4.19.7-stable review

index deed97fba979..ef573d719eb4 100644
@@ -2322,7 +2322,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	}
 }
 
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;

@@ -2337,7 +2337,7 @@ static void freeze_page(struct page *page)
 	VM_BUG_ON_PAGE(!unmap_success, page);
 }
 
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
 {
 	int i;
 	if (PageTransHuge(page)) {

@@ -2454,7 +2454,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
-	unfreeze_page(head);
+	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		struct page *subpage = head + i;

@@ -2635,7 +2635,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	/*
-	 * Racy check if we can split the page, before freeze_page() will
+	 * Racy check if we can split the page, before unmap_page() will
 	 * split PMDs
 	 */
 	if (!can_split_huge_page(head, &extra_pins)) {

@@ -2644,7 +2644,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	mlocked = PageMlocked(page);
-	freeze_page(head);
+	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */

@@ -2701,7 +2701,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 fail:		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
-		unfreeze_page(head);
+		remap_page(head);
 		ret = -EBUSY;
 	}
 

index 1e79fac3186b..85b7f9423352 100644
@@ -1627,16 +1627,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 						      address + PAGE_SIZE);
 		} else {
 			/*
-			 * We should not need to notify here as we reach this
-			 * case only from freeze_page() itself only call from
-			 * split_huge_page_to_list() so everything below must
-			 * be true:
-			 *   - page is not anonymous
-			 *   - page is locked
-			 *
-			 * So as it is a locked file back page thus it can not
-			 * be remove from the page cache and replace by a new
-			 * page before mmu_notifier_invalidate_range_end so no
+			 * This is a locked file-backed page, thus it cannot
+			 * be removed from the page cache and replaced by a new
+			 * page before mmu_notifier_invalidate_range_end, so no
 			 * concurrent thread might update its page table to
 			 * point at new page while a device still is using this
 			 * page.

index ef573d719eb4..c12b441a99f9 100644
@@ -2373,6 +2373,12 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
+	/* ->mapping in first tail page is compound_mapcount */
+	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+			page_tail);
+	page_tail->mapping = head->mapping;
+	page_tail->index = head->index + tail;
+
 	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 

@@ -2393,12 +2399,6 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	if (page_is_idle(head))
 		set_page_idle(page_tail);
 
-	/* ->mapping in first tail page is compound_mapcount */
-	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
-			page_tail);
-	page_tail->mapping = head->mapping;
-
-	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
 
 	/*

index c12b441a99f9..15310f14c25e 100644
@@ -2410,12 +2410,11 @@ static void __split_huge_page_tail(struct page *head, int tail,
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		unsigned long flags)
+		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	pgoff_t end = -1;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);

@@ -2423,9 +2422,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	if (!PageAnon(page))
-		end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */

@@ -2597,6 +2593,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	int count, mapcount, extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
+	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);

@@ -2619,6 +2616,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			ret = -EBUSY;
 			goto out;
 		}
+		end = -1;
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {

@@ -2632,6 +2630,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 		anon_vma = NULL;
 		i_mmap_lock_read(mapping);
+
+		/*
+		 *__split_huge_page() may need to trim off pages beyond EOF:
+		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+		 * which cannot be nested inside the page tree lock. So note
+		 * end now: i_size itself may be changed at any moment, but
+		 * head page lock is good enough to serialize the trimming.
+		 */
+		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
 	}
 
 	/*

@@ -2681,7 +2688,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (mapping)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
-		__split_huge_page(page, list, flags);
+		__split_huge_page(page, list, end, flags);
 		if (PageSwapCache(head)) {
 			swp_entry_t entry = { .val = page_private(head) };
 

index a31d740e6cd1..0378f758b065 100644
@@ -1349,6 +1349,16 @@ static void collapse_shmem(struct mm_struct *mm,
 	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
 		int n = min(iter.index, end) - index;
 
+		/*
+		 * Stop if extent has been hole-punched, and is now completely
+		 * empty (the more obvious i_size_read() check would take an
+		 * irq-unsafe seqlock on 32-bit).
+		 */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
+
 		/*
 		 * Handle holes in the radix tree: charge it from shmem and
 		 * insert relevant subpage of new_page into the radix-tree.

@@ -1459,6 +1469,11 @@ static void collapse_shmem(struct mm_struct *mm,
 	if (result == SCAN_SUCCEED && index < end) {
 		int n = end - index;
 
+		/* Stop if extent has been truncated, and is now empty */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
 		if (!shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
 			goto tree_locked;

index 0378f758b065..87dbb0fcfa1a 100644
@@ -1537,8 +1537,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		khugepaged_pages_collapsed++;
 	} else {
 		/* Something went wrong: rollback changes to the radix-tree */
-		shmem_uncharge(mapping->host, nr_none);
 		xa_lock_irq(&mapping->i_pages);
+		mapping->nrpages -= nr_none;
+		shmem_uncharge(mapping->host, nr_none);
+
 		radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
 			if (iter.index >= end)
 				break;

index 38d228a30fdc..cd6b4bc221eb 100644
@@ -297,12 +297,14 @@ bool shmem_charge(struct inode *inode, long pages)
 	if (!shmem_inode_acct_block(inode, pages))
 		return false;
 
+	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+	inode->i_mapping->nrpages += pages;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
-	inode->i_mapping->nrpages += pages;
 
 	return true;
 }

@@ -312,6 +314,8 @@ void shmem_uncharge(struct inode *inode, long pages)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long flags;
 
+	/* nrpages adjustment done by __delete_from_page_cache() or caller */
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced -= pages;
 	inode->i_blocks -= pages * BLOCKS_PER_PAGE;

index 87dbb0fcfa1a..068868763b78 100644
@@ -1498,7 +1498,12 @@ static void collapse_shmem(struct mm_struct *mm,
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.
 		 */
+		index = start;
 		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+			while (index < page->index) {
+				clear_highpage(new_page + (index % HPAGE_PMD_NR));
+				index++;
+			}
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);

@@ -1508,6 +1513,11 @@ static void collapse_shmem(struct mm_struct *mm,
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
 			put_page(page);
+			index++;
+		}
+		while (index < end) {
+			clear_highpage(new_page + (index % HPAGE_PMD_NR));
+			index++;
 		}
 
 		local_irq_save(flags);

index 068868763b78..d0a347e6fd08 100644
@@ -1330,13 +1330,12 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
+	__SetPageLocked(new_page);
+	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	__SetPageSwapBacked(new_page);
-	__SetPageLocked(new_page);
 	BUG_ON(!page_ref_freeze(new_page, 1));
 
-
 	/*
 	 * At this point the new_page is 'frozen' (page_count() is zero), locked
 	 * and not up-to-date. It's safe to insert it into radix tree, because

