+++ /dev/null
-From 8edc6e1688fc8f02c8c1f53a2ec4928cb1055f4d Mon Sep 17 00:00:00 2001
-From: Jan Kara <jack@suse.cz>
-Date: Thu, 13 Nov 2014 15:19:33 -0800
-Subject: [PATCH] fanotify: fix notification of groups with inode & mount marks
-
-fsnotify() needs to merge inode and mount marks lists when notifying
-groups about events so that ignore masks from inode marks are reflected
-in mount mark notifications and groups are notified in proper order
-(according to priorities).
-
-Currently the sorting of the lists done by fsnotify_add_inode_mark() /
-fsnotify_add_vfsmount_mark() and fsnotify() differed which resulted
-ignore masks not being used in some cases.
-
-Fix the problem by always using the same comparison function when
-sorting / merging the mark lists.
-
-Thanks to Heinrich Schuchardt for improvements of my patch.
-
-Link: https://bugzilla.kernel.org/show_bug.cgi?id=87721
-Signed-off-by: Jan Kara <jack@suse.cz>
-Reported-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
-Tested-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
----
- fs/notify/fsnotify.c | 36 +++++++++++++++++++++---------------
- fs/notify/fsnotify.h | 4 ++++
- fs/notify/inode_mark.c | 8 +++-----
- fs/notify/mark.c | 36 ++++++++++++++++++++++++++++++++++++
- fs/notify/vfsmount_mark.c | 8 +++-----
- 5 files changed, 67 insertions(+), 25 deletions(-)
-
-diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
-index 9d3e9c5..89326ac 100644
---- a/fs/notify/fsnotify.c
-+++ b/fs/notify/fsnotify.c
-@@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
- &fsnotify_mark_srcu);
- }
-
-+ /*
-+ * We need to merge inode & vfsmount mark lists so that inode mark
-+ * ignore masks are properly reflected for mount mark notifications.
-+ * That's why this traversal is so complicated...
-+ */
- while (inode_node || vfsmount_node) {
-- inode_group = vfsmount_group = NULL;
-+ inode_group = NULL;
-+ inode_mark = NULL;
-+ vfsmount_group = NULL;
-+ vfsmount_mark = NULL;
-
- if (inode_node) {
- inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
-@@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
- vfsmount_group = vfsmount_mark->group;
- }
-
-- if (inode_group > vfsmount_group) {
-- /* handle inode */
-- ret = send_to_group(to_tell, inode_mark, NULL, mask,
-- data, data_is, cookie, file_name);
-- /* we didn't use the vfsmount_mark */
-- vfsmount_group = NULL;
-- } else if (vfsmount_group > inode_group) {
-- ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
-- data, data_is, cookie, file_name);
-- inode_group = NULL;
-- } else {
-- ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
-- mask, data, data_is, cookie,
-- file_name);
-+ if (inode_group && vfsmount_group) {
-+ int cmp = fsnotify_compare_groups(inode_group,
-+ vfsmount_group);
-+ if (cmp > 0) {
-+ inode_group = NULL;
-+ inode_mark = NULL;
-+ } else if (cmp < 0) {
-+ vfsmount_group = NULL;
-+ vfsmount_mark = NULL;
-+ }
- }
-+ ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
-+ data, data_is, cookie, file_name);
-
- if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
- goto out;
-diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
-index 9c0898c..3b68b0a 100644
---- a/fs/notify/fsnotify.h
-+++ b/fs/notify/fsnotify.h
-@@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
- /* protects reads of inode and vfsmount marks list */
- extern struct srcu_struct fsnotify_mark_srcu;
-
-+/* compare two groups for sorting of marks lists */
-+extern int fsnotify_compare_groups(struct fsnotify_group *a,
-+ struct fsnotify_group *b);
-+
- extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
- __u32 mask);
- /* add a mark to an inode */
-diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
-index e849714..dfbf544 100644
---- a/fs/notify/inode_mark.c
-+++ b/fs/notify/inode_mark.c
-@@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
- {
- struct fsnotify_mark *lmark, *last = NULL;
- int ret = 0;
-+ int cmp;
-
- mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
-
-@@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
- goto out;
- }
-
-- if (mark->group->priority < lmark->group->priority)
-- continue;
--
-- if ((mark->group->priority == lmark->group->priority) &&
-- (mark->group < lmark->group))
-+ cmp = fsnotify_compare_groups(lmark->group, mark->group);
-+ if (cmp < 0)
- continue;
-
- hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
-diff --git a/fs/notify/mark.c b/fs/notify/mark.c
-index d90deaa..34c38fa 100644
---- a/fs/notify/mark.c
-+++ b/fs/notify/mark.c
-@@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
- }
-
- /*
-+ * Sorting function for lists of fsnotify marks.
