lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 26 Nov 2020 13:42:07 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Matthew Wilcox <willy@...radead.org>
Cc:     kan.liang@...ux.intel.com, mingo@...nel.org, acme@...nel.org,
        mark.rutland@....com, alexander.shishkin@...ux.intel.com,
        jolsa@...hat.com, eranian@...gle.com, christophe.leroy@...roup.eu,
        npiggin@...il.com, linuxppc-dev@...ts.ozlabs.org,
        mpe@...erman.id.au, will@...nel.org, aneesh.kumar@...ux.ibm.com,
        sparclinux@...r.kernel.org, davem@...emloft.net,
        catalin.marinas@....com, linux-arch@...r.kernel.org,
        linux-kernel@...r.kernel.org, ak@...ux.intel.com,
        dave.hansen@...el.com, kirill.shutemov@...ux.intel.com
Subject: Re: [PATCH v2 3/6] perf/core: Fix arch_perf_get_page_size()

On Thu, Nov 26, 2020 at 12:34:58PM +0000, Matthew Wilcox wrote:
> On Thu, Nov 26, 2020 at 01:01:17PM +0100, Peter Zijlstra wrote:
> > The (new) page-table walker in arch_perf_get_page_size() is broken in
> > various ways. Specifically while it is used in a lockless manner, it
> > doesn't depend on CONFIG_HAVE_FAST_GUP nor uses the proper _lockless
> > offset methods, nor is careful to only read each entry only once.
> > 
> > Also the hugetlb support is broken due to calling pte_page() without
> > first checking pte_special().
> > 
> > Rewrite the whole thing to be a proper lockless page-table walker and
> > employ the new pXX_leaf_size() pgtable functions to determine the
> > pagetable size without looking at the page-frames.
> > 
> > Fixes: 51b646b2d9f8 ("perf,mm: Handle non-page-table-aligned hugetlbfs")
> > Fixes: 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE")
> > Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> > Tested-by: Kan Liang <kan.liang@...ux.intel.com>
> > ---
> >  arch/arm64/include/asm/pgtable.h    |    3 +
> >  arch/sparc/include/asm/pgtable_64.h |   13 ++++
> >  arch/sparc/mm/hugetlbpage.c         |   19 ++++--
> >  include/linux/pgtable.h             |   16 +++++
> >  kernel/events/core.c                |  102 +++++++++++++-----------------------
> >  5 files changed, 82 insertions(+), 71 deletions(-)
> 
> This diffstat doesn't match the patch in this email ...

Urgh, no idea how I did that... I must've edited the diff and not done a
quilt-refresh. Updated below.

---
Subject: perf/core: Fix arch_perf_get_page_size()
From: Peter Zijlstra <peterz@...radead.org>
Date: Wed, 11 Nov 2020 13:43:57 +0100

The (new) page-table walker in arch_perf_get_page_size() is broken in
various ways. Specifically while it is used in a lockless manner, it
doesn't depend on CONFIG_HAVE_FAST_GUP nor uses the proper _lockless
offset methods, nor is careful to only read each entry only once.

Also the hugetlb support is broken due to calling pte_page() without
first checking pte_special().

Rewrite the whole thing to be a proper lockless page-table walker and
employ the new pXX_leaf_size() pgtable functions to determine the
pagetable size without looking at the page-frames.

Fixes: 51b646b2d9f8 ("perf,mm: Handle non-page-table-aligned hugetlbfs")
Fixes: 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE")
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Tested-by: Kan Liang <kan.liang@...ux.intel.com>
---
 kernel/events/core.c |  105 ++++++++++++++++++---------------------------------
 1 file changed, 39 insertions(+), 66 deletions(-)

--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -52,6 +52,7 @@
 #include <linux/mount.h>
 #include <linux/min_heap.h>
 #include <linux/highmem.h>
+#include <linux/pgtable.h>
 
 #include "internal.h"
 
@@ -7001,90 +7002,62 @@ static u64 perf_virt_to_phys(u64 virt)
 	return phys_addr;
 }
 
-#ifdef CONFIG_MMU
-
 /*
- * Return the MMU page size of a given virtual address.
- *
- * This generic implementation handles page-table aligned huge pages, as well
- * as non-page-table aligned hugetlbfs compound pages.
- *
- * If an architecture supports and uses non-page-table aligned pages in their
- * kernel mapping it will need to provide it's own implementation of this
- * function.
+ * Return the pagetable size of a given virtual address.
  */
-__weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
 {
-	struct page *page;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	pgd = pgd_offset(mm, addr);
-	if (pgd_none(*pgd))
-		return 0;
+	u64 size = 0;
 
-	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+#ifdef CONFIG_HAVE_FAST_GUP
+	pgd_t *pgdp, pgd;
+	p4d_t *p4dp, p4d;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
+
+	pgdp = pgd_offset(mm, addr);
+	pgd = READ_ONCE(*pgdp);
+	if (pgd_none(pgd))
 		return 0;
 
-	if (p4d_leaf(*p4d))
-		return 1ULL << P4D_SHIFT;
+	if (pgd_leaf(pgd))
+		return pgd_leaf_size(pgd);
 
-	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	p4dp = p4d_offset_lockless(pgdp, pgd, addr);
+	p4d = READ_ONCE(*p4dp);
+	if (!p4d_present(p4d))
 		return 0;
 
-	if (pud_leaf(*pud)) {
-#ifdef pud_page
-		page = pud_page(*pud);
-		if (PageHuge(page))
-			return page_size(compound_head(page));
-#endif
-		return 1ULL << PUD_SHIFT;
-	}
+	if (p4d_leaf(p4d))
+		return p4d_leaf_size(p4d);
 
-	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	pudp = pud_offset_lockless(p4dp, p4d, addr);
+	pud = READ_ONCE(*pudp);
+	if (!pud_present(pud))
 		return 0;
 
-	if (pmd_leaf(*pmd)) {
-#ifdef pmd_page
-		page = pmd_page(*pmd);
-		if (PageHuge(page))
-			return page_size(compound_head(page));
-#endif
-		return 1ULL << PMD_SHIFT;
-	}
+	if (pud_leaf(pud))
+		return pud_leaf_size(pud);
 
-	pte = pte_offset_map(pmd, addr);
-	if (!pte_present(*pte)) {
-		pte_unmap(pte);
+	pmdp = pmd_offset_lockless(pudp, pud, addr);
+	pmd = READ_ONCE(*pmdp);
+	if (!pmd_present(pmd))
 		return 0;
-	}
 
-	page = pte_page(*pte);
-	if (PageHuge(page)) {
-		u64 size = page_size(compound_head(page));
-		pte_unmap(pte);
-		return size;
-	}
+	if (pmd_leaf(pmd))
+		return pmd_leaf_size(pmd);
 
-	pte_unmap(pte);
-	return PAGE_SIZE;
-}
-
-#else
+	ptep = pte_offset_map(&pmd, addr);
+	pte = ptep_get_lockless(ptep);
+	if (pte_present(pte))
+		size = pte_leaf_size(pte);
+	pte_unmap(ptep);
+#endif /* CONFIG_HAVE_FAST_GUP */
 
-static u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
-{
-	return 0;
+	return size;
 }
 
-#endif
-
 static u64 perf_get_page_size(unsigned long addr)
 {
 	struct mm_struct *mm;
@@ -7109,7 +7082,7 @@ static u64 perf_get_page_size(unsigned l
 		mm = &init_mm;
 	}
 
-	size = arch_perf_get_page_size(mm, addr);
+	size = perf_get_pgtable_size(mm, addr);
 
 	local_irq_restore(flags);
 

Powered by blists - more mailing lists