These changes fix MM (soft-)dirty bit management in the procfs code & clean up the API.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmAtAgsRHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1gOnA/9GKJblgi88Qb23YwGKp0OfCMdLfx8FJa+
 dq0AB0jgzc8v2J8IITSs/qo/8o25IE9IPTjTfItn0E0jxz7Y8J16urb/vyWX6O2s
 jb4riT5fIRCXvhv9DooxSQerZePaOJXbHYa2BBk8yqNJPGbd5kr0SUGn3BQnBQhR
 0yAfqjrzBLMGzzSO+kK0nhGQH8BJZgYu94CHNnUZJtWcIb2ZC6lzZ7Lz0zi6ueRJ
 81JblV4NCOC9uy9I9odOwESu2TIxT9afq1C/6COyrKYx3sWY6xPOGQTxYZe1LITE
 lb57/95qc7SOIj7Y3aL4YRSVRYRihEU31qlAltwP4fEnz49qdHJOR1HQmjKVG8xs
 Uaa6kCYFeTKmh4SRRr8ZR/hUkebrFUT+9+db6LmBs/i4Kt09T+ZurXC4jqmUHMFn
 2nYCDH6RX153V1YwcHGkr4OWaUVWZwAZl+t0zIo7o7wQdkoAD75ydecW2R3nLMN7
 p1ofGPXmT8Wh4en8LngBawO/4bBuunezh4L3vpz0/EU3viK5+DRsyNKf+d+Tti28
 XCe7ID0GDGq7nIzSZxuyIxmAbWJxjI+7gWT2WUudrJxJ2rUUxPQms8GsQD54IMh5
 UILv9GMBNuV8iA/2c3B52ff5iFl7kp+SxVS3MRC6zTudIV9VV6bb7WpFb8FLOhsH
 3sEo0qDFab4=
 =qcXO
 -----END PGP SIGNATURE-----

Merge tag 'core-mm-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull tlb gather updates from Ingo Molnar:
 "Theses fix MM (soft-)dirty bit management in the procfs code & clean
  up the TLB gather API"

* tag 'core-mm-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ldt: Use tlb_gather_mmu_fullmm() when freeing LDT page-tables
  tlb: arch: Remove empty __tlb_remove_tlb_entry() stubs
  tlb: mmu_gather: Remove start/end arguments from tlb_gather_mmu()
  tlb: mmu_gather: Introduce tlb_gather_mmu_fullmm()
  tlb: mmu_gather: Remove unused start/end arguments from tlb_finish_mmu()
  mm: proc: Invalidate TLB after clearing soft-dirty page state

arch/ia64/include/asm/tlb.h

@@ -23,7 +23,7 @@
  * unmapping a portion of the virtual address space, these hooks are called according to
  * the following template:
  *
- *	tlb <- tlb_gather_mmu(mm, start, end);		// start unmap for address space MM
+ *	tlb <- tlb_gather_mmu(mm);			// start unmap for address space MM
  *	{
  *	  for each vma that needs a shootdown do {
  *	    tlb_start_vma(tlb, vma);
@@ -36,7 +36,7 @@
  *	    tlb_end_vma(tlb, vma);
  *	  }
  *	}
- *	tlb_finish_mmu(tlb, start, end);	// finish unmap for address space MM
+ *	tlb_finish_mmu(tlb);				// finish unmap for address space MM
  */
 #include <linux/mm.h>
 #include <linux/pagemap.h>

arch/sparc/include/asm/tlb_64.h

@@ -24,7 +24,6 @@ void flush_tlb_pending(void);
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #define tlb_flush(tlb)	flush_tlb_pending()
 
 /*

arch/x86/include/asm/tlb.h

@@ -4,7 +4,6 @@
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
 #define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);

arch/x86/kernel/ldt.c

@@ -398,9 +398,15 @@ static void free_ldt_pgtables(struct mm_struct *mm)
 	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
-	tlb_gather_mmu(&tlb, mm, start, end);
+	/*
+	 * Although free_pgd_range() is intended for freeing user
+	 * page-tables, it also works out for kernel mappings on x86.
+	 * We use tlb_gather_mmu_fullmm() to avoid confusing the
+	 * range-tracking logic in __tlb_adjust_range().
+	 */
+	tlb_gather_mmu_fullmm(&tlb, mm);
 	free_pgd_range(&tlb, start, end, start, end);
-	tlb_finish_mmu(&tlb, start, end);
+	tlb_finish_mmu(&tlb);
 #endif
 }
 

