summaryrefslogtreecommitdiffstats
path: root/drivers/iommu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu')
-rw-r--r--drivers/iommu/Kconfig3
-rw-r--r--drivers/iommu/amd_iommu.c56
-rw-r--r--drivers/iommu/amd_iommu_init.c2
-rw-r--r--drivers/iommu/arm-smmu-v3.c68
-rw-r--r--drivers/iommu/arm-smmu.c104
-rw-r--r--drivers/iommu/dma-iommu.c183
-rw-r--r--drivers/iommu/dmar.c6
-rw-r--r--drivers/iommu/exynos-iommu.c39
-rw-r--r--drivers/iommu/intel-iommu.c139
-rw-r--r--drivers/iommu/io-pgtable-arm-v7s.c6
-rw-r--r--drivers/iommu/io-pgtable-arm.c5
-rw-r--r--drivers/iommu/iommu.c180
-rw-r--r--drivers/iommu/ipmmu-vmsa.c2
-rw-r--r--drivers/iommu/of_iommu.c4
14 files changed, 631 insertions, 166 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 8ee54d71c7eb..37e204f3d9be 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -352,9 +352,6 @@ config MTK_IOMMU_V1
select IOMMU_API
select MEMORY
select MTK_SMI
- select COMMON_CLK_MT2701_MMSYS
- select COMMON_CLK_MT2701_IMGSYS
- select COMMON_CLK_MT2701_VDECSYS
help
Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is
Multimedia Memory Managememt Unit. This option enables remapping of
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index ba708c5bdaed..1b5b8c5361c5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1027,7 +1027,7 @@ again:
next_tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
left = (head - next_tail) % CMD_BUFFER_SIZE;
- if (left <= 2) {
+ if (left <= 0x20) {
struct iommu_cmd sync_cmd;
int ret;
@@ -3165,9 +3165,10 @@ static bool amd_iommu_capable(enum iommu_cap cap)
return false;
}
-static void amd_iommu_get_dm_regions(struct device *dev,
- struct list_head *head)
+static void amd_iommu_get_resv_regions(struct device *dev,
+ struct list_head *head)
{
+ struct iommu_resv_region *region;
struct unity_map_entry *entry;
int devid;
@@ -3176,41 +3177,56 @@ static void amd_iommu_get_dm_regions(struct device *dev,
return;
list_for_each_entry(entry, &amd_iommu_unity_map, list) {
- struct iommu_dm_region *region;
+ size_t length;
+ int prot = 0;
if (devid < entry->devid_start || devid > entry->devid_end)
continue;
- region = kzalloc(sizeof(*region), GFP_KERNEL);
+ length = entry->address_end - entry->address_start;
+ if (entry->prot & IOMMU_PROT_IR)
+ prot |= IOMMU_READ;
+ if (entry->prot & IOMMU_PROT_IW)
+ prot |= IOMMU_WRITE;
+
+ region = iommu_alloc_resv_region(entry->address_start,
+ length, prot,
+ IOMMU_RESV_DIRECT);
if (!region) {
pr_err("Out of memory allocating dm-regions for %s\n",
dev_name(dev));
return;
}
-
- region->start = entry->address_start;
- region->length = entry->address_end - entry->address_start;
- if (entry->prot & IOMMU_PROT_IR)
- region->prot |= IOMMU_READ;
- if (entry->prot & IOMMU_PROT_IW)
- region->prot |= IOMMU_WRITE;
-
list_add_tail(&region->list, head);
}
+
+ region = iommu_alloc_resv_region(MSI_RANGE_START,
+ MSI_RANGE_END - MSI_RANGE_START + 1,
+ 0, IOMMU_RESV_RESERVED);
+ if (!region)
+ return;
+ list_add_tail(&region->list, head);
+
+ region = iommu_alloc_resv_region(HT_RANGE_START,
+ HT_RANGE_END - HT_RANGE_START + 1,
+ 0, IOMMU_RESV_RESERVED);
+ if (!region)
+ return;
+ list_add_tail(&region->list, head);
}
-static void amd_iommu_put_dm_regions(struct device *dev,
+static void amd_iommu_put_resv_regions(struct device *dev,
struct list_head *head)
{
- struct iommu_dm_region *entry, *next;
+ struct iommu_resv_region *entry, *next;
list_for_each_entry_safe(entry, next, head, list)
kfree(entry);
}
-static void amd_iommu_apply_dm_region(struct device *dev,
+static void amd_iommu_apply_resv_region(struct device *dev,
struct iommu_domain *domain,
- struct iommu_dm_region *region)
+ struct iommu_resv_region *region)
{
struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
unsigned long start, end;
@@ -3234,9 +3250,9 @@ const struct iommu_ops amd_iommu_ops = {
.add_device = amd_iommu_add_device,
.remove_device = amd_iommu_remove_device,
.device_group = amd_iommu_device_group,
- .get_dm_regions = amd_iommu_get_dm_regions,
- .put_dm_regions = amd_iommu_put_dm_regions,
- .apply_dm_region = amd_iommu_apply_dm_region,
+ .get_resv_regions = amd_iommu_get_resv_regions,
+ .put_resv_regions = amd_iommu_put_resv_regions,
+ .apply_resv_region = amd_iommu_apply_resv_region,
.pgsize_bitmap = AMD_IOMMU_PGSIZES,
};
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6b9e66122528..04cdac7ab3e3 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2233,7 +2233,7 @@ static int __init early_amd_iommu_init(void)
*/
ret = check_ivrs_checksum(ivrs_base);
if (ret)
- return ret;
+ goto out;
amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 53751379dee3..5806a6acc94e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -269,9 +269,6 @@
#define STRTAB_STE_1_SHCFG_INCOMING 1UL
#define STRTAB_STE_1_SHCFG_SHIFT 44
-#define STRTAB_STE_1_PRIVCFG_UNPRIV 2UL
-#define STRTAB_STE_1_PRIVCFG_SHIFT 48
-
#define STRTAB_STE_2_S2VMID_SHIFT 0
#define STRTAB_STE_2_S2VMID_MASK 0xffffUL
#define STRTAB_STE_2_VTCR_SHIFT 32
@@ -412,6 +409,9 @@
/* High-level queue structures */
#define ARM_SMMU_POLL_TIMEOUT_US 100
+#define MSI_IOVA_BASE 0x8000000
+#define MSI_IOVA_LENGTH 0x100000
+
static bool disable_bypass;
module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
MODULE_PARM_DESC(disable_bypass,
@@ -1045,13 +1045,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
}
}
- /* Nuke the existing Config, as we're going to rewrite it */
- val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
-
- if (ste->valid)
- val |= STRTAB_STE_0_V;
- else
- val &= ~STRTAB_STE_0_V;
+ /* Nuke the existing STE_0 value, as we're going to rewrite it */
