Merge branch 'SLE15-SP1' into SLE15-SP1-AZURE

suse-commit: 8fa306690f3a2397a832d25fcbdfefa7d1f3b4a0

arch/powerpc/mm/init_64.c

@@ -156,6 +156,21 @@ static __meminit void vmemmap_list_populate(unsigned long phys,
 	vmemmap_list = vmem_back;
 }
 
+static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+				unsigned long page_size)
+{
+	unsigned long nr_pfn = page_size / sizeof(struct page);
+	unsigned long start_pfn = page_to_pfn((struct page *)start);
+
+	if ((start_pfn + nr_pfn) > altmap->end_pfn)
+		return true;
+
+	if (start_pfn < altmap->base_pfn)
+		return true;
+
+	return false;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -178,7 +193,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		 * fail due to alignment issues when using 16MB hugepages, so
 		 * fall back to system memory if the altmap allocation fail.
 		 */
-		if (altmap) {
+		if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
 			p = altmap_alloc_block_buf(page_size, altmap);
 			if (!p)
 				pr_debug("altmap block allocation failed, falling back to system memory");

arch/powerpc/platforms/pseries/papr_scm.c

@@ -124,7 +124,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p,
 	int len, read;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= read) {
@@ -178,7 +178,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p,
 	__be64 data_be;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= wrote) {

arch/x86/kernel/ftrace.c

@@ -21,7 +21,6 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/memory.h>
 
 #include <trace/syscall.h>
 
@@ -35,7 +34,6 @@
 
 int ftrace_arch_code_modify_prepare(void)
 {
-	mutex_lock(&text_mutex);
 	set_kernel_text_rw();
 	set_all_modules_text_rw();
 	return 0;
@@ -45,7 +43,6 @@ int ftrace_arch_code_modify_post_process(void)
 {
 	set_all_modules_text_ro();
 	set_kernel_text_ro();
-	mutex_unlock(&text_mutex);
 	return 0;
 }
 

drivers/net/xen-netfront.c

@@ -885,9 +885,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
-				  struct sk_buff *skb,
-				  struct sk_buff_head *list)
+static int xennet_fill_frags(struct netfront_queue *queue,
+			     struct sk_buff *skb,
+			     struct sk_buff_head *list)
 {
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
@@ -906,7 +906,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
 			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
-			return ~0U;
+			return -ENOENT;
 		}
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
@@ -917,7 +917,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		kfree_skb(nskb);
 	}
 
-	return cons;
+	queue->rx.rsp_cons = cons;
+
+	return 0;
 }
 
 static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
@@ -1043,8 +1045,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(queue, skb, &tmpq);
-		if (unlikely(i == ~0U))
+		if (unlikely(xennet_fill_frags(queue, skb, &tmpq)))
 			goto err;
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
@@ -1054,7 +1055,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 
 		__skb_queue_tail(&rxq, skb);
 
-		queue->rx.rsp_cons = ++i;
+		i = ++queue->rx.rsp_cons;
 		work_done++;
 	}
 

drivers/nvdimm/pfn_devs.c

@@ -612,9 +612,11 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	resource_size_t base = nsio->res.start + start_pad;
+	resource_size_t end = nsio->res.end - end_trunc;
 	struct vmem_altmap __altmap = {
 		.base_pfn = init_altmap_base(base),
 		.reserve = init_altmap_reserve(base),
+		.end_pfn = PHYS_PFN(end),
 	};
 
 	memcpy(res, &nsio->res, sizeof(*res));

drivers/pci/quirks.c

@@ -2231,6 +2231,12 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID,
 		quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_QLOGIC, 0x2261, quirk_blacklist_vpd);
+/*
+ * The Amazon Annapurna Labs 0x0031 device id is reused for other non Root Port
+ * device types, so the quirk is registered for the PCI_CLASS_BRIDGE_PCI class.
+ */
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031,
+			      PCI_CLASS_BRIDGE_PCI, 8, quirk_blacklist_vpd);
 
