From bd7d95cafb499e24903b7d21f9eeb2c5208160c2 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Fri, 9 Nov 2018 15:07:11 +0000
Subject: arm64: KVM: Consistently advance singlestep when emulating
 instructions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When we emulate a guest instruction, we don't advance the hardware
singlestep state machine, and thus the guest will receive a software
step exception after a next instruction which is not emulated by the
host.

We bodge around this in an ad-hoc fashion. Sometimes we explicitly check
whether userspace requested a single step, and fake a debug exception
from within the kernel. Other times, we advance the HW singlestep state
rely on the HW to generate the exception for us. Thus, the observed step
behaviour differs for host and guest.

Let's make this simpler and consistent by always advancing the HW
singlestep state machine when we skip an instruction. Thus we can rely
on the hardware to generate the singlestep exception for us, and never
need to explicitly check for an active-pending step, nor do we need to
fake a debug exception from the guest.

Cc: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/kvm_emulate.h     | 35 ++++++++++++++++++++------
 arch/arm64/include/asm/kvm_host.h        |  1 -
 arch/arm64/kvm/debug.c                   | 21 ----------------
 arch/arm64/kvm/handle_exit.c             | 14 +----------
 arch/arm64/kvm/hyp/switch.c              | 43 +++-----------------------------
 arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c | 12 ++++++---
 6 files changed, 41 insertions(+), 85 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 21247870def7..506386a3edde 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -24,6 +24,7 @@
 
 #include <linux/kvm_host.h>
 
+#include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
@@ -147,14 +148,6 @@ static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
-{
-	if (vcpu_mode_is_32bit(vcpu))
-		kvm_skip_instr32(vcpu, is_wide_instr);
-	else
-		*vcpu_pc(vcpu) += 4;
-}
-
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 {
 	*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
@@ -424,4 +417,30 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 	return data;		/* Leave LE untouched */
 }
 
+static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		kvm_skip_instr32(vcpu, is_wide_instr);
+	else
+		*vcpu_pc(vcpu) += 4;
+
+	/* advance the singlestep state machine */
+	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+}
+
+/*
+ * Skip an instruction which has been emulated at hyp while most guest sysregs
+ * are live.
+ */
+static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+{
+	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
+	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
+
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
+	write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
+	write_sysreg_el2(*vcpu_pc(vcpu), elr);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 52fbc823ff8c..7a5035f9c5c3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -445,7 +445,6 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
-bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 00d422336a45..f39801e4136c 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -236,24 +236,3 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 		}
 	}
 }
-
-
-/*
- * After successfully emulating an instruction, we might want to
- * return to user space with a KVM_EXIT_DEBUG. We can only do this
- * once the emulation is complete, though, so for userspace emulations
- * we have to wait until we have re-entered KVM before calling this
- * helper.
- *
- * Return true (and set exit_reason) to return to userspace or false
- * if no further action is required.
- */
-bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		run->exit_reason = KVM_EXIT_DEBUG;
-		run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
-		return true;
-	}
-	return false;
-}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 35a81bebd02b..b0643f9c4873 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -229,13 +229,6 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		handled = exit_handler(vcpu, run);
 	}
 
-	/*
-	 * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
-	 * structure if we need to return to userspace.
-	 */
-	if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
-		handled = 0;
-
 	return handled;
 }
 
@@ -269,12 +262,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_IRQ:
 		return 1;
 	case ARM_EXCEPTION_EL1_SERROR:
-		/* We may still need to return for single-step */
-		if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
-			&& kvm_arm_handle_step_debug(vcpu, run))
-			return 0;
-		else
-			return 1;
+		return 1;
 	case ARM_EXCEPTION_TRAP:
 		return handle_trap_exceptions(vcpu, run);
 	case ARM_EXCEPTION_HYP_GONE:
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 7cc175c88a37..4282f05771c1 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -305,33 +305,6 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-/* Skip an instruction which has been emulated. Returns true if
- * execution can continue or false if we need to exit hyp mode because
- * single-step was in effect.
- */
-static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
-{
-	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
-
-	if (vcpu_mode_is_32bit(vcpu)) {
-		vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
-		kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-		write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
-	} else {
-		*vcpu_pc(vcpu) += 4;
-	}
-
-	write_sysreg_el2(*vcpu_pc(vcpu), elr);
-
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		vcpu->arch.fault.esr_el2 =
-			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
-		return false;
-	} else {
-		return true;
-	}
-}
-
 static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
 {
 	struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state;
@@ -420,20 +393,12 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
-			if (ret ==  1 && __skip_instr(vcpu))
+			if (ret == 1)
 				return true;
 
-			if (ret == -1) {
-				/* Promote an illegal access to an
-				 * SError. If we would be returning
-				 * due to single-step clear the SS
-				 * bit so handle_exit knows what to
-				 * do after dealing with the error.
-				 */
-				if (!__skip_instr(vcpu))
-					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
 				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-			}
 
 			goto exit;
 		}
@@ -444,7 +409,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
-		if (ret == 1 && __skip_instr(vcpu))
+		if (ret == 1)
 			return true;
 	}
 
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 215c7c0eb3b0..9cbdd034a563 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -41,7 +41,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
  * Returns:
  *  1: GICV access successfully performed
  *  0: Not a GICV access
- * -1: Illegal GICV access
+ * -1: Illegal GICV access successfully performed
  */
 int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
@@ -61,12 +61,16 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 		return 0;
 
 	/* Reject anything but a 32bit access */
-	if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32))
+	if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) {
+		__kvm_skip_instr(vcpu);
 		return -1;
+	}
 
 	/* Not aligned? Don't bother */
-	if (fault_ipa & 3)
+	if (fault_ipa & 3) {
+		__kvm_skip_instr(vcpu);
 		return -1;
+	}
 
 	rd = kvm_vcpu_dabt_get_rd(vcpu);
 	addr  = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va;
@@ -88,5 +92,7 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 		vcpu_set_reg(vcpu, rd, data);
 	}
 
+	__kvm_skip_instr(vcpu);
+
 	return 1;
 }
-- 
cgit v1.2.3


From d1878af3a5a6ac00bc8a3edfecf80539ee9c546e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 6 Dec 2018 12:31:44 +0000
Subject: KVM: arm/arm64: Log PSTATE for unhandled sysregs

When KVM traps an unhandled sysreg/coproc access from a guest, it logs
the guest PC. To aid debugging, it would be helpful to know which
exception level the trap came from, along with other PSTATE/CPSR bits,
so let's log the PSTATE/CPSR too.

