Merge feature/page-reporting/5.15 into v5.15.79

* commit 'ad427234defd6cdfdc0c21ca5b64ef589b82a421':
  hv_balloon: Add support for configurable order free page reporting
  mm/page_reporting: Add checks for page_reporting_order param

Author: kelsey-steele

drivers/hv/hv_balloon.c

@@ -468,12 +468,16 @@ static bool do_hot_add;
  * the specified number of seconds.
  */
 static uint pressure_report_delay = 45;
+extern unsigned int page_reporting_order;
+#define HV_MAX_FAILURES	2
 
 /*
  * The last time we posted a pressure report to host.
  */
 static unsigned long last_post_time;
 
+static int hv_hypercall_multi_failure;
+
 module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
 
@@ -573,6 +577,10 @@ static struct hv_dynmem_device dm_device;
 
 static void post_status(struct hv_dynmem_device *dm);
 
+static void enable_page_reporting(void);
+
+static void disable_page_reporting(void);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static inline bool has_pfn_is_backed(struct hv_hotadd_state *has,
 				     unsigned long pfn)
@@ -1402,6 +1410,18 @@ static int dm_thread_func(void *dm_dev)
 		 */
 		reinit_completion(&dm_device.config_event);
 		post_status(dm);
+		/*
+		 * disable free page reporting if multiple hypercall
+		 * failure flag set. It is not done in the page_reporting
+		 * callback context as that causes a deadlock between
+		 * page_reporting_process() and page_reporting_unregister()
+		 */
+		if (hv_hypercall_multi_failure >= HV_MAX_FAILURES) {
+			pr_err("Multiple failures in cold memory discard hypercall, disabling page reporting\n");
+			disable_page_reporting();
+			/* Reset the flag after disabling reporting */
+			hv_hypercall_multi_failure = 0;
+		}
 	}
 
 	return 0;
@@ -1577,20 +1597,20 @@ static void balloon_onchannelcallback(void *context)
 
 }
 
-/* Hyper-V only supports reporting 2MB pages or higher */
-#define HV_MIN_PAGE_REPORTING_ORDER	9
-#define HV_MIN_PAGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << HV_MIN_PAGE_REPORTING_ORDER)
+#define HV_LARGE_REPORTING_ORDER	9
+#define HV_LARGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << \
+		HV_LARGE_REPORTING_ORDER)
 static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 		    struct scatterlist *sgl, unsigned int nents)
 {
 	unsigned long flags;
 	struct hv_memory_hint *hint;
-	int i;
+	int i, order;
 	u64 status;
 	struct scatterlist *sg;
 
 	WARN_ON_ONCE(nents > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
-	WARN_ON_ONCE(sgl->length < HV_MIN_PAGE_REPORTING_LEN);
+	WARN_ON_ONCE(sgl->length < (HV_HYP_PAGE_SIZE << page_reporting_order));
 	local_irq_save(flags);
 	hint = *(struct hv_memory_hint **)this_cpu_ptr(hyperv_pcpu_input_arg);
 	if (!hint) {
@@ -1605,21 +1625,53 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 
 		range = &hint->ranges[i];
 		range->address_space = 0;
-		/* page reporting only reports 2MB pages or higher */
-		range->page.largepage = 1;
-		range->page.additional_pages =
-			(sg->length / HV_MIN_PAGE_REPORTING_LEN) - 1;
-		range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB;
-		range->base_large_pfn =
-			page_to_hvpfn(sg_page(sg)) >> HV_MIN_PAGE_REPORTING_ORDER;
+		order = get_order(sg->length);
+		/*
+		 * Hyper-V expects the additional_pages field in the units
+		 * of one of these 3 sizes, 4Kbytes, 2Mbytes or 1Gbytes.
+		 * This is dictated by the values of the fields page.largesize
+		 * and page_size.
+		 * This code however, only uses 4Kbytes and 2Mbytes units
+		 * and not 1Gbytes unit.
+		 */
+
+		/* page reporting for pages 2MB or higher */
+		if (order >= HV_LARGE_REPORTING_ORDER ) {
+			range->page.largepage = 1;
+			range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB;
+			range->base_large_pfn = page_to_hvpfn(
+					sg_page(sg)) >> HV_LARGE_REPORTING_ORDER;
+			range->page.additional_pages =
+				(sg->length / HV_LARGE_REPORTING_LEN) - 1;
+		} else {
+			/* Page reporting for pages below 2MB */
+			range->page.basepfn = page_to_hvpfn(sg_page(sg));
+			range->page.largepage = false;
+			range->page.additional_pages =
+				(sg->length / HV_HYP_PAGE_SIZE) - 1;
+		}
+
 	}
 
