!245 KVM: arm64: Add support for FEAT_TLBIRANGE

Merge pull request !245 from 谢晓东/linux-5.4/devel

arch/arm64/include/asm/kvm_asm.h

@@ -58,6 +58,8 @@ extern char __kvm_hyp_init_end[];
 extern char __kvm_hyp_vector[];
 
 extern void __kvm_flush_vm_context(void);
+extern void __kvm_tlb_flush_vmid_range(struct kvm *kvm,
+					phys_addr_t start, unsigned long pages);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern void __kvm_flush_cpu_context(struct kvm_vcpu *vcpu);

arch/arm64/include/asm/kvm_host.h

@@ -671,6 +671,8 @@ void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
 void kvm_set_ipa_limit(void);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 

arch/arm64/include/asm/tlbflush.h

@@ -282,16 +282,77 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
  */
 #define MAX_TLBI_OPS	PTRS_PER_PTE
 
+/*
+ * __flush_tlb_range_op - Perform TLBI operation upon a range
+ *
+ * @op:	TLBI instruction that operates on a range (has 'r' prefix)
+ * @start:	The start address of the range
+ * @pages:	Range as the number of pages from 'start'
+ * @stride:	Flush granularity
+ * @asid:	The ASID of the task (0 for IPA instructions)
+ * @tlb_level:	Translation Table level hint, if known
+ * @tlbi_user:	If 'true', call an additional __tlbi_user()
+ *              (typically for user ASIDs). 'flase' for IPA instructions
+ *
+ * When the CPU does not support TLB range operations, flush the TLB
+ * entries one by one at the granularity of 'stride'. If the TLB
+ * range ops are supported, then:
+ *
+ * 1. If 'pages' is odd, flush the first page through non-range
+ *    operations;
+ *
+ * 2. For remaining pages: the minimum range granularity is decided
+ *    by 'scale', so multiple range TLBI operations may be required.
+ *    Start from scale = 0, flush the corresponding number of pages
+ *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+ *    until no pages left.
+ *
+ * Note that certain ranges can be represented by either num = 31 and
+ * scale or num = 0 and scale + 1. The loop below favours the latter
+ * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+ */
+#define __flush_tlb_range_op(op, start, pages, stride,			\
+				asid, tlb_level, tlbi_user)		\
+do {									\
+	int num = 0;							\
+	int scale = 0;							\
+	unsigned long addr;						\
+									\
+	while (pages > 0) {						\
+		if (!system_supports_tlb_range() ||			\
+		    pages % 2 == 1) {					\
+			addr = __TLBI_VADDR(start, asid);		\
+			__tlbi_level(op, addr, tlb_level);		\
+			if (tlbi_user)					\
+				__tlbi_user_level(op, addr, tlb_level);	\
+			start += stride;				\
+			pages -= stride >> PAGE_SHIFT;			\
+			continue;					\
+		}							\
+									\
+		num = __TLBI_RANGE_NUM(pages, scale);			\
+		if (num >= 0) {						\
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,	\
+						  num, tlb_level);	\
+			__tlbi(r##op, addr);				\
+			if (tlbi_user)					\
+				__tlbi_user(r##op, addr);		\
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
+			pages -= __TLBI_RANGE_PAGES(num, scale);	\
+		}							\
+		scale++;						\
+	}								\
+} while (0)
+
+#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
+	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)
+
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
 {
-	int num = 0;
+	unsigned long asid, pages;
-	int scale = 0;
-	unsigned long asid = ASID(vma->vm_mm);
-	unsigned long addr;
-	unsigned long pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
@@ -311,57 +372,13 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	}
 
 	dsb(ishst);
+	asid = ASID(vma->vm_mm);
+	
+	if (last_level)
+		__flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
+	else
+		__flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);
 
