summaryrefslogtreecommitdiff
path: root/drivers/iommu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu')
-rw-r--r--drivers/iommu/Kconfig25
-rw-r--r--drivers/iommu/amd_iommu.c54
-rw-r--r--drivers/iommu/amd_iommu_init.c8
-rw-r--r--drivers/iommu/amd_iommu_types.h6
-rw-r--r--drivers/iommu/arm-smmu-regs.h2
-rw-r--r--drivers/iommu/arm-smmu-v3.c355
-rw-r--r--drivers/iommu/arm-smmu.c11
-rw-r--r--drivers/iommu/dma-iommu.c47
-rw-r--r--drivers/iommu/dmar.c2
-rw-r--r--drivers/iommu/intel-iommu.c586
-rw-r--r--drivers/iommu/intel-pasid.c4
-rw-r--r--drivers/iommu/intel-svm.c19
-rw-r--r--drivers/iommu/intel_irq_remapping.c9
-rw-r--r--drivers/iommu/io-pgtable-arm.c91
-rw-r--r--drivers/iommu/io-pgtable.c1
-rw-r--r--drivers/iommu/iommu.c211
-rw-r--r--drivers/iommu/msm_iommu.c2
-rw-r--r--drivers/iommu/mtk_iommu.c8
-rw-r--r--drivers/iommu/tegra-smmu.c41
19 files changed, 1140 insertions, 342 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index eb1c8cd243f9..e559e43c8ac2 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -360,6 +360,31 @@ config ARM_SMMU
Say Y here if your SoC includes an IOMMU device implementing
the ARM SMMU architecture.
+config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT
+ bool "Default to disabling bypass on ARM SMMU v1 and v2"
+ depends on ARM_SMMU
+ default y
+ help
+ Say Y here to (by default) 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.
+
+ Any old kernels that existed before this KConfig was
+ introduced would default to _allowing_ bypass (AKA the
+ equivalent of NO for this config). However the default for
+ this option is YES because the old behavior is insecure.
+
+ There are few reasons to allow unmatched stream bypass, and
+ even fewer good ones. If saying YES here breaks your board
+ you should work on fixing your board. This KConfig option
+ is expected to be removed in the future and we'll simply
+ hardcode the bypass disable in the code.
+
+ NOTE: the kernel command line parameter
+ 'arm-smmu.disable_bypass' will continue to override this
+ config.
+
config ARM_SMMU_V3
bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
depends on ARM64
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index f7cdd2ab7f11..09c9e45f7fa2 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -165,7 +165,7 @@ static inline u16 get_pci_device_id(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
- return PCI_DEVID(pdev->bus->number, pdev->devfn);
+ return pci_dev_id(pdev);
}
static inline int get_acpihid_device_id(struct device *dev,
@@ -1723,31 +1723,6 @@ static void dma_ops_free_iova(struct dma_ops_domain *dma_dom,
*
****************************************************************************/
-/*
- * This function adds a protection domain to the global protection domain list
- */
-static void add_domain_to_list(struct protection_domain *domain)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&amd_iommu_pd_lock, flags);
- list_add(&domain->list, &amd_iommu_pd_list);
- spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
-}
-
-/*
- * This function removes a protection domain to the global
- * protection domain list
- */
-static void del_domain_from_list(struct protection_domain *domain)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&amd_iommu_pd_lock, flags);
- list_del(&domain->list);
- spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
-}
-
static u16 domain_id_alloc(void)
{
int id;
@@ -1838,8 +1813,6 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
if (!dom)
return;
- del_domain_from_list(&dom->domain);
-
put_iova_domain(&dom->iovad);
free_pagetable(&dom->domain);
@@ -1880,8 +1853,6 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
/* Initialize reserved ranges */
copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad);
- add_domain_to_list(&dma_dom->domain);
-
return dma_dom;
free_dma_dom:
@@ -2122,23 +2093,6 @@ out_err:
return ret;
}
-/* FIXME: Move this to PCI code */
-#define PCI_PRI_TLP_OFF (1 << 15)
-
-static bool pci_pri_tlp_required(struct pci_dev *pdev)
-{
- u16 status;
- int pos;
-
- pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
- if (!pos)
- return false;
-
- pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
-
- return (status & PCI_PRI_TLP_OFF) ? true : false;
-}
-
/*
* If a device is not yet associated with a domain, this function makes the
* device visible in the domain
@@ -2167,7 +2121,7 @@ static int attach_device(struct device *dev,
dev_data->ats.enabled = true;
dev_data->ats.qdep = pci_ats_queue_depth(pdev);
- dev_data->pri_tlp = pci_pri_tlp_required(pdev);
+ dev_data->pri_tlp = pci_prg_resp_pasid_required(pdev);
}
} else if (amd_iommu_iotlb_sup &&
pci_enable_ats(pdev, PAGE_SHIFT) == 0) {
@@ -2897,8 +2851,6 @@ static void protection_domain_free(struct protection_domain *domain)
if (!domain)
return;
- del_domain_from_list(domain);
-
if (domain->id)
domain_id_free(domain->id);
@@ -2928,8 +2880,6 @@ static struct protection_domain *protection_domain_alloc(void)
if (protection_domain_init(domain))
goto out_err;
- add_domain_to_list(domain);
-
return domain;
out_err:
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index ff40ba758cf3..f977df90d2a4 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -189,12 +189,6 @@ static bool amd_iommu_pc_present __read_mostly;
bool amd_iommu_force_isolation __read_mostly;
/*
- * List of protection domains - used during resume
- */
-LIST_HEAD(amd_iommu_pd_list);
-spinlock_t amd_iommu_pd_lock;
-
-/*
* Pointer to the device table which is shared by all AMD IOMMUs
* it is indexed by the PCI device id or the HT unit id and contains
* information about the domain the device belongs to as well as the
@@ -2526,8 +2520,6 @@ static int __init early_amd_iommu_init(void)
*/
__set_bit(0, amd_iommu_pd_alloc_bitmap);
- spin_lock_init(&amd_iommu_pd_lock);
-
/*
* now the data structures are allocated and basically initialized
* start the real acpi table scan
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 87965e4d9647..85c488b8daea 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -675,12 +675,6 @@ extern struct list_head amd_iommu_list;
extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
/*
- * Declarations for the global list of all protection domains
- */
-extern spinlock_t amd_iommu_pd_lock;
-extern struct list_head amd_iommu_pd_list;
-
-/*
* Structure defining one entry in the device table
*/
struct dev_table_entry {
diff --git a/drivers/iommu/arm-smmu-regs.h b/drivers/iommu/arm-smmu-regs.h
index a1226e4ab5f8..e9132a926761 100644
--- a/drivers/iommu/arm-smmu-regs.h
+++ b/drivers/iommu/arm-smmu-regs.h
@@ -147,6 +147,8 @@ enum arm_smmu_s2cr_privcfg {
#define CBAR_IRPTNDX_SHIFT 24
#define CBAR_IRPTNDX_MASK 0xff
+#define ARM_SMMU_GR1_CBFRSYNRA(n) (0x400 + ((n) << 2))
+
#define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2))
#define CBA2R_RW64_32BIT (0 << 0)
#define CBA2R_RW64_64BIT (1 << 0)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index d3880010c6cf..4d5a694f02c2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -29,6 +29,7 @@
#include <linux/of_iommu.h>
#include <linux/of_platform.h>
#include <linux/pci.h>
+#include <linux/pci-ats.h>
#include <linux/platform_device.h>
#include <linux/amba/bus.h>
@@ -86,6 +87,7 @@
#define IDR5_VAX_52_BIT 1
#define ARM_SMMU_CR0 0x20
+#define CR0_ATSCHK (1 << 4)
#define CR0_CMDQEN (1 << 3)
#define CR0_EVTQEN (1 << 2)
#define CR0_PRIQEN (1 << 1)
@@ -294,6 +296,7 @@
#define CMDQ_ERR_CERROR_NONE_IDX 0
#define CMDQ_ERR_CERROR_ILL_IDX 1
#define CMDQ_ERR_CERROR_ABT_IDX 2
+#define CMDQ_ERR_CERROR_ATC_INV_IDX 3
#define CMDQ_0_OP GENMASK_ULL(7, 0)
#define CMDQ_0_SSV (1UL << 11)
@@ -312,6 +315,12 @@
#define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12)
#define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12)
+#define CMDQ_ATC_0_SSID GENMASK_ULL(31, 12)
+#define CMDQ_ATC_0_SID GENMASK_ULL(63, 32)
+#define CMDQ_ATC_0_GLOBAL (1UL << 9)
+#define CMDQ_ATC_1_SIZE GENMASK_ULL(5, 0)
+#define CMDQ_ATC_1_ADDR_MASK GENMASK_ULL(63, 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)
@@ -433,6 +442,16 @@ struct arm_smmu_cmdq_ent {
u64 addr;
} tlbi;
+ #define CMDQ_OP_ATC_INV 0x40
+ #define ATC_INV_SIZE_ALL 52
+ struct {
+ u32 sid;
+ u32 ssid;
+ u64 addr;
+ u8 size;
+ bool global;
+ } atc;
+
#define CMDQ_OP_PRI_RESP 0x41
struct {
u32 sid;
@@ -505,19 +524,6 @@ struct arm_smmu_s2_cfg {
u64 vtcr;
};
-struct arm_smmu_strtab_ent {
- /*
- * An STE is "assigned" if the master emitting the corresponding SID
- * is attached to a domain. The behaviour of an unassigned STE is
- * determined by the disable_bypass parameter, whereas an assigned
- * STE behaves according to s1_cfg/s2_cfg, which themselves are
- * configured according to the domain type.