Acked-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/kvm/coproc.c     | 4 ++--
 arch/arm64/kvm/sys_regs.c | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index cb094e55dc5f..222c1635bc7a 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -602,8 +602,8 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 		}
 	} else {
 		/* If access function fails, it should complain. */
-		kvm_err("Unsupported guest CP15 access at: %08lx\n",
-			*vcpu_pc(vcpu));
+		kvm_err("Unsupported guest CP15 access at: %08lx [%08lx]\n",
+			*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
 		print_cp_instr(params);
 		kvm_inject_undefined(vcpu);
 	}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 22fbbdbece3c..ecbf67ccabf5 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1912,8 +1912,8 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 	}
 
-	kvm_err("Unsupported guest CP%d access at: %08lx\n",
-		cp, *vcpu_pc(vcpu));
+	kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n",
+		cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 }
@@ -2063,8 +2063,8 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 	if (likely(r)) {
 		perform_access(vcpu, params, r);
 	} else {
-		kvm_err("Unsupported guest sys_reg access at: %lx\n",
-			*vcpu_pc(vcpu));
+		kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n",
+			*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
 		print_sys_reg_instr(params);
 		kvm_inject_undefined(vcpu);
 	}
-- 
cgit v1.2.3


From f8df73388ee25b5e5f1d26249202e7126ca8139d Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:36 +0000
Subject: KVM: arm/arm64: Introduce helpers to manipulate page table entries

Introduce helpers to abstract architectural handling of the conversion
of pfn to page table entries and marking a PMD page table entry as a
block entry.

The helpers are introduced in preparation for supporting PUD hugepages
at stage 2 - which are supported on arm64 but do not exist on arm.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Acked-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h   |  5 +++++
 arch/arm64/include/asm/kvm_mmu.h |  5 +++++
 virt/kvm/arm/mmu.c               | 14 ++++++++------
 3 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 1098ffc3d54b..e6eff8bf5d7f 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -82,6 +82,11 @@ void kvm_clear_hyp_idmap(void);
 #define kvm_mk_pud(pmdp)	__pud(__pa(pmdp) | PMD_TYPE_TABLE)
 #define kvm_mk_pgd(pudp)	({ BUILD_BUG(); 0; })
 
+#define kvm_pfn_pte(pfn, prot)	pfn_pte(pfn, prot)
+#define kvm_pfn_pmd(pfn, prot)	pfn_pmd(pfn, prot)
+
+#define kvm_pmd_mkhuge(pmd)	pmd_mkhuge(pmd)
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= L_PTE_S2_RDWR;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 658657367f2f..13d482710292 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -184,6 +184,11 @@ void kvm_clear_hyp_idmap(void);
 #define kvm_mk_pgd(pudp)					\
 	__pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE)
 
+#define kvm_pfn_pte(pfn, prot)		pfn_pte(pfn, prot)
+#define kvm_pfn_pmd(pfn, prot)		pfn_pmd(pfn, prot)
+
+#define kvm_pmd_mkhuge(pmd)		pmd_mkhuge(pmd)
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= PTE_S2_RDWR;
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 6912529946fb..fb5325f7a1ac 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -607,7 +607,7 @@ static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
 	addr = start;
 	do {
 		pte = pte_offset_kernel(pmd, addr);
-		kvm_set_pte(pte, pfn_pte(pfn, prot));
+		kvm_set_pte(pte, kvm_pfn_pte(pfn, prot));
 		get_page(virt_to_page(pte));
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
@@ -1202,7 +1202,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 	pfn = __phys_to_pfn(pa);
 
 	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
-		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
+		pte_t pte = kvm_pfn_pte(pfn, PAGE_S2_DEVICE);
 
 		if (writable)
 			pte = kvm_s2pte_mkwrite(pte);
@@ -1611,8 +1611,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
 
 	if (vma_pagesize == PMD_SIZE) {
-		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
-		new_pmd = pmd_mkhuge(new_pmd);
+		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
+
+		new_pmd = kvm_pmd_mkhuge(new_pmd);
+
 		if (writable)
 			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
 
@@ -1621,7 +1623,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
-		pte_t new_pte = pfn_pte(pfn, mem_type);
+		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
 
 		if (writable) {
 			new_pte = kvm_s2pte_mkwrite(new_pte);
@@ -1878,7 +1880,7 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	 * just like a translation fault and clean the cache to the PoC.
 	 */
 	clean_dcache_guest_page(pfn, PAGE_SIZE);
-	stage2_pte = pfn_pte(pfn, PAGE_S2);
+	stage2_pte = kvm_pfn_pte(pfn, PAGE_S2);
 	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
 }
 
-- 
cgit v1.2.3


From 4ea5af53114091e23a8fc279f25637e6c4e892c6 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:37 +0000
Subject: KVM: arm64: Support dirty page tracking for PUD hugepages

In preparation for creating PUD hugepages at stage 2, add support for
write protecting PUD hugepages when they are encountered. Write
protecting guest tables is used to track dirty pages when migrating
VMs.

