[RFC PATCH 29/45] iommu/arm-smmu-v3: Move some functions to arm-smmu-v3-common.c
Jean-Philippe Brucker
jean-philippe at linaro.org
Wed Feb 1 04:53:13 PST 2023
Move functions that can be shared between normal and KVM drivers to
arm-smmu-v3-common.c
Only straightforward moves here. More subtle factoring will be done in
then next patches.
Signed-off-by: Jean-Philippe Brucker <jean-philippe at linaro.org>
---
drivers/iommu/arm/arm-smmu-v3/Makefile | 1 +
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 9 +
.../arm/arm-smmu-v3/arm-smmu-v3-common.c | 296 ++++++++++++++++++
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 293 -----------------
4 files changed, 306 insertions(+), 293 deletions(-)
create mode 100644 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common.c
diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile
index 54feb1ecccad..c4fcc796213c 100644
--- a/drivers/iommu/arm/arm-smmu-v3/Makefile
+++ b/drivers/iommu/arm/arm-smmu-v3/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o
arm_smmu_v3-objs-y += arm-smmu-v3.o
+arm_smmu_v3-objs-y += arm-smmu-v3-common.o
arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o
arm_smmu_v3-objs := $(arm_smmu_v3-objs-y)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 32ce835ab4eb..59e8101d4ff5 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -269,6 +269,15 @@ extern struct xarray arm_smmu_asid_xa;
extern struct mutex arm_smmu_asid_lock;
extern struct arm_smmu_ctx_desc quiet_cd;
+int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
+ unsigned int reg_off, unsigned int ack_off);
+int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr);
+int arm_smmu_device_disable(struct arm_smmu_device *smmu);
+bool arm_smmu_capable(struct device *dev, enum iommu_cap cap);
+struct iommu_group *arm_smmu_device_group(struct device *dev);
+int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args);
+int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu);
+
int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
struct arm_smmu_ctx_desc *cd);
void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common.c
new file mode 100644
index 000000000000..5e43329c0826
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-mapping.h>
+#include <linux/iopoll.h>
+#include <linux/pci.h>
+
+#include "arm-smmu-v3.h"
+
+int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
+{
+ u32 reg;
+ bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
+
+ /* IDR0 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
+
+ /* 2-level structures */
+ if (FIELD_GET(IDR0_ST_LVL, reg) == IDR0_ST_LVL_2LVL)
+ smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;
+
+ if (reg & IDR0_CD2L)
+ smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;
+
+ /*
+ * Translation table endianness.
+ * We currently require the same endianness as the CPU, but this
+ * could be changed later by adding a new IO_PGTABLE_QUIRK.
+ */
+ switch (FIELD_GET(IDR0_TTENDIAN, reg)) {
+ case IDR0_TTENDIAN_MIXED:
+ smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
+ break;
+#ifdef __BIG_ENDIAN
+ case IDR0_TTENDIAN_BE:
+ smmu->features |= ARM_SMMU_FEAT_TT_BE;
+ break;
+#else
+ case IDR0_TTENDIAN_LE:
+ smmu->features |= ARM_SMMU_FEAT_TT_LE;
+ break;
+#endif
+ default:
+ dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
+ return -ENXIO;
+ }
+
+ /* Boolean feature flags */
+ if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
+ smmu->features |= ARM_SMMU_FEAT_PRI;
+
+ if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
+ smmu->features |= ARM_SMMU_FEAT_ATS;
+
+ if (reg & IDR0_SEV)
+ smmu->features |= ARM_SMMU_FEAT_SEV;
+
+ if (reg & IDR0_MSI) {
+ smmu->features |= ARM_SMMU_FEAT_MSI;
+ if (coherent)
+ smmu->options |= ARM_SMMU_OPT_MSIPOLL;
+ }
+
+ if (reg & IDR0_HYP) {
+ smmu->features |= ARM_SMMU_FEAT_HYP;
+ if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+ smmu->features |= ARM_SMMU_FEAT_E2H;
+ }
+
+ /*
+ * The coherency feature as set by FW is used in preference to the ID
+ * register, but warn on mismatch.