- */
- bool assigned;
- struct arm_smmu_s1_cfg *s1_cfg;
- struct arm_smmu_s2_cfg *s2_cfg;
-};
-
struct arm_smmu_strtab_cfg {
__le64 *strtab;
dma_addr_t strtab_dma;
@@ -591,9 +597,14 @@ struct arm_smmu_device {
};
/* SMMU private data for each master */
-struct arm_smmu_master_data {
+struct arm_smmu_master {
struct arm_smmu_device *smmu;
- struct arm_smmu_strtab_ent ste;
+ struct device *dev;
+ struct arm_smmu_domain *domain;
+ struct list_head domain_head;
+ u32 *sids;
+ unsigned int num_sids;
+ bool ats_enabled :1;
};
/* SMMU private data for an IOMMU domain */
@@ -618,6 +629,9 @@ struct arm_smmu_domain {
};
struct iommu_domain domain;
+
+ struct list_head devices;
+ spinlock_t devices_lock;
};
struct arm_smmu_option_prop {
@@ -820,6 +834,14 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
case CMDQ_OP_TLBI_S12_VMALL:
cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
break;
+ case CMDQ_OP_ATC_INV:
+ cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
+ cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global);
+ cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SSID, ent->atc.ssid);
+ cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SID, ent->atc.sid);
+ cmd[1] |= FIELD_PREP(CMDQ_ATC_1_SIZE, ent->atc.size);
+ cmd[1] |= ent->atc.addr & CMDQ_ATC_1_ADDR_MASK;
+ break;
case CMDQ_OP_PRI_RESP:
cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid);
@@ -864,6 +886,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
[CMDQ_ERR_CERROR_NONE_IDX] = "No error",
[CMDQ_ERR_CERROR_ILL_IDX] = "Illegal command",
[CMDQ_ERR_CERROR_ABT_IDX] = "Abort on command fetch",
+ [CMDQ_ERR_CERROR_ATC_INV_IDX] = "ATC invalidate timeout",
};
int i;
@@ -883,6 +906,14 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
dev_err(smmu->dev, "retrying command fetch\n");
case CMDQ_ERR_CERROR_NONE_IDX:
return;
+ case CMDQ_ERR_CERROR_ATC_INV_IDX:
+ /*
+ * ATC Invalidation Completion timeout. CONS is still pointing
+ * at the CMD_SYNC. Attempt to complete other pending commands
+ * by repeating the CMD_SYNC, though we might well end up back
+ * here since the ATC invalidation may still be pending.
+ */
+ return;
case CMDQ_ERR_CERROR_ILL_IDX:
/* Fallthrough */
default:
@@ -999,7 +1030,7 @@ static int __arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
return ret;
}
-static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
{
int ret;
bool msi = (smmu->features & ARM_SMMU_FEAT_MSI) &&
@@ -1009,6 +1040,7 @@ static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
: __arm_smmu_cmdq_issue_sync(smmu);
if (ret)
dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
+ return ret;
}
/* Context descriptor manipulation functions */
@@ -1025,7 +1057,6 @@ static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
val |= ARM_SMMU_TCR2CD(tcr, EPD0);
val |= ARM_SMMU_TCR2CD(tcr, EPD1);
val |= ARM_SMMU_TCR2CD(tcr, IPS);
- val |= ARM_SMMU_TCR2CD(tcr, TBI0);
return val;
}
@@ -1085,8 +1116,8 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
arm_smmu_cmdq_issue_sync(smmu);
}
-static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
- __le64 *dst, struct arm_smmu_strtab_ent *ste)
+static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
+ __le64 *dst)
{
/*
* This is hideously complicated, but we only really care about
@@ -1106,6 +1137,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
*/
u64 val = le64_to_cpu(dst[0]);
bool ste_live = false;
+ struct arm_smmu_device *smmu = NULL;
+ struct arm_smmu_s1_cfg *s1_cfg = NULL;
+ struct arm_smmu_s2_cfg *s2_cfg = NULL;
+ struct arm_smmu_domain *smmu_domain = NULL;
struct arm_smmu_cmdq_ent prefetch_cmd = {
.opcode = CMDQ_OP_PREFETCH_CFG,
.prefetch = {
@@ -1113,6 +1148,25 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
},
};
+ if (master) {
+ smmu_domain = master->domain;
+ smmu = master->smmu;
+ }
+
+ if (smmu_domain) {
+ switch (smmu_domain->stage) {
+ case ARM_SMMU_DOMAIN_S1:
+ s1_cfg = &smmu_domain->s1_cfg;
+ break;
+ case ARM_SMMU_DOMAIN_S2:
+ case ARM_SMMU_DOMAIN_NESTED:
+ s2_cfg = &smmu_domain->s2_cfg;
+ break;
+ default:
+ break;
+ }
+ }
+
if (val & STRTAB_STE_0_V) {
switch (FIELD_GET(STRTAB_STE_0_CFG, val)) {
case STRTAB_STE_0_CFG_BYPASS:
@@ -1133,8 +1187,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
val = STRTAB_STE_0_V;
/* Bypass/fault */
- if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
- if (!ste->assigned && disable_bypass)
+ if (!smmu_domain || !(s1_cfg || s2_cfg)) {
+ if (!smmu_domain && disable_bypass)
val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT);
else
val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
@@ -1152,41 +1206,42 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
return;
}
- if (ste->s1_cfg) {
+ if (s1_cfg) {
BUG_ON(ste_live);
dst[1] = cpu_to_le64(
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
- FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS) |
-#endif
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) |
+ val |= (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) {
+ if (s2_cfg) {
BUG_ON(ste_live);
dst[2] = cpu_to_le64(
- FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) |
- FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) |
+ FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
+ FIELD_PREP(STRTAB_STE_2_VTCR, 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);
+ dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
}
+ if (master->ats_enabled)
+ dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+ STRTAB_STE_1_EATS_TRANS));
+
arm_smmu_sync_ste_for_sid(smmu, sid);
dst[0] = cpu_to_le64(val);
arm_smmu_sync_ste_for_sid(smmu, sid);
@@ -1199,10 +1254,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
{
unsigned int i;
- struct arm_smmu_strtab_ent ste = { .assigned = false };
for (i = 0; i < nent; ++i) {
- arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
+ arm_smmu_write_strtab_ent(NULL, -1, strtab);
strtab += STRTAB_STE_DWORDS;
}
}
@@ -1390,6 +1444,96 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
return IRQ_WAKE_THREAD;
}
+static void
+arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size,
+ struct arm_smmu_cmdq_ent *cmd)
+{
+ size_t log2_span;
+ size_t span_mask;
+ /* ATC invalidates are always on 4096-bytes pages */
+ size_t inval_grain_shift = 12;
+ unsigned long page_start, page_end;
+
+ *cmd = (struct arm_smmu_cmdq_ent) {
+ .opcode = CMDQ_OP_ATC_INV,
+ .substream_valid = !!ssid,
+ .atc.ssid = ssid,
+ };
+
+ if (!size) {
+ cmd->atc.size = ATC_INV_SIZE_ALL;
+ return;
+ }
+
+ page_start = iova >> inval_grain_shift;
+ page_end = (iova + size - 1) >> inval_grain_shift;
+
+ /*
+ * In an ATS Invalidate Request, the address must be aligned on the
+ * range size, which must be a power of two number of page sizes. We
+ * thus have to choose between grossly over-invalidating the region, or
+ * splitting the invalidation into multiple commands. For simplicity
+ * we'll go with the first solution, but should refine it in the future
+ * if multiple commands are shown to be more efficient.
