diff options
Diffstat (limited to 'drivers/iommu')
| -rw-r--r-- | drivers/iommu/amd_iommu.c | 2 | ||||
| -rw-r--r-- | drivers/iommu/arm-smmu-v3.c | 542 | ||||
| -rw-r--r-- | drivers/iommu/dma-iommu.c | 8 | ||||
| -rw-r--r-- | drivers/iommu/dmar.c | 2 | ||||
| -rw-r--r-- | drivers/iommu/exynos-iommu.c | 13 | ||||
| -rw-r--r-- | drivers/iommu/intel-iommu.c | 6 | ||||
| -rw-r--r-- | drivers/iommu/intel-svm.c | 19 | ||||
| -rw-r--r-- | drivers/iommu/io-pgtable-arm-v7s.c | 21 | ||||
| -rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 91 | ||||
| -rw-r--r-- | drivers/iommu/io-pgtable.h | 4 | ||||
| -rw-r--r-- | drivers/iommu/iommu.c | 6 | ||||
| -rw-r--r-- | drivers/iommu/mtk_iommu.c | 15 | ||||
| -rw-r--r-- | drivers/iommu/mtk_iommu.h | 1 | ||||
| -rw-r--r-- | drivers/iommu/mtk_iommu_v1.c | 54 | ||||
| -rw-r--r-- | drivers/iommu/omap-iommu.c | 2 | ||||
| -rw-r--r-- | drivers/iommu/rockchip-iommu.c | 592 |
16 files changed, 679 insertions, 699 deletions
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 6107e24bed8a..8c469b51185f 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3044,7 +3044,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, size_t unmap_size; if (domain->mode == PAGE_MODE_NONE) - return -EINVAL; + return 0; mutex_lock(&domain->api_lock); unmap_size = iommu_unmap_page(domain, iova, page_size); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 3f2f1fc68b52..1d647104bccc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -22,6 +22,8 @@ #include <linux/acpi.h> #include <linux/acpi_iort.h> +#include <linux/bitfield.h> +#include <linux/bitops.h> #include <linux/delay.h> #include <linux/dma-iommu.h> #include <linux/err.h> @@ -43,18 +45,15 @@ /* MMIO registers */ #define ARM_SMMU_IDR0 0x0 -#define IDR0_ST_LVL_SHIFT 27 -#define IDR0_ST_LVL_MASK 0x3 -#define IDR0_ST_LVL_2LVL (1 << IDR0_ST_LVL_SHIFT) -#define IDR0_STALL_MODEL_SHIFT 24 -#define IDR0_STALL_MODEL_MASK 0x3 -#define IDR0_STALL_MODEL_STALL (0 << IDR0_STALL_MODEL_SHIFT) -#define IDR0_STALL_MODEL_FORCE (2 << IDR0_STALL_MODEL_SHIFT) -#define IDR0_TTENDIAN_SHIFT 21 -#define IDR0_TTENDIAN_MASK 0x3 -#define IDR0_TTENDIAN_LE (2 << IDR0_TTENDIAN_SHIFT) -#define IDR0_TTENDIAN_BE (3 << IDR0_TTENDIAN_SHIFT) -#define IDR0_TTENDIAN_MIXED (0 << IDR0_TTENDIAN_SHIFT) +#define IDR0_ST_LVL GENMASK(28, 27) +#define IDR0_ST_LVL_2LVL 1 +#define IDR0_STALL_MODEL GENMASK(25, 24) +#define IDR0_STALL_MODEL_STALL 0 +#define IDR0_STALL_MODEL_FORCE 2 +#define IDR0_TTENDIAN GENMASK(22, 21) +#define IDR0_TTENDIAN_MIXED 0 +#define IDR0_TTENDIAN_LE 2 +#define IDR0_TTENDIAN_BE 3 #define IDR0_CD2L (1 << 19) #define IDR0_VMID16 (1 << 18) #define IDR0_PRI (1 << 16) @@ -64,10 +63,9 @@ #define IDR0_ATS (1 << 10) #define IDR0_HYP (1 << 9) #define IDR0_COHACC (1 << 4) -#define IDR0_TTF_SHIFT 2 -#define IDR0_TTF_MASK 0x3 -#define IDR0_TTF_AARCH64 (2 << IDR0_TTF_SHIFT) -#define IDR0_TTF_AARCH32_64 (3 << IDR0_TTF_SHIFT) +#define IDR0_TTF GENMASK(3, 2) +#define IDR0_TTF_AARCH64 2 +#define IDR0_TTF_AARCH32_64 3 #define IDR0_S1P (1 << 1) #define IDR0_S2P (1 << 0) @@ -75,31 +73,27 @@ #define IDR1_TABLES_PRESET (1 << 30) #define IDR1_QUEUES_PRESET (1 << 29) #define IDR1_REL (1 << 28) -#define IDR1_CMDQ_SHIFT 21 -#define IDR1_CMDQ_MASK 0x1f -#define IDR1_EVTQ_SHIFT 16 -#define IDR1_EVTQ_MASK 0x1f -#define IDR1_PRIQ_SHIFT 11 -#define IDR1_PRIQ_MASK 0x1f -#define IDR1_SSID_SHIFT 6 -#define IDR1_SSID_MASK 0x1f -#define IDR1_SID_SHIFT 0 -#define IDR1_SID_MASK 0x3f +#define IDR1_CMDQS GENMASK(25, 21) +#define IDR1_EVTQS GENMASK(20, 16) +#define IDR1_PRIQS GENMASK(15, 11) +#define IDR1_SSIDSIZE GENMASK(10, 6) +#define IDR1_SIDSIZE GENMASK(5, 0) #define ARM_SMMU_IDR5 0x14 -#define IDR5_STALL_MAX_SHIFT 16 -#define IDR5_STALL_MAX_MASK 0xffff +#define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) #define IDR5_GRAN16K (1 << 5) #define IDR5_GRAN4K (1 << 4) -#define IDR5_OAS_SHIFT 0 -#define IDR5_OAS_MASK 0x7 -#define IDR5_OAS_32_BIT (0 << IDR5_OAS_SHIFT) -#define IDR5_OAS_36_BIT (1 << IDR5_OAS_SHIFT) -#define IDR5_OAS_40_BIT (2 << IDR5_OAS_SHIFT) -#define IDR5_OAS_42_BIT (3 << IDR5_OAS_SHIFT) -#define IDR5_OAS_44_BIT (4 << IDR5_OAS_SHIFT) -#define IDR5_OAS_48_BIT (5 << IDR5_OAS_SHIFT) +#define IDR5_OAS GENMASK(2, 0) +#define IDR5_OAS_32_BIT 0 +#define IDR5_OAS_36_BIT 1 +#define IDR5_OAS_40_BIT 2 +#define IDR5_OAS_42_BIT 3 +#define IDR5_OAS_44_BIT 4 +#define IDR5_OAS_48_BIT 5 +#define IDR5_OAS_52_BIT 6 +#define IDR5_VAX GENMASK(11, 10) +#define IDR5_VAX_52_BIT 1 #define ARM_SMMU_CR0 0x20 #define CR0_CMDQEN (1 << 3) @@ -110,18 +104,16 @@ #define ARM_SMMU_CR0ACK 0x24 #define ARM_SMMU_CR1 0x28 -#define CR1_SH_NSH 0 -#define CR1_SH_OSH 2 -#define CR1_SH_ISH 3 +#define CR1_TABLE_SH GENMASK(11, 10) +#define CR1_TABLE_OC GENMASK(9, 8) +#define CR1_TABLE_IC GENMASK(7, 6) +#define CR1_QUEUE_SH GENMASK(5, 4) +#define CR1_QUEUE_OC GENMASK(3, 2) +#define CR1_QUEUE_IC GENMASK(1, 0) +/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */ #define CR1_CACHE_NC 0 #define CR1_CACHE_WB 1 #define CR1_CACHE_WT 2 -#define CR1_TABLE_SH_SHIFT 10 -#define CR1_TABLE_OC_SHIFT 8 -#define CR1_TABLE_IC_SHIFT 6 -#define CR1_QUEUE_SH_SHIFT 4 -#define CR1_QUEUE_OC_SHIFT 2 -#define CR1_QUEUE_IC_SHIFT 0 #define ARM_SMMU_CR2 0x2c #define CR2_PTM (1 << 2) @@ -129,8 +121,8 @@ #define CR2_E2H (1 << 0) #define ARM_SMMU_GBPA 0x44 -#define GBPA_ABORT (1 << 20) #define GBPA_UPDATE (1 << 31) +#define GBPA_ABORT (1 << 20) #define ARM_SMMU_IRQ_CTRL 0x50 #define IRQ_CTRL_EVTQ_IRQEN (1 << 2) @@ -158,18 +150,14 @@ #define ARM_SMMU_STRTAB_BASE 0x80 #define STRTAB_BASE_RA (1UL << 62) -#define STRTAB_BASE_ADDR_SHIFT 6 -#define STRTAB_BASE_ADDR_MASK 0x3ffffffffffUL +#define STRTAB_BASE_ADDR_MASK GENMASK_ULL(51, 6) #define ARM_SMMU_STRTAB_BASE_CFG 0x88 -#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT 0 -#define STRTAB_BASE_CFG_LOG2SIZE_MASK 0x3f -#define STRTAB_BASE_CFG_SPLIT_SHIFT 6 -#define STRTAB_BASE_CFG_SPLIT_MASK 0x1f -#define STRTAB_BASE_CFG_FMT_SHIFT 16 -#define STRTAB_BASE_CFG_FMT_MASK 0x3 -#define STRTAB_BASE_CFG_FMT_LINEAR (0 << STRTAB_BASE_CFG_FMT_SHIFT) -#define STRTAB_BASE_CFG_FMT_2LVL (1 << STRTAB_BASE_CFG_FMT_SHIFT) +#define STRTAB_BASE_CFG_FMT GENMASK(17, 16) +#define STRTAB_BASE_CFG_FMT_LINEAR 0 +#define STRTAB_BASE_CFG_FMT_2LVL 1 +#define STRTAB_BASE_CFG_SPLIT GENMASK(10, 6) +#define STRTAB_BASE_CFG_LOG2SIZE GENMASK(5, 0) #define ARM_SMMU_CMDQ_BASE 0x90 #define ARM_SMMU_CMDQ_PROD 0x98 @@ -190,14 +178,16 @@ #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc /* Common MSI config fields */ -#define MSI_CFG0_ADDR_SHIFT 2 -#define MSI_CFG0_ADDR_MASK 0x3fffffffffffUL -#define MSI_CFG2_SH_SHIFT 4 -#define MSI_CFG2_SH_NSH (0UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_SH_OSH (2UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_SH_ISH (3UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_MEMATTR_SHIFT 0 -#define MSI_CFG2_MEMATTR_DEVICE_nGnRE (0x1 << MSI_CFG2_MEMATTR_SHIFT) +#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) +#define MSI_CFG2_SH GENMASK(5, 4) +#define MSI_CFG2_MEMATTR GENMASK(3, 0) + +/* Common memory attribute values */ +#define ARM_SMMU_SH_NSH 0 +#define ARM_SMMU_SH_OSH 2 +#define ARM_SMMU_SH_ISH 3 +#define ARM_SMMU_MEMATTR_DEVICE_nGnRE 0x1 +#define ARM_SMMU_MEMATTR_OIWB 0xf #define Q_IDX(q, p) ((p) & ((1 << (q)->max_n_shift) - 1)) #define Q_WRP(q, p) ((p) & (1 << (q)->max_n_shift)) @@ -207,10 +197,8 @@ Q_IDX(q, p) * (q)->ent_dwords) #define Q_BASE_RWA (1UL << 62) -#define Q_BASE_ADDR_SHIFT 5 -#define Q_BASE_ADDR_MASK 0xfffffffffffUL -#define Q_BASE_LOG2SIZE_SHIFT 0 -#define Q_BASE_LOG2SIZE_MASK 0x1fUL +#define Q_BASE_ADDR_MASK GENMASK_ULL(51, 5) +#define Q_BASE_LOG2SIZE GENMASK(4, 0) /* * Stream table. @@ -223,187 +211,143 @@ #define STRTAB_SPLIT 8 #define STRTAB_L1_DESC_DWORDS 1 -#define STRTAB_L1_DESC_SPAN_SHIFT 0 -#define STRTAB_L1_DESC_SPAN_MASK 0x1fUL -#define STRTAB_L1_DESC_L2PTR_SHIFT 6 -#define STRTAB_L1_DESC_L2PTR_MASK 0x3ffffffffffUL +#define STRTAB_L1_DESC_SPAN GENMASK_ULL(4, 0) +#define STRTAB_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 6) #define STRTAB_STE_DWORDS 8 #define STRTAB_STE_0_V (1UL << 0) -#define STRTAB_STE_0_CFG_SHIFT 1 -#define STRTAB_STE_0_CFG_MASK 0x7UL -#define STRTAB_STE_0_CFG_ABORT (0UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_BYPASS (4UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_S1_TRANS (5UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_S2_TRANS (6UL << STRTAB_STE_0_CFG_SHIFT) - -#define STRTAB_STE_0_S1FMT_SHIFT 4 -#define STRTAB_STE_0_S1FMT_LINEAR (0UL << STRTAB_STE_0_S1FMT_SHIFT) -#define STRTAB_STE_0_S1CTXPTR_SHIFT 6 -#define STRTAB_STE_0_S1CTXPTR_MASK 0x3ffffffffffUL -#define STRTAB_STE_0_S1CDMAX_SHIFT 59 -#define STRTAB_STE_0_S1CDMAX_MASK 0x1fUL +#define STRTAB_STE_0_CFG GENMASK_ULL(3, 1) +#define STRTAB_STE_0_CFG_ABORT 0 +#define STRTAB_STE_0_CFG_BYPASS 4 +#define STRTAB_STE_0_CFG_S1_TRANS 5 +#define STRTAB_STE_0_CFG_S2_TRANS 6 + +#define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) +#define STRTAB_STE_0_S1FMT_LINEAR 0 +#define STRTAB_STE_0_S1CTXPTR_MASK GENMASK_ULL(51, 6) +#define STRTAB_STE_0_S1CDMAX GENMASK_ULL(63, 59) #define STRTAB_STE_1_S1C_CACHE_NC 0UL #define STRTAB_STE_1_S1C_CACHE_WBRA 1UL #define STRTAB_STE_1_S1C_CACHE_WT 2UL #define STRTAB_STE_1_S1C_CACHE_WB 3UL -#define STRTAB_STE_1_S1C_SH_NSH 0UL -#define STRTAB_STE_1_S1C_SH_OSH 2UL -#define STRTAB_STE_1_S1C_SH_ISH 3UL -#define STRTAB_STE_1_S1CIR_SHIFT 2 -#define STRTAB_STE_1_S1COR_SHIFT 4 -#define STRTAB_STE_1_S1CSH_SHIFT 6 +#define STRTAB_STE_1_S1CIR GENMASK_ULL(3, 2) +#define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) +#define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) #define STRTAB_STE_1_S1STALLD (1UL << 27) +#define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) #define STRTAB_STE_1_EATS_ABT 0UL #define STRTAB_STE_1_EATS_TRANS 1UL #define STRTAB_STE_1_EATS_S1CHK 2UL -#define STRTAB_STE_1_EATS_SHIFT 28 +#define