Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 22 Feb 2022 08:51:04 -0800
In-Reply-To: <20220222165212.2005066-1-kaleshsingh@google.com>
Message-Id: <20220222165212.2005066-4-kaleshsingh@google.com>
Mime-Version: 1.0
References: <20220222165212.2005066-1-kaleshsingh@google.com>
Subject: [PATCH v2 3/9] KVM: arm64: Add guard pages for KVM nVHE hypervisor stack
From:   Kalesh Singh <kaleshsingh@google.com>
Cc:     will@kernel.org, maz@kernel.org, qperret@google.com,
        tabba@google.com, surenb@google.com, kernel-team@android.com,
        Kalesh Singh <kaleshsingh@google.com>,
        Catalin Marinas <catalin.marinas@arm.com>,
        James Morse <james.morse@arm.com>,
        Alexandru Elisei <alexandru.elisei@arm.com>,
        Suzuki K Poulose <suzuki.poulose@arm.com>,
        Ard Biesheuvel <ardb@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Pasha Tatashin <pasha.tatashin@soleen.com>,
        Joey Gouly <joey.gouly@arm.com>,
        Peter Collingbourne <pcc@google.com>,
        Andrew Scull <ascull@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        kvmarm@lists.cs.columbia.edu
Content-Type: text/plain; charset="UTF-8"
To:     unlisted-recipients:; (no To-header on input)
Precedence: bulk

Maps the stack pages in the flexible private VA range and allocates
guard pages below the stack as unbacked VA space. The stack is aligned
to twice its size to aid overflow detection (implemented in a subsequent
patch in the series).

Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
---
 arch/arm64/include/asm/kvm_asm.h |  1 +
 arch/arm64/kvm/arm.c             | 32 +++++++++++++++++++++++++++++---
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index d5b0386ef765..2e277f2ed671 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -169,6 +169,7 @@ struct kvm_nvhe_init_params {
 	unsigned long tcr_el2;
 	unsigned long tpidr_el2;
 	unsigned long stack_hyp_va;
+	unsigned long stack_pa;
 	phys_addr_t pgd_pa;
 	unsigned long hcr_el2;
 	unsigned long vttbr;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index ecc5958e27fe..7e2e680c3ffb 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1541,7 +1541,6 @@ static void cpu_prepare_hyp_mode(int cpu)
 	tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET;
 	params->tcr_el2 = tcr;
 
-	params->stack_hyp_va = kern_hyp_va(per_cpu(kvm_arm_hyp_stack_page, cpu) + PAGE_SIZE);
 	params->pgd_pa = kvm_mmu_get_httbr();
 	if (is_protected_kvm_enabled())
 		params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS;
@@ -1990,14 +1989,41 @@ static int init_hyp_mode(void)
 	 * Map the Hyp stack pages
 	 */
 	for_each_possible_cpu(cpu) {
+		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
-					  PAGE_HYP);
+		unsigned long stack_hyp_va, guard_hyp_va;
 
+		/*
+		 * Private mappings are allocated downwards from io_map_base
+		 * so allocate the stack first then the guard page.
+		 *
+		 * The stack is aligned to twice its size to facilitate overflow
+		 * detection.
+		 */
+		err = __create_hyp_private_mapping(__pa(stack_page), PAGE_SIZE,
+						PAGE_SIZE * 2, &stack_hyp_va, PAGE_HYP);
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
 			goto out_err;
 		}
+
+		/* Allocate unbacked private VA range for stack guard page */
+		guard_hyp_va = hyp_alloc_private_va_range(PAGE_SIZE, PAGE_SIZE);
+		if (IS_ERR((void *)guard_hyp_va)) {
+			err = PTR_ERR((void *)guard_hyp_va);
+			kvm_err("Cannot allocate hyp stack guard page\n");
+			goto out_err;
+		}
+
+		/*
+		 * Save the stack PA in nvhe_init_params. This will be needed to recreate
+		 * the stack mapping in protected nVHE mode. __hyp_pa() won't do the right
+		 * thing there, since the stack has been mapped in the flexible private
+		 * VA space.
+		 */
+		params->stack_pa = __pa(stack_page) + PAGE_SIZE;
+
+		params->stack_hyp_va = stack_hyp_va + PAGE_SIZE;
 	}
 
 	for_each_possible_cpu(cpu) {
-- 
2.35.1.473.g83b2b277ed-goog