[SUGGESTION] KVM: RISC-V: detect gstage mode hierarchy

[Radim Krčmář]

2026-01-29T15:27:35+00:00, Radim Krčmář <radim.krcmar at oss.qualcomm.com>:
> (I'll reply with a patch later.)

Something like this would avoid a bit of technical debt.
The solution could be even more generic by returning a bitmap of
supported modes, but that would be larger refactoring...

Feel free to use it in the series, but beware: only compile-tested.
It's late and hope it at least boots. :)

Thanks.
---8<---
RISC-V ISA does not require a hierarchy of standard hgatp mode (i.e.
57x4 does not depend on 48x4 onr 39x4), yet future patches want to
assume that the hierarchy exists, for simplicity.

Only accept a hgatp mode if all narrower modes are supported as well.

All sensible RISC-V implementations should have the hierarchy, since
it's very cheap to add the narrower modes.

Signed-off-by: Radim Krčmář <rkrcmar at oss.qualcomm.com>
---
The hunk that removes the default values at the beginning of gstage.c
should have been a separate patch, sorry.
---
 arch/riscv/include/asm/kvm_gstage.h |  2 +-
 arch/riscv/kvm/gstage.c             | 66 ++++++++++++-----------------
 arch/riscv/kvm/main.c               |  6 ++-
 3 files changed, 32 insertions(+), 42 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_gstage.h b/arch/riscv/include/asm/kvm_gstage.h
index 595e2183173e..18db474ce583 100644
--- a/arch/riscv/include/asm/kvm_gstage.h
+++ b/arch/riscv/include/asm/kvm_gstage.h
@@ -67,6 +67,6 @@ void kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage,
 
 void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end);
 
-void kvm_riscv_gstage_mode_detect(void);
+unsigned long kvm_riscv_gstage_mode_detect(void);
 
 #endif
diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
index b67d60d722c2..678b304553bc 100644
--- a/arch/riscv/kvm/gstage.c
+++ b/arch/riscv/kvm/gstage.c
@@ -11,13 +11,8 @@
 #include <linux/pgtable.h>
 #include <asm/kvm_gstage.h>
 
-#ifdef CONFIG_64BIT
-unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV39X4;
-unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 3;
-#else
-unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV32X4;
-unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 2;
-#endif
+unsigned long kvm_riscv_gstage_mode __ro_after_init;
+unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init;
 
 #define gstage_pte_leaf(__ptep)	\
 	(pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC))
@@ -313,47 +308,38 @@ void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end
 	}
 }
 
-void __init kvm_riscv_gstage_mode_detect(void)
+static inline unsigned long __init __kvm_riscv_gstage_mode_detect(void)
 {
 #ifdef CONFIG_64BIT
-	/* Try Sv57x4 G-stage mode */
-	csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT);
-	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV57X4;
-		kvm_riscv_gstage_pgd_levels = 5;
-		goto done;
-	}
-
-	/* Try Sv48x4 G-stage mode */
-	csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
-	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV48X4;
-		kvm_riscv_gstage_pgd_levels = 4;
-		goto done;
-	}
-
-	/* Try Sv39x4 G-stage mode */
 	csr_write(CSR_HGATP, HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
-	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV39X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV39X4;
-		kvm_riscv_gstage_pgd_levels = 3;
-		goto done;
-	}
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) != HGATP_MODE_SV39X4)
+		return HGATP_MODE_OFF;
+
+	csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) != HGATP_MODE_SV48X4)
+		return HGATP_MODE_SV39X4;
+
+	csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT);
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) != HGATP_MODE_SV57X4)
+		return HGATP_MODE_SV48X4;
+
+	return HGATP_MODE_SV57X4;
 #else /* CONFIG_32BIT */
-	/* Try Sv32x4 G-stage mode */
 	csr_write(CSR_HGATP, HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
-	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV32X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV32X4;
-		kvm_riscv_gstage_pgd_levels = 2;
-		goto done;
-	}
+	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) != HGATP_MODE_SV32X4)
+		return HGATP_MODE_OFF;
+
+	return HGATP_MODE_SV32X4;
 #endif
+}
 
-	/* KVM depends on !HGATP_MODE_OFF */
-	kvm_riscv_gstage_mode = HGATP_MODE_OFF;
-	kvm_riscv_gstage_pgd_levels = 0;
+/* We could probably omit the HGATP write and fence. */
+unsigned long __init kvm_riscv_gstage_mode_detect(void)
+{
+	unsigned long gstage_mode = __kvm_riscv_gstage_mode_detect();
 
-done:
 	csr_write(CSR_HGATP, 0);
 	kvm_riscv_local_hfence_gvma_all();
+
+	return gstage_mode;
 }
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index 45536af521f0..58fd6ae8e04a 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -104,19 +104,23 @@ static int __init riscv_kvm_init(void)
 	if (rc && rc != -ENODEV)
 		return rc;
 
-	kvm_riscv_gstage_mode_detect();
+	kvm_riscv_gstage_mode = kvm_riscv_gstage_mode_detect();
 	switch (kvm_riscv_gstage_mode) {
 	case HGATP_MODE_SV32X4:
 		str = "Sv32x4";
+		kvm_riscv_gstage_pgd_levels = 2;
 		break;
 	case HGATP_MODE_SV39X4:
 		str = "Sv39x4";
+		kvm_riscv_gstage_pgd_levels = 3;
 		break;
 	case HGATP_MODE_SV48X4:
 		str = "Sv48x4";
+		kvm_riscv_gstage_pgd_levels = 4;
 		break;
 	case HGATP_MODE_SV57X4:
 		str = "Sv57x4";
+		kvm_riscv_gstage_pgd_levels = 5;
 		break;
 	default:
 		kvm_riscv_nacl_exit();
-- 
2.51.0