Merge tag 'kvm-arm-for-v4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into next

KVM/ARM Changes for v4.9 - Various cleanups and removal of redundant code - Two important fixes for not using an in-kernel irqchip - A bit of optimizations - Handle SError exceptions and present them to guests if appropriate - Proxying of GICV access at EL2 if guest mappings are unsafe - GICv3 on AArch32 on ARMv8 - Preparations for GICv3 save/restore, including ABI docs
2016-09-29 16:01:51 +02:00
commit 45ca877ad0
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,13 +21,16 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
+obj-y += $(KVM)/arm/aarch32.o

 obj-y += $(KVM)/arm/vgic/vgic.o
 obj-y += $(KVM)/arm/vgic/vgic-init.o
 obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
 obj-y += $(KVM)/arm/vgic/vgic-v2.o
+obj-y += $(KVM)/arm/vgic/vgic-v3.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
+obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
 obj-y += $(KVM)/irqchip.o
 obj-y += $(KVM)/arm/arch_timer.o
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1188,6 +1188,10 @@ static int init_common_resources(void)
 		return -ENOMEM;
 	}

+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
 	return 0;
 }

@@ -1253,10 +1257,6 @@ static void teardown_hyp_mode(void)

 static int init_vhe_mode(void)
 {
-	/* set size of VMID supported by CPU */
-	kvm_vmid_bits = kvm_get_vmid_bits();
-	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
-
 	kvm_info("VHE mode initialized successfully\n");
 	return 0;
 }
@@ -1340,10 +1340,6 @@ static int init_hyp_mode(void)
 		}
 	}

-	/* set size of VMID supported by CPU */
-	kvm_vmid_bits = kvm_get_vmid_bits();
-	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
-
 	kvm_info("Hyp mode initialized successfully\n");

 	return 0;
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -228,6 +228,35 @@ bool access_vm_reg(struct kvm_vcpu *vcpu,
 	return true;
 }

+static bool access_gic_sgi(struct kvm_vcpu *vcpu,
+			   const struct coproc_params *p,
+			   const struct coproc_reg *r)
+{
+	u64 reg;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
+	reg = (u64)*vcpu_reg(vcpu, p->Rt2) << 32;
+	reg |= *vcpu_reg(vcpu, p->Rt1) ;
+
+	vgic_v3_dispatch_sgi(vcpu, reg);
+
+	return true;
+}
+
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+			   const struct coproc_params *p,
+			   const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+
+	return true;
+}
+
 /*
 * We could trap ID_DFR0 and tell the guest we don't support performance
 * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
@@ -361,10 +390,16 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
 			access_vm_reg, reset_unknown, c10_AMAIR1},

+	/* ICC_SGI1R */
+	{ CRm64(12), Op1( 0), is64, access_gic_sgi},
+
 	/* VBAR: swapped by interrupt.S. */
 	{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
 			NULL, reset_val, c12_VBAR, 0x00000000 },

+	/* ICC_SRE */
+	{ CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre },
+
 	/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
 			access_vm_reg, reset_val, c13_CID, 0x00000000 },
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -161,105 +161,6 @@ unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
 	}
 }

-/*
- * A conditional instruction is allowed to trap, even though it
- * wouldn't be executed.  So let's re-implement the hardware, in
- * software!
- */
-bool kvm_condition_valid(struct kvm_vcpu *vcpu)
-{
-	unsigned long cpsr, cond, insn;
-
-	/*
-	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
-	 * catch undefined instructions, and then we won't get past
-	 * the arm_exit_handlers test anyway.
-	 */
-	BUG_ON(!kvm_vcpu_trap_get_class(vcpu));
-
-	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
-		return true;
-
-	cpsr = *vcpu_cpsr(vcpu);
-
-	/* Is condition field valid? */
-	if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT)
-		cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT;
-	else {
-		/* This can happen in Thumb mode: examine IT state. */
-		unsigned long it;
-
-		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
-
-		/* it == 0 => unconditional. */
-		if (it == 0)
-			return true;
-
-		/* The cond for this insn works out as the top 4 bits. */
-		cond = (it >> 4);
-	}
-
-	/* Shift makes it look like an ARM-mode instruction */
-	insn = cond << 28;
-	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
-}
-
-/**
- * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
- * @vcpu:	The VCPU pointer
- *
- * When exceptions occur while instructions are executed in Thumb IF-THEN
- * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
- * to do this little bit of work manually. The fields map like this:
- *
- * IT[7:0] -> CPSR[26:25],CPSR[15:10]
- */
-static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
-{
-	unsigned long itbits, cond;
-	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_arm = !(cpsr & PSR_T_BIT);
-
-	BUG_ON(is_arm && (cpsr & PSR_IT_MASK));
-
-	if (!(cpsr & PSR_IT_MASK))
-		return;
-
-	cond = (cpsr & 0xe000) >> 13;
-	itbits = (cpsr & 0x1c00) >> (10 - 2);
-	itbits |= (cpsr & (0x3 << 25)) >> 25;
-
-	/* Perform ITAdvance (see page A-52 in ARM DDI 0406C) */
-	if ((itbits & 0x7) == 0)
-		itbits = cond = 0;
-	else
-		itbits = (itbits << 1) & 0x1f;
-
-	cpsr &= ~PSR_IT_MASK;
-	cpsr |= cond << 13;
-	cpsr |= (itbits & 0x1c) << (10 - 2);
-	cpsr |= (itbits & 0x3) << 25;
-	*vcpu_cpsr(vcpu) = cpsr;
-}
-
-/**
- * kvm_skip_instr - skip a trapped instruction and proceed to the next
- * @vcpu: The vcpu pointer
- */
-void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
-{
-	bool is_thumb;
-
-	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_T_BIT);
-	if (is_thumb && !is_wide_instr)
-		*vcpu_pc(vcpu) += 2;
-	else
-		*vcpu_pc(vcpu) += 4;
-	kvm_adjust_itstate(vcpu);
-}
-
-
 /******************************************************************************
 * Inject exceptions into the guest
 */
@@ -402,3 +303,15 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	inject_abt(vcpu, true, addr);
 }
+
+/**
+ * kvm_inject_vabt - inject an async abort / SError into the guest
+ * @vcpu: The VCPU to receive the exception
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_vabt(struct kvm_vcpu *vcpu)
+{
+	vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VA);
+}
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -28,14 +28,6 @@