fs/exec.c

@@ -708,7 +708,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		return -ENOMEM;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, old_start, old_end);
+	tlb_gather_mmu(&tlb, mm);
 	if (new_end > old_start) {
 		/*
 		 * when the old and new regions overlap clear from new_end.
@@ -725,7 +725,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		free_pgd_range(&tlb, old_start, old_end, new_end,
 			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
-	tlb_finish_mmu(&tlb, old_start, old_end);
+	tlb_finish_mmu(&tlb);
 
 	/*
 	 * Shrink the vma to just the new range.  Always succeeds.

fs/proc/task_mmu.c

@@ -1210,7 +1210,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	enum clear_refs_types type;
-	struct mmu_gather tlb;
 	int itype;
 	int rv;
 
@@ -1249,7 +1248,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			goto out_unlock;
 		}
 
-		tlb_gather_mmu(&tlb, mm, 0, -1);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
@@ -1258,15 +1256,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				vma_set_page_prot(vma);
 			}
 
+			inc_tlb_flush_pending(mm);
 			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
 						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
 		walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops,
 				&cp);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
-		tlb_finish_mmu(&tlb, 0, -1);
+			flush_tlb_mm(mm);
+			dec_tlb_flush_pending(mm);
+		}
 out_unlock:
 		mmap_write_unlock(mm);
 out_mm:

include/asm-generic/tlb.h

@@ -46,7 +46,9 @@
  *
  * The mmu_gather API consists of:
  *
- *  - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *  - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu()
+ *
+ *    start and finish a mmu_gather
  *
  *    Finish in particular will issue a (final) TLB invalidate and free
  *    all (remaining) queued pages.
@@ -91,7 +93,7 @@
  *
  *  - mmu_gather::fullmm
  *
- *    A flag set by tlb_gather_mmu() to indicate we're going to free
+ *    A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free
  *    the entire mm; this allows a number of optimizations.
  *
  *    - We can ignore tlb_{start,end}_vma(); because we don't

include/linux/mm_types.h

@@ -588,10 +588,9 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 }
 
 struct mmu_gather;
-extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-				unsigned long start, unsigned long end);
-extern void tlb_finish_mmu(struct mmu_gather *tlb,
-				unsigned long start, unsigned long end);
+extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
+extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
+extern void tlb_finish_mmu(struct mmu_gather *tlb);
 
 static inline void init_tlb_flush_pending(struct mm_struct *mm)
 {

mm/hugetlb.c

@@ -4008,25 +4008,11 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			  unsigned long end, struct page *ref_page)
 {
-	struct mm_struct *mm;
 	struct mmu_gather tlb;
-	unsigned long tlb_start = start;
-	unsigned long tlb_end = end;
 
-	/*
-	 * If shared PMDs were possibly used within this vma range, adjust
-	 * start/end for worst case tlb flushing.
-	 * Note that we can not be sure if PMDs are shared until we try to
-	 * unmap pages.  However, we want to make sure TLB flushing covers
-	 * the largest possible range.
-	 */
-	adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);
-
-	mm = vma->vm_mm;
-
-	tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
-	tlb_finish_mmu(&tlb, tlb_start, tlb_end);
+	tlb_finish_mmu(&tlb);
 }
 
 /*

mm/madvise.c

@@ -506,9 +506,9 @@ static long madvise_cold(struct vm_area_struct *vma,
 		return -EINVAL;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
+	tlb_gather_mmu(&tlb, mm);
 	madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
-	tlb_finish_mmu(&tlb, start_addr, end_addr);
+	tlb_finish_mmu(&tlb);
 
 	return 0;
 }
@@ -558,9 +558,9 @@ static long madvise_pageout(struct vm_area_struct *vma,
 		return 0;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
+	tlb_gather_mmu(&tlb, mm);
 	madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
-	tlb_finish_mmu(&tlb, start_addr, end_addr);
+	tlb_finish_mmu(&tlb);
 
 	return 0;
 }
@@ -723,7 +723,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 				range.start, range.end);
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, range.start, range.end);
+	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
 
