbg_mmio_offset; + int dbg_cap_offset; #endif /* IOPF support */ @@ -837,6 +845,7 @@ struct devid_map { struct iommu_dev_data { /*Protect against attach/detach races */ struct mutex mutex; + spinlock_t dte_lock; /* DTE lock for 256-bit access */ struct list_head list; /* For domain->dev_list */ struct llist_node dev_data_list; /* For global dev_data_list */ @@ -845,6 +854,7 @@ struct iommu_dev_data { struct device *dev; u16 devid; /* PCI Device ID */ + unsigned int max_irqs; /* Maximum IRQs supported by device */ u32 max_pasids; /* Max supported PASIDs */ u32 flags; /* Holds AMD_IOMMU_DEVICE_FLAG_<*> */ int ats_qdep; @@ -881,7 +891,28 @@ extern struct list_head amd_iommu_list; * Structure defining one entry in the device table */ struct dev_table_entry { - u64 data[4]; + union { + u64 data[4]; + u128 data128[2]; + }; +}; + +/* + * Structure defining one entry in the command buffer + */ +struct iommu_cmd { + u32 data[4]; +}; + +/* + * Structure to sture persistent DTE flags from IVHD + */ +struct ivhd_dte_flags { + struct list_head list; + u16 segid; + u16 devid_first; + u16 devid_last; + struct dev_table_entry dte; }; /* @@ -908,9 +939,6 @@ struct unity_map_entry { * Data structures for device handling */ -/* size of the dma_ops aperture as power of 2 */ -extern unsigned amd_iommu_aperture_order; - extern bool amd_iommu_force_isolation; /* Max levels of glxval supported */ @@ -1040,7 +1068,6 @@ struct irq_2_irte { }; struct amd_ir_data { - u32 cached_ga_tag; struct amd_iommu *iommu; struct irq_2_irte irq_2_irte; struct msi_msg msi_entry; diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c index 545372fcc72f..10fa217a7119 100644 --- a/drivers/iommu/amd/debugfs.c +++ b/drivers/iommu/amd/debugfs.c @@ -11,22 +11,382 @@ #include <linux/pci.h> #include "amd_iommu.h" +#include "../irq_remapping.h" static struct dentry *amd_iommu_debugfs; -static DEFINE_MUTEX(amd_iommu_debugfs_lock); #define MAX_NAME_LEN 20 +#define OFS_IN_SZ 8 +#define DEVID_IN_SZ 16 -void amd_iommu_debugfs_setup(struct amd_iommu *iommu) +static int sbdf = -1; + +static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct seq_file *m = filp->private_data; + struct amd_iommu *iommu = m->private; + int ret; + + iommu->dbg_mmio_offset = -1; + + if (cnt > OFS_IN_SZ) + return -EINVAL; + + ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_mmio_offset); + if (ret) + return ret; + + if (iommu->dbg_mmio_offset > iommu->mmio_phys_end - 4) { + iommu->dbg_mmio_offset = -1; + return -EINVAL; + } + + return cnt; +} + +static int iommu_mmio_show(struct seq_file *m, void *unused) +{ + struct amd_iommu *iommu = m->private; + u64 value; + + if (iommu->dbg_mmio_offset < 0) { + seq_puts(m, "Please provide mmio register's offset\n"); + return 0; + } + + value = readq(iommu->mmio_base + iommu->dbg_mmio_offset); + seq_printf(m, "Offset:0x%x Value:0x%016llx\n", iommu->dbg_mmio_offset, value); + + return 0; +} +DEFINE_SHOW_STORE_ATTRIBUTE(iommu_mmio); + +static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct seq_file *m = filp->private_data; + struct amd_iommu *iommu = m->private; + int ret; + + iommu->dbg_cap_offset = -1; + + if (cnt > OFS_IN_SZ) + return -EINVAL; + + ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_cap_offset); + if (ret) + return ret; + + /* Capability register at offset 0x14 is the last IOMMU capability register. */ + if (iommu->dbg_cap_offset > 0x14) { + iommu->dbg_cap_offset = -1; + return -EINVAL; + } + + return cnt; +} + +static int iommu_capability_show(struct seq_file *m, void *unused) +{ + struct amd_iommu *iommu = m->private; + u32 value; + int err; + + if (iommu->dbg_cap_offset < 0) { + seq_puts(m, "Please provide capability register's offset in the range [0x00 - 0x14]\n"); + return 0; + } + + err = pci_read_config_dword(iommu->dev, iommu->cap_ptr + iommu->dbg_cap_offset, &value); + if (err) { + seq_printf(m, "Not able to read capability register at 0x%x\n", + iommu->dbg_cap_offset); + return 0; + } + + seq_printf(m, "Offset:0x%x Value:0x%08x\n", iommu->dbg_cap_offset, value); + + return 0; +} +DEFINE_SHOW_STORE_ATTRIBUTE(iommu_capability); + +static int iommu_cmdbuf_show(struct seq_file *m, void *unused) +{ + struct amd_iommu *iommu = m->private; + struct iommu_cmd *cmd; + unsigned long flag; + u32 head, tail; + int i; + + raw_spin_lock_irqsave(&iommu->lock, flag); + head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); + tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); + seq_printf(m, "CMD Buffer Head Offset:%d Tail Offset:%d\n", + (head >> 4) & 0x7fff, (tail >> 4) & 0x7fff); + for (i = 0; i < CMD_BUFFER_ENTRIES; i++) { + cmd = (struct iommu_cmd *)(iommu->cmd_buf + i * sizeof(*cmd)); + seq_printf(m, "%3d: %08x %08x %08x %08x\n", i, cmd->data[0], + cmd->data[1], cmd->data[2], cmd->data[3]); + } + raw_spin_unlock_irqrestore(&iommu->lock, flag); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(iommu_cmdbuf); + +static ssize_t devid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct amd_iommu_pci_seg *pci_seg; + int seg, bus, slot, func; + struct amd_iommu *iommu; + char *srcid_ptr; + u16 devid; + int i; + + sbdf = -1; + + if (cnt >= DEVID_IN_SZ) + return -EINVAL; + + srcid_ptr = memdup_user_nul(ubuf, cnt); + if (IS_ERR(srcid_ptr)) + return PTR_ERR(srcid_ptr); + + i = sscanf(srcid_ptr, "%x:%x:%x.%x", &seg, &bus, &slot, &func); + if (i != 4) { + i = sscanf(srcid_ptr, "%x:%x.%x", &bus, &slot, &func); + if (i != 3) { + kfree(srcid_ptr); + return -EINVAL; + } + seg = 0; + } + + devid = PCI_DEVID(bus, PCI_DEVFN(slot, func)); + + /* Check if user device id input is a valid input */ + for_each_pci_segment(pci_seg) { + if (pci_seg->id != seg) + continue; + if (devid > pci_seg->last_bdf) { + kfree(srcid_ptr); + return -EINVAL; + } + iommu = pci_seg->rlookup_table[devid]; + if (!iommu) { + kfree(srcid_ptr); + return -ENODEV; + } + break; + } + + if (pci_seg->id != seg) { + kfree(srcid_ptr); + return -EINVAL; + } + + sbdf = PCI_SEG_DEVID_TO_SBDF(seg, devid); + + kfree(srcid_ptr); + + return cnt; +} + +static int devid_show(struct seq_file *m, void *unused) { + u16 devid; + + if (sbdf >= 0) { + devid = PCI_SBDF_TO_DEVID(sbdf); + seq_printf(m, "%04x:%02x:%02x.%x\n", PCI_SBDF_TO_SEGID(sbdf), + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid)); + } else + seq_puts(m, "No or Invalid input provided\n"); + + return 0; +} +DEFINE_SHOW_STORE_ATTRIBUTE(devid); + +static void dump_dte(struct seq_file *m, struct amd_iommu_pci_seg *pci_seg, u16 devid) +{ + struct dev_table_entry *dev_table; + struct amd_iommu *iommu; + + iommu = pci_seg->rlookup_table[devid]; + if (!iommu) + return; + + dev_table = get_dev_table(iommu); + if (!dev_table) { + seq_puts(m, "Device table not found"); + return; + } + + seq_printf(m, "%-12s %16s %16s %16s %16s iommu\n", "DeviceId", + "QWORD[3]", "QWORD[2]", "QWORD[1]", "QWORD[0]"); + seq_printf(m, "%04x:%02x:%02x.%x ", pci_seg->id, PCI_BUS_NUM(devid), + PCI_SLOT(devid), PCI_FUNC(devid)); + for (int i = 3; i >= 0; --i) + seq_printf(m, "%016llx ", dev_table[devid].data[i]); + seq_printf(m, "iommu%d\n", iommu->index); +} + +static int iommu_devtbl_show(struct seq_file *m, void *unused) +{ + struct amd_iommu_pci_seg *pci_seg; + u16 seg, devid; + + if (sbdf < 0) { + seq_puts(m, "Enter a valid device ID to 'devid' file\n"); + return 0; + } + seg = PCI_SBDF_TO_SEGID(sbdf); + devid = PCI_SBDF_TO_DEVID(sbdf); + + for_each_pci_segment(pci_seg) { + if (pci_seg->id != seg) + continue; + dump_dte(m, pci_seg, devid); + break; + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(iommu_devtbl); + +static void dump_128_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len) +{ + struct irte_ga *ptr, *irte; + int index; + + for (index = 0; index < int_tab_len; index++) { + ptr = (struct irte_ga *)table->table; + irte = &ptr[index]; + + if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) && + !irte->lo.fields_vapic.valid) + continue; + else if (!irte->lo.fields_remap.valid) + continue; + seq_printf(m, "IRT[%04d] %016llx %016llx\n", index, irte->hi.val, irte->lo.val); + } +} + +static void dump_32_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len) +{ + union irte *ptr, *irte; + int index; + + for (index = 0; index < int_tab_len; index++) { + ptr = (union irte *)table->table; + irte = &ptr[index]; + + if (!irte->fields.valid) + continue; + seq_printf(m, "IRT[%04d] %08x\n", index, irte->val); + } +} + +static void dump_irte(struct seq_file *m, u16 devid, struct amd_iommu_pci_seg *pci_seg) +{ + struct dev_table_entry *dev_table; + struct irq_remap_table *table; + struct amd_iommu *iommu; + unsigned long flags; + u16 int_tab_len; + + table = pci_seg->irq_lookup_table[devid]; + if (!table) { + seq_printf(m, "IRQ lookup table not set for %04x:%02x:%02x:%x\n", + pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid)); + return; + } + + iommu = pci_seg->rlookup_table[devid]; + if (!iommu) + return; + + dev_table = get_dev_table(iommu); + if (!dev_table) { + seq_puts(m, "Device table not found"); + return; + } + + int_tab_len = dev_table[devid].data[2] & DTE_INTTABLEN_MASK; + if (int_tab_len != DTE_INTTABLEN_512 && int_tab_len != DTE_INTTABLEN_2K) { + seq_puts(m, "The device's DTE contains an invalid IRT length value."); + return; + } + + seq_printf(m, "DeviceId %04x:%02x:%02x.