-+ *
-+ * Fanotify supports different notification classes (reflected as priority of
-+ * notification group). Events shall be passed to notification groups in
-+ * decreasing priority order. To achieve this marks in notification lists for
-+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
-+ * are descending.
-+ *
-+ * Furthermore correct handling of the ignore mask requires processing inode
-+ * and vfsmount marks of each group together. Using the group address as
-+ * further sort criterion provides a unique sorting order and thus we can
-+ * merge inode and vfsmount lists of marks in linear time and find groups
-+ * present in both lists.
-+ *
-+ * A return value of 1 signifies that b has priority over a.
-+ * A return value of 0 signifies that the two marks have to be handled together.
-+ * A return value of -1 signifies that a has priority over b.
-+ */
-+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
-+{
-+ if (a == b)
-+ return 0;
-+ if (!a)
-+ return 1;
-+ if (!b)
-+ return -1;
-+ if (a->priority < b->priority)
-+ return 1;
-+ if (a->priority > b->priority)
-+ return -1;
-+ if (a < b)
-+ return 1;
-+ return -1;
-+}
-+
-+/*
- * Attach an initialized mark to a given group and fs object.
- * These marks may be used for the fsnotify backend to determine which
- * event types should be delivered to which group.
-diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
-index ac851e8..faefa72 100644
---- a/fs/notify/vfsmount_mark.c
-+++ b/fs/notify/vfsmount_mark.c
-@@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
- struct mount *m = real_mount(mnt);
- struct fsnotify_mark *lmark, *last = NULL;
- int ret = 0;
-+ int cmp;
-
- mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
-
-@@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
- goto out;
- }
-
-- if (mark->group->priority < lmark->group->priority)
-- continue;
--
-- if ((mark->group->priority == lmark->group->priority) &&
-- (mark->group < lmark->group))
-+ cmp = fsnotify_compare_groups(lmark->group, mark->group);
-+ if (cmp < 0)
- continue;
-
- hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
---
-1.8.3.1
-
+++ /dev/null
-From 3982d0807e02909957990f194c5ed2ffb6ab6c35 Mon Sep 17 00:00:00 2001
-From: Hugh Dickins <hughd@google.com>
-Date: Mon, 19 Jun 2017 04:03:24 -0700
-Subject: [PATCH 1/3] mm: larger stack guard gap, between vmas
-
-commit 1be7107fbe18eed3e319a6c3e83c78254b693acb upstream.
-
-Stack guard page is a useful feature to reduce a risk of stack smashing
-into a different mapping. We have been using a single page gap which
-is sufficient to prevent having stack adjacent to a different mapping.
-But this seems to be insufficient in the light of the stack usage in
-userspace. E.g. glibc uses as large as 64kB alloca() in many commonly
-used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX]
-which is 256kB or stack strings with MAX_ARG_STRLEN.
-
-This will become especially dangerous for suid binaries and the default
-no limit for the stack size limit because those applications can be
-tricked to consume a large portion of the stack and a single glibc call
-could jump over the guard page. These attacks are not theoretical,
-unfortunatelly.
-
-Make those attacks less probable by increasing the stack guard gap
-to 1MB (on systems with 4k pages; but make it depend on the page size
-because systems with larger base pages might cap stack allocations in
-the PAGE_SIZE units) which should cover larger alloca() and VLA stack
-allocations. It is obviously not a full fix because the problem is
-somehow inherent, but it should reduce attack space a lot.
-
-One could argue that the gap size should be configurable from userspace,
-but that can be done later when somebody finds that the new 1MB is wrong
-for some special case applications. For now, add a kernel command line
-option (stack_guard_gap) to specify the stack gap size (in page units).
-
-Implementation wise, first delete all the old code for stack guard page:
-because although we could get away with accounting one extra page in a
-stack vma, accounting a larger gap can break userspace - case in point,
-a program run with "ulimit -S -v 20000" failed when the 1MB gap was
-counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK
-and strict non-overcommit mode.
