9 files changed, 225 insertions, 214 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 2d9f1504d75e..2888024e0b0a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -575,5 +575,5 @@ config PGTABLE_MAPPING
           then you should select this. This causes zsmalloc to use page table
           mapping rather than copying for object mapping.
 
-          You can check speed with zsmalloc benchmark[1].
-          [1] https://github.com/spartacus06/zsmalloc
+          You can check speed with zsmalloc benchmark:
+          https://github.com/spartacus06/zsmapbench
diff --git a/mm/compaction.c b/mm/compaction.c
index b48c5259ea33..918577595ea8 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,7 +251,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 {
         int nr_scanned = 0, total_isolated = 0;
         struct page *cursor, *valid_page = NULL;
-        unsigned long nr_strict_required = end_pfn - blockpfn;
         unsigned long flags;
         bool locked = false;
 
@@ -264,11 +263,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
                 nr_scanned++;
                 if (!pfn_valid_within(blockpfn))
-                        continue;
+                        goto isolate_fail;
+
                 if (!valid_page)
                         valid_page = page;
                 if (!PageBuddy(page))
-                        continue;
+                        goto isolate_fail;
 
                 /*
                  * The zone lock must be held to isolate freepages.
@@ -289,12 +289,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
                 /* Recheck this is a buddy page under lock */
                 if (!PageBuddy(page))
-                        continue;
+                        goto isolate_fail;
 
                 /* Found a free page, break it into order-0 pages */
                 isolated = split_free_page(page);
-                if (!isolated && strict)
-                        break;
                 total_isolated += isolated;
                 for (i = 0; i < isolated; i++) {
                         list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
                 if (isolated) {
                         blockpfn += isolated - 1;
                         cursor += isolated - 1;
+                        continue;
                 }
+
+isolate_fail:
+                if (strict)
+                        break;
+                else
+                        continue;
+
         }
 
         trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
          * pages requested were isolated. If there were any failures, 0 is
          * returned and CMA will fail.
          */
-        if (strict && nr_strict_required > total_isolated)
+        if (strict && blockpfn < end_pfn)
                 total_isolated = 0;
 
         if (locked)
diff --git a/mm/fremap.c b/mm/fremap.c
index bbc4d660221a..34feba60a17e 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -23,28 +23,44 @@
 
 #include "internal.h"
 
+static int mm_counter(struct page *page)
+{
+        return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
                         unsigned long addr, pte_t *ptep)
 {
         pte_t pte = *ptep;
+        struct page *page;
+        swp_entry_t entry;
 
         if (pte_present(pte)) {
-                struct page *page;
-
                 flush_cache_page(vma, addr, pte_pfn(pte));
                 pte = ptep_clear_flush(vma, addr, ptep);
                 page = vm_normal_page(vma, addr, pte);
                 if (page) {
                         if (pte_dirty(pte))
                                 set_page_dirty(page);
+                        update_hiwater_rss(mm);
+                        dec_mm_counter(mm, mm_counter(page));
                         page_remove_rmap(page);
                         page_cache_release(page);
+                }
+        } else {        /* zap_pte() is not called when pte_none() */
+                if (!pte_file(pte)) {
                         update_hiwater_rss(mm);
-                        dec_mm_counter(mm, MM_FILEPAGES);
+                        entry = pte_to_swp_entry(pte);
+                        if (non_swap_entry(entry)) {
+                                if (is_migration_entry(entry)) {
+                                        page = migration_entry_to_page(entry);
+                                        dec_mm_counter(mm, mm_counter(page));
+                                }
+                        } else {
+                                free_swap_and_cache(entry);
+                                dec_mm_counter(mm, MM_SWAPENTS);
+                        }
                 }
-        } else {
-                if (!pte_file(pte))
-                        free_swap_and_cache(pte_to_swp_entry(pte));
                 pte_clear_not_present_full(mm, addr, ptep, 0);
         }
 }
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ae3c8f3595d4..4755c8576942 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1556,10 +1556,10 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 
 #ifdef CONFIG_COMPAT
 