%x\n", pci_seg->id, PCI_BUS_NUM(devid), + PCI_SLOT(devid), PCI_FUNC(devid)); + + raw_spin_lock_irqsave(&table->lock, flags); + if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + dump_128_irte(m, table, BIT(int_tab_len >> 1)); + else + dump_32_irte(m, table, BIT(int_tab_len >> 1)); + seq_puts(m, "\n"); + raw_spin_unlock_irqrestore(&table->lock, flags); +} + +static int iommu_irqtbl_show(struct seq_file *m, void *unused) +{ + struct amd_iommu_pci_seg *pci_seg; + u16 devid, seg; + + if (!irq_remapping_enabled) { + seq_puts(m, "Interrupt remapping is disabled\n"); + return 0; + } + + if (sbdf < 0) { + seq_puts(m, "Enter a valid device ID to 'devid' file\n"); + return 0; + } + + seg = PCI_SBDF_TO_SEGID(sbdf); + devid = PCI_SBDF_TO_DEVID(sbdf); + + for_each_pci_segment(pci_seg) { + if (pci_seg->id != seg) + continue; + dump_irte(m, devid, pci_seg); + break; + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(iommu_irqtbl); + +void amd_iommu_debugfs_setup(void) +{ + 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); + amd_iommu_debugfs = debugfs_create_dir("amd", iommu_debugfs_dir); + + for_each_iommu(iommu) { + iommu->dbg_mmio_offset = -1; + iommu->dbg_cap_offset = -1; + + snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index); + iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs); + + debugfs_create_file("mmio", 0644, iommu->debugfs, iommu, + &iommu_mmio_fops); + debugfs_create_file("capability", 0644, iommu->debugfs, iommu, + &iommu_capability_fops); + debugfs_create_file("cmdbuf", 0444, iommu->debugfs, iommu, + &iommu_cmdbuf_fops); + } - snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index); - iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs); + debugfs_create_file("devid", 0644, amd_iommu_debugfs, NULL, + &devid_fops); + debugfs_create_file("devtbl", 0444, amd_iommu_debugfs, NULL, + &iommu_devtbl_fops); + debugfs_create_file("irqtbl", 0444, amd_iommu_debugfs, NULL, + &iommu_irqtbl_fops); } diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 0e0a531042ac..8de689b2c5ed 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -12,7 +12,6 @@ #include <linux/acpi.h> #include <linux/list.h> #include <linux/bitmap.h> -#include <linux/slab.h> #include <linux/syscore_ops.h> #include <linux/interrupt.h> #include <linux/msi.h> @@ -152,7 +151,9 @@ struct ivmd_header { bool amd_iommu_dump; bool amd_iommu_irq_remap __read_mostly; -enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1; +enum protection_domain_mode amd_iommu_pgtable = PD_MODE_V1; +/* Host page table level */ +u8 amd_iommu_hpt_level; /* Guest page table level */ int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL; @@ -169,13 +170,16 @@ static int amd_iommu_target_ivhd_type; u64 amd_iommu_efr; u64 amd_iommu_efr2; +/* Host (v1) page table is not supported*/ +bool amd_iommu_hatdis; + /* 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 */ +LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ +LIST_HEAD(amd_ivhd_dev_flags_list); /* list of all IVHD device entry settings */ /* Number of IOMMUs present in the system */ static int amd_iommus_present; @@ -219,7 +223,6 @@ 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; @@ -245,17 +248,14 @@ static void init_translation_status(struct amd_iommu *iommu) iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED; } -static inline unsigned long tbl_size(int entry_size, int last_bdf) +int amd_iommu_get_num_iommus(void) { - unsigned shift = PAGE_SHIFT + - get_order((last_bdf + 1) * entry_size); - - return 1UL << shift; + return amd_iommus_present; } -int amd_iommu_get_num_iommus(void) +bool amd_iommu_ht_range_ignore(void) { - return amd_iommus_present; + return check_feature2(FEATURE_HT_RANGE_IGNORE); } /* @@ -412,33 +412,26 @@ static void iommu_set_device_table(struct amd_iommu *iommu) &entry, sizeof(entry)); } -/* Generic functions to enable/disable certain features of the IOMMU. */ -void iommu_feature_enable(struct amd_iommu *iommu, u8 bit) +static void iommu_feature_set(struct amd_iommu *iommu, u64 val, u64 mask, u8 shift) { u64 ctrl; ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); - ctrl |= (1ULL << bit); + mask <<= shift; + ctrl &= ~mask; + ctrl |= (val << shift) & mask; writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); } -static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit) +/* Generic functions to enable/disable certain features of the IOMMU. */ +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); + iommu_feature_set(iommu, 1ULL, 1ULL, bit); } -static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout) +static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit) { - 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); + iommu_feature_set(iommu, 0ULL, 1ULL, bit); } /* Function to enable the hardware */ @@ -643,8 +636,8 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table, u16 pci_ /* Allocate per PCI segment device table */ static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg) { - pci_seg->dev_table = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32, - get_order(pci_seg->dev_table_size)); + pci_seg->dev_table = iommu_alloc_pages_sz(GFP_KERNEL | GFP_DMA32, + pci_seg->dev_table_size); if (!pci_seg->dev_table) return -ENOMEM; @@ -653,16 +646,16 @@ static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg) static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg) { - iommu_free_pages(pci_seg->dev_table, - get_order(pci_seg->dev_table_size)); + iommu_free_pages(pci_seg->dev_table); 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 = iommu_alloc_pages(GFP_KERNEL, - get_order(pci_seg->rlookup_table_size)); + pci_seg->rlookup_table = kvcalloc(pci_seg->last_bdf + 1, + sizeof(*pci_seg->rlookup_table), + GFP_KERNEL); if (pci_seg->rlookup_table == NULL) return -ENOMEM; @@ -671,17 +664,15 @@ static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg) static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg) { - iommu_free_pages(pci_seg->rlookup_table, - get_order(pci_seg->rlookup_table_size)); + kvfree(pci_seg->rlookup_table); 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 = iommu_alloc_pages(GFP_KERNEL, - get_order(pci_seg->rlookup_table_size)); - kmemleak_alloc(pci_seg->irq_lookup_table, - pci_seg->rlookup_table_size, 1, GFP_KERNEL); + pci_seg->irq_lookup_table = kvcalloc(pci_seg->last_bdf + 1, + sizeof(*pci_seg->irq_lookup_table), + GFP_KERNEL); if (pci_seg->irq_lookup_table == NULL) return -ENOMEM; @@ -690,9 +681,7 @@ static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_se static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg) { - kmemleak_free(pci_seg->irq_lookup_table); - iommu_free_pages(pci_seg->irq_lookup_table, - get_order(pci_seg->rlookup_table_size)); + kvfree(pci_seg->irq_lookup_table); pci_seg->irq_lookup_table = NULL; } @@ -700,8 +689,9 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg) { int i; - pci_seg->alias_table = iommu_alloc_pages(GFP_KERNEL, - get_order(pci_seg->alias_table_size)); + pci_seg->alias_table = kvmalloc_array(pci_seg->last_bdf + 1, + sizeof(*pci_seg->alias_table), + GFP_KERNEL); if (!pci_seg->alias_table) return -ENOMEM; @@ -716,8 +706,7 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg) static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg) { - iommu_free_pages(pci_seg->alias_table, - get_order(pci_seg->alias_table_size)); + kvfree(pci_seg->alias_table); pci_seg->alias_table = NULL; } @@ -728,8 +717,7 @@ static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg) */ static int __init alloc_command_buffer(struct amd_iommu *iommu) { - iommu->cmd_buf = iommu_alloc_pages(GFP_KERNEL, - get_order(CMD_BUFFER_SIZE)); + iommu->cmd_buf = iommu_alloc_pages_sz(GFP_KERNEL, CMD_BUFFER_SIZE); return iommu->cmd_buf ? 0 : -ENOMEM; } @@ -826,20 +814,22 @@ static void iommu_disable_command_buffer(struct amd_iommu *iommu) static void __init free_command_buffer(struct amd_iommu *iommu) { - iommu_free_pages(iommu->cmd_buf, get_order(CMD_BUFFER_SIZE)); + iommu_free_pages(iommu->cmd_buf); } void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp, size_t size) { - int order = get_order(size); - void *buf = iommu_alloc_pages(gfp, order); + void *buf; - if (buf && - check_feature(FEATURE_SNP) && - set_memory_4k((unsigned long)buf, (1 << order))) { - iommu_free_pages(buf, order); - buf = NULL; + size = PAGE_ALIGN(size); + buf = iommu_alloc_pages_sz(gfp, size); + if (!buf) + return NULL; + if (check_feature(FEATURE_SNP) && + set_memory_4k((unsigned long)buf, size / PAGE_SIZE)) { + iommu_free_pages(buf); + return NULL; } return buf; @@ -882,14 +872,14 @@ static void iommu_disable_event_buffer(struct amd_iommu *iommu) static void __init free_event_buffer(struct amd_iommu *iommu) { - iommu_free_pages(iommu->evt_buf, get_order(EVT_BUFFER_SIZE)); + iommu_free_pages(iommu->evt_buf); } static void free_ga_log(struct amd_iommu *iommu) { #ifdef CONFIG_IRQ_REMAP - iommu_free_pages(iommu->ga_log, get_order(GA_LOG_SIZE)); - iommu_free_pages(iommu->ga_log_tail, get_order(8)); + iommu_free_pages(iommu->ga_log); + iommu_free_pages(iommu->ga_log_tail); #endif } @@ -934,11 +924,11 @@ 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 = iommu_alloc_pages(GFP_KERNEL, get_order(GA_LOG_SIZE)); + iommu->ga_log = iommu_alloc_pages_sz(GFP_KERNEL, GA_LOG_SIZE); if (!iommu->ga_log) goto err_out; - iommu->ga_log_tail = iommu_alloc_pages(GFP_KERNEL, get_order(8)); + iommu->ga_log_tail = iommu_alloc_pages_sz(GFP_KERNEL, 8); if (!iommu->ga_log_tail) goto err_out; @@ -959,7 +949,7 @@ static int __init alloc_cwwb_sem(struct amd_iommu *iommu) static void __init free_cwwb_sem(struct amd_iommu *iommu) { if (iommu->cmd_sem) - iommu_free_page((void *)iommu->cmd_sem); + iommu_free_pages((void *)iommu->cmd_sem); } static void iommu_enable_xt(struct amd_iommu *iommu) @@ -984,36 +974,12 @@ static void iommu_enable_gt(struct amd_iommu *iommu) } /* 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) +static void set_dte_bit(struct dev_table_entry *dte, 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); + dte->data[i] |= (1UL << _bit); } static bool __copy_device_table(struct amd_iommu *iommu) @@ -1057,8 +1023,8 @@ static bool __copy_device_table(struct amd_iommu *iommu) if (!old_devtb) return false; - pci_seg->old_dev_tbl_cpy = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32, - get_order(pci_seg->dev_table_size)); + pci_seg->old_dev_tbl_cpy = iommu_alloc_pages_sz( + GFP_KERNEL | GFP_DMA32, 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); @@ -1081,11 +1047,9 @@ static bool __copy_device_table(struct amd_iommu *iommu) } /* 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; + tmp = (DTE_GCR3_30_15 | DTE_GCR3_51_31); pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp; - tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A; - tmp |= DTE_FLAG_GV; + tmp = (DTE_GCR3_14_12 | DTE_FLAG_GV); pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp; } } @@ -1095,7 +1059,8 @@ static bool __copy_device_table(struct amd_iommu *iommu) 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)) { + (int_tab_len != DTE_INTTABLEN_512 && + int_tab_len != DTE_INTTABLEN_2K)) { pr_err("Wrong old irq remapping flag: %#x\n", devid); memunmap(old_devtb); return false; @@ -1136,42 +1101,107 @@ static bool copy_device_table(void) return true; } -void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid) +struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid) { - int sysmgt; + struct ivhd_dte_flags *e; + unsigned int best_len = UINT_MAX; + struct dev_table_entry *dte = NULL; + + for_each_ivhd_dte_flags(e) { + /* + * Need to go through the whole list to find the smallest range, + * which contains the devid. + */ + if ((e->segid == segid) && + (e->devid_first <= devid) && (devid <= e->devid_last)) { + unsigned int len = e->devid_last - e->devid_first; + + if (len < best_len) { + dte = &(e->dte); + best_len = len; + } + } + } + return dte; +} - sysmgt = get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1) | - (get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2) << 1); +static bool search_ivhd_dte_flags(u16 segid, u16 first, u16 last) +{ + struct ivhd_dte_flags *e; - if (sysmgt == 0x01) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_IW); + for_each_ivhd_dte_flags(e) { + if ((e->segid == segid) && + (e->devid_first == first) && + (e->devid_last == last)) + return true; + } + return false; } /* * 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) +static void __init +set_dev_entry_from_acpi_range(struct amd_iommu *iommu, u16 first, u16 last, + 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); + int i; + struct dev_table_entry dte = {}; + + /* Parse IVHD DTE setting flags and store information */ + if (flags) { + struct ivhd_dte_flags *d; + + if (search_ivhd_dte_flags(iommu->pci_seg->id, first, last)) + return; - amd_iommu_apply_erratum_63(iommu, devid); + d = kzalloc(sizeof(struct ivhd_dte_flags), GFP_KERNEL); + if (!d) + return; - amd_iommu_set_rlookup_table(iommu, devid); + pr_debug("%s: devid range %#x:%#x\n", __func__, first, last); + + if (flags & ACPI_DEVFLAG_INITPASS) + set_dte_bit(&dte, DEV_ENTRY_INIT_PASS); + if (flags & ACPI_DEVFLAG_EXTINT) + set_dte_bit(&dte, DEV_ENTRY_EINT_PASS); + if (flags & ACPI_DEVFLAG_NMI) + set_dte_bit(&dte, DEV_ENTRY_NMI_PASS); + if (flags & ACPI_DEVFLAG_SYSMGT1) + set_dte_bit(&dte, DEV_ENTRY_SYSMGT1); + if (flags & ACPI_DEVFLAG_SYSMGT2) + set_dte_bit(&dte, DEV_ENTRY_SYSMGT2); + if (flags & ACPI_DEVFLAG_LINT0) + set_dte_bit(&dte, DEV_ENTRY_LINT0_PASS); + if (flags & ACPI_DEVFLAG_LINT1) + set_dte_bit(&dte, DEV_ENTRY_LINT1_PASS); + + /* Apply erratum 63, which needs info in initial_dte */ + if (FIELD_GET(DTE_DATA1_SYSMGT_MASK, dte.data[1]) == 0x1) + dte.data[0] |= DTE_FLAG_IW; + + memcpy(&d->dte, &dte, sizeof(dte)); + d->segid = iommu->pci_seg->id; + d->devid_first = first; + d->devid_last = last; + list_add_tail(&d->list, &amd_ivhd_dev_flags_list); + } + + for (i = first; i <= last; i++) { + if (flags) { + struct dev_table_entry *dev_table = get_dev_table(iommu); + + memcpy(&dev_table[i], &dte, sizeof(dte)); + } + amd_iommu_set_rlookup_table(iommu, i); + } +} + +static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu, + u16 devid, u32 flags, u32 ext_flags) +{ + set_dev_entry_from_acpi_range(iommu, devid, devid, flags, ext_flags); } int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line) @@ -1239,7 +1269,7 @@ static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u32 *devid, entry->cmd_line = cmd_line; entry->root_devid = (entry->devid & (~0x7)); - pr_info("%s, add hid:%s, uid:%s, rdevid:%d\n", + pr_info("%s, add hid:%s, uid:%s, rdevid:%#x\n", entry->cmd_line ? "cmd" : "ivrs", entry->hid, entry->uid, entry->root_devid); @@ -1331,15 +1361,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, 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); + DUMP_printk(" DEV_ALL\t\t\tsetting: %#02x\n", e->flags); + set_dev_entry_from_acpi_range(iommu, 0, pci_seg->last_bdf, e->flags, 0); break; case IVHD_DEV_SELECT: - DUMP_printk(" DEV_SELECT\t\t\t devid: %04x:%02x:%02x.%x " - "flags: %02x\n", + DUMP_printk(" DEV_SELECT\t\t\tdevid: %04x:%02x:%02x.%x flags: %#02x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1350,8 +1377,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_SELECT_RANGE_START: - DUMP_printk(" DEV_SELECT_RANGE_START\t " - "devid: %04x:%02x:%02x.%x flags: %02x\n", + DUMP_printk(" DEV_SELECT_RANGE_START\tdevid: %04x:%02x:%02x.%x flags: %#02x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1364,8 +1390,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, 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", + DUMP_printk(" DEV_ALIAS\t\t\tdevid: %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), @@ -1382,9 +1407,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, 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", + DUMP_printk(" DEV_ALIAS_RANGE\t\tdevid: %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), @@ -1401,8 +1424,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_EXT_SELECT: - DUMP_printk(" DEV_EXT_SELECT\t\t devid: %04x:%02x:%02x.%x " - "flags: %02x ext: %08x\n", + DUMP_printk(" DEV_EXT_SELECT\t\tdevid: %04x:%02x:%02x.%x flags: %#02x ext: %08x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1414,8 +1436,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_EXT_SELECT_RANGE: - DUMP_printk(" DEV_EXT_SELECT_RANGE\t devid: " - "%04x:%02x:%02x.%x flags: %02x ext: %08x\n", + DUMP_printk(" DEV_EXT_SELECT_RANGE\tdevid: %04x:%02x:%02x.%x flags: %#02x ext: %08x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1428,21 +1449,18 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_RANGE_END: - DUMP_printk(" DEV_RANGE_END\t\t devid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_RANGE_END\t\tdevid: %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) { + 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); } + set_dev_entry_from_acpi_range(iommu, devid_start, devid, flags, ext_flags); + set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags); break; case IVHD_DEV_SPECIAL: { u8 handle, type; @@ -1461,11 +1479,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, else var = "UNKNOWN"; - DUMP_printk(" DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x, flags: %#02x\n", var, (int)handle, seg_id, PCI_BUS_NUM(devid), PCI_SLOT(devid), - PCI_FUNC(devid)); + PCI_FUNC(devid), + e->flags); ret = add_special_device(type, handle, &devid, false); if (ret) @@ -1525,11 +1544,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, } devid = PCI_SEG_DEVID_TO_SBDF(seg_id, e->devid); - DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x, flags: %#02x\n", hid, uid, seg_id, PCI_BUS_NUM(devid), PCI_SLOT(devid), - PCI_FUNC(devid)); + PCI_FUNC(devid), + e->flags); flags = e->flags; @@ -1578,9 +1598,9 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id, 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->dev_table_size = + max(roundup_pow_of_two((last_bdf + 1) * DEV_TABLE_ENTRY_SIZE), + SZ_4K); pci_seg->id = id; init_llist_head(&pci_seg->dev_data_list); @@ -1757,13 +1777,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, 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)) + /* GAM requires GA mode. */ + if ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0) amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; break; case 0x11: @@ -1773,13 +1788,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, 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)) { + /* XT and GAM require GA mode. */ + if ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0) { amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; break; } @@ -1787,6 +1797,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; + if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) { + pr_warn_once("Host Address Translation is not supported.\n"); + amd_iommu_hatdis = true; + } + early_iommu_features_init(iommu, h); break; @@ -2019,9 +2034,6 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) if (!iommu->dev) return -ENODEV; - /* Prevent binding other PCI device drivers to IOMMU devices */ - iommu->dev->match_driver = false; - /* ACPI _PRT won't have an IRQ for IOMMU */ iommu->dev->irq_managed = 1; @@ -2110,7 +2122,15 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) return ret; } - iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL); + ret = iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL); + if (ret || amd_iommu_pgtable == PD_MODE_NONE) { + /* + * Remove sysfs if DMA translation is not supported by the + * IOMMU. Do not return an error to enable IRQ remapping + * in state_next(), DTE[V, TV] must eventually be set to 0. + */ + iommu_device_sysfs_remove(&iommu->iommu); + } return pci_enable_device(iommu->dev); } @@ -2145,7 +2165,7 @@ static void print_iommu_info(void) if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) pr_info("X2APIC enabled\n"); } - if (amd_iommu_pgtable == AMD_IOMMU_V2) { + if (amd_iommu_pgtable == PD_MODE_V2) { pr_info("V2 page table enabled (Paging mode : %d level)\n", amd_iommu_gpt_level); } @@ -2332,7 +2352,7 @@ static struct irq_chip intcapxt_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = intcapxt_set_affinity, .irq_set_wake = intcapxt_set_wake, - .flags = IRQCHIP_MASK_ON_SUSPEND, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_MOVE_DEFERRED, }; static const struct irq_domain_ops intcapxt_domain_ops = { @@ -2571,13 +2591,13 @@ 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) + if (!dev_table || amd_iommu_pgtable == PD_MODE_NONE) return; for (devid = 0; devid <= pci_seg->last_bdf; ++devid) { - __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_VALID); + set_dte_bit(&dev_table[devid], DEV_ENTRY_VALID); if (!amd_iommu_snp_en) - __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_TRANSLATION); + set_dte_bit(&dev_table[devid], DEV_ENTRY_TRANSLATION); } } @@ -2605,8 +2625,7 @@ static void init_device_table(void) 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); + set_dte_bit(&pci_seg->dev_table[devid], DEV_ENTRY_IRQ_TBL_EN); } } @@ -2634,7 +2653,11 @@ static void iommu_init_flags(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_COHERENT_EN); /* Set IOTLB invalidation timeout to 1s */ - iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S); + iommu_feature_set(iommu, CTRL_INV_TO_1S, CTRL_INV_TO_MASK, CONTROL_INV_TIMEOUT); + + /* Enable Enhanced Peripheral Page Request Handling */ + if (check_feature(FEATURE_EPHSUP)) + iommu_feature_enable(iommu, CONTROL_EPH_EN); } static void iommu_apply_resume_quirks(struct amd_iommu *iommu) @@ -2723,6 +2746,17 @@ static void iommu_enable_irtcachedis(struct amd_iommu *iommu) iommu->irtcachedis_enabled ? "disabled" : "enabled"); } +static void iommu_enable_2k_int(struct amd_iommu *iommu) +{ + if (!FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2)) + return; + + iommu_feature_set(iommu, + CONTROL_NUM_INT_REMAP_MODE_2K, + CONTROL_NUM_INT_REMAP_MODE_MASK, + CONTROL_NUM_INT_REMAP_MODE); +} + static void early_enable_iommu(struct amd_iommu *iommu) { iommu_disable(iommu); @@ -2735,6 +2769,7 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_enable_ga(iommu); iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); + iommu_enable_2k_int(iommu); iommu_enable(iommu); amd_iommu_flush_all_caches(iommu); } @@ -2763,8 +2798,7 @@ static void early_enable_iommus(void) for_each_pci_segment(pci_seg) { if (pci_seg->old_dev_tbl_cpy != NULL) { - iommu_free_pages(pci_seg->old_dev_tbl_cpy, - get_order(pci_seg->dev_table_size)); + iommu_free_pages(pci_seg->old_dev_tbl_cpy); pci_seg->old_dev_tbl_cpy = NULL; } } @@ -2777,8 +2811,7 @@ static void early_enable_iommus(void) pr_info("Copied DEV table from previous kernel.\n"); for_each_pci_segment(pci_seg) { - iommu_free_pages(pci_seg->dev_table, - get_order(pci_seg->dev_table_size)); + iommu_free_pages(pci_seg->dev_table); pci_seg->dev_table = pci_seg->old_dev_tbl_cpy; } @@ -2791,6 +2824,7 @@ static void early_enable_iommus(void) iommu_enable_ga(iommu); iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); + iommu_enable_2k_int(iommu); iommu_set_device_table(iommu); amd_iommu_flush_all_caches(iommu); } @@ -2917,9 +2951,6 @@ static struct syscore_ops amd_iommu_syscore_ops = { 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(); } @@ -3018,8 +3049,9 @@ static void __init ivinfo_init(void *ivrs) static int __init early_amd_iommu_init(void) { struct acpi_table_header *ivrs_base; - int remap_cache_sz, ret; + int ret; acpi_status status; + u8 efr_hats; if (!amd_iommu_detected) return -ENODEV; @@ -3033,6 +3065,11 @@ static int __init early_amd_iommu_init(void) return -EINVAL; } + if (!boot_cpu_has(X86_FEATURE_CX16)) { + pr_err("Failed to initialize. The CMPXCHG16B feature is required.