+ *
+ * Find the smallest power of two that covers the range. The most
+ * significant differing bit between the start and end addresses,
+ * fls(start ^ end), indicates the required span. For example:
+ *
+ * We want to invalidate pages [8; 11]. This is already the ideal range:
+ * x = 0b1000 ^ 0b1011 = 0b11
+ * span = 1 << fls(x) = 4
+ *
+ * To invalidate pages [7; 10], we need to invalidate [0; 15]:
+ * x = 0b0111 ^ 0b1010 = 0b1101
+ * span = 1 << fls(x) = 16
+ */
+ log2_span = fls_long(page_start ^ page_end);
+ span_mask = (1ULL << log2_span) - 1;
+
+ page_start &= ~span_mask;
+
+ cmd->atc.addr = page_start << inval_grain_shift;
+ cmd->atc.size = log2_span;
+}
+
+static int arm_smmu_atc_inv_master(struct arm_smmu_master *master,
+ struct arm_smmu_cmdq_ent *cmd)
+{
+ int i;
+
+ if (!master->ats_enabled)
+ return 0;
+
+ for (i = 0; i < master->num_sids; i++) {
+ cmd->atc.sid = master->sids[i];
+ arm_smmu_cmdq_issue_cmd(master->smmu, cmd);
+ }
+
+ return arm_smmu_cmdq_issue_sync(master->smmu);
+}
+
+static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
+ int ssid, unsigned long iova, size_t size)
+{
+ int ret = 0;
+ unsigned long flags;
+ struct arm_smmu_cmdq_ent cmd;
+ struct arm_smmu_master *master;
+
+ if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS))
+ return 0;
+
+ arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd);
+
+ spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+ list_for_each_entry(master, &smmu_domain->devices, domain_head)
+ ret |= arm_smmu_atc_inv_master(master, &cmd);
+ spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+ return ret ? -ETIMEDOUT : 0;
+}
+
/* IO_PGTABLE API */
static void arm_smmu_tlb_sync(void *cookie)
{
@@ -1493,6 +1637,9 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
}
mutex_init(&smmu_domain->init_mutex);
+ INIT_LIST_HEAD(&smmu_domain->devices);
+ spin_lock_init(&smmu_domain->devices_lock);
+
return &smmu_domain->domain;
}
@@ -1688,55 +1835,97 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
return step;
}
-static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
+static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
{
int i, j;
- struct arm_smmu_master_data *master = fwspec->iommu_priv;
struct arm_smmu_device *smmu = master->smmu;
- for (i = 0; i < fwspec->num_ids; ++i) {
- u32 sid = fwspec->ids[i];
+ for (i = 0; i < master->num_sids; ++i) {
+ u32 sid = master->sids[i];
__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
/* Bridged PCI devices may end up with duplicated IDs */
for (j = 0; j < i; j++)
- if (fwspec->ids[j] == sid)
+ if (master->sids[j] == sid)
break;
if (j < i)
continue;
- arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste);
+ arm_smmu_write_strtab_ent(master, sid, step);
}
}
-static void arm_smmu_detach_dev(struct device *dev)
+static int arm_smmu_enable_ats(struct arm_smmu_master *master)
{
- struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
- struct arm_smmu_master_data *master = fwspec->iommu_priv;
+ int ret;
+ size_t stu;
+ struct pci_dev *pdev;
+ struct arm_smmu_device *smmu = master->smmu;
+ struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
- master->ste.assigned = false;
- arm_smmu_install_ste_for_dev(fwspec);
+ if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) ||
+ !(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled())
+ return -ENXIO;
+
+ pdev = to_pci_dev(master->dev);
+ if (pdev->untrusted)
+ return -EPERM;
+
+ /* Smallest Translation Unit: log2 of the smallest supported granule */
+ stu = __ffs(smmu->pgsize_bitmap);
+
+ ret = pci_enable_ats(pdev, stu);
+ if (ret)
+ return ret;
+
+ master->ats_enabled = true;
+ return 0;
+}
+
+static void arm_smmu_disable_ats(struct arm_smmu_master *master)
+{
+ if (!master->ats_enabled || !dev_is_pci(master->dev))
+ return;
+
+ pci_disable_ats(to_pci_dev(master->dev));
+ master->ats_enabled = false;
+}
+
+static void arm_smmu_detach_dev(struct arm_smmu_master *master)
+{
+ unsigned long flags;
+ struct arm_smmu_domain *smmu_domain = master->domain;
+
+ if (!smmu_domain)
+ return;
+
+ spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+ list_del(&master->domain_head);
+ spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+ master->domain = NULL;
+ arm_smmu_install_ste_for_dev(master);
+
+ /* Disabling ATS invalidates all ATC entries */
+ arm_smmu_disable_ats(master);
}
static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
int ret = 0;
+ unsigned long flags;
struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
struct arm_smmu_device *smmu;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
- struct arm_smmu_master_data *master;
- struct arm_smmu_strtab_ent *ste;
+ struct arm_smmu_master *master;
if (!fwspec)
return -ENOENT;
master = fwspec->iommu_priv;
smmu = master->smmu;
- ste = &master->ste;
- /* Already attached to a different domain? */
- if (ste->assigned)
- arm_smmu_detach_dev(dev);
+ arm_smmu_detach_dev(master);
mutex_lock(&smmu_domain->init_mutex);
@@ -1756,21 +1945,19 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
goto out_unlock;
}
- ste->assigned = true;
+ master->domain = smmu_domain;
- if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) {
- ste->s1_cfg = NULL;
- ste->s2_cfg = NULL;
- } else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
- ste->s1_cfg = &smmu_domain->s1_cfg;
- ste->s2_cfg = NULL;
- arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
- } else {
- ste->s1_cfg = NULL;
- ste->s2_cfg = &smmu_domain->s2_cfg;
- }
+ spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+ list_add(&master->domain_head, &smmu_domain->devices);
+ spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
- arm_smmu_install_ste_for_dev(fwspec);
+ if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
+ arm_smmu_enable_ats(master);
+
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+ arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg);
+
+ arm_smmu_install_ste_for_dev(master);
out_unlock:
mutex_unlock(&smmu_domain->init_mutex);
return ret;
@@ -1790,12 +1977,18 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
static size_t
arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
{
- struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+ int ret;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
if (!ops)
return 0;
- return ops->unmap(ops, iova, size);
+ ret = ops->unmap(ops, iova, size);
+ if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size))
+ return 0;
+
+ return ret;
}
static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
@@ -1860,7 +2053,7 @@ static int arm_smmu_add_device(struct device *dev)
{
int i, ret;
struct arm_smmu_device *smmu;
- struct arm_smmu_master_data *master;
+ struct arm_smmu_master *master;
struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
struct iommu_group *group;
@@ -1882,13 +2075,16 @@ static int arm_smmu_add_device(struct device *dev)
if (!master)
return -ENOMEM;
+ master->dev = dev;
master->smmu = smmu;
+ master->sids = fwspec->ids;
+ master->num_sids = fwspec->num_ids;
fwspec->iommu_priv = master;
}
/* Check the SIDs are in range of the SMMU and our stream table */
- for (i = 0; i < fwspec->num_ids; i++) {
- u32 sid = fwspec->ids[i];
+ for (i = 0; i < master->num_sids; i++) {
+ u32 sid = master->sids[i];
if (!arm_smmu_sid_in_range(smmu, sid))
return -ERANGE;
@@ -1913,7 +2109,7 @@ static int arm_smmu_add_device(struct device *dev)
static void arm_smmu_remove_device(struct device *dev)
{
struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
- struct arm_smmu_master_data *master;
+ struct arm_smmu_master *master;
struct arm_smmu_device *smmu;
if (!fwspec || fwspec->ops != &arm_smmu_ops)
@@ -1921,8 +2117,7 @@ static void arm_smmu_remove_device(struct device *dev)
master = fwspec->iommu_priv;
smmu = master->smmu;
- if (master && master->ste.assigned)
- arm_smmu_detach_dev(dev);
+ arm_smmu_detach_dev(master);
iommu_group_remove_device(dev);
iommu_device_unlink(&smmu->iommu, dev);
kfree(master);
@@ -2454,13 +2649,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
/* Clear CR0 and sync (disables SMMU and queue processing) */
reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
if (reg & CR0_SMMUEN) {
- if (is_kdump_kernel()) {
- arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
- arm_smmu_device_disable(smmu);
- return -EBUSY;
- }
-
dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
+ WARN_ON(is_kdump_kernel() && !disable_bypass);
+ arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
}
ret = arm_smmu_device_disable(smmu);
@@ -2547,12 +2738,24 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
}
}
+ if (smmu->features & ARM_SMMU_FEAT_ATS) {