Also, provide trivial implementations of required kvm_s2pud_* helpers
to allow sharing of code with arm32.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
[ Replaced BUG() => WARN_ON() in arm32 pud helpers ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h   | 15 +++++++++++++++
 arch/arm64/include/asm/kvm_mmu.h | 10 ++++++++++
 virt/kvm/arm/mmu.c               | 11 +++++++----
 3 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index e6eff8bf5d7f..9fe6c30eb2fc 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -87,6 +87,21 @@ void kvm_clear_hyp_idmap(void);
 
 #define kvm_pmd_mkhuge(pmd)	pmd_mkhuge(pmd)
 
+/*
+ * The following kvm_*pud*() functions are provided strictly to allow
+ * sharing code with arm64. They should never be called in practice.
+ */
+static inline void kvm_set_s2pud_readonly(pud_t *pud)
+{
+	WARN_ON(1);
+}
+
+static inline bool kvm_s2pud_readonly(pud_t *pud)
+{
+	WARN_ON(1);
+	return false;
+}
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= L_PTE_S2_RDWR;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 13d482710292..8da6d1b2a196 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -251,6 +251,16 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
 	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
 }
 
+static inline void kvm_set_s2pud_readonly(pud_t *pudp)
+{
+	kvm_set_s2pte_readonly((pte_t *)pudp);
+}
+
+static inline bool kvm_s2pud_readonly(pud_t *pudp)
+{
+	return kvm_s2pte_readonly((pte_t *)pudp);
+}
+
 #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
 
 #ifdef __PAGETABLE_PMD_FOLDED
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index fb5325f7a1ac..1c669c3c1208 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1347,9 +1347,12 @@ static void  stage2_wp_puds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_pud_addr_end(kvm, addr, end);
 		if (!stage2_pud_none(kvm, *pud)) {
-			/* TODO:PUD not supported, revisit later if supported */
-			BUG_ON(stage2_pud_huge(kvm, *pud));
-			stage2_wp_pmds(kvm, pud, addr, next);
+			if (stage2_pud_huge(kvm, *pud)) {
+				if (!kvm_s2pud_readonly(pud))
+					kvm_set_s2pud_readonly(pud);
+			} else {
+				stage2_wp_pmds(kvm, pud, addr, next);
+			}
 		}
 	} while (pud++, addr = next, addr != end);
 }
@@ -1392,7 +1395,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
  *
  * Called to start logging dirty pages after memory region
  * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
- * all present PMD and PTEs are write protected in the memory region.
+ * all present PUD, PMD and PTEs are write protected in the memory region.
  * Afterwards read of dirty page log can be called.
  *
  * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
-- 
cgit v1.2.3


From 86d1c55ea605025f78d026e7fc3a2bb4c3fc2d6a Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:38 +0000
Subject: KVM: arm64: Support PUD hugepage in stage2_is_exec()

In preparation for creating PUD hugepages at stage 2, add support for
detecting execute permissions on PUD page table entries. Faults due to
lack of execute permissions on page table entries is used to perform
i-cache invalidation on first execute.

Provide trivial implementations of arm32 helpers to allow sharing of
code.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
[ Replaced BUG() => WARN_ON(1) in arm32 PUD helpers ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h         |  6 ++++
 arch/arm64/include/asm/kvm_mmu.h       |  5 ++++
 arch/arm64/include/asm/pgtable-hwdef.h |  2 ++
 virt/kvm/arm/mmu.c                     | 53 ++++++++++++++++++++++++++++++----
 4 files changed, 61 insertions(+), 5 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 9fe6c30eb2fc..a49655fe7cd9 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -102,6 +102,12 @@ static inline bool kvm_s2pud_readonly(pud_t *pud)
 	return false;
 }
 
+static inline bool kvm_s2pud_exec(pud_t *pud)
+{
+	WARN_ON(1);
+	return false;
+}
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= L_PTE_S2_RDWR;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8da6d1b2a196..c755b37b3f92 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -261,6 +261,11 @@ static inline bool kvm_s2pud_readonly(pud_t *pudp)
 	return kvm_s2pte_readonly((pte_t *)pudp);
 }
 
+static inline bool kvm_s2pud_exec(pud_t *pudp)
+{
+	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
+}
+
 #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
 
 #ifdef __PAGETABLE_PMD_FOLDED
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 1d7d8da2ef9b..336e24cddc87 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -193,6 +193,8 @@
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
 
+#define PUD_S2_XN		(_AT(pudval_t, 2) << 53)  /* XN[1:0] */
+
 /*
  * Memory Attribute override for Stage-2 (MemAttr[3:0])
  */
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 1c669c3c1208..8e44dccd1b47 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1083,23 +1083,66 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	return 0;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+/*
+ * stage2_get_leaf_entry - walk the stage2 VM page tables and return
+ * true if a valid and present leaf-entry is found. A pointer to the
+ * leaf-entry is returned in the appropriate level variable - pudpp,
+ * pmdpp, ptepp.
+ */
+static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
+				  pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
 {
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pmdp = stage2_get_pmd(kvm, NULL, addr);
+	*pudpp = NULL;
+	*pmdpp = NULL;
+	*ptepp = NULL;
+
+	pudp = stage2_get_pud(kvm, NULL, addr);
+	if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
+		return false;
+
+	if (stage2_pud_huge(kvm, *pudp)) {
+		*pudpp = pudp;
+		return true;
+	}
+
+	pmdp = stage2_pmd_offset(kvm, pudp, addr);
 	if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
 		return false;
 
-	if (pmd_thp_or_huge(*pmdp))
-		return kvm_s2pmd_exec(pmdp);
+	if (pmd_thp_or_huge(*pmdp)) {
+		*pmdpp = pmdp;
+		return true;
+	}
 
 	ptep = pte_offset_kernel(pmdp, addr);
 	if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
 		return false;
 
-	return kvm_s2pte_exec(ptep);
+	*ptepp = ptep;
+	return true;
+}
+
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+{
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+	bool found;
+
+	found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
+	if (!found)
+		return false;
+
+	if (pudp)
+		return kvm_s2pud_exec(pudp);
+	else if (pmdp)
+		return kvm_s2pmd_exec(pmdp);
+	else
+		return kvm_s2pte_exec(ptep);
 }
 
 static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
-- 
cgit v1.2.3


From eb3f0624ea082def887acc79e97934e27d0188b7 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:39 +0000
Subject: KVM: arm64: Support handling access faults for PUD hugepages

In preparation for creating larger hugepages at Stage 2, extend the
access fault handling at Stage 2 to support PUD hugepages when
encountered.

