All of lore.kernel.org
 help / color / mirror / Atom feed
From: Quentin Perret <qperret@google.com>
To: maz@kernel.org, james.morse@arm.com, alexandru.elisei@arm.com,
	suzuki.poulose@arm.com, catalin.marinas@arm.com, will@kernel.org
Cc: linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, linux-kernel@vger.kernel.org,
	ardb@kernel.org, qwandor@google.com, tabba@google.com,
	dbrazdil@google.com, kernel-team@android.com,
	Quentin Perret <qperret@google.com>
Subject: [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode
Date: Thu, 29 Jul 2021 14:28:17 +0100	[thread overview]
Message-ID: <20210729132818.4091769-21-qperret@google.com> (raw)
In-Reply-To: <20210729132818.4091769-1-qperret@google.com>

The host kernel is currently able to change EL2 stage-1 mappings without
restrictions thanks to the __pkvm_create_mappings() hypercall. But in a
world where the host is no longer part of the TCB, this clearly poses a
problem.

To fix this, introduce a new hypercall to allow the host to share a
physical memory page with the hypervisor, and remove the
__pkvm_create_mappings() variant. The new hypercall implements
ownership and permission checks before allowing the sharing operation,
and it annotates the shared page in the hypervisor stage-1 and host
stage-2 page-tables.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  2 +-
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 11 +--
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 89 +++++++++++++++++++
 arch/arm64/kvm/mmu.c                          | 28 +++++-
 5 files changed, 119 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 432a9ea1f02e..aed2aa61766a 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -59,7 +59,7 @@
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs		13
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs		14
 #define __KVM_HOST_SMCCC_FUNC___pkvm_init			15
-#define __KVM_HOST_SMCCC_FUNC___pkvm_create_mappings		16
+#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp		16
 #define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping	17
 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector		18
 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize		19
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 7ce36fbf5158..3d78d7782f1b 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -49,6 +49,7 @@ extern struct host_kvm host_kvm;
 extern const u8 pkvm_hyp_id;
 
 int __pkvm_prot_finalize(void);
+int __pkvm_host_share_hyp(u64 pfn);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(u64 start, u64 end, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 7900d5b66ba3..2da6aa8da868 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -140,14 +140,11 @@ static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot);
 }
 
-static void handle___pkvm_create_mappings(struct kvm_cpu_context *host_ctxt)
+static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt)
 {
-	DECLARE_REG(unsigned long, start, host_ctxt, 1);
-	DECLARE_REG(unsigned long, size, host_ctxt, 2);
-	DECLARE_REG(unsigned long, phys, host_ctxt, 3);
-	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4);
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
 
-	cpu_reg(host_ctxt, 1) = __pkvm_create_mappings(start, size, phys, prot);
+	cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn);
 }
 
 static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt)
@@ -185,7 +182,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__vgic_v3_restore_aprs),
 	HANDLE_FUNC(__pkvm_init),
 	HANDLE_FUNC(__pkvm_cpu_set_vector),
-	HANDLE_FUNC(__pkvm_create_mappings),
+	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_create_private_mapping),
 	HANDLE_FUNC(__pkvm_prot_finalize),
 };
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 0ccea58df7e0..1b67f562b6fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -338,6 +338,95 @@ static int host_stage2_idmap(u64 addr)
 	return ret;
 }
 