\n"); + return -EINVAL; + } + /* * Validate checksum here so we don't need to do it when * we actually parse the table @@ -3059,13 +3096,37 @@ static int __init early_amd_iommu_init(void) FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL) amd_iommu_gpt_level = PAGE_MODE_5_LEVEL; - if (amd_iommu_pgtable == AMD_IOMMU_V2) { + efr_hats = FIELD_GET(FEATURE_HATS, amd_iommu_efr); + if (efr_hats != 0x3) { + /* + * efr[HATS] bits specify the maximum host translation level + * supported, with LEVEL 4 being initial max level. + */ + amd_iommu_hpt_level = efr_hats + PAGE_MODE_4_LEVEL; + } else { + pr_warn_once(FW_BUG "Disable host address translation due to invalid translation level (%#x).\n", + efr_hats); + amd_iommu_hatdis = true; + } + + if (amd_iommu_pgtable == PD_MODE_V2) { if (!amd_iommu_v2_pgtbl_supported()) { pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; + amd_iommu_pgtable = PD_MODE_V1; } } + if (amd_iommu_hatdis) { + /* + * Host (v1) page table is not available. Attempt to use + * Guest (v2) page table. + */ + if (amd_iommu_v2_pgtbl_supported()) + amd_iommu_pgtable = PD_MODE_V2; + else + amd_iommu_pgtable = PD_MODE_NONE; + } + /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -3075,22 +3136,7 @@ static int __init early_amd_iommu_init(void) 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; @@ -3171,7 +3217,7 @@ out: return true; } -static void iommu_snp_enable(void) +static __init void iommu_snp_enable(void) { #ifdef CONFIG_KVM_AMD_SEV if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) @@ -3185,7 +3231,7 @@ static void iommu_snp_enable(void) goto disable_snp; } - if (amd_iommu_pgtable != AMD_IOMMU_V1) { + if (amd_iommu_pgtable != PD_MODE_V1) { pr_warn("SNP: IOMMU is configured with V2 page table mode, SNP cannot be supported.\n"); goto disable_snp; } @@ -3196,6 +3242,14 @@ static void iommu_snp_enable(void) goto disable_snp; } + /* + * Enable host SNP support once SNP support is checked on IOMMU. + */ + if (snp_rmptable_init()) { + pr_warn("SNP: RMP initialization failed, SNP cannot be supported.\n"); + goto disable_snp; + } + pr_info("IOMMU SNP support enabled.\n"); return; @@ -3295,6 +3349,19 @@ static int __init iommu_go_to_state(enum iommu_init_state state) ret = state_next(); } + /* + * SNP platform initilazation requires IOMMUs to be fully configured. + * If the SNP support on IOMMUs has NOT been checked, simply mark SNP + * as unsupported. If the SNP support on IOMMUs has been checked and + * host SNP support enabled but RMP enforcement has not been enabled + * in IOMMUs, then the system is in a half-baked state, but can limp + * along as all memory should be Hypervisor-Owned in the RMP. WARN, + * but leave SNP as "supported" to avoid confusing the kernel. + */ + if (ret && cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !WARN_ON_ONCE(amd_iommu_snp_en)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return ret; } @@ -3352,7 +3419,6 @@ int amd_iommu_enable_faulting(unsigned int cpu) */ static int __init amd_iommu_init(void) { - struct amd_iommu *iommu; int ret; ret = iommu_go_to_state(IOMMU_INITIALIZED); @@ -3366,8 +3432,8 @@ static int __init amd_iommu_init(void) } #endif - for_each_iommu(iommu) - amd_iommu_debugfs_setup(iommu); + if (!ret) + amd_iommu_debugfs_setup(); return ret; } @@ -3398,25 +3464,28 @@ static bool amd_iommu_sme_check(void) * IOMMUs * ****************************************************************************/ -int __init amd_iommu_detect(void) +void __init amd_iommu_detect(void) { int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return -ENODEV; + goto disable_snp; if (!amd_iommu_sme_check()) - return -ENODEV; + goto disable_snp; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return ret; + goto disable_snp; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + return; - return 1; +disable_snp: + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); } /**************************************************************************** @@ -3464,9 +3533,9 @@ static int __init parse_amd_iommu_options(char *str) } 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; + amd_iommu_pgtable = PD_MODE_V1; } else if (strncmp(str, "pgtbl_v2", 8) == 0) { - amd_iommu_pgtable = AMD_IOMMU_V2; + amd_iommu_pgtable = PD_MODE_V2; } else if (strncmp(str, "irtcachedis", 11) == 0) { amd_iommu_irtcachedis = true; } else if (strncmp(str, "nohugepages", 11) == 0) { @@ -3569,7 +3638,7 @@ static int __init parse_ivrs_acpihid(char *str) { u32 seg = 0, bus, dev, fn; char *hid, *uid, *p, *addr; - char acpiid[ACPIID_LEN] = {0}; + char acpiid[ACPIID_LEN + 1] = { }; /* size with NULL terminator */ int i; addr = strchr(str, '@'); @@ -3595,7 +3664,7 @@ static int __init parse_ivrs_acpihid(char *str) /* We have the '@', make it the terminator to get just the acpiid */ *addr++ = 0; - if (strlen(str) > ACPIID_LEN + 1) + if (strlen(str) > ACPIID_LEN) goto not_found; if (sscanf(str, "=%s", acpiid) != 1) @@ -3626,6 +3695,14 @@ found: while (*uid == '0' && *(uid + 1)) uid++; + if (strlen(hid) >= ACPIHID_HID_LEN) { + pr_err("Invalid command line: hid is too long\n"); + return 1; + } else if (strlen(uid) >= ACPIHID_UID_LEN) { + pr_err("Invalid command line: uid is too long\n"); + return 1; + } + i = early_acpihid_map_size++; memcpy(early_acpihid_map[i].hid, hid, strlen(hid)); memcpy(early_acpihid_map[i].uid, uid, strlen(uid)); diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index f3399087859f..a91e71f981ef 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -47,21 +47,7 @@ static u64 *first_pte_l7(u64 *pte, unsigned long *page_size, 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) +static void free_pt_lvl(u64 *pt, struct iommu_pages_list *freelist, int lvl) { u64 *p; int i; @@ -84,20 +70,20 @@ static void free_pt_lvl(u64 *pt, struct list_head *freelist, int lvl) if (lvl > 2) free_pt_lvl(p, freelist, lvl - 1); else - free_pt_page(p, freelist); + iommu_pages_list_add(freelist, p); } - free_pt_page(pt, freelist); + iommu_pages_list_add(freelist, pt); } -static void free_sub_pt(u64 *root, int mode, struct list_head *freelist) +static void free_sub_pt(u64 *root, int mode, struct iommu_pages_list *freelist) { switch (mode) { case PAGE_MODE_NONE: case PAGE_MODE_7_LEVEL: break; case PAGE_MODE_1_LEVEL: - free_pt_page(root, freelist); + iommu_pages_list_add(freelist, root); break; case PAGE_MODE_2_LEVEL: case PAGE_MODE_3_LEVEL: @@ -128,7 +114,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, bool ret = true; u64 *pte; - pte = iommu_alloc_page_node(cfg->amd.nid, gfp); + pte = iommu_alloc_pages_node_sz(cfg->amd.nid, gfp, SZ_4K); if (!pte) return false; @@ -139,7 +125,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, goto out; ret = false; - if (WARN_ON_ONCE(pgtable->mode == PAGE_MODE_6_LEVEL)) + if (WARN_ON_ONCE(pgtable->mode == amd_iommu_hpt_level)) goto out; *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); @@ -153,7 +139,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, out: spin_unlock_irqrestore(&domain->lock, flags); - iommu_free_page(pte); + iommu_free_pages(pte); return ret; } @@ -220,7 +206,8 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, if (!IOMMU_PTE_PRESENT(__pte) || pte_level == PAGE_MODE_NONE) { - page = iommu_alloc_page_node(cfg->amd.nid, gfp); + page = iommu_alloc_pages_node_sz(cfg->amd.nid, gfp, + SZ_4K); if (!page) return NULL; @@ -229,7 +216,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, /* pte could have been changed somewhere. */ if (!try_cmpxchg64(pte, &__pte, __npte)) - iommu_free_page(page); + iommu_free_pages(page); else if (IOMMU_PTE_PRESENT(__pte)) *updated = true; @@ -306,7 +293,8 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, return pte; } -static void free_clear_pte(u64 *pte, u64 pteval, struct list_head *freelist) +static void free_clear_pte(u64 *pte, u64 pteval, + struct iommu_pages_list *freelist) { u64 *pt; int mode; @@ -335,7 +323,7 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova, int prot, gfp_t gfp, size_t *mapped) { struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); - LIST_HEAD(freelist); + struct iommu_pages_list freelist = IOMMU_PAGES_LIST_INIT(freelist); bool updated = false; u64 __pte, *pte; int ret, i, count; @@ -360,7 +348,7 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova, for (i = 0; i < count; ++i) free_clear_pte(&pte[i], pte[i], &freelist); - if (!list_empty(&freelist)) + if (!iommu_pages_list_empty(&freelist)) updated = true; if (count > 1) { @@ -531,14 +519,14 @@ static int iommu_v1_read_and_clear_dirty(struct io_pgtable_ops *ops, static void v1_free_pgtable(struct io_pgtable *iop) { struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, pgtbl); - LIST_HEAD(freelist); + struct iommu_pages_list freelist = IOMMU_PAGES_LIST_INIT(freelist); if (pgtable->mode == PAGE_MODE_NONE) return; /* Page-table is not visible to IOMMU anymore, so free it */ BUG_ON(pgtable->mode < PAGE_MODE_NONE || - pgtable->mode > PAGE_MODE_6_LEVEL); + pgtable->mode > amd_iommu_hpt_level); free_sub_pt(pgtable->root, pgtable->mode, &freelist); iommu_put_pages_list(&freelist); @@ -548,7 +536,8 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo { struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); - pgtable->root = iommu_alloc_page_node(cfg->amd.nid, GFP_KERNEL); + pgtable->root = + iommu_alloc_pages_node_sz(cfg->amd.nid, GFP_KERNEL, SZ_4K); if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index c616de2c5926..b47941353ccb 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -121,10 +121,10 @@ static void free_pgtable(u64 *pt, int level) if (level > 2) free_pgtable(p, level - 1); else - iommu_free_page(p); + iommu_free_pages(p); } - iommu_free_page(pt); + iommu_free_pages(pt); } /* Allocate page table */ @@ -152,14 +152,14 @@ static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova, } if (!IOMMU_PTE_PRESENT(__pte)) { - page = iommu_alloc_page_node(nid, gfp); + page = iommu_alloc_pages_node_sz(nid, gfp, SZ_4K); if (!page) return NULL; __npte = set_pgtable_attr(page); /* pte could have been changed somewhere. */ if (!try_cmpxchg64(pte, &__pte, __npte)) - iommu_free_page(page); + iommu_free_pages(page); else if (IOMMU_PTE_PRESENT(__pte)) *updated = true; @@ -181,7 +181,7 @@ static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova, if (pg_size == IOMMU_PAGE_SIZE_1G) free_pgtable(__pte, end_level - 1); else if (pg_size == IOMMU_PAGE_SIZE_2M) - iommu_free_page(__pte); + iommu_free_pages(__pte); } return pte; @@ -254,7 +254,7 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, pte = v2_alloc_pte(cfg->amd.nid, pgtable->pgd, iova, map_size, gfp, &updated); if (!pte) { - ret = -EINVAL; + ret = -ENOMEM; goto out; } @@ -346,7 +346,7 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); int ias = IOMMU_IN_ADDR_BIT_SIZE; - pgtable->pgd = iommu_alloc_page_node(cfg->amd.nid, GFP_KERNEL); + pgtable->pgd = iommu_alloc_pages_node_sz(cfg->amd.nid, GFP_KERNEL, SZ_4K); if (!pgtable->pgd) return NULL; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 3f691e1fd22c..eb348c63a8d0 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -25,6 +25,7 @@ #include <linux/notifier.h> #include <linux/export.