Provide trivial helpers for arm32 to allow sharing of code.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
[ Replaced BUG() => WARN_ON(1) in PUD helpers ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h   |  9 +++++++++
 arch/arm64/include/asm/kvm_mmu.h |  7 +++++++
 arch/arm64/include/asm/pgtable.h |  6 ++++++
 virt/kvm/arm/mmu.c               | 22 +++++++++++-----------
 4 files changed, 33 insertions(+), 11 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index a49655fe7cd9..3a407204b957 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -85,6 +85,9 @@ void kvm_clear_hyp_idmap(void);
 #define kvm_pfn_pte(pfn, prot)	pfn_pte(pfn, prot)
 #define kvm_pfn_pmd(pfn, prot)	pfn_pmd(pfn, prot)
 
+#define kvm_pud_pfn(pud)	({ WARN_ON(1); 0; })
+
+
 #define kvm_pmd_mkhuge(pmd)	pmd_mkhuge(pmd)
 
 /*
@@ -108,6 +111,12 @@ static inline bool kvm_s2pud_exec(pud_t *pud)
 	return false;
 }
 
+static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
+{
+	BUG();
+	return pud;
+}
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= L_PTE_S2_RDWR;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index c755b37b3f92..612032bbb428 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -187,6 +187,8 @@ void kvm_clear_hyp_idmap(void);
 #define kvm_pfn_pte(pfn, prot)		pfn_pte(pfn, prot)
 #define kvm_pfn_pmd(pfn, prot)		pfn_pmd(pfn, prot)
 
+#define kvm_pud_pfn(pud)		pud_pfn(pud)
+
 #define kvm_pmd_mkhuge(pmd)		pmd_mkhuge(pmd)
 
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
@@ -266,6 +268,11 @@ static inline bool kvm_s2pud_exec(pud_t *pudp)
 	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
 }
 
+static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
+{
+	return pud_mkyoung(pud);
+}
+
 #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
 
 #ifdef __PAGETABLE_PMD_FOLDED
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 50b1ef8584c0..f51e2271e6a3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -314,6 +314,11 @@ static inline pte_t pud_pte(pud_t pud)
 	return __pte(pud_val(pud));
 }
 
+static inline pud_t pte_pud(pte_t pte)
+{
+	return __pud(pte_val(pte));
+}
+
 static inline pmd_t pud_pmd(pud_t pud)
 {
 	return __pmd(pud_val(pud));
@@ -381,6 +386,7 @@ static inline int pmd_protnone(pmd_t pmd)
 #define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
+#define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
 #define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 8e44dccd1b47..bd749601195f 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1698,6 +1698,7 @@ out_unlock:
  */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	kvm_pfn_t pfn;
@@ -1707,24 +1708,23 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 
-	pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa);
-	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+	if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
 		goto out;
 
-	if (pmd_thp_or_huge(*pmd)) {	/* THP, HugeTLB */
+	if (pud) {		/* HugeTLB */
+		*pud = kvm_s2pud_mkyoung(*pud);
+		pfn = kvm_pud_pfn(*pud);
+		pfn_valid = true;
+	} else	if (pmd) {	/* THP, HugeTLB */
 		*pmd = pmd_mkyoung(*pmd);
 		pfn = pmd_pfn(*pmd);
 		pfn_valid = true;
-		goto out;
+	} else {
+		*pte = pte_mkyoung(*pte);	/* Just a page... */
+		pfn = pte_pfn(*pte);
+		pfn_valid = true;
 	}
 
-	pte = pte_offset_kernel(pmd, fault_ipa);
-	if (pte_none(*pte))		/* Nothing there either */
-		goto out;
-
-	*pte = pte_mkyoung(*pte);	/* Just a page... */
-	pfn = pte_pfn(*pte);
-	pfn_valid = true;
 out:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	if (pfn_valid)
-- 
cgit v1.2.3


From 35a63966194dd994f44150f07398c62f8dca011e Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:40 +0000
Subject: KVM: arm64: Update age handlers to support PUD hugepages

In preparation for creating larger hugepages at Stage 2, add support
to the age handling notifiers for PUD hugepages when encountered.

Provide trivial helpers for arm32 to allow sharing code.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
[ Replaced BUG() => WARN_ON(1) for arm32 PUD helpers ]
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h   |  6 ++++++
 arch/arm64/include/asm/kvm_mmu.h |  5 +++++
 arch/arm64/include/asm/pgtable.h |  1 +
 virt/kvm/arm/mmu.c               | 39 ++++++++++++++++++++-------------------
 4 files changed, 32 insertions(+), 19 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 3a407204b957..4b4b2146e6a0 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -117,6 +117,12 @@ static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
 	return pud;
 }
 
+static inline bool kvm_s2pud_young(pud_t pud)
+{
+	WARN_ON(1);
+	return false;
+}
+
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
 	pte_val(pte) |= L_PTE_S2_RDWR;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 612032bbb428..9f941f70775c 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -273,6 +273,11 @@ static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
 	return pud_mkyoung(pud);
 }
 
+static inline bool kvm_s2pud_young(pud_t pud)
+{
+	return pud_young(pud);
+}
+
 #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
 
 #ifdef __PAGETABLE_PMD_FOLDED
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index f51e2271e6a3..bb0f3f17a7a9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -386,6 +386,7 @@ static inline int pmd_protnone(pmd_t pmd)
 #define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
+#define pud_young(pud)		pte_young(pud_pte(pud))
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index bd749601195f..3893ea6a50bf 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1225,6 +1225,11 @@ static int stage2_pmdp_test_and_clear_young(pmd_t *pmd)
 	return stage2_ptep_test_and_clear_young((pte_t *)pmd);
 }
 
+static int stage2_pudp_test_and_clear_young(pud_t *pud)
+{
+	return stage2_ptep_test_and_clear_young((pte_t *)pud);
+}
+
 /**
  * kvm_phys_addr_ioremap - map a device range to guest IPA
  *
@@ -1932,42 +1937,38 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 
 static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
-	pmd = stage2_get_pmd(kvm, NULL, gpa);
-	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
+	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
 		return 0;
 
