[PATCH v3 2/2] KVM: arm64: ptdump: Fix shadow ptdump sleep-in-atomic-context problem

[Wei-Lin Chang]

Previously we exposed shadow page tables by creating a debugfs ptdump
file whenever a nested mmu instance gets bound to a new context, and
deleting the debugfs file whose context was getting unbound.

This turned out to be buggy, as the instance<->context binding process
is done with the mmu_lock held, and debugfs creation/deletion can sleep.

Change the approach and create a shadow ptdump file for each nested mmu
instead during kvm_vcpu_init_nested(), in a sleepable context. The files
will be named nested_mmu<index>, and reading it will return the nested
context's VTTBR, VTCR, and s2 enabled or not before dumping the shadow
page tables, given the nested mmu is valid.

Fixes: 19e15dc73f0f ("KVM: arm64: nv: Expose shadow page tables in debugfs")
Reported-by: Itaru Kitayama <itaru.kitayama at fujitsu.com>
Closes: https://lore.kernel.org/kvmarm/aiuF0KSvvv-ZozI1@sm-arm-grace07/
Signed-off-by: Wei-Lin Chang <weilin.chang at arm.com>
Cc: stable at vger.kernel.org
---
 arch/arm64/include/asm/kvm_host.h |  4 ----
 arch/arm64/include/asm/kvm_mmu.h  |  6 ++----
 arch/arm64/kvm/nested.c           |  9 ++++-----
 arch/arm64/kvm/ptdump.c           | 32 +++++++++++++++----------------
 4 files changed, 21 insertions(+), 30 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index cd9b9d2462f9..db177af9149f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -217,10 +217,6 @@ struct kvm_s2_mmu {
 	 */
 	bool	nested_stage2_enabled;
 
-#ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
-	struct dentry *shadow_pt_debugfs_dentry;
-#endif
-
 	/*
 	 * true when this MMU needs to be unmapped before being used for a new
 	 * purpose.
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6eae7e7e2a68..ac2b0637692a 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -392,12 +392,10 @@ static inline bool kvm_supports_cacheable_pfnmap(void)
 
 #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
 void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
-void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu);
-void kvm_nested_s2_ptdump_remove_debugfs(struct kvm_s2_mmu *mmu);
+void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu, int idx);
 #else
 static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {}
-static inline void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu) {}
-static inline void kvm_nested_s2_ptdump_remove_debugfs(struct kvm_s2_mmu *mmu) {}
+static inline void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu, int idx) {}
 #endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */
 
 #endif /* __ASSEMBLER__ */
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index b191365d97cc..41253fe45941 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -124,6 +124,9 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 			return ret;
 		}
 
+		for (i = 0; i < S2_MMU_PER_VCPU; i++)
+			kvm_nested_s2_ptdump_create_debugfs(&tmp[i], i + kvm->arch.nested_mmus_size);
+
 		guard(write_lock)(&kvm->mmu_lock);
 
 		for (i = 0; i < S2_MMU_PER_VCPU; i++)
@@ -837,10 +840,8 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
 
 	/* Make sure we don't forget to do the laundry */
-	if (kvm_s2_mmu_valid(s2_mmu)) {
-		kvm_nested_s2_ptdump_remove_debugfs(s2_mmu);
+	if (kvm_s2_mmu_valid(s2_mmu))
 		s2_mmu->pending_unmap = true;
-	}
 
 	/*
 	 * The virtual VMID (modulo CnP) will be used as a key when matching
@@ -854,8 +855,6 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 	s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
 	s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
 
-	kvm_nested_s2_ptdump_create_debugfs(s2_mmu);
-
 out:
 	atomic_inc(&s2_mmu->refcnt);
 
diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c
index 4ead856c181a..9411d6c2dafb 100644
--- a/arch/arm64/kvm/ptdump.c
+++ b/arch/arm64/kvm/ptdump.c
@@ -17,7 +17,7 @@
 
 #define MARKERS_LEN		2
 #define KVM_PGTABLE_MAX_LEVELS	(KVM_PGTABLE_LAST_LEVEL + 1)
-#define S2FNAMESZ		sizeof("0x0123456789abcdef-0x0123456789abcdef-s2-disabled")
+#define S2FNAMESZ		sizeof("nested_mmu0000")
 
 struct kvm_ptdump_guest_state {
 	struct kvm_s2_mmu	*mmu;
@@ -173,6 +173,15 @@ static int kvm_ptdump_guest_show(struct seq_file *m, void *unused)
 		.seq		= m,
 	};
 
+	if (kvm_is_nested_s2_mmu(kvm, mmu)) {
+		if (kvm_s2_mmu_valid(mmu))
+			seq_printf(m, "VTCR: 0x%016llx VTTBR: 0x%016llx s2: %s\n",
+				   mmu->tlb_vtcr, mmu->tlb_vttbr,
+				   mmu->nested_stage2_enabled ? "enabled" : "disabled");
+		else
+			return 0;
+	}
+
 	ret = kvm_pgtable_walk(mmu->pgt, 0, BIT(mmu->pgt->ia_bits), &walker);
 	if (ret)
 		return ret;
@@ -299,26 +308,15 @@ static const struct file_operations kvm_pgtable_levels_fops = {
 	.release	= kvm_pgtable_debugfs_close,
 };
 
-void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu)
+void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu, int idx)
 {
-	struct dentry *dent;
 	char file_name[S2FNAMESZ];
 
-	snprintf(file_name, sizeof(file_name), "0x%016llx-0x%016llx-s2-%sabled",
-		 mmu->tlb_vttbr,
-		 mmu->tlb_vtcr,
-		 mmu->nested_stage2_enabled ? "en" : "dis");
-
-	dent = debugfs_create_file(file_name, 0400,
-				   mmu->arch->debugfs_nv_dentry, mmu,
-				   &kvm_ptdump_guest_fops);
+	snprintf(file_name, sizeof(file_name), "nested_mmu%d", idx);
 
-	mmu->shadow_pt_debugfs_dentry = dent;
-}
-
-void kvm_nested_s2_ptdump_remove_debugfs(struct kvm_s2_mmu *mmu)
-{
-	debugfs_remove(mmu->shadow_pt_debugfs_dentry);
+	debugfs_create_file(file_name, 0400,
+			    mmu->arch->debugfs_nv_dentry, mmu,
+			    &kvm_ptdump_guest_fops);
 }
 
 void kvm_s2_ptdump_create_debugfs(struct kvm *kvm)
-- 
2.43.0