Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "RISC-V:
   - Fix missing PAGE_PFN_MASK

   - Fix SRCU deadlock caused by kvm_riscv_check_vcpu_requests()

  x86:
   - Fix for nested virtualization when TSC scaling is active

   - Estimate the size of fastcc subroutines conservatively, avoiding
     disastrous underestimation when return thunks are enabled

   - Avoid possible use of uninitialized fields of 'struct
     kvm_lapic_irq'

  Generic:
   - Mark as such the boolean values available from the statistics file
     descriptors

   - Clarify statistics documentation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: emulate: do not adjust size of fastop and setcc subroutines
  KVM: x86: Fully initialize 'struct kvm_lapic_irq' in kvm_pv_kick_cpu_op()
  Documentation: kvm: clarify histogram units
  kvm: stats: tell userspace which values are boolean
  x86/kvm: fix FASTOP_SIZE when return thunks are enabled
  KVM: nVMX: Always enable TSC scaling for L2 when it was enabled for L1
  RISC-V: KVM: Fix SRCU deadlock caused by kvm_riscv_check_vcpu_requests()
  riscv: Fix missing PAGE_PFN_MASK

Author: torvalds

Documentation/virt/kvm/api.rst

@@ -5657,6 +5657,7 @@ by a string of size ``name_size``.
 	#define KVM_STATS_UNIT_BYTES		(0x1 << KVM_STATS_UNIT_SHIFT)
 	#define KVM_STATS_UNIT_SECONDS		(0x2 << KVM_STATS_UNIT_SHIFT)
 	#define KVM_STATS_UNIT_CYCLES		(0x3 << KVM_STATS_UNIT_SHIFT)
+	#define KVM_STATS_UNIT_BOOLEAN		(0x4 << KVM_STATS_UNIT_SHIFT)
 	#define KVM_STATS_UNIT_MAX		KVM_STATS_UNIT_CYCLES
 
 	#define KVM_STATS_BASE_SHIFT		8
@@ -5702,14 +5703,13 @@ Bits 0-3 of ``flags`` encode the type:
     by the ``hist_param`` field. The range of the Nth bucket (1 <= N < ``size``)
     is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last
     bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity
-    value.) The bucket value indicates how many samples fell in the bucket's range.
+    value.)
   * ``KVM_STATS_TYPE_LOG_HIST``
     The statistic is reported as a logarithmic histogram. The number of
     buckets is specified by the ``size`` field. The range of the first bucket is
     [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF).
     Otherwise, The Nth bucket (1 < N < ``size``) covers
-    [pow(2, N-2), pow(2, N-1)). The bucket value indicates how many samples fell
-    in the bucket's range.
+    [pow(2, N-2), pow(2, N-1)).
 
 Bits 4-7 of ``flags`` encode the unit:
 
@@ -5724,6 +5724,15 @@ Bits 4-7 of ``flags`` encode the unit:
     It indicates that the statistics data is used to measure time or latency.
   * ``KVM_STATS_UNIT_CYCLES``
     It indicates that the statistics data is used to measure CPU clock cycles.
+  * ``KVM_STATS_UNIT_BOOLEAN``
+    It indicates that the statistic will always be either 0 or 1.  Boolean
+    statistics of "peak" type will never go back from 1 to 0.  Boolean
+    statistics can be linear histograms (with two buckets) but not logarithmic
+    histograms.
+
+Note that, in the case of histograms, the unit applies to the bucket
+ranges, while the bucket value indicates how many samples fell in the
+bucket's range.
 
 Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the
 unit:
@@ -5746,7 +5755,7 @@ the corresponding statistics data.
 
 The ``bucket_size`` field is used as a parameter for histogram statistics data.
 It is only used by linear histogram statistics data, specifying the size of a
-bucket.
+bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``.
 