STRTAB_STE_1_STRW GENMASK_ULL(31, 30) #define STRTAB_STE_1_STRW_NSEL1 0UL #define STRTAB_STE_1_STRW_EL2 2UL -#define STRTAB_STE_1_STRW_SHIFT 30 +#define STRTAB_STE_1_SHCFG GENMASK_ULL(45, 44) #define STRTAB_STE_1_SHCFG_INCOMING 1UL -#define STRTAB_STE_1_SHCFG_SHIFT 44 -#define STRTAB_STE_2_S2VMID_SHIFT 0 -#define STRTAB_STE_2_S2VMID_MASK 0xffffUL -#define STRTAB_STE_2_VTCR_SHIFT 32 -#define STRTAB_STE_2_VTCR_MASK 0x7ffffUL +#define STRTAB_STE_2_S2VMID GENMASK_ULL(15, 0) +#define STRTAB_STE_2_VTCR GENMASK_ULL(50, 32) #define STRTAB_STE_2_S2AA64 (1UL << 51) #define STRTAB_STE_2_S2ENDI (1UL << 52) #define STRTAB_STE_2_S2PTW (1UL << 54) #define STRTAB_STE_2_S2R (1UL << 58) -#define STRTAB_STE_3_S2TTB_SHIFT 4 -#define STRTAB_STE_3_S2TTB_MASK 0xfffffffffffUL +#define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) /* Context descriptor (stage-1 only) */ #define CTXDESC_CD_DWORDS 8 -#define CTXDESC_CD_0_TCR_T0SZ_SHIFT 0 -#define ARM64_TCR_T0SZ_SHIFT 0 -#define ARM64_TCR_T0SZ_MASK 0x1fUL -#define CTXDESC_CD_0_TCR_TG0_SHIFT 6 -#define ARM64_TCR_TG0_SHIFT 14 -#define ARM64_TCR_TG0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_IRGN0_SHIFT 8 -#define ARM64_TCR_IRGN0_SHIFT 8 -#define ARM64_TCR_IRGN0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_ORGN0_SHIFT 10 -#define ARM64_TCR_ORGN0_SHIFT 10 -#define ARM64_TCR_ORGN0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_SH0_SHIFT 12 -#define ARM64_TCR_SH0_SHIFT 12 -#define ARM64_TCR_SH0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_EPD0_SHIFT 14 -#define ARM64_TCR_EPD0_SHIFT 7 -#define ARM64_TCR_EPD0_MASK 0x1UL -#define CTXDESC_CD_0_TCR_EPD1_SHIFT 30 -#define ARM64_TCR_EPD1_SHIFT 23 -#define ARM64_TCR_EPD1_MASK 0x1UL +#define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0) +#define ARM64_TCR_T0SZ GENMASK_ULL(5, 0) +#define CTXDESC_CD_0_TCR_TG0 GENMASK_ULL(7, 6) +#define ARM64_TCR_TG0 GENMASK_ULL(15, 14) +#define CTXDESC_CD_0_TCR_IRGN0 GENMASK_ULL(9, 8) +#define ARM64_TCR_IRGN0 GENMASK_ULL(9, 8) +#define CTXDESC_CD_0_TCR_ORGN0 GENMASK_ULL(11, 10) +#define ARM64_TCR_ORGN0 GENMASK_ULL(11, 10) +#define CTXDESC_CD_0_TCR_SH0 GENMASK_ULL(13, 12) +#define ARM64_TCR_SH0 GENMASK_ULL(13, 12) +#define CTXDESC_CD_0_TCR_EPD0 (1ULL << 14) +#define ARM64_TCR_EPD0 (1ULL << 7) +#define CTXDESC_CD_0_TCR_EPD1 (1ULL << 30) +#define ARM64_TCR_EPD1 (1ULL << 23) #define CTXDESC_CD_0_ENDI (1UL << 15) #define CTXDESC_CD_0_V (1UL << 31) -#define CTXDESC_CD_0_TCR_IPS_SHIFT 32 -#define ARM64_TCR_IPS_SHIFT 32 -#define ARM64_TCR_IPS_MASK 0x7UL -#define CTXDESC_CD_0_TCR_TBI0_SHIFT 38 -#define ARM64_TCR_TBI0_SHIFT 37 -#define ARM64_TCR_TBI0_MASK 0x1UL +#define CTXDESC_CD_0_TCR_IPS GENMASK_ULL(34, 32) +#define ARM64_TCR_IPS GENMASK_ULL(34, 32) +#define CTXDESC_CD_0_TCR_TBI0 (1ULL << 38) +#define ARM64_TCR_TBI0 (1ULL << 37) #define CTXDESC_CD_0_AA64 (1UL << 41) #define CTXDESC_CD_0_S (1UL << 44) #define CTXDESC_CD_0_R (1UL << 45) #define CTXDESC_CD_0_A (1UL << 46) -#define CTXDESC_CD_0_ASET_SHIFT 47 -#define CTXDESC_CD_0_ASET_SHARED (0UL << CTXDESC_CD_0_ASET_SHIFT) -#define CTXDESC_CD_0_ASET_PRIVATE (1UL << CTXDESC_CD_0_ASET_SHIFT) -#define CTXDESC_CD_0_ASID_SHIFT 48 -#define CTXDESC_CD_0_ASID_MASK 0xffffUL - -#define CTXDESC_CD_1_TTB0_SHIFT 4 -#define CTXDESC_CD_1_TTB0_MASK 0xfffffffffffUL +#define CTXDESC_CD_0_ASET (1UL << 47) +#define CTXDESC_CD_0_ASID GENMASK_ULL(63, 48) -#define CTXDESC_CD_3_MAIR_SHIFT 0 +#define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ -#define ARM_SMMU_TCR2CD(tcr, fld) \ - (((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK) \ - << CTXDESC_CD_0_TCR_##fld##_SHIFT) +#define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ + FIELD_GET(ARM64_TCR_##fld, tcr)) /* Command queue */ #define CMDQ_ENT_DWORDS 2 #define CMDQ_MAX_SZ_SHIFT 8 -#define CMDQ_ERR_SHIFT 24 -#define CMDQ_ERR_MASK 0x7f +#define CMDQ_CONS_ERR GENMASK(30, 24) #define CMDQ_ERR_CERROR_NONE_IDX 0 #define CMDQ_ERR_CERROR_ILL_IDX 1 #define CMDQ_ERR_CERROR_ABT_IDX 2 -#define CMDQ_0_OP_SHIFT 0 -#define CMDQ_0_OP_MASK 0xffUL +#define CMDQ_0_OP GENMASK_ULL(7, 0) #define CMDQ_0_SSV (1UL << 11) -#define CMDQ_PREFETCH_0_SID_SHIFT 32 -#define CMDQ_PREFETCH_1_SIZE_SHIFT 0 -#define CMDQ_PREFETCH_1_ADDR_MASK ~0xfffUL +#define CMDQ_PREFETCH_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PREFETCH_1_SIZE GENMASK_ULL(4, 0) +#define CMDQ_PREFETCH_1_ADDR_MASK GENMASK_ULL(63, 12) -#define CMDQ_CFGI_0_SID_SHIFT 32 -#define CMDQ_CFGI_0_SID_MASK 0xffffffffUL +#define CMDQ_CFGI_0_SID GENMASK_ULL(63, 32) #define CMDQ_CFGI_1_LEAF (1UL << 0) -#define CMDQ_CFGI_1_RANGE_SHIFT 0 -#define CMDQ_CFGI_1_RANGE_MASK 0x1fUL +#define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) -#define CMDQ_TLBI_0_VMID_SHIFT 32 -#define CMDQ_TLBI_0_ASID_SHIFT 48 +#define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) +#define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) #define CMDQ_TLBI_1_LEAF (1UL << 0) -#define CMDQ_TLBI_1_VA_MASK ~0xfffUL -#define CMDQ_TLBI_1_IPA_MASK 0xfffffffff000UL - -#define CMDQ_PRI_0_SSID_SHIFT 12 -#define CMDQ_PRI_0_SSID_MASK 0xfffffUL -#define CMDQ_PRI_0_SID_SHIFT 32 -#define CMDQ_PRI_0_SID_MASK 0xffffffffUL -#define CMDQ_PRI_1_GRPID_SHIFT 0 -#define CMDQ_PRI_1_GRPID_MASK 0x1ffUL -#define CMDQ_PRI_1_RESP_SHIFT 12 -#define CMDQ_PRI_1_RESP_DENY (0UL << CMDQ_PRI_1_RESP_SHIFT) -#define CMDQ_PRI_1_RESP_FAIL (1UL << CMDQ_PRI_1_RESP_SHIFT) -#define CMDQ_PRI_1_RESP_SUCC (2UL << CMDQ_PRI_1_RESP_SHIFT) - -#define CMDQ_SYNC_0_CS_SHIFT 12 -#define CMDQ_SYNC_0_CS_NONE (0UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_CS_IRQ (1UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_CS_SEV (2UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_MSH_SHIFT 22 -#define CMDQ_SYNC_0_MSH_ISH (3UL << CMDQ_SYNC_0_MSH_SHIFT) -#define CMDQ_SYNC_0_MSIATTR_SHIFT 24 -#define CMDQ_SYNC_0_MSIATTR_OIWB (0xfUL << CMDQ_SYNC_0_MSIATTR_SHIFT) -#define CMDQ_SYNC_0_MSIDATA_SHIFT 32 -#define CMDQ_SYNC_0_MSIDATA_MASK 0xffffffffUL -#define CMDQ_SYNC_1_MSIADDR_SHIFT 0 -#define CMDQ_SYNC_1_MSIADDR_MASK 0xffffffffffffcUL +#define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) +#define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) + +#define CMDQ_PRI_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_PRI_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PRI_1_GRPID GENMASK_ULL(8, 0) +#define CMDQ_PRI_1_RESP GENMASK_ULL(13, 12) + +#define CMDQ_SYNC_0_CS GENMASK_ULL(13, 12) +#define CMDQ_SYNC_0_CS_NONE 0 +#define CMDQ_SYNC_0_CS_IRQ 1 +#define CMDQ_SYNC_0_CS_SEV 2 +#define CMDQ_SYNC_0_MSH GENMASK_ULL(23, 22) +#define CMDQ_SYNC_0_MSIATTR GENMASK_ULL(27, 24) +#define CMDQ_SYNC_0_MSIDATA GENMASK_ULL(63, 32) +#define CMDQ_SYNC_1_MSIADDR_MASK GENMASK_ULL(51, 2) /* Event queue */ #define EVTQ_ENT_DWORDS 4 #define EVTQ_MAX_SZ_SHIFT 7 -#define EVTQ_0_ID_SHIFT 0 -#define EVTQ_0_ID_MASK 0xffUL +#define EVTQ_0_ID GENMASK_ULL(7, 0) /* PRI queue */ #define PRIQ_ENT_DWORDS 2 #define PRIQ_MAX_SZ_SHIFT 8 -#define PRIQ_0_SID_SHIFT 0 -#define PRIQ_0_SID_MASK 0xffffffffUL -#define PRIQ_0_SSID_SHIFT 32 -#define PRIQ_0_SSID_MASK 0xfffffUL +#define PRIQ_0_SID GENMASK_ULL(31, 0) +#define PRIQ_0_SSID GENMASK_ULL(51, 32) #define PRIQ_0_PERM_PRIV (1UL << 58) #define PRIQ_0_PERM_EXEC (1UL << 59) #define PRIQ_0_PERM_READ (1UL << 60) @@ -411,10 +355,8 @@ #define PRIQ_0_PRG_LAST (1UL << 62) #define PRIQ_0_SSID_V (1UL << 63) -#define PRIQ_1_PRG_IDX_SHIFT 0 -#define PRIQ_1_PRG_IDX_MASK 0x1ffUL -#define PRIQ_1_ADDR_SHIFT 12 -#define PRIQ_1_ADDR_MASK 0xfffffffffffffUL +#define PRIQ_1_PRG_IDX GENMASK_ULL(8, 0) +#define PRIQ_1_ADDR_MASK GENMASK_ULL(63, 12) /* High-level queue structures */ #define ARM_SMMU_POLL_TIMEOUT_US 100 @@ -430,9 +372,9 @@ MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); enum pri_resp { - PRI_RESP_DENY, - PRI_RESP_FAIL, - PRI_RESP_SUCC, + PRI_RESP_DENY = 0, + PRI_RESP_FAIL = 1, + PRI_RESP_SUCC = 2, }; enum arm_smmu_msi_index { @@ -611,6 +553,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_STALLS (1 << 11) #define ARM_SMMU_FEAT_HYP (1 << 12) #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) +#define ARM_SMMU_FEAT_VAX (1 << 14) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -836,67 +779,64 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent) static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) { memset(cmd, 0, CMDQ_ENT_DWORDS << 3); - cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_0_OP, ent->opcode); switch (ent->opcode) { case CMDQ_OP_TLBI_EL2_ALL: case CMDQ_OP_TLBI_NSNH_ALL: break; case CMDQ_OP_PREFETCH_CFG: - cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT; - cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_PREFETCH_0_SID, ent->prefetch.sid); + cmd[1] |= FIELD_PREP(CMDQ_PREFETCH_1_SIZE, ent->prefetch.size); cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK; break; case CMDQ_OP_CFGI_STE: - cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT; - cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid); + cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf); break; case CMDQ_OP_CFGI_ALL: /* Cover the entire SID range */ - cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT; + cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); break; case CMDQ_OP_TLBI_NH_VA: - cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; - cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; break; case CMDQ_OP_TLBI_S2_IPA: - cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; - cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: - cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); /* Fallthrough */ case CMDQ_OP_TLBI_S12_VMALL: - cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; case CMDQ_OP_PRI_RESP: - cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0; - cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT; - cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT; - cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); + cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid); + cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SID, ent->pri.sid); + cmd[1] |= FIELD_PREP(CMDQ_PRI_1_GRPID, ent->pri.grpid); switch (ent->pri.resp) { case PRI_RESP_DENY: - cmd[1] |= CMDQ_PRI_1_RESP_DENY; - break; case PRI_RESP_FAIL: - cmd[1] |= CMDQ_PRI_1_RESP_FAIL; - break; case PRI_RESP_SUCC: - cmd[1] |= CMDQ_PRI_1_RESP_SUCC; break; default: return -EINVAL; } + cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp); break; case CMDQ_OP_CMD_SYNC: if (ent->sync.msiaddr) - cmd[0] |= CMDQ_SYNC_0_CS_IRQ; + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ); else - cmd[0] |= CMDQ_SYNC_0_CS_SEV; - cmd[0] |= CMDQ_SYNC_0_MSH_ISH | CMDQ_SYNC_0_MSIATTR_OIWB; - cmd[0] |= (u64)ent->sync.msidata << CMDQ_SYNC_0_MSIDATA_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIDATA, ent->sync.msidata); cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK; break; default: @@ -918,7 +858,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) u64 cmd[CMDQ_ENT_DWORDS]; struct arm_smmu_queue *q = &smmu->cmdq.q; u32 cons = readl_relaxed(q->cons_reg); - u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK; + u32 idx = FIELD_GET(CMDQ_CONS_ERR, cons); struct arm_smmu_cmdq_ent cmd_sync = { .opcode = CMDQ_OP_CMD_SYNC, }; @@ -1083,8 +1023,8 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu, #ifdef __BIG_ENDIAN CTXDESC_CD_0_ENDI | #endif - CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE | - CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT | + CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET | + CTXDESC_CD_0_AA64 | FIELD_PREP(CTXDESC_CD_0_ASID, cfg->cd.asid) | CTXDESC_CD_0_V; /* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */ @@ -1093,10 +1033,10 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu, cfg->cdptr[0] = cpu_to_le64(val); - val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT; + val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK; cfg->cdptr[1] = cpu_to_le64(val); - cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT); + cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair); } /* Stream table manipulation functions */ @@ -1105,10 +1045,8 @@ arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc) { u64 val = 0; - val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK) - << STRTAB_L1_DESC_SPAN_SHIFT; - val |= desc->l2ptr_dma & - STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT; + val |= FIELD_PREP(STRTAB_L1_DESC_SPAN, desc->span); + val |= desc->l2ptr_dma & STRTAB_L1_DESC_L2PTR_MASK; *dst = cpu_to_le64(val); } @@ -1156,10 +1094,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, }; if (val & STRTAB_STE_0_V) { - u64 cfg; - - cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT; - switch (cfg) { + switch (FIELD_GET(STRTAB_STE_0_CFG, val)) { case STRTAB_STE_0_CFG_BYPASS: break; case STRTAB_STE_0_CFG_S1_TRANS: @@ -1180,13 +1115,13 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, /* Bypass/fault */ if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) { if (!ste->assigned && disable_bypass) - val |= STRTAB_STE_0_CFG_ABORT; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT); else - val |= STRTAB_STE_0_CFG_BYPASS; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); dst[0] = cpu_to_le64(val); - dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING - << STRTAB_STE_1_SHCFG_SHIFT); + dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, + STRTAB_STE_1_SHCFG_INCOMING)); dst[2] = 0; /* Nuke the VMID */ /* * The SMMU can perform negative caching, so we must sync @@ -1200,41 +1135,36 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, if (ste->s1_cfg) { BUG_ON(ste_live); dst[1] = cpu_to_le64( - STRTAB_STE_1_S1C_CACHE_WBRA - << STRTAB_STE_1_S1CIR_SHIFT | - STRTAB_STE_1_S1C_CACHE_WBRA - << STRTAB_STE_1_S1COR_SHIFT | - STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT | + FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | + FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | + FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) | #ifdef CONFIG_PCI_ATS - STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT | + FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS) | #endif - STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT); + FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1)); if (smmu->features & ARM_SMMU_FEAT_STALLS && !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); - val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK - << STRTAB_STE_0_S1CTXPTR_SHIFT) | - STRTAB_STE_0_CFG_S1_TRANS; + val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | + FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS); } if (ste->s2_cfg) { BUG_ON(ste_live); dst[2] = cpu_to_le64( - ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT | - (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK) - << STRTAB_STE_2_VTCR_SHIFT | + FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) | + FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) | #ifdef __BIG_ENDIAN STRTAB_STE_2_S2ENDI | #endif STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2R); - dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & - STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT); + dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); - val |= STRTAB_STE_0_CFG_S2_TRANS; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } arm_smmu_sync_ste_for_sid(smmu, sid); @@ -1295,7 +1225,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) do { while (!queue_remove_raw(q, evt)) { - u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK; + u8 id = FIELD_GET(EVTQ_0_ID, evt[0]); dev_info(smmu->dev, "event 0x%02x received:\n", id); for (i = 0; i < ARRAY_SIZE(evt); ++i) @@ -1323,11 +1253,11 @@ static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt) u16 grpid; bool ssv, last; - sid = evt[0] >> PRIQ_0_SID_SHIFT & PRIQ_0_SID_MASK; - ssv = evt[0] & PRIQ_0_SSID_V; - ssid = ssv ? evt[0] >> PRIQ_0_SSID_SHIFT & PRIQ_0_SSID_MASK : 0; - last = evt[0] & PRIQ_0_PRG_LAST; - grpid = evt[1] >> PRIQ_1_PRG_IDX_SHIFT & PRIQ_1_PRG_IDX_MASK; + sid = FIELD_GET(PRIQ_0_SID, evt[0]); + ssv = FIELD_GET(PRIQ_0_SSID_V, evt[0]); + ssid = ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : 0; + last = FIELD_GET(PRIQ_0_PRG_LAST, evt[0]); + grpid = FIELD_GET(PRIQ_1_PRG_IDX, evt[1]); dev_info(smmu->dev, "unexpected PRI request received:\n"); dev_info(smmu->dev, @@ -1337,7 +1267,7 @@ static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt) evt[0] & PRIQ_0_PERM_READ ? "R" : "", evt[0] & PRIQ_0_PERM_WRITE ? "W" : "", evt[0] & PRIQ_0_PERM_EXEC ? "X" : "", - evt[1] & PRIQ_1_ADDR_MASK << PRIQ_1_ADDR_SHIFT); + evt[1] & PRIQ_1_ADDR_MASK); if (last) { struct arm_smmu_cmdq_ent cmd = { @@ -1664,7 +1594,8 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) switch (smmu_domain->stage) { case ARM_SMMU_DOMAIN_S1: - ias = VA_BITS; + ias = (smmu->features & ARM_SMMU_FEAT_VAX) ? 52 : 48; + ias = min_t(unsigned long, ias, VA_BITS); oas = smmu->ias; fmt = ARM_64_LPAE_S1; finalise_stage_fn = arm_smmu_domain_finalise_s1; @@ -1696,7 +1627,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) return -ENOMEM; domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; - domain->geometry.aperture_end = (1UL << ias) - 1; + domain->geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1; domain->geometry.force_aperture = true; ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg); @@ -2102,9 +2033,8 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu, q->ent_dwords = dwords; q->q_base = Q_BASE_RWA; - q->q_base |= q->base_dma & Q_BASE_ADDR_MASK << Q_BASE_ADDR_SHIFT; - q->q_base |= (q->max_n_shift & Q_BASE_LOG2SIZE_MASK) - << Q_BASE_LOG2SIZE_SHIFT; + q->q_base |= q->base_dma & Q_BASE_ADDR_MASK; + q->q_base |= FIELD_PREP(Q_BASE_LOG2SIZE, q->max_n_shift); q->prod = q->cons = 0; return 0; @@ -2186,11 +2116,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) cfg->strtab = strtab; /* Configure strtab_base_cfg for 2 levels */ - reg = STRTAB_BASE_CFG_FMT_2LVL; - reg |= (size & STRTAB_BASE_CFG_LOG2SIZE_MASK) - << STRTAB_BASE_CFG_LOG2SIZE_SHIFT; - reg |= (STRTAB_SPLIT & STRTAB_BASE_CFG_SPLIT_MASK) - << STRTAB_BASE_CFG_SPLIT_SHIFT; + reg = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_2LVL); + reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, size); + reg |= FIELD_PREP(STRTAB_BASE_CFG_SPLIT, STRTAB_SPLIT); cfg->strtab_base_cfg = reg; return arm_smmu_init_l1_strtab(smmu); @@ -2216,9 +2144,8 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu) cfg->num_l1_ents = 1 << smmu->sid_bits; /* Configure strtab_base_cfg for a linear table covering all SIDs */ - reg = STRTAB_BASE_CFG_FMT_LINEAR; - reg |= (smmu->sid_bits & STRTAB_BASE_CFG_LOG2SIZE_MASK) - << STRTAB_BASE_CFG_LOG2SIZE_SHIFT; + reg = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_LINEAR); + reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits); cfg->strtab_base_cfg = reg; arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents); @@ -2239,8 +2166,7 @@ static int arm_smmu_init_strtab(struct arm_smmu_device *smmu) return ret; /* Set the strtab base address */ - reg = smmu->strtab_cfg.strtab_dma & - STRTAB_BASE_ADDR_MASK << STRTAB_BASE_ADDR_SHIFT; + reg = smmu->strtab_cfg.strtab_dma & STRTAB_BASE_ADDR_MASK; reg |= STRTAB_BASE_RA; smmu->strtab_cfg.strtab_base = reg; @@ -2303,11 +2229,11 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index]; doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; - doorbell &= MSI_CFG0_ADDR_MASK << MSI_CFG0_ADDR_SHIFT; + doorbell &= MSI_CFG0_ADDR_MASK; writeq_relaxed(doorbell, smmu->base + cfg[0]); writel_relaxed(msg->data, smmu->base + cfg[1]); - writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); + writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); } static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) @@ -2328,10 +2254,15 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) if (!