Merge tag 'kvm-4.11-2' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more KVM updates from Radim Krčmář:
 "Second batch of KVM changes for the 4.11 merge window:

  PPC:
   - correct assumption about ASDR on POWER9
   - fix MMIO emulation on POWER9

  x86:
   - add a simple test for ioperm
   - cleanup TSS (going through KVM tree as the whole undertaking was
     caused by VMX's use of TSS)
   - fix nVMX interrupt delivery
   - fix some performance counters in the guest

  ... and two cleanup patches"

* tag 'kvm-4.11-2' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: nVMX: Fix pending events injection
  x86/kvm/vmx: remove unused variable in segment_base()
  selftests/x86: Add a basic selftest for ioperm
  x86/asm: Tidy up TSS limit code
  kvm: convert kvm.users_count from atomic_t to refcount_t
  KVM: x86: never specify a sample period for virtualized in_tx_cp counters
  KVM: PPC: Book3S HV: Don't use ASDR for real-mode HPT faults on POWER9
  KVM: PPC: Book3S HV: Fix software walk of guest process page tables

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -46,7 +46,7 @@ extern struct patb_entry *partition_tb;
 
 /* Bits in patb0 field */
 #define PATB_HR		(1UL << 63)
-#define RPDB_MASK	0x0ffffffffffff00fUL
+#define RPDB_MASK	0x0fffffffffffff00UL
 #define RPDB_SHIFT	(1UL << 8)
 #define RTS1_SHIFT	61		/* top 2 bits of radix tree size */
 #define RTS1_MASK	(3UL << RTS1_SHIFT)
@@ -57,6 +57,7 @@ extern struct patb_entry *partition_tb;
 /* Bits in patb1 field */
 #define PATB_GR		(1UL << 63)	/* guest uses radix; must match HR */
 #define PRTS_MASK	0x1f		/* process table size field */
+#define PRTB_MASK	0x0ffffffffffff000UL
 
 /*
  * Limit process table to PAGE_SIZE table. This

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -32,6 +32,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u32 pid;
 	int ret, level, ps;
 	__be64 prte, rpte;
+	unsigned long ptbl;
 	unsigned long root, pte, index;
 	unsigned long rts, bits, offset;
 	unsigned long gpa;
@@ -53,8 +54,8 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return -EINVAL;
 
 	/* Read partition table to find root of tree for effective PID */
-	ret = kvm_read_guest(kvm, kvm->arch.process_table + pid * 16,
-			     &prte, sizeof(prte));
+	ptbl = (kvm->arch.process_table & PRTB_MASK) + (pid * 16);
+	ret = kvm_read_guest(kvm, ptbl, &prte, sizeof(prte));
 	if (ret)
 		return ret;
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1787,12 +1787,12 @@ kvmppc_hdsi:
 	/* HPTE not found fault or protection fault? */
 	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
 	beq	1f			/* if not, send it to the guest */
+	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
+	beq	3f
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
 	b	4f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
-	beq	3f
 	clrrdi	r0, r4, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_DATA_SEGMENT
@@ -1879,12 +1879,12 @@ kvmppc_hisi:
 	bne	.Lradix_hisi		/* for radix, just save ASDR */
 	andis.	r0, r11, SRR1_ISI_NOPT@h
 	beq	1f
+	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
+	beq	3f
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
 	b	4f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
-	beq	3f
 	clrrdi	r0, r10, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_INST_SEGMENT

arch/x86/include/asm/desc.h

@@ -205,6 +205,8 @@ static inline void native_load_tr_desc(void)
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
 }
 
+DECLARE_PER_CPU(bool, __tss_limit_invalid);
+
 static inline void force_reload_TR(void)
 {
 	struct desc_struct *d = get_cpu_gdt_table(smp_processor_id());
@@ -220,18 +222,20 @@ static inline void force_reload_TR(void)
 	write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
 	load_TR_desc();
+	this_cpu_write(__tss_limit_invalid, false);
 }
 
-DECLARE_PER_CPU(bool, need_tr_refresh);
-
-static inline void refresh_TR(void)
+/*
+ * Call this if you need the TSS limit to be correct, which should be the case
+ * if and only if you have TIF_IO_BITMAP set or you're switching to a task
+ * with TIF_IO_BITMAP set.
+ */
+static inline void refresh_tss_limit(void)
 {
 	DEBUG_LOCKS_WARN_ON(preemptible());
 
