KVM changes for 4.16

ARM: - Include icache invalidation optimizations, improving VM startup time - Support for forwarded level-triggered interrupts, improving performance for timers and passthrough platform devices - A small fix for power-management notifiers, and some cosmetic changes PPC: - Add MMIO emulation for vector loads and stores - Allow HPT guests to run on a radix host on POWER9 v2.2 CPUs without requiring the complex thread synchronization of older CPU versions - Improve the handling of escalation interrupts with the XIVE interrupt controller - Support decrement register migration - Various cleanups and bugfixes. s390: - Cornelia Huck passed maintainership to Janosch Frank - Exitless interrupts for emulated devices - Cleanup of cpuflag handling - kvm_stat counter improvements - VSIE improvements - mm cleanup x86: - Hypervisor part of SEV - UMIP, RDPID, and MSR_SMI_COUNT emulation - Paravirtualized TLB shootdown using the new KVM_VCPU_PREEMPTED bit - Allow guests to see TOPOEXT, GFNI, VAES, VPCLMULQDQ, and more AVX512 features - Show vcpu id in its anonymous inode name - Many fixes and cleanups - Per-VCPU MSR bitmaps (already merged through x86/pti branch) - Stable KVM clock when nesting on Hyper-V (merged through x86/hyperv) -----BEGIN PGP SIGNATURE----- iQEcBAABCAAGBQJafvMtAAoJEED/6hsPKofo6YcH/Rzf2RmshrWaC3q82yfIV0Qz Z8N8yJHSaSdc3Jo6cmiVj0zelwAxdQcyjwlT7vxt5SL2yML+/Q0st9Hc3EgGGXPm Il99eJEl+2MYpZgYZqV8ff3mHS5s5Jms+7BITAeh6Rgt+DyNbykEAvzt+MCHK9cP xtsIZQlvRF7HIrpOlaRzOPp3sK2/MDZJ1RBE7wYItK3CUAmsHim/LVYKzZkRTij3 /9b4LP1yMMbziG+Yxt1o682EwJB5YIat6fmDG9uFeEVI5rWWN7WFubqs8gCjYy/p FX+BjpOdgTRnX+1m9GIj0Jlc/HKMXryDfSZS07Zy4FbGEwSiI5SfKECub4mDhuE= =C/uD -----END PGP SIGNATURE----- Merge tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Radim Krčmář: "ARM: - icache invalidation optimizations, improving VM startup time - support for forwarded level-triggered interrupts, improving performance for timers and passthrough platform devices - a small fix for power-management notifiers, and some cosmetic changes PPC: - add MMIO emulation for vector loads and stores - allow HPT guests to run on a radix host on POWER9 v2.2 CPUs without requiring the complex thread synchronization of older CPU versions - improve the handling of escalation interrupts with the XIVE interrupt controller - support decrement register migration - various cleanups and bugfixes. s390: - Cornelia Huck passed maintainership to Janosch Frank - exitless interrupts for emulated devices - cleanup of cpuflag handling - kvm_stat counter improvements - VSIE improvements - mm cleanup x86: - hypervisor part of SEV - UMIP, RDPID, and MSR_SMI_COUNT emulation - paravirtualized TLB shootdown using the new KVM_VCPU_PREEMPTED bit - allow guests to see TOPOEXT, GFNI, VAES, VPCLMULQDQ, and more AVX512 features - show vcpu id in its anonymous inode name - many fixes and cleanups - per-VCPU MSR bitmaps (already merged through x86/pti branch) - stable KVM clock when nesting on Hyper-V (merged through x86/hyperv)" * tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (197 commits) KVM: PPC: Book3S: Add MMIO emulation for VMX instructions KVM: PPC: Book3S HV: Branch inside feature section KVM: PPC: Book3S HV: Make HPT resizing work on POWER9 KVM: PPC: Book3S HV: Fix handling of secondary HPTEG in HPT resizing code KVM: PPC: Book3S PR: Fix broken select due to misspelling KVM: x86: don't forget vcpu_put() in kvm_arch_vcpu_ioctl_set_sregs() KVM: PPC: Book3S PR: Fix svcpu copying with preemption enabled KVM: PPC: Book3S HV: Drop locks before reading guest memory kvm: x86: remove efer_reload entry in kvm_vcpu_stat KVM: x86: AMD Processor Topology Information x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO when running nested kvm: embed vcpu id to dentry of vcpu anon inode kvm: Map PFN-type memory regions as writable (if possible) x86/kvm: Make it compile on 32bit and with HYPYERVISOR_GUEST=n KVM: arm/arm64: Fixup userspace irqchip static key optimization KVM: arm/arm64: Fix userspace_irqchip_in_use counting KVM: arm/arm64: Fix incorrect timer_is_pending logic MAINTAINERS: update KVM/s390 maintainers MAINTAINERS: add Halil as additional vfio-ccw maintainer MAINTAINERS: add David as a reviewer for KVM/s390 ...
2026-10-30 11:41:38 -04:00 · 2018-02-10 13:16:35 -08:00 · 2018-02-10 13:16:35 -08:00 · 15303ba5d1
commit 15303ba5d1
parent 9a61df9e5f 1ab03c072f
123 changed files with 6577 additions and 1416 deletions
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@ -435,6 +435,27 @@ alternative_endif
 	dsb	\domain
 	.endm