@@ -1365,13 +1364,13 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (n && !shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
-			break;
+			goto tree_locked;
 		}
-		nr_none += n;
 		for (; index < min(iter.index, end); index++) {
 			radix_tree_insert(&mapping->i_pages, index,
 					new_page + (index % HPAGE_PMD_NR));
 		}
+		nr_none += n;
 
 		/* We are done. */
 		if (index >= end)

@@ -1387,12 +1386,12 @@ static void collapse_shmem(struct mm_struct *mm,
 				result = SCAN_FAIL;
 				goto tree_unlocked;
 			}
-			xa_lock_irq(&mapping->i_pages);
 		} else if (trylock_page(page)) {
 			get_page(page);
+			xa_unlock_irq(&mapping->i_pages);
 		} else {
 			result = SCAN_PAGE_LOCK;
-			break;
+			goto tree_locked;
 		}
 
 		/*

@@ -1407,11 +1406,10 @@ static void collapse_shmem(struct mm_struct *mm,
 			result = SCAN_TRUNCATED;
 			goto out_unlock;
 		}
-		xa_unlock_irq(&mapping->i_pages);
 
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
-			goto out_isolate_failed;
+			goto out_unlock;
 		}
 
 		if (page_mapped(page))

@@ -1432,7 +1430,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (!page_ref_freeze(page, 3)) {
 			result = SCAN_PAGE_COUNT;
-			goto out_lru;
+			xa_unlock_irq(&mapping->i_pages);
+			putback_lru_page(page);
+			goto out_unlock;
 		}
 
 		/*

@@ -1448,17 +1448,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		slot = radix_tree_iter_resume(slot, &iter);
 		index++;
 		continue;
-out_lru:
-		xa_unlock_irq(&mapping->i_pages);
-		putback_lru_page(page);
-out_isolate_failed:
-		unlock_page(page);
-		put_page(page);
-		goto tree_unlocked;
 out_unlock:
 		unlock_page(page);
 		put_page(page);
-		break;
+		goto tree_unlocked;
 	}
 
 	/*

@@ -1466,7 +1459,7 @@ static void collapse_shmem(struct mm_struct *mm,
 	 * This code only triggers if there's nothing in radix tree
 	 * beyond 'end'.
 	 */
-	if (result == SCAN_SUCCEED && index < end) {
+	if (index < end) {
 		int n = end - index;
 
 		/* Stop if extent has been truncated, and is now empty */

@@ -1478,7 +1471,6 @@ static void collapse_shmem(struct mm_struct *mm,
 			result = SCAN_FAIL;
 			goto tree_locked;
 		}
-
 		for (; index < end; index++) {
 			radix_tree_insert(&mapping->i_pages, index,
 					new_page + (index % HPAGE_PMD_NR));

@@ -1486,14 +1478,19 @@ static void collapse_shmem(struct mm_struct *mm,
 		nr_none += n;
 	}
 
+	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (nr_none) {
+		struct zone *zone = page_zone(new_page);
+
+		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+	}
+
 tree_locked:
 	xa_unlock_irq(&mapping->i_pages);
 tree_unlocked:
 
 	if (result == SCAN_SUCCEED) {
-		unsigned long flags;
-		struct zone *zone = page_zone(new_page);
-
 		/*
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.

@@ -1507,11 +1504,11 @@ static void collapse_shmem(struct mm_struct *mm,
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);
-			unlock_page(page);
-			page_ref_unfreeze(page, 1);
 			page->mapping = NULL;
+			page_ref_unfreeze(page, 1);
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
+			unlock_page(page);
 			put_page(page);
 			index++;
 		}

@@ -1520,28 +1517,17 @@ static void collapse_shmem(struct mm_struct *mm,
 			index++;
 		}
 
-		local_irq_save(flags);
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
-		if (nr_none) {
-			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
-		}
-		local_irq_restore(flags);
-
-		/*
-		 * Remove pte page tables, so we can re-faulti
-		 * the page as huge.
-		 */
-		retract_page_tables(mapping, start);
-
 		/* Everything is ready, let's unfreeze the new_page */
-		set_page_dirty(new_page);
 		SetPageUptodate(new_page);
 		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);
-		unlock_page(new_page);
 
+		/*
+		 * Remove pte page tables, so we can re-fault the page as huge.
+		 */
+		retract_page_tables(mapping, start);
 		*hpage = NULL;
 
 		khugepaged_pages_collapsed++;

@@ -1573,8 +1559,8 @@ static void collapse_shmem(struct mm_struct *mm,
 			radix_tree_replace_slot(&mapping->i_pages, slot, page);
 			slot = radix_tree_iter_resume(slot, &iter);
 			xa_unlock_irq(&mapping->i_pages);
-			putback_lru_page(page);
 			unlock_page(page);
+			putback_lru_page(page);
 			xa_lock_irq(&mapping->i_pages);
 		}
 		VM_BUG_ON(nr_none);

@@ -1583,9 +1569,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		/* Unfreeze new_page, caller would take care about freeing it */
 		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
-		unlock_page(new_page);
 		new_page->mapping = NULL;
 	}
+
+	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
 	/* TODO: tracepoints */

index d0a347e6fd08..e2b13c04626e 100644
@@ -1287,7 +1287,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
- *  - allocate and freeze a new huge page;
+ *  - allocate and lock a new huge page;
  *  - scan over radix tree replacing old pages the new one
  *    + swap in pages if necessary;
  *    + fill in gaps;

@@ -1295,11 +1295,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *  - if replacing succeed:
  *    + copy data over;
  *    + free old pages;
- *    + unfreeze huge page;
+ *    + unlock huge page;
  *  - if replacing failed;
  *    + put all pages back and unfreeze them;
  *    + restore gaps in the radix-tree;
- *    + free huge page;
+ *    + unlock and free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
 		struct address_space *mapping, pgoff_t start,

@@ -1334,13 +1334,11 @@ static void collapse_shmem(struct mm_struct *mm,
 	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	BUG_ON(!page_ref_freeze(new_page, 1));
 
 	/*
-	 * At this point the new_page is 'frozen' (page_count() is zero), locked
-	 * and not up-to-date. It's safe to insert it into radix tree, because
-	 * nobody would be able to map it or use it in other way until we
-	 * unfreeze it.
+	 * At this point the new_page is locked and not up-to-date.
+	 * It's safe to insert it into the page cache, because nobody would
+	 * be able to map it or use it in another way until we unlock it.
 	 */
 
 	index = start;

@@ -1517,9 +1515,8 @@ static void collapse_shmem(struct mm_struct *mm,
 			index++;
 		}
 
-		/* Everything is ready, let's unfreeze the new_page */
 		SetPageUptodate(new_page);
-		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		page_ref_add(new_page, HPAGE_PMD_NR - 1);
 		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);