+ val = ste->valid ? STRTAB_STE_0_V : 0;
if (ste->bypass) {
val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
@@ -1076,9 +1071,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
#ifdef CONFIG_PCI_ATS
STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
#endif
- STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT |
- STRTAB_STE_1_PRIVCFG_UNPRIV <<
- STRTAB_STE_1_PRIVCFG_SHIFT);
+ STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
if (smmu->features & ARM_SMMU_FEAT_STALLS)
dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
@@ -1086,7 +1079,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
<< STRTAB_STE_0_S1CTXPTR_SHIFT) |
STRTAB_STE_0_CFG_S1_TRANS;
-
}
if (ste->s2_cfg) {
@@ -1375,8 +1367,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return true;
- case IOMMU_CAP_INTR_REMAP:
- return true; /* MSIs are just memory writes */
case IOMMU_CAP_NOEXEC:
return true;
default:
@@ -1891,6 +1881,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
return iommu_fwspec_add_ids(dev, args->args, 1);
}
+static void arm_smmu_get_resv_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_resv_region *region;
+ int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+ region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+ prot, IOMMU_RESV_MSI);
+ if (!region)
+ return;
+
+ list_add_tail(&region->list, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_resv_region *entry, *next;
+
+ list_for_each_entry_safe(entry, next, head, list)
+ kfree(entry);
+}
+
static struct iommu_ops arm_smmu_ops = {
.capable = arm_smmu_capable,
.domain_alloc = arm_smmu_domain_alloc,
@@ -1906,6 +1919,8 @@ static struct iommu_ops arm_smmu_ops = {
.domain_get_attr = arm_smmu_domain_get_attr,
.domain_set_attr = arm_smmu_domain_set_attr,
.of_xlate = arm_smmu_of_xlate,
+ .get_resv_regions = arm_smmu_get_resv_regions,
+ .put_resv_regions = arm_smmu_put_resv_regions,
.pgsize_bitmap = -1UL, /* Restricted during device attach */
};
@@ -1991,17 +2006,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
u32 size, l1size;
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
- /*
- * 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);
- }
+ /* 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);
cfg->num_l1_ents = 1 << size;
size += STRTAB_SPLIT;
@@ -2512,6 +2519,13 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
+ /*
+ * If the SMMU supports fewer bits than would fill a single L2 stream
+ * table, use a linear table instead.
+ */
+ if (smmu->sid_bits <= STRTAB_SPLIT)
+ smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;
+
/* IDR5 */
reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8fb4af2dfbfa..abf6496843a6 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -24,6 +24,7 @@
* - v7/v8 long-descriptor format
* - Non-secure access to the SMMU
* - Context fault reporting
+ * - Extended Stream ID (16 bit)
*/
#define pr_fmt(fmt) "arm-smmu: " fmt
@@ -87,6 +88,7 @@
#define sCR0_CLIENTPD (1 << 0)
#define sCR0_GFRE (1 << 1)
#define sCR0_GFIE (1 << 2)
+#define sCR0_EXIDENABLE (1 << 3)
#define sCR0_GCFGFRE (1 << 4)
#define sCR0_GCFGFIE (1 << 5)
#define sCR0_USFCFG (1 << 10)
@@ -126,6 +128,7 @@
#define ID0_NUMIRPT_MASK 0xff
#define ID0_NUMSIDB_SHIFT 9
#define ID0_NUMSIDB_MASK 0xf
+#define ID0_EXIDS (1 << 8)
#define ID0_NUMSMRG_SHIFT 0
#define ID0_NUMSMRG_MASK 0xff
@@ -169,6 +172,7 @@
#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
#define S2CR_CBNDX_SHIFT 0
#define S2CR_CBNDX_MASK 0xff
+#define S2CR_EXIDVALID (1 << 10)
#define S2CR_TYPE_SHIFT 16
#define S2CR_TYPE_MASK 0x3
enum arm_smmu_s2cr_type {
@@ -260,6 +264,7 @@ enum arm_smmu_s2cr_privcfg {
#define TTBCR2_SEP_SHIFT 15
#define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT)
+#define TTBCR2_AS (1 << 4)
#define TTBRn_ASID_SHIFT 48
@@ -281,6 +286,9 @@ enum arm_smmu_s2cr_privcfg {
#define FSYNR0_WNR (1 << 4)
+#define MSI_IOVA_BASE 0x8000000
+#define MSI_IOVA_LENGTH 0x100000
+
static int force_stage;
module_param(force_stage, int, S_IRUGO);
MODULE_PARM_DESC(force_stage,
@@ -351,6 +359,7 @@ struct arm_smmu_device {
#define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9)
#define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10)
#define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11)
+#define ARM_SMMU_FEAT_EXIDS (1 << 12)
u32 features;
#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
@@ -781,6 +790,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
reg2 = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
reg2 |= TTBCR2_SEP_UPSTREAM;
+ if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+ reg2 |= TTBCR2_AS;
}
if (smmu->version > ARM_SMMU_V1)
writel_relaxed(reg2, cb_base + ARM_SMMU_CB_TTBCR2);
@@ -1051,7 +1062,7 @@ static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
struct arm_smmu_smr *smr = smmu->smrs + idx;
u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT;
- if (smr->valid)
+ if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
reg |= SMR_VALID;
writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx));
}
@@ -1063,6 +1074,9 @@ static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
(s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT |
(s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT;
+ if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
+ smmu->smrs[idx].valid)
+ reg |= S2CR_EXIDVALID;
writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx));
}
@@ -1073,6 +1087,34 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
arm_smmu_write_smr(smmu, idx);
}
+/*
+ * The width of SMR's mask field depends on sCR0_EXIDENABLE, so this function
+ * should be called after sCR0 is written.