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/msi.h> #include <linux/irqdomain.h> #include <linux/percpu.h> @@ -63,32 +64,153 @@ static const struct iommu_dirty_ops amd_dirty_ops; int amd_iommu_max_glx_val = -1; /* - * general struct to manage commands send to an IOMMU - */ -struct iommu_cmd { - u32 data[4]; -}; - -/* * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap * to know which ones are already in use. */ DEFINE_IDA(pdom_ids); -struct kmem_cache *amd_iommu_irq_cache; - static int amd_iommu_attach_device(struct iommu_domain *dom, struct device *dev); static void set_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data); +static void iommu_flush_dte_sync(struct amd_iommu *iommu, u16 devid); + +static struct iommu_dev_data *find_dev_data(struct amd_iommu *iommu, u16 devid); + /**************************************************************************** * * Helper functions * ****************************************************************************/ +static __always_inline void amd_iommu_atomic128_set(__int128 *ptr, __int128 val) +{ + /* + * Note: + * We use arch_cmpxchg128_local() because: + * - Need cmpxchg16b instruction mainly for 128-bit store to DTE + * (not necessary for cmpxchg since this function is already + * protected by a spin_lock for this DTE). + * - Neither need LOCK_PREFIX nor try loop because of the spin_lock. + */ + arch_cmpxchg128_local(ptr, *ptr, val); +} + +static void write_dte_upper128(struct dev_table_entry *ptr, struct dev_table_entry *new) +{ + struct dev_table_entry old; + + old.data128[1] = ptr->data128[1]; + /* + * Preserve DTE_DATA2_INTR_MASK. This needs to be + * done here since it requires to be inside + * spin_lock(&dev_data->dte_lock) context. + */ + new->data[2] &= ~DTE_DATA2_INTR_MASK; + new->data[2] |= old.data[2] & DTE_DATA2_INTR_MASK; + + amd_iommu_atomic128_set(&ptr->data128[1], new->data128[1]); +} + +static void write_dte_lower128(struct dev_table_entry *ptr, struct dev_table_entry *new) +{ + amd_iommu_atomic128_set(&ptr->data128[0], new->data128[0]); +} + +/* + * Note: + * IOMMU reads the entire Device Table entry in a single 256-bit transaction + * but the driver is programming DTE using 2 128-bit cmpxchg. So, the driver + * need to ensure the following: + * - DTE[V|GV] bit is being written last when setting. + * - DTE[V|GV] bit is being written first when clearing. + * + * This function is used only by code, which updates DMA translation part of the DTE. + * So, only consider control bits related to DMA when updating the entry. + */ +static void update_dte256(struct amd_iommu *iommu, struct iommu_dev_data *dev_data, + struct dev_table_entry *new) +{ + unsigned long flags; + struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry *ptr = &dev_table[dev_data->devid]; + + spin_lock_irqsave(&dev_data->dte_lock, flags); + + if (!(ptr->data[0] & DTE_FLAG_V)) { + /* Existing DTE is not valid. */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!(new->data[0] & DTE_FLAG_V)) { + /* Existing DTE is valid. New DTE is not valid. */ + write_dte_lower128(ptr, new); + write_dte_upper128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!FIELD_GET(DTE_FLAG_GV, ptr->data[0])) { + /* + * Both DTEs are valid. + * Existing DTE has no guest page table. + */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!FIELD_GET(DTE_FLAG_GV, new->data[0])) { + /* + * Both DTEs are valid. + * Existing DTE has guest page table, + * new DTE has no guest page table, + */ + write_dte_lower128(ptr, new); + write_dte_upper128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (FIELD_GET(DTE_GPT_LEVEL_MASK, ptr->data[2]) != + FIELD_GET(DTE_GPT_LEVEL_MASK, new->data[2])) { + /* + * Both DTEs are valid and have guest page table, + * but have different number of levels. So, we need + * to upadte both upper and lower 128-bit value, which + * require disabling and flushing. + */ + struct dev_table_entry clear = {}; + + /* First disable DTE */ + write_dte_lower128(ptr, &clear); + iommu_flush_dte_sync(iommu, dev_data->devid); + + /* Then update DTE */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else { + /* + * Both DTEs are valid and have guest page table, + * and same number of levels. We just need to only + * update the lower 128-bit. So no need to disable DTE. + */ + write_dte_lower128(ptr, new); + } + + spin_unlock_irqrestore(&dev_data->dte_lock, flags); +} + +static void get_dte256(struct amd_iommu *iommu, struct iommu_dev_data *dev_data, + struct dev_table_entry *dte) +{ + unsigned long flags; + struct dev_table_entry *ptr; + struct dev_table_entry *dev_table = get_dev_table(iommu); + + ptr = &dev_table[dev_data->devid]; + + spin_lock_irqsave(&dev_data->dte_lock, flags); + dte->data128[0] = ptr->data128[0]; + dte->data128[1] = ptr->data128[1]; + spin_unlock_irqrestore(&dev_data->dte_lock, flags); +} + static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom) { return (pdom && (pdom->pd_mode == PD_MODE_V2)); @@ -113,7 +235,9 @@ 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; + struct acpihid_map_entry *p, *p1 = NULL; + int hid_count = 0; + bool fw_bug; if (!adev) return -ENODEV; @@ -121,12 +245,33 @@ static inline int get_acpihid_device_id(struct device *dev, 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; + p1 = p; + fw_bug = false; + hid_count = 1; + break; + } + + /* + * Count HID matches w/o UID, raise FW_BUG but allow exactly one match + */ + if (acpi_dev_hid_match(adev, p->hid)) { + p1 = p; + hid_count++; + fw_bug = true; } } - return -EINVAL; + + if (!p1) + return -EINVAL; + if (fw_bug) + dev_err_once(dev, FW_BUG "No ACPI device matched UID, but %d device%s matched HID.\n", + hid_count, hid_count > 1 ? "s" : ""); + if (hid_count > 1) + return -EINVAL; + if (entry) + *entry = p1; + + return p1->devid; } static inline int get_device_sbdf_id(struct device *dev) @@ -209,6 +354,7 @@ static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid) return NULL; mutex_init(&dev_data->mutex); + spin_lock_init(&dev_data->dte_lock); dev_data->devid = devid; ratelimit_default_init(&dev_data->rs); @@ -216,7 +362,7 @@ static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid) return dev_data; } -static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) +struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) { struct iommu_dev_data *dev_data; struct llist_node *node; @@ -236,9 +382,11 @@ static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) { + struct dev_table_entry new; struct amd_iommu *iommu; - struct dev_table_entry *dev_table; + struct iommu_dev_data *dev_data, *alias_data; u16 devid = pci_dev_id(pdev); + int ret = 0; if (devid == alias) return 0; @@ -247,13 +395,27 @@ static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) 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)); + /* Copy the data from pdev */ + dev_data = dev_iommu_priv_get(&pdev->dev); + if (!dev_data) { + pr_err("%s : Failed to get dev_data for 0x%x\n", __func__, devid); + ret = -EINVAL; + goto out; + } + get_dte256(iommu, dev_data, &new); - return 0; + /* Setup alias */ + alias_data = find_dev_data(iommu, alias); + if (!alias_data) { + pr_err("%s : Failed to get alias dev_data for 0x%x\n", __func__, alias); + ret = -EINVAL; + goto out; + } + update_dte256(iommu, alias_data, &new); + + amd_iommu_set_rlookup_table(iommu, alias); +out: + return ret; } static void clone_aliases(struct amd_iommu *iommu, struct device *dev) @@ -466,8 +628,8 @@ static inline void pdev_disable_cap_pasid(struct pci_dev *pdev) static void pdev_enable_caps(struct pci_dev *pdev) { - pdev_enable_cap_ats(pdev); pdev_enable_cap_pasid(pdev); + pdev_enable_cap_ats(pdev); pdev_enable_cap_pri(pdev); } @@ -526,6 +688,12 @@ static int iommu_init_device(struct amd_iommu *iommu, struct device *dev) return -ENOMEM; dev_data->dev = dev; + + /* + * The dev_iommu_priv_set() needes to be called before setup_aliases. + * Otherwise, subsequent call to dev_iommu_priv_get() will fail. + */ + dev_iommu_priv_set(dev, dev_data); setup_aliases(iommu, dev); /* @@ -539,8 +707,6 @@ static int iommu_init_device(struct amd_iommu *iommu, struct device *dev) dev_data->flags = pdev_get_caps(to_pci_dev(dev)); } - dev_iommu_priv_set(dev, dev_data); - return 0; } @@ -571,10 +737,13 @@ static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev) static void dump_dte_entry(struct amd_iommu *iommu, u16 devid) { int i; - struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry dte; + struct iommu_dev_data *dev_data = find_dev_data(iommu, devid); + + get_dte256(iommu, dev_data, &dte); for (i = 0; i < 4; ++i) - pr_err("DTE[%d]: %016llx\n", i, dev_table[devid].data[i]); + pr_err("DTE[%d]: %016llx\n", i, dte.data[i]); } static void dump_command(unsigned long phys_addr) @@ -714,7 +883,7 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt) int type, devid, flags, tag; volatile u32 *event = __evt; int count = 0; - u64 address; + u64 address, ctrl; u32 pasid; retry: @@ -724,6 +893,7 @@ retry: (event[1] & EVENT_DOMID_MASK_LO); flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; address = (u64)(((u64)event[3]) << 32) | event[2]; + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); if (type == 0) { /* Did we hit the erratum? */ @@ -745,6 +915,7 @@ retry: 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); + dev_err(dev, "Control Reg : 0x%llx\n", ctrl); dump_dte_entry(iommu, devid); break; case EVENT_TYPE_DEV_TAB_ERR: @@ -828,6 +999,14 @@ int amd_iommu_register_ga_log_notifier(int (*notifier)(u32)) { iommu_ga_log_notifier = notifier; + /* + * Ensure all in-flight IRQ handlers run to completion before returning + * to the caller, e.g. to ensure module code isn't unloaded while it's + * being executed in the IRQ handler. + */ + if (!notifier) + synchronize_rcu(); + return 0; } EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier); @@ -1261,6 +1440,15 @@ static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid) return iommu_queue_command(iommu, &cmd); } +static void iommu_flush_dte_sync(struct amd_iommu *iommu, u16 devid) +{ + int ret; + + ret = iommu_flush_dte(iommu, devid); + if (!ret) + iommu_completion_wait(iommu); +} + static void amd_iommu_flush_dte_all(struct