+ enables |= CR0_ATSCHK;
+ ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to enable ATS check\n");
+ return ret;
+ }
+ }
+
ret = arm_smmu_setup_irqs(smmu);
if (ret) {
dev_err(smmu->dev, "failed to setup irqs\n");
return ret;
}
+ if (is_kdump_kernel())
+ enables &= ~(CR0_EVTQEN | CR0_PRIQEN);
/* Enable the SMMU interface, or ensure bypass */
if (!bypass || disable_bypass) {
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 045d93884164..5e54cc0a28b3 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -110,7 +110,8 @@ static int force_stage;
module_param(force_stage, int, S_IRUGO);
MODULE_PARM_DESC(force_stage,
"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
-static bool disable_bypass;
+static bool disable_bypass =
+ IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT);
module_param(disable_bypass, bool, S_IRUGO);
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.");
@@ -569,12 +570,13 @@ static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = {
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
{
- u32 fsr, fsynr;
+ u32 fsr, fsynr, cbfrsynra;
unsigned long iova;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct arm_smmu_device *smmu = smmu_domain->smmu;
+ void __iomem *gr1_base = ARM_SMMU_GR1(smmu);
void __iomem *cb_base;
cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
@@ -585,10 +587,11 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
+ cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx));
dev_err_ratelimited(smmu->dev,
- "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n",
- fsr, iova, fsynr, cfg->cbndx);
+ "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
+ fsr, iova, fsynr, cbfrsynra, cfg->cbndx);
writel(fsr, cb_base + ARM_SMMU_CB_FSR);
return IRQ_HANDLED;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 13916fefeb27..129c4badf9ae 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -206,12 +206,13 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
return 0;
}
-static void iova_reserve_pci_windows(struct pci_dev *dev,
+static int iova_reserve_pci_windows(struct pci_dev *dev,
struct iova_domain *iovad)
{
struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
struct resource_entry *window;
unsigned long lo, hi;
+ phys_addr_t start = 0, end;
resource_list_for_each_entry(window, &bridge->windows) {
if (resource_type(window->res) != IORESOURCE_MEM)
@@ -221,6 +222,31 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
hi = iova_pfn(iovad, window->res->end - window->offset);
reserve_iova(iovad, lo, hi);
}
+
+ /* Get reserved DMA windows from host bridge */
+ resource_list_for_each_entry(window, &bridge->dma_ranges) {
+ end = window->res->start - window->offset;
+resv_iova:
+ if (end > start) {
+ lo = iova_pfn(iovad, start);
+ hi = iova_pfn(iovad, end);
+ reserve_iova(iovad, lo, hi);
+ } else {
+ /* dma_ranges list should be sorted */
+ dev_err(&dev->dev, "Failed to reserve IOVA\n");
+ return -EINVAL;
+ }
+
+ start = window->res->end - window->offset + 1;
+ /* If window is last entry */
+ if (window->node.next == &bridge->dma_ranges &&
+ end != ~(dma_addr_t)0) {
+ end = ~(dma_addr_t)0;
+ goto resv_iova;
+ }
+ }
+
+ return 0;
}
static int iova_reserve_iommu_regions(struct device *dev,
@@ -232,8 +258,11 @@ static int iova_reserve_iommu_regions(struct device *dev,
LIST_HEAD(resv_regions);
int ret = 0;
- if (dev_is_pci(dev))
- iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+ if (dev_is_pci(dev)) {
+ ret = iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+ if (ret)
+ return ret;
+ }
iommu_get_resv_regions(dev, &resv_regions);
list_for_each_entry(region, &resv_regions, list) {
@@ -619,17 +648,7 @@ out_free_pages:
int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
{
- unsigned long uaddr = vma->vm_start;
- unsigned int i, count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- int ret = -ENXIO;
-
- for (i = vma->vm_pgoff; i < count && uaddr < vma->vm_end; i++) {
- ret = vm_insert_page(vma, uaddr, pages[i]);
- if (ret)
- break;
- uaddr += PAGE_SIZE;
- }
- return ret;
+ return vm_map_pages(vma, pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
}
static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9c49300e9fb7..6d969a172fbb 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -145,7 +145,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
for (tmp = dev; tmp; tmp = tmp->bus->self)
level++;
- size = sizeof(*info) + level * sizeof(info->path[0]);
+ size = struct_size(info, path, level);
if (size <= sizeof(dmar_pci_notify_info_buf)) {
info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
} else {
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 28cb713d728c..a209199f3af6 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1391,7 +1391,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info)
/* pdev will be returned if device is not a vf */
pf_pdev = pci_physfn(pdev);
- info->pfsid = PCI_DEVID(pf_pdev->bus->number, pf_pdev->devfn);
+ info->pfsid = pci_dev_id(pf_pdev);
}
#ifdef CONFIG_INTEL_IOMMU_SVM
@@ -2341,32 +2341,33 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
}
static int domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
- struct scatterlist *sg, unsigned long phys_pfn,
- unsigned long nr_pages, int prot)
-{
- int ret;
- struct intel_iommu *iommu;
-
- /* Do the real mapping first */
- ret = __domain_mapping(domain, iov_pfn, sg, phys_pfn, nr_pages, prot);
- if (ret)
- return ret;
-
- /* Notify about the new mapping */
- if (domain_type_is_vm(domain)) {
- /* VM typed domains can have more than one IOMMUs */
- int iommu_id;
- for_each_domain_iommu(iommu_id, domain) {
- iommu = g_iommus[iommu_id];
- __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
- }
- } else {
- /* General domains only have one IOMMU */
- iommu = domain_get_iommu(domain);
- __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
- }
+ struct scatterlist *sg, unsigned long phys_pfn,
+ unsigned long nr_pages, int prot)
+{
+ int ret;
+ struct intel_iommu *iommu;
+
+ /* Do the real mapping first */
+ ret = __domain_mapping(domain, iov_pfn, sg, phys_pfn, nr_pages, prot);
+ if (ret)
+ return ret;
+
+ /* Notify about the new mapping */
+ if (domain_type_is_vm(domain)) {
+ /* VM typed domains can have more than one IOMMUs */
+ int iommu_id;
+
+ for_each_domain_iommu(iommu_id, domain) {
+ iommu = g_iommus[iommu_id];
+ __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
+ }
+ } else {
+ /* General domains only have one IOMMU */
+ iommu = domain_get_iommu(domain);
+ __mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
+ }
- return 0;
+ return 0;
}
static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
@@ -2485,6 +2486,8 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
info->domain = domain;
info->iommu = iommu;
info->pasid_table = NULL;
+ info->auxd_enabled = 0;
+ INIT_LIST_HEAD(&info->auxiliary_domains);
if (dev && dev_is_pci(dev)) {
struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -3412,9 +3415,12 @@ static int __init init_dmars(void)
iommu_identity_mapping |= IDENTMAP_ALL;
#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
- iommu_identity_mapping |= IDENTMAP_GFX;
+ dmar_map_gfx = 0;
#endif
+ if (!dmar_map_gfx)
+ iommu_identity_mapping |= IDENTMAP_GFX;
+
check_tylersburg_isoch();
if (iommu_identity_mapping) {
@@ -3496,7 +3502,13 @@ domains_done:
#ifdef CONFIG_INTEL_IOMMU_SVM
if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
+ /*
+ * Call dmar_alloc_hwirq() with dmar_global_lock held,
+ * could cause possible lock race condition.
+ */
+ up_write(&dmar_global_lock);
ret = intel_svm_enable_prq(iommu);
+ down_write(&dmar_global_lock);
if (ret)
goto free_iommu;
}
@@ -3606,45 +3618,40 @@ out:
}
/* Check if the dev needs to go through non-identity map and unmap process.*/
-static int iommu_no_mapping(struct device *dev)
+static bool iommu_need_mapping(struct device *dev)
{
int found;
if (iommu_dummy(dev))
- return 1;
+ return false;
if (!iommu_identity_mapping)
- return 0;
+ return true;
found = identity_mapping(dev);
if (found) {
if (iommu_should_identity_map(dev, 0))
- return 1;
- else {
- /*
- * 32 bit DMA is removed from si_domain and fall back
- * to non-identity mapping.
- */
- dmar_remove_one_dev_info(dev);
- dev_info(dev, "32bit DMA uses non-identity mapping\n");
- return 0;
- }
+ return false;
+
+ /*
+ * 32 bit DMA is removed from si_domain and fall back to
+ * non-identity mapping.
+ */
+ dmar_remove_one_dev_info(dev);
+ dev_info(dev, "32bit DMA uses non-identity mapping\n");
} else {
/*
* In case of a detached 64 bit DMA device from vm, the device
* is put into si_domain for identity mapping.