+ */
+ if (!!(reg & IDR0_COHACC) != coherent)
+ dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n",
+ coherent ? "true" : "false");
+
+ switch (FIELD_GET(IDR0_STALL_MODEL, reg)) {
+ case IDR0_STALL_MODEL_FORCE:
+ smmu->features |= ARM_SMMU_FEAT_STALL_FORCE;
+ fallthrough;
+ case IDR0_STALL_MODEL_STALL:
+ smmu->features |= ARM_SMMU_FEAT_STALLS;
+ }
+
+ if (reg & IDR0_S1P)
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+
+ if (reg & IDR0_S2P)
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+
+ if (!(reg & (IDR0_S1P | IDR0_S2P))) {
+ dev_err(smmu->dev, "no translation support!\n");
+ return -ENXIO;
+ }
+
+ /* We only support the AArch64 table format at present */
+ switch (FIELD_GET(IDR0_TTF, reg)) {
+ case IDR0_TTF_AARCH32_64:
+ smmu->ias = 40;
+ fallthrough;
+ case IDR0_TTF_AARCH64:
+ break;
+ default:
+ dev_err(smmu->dev, "AArch64 table format not supported!\n");
+ return -ENXIO;
+ }
+
+ /* ASID/VMID sizes */
+ smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
+ smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;
+
+ /* IDR1 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
+ if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
+ dev_err(smmu->dev, "embedded implementation not supported\n");
+ return -ENXIO;
+ }
+
+ /* Queue sizes, capped to ensure natural alignment */
+ smmu->cmdq.q.llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_CMDQS, reg));
+ if (smmu->cmdq.q.llq.max_n_shift <= ilog2(CMDQ_BATCH_ENTRIES)) {
+ /*
+ * We don't support splitting up batches, so one batch of
+ * commands plus an extra sync needs to fit inside the command
+ * queue. There's also no way we can handle the weird alignment
+ * restrictions on the base pointer for a unit-length queue.
+ */
+ dev_err(smmu->dev, "command queue size <= %d entries not supported\n",
+ CMDQ_BATCH_ENTRIES);
+ return -ENXIO;
+ }
+
+ smmu->evtq.q.llq.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_EVTQS, reg));
+ smmu->priq.q.llq.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT,
+ FIELD_GET(IDR1_PRIQS, reg));
+
+ /* SID/SSID sizes */
+ smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
+ smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+ smmu->iommu.max_pasids = 1UL << smmu->ssid_bits;
+
+ /*
+ * 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;
+
+ /* IDR3 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
+ if (FIELD_GET(IDR3_RIL, reg))
+ smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
+
+ /* IDR5 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
+
+ /* Maximum number of outstanding stalls */
+ smmu->evtq.max_stalls = FIELD_GET(IDR5_STALL_MAX, reg);
+
+ /* Page sizes */
+ if (reg & IDR5_GRAN64K)
+ smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
+ if (reg & IDR5_GRAN16K)
+ smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
+ if (reg & IDR5_GRAN4K)
+ smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+
+ /* Input address size */
+ if (FIELD_GET(IDR5_VAX, reg) == IDR5_VAX_52_BIT)
+ smmu->features |= ARM_SMMU_FEAT_VAX;
+
+ /* Output address size */
+ switch (FIELD_GET(IDR5_OAS, reg)) {
+ case IDR5_OAS_32_BIT:
+ smmu->oas = 32;
+ break;
+ case IDR5_OAS_36_BIT:
+ smmu->oas = 36;
+ break;
+ case IDR5_OAS_40_BIT:
+ smmu->oas = 40;
+ break;
+ case IDR5_OAS_42_BIT:
+ smmu->oas = 42;
+ break;
+ case IDR5_OAS_44_BIT:
+ smmu->oas = 44;
+ break;
+ case IDR5_OAS_52_BIT:
+ smmu->oas = 52;
+ smmu->pgsize_bitmap |= 1ULL << 42; /* 4TB */
+ break;
+ default:
+ dev_info(smmu->dev,
+ "unknown output address size. Truncating to 48-bit\n");
+ fallthrough;
+ case IDR5_OAS_48_BIT:
+ smmu->oas = 48;
+ }
+
+ /* Set the DMA mask for our table walker */
+ if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
+ dev_warn(smmu->dev,
+ "failed to set DMA mask for table walker\n");