@@ -1566,8 +1563,6 @@ static void collapse_shmem(struct mm_struct *mm,
 		VM_BUG_ON(nr_none);
 		xa_unlock_irq(&mapping->i_pages);
 
-		/* Unfreeze new_page, caller would take care about freeing it */
-		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
 		new_page->mapping = NULL;
 	}

index e2b13c04626e..fde5820be24d 100644
@@ -1398,7 +1398,15 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(!PageUptodate(page), page);
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		/*
+		 * If file was truncated then extended, or hole-punched, before
+		 * we locked the first page, then a THP might be there already.
+		 */
+		if (PageTransCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unlock;
+		}
 
 		if (page_mapping(page) != mapping) {
 			result = SCAN_TRUNCATED;

@@ -3020,6 +3020,7 @@ static const struct dev_pm_ops lan743x_p
 
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) },
 	{ 0, }
 };
 

@@ -548,6 +548,7 @@ struct lan743x_adapter;
 /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */
 #define PCI_VENDOR_ID_SMSC		PCI_VENDOR_ID_EFAR
 #define PCI_DEVICE_ID_SMSC_LAN7430	(0x7430)
+#define PCI_DEVICE_ID_SMSC_LAN7431	(0x7431)
 
 #define PCI_CONFIG_LENGTH		(0x1000)
 

@@ -5945,11 +5945,14 @@ bool napi_complete_done(struct napi_stru
 		if (work_done)
 			timeout = n->dev->gro_flush_timeout;
 
+		/* When the NAPI instance uses a timeout and keeps postponing
+		 * it, we need to bound somehow the time packets are kept in
+		 * the GRO layer
+		 */
+		napi_gro_flush(n, !!timeout);
 		if (timeout)
 			hrtimer_start(&n->timer, ns_to_ktime(timeout),
 				      HRTIMER_MODE_REL_PINNED);
-		else
-			napi_gro_flush(n, false);
 	}
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */

@@ -585,10 +585,12 @@ static void nicvf_free_snd_queue(struct
 	if (!sq->dmem.base)
 		return;
 
-	if (sq->tso_hdrs)
+	if (sq->tso_hdrs) {
 		dma_free_coherent(&nic->pdev->dev,
 				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
+		sq->tso_hdrs = NULL;
+	}
 
 	/* Free pending skbs in the queue */
 	smp_rmb();

@@ -1311,6 +1311,22 @@ static inline void skb_zcopy_set(struct
 	}
 }
 
+static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
+{
+	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
+	skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+}
+
+static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
+{
+	return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
+}
+
+static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
+{
+	return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
+}
+
 /* Release a reference on a zerocopy structure */
 static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 {

@@ -1320,7 +1336,7 @@ static inline void skb_zcopy_clear(struc
 		if (uarg->callback == sock_zerocopy_callback) {
 			uarg->zerocopy = uarg->zerocopy && zerocopy;
 			sock_zerocopy_put(uarg);
-		} else {
+		} else if (!skb_zcopy_is_nouarg(skb)) {
 			uarg->callback(uarg, zerocopy);
 		}
 

@@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct
 		void *ph;
 		__u32 ts;
 
-		ph = skb_shinfo(skb)->destructor_arg;
+		ph = skb_zcopy_get_nouarg(skb);
 		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);

@@ -2461,7 +2461,7 @@ static int tpacket_fill_skb(struct packe
 	skb->mark = po->sk.sk_mark;
 	skb->tstamp = sockc->transmit_time;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
-	skb_shinfo(skb)->destructor_arg = ph.raw;
+	skb_zcopy_set_nouarg(skb, ph.raw);
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);

@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_b
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 

@@ -4912,6 +4912,11 @@ void skb_scrub_packet(struct sk_buff *sk
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+	skb->offload_mr_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 

@@ -70,7 +70,8 @@ static const unsigned long guest_offload
 	VIRTIO_NET_F_GUEST_TSO4,
 	VIRTIO_NET_F_GUEST_TSO6,
 	VIRTIO_NET_F_GUEST_ECN,
-	VIRTIO_NET_F_GUEST_UFO
+	VIRTIO_NET_F_GUEST_UFO,
+	VIRTIO_NET_F_GUEST_CSUM
 };
 
 struct virtnet_stat_desc {

@@ -2285,9 +2286,6 @@ static int virtnet_clear_guest_offloads(
 	if (!vi->guest_offloads)
 		return 0;
 
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads = 1ULL << VIRTIO_NET_F_GUEST_CSUM;
-
 	return virtnet_set_guest_offloads(vi, offloads);
 }
 

@@ -2297,8 +2295,6 @@ static int virtnet_restore_guest_offload
 
 	if (!vi->guest_offloads)
 		return 0;
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads |= 1ULL << VIRTIO_NET_F_GUEST_CSUM;
 
 	return virtnet_set_guest_offloads(vi, offloads);
 }

@@ -1930,6 +1930,14 @@ int phy_driver_register(struct phy_drive
 	new_driver->mdiodrv.driver.remove = phy_remove;
 	new_driver->mdiodrv.driver.owner = owner;
 
+	/* The following works around an issue where the PHY driver doesn't bind
+	 * to the device, resulting in the genphy driver being used instead of
+	 * the dedicated driver. The root cause of the issue isn't known yet
+	 * and seems to be in the base driver core. Once this is fixed we may
+	 * remove this workaround.
+	 */
+	new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
+
 	retval = driver_register(&new_driver->mdiodrv.driver);
 	if (retval) {
 		pr_err("%s: Error %d in registering driver\n",

@@ -584,12 +584,15 @@ static void  tipc_node_clear_links(struc
 /* tipc_node_cleanup - delete nodes that does not
  * have active links for NODE_CLEANUP_AFTER time
  */
-static int tipc_node_cleanup(struct tipc_node *peer)
+static bool tipc_node_cleanup(struct tipc_node *peer)
 {
 	struct tipc_net *tn = tipc_net(peer->net);
 	bool deleted = false;
 
-	spin_lock_bh(&tn->node_list_lock);
+	/* If lock held by tipc_node_stop() the node will be deleted anyway */
+	if (!spin_trylock_bh(&tn->node_list_lock))
+		return false;
+
 	tipc_node_write_lock(peer);
 
 	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {

@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/ptrace.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>

@@ -180,6 +181,19 @@ static void sync_current_stack_to_mm(str
 	}
 }
 
+static bool ibpb_needed(struct task_struct *tsk, u64 last_ctx_id)
+{
+	/*
+	 * Check if the current (previous) task has access to the memory
+	 * of the @tsk (next) task. If access is denied, make sure to
+	 * issue a IBPB to stop user->user Spectre-v2 attacks.
+	 *
+	 * Note: __ptrace_may_access() returns 0 or -ERRNO.
+	 */
+	return (tsk && tsk->mm && tsk->mm->context.ctx_id != last_ctx_id &&
+		ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB));
+}
+
 void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {

