On 1/27/23 4:05 AM, Peter Xu wrote:
> On Tue, Jan 24, 2023 at 01:43:20PM +0500, Muhammad Usama Anjum wrote:
>> Add new WP Async mode (UFFD_FEATURE_WP_ASYNC) which resolves the page
>> faults on its own. It can be used to track that which pages have been
>> written-to from the time the pages were write-protected. It is very
>> efficient way to track the changes as uffd is by nature pte/pmd based.
>>
>> UFFD synchronous WP sends the page faults to the userspace where the
>> pages which have been written-to can be tracked. But it is not efficient.
>> This is why this asynchronous version is being added. After setting the
>> WP Async, the pages which have been written to can be found in the pagemap
>> file or information can be obtained from the PAGEMAP_IOCTL.
>>
>> Suggested-by: Peter Xu <peterx@xxxxxxxxxx>
>> Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
>> ---
>> Changes in v7:
>> - Remove UFFDIO_WRITEPROTECT_MODE_ASYNC_WP and add UFFD_FEATURE_WP_ASYNC
>> - Handle automatic page fault resolution in better way (thanks to Peter)
>> ---
>> fs/userfaultfd.c | 11 +++++++++++
>> include/linux/userfaultfd_k.h | 6 ++++++
>> include/uapi/linux/userfaultfd.h | 8 +++++++-
>> mm/memory.c | 29 +++++++++++++++++++++++++++--
>> 4 files changed, 51 insertions(+), 3 deletions(-)
>>
>> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
>> index 15a5bf765d43..b82af02092ce 100644
>> --- a/fs/userfaultfd.c
>> +++ b/fs/userfaultfd.c
>> @@ -1867,6 +1867,10 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
>> mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
>> mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
>>
>> + /* Write protection cannot be disabled in case of aync WP */
>
> s/aync/async/
>
> A slight reworded version:
>
> /* Unprotection is not supported if in async WP mode */
>
Will fix in next version.
>> + if (!mode_wp && (ctx->features & UFFD_FEATURE_WP_ASYNC))
>> + return -EINVAL;
>> +
>> if (mode_wp && mode_dontwake)
>> return -EINVAL;
>>
>> @@ -1950,6 +1954,13 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
>> return ret;
>> }
>>
>> +int userfaultfd_wp_async(struct vm_area_struct *vma)
>> +{
>> + struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
>> +
>> + return (ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC));
>> +}
>> +
>> static inline unsigned int uffd_ctx_features(__u64 user_features)
>> {
>> /*
>> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
>> index 9df0b9a762cc..5db51fccae1d 100644
>> --- a/include/linux/userfaultfd_k.h
>> +++ b/include/linux/userfaultfd_k.h
>> @@ -179,6 +179,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
>> unsigned long end, struct list_head *uf);
>> extern void userfaultfd_unmap_complete(struct mm_struct *mm,
>> struct list_head *uf);
>> +extern int userfaultfd_wp_async(struct vm_area_struct *vma);
>>
>> #else /* CONFIG_USERFAULTFD */
>>
>> @@ -274,6 +275,11 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
>> return false;
>> }
>>
>> +int userfaultfd_wp_async(struct vm_area_struct *vma)
>> +{
>> + return false;
>> +}
>> +
>> #endif /* CONFIG_USERFAULTFD */
>>
>> static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
>> diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
>> index 005e5e306266..f4252ef40071 100644
>> --- a/include/uapi/linux/userfaultfd.h
>> +++ b/include/uapi/linux/userfaultfd.h
>> @@ -38,7 +38,8 @@
>> UFFD_FEATURE_MINOR_HUGETLBFS | \
>> UFFD_FEATURE_MINOR_SHMEM | \
>> UFFD_FEATURE_EXACT_ADDRESS | \
>> - UFFD_FEATURE_WP_HUGETLBFS_SHMEM)
>> + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \
>> + UFFD_FEATURE_WP_ASYNC)
>> #define UFFD_API_IOCTLS \
>> ((__u64)1 << _UFFDIO_REGISTER | \
>> (__u64)1 << _UFFDIO_UNREGISTER | \
>> @@ -203,6 +204,10 @@ struct uffdio_api {
>> *
>> * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
>> * write-protection mode is supported on both shmem and hugetlbfs.
>> + *
>> + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection
>> + * asynchronous mode is supported in which the write fault is automatically
>> + * resolved and write-protection is un-set.
>> */
>> #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
>> #define UFFD_FEATURE_EVENT_FORK (1<<1)
>> @@ -217,6 +222,7 @@ struct uffdio_api {
>> #define UFFD_FEATURE_MINOR_SHMEM (1<<10)
>> #define UFFD_FEATURE_EXACT_ADDRESS (1<<11)
>> #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12)
>> +#define UFFD_FEATURE_WP_ASYNC (1<<13)
>> __u64 features;
>>
>> __u64 ioctls;
>> diff --git a/mm/memory.c b/mm/memory.c
>> index 4000e9f017e0..8c03b133d483 100644
>> --- a/mm/memory.c
>> +++ b/mm/memory.c
>> @@ -3351,6 +3351,18 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
>>
>> if (likely(!unshare)) {
>> if (userfaultfd_pte_wp(vma, *vmf->pte)) {
>> + if (userfaultfd_wp_async(vma)) {
>> + /*
>> + * Nothing needed (cache flush, TLB invalidations,
>> + * etc.) because we're only removing the uffd-wp bit,
>> + * which is completely invisible to the user. This
>> + * falls through to possible CoW.
>
> Here it says it falls through to CoW, but..
>
>> + */
>> + pte_unmap_unlock(vmf->pte, vmf->ptl);
>> + set_pte_at(vma->vm_mm, vmf->address, vmf->pte,
>> + pte_clear_uffd_wp(*vmf->pte));
>> + return 0;
>
> ... it's not doing so. The original lines should do:
>
> https://lore.kernel.org/all/Y8qq0dKIJBshua+X@x1n/
>
> Side note: you cannot modify pgtable after releasing the pgtable lock.
> It's racy.
If I don't unlock and return after removing the UFFD_WP flag in case of
async wp, the target just gets stuck. Maybe the pte lock is not unlocked in
some path.
If I unlock and don't return, the crash happens.
So I'd put unlock and return from here. Please comment on the below patch
and what do you think should be done. I've missed something.
>
>> + }
>> pte_unmap_unlock(vmf->pte, vmf->ptl);
>> return handle_userfault(vmf, VM_UFFD_WP);
>> }
>> @@ -4812,8 +4824,21 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
>>
>> if (vma_is_anonymous(vmf->vma)) {
>> if (likely(!unshare) &&
>> - userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
>> - return handle_userfault(vmf, VM_UFFD_WP);
>> + userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) {
>> + if (userfaultfd_wp_async(vmf->vma)) {
>> + /*
>> + * Nothing needed (cache flush, TLB invalidations,
>> + * etc.) because we're only removing the uffd-wp bit,
>> + * which is completely invisible to the user. This
>> + * falls through to possible CoW.
>> + */
>> + set_pmd_at(vmf->vma->vm_mm, vmf->address, vmf->pmd,
>> + pmd_clear_uffd_wp(*vmf->pmd));
>
> This is for THP, not hugetlb.
>
> Clearing uffd-wp bit here for the whole pmd is wrong to me, because we
> track writes in small page sizes only. We should just split.
By detecting if the fault is async wp, just splitting the PMD doesn't work.
The below given snippit is working right now. But definately, the fault of
the whole PMD is being resolved which if we can bypass by correctly
splitting would be highly desirable. Can you please take a look on UFFD
side and suggest the changes? It would be much appreciated. I'm attaching
WIP v9 patches for you to apply on next(next-20230105) and pagemap_ioctl
selftest can be ran to test things after making changes.
>
> The relevant code for hugetlb resides in hugetlb_fault().
>
>> + return 0;
>> + } else {
>> + return handle_userfault(vmf, VM_UFFD_WP);
>> + }
>> + }
>> return do_huge_pmd_wp_page(vmf);
>> }
>>
>> --
>> 2.30.2
>>
>
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3351,6 +3351,18 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
if (likely(!unshare)) {
if (userfaultfd_pte_wp(vma, *vmf->pte)) {
+ if (userfaultfd_wp_async(vma)) {
+ set_pte_at(vma->vm_mm, vmf->address,
+ vmf->pte,
+ pte_clear_uffd_wp(*vmf->pte));
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ return 0;
+ }
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_WP);
}
@@ -4812,8 +4824,21 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault
*vmf)
if (vma_is_anonymous(vmf->vma)) {
if (likely(!unshare) &&
- userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
- return handle_userfault(vmf, VM_UFFD_WP);
+ userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) {
+ if (userfaultfd_wp_async(vmf->vma)) {
+ set_pmd_at(vmf->vma->vm_mm, vmf->address,
+ vmf->pmd,
+ pmd_clear_uffd_wp(*vmf->pmd));
+ return 0;
+ } else {
+ return handle_userfault(vmf, VM_UFFD_WP);
+ }
+ }
return do_huge_pmd_wp_page(vmf);
}
--
BR,
Muhammad Usama AnjumFrom 774e3cd2e67f5e94f9994a75aac3a3e13ccd6deb Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Date: Fri, 27 Jan 2023 11:42:53 +0500
Subject: [PATCH WIP v9 0/4] Implement IOCTL to get and/or the clear info about
PTEs
*Changes in v9:*
- Fix build warnings and errors which were happening on some configs
- Simplify pagemap ioctl's code
*Changes in v8:*
- Update uffd async wp implementation
- Improve PAGEMAP_IOCTL implementation
*Changes in v7:*
- Add uffd wp async
- Update the IOCTL to use uffd under the hood instead of soft-dirty
flags
Hello,
Note:
Soft-dirty pages and pages which have been written-to are synonyms. As
kernel already has soft-dirty feature inside which we have given up to
use, we are using written-to terminology while using UFFD async WP under
the hood.