*/
- if (iommu_should_identity_map(dev, 0)) {
- int ret;
- ret = domain_add_dev_info(si_domain, dev);
- if (!ret) {
- dev_info(dev, "64bit DMA uses identity mapping\n");
- return 1;
- }
+ if (iommu_should_identity_map(dev, 0) &&
+ !domain_add_dev_info(si_domain, dev)) {
+ dev_info(dev, "64bit DMA uses identity mapping\n");
+ return false;
}
}
- return 0;
+ return true;
}
static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
@@ -3660,9 +3667,6 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
BUG_ON(dir == DMA_NONE);
- if (iommu_no_mapping(dev))
- return paddr;
-
domain = get_valid_domain_for_dev(dev);
if (!domain)
return DMA_MAPPING_ERROR;
@@ -3711,15 +3715,20 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
unsigned long attrs)
{
- return __intel_map_single(dev, page_to_phys(page) + offset, size,
- dir, *dev->dma_mask);
+ if (iommu_need_mapping(dev))
+ return __intel_map_single(dev, page_to_phys(page) + offset,
+ size, dir, *dev->dma_mask);
+ return dma_direct_map_page(dev, page, offset, size, dir, attrs);
}
static dma_addr_t intel_map_resource(struct device *dev, phys_addr_t phys_addr,
size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
- return __intel_map_single(dev, phys_addr, size, dir, *dev->dma_mask);
+ if (iommu_need_mapping(dev))
+ return __intel_map_single(dev, phys_addr, size, dir,
+ *dev->dma_mask);
+ return dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
}
static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
@@ -3730,9 +3739,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
unsigned long iova_pfn;
struct intel_iommu *iommu;
struct page *freelist;
-
- if (iommu_no_mapping(dev))
- return;
+ struct pci_dev *pdev = NULL;
domain = find_domain(dev);
BUG_ON(!domain);
@@ -3745,11 +3752,14 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
start_pfn = mm_to_dma_pfn(iova_pfn);
last_pfn = start_pfn + nrpages - 1;
+ if (dev_is_pci(dev))
+ pdev = to_pci_dev(dev);
+
dev_dbg(dev, "Device unmapping: pfn %lx-%lx\n", start_pfn, last_pfn);
freelist = domain_unmap(domain, start_pfn, last_pfn);
- if (intel_iommu_strict) {
+ if (intel_iommu_strict || (pdev && pdev->untrusted)) {
iommu_flush_iotlb_psi(iommu, domain, start_pfn,
nrpages, !freelist, 0);
/* free iova */
@@ -3769,7 +3779,17 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
- intel_unmap(dev, dev_addr, size);
+ if (iommu_need_mapping(dev))
+ intel_unmap(dev, dev_addr, size);
+ else
+ dma_direct_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static void intel_unmap_resource(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (iommu_need_mapping(dev))
+ intel_unmap(dev, dev_addr, size);
}
static void *intel_alloc_coherent(struct device *dev, size_t size,
@@ -3779,28 +3799,17 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
struct page *page = NULL;
int order;
+ if (!iommu_need_mapping(dev))
+ return dma_direct_alloc(dev, size, dma_handle, flags, attrs);
+
size = PAGE_ALIGN(size);
order = get_order(size);
- if (!iommu_no_mapping(dev))
- flags &= ~(GFP_DMA | GFP_DMA32);
- else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
- if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
- flags |= GFP_DMA;
- else
- flags |= GFP_DMA32;
- }
-
if (gfpflags_allow_blocking(flags)) {
unsigned int count = size >> PAGE_SHIFT;
page = dma_alloc_from_contiguous(dev, count, order,
flags & __GFP_NOWARN);
- if (page && iommu_no_mapping(dev) &&
- page_to_phys(page) + size > dev->coherent_dma_mask) {
- dma_release_from_contiguous(dev, page, count);
- page = NULL;
- }
}
if (!page)
@@ -3826,6 +3835,9 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
int order;
struct page *page = virt_to_page(vaddr);
+ if (!iommu_need_mapping(dev))
+ return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+
size = PAGE_ALIGN(size);
order = get_order(size);
@@ -3843,6 +3855,9 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
struct scatterlist *sg;
int i;
+ if (!iommu_need_mapping(dev))
+ return dma_direct_unmap_sg(dev, sglist, nelems, dir, attrs);
+
for_each_sg(sglist, sg, nelems, i) {
nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg));
}
@@ -3850,20 +3865,6 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
}
-static int intel_nontranslate_map_sg(struct device *hddev,
- struct scatterlist *sglist, int nelems, int dir)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nelems, i) {
- BUG_ON(!sg_page(sg));
- sg->dma_address = sg_phys(sg);
- sg->dma_length = sg->length;
- }
- return nelems;
-}
-
static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
enum dma_data_direction dir, unsigned long attrs)
{
@@ -3878,8 +3879,8 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
struct intel_iommu *iommu;
BUG_ON(dir == DMA_NONE);
- if (iommu_no_mapping(dev))
- return intel_nontranslate_map_sg(dev, sglist, nelems, dir);
+ if (!iommu_need_mapping(dev))
+ return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
domain = get_valid_domain_for_dev(dev);
if (!domain)
@@ -3929,7 +3930,7 @@ static const struct dma_map_ops intel_dma_ops = {
.map_page = intel_map_page,
.unmap_page = intel_unmap_page,
.map_resource = intel_map_resource,
- .unmap_resource = intel_unmap_page,
+ .unmap_resource = intel_unmap_resource,
.dma_supported = dma_direct_supported,
};
@@ -4055,9 +4056,7 @@ static void __init init_no_remapping_devices(void)
/* This IOMMU has *only* gfx devices. Either bypass it or
set the gfx_mapped flag, as appropriate */
- if (dmar_map_gfx) {
- intel_iommu_gfx_mapped = 1;
- } else {
+ if (!dmar_map_gfx) {
drhd->ignored = 1;
for_each_active_dev_scope(drhd->devices,
drhd->devices_cnt, i, dev)
@@ -4086,7 +4085,7 @@ static int init_iommu_hw(void)
iommu_disable_protect_mem_regions(iommu);
continue;
}
-
+
iommu_flush_write_buffer(iommu);
iommu_set_root_entry(iommu);
@@ -4896,6 +4895,9 @@ int __init intel_iommu_init(void)
goto out_free_reserved_range;
}
+ if (dmar_map_gfx)
+ intel_iommu_gfx_mapped = 1;
+
init_no_remapping_devices();
ret = init_dmars();
@@ -5065,35 +5067,139 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
domain_exit(to_dmar_domain(domain));
}
-static int intel_iommu_attach_device(struct iommu_domain *domain,
- struct device *dev)
+/*
+ * Check whether a @domain could be attached to the @dev through the
+ * aux-domain attach/detach APIs.
+ */
+static inline bool
+is_aux_domain(struct device *dev, struct iommu_domain *domain)
{
- struct dmar_domain *dmar_domain = to_dmar_domain(domain);
- struct intel_iommu *iommu;
- int addr_width;
- u8 bus, devfn;
+ struct device_domain_info *info = dev->archdata.iommu;
- if (device_is_rmrr_locked(dev)) {
- dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n");
- return -EPERM;
- }
+ return info && info->auxd_enabled &&
+ domain->type == IOMMU_DOMAIN_UNMANAGED;
+}
- /* normally dev is not mapped */
- if (unlikely(domain_context_mapped(dev))) {
- struct dmar_domain *old_domain;
+static void auxiliary_link_device(struct dmar_domain *domain,
+ struct device *dev)
+{
+ struct device_domain_info *info = dev->archdata.iommu;
- old_domain = find_domain(dev);
- if (old_domain) {
- rcu_read_lock();
- dmar_remove_one_dev_info(dev);
- rcu_read_unlock();
+ assert_spin_locked(&device_domain_lock);
+ if (WARN_ON(!info))
+ return;
- if (!domain_type_is_vm_or_si(old_domain) &&
- list_empty(&old_domain->devices))
- domain_exit(old_domain);
+ domain->auxd_refcnt++;
+ list_add(&domain->auxd, &info->auxiliary_domains);
+}
+
+static void auxiliary_unlink_device(struct dmar_domain *domain,
+ struct device *dev)
+{
+ struct device_domain_info *info = dev->archdata.iommu;
+
+ assert_spin_locked(&device_domain_lock);
+ if (WARN_ON(!info))
+ return;
+
+ list_del(&domain->auxd);
+ domain->auxd_refcnt--;
+
+ if (!domain->auxd_refcnt && domain->default_pasid > 0)
+ intel_pasid_free_id(domain->default_pasid);
+}
+
+static int aux_domain_add_dev(struct dmar_domain *domain,
+ struct device *dev)
+{
+ int ret;
+ u8 bus, devfn;
+ unsigned long flags;
+ struct intel_iommu *iommu;
+
+ iommu = device_to_iommu(dev, &bus, &devfn);
+ if (!iommu)
+ return -ENODEV;
+
+ if (domain->default_pasid <= 0) {
+ int pasid;
+
+ pasid = intel_pasid_alloc_id(domain, PASID_MIN,
+ pci_max_pasids(to_pci_dev(dev)),
+ GFP_KERNEL);
+ if (pasid <= 0) {
+ pr_err("Can't allocate default pasid\n");
+ return -ENODEV;
}
+ domain->default_pasid = pasid;
}
+ spin_lock_irqsave(&device_domain_lock, flags);
+ /*
+ * iommu->lock must be held to attach domain to iommu and setup the
+ * pasid entry for second level translation.