-
-Instead of keeping gap inside the stack vma, maintain the stack guard
-gap as a gap between vmas: using vm_start_gap() in place of vm_start
-(or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few
-places which need to respect the gap - mainly arch_get_unmapped_area(),
-and and the vma tree's subtree_gap support for that.
-
-Original-patch-by: Oleg Nesterov <oleg@redhat.com>
-Original-patch-by: Michal Hocko <mhocko@suse.com>
-Signed-off-by: Hugh Dickins <hughd@google.com>
-Acked-by: Michal Hocko <mhocko@suse.com>
-Tested-by: Helge Deller <deller@gmx.de> # parisc
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-[wt: backport to 4.11: adjust context]
-[wt: backport to 4.9: adjust context ; kernel doc was not in admin-guide]
-[wt: backport to 4.4: adjust context ; drop ppc hugetlb_radix changes]
-Signed-off-by: Willy Tarreau <w@1wt.eu>
-[gkh: minor build fixes for 4.4]
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- Documentation/kernel-parameters.txt | 7 ++
- arch/arc/mm/mmap.c | 2 +-
- arch/arm/mm/mmap.c | 4 +-
- arch/frv/mm/elf-fdpic.c | 2 +-
- arch/mips/mm/mmap.c | 2 +-
- arch/parisc/kernel/sys_parisc.c | 15 ++--
- arch/powerpc/mm/slice.c | 2 +-
- arch/s390/mm/mmap.c | 4 +-
- arch/sh/mm/mmap.c | 4 +-
- arch/sparc/kernel/sys_sparc_64.c | 4 +-
- arch/sparc/mm/hugetlbpage.c | 2 +-
- arch/tile/mm/hugetlbpage.c | 2 +-
- arch/x86/kernel/sys_x86_64.c | 4 +-
- arch/x86/mm/hugetlbpage.c | 2 +-
- arch/xtensa/kernel/syscall.c | 2 +-
- fs/hugetlbfs/inode.c | 2 +-
- fs/proc/task_mmu.c | 4 -
- include/linux/mm.h | 53 ++++++-------
- mm/gup.c | 5 --
- mm/memory.c | 38 ---------
- mm/mmap.c | 149 +++++++++++++++++++++---------------
- 21 files changed, 149 insertions(+), 160 deletions(-)
-
-diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
-index c360f80..9738c8b 100644
---- a/Documentation/kernel-parameters.txt
-+++ b/Documentation/kernel-parameters.txt
-@@ -3576,6 +3576,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
- spia_pedr=
- spia_peddr=
-
-+ stack_guard_gap= [MM]
-+ override the default stack gap protection. The value
-+ is in page units and it defines how many pages prior
-+ to (for stacks growing down) resp. after (for stacks
-+ growing up) the main stack are reserved for no other
-+ mapping. Default value is 256 pages.
-+
- stacktrace [FTRACE]
- Enabled the stack tracer on boot up.