This IOCTL, PAGEMAP_SCAN on pagemap file can be used to get and/or clear
the info about page table entries. The following operations are
supported in this ioctl:
- Get the information if the pages have been written-to (PAGE_IS_WT),
file mapped (PAGE_IS_FILE), present (PAGE_IS_PRESENT) or swapped
(PAGE_IS_SWAPPED).
- Write-protect the pages (PAGEMAP_WP_ENGAGE) to start finding which
pages have been written-to.
- Find pages which have been written-to and write protect the pages
(atomic PAGE_IS_WT + PAGEMAP_WP_ENGAGE)
It is possible to find and clear soft-dirty pages entirely in userspace.
But it isn't efficient:
- The mprotect and SIGSEGV handler for bookkeeping
- The userfaultfd wp with the handler for bookkeeping
Some benchmarks can be seen here[1]. This series adds features that weren't
present earlier:
- There is no atomic get soft-dirty PTE bit status and clear present in
the kernel.
- The pages which have been written-to can not be found in accurate way.
(Kernel's soft-dirty PTE bit + sof_dirty VMA bit shows more soft-dirty
pages than there actually are.)
Historically, soft-dirty PTE bit tracking has been used in the CRIU
project. The procfs interface is enough for finding the soft-dirty bit
status and clearing the soft-dirty bit of all the pages of a process.
We have the use case where we need to track the soft-dirty PTE bit for
only specific pages on demand. We need this tracking and clear mechanism
of a region of memory while the process is running to emulate the
getWriteWatch() syscall of Windows.
*(Moved to using UFFD instead of soft-dirty to find pages which have been
written-to from v7 patch series)*:
Stop using the soft-dirty flags for finding which pages have been
written to. It is too delicate and wrong as it shows more soft-dirty
pages than the actual soft-dirty pages. There is no interest in
correcting it [2][3] as this is how the feature was written years ago.
It shouldn't be updated to changed behaviour. Peter Xu has suggested
using the async version of the UFFD WP [4] as it is based inherently
on the PTEs.
So in this patch series, I've added a new mode to the UFFD which is
asynchronous version of the write protect. When this variant of the
UFFD WP is used, the page faults are resolved automatically by the
kernel. The pages which have been written-to can be found by reading
pagemap file (!PM_UFFD_WP). This feature can be used successfully to
find which pages have been written to from the time the pages were
write protected. This works just like the soft-dirty flag without
showing any extra pages which aren't soft-dirty in reality.
The information related to pages if the page is file mapped, present and
swapped is required for the CRIU project [5][6]. The addition of the
required mask, any mask, excluded mask and return masks are also required
for the CRIU project [5].
The IOCTL returns the addresses of the pages which match the specific masks.
The page addresses are returned in struct page_region in a compact form.
The max_pages is needed to support a use case where user only wants to get
a specific number of pages. So there is no need to find all the pages of
interest in the range when max_pages is specified. The IOCTL returns when
the maximum number of the pages are found. The max_pages is optional. If
max_pages is specified, it must be equal or greater than the vec_size.
This restriction is needed to handle worse case when one page_region only
contains info of one page and it cannot be compacted. This is needed to
emulate the Windows getWriteWatch() syscall.
The patch series include the detailed selftest which can be used as an example
for the uffd async wp test and PAGEMAP_IOCTL. It shows the interface usages as
well.
[1] https://lore.kernel.org/lkml/54d4c322-cd6e-eefd-b161-2af2b56aae24@xxxxxxxxxxxxx/
[2] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@xxxxxxxxxxxxx
[3] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@xxxxxxxxxxxxx
[4] https://lore.kernel.org/all/Y6Hc2d+7eTKs7AiH@x1n
[5] https://lore.kernel.org/all/YyiDg79flhWoMDZB@xxxxxxxxx/
[6] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@xxxxxxxxxx/
Regards,
Muhammad Usama Anjum
Muhammad Usama Anjum (4):
userfaultfd: Add UFFD WP Async support
userfaultfd: split mwriteprotect_range()
fs/proc/task_mmu: Implement IOCTL to get and/or the clear info about
PTEs
selftests: vm: add pagemap ioctl tests
fs/proc/task_mmu.c | 283 +++++++
fs/userfaultfd.c | 21 +
include/linux/userfaultfd_k.h | 17 +
include/uapi/linux/fs.h | 50 ++
include/uapi/linux/userfaultfd.h | 8 +-
mm/memory.c | 29 +-
mm/userfaultfd.c | 40 +-
tools/include/uapi/linux/fs.h | 50 ++
tools/testing/selftests/vm/.gitignore | 1 +
tools/testing/selftests/vm/Makefile | 5 +-
tools/testing/selftests/vm/pagemap_ioctl.c | 880 +++++++++++++++++++++
11 files changed, 1364 insertions(+), 20 deletions(-)
create mode 100644 tools/testing/selftests/vm/pagemap_ioctl.c
--
2.30.2
From 5fb45900be6104936d88c3a2e3bd14ea937dd920 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Date: Tue, 3 Jan 2023 12:47:31 +0500
Subject: [PATCH WIP v9 1/4] userfaultfd: Add UFFD WP Async support
Add new WP Async mode (UFFD_FEATURE_WP_ASYNC) which resolves the page
faults on its own. It can be used to track that which pages have been
written-to from the time the pages were write-protected. It is very
efficient way to track the changes as uffd is by nature pte/pmd based.
UFFD synchronous WP sends the page faults to the userspace where the
pages which have been written-to can be tracked. But it is not efficient.
This is why this asynchronous version is being added. After setting the
WP Async, the pages which have been written to can be found in the pagemap
file or information can be obtained from the PAGEMAP_IOCTL.
Suggested-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
---
Changes in v7:
- Remove UFFDIO_WRITEPROTECT_MODE_ASYNC_WP and add UFFD_FEATURE_WP_ASYNC
- Handle automatic page fault resolution in better way (thanks to Peter)
---
fs/userfaultfd.c | 11 +++++++++++
include/linux/userfaultfd_k.h | 6 ++++++
include/uapi/linux/userfaultfd.h | 8 +++++++-
mm/memory.c | 29 +++++++++++++++++++++++++++--
4 files changed, 51 insertions(+), 3 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 15a5bf765d43..c17835a0e842 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1867,6 +1867,10 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
+ /* The unprotection is not supported if in async WP mode */
+ if (!mode_wp && (ctx->features & UFFD_FEATURE_WP_ASYNC))
+ return -EINVAL;
+
if (mode_wp && mode_dontwake)
return -EINVAL;
@@ -1950,6 +1954,13 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
return ret;
}
+int userfaultfd_wp_async(struct vm_area_struct *vma)
+{
+ struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ return (ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC));
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9df0b9a762cc..94dcb4dc1b4a 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -179,6 +179,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
unsigned long end, struct list_head *uf);
extern void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf);
+extern int userfaultfd_wp_async(struct vm_area_struct *vma);
#else /* CONFIG_USERFAULTFD */
@@ -274,6 +275,11 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
return false;
}
+static inline int userfaultfd_wp_async(struct vm_area_struct *vma)
+{
+ return false;
+}
+
#endif /* CONFIG_USERFAULTFD */
static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 005e5e306266..f4252ef40071 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -38,7 +38,8 @@
UFFD_FEATURE_MINOR_HUGETLBFS | \
UFFD_FEATURE_MINOR_SHMEM | \
UFFD_FEATURE_EXACT_ADDRESS | \
- UFFD_FEATURE_WP_HUGETLBFS_SHMEM)
+ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \
+ UFFD_FEATURE_WP_ASYNC)
#define UFFD_API_IOCTLS \
((__u64)1 << _UFFDIO_REGISTER | \
(__u64)1 << _UFFDIO_UNREGISTER | \
@@ -203,6 +204,10 @@ struct uffdio_api {
*
* UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
* write-protection mode is supported on both shmem and hugetlbfs.
+ *
+ * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection
+ * asynchronous mode is supported in which the write fault is automatically
+ * resolved and write-protection is un-set.
*/
#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
#define UFFD_FEATURE_EVENT_FORK (1<<1)
@@ -217,6 +222,7 @@ struct uffdio_api {
#define UFFD_FEATURE_MINOR_SHMEM (1<<10)
#define UFFD_FEATURE_EXACT_ADDRESS (1<<11)
#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12)
+#define UFFD_FEATURE_WP_ASYNC (1<<13)
__u64 features;
__u64 ioctls;
diff --git a/mm/memory.c b/mm/memory.c
index 4000e9f017e0..da53fb53ddb7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3351,6 +3351,18 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
if (likely(!unshare)) {
if (userfaultfd_pte_wp(vma, *vmf->pte)) {
+ if (userfaultfd_wp_async(vma)) {
+ /*
+ * Nothing needed (cache flush, TLB invalidations,
+ * etc.) because we're only removing the uffd-wp bit,
+ * which is completely invisible to the user. This
+ * falls through to possible CoW.