+static inline bool check_prot(enum kvm_pgtable_prot prot,
+			      enum kvm_pgtable_prot required,
+			      enum kvm_pgtable_prot denied)
+{
+	return (prot & (required | denied)) == required;
+}
+
+int __pkvm_host_share_hyp(u64 pfn)
+{
+	phys_addr_t addr = hyp_pfn_to_phys(pfn);
+	enum kvm_pgtable_prot prot, cur;
+	void *virt = __hyp_va(addr);
+	enum pkvm_page_state state;
+	kvm_pte_t pte;
+	u32 level;
+	int ret;
+
+	if (!range_is_memory(addr, addr + PAGE_SIZE))
+		return -EINVAL;
+
+	hyp_spin_lock(&host_kvm.lock);
+	hyp_spin_lock(&pkvm_pgd_lock);
+
+	ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level);
+	if (ret)
+		goto unlock;
+	if (!pte)
+		goto map_shared;
+
+	/*
+	 * Check attributes in the host stage-2 PTE. We need the page to be:
+	 *  - mapped RWX as we're sharing memory;
+	 *  - not borrowed, as that implies absence of ownership.
+	 * Otherwise, we can't let it got through
+	 */
+	cur = kvm_pgtable_stage2_pte_prot(pte);
+	prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, KVM_PGTABLE_PROT_RWX, prot)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	state = pkvm_getstate(cur);
+	if (state == PKVM_PAGE_OWNED)
+		goto map_shared;
+
+	/*
+	 * Tolerate double-sharing the same page, but this requires
+	 * cross-checking the hypervisor stage-1.
+	 */
+	if (state != PKVM_PAGE_SHARED_OWNED) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, &level);
+	if (ret)
+		goto unlock;
+
+	/*
+	 * If the page has been shared with the hypervisor, it must be
+	 * SHARED_BORROWED already.
+	 */
+	cur = kvm_pgtable_hyp_pte_prot(pte);
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, prot, ~prot))
+		ret = EPERM;
+	goto unlock;
+
+map_shared:
+	/*
+	 * If the page is not yet shared, adjust mappings in both page-tables
+	 * while both locks are held.
+	 */
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+	prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED);
+	ret = host_stage2_idmap_locked(addr, addr + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+unlock:
+	hyp_spin_unlock(&pkvm_pgd_lock);
+	hyp_spin_unlock(&host_kvm.lock);
+
+	return ret;
+}
+
 void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_vcpu_fault_info fault;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0625bf2353c2..cbab146cda6a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -259,10 +259,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size,
 {
 	int err;
 
-	if (!kvm_host_owns_hyp_mappings()) {
-		return kvm_call_hyp_nvhe(__pkvm_create_mappings,
-					 start, size, phys, prot);
-	}
+	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
+		return -EINVAL;
 
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
@@ -282,6 +280,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
 	}
 }
 
+static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end)
+{
+	phys_addr_t addr;
+	int ret;
+
+	for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp,
+					__phys_to_pfn(addr));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
@@ -302,6 +315,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	if (is_kernel_in_hyp_mode())
 		return 0;
 
+	if (!kvm_host_owns_hyp_mappings()) {
+		if (WARN_ON(prot != PAGE_HYP))
+			return -EPERM;
+		return pkvm_share_hyp(kvm_kaddr_to_phys(from),
+				      kvm_kaddr_to_phys(to));
+	}
+
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
-- 
2.32.0.432.gabb21c7263-goog


WARNING: multiple messages have this Message-ID
From: Quentin Perret <qperret@google.com>
To: maz@kernel.org, james.morse@arm.com, alexandru.elisei@arm.com,
	 suzuki.poulose@arm.com, catalin.marinas@arm.com,
	will@kernel.org
Cc: qwandor@google.com, linux-kernel@vger.kernel.org,
	kvmarm@lists.cs.columbia.edu,
	linux-arm-kernel@lists.infradead.org, kernel-team@android.com
Subject: [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode
Date: Thu, 29 Jul 2021 14:28:17 +0100	[thread overview]
Message-ID: <20210729132818.4091769-21-qperret@google.com> (raw)
In-Reply-To: <20210729132818.4091769-1-qperret@google.com>

The host kernel is currently able to change EL2 stage-1 mappings without
restrictions thanks to the __pkvm_create_mappings() hypercall. But in a
world where the host is no longer part of the TCB, this clearly poses a
problem.

To fix this, introduce a new hypercall to allow the host to share a
physical memory page with the hypervisor, and remove the
__pkvm_create_mappings() variant. The new hypercall implements
ownership and permission checks before allowing the sharing operation,
and it annotates the shared page in the hypervisor stage-1 and host
stage-2 page-tables.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  2 +-
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 11 +--
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 89 +++++++++++++++++++
 arch/arm64/kvm/mmu.c                          | 28 +++++-
 5 files changed, 119 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 432a9ea1f02e..aed2aa61766a 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -59,7 +59,7 @@
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs		13
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs		14
 #define __KVM_HOST_SMCCC_FUNC___pkvm_init			15
-#define __KVM_HOST_SMCCC_FUNC___pkvm_create_mappings		16
+#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp		16
 #define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping	17
 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector		18
 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize		19
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 7ce36fbf5158..3d78d7782f1b 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -49,6 +49,7 @@ extern struct host_kvm host_kvm;
 extern const u8 pkvm_hyp_id;
 
 int __pkvm_prot_finalize(void);
+int __pkvm_host_share_hyp(u64 pfn);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(u64 start, u64 end, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 7900d5b66ba3..2da6aa8da868 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -140,14 +140,11 @@ static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot);
 }
 