 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);

-static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* SVC called from Hyp mode should never get here */
-	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
-	BUG();
-	return -EINVAL; /* Squash warning */
-}
-
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
@@ -59,22 +51,6 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }

-static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* The hypervisor should never cause aborts */
-	kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
-		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
-	return -EFAULT;
-}
-
-static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* This is either an error in the ws. code or an external abort */
-	kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
-		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
-	return -EFAULT;
-}
-
 /**
 * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests
 * @vcpu:	the vcpu pointer
@@ -112,13 +88,10 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
 	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
 	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
-	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
 	[HSR_EC_HVC]		= handle_hvc,
 	[HSR_EC_SMC]		= handle_smc,
 	[HSR_EC_IABT]		= kvm_handle_guest_abort,
-	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
 	[HSR_EC_DABT]		= kvm_handle_guest_abort,
-	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
 };

 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
@@ -144,6 +117,25 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 {
 	exit_handle_fn exit_handler;

+	if (ARM_ABORT_PENDING(exception_index)) {
+		u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+
+		/*
+		 * HVC/SMC already have an adjusted PC, which we need
+		 * to correct in order to return to after having
+		 * injected the abort.
+		 */
+		if (hsr_ec == HSR_EC_HVC || hsr_ec == HSR_EC_SMC) {
+			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
+			*vcpu_pc(vcpu) -= adj;
+		}
+
+		kvm_inject_vabt(vcpu);
+		return 1;
+	}
+
+	exception_index = ARM_EXCEPTION_CODE(exception_index);
+
 	switch (exception_index) {
 	case ARM_EXCEPTION_IRQ:
 		return 1;
@@ -160,6 +152,9 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		exit_handler = kvm_get_exit_handler(vcpu);

 		return exit_handler(vcpu, run);
+	case ARM_EXCEPTION_DATA_ABORT:
+		kvm_inject_vabt(vcpu);
+		return 1;
 	default:
 		kvm_pr_unimpl("Unsupported exception type: %d",
 			      exception_index);
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -5,6 +5,7 @@
 KVM=../../../../virt/kvm

 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o

 obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
--- a/arch/arm/kvm/hyp/entry.S
+++ b/arch/arm/kvm/hyp/entry.S
@@ -18,6 +18,7 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>

 	.arch_extension     virt

@@ -63,6 +64,36 @@ ENTRY(__guest_exit)
 	ldr	lr, [r0, #4]

 	mov	r0, r1
+	mrs	r1, SPSR
+	mrs	r2, ELR_hyp
+	mrc	p15, 4, r3, c5, c2, 0	@ HSR
+
+	/*
+	 * Force loads and stores to complete before unmasking aborts
+	 * and forcing the delivery of the exception. This gives us a
+	 * single instruction window, which the handler will try to
+	 * match.
+	 */
+	dsb	sy
+	cpsie	a
+
+	.global	abort_guest_exit_start
+abort_guest_exit_start:
+
+	isb
+
+	.global	abort_guest_exit_end
+abort_guest_exit_end:
+
+	/*
+	 * If we took an abort, r0[31] will be set, and cmp will set
+	 * the N bit in PSTATE.
+	 */
+	cmp	r0, #0
+	msrmi	SPSR_cxsf, r1
+	msrmi	ELR_hyp, r2
+	mcrmi	p15, 4, r3, c5, c2, 0	@ HSR
+
 	bx	lr
 ENDPROC(__guest_exit)