-asmlinkage long compat_sys_get_mempolicy(int __user *policy,
-                                     compat_ulong_t __user *nmask,
-                                     compat_ulong_t maxnode,
-                                     compat_ulong_t addr, compat_ulong_t flags)
+COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
+                       compat_ulong_t __user *, nmask,
+                       compat_ulong_t, maxnode,
+                       compat_ulong_t, addr, compat_ulong_t, flags)
 {
         long err;
         unsigned long __user *nm = NULL;
@@ -1586,8 +1586,8 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy,
         return err;
 }
 
-asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
-                                     compat_ulong_t maxnode)
+COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
+                       compat_ulong_t, maxnode)
 {
         long err = 0;
         unsigned long __user *nm = NULL;
@@ -1609,9 +1609,9 @@ asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
         return sys_set_mempolicy(mode, nm, nr_bits+1);
 }
 
-asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
-                             compat_ulong_t mode, compat_ulong_t __user *nmask,
-                             compat_ulong_t maxnode, compat_ulong_t flags)
+COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
+                       compat_ulong_t, mode, compat_ulong_t __user *, nmask,
+                       compat_ulong_t, maxnode, compat_ulong_t, flags)
 {
         long err = 0;
         unsigned long __user *nm = NULL;
@@ -2301,35 +2301,6 @@ static void sp_free(struct sp_node *n)
         kmem_cache_free(sn_cache, n);
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-        /* Never defer a private fault */
-        if (cpupid_match_pid(p, last_cpupid))
-                return false;
-
-        if (p->numa_migrate_deferred) {
-                p->numa_migrate_deferred--;
-                return true;
-        }
-        return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-        p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
-}
-#else
-static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-        return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2403,52 +2374,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
         /* Migrate the page towards the node whose CPU is referencing it */
         if (pol->flags & MPOL_F_MORON) {
-                int last_cpupid;
-                int this_cpupid;
-
                 polnid = thisnid;
-                this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
-
-                /*
-                 * Multi-stage node selection is used in conjunction
-                 * with a periodic migration fault to build a temporal
-                 * task<->page relation. By using a two-stage filter we
-                 * remove short/unlikely relations.
-                 *
-                 * Using P(p) ~ n_p / n_t as per frequentist
-                 * probability, we can equate a task's usage of a
-                 * particular page (n_p) per total usage of this
-                 * page (n_t) (in a given time-span) to a probability.
-                 *
-                 * Our periodic faults will sample this probability and
-                 * getting the same result twice in a row, given these
-                 * samples are fully independent, is then given by
-                 * P(n)^2, provided our sample period is sufficiently
-                 * short compared to the usage pattern.
-                 *
-                 * This quadric squishes small probabilities, making
-                 * it less likely we act on an unlikely task<->page
-                 * relation.
-                 */
-                last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-                if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
 
-                        /* See sysctl_numa_balancing_migrate_deferred comment */
-                        if (!cpupid_match_pid(current, last_cpupid))
-                                defer_numa_migrate(current);
-
-                        goto out;
-                }
-
-                /*
-                 * The quadratic filter above reduces extraneous migration
-                 * of shared pages somewhat. This code reduces it even more,
-                 * reducing the overhead of page migrations of shared pages.
-                 * This makes workloads with shared pages rely more on
-                 * "move task near its memory", and less on "move memory
-                 * towards its task", which is exactly what we want.
-                 */
-                if (numa_migrate_deferred(current, last_cpupid))
+                if (!should_numa_migrate_memory(current, page, curnid, thiscpu))
                         goto out;
         }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 482a33d89134..bed48809e5d0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -178,6 +178,37 @@ out:
 }
 