+ */
+ set_pte_at(vma->vm_mm, vmf->address, vmf->pte,
+ pte_clear_uffd_wp(*vmf->pte));
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ return 0;
+ }
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_WP);
}
@@ -4812,8 +4824,21 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
if (vma_is_anonymous(vmf->vma)) {
if (likely(!unshare) &&
- userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
- return handle_userfault(vmf, VM_UFFD_WP);
+ userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) {
+ if (userfaultfd_wp_async(vmf->vma)) {
+ /*
+ * Nothing needed (cache flush, TLB invalidations,
+ * etc.) because we're only removing the uffd-wp bit,
+ * which is completely invisible to the user. This
+ * falls through to possible CoW.
+ */
+ set_pmd_at(vmf->vma->vm_mm, vmf->address, vmf->pmd,
+ pmd_clear_uffd_wp(*vmf->pmd));
+ return 0;
+ } else {
+ return handle_userfault(vmf, VM_UFFD_WP);
+ }
+ }
return do_huge_pmd_wp_page(vmf);
}
--
2.30.2
From ee03645744e3129fb93022bfeb003b89252923ac Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Date: Tue, 3 Jan 2023 12:48:59 +0500
Subject: [PATCH WIP v9 2/4] userfaultfd: split mwriteprotect_range()
Split mwriteprotect_range() to create a unlocked version. This
will be used in the next patch to write protect a memory area.
Add a helper function, wp_range_async() as well.
Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
---
Changes in v7:
- Remove async being set in the PAGEMAP_IOCTL
---
fs/userfaultfd.c | 10 +++++++++
include/linux/userfaultfd_k.h | 11 ++++++++++
mm/userfaultfd.c | 40 ++++++++++++++++++++++-------------
3 files changed, 46 insertions(+), 15 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index c17835a0e842..8791a2d371c1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1961,6 +1961,16 @@ int userfaultfd_wp_async(struct vm_area_struct *vma)
return (ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC));
}
+int wp_range_async(struct vm_area_struct *vma, unsigned long start, unsigned long len)
+{
+ struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ if (!ctx)
+ return -1;
+
+ return __mwriteprotect_range(ctx->mm, start, len, true, &ctx->mmap_changing);
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 94dcb4dc1b4a..76407d21d03b 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -73,6 +73,9 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
extern int mwriteprotect_range(struct mm_struct *dst_mm,
unsigned long start, unsigned long len,
bool enable_wp, atomic_t *mmap_changing);
+extern int __mwriteprotect_range(struct mm_struct *dst_mm,
+ unsigned long start, unsigned long len,
+ bool enable_wp, atomic_t *mmap_changing);
extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
unsigned long start, unsigned long len, bool enable_wp);
@@ -180,6 +183,8 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
extern void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf);
extern int userfaultfd_wp_async(struct vm_area_struct *vma);
+extern int wp_range_async(struct vm_area_struct *vma, unsigned long start,
+ unsigned long len);
#else /* CONFIG_USERFAULTFD */
@@ -280,6 +285,12 @@ static inline int userfaultfd_wp_async(struct vm_area_struct *vma)
return false;
}
+static inline int wp_range_async(struct vm_area_struct *vma, unsigned long start,
+ unsigned long len)
+{
+ return -1;
+}
+
#endif /* CONFIG_USERFAULTFD */
static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 65ad172add27..9d8a43faf764 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -734,25 +734,13 @@ void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma,
tlb_finish_mmu(&tlb);
}
-int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, bool enable_wp,
- atomic_t *mmap_changing)
+int __mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
+ unsigned long len, bool enable_wp,
+ atomic_t *mmap_changing)
{
struct vm_area_struct *dst_vma;
unsigned long page_mask;
int err;
-
- /*
- * Sanitize the command parameters:
- */
- BUG_ON(start & ~PAGE_MASK);
- BUG_ON(len & ~PAGE_MASK);
-
- /* Does the address range wrap, or is the span zero-sized? */
- BUG_ON(start + len <= start);
-
- mmap_read_lock(dst_mm);
-
/*
* If memory mappings are changing because of non-cooperative
* operation (e.g. mremap) running in parallel, bail out and
@@ -783,6 +771,28 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
err = 0;
out_unlock:
+ return err;
+}
+
+int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
+ unsigned long len, bool enable_wp,
+ atomic_t *mmap_changing)
+{
+ int err;
+
+ /*
+ * Sanitize the command parameters:
+ */
+ BUG_ON(start & ~PAGE_MASK);
+ BUG_ON(len & ~PAGE_MASK);
+
+ /* Does the address range wrap, or is the span zero-sized? */
+ BUG_ON(start + len <= start);
+
+ mmap_read_lock(dst_mm);
+
+ err = __mwriteprotect_range(dst_mm, start, len, enable_wp, mmap_changing);
+
mmap_read_unlock(dst_mm);
return err;
}
--
2.30.2
From ff4453af31a0504cc09647bbfffc11eaf80b07b8 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Date: Tue, 3 Jan 2023 12:50:21 +0500
Subject: [PATCH WIP v9 3/4] fs/proc/task_mmu: Implement IOCTL to get and/or
the clear info about PTEs
This IOCTL, PAGEMAP_SCAN on pagemap file can be used to get and/or clear
the info about page table entries. The following operations are supported
in this ioctl:
- Get the information if the pages have been written-to (PAGE_IS_WT),
file mapped (PAGE_IS_FILE), present (PAGE_IS_PRESENT) or swapped
(PAGE_IS_SWAPPED).
- Write-protect the pages (PAGEMAP_WP_ENGAGE) to start finding which
pages have been written-to.
- Find pages which have been written-to and write protect the pages
(atomic PAGE_IS_WT + PAGEMAP_WP_ENGAGE)
The uffd should have been registered on the memory range before performing
any WP/WT (Write Protect/Writtern-To) related operations with the IOCTL.
struct pagemap_scan_args is used as the argument of the IOCTL. In this
struct:
- The range is specified through start and len.
- The output buffer of struct page_region array and size is specified as
vec and vec_len.
- The optional maximum requested pages are specified in the max_pages.
- The flags can be specified in the flags field. The PAGEMAP_WP_ENGAGE
is the only added flag at this time.
- The masks are specified in required_mask, anyof_mask, excluded_ mask
and return_mask.
This IOCTL can be extended to get information about more PTE bits. This
IOCTL doesn't support hugetlbs at the moment. No information about
hugetlb can be obtained. This patch has evolved from a basic patch from
Gabriel Krisman Bertazi.
Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
---
Change in v8:
- Correct is_pte_uffd_wp()
- Improve readability and error checks
- Remove some un-needed code
Changes in v7:
- Rebase on top of latest next
- Fix some corner cases
- Base soft-dirty on the uffd wp async
- Update the terminologies
- Optimize the memory usage inside the ioctl
Changes in v6:
- Rename variables and update comments
- Make IOCTL independent of soft_dirty config
- Change masks and bitmap type to _u64
- Improve code quality
Changes in v5:
- Remove tlb flushing even for clear operation
Changes in v4:
- Update the interface and implementation
Changes in v3:
- Tighten the user-kernel interface by using explicit types and add more
error checking
Changes in v2:
- Convert the interface from syscall to ioctl
- Remove pidfd support as it doesn't make sense in ioctl
---
fs/proc/task_mmu.c | 283 ++++++++++++++++++++++++++++++++++
include/uapi/linux/fs.h | 50 ++++++
tools/include/uapi/linux/fs.h | 50 ++++++
3 files changed, 383 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e35a0398db63..64a6597aec06 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -19,6 +19,7 @@
#include <linux/shmem_fs.h>
#include <linux/uaccess.h>
#include <linux/pkeys.h>
+#include <linux/minmax.h>
#include <asm/elf.h>
#include <asm/tlb.h>
@@ -1135,6 +1136,22 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
}
#endif
+static inline bool is_pte_uffd_wp(pte_t pte)
+{
+ if ((pte_present(pte) && pte_uffd_wp(pte)) ||
+ (is_swap_pte(pte) && pte_swp_uffd_wp_any(pte)))
+ return true;
+ return false;
+}
+
+static inline bool is_pmd_uffd_wp(pmd_t pmd)
+{
+ if ((pmd_present(pmd) && pmd_uffd_wp(pmd)) ||
+ (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd)))
+ return true;
+ return false;
+}
+
#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
@@ -1763,11 +1780,277 @@ static int pagemap_release(struct inode *inode, struct file *file)
return 0;
}
+#define PAGEMAP_OP_MASK (PAGE_IS_WT | PAGE_IS_FILE | \
+ PAGE_IS_PRESENT | PAGE_IS_SWAPPED)
+#define PAGEMAP_NONWT_OP_MASK (PAGE_IS_FILE | PAGE_IS_PRESENT | PAGE_IS_SWAPPED)
+#define IS_WP_ENGAGE_OP(a) (a->flags & PAGEMAP_WP_ENGAGE)
+#define IS_GET_OP(a) (a->vec)
+#define PAGEMAP_SCAN_BITMAP(wt, file, present, swap) \
+ (wt | file << 1 | present << 2 | swap << 3)
+#define IS_WT_REQUIRED(a) \
+ ((a->required_mask & PAGE_IS_WT) || \
+ (a->anyof_mask & PAGE_IS_WT))
+#define HAS_NO_SPACE(p) (p->max_pages && (p->found_pages == p->max_pages))
+
+struct pagemap_scan_private {
+ struct page_region *vec;
+ struct page_region prev;
+ unsigned long vec_len, vec_index;
+ unsigned int max_pages, found_pages, flags;
+ unsigned long required_mask, anyof_mask, excluded_mask, return_mask;
+};
+
+static int pagemap_scan_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (IS_WT_REQUIRED(p) && !userfaultfd_wp(vma) && !userfaultfd_wp_async(vma))
+ return -EPERM;
+ if (vma->vm_flags & VM_PFNMAP)
+ return 1;
+ return 0;
+}
+
+static inline int add_to_out(bool wt, bool file, bool pres, bool swap,
+ struct pagemap_scan_private *p, unsigned long addr, unsigned int len)
+{
+ unsigned long bitmap, cur = PAGEMAP_SCAN_BITMAP(wt, file, pres, swap);
+ bool cpy = true;
+ struct page_region *prev = &p->prev;
+
+ if (HAS_NO_SPACE(p))
+ return -ENOSPC;
+
+ if (p->max_pages && p->found_pages + len >= p->max_pages)
+ len = p->max_pages - p->found_pages;
+ if (!len)
+ return -EINVAL;
+
+ if (p->required_mask)
+ cpy = ((p->required_mask & cur) == p->required_mask);
+ if (cpy && p->anyof_mask)
+ cpy = (p->anyof_mask & cur);
+ if (cpy && p->excluded_mask)
+ cpy = !(p->excluded_mask & cur);
+ bitmap = cur & p->return_mask;
+ if (cpy && bitmap) {
+ if ((prev->len) && (prev->bitmap == bitmap) &&
+ (prev->start + prev->len * PAGE_SIZE == addr)) {
+ prev->len += len;
+ p->found_pages += len;
+ } else if (p->vec_index < p->vec_len) {
+ if (prev->len) {
+ memcpy(&p->vec[p->vec_index], prev, sizeof(struct page_region));
+ p->vec_index++;
+ }
+ prev->start = addr;
+ prev->len = len;
+ prev->bitmap = bitmap;
+ p->found_pages += len;
+ } else {
+ return -ENOSPC;
+ }
+ }
+ return 0;
+}
+
+static inline int export_prev_to_out(struct pagemap_scan_private *p, struct page_region __user *vec,
+ unsigned long *vec_index)
+{
+ struct page_region *prev = &p->prev;
+
+ if (prev->len) {
+ if (copy_to_user(&vec[*vec_index], prev, sizeof(struct page_region)))
+ return -EFAULT;
+ p->vec_index++;
+ (*vec_index)++;
+ prev->len = 0;
+ }
+ return 0;
+}
+
+static inline int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long addr = end;
+ spinlock_t *ptl;
+ int ret = 0, ret2;
+ pte_t *pte;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
+ bool pmd_wt;
+
+ pmd_wt = !is_pmd_uffd_wp(*pmd);
+ /*
+ * Break huge page into small pages if operation needs to be performed is
+ * on a portion of the huge page.
+ */
+ if (pmd_wt && IS_WP_ENGAGE_OP(p) && (end - start < HPAGE_SIZE)) {
+ spin_unlock(ptl);
+ split_huge_pmd(vma, pmd, start);
+ goto process_smaller_pages;
+ }
+ if (IS_GET_OP(p))
+ ret = add_to_out(pmd_wt, vma->vm_file, pmd_present(*pmd),
+ is_swap_pmd(*pmd), p, start, (end - start)/PAGE_SIZE);
+ spin_unlock(ptl);
+ if (!ret) {
+ if (pmd_wt && IS_WP_ENGAGE_OP(p))
+ ret = wp_range_async(vma, start, HPAGE_SIZE);
+ }
+ return ret;
+ }
+process_smaller_pages:
+ if (pmd_trans_unstable(pmd))
+ return 0;
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+ if (IS_GET_OP(p)) {
+ for (addr = start; addr < end && !ret; pte++, addr += PAGE_SIZE)
+ ret = add_to_out(!is_pte_uffd_wp(*pte), vma->vm_file, pte_present(*pte),
+ is_swap_pte(*pte), p, addr, 1);
+ }
+ pte_unmap_unlock(pte - 1, ptl);
+ if ((!ret || ret == -ENOSPC) && IS_WP_ENGAGE_OP(p))
+ ret2 = wp_range_async(vma, start, addr - start);
+ if (ret2)
+ ret = ret2;
+
+ cond_resched();
+ return ret;
+}
+
+static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end, int depth,
+ struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ int ret = 0;
+
+ if (vma)
+ ret = add_to_out(false, vma->vm_file, false, false, p, addr,
+ (end - addr)/PAGE_SIZE);
+ return ret;
+}
+
+/* No hugetlb support is present. */
+static const struct mm_walk_ops pagemap_scan_ops = {
+ .test_walk = pagemap_scan_test_walk,
+ .pmd_entry = pagemap_scan_pmd_entry,
+ .pte_hole = pagemap_scan_pte_hole,
+};
+
+static long do_pagemap_cmd(struct mm_struct *mm, struct pagemap_scan_arg *arg)
+{
+ unsigned long empty_slots, vec_index = 0;
+ unsigned long __user start, end;
+ unsigned long __start, __end;
+ struct page_region __user *vec;
+ struct pagemap_scan_private p;
+ int ret;
+
+ start = (unsigned long)untagged_addr(arg->start);
+ vec = (struct page_region *)(unsigned long)untagged_addr(arg->vec);
+ if ((!IS_ALIGNED(start, PAGE_SIZE)) || (!access_ok((void __user *)start, arg->len)))
+ return -EINVAL;
+ if (IS_GET_OP(arg) && ((arg->vec_len == 0) ||
+ (!access_ok((void __user *)vec, arg->vec_len * sizeof(struct page_region)))))
+ return -ENOMEM;
+ if ((arg->flags & ~PAGEMAP_WP_ENGAGE) || (arg->required_mask & ~PAGEMAP_OP_MASK) ||
+ (arg->anyof_mask & ~PAGEMAP_OP_MASK) || (arg->excluded_mask & ~PAGEMAP_OP_MASK) ||
+ (arg->return_mask & ~PAGEMAP_OP_MASK))
+ return -EINVAL;
+ if (IS_GET_OP(arg) && ((!arg->required_mask && !arg->anyof_mask && !arg->excluded_mask) ||
+ !arg->return_mask))
+ return -EINVAL;
+ /* The non-WT flags cannot be obtained if PAGEMAP_WP_ENGAGE is also specified. */
+ if (IS_WP_ENGAGE_OP(arg) && ((arg->required_mask & PAGEMAP_NONWT_OP_MASK) ||
+ (arg->anyof_mask & PAGEMAP_NONWT_OP_MASK)))
+ return -EINVAL;
+
+ end = start + arg->len;
+ p.max_pages = arg->max_pages;
+ p.found_pages = 0;
+ p.flags = arg->flags;
+ p.required_mask = arg->required_mask;
+ p.anyof_mask = arg->anyof_mask;
+ p.excluded_mask = arg->excluded_mask;
+ p.return_mask = arg->return_mask;
+ p.prev.len = 0;
+ p.vec_len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+
+ if (IS_GET_OP(arg)) {
+ p.vec = kmalloc_array(p.vec_len, sizeof(struct page_region), GFP_KERNEL);
+ if (!p.vec)
+ return -ENOMEM;
+ } else {
+ p.vec = NULL;
+ }
+ __start = __end = start;
+ while (!ret && __end < end) {
+ p.vec_index = 0;
+ empty_slots = arg->vec_len - vec_index;
+ if (p.vec_len > empty_slots)
+ p.vec_len = empty_slots;
+
+ __end = (__start + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK;
+ if (__end > end)
+ __end = end;
+
+ mmap_read_lock(mm);
+ ret = walk_page_range(mm, __start, __end, &pagemap_scan_ops, &p);
+ mmap_read_unlock(mm);
+ if (!(!ret || ret == -ENOSPC))
+ goto free_data;
+
+ __start = __end;
+ if (IS_GET_OP(arg) && p.vec_index) {
+ if (copy_to_user(&vec[vec_index], p.vec,
+ p.vec_index * sizeof(struct page_region))) {
+ ret = -EFAULT;