-	/*
-	 * When the CPU does not support TLB range operations, flush the TLB
-	 * entries one by one at the granularity of 'stride'. If the the TLB
-	 * range ops are supported, then:
-	 *
-	 * 1. If 'pages' is odd, flush the first page through non-range
-	 *    operations;
-	 *
-	 * 2. For remaining pages: the minimum range granularity is decided
-	 *    by 'scale', so multiple range TLBI operations may be required.
-	 *    Start from scale = 0, flush the corresponding number of pages
-	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
-	 *    until no pages left.
-	 *
-	 * Note that certain ranges can be represented by either num = 31 and
-	 * scale or num = 0 and scale + 1. The loop below favours the latter
-	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
-	 */
-	while (pages > 0) {
-		if (!system_supports_tlb_range() ||
-		    pages % 2 == 1) {
-			addr = __TLBI_VADDR(start, asid);
-			if (last_level) {
-				__tlbi_level(vale1is, addr, tlb_level);
-				__tlbi_user_level(vale1is, addr, tlb_level);
-			} else {
-				__tlbi_level(vae1is, addr, tlb_level);
-				__tlbi_user_level(vae1is, addr, tlb_level);
-			}
-			start += stride;
-			pages -= stride >> PAGE_SHIFT;
-			continue;
-		}
-
-		num = __TLBI_RANGE_NUM(pages, scale);
-		if (num >= 0) {
-			addr = __TLBI_VADDR_RANGE(start, asid, scale,
-						  num, tlb_level);
-			if (last_level) {
-				__tlbi(rvale1is, addr);
-				__tlbi_user(rvale1is, addr);
-			} else {
-				__tlbi(rvae1is, addr);
-				__tlbi_user(rvae1is, addr);
-			}
-			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
-			pages -= __TLBI_RANGE_PAGES(num, scale);
-		}
-		scale++;
-	}
 	dsb(ish);
 }
 

arch/arm64/kvm/Kconfig

@@ -24,7 +24,6 @@ config KVM
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
-	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT

arch/arm64/kvm/hyp/tlb.c

@@ -165,6 +165,41 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
+void __hyp_text __kvm_tlb_flush_vmid_range(struct kvm *kvm,
+				phys_addr_t start, unsigned long pages)
+{
+	struct tlb_inv_context cxt;
+	unsigned long stride;
+
+	/*
+	 * Since the range of addresses may not be mapped at
+	 * the same level, assume the worst case as PAGE_SIZE
+	 */
+	stride = PAGE_SIZE;
+	start = round_down(start, stride);
+
+
+	if (has_vhe())
+		dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	/* See the comment in __kvm_tlb_flush_vmid_ipa() */
+	if (!has_vhe() && icache_is_vpipt())
+		__flush_icache_all();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 {
 	struct tlb_inv_context cxt;

include/linux/kvm_host.h

@@ -813,6 +813,9 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
@@ -917,11 +920,23 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	return -ENOTSUPP;
 }
+#else
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
+#endif
+
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+						    gfn_t gfn, u64 nr_pages)
+{
+	return -EOPNOTSUPP;
+}
+#else
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
 #endif
 
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA

virt/kvm/Kconfig

@@ -36,9 +36,6 @@ config HAVE_KVM_CPU_RELAX_INTERCEPT
 config KVM_VFIO
        bool
 
-config HAVE_KVM_ARCH_TLB_FLUSH_ALL
-       bool
-
 config HAVE_KVM_INVALID_WAKEUPS
        bool
 