amd_iommu *iommu) { u32 devid; @@ -1415,6 +1603,7 @@ static int domain_flush_pages_v2(struct protection_domain *pdom, struct iommu_cmd cmd; int ret = 0; + lockdep_assert_held(&pdom->lock); list_for_each_entry(dev_data, &pdom->dev_list, list) { struct amd_iommu *iommu = get_amd_iommu_from_dev(dev_data->dev); u16 domid = dev_data->gcr3_info.domid; @@ -1464,6 +1653,8 @@ static void __domain_flush_pages(struct protection_domain *domain, ioasid_t pasid = IOMMU_NO_PASID; bool gn = false; + lockdep_assert_held(&domain->lock); + if (pdom_is_v2_pgtbl_mode(domain)) { gn = true; ret = domain_flush_pages_v2(domain, address, size); @@ -1585,6 +1776,8 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain) { struct iommu_dev_data *dev_data; + lockdep_assert_held(&domain->lock); + list_for_each_entry(dev_data, &domain->dev_list, list) { struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev); @@ -1598,15 +1791,6 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain) domain_flush_complete(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_all(domain); -} - int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag) { struct iommu_dev_data *dev_data; @@ -1653,7 +1837,7 @@ static void free_gcr3_tbl_level1(u64 *tbl) ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK); - iommu_free_page(ptr); + iommu_free_pages(ptr); } } @@ -1686,7 +1870,7 @@ static void free_gcr3_table(struct gcr3_tbl_info *gcr3_info) /* Free per device domain ID */ pdom_id_free(gcr3_info->domid); - iommu_free_page(gcr3_info->gcr3_tbl); + iommu_free_pages(gcr3_info->gcr3_tbl); gcr3_info->gcr3_tbl = NULL; } @@ -1725,7 +1909,7 @@ static int setup_gcr3_table(struct gcr3_tbl_info *gcr3_info, return -ENOSPC; gcr3_info->domid = domid; - gcr3_info->gcr3_tbl = iommu_alloc_page_node(nid, GFP_ATOMIC); + gcr3_info->gcr3_tbl = iommu_alloc_pages_node_sz(nid, GFP_ATOMIC, SZ_4K); if (gcr3_info->gcr3_tbl == NULL) { pdom_id_free(domid); return -ENOMEM; @@ -1821,90 +2005,109 @@ int amd_iommu_clear_gcr3(struct iommu_dev_data *dev_data, ioasid_t pasid) return ret; } +static void make_clear_dte(struct iommu_dev_data *dev_data, struct dev_table_entry *ptr, + struct dev_table_entry *new) +{ + /* All existing DTE must have V bit set */ + new->data128[0] = DTE_FLAG_V; + new->data128[1] = 0; +} + +/* + * Note: + * The old value for GCR3 table and GPT have been cleared from caller. + */ +static void set_dte_gcr3_table(struct amd_iommu *iommu, + struct iommu_dev_data *dev_data, + struct dev_table_entry *target) +{ + struct gcr3_tbl_info *gcr3_info = &dev_data->gcr3_info; + u64 gcr3; + + if (!gcr3_info->gcr3_tbl) + return; + + pr_debug("%s: devid=%#x, glx=%#x, gcr3_tbl=%#llx\n", + __func__, dev_data->devid, gcr3_info->glx, + (unsigned long long)gcr3_info->gcr3_tbl); + + gcr3 = iommu_virt_to_phys(gcr3_info->gcr3_tbl); + + target->data[0] |= DTE_FLAG_GV | + FIELD_PREP(DTE_GLX, gcr3_info->glx) | + FIELD_PREP(DTE_GCR3_14_12, gcr3 >> 12); + if (pdom_is_v2_pgtbl_mode(dev_data->domain)) + target->data[0] |= DTE_FLAG_GIOV; + + target->data[1] |= FIELD_PREP(DTE_GCR3_30_15, gcr3 >> 15) | + FIELD_PREP(DTE_GCR3_51_31, gcr3 >> 31); + + /* Guest page table can only support 4 and 5 levels */ + if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) + target->data[2] |= FIELD_PREP(DTE_GPT_LEVEL_MASK, GUEST_PGTABLE_5_LEVEL); + else + target->data[2] |= FIELD_PREP(DTE_GPT_LEVEL_MASK, GUEST_PGTABLE_4_LEVEL); +} + static void set_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - u64 pte_root = 0; - u64 flags = 0; - u32 old_domid; - u16 devid = dev_data->devid; u16 domid; + u32 old_domid; + struct dev_table_entry *initial_dte; + struct dev_table_entry new = {}; struct protection_domain *domain = dev_data->domain; - struct dev_table_entry *dev_table = get_dev_table(iommu); struct gcr3_tbl_info *gcr3_info = &dev_data->gcr3_info; + struct dev_table_entry *dte = &get_dev_table(iommu)[dev_data->devid]; if (gcr3_info && gcr3_info->gcr3_tbl) domid = dev_data->gcr3_info.domid; else domid = domain->id; + make_clear_dte(dev_data, dte, &new); + if (domain->iop.mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->iop.root); + new.data[0] |= iommu_virt_to_phys(domain->iop.root); - pte_root |= (domain->iop.mode & DEV_ENTRY_MODE_MASK) + new.data[0] |= (domain->iop.mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; - pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V; + new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW; /* - * When SNP is enabled, Only set TV bit when IOMMU - * page translation is in use. + * When SNP is enabled, we can only support TV=1 with non-zero domain ID. + * This is prevented by the SNP-enable and IOMMU_DOMAIN_IDENTITY check in + * do_iommu_domain_alloc(). */ - if (!amd_iommu_snp_en || (domid != 0)) - pte_root |= DTE_FLAG_TV; - - flags = dev_table[devid].data[1]; - - if (dev_data->ats_enabled) - flags |= DTE_FLAG_IOTLB; + WARN_ON(amd_iommu_snp_en && (domid == 0)); + new.data[0] |= DTE_FLAG_TV; if (dev_data->ppr) - pte_root |= 1ULL << DEV_ENTRY_PPR; + new.data[0] |= 1ULL << DEV_ENTRY_PPR; if (domain->dirty_tracking) - pte_root |= DTE_FLAG_HAD; - - if (gcr3_info && gcr3_info->gcr3_tbl) { - u64 gcr3 = iommu_virt_to_phys(gcr3_info->gcr3_tbl); - u64 glx = gcr3_info->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; + new.data[0] |= DTE_FLAG_HAD; - 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 (dev_data->ats_enabled) + new.data[1] |= DTE_FLAG_IOTLB; - if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) { - dev_table[devid].data[2] |= - ((u64)GUEST_PGTABLE_5_LEVEL << DTE_GPT_LEVEL_SHIFT); - } + old_domid = READ_ONCE(dte->data[1]) & DEV_DOMID_MASK; + new.data[1] |= domid; - /* GIOV is supported with V2 page table mode only */ - if (pdom_is_v2_pgtbl_mode(domain)) - pte_root |= DTE_FLAG_GIOV; + /* + * Restore cached persistent DTE bits, which can be set by information + * in IVRS table. See set_dev_entry_from_acpi(). + */ + initial_dte = amd_iommu_get_ivhd_dte_flags(iommu->pci_seg->id, dev_data->devid); + if (initial_dte) { + new.data128[0] |= initial_dte->data128[0]; + new.data128[1] |= initial_dte->data128[1]; } - flags &= ~DEV_DOMID_MASK; - flags |= domid; + set_dte_gcr3_table(iommu, dev_data, &new); - old_domid = dev_table[devid].data[1] & DEV_DOMID_MASK; - dev_table[devid].data[1] = flags; - dev_table[devid].data[0] = pte_root; + update_dte256(iommu, dev_data, &new); /* * A kdump kernel might be replacing a domain ID that was copied from @@ -1916,19 +2119,16 @@ static void set_dte_entry(struct amd_iommu *iommu, } } -static void clear_dte_entry(struct amd_iommu *iommu, u16 devid) +/* + * Clear DMA-remap related flags to block all DMA (blockeded domain) + */ +static void clear_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry new = {}; + struct dev_table_entry *dte = &get_dev_table(iommu)[dev_data->devid]; - /* 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); + make_clear_dte(dev_data, dte, &new); + update_dte256(iommu, dev_data, &new); } /* Update and flush DTE for the given device */ @@ -1939,7 +2139,7 @@ static void dev_update_dte(struct iommu_dev_data *dev_data, bool set) if (set) set_dte_entry(iommu, dev_data); else - clear_dte_entry(iommu, dev_data->devid); + clear_dte_entry(iommu, dev_data); clone_aliases(iommu, dev_data->dev); device_flush_dte(dev_data); @@ -2002,7 +2202,6 @@ static int pdom_attach_iommu(struct amd_iommu *iommu, struct protection_domain *pdom) { struct pdom_iommu_info *pdom_iommu_info, *curr; - struct io_pgtable_cfg *cfg = &pdom->iop.pgtbl.cfg; unsigned long flags; int ret = 0; @@ -2031,10 +2230,6 @@ static int pdom_attach_iommu(struct amd_iommu *iommu, goto out_unlock; } - /* Update NUMA Node ID */ - if (cfg->amd.nid == NUMA_NO_NODE) - cfg->amd.nid = dev_to_node(&iommu->dev->dev); - out_unlock: spin_unlock_irqrestore(&pdom->lock, flags); return ret; @@ -2073,6 +2268,7 @@ static int attach_device(struct device *dev, struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data); struct pci_dev *pdev; + unsigned long flags; int ret = 0; mutex_lock(&dev_data->mutex); @@ -2113,7 +2309,9 @@ static int attach_device(struct device *dev, /* Update data structures */ dev_data->domain = domain; + spin_lock_irqsave(&domain->lock, flags); list_add(&dev_data->list, &domain->dev_list); + spin_unlock_irqrestore(&domain->lock, flags); /* Update device table */ dev_update_dte(dev_data, true); @@ -2160,6 +2358,7 @@ static void detach_device(struct device *dev) /* Flush IOTLB and wait for the flushes to finish */ spin_lock_irqsave(&domain->lock, flags); amd_iommu_domain_flush_all(domain); + list_del(&dev_data->list); spin_unlock_irqrestore(&domain->lock, flags); /* Clear GCR3 table */ @@ -2168,7 +2367,6 @@ static void detach_device(struct device *dev) /* Update data structures */ dev_data->domain = NULL; - list_del(&dev_data->list); /* decrease reference counters - needs to happen after the flushes */ pdom_detach_iommu(iommu, domain); @@ -2220,9 +2418,22 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) pci_max_pasids(to_pci_dev(dev))); } + if (amd_iommu_pgtable == PD_MODE_NONE) { + pr_warn_once("%s: DMA translation not supported by iommu.\n", + __func__); + iommu_dev = ERR_PTR(-ENODEV); + goto out_err; + } + out_err: + iommu_completion_wait(iommu); + if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2)) + dev_data->max_irqs = MAX_IRQS_PER_TABLE_2K; + else + dev_data->max_irqs = MAX_IRQS_PER_TABLE_512; + if (dev_is_pci(dev)) pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT); @@ -2259,25 +2470,15 @@ static struct iommu_group *amd_iommu_device_group(struct device *dev) * *****************************************************************************/ -void protection_domain_free(struct protection_domain *domain) -{ - WARN_ON(!list_empty(&domain->dev_list)); - if (domain->domain.type & __IOMMU_DOMAIN_PAGING) - free_io_pgtable_ops(&domain->iop.pgtbl.ops); - pdom_id_free(domain->id); - kfree(domain); -} - -static void protection_domain_init(struct protection_domain *domain, int nid) +static void protection_domain_init(struct protection_domain *domain) { spin_lock_init(&domain->lock); INIT_LIST_HEAD(&domain->dev_list); INIT_LIST_HEAD(&domain->dev_data_list); xa_init(&domain->iommu_array); - domain->iop.pgtbl.cfg.amd.nid = nid; } -struct protection_domain *protection_domain_alloc(unsigned int type, int nid) +struct protection_domain *protection_domain_alloc(void) { struct protection_domain *domain; int domid; @@ -2293,78 +2494,82 @@ struct protection_domain *protection_domain_alloc(unsigned int type, int nid) } domain->id = domid; - protection_domain_init(domain, nid); + protection_domain_init(domain); return domain; } static int pdom_setup_pgtable(struct protection_domain *domain, - unsigned int type, int pgtable) + struct device *dev) { struct io_pgtable_ops *pgtbl_ops; + enum io_pgtable_fmt fmt; - /* No need to allocate io pgtable ops in passthrough mode */ - if (!