Against mm/mm-unstable.
There is interest in supporting uprobes on hugetlb pages [1]. Having
uprobe_write_opcode() implement COW-breaking itself is really far from
optimal, and having to add hugetlb COW-breaking to implement hugetlb
support really does sound wrong.
Further, I think the current code doesn't really handle some things
properly (see patch #3) when replacing/zapping pages.
Let's rewrite it, to leave COW-breaking to the fault handler, and handle
registration/unregistration by temporarily unmapping the anonymous page,
modifying it, and mapping it again. We still have to implement
zapping of anonymous pages ourselves, unfortunately.
Note that we now won't have to allocate another anonymous folio when
unregistering (which will be beneficial for hugetlb as well), we can simply
modify the already-mapped one from the registration (if any). When
registering a uprobe, we'll first trigger a write fault to break COW to
then modify the already-mapped page.
Briefly sanity tested with perf:
[root@localhost ~]# perf probe -x /usr/bin/bash -a main
...
[root@localhost ~]# perf record -e probe_bash:main -aR sleep 10 &
[1] 2196
[root@localhost ~]# bash
[root@localhost ~]# exit
exit
[root@localhost ~]# bash
[root@localhost ~]# exit
exit
[root@localhost ~]# [ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.287 MB perf.data (8 samples) ]
...
[root@localhost ~]# perf report --stdio
# To display the perf.data header info, please use --header/--header-only optio>
#
#
# Total Lost Samples: 0
#
# Samples: 8 of event 'probe_bash:main'
# Event count (approx.): 8
#
# Overhead Command Shared Object Symbol
# ........ ........... ............. ........
#
75.00% grepconf.sh bash [.] main
25.00% bash bash [.] main
...
Are there any uprobe tests / benchmarks that are worth running?
[1] https://lkml.kernel.org/r/[email protected]
Cc: Andrew Morton <[email protected]>
Cc: Guillaume Morin <[email protected]>
Cc: Russell King <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Ian Rogers <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: "Liang, Kan" <[email protected]>
David Hildenbrand (3):
kernel/events/uprobes: pass VMA instead of MM to install_breakpoint()
kernel/events/uprobes: pass VMA to set_swbp(), set_orig_insn() and
uprobe_write_opcode()
kernel/events/uprobes: uprobe_write_opcode() rewrite
arch/arm/probes/uprobes/core.c | 4 +-
include/linux/uprobes.h | 6 +-
kernel/events/uprobes.c | 387 +++++++++++++++++++--------------
3 files changed, 223 insertions(+), 174 deletions(-)
base-commit: 065d3634d60843b8e338d405b844cc7f2e5e1c66
--
2.45.1
... and remove the "MM" argument from remove_breakpoint(), because it
can easily be derived from the VMA.
Signed-off-by: David Hildenbrand <[email protected]>
---
kernel/events/uprobes.c | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2c83ba776fc7b..c6d6b7a8e4410 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -886,10 +886,10 @@ static bool filter_chain(struct uprobe *uprobe,
return ret;
}
-static int
-install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long vaddr)
+static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+ unsigned long vaddr)
{
+ struct mm_struct *mm = vma->vm_mm;
bool first_uprobe;
int ret;
@@ -914,9 +914,11 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
return ret;
}
-static int
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+ unsigned long vaddr)
{
+ struct mm_struct *mm = vma->vm_mm;
+
set_bit(MMF_RECALC_UPROBES, &mm->flags);
return set_orig_insn(&uprobe->arch, mm, vaddr);
}
@@ -1061,11 +1063,11 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
/* consult only the "caller", new consumer. */
if (consumer_filter(new,
UPROBE_FILTER_REGISTER, mm))
- err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+ err = install_breakpoint(uprobe, vma, info->vaddr);
} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
if (!filter_chain(uprobe,
UPROBE_FILTER_UNREGISTER, mm))
- err |= remove_breakpoint(uprobe, mm, info->vaddr);
+ err |= remove_breakpoint(uprobe, vma, info->vaddr);
}
unlock:
@@ -1250,7 +1252,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
continue;
vaddr = offset_to_vaddr(vma, uprobe->offset);
- err |= remove_breakpoint(uprobe, mm, vaddr);
+ err |= remove_breakpoint(uprobe, vma, vaddr);
}
mmap_read_unlock(mm);
@@ -1386,7 +1388,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
if (!fatal_signal_pending(current) &&
filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) {
unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
- install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
+ install_breakpoint(uprobe, vma, vaddr);
}
put_uprobe(uprobe);
}
--
2.45.1
uprobe_write_opcode() does some pretty low-level things that really, it
shouldn't be doing: for example, manually breaking COW by allocating
anonymous folios and replacing mapped pages.
