summaryrefslogtreecommitdiff
path: root/drivers/iommu/arm-smmu-v3.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu/arm-smmu-v3.c')
-rw-r--r--drivers/iommu/arm-smmu-v3.c126
1 files changed, 73 insertions, 53 deletions
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8e9ec81ce4bb..dafaf59dc3b8 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -118,6 +118,7 @@
#define ARM_SMMU_IRQ_CTRL 0x50
#define IRQ_CTRL_EVTQ_IRQEN (1 << 2)
+#define IRQ_CTRL_PRIQ_IRQEN (1 << 1)
#define IRQ_CTRL_GERROR_IRQEN (1 << 0)
#define ARM_SMMU_IRQ_CTRLACK 0x54
@@ -173,14 +174,14 @@
#define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc
/* Common MSI config fields */
-#define MSI_CFG0_SH_SHIFT 60
-#define MSI_CFG0_SH_NSH (0UL << MSI_CFG0_SH_SHIFT)
-#define MSI_CFG0_SH_OSH (2UL << MSI_CFG0_SH_SHIFT)
-#define MSI_CFG0_SH_ISH (3UL << MSI_CFG0_SH_SHIFT)
-#define MSI_CFG0_MEMATTR_SHIFT 56
-#define MSI_CFG0_MEMATTR_DEVICE_nGnRE (0x1 << MSI_CFG0_MEMATTR_SHIFT)
#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 Q_IDX(q, p) ((p) & ((1 << (q)->max_n_shift) - 1))
#define Q_WRP(q, p) ((p) & (1 << (q)->max_n_shift))
@@ -199,9 +200,10 @@
* Stream table.
*
* Linear: Enough to cover 1 << IDR1.SIDSIZE entries
- * 2lvl: 8k L1 entries, 256 lazy entries per table (each table covers a PCI bus)
+ * 2lvl: 128k L1 entries,
+ * 256 lazy entries per table (each table covers a PCI bus)
*/
-#define STRTAB_L1_SZ_SHIFT 16
+#define STRTAB_L1_SZ_SHIFT 20
#define STRTAB_SPLIT 8
#define STRTAB_L1_DESC_DWORDS 1
@@ -269,10 +271,10 @@
#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 24
+#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 26
+#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
@@ -542,6 +544,9 @@ struct arm_smmu_device {
#define ARM_SMMU_FEAT_HYP (1 << 12)
u32 features;
+#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0)
+ u32 options;
+
struct arm_smmu_cmdq cmdq;
struct arm_smmu_evtq evtq;
struct arm_smmu_priq priq;
@@ -602,11 +607,35 @@ struct arm_smmu_domain {
static DEFINE_SPINLOCK(arm_smmu_devices_lock);
static LIST_HEAD(arm_smmu_devices);
+struct arm_smmu_option_prop {
+ u32 opt;
+ const char *prop;
+};
+
+static struct arm_smmu_option_prop arm_smmu_options[] = {
+ { ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
+ { 0, NULL},
+};
+
static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
{
return container_of(dom, struct arm_smmu_domain, domain);
}
+static void parse_driver_options(struct arm_smmu_device *smmu)
+{
+ int i = 0;
+
+ do {
+ if (of_property_read_bool(smmu->dev->of_node,
+ arm_smmu_options[i].prop)) {
+ smmu->options |= arm_smmu_options[i].opt;
+ dev_notice(smmu->dev, "option %s\n",
+ arm_smmu_options[i].prop);
+ }
+ } while (arm_smmu_options[++i].opt);
+}
+
/* Low-level queue manipulation functions */
static bool queue_full(struct arm_smmu_queue *q)
{
@@ -1036,7 +1065,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
arm_smmu_sync_ste_for_sid(smmu, sid);
/* It's likely that we'll want to use the new STE soon */
- arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+ if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH))
+ arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
}
static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
@@ -1064,7 +1094,7 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
return 0;
size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
- strtab = &cfg->strtab[sid >> STRTAB_SPLIT << STRTAB_L1_DESC_DWORDS];
+ strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
desc->span = STRTAB_SPLIT + 1;
desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
@@ -1301,33 +1331,10 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
arm_smmu_cmdq_issue_cmd(smmu, &cmd);
}
-static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
-{
- struct arm_smmu_domain *smmu_domain = cookie;
- struct arm_smmu_device *smmu = smmu_domain->smmu;
- unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
- if (smmu->features & ARM_SMMU_FEAT_COHERENCY) {
- dsb(ishst);
- } else {
- dma_addr_t dma_addr;
- struct device *dev = smmu->dev;
-
- dma_addr = dma_map_page(dev, virt_to_page(addr), offset, size,
- DMA_TO_DEVICE);
-
- if (dma_mapping_error(dev, dma_addr))
- dev_err(dev, "failed to flush pgtable at %p\n", addr);
- else
- dma_unmap_page(dev, dma_addr, size, DMA_TO_DEVICE);
- }
-}
-
static struct iommu_gather_ops arm_smmu_gather_ops = {
.tlb_flush_all = arm_smmu_tlb_inv_context,
.tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
.tlb_sync = arm_smmu_tlb_sync,
- .flush_pgtable = arm_smmu_flush_pgtable,
};
/* IOMMU API */
@@ -1502,6 +1509,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
.ias = ias,
.oas = oas,
.tlb = &arm_smmu_gather_ops,
+ .iommu_dev = smmu->dev,
};
pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
@@ -2020,21 +2028,31 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
{
void *strtab;
u64 reg;
- u32 size;
+ u32 size, l1size;
int ret;
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
- /* Calculate the L1 size, capped to the SIDSIZE */
- size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
- size = min(size, smmu->sid_bits - STRTAB_SPLIT);
- if (size + STRTAB_SPLIT < smmu->sid_bits)
+ /*
+ * If we can resolve everything with a single L2 table, then we
+ * just need a single L1 descriptor. Otherwise, calculate the L1
+ * size, capped to the SIDSIZE.
+ */
+ if (smmu->sid_bits < STRTAB_SPLIT) {
+ size = 0;
+ } else {
+ size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
+ size = min(size, smmu->sid_bits - STRTAB_SPLIT);
+ }
+ cfg->num_l1_ents = 1 << size;
+
+ size += STRTAB_SPLIT;
+ if (size < smmu->sid_bits)
dev_warn(smmu->dev,
"2-level strtab only covers %u/%u bits of SID\n",
- size + STRTAB_SPLIT, smmu->sid_bits);
+ size, smmu->sid_bits);
- cfg->num_l1_ents = 1 << size;
- size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
- strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+ l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
+ strtab = dma_zalloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
GFP_KERNEL);
if (!strtab) {
dev_err(smmu->dev,
@@ -2055,8 +2073,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
ret = arm_smmu_init_l1_strtab(smmu);
if (ret)
dma_free_coherent(smmu->dev,
- cfg->num_l1_ents *
- (STRTAB_L1_DESC_DWORDS << 3),
+ l1size,
strtab,
cfg->strtab_dma);
return ret;
@@ -2168,6 +2185,7 @@ static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
{
int ret, irq;
+ u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;
/* Disable IRQs first */
ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
@@ -2222,13 +2240,13 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
if (IS_ERR_VALUE(ret))
dev_warn(smmu->dev,
"failed to enable priq irq\n");
+ else
+ irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
}
}
/* Enable interrupt generation on the SMMU */
- ret = arm_smmu_write_reg_sync(smmu,
- IRQ_CTRL_EVTQ_IRQEN |
- IRQ_CTRL_GERROR_IRQEN,
+ ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
if (ret)
dev_warn(smmu->dev, "failed to enable irqs\n");
@@ -2510,12 +2528,12 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
case IDR5_OAS_44_BIT:
smmu->oas = 44;
break;
+ default:
+ dev_info(smmu->dev,
+ "unknown output address size. Truncating to 48-bit\n");
+ /* Fallthrough */
case IDR5_OAS_48_BIT:
smmu->oas = 48;
- break;
- default:
- dev_err(smmu->dev, "unknown output address size!\n");
- return -ENXIO;
}
/* Set the DMA mask for our table walker */
@@ -2573,6 +2591,8 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
if (irq > 0)
smmu->gerr_irq = irq;
+ parse_driver_options(smmu);
+
/* Probe the h/w */
ret = arm_smmu_device_probe(smmu);
if (ret)
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-17 15:42:03 +0300