-
-diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
-index 2e06d56..cf4ae69 100644
---- a/arch/arc/mm/mmap.c
-+++ b/arch/arc/mm/mmap.c
-@@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
-
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
-index 407dc78..c469c06 100644
---- a/arch/arm/mm/mmap.c
-+++ b/arch/arm/mm/mmap.c
-@@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
-
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-@@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c
-index 836f147..efa59f1 100644
---- a/arch/frv/mm/elf-fdpic.c
-+++ b/arch/frv/mm/elf-fdpic.c
-@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
- addr = PAGE_ALIGN(addr);
- vma = find_vma(current->mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- goto success;
- }
-
-diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
-index 5c81fdd..025cb31 100644
---- a/arch/mips/mm/mmap.c
-+++ b/arch/mips/mm/mmap.c
-@@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
-
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
-index 5aba01a..4dda73c 100644
---- a/arch/parisc/kernel/sys_parisc.c
-+++ b/arch/parisc/kernel/sys_parisc.c
-@@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
- {
- struct mm_struct *mm = current->mm;
-- struct vm_area_struct *vma;
-+ struct vm_area_struct *vma, *prev;
- unsigned long task_size = TASK_SIZE;
- int do_color_align, last_mmap;
- struct vm_unmapped_area_info info;
-@@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
- else
- addr = PAGE_ALIGN(addr);
-
-- vma = find_vma(mm, addr);
-+ vma = find_vma_prev(mm, addr, &prev);
- if (task_size - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)) &&
-+ (!prev || addr >= vm_end_gap(prev)))
- goto found_addr;
- }
-
-@@ -141,7 +142,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
- {
-- struct vm_area_struct *vma;
-+ struct vm_area_struct *vma, *prev;
- struct mm_struct *mm = current->mm;
- unsigned long addr = addr0;
- int do_color_align, last_mmap;
-@@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- addr = COLOR_ALIGN(addr, last_mmap, pgoff);
- else
- addr = PAGE_ALIGN(addr);
-- vma = find_vma(mm, addr);
-+
-+ vma = find_vma_prev(mm, addr, &prev);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)) &&
-+ (!prev || addr >= vm_end_gap(prev)))
- goto found_addr;
- }
-
-diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
-index 0f432a7..6ad12b2 100644
---- a/arch/powerpc/mm/slice.c
-+++ b/arch/powerpc/mm/slice.c
-@@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
- if ((mm->task_size - len) < addr)
- return 0;
- vma = find_vma(mm, addr);
-- return (!vma || (addr + len) <= vma->vm_start);
-+ return (!vma || (addr + len) <= vm_start_gap(vma));
- }
-
- static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
-diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
-index f2b6b1d..126c4a9 100644
---- a/arch/s390/mm/mmap.c
-+++ b/arch/s390/mm/mmap.c
-@@ -97,7 +97,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-@@ -135,7 +135,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
-index 6777177..7df7d59 100644
---- a/arch/sh/mm/mmap.c
-+++ b/arch/sh/mm/mmap.c
-@@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
-
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-@@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
-
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
-index c690c8e..7f0f7c01 100644
---- a/arch/sparc/kernel/sys_sparc_64.c
-+++ b/arch/sparc/kernel/sys_sparc_64.c
-@@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
-
- vma = find_vma(mm, addr);
- if (task_size - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-@@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
-
- vma = find_vma(mm, addr);
- if (task_size - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
-index da11424..ffa842b 100644
---- a/arch/sparc/mm/hugetlbpage.c
-+++ b/arch/sparc/mm/hugetlbpage.c
-@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- addr = ALIGN(addr, HPAGE_SIZE);
- vma = find_vma(mm, addr);
- if (task_size - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
- if (mm->get_unmapped_area == arch_get_unmapped_area)
-diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
-index c034dc3..c97ee6c 100644
---- a/arch/tile/mm/hugetlbpage.c
-+++ b/arch/tile/mm/hugetlbpage.c
-@@ -232,7 +232,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- addr = ALIGN(addr, huge_page_size(h));
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
- if (current->mm->get_unmapped_area == arch_get_unmapped_area)
-diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
-index 10e0272..136ad7c 100644
---- a/arch/x86/kernel/sys_x86_64.c
-+++ b/arch/x86/kernel/sys_x86_64.c
-@@ -143,7 +143,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (end - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-@@ -186,7 +186,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
-index 42982b2..39bdaf3 100644
---- a/arch/x86/mm/hugetlbpage.c
-+++ b/arch/x86/mm/hugetlbpage.c
-@@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- addr = ALIGN(addr, huge_page_size(h));
