mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: fangyu.yu@linux.alibaba.com
To: tomasz.jeznach@linux.dev, joro@8bytes.org, will@kernel.org,
	robin.murphy@arm.com, pjw@kernel.org, palmer@dabbelt.com,
	aou@eecs.berkeley.edu, alex@ghiti.fr, baolu.lu@linux.intel.com,
	jroedel@suse.de, zong.li@sifive.com,
	andrew.jones@oss.qualcomm.com, anup@brainfault.org,
	jgg@nvidia.com, jgg@ziepe.ca, kevin.tian@intel.com,
	atish.patra@linux.dev, skhawaja@google.com, vasant.hegde@amd.com,
	joerg.roedel@amd.com
Cc: fangyu.yu@linux.alibaba.com, guoren@kernel.org,
	iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
	linux-riscv@lists.infradead.org, kvm-riscv@lists.infradead.org
Subject: [RFC PATCH v4 01/10] iommupt: Add RISC-V Second-stage (iohgatp) page table support
Date: Tue, 15 Sep 2026 11:28:20 +0800	[thread overview]
Message-ID: <20260915032828.11250-2-fangyu.yu@linux.alibaba.com> (raw)
In-Reply-To: <20260915032828.11250-1-fangyu.yu@linux.alibaba.com>

From: Fangyu Yu <fangyu.yu@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@linux.alibaba.com>
---
 drivers/iommu/generic_pt/fmt/iommu_riscv64.c |   2 +-
 drivers/iommu/generic_pt/fmt/riscv.h         | 109 +++++++++++++++----
 include/linux/generic_pt/common.h            |   4 +
 include/linux/generic_pt/iommu.h             |  11 ++
 4 files changed, 102 insertions(+), 24 deletions(-)

diff --git a/drivers/iommu/generic_pt/fmt/iommu_riscv64.c b/drivers/iommu/generic_pt/fmt/iommu_riscv64.c
index 1bb74114fb02..fa61839e5599 100644
--- a/drivers/iommu/generic_pt/fmt/iommu_riscv64.c
+++ b/drivers/iommu/generic_pt/fmt/iommu_riscv64.c
@@ -8,7 +8,7 @@
 	(BIT(PT_FEAT_SIGN_EXTEND) | BIT(PT_FEAT_FLUSH_RANGE) | \
 	 BIT(PT_FEAT_RISCV_SVNAPOT_64K) |                      \
 	 BIT(PT_FEAT_DETAILED_GATHER) |                        \
-	 BIT(PT_FEAT_RISCV_SVPBMT))
+	 BIT(PT_FEAT_RISCV_SVPBMT) | BIT(PT_FEAT_RISCV_S2))
 #define PT_FORCE_ENABLED_FEATURES BIT(PT_FEAT_DETAILED_GATHER)
 
 #include "iommu_template.h"
diff --git a/drivers/iommu/generic_pt/fmt/riscv.h b/drivers/iommu/generic_pt/fmt/riscv.h
index ae9a76514416..d4445e463fa9 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
@@ -126,6 +135,12 @@ riscvpt_entry_num_contig_lg2(const struct pt_state *pts)
 
 static inline unsigned int riscvpt_num_items_lg2(const struct pt_state *pts)
 {
+	/*
+	 * It is not allowed to call pt_num_items_lg2() at the top level, this
+	 * API restriction is specifically an optimization avoid overheads
+	 * dealing with concatenated tables here.
+	 */
+	PT_WARN_ON(pts->level == pts->range->top_level);
 	return PT_TABLEMEM_LG2SZ - ilog2(sizeof(u64));
 }
 #define pt_num_items_lg2 riscvpt_num_items_lg2
@@ -261,20 +276,41 @@ riscvpt_iommu_fmt_init(struct pt_iommu_riscv_64 *iommu_table,
 		       const struct pt_iommu_riscv_64_cfg *cfg)
 {
 	struct pt_riscv *table = &iommu_table->riscv_64pt;
-
-	switch (cfg->common.hw_max_vasz_lg2) {
-	case 39:
-		pt_top_set_level(&table->common, 2);
-		break;
-	case 48:
-		pt_top_set_level(&table->common, 3);
-		break;
-	case 57:
-		pt_top_set_level(&table->common, 4);
-		break;
-	default:
-		return -EINVAL;
+	unsigned int top_level;
+
+	if (pt_feature(&table->common, PT_FEAT_RISCV_S2)) {
+		/* Second-stage (iohgatp): Sv39x4 / Sv48x4 / Sv57x4. */
+		switch (cfg->common.hw_max_vasz_lg2) {
+		case 41:
+			top_level = 2;
+			break;
+		case 50:
+			top_level = 3;
+			break;
+		case 59:
+			top_level = 4;
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		/* First-stage (fsc/iosatp): Sv39 / Sv48 / Sv57. */
+		switch (cfg->common.hw_max_vasz_lg2) {
+		case 39:
+			top_level = 2;
+			break;
+		case 48:
+			top_level = 3;
+			break;
+		case 57:
+			top_level = 4;
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
+
+	pt_top_set_level(&table->common, top_level);
 	table->common.max_oasz_lg2 =
 		min(PT_MAX_OUTPUT_ADDRESS_LG2, cfg->common.hw_max_oasz_lg2);
 	return 0;
@@ -292,30 +328,57 @@ 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)
+	 *
+	 * 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;
+	if (pt_feature(&table->riscv_64pt.common, PT_FEAT_RISCV_S2))
+		info->iohgatp_mode = top_range->top_level + 6;
+	else
+		info->fsc_iosatp_mode = top_range->top_level + 6;
 }
 #define pt_iommu_fmt_hw_info riscvpt_iommu_fmt_hw_info
 
