[pull] master from torvalds:master

arch/x86/hyperv/hv_init.c

@@ -73,7 +73,8 @@ static int hv_cpu_init(unsigned int cpu)
 	struct page *pg;
 
 	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-	pg = alloc_page(GFP_KERNEL);
+	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
+	pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
 	if (unlikely(!pg))
 		return -ENOMEM;
 	*input_arg = page_address(pg);
@@ -254,6 +255,7 @@ static int __init hv_pci_init(void)
 static int hv_suspend(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
+	int ret;
 
 	/*
 	 * Reset the hypercall page as it is going to be invalidated
@@ -270,12 +272,17 @@ static int hv_suspend(void)
 	hypercall_msr.enable = 0;
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	return 0;
+	ret = hv_cpu_die(0);
+	return ret;
 }
 
 static void hv_resume(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
+	int ret;
+
+	ret = hv_cpu_init(0);
+	WARN_ON(ret);
 
 	/* Re-enable the hypercall page */
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -288,6 +295,7 @@ static void hv_resume(void)
 	hv_hypercall_pg_saved = NULL;
 }
 
+/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */
 static struct syscore_ops hv_syscore_ops = {
 	.suspend	= hv_suspend,
 	.resume		= hv_resume,

arch/x86/include/asm/mshyperv.h

@@ -35,6 +35,8 @@ typedef int (*hyperv_fill_flush_list_func)(
 	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
 #define hv_set_synint_state(int_num, val) \
 	wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_recommend_using_aeoi() \
+	(!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
 
 #define hv_get_crash_ctl(val) \
 	rdmsrl(HV_X64_MSR_CRASH_CTL, val)

drivers/hv/hv.c

@@ -184,11 +184,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 
 	shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
 	shared_sint.masked = false;
-	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
-		shared_sint.auto_eoi = false;
-	else
-		shared_sint.auto_eoi = true;
-
+	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	/* Enable the global synic bit */

drivers/hv/hv_trace.h

@@ -286,8 +286,8 @@ TRACE_EVENT(vmbus_send_tl_connect_request,
 		    __field(int, ret)
 		    ),
 	    TP_fast_assign(
-		    memcpy(__entry->guest_id, &msg->guest_endpoint_id.b, 16);
-		    memcpy(__entry->host_id, &msg->host_service_id.b, 16);
+		    export_guid(__entry->guest_id, &msg->guest_endpoint_id);
+		    export_guid(__entry->host_id, &msg->host_service_id);
 		    __entry->ret = ret;
 		    ),
 	    TP_printk("sending guest_endpoint_id %pUl, host_service_id %pUl, "

drivers/hv/vmbus_drv.c

@@ -978,6 +978,9 @@ static int vmbus_resume(struct device *child_device)
 
 	return drv->resume(dev);
 }
+#else
+#define vmbus_suspend NULL
+#define vmbus_resume NULL
 #endif /* CONFIG_PM_SLEEP */
 
 /*
@@ -997,11 +1000,22 @@ static void vmbus_device_release(struct device *device)
 }
 
 /*
- * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
- * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm.
+ * Note: we must use the "noirq" ops: see the comment before vmbus_bus_pm.
+ *
+ * suspend_noirq/resume_noirq are set to NULL to support Suspend-to-Idle: we
+ * shouldn't suspend the vmbus devices upon Suspend-to-Idle, otherwise there
+ * is no way to wake up a Generation-2 VM.
+ *
+ * The other 4 ops are for hibernation.
  */
+
 static const struct dev_pm_ops vmbus_pm = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume)
+	.suspend_noirq	= NULL,
+	.resume_noirq	= NULL,
+	.freeze_noirq	= vmbus_suspend,
+	.thaw_noirq	= vmbus_resume,
+	.poweroff_noirq	= vmbus_suspend,
+	.restore_noirq	= vmbus_resume,
 };
 
 /* The one and only one */
@@ -2281,6 +2295,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	return 0;
 }
+#else
+#define vmbus_bus_suspend NULL
+#define vmbus_bus_resume NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
@@ -2291,16 +2308,24 @@ static const struct acpi_device_id vmbus_acpi_device_ids[] = {
 MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
 