-	if (pmd_thp_or_huge(*pmd))	/* THP, HugeTLB */
+	if (pud)
+		return stage2_pudp_test_and_clear_young(pud);
+	else if (pmd)
 		return stage2_pmdp_test_and_clear_young(pmd);
-
-	pte = pte_offset_kernel(pmd, gpa);
-	if (pte_none(*pte))
-		return 0;
-
-	return stage2_ptep_test_and_clear_young(pte);
+	else
+		return stage2_ptep_test_and_clear_young(pte);
 }
 
 static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
-	pmd = stage2_get_pmd(kvm, NULL, gpa);
-	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
+	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
 		return 0;
 
-	if (pmd_thp_or_huge(*pmd))		/* THP, HugeTLB */
+	if (pud)
+		return kvm_s2pud_young(*pud);
+	else if (pmd)
 		return pmd_young(*pmd);
-
-	pte = pte_offset_kernel(pmd, gpa);
-	if (!pte_none(*pte))		/* Just a page... */
+	else
 		return pte_young(*pte);
-
-	return 0;
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
-- 
cgit v1.2.3


From b8e0ba7c8bea994011aff3b4c35256b180fab874 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 11 Dec 2018 17:10:41 +0000
Subject: KVM: arm64: Add support for creating PUD hugepages at stage 2

KVM only supports PMD hugepages at stage 2. Now that the various page
handling routines are updated, extend the stage 2 fault handling to
map in PUD hugepages.

Addition of PUD hugepage support enables additional page sizes (e.g.,
1G with 4K granule) which can be useful on cores that support mapping
larger block sizes in the TLB entries.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
[ Replace BUG() => WARN_ON(1) for arm32 PUD helpers ]
Signed-off-by: Suzuki Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_mmu.h         |  20 +++++++
 arch/arm/include/asm/stage2_pgtable.h  |   5 ++
 arch/arm64/include/asm/kvm_mmu.h       |  16 +++++
 arch/arm64/include/asm/pgtable-hwdef.h |   2 +
 arch/arm64/include/asm/pgtable.h       |   2 +
 virt/kvm/arm/mmu.c                     | 104 +++++++++++++++++++++++++++++++--
 6 files changed, 143 insertions(+), 6 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 4b4b2146e6a0..3a875fc1b63c 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -84,11 +84,14 @@ void kvm_clear_hyp_idmap(void);
 
 #define kvm_pfn_pte(pfn, prot)	pfn_pte(pfn, prot)
 #define kvm_pfn_pmd(pfn, prot)	pfn_pmd(pfn, prot)
+#define kvm_pfn_pud(pfn, prot)	(__pud(0))
 
 #define kvm_pud_pfn(pud)	({ WARN_ON(1); 0; })
 
 
 #define kvm_pmd_mkhuge(pmd)	pmd_mkhuge(pmd)
+/* No support for pud hugepages */
+#define kvm_pud_mkhuge(pud)	( {WARN_ON(1); pud; })
 
 /*
  * The following kvm_*pud*() functions are provided strictly to allow
@@ -105,6 +108,23 @@ static inline bool kvm_s2pud_readonly(pud_t *pud)
 	return false;
 }
 
+static inline void kvm_set_pud(pud_t *pud, pud_t new_pud)
+{
+	WARN_ON(1);
+}
+
+static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
+{
+	WARN_ON(1);
+	return pud;
+}
+
+static inline pud_t kvm_s2pud_mkexec(pud_t pud)
+{
+	WARN_ON(1);
+	return pud;
+}
+
 static inline bool kvm_s2pud_exec(pud_t *pud)
 {
 	WARN_ON(1);
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index f6a7ea805232..f9017167a8d1 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -68,4 +68,9 @@ stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 #define stage2_pmd_table_empty(kvm, pmdp)	kvm_page_empty(pmdp)
 #define stage2_pud_table_empty(kvm, pudp)	false
 
+static inline bool kvm_stage2_has_pud(struct kvm *kvm)
+{
+	return false;
+}
+
 #endif	/* __ARM_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 9f941f70775c..8af4b1befa42 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -184,12 +184,16 @@ void kvm_clear_hyp_idmap(void);
 #define kvm_mk_pgd(pudp)					\
 	__pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE)
 
+#define kvm_set_pud(pudp, pud)		set_pud(pudp, pud)
+
 #define kvm_pfn_pte(pfn, prot)		pfn_pte(pfn, prot)
 #define kvm_pfn_pmd(pfn, prot)		pfn_pmd(pfn, prot)
+#define kvm_pfn_pud(pfn, prot)		pfn_pud(pfn, prot)
 
 #define kvm_pud_pfn(pud)		pud_pfn(pud)
 
 #define kvm_pmd_mkhuge(pmd)		pmd_mkhuge(pmd)
+#define kvm_pud_mkhuge(pud)		pud_mkhuge(pud)
 
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
@@ -203,6 +207,12 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
 	return pmd;
 }
 
+static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
+{
+	pud_val(pud) |= PUD_S2_RDWR;
+	return pud;
+}
+
 static inline pte_t kvm_s2pte_mkexec(pte_t pte)
 {
 	pte_val(pte) &= ~PTE_S2_XN;
@@ -215,6 +225,12 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
 	return pmd;
 }
 
+static inline pud_t kvm_s2pud_mkexec(pud_t pud)
+{
+	pud_val(pud) &= ~PUD_S2_XN;
+	return pud;
+}
+
 static inline void kvm_set_s2pte_readonly(pte_t *ptep)
 {
 	pteval_t old_pteval, pteval;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 336e24cddc87..6f1c187f1c86 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -193,6 +193,8 @@
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
 
+#define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
+#define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */
 #define PUD_S2_XN		(_AT(pudval_t, 2) << 53)  /* XN[1:0] */
 