-static void handle___pkvm_create_mappings(struct kvm_cpu_context *host_ctxt)
+static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt)
 {
-	DECLARE_REG(unsigned long, start, host_ctxt, 1);
-	DECLARE_REG(unsigned long, size, host_ctxt, 2);
-	DECLARE_REG(unsigned long, phys, host_ctxt, 3);
-	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4);
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
 
-	cpu_reg(host_ctxt, 1) = __pkvm_create_mappings(start, size, phys, prot);
+	cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn);
 }
 
 static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt)
@@ -185,7 +182,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__vgic_v3_restore_aprs),
 	HANDLE_FUNC(__pkvm_init),
 	HANDLE_FUNC(__pkvm_cpu_set_vector),
-	HANDLE_FUNC(__pkvm_create_mappings),
+	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_create_private_mapping),
 	HANDLE_FUNC(__pkvm_prot_finalize),
 };
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 0ccea58df7e0..1b67f562b6fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -338,6 +338,95 @@ static int host_stage2_idmap(u64 addr)
 	return ret;
 }
 
+static inline bool check_prot(enum kvm_pgtable_prot prot,
+			      enum kvm_pgtable_prot required,
+			      enum kvm_pgtable_prot denied)
+{
+	return (prot & (required | denied)) == required;
+}
+
+int __pkvm_host_share_hyp(u64 pfn)
+{
+	phys_addr_t addr = hyp_pfn_to_phys(pfn);
+	enum kvm_pgtable_prot prot, cur;
+	void *virt = __hyp_va(addr);
+	enum pkvm_page_state state;
+	kvm_pte_t pte;
+	u32 level;
+	int ret;
+
+	if (!range_is_memory(addr, addr + PAGE_SIZE))
+		return -EINVAL;
+
+	hyp_spin_lock(&host_kvm.lock);
+	hyp_spin_lock(&pkvm_pgd_lock);
+
+	ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level);
+	if (ret)
+		goto unlock;
+	if (!pte)
+		goto map_shared;
+
+	/*
+	 * Check attributes in the host stage-2 PTE. We need the page to be:
+	 *  - mapped RWX as we're sharing memory;
+	 *  - not borrowed, as that implies absence of ownership.
+	 * Otherwise, we can't let it got through
+	 */
+	cur = kvm_pgtable_stage2_pte_prot(pte);
+	prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, KVM_PGTABLE_PROT_RWX, prot)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	state = pkvm_getstate(cur);
+	if (state == PKVM_PAGE_OWNED)
+		goto map_shared;
+
+	/*
+	 * Tolerate double-sharing the same page, but this requires
+	 * cross-checking the hypervisor stage-1.
+	 */
+	if (state != PKVM_PAGE_SHARED_OWNED) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, &level);
+	if (ret)
+		goto unlock;
+
+	/*
+	 * If the page has been shared with the hypervisor, it must be
+	 * SHARED_BORROWED already.
+	 */
+	cur = kvm_pgtable_hyp_pte_prot(pte);
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, prot, ~prot))
+		ret = EPERM;
+	goto unlock;
+
+map_shared:
+	/*
+	 * If the page is not yet shared, adjust mappings in both page-tables
+	 * while both locks are held.
+	 */
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+	prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED);
+	ret = host_stage2_idmap_locked(addr, addr + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+unlock:
+	hyp_spin_unlock(&pkvm_pgd_lock);
+	hyp_spin_unlock(&host_kvm.lock);
+
+	return ret;
+}
+
 void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_vcpu_fault_info fault;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0625bf2353c2..cbab146cda6a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -259,10 +259,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size,
 {
 	int err;
 
-	if (!kvm_host_owns_hyp_mappings()) {
-		return kvm_call_hyp_nvhe(__pkvm_create_mappings,
-					 start, size, phys, prot);
-	}
+	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
+		return -EINVAL;
 
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
@@ -282,6 +280,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
 	}
 }
 
+static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end)
+{
+	phys_addr_t addr;
+	int ret;
+
+	for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp,
+					__phys_to_pfn(addr));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
@@ -302,6 +315,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	if (is_kernel_in_hyp_mode())
 		return 0;
 