+ */
+static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
+{
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ u32 smr;
+
+ if (!smmu->smrs)
+ return;
+
+ /*
+ * SMR.ID bits may not be preserved if the corresponding MASK
+ * bits are set, so check each one separately. We can reject
+ * masters later if they try to claim IDs outside these masks.
+ */
+ smr = smmu->streamid_mask << SMR_ID_SHIFT;
+ writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+ smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+ smmu->streamid_mask = smr >> SMR_ID_SHIFT;
+
+ smr = smmu->streamid_mask << SMR_MASK_SHIFT;
+ writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+ smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+ smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
+}
+
static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
{
struct arm_smmu_smr *smrs = smmu->smrs;
@@ -1217,7 +1259,7 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
continue;
s2cr[idx].type = type;
- s2cr[idx].privcfg = S2CR_PRIVCFG_UNPRIV;
+ s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
s2cr[idx].cbndx = cbndx;
arm_smmu_write_s2cr(smmu, idx);
}
@@ -1374,8 +1416,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
* requests.
*/
return true;
- case IOMMU_CAP_INTR_REMAP:
- return true; /* MSIs are just memory writes */
case IOMMU_CAP_NOEXEC:
return true;
default:
@@ -1561,6 +1601,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
return iommu_fwspec_add_ids(dev, &fwid, 1);
}
+static void arm_smmu_get_resv_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_resv_region *region;
+ int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+ region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+ prot, IOMMU_RESV_MSI);
+ if (!region)
+ return;
+
+ list_add_tail(&region->list, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_resv_region *entry, *next;
+
+ list_for_each_entry_safe(entry, next, head, list)
+ kfree(entry);
+}
+
static struct iommu_ops arm_smmu_ops = {
.capable = arm_smmu_capable,
.domain_alloc = arm_smmu_domain_alloc,
@@ -1576,6 +1639,8 @@ static struct iommu_ops arm_smmu_ops = {
.domain_get_attr = arm_smmu_domain_get_attr,
.domain_set_attr = arm_smmu_domain_set_attr,
.of_xlate = arm_smmu_of_xlate,
+ .get_resv_regions = arm_smmu_get_resv_regions,
+ .put_resv_regions = arm_smmu_put_resv_regions,
.pgsize_bitmap = -1UL, /* Restricted during device attach */
};
@@ -1660,6 +1725,9 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
if (smmu->features & ARM_SMMU_FEAT_VMID16)
reg |= sCR0_VMID16EN;
+ if (smmu->features & ARM_SMMU_FEAT_EXIDS)
+ reg |= sCR0_EXIDENABLE;
+
/* Push the button */
__arm_smmu_tlb_sync(smmu);
writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
@@ -1747,11 +1815,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
"\t(IDR0.CTTW overridden by FW configuration)\n");
/* Max. number of entries we have for stream matching/indexing */
- size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+ if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+ smmu->features |= ARM_SMMU_FEAT_EXIDS;
+ size = 1 << 16;
+ } else {
+ size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+ }
smmu->streamid_mask = size - 1;
if (id & ID0_SMS) {
- u32 smr;
-
smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK;
if (size == 0) {
@@ -1760,21 +1831,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
return -ENODEV;
}
- /*
- * SMR.ID bits may not be preserved if the corresponding MASK
- * bits are set, so check each one separately. We can reject
- * masters later if they try to claim IDs outside these masks.
- */
- smr = smmu->streamid_mask << SMR_ID_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->streamid_mask = smr >> SMR_ID_SHIFT;
-
- smr = smmu->streamid_mask << SMR_MASK_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
-
/* Zero-initialised to mark as invalid */
smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs),
GFP_KERNEL);
@@ -1782,8 +1838,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
return -ENOMEM;
dev_notice(smmu->dev,
- "\tstream matching with %lu register groups, mask 0x%x",
- size, smmu->smr_mask_mask);
+ "\tstream matching with %lu register groups", size);
}
/* s2cr->type == 0 means translation, so initialise explicitly */
smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
@@ -2123,6 +2178,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, smmu);
arm_smmu_device_reset(smmu);
+ arm_smmu_test_smr_masks(smmu);
/* Oh, for a proper bus abstraction */
if (!iommu_present(&platform_bus_type))
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 2db0d641cf45..48d36ce59efb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -37,15 +37,50 @@ struct iommu_dma_msi_page {
phys_addr_t phys;
};
+enum iommu_dma_cookie_type {
+ IOMMU_DMA_IOVA_COOKIE,
+ IOMMU_DMA_MSI_COOKIE,
+};
+
struct iommu_dma_cookie {
- struct iova_domain iovad;
- struct list_head msi_page_list;
- spinlock_t msi_lock;
+ enum iommu_dma_cookie_type type;
+ union {
+ /* Full allocator for IOMMU_DMA_IOVA_COOKIE */
+ struct iova_domain iovad;
+ /* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
+ dma_addr_t msi_iova;
+ };
+ struct list_head msi_page_list;
+ spinlock_t msi_lock;
};
+static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
+{
+ if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+ return cookie->iovad.granule;
+ return PAGE_SIZE;
+}
+
static inline struct iova_domain *cookie_iovad(struct iommu_domain *domain)
{
- return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad;
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+
+ if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+ return &cookie->iovad;
+ return NULL;
+}
+
+static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
+{
+ struct iommu_dma_cookie *cookie;
+
+ cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+ if (cookie) {
+ spin_lock_init(&cookie->msi_lock);
+ INIT_LIST_HEAD(&cookie->msi_page_list);
+ cookie->type = type;
+ }
+ return cookie;
}
int iommu_dma_init(void)
@@ -62,25 +97,53 @@ int iommu_dma_init(void)
*/
int iommu_get_dma_cookie(struct iommu_domain *domain)
{
+ if (domain->iova_cookie)
+ return -EEXIST;
+
+ domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
+ if (!domain->iova_cookie)
+ return -ENOMEM;
+
+ return 0;
+}
+EXPORT_SYMBOL(iommu_get_dma_cookie);
+
+/**
+ * iommu_get_msi_cookie - Acquire just MSI remapping resources
+ * @domain: IOMMU domain to prepare
+ * @base: Start address of IOVA region for MSI mappings
+ *
+ * Users who manage their own IOVA allocation and do not want DMA API support,
+ * but would still like to take advantage of automatic MSI remapping, can use
+ * this to initialise their own domain appropriately. Users should reserve a
+ * contiguous IOVA region, starting at @base, large enough to accommodate the
+ * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
+ * used by the devices attached to @domain.