 /*
- * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
- * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the
- * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the
- * pci "noirq" restore callback runs before "non-noirq" callbacks (see
+ * Note: we must use the "no_irq" ops, otherwise hibernation can not work with
+ * PCI device assignment, because "pci_dev_pm_ops" uses the "noirq" ops: in
+ * the resume path, the pci "noirq" restore op runs before "non-noirq" op (see
  * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
  * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
- * resume callback must also run via the "noirq" callbacks.
+ * resume callback must also run via the "noirq" ops.
+ *
+ * Set suspend_noirq/resume_noirq to NULL for Suspend-to-Idle: see the comment
+ * earlier in this file before vmbus_pm.
  */
+
 static const struct dev_pm_ops vmbus_bus_pm = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume)
+	.suspend_noirq	= NULL,
+	.resume_noirq	= NULL,
+	.freeze_noirq	= vmbus_bus_suspend,
+	.thaw_noirq	= vmbus_bus_resume,
+	.poweroff_noirq	= vmbus_bus_suspend,
+	.restore_noirq	= vmbus_bus_resume
 };
 
 static struct acpi_driver vmbus_acpi_driver = {

fs/btrfs/block-group.c

@@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_put_group;
 	}
 
 	/*
@@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
-			goto out;
+			goto out_put_group;
 		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
@@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
-		goto out;
+		goto out_put_group;
 	if (ret > 0)
 		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
-			goto out;
+			goto out_put_group;
 		btrfs_release_path(path);
 	}
 
@@ -1102,9 +1102,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = remove_block_group_free_space(trans, block_group);
 	if (ret)
-		goto out;
+		goto out_put_group;
 
-	btrfs_put_block_group(block_group);
+	/* Once for the block groups rbtree */
 	btrfs_put_block_group(block_group);
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -1127,6 +1127,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		/* once for the tree */
 		free_extent_map(em);
 	}
+
+out_put_group:
+	/* Once for the lookup reference */
+	btrfs_put_block_group(block_group);
 out:
 	if (remove_rsv)
 		btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1288,11 +1292,15 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto err;
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 
 	return true;
 
 err:
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 	btrfs_dec_block_group_ro(bg);
 	return false;
 }

fs/btrfs/discard.h

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef BTRFS_DISCARD_H
 #define BTRFS_DISCARD_H

fs/btrfs/disk-io.c

@@ -2036,9 +2036,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++)
 			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
 	}
-
-	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
-		btrfs_free_log_root_tree(NULL, fs_info);
 }
 
 static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
@@ -3888,7 +3885,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
-		btrfs_free_log(NULL, root);
+		ASSERT(root->log_root == NULL);
 		if (root->reloc_root) {
 			btrfs_put_root(root->reloc_root);
 			root->reloc_root = NULL;
@@ -4211,6 +4208,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 	up_write(&fs_info->cleanup_work_sem);
 }
 
+static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *gang[8];
+	u64 root_objectid = 0;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, root_objectid,
+					     ARRAY_SIZE(gang))) != 0) {
+		int i;
+
+		for (i = 0; i < ret; i++)
+			gang[i] = btrfs_grab_root(gang[i]);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
+
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
+				continue;
+			root_objectid = gang[i]->root_key.objectid;
+			btrfs_free_log(NULL, gang[i]);
+			btrfs_put_root(gang[i]);
+		}
+		root_objectid++;
+		spin_lock(&fs_info->fs_roots_radix_lock);
+	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	btrfs_free_log_root_tree(NULL, fs_info);
+}
+
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -4603,6 +4630,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_delayed_inodes(fs_info);
 	btrfs_assert_delayed_root_empty(fs_info);
 	btrfs_destroy_all_delalloc_inodes(fs_info);
+	btrfs_drop_all_logs(fs_info);
 	mutex_unlock(&fs_info->transaction_kthread_mutex);
 
 	return 0;

fs/btrfs/relocation.c

@@ -4559,6 +4559,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		if (IS_ERR(fs_root)) {
 			err = PTR_ERR(fs_root);
 			list_add_tail(&reloc_root->root_list, &reloc_roots);
+			btrfs_end_transaction(trans);
 			goto out_unset;
 		}
 

include/uapi/linux/hyperv.h

@@ -119,8 +119,8 @@ enum hv_fcopy_op {
 
 struct hv_fcopy_hdr {
 	__u32 operation;
-	uuid_le service_id0; /* currently unused */
-	uuid_le service_id1; /* currently unused */
+	__u8 service_id0[16]; /* currently unused */
+	__u8 service_id1[16]; /* currently unused */
 } __attribute__((packed));
 
 #define OVER_WRITE	0x1