virt/kvm/arm/mmu.c

@@ -49,14 +49,15 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 }
 
 /**
- * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8
+ * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8
  * @kvm:	pointer to kvm structure.
  *
  * Interface to HYP function to flush all VM TLB entries
  */
-void kvm_flush_remote_tlbs(struct kvm *kvm)
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+	return 0;
 }
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -64,6 +65,48 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
+/**
+ * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries
+ *
+ * @kvm:	pointer to kvm structure
+ * @addr:	The base Intermediate physical address from which to invalidate
+ * @size:	Size of the range from the base to invalidate
+ */
+
+void kvm_tlb_flush_vmid_range(struct kvm *kvm, 
+			phys_addr_t addr, size_t size)
+{
+	unsigned long pages, inval_pages;
+
+	if (!system_supports_tlb_range()) {
+		kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+		return;
+	}
+
+	pages = size >> PAGE_SHIFT;
+	while (pages > 0) {
+		inval_pages = min(pages, MAX_TLBI_RANGE_PAGES);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_range,
+			       	kvm, addr, inval_pages);
+
+		addr += inval_pages << PAGE_SHIFT;
+		pages -= inval_pages;
+	}
+}
+
+static bool stage2_unmap_defer_tlb_flush(void)
+{
+	/*
+	 * If FEAT_TLBIRANGE is implemented, defer the individual
+	 * TLB invalidations until the entire walk is finished, and
+	 * then use the range-based TLBI instructions to do the
+	 * invalidations. Condition deferred TLB invalidation on the
+	 * system supporting FWB as the optimization is entirely
+	 * pointless when the unmap walker needs to perform CMOs.
+	 */
+	return system_supports_tlb_range() && cpus_have_const_cap(ARM64_HAS_STAGE2_FWB);
+}
+
 /*
  * D-Cache management functions. They take the page table entries by
  * value, as they are flushing the cache using the kernel mapping (or
@@ -84,6 +127,15 @@ static void kvm_flush_dcache_pud(pud_t pud)
 	__kvm_flush_dcache_pud(pud);
 }
 
+
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+	       				gfn_t gfn, u64 nr_pages)
+{
+	kvm_tlb_flush_vmid_range(kvm,gfn << PAGE_SHIFT,
+		       			nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
 static bool kvm_is_device_pfn(unsigned long pfn)
 {
 	return !pfn_valid(pfn);
@@ -249,9 +301,10 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 	do {
 		if (!pte_none(*pte)) {
 			pte_t old_pte = *pte;
-
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(kvm, addr);
+			
+			if (!stage2_unmap_defer_tlb_flush())
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -354,6 +407,11 @@ static void __unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size,
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
 			unmap_stage2_puds(kvm, pgd, addr, next);
+		
+		if (stage2_unmap_defer_tlb_flush())
+			/* Perform the deferred TLB invalidations */
+			kvm_tlb_flush_vmid_range(kvm, addr, size);
+
 		/*
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
@@ -1553,7 +1611,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	spin_lock(&kvm->mmu_lock);
 	stage2_wp_range(kvm, start, end);
 	spin_unlock(&kvm->mmu_lock);
-	kvm_flush_remote_tlbs(kvm);
+	kvm_flush_remote_tlbs_memslot(kvm, memslot);
 }
 
 /**

virt/kvm/kvm_main.c

@@ -295,7 +295,33 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	return called;
 }
 
-#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
+{
+	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
+		return;
+
+	/*
+	 * Fall back to a flushing entire TLBs if the architecture range-based
+	 * TLB invalidation is unsupported or can't be performed for whatever
+	 * reason.
+	 */
+	kvm_flush_remote_tlbs(kvm);
+}
+
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot)
+{
+	/*
+	 * All current use cases for flushing the TLBs for a specific memslot
+	 * are related to dirty logging, and many do the TLB flush out of
+	 * mmu_lock. The interaction between the various operations on memslot
+	 * must be serialized by slots_locks to ensure the TLB flush from one
+	 * operation is observed by any other operation on the same memslot.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
+}
+
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
 	/*
@@ -315,13 +341,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	 * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
 	 * barrier here.
 	 */
-	if (!kvm_arch_flush_remote_tlb(kvm)
+	if (!kvm_arch_flush_remote_tlbs(kvm)
 	    || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
 	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
-#endif
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
@@ -1317,7 +1342,8 @@ int kvm_get_dirty_log_protect(struct kvm *kvm,
 		}
 		spin_unlock(&kvm->mmu_lock);
 	}
-
+	if (flush)
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		return -EFAULT;
 	return 0;
@@ -1393,6 +1419,9 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 		}
 	}
 	spin_unlock(&kvm->mmu_lock);
+	
+	if(flush)
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	return 0;
 }