diff mbox series

[1/6] arm64/vdso: use the fault callback to map vvar pages

Message ID 20200624083321.144975-2-avagin@gmail.com (mailing list archive)
State New, archived
Headers show
Series arm64: add the time namespace support | expand

Commit Message

Andrei Vagin June 24, 2020, 8:33 a.m. UTC
Currently the vdso has no awareness of time namespaces, which may
apply distinct offsets to processes in different namespaces. To handle
this within the vdso, we'll need to expose a per-namespace data page.

As a preparatory step, this patch separates the vdso data page from
the code pages, and has it faulted in via its own fault callback.
Subsquent patches will extend this to support distinct pages per time
namespace.

The vvar vma has to be installed with the VM_PFNMAP flag to handle
faults via its vma fault callback.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
---
 arch/arm64/kernel/vdso.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

Comments

Andrei Vagin July 27, 2020, 6:45 a.m. UTC | #1
On Fri, Jul 24, 2020 at 06:26:23PM +0100, Catalin Marinas wrote:
> On Wed, 24 Jun 2020 01:33:16 -0700, Andrei Vagin wrote:
> > Currently the vdso has no awareness of time namespaces, which may
> > apply distinct offsets to processes in different namespaces. To handle
> > this within the vdso, we'll need to expose a per-namespace data page.
> > 
> > As a preparatory step, this patch separates the vdso data page from
> > the code pages, and has it faulted in via its own fault callback.
> > Subsquent patches will extend this to support distinct pages per time
> > namespace.
> > 
> > [...]
> 
> Applied to arm64 (for-next/timens), provisionally.
> 
> One potential issue I did not check is the compat vDSO. The arm32 port
> does not support timens currently. IIUC, with these patches and
> COMPAT_VDSO enabled, it will allow timens for compat processes. Normally
> I'd like the arm32 support first before updating compat but I don't
> think there would be any interface incompatibility here.
> 
> However, does this still work for arm32 processes if COMPAT_VDSO is
> disabled in the arm64 kernel?

Yes, it does. I checked that the timens test passes with and without
COMPAT_VDSO:

[avagin@laptop linux]$ git describe HEAD
v5.8-rc3-6-g9614cc576d76

alpine:/tip/tools/testing/selftests/timens# readelf  -h ./timens
ELF Header:
  Magic:   7f 45 4c 46 01 01 01 00 00 00 00 00 00 00 00 00 
  Class:                             ELF32
  Data:                              2's complement, little endian
  Version:                           1 (current)
  OS/ABI:                            UNIX - System V
  ABI Version:                       0
  Type:                              DYN (Shared object file)
  Machine:                           ARM
  Version:                           0x1
  Entry point address:               0x711
  Start of program headers:          52 (bytes into file)
  Start of section headers:          15444 (bytes into file)
  Flags:                             0x5000400, Version5 EABI,
hard-float ABI
  Size of this header:               52 (bytes)
  Size of program headers:           32 (bytes)
  Number of program headers:         7
  Size of section headers:           40 (bytes)
  Number of section headers:         32
  Section header string table index: 31

alpine:/tip/tools/testing/selftests/timens# uname -a
Linux arm64-alpine 5.8.0-rc3+ #100 SMP Sun Jul 26 23:21:07 PDT 2020
aarch64 Linux


[avagin@laptop linux]$ cat  .config | grep VDSO
CONFIG_COMPAT_VDSO=y
CONFIG_THUMB2_COMPAT_VDSO=y
CONFIG_HAVE_GENERIC_VDSO=y
CONFIG_GENERIC_COMPAT_VDSO=y
CONFIG_GENERIC_VDSO_TIME_NS=y


alpine:/tip/tools/testing/selftests/timens# ./timens
1..10
ok 1 Passed for CLOCK_BOOTTIME (syscall)
ok 2 Passed for CLOCK_BOOTTIME (vdso)
not ok 3 # SKIP CLOCK_BOOTTIME_ALARM isn't supported
not ok 4 # SKIP CLOCK_BOOTTIME_ALARM isn't supported
ok 5 Passed for CLOCK_MONOTONIC (syscall)
ok 6 Passed for CLOCK_MONOTONIC (vdso)
ok 7 Passed for CLOCK_MONOTONIC_COARSE (syscall)
ok 8 Passed for CLOCK_MONOTONIC_COARSE (vdso)
ok 9 Passed for CLOCK_MONOTONIC_RAW (syscall)
ok 10 Passed for CLOCK_MONOTONIC_RAW (vdso)
# Pass 8 Fail 0 Xfail 0 Xpass 0 Skip 2 Error 0


[avagin@laptop linux]$ cat  .config | grep VDSO
# CONFIG_COMPAT_VDSO is not set
CONFIG_HAVE_GENERIC_VDSO=y
CONFIG_GENERIC_VDSO_TIME_NS=y

alpine:/tip/tools/testing/selftests/timens# ./timens
1..10
ok 1 Passed for CLOCK_BOOTTIME (syscall)
ok 2 Passed for CLOCK_BOOTTIME (vdso)
not ok 3 # SKIP CLOCK_BOOTTIME_ALARM isn't supported
not ok 4 # SKIP CLOCK_BOOTTIME_ALARM isn't supported
ok 5 Passed for CLOCK_MONOTONIC (syscall)
ok 6 Passed for CLOCK_MONOTONIC (vdso)
ok 7 Passed for CLOCK_MONOTONIC_COARSE (syscall)
ok 8 Passed for CLOCK_MONOTONIC_COARSE (vdso)
ok 9 Passed for CLOCK_MONOTONIC_RAW (syscall)
ok 10 Passed for CLOCK_MONOTONIC_RAW (vdso)
# Pass 8 Fail 0 Xfail 0 Xpass 0 Skip 2 Error 0

Thanks,
Andrei
diff mbox series

Patch

diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 4e016574bd91..7c4620451fa5 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -107,29 +107,32 @@  static int __vdso_init(enum vdso_abi abi)
 			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages + 1,
+	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages,
 				sizeof(struct page *),
 				GFP_KERNEL);
 	if (vdso_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
 	/* Grab the vDSO code pages. */
 	pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
 
 	for (i = 0; i < vdso_info[abi].vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
 
-	vdso_info[abi].dm->pages = &vdso_pagelist[0];
-	vdso_info[abi].cm->pages = &vdso_pagelist[1];
+	vdso_info[abi].cm->pages = vdso_pagelist;
 
 	return 0;
 }
 
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	if (vmf->pgoff == 0)
+		return vmf_insert_pfn(vma, vmf->address,
+				sym_to_pfn(vdso_data));
+	return VM_FAULT_SIGBUS;
+}
+
 static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
@@ -150,7 +153,7 @@  static int __setup_additional_pages(enum vdso_abi abi,
 	}
 
 	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
+				       VM_READ|VM_MAYREAD|VM_PFNMAP,
 				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
 		goto up_fail;
@@ -209,6 +212,7 @@  static struct vm_special_mapping aarch32_vdso_maps[] = {
 #ifdef CONFIG_COMPAT_VDSO
 	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
+		.fault = vvar_fault,
 	},
 	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
@@ -376,6 +380,7 @@  enum aarch64_map {
 static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
 	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
+		.fault = vvar_fault,
 	},
 	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",