 /*
+ * Congratulations to trinity for discovering this bug.
+ * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
+ * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
+ * replace the specified range by file ptes throughout (maybe populated after).
+ * If page migration finds a page within that range, while it's still located
+ * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
+ * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
+ * But if the migrating page is in a part of the vma outside the range to be
+ * remapped, then it will not be cleared, and remove_migration_ptes() needs to
+ * deal with it.  Fortunately, this part of the vma is of course still linear,
+ * so we just need to use linear location on the nonlinear list.
+ */
+static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
+                struct address_space *mapping, void *arg)
+{
+        struct vm_area_struct *vma;
+        /* hugetlbfs does not support remap_pages, so no huge pgoff worries */
+        pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+        unsigned long addr;
+
+        list_for_each_entry(vma,
+                &mapping->i_mmap_nonlinear, shared.nonlinear) {
+
+                addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+                if (addr >= vma->vm_start && addr < vma->vm_end)
+                        remove_migration_pte(page, vma, addr, arg);
+        }
+        return SWAP_AGAIN;
+}
+
+/*
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
  */
@@ -186,6 +217,7 @@ static void remove_migration_ptes(struct page *old, struct page *new)
         struct rmap_walk_control rwc = {
                 .rmap_one = remove_migration_pte,
                 .arg = old,
+                .file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
         };
 
         rmap_walk(new, &rwc);
@@ -1158,7 +1190,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
                                         pm->node);
         else
                 return alloc_pages_exact_node(pm->node,
-                                GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+                                GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
 /*
@@ -1544,9 +1576,9 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
         struct page *newpage;
 
         newpage = alloc_pages_exact_node(nid,
-                                         (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
-                                          __GFP_NOMEMALLOC | __GFP_NORETRY |
-                                          __GFP_NOWARN) &
+                                         (GFP_HIGHUSER_MOVABLE |
+                                          __GFP_THISNODE | __GFP_NOMEMALLOC |
+                                          __GFP_NORETRY | __GFP_NOWARN) &
                                          ~GFP_IOFS, 0);
 
         return newpage;
@@ -1747,7 +1779,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
                 goto out_dropref;
 
         new_page = alloc_pages_node(node,
-                (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+                (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+                HPAGE_PMD_ORDER);
         if (!new_page)
                 goto out_fail;
 
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 8a8cd0265e52..f802c2d216a7 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -31,6 +31,9 @@ void use_mm(struct mm_struct *mm)
         tsk->mm = mm;
         switch_mm(active_mm, mm, tsk);
         task_unlock(tsk);
+#ifdef finish_arch_post_lock_switch
+        finish_arch_post_lock_switch();
+#endif
 
         if (active_mm != mm)
                 mmdrop(active_mm);
diff --git a/mm/percpu.c b/mm/percpu.c
index 036cfe07050f..63e24fb4387b 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -102,10 +102,11 @@ struct pcpu_chunk {
         int                     free_size;      /* free bytes in the chunk */
         int                     contig_hint;    /* max contiguous size hint */
         void                    *base_addr;     /* base address of this chunk */
-        int                     map_used;       /* # of map entries used */
+        int                     map_used;       /* # of map entries used before the sentry */
         int                     map_alloc;      /* # of map entries allocated */
         int                     *map;           /* allocation map */
         void                    *data;          /* chunk data */
+        int                     first_free;     /* no free below this */
         bool                    immutable;      /* no [de]population allowed */
         unsigned long           populated[];    /* populated bitmap */
 };
@@ -356,11 +357,11 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
 {
         int new_alloc;
 