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
- if (mm->get_unmapped_area == arch_get_unmapped_area)
-diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
-index 83cf496..3aaaae1 100644
---- a/arch/xtensa/kernel/syscall.c
-+++ b/arch/xtensa/kernel/syscall.c
-@@ -87,7 +87,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
- /* At this point: (!vmm || addr < vmm->vm_end). */
- if (TASK_SIZE - len < addr)
- return -ENOMEM;
-- if (!vmm || addr + len <= vmm->vm_start)
-+ if (!vmm || addr + len <= vm_start_gap(vmm))
- return addr;
- addr = vmm->vm_end;
- if (flags & MAP_SHARED)
-diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
-index 595ebdb..a17da8b5 100644
---- a/fs/hugetlbfs/inode.c
-+++ b/fs/hugetlbfs/inode.c
-@@ -191,7 +191,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- addr = ALIGN(addr, huge_page_size(h));
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
-diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
-index d598b9c..cb7020c 100644
---- a/fs/proc/task_mmu.c
-+++ b/fs/proc/task_mmu.c
-@@ -295,11 +295,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
-
- /* We don't show the stack guard page in /proc/maps */
- start = vma->vm_start;
-- if (stack_guard_page_start(vma, start))
-- start += PAGE_SIZE;
- end = vma->vm_end;
-- if (stack_guard_page_end(vma, end))
-- end -= PAGE_SIZE;
-
- seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
- seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
-diff --git a/include/linux/mm.h b/include/linux/mm.h
-index f0ffa01..55f950a 100644
---- a/include/linux/mm.h
-+++ b/include/linux/mm.h
-@@ -1278,39 +1278,11 @@ int clear_page_dirty_for_io(struct page *page);
-
- int get_cmdline(struct task_struct *task, char *buffer, int buflen);
-
--/* Is the vma a continuation of the stack vma above it? */
--static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
--{
-- return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
--}
--
- static inline bool vma_is_anonymous(struct vm_area_struct *vma)
- {
- return !vma->vm_ops;
- }
-
--static inline int stack_guard_page_start(struct vm_area_struct *vma,
-- unsigned long addr)
--{
-- return (vma->vm_flags & VM_GROWSDOWN) &&
-- (vma->vm_start == addr) &&
-- !vma_growsdown(vma->vm_prev, addr);
--}
--
--/* Is the vma a continuation of the stack vma below it? */
--static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
--{
-- return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
--}
--
--static inline int stack_guard_page_end(struct vm_area_struct *vma,
-- unsigned long addr)
--{
-- return (vma->vm_flags & VM_GROWSUP) &&
-- (vma->vm_end == addr) &&
-- !vma_growsup(vma->vm_next, addr);
--}
--
- int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
-
- extern unsigned long move_page_tables(struct vm_area_struct *vma,
-@@ -2012,6 +1984,7 @@ void page_cache_async_readahead(struct address_space *mapping,
- pgoff_t offset,
- unsigned long size);
-
-+extern unsigned long stack_guard_gap;
- /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
- extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
-
-@@ -2040,6 +2013,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
- return vma;
- }
-
-+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
-+{
-+ unsigned long vm_start = vma->vm_start;
-+
-+ if (vma->vm_flags & VM_GROWSDOWN) {
-+ vm_start -= stack_guard_gap;
-+ if (vm_start > vma->vm_start)
-+ vm_start = 0;
-+ }
-+ return vm_start;
-+}
-+
-+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
-+{
-+ unsigned long vm_end = vma->vm_end;
-+
-+ if (vma->vm_flags & VM_GROWSUP) {
-+ vm_end += stack_guard_gap;
-+ if (vm_end < vma->vm_end)
-+ vm_end = -PAGE_SIZE;
-+ }
-+ return vm_end;
-+}
-+
- static inline unsigned long vma_pages(struct vm_area_struct *vma)
- {
- return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-diff --git a/mm/gup.c b/mm/gup.c
-index 4b0b7e7..b599526 100644
---- a/mm/gup.c
-+++ b/mm/gup.c
-@@ -312,11 +312,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
- /* mlock all present pages, but do not fault in new pages */
- if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
- return -ENOENT;
-- /* For mm_populate(), just skip the stack guard page. */
-- if ((*flags & FOLL_POPULATE) &&
-- (stack_guard_page_start(vma, address) ||
-- stack_guard_page_end(vma, address + PAGE_SIZE)))
-- return -ENOENT;
- if (*flags & FOLL_WRITE)
- fault_flags |= FAULT_FLAG_WRITE;
- if (nonblocking)
-diff --git a/mm/memory.c b/mm/memory.c
-index 76dcee3..e6fa134 100644
---- a/mm/memory.c
-+++ b/mm/memory.c
-@@ -2662,40 +2662,6 @@ out_release:
- }
-
- /*
-- * This is like a special single-page "expand_{down|up}wards()",
-- * except we must first make sure that 'address{-|+}PAGE_SIZE'
-- * doesn't hit another vma.
-- */
--static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
--{
-- address &= PAGE_MASK;
-- if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-- struct vm_area_struct *prev = vma->vm_prev;
--
-- /*
-- * Is there a mapping abutting this one below?
-- *
-- * That's only ok if it's the same stack mapping
-- * that has gotten split..