 The ``name`` field is the name string of the statistics data. The name string
 starts at the end of ``struct kvm_stats_desc``.  The maximum length including

arch/riscv/include/asm/pgtable-64.h

@@ -175,7 +175,7 @@ static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot)
 
 static inline unsigned long _pud_pfn(pud_t pud)
 {
-	return pud_val(pud) >> _PAGE_PFN_SHIFT;
+	return __page_val_to_pfn(pud_val(pud));
 }
 
 static inline pmd_t *pud_pgtable(pud_t pud)
@@ -278,21 +278,21 @@ static inline p4d_t pfn_p4d(unsigned long pfn, pgprot_t prot)
 
 static inline unsigned long _p4d_pfn(p4d_t p4d)
 {
-	return p4d_val(p4d) >> _PAGE_PFN_SHIFT;
+	return __page_val_to_pfn(p4d_val(p4d));
 }
 
 static inline pud_t *p4d_pgtable(p4d_t p4d)
 {
 	if (pgtable_l4_enabled)
-		return (pud_t *)pfn_to_virt(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+		return (pud_t *)pfn_to_virt(__page_val_to_pfn(p4d_val(p4d)));
 
 	return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) });
 }
 #define p4d_page_vaddr(p4d)	((unsigned long)p4d_pgtable(p4d))
 
 static inline struct page *p4d_page(p4d_t p4d)
 {
-	return pfn_to_page(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+	return pfn_to_page(__page_val_to_pfn(p4d_val(p4d)));
 }
 
 #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
@@ -347,15 +347,15 @@ static inline void pgd_clear(pgd_t *pgd)
 static inline p4d_t *pgd_pgtable(pgd_t pgd)
 {
 	if (pgtable_l5_enabled)
-		return (p4d_t *)pfn_to_virt(pgd_val(pgd) >> _PAGE_PFN_SHIFT);
+		return (p4d_t *)pfn_to_virt(__page_val_to_pfn(pgd_val(pgd)));
 
 	return (p4d_t *)p4d_pgtable((p4d_t) { pgd_val(pgd) });
 }
 #define pgd_page_vaddr(pgd)	((unsigned long)pgd_pgtable(pgd))
 
 static inline struct page *pgd_page(pgd_t pgd)
 {
-	return pfn_to_page(pgd_val(pgd) >> _PAGE_PFN_SHIFT);
+	return pfn_to_page(__page_val_to_pfn(pgd_val(pgd)));
 }
 #define pgd_page(pgd)	pgd_page(pgd)
 

arch/riscv/include/asm/pgtable.h

@@ -261,7 +261,7 @@ static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
 
 static inline unsigned long _pgd_pfn(pgd_t pgd)
 {
-	return pgd_val(pgd) >> _PAGE_PFN_SHIFT;
+	return __page_val_to_pfn(pgd_val(pgd));
 }
 
 static inline struct page *pmd_page(pmd_t pmd)
@@ -590,14 +590,14 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd)
 	return __pmd(pmd_val(pmd) & ~(_PAGE_PRESENT|_PAGE_PROT_NONE));
 }
 
-#define __pmd_to_phys(pmd)  (pmd_val(pmd) >> _PAGE_PFN_SHIFT << PAGE_SHIFT)
+#define __pmd_to_phys(pmd)  (__page_val_to_pfn(pmd_val(pmd)) << PAGE_SHIFT)
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT);
 }
 
-#define __pud_to_phys(pud)  (pud_val(pud) >> _PAGE_PFN_SHIFT << PAGE_SHIFT)
+#define __pud_to_phys(pud)  (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT)
 
 static inline unsigned long pud_pfn(pud_t pud)
 {

arch/riscv/kvm/mmu.c

@@ -54,7 +54,7 @@ static inline unsigned long gstage_pte_index(gpa_t addr, u32 level)
 
 static inline unsigned long gstage_pte_page_vaddr(pte_t pte)
 {
-	return (unsigned long)pfn_to_virt(pte_val(pte) >> _PAGE_PFN_SHIFT);
+	return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte)));
 }
 
 static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level)

arch/riscv/kvm/vcpu.c

@@ -781,9 +781,11 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
+			kvm_vcpu_srcu_read_unlock(vcpu);
 			rcuwait_wait_event(wait,
 				(!vcpu->arch.power_off) && (!vcpu->arch.pause),
 				TASK_INTERRUPTIBLE);
+			kvm_vcpu_srcu_read_lock(vcpu);
 
 			if (vcpu->arch.power_off || vcpu->arch.pause) {
 				/*

arch/x86/kvm/emulate.c

@@ -189,9 +189,6 @@
 #define X8(x...) X4(x), X4(x)
 #define X16(x...) X8(x), X8(x)
 