+	if (!kvm_host_owns_hyp_mappings()) {
+		if (WARN_ON(prot != PAGE_HYP))
+			return -EPERM;
+		return pkvm_share_hyp(kvm_kaddr_to_phys(from),
+				      kvm_kaddr_to_phys(to));
+	}
+
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
-- 
2.32.0.432.gabb21c7263-goog

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

WARNING: multiple messages have this Message-ID
From: Quentin Perret <qperret@google.com>
To: maz@kernel.org, james.morse@arm.com, alexandru.elisei@arm.com,
	 suzuki.poulose@arm.com, catalin.marinas@arm.com,
	will@kernel.org
Cc: linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu,  linux-kernel@vger.kernel.org,
	ardb@kernel.org, qwandor@google.com,  tabba@google.com,
	dbrazdil@google.com, kernel-team@android.com,
	 Quentin Perret <qperret@google.com>
Subject: [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode
Date: Thu, 29 Jul 2021 14:28:17 +0100	[thread overview]
Message-ID: <20210729132818.4091769-21-qperret@google.com> (raw)
In-Reply-To: <20210729132818.4091769-1-qperret@google.com>

The host kernel is currently able to change EL2 stage-1 mappings without
restrictions thanks to the __pkvm_create_mappings() hypercall. But in a
world where the host is no longer part of the TCB, this clearly poses a
problem.

To fix this, introduce a new hypercall to allow the host to share a
physical memory page with the hypervisor, and remove the
__pkvm_create_mappings() variant. The new hypercall implements
ownership and permission checks before allowing the sharing operation,
and it annotates the shared page in the hypervisor stage-1 and host
stage-2 page-tables.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  2 +-
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 11 +--
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 89 +++++++++++++++++++
 arch/arm64/kvm/mmu.c                          | 28 +++++-
 5 files changed, 119 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 432a9ea1f02e..aed2aa61766a 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -59,7 +59,7 @@
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs		13
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs		14
 #define __KVM_HOST_SMCCC_FUNC___pkvm_init			15
-#define __KVM_HOST_SMCCC_FUNC___pkvm_create_mappings		16
+#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp		16
 #define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping	17
 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector		18
 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize		19
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 7ce36fbf5158..3d78d7782f1b 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -49,6 +49,7 @@ extern struct host_kvm host_kvm;
 extern const u8 pkvm_hyp_id;
 
 int __pkvm_prot_finalize(void);
+int __pkvm_host_share_hyp(u64 pfn);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(u64 start, u64 end, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 7900d5b66ba3..2da6aa8da868 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -140,14 +140,11 @@ static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot);
 }
 
-static void handle___pkvm_create_mappings(struct kvm_cpu_context *host_ctxt)
+static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt)
 {
-	DECLARE_REG(unsigned long, start, host_ctxt, 1);
-	DECLARE_REG(unsigned long, size, host_ctxt, 2);
-	DECLARE_REG(unsigned long, phys, host_ctxt, 3);
-	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4);
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
 
-	cpu_reg(host_ctxt, 1) = __pkvm_create_mappings(start, size, phys, prot);
+	cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn);
 }
 
 static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt)
@@ -185,7 +182,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__vgic_v3_restore_aprs),
 	HANDLE_FUNC(__pkvm_init),
 	HANDLE_FUNC(__pkvm_cpu_set_vector),
-	HANDLE_FUNC(__pkvm_create_mappings),
+	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_create_private_mapping),
 	HANDLE_FUNC(__pkvm_prot_finalize),
 };
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 0ccea58df7e0..1b67f562b6fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -338,6 +338,95 @@ static int host_stage2_idmap(u64 addr)
 	return ret;
 }
 