-- */
-- if (prev && prev->vm_end == address)
-- return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
--
-- return expand_downwards(vma, address - PAGE_SIZE);
-- }
-- if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
-- struct vm_area_struct *next = vma->vm_next;
--
-- /* As VM_GROWSDOWN but s/below/above/ */
-- if (next && next->vm_start == address + PAGE_SIZE)
-- return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
--
-- return expand_upwards(vma, address + PAGE_SIZE);
-- }
-- return 0;
--}
--
--/*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
-@@ -2715,10 +2681,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
- if (vma->vm_flags & VM_SHARED)
- return VM_FAULT_SIGBUS;
-
-- /* Check if we need to add a guard page to the stack */
-- if (check_stack_guard_page(vma, address) < 0)
-- return VM_FAULT_SIGSEGV;
--
- /* Use the zero-page for reads */
- if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
- entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
-diff --git a/mm/mmap.c b/mm/mmap.c
-index 455772a..5e043dd 100644
---- a/mm/mmap.c
-+++ b/mm/mmap.c
-@@ -288,6 +288,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
- unsigned long retval;
- unsigned long newbrk, oldbrk;
- struct mm_struct *mm = current->mm;
-+ struct vm_area_struct *next;
- unsigned long min_brk;
- bool populate;
-
-@@ -332,7 +333,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
- }
-
- /* Check against existing mmap mappings. */
-- if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
-+ next = find_vma(mm, oldbrk);
-+ if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
- goto out;
-
- /* Ok, looks good - let it rip. */
-@@ -355,10 +357,22 @@ out:
-
- static long vma_compute_subtree_gap(struct vm_area_struct *vma)
- {
-- unsigned long max, subtree_gap;
-- max = vma->vm_start;
-- if (vma->vm_prev)
-- max -= vma->vm_prev->vm_end;
-+ unsigned long max, prev_end, subtree_gap;
-+
-+ /*
-+ * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
-+ * allow two stack_guard_gaps between them here, and when choosing
-+ * an unmapped area; whereas when expanding we only require one.
-+ * That's a little inconsistent, but keeps the code here simpler.
-+ */
-+ max = vm_start_gap(vma);
-+ if (vma->vm_prev) {
-+ prev_end = vm_end_gap(vma->vm_prev);
-+ if (max > prev_end)
-+ max -= prev_end;
-+ else
-+ max = 0;
-+ }
- if (vma->vm_rb.rb_left) {
- subtree_gap = rb_entry(vma->vm_rb.rb_left,
- struct vm_area_struct, vm_rb)->rb_subtree_gap;
-@@ -451,7 +465,7 @@ static void validate_mm(struct mm_struct *mm)
- anon_vma_unlock_read(anon_vma);
- }
-
-- highest_address = vma->vm_end;
-+ highest_address = vm_end_gap(vma);
- vma = vma->vm_next;
- i++;
- }
-@@ -620,7 +634,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
- if (vma->vm_next)
- vma_gap_update(vma->vm_next);
- else
-- mm->highest_vm_end = vma->vm_end;
-+ mm->highest_vm_end = vm_end_gap(vma);
-
- /*
- * vma->vm_prev wasn't known when we followed the rbtree to find the
-@@ -866,7 +880,7 @@ again: remove_next = 1 + (end > next->vm_end);
- vma_gap_update(vma);
- if (end_changed) {
- if (!next)
-- mm->highest_vm_end = end;
-+ mm->highest_vm_end = vm_end_gap(vma);
- else if (!adjust_next)
- vma_gap_update(next);
- }
-@@ -909,7 +923,7 @@ again: remove_next = 1 + (end > next->vm_end);
- else if (next)
- vma_gap_update(next);
- else
-- mm->highest_vm_end = end;
-+ VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
- }
- if (insert && file)
- uprobe_mmap(insert);
-@@ -1741,7 +1755,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
-
- while (true) {
- /* Visit left subtree if it looks promising */
-- gap_end = vma->vm_start;
-+ gap_end = vm_start_gap(vma);
- if (gap_end >= low_limit && vma->vm_rb.rb_left) {
- struct vm_area_struct *left =
- rb_entry(vma->vm_rb.rb_left,
-@@ -1752,7 +1766,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
