Merge branch 'for-5.20/io_uring' into for-5.20/io_uring-zerocopy-send

* for-5.20/io_uring: (716 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 36 insertions, 32 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index ff3e82553a76..492dce43236e 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -158,9 +158,24 @@
  *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
  *  and therefore doesn't naturally serialize with software page-table walkers.
  *
+ *  MMU_GATHER_NO_FLUSH_CACHE
+ *
+ *  Indicates the architecture has flush_cache_range() but it needs *NOT* be called
+ *  before unmapping a VMA.
+ *
+ *  NOTE: strictly speaking we shouldn't have this knob and instead rely on
+ *	  flush_cache_range() being a NOP, except Sparc64 seems to be
+ *	  different here.
+ *
+ *  MMU_GATHER_MERGE_VMAS
+ *
+ *  Indicates the architecture wants to merge ranges over VMAs; typical when
+ *  multiple range invalidates are more expensive than a full invalidate.
+ *
  *  MMU_GATHER_NO_RANGE
  *
- *  Use this if your architecture lacks an efficient flush_tlb_range().
+ *  Use this if your architecture lacks an efficient flush_tlb_range(). This
+ *  option implies MMU_GATHER_MERGE_VMAS above.
  *
  *  MMU_GATHER_NO_GATHER
  *
@@ -288,6 +303,7 @@ struct mmu_gather {
 	 */
 	unsigned int		vma_exec : 1;
 	unsigned int		vma_huge : 1;
+	unsigned int		vma_pfn  : 1;
 
 	unsigned int		batch_count;
 
@@ -334,8 +350,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 
 #ifdef CONFIG_MMU_GATHER_NO_RANGE
 
-#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
-#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#if defined(tlb_flush)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush()
 #endif
 
 /*
@@ -352,20 +368,9 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		flush_tlb_mm(tlb->mm);
 }
 
-static inline void
-tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
-
-#define tlb_end_vma tlb_end_vma
-static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
-
 #else /* CONFIG_MMU_GATHER_NO_RANGE */
 
 #ifndef tlb_flush
-
-#if defined(tlb_start_vma) || defined(tlb_end_vma)
-#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
-#endif
-
 /*
  * When an architecture does not provide its own tlb_flush() implementation
  * but does have a reasonably efficient flush_vma_range() implementation
@@ -385,6 +390,9 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		flush_tlb_range(&vma, tlb->start, tlb->end);
 	}
 }
+#endif
+
+#endif /* CONFIG_MMU_GATHER_NO_RANGE */
 
 static inline void
 tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
@@ -402,17 +410,9 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
 	 */
 	tlb->vma_huge = is_vm_hugetlb_page(vma);
 	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
+	tlb->vma_pfn  = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP));
 }
 
-#else
-
-static inline void
-tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
-
-#endif
-
-#endif /* CONFIG_MMU_GATHER_NO_RANGE */
-
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	/*
@@ -486,32 +486,36 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
  * case where we're doing a full MM flush.  When we're doing a munmap,
  * the vmas are adjusted to only cover the region to be torn down.
  */
-#ifndef tlb_start_vma
 static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (tlb->fullmm)
 		return;
 
 	tlb_update_vma_flags(tlb, vma);
+#ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE
 	flush_cache_range(vma, vma->vm_start, vma->vm_end);
-}
 #endif
+}
 
-#ifndef tlb_end_vma
 static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (tlb->fullmm)
 		return;
 
 	/*
-	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
-	 * the ranges growing with the unused space between consecutive VMAs,
-	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
-	 * this.
+	 * VM_PFNMAP is more fragile because the core mm will not track the
+	 * page mapcount -- there might not be page-frames for these PFNs after
+	 * all. Force flush TLBs for such ranges to avoid munmap() vs
+	 * unmap_mapping_range() races.
 	 */
-	tlb_flush_mmu_tlbonly(tlb);
+	if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) {
+		/*
+		 * Do a TLB flush and reset the range at VMA boundaries; this avoids
+		 * the ranges growing with the unused space between consecutive VMAs.
+		 */
+		tlb_flush_mmu_tlbonly(tlb);
+	}
 }
-#endif
 
 /*
  * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,