+
+ smmu->ias = max(smmu->ias, smmu->oas);
+
+ if (arm_smmu_sva_supported(smmu))
+ smmu->features |= ARM_SMMU_FEAT_SVA;
+
+ dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
+ smmu->ias, smmu->oas, smmu->features);
+ return 0;
+}
+
+int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
+ unsigned int reg_off, unsigned int ack_off)
+{
+ u32 reg;
+
+ writel_relaxed(val, smmu->base + reg_off);
+ return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
+ 1, ARM_SMMU_POLL_TIMEOUT_US);
+}
+
+/* GBPA is "special" */
+int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
+{
+ int ret;
+ u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;
+
+ ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
+ 1, ARM_SMMU_POLL_TIMEOUT_US);
+ if (ret)
+ return ret;
+
+ reg &= ~clr;
+ reg |= set;
+ writel_relaxed(reg | GBPA_UPDATE, gbpa);
+ ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
+ 1, ARM_SMMU_POLL_TIMEOUT_US);
+
+ if (ret)
+ dev_err(smmu->dev, "GBPA not responding to update\n");
+ return ret;
+}
+
+int arm_smmu_device_disable(struct arm_smmu_device *smmu)
+{
+ int ret;
+
+ ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
+ if (ret)
+ dev_err(smmu->dev, "failed to clear cr0\n");
+
+ return ret;
+}
+
+bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
+{
+ struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+ switch (cap) {
+ case IOMMU_CAP_CACHE_COHERENCY:
+ /* Assume that a coherent TCU implies coherent TBUs */
+ return master->smmu->features & ARM_SMMU_FEAT_COHERENCY;
+ case IOMMU_CAP_NOEXEC:
+ return true;
+ default:
+ return false;
+ }
+}
+
+
+struct iommu_group *arm_smmu_device_group(struct device *dev)
+{
+ struct iommu_group *group;
+
+ /*
+ * We don't support devices sharing stream IDs other than PCI RID
+ * aliases, since the necessary ID-to-device lookup becomes rather
+ * impractical given a potential sparse 32-bit stream ID space.
+ */
+ if (dev_is_pci(dev))
+ group = pci_device_group(dev);
+ else
+ group = generic_device_group(dev);
+
+ return group;
+}
+
+int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+ return iommu_fwspec_add_ids(dev, args->args, 1);
+}
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index bcbd691ca96a..08fd79f66d29 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -17,13 +17,11 @@
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io-pgtable.h>
-#include <linux/iopoll.h>
#include <linux/module.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
-#include <linux/pci.h>
#include <linux/pci-ats.h>
#include <linux/platform_device.h>
@@ -1642,8 +1640,6 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
return IRQ_HANDLED;
}
-static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
-
static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
{
u32 gerror, gerrorn, active;
@@ -1990,21 +1986,6 @@ static const struct iommu_flush_ops arm_smmu_flush_ops = {
};
/* IOMMU API */
-static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
-{
- struct arm_smmu_master *master = dev_iommu_priv_get(dev);
-
- switch (cap) {
- case IOMMU_CAP_CACHE_COHERENCY:
- /* Assume that a coherent TCU implies coherent TBUs */
- return master->smmu->features & ARM_SMMU_FEAT_COHERENCY;
- case IOMMU_CAP_NOEXEC:
- return true;
- default:
- return false;
- }
-}
-
static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
{
struct arm_smmu_domain *smmu_domain;
@@ -2698,23 +2679,6 @@ static void arm_smmu_release_device(struct device *dev)
kfree(master);
}
-static struct iommu_group *arm_smmu_device_group(struct device *dev)
-{
- struct iommu_group *group;
-
- /*
- * We don't support devices sharing stream IDs other than PCI RID
- * aliases, since the necessary ID-to-device lookup becomes rather
- * impractical given a potential sparse 32-bit stream ID space.