 /*
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bb0f3f17a7a9..576128635f3c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -390,6 +390,8 @@ static inline int pmd_protnone(pmd_t pmd)
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
+#define pud_mkhuge(pud)		(__pud(pud_val(pud) & ~PUD_TABLE_BIT))
+
 #define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
 #define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 3893ea6a50bf..2dcff38868d4 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -115,6 +115,25 @@ static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
 	put_page(virt_to_page(pmd));
 }
 
+/**
+ * stage2_dissolve_pud() - clear and flush huge PUD entry
+ * @kvm:	pointer to kvm structure.
+ * @addr:	IPA
+ * @pud:	pud pointer for IPA
+ *
+ * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. Marks all
+ * pages in the range dirty.
+ */
+static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
+{
+	if (!stage2_pud_huge(kvm, *pudp))
+		return;
+
+	stage2_pud_clear(kvm, pudp);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	put_page(virt_to_page(pudp));
+}
+
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 				  int min, int max)
 {
@@ -1022,7 +1041,7 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
-	if (!pud)
+	if (!pud || stage2_pud_huge(kvm, *pud))
 		return NULL;
 
 	if (stage2_pud_none(kvm, *pud)) {
@@ -1083,6 +1102,36 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	return 0;
 }
 
+static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			       phys_addr_t addr, const pud_t *new_pudp)
+{
+	pud_t *pudp, old_pud;
+
+	pudp = stage2_get_pud(kvm, cache, addr);
+	VM_BUG_ON(!pudp);
+
+	old_pud = *pudp;
+
+	/*
+	 * A large number of vcpus faulting on the same stage 2 entry,
+	 * can lead to a refault due to the
+	 * stage2_pud_clear()/tlb_flush(). Skip updating the page
+	 * tables if there is no change.
+	 */
+	if (pud_val(old_pud) == pud_val(*new_pudp))
+		return 0;
+
+	if (stage2_pud_present(kvm, old_pud)) {
+		stage2_pud_clear(kvm, pudp);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	} else {
+		get_page(virt_to_page(pudp));
+	}
+
+	kvm_set_pud(pudp, *new_pudp);
+	return 0;
+}
+
 /*
  * stage2_get_leaf_entry - walk the stage2 VM page tables and return
  * true if a valid and present leaf-entry is found. A pointer to the
@@ -1149,6 +1198,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			  phys_addr_t addr, const pte_t *new_pte,
 			  unsigned long flags)
 {
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
 	bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
@@ -1157,7 +1207,31 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	VM_BUG_ON(logging_active && !cache);
 
 	/* Create stage-2 page table mapping - Levels 0 and 1 */
-	pmd = stage2_get_pmd(kvm, cache, addr);
+	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud) {
+		/*
+		 * Ignore calls from kvm_set_spte_hva for unallocated
+		 * address ranges.
+		 */
+		return 0;
+	}
+
+	/*
+	 * While dirty page logging - dissolve huge PUD, then continue
+	 * on to allocate page.
+	 */
+	if (logging_active)
+		stage2_dissolve_pud(kvm, addr, pud);
+
+	if (stage2_pud_none(kvm, *pud)) {
+		if (!cache)
+			return 0; /* ignore calls from kvm_set_spte_hva */
+		pmd = mmu_memory_cache_alloc(cache);
+		stage2_pud_populate(kvm, pud, pmd);
+		get_page(virt_to_page(pud));
+	}
+
+	pmd = stage2_pmd_offset(kvm, pud, addr);
 	if (!pmd) {
 		/*
 		 * Ignore calls from kvm_set_spte_hva for unallocated
@@ -1557,12 +1631,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	vma_pagesize = vma_kernel_pagesize(vma);
-	if (vma_pagesize == PMD_SIZE && !logging_active) {
-		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
+	/*
+	 * PUD level may not exist for a VM but PMD is guaranteed to
+	 * exist.
+	 */
+	if ((vma_pagesize == PMD_SIZE ||
+	     (vma_pagesize == PUD_SIZE && kvm_stage2_has_pud(kvm))) &&
+	    !logging_active) {
+		gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
 	} else {
 		/*
 		 * Fallback to PTE if it's not one of the Stage 2
-		 * supported hugepage sizes
+		 * supported hugepage sizes or the corresponding level
+		 * doesn't exist
 		 */
 		vma_pagesize = PAGE_SIZE;
 
@@ -1661,7 +1742,18 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	needs_exec = exec_fault ||
 		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
 
-	if (vma_pagesize == PMD_SIZE) {
+	if (vma_pagesize == PUD_SIZE) {
+		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
+
+		new_pud = kvm_pud_mkhuge(new_pud);
+		if (writable)
+			new_pud = kvm_s2pud_mkwrite(new_pud);
+
+		if (needs_exec)
+			new_pud = kvm_s2pud_mkexec(new_pud);
+
+		ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
+	} else if (vma_pagesize == PMD_SIZE) {
 		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
 
 		new_pmd = kvm_pmd_mkhuge(new_pmd);
-- 
cgit v1.2.3


From 6992195cc6c6c4d673a3266ae59cbeeb746d61af Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@arm.com>
Date: Tue, 6 Nov 2018 13:33:38 +0100
Subject: KVM: arm64: Clarify explanation of STAGE2_PGTABLE_LEVELS

In attempting to re-construct the logic for our stage 2 page table
layout I found the reasoning in the comment explaining how we calculate
the number of levels used for stage 2 page tables a bit backwards.

This commit attempts to clarify the comment, to make it slightly easier
to read without having the Arm ARM open on the right page.