(smmu->features & ARM_SMMU_FEAT_MSI)) return; + if (!dev->msi_domain) { + dev_info(smmu->dev, "msi_domain absent - falling back to wired irqs\n"); + return; + } + /* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */ ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg); if (ret) { - dev_warn(dev, "failed to allocate MSIs\n"); + dev_warn(dev, "failed to allocate MSIs - falling back to wired irqs\n"); return; } @@ -2370,6 +2301,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) "arm-smmu-v3-evtq", smmu); if (ret < 0) dev_warn(smmu->dev, "failed to enable evtq irq\n"); + } else { + dev_warn(smmu->dev, "no evtq irq - events will not be reported!\n"); } irq = smmu->gerr_irq; @@ -2378,6 +2311,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) 0, "arm-smmu-v3-gerror", smmu); if (ret < 0) dev_warn(smmu->dev, "failed to enable gerror irq\n"); + } else { + dev_warn(smmu->dev, "no gerr irq - errors will not be reported!\n"); } if (smmu->features & ARM_SMMU_FEAT_PRI) { @@ -2391,6 +2326,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) if (ret < 0) dev_warn(smmu->dev, "failed to enable priq irq\n"); + } else { + dev_warn(smmu->dev, "no priq irq - PRI will be broken\n"); } } } @@ -2463,12 +2400,12 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return ret; /* CR1 (table and queue memory attributes) */ - reg = (CR1_SH_ISH << CR1_TABLE_SH_SHIFT) | - (CR1_CACHE_WB << CR1_TABLE_OC_SHIFT) | - (CR1_CACHE_WB << CR1_TABLE_IC_SHIFT) | - (CR1_SH_ISH << CR1_QUEUE_SH_SHIFT) | - (CR1_CACHE_WB << CR1_QUEUE_OC_SHIFT) | - (CR1_CACHE_WB << CR1_QUEUE_IC_SHIFT); + reg = FIELD_PREP(CR1_TABLE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_TABLE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_TABLE_IC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_QUEUE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_IC, CR1_CACHE_WB); writel_relaxed(reg, smmu->base + ARM_SMMU_CR1); /* CR2 (random crap) */ @@ -2578,7 +2515,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0); /* 2-level structures */ - if ((reg & IDR0_ST_LVL_MASK << IDR0_ST_LVL_SHIFT) == IDR0_ST_LVL_2LVL) + if (FIELD_GET(IDR0_ST_LVL, reg) == IDR0_ST_LVL_2LVL) smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB; if (reg & IDR0_CD2L) @@ -2589,7 +2526,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) * We currently require the same endianness as the CPU, but this * could be changed later by adding a new IO_PGTABLE_QUIRK. */ - switch (reg & IDR0_TTENDIAN_MASK << IDR0_TTENDIAN_SHIFT) { + switch (FIELD_GET(IDR0_TTENDIAN, reg)) { case IDR0_TTENDIAN_MIXED: smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE; break; @@ -2631,7 +2568,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n", coherent ? "true" : "false"); - switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) { + switch (FIELD_GET(IDR0_STALL_MODEL, reg)) { case IDR0_STALL_MODEL_FORCE: smmu->features |= ARM_SMMU_FEAT_STALL_FORCE; /* Fallthrough */ @@ -2651,7 +2588,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) } /* We only support the AArch64 table format at present */ - switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) { + switch (FIELD_GET(IDR0_TTF, reg)) { case IDR0_TTF_AARCH32_64: smmu->ias = 40; /* Fallthrough */ @@ -2674,22 +2611,22 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) } /* Queue sizes, capped at 4k */ - smmu->cmdq.q.max_n_shift = min((u32)CMDQ_MAX_SZ_SHIFT, - reg >> IDR1_CMDQ_SHIFT & IDR1_CMDQ_MASK); + smmu->cmdq.q.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_CMDQS, reg)); if (!smmu->cmdq.q.max_n_shift) { /* Odd alignment restrictions on the base, so ignore for now */ dev_err(smmu->dev, "unit-length command queue not supported\n"); return -ENXIO; } - smmu->evtq.q.max_n_shift = min((u32)EVTQ_MAX_SZ_SHIFT, - reg >> IDR1_EVTQ_SHIFT & IDR1_EVTQ_MASK); - smmu->priq.q.max_n_shift = min((u32)PRIQ_MAX_SZ_SHIFT, - reg >> IDR1_PRIQ_SHIFT & IDR1_PRIQ_MASK); + smmu->evtq.q.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_EVTQS, reg)); + smmu->priq.q.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_PRIQS, reg)); /* SID/SSID sizes */ - smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK; - smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK; + smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg); + smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg); /* * If the SMMU supports fewer bits than would fill a single L2 stream @@ -2702,8 +2639,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); /* Maximum number of outstanding stalls */ - smmu->evtq.max_stalls = reg >> IDR5_STALL_MAX_SHIFT - & IDR5_STALL_MAX_MASK; + smmu->evtq.max_stalls = FIELD_GET(IDR5_STALL_MAX, reg); /* Page sizes */ if (reg & IDR5_GRAN64K) @@ -2713,13 +2649,12 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (reg & IDR5_GRAN4K) smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G; - if (arm_smmu_ops.pgsize_bitmap == -1UL) - arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap; - else - arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap; + /* Input address size */ + if (FIELD_GET(IDR5_VAX, reg) == IDR5_VAX_52_BIT) + smmu->features |= ARM_SMMU_FEAT_VAX; /* Output address size */ - switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) { + switch (FIELD_GET(IDR5_OAS, reg)) { case IDR5_OAS_32_BIT: smmu->oas = 32; break; @@ -2735,6 +2670,10 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) case IDR5_OAS_44_BIT: smmu->oas = 44; break; + case IDR5_OAS_52_BIT: + smmu->oas = 52; + smmu->pgsize_bitmap |= 1ULL << 42; /* 4TB */ + break; default: dev_info(smmu->dev, "unknown output address size. Truncating to 48-bit\n"); @@ -2743,6 +2682,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->oas = 48; } + if (arm_smmu_ops.pgsize_bitmap == -1UL) + arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap; + else + arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap; + /* Set the DMA mask for our table walker */ if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas))) dev_warn(smmu->dev, diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 25914d36c5ac..f05f3cf90756 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -19,6 +19,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/acpi_iort.h> #include <linux/device.h> #include <linux/dma-iommu.h> #include <linux/gfp.h> @@ -167,13 +168,18 @@ EXPORT_SYMBOL(iommu_put_dma_cookie); * * IOMMU drivers can use this to implement their .get_resv_regions callback * for general non-IOMMU-specific reservations. Currently, this covers host - * bridge windows for PCI devices. + * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI + * based ARM platforms that may require HW MSI reservation. */ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) { struct pci_host_bridge *bridge; struct resource_entry *window; + if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) && + iort_iommu_msi_get_resv_regions(dev, list) < 0) + return; + if (!dev_is_pci(dev)) return; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 9a7ffd13c7f0..accf58388bdb 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -806,7 +806,7 @@ int __init dmar_dev_scope_init(void) return dmar_dev_scope_status; } -void dmar_register_bus_notifier(void) +void __init dmar_register_bus_notifier(void) { bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb); } diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 2138102ef611..210715f08cf6 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1238,17 +1238,6 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain, return phys; } -static struct iommu_group *get_device_iommu_group(struct device *dev) -{ - struct iommu_group *group; - - group = iommu_group_get(dev); - if (!group) - group = iommu_group_alloc(); - - return group; -} - static int exynos_iommu_add_device(struct device *dev) { struct exynos_iommu_owner *owner = dev->archdata.iommu; @@ -1344,7 +1333,7 @@ static const struct iommu_ops exynos_iommu_ops = { .unmap = exynos_iommu_unmap, .map_sg = default_iommu_map_sg, .iova_to_phys = exynos_iommu_iova_to_phys, - .device_group = get_device_iommu_group, + .device_group = generic_device_group, .add_device = exynos_iommu_add_device, .remove_device = exynos_iommu_remove_device, .pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 582fd01cb7d1..d49e0d3ab748 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5072,7 +5072,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, { struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct page *freelist = NULL; - struct intel_iommu *iommu; unsigned long start_pfn, last_pfn; unsigned int npages; int iommu_id, level = 0; @@ -5091,12 +5090,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, npages = last_pfn - start_pfn + 1; - for_each_domain_iommu(iommu_id, dmar_domain) { - iommu = g_iommus[iommu_id]; - + for_each_domain_iommu(iommu_id, dmar_domain) iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain, start_pfn, npages, !freelist, 0); - } dma_free_pagelist(freelist); diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 35a408d0ae4f..e8cd984cf9c8 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -205,7 +205,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d * for example, an "address" value of 0x12345f000 will * flush from 0x123440000 to 0x12347ffff (256KiB). */ unsigned long last = address + ((unsigned long)(pages - 1) << VTD_PAGE_SHIFT); - unsigned long mask = __rounddown_pow_of_two(address ^ last);; + unsigned long mask = __rounddown_pow_of_two(address ^ last); desc.high = QI_DEV_EIOTLB_ADDR((address & ~mask) | (mask - 1)) | QI_DEV_EIOTLB_SIZE; } else { @@ -396,6 +396,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ pasid_max - 1, GFP_KERNEL); if (ret < 0) { kfree(svm); + kfree(sdev); goto out; } svm->pasid = ret; @@ -422,17 +423,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ iommu->pasid_table[svm->pasid].val = pasid_entry_val; wmb(); - /* In caching mode, we still have to flush with PASID 0 when - * a PASID table entry