- }
- }
-
-- gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
-+ gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
- check_current:
- /* Check if current node has a suitable gap */
- if (gap_start > high_limit)
-@@ -1779,8 +1793,8 @@ check_current:
- vma = rb_entry(rb_parent(prev),
- struct vm_area_struct, vm_rb);
- if (prev == vma->vm_rb.rb_left) {
-- gap_start = vma->vm_prev->vm_end;
-- gap_end = vma->vm_start;
-+ gap_start = vm_end_gap(vma->vm_prev);
-+ gap_end = vm_start_gap(vma);
- goto check_current;
- }
- }
-@@ -1844,7 +1858,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
-
- while (true) {
- /* Visit right subtree if it looks promising */
-- gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
-+ gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
- if (gap_start <= high_limit && vma->vm_rb.rb_right) {
- struct vm_area_struct *right =
- rb_entry(vma->vm_rb.rb_right,
-@@ -1857,7 +1871,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
-
- check_current:
- /* Check if current node has a suitable gap */
-- gap_end = vma->vm_start;
-+ gap_end = vm_start_gap(vma);
- if (gap_end < low_limit)
- return -ENOMEM;
- if (gap_start <= high_limit && gap_end - gap_start >= length)
-@@ -1883,7 +1897,7 @@ check_current:
- struct vm_area_struct, vm_rb);
- if (prev == vma->vm_rb.rb_right) {
- gap_start = vma->vm_prev ?
-- vma->vm_prev->vm_end : 0;
-+ vm_end_gap(vma->vm_prev) : 0;
- goto check_current;
- }
- }
-@@ -1921,7 +1935,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
- {
- struct mm_struct *mm = current->mm;
-- struct vm_area_struct *vma;
-+ struct vm_area_struct *vma, *prev;
- struct vm_unmapped_area_info info;
-
- if (len > TASK_SIZE - mmap_min_addr)
-@@ -1932,9 +1946,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
-
- if (addr) {
- addr = PAGE_ALIGN(addr);
-- vma = find_vma(mm, addr);
-+ vma = find_vma_prev(mm, addr, &prev);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)) &&
-+ (!prev || addr >= vm_end_gap(prev)))
- return addr;
- }
-
-@@ -1957,7 +1972,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
- {
-- struct vm_area_struct *vma;
-+ struct vm_area_struct *vma, *prev;
- struct mm_struct *mm = current->mm;
- unsigned long addr = addr0;
- struct vm_unmapped_area_info info;
-@@ -1972,9 +1987,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- /* requesting a specific address */
- if (addr) {
- addr = PAGE_ALIGN(addr);
-- vma = find_vma(mm, addr);
-+ vma = find_vma_prev(mm, addr, &prev);
- if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-- (!vma || addr + len <= vma->vm_start))
-+ (!vma || addr + len <= vm_start_gap(vma)) &&
-+ (!prev || addr >= vm_end_gap(prev)))
- return addr;
- }
-
-@@ -2099,21 +2115,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
- * update accounting. This is shared with both the
- * grow-up and grow-down cases.
- */
--static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
-+static int acct_stack_growth(struct vm_area_struct *vma,
-+ unsigned long size, unsigned long grow)
- {
- struct mm_struct *mm = vma->vm_mm;
- struct rlimit *rlim = current->signal->rlim;
-- unsigned long new_start, actual_size;
-+ unsigned long new_start;
-
- /* address space limit tests */
- if (!may_expand_vm(mm, grow))
- return -ENOMEM;
-
- /* Stack limit test */
-- actual_size = size;
-- if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
-- actual_size -= PAGE_SIZE;
-- if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
-+ if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
- return -ENOMEM;
-
- /* mlock limit tests */
-@@ -2151,17 +2165,30 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
- int expand_upwards(struct vm_area_struct *vma, unsigned long address)
- {
- struct mm_struct *mm = vma->vm_mm;
-+ struct vm_area_struct *next;
-+ unsigned long gap_addr;
- int error = 0;
-