 #if defined(GENERIC_PT_KUNIT)
 static const struct pt_iommu_riscv_64_cfg riscv_64_kunit_fmt_cfgs[] = {
-	[0] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+	/* First-stage (fsc/iosatp): Sv39 / Sv48 / Sv57 */
+	[0] = { .common.features = BIT(PT_FEAT_SIGN_EXTEND) |
+				      BIT(PT_FEAT_RISCV_SVNAPOT_64K),
 		.common.hw_max_oasz_lg2 = 56,
 		.common.hw_max_vasz_lg2 = 39 },
-	[1] = { .common.features = 0,
+	[1] = { .common.features = BIT(PT_FEAT_SIGN_EXTEND),
 		.common.hw_max_oasz_lg2 = 56,
 		.common.hw_max_vasz_lg2 = 48 },
-	[2] = { .common.features = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+	[2] = { .common.features = BIT(PT_FEAT_SIGN_EXTEND) |
+				      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_S2) |
+				      BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+		.common.hw_max_oasz_lg2 = 56,
+		.common.hw_max_vasz_lg2 = 41 },
+	[4] = { .common.features = BIT(PT_FEAT_RISCV_S2),
+		.common.hw_max_oasz_lg2 = 56,
+		.common.hw_max_vasz_lg2 = 50 },
+	[5] = { .common.features = BIT(PT_FEAT_RISCV_S2) |
+				      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
+/* Sign extension is only valid for first-stage configs, not S2. */
 enum {
-	KUNIT_FMT_FEATURES = BIT(PT_FEAT_RISCV_SVNAPOT_64K),
+	KUNIT_FMT_FEATURES = BIT(PT_FEAT_SIGN_EXTEND) |
+			     BIT(PT_FEAT_RISCV_SVNAPOT_64K) |
+			     BIT(PT_FEAT_RISCV_S2),
 };
 #endif
 
diff --git a/include/linux/generic_pt/common.h b/include/linux/generic_pt/common.h
index 07ef1c8341a4..f2e130c2b804 100644
--- a/include/linux/generic_pt/common.h
+++ b/include/linux/generic_pt/common.h
@@ -197,6 +197,10 @@ enum {
 	 * Support Svpbmt extension: encode page-based memory type (PBMT) in PTEs.
 	 */
 	PT_FEAT_RISCV_SVPBMT,
+	/*
+	 * Using second-stage / iohgatp address translation.
+	 */
+	PT_FEAT_RISCV_S2,
 
 };
 
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
index dd0edd02a48a..2eed9b78f56c 100644
--- a/include/linux/generic_pt/iommu.h
+++ b/include/linux/generic_pt/iommu.h
@@ -328,7 +328,18 @@ struct pt_iommu_riscv_64_cfg {
 
 struct pt_iommu_riscv_64_hw_info {
 	u64 ppn;
+	/*
+	 * 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.
+	 */
+	u8 iohgatp_mode;
 };
 
 IOMMU_FORMAT(riscv_64, riscv_64pt);
-- 
2.50.1


  reply	other threads:[~2026-09-15  3:28 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-15  3:28 [RFC PATCH v4 00/10] iommu/riscv: Add hardware dirty tracking for second-stage domains fangyu.yu
2026-09-15  3:28 ` fangyu.yu [this message]
2026-09-15  3:28 ` [RFC PATCH v4 02/10] iommupt: Add RISC-V dirty tracking PTE ops fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 03/10] iommu/riscv: report iommu capabilities fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 04/10] iommu/riscv: use data structure instead of individual values fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 05/10] iommu/riscv: support GSCID and GVMA invalidation command fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 06/10] RISC-V: KVM: Enable KVM_VFIO interfaces on RISC-V arch fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 07/10] iommu/riscv: Add domain_alloc_paging_flags for second-stage domain fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 08/10] iommu/riscv: Pre-enable GADE for second-stage domains fangyu.yu
2026-09-15  3:28 ` [RFC PATCH v4 09/10] iommu/riscv: Add dirty tracking support " fangyu.yu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260915032828.11250-2-fangyu.yu@linux.alibaba.com \
    --to=fangyu.yu@linux.alibaba.com \
    --cc=alex@ghiti.fr \
    --cc=andrew.jones@oss.qualcomm.com \
    --cc=anup@brainfault.org \
    --cc=aou@eecs.berkeley.edu \
    --cc=atish.patra@linux.dev \
    --cc=baolu.lu@linux.intel.com \
    --cc=guoren@kernel.org \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@nvidia.com \
    --cc=jgg@ziepe.ca \
    --cc=joerg.roedel@amd.com \
    --cc=joro@8bytes.org \
    --cc=jroedel@suse.de \
    --cc=kevin.tian@intel.com \
    --cc=kvm-riscv@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@dabbelt.com \
    --cc=pjw@kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=skhawaja@google.com \
    --cc=tomasz.jeznach@linux.dev \
    --cc=vasant.hegde@amd.com \
    --cc=will@kernel.org \
    --cc=zong.li@sifive.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®