- */
- if (dev_is_pci(dev))
- group = pci_device_group(dev);
- else
- group = generic_device_group(dev);
-
- return group;
-}
-
static int arm_smmu_enable_nesting(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -2730,11 +2694,6 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
return ret;
}
-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)
{
@@ -3081,38 +3040,6 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
return arm_smmu_init_strtab(smmu);
}
-static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
- unsigned int reg_off, unsigned int ack_off)
-{
- u32 reg;
-
- writel_relaxed(val, smmu->base + reg_off);
- return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
- 1, ARM_SMMU_POLL_TIMEOUT_US);
-}
-
-/* GBPA is "special" */
-static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
-{
- int ret;
- u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;
-
- ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
- 1, ARM_SMMU_POLL_TIMEOUT_US);
- if (ret)
- return ret;
-
- reg &= ~clr;
- reg |= set;
- writel_relaxed(reg | GBPA_UPDATE, gbpa);
- ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
- 1, ARM_SMMU_POLL_TIMEOUT_US);
-
- if (ret)
- dev_err(smmu->dev, "GBPA not responding to update\n");
- return ret;
-}
-
static void arm_smmu_free_msis(void *data)
{
struct device *dev = data;
@@ -3258,17 +3185,6 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
return 0;
}
-static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
-{
- int ret;
-
- ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
- if (ret)
- dev_err(smmu->dev, "failed to clear cr0\n");
-
- return ret;
-}
-
static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
{
int ret;
@@ -3404,215 +3320,6 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
return 0;
}
-static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
-{
- u32 reg;
- bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
-
- /* IDR0 */
- reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
-
- /* 2-level structures */
- if (FIELD_GET(IDR0_ST_LVL, reg) == IDR0_ST_LVL_2LVL)
- smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;
-
- if (reg & IDR0_CD2L)
- smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;
-
- /*
- * Translation table endianness.
- * We currently require the same endianness as the CPU, but this
- * could be changed later by adding a new IO_PGTABLE_QUIRK.
- */
- switch (FIELD_GET(IDR0_TTENDIAN, reg)) {
- case IDR0_TTENDIAN_MIXED:
- smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
- break;
-#ifdef __BIG_ENDIAN
- case IDR0_TTENDIAN_BE:
- smmu->features |= ARM_SMMU_FEAT_TT_BE;
- break;
-#else
- case IDR0_TTENDIAN_LE:
- smmu->features |= ARM_SMMU_FEAT_TT_LE;
- break;
-#endif
- default:
- dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
- return -ENXIO;
- }
-
- /* Boolean feature flags */
- if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
- smmu->features |= ARM_SMMU_FEAT_PRI;
-
- if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
- smmu->features |= ARM_SMMU_FEAT_ATS;
-
- if (reg & IDR0_SEV)
- smmu->features |= ARM_SMMU_FEAT_SEV;
-
- if (reg & IDR0_MSI) {
- smmu->features |= ARM_SMMU_FEAT_MSI;
- if (coherent)
- smmu->options |= ARM_SMMU_OPT_MSIPOLL;
- }
-
- if (reg & IDR0_HYP) {
- smmu->features |= ARM_SMMU_FEAT_HYP;
- if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
- smmu->features |= ARM_SMMU_FEAT_E2H;
- }
-
- /*
- * The coherency feature as set by FW is used in preference to the ID
- * register, but warn on mismatch.