(type & __IOMMU_DOMAIN_PAGING)) - return 0; - - switch (pgtable) { - case AMD_IOMMU_V1: - domain->pd_mode = PD_MODE_V1; + switch (domain->pd_mode) { + case PD_MODE_V1: + fmt = AMD_IOMMU_V1; break; - case AMD_IOMMU_V2: - domain->pd_mode = PD_MODE_V2; + case PD_MODE_V2: + fmt = AMD_IOMMU_V2; break; - default: - return -EINVAL; + case PD_MODE_NONE: + WARN_ON_ONCE(1); + return -EPERM; } - pgtbl_ops = - alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl.cfg, domain); + domain->iop.pgtbl.cfg.amd.nid = dev_to_node(dev); + pgtbl_ops = alloc_io_pgtable_ops(fmt, &domain->iop.pgtbl.cfg, domain); if (!pgtbl_ops) return -ENOMEM; return 0; } -static inline u64 dma_max_address(int pgtable) +static inline u64 dma_max_address(enum protection_domain_mode pgtable) { - if (pgtable == AMD_IOMMU_V1) - return ~0ULL; + if (pgtable == PD_MODE_V1) + return PM_LEVEL_SIZE(amd_iommu_hpt_level); - /* V2 with 4/5 level page table */ - return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1); + /* + * V2 with 4/5 level page table. Note that "2.2.6.5 AMD64 4-Kbyte Page + * Translation" shows that the V2 table sign extends the top of the + * address space creating a reserved region in the middle of the + * translation, just like the CPU does. Further Vasant says the docs are + * incomplete and this only applies to non-zero PASIDs. If the AMDv2 + * page table is assigned to the 0 PASID then there is no sign extension + * check. + * + * Since the IOMMU must have a fixed geometry, and the core code does + * not understand sign extended addressing, we have to chop off the high + * bit to get consistent behavior with attachments of the domain to any + * PASID. + */ + return ((1ULL << (PM_LEVEL_SHIFT(amd_iommu_gpt_level) - 1)) - 1); } static bool amd_iommu_hd_support(struct amd_iommu *iommu) { + if (amd_iommu_hatdis) + return false; + return iommu && (iommu->features & FEATURE_HDSUP); } -static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, - struct device *dev, - u32 flags, int pgtable) +static struct iommu_domain * +do_iommu_domain_alloc(struct device *dev, u32 flags, + enum protection_domain_mode pgtable) { bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; + struct amd_iommu *iommu = get_amd_iommu_from_dev(dev); struct protection_domain *domain; - struct amd_iommu *iommu = NULL; int ret; - if (dev) - iommu = get_amd_iommu_from_dev(dev); - - /* - * 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 ERR_PTR(-EINVAL); - - domain = protection_domain_alloc(type, - dev ? dev_to_node(dev) : NUMA_NO_NODE); + domain = protection_domain_alloc(); if (!domain) return ERR_PTR(-ENOMEM); - ret = pdom_setup_pgtable(domain, type, pgtable); + domain->pd_mode = pgtable; + ret = pdom_setup_pgtable(domain, dev); if (ret) { pdom_id_free(domain->id); kfree(domain); @@ -2376,79 +2581,56 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, domain->domain.geometry.force_aperture = true; domain->domain.pgsize_bitmap = domain->iop.pgtbl.cfg.pgsize_bitmap; - if (iommu) { - domain->domain.type = type; - domain->domain.ops = iommu->iommu.ops->default_domain_ops; + domain->domain.type = IOMMU_DOMAIN_UNMANAGED; + domain->domain.ops = iommu->iommu.ops->default_domain_ops; - if (dirty_tracking) - domain->domain.dirty_ops = &amd_dirty_ops; - } + if (dirty_tracking) + domain->domain.dirty_ops = &amd_dirty_ops; return &domain->domain; } -static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type) -{ - struct iommu_domain *domain; - int pgtable = amd_iommu_pgtable; - - /* - * Force IOMMU v1 page table when allocating - * domain for pass-through devices. - */ - if (type == IOMMU_DOMAIN_UNMANAGED) - pgtable = AMD_IOMMU_V1; - - domain = do_iommu_domain_alloc(type, NULL, 0, pgtable); - if (IS_ERR(domain)) - return NULL; - - return domain; -} - static struct iommu_domain * amd_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags, const struct iommu_user_data *user_data) { - unsigned int type = IOMMU_DOMAIN_UNMANAGED; - struct amd_iommu *iommu = NULL; + struct amd_iommu *iommu = get_amd_iommu_from_dev(dev); const u32 supported_flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_PASID; - if (dev) - iommu = get_amd_iommu_from_dev(dev); - if ((flags & ~supported_flags) || user_data) return ERR_PTR(-EOPNOTSUPP); - /* Allocate domain with v2 page table if IOMMU supports PASID. */ - if (flags & IOMMU_HWPT_ALLOC_PASID) { + switch (flags & supported_flags) { + case IOMMU_HWPT_ALLOC_DIRTY_TRACKING: + /* Allocate domain with v1 page table for dirty tracking */ + if (!amd_iommu_hd_support(iommu)) + break; + return do_iommu_domain_alloc(dev, flags, PD_MODE_V1); + case IOMMU_HWPT_ALLOC_PASID: + /* Allocate domain with v2 page table if IOMMU supports PASID. */ if (!amd_iommu_pasid_supported()) - return ERR_PTR(-EOPNOTSUPP); - - return do_iommu_domain_alloc(type, dev, flags, AMD_IOMMU_V2); - } - - /* Allocate domain with v1 page table for dirty tracking */ - if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) { - if (iommu && amd_iommu_hd_support(iommu)) { - return do_iommu_domain_alloc(type, dev, - flags, AMD_IOMMU_V1); - } - - return ERR_PTR(-EOPNOTSUPP); + break; + return do_iommu_domain_alloc(dev, flags, PD_MODE_V2); + case 0: + /* If nothing specific is required use the kernel commandline default */ + return do_iommu_domain_alloc(dev, 0, amd_iommu_pgtable); + default: + break; } - - /* If nothing specific is required use the kernel commandline default */ - return do_iommu_domain_alloc(type, dev, 0, amd_iommu_pgtable); + return ERR_PTR(-EOPNOTSUPP); } void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain = to_pdomain(dom); - protection_domain_free(domain); + WARN_ON(!list_empty(&domain->dev_list)); + if (domain->domain.type & __IOMMU_DOMAIN_PAGING) + free_io_pgtable_ops(&domain->iop.pgtbl.ops); + pdom_id_free(domain->id); + kfree(domain); } static int blocked_domain_attach_device(struct iommu_domain *domain, @@ -2467,10 +2649,19 @@ static int blocked_domain_attach_device(struct iommu_domain *domain, return 0; } +static int blocked_domain_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old) +{ + amd_iommu_remove_dev_pasid(dev, pasid, old); + return 0; +} + static struct iommu_domain blocked_domain = { .type = IOMMU_DOMAIN_BLOCKED, .ops = &(const struct iommu_domain_ops) { .attach_dev = blocked_domain_attach_device, + .set_dev_pasid = blocked_domain_set_dev_pasid, } }; @@ -2490,7 +2681,7 @@ void amd_iommu_init_identity_domain(void) identity_domain.id = pdom_id_alloc(); - protection_domain_init(&identity_domain, NUMA_NO_NODE); + protection_domain_init(&identity_domain); } /* Same as blocked domain except it supports only ops->attach_dev() */ @@ -2658,12 +2849,12 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, bool enable) { struct protection_domain *pdomain = to_pdomain(domain); - struct dev_table_entry *dev_table; + struct dev_table_entry *dte; struct iommu_dev_data *dev_data; bool domain_flush = false; struct amd_iommu *iommu; unsigned long flags; - u64 pte_root; + u64 new; spin_lock_irqsave(&pdomain->lock, flags); if (!(pdomain->dirty_tracking ^ enable)) { @@ -2672,16 +2863,15 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, } list_for_each_entry(dev_data, &pdomain->dev_list, list) { + spin_lock(&dev_data->dte_lock); iommu = get_amd_iommu_from_dev_data(dev_data); - - dev_table = get_dev_table(iommu); - pte_root = dev_table[dev_data->devid].data[0]; - - pte_root = (enable ? pte_root | DTE_FLAG_HAD : - pte_root & ~DTE_FLAG_HAD); + dte = &get_dev_table(iommu)[dev_data->devid]; + new = dte->data[0]; + new = (enable ? new | DTE_FLAG_HAD : new & ~DTE_FLAG_HAD); + dte->data[0] = new; + spin_unlock(&dev_data->dte_lock); /* Flush device DTE */ - dev_table[dev_data->devid].data[0] = pte_root; device_flush_dte(dev_data); domain_flush = true; } @@ -2769,6 +2959,9 @@ static void amd_iommu_get_resv_regions(struct device *dev, return; list_add_tail(®ion->list, head); + if (amd_iommu_ht_range_ignore()) + return; + region = iommu_alloc_resv_region(HT_RANGE_START, HT_RANGE_END - HT_RANGE_START + 1, 0, IOMMU_RESV_RESERVED, GFP_KERNEL); @@ -2845,44 +3038,11 @@ static const struct iommu_dirty_ops amd_dirty_ops = { .read_and_clear_dirty = amd_iommu_read_and_clear_dirty, }; -static int amd_iommu_dev_enable_feature(struct device *dev, - enum iommu_dev_features feat) -{ - int ret = 0; - - switch (feat) { - case IOMMU_DEV_FEAT_IOPF: - case IOMMU_DEV_FEAT_SVA: - break; - default: - ret = -EINVAL; - break; - } - return ret; -} - -static int amd_iommu_dev_disable_feature(struct device *dev, - enum iommu_dev_features feat) -{ - int ret = 0; - - switch (feat) { - case IOMMU_DEV_FEAT_IOPF: - case IOMMU_DEV_FEAT_SVA: - break; - default: - ret = -EINVAL; - break; - } - return ret; -} - const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .blocked_domain = &blocked_domain, .release_domain = &release_domain, .identity_domain = &identity_domain.domain, - .domain_alloc = amd_iommu_domain_alloc, .domain_alloc_paging_flags = amd_iommu_domain_alloc_paging_flags, .domain_alloc_sva = amd_iommu_domain_alloc_sva, .probe_device = amd_iommu_probe_device, @@ -2891,9 +3051,6 @@ const struct iommu_ops amd_iommu_ops = { .get_resv_regions = amd_iommu_get_resv_regions, .is_attach_deferred = amd_iommu_is_attach_deferred, .def_domain_type = amd_iommu_def_domain_type, - .dev_enable_feat = amd_iommu_dev_enable_feature, - .dev_disable_feat = amd_iommu_dev_disable_feature, - .remove_dev_pasid = amd_iommu_remove_dev_pasid, .page_response = amd_iommu_page_response, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = amd_iommu_attach_device, @@ -2945,20 +3102,33 @@ out: raw_spin_unlock_irqrestore(&iommu->lock, flags); } +static inline u8 iommu_get_int_tablen(struct iommu_dev_data *dev_data) +{ + if (dev_data && dev_data->max_irqs == MAX_IRQS_PER_TABLE_2K) + return DTE_INTTABLEN_2K; + return DTE_INTTABLEN_512; +} + 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); + u64 new; + struct dev_table_entry *dte = &get_dev_table(iommu)[devid]; + struct iommu_dev_data *dev_data = search_dev_data(iommu, devid); + + if (dev_data) + spin_lock(&dev_data->dte_lock); - 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; + new = READ_ONCE(dte->data[2]); + new &= ~DTE_IRQ_PHYS_ADDR_MASK; + new |= iommu_virt_to_phys(table->table); + new |= DTE_IRQ_REMAP_INTCTL; + new |= iommu_get_int_tablen(dev_data); + new |= DTE_IRQ_REMAP_ENABLE; + WRITE_ONCE(dte->data[2], new); - dev_table[devid].data[2] = dte; + if (dev_data) + spin_unlock(&dev_data->dte_lock); } static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid) @@ -2979,7 +3149,7 @@ static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid) return table; } -static struct irq_remap_table *__alloc_irq_table(void) +static struct irq_remap_table *__alloc_irq_table(int nid, size_t size) { struct irq_remap_table *table; @@ -2987,19 +3157,14 @@ static struct irq_remap_table *__alloc_irq_table(void) if (!table) return NULL; - table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL); + table->table = iommu_alloc_pages_node_sz( + nid, GFP_KERNEL, max(DTE_INTTAB_ALIGNMENT, size)); 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; } @@ -3031,13 +3196,23 @@ static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias, return 0; } +static inline size_t get_irq_table_size(unsigned int max_irqs) +{ + if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + return max_irqs * sizeof(u32); + + return max_irqs * (sizeof(u64) * 2); +} + static struct irq_remap_table *alloc_irq_table(struct amd_iommu *iommu, - u16 devid, struct pci_dev *pdev) + u16 devid, struct pci_dev *pdev, + unsigned int max_irqs) { struct irq_remap_table *table = NULL; struct irq_remap_table *new_table = NULL; struct amd_iommu_pci_seg *pci_seg; unsigned long flags; + int nid = iommu && iommu->dev ? dev_to_node(&iommu->dev->dev) : NUMA_NO_NODE; u16 alias; spin_lock_irqsave(&iommu_table_lock, flags); @@ -3056,7 +3231,7 @@ static struct irq_remap_table *alloc_irq_table(struct amd_iommu *iommu, spin_unlock_irqrestore(&iommu_table_lock, flags); /* Nothing there yet, allocate new irq remapping table */ - new_table = __alloc_irq_table(); + new_table = __alloc_irq_table(nid, get_irq_table_size(max_irqs)); if (!new_table) return NULL; @@ -3091,20 +3266,21 @@ out_unlock: spin_unlock_irqrestore(&iommu_table_lock, flags); if (new_table) { - kmem_cache_free(amd_iommu_irq_cache, new_table->table); + iommu_free_pages(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) + bool align, struct pci_dev *pdev, + unsigned long max_irqs) { struct irq_remap_table *table; int index, c, alignment = 1; unsigned long flags; - table = alloc_irq_table(iommu, devid, pdev); + table = alloc_irq_table(iommu, devid, pdev, max_irqs); if (!table) return -ENODEV; @@ -3115,7 +3291,7 @@ static int alloc_irq_index(struct amd_iommu *iommu, u16 devid, int count, /* Scan table for free entries */ for (index = ALIGN(table->min_index, alignment), c = 0; - index < MAX_IRQS_PER_TABLE;) { + index < max_irqs;) { if (!iommu->irte_ops->is_allocated(table, index)) { c += 1; } else { @@ -3385,6 +3561,14 @@ 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; + /* + * The struct msi_msg.dest_mode_logical is used to set the DM bit + * in MSI Message Address Register. For device w/ 2K int-remap support, + * this is bit must be set to 1 regardless of the actual destination + * mode, which is signified by the IRTE[DM]. + */ + if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2)) + msg->arch_addr_lo.dest_mode_logical = true; msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; } @@ -3447,6 +3631,8 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, struct amd_ir_data *data = NULL; struct amd_iommu *iommu; struct irq_cfg *cfg; + struct iommu_dev_data *dev_data; + unsigned long max_irqs; int i, ret, devid, seg, sbdf; int index; @@ -3465,6 +3651,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, if (!iommu) return -EINVAL; + dev_data = search_dev_data(iommu, devid); + max_irqs = dev_data ? dev_data->max_irqs : MAX_IRQS_PER_TABLE_512; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); if (ret < 0) return ret; @@ -3472,7 +3661,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) { struct irq_remap_table *table; - table = alloc_irq_table(iommu, devid, NULL); + table = alloc_irq_table(iommu, devid, NULL, max_irqs); if (table) { if (!table->min_index) { /* @@ -3493,9 +3682,11 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, 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)); + msi_desc_to_pci_dev(info->desc), + max_irqs); } else { - index = alloc_irq_index(iommu, devid, nr_irqs, false, NULL); + index = alloc_irq_index(iommu, devid, nr_irqs, false, NULL, + max_irqs); } if (index < 0) { @@ -3532,7 +3723,6 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, 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; @@ -3634,13 +3824,70 @@ static const struct irq_domain_ops amd_ir_domain_ops = { .deactivate = irq_remapping_deactivate, }; -int amd_iommu_activate_guest_mode(void *data) +static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu, + bool ga_log_intr) +{ + if (cpu >= 0) { + entry->lo.fields_vapic.destination = + APICID_TO_IRTE_DEST_LO(cpu); + entry->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cpu); + entry->lo.fields_vapic.is_run = true; + entry->lo.fields_vapic.ga_log_intr = false; + } else { + entry->lo.fields_vapic.is_run = false; + entry->lo.fields_vapic.ga_log_intr = ga_log_intr; + } +} + +/* + * Update the pCPU information for an IRTE that is configured to post IRQs to + * a vCPU, without issuing an IOMMU invalidation for the IRTE. + * + * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination + * with the pCPU's APIC ID, set IsRun, and clear GALogIntr. If the vCPU isn't + * associated with a pCPU (@cpu < 0), clear IsRun and set/clear GALogIntr based + * on input from the caller (e.g. KVM only requests GALogIntr when the vCPU is + * blocking and requires a notification wake event). I.e. treat vCPUs that are + * associated with a pCPU as running. This API is intended to be used when a + * vCPU is scheduled in/out (or stops running for any reason), to do a fast + * update of IsRun, GALogIntr, and (conditionally) Destination. + * + * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached + * and thus don't require an invalidation to ensure the IOMMU consumes fresh + * information. + */ +int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + if (!ir_data->iommu) + return -ENODEV; + + __amd_iommu_update_ga(entry, cpu, ga_log_intr); + + return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry); +} +EXPORT_SYMBOL(amd_iommu_update_ga); + +int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr) { 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) + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry) return 0; valid = entry->lo.fields_vapic.valid; @@ -3650,11 +3897,12 @@ int amd_iommu_activate_guest_mode(void *data) 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; + __amd_iommu_update_ga(entry, cpu, ga_log_intr); + return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, ir_data->irq_2_irte.index, entry); } @@ -3667,8 +3915,10 @@ int amd_iommu_deactivate_guest_mode(void *data) 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) + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry || !entry->lo.fields_vapic.guest_mode) return 0; valid = entry->lo.fields_remap.valid; @@ -3690,15 +3940,17 @@ int amd_iommu_deactivate_guest_mode(void *data) } EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); -static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) +static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info) { int ret; - struct amd_iommu_pi_data *pi_data = vcpu_info; - struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data; + struct amd_iommu_pi_data *pi_data = info; 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 (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + if (ir_data->iommu == NULL) return -EINVAL; @@ -3709,38 +3961,23 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) * we should not modify the IRTE */ if (!dev_data || !dev_data->use_vapic) - return 0; + return -EINVAL; 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; - } + if (pi_data) { + pi_data->ir_data = ir_data; - 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_root_ptr = (pi_data->vapic_addr >> 12); + ir_data->ga_vector = pi_data->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; + if (pi_data->is_guest_mode) + ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu, + pi_data->ga_log_intr); + else + ret = amd_iommu_deactivate_guest_mode(ir_data); } 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; @@ -3807,54 +4044,30 @@ static struct irq_chip amd_ir_chip = { static const struct msi_parent_ops amdvi_msi_parent_ops = { .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | MSI_FLAG_MULTI_PCI_MSI, + .bus_select_token = DOMAIN_BUS_AMDVI, + .bus_select_mask = MATCH_PCI_MSI, .prefix = "IR-", .init_dev_msi_info = msi_parent_init_dev_msi_info, }; int amd_iommu_create_irq_domain(struct amd_iommu *iommu) { - struct fwnode_handle *fn; + struct irq_domain_info info = { + .fwnode = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index), + .ops = &amd_ir_domain_ops, + .domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI, + .host_data = iommu, + .parent = arch_get_ir_parent_domain(), + }; - fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index); - if (!fn) + if (!info.fwnode) return -ENOMEM; - iommu->ir_domain = irq_domain_create_hierarchy(arch_get_ir_parent_domain(), 0, 0, - fn, &amd_ir_domain_ops, iommu); + + iommu->ir_domain = msi_create_parent_irq_domain(&info, &amdvi_msi_parent_ops); if (!iommu->ir_domain) { - irq_domain_free_fwnode(fn); + irq_domain_free_fwnode(info.fwnode); return -ENOMEM; } - - irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_AMDVI); - iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT | - IRQ_DOMAIN_FLAG_ISOLATED_MSI; - iommu->ir_domain->msi_parent_ops = &amdvi_msi_parent_ops; - return 0; } - -int amd_iommu_update_ga(int cpu, bool is_run, void *data) -{ - struct amd_ir_data *ir_data = (struct amd_ir_data *)data; - struct irte_ga *entry = (struct irte_ga *) ir_data->entry; - - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || !entry->lo.fields_vapic.guest_mode) - return 0; - - if (!ir_data->iommu) - return -ENODEV; - - if (cpu >= 0) { - entry->lo.fields_vapic.destination = - APICID_TO_IRTE_DEST_LO(cpu); - entry->hi.fields.destination = - APICID_TO_IRTE_DEST_HI(cpu); - } - entry->lo.fields_vapic.is_run = is_run; - - return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry); -} -EXPORT_SYMBOL(amd_iommu_update_ga); #endif diff --git a/drivers/iommu/amd/pasid.c b/drivers/iommu/amd/pasid.c index 8c73a30c2800..77c8e9a91cbc 100644 --- a/drivers/iommu/amd/pasid.c +++ b/drivers/iommu/amd/pasid.c @@ -185,16 +185,17 @@ struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct protection_domain *pdom; int ret; - pdom = protection_domain_alloc(IOMMU_DOMAIN_SVA, dev_to_node(dev)); + pdom = protection_domain_alloc(); if (!pdom) return ERR_PTR(-ENOMEM); pdom->domain.ops = &amd_sva_domain_ops; pdom->mn.ops = &sva_mn; + pdom->domain.type = IOMMU_DOMAIN_SVA; ret = mmu_notifier_register(&pdom->mn, mm); if (ret) { - protection_domain_free(pdom); + amd_iommu_domain_free(&pdom->domain); return ERR_PTR(ret); } diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index 7c67d69f0b8c..e6767c057d01 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -48,7 +48,7 @@ void amd_iommu_enable_ppr_log(struct amd_iommu *iommu) void __init amd_iommu_free_ppr_log(struct amd_iommu *iommu) { - iommu_free_pages(iommu->ppr_log, get_order(PPR_LOG_SIZE)); + iommu_free_pages(iommu->ppr_log); } /* |