Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

S390 bpf_jit.S is removed in net-next and had changes in 'net',
since that code isn't used any more take the removal.

TLS data structures split the TX and RX components in 'net-next',
put the new struct members from the bug fix in 'net' into the RX
part.

The 'net-next' tree had some reworking of how the ERSPAN code works in
the GRE tunneling code, overlapping with a one-line headroom
calculation fix in 'net'.

Overlapping changes in __sock_map_ctx_update_elem(), keep the bits
that read the prog members via READ_ONCE() into local variables
before using them.

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 111 insertions, 74 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index d5004d82a1d6d..e14c01513bfd0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -636,6 +636,7 @@ config DEFERRED_STRUCT_PAGE_INIT
 	default n
 	depends on NO_BOOTMEM
 	depends on !FLATMEM
+	depends on !NEED_PER_CPU_KM
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
 	  single thread. On very large machines this can take a considerable
diff --git a/mm/gup.c b/mm/gup.c
index 76af4cfeaf681..541904a7c60fd 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (vm_flags & (VM_IO | VM_PFNMAP))
 		return -EFAULT;
 
+	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+		return -EFAULT;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/migrate.c b/mm/migrate.c
index 568433023831a..8c0af0f7cab18 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -528,14 +528,12 @@ int migrate_page_move_mapping(struct address_space *mapping,
 		int i;
 		int index = page_index(page);
 
-		for (i = 0; i < HPAGE_PMD_NR; i++) {
+		for (i = 1; i < HPAGE_PMD_NR; i++) {
 			pslot = radix_tree_lookup_slot(&mapping->i_pages,
 						       index + i);
 			radix_tree_replace_slot(&mapping->i_pages, pslot,
 						newpage + i);
 		}
-	} else {
-		radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
 	}
 
 	/*
diff --git a/mm/mmap.c b/mm/mmap.c
index 6fc4357600863..fc41c0543d7fa 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1327,7 +1327,7 @@ static inline int mlock_future_check(struct mm_struct *mm,
 static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode))
-		return inode->i_sb->s_maxbytes;
+		return MAX_LFS_FILESIZE;
 
 	if (S_ISBLK(inode->i_mode))
 		return MAX_LFS_FILESIZE;
@@ -3056,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm)
 	/* mm's last user has gone, and its about to be pulled down */
 	mmu_notifier_release(mm);
 
+	if (unlikely(mm_is_oom_victim(mm))) {
+		/*
+		 * Manually reap the mm to free as much memory as possible.
+		 * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
+		 * this mm from further consideration.  Taking mm->mmap_sem for
+		 * write after setting MMF_OOM_SKIP will guarantee that the oom
+		 * reaper will not run on this mm again after mmap_sem is
+		 * dropped.
+		 *
+		 * Nothing can be holding mm->mmap_sem here and the above call
+		 * to mmu_notifier_release(mm) ensures mmu notifier callbacks in
+		 * __oom_reap_task_mm() will not block.
+		 *
+		 * This needs to be done before calling munlock_vma_pages_all(),
+		 * which clears VM_LOCKED, otherwise the oom reaper cannot
+		 * reliably test it.
+		 */
+		mutex_lock(&oom_lock);
+		__oom_reap_task_mm(mm);
+		mutex_unlock(&oom_lock);
+
+		set_bit(MMF_OOM_SKIP, &mm->flags);
+		down_write(&mm->mmap_sem);
+		up_write(&mm->mmap_sem);
+	}
+
 	if (mm->locked_vm) {
 		vma = mm->mmap;
 		while (vma) {
@@ -3077,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm)
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
-
-	if (unlikely(mm_is_oom_victim(mm))) {
-		/*
-		 * Wait for oom_reap_task() to stop working on this
-		 * mm. Because MMF_OOM_SKIP is already set before
-		 * calling down_read(), oom_reap_task() will not run
-		 * on this "mm" post up_write().
-		 *
-		 * mm_is_oom_victim() cannot be set from under us
-		 * either because victim->mm is already set to NULL
-		 * under task_lock before calling mmput and oom_mm is
-		 * set not NULL by the OOM killer only if victim->mm
-		 * is found not NULL while holding the task_lock.
-		 */
-		set_bit(MMF_OOM_SKIP, &mm->flags);
-		down_write(&mm->mmap_sem);
-		up_write(&mm->mmap_sem);
-	}
 	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ff992fa8760aa..8ba6cb88cf58a 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
 	return false;
 }
 
