[CRIU] [PATCHv7 21/33] x86/vdso: Add timens page

[Dmitry Safonov]

To support time namespaces in the VDSO with a minimal impact on regular non
time namespace affected tasks, the namespace handling needs to be hidden in
a slow path.

The most obvious place is vdso_seq_begin(). If a task belongs to a time
namespace then the VVAR page which contains the system wide VDSO data is
replaced with a namespace specific page which has the same layout as the
VVAR page. That page has vdso_data->seq set to 1 to enforce the slow path
and vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time
namespace handling path.

The extra check in the case that vdso_data->seq is odd, e.g. a concurrent
update of the VDSO data is in progress, is not really affecting regular
tasks which are not part of a time namespace as the task is spin waiting
for the update to finish and vdso_data->seq to become even again.

If a time namespace task hits that code path, it invokes the corresponding
time getter function which retrieves the real VVAR page, reads host time
and then adds the offset for the requested clock which is stored in the
special VVAR page.

Allocate Timens page among VVAR pages and place vdso_data on it.
Provide __arch_get_timens_vdso_data() helper for VDSO code to get the
code-relative position of VVARs on that special page.

Co-developed-by: Andrei Vagin <avagin at openvz.org>
Signed-off-by: Andrei Vagin <avagin at openvz.org>
Signed-off-by: Dmitry Safonov <dima at arista.com>
---
 arch/x86/Kconfig                         |  1 +
 arch/x86/entry/vdso/vdso-layout.lds.S    | 11 +++++++++--
 arch/x86/entry/vdso/vdso2c.c             |  3 +++
 arch/x86/include/asm/vdso.h              |  1 +
 arch/x86/include/asm/vdso/gettimeofday.h |  9 +++++++++
 arch/x86/include/asm/vvar.h              |  5 ++++-
 6 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d6e1faa28c58..15f076eb2b1c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -226,6 +226,7 @@ config X86
 	select VIRT_TO_BUS
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
+	select VDSO_TIMENS			if TIME_NS
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 2330daad67c3..ea7e0155c604 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -16,8 +16,8 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 3 * PAGE_SIZE;
-	vvar_page = vvar_start;
+	vvar_start = . - 4 * PAGE_SIZE;
+	vvar_page  = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
 #define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
@@ -26,6 +26,13 @@ SECTIONS
 
 	pvclock_page = vvar_start + PAGE_SIZE;
 	hvclock_page = vvar_start + 2 * PAGE_SIZE;
+	timens_page  = vvar_start + 3 * PAGE_SIZE;
+
+#undef _ASM_X86_VVAR_H
+	/* Place all vvars in timens too at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) timens_ ## name = timens_page + offset;
+#include <asm/vvar.h>
+#undef EMIT_VVAR
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 3a4d8d4d39f8..3842873b3ae3 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -75,12 +75,14 @@ enum {
 	sym_vvar_page,
 	sym_pvclock_page,
 	sym_hvclock_page,
+	sym_timens_page,
 };
 
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_pvclock_page,
 	sym_hvclock_page,
+	sym_timens_page,
 };
 
 struct vdso_sym {
@@ -93,6 +95,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_hvclock_page] = {"hvclock_page", true},
+	[sym_timens_page] = {"timens_page", true},
 	{"VDSO32_NOTE_MASK", true},
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 230474e2ddb5..bbcdc7b8f963 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -21,6 +21,7 @@ struct vdso_image {
 	long sym_vvar_page;
 	long sym_pvclock_page;
 	long sym_hvclock_page;
+	long sym_timens_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index e9ee139cf29e..39a551df4fea 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -21,6 +21,7 @@
 #include <clocksource/hyperv_timer.h>
 
 #define __vdso_data (VVAR(_vdso_data))
+#define __timens_vdso_data (TIMENS(_vdso_data))
 
 #define VDSO_HAS_TIME 1
 
@@ -56,6 +57,14 @@ extern struct ms_hyperv_tsc_page hvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
+#ifdef CONFIG_VDSO_TIMENS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return __timens_vdso_data;
+}
+#endif
+
 #ifndef BUILD_VDSO32
 
 static __always_inline
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index ff2de3025388..183e98e49ab9 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -33,9 +33,12 @@ extern char __vvar_page;
 
 #define DECLARE_VVAR(offset, type, name)				\
 	extern type vvar_ ## name[CS_BASES]				\
-	__attribute__((visibility("hidden")));
+	__attribute__((visibility("hidden")));				\
+	extern type timens_ ## name[CS_BASES]				\
+	__attribute__((visibility("hidden")));				\
 
 #define VVAR(name) (vvar_ ## name)
+#define TIMENS(name) (timens_ ## name)
 
 #define DEFINE_VVAR(type, name)						\
 	type name[CS_BASES]						\
-- 
2.23.0