Merge branch kvm-arm64/tlbi-range into kvmarm-master/next

* kvm-arm64/tlbi-range:
  : .
  : FEAT_TLBIRANGE support, courtesy of Raghavendra Rao Ananta.
  : From the cover letter:
  :
  : "In certain code paths, KVM/ARM currently invalidates the entire VM's
  : page-tables instead of just invalidating a necessary range. For example,
  : when collapsing a table PTE to a block PTE, instead of iterating over
  : each PTE and flushing them, KVM uses 'vmalls12e1is' TLBI operation to
  : flush all the entries. This is inefficient since the guest would have
  : to refill the TLBs again, even for the addresses that aren't covered
  : by the table entry. The performance impact would scale poorly if many
  : addresses in the VM is going through this remapping.
  :
  : For architectures that implement FEAT_TLBIRANGE, KVM can replace such
  : inefficient paths by performing the invalidations only on the range of
  : addresses that are in scope. This series tries to achieve the same in
  : the areas of stage-2 map, unmap and write-protecting the pages."
  : .
  KVM: arm64: Use TLBI range-based instructions for unmap
  KVM: arm64: Invalidate the table entries upon a range
  KVM: arm64: Flush only the memslot after write-protect
  KVM: arm64: Implement kvm_arch_flush_remote_tlbs_range()
  KVM: arm64: Define kvm_tlb_flush_vmid_range()
  KVM: arm64: Implement __kvm_tlb_flush_vmid_range()
  arm64: tlb: Implement __flush_s2_tlb_range_op()
  arm64: tlb: Refactor the core flush algorithm of __flush_tlb_range
  KVM: Move kvm_arch_flush_remote_tlbs_memslot() to common code
  KVM: Allow range-based TLB invalidation from common code
  KVM: Remove CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
  KVM: arm64: Use kvm_arch_flush_remote_tlbs()
  KVM: Declare kvm_arch_flush_remote_tlbs() globally
  KVM: Rename kvm_arch_flush_remote_tlb() to kvm_arch_flush_remote_tlbs()

Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Marc Zyngier

arch/arm64/include/asm/kvm_asm.h

@@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
@@ -229,6 +230,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 					 phys_addr_t ipa,
 					 int level);
+extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+					phys_addr_t start, unsigned long pages);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);

arch/arm64/include/asm/kvm_host.h

@@ -1120,6 +1120,10 @@ int __init kvm_set_ipa_limit(void);
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 static inline bool kvm_vm_is_protected(struct kvm *kvm)
 {
 	return false;

arch/arm64/include/asm/kvm_pgtable.h

@@ -746,4 +746,14 @@ enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
  *	   kvm_pgtable_prot format.
  */
 enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
+
+/**
+ * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries
+ *
+ * @mmu:	Stage-2 KVM MMU struct
+ * @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_s2_mmu *mmu,
+				phys_addr_t addr, size_t size);
 #endif	/* __ARM64_KVM_PGTABLE_H__ */

arch/arm64/include/asm/tlbflush.h

@@ -278,14 +278,77 @@ 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;
-	int scale = 0;
-	unsigned long asid, addr, pages;
+	unsigned long asid, pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
@@ -307,56 +370,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ishst);
 	asid = ASID(vma->vm_mm);
 
-	/*
-	 * 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.
-	 */
-	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++;
-	}
+	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);
+
 	dsb(ish);
 }
 

arch/arm64/kvm/Kconfig

@@ -25,7 +25,6 @@ menuconfig 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_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK

arch/arm64/kvm/arm.c

@@ -1534,12 +1534,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 					struct kvm_arm_device_addr *dev_addr)
 {

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -135,6 +135,16 @@ static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctx
 	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
 }
 
+static void
+handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
+	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
+	DECLARE_REG(unsigned long, pages, host_ctxt, 3);
+
+	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
+}
+
 static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -327,6 +337,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),

arch/arm64/kvm/hyp/nvhe/tlb.c

@@ -182,6 +182,36 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	__tlb_switch_to_host(&cxt);
 }
 
+void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				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);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt, false);
+
+	__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 (icache_is_vpipt())
+		icache_inval_all_pou();
+
+	__tlb_switch_to_host(&cxt);
+}
+
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;

arch/arm64/kvm/hyp/pgtable.c

@@ -670,6 +670,26 @@ static bool stage2_has_fwb(struct kvm_pgtable *pgt)
 	return !(pgt->flags & KVM_PGTABLE_S2_NOFWB);
 }
 
+void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t addr, size_t size)
+{
+	unsigned long pages, inval_pages;
+
+	if (!system_supports_tlb_range()) {
+		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+		return;
+	}
+
+	pages = size >> PAGE_SHIFT;
+	while (pages > 0) {
+		inval_pages = min(pages, MAX_TLBI_RANGE_PAGES);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages);
+
+		addr += inval_pages << PAGE_SHIFT;
+		pages -= inval_pages;
+	}
+}
+
 #define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt))
 
 static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot,
@@ -786,7 +806,8 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 		 * evicted pte value (if any).
 		 */
 		if (kvm_pte_table(ctx->old, ctx->level))
-			kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+			kvm_tlb_flush_vmid_range(mmu, ctx->addr,
+						kvm_granule_size(ctx->level));
 		else if (kvm_pte_valid(ctx->old))
 			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
 				     ctx->addr, ctx->level);
@@ -810,16 +831,36 @@ static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t n
 	smp_store_release(ctx->ptep, new);
 }
 
-static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu,
-			   struct kvm_pgtable_mm_ops *mm_ops)
+static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt)
+{
+	/*
+	 * 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() && stage2_has_fwb(pgt);
+}
+
+static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
+				struct kvm_s2_mmu *mmu,
+				struct kvm_pgtable_mm_ops *mm_ops)
 {
+	struct kvm_pgtable *pgt = ctx->arg;
+
 	/*
-	 * Clear the existing PTE, and perform break-before-make with
-	 * TLB maintenance if it was valid.
+	 * Clear the existing PTE, and perform break-before-make if it was
+	 * valid. Depending on the system support, defer the TLB maintenance
+	 * for the same until the entire unmap walk is completed.
 	 */
 	if (kvm_pte_valid(ctx->old)) {
 		kvm_clear_pte(ctx->ptep);
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+
+		if (!stage2_unmap_defer_tlb_flush(pgt))
+			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
+					ctx->addr, ctx->level);
 	}
 
 	mm_ops->put_page(ctx->ptep);
@@ -1077,7 +1118,7 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	 * block entry and rely on the remaining portions being faulted
 	 * back lazily.
 	 */
-	stage2_put_pte(ctx, mmu, mm_ops);
+	stage2_unmap_put_pte(ctx, mmu, mm_ops);
 
 	if (need_flush && mm_ops->dcache_clean_inval_poc)
 		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
@@ -1091,13 +1132,19 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
+	int ret;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_unmap_walker,
 		.arg	= pgt,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	return kvm_pgtable_walk(pgt, addr, size, &walker);
+	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
+	if (stage2_unmap_defer_tlb_flush(pgt))
+		/* Perform the deferred TLB invalidations */
+		kvm_tlb_flush_vmid_range(pgt->mmu, addr, size);
+
+	return ret;
 }
 
 struct stage2_attr_data {