-
 #ifdef CONFIG_MMU
 /*
  * OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
 static struct task_struct *oom_reaper_list;
 static DEFINE_SPINLOCK(oom_reaper_lock);
 
-static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+void __oom_reap_task_mm(struct mm_struct *mm)
 {
-	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
+
+	/*
+	 * Tell all users of get_user/copy_from_user etc... that the content
+	 * is no longer stable. No barriers really needed because unmapping
+	 * should imply barriers already and the reader would hit a page fault
+	 * if it stumbled over a reaped memory.
+	 */
+	set_bit(MMF_UNSTABLE, &mm->flags);
+
+	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+		if (!can_madv_dontneed_vma(vma))
+			continue;
+
+		/*
+		 * Only anonymous pages have a good chance to be dropped
+		 * without additional steps which we cannot afford as we
+		 * are OOM already.
+		 *
+		 * We do not even care about fs backed pages because all
+		 * which are reclaimable have already been reclaimed and
+		 * we do not want to block exit_mmap by keeping mm ref
+		 * count elevated without a good reason.
+		 */
+		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+			const unsigned long start = vma->vm_start;
+			const unsigned long end = vma->vm_end;
+			struct mmu_gather tlb;
+
+			tlb_gather_mmu(&tlb, mm, start, end);
+			mmu_notifier_invalidate_range_start(mm, start, end);
+			unmap_page_range(&tlb, vma, start, end, NULL);
+			mmu_notifier_invalidate_range_end(mm, start, end);
+			tlb_finish_mmu(&tlb, start, end);
+		}
+	}
+}
+
+static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
 	bool ret = true;
 
 	/*
 	 * We have to make sure to not race with the victim exit path
 	 * and cause premature new oom victim selection:
-	 * __oom_reap_task_mm		exit_mm
+	 * oom_reap_task_mm		exit_mm
 	 *   mmget_not_zero
 	 *				  mmput
 	 *				    atomic_dec_and_test
@@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 
 	trace_start_task_reaping(tsk->pid);
 
-	/*
-	 * Tell all users of get_user/copy_from_user etc... that the content
-	 * is no longer stable. No barriers really needed because unmapping
-	 * should imply barriers already and the reader would hit a page fault
-	 * if it stumbled over a reaped memory.
-	 */
-	set_bit(MMF_UNSTABLE, &mm->flags);
-
-	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
-		if (!can_madv_dontneed_vma(vma))
-			continue;
+	__oom_reap_task_mm(mm);
 
-		/*
-		 * Only anonymous pages have a good chance to be dropped
-		 * without additional steps which we cannot afford as we
-		 * are OOM already.
-		 *
-		 * We do not even care about fs backed pages because all
-		 * which are reclaimable have already been reclaimed and
-		 * we do not want to block exit_mmap by keeping mm ref
-		 * count elevated without a good reason.
-		 */
-		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
-			const unsigned long start = vma->vm_start;
-			const unsigned long end = vma->vm_end;
-
-			tlb_gather_mmu(&tlb, mm, start, end);
-			mmu_notifier_invalidate_range_start(mm, start, end);
-			unmap_page_range(&tlb, vma, start, end, NULL);
-			mmu_notifier_invalidate_range_end(mm, start, end);
-			tlb_finish_mmu(&tlb, start, end);
-		}
-	}
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
 			task_pid_nr(tsk), tsk->comm,
 			K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk)
 	struct mm_struct *mm = tsk->signal->oom_mm;
 