+ goto free_data;
+ }
+ vec_index += p.vec_index;
+ }
+ }
+ if (!ret || ret == -ENOSPC)
+ ret = export_prev_to_out(&p, vec, &vec_index);
+ if (!ret)
+ ret = vec_index;
+free_data:
+ if (IS_GET_OP(arg))
+ kfree(p.vec);
+
+ return ret;
+}
+
+static long pagemap_scan_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pagemap_scan_arg __user *uarg = (struct pagemap_scan_arg __user *)arg;
+ struct mm_struct *mm = file->private_data;
+ struct pagemap_scan_arg argument;
+
+ if (cmd == PAGEMAP_SCAN) {
+ if (copy_from_user(&argument, uarg, sizeof(struct pagemap_scan_arg)))
+ return -EFAULT;
+ return do_pagemap_cmd(mm, &argument);
+ }
+ return -EINVAL;
+}
+
const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
.open = pagemap_open,
.release = pagemap_release,
+ .unlocked_ioctl = pagemap_scan_ioctl,
+ .compat_ioctl = pagemap_scan_ioctl,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index b7b56871029c..6d03a903a745 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -305,4 +305,54 @@ typedef int __bitwise __kernel_rwf_t;
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND)
+/* Pagemap ioctl */
+#define PAGEMAP_SCAN _IOWR('f', 16, struct pagemap_scan_arg)
+
+/* Bits are set in the bitmap of the page_region and masks in pagemap_scan_args */
+#define PAGE_IS_WT (1 << 0)
+#define PAGE_IS_FILE (1 << 1)
+#define PAGE_IS_PRESENT (1 << 2)
+#define PAGE_IS_SWAPPED (1 << 3)
+
+/*
+ * struct page_region - Page region with bitmap flags
+ * @start: Start of the region
+ * @len: Length of the region
+ * bitmap: Bits sets for the region
+ */
+struct page_region {
+ __u64 start;
+ __u64 len;
+ __u64 bitmap;
+};
+
+/*
+ * struct pagemap_scan_arg - Pagemap ioctl argument
+ * @start: Starting address of the region
+ * @len: Length of the region (All the pages in this length are included)
+ * @vec: Address of page_region struct array for output
+ * @vec_len: Length of the page_region struct array
+ * @max_pages: Optional max return pages
+ * @flags: Flags for the IOCTL
+ * @required_mask: Required mask - All of these bits have to be set in the PTE
+ * @anyof_mask: Any mask - Any of these bits are set in the PTE
+ * @excluded_mask: Exclude mask - None of these bits are set in the PTE
+ * @return_mask: Bits that are to be reported in page_region
+ */
+struct pagemap_scan_arg {
+ __u64 start;
+ __u64 len;
+ __u64 vec;
+ __u64 vec_len;
+ __u32 max_pages;
+ __u32 flags;
+ __u64 required_mask;
+ __u64 anyof_mask;
+ __u64 excluded_mask;
+ __u64 return_mask;
+};
+
+/* Special flags */
+#define PAGEMAP_WP_ENGAGE (1 << 0)
+
#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index b7b56871029c..6d03a903a745 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -305,4 +305,54 @@ typedef int __bitwise __kernel_rwf_t;
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND)
+/* Pagemap ioctl */
+#define PAGEMAP_SCAN _IOWR('f', 16, struct pagemap_scan_arg)
+
+/* Bits are set in the bitmap of the page_region and masks in pagemap_scan_args */
+#define PAGE_IS_WT (1 << 0)
+#define PAGE_IS_FILE (1 << 1)
+#define PAGE_IS_PRESENT (1 << 2)
+#define PAGE_IS_SWAPPED (1 << 3)
+
+/*
+ * struct page_region - Page region with bitmap flags
+ * @start: Start of the region
+ * @len: Length of the region
+ * bitmap: Bits sets for the region
+ */
+struct page_region {
+ __u64 start;
+ __u64 len;
+ __u64 bitmap;
+};
+
+/*
+ * struct pagemap_scan_arg - Pagemap ioctl argument
+ * @start: Starting address of the region
+ * @len: Length of the region (All the pages in this length are included)
+ * @vec: Address of page_region struct array for output
+ * @vec_len: Length of the page_region struct array
+ * @max_pages: Optional max return pages
+ * @flags: Flags for the IOCTL
+ * @required_mask: Required mask - All of these bits have to be set in the PTE
+ * @anyof_mask: Any mask - Any of these bits are set in the PTE
+ * @excluded_mask: Exclude mask - None of these bits are set in the PTE
+ * @return_mask: Bits that are to be reported in page_region
+ */
+struct pagemap_scan_arg {
+ __u64 start;
+ __u64 len;
+ __u64 vec;
+ __u64 vec_len;
+ __u32 max_pages;
+ __u32 flags;
+ __u64 required_mask;
+ __u64 anyof_mask;
+ __u64 excluded_mask;
+ __u64 return_mask;
+};
+
+/* Special flags */
+#define PAGEMAP_WP_ENGAGE (1 << 0)
+
#endif /* _UAPI_LINUX_FS_H */
--
2.30.2
From 774e3cd2e67f5e94f9994a75aac3a3e13ccd6deb Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Date: Tue, 24 Jan 2023 13:36:23 +0500
Subject: [PATCH WIP v9 4/4] selftests: vm: add pagemap ioctl tests
Add pagemap ioctl tests. Add several different types of tests to judge
the correction of the interface.
Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
---
Chages in v7:
- Add and update all test cases
Changes in v6:
- Rename variables
Changes in v4:
- Updated all the tests to conform to new IOCTL
Changes in v3:
- Add another test to do sanity of flags
Changes in v2:
- Update the tests to use the ioctl interface instead of syscall
TAP version 13
1..54
ok 1 sanity_tests_sd wrong flag specified
ok 2 sanity_tests_sd wrong mask specified
ok 3 sanity_tests_sd wrong return mask specified
ok 4 sanity_tests_sd mixture of correct and wrong flag
ok 5 sanity_tests_sd Clear area with larger vec size
ok 6 sanity_tests_sd Repeated pattern of dirty and non-dirty pages
ok 7 sanity_tests_sd Repeated pattern of dirty and non-dirty pages in parts
ok 8 sanity_tests_sd Two regions
ok 9 Page testing: all new pages must be soft dirty
ok 10 Page testing: all pages must not be soft dirty
ok 11 Page testing: all pages dirty other than first and the last one
ok 12 Page testing: only middle page dirty
ok 13 Page testing: only two middle pages dirty
ok 14 Page testing: only get 2 dirty pages and clear them as well
ok 15 Page testing: Range clear only
ok 16 Large Page testing: all new pages must be soft dirty
ok 17 Large Page testing: all pages must not be soft dirty
ok 18 Large Page testing: all pages dirty other than first and the last one
ok 19 Large Page testing: only middle page dirty
ok 20 Large Page testing: only two middle pages dirty
ok 21 Large Page testing: only get 2 dirty pages and clear them as well
ok 22 Large Page testing: Range clear only
ok 23 Huge page testing: all new pages must be soft dirty
ok 24 Huge page testing: all pages must not be soft dirty
ok 25 Huge page testing: all pages dirty other than first and the last one
ok 26 Huge page testing: only middle page dirty
ok 27 Huge page testing: only two middle pages dirty
ok 28 Huge page testing: only get 2 dirty pages and clear them as well
ok 29 Huge page testing: Range clear only
ok 30 hpage_unit_tests all new huge page must be dirty
ok 31 hpage_unit_tests all the huge page must not be dirty
ok 32 hpage_unit_tests all the huge page must be dirty and clear
ok 33 hpage_unit_tests only middle page dirty
ok 34 hpage_unit_tests clear first half of huge page
ok 35 hpage_unit_tests clear first half of huge page with limited buffer
ok 36 hpage_unit_tests clear second half huge page
ok 37 Test test_simple
ok 38 mprotect_tests Both pages dirty
ok 39 mprotect_tests Both pages are not soft dirty
ok 40 mprotect_tests Both pages dirty after remap and mprotect
ok 41 mprotect_tests Clear and make the pages dirty
ok 42 sanity_tests clear op can only be specified with PAGE_IS_WT
ok 43 sanity_tests required_mask specified
ok 44 sanity_tests anyof_mask specified
ok 45 sanity_tests excluded_mask specified
ok 46 sanity_tests required_mask and anyof_mask specified
ok 47 sanity_tests Get sd and present pages with anyof_mask
ok 48 sanity_tests Get all the pages with required_mask
ok 49 sanity_tests Get sd and present pages with required_mask and anyof_mask
ok 50 sanity_tests Don't get sd pages
ok 51 sanity_tests Don't get present pages
ok 52 sanity_tests Find dirty present pages with return mask
ok 53 sanity_tests Memory mapped file
ok 54 unmapped_region_tests Get status of pages
# Totals: pass:54 fail:0 xfail:0 xpass:0 skip:0 error:0
---
tools/testing/selftests/vm/.gitignore | 1 +
tools/testing/selftests/vm/Makefile | 5 +-
tools/testing/selftests/vm/pagemap_ioctl.c | 880 +++++++++++++++++++++
3 files changed, 884 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/vm/pagemap_ioctl.c
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 1f8c36a9fa10..9e7e0ae26582 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -17,6 +17,7 @@ mremap_dontunmap
mremap_test
on-fault-limit
transhuge-stress
+pagemap_ioctl
protection_keys
protection_keys_32
protection_keys_64
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 89c14e41bd43..54c074440a1b 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -24,9 +24,8 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p