Further, it does seem to do some shaky things: for example, writing to
possible COW-shared anonymous pages or zapping anonymous pages that might
be pinned. We're also not taking care of uffd, uffd-wp, softdirty ...
although rather corner cases here. Let's just get it right like ordinary
ptrace writes would.
Let's rewrite the code, leaving COW-breaking to core-MM, triggered by
FOLL_FORCE|FOLL_WRITE (note that the code was already using FOLL_FORCE).
We'll use GUP to lookup/faultin the page and break COW if required. Then,
we'll walk the page tables using walk_page_range_vma(), to perform our page
modification atomically by temporarily unmap+flushing the PTE that maps an
anonymous page.
Unfortunately, we still have to implement the zapping logic manually,
because we only want to zap in specific circumstances (e.g., page
content identical).
Note that we can handle large folios just fine. walk_page_range_vma() will
call split_huge_pmd() for us. We can drop the WARN and stop using
FOLL_SPLIT_PMD. If split_huge_pmd() decides to zap a PMD-mapped file THP,
there is nothing to do when unregistering. Document that.
Signed-off-by: David Hildenbrand <[email protected]>
---
kernel/events/uprobes.c | 342 +++++++++++++++++++++++-----------------
1 file changed, 194 insertions(+), 148 deletions(-)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f2b1fef7f1d62..a22f2e9fd6456 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -26,6 +26,7 @@
#include <linux/task_work.h>
#include <linux/shmem_fs.h>
#include <linux/khugepaged.h>
+#include <linux/pagewalk.h>
#include <linux/uprobes.h>
@@ -137,80 +138,6 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start);
}
-/**
- * __replace_page - replace page in vma by new page.
- * based on replace_page in mm/ksm.c
- *
- * @vma: vma that holds the pte pointing to page
- * @addr: address the old @page is mapped at
- * @old_page: the page we are replacing by new_page
- * @new_page: the modified page we replace page by
- *
- * If @new_page is NULL, only unmap @old_page.
- *
- * Returns 0 on success, negative error code otherwise.
- */
-static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
- struct page *old_page, struct page *new_page)
-{
- struct folio *old_folio = page_folio(old_page);
- struct folio *new_folio;
- struct mm_struct *mm = vma->vm_mm;
- DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
- int err;
- struct mmu_notifier_range range;
-
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
- addr + PAGE_SIZE);
-
- if (new_page) {
- new_folio = page_folio(new_page);
- err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
- if (err)
- return err;
- }
-
- /* For folio_free_swap() below */
- folio_lock(old_folio);
-
- mmu_notifier_invalidate_range_start(&range);
- err = -EAGAIN;
- if (!page_vma_mapped_walk(&pvmw))
- goto unlock;
- VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
-
- if (new_page) {
- folio_get(new_folio);
- folio_add_new_anon_rmap(new_folio, vma, addr);
- folio_add_lru_vma(new_folio, vma);
- } else
- /* no new page, just dec_mm_counter for old_page */
- dec_mm_counter(mm, MM_ANONPAGES);
-
- if (!folio_test_anon(old_folio)) {
- dec_mm_counter(mm, mm_counter_file(old_folio));
- inc_mm_counter(mm, MM_ANONPAGES);
- }
-
- flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte)));
- ptep_clear_flush(vma, addr, pvmw.pte);
- if (new_page)
- set_pte_at(mm, addr, pvmw.pte,
- mk_pte(new_page, vma->vm_page_prot));
-
- folio_remove_rmap_pte(old_folio, old_page, vma);
- if (!folio_mapped(old_folio))
- folio_free_swap(old_folio);
- page_vma_mapped_walk_done(&pvmw);
- folio_put(old_folio);
-
- err = 0;
- unlock:
- mmu_notifier_invalidate_range_end(&range);
- folio_unlock(old_folio);
- return err;
-}
-
/**
* is_swbp_insn - check if instruction is breakpoint instruction.
* @insn: instruction to be checked.