+ */
+ spin_lock(&iommu->lock);
+ ret = domain_attach_iommu(domain, iommu);
+ if (ret)
+ goto attach_failed;
+
+ /* Setup the PASID entry for mediated devices: */
+ ret = intel_pasid_setup_second_level(iommu, domain, dev,
+ domain->default_pasid);
+ if (ret)
+ goto table_failed;
+ spin_unlock(&iommu->lock);
+
+ auxiliary_link_device(domain, dev);
+
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+
+ return 0;
+
+table_failed:
+ domain_detach_iommu(domain, iommu);
+attach_failed:
+ spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ if (!domain->auxd_refcnt && domain->default_pasid > 0)
+ intel_pasid_free_id(domain->default_pasid);
+
+ return ret;
+}
+
+static void aux_domain_remove_dev(struct dmar_domain *domain,
+ struct device *dev)
+{
+ struct device_domain_info *info;
+ struct intel_iommu *iommu;
+ unsigned long flags;
+
+ if (!is_aux_domain(dev, &domain->domain))
+ return;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ info = dev->archdata.iommu;
+ iommu = info->iommu;
+
+ auxiliary_unlink_device(domain, dev);
+
+ spin_lock(&iommu->lock);
+ intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid);
+ domain_detach_iommu(domain, iommu);
+ spin_unlock(&iommu->lock);
+
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static int prepare_domain_attach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+ struct intel_iommu *iommu;
+ int addr_width;
+ u8 bus, devfn;
+
iommu = device_to_iommu(dev, &bus, &devfn);
if (!iommu)
return -ENODEV;
@@ -5126,7 +5232,58 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
dmar_domain->agaw--;
}
- return domain_add_dev_info(dmar_domain, dev);
+ return 0;
+}
+
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ int ret;
+
+ if (device_is_rmrr_locked(dev)) {
+ dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n");
+ return -EPERM;
+ }
+
+ if (is_aux_domain(dev, domain))
+ return -EPERM;
+
+ /* normally dev is not mapped */
+ if (unlikely(domain_context_mapped(dev))) {
+ struct dmar_domain *old_domain;
+
+ old_domain = find_domain(dev);
+ if (old_domain) {
+ rcu_read_lock();
+ dmar_remove_one_dev_info(dev);
+ rcu_read_unlock();
+
+ if (!domain_type_is_vm_or_si(old_domain) &&
+ list_empty(&old_domain->devices))
+ domain_exit(old_domain);
+ }
+ }
+
+ ret = prepare_domain_attach_device(domain, dev);
+ if (ret)
+ return ret;
+
+ return domain_add_dev_info(to_dmar_domain(domain), dev);
+}
+
+static int intel_iommu_aux_attach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ int ret;
+
+ if (!is_aux_domain(dev, domain))
+ return -EPERM;
+
+ ret = prepare_domain_attach_device(domain, dev);
+ if (ret)
+ return ret;
+
+ return aux_domain_add_dev(to_dmar_domain(domain), dev);
}
static void intel_iommu_detach_device(struct iommu_domain *domain,
@@ -5135,6 +5292,12 @@ static void intel_iommu_detach_device(struct iommu_domain *domain,
dmar_remove_one_dev_info(dev);
}
+static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ aux_domain_remove_dev(to_dmar_domain(domain), dev);
+}
+
static int intel_iommu_map(struct iommu_domain *domain,
unsigned long iova, phys_addr_t hpa,
size_t size, int iommu_prot)
@@ -5223,6 +5386,42 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
return phys;
}
+static inline bool scalable_mode_support(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ bool ret = true;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!sm_supported(iommu)) {
+ ret = false;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static inline bool iommu_pasid_support(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ bool ret = true;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!pasid_supported(iommu)) {
+ ret = false;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
static bool intel_iommu_capable(enum iommu_cap cap)
{
if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -5307,8 +5506,7 @@ static void intel_iommu_put_resv_regions(struct device *dev,
}
}
-#ifdef CONFIG_INTEL_IOMMU_SVM
-int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
+int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
{
struct device_domain_info *info;
struct context_entry *context;
@@ -5317,7 +5515,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
u64 ctx_lo;
int ret;
- domain = get_valid_domain_for_dev(sdev->dev);
+ domain = get_valid_domain_for_dev(dev);
if (!domain)
return -EINVAL;
@@ -5325,7 +5523,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
spin_lock(&iommu->lock);
ret = -EINVAL;
- info = sdev->dev->archdata.iommu;
+ info = dev->archdata.iommu;
if (!info || !info->pasid_supported)
goto out;
@@ -5335,14 +5533,13 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
ctx_lo = context[0].lo;
- sdev->did = FLPT_DEFAULT_DID;
- sdev->sid = PCI_DEVID(info->bus, info->devfn);
-
if (!(ctx_lo & CONTEXT_PASIDE)) {
ctx_lo |= CONTEXT_PASIDE;
context[0].lo = ctx_lo;
wmb();
- iommu->flush.flush_context(iommu, sdev->did, sdev->sid,
+ iommu->flush.flush_context(iommu,
+ domain->iommu_did[iommu->seq_id],
+ PCI_DEVID(info->bus, info->devfn),
DMA_CCMD_MASK_NOBIT,
DMA_CCMD_DEVICE_INVL);
}
@@ -5351,12 +5548,6 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
if (!info->pasid_enabled)
iommu_enable_dev_iotlb(info);
- if (info->ats_enabled) {
- sdev->dev_iotlb = 1;
- sdev->qdep = info->ats_qdep;
- if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
- sdev->qdep = 0;
- }
ret = 0;
out:
@@ -5366,6 +5557,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
return ret;
}
+#ifdef CONFIG_INTEL_IOMMU_SVM
struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
{
struct intel_iommu *iommu;
@@ -5387,12 +5579,142 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
}
#endif /* CONFIG_INTEL_IOMMU_SVM */
+static int intel_iommu_enable_auxd(struct device *dev)
+{
+ struct device_domain_info *info;
+ struct intel_iommu *iommu;
+ unsigned long flags;
+ u8 bus, devfn;
+ int ret;
+
+ iommu = device_to_iommu(dev, &bus, &devfn);
+ if (!iommu || dmar_disabled)
+ return -EINVAL;
+
+ if (!sm_supported(iommu) || !pasid_supported(iommu))
+ return -EINVAL;
+
+ ret = intel_iommu_enable_pasid(iommu, dev);
+ if (ret)
+ return -ENODEV;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ info = dev->archdata.iommu;
+ info->auxd_enabled = 1;
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+
+ return 0;
+}
+
+static int intel_iommu_disable_auxd(struct device *dev)
+{
+ struct device_domain_info *info;
+ unsigned long flags;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ info = dev->archdata.iommu;
+ if (!WARN_ON(!info))
+ info->auxd_enabled = 0;
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+
+ return 0;
+}
+
+/*
+ * A PCI express designated vendor specific extended capability is defined
+ * in the section 3.7 of Intel scalable I/O virtualization technical spec
+ * for system software and tools to detect endpoint devices supporting the
+ * Intel scalable IO virtualization without host driver dependency.
+ *
+ * Returns the address of the matching extended capability structure within
+ * the device's PCI configuration space or 0 if the device does not support
+ * it.
+ */
+static int siov_find_pci_dvsec(struct pci_dev *pdev)
+{
+ int pos;
+ u16 vendor, id;
+
+ pos = pci_find_next_ext_capability(pdev, 0, 0x23);
+ while (pos) {
+ pci_read_config_word(pdev, pos + 4, &vendor);
+ pci_read_config_word(pdev, pos + 8, &id);
+ if (vendor == PCI_VENDOR_ID_INTEL && id == 5)
+ return pos;
+
+ pos = pci_find_next_ext_capability(pdev, pos, 0x23);
+ }
+
+ return 0;
+}
+
+static bool
+intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat)
+{
+ if (feat == IOMMU_DEV_FEAT_AUX) {
+ int ret;
+
+ if (!dev_is_pci(dev) || dmar_disabled ||
+ !scalable_mode_support() || !iommu_pasid_support())
+ return false;
+
+ ret = pci_pasid_features(to_pci_dev(dev));
+ if (ret < 0)
+ return false;
+
+ return !!siov_find_pci_dvsec(to_pci_dev(dev));
+ }
+
+ return false;
+}
+
+static int
+intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+ if (feat == IOMMU_DEV_FEAT_AUX)
+ return intel_iommu_enable_auxd(dev);
+
+ return -ENODEV;
+}
+
+static int
+intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+ if (feat == IOMMU_DEV_FEAT_AUX)
+ return intel_iommu_disable_auxd(dev);
+
+ return -ENODEV;
+}
+
+static bool
+intel_iommu_dev_feat_enabled(struct device *dev, enum iommu_dev_features feat)
+{
+ struct device_domain_info *info = dev->archdata.iommu;
+
+ if (feat == IOMMU_DEV_FEAT_AUX)
+ return scalable_mode_support() && info && info->auxd_enabled;
+
+ return false;
+}
+
+static int
+intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+{
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+ return dmar_domain->default_pasid > 0 ?
