Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Highlights:

   - AMD KFD driver merge

     This is the AMD HSA interface for exposing a lowlevel interface for
     GPGPU use.  They have an open source userspace built on top of this
     interface, and the code looks as good as it was going to get out of
     tree.

   - Initial atomic modesetting work

     The need for an atomic modesetting interface to allow userspace to
     try and send a complete set of modesetting state to the driver has
     arisen, and been suffering from neglect this past year.  No more,
     the start of the common code and changes for msm driver to use it
     are in this tree.  Ongoing work to get the userspace ioctl finished
     and the code clean will probably wait until next kernel.

   - DisplayID 1.3 and tiled monitor exposed to userspace.

     Tiled monitor property is now exposed for userspace to make use of.

   - Rockchip drm driver merged.

   - imx gpu driver moved out of staging

  Other stuff:

   - core:
        panel - MIPI DSI + new panels.
        expose suggested x/y properties for virtual GPUs

   - i915:
        Initial Skylake (SKL) support
        gen3/4 reset work
        start of dri1/ums removal
        infoframe tracking
        fixes for lots of things.

   - nouveau:
        tegra k1 voltage support
        GM204 modesetting support
        GT21x memory reclocking work

   - radeon:
        CI dpm fixes
        GPUVM improvements
        Initial DPM fan control

   - rcar-du:
        HDMI support added
        removed some support for old boards
        slave encoder driver for Analog Devices adv7511

   - exynos:
        Exynos4415 SoC support

   - msm:
        a4xx gpu support
        atomic helper conversion

   - tegra:
        iommu support
        universal plane support
        ganged-mode DSI support

   - sti:
        HDMI i2c improvements

   - vmwgfx:
        some late fixes.

   - qxl:
        use suggested x/y properties"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (969 commits)
  drm: sti: fix module compilation issue
  drm/i915: save/restore GMBUS freq across suspend/resume on gen4
  drm: sti: correctly cleanup CRTC and planes
  drm: sti: add HQVDP plane
  drm: sti: add cursor plane
  drm: sti: enable auxiliary CRTC
  drm: sti: fix delay in VTG programming
  drm: sti: prepare sti_tvout to support auxiliary crtc
  drm: sti: use drm_crtc_vblank_{on/off} instead of drm_vblank_{on/off}
  drm: sti: fix hdmi avi infoframe
  drm: sti: remove event lock while disabling vblank
  drm: sti: simplify gdp code
  drm: sti: clear all mixer control
  drm: sti: remove gpio for HDMI hot plug detection
  drm: sti: allow to change hdmi ddc i2c adapter
  drm/doc: Document drm_add_modes_noedid() usage
  drm/i915: Remove '& 0xffff' from the mask given to WA_REG()
  drm/i915: Invert the mask and val arguments in wa_add() and WA_REG()
  drm: Zero out DRM object memory upon cleanup
  drm/i915/bdw: Fix the write setting up the WIZ hashing mode
  ...

8 files changed, 44 insertions, 11 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 11ef7ec40d13..2805d71cf476 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -37,7 +37,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 
         if (pte_present(pte)) {
                 flush_cache_page(vma, addr, pte_pfn(pte));
-                pte = ptep_clear_flush(vma, addr, ptep);
+                pte = ptep_clear_flush_notify(vma, addr, ptep);
                 page = vm_normal_page(vma, addr, pte);
                 if (page) {
                         if (pte_dirty(pte))
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 46f96c23cc27..817a875f2b8c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1035,7 +1035,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
                 goto out_free_pages;
         VM_BUG_ON_PAGE(!PageHead(page), page);
 
-        pmdp_clear_flush(vma, haddr, pmd);
+        pmdp_clear_flush_notify(vma, haddr, pmd);
         /* leave pmd empty until pte is filled */
 
         pgtable = pgtable_trans_huge_withdraw(mm, pmd);
@@ -1178,7 +1178,7 @@ alloc:
                 pmd_t entry;
                 entry = mk_huge_pmd(new_page, vma->vm_page_prot);
                 entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-                pmdp_clear_flush(vma, haddr, pmd);
+                pmdp_clear_flush_notify(vma, haddr, pmd);
                 page_add_new_anon_rmap(new_page, vma, haddr);
                 mem_cgroup_commit_charge(new_page, memcg, false);
                 lru_cache_add_active_or_unevictable(new_page, vma);
@@ -1512,7 +1512,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
                 pmd_t entry;
                 ret = 1;
                 if (!prot_numa) {
-                        entry = pmdp_get_and_clear(mm, addr, pmd);
+                        entry = pmdp_get_and_clear_notify(mm, addr, pmd);
                         if (pmd_numa(entry))
                                 entry = pmd_mknonnuma(entry);
                         entry = pmd_modify(entry, newprot);
@@ -1644,6 +1644,7 @@ static int __split_huge_page_splitting(struct page *page,
                  * serialize against split_huge_page*.
                  */
                 pmdp_splitting_flush(vma, address, pmd);
+
                 ret = 1;
                 spin_unlock(ptl);
         }
@@ -2834,7 +2835,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
         pmd_t _pmd;
         int i;
 
