[PATCH v2 09/46] mm: add MADV_SPLIT to enable HugeTLB HGM

[James Houghton <jthoughton@google.com>]

Issuing ioctl(MADV_SPLIT) on a HugeTLB address range will enable
HugeTLB HGM. MADV_SPLIT was chosen for the name so that this API can be
applied to non-HugeTLB memory in the future, if such an application is
to arise.

MADV_SPLIT provides several API changes for some syscalls on HugeTLB
address ranges:
1. UFFDIO_CONTINUE is allowed for MAP_SHARED VMAs at PAGE_SIZE
   alignment.
2. read()ing a page fault event from a userfaultfd will yield a
   PAGE_SIZE-rounded address, instead of a huge-page-size-rounded
   address (unless UFFD_FEATURE_EXACT_ADDRESS is used).

There is no way to disable the API changes that come with issuing
MADV_SPLIT. MADV_COLLAPSE can be used to collapse high-granularity page
table mappings that come from the extended functionality that comes with
using MADV_SPLIT.

For post-copy live migration, the expected use-case is:
1. mmap(MAP_SHARED, some_fd) primary mapping
2. mmap(MAP_SHARED, some_fd) alias mapping
3. MADV_SPLIT the primary mapping
4. UFFDIO_REGISTER/etc. the primary mapping
5. Copy memory contents into alias mapping and UFFDIO_CONTINUE the
   corresponding PAGE_SIZE sections in the primary mapping.

More API changes may be added in the future.

Signed-off-by: James Houghton <jthoughton@google.com>

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 763929e814e9..7a26f3648b90 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -78,6 +78,8 @@
 
 #define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
 
+#define MADV_SPLIT	26		/* Enable hugepage high-granularity APIs */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index c6e1fc77c996..f8a74a3a0928 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -105,6 +105,8 @@
 
 #define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
 
+#define MADV_SPLIT	26		/* Enable hugepage high-granularity APIs */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 68c44f99bc93..a6dc6a56c941 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -72,6 +72,8 @@
 
 #define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
 
+#define MADV_SPLIT	74		/* Enable hugepage high-granularity APIs */
+
 #define MADV_HWPOISON     100		/* poison a page for testing */
 #define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
 
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 1ff0c858544f..f98a77c430a9 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -113,6 +113,8 @@
 
 #define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
 
+#define MADV_SPLIT	26		/* Enable hugepage high-granularity APIs */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index 6ce1f1ceb432..996e8ded092f 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -79,6 +79,8 @@
 
 #define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
 
+#define MADV_SPLIT	26		/* Enable hugepage high-granularity APIs */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/mm/madvise.c b/mm/madvise.c
index c2202f51e9dd..8c004c678262 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1006,6 +1006,28 @@ static long madvise_remove(struct vm_area_struct *vma,
 	return error;
 }
 
+static int madvise_split(struct vm_area_struct *vma,
+			 unsigned long *new_flags)
+{
+#ifdef CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING
+	if (!is_vm_hugetlb_page(vma) || !hugetlb_hgm_eligible(vma))
+		return -EINVAL;
+
+	/*
+	 * PMD sharing doesn't work with HGM. If this MADV_SPLIT is on part
+	 * of a VMA, then we will split the VMA. Here, we're unsharing before
+	 * splitting because it's simpler, although we may be unsharing more
+	 * than we need.
+	 */
+	hugetlb_unshare_all_pmds(vma);
+
+	*new_flags |= VM_HUGETLB_HGM;
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
 /*
  * Apply an madvise behavior to a region of a vma.  madvise_update_vma
  * will handle splitting a vm area into separate areas, each area with its own
@@ -1084,6 +1106,11 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 		break;
 	case MADV_COLLAPSE:
 		return madvise_collapse(vma, prev, start, end);
+	case MADV_SPLIT:
+		error = madvise_split(vma, &new_flags);
+		if (error)
+			goto out;
+		break;
 	}
 
 	anon_name = anon_vma_name(vma);
@@ -1178,6 +1205,9 @@ madvise_behavior_valid(int behavior)
 	case MADV_HUGEPAGE:
 	case MADV_NOHUGEPAGE:
 	case MADV_COLLAPSE:
+#endif
+#ifdef CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING
+	case MADV_SPLIT:
 #endif
 	case MADV_DONTDUMP:
 	case MADV_DODUMP:
@@ -1368,6 +1398,8 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
  *		transparent huge pages so the existing pages will not be
  *		coalesced into THP and new pages will not be allocated as THP.
  *  MADV_COLLAPSE - synchronously coalesce pages into new THP.
+ *  MADV_SPLIT - allow HugeTLB pages to be mapped at PAGE_SIZE. This allows
+ *		UFFDIO_CONTINUE to accept PAGE_SIZE-aligned regions.
  *  MADV_DONTDUMP - the application wants to prevent pages in the given range
  *		from being included in its core dump.
  *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
-- 
2.39.2.637.g21b0678d19-goog