Merge remote-tracking branch 'kvm/next' into kvm-next-5.20

KVM/s390, KVM/x86 and common infrastructure changes for 5.20

x86:

* Permit guests to ignore single-bit ECC errors

* Fix races in gfn->pfn cache refresh; do not pin pages tracked by the cache

* Intel IPI virtualization

* Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS

* PEBS virtualization

* Simplify PMU emulation by just using PERF_TYPE_RAW events

* More accurate event reinjection on SVM (avoid retrying instructions)

* Allow getting/setting the state of the speaker port data bit

* Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls are inconsistent

* "Notify" VM exit (detect microarchitectural hangs) for Intel

* Cleanups for MCE MSR emulation

s390:

* add an interface to provide a hypervisor dump for secure guests

* improve selftests to use TAP interface

* enable interpretive execution of zPCI instructions (for PCI passthrough)

* First part of deferred teardown

* CPU Topology

* PV attestation

* Minor fixes

Generic:

* new selftests API using struct kvm_vcpu instead of a (vm, id) tuple

x86:

* Use try_cmpxchg64 instead of cmpxchg64

* Bugfixes

* Ignore benign host accesses to PMU MSRs when PMU is disabled

* Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

* x86/MMU: Allow NX huge pages to be disabled on a per-vm basis

* Port eager page splitting to shadow MMU as well

* Enable CMCI capability by default and handle injected UCNA errors

* Expose pid of vcpu threads in debugfs

* x2AVIC support for AMD

* cleanup PIO emulation

* Fixes for LLDT/LTR emulation

* Don't require refcounted "struct page" to create huge SPTEs

x86 cleanups:

* Use separate namespaces for guest PTEs and shadow PTEs bitmasks

* PIO emulation

* Reorganize rmap API, mostly around rmap destruction

* Do not workaround very old KVM bugs for L0 that runs with nesting enabled

* new selftests API for CPUID

1 files changed, 31 insertions, 18 deletions

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index f8382abe22ff..047c583596bb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -244,6 +244,9 @@ enum x86_transfer_type {
 
 static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
 {
+	if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+		nr &= NR_EMULATOR_GPRS - 1;
+
 	if (!(ctxt->regs_valid & (1 << nr))) {
 		ctxt->regs_valid |= 1 << nr;
 		ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
@@ -253,6 +256,12 @@ static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
 
 static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
 {
+	if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+		nr &= NR_EMULATOR_GPRS - 1;
+
+	BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+	BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+
 	ctxt->regs_valid |= 1 << nr;
 	ctxt->regs_dirty |= 1 << nr;
 	return &ctxt->_regs[nr];
@@ -266,9 +275,10 @@ static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
 
 static void writeback_registers(struct x86_emulate_ctxt *ctxt)
 {
+	unsigned long dirty = ctxt->regs_dirty;
 	unsigned reg;
 
-	for_each_set_bit(reg, (ulong *)&ctxt->regs_dirty, 16)
+	for_each_set_bit(reg, &dirty, NR_EMULATOR_GPRS)
 		ctxt->ops->write_gpr(ctxt, reg, ctxt->_regs[reg]);
 }
 
@@ -615,7 +625,9 @@ static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
 static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec,
 			     u32 error, bool valid)
 {
-	WARN_ON(vec > 0x1f);
+	if (KVM_EMULATOR_BUG_ON(vec > 0x1f, ctxt))
+		return X86EMUL_UNHANDLEABLE;
+
 	ctxt->exception.vector = vec;
 	ctxt->exception.error_code = error;
 	ctxt->exception.error_code_valid = valid;
@@ -1362,7 +1374,8 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt,
 	if (mc->pos < mc->end)
 		goto read_cached;
 
-	WARN_ON((mc->end + size) >= sizeof(mc->data));
+	if (KVM_EMULATOR_BUG_ON((mc->end + size) >= sizeof(mc->data), ctxt))
+		return X86EMUL_UNHANDLEABLE;
 
 	rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, size,
 				      &ctxt->exception);
@@ -1687,16 +1700,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	case VCPU_SREG_TR:
 		if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
 			goto exception;
-		if (!seg_desc.p) {
-			err_vec = NP_VECTOR;
-			goto exception;
-		}
-		old_desc = seg_desc;
-		seg_desc.type |= 2; /* busy */
-		ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
-						  sizeof(seg_desc), &ctxt->exception);
-		if (ret != X86EMUL_CONTINUE)
-			return ret;
 		break;
 	case VCPU_SREG_LDTR:
 		if (seg_desc.s || seg_desc.type != 2)
@@ -1734,8 +1737,17 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 		if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
-				((u64)base3 << 32), ctxt))
-			return emulate_gp(ctxt, 0);
+						 ((u64)base3 << 32), ctxt))
+			return emulate_gp(ctxt, err_code);
+	}
+
+	if (seg == VCPU_SREG_TR) {
+		old_desc = seg_desc;
+		seg_desc.type |= 2; /* busy */
+		ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
+						  sizeof(seg_desc), &ctxt->exception);
+		if (ret != X86EMUL_CONTINUE)
+			return ret;
 	}
 load:
 	ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
@@ -2432,7 +2444,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
 	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
 
-	for (i = 0; i < 8; i++)
+	for (i = 0; i < NR_EMULATOR_GPRS; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
@@ -2489,7 +2501,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	u16 selector;
 	int i, r;
 
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < NR_EMULATOR_GPRS; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
 
 	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
@@ -5719,7 +5731,8 @@ writeback:
 
 done:
 	if (rc == X86EMUL_PROPAGATE_FAULT) {
-		WARN_ON(ctxt->exception.vector > 0x1f);
+		if (KVM_EMULATOR_BUG_ON(ctxt->exception.vector > 0x1f, ctxt))
+			return EMULATION_FAILED;
 		ctxt->have_exception = true;
 	}
 	if (rc == X86EMUL_INTERCEPTED)