@@ -438,6 +365,120 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
return ret;
}
+static bool orig_page_is_identical(struct vm_area_struct *vma,
+ unsigned long vaddr, struct page *page, bool *large)
+{
+ const pgoff_t index = vaddr_to_offset(vma, vaddr) >> PAGE_SHIFT;
+ struct page *orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
+ index);
+ struct folio *orig_folio;
+ bool identical;
+
+ if (!orig_page)
+ return false;
+ orig_folio = page_folio(orig_page);
+
+ *large = folio_test_large(orig_folio);
+ identical = folio_test_uptodate(orig_folio) &&
+ pages_identical(page, orig_page);
+ folio_put(orig_folio);
+ return identical;
+}
+
+#define UWO_NO_PGTABLE 0
+#define UWO_RETRY 1
+#define UWO_RETRY_WRITE_FAULT 2
+#define UWO_DONE 3
+#define UWO_DONE_COLLAPSE 4
+
+struct uwo_data {
+ unsigned long opcode_vaddr;
+ uprobe_opcode_t opcode;
+};
+
+static int __write_opcode_pte(pte_t *ptep, unsigned long vaddr,
+ unsigned long next, struct mm_walk *walk)
+{
+ struct uwo_data *data = walk->private;
+ const bool is_register = !!is_swbp_insn(&data->opcode);
+ pte_t pte = ptep_get(ptep);
+ struct folio *folio = NULL;
+ struct page *page;
+ bool large;
+
+ if (!pte_present(pte))
+ return UWO_RETRY;
+ page = vm_normal_page(walk->vma, vaddr, pte);
+ if (page)
+ folio = page_folio(page);
+
+ /*
+ * If we don't find an anonymous folio when unregistering, we're done.
+ */
+ if (!folio || !folio_test_anon(folio))
+ return is_register ? UWO_RETRY_WRITE_FAULT : UWO_DONE;
+
+ /*
+ * See can_follow_write_pte(): we'd actually prefer a writable PTE here,
+ * but when unregistering we might no longer have VM_WRITE ...
+ */
+ if (!pte_write(pte)) {
+ if (!PageAnonExclusive(page))
+ return UWO_RETRY_WRITE_FAULT;
+ if (unlikely(userfaultfd_pte_wp(walk->vma, pte)))
+ return UWO_RETRY_WRITE_FAULT;
+ /* SOFTDIRTY is handled via pte_mkdirty() below. */
+ }
+
+ /* Unmap + flush the TLB, such that we can write atomically .*/
+ flush_cache_page(walk->vma, vaddr, pte_pfn(pte));
+ pte = ptep_clear_flush(walk->vma, vaddr, ptep);
+ copy_to_page(page, data->opcode_vaddr, &data->opcode,
+ UPROBE_SWBP_INSN_SIZE);
+
+ /*
+ * When unregistering, we may only zap a PTE if uffd is disabled and
+ * there are no unexpected folio references ...
+ */
+ if (is_register || userfaultfd_missing(walk->vma) ||
+ (folio_ref_count(folio) != folio_mapcount(folio) +
+ folio_test_swapcache(folio) * folio_nr_pages(folio)))
+ goto remap;
+
+ /*
+ * ... and the mapped page is identical to the original page that
+ * would get faulted in on next access.
+ */
+ if (!orig_page_is_identical(walk->vma, vaddr, page, &large))
+ goto remap;
+
+ /* Zap it and try to reclaim swap space. */
+ dec_mm_counter(walk->mm, MM_ANONPAGES);
+ folio_remove_rmap_pte(folio, page, walk->vma);
+ if (!folio_mapped(folio) && folio_test_swapcache(folio) &&
+ folio_trylock(folio)) {
+ folio_free_swap(folio);
+ folio_unlock(folio);
+ }
+ folio_put(folio);
+
+ return large ? UWO_DONE_COLLAPSE : UWO_DONE;
+remap:
+ /*
+ * Make sure that our copy_to_page() changes become visible before the
+ * set_pte_at() write.
+ */
+ smp_wmb();
+ /* We modified the page. Make sure to mark the PTE dirty. */
+ set_pte_at(walk->mm, vaddr, ptep, pte_mkdirty(pte));
+ return UWO_DONE;
+}
+
+static const struct mm_walk_ops write_opcode_ops = {
+ .pte_entry = __write_opcode_pte,
+ .walk_lock = PGWALK_WRLOCK,
+};
+
/*
* NOTE:
* Expect the breakpoint instruction to be the smallest size instruction for
@@ -450,111 +491,116 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
* uprobe_write_opcode - write the opcode at a given virtual address.
* @auprobe: arch specific probepoint information.
* @vma: the probed virtual memory area.
- * @vaddr: the virtual address to store the opcode.
- * @opcode: opcode to be written at @vaddr.
+ * @opcode_vaddr: the virtual address to store the opcode.
+ * @opcode: opcode to be written at @opcode_vaddr.
*
* Called with mm->mmap_lock held for write.
* Return 0 (success) or a negative errno.