-        pmdp_clear_flush(vma, haddr, pmd);
+        pmdp_clear_flush_notify(vma, haddr, pmd);
         /* leave pmd empty until pte is filled */
 
         pgtable = pgtable_trans_huge_withdraw(mm, pmd);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 47f6070d7c46..85032de5e20f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2598,8 +2598,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                         }
                         set_huge_pte_at(dst, addr, dst_pte, entry);
                 } else {
-                        if (cow)
+                        if (cow) {
                                 huge_ptep_set_wrprotect(src, addr, src_pte);
+                                mmu_notifier_invalidate_range(src, mmun_start,
+                                                                   mmun_end);
+                        }
                         entry = huge_ptep_get(src_pte);
                         ptepage = pte_page(entry);
                         get_page(ptepage);
@@ -2901,6 +2904,7 @@ retry_avoidcopy:
 
                 /* Break COW */
                 huge_ptep_clear_flush(vma, address, ptep);
+                mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
                 set_huge_pte_at(mm, address, ptep,
                                 make_huge_pte(vma, new_page, 1));
                 page_remove_rmap(old_page);
@@ -3376,6 +3380,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
          * and that page table be reused and filled with junk.
          */
         flush_tlb_range(vma, start, end);
+        mmu_notifier_invalidate_range(mm, start, end);
         i_mmap_unlock_write(vma->vm_file->f_mapping);
         mmu_notifier_invalidate_range_end(mm, start, end);
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 6b2e337bc03c..d247efab5073 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -892,7 +892,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
                  * this assure us that no O_DIRECT can happen after the check
                  * or in the middle of the check.
                  */
-                entry = ptep_clear_flush(vma, addr, ptep);
+                entry = ptep_clear_flush_notify(vma, addr, ptep);
                 /*
                  * Check that no O_DIRECT or similar I/O is in progress on the
                  * page
@@ -960,7 +960,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
         page_add_anon_rmap(kpage, vma, addr);
 
         flush_cache_page(vma, addr, pte_pfn(*ptep));
-        ptep_clear_flush(vma, addr, ptep);
+        ptep_clear_flush_notify(vma, addr, ptep);
         set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
         page_remove_rmap(page);
diff --git a/mm/memory.c b/mm/memory.c
index fbf74112de5b..c3b9097251c5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -239,6 +239,7 @@ static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
                 return;
 
         tlb_flush(tlb);
+        mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
         tlb_table_flush(tlb);
 #endif
@@ -2220,7 +2221,7 @@ gotten:
                  * seen in the presence of one thread doing SMC and another
                  * thread doing COW.
                  */
-                ptep_clear_flush(vma, address, page_table);
+                ptep_clear_flush_notify(vma, address, page_table);
                 page_add_new_anon_rmap(new_page, vma, address);
                 mem_cgroup_commit_charge(new_page, memcg, false);
                 lru_cache_add_active_or_unevictable(new_page, vma);
diff --git a/mm/migrate.c b/mm/migrate.c
index 253474c22239..b1d02127e1be 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1862,7 +1862,7 @@ fail_putback:
          */
         flush_cache_range(vma, mmun_start, mmun_end);
         page_add_anon_rmap(new_page, vma, mmun_start);
-        pmdp_clear_flush(vma, mmun_start, pmd);
+        pmdp_clear_flush_notify(vma, mmun_start, pmd);
         set_pmd_at(mm, mmun_start, pmd, entry);
         flush_tlb_range(vma, mmun_start, mmun_end);
         update_mmu_cache_pmd(vma, address, &entry);
@@ -1870,6 +1870,7 @@ fail_putback:
         if (page_count(page) != 2) {
                 set_pmd_at(mm, mmun_start, pmd, orig_entry);
                 flush_tlb_range(vma, mmun_start, mmun_end);
+                mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
                 update_mmu_cache_pmd(vma, address, &entry);
                 page_remove_rmap(new_page);
                 goto fail_putback;
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 2c8da9825fe3..3b9b3d0741b2 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -193,6 +193,16 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 
         id = srcu_read_lock(&srcu);
         hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+                /*
+                 * Call invalidate_range here too to avoid the need for the
+                 * subsystem of having to register an invalidate_range_end
+                 * call-back when there is invalidate_range already. Usually a
+                 * subsystem registers either invalidate_range_start()/end() or
+                 * invalidate_range(), so this will be no additional overhead
+                 * (besides the pointer check).
+                 */
+                if (mn->ops->invalidate_range)
+                        mn->ops->invalidate_range(mn, mm, start, end);
                 if (mn->ops->invalidate_range_end)
                         mn->ops->invalidate_range_end(mn, mm, start, end);
         }
@@ -200,6 +210,21 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
 
+void __mmu_notifier_invalidate_range(struct mm_struct *mm,
+                                  unsigned long start, unsigned long end)
+{
+        struct mmu_notifier *mn;
+        int id;
+
+        id = srcu_read_lock(&srcu);
+        hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+                if (mn->ops->invalidate_range)
+                        mn->ops->invalidate_range(mn, mm, start, end);
+        }
+        srcu_read_unlock(&srcu, id);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range);
+
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
                                     struct mm_struct *mm,
                                     int take_mmap_sem)
diff --git a/mm/rmap.c b/mm/rmap.c
index c52f43a69eea..45ba250babd8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1380,7 +1380,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 
                 /* Nuke the page table entry. */
                 flush_cache_page(vma, address, pte_pfn(*pte));
-                pteval = ptep_clear_flush(vma, address, pte);
+                pteval = ptep_clear_flush_notify(vma, address, pte);
 
                 /* If nonlinear, store the file page offset in the pte. */
                 if (page->index != linear_page_index(vma, address)) {