- */
- if (!!(reg & IDR0_COHACC) != coherent)
- dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n",
- coherent ? "true" : "false");
-
- switch (FIELD_GET(IDR0_STALL_MODEL, reg)) {
- case IDR0_STALL_MODEL_FORCE:
- smmu->features |= ARM_SMMU_FEAT_STALL_FORCE;
- fallthrough;
- case IDR0_STALL_MODEL_STALL:
- smmu->features |= ARM_SMMU_FEAT_STALLS;
- }
-
- if (reg & IDR0_S1P)
- smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
-
- if (reg & IDR0_S2P)
- smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
-
- if (!(reg & (IDR0_S1P | IDR0_S2P))) {
- dev_err(smmu->dev, "no translation support!\n");
- return -ENXIO;
- }
-
- /* We only support the AArch64 table format at present */
- switch (FIELD_GET(IDR0_TTF, reg)) {
- case IDR0_TTF_AARCH32_64:
- smmu->ias = 40;
- fallthrough;
- case IDR0_TTF_AARCH64:
- break;
- default:
- dev_err(smmu->dev, "AArch64 table format not supported!\n");
- return -ENXIO;
- }
-
- /* ASID/VMID sizes */
- smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
- smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;
-
- /* IDR1 */
- reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
- if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
- dev_err(smmu->dev, "embedded implementation not supported\n");
- return -ENXIO;
- }
-
- /* Queue sizes, capped to ensure natural alignment */
- smmu->cmdq.q.llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_CMDQS, reg));
- if (smmu->cmdq.q.llq.max_n_shift <= ilog2(CMDQ_BATCH_ENTRIES)) {
- /*
- * We don't support splitting up batches, so one batch of
- * commands plus an extra sync needs to fit inside the command
- * queue. There's also no way we can handle the weird alignment
- * restrictions on the base pointer for a unit-length queue.
- */
- dev_err(smmu->dev, "command queue size <= %d entries not supported\n",
- CMDQ_BATCH_ENTRIES);
- return -ENXIO;
- }
-
- smmu->evtq.q.llq.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_EVTQS, reg));
- smmu->priq.q.llq.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT,
- FIELD_GET(IDR1_PRIQS, reg));
-
- /* SID/SSID sizes */
- smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
- smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
- smmu->iommu.max_pasids = 1UL << smmu->ssid_bits;
-
- /*
- * 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;
-
- /* IDR3 */
- reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
- if (FIELD_GET(IDR3_RIL, reg))
- smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
-
- /* IDR5 */
- reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
-
- /* Maximum number of outstanding stalls */
- smmu->evtq.max_stalls = FIELD_GET(IDR5_STALL_MAX, reg);
-
- /* Page sizes */
- if (reg & IDR5_GRAN64K)
- smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
- if (reg & IDR5_GRAN16K)
- smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
- if (reg & IDR5_GRAN4K)
- smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
-
- /* Input address size */
- if (FIELD_GET(IDR5_VAX, reg) == IDR5_VAX_52_BIT)
- smmu->features |= ARM_SMMU_FEAT_VAX;
-
- /* Output address size */
- switch (FIELD_GET(IDR5_OAS, reg)) {
- case IDR5_OAS_32_BIT:
- smmu->oas = 32;
- break;
- case IDR5_OAS_36_BIT:
- smmu->oas = 36;
- break;
- case IDR5_OAS_40_BIT:
- smmu->oas = 40;
- break;
- case IDR5_OAS_42_BIT:
- smmu->oas = 42;
- break;
- case IDR5_OAS_44_BIT:
- smmu->oas = 44;
- break;
- case IDR5_OAS_52_BIT:
- smmu->oas = 52;
- smmu->pgsize_bitmap |= 1ULL << 42; /* 4TB */
- break;
- default:
- dev_info(smmu->dev,
- "unknown output address size. Truncating to 48-bit\n");
- fallthrough;
- case IDR5_OAS_48_BIT:
- smmu->oas = 48;
- }
-
- /* Set the DMA mask for our table walker */
- if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
- dev_warn(smmu->dev,
- "failed to set DMA mask for table walker\n");
-
- smmu->ias = max(smmu->ias, smmu->oas);
-
- if (arm_smmu_sva_supported(smmu))
- smmu->features |= ARM_SMMU_FEAT_SVA;
-
- dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
- smmu->ias, smmu->oas, smmu->features);
- return 0;
-}
-
#ifdef CONFIG_ACPI
static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu)
{
--
2.39.0
More information about the linux-arm-kernel
mailing list