*/
int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
- unsigned long vaddr, uprobe_opcode_t opcode)
-{
- struct mm_struct *mm = vma->vm_mm;
- struct uprobe *uprobe;
- struct page *old_page, *new_page;
- int ret, is_register, ref_ctr_updated = 0;
- bool orig_page_huge = false;
+ const unsigned long opcode_vaddr, uprobe_opcode_t opcode)
+{
+ struct uprobe *uprobe = container_of(auprobe, struct uprobe, arch);
+ const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+ const bool is_register = !!is_swbp_insn(&opcode);
+ struct uwo_data data = {
+ .opcode = opcode,
+ .opcode_vaddr = opcode_vaddr,
+ };
unsigned int gup_flags = FOLL_FORCE;
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_notifier_range range;
+ int ret, ref_ctr_updated = 0;
+ struct page *page;
- is_register = is_swbp_insn(&opcode);
- uprobe = container_of(auprobe, struct uprobe, arch);
+ if (WARN_ON_ONCE(!is_cow_mapping(vma->vm_flags)))
+ return -EINVAL;
-retry:
+ /*
+ * When registering, we have to break COW to get an exclusive anonymous
+ * page that we can safely modify. Use FOLL_WRITE to trigger a write
+ * fault if required. When unregistering, we might be lucky and the
+ * anon page is already gone. So defer write faults until really
+ * required.
+ */
if (is_register)
- gup_flags |= FOLL_SPLIT_PMD;
- /* Read the page with vaddr into memory */
- ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &old_page, NULL);
+ gup_flags |= FOLL_WRITE;
+
+retry:
+ ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &page, NULL);
if (ret != 1)
- return ret;
+ goto out;
- ret = verify_opcode(old_page, vaddr, &opcode);
+ ret = verify_opcode(page, opcode_vaddr, &opcode);
+ put_page(page);
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;
- }
+ goto out;
/* 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);
if (ret)
- goto put_old;
-
+ goto out;
ref_ctr_updated = 1;
}
- ret = 0;
- if (!is_register && !PageAnon(old_page))
- goto put_old;
-
- ret = anon_vma_prepare(vma);
- if (ret)
- goto put_old;
-
- ret = -ENOMEM;
- new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
- if (!new_page)
- goto put_old;
-
- __SetPageUptodate(new_page);
- copy_highpage(new_page, old_page);
- copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
-
if (!is_register) {
- struct page *orig_page;
- pgoff_t index;
-
- VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
-
- index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
- orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
- index);
-
- if (orig_page) {
- if (PageUptodate(orig_page) &&
- pages_identical(new_page, orig_page)) {
- /* let go new_page */
- put_page(new_page);
- new_page = NULL;
-
- if (PageCompound(orig_page))
- orig_page_huge = true;
- }
- put_page(orig_page);
- }
+ /*
+ * In the common case, we'll be able to zap the page when
+ * unregistering. So trigger MMU notifiers now, as we won't
+ * be able to do it under PTL.
+ */
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+ vaddr, vaddr + PAGE_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
}
- ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
- if (new_page)
- put_page(new_page);
-put_old:
- put_page(old_page);
+ /*
+ * Perform another page table walk and perform the actual page
+ * modification.
+ */
+ ret = walk_page_range_vma(vma, vaddr, vaddr + PAGE_SIZE,
+ &write_opcode_ops, &data);
- if (unlikely(ret == -EAGAIN))
- goto retry;
+ if (!is_register)
+ mmu_notifier_invalidate_range_end(&range);
+ switch (ret) {
+ case UWO_NO_PGTABLE: /* walk_page_range_vma() returned 0. */
+ /*
+ * walk_page_range_vma() did not find anything. If there
+ * would have been a PMD-mapped file THP, it could have
+ * simply been zapped; in that (unlikely) case, there is
+ * nothing to when unregistering.
+ *
+ * If we had a PMD-mapped anonymous folio,
+ * walk_page_range_vma() would have PTE-mapped it for us
+ * and walked it.
+ */
+ if (is_register)
+ goto retry;
+ break;
+ case UWO_RETRY_WRITE_FAULT:
+ gup_flags |= FOLL_WRITE;
+ fallthrough;
+ case UWO_RETRY:
+ goto retry;
+ case UWO_DONE_COLLAPSE:
+ case UWO_DONE:
+ break;
+ default:
+ VM_WARN_ON_ONCE(1);
+ }
+out:
/* Revert back reference counter if instruction update failed. */
- if (ret && is_register && ref_ctr_updated)
+ if (ret < 0 && is_register && ref_ctr_updated)
update_ref_ctr(uprobe, mm, -1);
/* try collapse pmd for compound page */
- if (!ret && orig_page_huge)
+ if (ret == UWO_DONE_COLLAPSE)
collapse_pte_mapped_thp(mm, vaddr, false);
- return ret;
+ return ret < 0 ? ret : 0;
}
/**
--
2.45.1
We already have the VMA, no need to look it up using
get_user_page_vma_remote(). We can now switch to
get_user_pages_remote().