 /*
  * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
@@ -2853,6 +2859,24 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, 0x10a1,
 			quirk_msi_intx_disable_qca_bug);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, 0xe091,
 			quirk_msi_intx_disable_qca_bug);
+
+/*
+ * Amazon's Annapurna Labs 1c36:0031 Root Ports don't support MSI-X, so it
+ * should be disabled on platforms where the device (mistakenly) advertises it.
+ *
+ * Notice that this quirk also disables MSI (which may work, but hasn't been
+ * tested), since currently there is no standard way to disable only MSI-X.
+ *
+ * The 0031 device id is reused for other non Root Port device types,
+ * therefore the quirk is registered for the PCI_CLASS_BRIDGE_PCI class.
+ */
+static void quirk_al_msi_disable(struct pci_dev *dev)
+{
+	dev->no_msi = 1;
+	pci_warn(dev, "Disabling MSI/MSI-X\n");
+}
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031,
+			      PCI_CLASS_BRIDGE_PCI, 8, quirk_al_msi_disable);
 #endif /* CONFIG_PCI_MSI */
 
 /* Allow manual resource allocation for PCI hotplug bridges
@@ -4520,6 +4544,24 @@ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags)
 	return ret;
 }
 
+static int pci_quirk_al_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	if (pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT)
+		return -ENOTTY;
+
+	/*
+	 * Amazon's Annapurna Labs root ports don't include an ACS capability,
+	 * but do include ACS-like functionality. The hardware doesn't support
+	 * peer-to-peer transactions via the root port and each has a unique
+	 * segment number.
+	 *
+	 * Additionally, the root ports cannot send traffic to each other.
+	 */
+	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+
+	return acs_flags ? 0 : 1;
+}
+
 /*
  * Sunrise Point PCH root ports implement ACS, but unfortunately as shown in
  * the datasheet (Intel 100 Series Chipset Family PCH Datasheet, Vol. 2,
@@ -4711,6 +4753,8 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
+	/* Amazon Annapurna Labs */
+	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
 	{ 0 }
 };
 

drivers/xen/xenbus/xenbus_dev_frontend.c

@@ -55,6 +55,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/miscdevice.h>
+#include <linux/workqueue.h>
 
 #include <xen/xenbus.h>
 #include <xen/xen.h>
@@ -113,6 +114,8 @@ struct xenbus_file_priv {
 	wait_queue_head_t read_waitq;
 
 	struct kref kref;
+
+	struct work_struct wq;
 };
 
 /* Read out any raw xenbus messages queued up. */
@@ -297,14 +300,14 @@ static void watch_fired(struct xenbus_watch *watch,
 	mutex_unlock(&adap->dev_data->reply_mutex);
 }
 
-static void xenbus_file_free(struct kref *kref)
+static void xenbus_worker(struct work_struct *wq)
 {
 	struct xenbus_file_priv *u;
 	struct xenbus_transaction_holder *trans, *tmp;
 	struct watch_adapter *watch, *tmp_watch;
 	struct read_buffer *rb, *tmp_rb;
 
-	u = container_of(kref, struct xenbus_file_priv, kref);
+	u = container_of(wq, struct xenbus_file_priv, wq);
 
 	/*
 	 * No need for locking here because there are no other users,
@@ -330,6 +333,18 @@ static void xenbus_file_free(struct kref *kref)
 	kfree(u);
 }
 
+static void xenbus_file_free(struct kref *kref)
+{
+	struct xenbus_file_priv *u;
+
+	/*
+	 * We might be called in xenbus_thread().
+	 * Use workqueue to avoid deadlock.
+	 */
+	u = container_of(kref, struct xenbus_file_priv, kref);
+	schedule_work(&u->wq);
+}
+
 static struct xenbus_transaction_holder *xenbus_get_transaction(
 	struct xenbus_file_priv *u, uint32_t tx_id)
 {
@@ -626,6 +641,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
 	INIT_LIST_HEAD(&u->watches);
 	INIT_LIST_HEAD(&u->read_buffers);
 	init_waitqueue_head(&u->read_waitq);
+	INIT_WORK(&u->wq, xenbus_worker);
 
 	mutex_init(&u->reply_mutex);
 	mutex_init(&u->msgbuffer_mutex);

