The patch titled
Subject: kernel/events/uprobes.c: only do FOLL_SPLIT_PMD for uprobe register
has been added to the -mm tree. Its filename is
uprobe-only-do-foll_split_pmd-for-uprobe-register.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/uprobe-only-do-foll_split_pmd-for-uprobe-register.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/uprobe-only-do-foll_split_pmd-for-uprobe-register.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Song Liu <songliubraving@xxxxxx>
Subject: kernel/events/uprobes.c: only do FOLL_SPLIT_PMD for uprobe register
Attaching uprobe to text section in THP splits the PMD mapped page table
into PTE mapped entries. On uprobe detach, we would like to regroup PMD
mapped page table entry to regain performance benefit of THP.
However, the regroup is broken For perf_event based trace_uprobe. This is
because perf_event based trace_uprobe calls uprobe_unregister twice on
close: first in TRACE_REG_PERF_CLOSE, then in TRACE_REG_PERF_UNREGISTER.
The second call will split the PMD mapped page table entry, which is not
the desired behavior.
Fix this by only use FOLL_SPLIT_PMD for uprobe register case.
Add a WARN() to confirm uprobe unregister never work on huge pages, and
abort the operation when this WARN() triggers.
Link: http://lkml.kernel.org/r/20191017164223.2762148-6-songliubraving@xxxxxx
Fixes: 5a52c9df62b4 ("uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT")
Signed-off-by: Song Liu <songliubraving@xxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: William Kucharski <william.kucharski@xxxxxxxxxx>
Cc: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/events/uprobes.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
--- a/kernel/events/uprobes.c~uprobe-only-do-foll_split_pmd-for-uprobe-register
+++ a/kernel/events/uprobes.c
@@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_upro
struct vm_area_struct *vma;
int ret, is_register, ref_ctr_updated = 0;
bool orig_page_huge = false;
+ unsigned int gup_flags = FOLL_FORCE;
is_register = is_swbp_insn(&opcode);
uprobe = container_of(auprobe, struct uprobe, arch);
retry:
+ if (is_register)
+ gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
- ret = get_user_pages_remote(NULL, mm, vaddr, 1,
- FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL);
+ ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+ &old_page, &vma, NULL);
if (ret <= 0)
return ret;
@@ -489,6 +492,12 @@ retry:
if (ret <= 0)
goto put_old;
+ if (WARN(!is_register && PageCompound(old_page),
+ "uprobe unregister should never work on compound page\n")) {
+ ret = -EINVAL;
+ goto put_old;
+ }
+
/* We are going to replace instruction, update ref_ctr. */
if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
_
Patches currently in -mm which might be from songliubraving@xxxxxx are
uprobe-only-do-foll_split_pmd-for-uprobe-register.patch