# things despite using incorrect values such as an *occasionally* incomplete
# LDLIBS.
MAKEFLAGS += --no-builtin-rules
-
CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/usr/include $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
-LDLIBS = -lrt -lpthread
+LDLIBS = -lrt -lpthread -lm
TEST_GEN_FILES = cow
TEST_GEN_FILES += compaction_test
TEST_GEN_FILES += gup_test
@@ -52,6 +51,7 @@ TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += userfaultfd
+TEST_GEN_PROGS += pagemap_ioctl
TEST_GEN_PROGS += soft-dirty
TEST_GEN_PROGS += split_huge_page_test
TEST_GEN_FILES += ksm_tests
@@ -103,6 +103,7 @@ $(OUTPUT)/cow: vm_util.c
$(OUTPUT)/khugepaged: vm_util.c
$(OUTPUT)/ksm_functional_tests: vm_util.c
$(OUTPUT)/madv_populate: vm_util.c
+$(OUTPUT)/pagemap_ioctl: vm_util.c
$(OUTPUT)/soft-dirty: vm_util.c
$(OUTPUT)/split_huge_page_test: vm_util.c
$(OUTPUT)/userfaultfd: vm_util.c
diff --git a/tools/testing/selftests/vm/pagemap_ioctl.c b/tools/testing/selftests/vm/pagemap_ioctl.c
new file mode 100644
index 000000000000..877646f9ee8a
--- /dev/null
+++ b/tools/testing/selftests/vm/pagemap_ioctl.c
@@ -0,0 +1,880 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <errno.h>
+#include <malloc.h>
+#include "vm_util.h"
+#include "../kselftest.h"
+#include <linux/types.h>
+#include <linux/userfaultfd.h>
+#include <linux/fs.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <math.h>
+#include <asm/unistd.h>
+
+#define PAGEMAP_OP_MASK (PAGE_IS_WT | PAGE_IS_FILE | \
+ PAGE_IS_PRESENT | PAGE_IS_SWAPPED)
+#define PAGEMAP_NON_WT_MASK (PAGE_IS_FILE | PAGE_IS_PRESENT | \
+ PAGE_IS_SWAPPED)
+
+#define TEST_ITERATIONS 10
+#define PAGEMAP "/proc/self/pagemap"
+int pagemap_fd;
+int uffd;
+int page_size;
+int hpage_size;
+
+static long pagemap_ioctl(void *start, int len, void *vec, int vec_len, int flag,
+ int max_pages, long required_mask, long anyof_mask, long excluded_mask,
+ long return_mask)
+{
+ struct pagemap_scan_arg arg;
+ int ret;
+
+ arg.start = (uintptr_t)start;
+ arg.len = len;
+ arg.vec = (uintptr_t)vec;
+ arg.vec_len = vec_len;
+ arg.flags = flag;
+ arg.max_pages = max_pages;
+ arg.required_mask = required_mask;
+ arg.anyof_mask = anyof_mask;
+ arg.excluded_mask = excluded_mask;
+ arg.return_mask = return_mask;
+
+ ret = ioctl(pagemap_fd, PAGEMAP_SCAN, &arg);
+
+ return ret;
+}
+
+int init_uffd(void)
+{
+ struct uffdio_api uffdio_api;
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ if (uffd == -1)
+ ksft_exit_fail_msg("uffd syscall failed\n");
+
+ uffdio_api.api = UFFD_API;
+ uffdio_api.features = UFFD_FEATURE_WP_ASYNC;
+ if (ioctl(uffd, UFFDIO_API, &uffdio_api))
+ ksft_exit_fail_msg("UFFDIO_API\n");
+
+ if (uffdio_api.api != UFFD_API)
+ ksft_exit_fail_msg("UFFDIO_API error %llu\n", uffdio_api.api);
+
+ return 0;
+}
+
+int wp_init(void *lpBaseAddress, int dwRegionSize)
+{
+ struct uffdio_register uffdio_register;
+ struct uffdio_writeprotect wp;
+
+ /* TODO: can it be avoided? Write protect doesn't engage on the pages if they aren't
+ * present already. The pages can be made present by writing to them.
+ */
+ memset(lpBaseAddress, -1, dwRegionSize);
+
+ uffdio_register.range.start = (unsigned long)lpBaseAddress;
+ uffdio_register.range.len = dwRegionSize;
+ uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1)
+ ksft_exit_fail_msg("ioctl(UFFDIO_REGISTER)\n");
+
+ if (!(uffdio_register.ioctls & UFFDIO_WRITEPROTECT))
+ ksft_exit_fail_msg("ioctl set is incorrect\n");
+
+ if (rand() % 2) {
+ wp.range.start = (unsigned long)lpBaseAddress;
+ wp.range.len = dwRegionSize;
+ wp.mode = UFFDIO_WRITEPROTECT_MODE_WP;
+
+ if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp) == -1)
+ ksft_exit_fail_msg("ioctl(UFFDIO_WRITEPROTECT)\n");
+ } else {
+ if (pagemap_ioctl(lpBaseAddress, dwRegionSize, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0) < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", 1, errno, strerror(errno));
+ }
+ return 0;
+}
+
+int wp_free(void *lpBaseAddress, int dwRegionSize)
+{
+ struct uffdio_register uffdio_register;
+
+ uffdio_register.range.start = (unsigned long)lpBaseAddress;
+ uffdio_register.range.len = dwRegionSize;
+ uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
+ if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range))
+ ksft_exit_fail_msg("ioctl unregister failure\n");
+ return 0;
+}
+
+int clear_softdirty_wp(void *lpBaseAddress, int dwRegionSize)
+{
+ struct uffdio_writeprotect wp;
+
+ if (rand() % 2) {
+ wp.range.start = (unsigned long)lpBaseAddress;
+ wp.range.len = dwRegionSize;
+ wp.mode = UFFDIO_WRITEPROTECT_MODE_WP;
+
+ if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp) == -1)
+ ksft_exit_fail_msg("ioctl(UFFDIO_WRITEPROTECT)\n");
+ } else {
+ if (pagemap_ioctl(lpBaseAddress, dwRegionSize, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0) < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", 1, errno, strerror(errno));
+ }
+ return 0;
+}
+
+int sanity_tests_sd(void)
+{
+ char *mem, *m[2];
+ int mem_size, vec_size, ret, ret2, ret3, i, num_pages = 10;
+ struct page_region *vec;
+
+ vec_size = 100;
+ mem_size = num_pages * page_size;
+
+ vec = malloc(sizeof(struct page_region) * vec_size);
+ if (!vec)
+ ksft_exit_fail_msg("error nomem\n");
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+
+ wp_init(mem, mem_size);
+
+ /* 1. wrong operation */
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, -1,
+ 0, PAGE_IS_WT, 0, 0, PAGE_IS_WT) < 0,
+ "%s wrong flag specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 8,
+ 0, 0x1111, 0, 0, PAGE_IS_WT) < 0,
+ "%s wrong mask specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0,
+ 0, PAGE_IS_WT, 0, 0, 0x1000) < 0,
+ "%s wrong return mask specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size,
+ PAGEMAP_WP_ENGAGE | 0x32,
+ 0, PAGE_IS_WT, 0, 0, PAGE_IS_WT) < 0,
+ "%s mixture of correct and wrong flag\n", __func__);
+
+ /* 2. Clear area with larger vec size */
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, PAGEMAP_WP_ENGAGE, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ ksft_test_result(ret >= 0, "%s Clear area with larger vec size\n", __func__);
+
+ /* 3. Repeated pattern of dirty and non-dirty pages */
+ for (i = 0; i < mem_size; i += 2 * page_size)
+ mem[i]++;
+
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == mem_size/(page_size * 2),
+ "%s Repeated pattern of dirty and non-dirty pages\n", __func__);
+
+ /* 4. Repeated pattern of dirty and non-dirty pages in parts */
+ ret = pagemap_ioctl(mem, mem_size, vec, num_pages/5, PAGEMAP_WP_ENGAGE,
+ num_pages/2 - 2, PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ret2 = pagemap_ioctl(mem, mem_size, vec, 2, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (ret2 < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno));
+
+ ret3 = pagemap_ioctl(mem, mem_size, vec, num_pages/2, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (ret3 < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret3, errno, strerror(errno));
+
+ ksft_test_result((ret + ret3) == num_pages/2 && ret2 == 2,
+ "%s Repeated pattern of dirty and non-dirty pages in parts\n", __func__);
+
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 5. Two regions */
+ m[0] = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (m[0] == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ m[1] = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (m[1] == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+
+ wp_init(m[0], mem_size);
+ wp_init(m[1], mem_size);
+
+ memset(m[0], 'a', mem_size);
+ memset(m[1], 'b', mem_size);
+
+ ret = pagemap_ioctl(m[0], mem_size, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ret = pagemap_ioctl(m[1], mem_size, vec, 1, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len == mem_size/page_size,
+ "%s Two regions\n", __func__);
+
+ wp_free(m[0], mem_size);
+ wp_free(m[1], mem_size);
+ munmap(m[0], mem_size);
+ munmap(m[1], mem_size);
+
+ free(vec);
+ return 0;
+}
+
+int base_tests(char *prefix, char *mem, int mem_size, int skip)
+{
+ int vec_size, ret, dirty, dirty2;
+ struct page_region *vec, *vec2;
+
+ if (skip) {
+ ksft_test_result_skip("%s all new pages must be soft dirty\n", prefix);
+ ksft_test_result_skip("%s all pages must not be soft dirty\n", prefix);