+ */
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
struct iommu_dma_cookie *cookie;
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
if (domain->iova_cookie)
return -EEXIST;
- cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+ cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
if (!cookie)
return -ENOMEM;
- spin_lock_init(&cookie->msi_lock);
- INIT_LIST_HEAD(&cookie->msi_page_list);
+ cookie->msi_iova = base;
domain->iova_cookie = cookie;
return 0;
}
-EXPORT_SYMBOL(iommu_get_dma_cookie);
+EXPORT_SYMBOL(iommu_get_msi_cookie);
/**
* iommu_put_dma_cookie - Release a domain's DMA mapping resources
- * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
+ * iommu_get_msi_cookie()
*
* IOMMU drivers should normally call this from their domain_free callback.
*/
@@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
if (!cookie)
return;
- if (cookie->iovad.granule)
+ if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
put_iova_domain(&cookie->iovad);
list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
@@ -137,11 +200,13 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
u64 size, struct device *dev)
{
- struct iova_domain *iovad = cookie_iovad(domain);
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
unsigned long order, base_pfn, end_pfn;
+ bool pci = dev && dev_is_pci(dev);
- if (!iovad)
- return -ENODEV;
+ if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+ return -EINVAL;
/* Use the smallest supported page size for IOVA granularity */
order = __ffs(domain->pgsize_bitmap);
@@ -161,19 +226,31 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
end_pfn = min_t(unsigned long, end_pfn,
domain->geometry.aperture_end >> order);
}
+ /*
+ * PCI devices may have larger DMA masks, but still prefer allocating
+ * within a 32-bit mask to avoid DAC addressing. Such limitations don't
+ * apply to the typical platform device, so for those we may as well
+ * leave the cache limit at the top of their range to save an rb_last()
+ * traversal on every allocation.
+ */
+ if (pci)
+ end_pfn &= DMA_BIT_MASK(32) >> order;
- /* All we can safely do with an existing domain is enlarge it */
+ /* start_pfn is always nonzero for an already-initialised domain */
if (iovad->start_pfn) {
if (1UL << order != iovad->granule ||
- base_pfn != iovad->start_pfn ||
- end_pfn < iovad->dma_32bit_pfn) {
+ base_pfn != iovad->start_pfn) {
pr_warn("Incompatible range for DMA domain\n");
return -EFAULT;
}
- iovad->dma_32bit_pfn = end_pfn;
+ /*
+ * If we have devices with different DMA masks, move the free
+ * area cache limit down for the benefit of the smaller one.
+ */
+ iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn);
} else {
init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
- if (dev && dev_is_pci(dev))
+ if (pci)
iova_reserve_pci_windows(to_pci_dev(dev), iovad);
}
return 0;
@@ -181,16 +258,22 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
EXPORT_SYMBOL(iommu_dma_init_domain);
/**
- * dma_direction_to_prot - Translate DMA API directions to IOMMU API page flags
+ * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
+ * page flags.
* @dir: Direction of DMA transfer
* @coherent: Is the DMA master cache-coherent?
+ * @attrs: DMA attributes for the mapping
*
* Return: corresponding IOMMU API page protection flags
*/
-int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
+int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+ unsigned long attrs)
{
int prot = coherent ? IOMMU_CACHE : 0;
+ if (attrs & DMA_ATTR_PRIVILEGED)
+ prot |= IOMMU_PRIV;
+
switch (dir) {
case DMA_BIDIRECTIONAL:
return prot | IOMMU_READ | IOMMU_WRITE;
@@ -204,19 +287,28 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
}
static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size,
- dma_addr_t dma_limit)
+ dma_addr_t dma_limit, struct device *dev)
{
struct iova_domain *iovad = cookie_iovad(domain);
unsigned long shift = iova_shift(iovad);
unsigned long length = iova_align(iovad, size) >> shift;
+ struct iova *iova = NULL;
if (domain->geometry.force_aperture)
dma_limit = min(dma_limit, domain->geometry.aperture_end);
+
+ /* Try to get PCI devices a SAC address */
+ if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
+ iova = alloc_iova(iovad, length, DMA_BIT_MASK(32) >> shift,
+ true);
/*
* Enforce size-alignment to be safe - there could perhaps be an
* attribute to control this per-device, or at least per-domain...
*/
- return alloc_iova(iovad, length, dma_limit >> shift, true);
+ if (!iova)
+ iova = alloc_iova(iovad, length, dma_limit >> shift, true);
+
+ return iova;
}
/* The IOVA allocator knows what we mapped, so just unmap whatever that was */
@@ -369,7 +461,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
if (!pages)
return NULL;
- iova = __alloc_iova(domain, size, dev->coherent_dma_mask);
+ iova = __alloc_iova(domain, size, dev->coherent_dma_mask, dev);
if (!iova)
goto out_free_pages;
@@ -440,7 +532,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
struct iova_domain *iovad = cookie_iovad(domain);
size_t iova_off = iova_offset(iovad, phys);
size_t len = iova_align(iovad, size + iova_off);
- struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev));
+ struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev), dev);
if (!iova)
return DMA_ERROR_CODE;
@@ -598,7 +690,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
prev = s;
}
- iova = __alloc_iova(domain, iova_len, dma_get_mask(dev));
+ iova = __alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
if (!iova)
goto out_restore_sg;
@@ -633,7 +725,7 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
return __iommu_dma_map(dev, phys, size,
- dma_direction_to_prot(dir, false) | IOMMU_MMIO);
+ dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
}
void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -642,16 +734,6 @@ void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
}
-int iommu_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * 'Special' IOMMUs which don't have the same addressing capability
- * as the CPU will have to wait until we have some way to query that
- * before they'll be able to use this framework.