 	/* Retry the down_read_trylock(mmap_sem) a few times */
-	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
+	while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
 		schedule_timeout_idle(HZ/10);
 
 	if (attempts <= MAX_OOM_REAP_RETRIES ||
 	    test_bit(MMF_OOM_SKIP, &mm->flags))
 		goto done;
 
-
 	pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
 		task_pid_nr(tsk), tsk->comm);
 	debug_show_all_locks();
diff --git a/mm/sparse.c b/mm/sparse.c
index 62eef264a7bd3..73dc2fcc0eab2 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 	unsigned long pfn;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		unsigned long section_nr = pfn_to_section_nr(start_pfn);
+		unsigned long section_nr = pfn_to_section_nr(pfn);
 		struct mem_section *ms;
 
 		/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 536332e988b87..a2b9518980ce4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = {
 	"nr_vmscan_immediate_reclaim",
 	"nr_dirtied",
 	"nr_written",
-	"nr_indirectly_reclaimable",
+	"", /* nr_indirectly_reclaimable */
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
@@ -1740,6 +1740,10 @@ static int vmstat_show(struct seq_file *m, void *arg)
 	unsigned long *l = arg;
 	unsigned long off = l - (unsigned long *)m->private;
 
+	/* Skip hidden vmstat items. */
+	if (*vmstat_text[off] == '\0')
+		return 0;
+
 	seq_puts(m, vmstat_text[off]);
 	seq_put_decimal_ull(m, " ", *l);
 	seq_putc(m, '\n');
diff --git a/mm/z3fold.c b/mm/z3fold.c
index c0bca6153b95d..4b366d181f35d 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
 	PAGE_HEADLESS = 0,
 	MIDDLE_CHUNK_MAPPED,
 	NEEDS_COMPACTING,
-	PAGE_STALE
+	PAGE_STALE,
+	UNDER_RECLAIM
 };
 
 /*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page,
 	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
 	clear_bit(NEEDS_COMPACTING, &page->private);
 	clear_bit(PAGE_STALE, &page->private);
+	clear_bit(UNDER_RECLAIM, &page->private);
 
 	spin_lock_init(&zhdr->page_lock);
 	kref_init(&zhdr->refcount);
@@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		atomic64_dec(&pool->pages_nr);
 		return;
 	}
+	if (test_bit(UNDER_RECLAIM, &page->private)) {
+		z3fold_page_unlock(zhdr);
+		return;
+	}
 	if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
 		z3fold_page_unlock(zhdr);
 		return;
@@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			kref_get(&zhdr->refcount);
 			list_del_init(&zhdr->buddy);
 			zhdr->cpu = -1;
+			set_bit(UNDER_RECLAIM, &page->private);
+			break;
 		}
 
 		list_del_init(&page->lru);
@@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 				goto next;
 		}
 next:
-		spin_lock(&pool->lock);
 		if (test_bit(PAGE_HEADLESS, &page->private)) {
 			if (ret == 0) {
-				spin_unlock(&pool->lock);
 				free_z3fold_page(page);
 				return 0;
 			}
-		} else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
-			atomic64_dec(&pool->pages_nr);
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
+			spin_unlock(&pool->lock);
+		} else {
+			z3fold_page_lock(zhdr);
+			clear_bit(UNDER_RECLAIM, &page->private);
+			if (kref_put(&zhdr->refcount,
+					release_z3fold_page_locked)) {
+				atomic64_dec(&pool->pages_nr);
+				return 0;
+			}
+			/*
+			 * if we are here, the page is still not completely
+			 * free. Take the global pool lock then to be able
+			 * to add it back to the lru list
+			 */
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
-			return 0;
+			z3fold_page_unlock(zhdr);
 		}
 
-		/*
-		 * Add to the beginning of LRU.
-		 * Pool lock has to be kept here to ensure the page has
-		 * not already been released
-		 */
-		list_add(&page->lru, &pool->lru);
+		/* We started off locked to we need to lock the pool back */
+		spin_lock(&pool->lock);
 	}
 	spin_unlock(&pool->lock);
 	return -EAGAIN;