 	mmu_notifier_invalidate_range_start(&range);
@@ -732,7 +732,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 			&madvise_free_walk_ops, &tlb);
 	tlb_end_vma(&tlb, vma);
 	mmu_notifier_invalidate_range_end(&range);
-	tlb_finish_mmu(&tlb, range.start, range.end);
+	tlb_finish_mmu(&tlb);
 
 	return 0;
 }

mm/memory.c

@@ -1534,13 +1534,13 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
 				start, start + size);
-	tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
 	for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next)
 		unmap_single_vma(&tlb, vma, start, range.end, NULL);
 	mmu_notifier_invalidate_range_end(&range);
-	tlb_finish_mmu(&tlb, start, range.end);
+	tlb_finish_mmu(&tlb);
 }
 
 /**
@@ -1561,12 +1561,12 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
 				address, address + size);
-	tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
 	unmap_single_vma(&tlb, vma, address, range.end, details);
 	mmu_notifier_invalidate_range_end(&range);
-	tlb_finish_mmu(&tlb, address, range.end);
+	tlb_finish_mmu(&tlb);
 }
 
 /**

mm/mmap.c

@@ -2671,12 +2671,12 @@ static void unmap_region(struct mm_struct *mm,
 	struct mmu_gather tlb;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, start, end);
+	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
 				 next ? next->vm_start : USER_PGTABLES_CEILING);
-	tlb_finish_mmu(&tlb, start, end);
+	tlb_finish_mmu(&tlb);
 }
 
 /*
@@ -3214,12 +3214,12 @@ void exit_mmap(struct mm_struct *mm)
 
 	lru_add_drain();
 	flush_cache_mm(mm);
-	tlb_gather_mmu(&tlb, mm, 0, -1);
+	tlb_gather_mmu_fullmm(&tlb, 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);
 	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
-	tlb_finish_mmu(&tlb, 0, -1);
+	tlb_finish_mmu(&tlb);
 
 	/*
 	 * Walk the list again, actually closing and freeing it,

mm/mmu_gather.c

@@ -253,21 +253,17 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
  * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
  * @tlb: the mmu_gather structure to initialize
  * @mm: the mm_struct of the target address space
- * @start: start of the region that will be removed from the page-table
- * @end: end of the region that will be removed from the page-table
+ * @fullmm: @mm is without users and we're going to destroy the full address
+ *	    space (exit/execve)
  *
  * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm. The @start and @end are set to 0 and -1
- * respectively when @mm is without users and we're going to destroy
- * the full address space (exit/execve).
+ * tear-down from @mm.
  */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
+static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			     bool fullmm)
 {
 	tlb->mm = mm;
-
-	/* Is it from 0 to ~0? */
-	tlb->fullmm     = !(start | (end+1));
+	tlb->fullmm = fullmm;
 
 #ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb->need_flush_all = 0;
@@ -287,17 +283,24 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	inc_tlb_flush_pending(tlb->mm);
 }
 
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
+{
+	__tlb_gather_mmu(tlb, mm, false);
+}
+
+void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
+{
+	__tlb_gather_mmu(tlb, mm, true);
+}
+
 /**
  * tlb_finish_mmu - finish an mmu_gather structure
  * @tlb: the mmu_gather structure to finish
- * @start: start of the region that will be removed from the page-table
- * @end: end of the region that will be removed from the page-table
  *
  * Called at the end of the shootdown operation to free up any resources that
  * were required.
  */
-void tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end)
+void tlb_finish_mmu(struct mmu_gather *tlb)
 {
 	/*
 	 * If there are parallel threads are doing PTE changes on same range

mm/oom_kill.c

@@ -546,15 +546,15 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
 			mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
 						vma, mm, vma->vm_start,
 						vma->vm_end);
-			tlb_gather_mmu(&tlb, mm, range.start, range.end);
+			tlb_gather_mmu(&tlb, mm);
 			if (mmu_notifier_invalidate_range_start_nonblock(&range)) {
-				tlb_finish_mmu(&tlb, range.start, range.end);
+				tlb_finish_mmu(&tlb);
 				ret = false;
 				continue;
 			}
 			unmap_page_range(&tlb, vma, range.start, range.end, NULL);
 			mmu_notifier_invalidate_range_end(&range);
-			tlb_finish_mmu(&tlb, range.start, range.end);
+			tlb_finish_mmu(&tlb);
 		}
 	}