While we're at it, fixup a typo in a comment that was recently changed.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/stage2_pgtable.h | 16 +++++++---------
 virt/kvm/arm/mmu.c                      |  2 +-
 2 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index d352f6df8d2c..5412fa40825e 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -30,16 +30,14 @@
 #define pt_levels_pgdir_shift(lvls)	ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
 
 /*
- * The hardware supports concatenation of up to 16 tables at stage2 entry level
- * and we use the feature whenever possible.
+ * The hardware supports concatenation of up to 16 tables at stage2 entry
+ * level and we use the feature whenever possible, which means we resolve 4
+ * additional bits of address at the entry level.
  *
- * Now, the minimum number of bits resolved at any level is (PAGE_SHIFT - 3).
- * On arm64, the smallest PAGE_SIZE supported is 4k, which means
- *             (PAGE_SHIFT - 3) > 4 holds for all page sizes.
- * This implies, the total number of page table levels at stage2 expected
- * by the hardware is actually the number of levels required for (IPA_SHIFT - 4)
- * in normal translations(e.g, stage1), since we cannot have another level in
- * the range (IPA_SHIFT, IPA_SHIFT - 4).
+ * This implies, the total number of page table levels required for
+ * IPA_SHIFT at stage2 expected by the hardware can be calculated using
+ * the same logic used for the (non-collapsable) stage1 page tables but for
+ * (IPA_SHIFT - 4).
  */
 #define stage2_pgtable_levels(ipa)	ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
 #define kvm_stage2_levels(kvm)		VTCR_EL2_LVLS(kvm->arch.vtcr)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 2dcff38868d4..f605514395a1 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1356,7 +1356,7 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
 	struct page *page = pfn_to_page(pfn);
 
 	/*
-	 * PageTransCompoungMap() returns true for THP and
+	 * PageTransCompoundMap() returns true for THP and
 	 * hugetlbfs. Make sure the adjustment is done only for THP
 	 * pages.
 	 */
-- 
cgit v1.2.3


From 71a7e47f39a2fb971ef9934e98ba089581eff641 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@arm.com>
Date: Mon, 3 Dec 2018 21:31:24 +0100
Subject: KVM: arm/arm64: Fixup the kvm_exit tracepoint

The kvm_exit tracepoint strangely always reported exits as being IRQs.
This seems to be because either the __print_symbolic or the tracepoint
macros use a variable named idx.

Take this chance to update the fields in the tracepoint to reflect the
concepts in the arm64 architecture that we pass to the tracepoint and
move the exception type table to the same location and header files as
the exits code.

We also clear out the exception code to 0 for IRQ exits (which
translates to UNKNOWN in text) to make it slighyly less confusing to
parse the trace output.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/kvm_arm.h |  4 ----
 arch/arm64/include/asm/kvm_asm.h |  6 ++++++
 virt/kvm/arm/trace.h             | 18 +++++++++---------
 3 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6f602af5263c..9921bb7ab6d8 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -320,10 +320,6 @@
 #define PAR_TO_HPFAR(par)		\
 	(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
 
-#define kvm_arm_exception_type	\
-	{0, "IRQ" }, 		\
-	{1, "TRAP" }
-
 #define ECN(x) { ESR_ELx_EC_##x, #x }
 
 #define kvm_arm_exception_class \
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index aea01a09eb94..b2e12c99db7d 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -34,6 +34,12 @@
 /* The hyp-stub will return this for any kvm_call_hyp() call */
 #define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
 
+#define kvm_arm_exception_type					\
+	{ARM_EXCEPTION_IRQ,		"IRQ"		},	\
+	{ARM_EXCEPTION_EL1_SERROR, 	"SERROR"	},	\
+	{ARM_EXCEPTION_TRAP, 		"TRAP"		},	\
+	{ARM_EXCEPTION_HYP_GONE,	"HYP_GONE"	}
+
 #ifndef __ASSEMBLY__
 
 #include <linux/mm.h>
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
index 57b3edebbb40..f21f04f8036d 100644
--- a/virt/kvm/arm/trace.h
+++ b/virt/kvm/arm/trace.h
@@ -26,25 +26,25 @@ TRACE_EVENT(kvm_entry,
 );
 
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
-	TP_ARGS(idx, exit_reason, vcpu_pc),
+	TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc),
+	TP_ARGS(ret, esr_ec, vcpu_pc),
 
 	TP_STRUCT__entry(
-		__field(	int,		idx		)
-		__field(	unsigned int,	exit_reason	)
+		__field(	int,		ret		)
+		__field(	unsigned int,	esr_ec		)
 		__field(	unsigned long,	vcpu_pc		)
 	),
 
 	TP_fast_assign(
-		__entry->idx			= idx;
-		__entry->exit_reason		= exit_reason;
+		__entry->ret			= ARM_EXCEPTION_CODE(ret);
+		__entry->esr_ec = (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_TRAP) ? esr_ec : 0;
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
 	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
-		  __print_symbolic(__entry->idx, kvm_arm_exception_type),
-		  __entry->exit_reason,
-		  __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
+		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
+		  __entry->esr_ec,
+		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
 		  __entry->vcpu_pc)
 );
 
-- 
cgit v1.2.3


From da6f16662a6eba3de0d1a39f3b8913d38754bb2b Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@arm.com>
Date: Thu, 29 Nov 2018 12:20:01 +0100
Subject: KVM: arm64: Make vcpu const in vcpu_read_sys_reg

vcpu_read_sys_reg should not be modifying the VCPU structure.
Eventually, to handle EL2 sysregs for nested virtualization, we will
call vcpu_read_sys_reg from places that have a const vcpu pointer, which
will complain about the lack of the const modifier on the read path.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/kvm_host.h | 2 +-
 arch/arm64/kvm/sys_regs.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/arm64')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 7a5035f9c5c3..c22e50ba3473 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -319,7 +319,7 @@ struct kvm_vcpu_arch {
  */
 #define __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
 
-u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg);
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
 
 /*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ecbf67ccabf5..965c6f1706d6 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -76,7 +76,7 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	if (!vcpu->arch.sysregs_loaded_on_cpu)
 		goto immediate_read;
-- 
cgit v1.2.3


From 599d79dcd18fa0f88ae15b7042c9d6b011a678b2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 4 Dec 2018 10:44:22 +0000
Subject: arm64: KVM: Add trapped system register access tracepoint

We're pretty blind when it comes to system register tracing,
and rely on the ESR value displayed by kvm_handle_sys, which
isn't much.

Instead, let's add an actual name to the sysreg entries, so that
we can finally print it as we're about to perform the access
itself.

