x86/vdso: Add time napespace page

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 the time namespace 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@openvz.org>
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20191112012724.250792-23-dima@arista.com

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e894995366064ca3a3d3b58143a61057f99095e..a2488c372fa1698f484ce03ebac0f805aa7a27e0 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -124,6 +124,7 @@ config X86
        select GENERIC_STRNLEN_USER
        select GENERIC_TIME_VSYSCALL
        select GENERIC_GETTIMEOFDAY
+       select GENERIC_VDSO_TIME_NS
        select GUP_GET_PTE_LOW_HIGH             if X86_PAE
        select HARDLOCKUP_CHECK_TIMESTAMP       if X86_64
        select HAVE_ACPI_APEI                   if ACPI

diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 2330daad67c30866524eeecbcef36a657e6ed606..ea7e0155c604ee85b7f741b75b5e367419dda69a 100644 (file)
--- 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 3a4d8d4d39f87bb073c4c8b7504a293344ef3cfe..3842873b3ae3b6c5af587544e8e4c4804ea1f3af 100644 (file)
--- 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 230474e2ddb5b3eb687cdd647a15f750a65e5f32..bbcdc7b8f963c076186fbc706938b67b4bc61823 100644 (file)
--- 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 52c3bcd672cf5c0bcd5d558b490b8474fca85533..6ee1f7dba34bf4bfc87299a592ed38f76eb86b35 100644 (file)
--- 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 +57,13 @@ extern struct ms_hyperv_tsc_page hvclock_page
        __attribute__((visibility("hidden")));
 #endif
 
+#ifdef CONFIG_TIME_NS
+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 ff2de30253881936839fa4a3bcdd747798d006ad..183e98e49ab943aeaf9e7ecc183c2f383545887d 100644 (file)
--- 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]                                             \