-        if (chunk->map_alloc >= chunk->map_used + 2)
+        if (chunk->map_alloc >= chunk->map_used + 3)
                 return 0;
 
         new_alloc = PCPU_DFL_MAP_ALLOC;
-        while (new_alloc < chunk->map_used + 2)
+        while (new_alloc < chunk->map_used + 3)
                 new_alloc *= 2;
 
         return new_alloc;
@@ -418,48 +419,6 @@ out_unlock:
 }
 
 /**
- * pcpu_split_block - split a map block
- * @chunk: chunk of interest
- * @i: index of map block to split
- * @head: head size in bytes (can be 0)
- * @tail: tail size in bytes (can be 0)
- *
- * Split the @i'th map block into two or three blocks.  If @head is
- * non-zero, @head bytes block is inserted before block @i moving it
- * to @i+1 and reducing its size by @head bytes.
- *
- * If @tail is non-zero, the target block, which can be @i or @i+1
- * depending on @head, is reduced by @tail bytes and @tail byte block
- * is inserted after the target block.
- *
- * @chunk->map must have enough free slots to accommodate the split.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
-                             int head, int tail)
-{
-        int nr_extra = !!head + !!tail;
-
-        BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);
-
-        /* insert new subblocks */
-        memmove(&chunk->map[i + nr_extra], &chunk->map[i],
-                sizeof(chunk->map[0]) * (chunk->map_used - i));
-        chunk->map_used += nr_extra;
-
-        if (head) {
-                chunk->map[i + 1] = chunk->map[i] - head;
-                chunk->map[i++] = head;
-        }
-        if (tail) {
-                chunk->map[i++] -= tail;
-                chunk->map[i] = tail;
-        }
-}
-
-/**
  * pcpu_alloc_area - allocate area from a pcpu_chunk
  * @chunk: chunk of interest
  * @size: wanted size in bytes
@@ -483,19 +442,27 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
         int oslot = pcpu_chunk_slot(chunk);
         int max_contig = 0;
         int i, off;
+        bool seen_free = false;
+        int *p;
 
-        for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
-                bool is_last = i + 1 == chunk->map_used;
+        for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) {
                 int head, tail;
+                int this_size;
+
+                off = *p;
+                if (off & 1)
+                        continue;
 
                 /* extra for alignment requirement */
                 head = ALIGN(off, align) - off;
-                BUG_ON(i == 0 && head != 0);
 
-                if (chunk->map[i] < 0)
-                        continue;
-                if (chunk->map[i] < head + size) {
-                        max_contig = max(chunk->map[i], max_contig);
+                this_size = (p[1] & ~1) - off;
+                if (this_size < head + size) {
+                        if (!seen_free) {
+                                chunk->first_free = i;
+                                seen_free = true;
+                        }
+                        max_contig = max(this_size, max_contig);
                         continue;
                 }
 
@@ -505,44 +472,59 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
                  * than sizeof(int), which is very small but isn't too
                  * uncommon for percpu allocations.
                  */
-                if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
-                        if (chunk->map[i - 1] > 0)
-                                chunk->map[i - 1] += head;
-                        else {
-                                chunk->map[i - 1] -= head;
+                if (head && (head < sizeof(int) || !(p[-1] & 1))) {
+                        *p = off += head;
+                        if (p[-1] & 1)
                                 chunk->free_size -= head;
-                        }
-                        chunk->map[i] -= head;
-                        off += head;
+                        else
+                                max_contig = max(*p - p[-1], max_contig);
+                        this_size -= head;
                         head = 0;
                 }
 
                 /* if tail is small, just keep it around */
-                tail = chunk->map[i] - head - size;
-                if (tail < sizeof(int))
+                tail = this_size - head - size;
+                if (tail < sizeof(int)) {
                         tail = 0;
+                        size = this_size - head;
+                }
 
                 /* split if warranted */
                 if (head || tail) {
-                        pcpu_split_block(chunk, i, head, tail);
+                        int nr_extra = !!head + !!tail;
+
+                        /* insert new subblocks */
+                        memmove(p + nr_extra + 1, p + 1,
+                                sizeof(chunk->map[0]) * (chunk->map_used - i));
+                        chunk->map_used += nr_extra;
+
                         if (head) {
-                                i++;
-                                off += head;
-                                max_contig = max(chunk->map[i - 1], max_contig);
+                                if (!seen_free) {
+                                        chunk->first_free = i;
+                                        seen_free = true;
+                                }
+                                *++p = off += head;
+                                ++i;
+                                max_contig = max(head, max_contig);
+                        }
+                        if (tail) {
+                                p[1] = off + size;
+                                max_contig = max(tail, max_contig);
                         }
-                        if (tail)
-                                max_contig = max(chunk->map[i + 1], max_contig);
                 }
 