-#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
-#define FASTOP_SIZE (8 * (1 + HAS_KERNEL_IBT))
-
 struct opcode {
 	u64 flags;
 	u8 intercept;
@@ -306,9 +303,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
  * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
  * different operand sizes can be reached by calculation, rather than a jump
  * table (which would be bigger than the code).
+ *
+ * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR
+ * and 1 for the straight line speculation INT3, leaves 7 bytes for the
+ * body of the function.  Currently none is larger than 4.
  */
 static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
+#define FASTOP_SIZE	16
+
 #define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
@@ -442,11 +445,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
  * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
  * INT3				[1 byte; CONFIG_SLS]
  */
-#define RET_LENGTH	(1 + (4 * IS_ENABLED(CONFIG_RETHUNK)) + \
-			 IS_ENABLED(CONFIG_SLS))
-#define SETCC_LENGTH	(ENDBR_INSN_SIZE + 3 + RET_LENGTH)
-#define SETCC_ALIGN	(4 << ((SETCC_LENGTH > 4) & 1) << ((SETCC_LENGTH > 8) & 1))
-static_assert(SETCC_LENGTH <= SETCC_ALIGN);
+#define SETCC_ALIGN	16
 
 #define FOP_SETCC(op) \
 	".align " __stringify(SETCC_ALIGN) " \n\t" \

arch/x86/kvm/vmx/nested.c

@@ -2278,7 +2278,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_ENABLE_VMFUNC |
-				  SECONDARY_EXEC_TSC_SCALING |
 				  SECONDARY_EXEC_DESC);
 
 		if (nested_cpu_has(vmcs12,

arch/x86/kvm/x86.c

@@ -298,7 +298,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
 	STATS_DESC_COUNTER(VCPU, preemption_reported),
 	STATS_DESC_COUNTER(VCPU, preemption_other),
-	STATS_DESC_ICOUNTER(VCPU, guest_mode)
+	STATS_DESC_IBOOLEAN(VCPU, guest_mode)
 };
 
 const struct kvm_stats_header kvm_vcpu_stats_header = {
@@ -9143,15 +9143,17 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
  */
 static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
 {
-	struct kvm_lapic_irq lapic_irq;
-
-	lapic_irq.shorthand = APIC_DEST_NOSHORT;
-	lapic_irq.dest_mode = APIC_DEST_PHYSICAL;
-	lapic_irq.level = 0;
-	lapic_irq.dest_id = apicid;
-	lapic_irq.msi_redir_hint = false;
+	/*
+	 * All other fields are unused for APIC_DM_REMRD, but may be consumed by
+	 * common code, e.g. for tracing. Defer initialization to the compiler.
+	 */
+	struct kvm_lapic_irq lapic_irq = {
+		.delivery_mode = APIC_DM_REMRD,
+		.dest_mode = APIC_DEST_PHYSICAL,
+		.shorthand = APIC_DEST_NOSHORT,
+		.dest_id = apicid,
+	};
 
-	lapic_irq.delivery_mode = APIC_DM_REMRD;
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 

include/linux/kvm_host.h

@@ -1822,6 +1822,15 @@ struct _kvm_stats_desc {
 	STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
 		KVM_STATS_BASE_POW10, 0)
 
+/* Instantaneous boolean value, read only */
+#define STATS_DESC_IBOOLEAN(SCOPE, name)				       \
+	STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN,		       \
+		KVM_STATS_BASE_POW10, 0)
+/* Peak (sticky) boolean value, read/write */
+#define STATS_DESC_PBOOLEAN(SCOPE, name)				       \
+	STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN,		       \
+		KVM_STATS_BASE_POW10, 0)
+
 /* Cumulative time in nanosecond */
 #define STATS_DESC_TIME_NSEC(SCOPE, name)				       \
 	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS,	       \
@@ -1853,7 +1862,7 @@ struct _kvm_stats_desc {
 			HALT_POLL_HIST_COUNT),				       \
 	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist,	       \
 			HALT_POLL_HIST_COUNT),				       \
-	STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking)
+	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
 extern struct dentry *kvm_debugfs_dir;
 

include/uapi/linux/kvm.h

@@ -2083,6 +2083,7 @@ struct kvm_stats_header {
 #define KVM_STATS_UNIT_BYTES		(0x1 << KVM_STATS_UNIT_SHIFT)
 #define KVM_STATS_UNIT_SECONDS		(0x2 << KVM_STATS_UNIT_SHIFT)
 #define KVM_STATS_UNIT_CYCLES		(0x3 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BOOLEAN		(0x4 << KVM_STATS_UNIT_SHIFT)
 #define KVM_STATS_UNIT_MAX		KVM_STATS_UNIT_CYCLES
 
 #define KVM_STATS_BASE_SHIFT		8