+/*
+ * Macro to perform an instruction cache maintenance for the interval
+ * [start, end)
+ *
+ * 	start, end:	virtual addresses describing the region
+ *	label:		A label to branch to on user fault.
+ * 	Corrupts:	tmp1, tmp2
+ */
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+	icache_line_size \tmp1, \tmp2
+	sub	\tmp2, \tmp1, #1
+	bic	\tmp2, \start, \tmp2
+9997:
+USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
+	add	\tmp2, \tmp2, \tmp1
+	cmp	\tmp2, \end
+	b.lo	9997b
+	dsb	ish
+	isb
+	.endm
+
 /*
 * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
 */
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@ -52,6 +52,12 @@
 *		- start  - virtual start address
 *		- end    - virtual end address
 *
+ *	invalidate_icache_range(start, end)
+ *
+ *		Invalidate the I-cache in the region described by start, end.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
 *	__flush_cache_user_range(start, end)
 *
 *		Ensure coherency between the I-cache and the D-cache in the
@ -66,6 +72,7 @@
 *		- size   - region size
 */
 extern void flush_icache_range(unsigned long start, unsigned long end);
+extern int  invalidate_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
 extern void __clean_dcache_area_poc(void *addr, size_t len);
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@ -48,6 +48,8 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)

+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@ -20,7 +20,6 @@

 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
-#include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>

 #define __hyp_text __section(.hyp.text) notrace
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@ -173,6 +173,18 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
 	return pmd;
 }

+static inline pte_t kvm_s2pte_mkexec(pte_t pte)
+{
+	pte_val(pte) &= ~PTE_S2_XN;
+	return pte;
+}
+
+static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_S2_XN;
+	return pmd;
+}
+
 static inline void kvm_set_s2pte_readonly(pte_t *pte)
 {
 	pteval_t old_pteval, pteval;
@ -191,6 +203,11 @@ static inline bool kvm_s2pte_readonly(pte_t *pte)
 	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
 }

+static inline bool kvm_s2pte_exec(pte_t *pte)
+{
+	return !(pte_val(*pte) & PTE_S2_XN);
+}
+
 static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
 {
 	kvm_set_s2pte_readonly((pte_t *)pmd);
@ -201,6 +218,11 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	return kvm_s2pte_readonly((pte_t *)pmd);
 }

+static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+{
+	return !(pmd_val(*pmd) & PMD_S2_XN);
+}
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
@ -230,21 +252,25 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }

-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
-					       kvm_pfn_t pfn,
-					       unsigned long size)
+static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
 {
 	void *va = page_address(pfn_to_page(pfn));

 	kvm_flush_dcache_to_poc(va, size);
+}

+static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
+						  unsigned long size)
+{
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
-		flush_icache_range((unsigned long)va,
-				   (unsigned long)va + size);
+		void *va = page_address(pfn_to_page(pfn));
+
+		invalidate_icache_range((unsigned long)va,
+					(unsigned long)va + size);
 	}
 }

--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@ -187,9 +187,11 @@
 */
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
+#define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */

 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
+#define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */

 /*
 * Memory Attribute override for Stage-2 (MemAttr[3:0])
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@ -67,8 +67,8 @@
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)

-#define PAGE_S2			__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
+#define PAGE_S2			__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)

 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@ -361,10 +361,16 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
+	int ret = 0;
+
+	vcpu_load(vcpu);
+
 	trace_kvm_set_guest_debug(vcpu, dbg->control);

-	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK)
-		return -EINVAL;
+	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
+		ret = -EINVAL;
+		goto out;
+	}

 	if (dbg->control & KVM_GUESTDBG_ENABLE) {
 		vcpu->guest_debug = dbg->control;
@ -378,7 +384,10 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 		/* If not enabled clear all flags */
 		vcpu->guest_debug = 0;
 	}
-	return 0;
+
+out:
+	vcpu_put(vcpu);
+	return ret;
 }

 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@ -21,6 +21,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>

 #define read_debug(r,n)		read_sysreg(r##n##_el1)
 #define write_debug(v,r,n)	write_sysreg(v, r##n##_el1)
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@ -24,6 +24,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>

--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@ -16,6 +16,7 @@
 */

 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 #include <asm/tlbflush.h>

 static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@ -60,16 +60,7 @@ user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	b.lo	1b
 	dsb	ish

-	icache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x4, x0, x3
-1:
-USER(9f, ic	ivau, x4	)		// invalidate I line PoU
-	add	x4, x4, x2
-	cmp	x4, x1
-	b.lo	1b
-	dsb	ish
-	isb
+	invalidate_icache_by_line x0, x1, x2, x3, 9f
 	mov	x0, #0
 1:
 	uaccess_ttbr0_disable x1, x2
@ -80,6 +71,27 @@ USER(9f, ic	ivau, x4	)		// invalidate I line PoU
 ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)

+/*
+ *	invalidate_icache_range(start,end)
+ *
+ *	Ensure that the I cache is invalid within specified region.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(invalidate_icache_range)
+	uaccess_ttbr0_enable x2, x3, x4
+
+	invalidate_icache_by_line x0, x1, x2, x3, 2f
+	mov	x0, xzr
+1:
+	uaccess_ttbr0_disable x1, x2
+	ret
+2:
+	mov	x0, #-EFAULT
+	b	1b
+ENDPROC(invalidate_icache_range)
+
 /*
 *	__flush_dcache_area(kaddr, size)
 *