[RFC PATCH v2 01/10] iommupt: Add RISC-V Second-stage (iohgatp) page table support
fangyu.yu at linux.alibaba.com
fangyu.yu at linux.alibaba.com
Thu May 7 04:36:57 PDT 2026
From: Fangyu Yu <fangyu.yu at linux.alibaba.com>
Add support for Sv39x4/Sv48x4/Sv57x4 Second-stage page tables used by
the RISC-V IOMMU iohgatp register. The x4 root page table is 16 KiB
instead of the usual 4 KiB, covering 2 extra GPA bits (hw_max_vasz_lg2
= 41/50/59).
Signed-off-by: Fangyu Yu <fangyu.yu at linux.alibaba.com>
---
drivers/iommu/generic_pt/fmt/riscv.h | 61 +++++++++++++++++++++++++---
include/linux/generic_pt/common.h | 5 ++-
include/linux/generic_pt/iommu.h | 17 +++++++-
3 files changed, 76 insertions(+), 7 deletions(-)
diff --git a/drivers/iommu/generic_pt/fmt/riscv.h b/drivers/iommu/generic_pt/fmt/riscv.h
index a7fef6266a36..777887335696 100644
--- a/drivers/iommu/generic_pt/fmt/riscv.h
+++ b/drivers/iommu/generic_pt/fmt/riscv.h
@@ -37,7 +37,16 @@ enum {
PT_MAX_OUTPUT_ADDRESS_LG2 = 34,
PT_MAX_TOP_LEVEL = 1,
#else
- PT_MAX_VA_ADDRESS_LG2 = 57,
+ /*
+ * PT_MAX_VA_ADDRESS_LG2 is the upper bound accepted by the generic
+ * pt_iommu_init() range check. It must cover both first-stage and
+ * second-stage (G-stage) modes:
+ *
+ * First-stage (fsc/iosatp): Sv39=39, Sv48=48, Sv57=57
+ * Second-stage (iohgatp): Sv39x4=41, Sv48x4=50, Sv57x4=59
+ *
+ */
+ PT_MAX_VA_ADDRESS_LG2 = 59,
PT_MAX_OUTPUT_ADDRESS_LG2 = 56,
PT_MAX_TOP_LEVEL = 4,
#endif
@@ -124,6 +133,14 @@ riscvpt_entry_num_contig_lg2(const struct pt_state *pts)
static inline unsigned int riscvpt_num_items_lg2(const struct pt_state *pts)
{
+ /*
+ * Second-stage (iohgatp) root page tables have 4x the usual number of
+ * entries (2048 = 2^11 instead of 512 = 2^9) to cover the 2 extra GPA
+ * bits in Sv39x4/Sv48x4/Sv57x4. Only the root (top) level is
+ * enlarged; all other levels remain at the standard 9-bit index width.
+ */
+ if (pts_feature(pts, PT_FEAT_RISCV_S2) && pts->level == pts->range->top_level)
+ return PT_TABLEMEM_LG2SZ - ilog2(sizeof(u64)) + 2;
return PT_TABLEMEM_LG2SZ - ilog2(sizeof(u64));
}
#define pt_num_items_lg2 riscvpt_num_items_lg2
@@ -254,6 +271,7 @@ riscvpt_iommu_fmt_init(struct pt_iommu_riscv_64 *iommu_table,
struct pt_riscv *table = &iommu_table->riscv_64pt;
switch (cfg->common.hw_max_vasz_lg2) {
+ /* First-stage (fsc/iosatp): Sv39 / Sv48 / Sv57 */
case 39:
pt_top_set_level(&table->common, 2);
break;
@@ -263,6 +281,19 @@ riscvpt_iommu_fmt_init(struct pt_iommu_riscv_64 *iommu_table,
case 57:
pt_top_set_level(&table->common, 4);
break;
+ /*
+ * Second-stage (iohgatp): Sv39x4 / Sv48x4 / Sv57x4.
+ * The top level is the same as for the first-stage counterpart.