- */
- return 1;
-}
-
int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return dma_addr == DMA_ERROR_CODE;
@@ -662,11 +744,12 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
{
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iommu_dma_msi_page *msi_page;
- struct iova_domain *iovad = &cookie->iovad;
+ struct iova_domain *iovad = cookie_iovad(domain);
struct iova *iova;
int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+ size_t size = cookie_msi_granule(cookie);
- msi_addr &= ~(phys_addr_t)iova_mask(iovad);
+ msi_addr &= ~(phys_addr_t)(size - 1);
list_for_each_entry(msi_page, &cookie->msi_page_list, list)
if (msi_page->phys == msi_addr)
return msi_page;
@@ -675,13 +758,18 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
if (!msi_page)
return NULL;
- iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev));
- if (!iova)
- goto out_free_page;
-
msi_page->phys = msi_addr;
- msi_page->iova = iova_dma_addr(iovad, iova);
- if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot))
+ if (iovad) {
+ iova = __alloc_iova(domain, size, dma_get_mask(dev), dev);
+ if (!iova)
+ goto out_free_page;
+ msi_page->iova = iova_dma_addr(iovad, iova);
+ } else {
+ msi_page->iova = cookie->msi_iova;
+ cookie->msi_iova += size;
+ }
+
+ if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
goto out_free_iova;
INIT_LIST_HEAD(&msi_page->list);
@@ -689,7 +777,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
return msi_page;
out_free_iova:
- __free_iova(iovad, iova);
+ if (iovad)
+ __free_iova(iovad, iova);
+ else
+ cookie->msi_iova -= size;
out_free_page:
kfree(msi_page);
return NULL;
@@ -730,7 +821,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
msg->data = ~0U;
} else {
msg->address_hi = upper_32_bits(msi_page->iova);
- msg->address_lo &= iova_mask(&cookie->iovad);
+ msg->address_lo &= cookie_msi_granule(cookie) - 1;
msg->address_lo += lower_32_bits(msi_page->iova);
}
}
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index fc13146f8d16..d9c0decfc91a 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -905,8 +905,10 @@ int __init detect_intel_iommu(void)
x86_init.iommu.iommu_init = intel_iommu_init;
#endif
- acpi_put_table(dmar_tbl);
- dmar_tbl = NULL;
+ if (dmar_tbl) {
+ acpi_put_table(dmar_tbl);
+ dmar_tbl = NULL;
+ }
up_write(&dmar_global_lock);
return ret ? 1 : -ENODEV;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 778ecccd7a29..a7e0821c9967 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -383,13 +383,14 @@ static void show_fault_information(struct sysmmu_drvdata *data,
{
sysmmu_pte_t *ent;
- dev_err(data->sysmmu, "%s FAULT occurred at %#x (page table base: %pa)\n",
- finfo->name, fault_addr, &data->pgtable);
+ dev_err(data->sysmmu, "%s: %s FAULT occurred at %#x\n",
+ dev_name(data->master), finfo->name, fault_addr);
+ dev_dbg(data->sysmmu, "Page table base: %pa\n", &data->pgtable);
ent = section_entry(phys_to_virt(data->pgtable), fault_addr);
- dev_err(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
+ dev_dbg(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
if (lv1ent_page(ent)) {
ent = page_entry(ent, fault_addr);
- dev_err(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
+ dev_dbg(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
}
}
@@ -755,6 +756,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
DMA_TO_DEVICE);
/* For mapping page table entries we rely on dma == phys */
BUG_ON(handle != virt_to_phys(domain->pgtable));
+ if (dma_mapping_error(dma_dev, handle))
+ goto err_lv2ent;
spin_lock_init(&domain->lock);
spin_lock_init(&domain->pgtablelock);
@@ -766,6 +769,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
return &domain->domain;
+err_lv2ent:
+ free_pages((unsigned long)domain->lv2entcnt, 1);
err_counter:
free_pages((unsigned long)domain->pgtable, 2);
err_dma_cookie:
@@ -909,6 +914,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
}
if (lv1ent_fault(sent)) {
+ dma_addr_t handle;
sysmmu_pte_t *pent;
bool need_flush_flpd_cache = lv1ent_zero(sent);
@@ -920,7 +926,12 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
update_pte(sent, mk_lv1ent_page(virt_to_phys(pent)));
kmemleak_ignore(pent);
*pgcounter = NUM_LV2ENTRIES;
- dma_map_single(dma_dev, pent, LV2TABLE_SIZE, DMA_TO_DEVICE);
+ handle = dma_map_single(dma_dev, pent, LV2TABLE_SIZE,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dma_dev, handle)) {
+ kmem_cache_free(lv2table_kmem_cache, pent);
+ return ERR_PTR(-EADDRINUSE);
+ }
/*
* If pre-fetched SLPD is a faulty SLPD in zero_l2_table,
@@ -1243,9 +1254,21 @@ static int exynos_iommu_add_device(struct device *dev)
static void exynos_iommu_remove_device(struct device *dev)
{
+ struct exynos_iommu_owner *owner = dev->archdata.iommu;
+
if (!has_sysmmu(dev))
return;
+ if (owner->domain) {
+ struct iommu_group *group = iommu_group_get(dev);
+
+ if (group) {
+ WARN_ON(owner->domain !=
+ iommu_group_default_domain(group));
+ exynos_iommu_detach_device(owner->domain, dev);
+ iommu_group_put(group);
+ }
+ }
iommu_group_remove_device(dev);
}
@@ -1254,7 +1277,7 @@ static int exynos_iommu_of_xlate(struct device *dev,
{
struct exynos_iommu_owner *owner = dev->archdata.iommu;
struct platform_device *sysmmu = of_find_device_by_node(spec->np);
- struct sysmmu_drvdata *data;
+ struct sysmmu_drvdata *data, *entry;
if (!sysmmu)
return -ENODEV;
@@ -1273,6 +1296,10 @@ static int exynos_iommu_of_xlate(struct device *dev,
dev->archdata.iommu = owner;
}
+ list_for_each_entry(entry, &owner->controllers, owner_node)
+ if (entry == data)
+ return 0;
+
list_add_tail(&data->owner_node, &owner->controllers);
data->master = dev;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index cbe7c49b7565..f5e02f8e7371 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -440,6 +440,7 @@ struct dmar_rmrr_unit {
u64 end_address; /* reserved end address */
struct dmar_dev_scope *devices; /* target devices */
int devices_cnt; /* target device count */
+ struct iommu_resv_region *resv; /* reserved region handle */
};
struct dmar_atsr_unit {
@@ -1144,7 +1145,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
if (!dma_pte_present(pte) || dma_pte_superpage(pte))
goto next;
- level_pfn = pfn & level_mask(level - 1);
+ level_pfn = pfn & level_mask(level);
level_pte = phys_to_virt(dma_pte_addr(pte));
if (level > 2)
@@ -2037,6 +2038,25 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
if (context_present(context))
goto out_unlock;
+ /*
+ * For kdump cases, old valid entries may be cached due to the
+ * in-flight DMA and copied pgtable, but there is no unmapping
+ * behaviour for them, thus we need an explicit cache flush for
+ * the newly-mapped device. For kdump, at this point, the device
+ * is supposed to finish reset at its driver probe stage, so no
+ * in-flight DMA will exist, and we don't need to worry anymore
+ * hereafter.