becomes present. Not entirely clear - * *why* that would be the case — surely we could just issue - * a flush with the PASID value that we've changed? The PASID - * is the index into the table, after all. It's not like domain - * IDs in the case of the equivalent context-entry change in - * caching mode. And for that matter it's not entirely clear why - * a VMM would be in the business of caching the PASID table - * anyway. Surely that can be left entirely to the guest? */ + + /* + * Flush PASID cache when a PASID table entry becomes + * present. + */ if (cap_caching_mode(iommu->cap)) - intel_flush_pasid_dev(svm, sdev, 0); + intel_flush_pasid_dev(svm, sdev, svm->pasid); } list_add_rcu(&sdev->list, &svm->devs); diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 2ca08dc9331c..10e4a3d11c02 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -357,8 +357,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl) return false; } -static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long, - size_t, int, arm_v7s_iopte *); +static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long, + size_t, int, arm_v7s_iopte *); static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data, unsigned long iova, phys_addr_t paddr, int prot, @@ -541,9 +541,10 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data, return pte; } -static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, - unsigned long iova, size_t size, - arm_v7s_iopte blk_pte, arm_v7s_iopte *ptep) +static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, + unsigned long iova, size_t size, + arm_v7s_iopte blk_pte, + arm_v7s_iopte *ptep) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_v7s_iopte pte, *tablep; @@ -584,9 +585,9 @@ static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, return size; } -static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_v7s_iopte *ptep) +static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_v7s_iopte *ptep) { arm_v7s_iopte pte[ARM_V7S_CONT_PAGES]; struct io_pgtable *iop = &data->iop; @@ -656,8 +657,8 @@ static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep); } -static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) +static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 51e5c43caed1..39c2a056da21 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -21,6 +21,7 @@ #define pr_fmt(fmt) "arm-lpae io-pgtable: " fmt #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/iommu.h> #include <linux/kernel.h> #include <linux/sizes.h> @@ -32,7 +33,7 @@ #include "io-pgtable.h" -#define ARM_LPAE_MAX_ADDR_BITS 48 +#define ARM_LPAE_MAX_ADDR_BITS 52 #define ARM_LPAE_S2_MAX_CONCAT_PAGES 16 #define ARM_LPAE_MAX_LEVELS 4 @@ -86,6 +87,8 @@ #define ARM_LPAE_PTE_TYPE_TABLE 3 #define ARM_LPAE_PTE_TYPE_PAGE 3 +#define ARM_LPAE_PTE_ADDR_MASK GENMASK_ULL(47,12) + #define ARM_LPAE_PTE_NSTABLE (((arm_lpae_iopte)1) << 63) #define ARM_LPAE_PTE_XN (((arm_lpae_iopte)3) << 53) #define ARM_LPAE_PTE_AF (((arm_lpae_iopte)1) << 10) @@ -159,6 +162,7 @@ #define ARM_LPAE_TCR_PS_42_BIT 0x3ULL #define ARM_LPAE_TCR_PS_44_BIT 0x4ULL #define ARM_LPAE_TCR_PS_48_BIT 0x5ULL +#define ARM_LPAE_TCR_PS_52_BIT 0x6ULL #define ARM_LPAE_MAIR_ATTR_SHIFT(n) ((n) << 3) #define ARM_LPAE_MAIR_ATTR_MASK 0xff @@ -170,9 +174,7 @@ #define ARM_LPAE_MAIR_ATTR_IDX_DEV 2 /* IOPTE accessors */ -#define iopte_deref(pte,d) \ - (__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1) \ - & ~(ARM_LPAE_GRANULE(d) - 1ULL))) +#define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d)) #define iopte_type(pte,l) \ (((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK) @@ -184,12 +186,6 @@ (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) : \ (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK)) -#define iopte_to_pfn(pte,d) \ - (((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift) - -#define pfn_to_iopte(pfn,d) \ - (((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) - struct arm_lpae_io_pgtable { struct io_pgtable iop; @@ -203,6 +199,27 @@ struct arm_lpae_io_pgtable { typedef u64 arm_lpae_iopte; +static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr, + struct arm_lpae_io_pgtable *data) +{ + arm_lpae_iopte pte = paddr; + + /* Of the bits which overlap, either 51:48 or 15:12 are always RES0 */ + return (pte | (pte >> (48 - 12))) & ARM_LPAE_PTE_ADDR_MASK; +} + +static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte, + struct arm_lpae_io_pgtable *data) +{ + u64 paddr = pte & ARM_LPAE_PTE_ADDR_MASK; + + if (data->pg_shift < 16) + return paddr; + + /* Rotate the packed high-order bits back to the top */ + return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4); +} + static bool selftest_running = false; static dma_addr_t __arm_lpae_dma_addr(void *pages) @@ -268,9 +285,9 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, __arm_lpae_sync_pte(ptep, cfg); } -static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep); +static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep); static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, phys_addr_t paddr, arm_lpae_iopte prot, @@ -287,7 +304,7 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, pte |= ARM_LPAE_PTE_TYPE_BLOCK; pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS; - pte |= pfn_to_iopte(paddr >> data->pg_shift, data); + pte |= paddr_to_iopte(paddr, data); __arm_lpae_set_pte(ptep, pte, &data->iop.cfg); } @@ -506,10 +523,10 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop) kfree(data); } -static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, - arm_lpae_iopte blk_pte, int lvl, - arm_lpae_iopte *ptep) +static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, + arm_lpae_iopte blk_pte, int lvl, + arm_lpae_iopte *ptep) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte pte, *tablep; @@ -528,7 +545,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, if (size == split_sz) unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data); - blk_paddr = iopte_to_pfn(blk_pte, data) << data->pg_shift; + blk_paddr = iopte_to_paddr(blk_pte, data); pte = iopte_prot(blk_pte); for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) { @@ -560,9 +577,9 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, return size; } -static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep) +static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep) { arm_lpae_iopte pte; struct io_pgtable *iop = &data->iop; @@ -606,8 +623,8 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep); } -static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) +static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); arm_lpae_iopte *ptep = data->pgd; @@ -652,12 +669,13 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, found_translation: iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1); - return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova; + return iopte_to_paddr(pte, data) | iova; } static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) { - unsigned long granule; + unsigned long granule, page_sizes; + unsigned int max_addr_bits = 48; /* * We need to restrict the supported page sizes to match the @@ -677,17 +695,24 @@ static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) switch (granule) { case SZ_4K: - cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); + page_sizes = (SZ_4K | SZ_2M | SZ_1G); break; case SZ_16K: - cfg->pgsize_bitmap &= (SZ_16K | SZ_32M); + page_sizes = (SZ_16K | SZ_32M); break; case SZ_64K: - cfg->pgsize_bitmap &= (SZ_64K | SZ_512M); + max_addr_bits = 52; + page_sizes = (SZ_64K | SZ_512M); + if (cfg->oas > 48) + page_sizes |= 1ULL << 42; /* 4TB */ break; default: - cfg->pgsize_bitmap = 0; + page_sizes = 0; } + + cfg->pgsize_bitmap &= page_sizes; + cfg->ias = min(cfg->ias, max_addr_bits); + cfg->oas = min(cfg->oas, max_addr_bits); } static struct arm_lpae_io_pgtable * @@ -784,6 +809,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) case 48: reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT); break; + case 52: + reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; default: goto out_free_data; } @@ -891,6 +919,9 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) case 48: reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT); break; + case 52: + reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; default: goto out_free_data; } diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h index cd2e1eafffe6..2df79093cad9 100644 --- a/drivers/iommu/io-pgtable.h +++ b/drivers/iommu/io-pgtable.h @@ -119,8 +119,8 @@ struct io_pgtable_cfg { struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot); - int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, - size_t size); + size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, + size_t size); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 69fef991c651..d2aa23202bb9 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1573,10 +1573,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain, if (unlikely(ops->unmap == NULL || domain->pgsize_bitmap == 0UL)) - return -ENODEV; + return 0; if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) - return -EINVAL; + return 0; /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->pgsize_bitmap); @@ -1589,7 +1589,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain, if (!IS_ALIGNED(iova | size, min_pagesz)) { pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n", iova, size, min_pagesz); - return -EINVAL; + return 0; } pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f227d73e7bf6..f2832a10fcea 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -60,7 +60,7 @@ (((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data)) #define REG_MMU_IVRP_PADDR 0x114 -#define F_MMU_IVRP_PA_SET(pa, ext) (((pa) >> 1) | ((!!