@@ -262,18 +276,13 @@ void switch_mm_irqs_off(struct mm_struct
 		 * one process from doing Spectre-v2 attacks on another.
 		 *
 		 * As an optimization, flush indirect branches only when
-		 * switching into processes that disable dumping. This
-		 * protects high value processes like gpg, without having
-		 * too high performance overhead. IBPB is *expensive*!
-		 *
-		 * This will not flush branches when switching into kernel
-		 * threads. It will also not flush if we switch to idle
-		 * thread and back to the same process. It will flush if we
-		 * switch to a different non-dumpable process.
+		 * switching into a processes that can't be ptrace by the
+		 * current one (as in such case, attacker has much more
+		 * convenient way how to tamper with the next process than
+		 * branch buffer poisoning).
 		 */
-		if (tsk && tsk->mm &&
-		    tsk->mm->context.ctx_id != last_ctx_id &&
-		    get_dumpable(tsk->mm) != SUID_DUMP_USER)
+		if (static_cpu_has(X86_FEATURE_USE_IBPB) &&
+				ibpb_needed(tsk, last_ctx_id))
 			indirect_branch_prediction_barrier();
 
 		if (IS_ENABLED(CONFIG_VMAP_STACK)) {

@@ -62,14 +62,17 @@ extern void exit_ptrace(struct task_stru
 #define PTRACE_MODE_READ	0x01
 #define PTRACE_MODE_ATTACH	0x02
 #define PTRACE_MODE_NOAUDIT	0x04
-#define PTRACE_MODE_FSCREDS 0x08
-#define PTRACE_MODE_REALCREDS 0x10
+#define PTRACE_MODE_FSCREDS	0x08
+#define PTRACE_MODE_REALCREDS	0x10
+#define PTRACE_MODE_SCHED	0x20
+#define PTRACE_MODE_IBPB	0x40
 
 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */
 #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS)
 #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS)
+#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB)
 
 /**
  * ptrace_may_access - check whether the caller is permitted to access

@@ -87,6 +90,20 @@ extern void exit_ptrace(struct task_stru
  */
 extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
+/**
+ * ptrace_may_access - check whether the caller is permitted to access
+ * a target task.
+ * @task: target task
+ * @mode: selects type of access and caller credentials
+ *
+ * Returns true on success, false on denial.
+ *
+ * Similar to ptrace_may_access(). Only to be called from context switch
+ * code. Does not call into audit and the regular LSM hooks due to locking
+ * constraints.
+ */
+extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode);
+
 static inline int ptrace_reparented(struct task_struct *child)
 {
 	return !same_thread_group(child->real_parent, child->parent);

@@ -261,6 +261,9 @@ static int ptrace_check_attach(struct ta
 
 static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 {
+	if (mode & PTRACE_MODE_SCHED)
+		return false;
+
 	if (mode & PTRACE_MODE_NOAUDIT)
 		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
 	else

@@ -328,9 +331,16 @@ ok:
 	     !ptrace_has_cap(mm->user_ns, mode)))
 	    return -EPERM;
 
+	if (mode & PTRACE_MODE_SCHED)
+		return 0;
 	return security_ptrace_access_check(task, mode);
 }
 
+bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode)
+{
+	return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED);
+}
+
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	int err;

@@ -162,11 +162,12 @@
 	_ASM_PTR " 999b\n\t"					\
 	".popsection\n\t"
 
-#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_64
 
 /*
- * Since the inline asm uses the %V modifier which is only in newer GCC,
- * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ * Inline asm uses the %V modifier which is only in newer GCC
+ * which is ensured when CONFIG_RETPOLINE is defined.
  */
 # define CALL_NOSPEC						\
 	ANNOTATE_NOSPEC_ALTERNATIVE				\

@@ -181,7 +182,7 @@
 	X86_FEATURE_RETPOLINE_AMD)
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
-#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+#else /* CONFIG_X86_32 */
 /*
  * For i386 we use the original ret-equivalent retpoline, because
  * otherwise we'll run out of registers. We don't care about CET

@@ -211,6 +212,7 @@
 	X86_FEATURE_RETPOLINE_AMD)
 
 # define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
 #else /* No retpoline for C / inline asm */
 # define CALL_NOSPEC "call *%[thunk_target]\n"
 # define THUNK_TARGET(addr) [thunk_target] "rm" (addr)

@@ -252,7 +252,7 @@ static void __init spec2_print_if_secure
 
 static inline bool retp_compiler(void)
 {
-	return __is_defined(RETPOLINE);
+	return __is_defined(CONFIG_RETPOLINE);
 }
 
 static inline bool match_option(const char *arg, int arglen, const char *opt)

@@ -842,6 +842,22 @@ static ssize_t l1tf_show_state(char *buf
 }
 #endif
 
+static char *stibp_state(void)
+{
+	if (x86_spec_ctrl_base & SPEC_CTRL_STIBP)
+		return ", STIBP";
+	else
+		return "";
+}
+
+static char *ibpb_state(void)
+{
+	if (boot_cpu_has(X86_FEATURE_USE_IBPB))
+		return ", IBPB";
+	else
+		return "";
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {

@@ -863,9 +879,9 @@ static ssize_t cpu_show_common(struct de
 
 	case X86_BUG_SPECTRE_V2:
 		return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-			       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+			       ibpb_state(),
 			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-			       (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "",
+			       stibp_state(),
 			       boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
 			       spectre_v2_module_string());
 

@@ -320,6 +320,10 @@ static bool stibp_needed(void)
 	if (spectre_v2_enabled == SPECTRE_V2_NONE)
 		return false;
 
+	/* Enhanced IBRS makes using STIBP unnecessary. */
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return false;
+
 	if (!boot_cpu_has(X86_FEATURE_STIBP))
 		return false;
 

@@ -844,6 +848,9 @@ static ssize_t l1tf_show_state(char *buf
 
 static char *stibp_state(void)
 {
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return "";
+
 	if (x86_spec_ctrl_base & SPEC_CTRL_STIBP)
 		return ", STIBP";
 	else

@@ -5741,15 +5741,10 @@ int sched_cpu_activate(unsigned int cpu)
 
 #ifdef CONFIG_SCHED_SMT
 	/*
-	 * The sched_smt_present static key needs to be evaluated on every
-	 * hotplug event because at boot time SMT might be disabled when
-	 * the number of booted CPUs is limited.
-	 *
-	 * If then later a sibling gets hotplugged, then the key would stay
-	 * off and SMT scheduling would never be functional.
+	 * When going up, increment the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
-		static_branch_enable_cpuslocked(&sched_smt_present);
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_inc_cpuslocked(&sched_smt_present);
 #endif
 	set_cpu_active(cpu, true);
 