 	status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0,
 				     hint, NULL);
 	local_irq_restore(flags);
-	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+	if (!hv_result_success(status)) {
+
 		pr_err("Cold memory discard hypercall failed with status %llx\n",
-			status);
+				status);
+		if (hv_hypercall_multi_failure > 0)
+			hv_hypercall_multi_failure++;
+
+		if (hv_result(status) == HV_STATUS_INVALID_PARAMETER) {
+			pr_err("Underlying Hyper-V does not support order less than 9. Hypercall failed\n");
+			pr_err("Defaulting to page_reporting_order %d\n",
+					pageblock_order);
+			page_reporting_order = pageblock_order;
+			hv_hypercall_multi_failure++;
+			return -EINVAL;
+		}
+
 		return -EINVAL;
 	}
 
@@ -1630,25 +1682,25 @@ static void enable_page_reporting(void)
 {
 	int ret;
 
-	/* Essentially, validating 'PAGE_REPORTING_MIN_ORDER' is big enough. */
-	if (pageblock_order < HV_MIN_PAGE_REPORTING_ORDER) {
-		pr_debug("Cold memory discard is only supported on 2MB pages and above\n");
-		return;
-	}
-
 	if (!hv_query_ext_cap(HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT)) {
 		pr_debug("Cold memory discard hint not supported by Hyper-V\n");
 		return;
 	}
 
 	BUILD_BUG_ON(PAGE_REPORTING_CAPACITY > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
 	dm_device.pr_dev_info.report = hv_free_page_report;
+	/*
+	 * We let the page_reporting_order parameter decide the order
+	 * in the page_reporting code
+	 */
+	dm_device.pr_dev_info.order = 0;
 	ret = page_reporting_register(&dm_device.pr_dev_info);
 	if (ret < 0) {
 		dm_device.pr_dev_info.report = NULL;
 		pr_err("Failed to enable cold memory discard: %d\n", ret);
 	} else {
-		pr_info("Cold memory discard hint enabled\n");
+		pr_info("Cold memory discard hint enabled with order %d\n",
+				page_reporting_order);
 	}
 }
 

mm/page_reporting.c

@@ -11,10 +11,42 @@
 #include "page_reporting.h"
 #include "internal.h"
 
-unsigned int page_reporting_order = MAX_ORDER;
-module_param(page_reporting_order, uint, 0644);
+/* Initialize to an unsupported value */
+unsigned int page_reporting_order = -1;
+
+static int page_order_update_notify(const char *val, const struct kernel_param *kp)
+{
+	/*
+	 * If param is set beyond this limit, order is set to default
+	 * pageblock_order value
+	 */
+	return  param_set_uint_minmax(val, kp, 0, MAX_ORDER-1);
+}
+
+static const struct kernel_param_ops page_reporting_param_ops = {
+	.set = &page_order_update_notify,
+	/*
+	 * For the get op, use param_get_int instead of param_get_uint.
+	 * This is to make sure that when unset the initialized value of
+	 * -1 is shown correctly
+	 */
+	.get = &param_get_int,
+};
+
+module_param_cb(page_reporting_order, &page_reporting_param_ops,
+			&page_reporting_order, 0644);
 MODULE_PARM_DESC(page_reporting_order, "Set page reporting order");
 
+/*
+ * This symbol is also a kernel parameter. Export the page_reporting_order
+ * symbol so that other drivers can access it to control order values without
+ * having to introduce another configurable parameter. Only one driver can
+ * register with the page_reporting driver for the service, so we have just
+ * one control parameter for the use case(which can be accessed in both
+ * drivers)
+ */
+EXPORT_SYMBOL_GPL(page_reporting_order);
+
 #define PAGE_REPORTING_DELAY	(2 * HZ)
 static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly;
 
@@ -330,10 +362,18 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
 	}
 
 	/*
-	 * Update the page reporting order if it's specified by driver.
-	 * Otherwise, it falls back to @pageblock_order.
+	 * If the page_reporting_order value is not set, we check if
+	 * an order is provided from the driver that is performing the
+	 * registration. If that is not provided either, we default to
+	 * pageblock_order.
 	 */
-	page_reporting_order = prdev->order ? : pageblock_order;
+
+	if (page_reporting_order == -1) {
+		if (prdev->order > 0 && prdev->order <= MAX_ORDER)
+			page_reporting_order = prdev->order;
+		else
+			page_reporting_order = pageblock_order;
+	}
 
 	/* initialize state and work structures */
 	atomic_set(&prdev->state, PAGE_REPORTING_IDLE);