+static inline bool check_prot(enum kvm_pgtable_prot prot,
+			      enum kvm_pgtable_prot required,
+			      enum kvm_pgtable_prot denied)
+{
+	return (prot & (required | denied)) == required;
+}
+
+int __pkvm_host_share_hyp(u64 pfn)
+{
+	phys_addr_t addr = hyp_pfn_to_phys(pfn);
+	enum kvm_pgtable_prot prot, cur;
+	void *virt = __hyp_va(addr);
+	enum pkvm_page_state state;
+	kvm_pte_t pte;
+	u32 level;
+	int ret;
+
+	if (!range_is_memory(addr, addr + PAGE_SIZE))
+		return -EINVAL;
+
+	hyp_spin_lock(&host_kvm.lock);
+	hyp_spin_lock(&pkvm_pgd_lock);
+
+	ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level);
+	if (ret)
+		goto unlock;
+	if (!pte)
+		goto map_shared;
+
+	/*
+	 * Check attributes in the host stage-2 PTE. We need the page to be:
+	 *  - mapped RWX as we're sharing memory;
+	 *  - not borrowed, as that implies absence of ownership.
+	 * Otherwise, we can't let it got through
+	 */
+	cur = kvm_pgtable_stage2_pte_prot(pte);
+	prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, KVM_PGTABLE_PROT_RWX, prot)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	state = pkvm_getstate(cur);
+	if (state == PKVM_PAGE_OWNED)
+		goto map_shared;
+
+	/*
+	 * Tolerate double-sharing the same page, but this requires
+	 * cross-checking the hypervisor stage-1.
+	 */
+	if (state != PKVM_PAGE_SHARED_OWNED) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, &level);
+	if (ret)
+		goto unlock;
+
+	/*
+	 * If the page has been shared with the hypervisor, it must be
+	 * SHARED_BORROWED already.
+	 */
+	cur = kvm_pgtable_hyp_pte_prot(pte);
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	if (!check_prot(cur, prot, ~prot))
+		ret = EPERM;
+	goto unlock;
+
+map_shared:
+	/*
+	 * If the page is not yet shared, adjust mappings in both page-tables
+	 * while both locks are held.
+	 */
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+	prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED);
+	ret = host_stage2_idmap_locked(addr, addr + PAGE_SIZE, prot);
+	BUG_ON(ret);
+
+unlock:
+	hyp_spin_unlock(&pkvm_pgd_lock);
+	hyp_spin_unlock(&host_kvm.lock);
+
+	return ret;
+}
+
 void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_vcpu_fault_info fault;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0625bf2353c2..cbab146cda6a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -259,10 +259,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size,
 {
 	int err;
 
-	if (!kvm_host_owns_hyp_mappings()) {
-		return kvm_call_hyp_nvhe(__pkvm_create_mappings,
-					 start, size, phys, prot);
-	}
+	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
+		return -EINVAL;
 
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
@@ -282,6 +280,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
 	}
 }
 
+static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end)
+{
+	phys_addr_t addr;
+	int ret;
+
+	for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp,
+					__phys_to_pfn(addr));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
@@ -302,6 +315,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	if (is_kernel_in_hyp_mode())
 		return 0;
 
+	if (!kvm_host_owns_hyp_mappings()) {
+		if (WARN_ON(prot != PAGE_HYP))
+			return -EPERM;
+		return pkvm_share_hyp(kvm_kaddr_to_phys(from),
+				      kvm_kaddr_to_phys(to));
+	}
+
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
-- 
2.32.0.432.gabb21c7263-goog


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2021-07-29 13:29 UTC|newest]