-	if (unlikely(this_cpu_read(need_tr_refresh))) {
+	if (unlikely(this_cpu_read(__tss_limit_invalid)))
 		force_reload_TR();
-		this_cpu_write(need_tr_refresh, false);
-	}
 }
 
 /*
@@ -250,7 +254,7 @@ static inline void invalidate_tss_limit(void)
 	if (unlikely(test_thread_flag(TIF_IO_BITMAP)))
 		force_reload_TR();
 	else
-		this_cpu_write(need_tr_refresh, true);
+		this_cpu_write(__tss_limit_invalid, true);
 }
 
 static inline void native_load_gdt(const struct desc_ptr *dtr)

arch/x86/kernel/ioport.c

@@ -48,8 +48,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 		t->io_bitmap_ptr = bitmap;
 		set_thread_flag(TIF_IO_BITMAP);
 
+		/*
+		 * Now that we have an IO bitmap, we need our TSS limit to be
+		 * correct.  It's fine if we are preempted after doing this:
+		 * with TIF_IO_BITMAP set, context switches will keep our TSS
+		 * limit correct.
+		 */
 		preempt_disable();
-		refresh_TR();
+		refresh_tss_limit();
 		preempt_enable();
 	}
 

arch/x86/kernel/process.c

@@ -69,8 +69,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
-DEFINE_PER_CPU(bool, need_tr_refresh);
-EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh);
+DEFINE_PER_CPU(bool, __tss_limit_invalid);
+EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
 
 /*
  * this gets called so that we can store lazy state into memory and copy the
@@ -222,7 +222,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 * Make sure that the TSS limit is correct for the CPU
 		 * to notice the IO bitmap.
 		 */
-		refresh_TR();
+		refresh_tss_limit();
 	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
 		/*
 		 * Clear any possible leftover bits:

arch/x86/kvm/pmu.c

@@ -113,12 +113,19 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.config = config,
 	};
 
+	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
+
 	if (in_tx)
 		attr.config |= HSW_IN_TX;
-	if (in_tx_cp)
+	if (in_tx_cp) {
+		/*
+		 * HSW_IN_TX_CHECKPOINTED is not supported with nonzero
+		 * period. Just clear the sample period so at least
+		 * allocating the counter doesn't fail.
+		 */
+		attr.sample_period = 0;
 		attr.config |= HSW_IN_TX_CHECKPOINTED;
-
-	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
+	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 intr ? kvm_perf_overflow_intr :

arch/x86/kvm/vmx.c

@@ -2053,7 +2053,6 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 static unsigned long segment_base(u16 selector)
 {
 	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
-	struct desc_struct *d;
 	struct desc_struct *table;
 	unsigned long v;
 
@@ -10642,6 +10641,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (vcpu->arch.exception.pending ||
+		vcpu->arch.nmi_injected ||
+		vcpu->arch.interrupt.pending)
+		return -EBUSY;
+
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
 		if (vmx->nested.nested_run_pending)
@@ -10651,8 +10655,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 	}
 
 	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
-		if (vmx->nested.nested_run_pending ||
-		    vcpu->arch.interrupt.pending)
+		if (vmx->nested.nested_run_pending)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  NMI_VECTOR | INTR_TYPE_NMI_INTR |

include/linux/kvm_host.h

@@ -26,6 +26,7 @@
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
 #include <linux/swait.h>
+#include <linux/refcount.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -401,7 +402,7 @@ struct kvm {
 #endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
-	atomic_t users_count;
+	refcount_t users_count;
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
 	spinlock_t ring_lock;

tools/testing/selftests/x86/Makefile

@@ -5,7 +5,7 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test \
+			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
 			protection_keys test_vdso
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \

tools/testing/selftests/x86/ioperm.c

@@ -0,0 +1,170 @@
+/*
+ * ioperm.c - Test case for ioperm(2)
+ * Copyright (c) 2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdbool.h>
+#include <sched.h>
+#include <sys/io.h>
+
+static int nerrs = 0;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+static bool try_outb(unsigned short port)
+{
+	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		return false;
+	} else {
+		asm volatile ("outb %%al, %w[port]"
+			      : : [port] "Nd" (port), "a" (0));
+		return true;
+	}
+	clearhandler(SIGSEGV);
+}
+
+static void expect_ok(unsigned short port)
+{
+	if (!try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx failed\n", port);
+		exit(1);
+	}
+
+	printf("[OK]\toutb to 0x%02hx worked\n", port);
+}
+
+static void expect_gp(unsigned short port)
+{
+	if (try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx worked\n", port);
+		exit(1);
+	}
+
+	printf("[OK]\toutb to 0x%02hx failed\n", port);
+}
+
+int main(void)
+{
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		err(1, "sched_setaffinity to CPU 0");
+
+	expect_gp(0x80);
+	expect_gp(0xed);
+
+	/*
+	 * Probe for ioperm support.  Note that clearing ioperm bits
+	 * works even as nonroot.
+	 */
+	printf("[RUN]\tenable 0x80\n");
+	if (ioperm(0x80, 1, 1) != 0) {
+		printf("[OK]\tioperm(0x80, 1, 1) failed (%d) -- try running as root\n",
+		       errno);
+		return 0;
+	}
+	expect_ok(0x80);
+	expect_gp(0xed);
+
+	printf("[RUN]\tdisable 0x80\n");
+	if (ioperm(0x80, 1, 0) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+	expect_gp(0x80);
+	expect_gp(0xed);
+
+	/* Make sure that fork() preserves ioperm. */
+	if (ioperm(0x80, 1, 1) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+
+	pid_t child = fork();
+	if (child == -1)
+		err(1, "fork");
+
+	if (child == 0) {
+		printf("[RUN]\tchild: check that we inherited permissions\n");
+		expect_ok(0x80);
+		expect_gp(0xed);
+		return 0;
+	} else {
+		int status;
+		if (waitpid(child, &status, 0) != child ||
+		    !WIFEXITED(status)) {
+			printf("[FAIL]\tChild died\n");
+			nerrs++;
+		} else if (WEXITSTATUS(status) != 0) {
+			printf("[FAIL]\tChild failed\n");
+			nerrs++;
+		} else {
+			printf("[OK]\tChild succeeded\n");
+		}
+	}
+
+	/* Test the capability checks. */
+
+	printf("\tDrop privileges\n");
+	if (setresuid(1, 1, 1) != 0) {
+		printf("[WARN]\tDropping privileges failed\n");
+		return 0;
+	}
+
+	printf("[RUN]\tdisable 0x80\n");
+	if (ioperm(0x80, 1, 0) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+	printf("[OK]\tit worked\n");
+
+	printf("[RUN]\tenable 0x80 again\n");
+	if (ioperm(0x80, 1, 1) == 0) {
+		printf("[FAIL]\tit succeeded but should have failed.\n");
+		return 1;
+	}
+	printf("[OK]\tit failed\n");
+	return 0;
+}

virt/kvm/kvm_main.c

@@ -619,7 +619,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
-	atomic_set(&kvm->users_count, 1);
+	refcount_set(&kvm->users_count, 1);
 	INIT_LIST_HEAD(&kvm->devices);
 
 	r = kvm_arch_init_vm(kvm, type);
@@ -749,13 +749,13 @@ static void kvm_destroy_vm(struct kvm *kvm)
 
 void kvm_get_kvm(struct kvm *kvm)
 {
-	atomic_inc(&kvm->users_count);
+	refcount_inc(&kvm->users_count);
 }
 EXPORT_SYMBOL_GPL(kvm_get_kvm);
 
 void kvm_put_kvm(struct kvm *kvm)
 {
-	if (atomic_dec_and_test(&kvm->users_count))
+	if (refcount_dec_and_test(&kvm->users_count))
 		kvm_destroy_vm(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_put_kvm);
@@ -3641,7 +3641,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 	 * To avoid the race between open and the removal of the debugfs
 	 * directory we test against the users count.
 	 */
-	if (!atomic_add_unless(&stat_data->kvm->users_count, 1, 0))
+	if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
 		return -ENOENT;
 
 	if (simple_attr_open(inode, file, get, set, fmt)) {