+ ksft_test_result_skip("%s all pages dirty other than first and the last one\n",
+ prefix);
+ ksft_test_result_skip("%s only middle page dirty\n", prefix);
+ ksft_test_result_skip("%s only two middle pages dirty\n", prefix);
+ ksft_test_result_skip("%s only get 2 dirty pages and clear them as well\n", prefix);
+ ksft_test_result_skip("%s Range clear only\n", prefix);
+ return 0;
+ }
+
+ vec_size = mem_size/page_size;
+ vec = malloc(sizeof(struct page_region) * vec_size);
+ vec2 = malloc(sizeof(struct page_region) * vec_size);
+
+ /* 1. all new pages must be not be soft dirty */
+ dirty = pagemap_ioctl(mem, mem_size, vec, 1, PAGEMAP_WP_ENGAGE, vec_size - 2,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ dirty2 = pagemap_ioctl(mem, mem_size, vec2, 1, PAGEMAP_WP_ENGAGE, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (dirty2 < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty2, errno, strerror(errno));
+
+ ksft_test_result(dirty == 0 && dirty2 == 0,
+ "%s all new pages must be soft dirty\n", prefix);
+
+ /* 2. all pages must not be soft dirty */
+ dirty = pagemap_ioctl(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(dirty == 0, "%s all pages must not be soft dirty\n", prefix);
+
+ /* 3. all pages dirty other than first and the last one */
+ memset(mem + page_size, 0, mem_size - (2 * page_size));
+
+ dirty = pagemap_ioctl(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(dirty == 1 && vec[0].len >= vec_size - 2 && vec[0].len <= vec_size,
+ "%s all pages dirty other than first and the last one\n", prefix);
+
+ /* 4. only middle page dirty */
+ clear_softdirty_wp(mem, mem_size);
+ mem[vec_size/2 * page_size]++;
+
+ dirty = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WT, 0, 0,
+ PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(dirty == 1 && vec[0].len >= 1,
+ "%s only middle page dirty\n", prefix);
+
+ /* 5. only two middle pages dirty and walk over only middle pages */
+ clear_softdirty_wp(mem, mem_size);
+ mem[vec_size/2 * page_size]++;
+ mem[(vec_size/2 + 1) * page_size]++;
+
+ dirty = pagemap_ioctl(&mem[vec_size/2 * page_size], 2 * page_size, vec, 1, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(dirty == 1 && vec[0].start == (uintptr_t)(&mem[vec_size/2 * page_size]) &&
+ vec[0].len == 2,
+ "%s only two middle pages dirty\n", prefix);
+
+ /* 6. only get 2 dirty pages and clear them as well */
+ memset(mem, -1, mem_size);
+
+ /* get and clear second and third pages */
+ ret = pagemap_ioctl(mem + page_size, 2 * page_size, vec, 1, PAGEMAP_WP_ENGAGE,
+ 2, PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ dirty = pagemap_ioctl(mem, mem_size, vec2, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len == 2 &&
+ vec[0].start == (uintptr_t)(mem + page_size) &&
+ dirty == 2 && vec2[0].len == 1 && vec2[0].start == (uintptr_t)mem &&
+ vec2[1].len == vec_size - 3 &&
+ vec2[1].start == (uintptr_t)(mem + 3 * page_size),
+ "%s only get 2 dirty pages and clear them as well\n", prefix);
+
+ /* 7. Range clear only */
+ memset(mem, -1, mem_size);
+
+ dirty = pagemap_ioctl(mem, mem_size, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ dirty2 = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (dirty2 < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty2, errno, strerror(errno));
+
+ ksft_test_result(dirty == 0 && dirty2 == 0, "%s Range clear only\n",
+ prefix);
+
+ free(vec);
+ free(vec2);
+ return 0;
+}
+
+void *gethugepage(int map_size)
+{
+ int ret;
+ char *map;
+
+ map = memalign(hpage_size, map_size);
+ if (!map)
+ ksft_exit_fail_msg("memalign failed %d %s\n", errno, strerror(errno));
+
+ ret = madvise(map, map_size, MADV_HUGEPAGE);
+ if (ret)
+ ksft_exit_fail_msg("madvise failed %d %d %s\n", ret, errno, strerror(errno));
+
+ wp_init(map, map_size);
+
+ if (check_huge_anon(map, map_size/hpage_size, hpage_size))
+ return map;
+
+ free(map);
+ return NULL;
+
+}
+
+int hpage_unit_tests(void)
+{
+ char *map;
+ int ret;
+ size_t num_pages = 10;
+ int map_size = hpage_size * num_pages;
+ int vec_size = map_size/page_size;
+ struct page_region *vec, *vec2;
+
+ vec = malloc(sizeof(struct page_region) * vec_size);
+ vec2 = malloc(sizeof(struct page_region) * vec_size);
+ if (!vec || !vec2)
+ ksft_exit_fail_msg("malloc failed\n");
+
+ map = gethugepage(map_size);
+ if (map) {
+ /* 1. all new huge page must not be dirty */
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, PAGEMAP_WP_ENGAGE, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 0, "%s all new huge page must be dirty\n", __func__);
+
+ /* 2. all the huge page must not be dirty */
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 0, "%s all the huge page must not be dirty\n", __func__);
+
+ /* 3. all the huge page must be dirty and clear dirty as well */
+ memset(map, -1, map_size);
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, PAGEMAP_WP_ENGAGE, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].start == (uintptr_t)map &&
+ vec[0].len == vec_size && vec[0].bitmap == PAGE_IS_WT,
+ "%s all the huge page must be dirty and clear\n", __func__);
+
+ /* 4. only middle page dirty */
+ wp_free(map, map_size);
+ free(map);
+ map = gethugepage(map_size);
+ wp_init(map, map_size);
+ clear_softdirty_wp(map, map_size);
+ map[vec_size/2 * page_size]++;
+
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len > 0,
+ "%s only middle page dirty\n", __func__);
+
+ wp_free(map, map_size);
+ free(map);
+ } else {
+ ksft_test_result_skip("all new huge page must be dirty\n");
+ ksft_test_result_skip("all the huge page must not be dirty\n");
+ ksft_test_result_skip("all the huge page must be dirty and clear\n");
+ ksft_test_result_skip("only middle page dirty\n");
+ }
+
+ /* 5. clear first half of huge page */
+ map = gethugepage(map_size);
+ if (map) {
+
+ memset(map, 0, map_size);
+
+ ret = pagemap_ioctl(map, map_size/2, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len == vec_size/2 &&
+ vec[0].start == (uintptr_t)(map + map_size/2),
+ "%s clear first half of huge page\n", __func__);
+ wp_free(map, map_size);
+ free(map);
+ } else {
+ ksft_test_result_skip("clear first half of huge page\n");
+ }
+
+ /* 6. clear first half of huge page with limited buffer */
+ map = gethugepage(map_size);
+ if (map) {
+ memset(map, 0, map_size);
+
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, PAGEMAP_WP_ENGAGE,
+ vec_size/2, PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len == vec_size/2 &&
+ vec[0].start == (uintptr_t)(map + map_size/2),
+ "%s clear first half of huge page with limited buffer\n",
+ __func__);
+ wp_free(map, map_size);
+ free(map);
+ } else {
+ ksft_test_result_skip("clear first half of huge page with limited buffer\n");
+ }
+
+ /* 7. clear second half of huge page */
+ map = gethugepage(map_size);
+ if (map) {
+ memset(map, -1, map_size);
+ ret = pagemap_ioctl(map + map_size/2, map_size/2, NULL, 0, PAGEMAP_WP_ENGAGE,
+ 0, 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ret = pagemap_ioctl(map, map_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec[0].len == vec_size/2,
+ "%s clear second half huge page\n", __func__);
+ wp_free(map, map_size);
+ free(map);
+ } else {
+ ksft_test_result_skip("clear second half huge page\n");
+ }
+
+ free(vec);
+ free(vec2);
+ return 0;
+}
+
+int unmapped_region_tests(void)
+{
+ void *start = (void *)0x10000000;
+ int dirty, len = 0x00040000;
+ int vec_size = len / page_size;
+ struct page_region *vec = malloc(sizeof(struct page_region) * vec_size);
+
+ /* 1. Get dirty pages */
+ dirty = pagemap_ioctl(start, len, vec, vec_size, 0, 0, PAGEMAP_NON_WT_MASK, 0, 0,
+ PAGEMAP_NON_WT_MASK);
+ if (dirty < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", dirty, errno, strerror(errno));
+
+ ksft_test_result(dirty >= 0, "%s Get status of pages\n", __func__);
+
+ free(vec);
+ return 0;
+}
+
+static void test_simple(void)
+{
+ int i;
+ char *map;
+ struct page_region vec;
+
+ map = aligned_alloc(page_size, page_size);
+ if (!map)
+ ksft_exit_fail_msg("aligned_alloc failed\n");
+ wp_init(map, page_size);
+
+ clear_softdirty_wp(map, page_size);
+
+ for (i = 0 ; i < TEST_ITERATIONS; i++) {
+ if (pagemap_ioctl(map, page_size, &vec, 1, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT) == 1) {
+ ksft_print_msg("dirty bit was 1, but should be 0 (i=%d)\n", i);