The new tracepoint is conveniently called kvm_sys_access.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/kvm/sys_regs.c |  2 ++
 arch/arm64/kvm/sys_regs.h |  4 ++++
 arch/arm64/kvm/trace.h    | 35 +++++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

(limited to 'arch/arm64')

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 965c6f1706d6..a1f57fcb1bdb 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1850,6 +1850,8 @@ static void perform_access(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *params,
 			   const struct sys_reg_desc *r)
 {
+	trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
+
 	/*
 	 * Not having an accessor means that we have configured a trap
 	 * that we don't know how to handle. This certainly qualifies
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index cd710f8b63e0..3b1bc7f01d0b 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -35,6 +35,9 @@ struct sys_reg_params {
 };
 
 struct sys_reg_desc {
+	/* Sysreg string for debug */
+	const char *name;
+
 	/* MRS/MSR instruction which accesses it. */
 	u8	Op0;
 	u8	Op1;
@@ -130,6 +133,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 #define Op2(_x) 	.Op2 = _x
 
 #define SYS_DESC(reg)					\
+	.name = #reg,					\
 	Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)),	\
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h
index 3b82fb1ddd09..eab91ad0effb 100644
--- a/arch/arm64/kvm/trace.h
+++ b/arch/arm64/kvm/trace.h
@@ -3,6 +3,7 @@
 #define _TRACE_ARM64_KVM_H
 
 #include <linux/tracepoint.h>
+#include "sys_regs.h"
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
@@ -152,6 +153,40 @@ TRACE_EVENT(kvm_handle_sys_reg,
 	TP_printk("HSR 0x%08lx", __entry->hsr)
 );
 
+TRACE_EVENT(kvm_sys_access,
+	TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg),
+	TP_ARGS(vcpu_pc, params, reg),
+
+	TP_STRUCT__entry(
+		__field(unsigned long,			vcpu_pc)
+		__field(bool,				is_write)
+		__field(const char *,			name)
+		__field(u8,				Op0)
+		__field(u8,				Op1)
+		__field(u8,				CRn)
+		__field(u8,				CRm)
+		__field(u8,				Op2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->is_write = params->is_write;
+		__entry->name = reg->name;
+		__entry->Op0 = reg->Op0;
+		__entry->Op0 = reg->Op0;
+		__entry->Op1 = reg->Op1;
+		__entry->CRn = reg->CRn;
+		__entry->CRm = reg->CRm;
+		__entry->Op2 = reg->Op2;
+	),
+
+	TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s",
+		  __entry->vcpu_pc, __entry->name ?: "UNKN",
+		  __entry->Op0, __entry->Op1, __entry->CRn,
+		  __entry->CRm, __entry->Op2,
+		  __entry->is_write ? "write" : "read")
+);
+
 TRACE_EVENT(kvm_set_guest_debug,
 	TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
 	TP_ARGS(vcpu, guest_debug),
-- 
cgit v1.2.3


From df655b75c43fba0f2621680ab261083297fd6d16 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Thu, 13 Dec 2018 16:06:14 +0000
Subject: arm64: KVM: Avoid setting the upper 32 bits of VTCR_EL2 to 1

Although bit 31 of VTCR_EL2 is RES1, we inadvertently end up setting all
of the upper 32 bits to 1 as well because we define VTCR_EL2_RES1 as
signed, which is sign-extended when assigning to kvm->arch.vtcr.

Lucky for us, the architecture currently treats these upper bits as RES0
so, whilst we've been naughty, we haven't set fire to anything yet.

Cc: <stable@vger.kernel.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/kvm_arm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/arm64')

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 9921bb7ab6d8..9c1a065b78ea 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -104,7 +104,7 @@
 			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
 
 /* VTCR_EL2 Registers bits */
-#define VTCR_EL2_RES1		(1 << 31)
+#define VTCR_EL2_RES1		(1U << 31)
 #define VTCR_EL2_HD		(1 << 22)
 #define VTCR_EL2_HA		(1 << 21)
 #define VTCR_EL2_PS_SHIFT	TCR_EL2_PS_SHIFT
-- 
cgit v1.2.3


From 58466766cd35754a061414c0c93225db2962948e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Wed, 19 Dec 2018 08:28:38 +0000
Subject: arm/arm64: KVM: Add ARM_EXCEPTION_IS_TRAP macro

32 and 64bit use different symbols to identify the traps.
32bit has a fine grained approach (prefetch abort, data abort and HVC),
while 64bit is pretty happy with just "trap".

This has been fine so far, except that we now need to decode some
of that in tracepoints that are common to both architectures.

Introduce ARM_EXCEPTION_IS_TRAP which abstracts the trap symbols
and make the tracepoint use it.

Acked-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_asm.h   | 4 ++++
 arch/arm64/include/asm/kvm_asm.h | 1 +
 virt/kvm/arm/trace.h             | 2 +-
 3 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'arch/arm64')

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 231e87ad45d5..35491af87985 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -23,6 +23,10 @@
 
 #define ARM_EXIT_WITH_ABORT_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT))
+#define ARM_EXCEPTION_IS_TRAP(x)					\
+	(ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_PREF_ABORT	||	\
+	 ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_DATA_ABORT	||	\
+	 ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_HVC)
 #define ARM_ABORT_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT))
 
 #define ARM_EXCEPTION_RESET	  0
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b2e12c99db7d..f5b79e995f40 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -25,6 +25,7 @@
 
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
+#define ARM_EXCEPTION_IS_TRAP(x)  (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
 #define ARM_SERROR_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
 
 #define ARM_EXCEPTION_IRQ	  0
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
index f21f04f8036d..3828beab93f2 100644
--- a/virt/kvm/arm/trace.h
+++ b/virt/kvm/arm/trace.h
@@ -37,7 +37,7 @@ TRACE_EVENT(kvm_exit,
 
 	TP_fast_assign(
 		__entry->ret			= ARM_EXCEPTION_CODE(ret);
-		__entry->esr_ec = (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_TRAP) ? esr_ec : 0;
+		__entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0;
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-- 
cgit v1.2.3