(ext)) << 31)) + #define REG_MMU_VLD_PA_RNG 0x118 #define F_MMU_VLD_PA_RNG(EA, SA) (((EA) << 8) | (SA)) @@ -539,8 +539,13 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) F_INT_PRETETCH_TRANSATION_FIFO_FAULT; writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL); - writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB), - data->base + REG_MMU_IVRP_PADDR); + if (data->m4u_plat == M4U_MT8173) + regval = (data->protect_base >> 1) | (data->enable_4GB << 31); + else + regval = lower_32_bits(data->protect_base) | + upper_32_bits(data->protect_base); + writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR); + if (data->enable_4GB && data->m4u_plat != M4U_MT8173) { /* * If 4GB mode is enabled, the validate PA range is from @@ -695,6 +700,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev) reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG); reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0); reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL); + reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR); clk_disable_unprepare(data->bclk); return 0; } @@ -717,8 +723,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev) writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG); writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0); writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL); - writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB), - base + REG_MMU_IVRP_PADDR); + writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR); if (data->m4u_dom) writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0], base + REG_MMU_PT_BASE_ADDR); diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index b4451a1c7c2f..778498b8633f 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -32,6 +32,7 @@ struct mtk_iommu_suspend_reg { u32 ctrl_reg; u32 int_control0; u32 int_main_control; + u32 ivrp_paddr; }; enum mtk_iommu_plat { diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 542930cd183d..1b1b77594897 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -418,20 +418,12 @@ static int mtk_iommu_create_mapping(struct device *dev, m4udev->archdata.iommu = mtk_mapping; } - ret = arm_iommu_attach_device(dev, mtk_mapping); - if (ret) - goto err_release_mapping; - return 0; - -err_release_mapping: - arm_iommu_release_mapping(mtk_mapping); - m4udev->archdata.iommu = NULL; - return ret; } static int mtk_iommu_add_device(struct device *dev) { + struct dma_iommu_mapping *mtk_mapping; struct of_phandle_args iommu_spec; struct of_phandle_iterator it; struct mtk_iommu_data *data; @@ -452,15 +444,30 @@ static int mtk_iommu_add_device(struct device *dev) if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) return -ENODEV; /* Not a iommu client device */ - data = dev->iommu_fwspec->iommu_priv; - iommu_device_link(&data->iommu, dev); - - group = iommu_group_get_for_dev(dev); + /* + * This is a short-term bodge because the ARM DMA code doesn't + * understand multi-device groups, but we have to call into it + * successfully (and not just rely on a normal IOMMU API attach + * here) in order to set the correct DMA API ops on @dev. + */ + group = iommu_group_alloc(); if (IS_ERR(group)) return PTR_ERR(group); + err = iommu_group_add_device(group, dev); iommu_group_put(group); - return 0; + if (err) + return err; + + data = dev->iommu_fwspec->iommu_priv; + mtk_mapping = data->dev->archdata.iommu; + err = arm_iommu_attach_device(dev, mtk_mapping); + if (err) { + iommu_group_remove_device(dev); + return err; + } + + return iommu_device_link(&data->iommu, dev);; } static void mtk_iommu_remove_device(struct device *dev) @@ -477,24 +484,6 @@ static void mtk_iommu_remove_device(struct device *dev) iommu_fwspec_free(dev); } -static struct iommu_group *mtk_iommu_device_group(struct device *dev) -{ - struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - - if (!data) - return ERR_PTR(-ENODEV); - - /* All the client devices are in the same m4u iommu-group */ - if (!data->m4u_group) { - data->m4u_group = iommu_group_alloc(); - if (IS_ERR(data->m4u_group)) - dev_err(dev, "Failed to allocate M4U IOMMU group\n"); - } else { - iommu_group_ref_get(data->m4u_group); - } - return data->m4u_group; -} - static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) { u32 regval; @@ -547,7 +536,6 @@ static struct iommu_ops mtk_iommu_ops = { .iova_to_phys = mtk_iommu_iova_to_phys, .add_device = mtk_iommu_add_device, .remove_device = mtk_iommu_remove_device, - .device_group = mtk_iommu_device_group, .pgsize_bitmap = ~0UL << MT2701_IOMMU_PAGE_SHIFT, }; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index e135ab830ebf..c33b7b104e72 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1536,7 +1536,7 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev) struct iommu_group *group = ERR_PTR(-EINVAL); if (arch_data->iommu_dev) - group = arch_data->iommu_dev->group; + group = iommu_group_ref_get(arch_data->iommu_dev->group); return group; } diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 9d991c2d8767..5fc8656c60f9 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -4,6 +4,7 @@ * published by the Free Software Foundation. */ +#include <linux/clk.h> #include <linux/compiler.h> #include <linux/delay.h> #include <linux/device.h> @@ -13,13 +14,15 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iommu.h> -#include <linux/jiffies.h> +#include <linux/iopoll.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_iommu.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -36,7 +39,10 @@ #define RK_MMU_AUTO_GATING 0x24 #define DTE_ADDR_DUMMY 0xCAFEBABE -#define FORCE_RESET_TIMEOUT 100 /* ms */ + +#define RK_MMU_POLL_PERIOD_US 100 +#define RK_MMU_FORCE_RESET_TIMEOUT_US 100000 +#define RK_MMU_POLL_TIMEOUT_US 1000 /* RK_MMU_STATUS fields */ #define RK_MMU_STATUS_PAGING_ENABLED BIT(0) @@ -73,11 +79,8 @@ */ #define RK_IOMMU_PGSIZE_BITMAP 0x007ff000 -#define IOMMU_REG_POLL_COUNT_FAST 1000 - struct rk_iommu_domain { struct list_head iommus; - struct platform_device *pdev; u32 *dt; /* page directory table */ dma_addr_t dt_dma; spinlock_t iommus_lock; /* lock for iommus list */ @@ -86,24 +89,37 @@ struct rk_iommu_domain { struct iommu_domain domain; }; +/* list of clocks required by IOMMU */ +static const char * const rk_iommu_clocks[] = { + "aclk", "iface", +}; + struct rk_iommu { struct device *dev; void __iomem **bases; int num_mmu; - int *irq; - int num_irq; + struct clk_bulk_data *clocks; + int num_clocks; bool reset_disabled; struct iommu_device iommu; struct list_head node; /* entry in rk_iommu_domain.iommus */ struct iommu_domain *domain; /* domain to which iommu is attached */ + struct iommu_group *group; +}; + +struct rk_iommudata { + struct device_link *link; /* runtime PM link from IOMMU to master */ + struct rk_iommu *iommu; }; +static struct device *dma_dev; + static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma, unsigned int count) { size_t size = count * sizeof(u32); /* count of u32 entry */ - dma_sync_single_for_device(&dom->pdev->dev, dma, size, DMA_TO_DEVICE); + dma_sync_single_for_device(dma_dev, dma, size, DMA_TO_DEVICE); } static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom) @@ -111,27 +127,6 @@ static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom) return container_of(dom, struct rk_iommu_domain, domain); } -/** - * Inspired by _wait_for in intel_drv.h - * This is NOT safe for use in interrupt context. - * - * Note that it's important that we check the condition again after having - * timed out, since the timeout could be due to preemption or similar and - * we've never had a chance to check the condition before the timeout. - */ -#define rk_wait_for(COND, MS) ({ \ - unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1; \ - int ret__ = 0; \ - while (!(COND)) { \ - if (time_after(jiffies, timeout__)) { \ - ret__ = (COND) ? 0 : -ETIMEDOUT; \ - break; \ - } \ - usleep_range(50, 100); \ - } \ - ret__; \ -}) - /* * The Rockchip rk3288 iommu uses a 2-level page table. * The first level is the "Directory Table" (DT). @@ -296,19 +291,21 @@ static void rk_iommu_base_command(void __iomem *base, u32 command) { writel(command, base + RK_MMU_COMMAND); } -static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova, +static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova_start, size_t size) { int i; - - dma_addr_t iova_end = iova + size; + dma_addr_t iova_end = iova_start + size; /* * TODO(djkurtz): Figure out when it is more efficient to shootdown the * entire iotlb rather than iterate over individual iovas. */ - for (i = 0; i < iommu->num_mmu; i++) - for (; iova < iova_end; iova += SPAGE_SIZE) + for (i = 0; i < iommu->num_mmu; i++) { + dma_addr_t iova; + + for (iova = iova_start; iova < iova_end; iova += SPAGE_SIZE) rk_iommu_write(iommu->bases[i], RK_MMU_ZAP_ONE_LINE, iova); + } } static bool rk_iommu_is_stall_active(struct rk_iommu *iommu) @@ -335,9 +332,21 @@ static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu) return enable; } +static bool rk_iommu_is_reset_done(struct rk_iommu *iommu) +{ + bool done = true; + int i; + + for (i = 0; i < iommu->num_mmu; i++) + done &= rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0; + + return done; +} + static int rk_iommu_enable_stall(struct rk_iommu *iommu) { int ret, i; + bool val; if (rk_iommu_is_stall_active(iommu)) return 0; @@ -348,7 +357,9 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu) rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL); - ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val, + val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n", @@ -360,13 +371,16 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu) static int rk_iommu_disable_stall(struct rk_iommu *iommu) { int ret, i; + bool val; if (!rk_iommu_is_stall_active(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL); - ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val, + !val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n", @@ -378,13 +392,16 @@ static int rk_iommu_disable_stall(struct rk_iommu *iommu) static int rk_iommu_enable_paging(struct rk_iommu *iommu) { int ret, i; + bool