+ break;
+ }
+
+ clear_softdirty_wp(map, page_size);
+ /* Write something to the page to get the dirty bit enabled on the page */
+ map[0]++;
+
+ if (pagemap_ioctl(map, page_size, &vec, 1, 0, 0,
+ PAGE_IS_WT, 0, 0, PAGE_IS_WT) == 0) {
+ ksft_print_msg("dirty bit was 0, but should be 1 (i=%d)\n", i);
+ break;
+ }
+
+ clear_softdirty_wp(map, page_size);
+ }
+ wp_free(map, page_size);
+ free(map);
+
+ ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__);
+}
+
+int sanity_tests(void)
+{
+ char *mem, *fmem;
+ int mem_size, vec_size, ret;
+ struct page_region *vec;
+
+ /* 1. wrong operation */
+ mem_size = 10 * page_size;
+ vec_size = mem_size / page_size;
+
+ vec = malloc(sizeof(struct page_region) * vec_size);
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED || vec == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+
+ wp_init(mem, mem_size);
+
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, PAGEMAP_WP_ENGAGE, 0,
+ PAGEMAP_OP_MASK, 0, 0, PAGEMAP_OP_MASK) < 0,
+ "%s clear op can only be specified with PAGE_IS_WT\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ PAGEMAP_OP_MASK, 0, 0, PAGEMAP_OP_MASK) >= 0,
+ "%s required_mask specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, PAGEMAP_OP_MASK, 0, PAGEMAP_OP_MASK) >= 0,
+ "%s anyof_mask specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, 0, PAGEMAP_OP_MASK, PAGEMAP_OP_MASK) >= 0,
+ "%s excluded_mask specified\n", __func__);
+ ksft_test_result(pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ PAGEMAP_OP_MASK, PAGEMAP_OP_MASK, 0, PAGEMAP_OP_MASK) >= 0,
+ "%s required_mask and anyof_mask specified\n", __func__);
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 2. Get sd and present pages with anyof_mask */
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem, mem_size);
+
+ memset(mem, 0, mem_size);
+
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, PAGEMAP_OP_MASK, 0, PAGEMAP_OP_MASK);
+ ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && vec[0].len == vec_size &&
+ vec[0].bitmap == (PAGE_IS_WT | PAGE_IS_PRESENT),
+ "%s Get sd and present pages with anyof_mask\n", __func__);
+
+ /* 3. Get sd and present pages with required_mask */
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ PAGEMAP_OP_MASK, 0, 0, PAGEMAP_OP_MASK);
+ ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && vec[0].len == vec_size &&
+ vec[0].bitmap == (PAGE_IS_WT | PAGE_IS_PRESENT),
+ "%s Get all the pages with required_mask\n", __func__);
+
+ /* 4. Get sd and present pages with required_mask and anyof_mask */
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ PAGE_IS_WT, PAGE_IS_PRESENT, 0, PAGEMAP_OP_MASK);
+ ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && vec[0].len == vec_size &&
+ vec[0].bitmap == (PAGE_IS_WT | PAGE_IS_PRESENT),
+ "%s Get sd and present pages with required_mask and anyof_mask\n",
+ __func__);
+
+ /* 5. Don't get sd pages */
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, 0, PAGE_IS_WT, PAGEMAP_OP_MASK);
+ ksft_test_result(ret == 0, "%s Don't get sd pages\n", __func__);
+
+ /* 6. Don't get present pages */
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, 0, PAGE_IS_PRESENT, PAGEMAP_OP_MASK);
+ ksft_test_result(ret == 0, "%s Don't get present pages\n", __func__);
+
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 8. Find dirty present pages with return mask */
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem, mem_size);
+
+ memset(mem, 0, mem_size);
+
+ ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0,
+ 0, PAGEMAP_OP_MASK, 0, PAGE_IS_WT);
+ ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)mem && vec[0].len == vec_size &&
+ vec[0].bitmap == PAGE_IS_WT,
+ "%s Find dirty present pages with return mask\n", __func__);
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 9. Memory mapped file */
+ int fd;
+ struct stat sbuf;
+
+ fd = open(__FILE__, O_RDONLY);
+ if (fd < 0) {
+ ksft_test_result_skip("%s Memory mapped file\n");
+ goto free_vec_and_return;
+ }
+
+ ret = stat(__FILE__, &sbuf);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ fmem = mmap(NULL, sbuf.st_size, PROT_READ, MAP_SHARED, fd, 0);
+ if (fmem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+
+ ret = pagemap_ioctl(fmem, sbuf.st_size, vec, vec_size, 0, 0,
+ 0, PAGEMAP_NON_WT_MASK, 0, PAGEMAP_NON_WT_MASK);
+
+ ksft_test_result(ret >= 0 && vec[0].start == (uintptr_t)fmem &&
+ vec[0].len == ceilf((float)sbuf.st_size/page_size) &&
+ vec[0].bitmap == PAGE_IS_FILE,
+ "%s Memory mapped file\n", __func__);
+
+ munmap(fmem, sbuf.st_size);
+ close(fd);
+
+free_vec_and_return:
+ free(vec);
+ return 0;
+}
+
+int mprotect_tests(void)
+{
+ int ret;
+ char *mem, *mem2;
+ struct page_region vec;
+ int pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+
+ if (pagemap_fd < 0) {
+ fprintf(stderr, "open() failed\n");
+ exit(1);
+ }
+
+ /* 1. Map two pages */
+ mem = mmap(0, 2 * page_size, PROT_READ|PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem, 2 * page_size);
+
+ /* Populate both pages. */
+ memset(mem, 1, 2 * page_size);
+
+ ret = pagemap_ioctl(mem, 2 * page_size, &vec, 1, 0, 0, PAGE_IS_WT,
+ 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec.len == 2, "%s Both pages dirty\n", __func__);
+
+ /* 2. Start softdirty tracking. Clear VM_SOFTDIRTY and clear the softdirty PTE bit. */
+ ret = pagemap_ioctl(mem, 2 * page_size, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(pagemap_ioctl(mem, 2 * page_size, &vec, 1, 0, 0, PAGE_IS_WT,
+ 0, 0, PAGE_IS_WT) == 0,
+ "%s Both pages are not soft dirty\n", __func__);
+
+ /* 3. Remap the second page */
+ mem2 = mmap(mem + page_size, page_size, PROT_READ|PROT_WRITE,
+ MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);
+ if (mem2 == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem2, page_size);
+
+ /* Protect + unprotect. */
+ mprotect(mem, 2 * page_size, PROT_READ);
+ mprotect(mem, 2 * page_size, PROT_READ|PROT_WRITE);
+
+ /* Modify both pages. */
+ memset(mem, 2, 2 * page_size);
+
+ ret = pagemap_ioctl(mem, 2 * page_size, &vec, 1, 0, 0, PAGE_IS_WT,
+ 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec.len == 2,
+ "%s Both pages dirty after remap and mprotect\n", __func__);
+
+ /* 4. Clear and make the pages dirty */
+ ret = pagemap_ioctl(mem, 2 * page_size, NULL, 0, PAGEMAP_WP_ENGAGE, 0,
+ 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ memset(mem, 'A', 2 * page_size);
+
+ ret = pagemap_ioctl(mem, 2 * page_size, &vec, 1, 0, 0, PAGE_IS_WT,
+ 0, 0, PAGE_IS_WT);
+ if (ret < 0)
+ ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+
+ ksft_test_result(ret == 1 && vec.len == 2,
+ "%s Clear and make the pages dirty\n", __func__);
+
+ wp_free(mem, 2 * page_size);
+ munmap(mem, 2 * page_size);
+ return 0;
+}
+
+int main(void)
+{
+ char *mem, *map;
+ int mem_size;
+
+ ksft_print_header();
+ ksft_set_plan(54);
+
+ page_size = getpagesize();
+ hpage_size = read_pmd_pagesize();
+
+ pagemap_fd = open(PAGEMAP, O_RDWR);
+ if (pagemap_fd < 0)
+ return -EINVAL;
+
+ if (init_uffd())
+ ksft_exit_fail_msg("uffd init failed\n");
+
+ /*
+ * Soft-dirty PTE bit tests
+ */
+
+ /* 1. Sanity testing */
+ sanity_tests_sd();
+
+ /* 2. Normal page testing */
+ mem_size = 10 * page_size;
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem, mem_size);
+
+ base_tests("Page testing:", mem, mem_size, 0);
+
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 3. Large page testing */
+ mem_size = 512 * 10 * page_size;
+ mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (mem == MAP_FAILED)
+ ksft_exit_fail_msg("error nomem\n");
+ wp_init(mem, mem_size);
+
+ base_tests("Large Page testing:", mem, mem_size, 0);
+
+ wp_free(mem, mem_size);
+ munmap(mem, mem_size);
+
+ /* 4. Huge page testing */
+ map = gethugepage(hpage_size);
+ if (map) {
+ base_tests("Huge page testing:", map, hpage_size, 0);
+ wp_free(map, hpage_size);
+ free(map);
+ } else {
+ base_tests("Huge page testing:", NULL, 0, 1);
+ }
+
+ /* 6. Huge page tests */
+ hpage_unit_tests();
+
+ /* 7. Iterative test */
+ test_simple();
+
+ /* 8. Mprotect test */
+ mprotect_tests();
+
+ /*
+ * Other PTE bit tests
+ */
+
+ /* 1. Sanity testing */
+ sanity_tests();
+
+ /* 2. Unmapped address test */
+ unmapped_region_tests();
+
+ close(pagemap_fd);
+ return ksft_exit_pass();
+}
--
2.30.2