Signed-off-by: David Hildenbrand <[email protected]>
---
arch/arm/probes/uprobes/core.c | 4 ++--
include/linux/uprobes.h | 6 +++---
kernel/events/uprobes.c | 33 +++++++++++++++++----------------
3 files changed, 22 insertions(+), 21 deletions(-)
diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c
index f5f790c6e5f89..885e0c5e8c20d 100644
--- a/arch/arm/probes/uprobes/core.c
+++ b/arch/arm/probes/uprobes/core.c
@@ -26,10 +26,10 @@ bool is_swbp_insn(uprobe_opcode_t *insn)
(UPROBE_SWBP_ARM_INSN & 0x0fffffff);
}
-int set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
+int set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
unsigned long vaddr)
{
- return uprobe_write_opcode(auprobe, mm, vaddr,
+ return uprobe_write_opcode(auprobe, vma, vaddr,
__opcode_to_mem_arm(auprobe->bpinsn));
}
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index f46e0ca0169c7..77580dba6f8de 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -103,13 +103,13 @@ struct uprobes_state {
};
extern void __init uprobes_init(void);
-extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
-extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
+extern int set_swbp(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr);
+extern int set_orig_insn(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr);
extern bool is_swbp_insn(uprobe_opcode_t *insn);
extern bool is_trap_insn(uprobe_opcode_t *insn);
extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
-extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
+extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t);
extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c6d6b7a8e4410..f2b1fef7f1d62 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -449,19 +449,19 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
*
* uprobe_write_opcode - write the opcode at a given virtual address.
* @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
* @vaddr: the virtual address to store the opcode.
* @opcode: opcode to be written at @vaddr.
*
* Called with mm->mmap_lock held for write.
* Return 0 (success) or a negative errno.
*/
-int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
- unsigned long vaddr, uprobe_opcode_t opcode)
+int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+ unsigned long vaddr, uprobe_opcode_t opcode)
{
+ struct mm_struct *mm = vma->vm_mm;
struct uprobe *uprobe;
struct page *old_page, *new_page;
- struct vm_area_struct *vma;
int ret, is_register, ref_ctr_updated = 0;
bool orig_page_huge = false;
unsigned int gup_flags = FOLL_FORCE;
@@ -473,9 +473,9 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
if (is_register)
gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
- old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
- if (IS_ERR(old_page))
- return PTR_ERR(old_page);
+ ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &old_page, NULL);
+ if (ret != 1)
+ return ret;
ret = verify_opcode(old_page, vaddr, &opcode);
if (ret <= 0)
@@ -560,30 +560,31 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
/**
* set_swbp - store breakpoint at a given address.
* @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
* @vaddr: the virtual address to insert the opcode.
*
* For mm @mm, store the breakpoint instruction at @vaddr.
* Return 0 (success) or a negative errno.
*/
-int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+ unsigned long vaddr)
{
- return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+ return uprobe_write_opcode(auprobe, vma, vaddr, UPROBE_SWBP_INSN);
}
/**
* set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
* @auprobe: arch specific probepoint information.
* @vaddr: the virtual address to insert the opcode.
*
* For mm @mm, restore the original opcode (opcode) at @vaddr.
* Return 0 (success) or a negative errno.
*/
-int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_orig_insn(struct arch_uprobe *auprobe,
+ struct vm_area_struct *vma, unsigned long vaddr)
{
- return uprobe_write_opcode(auprobe, mm, vaddr,
+ return uprobe_write_opcode(auprobe, vma, vaddr,
*(uprobe_opcode_t *)&auprobe->insn);
}
@@ -905,7 +906,7 @@ static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
if (first_uprobe)
set_bit(MMF_HAS_UPROBES, &mm->flags);
- ret = set_swbp(&uprobe->arch, mm, vaddr);
+ ret = set_swbp(&uprobe->arch, vma, vaddr);
if (!ret)
clear_bit(MMF_RECALC_UPROBES, &mm->flags);
else if (first_uprobe)
@@ -920,7 +921,7 @@ static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
struct mm_struct *mm = vma->vm_mm;
set_bit(MMF_RECALC_UPROBES, &mm->flags);
- return set_orig_insn(&uprobe->arch, mm, vaddr);
+ return set_orig_insn(&uprobe->arch, vma, vaddr);
}
static inline bool uprobe_is_active(struct uprobe *uprobe)
--
2.45.1