@@ -5793,6 +5788,14 @@ int sched_cpu_deactivate(unsigned int cp
 	 */
 	synchronize_rcu_mult(call_rcu, call_rcu_sched);
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * When going down, decrement the number of cores with SMT present.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+
 	if (!sched_smp_initialized)
 		return 0;
 

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_SMT_H
+#define _LINUX_SCHED_SMT_H
+
+#include <linux/static_key.h>
+
+#ifdef CONFIG_SCHED_SMT
+extern struct static_key_false sched_smt_present;
+
+static __always_inline bool sched_smt_active(void)
+{
+	return static_branch_likely(&sched_smt_present);
+}
+#else
+static inline bool sched_smt_active(void) { return false; }
+#endif
+
+#endif

@@ -23,6 +23,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/smt.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/task.h>

@@ -930,9 +931,6 @@ static inline int cpu_of(struct rq *rq)
 
 
 #ifdef CONFIG_SCHED_SMT
-
-extern struct static_key_false sched_smt_present;
-
 extern void __update_idle_core(struct rq *rq);
 
 static inline void update_idle_core(struct rq *rq)

@@ -124,29 +124,6 @@ void __init check_bugs(void)
 #endif
 }
 
-/* The kernel command line selection */
-enum spectre_v2_mitigation_cmd {
-	SPECTRE_V2_CMD_NONE,
-	SPECTRE_V2_CMD_AUTO,
-	SPECTRE_V2_CMD_FORCE,
-	SPECTRE_V2_CMD_RETPOLINE,
-	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
-	SPECTRE_V2_CMD_RETPOLINE_AMD,
-};
-
-static const char *spectre_v2_strings[] = {
-	[SPECTRE_V2_NONE]			= "Vulnerable",
-	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
-	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
-	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
-};
-
-#undef pr_fmt
-#define pr_fmt(fmt)     "Spectre V2 : " fmt
-
-static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
-	SPECTRE_V2_NONE;
-
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {

@@ -216,6 +193,12 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+	SPECTRE_V2_NONE;
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 

@@ -237,18 +220,6 @@ static inline const char *spectre_v2_mod
 static inline const char *spectre_v2_module_string(void) { return ""; }
 #endif
 
-static void __init spec2_print_if_insecure(const char *reason)
-{
-	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s selected on command line.\n", reason);
-}
-
-static void __init spec2_print_if_secure(const char *reason)
-{
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s selected on command line.\n", reason);
-}
-
 static inline bool match_option(const char *arg, int arglen, const char *opt)
 {
 	int len = strlen(opt);

@@ -256,24 +227,53 @@ static inline bool match_option(const ch
 	return len == arglen && !strncmp(arg, opt, len);
 }
 
+/* The kernel command line selection for spectre v2 */
+enum spectre_v2_mitigation_cmd {
+	SPECTRE_V2_CMD_NONE,
+	SPECTRE_V2_CMD_AUTO,
+	SPECTRE_V2_CMD_FORCE,
+	SPECTRE_V2_CMD_RETPOLINE,
+	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+	SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+	[SPECTRE_V2_NONE]			= "Vulnerable",
+	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
+	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
+};
+
 static const struct {
 	const char *option;
 	enum spectre_v2_mitigation_cmd cmd;
 	bool secure;
 } mitigation_options[] = {
-	{ "off",               SPECTRE_V2_CMD_NONE,              false },
-	{ "on",                SPECTRE_V2_CMD_FORCE,             true },
-	{ "retpoline",         SPECTRE_V2_CMD_RETPOLINE,         false },
-	{ "retpoline,amd",     SPECTRE_V2_CMD_RETPOLINE_AMD,     false },
-	{ "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
-	{ "auto",              SPECTRE_V2_CMD_AUTO,              false },
+	{ "off",		SPECTRE_V2_CMD_NONE,		  false },
+	{ "on",			SPECTRE_V2_CMD_FORCE,		  true  },
+	{ "retpoline",		SPECTRE_V2_CMD_RETPOLINE,	  false },
+	{ "retpoline,amd",	SPECTRE_V2_CMD_RETPOLINE_AMD,	  false },
+	{ "retpoline,generic",	SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
+	{ "auto",		SPECTRE_V2_CMD_AUTO,		  false },
 };
 
+static void __init spec2_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s selected on command line.\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s selected on command line.\n", reason);
+}
+
 static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 {
+	enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
 	char arg[20];
 	int ret, i;
-	enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
 
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;

@@ -316,48 +316,6 @@ static enum spectre_v2_mitigation_cmd __
 	return cmd;
 }
 
-static bool stibp_needed(void)
-{
-	if (spectre_v2_enabled == SPECTRE_V2_NONE)
-		return false;
-
-	/* Enhanced IBRS makes using STIBP unnecessary. */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
-		return false;
-
-	if (!boot_cpu_has(X86_FEATURE_STIBP))
-		return false;
-
-	return true;
-}
-
-static void update_stibp_msr(void *info)
-{
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
-}
-
-void arch_smt_update(void)
-{
-	u64 mask;
-
-	if (!stibp_needed())
-		return;
-
-	mutex_lock(&spec_ctrl_mutex);
-
-	mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP;
-	if (sched_smt_active())
-		mask |= SPEC_CTRL_STIBP;
-
-	if (mask != x86_spec_ctrl_base) {
-		pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
-			mask & SPEC_CTRL_STIBP ? "Enabling" : "Disabling");
-		x86_spec_ctrl_base = mask;
-		on_each_cpu(update_stibp_msr, NULL, 1);
-	}
-	mutex_unlock(&spec_ctrl_mutex);
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();

@@ -460,6 +418,48 @@ specv2_set_mode:
 	arch_smt_update();
 }
 
+static bool stibp_needed(void)
+{
+	if (spectre_v2_enabled == SPECTRE_V2_NONE)
+		return false;
+
+	/* Enhanced IBRS makes using STIBP unnecessary. */
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return false;
+
+	if (!boot_cpu_has(X86_FEATURE_STIBP))
+		return false;
+
+	return true;
+}
+
+static void update_stibp_msr(void *info)
+{
+	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+}
+
+void arch_smt_update(void)
+{
+	u64 mask;
+
+	if (!stibp_needed())
+		return;
+
+	mutex_lock(&spec_ctrl_mutex);
+
+	mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP;
+	if (sched_smt_active())
+		mask |= SPEC_CTRL_STIBP;
+
+	if (mask != x86_spec_ctrl_base) {
+		pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
+			mask & SPEC_CTRL_STIBP ? "Enabling" : "Disabling");
+		x86_spec_ctrl_base = mask;
+		on_each_cpu(update_stibp_msr, NULL, 1);
+	}
+	mutex_unlock(&spec_ctrl_mutex);
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
 

@@ -237,7 +237,7 @@ enum spectre_v2_mitigation_cmd {
 	SPECTRE_V2_CMD_RETPOLINE_AMD,
 };
 