- if (!(vma->vm_flags & VM_GROWSUP))
- return -EFAULT;
-
- /* Guard against wrapping around to address 0. */
-- if (address < PAGE_ALIGN(address+4))
-- address = PAGE_ALIGN(address+4);
-- else
-+ address &= PAGE_MASK;
-+ address += PAGE_SIZE;
-+ if (!address)
- return -ENOMEM;
-
-+ /* Enforce stack_guard_gap */
-+ gap_addr = address + stack_guard_gap;
-+ if (gap_addr < address)
-+ return -ENOMEM;
-+ next = vma->vm_next;
-+ if (next && next->vm_start < gap_addr) {
-+ if (!(next->vm_flags & VM_GROWSUP))
-+ return -ENOMEM;
-+ /* Check that both stack segments have the same anon_vma? */
-+ }
-+
- /* We must make sure the anon_vma is allocated. */
- if (unlikely(anon_vma_prepare(vma)))
- return -ENOMEM;
-@@ -2206,7 +2233,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
- if (vma->vm_next)
- vma_gap_update(vma->vm_next);
- else
-- mm->highest_vm_end = address;
-+ mm->highest_vm_end = vm_end_gap(vma);
- spin_unlock(&mm->page_table_lock);
-
- perf_event_mmap(vma);
-@@ -2227,6 +2254,8 @@ int expand_downwards(struct vm_area_struct *vma,
- unsigned long address)
- {
- struct mm_struct *mm = vma->vm_mm;
-+ struct vm_area_struct *prev;
-+ unsigned long gap_addr;
- int error;
-
- address &= PAGE_MASK;
-@@ -2234,6 +2263,17 @@ int expand_downwards(struct vm_area_struct *vma,
- if (error)
- return error;
-
-+ /* Enforce stack_guard_gap */
-+ gap_addr = address - stack_guard_gap;
-+ if (gap_addr > address)
-+ return -ENOMEM;
-+ prev = vma->vm_prev;
-+ if (prev && prev->vm_end > gap_addr) {
-+ if (!(prev->vm_flags & VM_GROWSDOWN))
-+ return -ENOMEM;
-+ /* Check that both stack segments have the same anon_vma? */
-+ }
-+
- /* We must make sure the anon_vma is allocated. */
- if (unlikely(anon_vma_prepare(vma)))
- return -ENOMEM;
-@@ -2289,28 +2329,25 @@ int expand_downwards(struct vm_area_struct *vma,
- return error;
- }
-
--/*
-- * Note how expand_stack() refuses to expand the stack all the way to
-- * abut the next virtual mapping, *unless* that mapping itself is also
-- * a stack mapping. We want to leave room for a guard page, after all
-- * (the guard page itself is not added here, that is done by the
-- * actual page faulting logic)
-- *
-- * This matches the behavior of the guard page logic (see mm/memory.c:
-- * check_stack_guard_page()), which only allows the guard page to be
-- * removed under these circumstances.
-- */
-+/* enforced gap between the expanding stack and other mappings. */
-+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
-+
-+static int __init cmdline_parse_stack_guard_gap(char *p)
-+{
-+ unsigned long val;
-+ char *endptr;
-+
-+ val = simple_strtoul(p, &endptr, 10);
-+ if (!*endptr)
-+ stack_guard_gap = val << PAGE_SHIFT;
-+
-+ return 0;
-+}
-+__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
-+
- #ifdef CONFIG_STACK_GROWSUP
- int expand_stack(struct vm_area_struct *vma, unsigned long address)
- {
-- struct vm_area_struct *next;
--
-- address &= PAGE_MASK;
-- next = vma->vm_next;
-- if (next && next->vm_start == address + PAGE_SIZE) {
-- if (!(next->vm_flags & VM_GROWSUP))
-- return -ENOMEM;
-- }
- return expand_upwards(vma, address);
- }
-
-@@ -2332,14 +2369,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
- #else
- int expand_stack(struct vm_area_struct *vma, unsigned long address)
- {
-- struct vm_area_struct *prev;
--
-- address &= PAGE_MASK;
-- prev = vma->vm_prev;
-- if (prev && prev->vm_end == address) {
-- if (!(prev->vm_flags & VM_GROWSDOWN))
-- return -ENOMEM;
-- }
- return expand_downwards(vma, address);
- }
-
-@@ -2437,7 +2466,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
- vma->vm_prev = prev;
- vma_gap_update(vma);
- } else
-- mm->highest_vm_end = prev ? prev->vm_end : 0;
-+ mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
- tail_vma->vm_next = NULL;
-
- /* Kill the cache */
---
-2.1.4
-
Code Review / AGL / meta-agl.git / commitdiff