+ dmar_domain->default_pasid : -EINVAL;
+}
+
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,
+ .aux_attach_dev = intel_iommu_aux_attach_device,
+ .aux_detach_dev = intel_iommu_aux_detach_device,
+ .aux_get_pasid = intel_iommu_aux_get_pasid,
.map = intel_iommu_map,
.unmap = intel_iommu_unmap,
.iova_to_phys = intel_iommu_iova_to_phys,
@@ -5401,6 +5723,10 @@ const struct iommu_ops intel_iommu_ops = {
.get_resv_regions = intel_iommu_get_resv_regions,
.put_resv_regions = intel_iommu_put_resv_regions,
.device_group = pci_device_group,
+ .dev_has_feat = intel_iommu_dev_has_feat,
+ .dev_feat_enabled = intel_iommu_dev_feat_enabled,
+ .dev_enable_feat = intel_iommu_dev_enable_feat,
+ .dev_disable_feat = intel_iommu_dev_disable_feat,
.pgsize_bitmap = INTEL_IOMMU_PGSIZES,
};
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index 03b12d2ee213..2fefeafda437 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -154,8 +154,10 @@ int intel_pasid_alloc_table(struct device *dev)
order = size ? get_order(size) : 0;
pages = alloc_pages_node(info->iommu->node,
GFP_KERNEL | __GFP_ZERO, order);
- if (!pages)
+ if (!pages) {
+ kfree(pasid_table);
return -ENOMEM;
+ }
pasid_table->table = page_address(pages);
pasid_table->order = order;
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 3a4b09ae8561..8f87304f915c 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -228,6 +228,7 @@ static LIST_HEAD(global_svm_list);
int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops)
{
struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+ struct device_domain_info *info;
struct intel_svm_dev *sdev;
struct intel_svm *svm = NULL;
struct mm_struct *mm = NULL;
@@ -291,13 +292,29 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
}
sdev->dev = dev;
- ret = intel_iommu_enable_pasid(iommu, sdev);
+ ret = intel_iommu_enable_pasid(iommu, dev);
if (ret || !pasid) {
/* If they don't actually want to assign a PASID, this is
* just an enabling check/preparation. */
kfree(sdev);
goto out;
}
+
+ info = dev->archdata.iommu;
+ if (!info || !info->pasid_supported) {
+ kfree(sdev);
+ goto out;
+ }
+
+ sdev->did = FLPT_DEFAULT_DID;
+ sdev->sid = PCI_DEVID(info->bus, info->devfn);
+ if (info->ats_enabled) {
+ sdev->dev_iotlb = 1;
+ sdev->qdep = info->ats_qdep;
+ if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
+ sdev->qdep = 0;
+ }
+
/* Finish the setup now we know we're keeping it */
sdev->users = 1;
sdev->ops = ops;
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 2d74641b7f7b..4160aa9f3f80 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -424,7 +424,7 @@ static int set_msi_sid(struct irte *irte, struct pci_dev *dev)
set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, data.alias);
else
set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
- PCI_DEVID(dev->bus->number, dev->devfn));
+ pci_dev_id(dev));
return 0;
}
@@ -548,8 +548,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
goto out_free_table;
}
- bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES),
- sizeof(long), GFP_ATOMIC);
+ bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC);
if (bitmap == NULL) {
pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
goto out_free_pages;
@@ -616,7 +615,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
return 0;
out_free_bitmap:
- kfree(bitmap);
+ bitmap_free(bitmap);
out_free_pages:
__free_pages(pages, INTR_REMAP_PAGE_ORDER);
out_free_table:
@@ -640,7 +639,7 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
}
free_pages((unsigned long)iommu->ir_table->base,
INTR_REMAP_PAGE_ORDER);
- kfree(iommu->ir_table->bitmap);
+ bitmap_free(iommu->ir_table->bitmap);
kfree(iommu->ir_table);
iommu->ir_table = NULL;
}
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index d3700ec15cbd..4e21efbc4459 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -172,6 +172,10 @@
#define ARM_LPAE_MAIR_ATTR_IDX_CACHE 1
#define ARM_LPAE_MAIR_ATTR_IDX_DEV 2
+#define ARM_MALI_LPAE_TTBR_ADRMODE_TABLE (3u << 0)
+#define ARM_MALI_LPAE_TTBR_READ_INNER BIT(2)
+#define ARM_MALI_LPAE_TTBR_SHARE_OUTER BIT(4)
+
/* IOPTE accessors */
#define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
@@ -180,11 +184,6 @@
#define iopte_prot(pte) ((pte) & ARM_LPAE_PTE_ATTR_MASK)
-#define iopte_leaf(pte,l) \
- (l == (ARM_LPAE_MAX_LEVELS - 1) ? \
- (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) : \
- (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK))
-
struct arm_lpae_io_pgtable {
struct io_pgtable iop;
@@ -198,6 +197,15 @@ struct arm_lpae_io_pgtable {
typedef u64 arm_lpae_iopte;
+static inline bool iopte_leaf(arm_lpae_iopte pte, int lvl,
+ enum io_pgtable_fmt fmt)
+{
+ if (lvl == (ARM_LPAE_MAX_LEVELS - 1) && fmt != ARM_MALI_LPAE)
+ return iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_PAGE;
+
+ return iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_BLOCK;
+}
+
static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr,
struct arm_lpae_io_pgtable *data)
{
@@ -303,12 +311,14 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
pte |= ARM_LPAE_PTE_NS;
- if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+ if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
pte |= ARM_LPAE_PTE_TYPE_PAGE;
else
pte |= ARM_LPAE_PTE_TYPE_BLOCK;
- pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS;
+ if (data->iop.fmt != ARM_MALI_LPAE)
+ pte |= ARM_LPAE_PTE_AF;
+ pte |= ARM_LPAE_PTE_SH_IS;
pte |= paddr_to_iopte(paddr, data);
__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
@@ -321,7 +331,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
{
arm_lpae_iopte pte = *ptep;
- if (iopte_leaf(pte, lvl)) {
+ if (iopte_leaf(pte, lvl, data->iop.fmt)) {
/* We require an unmap first */
WARN_ON(!selftest_running);
return -EEXIST;
@@ -409,7 +419,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
__arm_lpae_sync_pte(ptep, cfg);
}
- if (pte && !iopte_leaf(pte, lvl)) {
+ if (pte && !iopte_leaf(pte, lvl, data->iop.fmt)) {
cptep = iopte_deref(pte, data);
} else if (pte) {
/* We require an unmap first */
@@ -429,31 +439,37 @@ 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_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);
- else if (prot & IOMMU_CACHE)
- pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
- << ARM_LPAE_PTE_ATTRINDX_SHIFT);
} else {
pte = ARM_LPAE_PTE_HAP_FAULT;
if (prot & IOMMU_READ)
pte |= ARM_LPAE_PTE_HAP_READ;
if (prot & IOMMU_WRITE)
pte |= ARM_LPAE_PTE_HAP_WRITE;
+ }
+
+ /*
+ * Note that this logic is structured to accommodate Mali LPAE
+ * having stage-1-like attributes but stage-2-like permissions.
+ */
+ if (data->iop.fmt == ARM_64_LPAE_S2 ||
+ data->iop.fmt == ARM_32_LPAE_S2) {
if (prot & IOMMU_MMIO)
pte |= ARM_LPAE_PTE_MEMATTR_DEV;
else if (prot & IOMMU_CACHE)
pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
else
pte |= ARM_LPAE_PTE_MEMATTR_NC;
+ } else {
+ if (prot & IOMMU_MMIO)
+ pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
+ << ARM_LPAE_PTE_ATTRINDX_SHIFT);
+ else if (prot & IOMMU_CACHE)
+ pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
+ << ARM_LPAE_PTE_ATTRINDX_SHIFT);
}
if (prot & IOMMU_NOEXEC)
@@ -511,7 +527,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
while (ptep != end) {
arm_lpae_iopte pte = *ptep++;
- if (!pte || iopte_leaf(pte, lvl))
+ if (!pte || iopte_leaf(pte, lvl, data->iop.fmt))
continue;
__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
@@ -602,7 +618,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
__arm_lpae_set_pte(ptep, 0, &iop->cfg);
- if (!iopte_leaf(pte, lvl)) {
+ if (!iopte_leaf(pte, lvl, iop->fmt)) {
/* Also flush any partial walks */
io_pgtable_tlb_add_flush(iop, iova, size,
ARM_LPAE_GRANULE(data), false);
@@ -621,7 +637,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
}
return size;
- } else if (iopte_leaf(pte, lvl)) {
+ } else if (iopte_leaf(pte, lvl, iop->fmt)) {
/*
* Insert a table at the next level to map the old region,
* minus the part we want to unmap
@@ -669,7 +685,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
return 0;
/* Leaf entry? */
- if (iopte_leaf(pte,lvl))
+ if (iopte_leaf(pte, lvl, data->iop.fmt))
goto found_translation;
/* Take it to the next level */
@@ -995,6 +1011,32 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
return iop;
}
+static struct io_pgtable *
+arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+ struct io_pgtable *iop;
+
+ if (cfg->ias != 48 || cfg->oas > 40)
+ return NULL;
+
+ cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+ iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
+ if (iop) {
+ u64 mair, ttbr;
+
+ /* Copy values as union fields overlap */
+ mair = cfg->arm_lpae_s1_cfg.mair[0];
+ ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+
+ cfg->arm_mali_lpae_cfg.memattr = mair;
+ cfg->arm_mali_lpae_cfg.transtab = ttbr |
+ ARM_MALI_LPAE_TTBR_READ_INNER |
+ ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+ }
+
+ return iop;
+}
+
struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
.alloc = arm_64_lpae_alloc_pgtable_s1,
.free = arm_lpae_free_pgtable,
@@ -1015,6 +1057,11 @@ struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
.free = arm_lpae_free_pgtable,
};
+struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+ .alloc = arm_mali_lpae_alloc_pgtable,
+ .free = arm_lpae_free_pgtable,
+};
+
#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
static struct io_pgtable_cfg *cfg_cookie;
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index 93f2880be6c6..5227cfdbb65b 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -30,6 +30,7 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,
[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
+ [ARM_MALI_LPAE] = &io_pgtable_arm_mali_lpae_init_fns,
#endif
#ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S
[ARM_V7S] = &io_pgtable_arm_v7s_init_fns,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 109de67d5d72..67ee6623f9b2 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -45,10 +45,6 @@ static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
#endif
static bool iommu_dma_strict __read_mostly = true;
-struct iommu_callback_data {
- const struct iommu_ops *ops;
-};
-
struct iommu_group {
struct kobject kobj;
struct kobject *devices_kobj;
@@ -1217,9 +1213,6 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
{
int err;
struct notifier_block *nb;
- struct iommu_callback_data cb = {
- .ops = ops,
- };
nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
if (!nb)
@@ -1231,7 +1224,7 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
if (err)
goto out_free;
- err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
+ err = bus_for_each_dev(bus, NULL, NULL, add_iommu_group);
if (err)
goto out_err;
@@ -1240,7 +1233,7 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
out_err:
/* Clean up */
- bus_for_each_dev(bus, NULL, &cb, remove_iommu_group);
+ bus_for_each_dev(bus, NULL, NULL, remove_iommu_group);
bus_unregister_notifier(bus, nb);
out_free:
@@ -2039,3 +2032,203 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
+
+/*
+ * Per device IOMMU features.