-static const char *spectre_v2_strings[] = {
+static const char * const spectre_v2_strings[] = {
 	[SPECTRE_V2_NONE]			= "Vulnerable",
 	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
 	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",

@@ -474,7 +474,7 @@ enum ssb_mitigation_cmd {
 	SPEC_STORE_BYPASS_CMD_SECCOMP,
 };
 
-static const char *ssb_strings[] = {
+static const char * const ssb_strings[] = {
 	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
 	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled",
 	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl",

@@ -814,7 +814,7 @@ early_param("l1tf", l1tf_cmdline);
 #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
-static const char *l1tf_vmx_states[] = {
+static const char * const l1tf_vmx_states[] = {
 	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
 	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
 	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",

@@ -248,7 +248,7 @@ static const struct {
 	const char *option;
 	enum spectre_v2_mitigation_cmd cmd;
 	bool secure;
-} mitigation_options[] = {
+} mitigation_options[] __initdata = {
 	{ "off",		SPECTRE_V2_CMD_NONE,		  false },
 	{ "on",			SPECTRE_V2_CMD_FORCE,		  true  },
 	{ "retpoline",		SPECTRE_V2_CMD_RETPOLINE,	  false },

@@ -484,7 +484,7 @@ static const char * const ssb_strings[]
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] = {
+} ssb_mitigation_options[]  __initdata = {
 	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
 	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
 	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */

@@ -3,6 +3,8 @@
 #ifndef _ASM_X86_NOSPEC_BRANCH_H_
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
+#include <linux/static_key.h>
+
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>

@@ -226,6 +228,12 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS_ENHANCED,
 };
 
+/* The indirect branch speculation control variants */
+enum spectre_v2_user_mitigation {
+	SPECTRE_V2_USER_NONE,
+	SPECTRE_V2_USER_STRICT,
+};
+
 /* The Speculative Store Bypass disable variants */
 enum ssb_mitigation {
 	SPEC_STORE_BYPASS_NONE,

@@ -303,6 +311,8 @@ do {									\
 	preempt_enable();						\
 } while (0)
 
+DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
+
 #endif /* __ASSEMBLY__ */
 
 /*

179 lines not on this page · raw message

@@ -312,6 +312,8 @@ do {									\
 } while (0)
 
 DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
+DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
+DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 #endif /* __ASSEMBLY__ */
 

@@ -185,10 +185,14 @@ struct tlb_state {
 
 #define LOADED_MM_SWITCHING ((struct mm_struct *)1)
 
+	/* Last user mm for optimizing IBPB */
+	union {
+		struct mm_struct	*last_user_mm;
+		unsigned long		last_user_mm_ibpb;
+	};
+
 	u16 loaded_mm_asid;
 	u16 next_asid;
-	/* last user mm's ctx id */
-	u64 last_ctx_id;
 
 	/*
 	 * We can be in one of several states:

@@ -56,6 +56,10 @@ u64 __ro_after_init x86_amd_ls_cfg_ssbd_
 
 /* Control conditional STIPB in switch_to() */
 DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp);
+/* Control conditional IBPB in switch_mm() */
+DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
+/* Control unconditional IBPB in switch_mm() */
+DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 void __init check_bugs(void)
 {

@@ -331,7 +335,17 @@ spectre_v2_user_select_mitigation(enum s
 	/* Initialize Indirect Branch Prediction Barrier */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
+
+		switch (mode) {
+		case SPECTRE_V2_USER_STRICT:
+			static_branch_enable(&switch_mm_always_ibpb);
+			break;
+		default:
+			break;
+		}
+
+		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
+			mode == SPECTRE_V2_USER_STRICT ? "always-on" : "conditional");
 	}
 
 	/* If enhanced IBRS is enabled no STIPB required */

@@ -953,10 +967,15 @@ static char *stibp_state(void)
 
 static char *ibpb_state(void)
 {
-	if (boot_cpu_has(X86_FEATURE_USE_IBPB))
-		return ", IBPB";
-	else
-		return "";
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		switch (spectre_v2_user) {
+		case SPECTRE_V2_USER_NONE:
+			return ", IBPB: disabled";
+		case SPECTRE_V2_USER_STRICT:
+			return ", IBPB: always-on";
+		}
+	}
+	return "";
 }
 
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,

159 lines not on this page · raw message

@@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_stru
 #define PTRACE_MODE_NOAUDIT	0x04
 #define PTRACE_MODE_FSCREDS	0x08
 #define PTRACE_MODE_REALCREDS	0x10
-#define PTRACE_MODE_SCHED	0x20
-#define PTRACE_MODE_IBPB	0x40
 
 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */
 #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS)
 #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS)
-#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB)
 
 /**
  * ptrace_may_access - check whether the caller is permitted to access

@@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_stru
  */
 extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
-/**
- * ptrace_may_access - check whether the caller is permitted to access
- * a target task.
- * @task: target task
- * @mode: selects type of access and caller credentials
- *
- * Returns true on success, false on denial.
- *
- * Similar to ptrace_may_access(). Only to be called from context switch
- * code. Does not call into audit and the regular LSM hooks due to locking
- * constraints.
- */
-extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode);
-
 static inline int ptrace_reparented(struct task_struct *child)
 {
 	return !same_thread_group(child->real_parent, child->parent);

@@ -261,9 +261,6 @@ static int ptrace_check_attach(struct ta
 
 static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 {
-	if (mode & PTRACE_MODE_SCHED)
-		return false;
-
 	if (mode & PTRACE_MODE_NOAUDIT)
 		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
 	else

@@ -331,16 +328,9 @@ ok:
 	     !ptrace_has_cap(mm->user_ns, mode)))
 	    return -EPERM;
 
-	if (mode & PTRACE_MODE_SCHED)
-		return 0;
 	return security_ptrace_access_check(task, mode);
 }
 
-bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode)
-{
-	return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED);
-}
-
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	int err;

@@ -700,10 +700,29 @@ static void ssb_select_mitigation(void)
 #undef pr_fmt
 #define pr_fmt(fmt)     "Speculation prctl: " fmt
 
-static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+static void task_update_spec_tif(struct task_struct *tsk, int tifbit, bool on)
 {
 	bool update;
 
+	if (on)
+		update = !test_and_set_tsk_thread_flag(tsk, tifbit);
+	else
+		update = test_and_clear_tsk_thread_flag(tsk, tifbit);
+
+	/*
+	 * Immediately update the speculation control MSRs for the current
+	 * task, but for a non-current task delay setting the CPU
+	 * mitigation until it is scheduled next.
+	 *
+	 * This can only happen for SECCOMP mitigation. For PRCTL it's
+	 * always the current task.
+	 */
+	if (tsk == current && update)
+		speculation_ctrl_update_current();
+}
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
 	    ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
 		return -ENXIO;