+ */
+ if (context_copied(context)) {
+ u16 did_old = context_domain_id(context);
+
+ if (did_old >= 0 && did_old < cap_ndoms(iommu->cap))
+ iommu->flush.flush_context(iommu, did_old,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ }
+
pgd = domain->pgd;
context_clear_entry(context);
@@ -3306,13 +3326,14 @@ static int __init init_dmars(void)
iommu_identity_mapping |= IDENTMAP_GFX;
#endif
+ check_tylersburg_isoch();
+
if (iommu_identity_mapping) {
ret = si_domain_init(hw_pass_through);
if (ret)
goto free_iommu;
}
- check_tylersburg_isoch();
/*
* If we copied translations from a previous kernel in the kdump
@@ -4227,27 +4248,40 @@ static inline void init_iommu_pm_ops(void) {}
int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
{
struct acpi_dmar_reserved_memory *rmrr;
+ int prot = DMA_PTE_READ|DMA_PTE_WRITE;
struct dmar_rmrr_unit *rmrru;
+ size_t length;
rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
if (!rmrru)
- return -ENOMEM;
+ goto out;
rmrru->hdr = header;
rmrr = (struct acpi_dmar_reserved_memory *)header;
rmrru->base_address = rmrr->base_address;
rmrru->end_address = rmrr->end_address;
+
+ length = rmrr->end_address - rmrr->base_address + 1;
+ rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot,
+ IOMMU_RESV_DIRECT);
+ if (!rmrru->resv)
+ goto free_rmrru;
+
rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
((void *)rmrr) + rmrr->header.length,
&rmrru->devices_cnt);
- if (rmrru->devices_cnt && rmrru->devices == NULL) {
- kfree(rmrru);
- return -ENOMEM;
- }
+ if (rmrru->devices_cnt && rmrru->devices == NULL)
+ goto free_all;
list_add(&rmrru->list, &dmar_rmrr_units);
return 0;
+free_all:
+ kfree(rmrru->resv);
+free_rmrru:
+ kfree(rmrru);
+out:
+ return -ENOMEM;
}
static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
@@ -4461,6 +4495,7 @@ static void intel_iommu_free_dmars(void)
list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
list_del(&rmrru->list);
dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
+ kfree(rmrru->resv);
kfree(rmrru);
}
@@ -5187,7 +5222,65 @@ static void intel_iommu_remove_device(struct device *dev)
iommu_device_unlink(&iommu->iommu, dev);
}
+static void intel_iommu_get_resv_regions(struct device *device,
+ struct list_head *head)
+{
+ struct iommu_resv_region *reg;
+ struct dmar_rmrr_unit *rmrr;
+ struct device *i_dev;
+ int i;
+
+ rcu_read_lock();
+ for_each_rmrr_units(rmrr) {
+ for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+ i, i_dev) {
+ if (i_dev != device)
+ continue;
+
+ list_add_tail(&rmrr->resv->list, head);
+ }
+ }
+ rcu_read_unlock();
+
+ reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
+ IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
+ 0, IOMMU_RESV_RESERVED);
+ if (!reg)
+ return;
+ list_add_tail(&reg->list, head);
+}
+
+static void intel_iommu_put_resv_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_resv_region *entry, *next;
+
+ list_for_each_entry_safe(entry, next, head, list) {
+ if (entry->type == IOMMU_RESV_RESERVED)
+ kfree(entry);
+ }
+}
+
#ifdef CONFIG_INTEL_IOMMU_SVM
+#define MAX_NR_PASID_BITS (20)
+static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
+{
+ /*
+ * Convert ecap_pss to extend context entry pts encoding, also
+ * respect the soft pasid_max value set by the iommu.
