KVM: arm64: Split huge pages when dirty logging is enabled

Split huge pages eagerly when enabling dirty logging. The goal is to
avoid doing it while faulting on write-protected pages, which
negatively impacts guest performance.

A memslot marked for dirty logging is split in 1GB pieces at a time.
This is in order to release the mmu_lock and give other kernel threads
the opportunity to run, and also in order to allocate enough pages to
split a 1GB range worth of huge pages (or a single 1GB huge page).
Note that these page allocations can fail, so eager page splitting is
best-effort.  This is not a correctness issue though, as huge pages
can still be split on write-faults.

Eager page splitting only takes effect when the huge page mapping has
been existing in the stage-2 page table. Otherwise, the huge page will
be mapped to multiple non-huge pages on page fault.

The benefits of eager page splitting are the same as in x86, added
with commit a3fe5db ("KVM: x86/mmu: Split huge pages mapped by
the TDP MMU when dirty logging is enabled"). For example, when running
dirty_log_perf_test with 64 virtual CPUs (Ampere Altra), 1GB per vCPU,
50% reads, and 2MB HugeTLB memory, the time it takes vCPUs to access
all of their memory after dirty logging is enabled decreased by 44%
from 2.58s to 1.42s.

Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Link: https://lore.kernel.org/r/20230426172330.1439644-10-ricarkol@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: Ricardo Koller

arch/arm64/kvm/mmu.c

@@ -31,14 +31,21 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
 
 static unsigned long __ro_after_init io_map_base;
 
-static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
+					   phys_addr_t size)
 {
-	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
 	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
 
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
+
+	return __stage2_range_addr_end(addr, end, size);
+}
+
 /*
  * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
  * we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
@@ -75,6 +82,79 @@ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 #define stage2_apply_range_resched(mmu, addr, end, fn)			\
 	stage2_apply_range(mmu, addr, end, fn, true)
 
+/*
+ * Get the maximum number of page-tables pages needed to split a range
+ * of blocks into PAGE_SIZE PTEs. It assumes the range is already
+ * mapped at level 2, or at level 1 if allowed.
+ */
+static int kvm_mmu_split_nr_page_tables(u64 range)
+{
+	int n = 0;
+
+	if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
+		n += DIV_ROUND_UP_ULL(range, PUD_SIZE);
+	n += DIV_ROUND_UP_ULL(range, PMD_SIZE);
+	return n;
+}
+
+static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
+{
+	struct kvm_mmu_memory_cache *cache;
+	u64 chunk_size, min;
+
+	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
+		return true;
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	min = kvm_mmu_split_nr_page_tables(chunk_size);
+	cache = &kvm->arch.mmu.split_page_cache;
+	return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
+}
+
+static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
+				    phys_addr_t end)
+{
+	struct kvm_mmu_memory_cache *cache;
+	struct kvm_pgtable *pgt;
+	int ret, cache_capacity;
+	u64 next, chunk_size;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);
+
+	if (chunk_size == 0)
+		return 0;
+
+	cache = &kvm->arch.mmu.split_page_cache;
+
+	do {
+		if (need_split_memcache_topup_or_resched(kvm)) {
+			write_unlock(&kvm->mmu_lock);
+			cond_resched();
+			/* Eager page splitting is best-effort. */
+			ret = __kvm_mmu_topup_memory_cache(cache,
+							   cache_capacity,
+							   cache_capacity);
+			write_lock(&kvm->mmu_lock);
+			if (ret)
+				break;
+		}
+
+		pgt = kvm->arch.mmu.pgt;
+		if (!pgt)
+			return -EINVAL;
+
+		next = __stage2_range_addr_end(addr, end, chunk_size);
+		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
+		if (ret)
+			break;
+	} while (addr = next, addr != end);
+
+	return ret;
+}
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
@@ -793,6 +873,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 void kvm_uninit_stage2_mmu(struct kvm *kvm)
 {
 	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 }
 
 static void stage2_unmap_memslot(struct kvm *kvm,
@@ -1019,6 +1100,34 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
+/**
+ * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
+ *				   pages for memory slot
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot to split
+ *
+ * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
+ */
+static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	phys_addr_t start, end;
+
+	lockdep_assert_held(&kvm->slots_lock);
+
+	slots = kvm_memslots(kvm);
+	memslot = id_to_memslot(slots, slot);
+
+	start = memslot->base_gfn << PAGE_SHIFT;
+	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	write_lock(&kvm->mmu_lock);
+	kvm_mmu_split_huge_pages(kvm, start, end);
+	write_unlock(&kvm->mmu_lock);
+}
+
 /*
  * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
  * dirty pages.
@@ -1812,8 +1921,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 			return;
 
 		/*
-		 * Pages are write-protected on either of these two
-		 * cases:
+		 * Huge and normal pages are write-protected and split
+		 * on either of these two cases:
 		 *
 		 * 1. with initial-all-set: gradually with CLEAR ioctls,
 		 */
@@ -1825,6 +1934,16 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		 *    enabling dirty logging.
 		 */
 		kvm_mmu_wp_memory_region(kvm, new->id);
+		kvm_mmu_split_memory_region(kvm, new->id);
+	} else {
+		/*
+		 * Free any leftovers from the eager page splitting cache. Do
+		 * this when deleting, moving, disabling dirty logging, or
+		 * creating the memslot (a nop). Doing it for deletes makes
+		 * sure we don't leak memory, and there's no need to keep the
+		 * cache around for any of the other cases.
+		 */
+		kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 	}
 }