val; if (rk_iommu_is_paging_enabled(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING); - ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val, + val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n", @@ -396,13 +413,16 @@ static int rk_iommu_enable_paging(struct rk_iommu *iommu) static int rk_iommu_disable_paging(struct rk_iommu *iommu) { int ret, i; + bool val; if (!rk_iommu_is_paging_enabled(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING); - ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val, + !val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n", @@ -415,6 +435,7 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) { int ret, i; u32 dte_addr; + bool val; if (iommu->reset_disabled) return 0; @@ -435,13 +456,12 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET); - for (i = 0; i < iommu->num_mmu; i++) { - ret = rk_wait_for(rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0x00000000, - FORCE_RESET_TIMEOUT); - if (ret) { - dev_err(iommu->dev, "FORCE_RESET command timed out\n"); - return ret; - } + ret = readx_poll_timeout(rk_iommu_is_reset_done, iommu, val, + val, RK_MMU_FORCE_RESET_TIMEOUT_US, + RK_MMU_POLL_TIMEOUT_US); + if (ret) { + dev_err(iommu->dev, "FORCE_RESET command timed out\n"); + return ret; } return 0; @@ -503,6 +523,12 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) irqreturn_t ret = IRQ_NONE; int i; + if (WARN_ON(!pm_runtime_get_if_in_use(iommu->dev))) + return 0; + + if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks))) + goto out; + for (i = 0; i < iommu->num_mmu; i++) { int_status = rk_iommu_read(iommu->bases[i], RK_MMU_INT_STATUS); if (int_status == 0) @@ -549,6 +575,10 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) rk_iommu_write(iommu->bases[i], RK_MMU_INT_CLEAR, int_status); } + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + +out: + pm_runtime_put(iommu->dev); return ret; } @@ -590,8 +620,17 @@ static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain, spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_for_each(pos, &rk_domain->iommus) { struct rk_iommu *iommu; + iommu = list_entry(pos, struct rk_iommu, node); - rk_iommu_zap_lines(iommu, iova, size); + + /* Only zap TLBs of IOMMUs that are powered on. */ + if (pm_runtime_get_if_in_use(iommu->dev)) { + WARN_ON(clk_bulk_enable(iommu->num_clocks, + iommu->clocks)); + rk_iommu_zap_lines(iommu, iova, size); + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + pm_runtime_put(iommu->dev); + } } spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); } @@ -608,7 +647,6 @@ static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain, static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, dma_addr_t iova) { - struct device *dev = &rk_domain->pdev->dev; u32 *page_table, *dte_addr; u32 dte_index, dte; phys_addr_t pt_phys; @@ -626,9 +664,9 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, if (!page_table) return ERR_PTR(-ENOMEM); - pt_dma = dma_map_single(dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE); - if (dma_mapping_error(dev, pt_dma)) { - dev_err(dev, "DMA mapping error while allocating page table\n"); + pt_dma = dma_map_single(dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dma_dev, pt_dma)) { + dev_err(dma_dev, "DMA mapping error while allocating page table\n"); free_page((unsigned long)page_table); return ERR_PTR(-ENOMEM); } @@ -790,52 +828,46 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, static struct rk_iommu *rk_iommu_from_dev(struct device *dev) { - struct iommu_group *group; - struct device *iommu_dev; - struct rk_iommu *rk_iommu; + struct rk_iommudata *data = dev->archdata.iommu; - group = iommu_group_get(dev); - if (!group) - return NULL; - iommu_dev = iommu_group_get_iommudata(group); - rk_iommu = dev_get_drvdata(iommu_dev); - iommu_group_put(group); + return data ? data->iommu : NULL; +} + +/* Must be called with iommu powered on and attached */ +static void rk_iommu_disable(struct rk_iommu *iommu) +{ + int i; - return rk_iommu; + /* Ignore error while disabling, just keep going */ + WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)); + rk_iommu_enable_stall(iommu); + rk_iommu_disable_paging(iommu); + for (i = 0; i < iommu->num_mmu; i++) { + rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0); + rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0); + } + rk_iommu_disable_stall(iommu); + clk_bulk_disable(iommu->num_clocks, iommu->clocks); } -static int rk_iommu_attach_device(struct iommu_domain *domain, - struct device *dev) +/* Must be called with iommu powered on and attached */ +static int rk_iommu_enable(struct rk_iommu *iommu) { - struct rk_iommu *iommu; + struct iommu_domain *domain = iommu->domain; struct rk_iommu_domain *rk_domain = to_rk_domain(domain); - unsigned long flags; int ret, i; - /* - * Allow 'virtual devices' (e.g., drm) to attach to domain. - * Such a device does not belong to an iommu group. - */ - iommu = rk_iommu_from_dev(dev); - if (!iommu) - return 0; + ret = clk_bulk_enable(iommu->num_clocks, iommu->clocks); + if (ret) + return ret; ret = rk_iommu_enable_stall(iommu); if (ret) - return ret; + goto out_disable_clocks; ret = rk_iommu_force_reset(iommu); if (ret) - return ret; - - iommu->domain = domain; - - for (i = 0; i < iommu->num_irq; i++) { - ret = devm_request_irq(iommu->dev, iommu->irq[i], rk_iommu_irq, - IRQF_SHARED, dev_name(dev), iommu); - if (ret) - return ret; - } + goto out_disable_stall; for (i = 0; i < iommu->num_mmu; i++) { rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, @@ -845,18 +877,12 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, } ret = rk_iommu_enable_paging(iommu); - if (ret) - return ret; - - spin_lock_irqsave(&rk_domain->iommus_lock, flags); - list_add_tail(&iommu->node, &rk_domain->iommus); - spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); - - dev_dbg(dev, "Attached to iommu domain\n"); +out_disable_stall: rk_iommu_disable_stall(iommu); - - return 0; +out_disable_clocks: + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + return ret; } static void rk_iommu_detach_device(struct iommu_domain *domain, @@ -865,60 +891,90 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, struct rk_iommu *iommu; struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; - int i; /* Allow 'virtual devices' (eg drm) to detach from domain */ iommu = rk_iommu_from_dev(dev); if (!iommu) return; + dev_dbg(dev, "Detaching from iommu domain\n"); + + /* iommu already detached */ + if (iommu->domain != domain) + return; + + iommu->domain = NULL; + spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_del_init(&iommu->node); spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); - /* Ignore error while disabling, just keep going */ - rk_iommu_enable_stall(iommu); - rk_iommu_disable_paging(iommu); - for (i = 0; i < iommu->num_mmu; i++) { - rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0); - rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0); + if (pm_runtime_get_if_in_use(iommu->dev)) { + rk_iommu_disable(iommu); + pm_runtime_put(iommu->dev); } - rk_iommu_disable_stall(iommu); +} - for (i = 0; i < iommu->num_irq; i++) - devm_free_irq(iommu->dev, iommu->irq[i], iommu); +static int rk_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); + unsigned long flags; + int ret; - iommu->domain = NULL; + /* + * Allow 'virtual devices' (e.g., drm) to attach to domain. + * Such a device does not belong to an iommu group. + */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return 0; + + dev_dbg(dev, "Attaching to iommu domain\n"); + + /* iommu already attached */ + if (iommu->domain == domain) + return 0; - dev_dbg(dev, "Detached from iommu domain\n"); + if (iommu->domain) + rk_iommu_detach_device(iommu->domain, dev); + + iommu->domain = domain; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_add_tail(&iommu->node, &rk_domain->iommus); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + if (!pm_runtime_get_if_in_use(iommu->dev)) + return 0; + + ret = rk_iommu_enable(iommu); + if (ret) + rk_iommu_detach_device(iommu->domain, dev); + + pm_runtime_put(iommu->dev); + + return ret; } static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) { struct rk_iommu_domain *rk_domain; - struct platform_device *pdev; - struct device *iommu_dev; if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA) return NULL; - /* Register a pdev per domain, so DMA API can base on this *dev - * even some virtual master doesn't have an iommu slave - */ - pdev = platform_device_register_simple("rk_iommu_domain", - PLATFORM_DEVID_AUTO, NULL, 0); - if (IS_ERR(pdev)) + if (!dma_dev) return NULL; - rk_domain = devm_kzalloc(&pdev->dev, sizeof(*rk_domain), GFP_KERNEL); + rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL); if (!rk_domain) - goto err_unreg_pdev; - - rk_domain->pdev = pdev; + return NULL; if (type == IOMMU_DOMAIN_DMA && iommu_get_dma_cookie(&rk_domain->domain)) - goto err_unreg_pdev; + return NULL; /* * rk32xx iommus use a 2 level pagetable. @@ -929,11 +985,10 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) if (!rk_domain->dt) goto err_put_cookie; - iommu_dev = &pdev->dev; - rk_domain->dt_dma = dma_map_single(iommu_dev, rk_domain->dt, + rk_domain->dt_dma = dma_map_single(dma_dev, rk_domain->dt, SPAGE_SIZE, DMA_TO_DEVICE); - if (dma_mapping_error(iommu_dev, rk_domain->dt_dma)) { - dev_err(iommu_dev, "DMA map error for DT\n"); + if (dma_mapping_error(dma_dev, rk_domain->dt_dma)) { + dev_err(dma_dev, "DMA map error for DT\n"); goto err_free_dt; } @@ -954,8 +1009,6 @@ err_free_dt: err_put_cookie: if (type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); -err_unreg_pdev: - platform_device_unregister(pdev); return NULL; } @@ -972,126 +1025,82 @@ static void rk_iommu_domain_free(struct iommu_domain *domain) if (rk_dte_is_pt_valid(dte)) { phys_addr_t pt_phys = rk_dte_pt_address(dte); u32 *page_table = phys_to_virt(pt_phys); - dma_unmap_single(&rk_domain->pdev->dev, pt_phys, + dma_unmap_single(dma_dev, pt_phys, SPAGE_SIZE, DMA_TO_DEVICE); free_page((unsigned long)page_table); } } - dma_unmap_single(&rk_domain->pdev->dev, rk_domain->dt_dma, + dma_unmap_single(dma_dev, rk_domain->dt_dma, SPAGE_SIZE, DMA_TO_DEVICE); free_page((unsigned long)rk_domain->dt); if (domain->type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); - - platform_device_unregister(rk_domain->pdev); } -static bool rk_iommu_is_dev_iommu_master(struct device *dev) +static int rk_iommu_add_device(struct device *dev) { - struct device_node *np = dev->of_node; - int ret; - - /* - * An iommu master has an iommus property containing a list of phandles - * to iommu nodes, each with an #iommu-cells property with value 0. - */ - ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells"); - return (ret > 0); -} + struct iommu_group *group; + struct rk_iommu *iommu; + struct rk_iommudata *data; -static int rk_iommu_group_set_iommudata(struct iommu_group *group, - struct device *dev) -{ - struct device_node *np = dev->of_node; - struct platform_device *pd; - int ret; - struct of_phandle_args args; + data = dev->archdata.iommu; + if (!data) + return -ENODEV; - /* - * An iommu master has an iommus property containing a list of phandles - * to iommu nodes, each with an #iommu-cells property with value 0. - */ - ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0, - &args); - if (ret) { - dev_err(dev, "of_parse_phandle_with_args(%pOF) => %d\n", - np, ret); - return ret; - } - if (args.args_count != 0) { - dev_err(dev, "incorrect number of iommu params found for %pOF (found %d, expected 0)\n", - args.np, args.args_count); - return -EINVAL; - } + iommu = rk_iommu_from_dev(dev); - pd = of_find_device_by_node(args.np); - of_node_put(args.np); - if (!pd) { - dev_err(dev, "iommu %pOF not found\n", args.np); - return -EPROBE_DEFER; - } + group = iommu_group_get_for_dev(dev); + if (IS_ERR(group)) + return PTR_ERR(group); + iommu_group_put(group); - /* TODO(djkurtz): handle multiple slave iommus for a single master */ - iommu_group_set_iommudata(group, &pd->dev, NULL); + iommu_device_link(&iommu->iommu, dev); + data->link = device_link_add(dev, iommu->dev, DL_FLAG_PM_RUNTIME); return 0; } -static int rk_iommu_add_device(struct device *dev) +static void rk_iommu_remove_device(struct device *dev) { - struct iommu_group *group; struct rk_iommu *iommu; - int ret; - - if (!rk_iommu_is_dev_iommu_master(dev)) - return -ENODEV; + struct rk_iommudata *data = dev->archdata.iommu; - group = iommu_group_get(dev); - if (!group) { - group = iommu_group_alloc(); - if (IS_ERR(group)) { - dev_err(dev, "Failed to allocate IOMMU group\n"); - return PTR_ERR(group); - } - } + iommu = rk_iommu_from_dev(dev); - ret = iommu_group_add_device(group, dev); - if (ret) - goto err_put_group; + device_link_del(data->link); + iommu_device_unlink(&iommu->iommu, dev); + iommu_group_remove_device(dev); +} - ret = rk_iommu_group_set_iommudata(group, dev); - if (ret) - goto err_remove_device; +static struct iommu_group *rk_iommu_device_group(struct device *dev) +{ + struct rk_iommu *iommu; iommu = rk_iommu_from_dev(dev); - if (iommu) - iommu_device_link(&iommu->iommu, dev); - - iommu_group_put(group); - - return 0; -err_remove_device: - iommu_group_remove_device(dev); -err_put_group: - iommu_group_put(group); - return ret; + return iommu_group_ref_get(iommu->group); } -static void rk_iommu_remove_device(struct device *dev) +static int rk_iommu_of_xlate(struct device *dev, + struct of_phandle_args *args) { - struct rk_iommu *iommu; + struct platform_device *iommu_dev; + struct rk_iommudata *data; - if (!rk_iommu_is_dev_iommu_master(dev)) - return; + data = devm_kzalloc(dma_dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; - iommu = rk_iommu_from_dev(dev); - if (iommu) - iommu_device_unlink(&iommu->iommu, dev); + iommu_dev = of_find_device_by_node(args->np); - iommu_group_remove_device(dev); + data->iommu = platform_get_drvdata(iommu_dev); + dev->archdata.iommu = data; + + of_dev_put(iommu_dev); + + return 0; } static const struct iommu_ops rk_iommu_ops = { @@ -1105,31 +1114,9 @@ static const struct iommu_ops rk_iommu_ops = { .add_device = rk_iommu_add_device, .remove_device = rk_iommu_remove_device, .iova_to_phys = rk_iommu_iova_to_phys, + .device_group = rk_iommu_device_group, .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, -}; - -static int rk_iommu_domain_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - - dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; - - /* Set dma_ops for dev, otherwise it would be dummy_dma_ops */ - arch_setup_dma_ops(dev, 0, DMA_BIT_MASK(32), NULL, false); - - dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); - dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); - - return 0; -} - -static struct platform_driver rk_iommu_domain_driver = { - .probe = rk_iommu_domain_probe, - .driver = { - .name = "rk_iommu_domain", - }, + .of_xlate = rk_iommu_of_xlate, }; static int rk_iommu_probe(struct platform_device *pdev) @@ -1138,7 +1125,7 @@ static int rk_iommu_probe(struct platform_device *pdev) struct rk_iommu *iommu; struct resource *res; int num_res = pdev->num_resources; - int err, i; + int err, i, irq; iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); if (!iommu) @@ -1165,50 +1152,108 @@ static int rk_iommu_probe(struct platform_device *pdev) if (iommu->num_mmu == 0) return PTR_ERR(iommu->bases[0]); - iommu->num_irq = platform_irq_count(pdev); - if (iommu->num_irq < 0) - return iommu->num_irq; - if (iommu->num_irq == 0) - return -ENXIO; - - iommu->irq = devm_kcalloc(dev, iommu->num_irq, sizeof(*iommu->irq), - GFP_KERNEL); - if (!iommu->irq) - return -ENOMEM; + i = 0; + while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) { + if (irq < 0) + return irq; - for (i = 0; i < iommu->num_irq; i++) { - iommu->irq[i] = platform_get_irq(pdev, i); - if (iommu->irq[i] < 0) { - dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq[i]); - return -ENXIO; - } + err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, + IRQF_SHARED, dev_name(dev), iommu); + if (err) + return err; } iommu->reset_disabled = device_property_read_bool(dev, "rockchip,disable-mmu-reset"); - err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev)); + iommu->num_clocks = ARRAY_SIZE(rk_iommu_clocks); + iommu->clocks = devm_kcalloc(iommu->dev, iommu->num_clocks, + sizeof(*iommu->clocks), GFP_KERNEL); + if (!iommu->clocks) + return -ENOMEM; + + for (i = 0; i < iommu->num_clocks; ++i) + iommu->clocks[i].id = rk_iommu_clocks[i]; + + err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks); + if (err) + return err; + + err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks); if (err) return err; + iommu->group = iommu_group_alloc(); + if (IS_ERR(iommu->group)) { + err = PTR_ERR(iommu->group); + goto err_unprepare_clocks; + } + + err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev)); + if (err) + goto err_put_group; + iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops); + iommu_device_set_fwnode(&iommu->iommu, &dev->of_node->fwnode); + err = iommu_device_register(&iommu->iommu); + if (err) + goto err_remove_sysfs; + + /* + * Use the first registered IOMMU device for domain to use with DMA + * API, since a domain might not physically correspond to a single + * IOMMU device.. + */ + if (!dma_dev) + dma_dev = &pdev->dev; + + bus_set_iommu(&platform_bus_type, &rk_iommu_ops); + pm_runtime_enable(dev); + + return 0; +err_remove_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); +err_put_group: + iommu_group_put(iommu->group); +err_unprepare_clocks: + clk_bulk_unprepare(iommu->num_clocks, iommu->clocks); return err; } -static int rk_iommu_remove(struct platform_device *pdev) +static void rk_iommu_shutdown(struct platform_device *pdev) { - struct rk_iommu *iommu = platform_get_drvdata(pdev); + pm_runtime_force_suspend(&pdev->dev); +} - if (iommu) { - iommu_device_sysfs_remove(&iommu->iommu); - iommu_device_unregister(&iommu->iommu); - } +static int __maybe_unused rk_iommu_suspend(struct device *dev) +{ + struct rk_iommu *iommu = dev_get_drvdata(dev); + if (!iommu->domain) + return 0; + + rk_iommu_disable(iommu); return 0; } +static int __maybe_unused rk_iommu_resume(struct device *dev) +{ + struct rk_iommu *iommu = dev_get_drvdata(dev); + + if (!iommu->domain) + return 0; + + return rk_iommu_enable(iommu); +} + +static const struct dev_pm_ops rk_iommu_pm_ops = { + SET_RUNTIME_PM_OPS(rk_iommu_suspend, rk_iommu_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) +}; + static const struct of_device_id rk_iommu_dt_ids[] = { { .compatible = "rockchip,iommu" }, { /* sentinel */ } @@ -1217,45 +1262,22 @@ MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids); static struct platform_driver rk_iommu_driver = { .probe = rk_iommu_probe, - .remove = rk_iommu_remove, + .shutdown = rk_iommu_shutdown, .driver = { .name = "rk_iommu", .of_match_table = rk_iommu_dt_ids, + .pm = &rk_iommu_pm_ops, + .suppress_bind_attrs = true, }, }; static int __init rk_iommu_init(void) { - struct device_node *np; - int ret; - - np = of_find_matching_node(NULL, rk_iommu_dt_ids); - if (!np) - return 0; - - of_node_put(np); - - ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops); - if (ret) - return ret; - - ret = platform_driver_register(&rk_iommu_domain_driver); - if (ret) - return ret; - - ret = platform_driver_register(&rk_iommu_driver); - if (ret) - platform_driver_unregister(&rk_iommu_domain_driver); - return ret; + return platform_driver_register(&rk_iommu_driver); } -static void __exit rk_iommu_exit(void) -{ - platform_driver_unregister(&rk_iommu_driver); - platform_driver_unregister(&rk_iommu_domain_driver); -} - subsys_initcall(rk_iommu_init); -module_exit(rk_iommu_exit); + +IOMMU_OF_DECLARE(rk_iommu_of, "rockchip,iommu"); MODULE_DESCRIPTION("IOMMU API for Rockchip"); MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>"); |