+ * - number of PASID bits = ecap_pss + 1
+ * - number of PASID table entries = 2^(pts + 5)
+ * Therefore, pts = ecap_pss - 4
+ * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15
+ */
+ if (ecap_pss(iommu->ecap) < 5)
+ return 0;
+
+ /* pasid_max is encoded as actual number of entries not the bits */
+ return find_first_bit((unsigned long *)&iommu->pasid_max,
+ MAX_NR_PASID_BITS) - 5;
+}
+
int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
{
struct device_domain_info *info;
@@ -5220,7 +5313,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
if (!(ctx_lo & CONTEXT_PASIDE)) {
context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
- context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap);
+ context[1].lo = (u64)virt_to_phys(iommu->pasid_table) |
+ intel_iommu_get_pts(iommu);
+
wmb();
/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
* extended to permit requests-with-PASID if the PASIDE bit
@@ -5296,19 +5391,21 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
#endif /* CONFIG_INTEL_IOMMU_SVM */
const struct iommu_ops intel_iommu_ops = {
- .capable = intel_iommu_capable,
- .domain_alloc = intel_iommu_domain_alloc,
- .domain_free = intel_iommu_domain_free,
- .attach_dev = intel_iommu_attach_device,
- .detach_dev = intel_iommu_detach_device,
- .map = intel_iommu_map,
- .unmap = intel_iommu_unmap,
- .map_sg = default_iommu_map_sg,
- .iova_to_phys = intel_iommu_iova_to_phys,
- .add_device = intel_iommu_add_device,
- .remove_device = intel_iommu_remove_device,
- .device_group = pci_device_group,
- .pgsize_bitmap = INTEL_IOMMU_PGSIZES,
+ .capable = intel_iommu_capable,
+ .domain_alloc = intel_iommu_domain_alloc,
+ .domain_free = intel_iommu_domain_free,
+ .attach_dev = intel_iommu_attach_device,
+ .detach_dev = intel_iommu_detach_device,
+ .map = intel_iommu_map,
+ .unmap = intel_iommu_unmap,
+ .map_sg = default_iommu_map_sg,
+ .iova_to_phys = intel_iommu_iova_to_phys,
+ .add_device = intel_iommu_add_device,
+ .remove_device = intel_iommu_remove_device,
+ .get_resv_regions = intel_iommu_get_resv_regions,
+ .put_resv_regions = intel_iommu_put_resv_regions,
+ .device_group = pci_device_group,
+ .pgsize_bitmap = INTEL_IOMMU_PGSIZES,
};
static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 0769276c0537..1c049e2e12bf 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -265,7 +265,9 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
if (!(prot & IOMMU_MMIO))
pte |= ARM_V7S_ATTR_TEX(1);
if (ap) {
- pte |= ARM_V7S_PTE_AF | ARM_V7S_PTE_AP_UNPRIV;
+ pte |= ARM_V7S_PTE_AF;
+ if (!(prot & IOMMU_PRIV))
+ pte |= ARM_V7S_PTE_AP_UNPRIV;
if (!(prot & IOMMU_WRITE))
pte |= ARM_V7S_PTE_AP_RDONLY;
}
@@ -288,6 +290,8 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl)
if (!(attr & ARM_V7S_PTE_AP_RDONLY))
prot |= IOMMU_WRITE;
+ if (!(attr & ARM_V7S_PTE_AP_UNPRIV))
+ prot |= IOMMU_PRIV;
if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
prot |= IOMMU_MMIO;
else if (pte & ARM_V7S_ATTR_C)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a40ce3406fef..feacc54bec68 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -350,11 +350,14 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
if (data->iop.fmt == ARM_64_LPAE_S1 ||
data->iop.fmt == ARM_32_LPAE_S1) {
- pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG;
+ pte = ARM_LPAE_PTE_nG;
if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
pte |= ARM_LPAE_PTE_AP_RDONLY;
+ if (!(prot & IOMMU_PRIV))
+ pte |= ARM_LPAE_PTE_AP_UNPRIV;
+
if (prot & IOMMU_MMIO)
pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 162d865e2e29..8ea14f41a979 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -68,6 +68,12 @@ struct iommu_group_attribute {
const char *buf, size_t count);
};
+static const char * const iommu_group_resv_type_string[] = {
+ [IOMMU_RESV_DIRECT] = "direct",
+ [IOMMU_RESV_RESERVED] = "reserved",
+ [IOMMU_RESV_MSI] = "msi",
+};
+
#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \
struct iommu_group_attribute iommu_group_attr_##_name = \
__ATTR(_name, _mode, _show, _store)
@@ -152,8 +158,131 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
return sprintf(buf, "%s\n", group->name);
}
+/**
+ * iommu_insert_resv_region - Insert a new region in the
+ * list of reserved regions.
+ * @new: new region to insert
+ * @regions: list of regions
+ *
+ * The new element is sorted by address with respect to the other
+ * regions of the same type. In case it overlaps with another
+ * region of the same type, regions are merged. In case it
+ * overlaps with another region of different type, regions are
+ * not merged.
+ */
+static int iommu_insert_resv_region(struct iommu_resv_region *new,
+ struct list_head *regions)
+{
+ struct iommu_resv_region *region;
+ phys_addr_t start = new->start;
+ phys_addr_t end = new->start + new->length - 1;
+ struct list_head *pos = regions->next;
+
+ while (pos != regions) {
+ struct iommu_resv_region *entry =
+ list_entry(pos, struct iommu_resv_region, list);
+ phys_addr_t a = entry->start;
+ phys_addr_t b = entry->start + entry->length - 1;
+ int type = entry->type;
+
+ if (end < a) {
+ goto insert;
+ } else if (start > b) {
+ pos = pos->next;
+ } else if ((start >= a) && (end <= b)) {
+ if (new->type == type)
+ goto done;
+ else
+ pos = pos->next;
+ } else {
+ if (new->type == type) {
+ phys_addr_t new_start = min(a, start);
+ phys_addr_t new_end = max(b, end);
+
+ list_del(&entry->list);
+ entry->start = new_start;
+ entry->length = new_end - new_start + 1;
+ iommu_insert_resv_region(entry, regions);
+ } else {
+ pos = pos->next;
+ }
+ }
+ }
+insert:
+ region = iommu_alloc_resv_region(new->start, new->length,
+ new->prot, new->type);
+ if (!region)
+ return -ENOMEM;
+
+ list_add_tail(&region->list, pos);
+done:
+ return 0;
+}
+
+static int
+iommu_insert_device_resv_regions(struct list_head *dev_resv_regions,
+ struct list_head *group_resv_regions)
+{
+ struct iommu_resv_region *entry;
+ int ret = 0;
+
+ list_for_each_entry(entry, dev_resv_regions, list) {
