[RFC][Patch v9 5/6] KVM: Enabling guest free page hinting via static key

[Nitesh Narayan Lal]

This patch enables the guest free page hinting support
to enable or disable based on the STATIC key which
could be set via sysctl.

Signed-off-by: Nitesh Narayan Lal <nitesh@xxxxxxxxxx>
---
 Documentation/sysctl/vm.txt     | 12 ++++++++++++
 drivers/virtio/virtio_balloon.c |  4 ++++
 include/linux/page_hinting.h    |  5 +++++
 kernel/sysctl.c                 | 12 ++++++++++++
 virt/kvm/page_hinting.c         | 26 ++++++++++++++++++++++++++
 5 files changed, 59 insertions(+)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 187ce4f599a2..eae9180ea0aa 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -31,6 +31,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
+- guest_free_page_hinting
 - hugetlb_shm_group
 - laptop_mode
 - legacy_va_layout
@@ -255,6 +256,17 @@ fragmentation index is <= extfrag_threshold. The default value is 500.
 
 ==============================================================
 
+guest_free_page_hinting
+
+This parameter enables the kernel to report KVM guest free pages to the host
+via virtio balloon driver. QEMU receives these free page hints and frees them
+by performing MADVISE_DONTNEED on it.
+
+It depends on VIRTIO_BALLOON for its functionality. In case VIRTIO_BALLOON
+driver is missing, this feature is disabled by default.
+
+==============================================================
+
 highmem_is_dirtyable
 
 Available only for systems with CONFIG_HIGHMEM enabled (32b systems).
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index e82c72cd916b..171fd72ef2ae 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -164,12 +164,16 @@ static void hinting_ack(struct virtqueue *vq)
 
 static void enable_hinting(struct virtio_balloon *vb)
 {
+	guest_free_page_hinting_flag = 1;
+	static_branch_enable(&guest_free_page_hinting_key);
 	request_hypercall = (void *)&virtballoon_page_hinting;
 	balloon_ptr = vb;
 }
 
 static void disable_hinting(void)
 {
+	guest_free_page_hinting_flag = 0;
+	static_branch_enable(&guest_free_page_hinting_key);
 	balloon_ptr = NULL;
 }
 #endif
diff --git a/include/linux/page_hinting.h b/include/linux/page_hinting.h
index a32af8851081..60e0a21bfbe6 100644
--- a/include/linux/page_hinting.h
+++ b/include/linux/page_hinting.h
@@ -12,6 +12,8 @@
 #define FREE_PAGE_HINTING_MIN_ORDER	(MAX_ORDER - 1)
 
 extern void *balloon_ptr;
+extern int guest_free_page_hinting_flag;
+extern struct static_key_false guest_free_page_hinting_key;
 
 void guest_free_page_enqueue(struct page *page, int order);
 void guest_free_page_try_hinting(void);
@@ -22,3 +24,6 @@ extern void __free_one_page(struct page *page, unsigned long pfn,
 void release_buddy_pages(void *obj_to_free, int entries);
 extern int (*request_hypercall)(void *balloon_ptr,
 				void *hinting_req, int entries);
+int guest_free_page_hinting_sysctl(struct ctl_table *table, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ba4d9e85feb8..7b2970e9e937 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -96,6 +96,9 @@
 #ifdef CONFIG_LOCKUP_DETECTOR
 #include <linux/nmi.h>
 #endif
+#ifdef CONFIG_KVM_FREE_PAGE_HINTING
+#include <linux/page_hinting.h>
+#endif
 
 #if defined(CONFIG_SYSCTL)
 
@@ -1690,6 +1693,15 @@ static struct ctl_table vm_table[] = {
 		.extra1		= (void *)&mmap_rnd_compat_bits_min,
 		.extra2		= (void *)&mmap_rnd_compat_bits_max,
 	},
+#endif
+#ifdef CONFIG_KVM_FREE_PAGE_HINTING
+	{
+		.procname       = "guest-free-page-hinting",
+		.data           = &guest_free_page_hinting_flag,
+		.maxlen         = sizeof(guest_free_page_hinting_flag),
+		.mode           = 0644,
+		.proc_handler   = guest_free_page_hinting_sysctl,
+	},
 #endif
 	{ }
 };
diff --git a/virt/kvm/page_hinting.c b/virt/kvm/page_hinting.c
index eb0c0ddfe990..5980682e0b86 100644
--- a/virt/kvm/page_hinting.c
+++ b/virt/kvm/page_hinting.c
@@ -36,6 +36,28 @@ EXPORT_SYMBOL(request_hypercall);
 void *balloon_ptr;
 EXPORT_SYMBOL(balloon_ptr);
 
+struct static_key_false guest_free_page_hinting_key  = STATIC_KEY_FALSE_INIT;
+EXPORT_SYMBOL(guest_free_page_hinting_key);
+static DEFINE_MUTEX(hinting_mutex);
+int guest_free_page_hinting_flag;
+EXPORT_SYMBOL(guest_free_page_hinting_flag);
+
+int guest_free_page_hinting_sysctl(struct ctl_table *table, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	int ret;
+
+	mutex_lock(&hinting_mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (guest_free_page_hinting_flag)
+		static_key_enable(&guest_free_page_hinting_key.key);
+	else
+		static_key_disable(&guest_free_page_hinting_key.key);
+	mutex_unlock(&hinting_mutex);
+	return ret;
+}
+
 void release_buddy_pages(void *hinting_req, int entries)
 {
 	int i = 0;
@@ -223,6 +245,8 @@ void guest_free_page_enqueue(struct page *page, int order)
 	struct guest_free_pages *hinting_obj;
 	int l_idx;
 
+	if (!static_branch_unlikely(&guest_free_page_hinting_key))
+		return;
 	/*
 	 * use of global variables may trigger a race condition between irq and
 	 * process context causing unwanted overwrites. This will be replaced
@@ -258,6 +282,8 @@ void guest_free_page_try_hinting(void)
 {
 	struct guest_free_pages *hinting_obj;
 
+	if (!static_branch_unlikely(&guest_free_page_hinting_key))
+		return;
 	hinting_obj = this_cpu_ptr(&free_pages_obj);
 	if (hinting_obj->free_pages_idx >= HINTING_THRESHOLD)
 		guest_free_page_hinting();
-- 
2.17.2