@@ -714,28 +733,20 @@ static int ssb_prctl_set(struct task_str
 		if (task_spec_ssb_force_disable(task))
 			return -EPERM;
 		task_clear_spec_ssb_disable(task);
-		update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task, TIF_SSBD, false);
 		break;
 	case PR_SPEC_DISABLE:
 		task_set_spec_ssb_disable(task);
-		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task, TIF_SSBD, true);
 		break;
 	case PR_SPEC_FORCE_DISABLE:
 		task_set_spec_ssb_disable(task);
 		task_set_spec_ssb_force_disable(task);
-		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task, TIF_SSBD, true);
 		break;
 	default:
 		return -ERANGE;
 	}
-
-	/*
-	 * If being set on non-current task, delay setting the CPU
-	 * mitigation until it is next scheduled.
-	 */
-	if (task == current && update)
-		speculation_ctrl_update_current();
-
 	return 0;
 }
 

@@ -528,40 +528,44 @@ specv2_set_mode:
 	arch_smt_update();
 }
 
-static bool stibp_needed(void)
+static void update_stibp_msr(void * __unused)
 {
-	/* Enhanced IBRS makes using STIBP unnecessary. */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
-		return false;
-
-	/* Check for strict user mitigation mode */
-	return spectre_v2_user == SPECTRE_V2_USER_STRICT;
+	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 }
 
-static void update_stibp_msr(void *info)
+/* Update x86_spec_ctrl_base in case SMT state changed. */
+static void update_stibp_strict(void)
 {
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+	u64 mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP;
+
+	if (sched_smt_active())
+		mask |= SPEC_CTRL_STIBP;
+
+	if (mask == x86_spec_ctrl_base)
+		return;
+
+	pr_info("Update user space SMT mitigation: STIBP %s\n",
+		mask & SPEC_CTRL_STIBP ? "always-on" : "off");
+	x86_spec_ctrl_base = mask;
+	on_each_cpu(update_stibp_msr, NULL, 1);
 }
 
 void arch_smt_update(void)
 {
-	u64 mask;
-
-	if (!stibp_needed())
+	/* Enhanced IBRS implies STIBP. No update required. */
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return;
 
 	mutex_lock(&spec_ctrl_mutex);
 
-	mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP;
-	if (sched_smt_active())
-		mask |= SPEC_CTRL_STIBP;
-
-	if (mask != x86_spec_ctrl_base) {
-		pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
-			mask & SPEC_CTRL_STIBP ? "Enabling" : "Disabling");
-		x86_spec_ctrl_base = mask;
-		on_each_cpu(update_stibp_msr, NULL, 1);
+	switch (spectre_v2_user) {
+	case SPECTRE_V2_USER_NONE:
+		break;
+	case SPECTRE_V2_USER_STRICT:
+		update_stibp_strict();
+		break;
 	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 

@@ -233,6 +233,7 @@ enum spectre_v2_user_mitigation {
 	SPECTRE_V2_USER_NONE,
 	SPECTRE_V2_USER_STRICT,
 	SPECTRE_V2_USER_PRCTL,
+	SPECTRE_V2_USER_SECCOMP,
 };
 
 /* The Speculative Store Bypass disable variants */

@@ -256,12 +256,14 @@ enum spectre_v2_user_cmd {
 	SPECTRE_V2_USER_CMD_AUTO,
 	SPECTRE_V2_USER_CMD_FORCE,
 	SPECTRE_V2_USER_CMD_PRCTL,
+	SPECTRE_V2_USER_CMD_SECCOMP,
 };
 
 static const char * const spectre_v2_user_strings[] = {
 	[SPECTRE_V2_USER_NONE]		= "User space: Vulnerable",
 	[SPECTRE_V2_USER_STRICT]	= "User space: Mitigation: STIBP protection",
 	[SPECTRE_V2_USER_PRCTL]		= "User space: Mitigation: STIBP via prctl",
+	[SPECTRE_V2_USER_SECCOMP]	= "User space: Mitigation: STIBP via seccomp and prctl",
 };
 
 static const struct {

@@ -273,6 +275,7 @@ static const struct {
 	{ "off",	SPECTRE_V2_USER_CMD_NONE,	false },
 	{ "on",		SPECTRE_V2_USER_CMD_FORCE,	true  },
 	{ "prctl",	SPECTRE_V2_USER_CMD_PRCTL,	false },
+	{ "seccomp",	SPECTRE_V2_USER_CMD_SECCOMP,	false },
 };
 
 static void __init spec_v2_user_print_cond(const char *reason, bool secure)

@@ -332,10 +335,16 @@ spectre_v2_user_select_mitigation(enum s
 	case SPECTRE_V2_USER_CMD_FORCE:
 		mode = SPECTRE_V2_USER_STRICT;
 		break;
-	case SPECTRE_V2_USER_CMD_AUTO:
 	case SPECTRE_V2_USER_CMD_PRCTL:
 		mode = SPECTRE_V2_USER_PRCTL;
 		break;
+	case SPECTRE_V2_USER_CMD_AUTO:
+	case SPECTRE_V2_USER_CMD_SECCOMP:
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			mode = SPECTRE_V2_USER_SECCOMP;
+		else
+			mode = SPECTRE_V2_USER_PRCTL;
+		break;
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier */

@@ -347,6 +356,7 @@ spectre_v2_user_select_mitigation(enum s
 			static_branch_enable(&switch_mm_always_ibpb);
 			break;
 		case SPECTRE_V2_USER_PRCTL:
+		case SPECTRE_V2_USER_SECCOMP:
 			static_branch_enable(&switch_mm_cond_ibpb);
 			break;
 		default:

@@ -589,6 +599,7 @@ void arch_smt_update(void)
 		update_stibp_strict();
 		break;
 	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
 		update_indir_branch_cond();
 		break;
 	}

@@ -831,6 +842,8 @@ void arch_seccomp_spec_mitigate(struct t
 {
 	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
 		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+	if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP)
+		ib_prctl_set(task, PR_SPEC_FORCE_DISABLE);
 }
 #endif
 

@@ -862,6 +875,7 @@ static int ib_prctl_get(struct task_stru
 	case SPECTRE_V2_USER_NONE:
 		return PR_SPEC_ENABLE;
 	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))

@@ -1061,6 +1075,7 @@ static char *stibp_state(void)
 	case SPECTRE_V2_USER_STRICT:
 		return ", STIBP: forced";
 	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
 		if (static_key_enabled(&switch_to_cond_stibp))
 			return ", STIBP: conditional";
 	}