--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -81,7 +81,6 @@ __kvm_hyp_vector:
 	invalid_vector	hyp_undef	ARM_EXCEPTION_UNDEFINED
 	invalid_vector	hyp_svc		ARM_EXCEPTION_SOFTWARE
 	invalid_vector	hyp_pabt	ARM_EXCEPTION_PREF_ABORT
-	invalid_vector	hyp_dabt	ARM_EXCEPTION_DATA_ABORT
 	invalid_vector	hyp_fiq		ARM_EXCEPTION_FIQ

 ENTRY(__hyp_do_panic)
@@ -164,6 +163,21 @@ hyp_irq:
 	load_vcpu r0			@ Load VCPU pointer to r0
 	b	__guest_exit

+hyp_dabt:
+	push	{r0, r1}
+	mrs	r0, ELR_hyp
+	ldr	r1, =abort_guest_exit_start
+THUMB(	add	r1, r1, #1)
+	cmp	r0, r1
+	ldrne	r1, =abort_guest_exit_end
+THUMB(	addne	r1, r1, #1)
+	cmpne	r0, r1
+	pop	{r0, r1}
+	bne	__hyp_panic
+
+	orr	r0, r0, #(1 << ARM_EXIT_WITH_ABORT_BIT)
+	eret
+
 	.ltorg

 	.popsection
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -14,6 +14,7 @@
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
+#include <linux/jump_label.h>

 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
@@ -54,6 +55,15 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	u32 val;

+	/*
+	 * If we pended a virtual abort, preserve it until it gets
+	 * cleared. See B1.9.9 (Virtual Abort exception) for details,
+	 * but the crucial bit is the zeroing of HCR.VA in the
+	 * pseudocode.
+	 */
+	if (vcpu->arch.hcr & HCR_VA)
+		vcpu->arch.hcr = read_sysreg(HCR);
+
 	write_sysreg(0, HCR);
 	write_sysreg(0, HSTR);
 	val = read_sysreg(HDCR);
@@ -74,14 +84,21 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
 	write_sysreg(read_sysreg(MIDR), VPIDR);
 }

+
 static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
 {
-	__vgic_v2_save_state(vcpu);
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+		__vgic_v3_save_state(vcpu);
+	else
+		__vgic_v2_save_state(vcpu);
 }

 static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
 {
-	__vgic_v2_restore_state(vcpu);
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+		__vgic_v3_restore_state(vcpu);
+	else
+		__vgic_v2_restore_state(vcpu);
 }

 static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
@@ -134,7 +151,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }

-static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
+int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
@@ -191,8 +208,6 @@ again:
 	return exit_code;
 }

-__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
-
 static const char * const __hyp_panic_string[] = {
 	[ARM_EXCEPTION_RESET]      = "\nHYP panic: RST   PC:%08x CPSR:%08x",
 	[ARM_EXCEPTION_UNDEFINED]  = "\nHYP panic: UNDEF PC:%08x CPSR:%08x",
--- a/arch/arm/kvm/hyp/tlb.c
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -34,7 +34,7 @@
 * As v7 does not support flushing per IPA, just nuke the whole TLB
 * instead, ignoring the ipa value.
 */
-static void __hyp_text __tlb_flush_vmid(struct kvm *kvm)
+void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 {
 	dsb(ishst);

@@ -50,21 +50,14 @@ static void __hyp_text __tlb_flush_vmid(struct kvm *kvm)
 	write_sysreg(0, VTTBR);
 }

-__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm);
-
-static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
-	__tlb_flush_vmid(kvm);
+	__kvm_tlb_flush_vmid(kvm);
 }

-__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm,
-							    phys_addr_t ipa);
-
-static void __hyp_text __tlb_flush_vm_context(void)
+void __hyp_text __kvm_flush_vm_context(void)
 {
 	write_sysreg(0, TLBIALLNSNHIS);
 	write_sysreg(0, ICIALLUIS);
 	dsb(ish);
 }
-
-__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void);
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -126,12 +126,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 	int access_size;
 	bool sign_extend;

-	if (kvm_vcpu_dabt_isextabt(vcpu)) {
-		/* cache operation on I/O addr, tell guest unsupported */
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
-	}
-
 	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
 		/* page table accesses IO mem: tell guest to fix its TTBR */
 		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -744,7 +744,6 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 	if (!pgd)
 		return -ENOMEM;

-	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
 }
@@ -936,7 +935,6 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 		if (!cache)
 			return 0; /* ignore calls from kvm_set_spte_hva */
 		pte = mmu_memory_cache_alloc(cache);
-		kvm_clean_pte(pte);
 		pmd_populate_kernel(NULL, pmd, pte);
 		get_page(virt_to_page(pmd));
 	}
@@ -1434,6 +1432,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	int ret, idx;

 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+	if (unlikely(!is_iabt && kvm_vcpu_dabt_isextabt(vcpu))) {
+		kvm_inject_vabt(vcpu);
+		return 1;
+	}
+
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);

 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),