+                if (!seen_free)
+                        chunk->first_free = i + 1;
+
                 /* update hint and mark allocated */
-                if (is_last)
+                if (i + 1 == chunk->map_used)
                         chunk->contig_hint = max_contig; /* fully scanned */
                 else
                         chunk->contig_hint = max(chunk->contig_hint,
                                                  max_contig);
 
-                chunk->free_size -= chunk->map[i];
-                chunk->map[i] = -chunk->map[i];
+                chunk->free_size -= size;
+                *p |= 1;
 
                 pcpu_chunk_relocate(chunk, oslot);
                 return off;
@@ -570,34 +552,50 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
 {
         int oslot = pcpu_chunk_slot(chunk);
-        int i, off;
-
-        for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
-                if (off == freeme)
-                        break;
+        int off = 0;
+        unsigned i, j;
+        int to_free = 0;
+        int *p;
+
+        freeme |= 1;    /* we are searching for <given offset, in use> pair */
+
+        i = 0;
+        j = chunk->map_used;
+        while (i != j) {
+                unsigned k = (i + j) / 2;
+                off = chunk->map[k];
+                if (off < freeme)
+                        i = k + 1;
+                else if (off > freeme)
+                        j = k;
+                else
+                        i = j = k;
+        }
         BUG_ON(off != freeme);
-        BUG_ON(chunk->map[i] > 0);
 
-        chunk->map[i] = -chunk->map[i];
-        chunk->free_size += chunk->map[i];
+        if (i < chunk->first_free)
+                chunk->first_free = i;
 
+        p = chunk->map + i;
+        *p = off &= ~1;
+        chunk->free_size += (p[1] & ~1) - off;
+
+        /* merge with next? */
+        if (!(p[1] & 1))
+                to_free++;
         /* merge with previous? */
-        if (i > 0 && chunk->map[i - 1] >= 0) {
-                chunk->map[i - 1] += chunk->map[i];
-                chunk->map_used--;
-                memmove(&chunk->map[i], &chunk->map[i + 1],
-                        (chunk->map_used - i) * sizeof(chunk->map[0]));
+        if (i > 0 && !(p[-1] & 1)) {
+                to_free++;
                 i--;
+                p--;
         }
-        /* merge with next? */
-        if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
-                chunk->map[i] += chunk->map[i + 1];
-                chunk->map_used--;
-                memmove(&chunk->map[i + 1], &chunk->map[i + 2],
-                        (chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
+        if (to_free) {
+                chunk->map_used -= to_free;
+                memmove(p + 1, p + 1 + to_free,
+                        (chunk->map_used - i) * sizeof(chunk->map[0]));
         }
 
-        chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
+        chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint);
         pcpu_chunk_relocate(chunk, oslot);
 }
 
@@ -617,7 +615,9 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
         }
 
         chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
-        chunk->map[chunk->map_used++] = pcpu_unit_size;
+        chunk->map[0] = 0;
+        chunk->map[1] = pcpu_unit_size | 1;
+        chunk->map_used = 1;
 
         INIT_LIST_HEAD(&chunk->list);
         chunk->free_size = pcpu_unit_size;
@@ -713,6 +713,16 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
         unsigned long flags;
         void __percpu *ptr;
 
+        /*
+         * We want the lowest bit of offset available for in-use/free
+         * indicator, so force >= 16bit alignment and make size even.
+         */
+        if (unlikely(align < 2))
+                align = 2;
+
+        if (unlikely(size & 1))
+                size++;
+
         if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
                 WARN(true, "illegal size (%zu) or align (%zu) for "
                      "percpu allocation\n", size, align);
@@ -1343,9 +1353,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
         }
         schunk->contig_hint = schunk->free_size;
 