Thread overview: 135+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-29 13:27 [PATCH v3 00/21] Track shared pages at EL2 " Quentin Perret
2021-07-29 13:27 ` Quentin Perret
2021-07-29 13:27 ` Quentin Perret
2021-07-29 13:27 ` [PATCH v3 01/21] KVM: arm64: Add hyp_spin_is_locked() for basic locking assertions at EL2 Quentin Perret
2021-07-29 13:27   ` Quentin Perret
2021-07-29 13:27   ` Quentin Perret
2021-07-29 13:27 ` [PATCH v3 02/21] KVM: arm64: Introduce hyp_assert_lock_held() Quentin Perret
2021-07-29 13:27   ` Quentin Perret
2021-07-29 13:27   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 03/21] KVM: arm64: Provide the host_stage2_try() helper macro Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:36   ` Fuad Tabba
2021-08-02  9:36     ` Fuad Tabba
2021-08-02  9:36     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 04/21] KVM: arm64: Introduce helper to retrieve a PTE and its level Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 05/21] KVM: arm64: Expose page-table helpers Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 06/21] KVM: arm64: Optimize host memory aborts Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:37   ` Fuad Tabba
2021-08-02  9:37     ` Fuad Tabba
2021-08-02  9:37     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 07/21] KVM: arm64: Rename KVM_PTE_LEAF_ATTR_S2_IGNORED Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:37   ` Fuad Tabba
2021-08-02  9:37     ` Fuad Tabba
2021-08-02  9:37     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 08/21] KVM: arm64: Don't overwrite software bits with owner id Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:38   ` Fuad Tabba
2021-08-02  9:38     ` Fuad Tabba
2021-08-02  9:38     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 09/21] KVM: arm64: Tolerate re-creating hyp mappings to set software bits Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:50   ` Fuad Tabba
2021-08-02  9:50     ` Fuad Tabba
2021-08-02  9:50     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 10/21] KVM: arm64: Enable forcing page-level stage-2 mappings Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02  9:49   ` Fuad Tabba
2021-08-02  9:49     ` Fuad Tabba
2021-08-02  9:49     ` Fuad Tabba
2021-08-03 10:13     ` Quentin Perret
2021-08-03 10:13       ` Quentin Perret
2021-08-03 10:13       ` Quentin Perret
2021-08-03 10:43       ` Fuad Tabba
2021-08-03 10:43         ` Fuad Tabba
2021-08-03 10:43         ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 11/21] KVM: arm64: Allow populating software bits Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 12/21] KVM: arm64: Add helpers to tag shared pages in SW bits Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02 10:30   ` Fuad Tabba
2021-08-02 10:30     ` Fuad Tabba
2021-08-02 10:30     ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 13/21] KVM: arm64: Expose host stage-2 manipulation helpers Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02 11:13   ` Fuad Tabba
2021-08-02 11:13     ` Fuad Tabba
2021-08-02 11:13     ` Fuad Tabba
2021-08-03 10:20     ` Quentin Perret
2021-08-03 10:20       ` Quentin Perret
2021-08-03 10:20       ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 14/21] KVM: arm64: Expose pkvm_hyp_id Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 15/21] KVM: arm64: Introduce addr_is_memory() Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02 14:52   ` Fuad Tabba
2021-08-02 14:52     ` Fuad Tabba
2021-08-02 14:52     ` Fuad Tabba
2021-08-03 10:23     ` Quentin Perret
2021-08-03 10:23       ` Quentin Perret
2021-08-03 10:23       ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 16/21] KVM: arm64: Enable retrieving protections attributes of PTEs Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-02 14:52   ` Fuad Tabba
2021-08-02 14:52     ` Fuad Tabba
2021-08-02 14:52     ` Fuad Tabba
2021-08-03 10:24     ` Quentin Perret
2021-08-03 10:24       ` Quentin Perret
2021-08-03 10:24       ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 17/21] KVM: arm64: Mark host bss and rodata section as shared Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-03  5:02   ` Fuad Tabba
2021-08-03  5:02     ` Fuad Tabba
2021-08-03  5:02     ` Fuad Tabba
2021-08-03 10:34     ` Quentin Perret
2021-08-03 10:34       ` Quentin Perret
2021-08-03 10:34       ` Quentin Perret
2021-08-03 10:54       ` Fuad Tabba
2021-08-03 10:54         ` Fuad Tabba
2021-08-03 10:54         ` Fuad Tabba
2021-07-29 13:28 ` [PATCH v3 18/21] KVM: arm64: Remove __pkvm_mark_hyp Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 19/21] KVM: arm64: Refactor protected nVHE stage-1 locking Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-03  5:31   ` Fuad Tabba
2021-08-03  5:31     ` Fuad Tabba
2021-08-03  5:31     ` Fuad Tabba
2021-08-03 10:37     ` Quentin Perret
2021-08-03 10:37       ` Quentin Perret
2021-08-03 10:37       ` Quentin Perret
2021-08-03 10:51       ` Fuad Tabba
2021-08-03 10:51         ` Fuad Tabba
2021-08-03 10:51         ` Fuad Tabba
2021-07-29 13:28 ` Quentin Perret [this message]
2021-07-29 13:28   ` [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-08-03  8:22   ` Fuad Tabba
2021-08-03  8:22     ` Fuad Tabba
2021-08-03  8:22     ` Fuad Tabba
2021-08-03 10:43     ` Quentin Perret
2021-08-03 10:43       ` Quentin Perret
2021-08-03 10:43       ` Quentin Perret
2021-07-29 13:28 ` [PATCH v3 21/21] KVM: arm64: Make __pkvm_create_mappings static Quentin Perret
2021-07-29 13:28   ` Quentin Perret
2021-07-29 13:28   ` Quentin Perret

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=20210729132818.4091769-21-qperret@google.com \
    --to=qperret@google.com \
    --cc=alexandru.elisei@arm.com \
    --cc=ardb@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=dbrazdil@google.com \
    --cc=james.morse@arm.com \
    --cc=kernel-team@android.com \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=qwandor@google.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tabba@google.com \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.