diff mbox series

[v2,5/5] uprobe: only do FOLL_SPLIT_PMD for uprobe register

Message ID 20191017164223.2762148-6-songliubraving@fb.com (mailing list archive)
State New, archived
Headers show
Series Fixes for THP in page cache | expand

Commit Message

Song Liu Oct. 17, 2019, 4:42 p.m. UTC 
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.

Fixes: 5a52c9df62b4 ("uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT")
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 kernel/events/uprobes.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

Comments

Srikar Dronamraju Oct. 18, 2019, 12:52 p.m. UTC | #1 
* Song Liu <songliubraving@fb.com> [2019-10-17 09:42:22]:

> 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.
> 
> Fixes: 5a52c9df62b4 ("uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT")
> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> Cc: Oleg Nesterov <oleg@redhat.com>
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---

Looks good to me.

Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

>  kernel/events/uprobes.c | 13 +++++++++++--
>  1 file changed, 11 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
> index 94d38a39d72e..c74761004ee5 100644
> --- a/kernel/events/uprobes.c
> +++ b/kernel/events/uprobes.c
> @@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
>  	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 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
>  	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);
> -- 
> 2.17.1
>
diff mbox series

Patch

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 94d38a39d72e..c74761004ee5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -474,14 +474,17 @@  int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	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 @@  int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	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);