+ ret = iommu_insert_resv_region(entry, group_resv_regions);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
+int iommu_get_group_resv_regions(struct iommu_group *group,
+ struct list_head *head)
+{
+ struct group_device *device;
+ int ret = 0;
+
+ mutex_lock(&group->mutex);
+ list_for_each_entry(device, &group->devices, list) {
+ struct list_head dev_resv_regions;
+
+ INIT_LIST_HEAD(&dev_resv_regions);
+ iommu_get_resv_regions(device->dev, &dev_resv_regions);
+ ret = iommu_insert_device_resv_regions(&dev_resv_regions, head);
+ iommu_put_resv_regions(device->dev, &dev_resv_regions);
+ if (ret)
+ break;
+ }
+ mutex_unlock(&group->mutex);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions);
+
+static ssize_t iommu_group_show_resv_regions(struct iommu_group *group,
+ char *buf)
+{
+ struct iommu_resv_region *region, *next;
+ struct list_head group_resv_regions;
+ char *str = buf;
+
+ INIT_LIST_HEAD(&group_resv_regions);
+ iommu_get_group_resv_regions(group, &group_resv_regions);
+
+ list_for_each_entry_safe(region, next, &group_resv_regions, list) {
+ str += sprintf(str, "0x%016llx 0x%016llx %s\n",
+ (long long int)region->start,
+ (long long int)(region->start +
+ region->length - 1),
+ iommu_group_resv_type_string[region->type]);
+ kfree(region);
+ }
+
+ return (str - buf);
+}
+
static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);
+static IOMMU_GROUP_ATTR(reserved_regions, 0444,
+ iommu_group_show_resv_regions, NULL);
+
static void iommu_group_release(struct kobject *kobj)
{
struct iommu_group *group = to_iommu_group(kobj);
@@ -231,6 +360,11 @@ struct iommu_group *iommu_group_alloc(void)
*/
kobject_put(&group->kobj);
+ ret = iommu_group_create_file(group,
+ &iommu_group_attr_reserved_regions);
+ if (ret)
+ return ERR_PTR(ret);
+
pr_debug("Allocated group %d\n", group->id);
return group;
@@ -337,7 +471,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
struct device *dev)
{
struct iommu_domain *domain = group->default_domain;
- struct iommu_dm_region *entry;
+ struct iommu_resv_region *entry;
struct list_head mappings;
unsigned long pg_size;
int ret = 0;
@@ -350,18 +484,21 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
pg_size = 1UL << __ffs(domain->pgsize_bitmap);
INIT_LIST_HEAD(&mappings);
- iommu_get_dm_regions(dev, &mappings);
+ iommu_get_resv_regions(dev, &mappings);
/* We need to consider overlapping regions for different devices */
list_for_each_entry(entry, &mappings, list) {
dma_addr_t start, end, addr;
- if (domain->ops->apply_dm_region)
- domain->ops->apply_dm_region(dev, domain, entry);
+ if (domain->ops->apply_resv_region)
+ domain->ops->apply_resv_region(dev, domain, entry);
start = ALIGN(entry->start, pg_size);
end = ALIGN(entry->start + entry->length, pg_size);
+ if (entry->type != IOMMU_RESV_DIRECT)
+ continue;
+
for (addr = start; addr < end; addr += pg_size) {
phys_addr_t phys_addr;
@@ -377,7 +514,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
}
out:
- iommu_put_dm_regions(dev, &mappings);
+ iommu_put_resv_regions(dev, &mappings);
return ret;
}
@@ -1589,20 +1726,38 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
}
EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
-void iommu_get_dm_regions(struct device *dev, struct list_head *list)
+void iommu_get_resv_regions(struct device *dev, struct list_head *list)
{
const struct iommu_ops *ops = dev->bus->iommu_ops;
- if (ops && ops->get_dm_regions)
- ops->get_dm_regions(dev, list);
+ if (ops && ops->get_resv_regions)
+ ops->get_resv_regions(dev, list);
}
-void iommu_put_dm_regions(struct device *dev, struct list_head *list)
+void iommu_put_resv_regions(struct device *dev, struct list_head *list)
{
const struct iommu_ops *ops = dev->bus->iommu_ops;
- if (ops && ops->put_dm_regions)
- ops->put_dm_regions(dev, list);
+ if (ops && ops->put_resv_regions)
+ ops->put_resv_regions(dev, list);
+}
+
+struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
+ size_t length,
+ int prot, int type)
+{
+ struct iommu_resv_region *region;
+
+ region = kzalloc(sizeof(*region), GFP_KERNEL);
+ if (!region)
+ return NULL;
+
+ INIT_LIST_HEAD(&region->list);
+ region->start = start;
+ region->length = length;
+ region->prot = prot;
+ region->type = type;
+ return region;
}
/* Request that a device is direct mapped by the IOMMU */
@@ -1719,13 +1874,14 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
fwspec = krealloc(dev->iommu_fwspec, size, GFP_KERNEL);
if (!fwspec)
return -ENOMEM;
+
+ dev->iommu_fwspec = fwspec;
}
for (i = 0; i < num_ids; i++)
fwspec->ids[fwspec->num_ids + i] = ids[i];
fwspec->num_ids += num_ids;
- dev->iommu_fwspec = fwspec;
return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ace331da6459..b7e14ee863f9 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -313,6 +313,8 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
domain->cfg.ias = 32;
domain->cfg.oas = 40;
domain->cfg.tlb = &ipmmu_gather_ops;
+ domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
+ domain->io_domain.geometry.force_aperture = true;
/*
* TODO: Add support for coherent walk through CCI with DVM and remove
* cache handling. For now, delegate it to the io-pgtable code.
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 0f57ddc4ecc2..2683e9fc0dcf 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -127,7 +127,7 @@ static const struct iommu_ops
"iommu-map-mask", &iommu_spec.np, iommu_spec.args))
return NULL;
- ops = of_iommu_get_ops(iommu_spec.np);
+ ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode);
if (!ops || !ops->of_xlate ||
iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) ||
ops->of_xlate(&pdev->dev, &iommu_spec))
@@ -157,7 +157,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
"#iommu-cells", idx,
&iommu_spec)) {
np = iommu_spec.np;
- ops = of_iommu_get_ops(np);
+ ops = iommu_ops_from_fwnode(&np->fwnode);
if (!ops || !ops->of_xlate ||
iommu_fwspec_init(dev, &np->fwnode, ops) ||
OpenPOWER on IntegriCloud