+ */
+bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->dev_has_feat)
+ return ops->dev_has_feat(dev, feat);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_has_feature);
+
+int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->dev_enable_feat)
+ return ops->dev_enable_feat(dev, feat);
+
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
+
+/*
+ * The device drivers should do the necessary cleanups before calling this.
+ * For example, before disabling the aux-domain feature, the device driver
+ * should detach all aux-domains. Otherwise, this will return -EBUSY.
+ */
+int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->dev_disable_feat)
+ return ops->dev_disable_feat(dev, feat);
+
+ return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_disable_feature);
+
+bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->dev_feat_enabled)
+ return ops->dev_feat_enabled(dev, feat);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
+
+/*
+ * Aux-domain specific attach/detach.
+ *
+ * Only works if iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX) returns
+ * true. Also, as long as domains are attached to a device through this
+ * interface, any tries to call iommu_attach_device() should fail
+ * (iommu_detach_device() can't fail, so we fail when trying to re-attach).
+ * This should make us safe against a device being attached to a guest as a
+ * whole while there are still pasid users on it (aux and sva).
+ */
+int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+ int ret = -ENODEV;
+
+ if (domain->ops->aux_attach_dev)
+ ret = domain->ops->aux_attach_dev(domain, dev);
+
+ if (!ret)
+ trace_attach_device_to_domain(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_attach_device);
+
+void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+ if (domain->ops->aux_detach_dev) {
+ domain->ops->aux_detach_dev(domain, dev);
+ trace_detach_device_from_domain(dev);
+ }
+}
+EXPORT_SYMBOL_GPL(iommu_aux_detach_device);
+
+int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+{
+ int ret = -ENODEV;
+
+ if (domain->ops->aux_get_pasid)
+ ret = domain->ops->aux_get_pasid(domain, dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_get_pasid);
+
+/**
+ * iommu_sva_bind_device() - Bind a process address space to a device
+ * @dev: the device
+ * @mm: the mm to bind, caller must hold a reference to it
+ *
+ * Create a bond between device and address space, allowing the device to access
+ * the mm using the returned PASID. If a bond already exists between @device and
+ * @mm, it is returned and an additional reference is taken. Caller must call
+ * iommu_sva_unbind_device() to release each reference.
+ *
+ * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
+ * initialize the required SVA features.
+ *
+ * On error, returns an ERR_PTR value.
+ */
+struct iommu_sva *
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+ struct iommu_group *group;
+ struct iommu_sva *handle = ERR_PTR(-EINVAL);
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (!ops || !ops->sva_bind)
+ return ERR_PTR(-ENODEV);
+
+ group = iommu_group_get(dev);
+ if (!group)
+ return ERR_PTR(-ENODEV);
+
+ /* Ensure device count and domain don't change while we're binding */
+ mutex_lock(&group->mutex);
+
+ /*
+ * To keep things simple, SVA currently doesn't support IOMMU groups
+ * with more than one device. Existing SVA-capable systems are not
+ * affected by the problems that required IOMMU groups (lack of ACS
+ * isolation, device ID aliasing and other hardware issues).
+ */
+ if (iommu_group_device_count(group) != 1)
+ goto out_unlock;
+
+ handle = ops->sva_bind(dev, mm, drvdata);
+
+out_unlock:
+ mutex_unlock(&group->mutex);
+ iommu_group_put(group);
+
+ return handle;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
+
+/**
+ * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
+ * @handle: the handle returned by iommu_sva_bind_device()
+ *
+ * Put reference to a bond between device and address space. The device should
+ * not be issuing any more transaction for this PASID. All outstanding page
+ * requests for this PASID must have been flushed to the IOMMU.
+ *
+ * Returns 0 on success, or an error value
+ */
+void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+ struct iommu_group *group;
+ struct device *dev = handle->dev;
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (!ops || !ops->sva_unbind)
+ return;
+
+ group = iommu_group_get(dev);
+ if (!group)
+ return;
+
+ mutex_lock(&group->mutex);
+ ops->sva_unbind(handle);
+ mutex_unlock(&group->mutex);
+
+ iommu_group_put(group);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
+
+int iommu_sva_set_ops(struct iommu_sva *handle,
+ const struct iommu_sva_ops *sva_ops)
+{
+ if (handle->ops && handle->ops != sva_ops)
+ return -EEXIST;
+
+ handle->ops = sva_ops;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_set_ops);
+
+int iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+ const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
+
+ if (!ops || !ops->sva_get_pasid)
+ return IOMMU_PASID_INVALID;
+
+ return ops->sva_get_pasid(handle);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 9fb0eb7a4d02..b4b87d6ae67f 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -34,7 +34,7 @@
#include <linux/of_iommu.h>
#include <asm/cacheflush.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
#include "msm_iommu_hw-8xxx.h"
#include "msm_iommu.h"
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index de3e02277b70..b66d11b0286e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -632,16 +632,20 @@ static int mtk_iommu_probe(struct platform_device *pdev)
if (!larbnode)
return -EINVAL;
- if (!of_device_is_available(larbnode))
+ if (!of_device_is_available(larbnode)) {
+ of_node_put(larbnode);
continue;
+ }
ret = of_property_read_u32(larbnode, "mediatek,larb-id", &id);
if (ret)/* The id is consecutive if there is no this property */
id = i;
plarbdev = of_find_device_by_node(larbnode);
- if (!plarbdev)
+ if (!plarbdev) {
+ of_node_put(larbnode);
return -EPROBE_DEFER;
+ }
data->smi_imu.larb_imu[id].dev = &plarbdev->dev;
component_match_add_release(dev, &match, release_of,
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 5182c7d6171e..463ee08f7d3a 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -102,7 +102,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
#define SMMU_TLB_FLUSH_VA_MATCH_ALL (0 << 0)
#define SMMU_TLB_FLUSH_VA_MATCH_SECTION (2 << 0)
#define SMMU_TLB_FLUSH_VA_MATCH_GROUP (3 << 0)
-#define SMMU_TLB_FLUSH_ASID(x) (((x) & 0x7f) << 24)
#define SMMU_TLB_FLUSH_VA_SECTION(addr) ((((addr) & 0xffc00000) >> 12) | \
SMMU_TLB_FLUSH_VA_MATCH_SECTION)
#define SMMU_TLB_FLUSH_VA_GROUP(addr) ((((addr) & 0xffffc000) >> 12) | \
@@ -146,8 +145,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
#define SMMU_PDE_ATTR (SMMU_PDE_READABLE | SMMU_PDE_WRITABLE | \
SMMU_PDE_NONSECURE)
-#define SMMU_PTE_ATTR (SMMU_PTE_READABLE | SMMU_PTE_WRITABLE | \
- SMMU_PTE_NONSECURE)
static unsigned int iova_pd_index(unsigned long iova)
{
@@ -205,8 +202,12 @@ static inline void smmu_flush_tlb_asid(struct tegra_smmu *smmu,
{
u32 value;
- value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
- SMMU_TLB_FLUSH_VA_MATCH_ALL;
+ if (smmu->soc->num_asids == 4)
+ value = (asid & 0x3) << 29;
+ else
+ value = (asid & 0x7f) << 24;
+
+ value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_MATCH_ALL;
smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}
@@ -216,8 +217,12 @@ static inline void smmu_flush_tlb_section(struct tegra_smmu *smmu,
{
u32 value;
- value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
- SMMU_TLB_FLUSH_VA_SECTION(iova);
+ if (smmu->soc->num_asids == 4)
+ value = (asid & 0x3) << 29;
+ else
+ value = (asid & 0x7f) << 24;
+
+ value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_SECTION(iova);
smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}
@@ -227,8 +232,12 @@ static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
{
u32 value;
- value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
- SMMU_TLB_FLUSH_VA_GROUP(iova);
+ if (smmu->soc->num_asids == 4)
+ value = (asid & 0x3) << 29;
+ else
+ value = (asid & 0x7f) << 24;
+
+ value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_GROUP(iova);
smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}
@@ -316,6 +325,9 @@ static void tegra_smmu_domain_free(struct iommu_domain *domain)
/* TODO: free page directory and page tables */
+ WARN_ON_ONCE(as->use_count);
+ kfree(as->count);
+ kfree(as->pts);
kfree(as);
}
@@ -645,6 +657,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
{
struct tegra_smmu_as *as = to_smmu_as(domain);
dma_addr_t pte_dma;
+ u32 pte_attrs;
u32 *pte;
pte = as_get_pte(as, iova, &pte_dma);
@@ -655,8 +668,16 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
if (*pte == 0)
tegra_smmu_pte_get_use(as, iova);
+ pte_attrs = SMMU_PTE_NONSECURE;
+
+ if (prot & IOMMU_READ)
+ pte_attrs |= SMMU_PTE_READABLE;
+
+ if (prot & IOMMU_WRITE)
+ pte_attrs |= SMMU_PTE_WRITABLE;
+
tegra_smmu_set_pte(as, iova, pte, pte_dma,
- __phys_to_pfn(paddr) | SMMU_PTE_ATTR);
+ __phys_to_pfn(paddr) | pte_attrs);
return 0;
}