+ */
+ case 41:
+ pt_top_set_level(&table->common, 2);
+ break;
+ case 50:
+ pt_top_set_level(&table->common, 3);
+ break;
+ case 59:
+ pt_top_set_level(&table->common, 4);
+ break;
default:
return -EINVAL;
}
@@ -283,10 +314,17 @@ riscvpt_iommu_fmt_hw_info(struct pt_iommu_riscv_64 *table,
PT_WARN_ON(top_phys & ~PT_TOP_PHYS_MASK);
/*
- * See Table 3. Encodings of iosatp.MODE field" for DC.tx.SXL = 0:
- * 8 = Sv39 = top level 2
- * 9 = Sv38 = top level 3
- * 10 = Sv57 = top level 4
+ * Both first-stage (fsc/iosatp) and second-stage (iohgatp) share the
+ * same MODE numeric values for a given top level:
+ * top_level 2 -> MODE 8 (Sv39 / Sv39x4)
+ * top_level 3 -> MODE 9 (Sv48 / Sv48x4)
+ * top_level 4 -> MODE 10 (Sv57 / Sv57x4)
+ *
+ * The union members fsc_iosatp_mode and iohgatp_mode occupy the same
+ * byte; the caller selects the appropriate name based on domain type.
+ *
+ * See "Table 3. Encodings of iosatp.MODE field" (DC.tc.SXL = 0) and
+ * "Table 2. Encoding of iohgatp.MODE field" in the RISC-V IOMMU spec.
*/
info->fsc_iosatp_mode = top_range->top_level + 6;
}
@@ -294,6 +332,7 @@ riscvpt_iommu_fmt_hw_info(struct pt_iommu_riscv_64 *table,
#if defined(GENERIC_PT_KUNIT)
static const struct pt_iommu_riscv_64_cfg riscv_64_kunit_fmt_cfgs[] = {
+ /* First-stage (fsc/iosatp): Sv39 / Sv48 / Sv57 */
[0] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
.common.hw_max_oasz_lg2 = 56,
.common.hw_max_vasz_lg2 = 39 },
@@ -303,6 +342,18 @@ static const struct pt_iommu_riscv_64_cfg riscv_64_kunit_fmt_cfgs[] = {
[2] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
.common.hw_max_oasz_lg2 = 56,
.common.hw_max_vasz_lg2 = 57 },
+ /*
+ * Second-stage (iohgatp): Sv39x4 / Sv48x4 / Sv57x4.
+ */
+ [3] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+ .common.hw_max_oasz_lg2 = 56,
+ .common.hw_max_vasz_lg2 = 41 },
+ [4] = { .common.features = 0,
+ .common.hw_max_oasz_lg2 = 56,
+ .common.hw_max_vasz_lg2 = 50 },
+ [5] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+ .common.hw_max_oasz_lg2 = 56,
+ .common.hw_max_vasz_lg2 = 59 },
};
#define kunit_fmt_cfgs riscv_64_kunit_fmt_cfgs
enum {
diff --git a/include/linux/generic_pt/common.h b/include/linux/generic_pt/common.h
index fc5d0b5edadc..59448125159e 100644
--- a/include/linux/generic_pt/common.h
+++ b/include/linux/generic_pt/common.h
@@ -188,7 +188,10 @@ enum {
* Support the 64k contiguous page size following the Svnapot extension.
*/
PT_FEAT_RISCV_SVNAPOT_64K = PT_FEAT_FMT_START,
-
+ /*
+ * Using second-stage / iohgatp address translation.
+ */
+ PT_FEAT_RISCV_S2,
};
struct pt_x86_64 {
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
index dd0edd02a48a..f27d229ff318 100644
--- a/include/linux/generic_pt/iommu.h
+++ b/include/linux/generic_pt/iommu.h
@@ -328,7 +328,22 @@ struct pt_iommu_riscv_64_cfg {
struct pt_iommu_riscv_64_hw_info {
u64 ppn;
- u8 fsc_iosatp_mode;
+ union {
+ /*
+ * First-stage (fsc/iosatp) MODE encoding:
+ * 8 = Sv39, 9 = Sv48, 10 = Sv57
+ * Used to program DC.fsc.iosatp.MODE.
+ */
+ u8 fsc_iosatp_mode;
+ /*
+ * Second-stage (iohgatp) MODE encoding:
+ * 8 = Sv39x4, 9 = Sv48x4, 10 = Sv57x4
+ * Used to program DC.iohgatp.MODE.
+ * The numeric values are identical to fsc_iosatp_mode;
+ * the caller selects the interpretation based on domain type.
+ */
+ u8 iohgatp_mode;
+ };
};
IOMMU_FORMAT(riscv_64, riscv_64pt);
--
2.50.1
More information about the linux-riscv
mailing list