fs/btrfs/qgroup.c

@@ -3452,6 +3452,9 @@ int btrfs_qgroup_reserve_data(struct inode *inode,
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
 				 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
 				 GFP_NOFS);
+	/* Also free data bytes of already reserved one */
+	btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid,
+				  orig_reserved, BTRFS_QGROUP_RSV_DATA);
 	extent_changeset_release(reserved);
 	return ret;
 }
@@ -3496,7 +3499,7 @@ static int qgroup_free_reserved_data(struct inode *inode,
 		 * EXTENT_QGROUP_RESERVED, we won't double free.
 		 * So not need to rush.
 		 */
-		ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree,
+		ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree,
 				free_start, free_start + free_len - 1,
 				EXTENT_QGROUP_RESERVED, &changeset);
 		if (ret < 0)

fs/btrfs/relocation.c

@@ -1478,6 +1478,13 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	int clear_rsv = 0;
 	int ret;
 
+	/*
+	 * The subvolume has reloc tree but the swap is finished, no need to
+	 * create/update the dead reloc tree
+	 */
+	if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state))
+		return 0;
+
 	if (root->reloc_root) {
 		reloc_root = root->reloc_root;
 		reloc_root->last_trans = trans->transid;
@@ -2228,7 +2235,6 @@ static int clean_dirty_subvols(struct reloc_control *rc)
 			/* Merged subvolume, cleanup its reloc root */
 			struct btrfs_root *reloc_root = root->reloc_root;
 
-			clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
 			list_del_init(&root->reloc_dirty_list);
 			root->reloc_root = NULL;
 			if (reloc_root) {
@@ -2237,6 +2243,7 @@ static int clean_dirty_subvols(struct reloc_control *rc)
 				if (ret2 < 0 && !ret)
 					ret = ret2;
 			}
+			clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
 			btrfs_put_fs_root(root);
 		} else {
 			/* Orphan reloc tree, just clean it up */

fs/ceph/inode.c

@@ -531,13 +531,16 @@ static void ceph_i_callback(struct rcu_head *head)
 	kmem_cache_free(ceph_inode_cachep, ci);
 }
 
-void ceph_destroy_inode(struct inode *inode)
+void ceph_evict_inode(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_inode_frag *frag;
 	struct rb_node *n;
 
-	dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
+	dout("evict_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
 
 	ceph_fscache_unregister_inode_cookie(ci);
 
@@ -579,7 +582,10 @@ void ceph_destroy_inode(struct inode *inode)
 		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
 	ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
+}
 
+void ceph_destroy_inode(struct inode *inode)
+{
 	call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 

fs/ceph/super.c

@@ -830,6 +830,7 @@ static const struct super_operations ceph_super_ops = {
 	.destroy_inode	= ceph_destroy_inode,
 	.write_inode    = ceph_write_inode,
 	.drop_inode	= ceph_drop_inode,
+	.evict_inode	= ceph_evict_inode,
 	.sync_fs        = ceph_sync_fs,
 	.put_super	= ceph_put_super,
 	.remount_fs	= ceph_remount,

fs/ceph/super.h

@@ -858,6 +858,7 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
 extern const struct inode_operations ceph_file_iops;
 
 extern struct inode *ceph_alloc_inode(struct super_block *sb);
+extern void ceph_evict_inode(struct inode *inode);
 extern void ceph_destroy_inode(struct inode *inode);
 extern int ceph_drop_inode(struct inode *inode);
 

include/linux/memremap.h

@@ -22,6 +22,9 @@ struct vmem_altmap {
 	unsigned long free;
 	unsigned long align;
 	unsigned long alloc;
+#ifndef __GENKSYMS__
+	const unsigned long end_pfn;
+#endif
 };
 
 /*

include/linux/pci_ids.h

@@ -2551,6 +2551,8 @@
 
 #define PCI_VENDOR_ID_ASMEDIA		0x1b21
 
+#define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS	0x1c36
+
 #define PCI_VENDOR_ID_CIRCUITCO		0x1cc8
 #define PCI_SUBSYSTEM_ID_CIRCUITCO_MINNOWBOARD	0x0001