@@ -256,7 +256,9 @@ enum spectre_v2_user_cmd {
 	SPECTRE_V2_USER_CMD_AUTO,
 	SPECTRE_V2_USER_CMD_FORCE,
 	SPECTRE_V2_USER_CMD_PRCTL,
+	SPECTRE_V2_USER_CMD_PRCTL_IBPB,
 	SPECTRE_V2_USER_CMD_SECCOMP,
+	SPECTRE_V2_USER_CMD_SECCOMP_IBPB,
 };
 
 static const char * const spectre_v2_user_strings[] = {

@@ -271,11 +273,13 @@ static const struct {
 	enum spectre_v2_user_cmd	cmd;
 	bool				secure;
 } v2_user_options[] __initdata = {
-	{ "auto",	SPECTRE_V2_USER_CMD_AUTO,	false },
-	{ "off",	SPECTRE_V2_USER_CMD_NONE,	false },
-	{ "on",		SPECTRE_V2_USER_CMD_FORCE,	true  },
-	{ "prctl",	SPECTRE_V2_USER_CMD_PRCTL,	false },
-	{ "seccomp",	SPECTRE_V2_USER_CMD_SECCOMP,	false },
+	{ "auto",		SPECTRE_V2_USER_CMD_AUTO,		false },
+	{ "off",		SPECTRE_V2_USER_CMD_NONE,		false },
+	{ "on",			SPECTRE_V2_USER_CMD_FORCE,		true  },
+	{ "prctl",		SPECTRE_V2_USER_CMD_PRCTL,		false },
+	{ "prctl,ibpb",		SPECTRE_V2_USER_CMD_PRCTL_IBPB,		false },
+	{ "seccomp",		SPECTRE_V2_USER_CMD_SECCOMP,		false },
+	{ "seccomp,ibpb",	SPECTRE_V2_USER_CMD_SECCOMP_IBPB,	false },
 };
 
 static void __init spec_v2_user_print_cond(const char *reason, bool secure)

@@ -321,6 +325,7 @@ spectre_v2_user_select_mitigation(enum s
 {
 	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
 	bool smt_possible = IS_ENABLED(CONFIG_SMP);
+	enum spectre_v2_user_cmd cmd;
 
 	if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
 		return;

@@ -329,17 +334,20 @@ spectre_v2_user_select_mitigation(enum s
 	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
 		smt_possible = false;
 
-	switch (spectre_v2_parse_user_cmdline(v2_cmd)) {
+	cmd = spectre_v2_parse_user_cmdline(v2_cmd);
+	switch (cmd) {
 	case SPECTRE_V2_USER_CMD_NONE:
 		goto set_mode;
 	case SPECTRE_V2_USER_CMD_FORCE:
 		mode = SPECTRE_V2_USER_STRICT;
 		break;
 	case SPECTRE_V2_USER_CMD_PRCTL:
+	case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
 		mode = SPECTRE_V2_USER_PRCTL;
 		break;
 	case SPECTRE_V2_USER_CMD_AUTO:
 	case SPECTRE_V2_USER_CMD_SECCOMP:
+	case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
 		if (IS_ENABLED(CONFIG_SECCOMP))
 			mode = SPECTRE_V2_USER_SECCOMP;
 		else

@@ -351,12 +359,15 @@ spectre_v2_user_select_mitigation(enum s
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 
-		switch (mode) {
-		case SPECTRE_V2_USER_STRICT:
+		switch (cmd) {
+		case SPECTRE_V2_USER_CMD_FORCE:
+		case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
+		case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
 			static_branch_enable(&switch_mm_always_ibpb);
 			break;
-		case SPECTRE_V2_USER_PRCTL:
-		case SPECTRE_V2_USER_SECCOMP:
+		case SPECTRE_V2_USER_CMD_PRCTL:
+		case SPECTRE_V2_USER_CMD_AUTO:
+		case SPECTRE_V2_USER_CMD_SECCOMP:
 			static_branch_enable(&switch_mm_cond_ibpb);
 			break;
 		default:

@@ -364,7 +375,8 @@ spectre_v2_user_select_mitigation(enum s
 		}
 
 		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
-			mode == SPECTRE_V2_USER_STRICT ? "always-on" : "conditional");
+			static_key_enabled(&switch_mm_always_ibpb) ?
+			"always-on" : "conditional");
 	}
 
 	/* If enhanced IBRS is enabled no STIPB required */

@@ -1046,7 +1046,8 @@ struct kvm_x86_ops {
 	bool (*has_wbinvd_exit)(void);
 
 	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
-	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+	/* Returns actual tsc_offset set in active VMCS */
+	u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 

@@ -1444,7 +1444,7 @@ static u64 svm_read_l1_tsc_offset(struct
 	return vcpu->arch.tsc_offset;
 }
 
-static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;

@@ -1462,6 +1462,7 @@ static void svm_write_tsc_offset(struct
 	svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
+	return svm->vmcb->control.tsc_offset;
 }
 
 static void avic_init_vmcb(struct vcpu_svm *svm)

@@ -7155,7 +7156,7 @@ static struct kvm_x86_ops svm_x86_ops __
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
 	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
-	.write_tsc_offset = svm_write_tsc_offset,
+	.write_l1_tsc_offset = svm_write_l1_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
 

@@ -3433,11 +3433,9 @@ static u64 vmx_read_l1_tsc_offset(struct
 	return vcpu->arch.tsc_offset;
 }
 
-/*
- * writes 'offset' into guest's timestamp counter offset register
- */
-static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
+	u64 active_offset = offset;
 	if (is_guest_mode(vcpu)) {
 		/*
 		 * We're here if L1 chose not to trap WRMSR to TSC. According

@@ -3445,17 +3443,16 @@ static void vmx_write_tsc_offset(struct
 		 * set for L2 remains unchanged, and still needs to be added
 		 * to the newly set TSC to get L2's TSC.
 		 */
-		struct vmcs12 *vmcs12;
-		/* recalculate vmcs02.TSC_OFFSET: */
-		vmcs12 = get_vmcs12(vcpu);
-		vmcs_write64(TSC_OFFSET, offset +
-			(nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ?
-			 vmcs12->tsc_offset : 0));
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING))
+			active_offset += vmcs12->tsc_offset;
 	} else {
 		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
 					   vmcs_read64(TSC_OFFSET), offset);
-		vmcs_write64(TSC_OFFSET, offset);
 	}
+
+	vmcs_write64(TSC_OFFSET, active_offset);
+	return active_offset;
 }
 
 /*

@@ -14203,7 +14200,7 @@ static struct kvm_x86_ops vmx_x86_ops __
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
 	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
-	.write_tsc_offset = vmx_write_tsc_offset,
+	.write_l1_tsc_offset = vmx_write_l1_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
 

@@ -1582,8 +1582,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
 static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
-	kvm_x86_ops->write_tsc_offset(vcpu, offset);
-	vcpu->arch.tsc_offset = offset;
+	vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset);
 }
 
 static inline bool kvm_check_tsc_unstable(void)