lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230105101844.1893104-10-jthoughton@google.com>
Date:   Thu,  5 Jan 2023 10:18:07 +0000
From:   James Houghton <jthoughton@...gle.com>
To:     Mike Kravetz <mike.kravetz@...cle.com>,
        Muchun Song <songmuchun@...edance.com>,
        Peter Xu <peterx@...hat.com>
Cc:     David Hildenbrand <david@...hat.com>,
        David Rientjes <rientjes@...gle.com>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        Mina Almasry <almasrymina@...gle.com>,
        "Zach O'Keefe" <zokeefe@...gle.com>,
        Manish Mishra <manish.mishra@...anix.com>,
        Naoya Horiguchi <naoya.horiguchi@....com>,
        "Dr . David Alan Gilbert" <dgilbert@...hat.com>,
        "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Baolin Wang <baolin.wang@...ux.alibaba.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Yang Shi <shy828301@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org,
        James Houghton <jthoughton@...gle.com>
Subject: [PATCH 09/46] mm: add MADV_SPLIT to enable HugeTLB HGM

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@...gle.com>
---
 arch/alpha/include/uapi/asm/mman.h     |  2 ++
 arch/mips/include/uapi/asm/mman.h      |  2 ++
 arch/parisc/include/uapi/asm/mman.h    |  2 ++
 arch/xtensa/include/uapi/asm/mman.h    |  2 ++
 include/linux/hugetlb.h                |  2 ++
 include/uapi/asm-generic/mman-common.h |  2 ++
 mm/hugetlb.c                           |  3 +--
 mm/madvise.c                           | 26 ++++++++++++++++++++++++++
 8 files changed, 39 insertions(+), 2 deletions(-)

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/linux/hugetlb.h b/include/linux/hugetlb.h
index 8713d9c4f86c..16fc3e381801 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -109,6 +109,8 @@ struct hugetlb_vma_lock {
 	struct vm_area_struct *vma;
 };
 
+void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
+
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 
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/hugetlb.c b/mm/hugetlb.c
index d27fe05d5ef6..5bd53ae8ca4b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -92,7 +92,6 @@ struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
-static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
@@ -361,7 +360,7 @@ static void hugetlb_vma_lock_free(struct vm_area_struct *vma)
 	}
 }
 
-static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
+void hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
 {
 	struct hugetlb_vma_lock *vma_lock;
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 025be3517af1..04ee28992e52 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1011,6 +1011,24 @@ static long madvise_remove(struct vm_area_struct *vma,
 	return error;
 }
 
+static int madvise_split(struct vm_area_struct *vma,
+			 unsigned long *new_flags)
+{
+	if (!is_vm_hugetlb_page(vma) || !hugetlb_hgm_eligible(vma))
+		return -EINVAL;
+	/*
+	 * Attempt to allocate the VMA lock again. If it isn't allocated,
+	 * MADV_COLLAPSE won't work.
+	 */
+	hugetlb_vma_lock_alloc(vma);
+
+	/* PMD sharing doesn't work with HGM. */
+	hugetlb_unshare_all_pmds(vma);
+
+	*new_flags |= VM_HUGETLB_HGM;
+	return 0;
+}
+
 /*
  * 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
@@ -1089,6 +1107,11 @@ 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);
@@ -1183,6 +1206,9 @@ 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:
-- 
2.39.0.314.g84b9a713c41-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