-        schunk->map[schunk->map_used++] = -ai->static_size;
+        schunk->map[0] = 1;
+        schunk->map[1] = ai->static_size;
+        schunk->map_used = 1;
         if (schunk->free_size)
-                schunk->map[schunk->map_used++] = schunk->free_size;
+                schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size);
+        else
+                schunk->map[1] |= 1;
 
         /* init dynamic chunk if necessary */
         if (dyn_size) {
@@ -1358,8 +1372,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
                 bitmap_fill(dchunk->populated, pcpu_unit_pages);
 
                 dchunk->contig_hint = dchunk->free_size = dyn_size;
-                dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
-                dchunk->map[dchunk->map_used++] = dchunk->free_size;
+                dchunk->map[0] = 1;
+                dchunk->map[1] = pcpu_reserved_chunk_limit;
+                dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1;
+                dchunk->map_used = 2;
         }
 
         /* link the first chunk in */
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index fd26d0433509..3c5cf68566ec 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -456,25 +456,23 @@ free_iovecs:
         return rc;
 }
 
-asmlinkage ssize_t
-compat_sys_process_vm_readv(compat_pid_t pid,
-                            const struct compat_iovec __user *lvec,
-                            unsigned long liovcnt,
-                            const struct compat_iovec __user *rvec,
-                            unsigned long riovcnt,
-                            unsigned long flags)
+COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
+                       const struct compat_iovec __user *, lvec,
+                       compat_ulong_t, liovcnt,
+                       const struct compat_iovec __user *, rvec,
+                       compat_ulong_t, riovcnt,
+                       compat_ulong_t, flags)
 {
         return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
                                     riovcnt, flags, 0);
 }
 
-asmlinkage ssize_t
-compat_sys_process_vm_writev(compat_pid_t pid,
-                             const struct compat_iovec __user *lvec,
-                             unsigned long liovcnt,
-                             const struct compat_iovec __user *rvec,
-                             unsigned long riovcnt,
-                             unsigned long flags)
+COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
+                       const struct compat_iovec __user *, lvec,
+                       compat_ulong_t, liovcnt,
+                       const struct compat_iovec __user *, rvec,
+                       compat_ulong_t, riovcnt,
+                       compat_ulong_t, flags)
 {
         return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
                                     riovcnt, flags, 1);
diff --git a/mm/rmap.c b/mm/rmap.c
index d9d42316a99a..11cf322f8133 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1165,6 +1165,16 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                 }
                 set_pte_at(mm, address, pte,
                            swp_entry_to_pte(make_hwpoison_entry(page)));
+        } else if (pte_unused(pteval)) {
+                /*
+                 * The guest indicated that the page content is of no
+                 * interest anymore. Simply discard the pte, vmscan
+                 * will take care of the rest.
+                 */
+                if (PageAnon(page))
+                        dec_mm_counter(mm, MM_ANONPAGES);
+                else
+                        dec_mm_counter(mm, MM_FILEPAGES);
         } else if (PageAnon(page)) {
                 swp_entry_t entry = { .val = page_private(page) };
                 pte_t swp_pte;
@@ -1360,8 +1370,9 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 }
 
 static int try_to_unmap_nonlinear(struct page *page,
-                struct address_space *mapping, struct vm_area_struct *vma)
+                struct address_space *mapping, void *arg)
 {
+        struct vm_area_struct *vma;
         int ret = SWAP_AGAIN;
         unsigned long cursor;
         unsigned long max_nl_cursor = 0;
@@ -1663,7 +1674,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
         if (list_empty(&mapping->i_mmap_nonlinear))
                 goto done;
 
-        ret = rwc->file_nonlinear(page, mapping, vma);
+        ret = rwc->file_nonlinear(page, mapping, rwc->arg);
 
 done:
         mutex_unlock(&mapping->i_mmap_mutex);