Re: [PATCHv5 23/37] x86/vdso: Add offsets page in vvar

From: Andrei Vagin <redacted>

As modern applications fetch time from VDSO without entering the kernel,
it's needed to provide offsets for userspace code inside time namespace.

A page for timens offsets is allocated on time namespace construction.
Put that page into VVAR for tasks inside timens and zero page for
host processes.

As VDSO code is already optimized as much as possible in terms of speed,
any new if-condition in VDSO code is undesirable; the goal is to provide
two .so(s), as was originally suggested by Andy and Thomas:
- for host tasks with optimized-out clk_to_ns() without any penalty
- for processes inside timens with clk_to_ns()
For this purpose, define clk_to_ns() under CONFIG_TIME_NS.

To eliminate any performance regression, clk_to_ns() will be called
under static_branch with follow-up patches, that adds support for
patching vdso.

VDSO mappings are platform-specific, add Kconfig dependency for arch.

Signed-off-by: Andrei Vagin <redacted>
Co-developed-by: Dmitry Safonov <redacted>
Signed-off-by: Dmitry Safonov <redacted>
---
 arch/Kconfig                          |  5 +++
 arch/x86/Kconfig                      |  1 +
 arch/x86/entry/vdso/vdso-layout.lds.S |  9 ++++-
 arch/x86/entry/vdso/vdso2c.c          |  3 ++
 arch/x86/entry/vdso/vma.c             | 12 +++++++
 arch/x86/include/asm/vdso.h           |  1 +
 init/Kconfig                          |  1 +
 lib/vdso/gettimeofday.c               | 47 +++++++++++++++++++++++++++
 8 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index a7b57dd42c26..e43d27f510ec 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig

@@ -729,6 +729,11 @@ config HAVE_ARCH_NVRAM_OPS
 config ISA_BUS_API
        def_bool ISA

+config ARCH_HAS_VDSO_TIME_NS
+       bool
+       help
+        VDSO can add time-ns offsets without entering kernel.
+
 #
 # ABI hall of shame
 #

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 222855cc0158..91615938b470 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig

@@ -81,6 +81,7 @@ config X86
        select ARCH_HAS_STRICT_MODULE_RWX
        select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
        select ARCH_HAS_UBSAN_SANITIZE_ALL
+       select ARCH_HAS_VDSO_TIME_NS
        select ARCH_HAVE_NMI_SAFE_CMPXCHG
        select ARCH_MIGHT_HAVE_ACPI_PDC         if ACPI
        select ARCH_MIGHT_HAVE_PC_PARPORT

diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 93c6dc7812d0..ba216527e59f 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S

@@ -7,6 +7,12 @@
  * This script controls its layout.
  */

+#ifdef CONFIG_TIME_NS
+# define TIMENS_SZ     PAGE_SIZE
+#else
+# define TIMENS_SZ     0
+#endif
+
 SECTIONS
 {
        /*

@@ -16,7 +22,7 @@ SECTIONS
         * segment.
         */

-       vvar_start = . - 3 * PAGE_SIZE;
+       vvar_start = . - (3 * PAGE_SIZE + TIMENS_SZ);
        vvar_page = vvar_start;

        /* Place all vvars at the offsets in asm/vvar.h. */

@@ -28,6 +34,7 @@ SECTIONS

        pvclock_page = vvar_start + PAGE_SIZE;
        hvclock_page = vvar_start + 2 * PAGE_SIZE;
+       timens_page = vvar_start + 3 * PAGE_SIZE;

        . = SIZEOF_HEADERS;

diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index ce67370d14e5..7380908045c7 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/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 2dc4f0b5481c..9bd66f84db5e 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c

@@ -14,6 +14,7 @@
 #include <linux/elf.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
+#include <linux/time_namespace.h>
 #include <asm/pvclock.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>

@@ -23,6 +24,7 @@
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
 #include <clocksource/hyperv_timer.h>
+#include <asm/page.h>

 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;

@@ -135,6 +137,16 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
                if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
                        return vmf_insert_pfn(vma, vmf->address,
                                        vmalloc_to_pfn(tsc_pg));
+       } else if (sym_offset == image->sym_timens_page) {
+               struct time_namespace *ns = current->nsproxy->time_ns;