[PATCH v2 07/13] kvm: Add arch-generic interface for hw-accelerated dirty-bitmap cleaning

@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2026 ARM Ltd.
+ * Author: Leonardo Bras <leo.bras@arm.com>
+ */
+
+#ifndef __KVM_DIRTY_BIT_H__
+#define __KVM_DIRTY_BIT_H__
+
+#ifndef CONFIG_HAVE_KVM_HW_DIRTY_BIT
+
+static inline int kvm_arch_dirty_log_clear(struct kvm *kvm,
+					   struct kvm_memory_slot *memslot,
+					   struct kvm_clear_dirty_log *log,
+					   unsigned long *bitmap,
+					   bool *flush)
+{
+	return -ENXIO;
+}
+
+#else /* CONFIG_HAVE_KVM_HW_DIRTY_BIT */
+
+#include <asm/kvm_dirty_bit.h>
+
+#endif /* CONFIG_HAVE_KVM_HW_DIRTY_BIT */
+
+#endif /* __KVM_DIRTY_BIT_H__ */

@@ -58,20 +58,21 @@
 #include "async_pf.h"
 #include "kvm_mm.h"
 #include "vfio.h"
 
 #include <trace/events/ipi.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
 #include <linux/kvm_dirty_ring.h>
+#include <linux/kvm_dirty_bit.h>
 
 
 /* Worst case buffer size needed for holding an integer. */
 #define ITOA_MAX_LEN 12
 
 MODULE_AUTHOR("Qumranet");
 MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor");
 MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */

@@ -2255,39 +2256,44 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 		 * is some code duplication between this function and
 		 * kvm_get_dirty_log, but hopefully all architecture
 		 * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log
 		 * can be eliminated.
 		 */
 		dirty_bitmap_buffer = dirty_bitmap;
 	} else {
 		dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
 		memset(dirty_bitmap_buffer, 0, n);
 
+		if (kvm_arch_dirty_log_clear(kvm, memslot, NULL,
+					     dirty_bitmap_buffer, &flush) >= 0)
+			goto out;
+
 		KVM_MMU_LOCK(kvm);
 		for (i = 0; i < n / sizeof(long); i++) {
 			unsigned long mask;
 			gfn_t offset;
 
 			if (!dirty_bitmap[i])
 				continue;
 
 			flush = true;
 			mask = xchg(&dirty_bitmap[i], 0);
 			dirty_bitmap_buffer[i] = mask;
 
 			offset = i * BITS_PER_LONG;
 			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
 								offset, mask);
 		}
 		KVM_MMU_UNLOCK(kvm);
 	}
 
+out:
 	if (flush)
 		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		return -EFAULT;
 	return 0;
 }
 
 
 /**

@@ -2366,45 +2372,50 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	    (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
 	    return -EINVAL;
 
 	kvm_arch_sync_dirty_log(kvm, memslot);
 
 	flush = false;
 	dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
 	if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
 		return -EFAULT;
 
+	if (kvm_arch_dirty_log_clear(kvm, memslot, log, dirty_bitmap_buffer,
+				     &flush) >= 0)
+		goto out;
+
 	KVM_MMU_LOCK(kvm);
 	for (offset = log->first_page, i = offset / BITS_PER_LONG,
 		 n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
 	     i++, offset += BITS_PER_LONG) {
 		unsigned long mask = *dirty_bitmap_buffer++;
 		atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
 		if (!mask)
 			continue;
 
 		mask &= atomic_long_fetch_andnot(mask, p);
 
 		/*
 		 * mask contains the bits that really have been cleared.  This
 		 * never includes any bits beyond the length of the memslot (if
 		 * the length is not aligned to 64 pages), therefore it is not
 		 * a problem if userspace sets them in log->dirty_bitmap.
 		*/
 		if (mask) {
 			flush = true;
+
 			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
 								offset, mask);
 		}
 	}
 	KVM_MMU_UNLOCK(kvm);
-
+out:
 	if (flush)
 		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	return 0;
 }
 
 static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 					struct kvm_clear_dirty_log *log)
 {
 	int r;

@@ -13,20 +13,23 @@ config HAVE_KVM_PFNCACHE
 
 config HAVE_KVM_IRQCHIP
        bool
 
 config HAVE_KVM_IRQ_ROUTING
        bool
 
 config HAVE_KVM_DIRTY_RING
        bool
 
+config HAVE_KVM_HW_DIRTY_BIT
+       bool
+
 # Only strongly ordered architectures can select this, as it doesn't
 # put any explicit constraint on userspace ordering. They can also
 # select the _ACQ_REL version.
 config HAVE_KVM_DIRTY_RING_TSO
        bool
        select HAVE_KVM_DIRTY_RING
        depends on X86
 
 # Weakly ordered architectures can only select this, advertising
 # to userspace the additional ordering requirements.