Similarly to the 64-bit vdso, make 32-bit vdso mapping per-ve.
This will allow per container modification of the linux version
xin .note section of vdso and monotonic time.

https://jira.sw.ru/browse/PSBM-121668
Signed-off-by: Andrey Ryabinin <aryabi...@virtuozzo.com>
---
 arch/x86/entry/vdso/vma.c    |  4 ++--
 arch/x86/kernel/process_64.c |  2 +-
 include/linux/ve.h           |  1 +
 kernel/ve/ve.c               | 35 +++++++++++++++++++++--------------
 4 files changed, 25 insertions(+), 17 deletions(-)

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index c48deffc1473..538c6730f436 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -56,7 +56,7 @@ static void vdso_fix_landing(const struct vdso_image *image,
                struct vm_area_struct *new_vma)
 {
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-       if (in_ia32_syscall() && image == &vdso_image_32) {
+       if (in_ia32_syscall() && image == get_exec_env()->vdso_32) {
                struct pt_regs *regs = current_pt_regs();
                unsigned long vdso_land = image->sym_int80_landing_pad;
                unsigned long old_land_addr = vdso_land +
@@ -281,7 +281,7 @@ static int load_vdso32(void)
        if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
                return 0;
 
-       return map_vdso(&vdso_image_32, 0);
+       return map_vdso(get_exec_env()->vdso_32, 0);
 }
 #endif
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a010d4b9d126..dddd22215141 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -686,7 +686,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, 
unsigned long arg2)
 # endif
 # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
        case ARCH_MAP_VDSO_32:
-               return prctl_map_vdso(&vdso_image_32, arg2);
+               return prctl_map_vdso(get_exec_env()->vdso_32, arg2);
 # endif
        case ARCH_MAP_VDSO_64:
                return prctl_map_vdso(get_exec_env()->vdso_64, arg2);
diff --git a/include/linux/ve.h b/include/linux/ve.h
index 0e85a4032c3a..5b1962ff4c66 100644
--- a/include/linux/ve.h
+++ b/include/linux/ve.h
@@ -95,6 +95,7 @@ struct ve_struct {
        struct cn_private       *cn;
 #endif
        struct vdso_image       *vdso_64;
+       struct vdso_image       *vdso_32;
 };
 
 #define VE_MEMINFO_DEFAULT     1       /* default behaviour */
diff --git a/kernel/ve/ve.c b/kernel/ve/ve.c
index 186deb3f88f4..03b8d126a0ed 100644
--- a/kernel/ve/ve.c
+++ b/kernel/ve/ve.c
@@ -58,6 +58,7 @@ struct ve_struct ve0 = {
        .netns_max_nr           = INT_MAX,
        .meminfo_val            = VE_MEMINFO_SYSTEM,
        .vdso_64                = (struct vdso_image*)&vdso_image_64,
+       .vdso_32                = (struct vdso_image*)&vdso_image_32,
 };
 EXPORT_SYMBOL(ve0);
 
@@ -540,13 +541,12 @@ static __u64 ve_setup_iptables_mask(__u64 init_mask)
 }
 #endif
 
-static int copy_vdso(struct ve_struct *ve)
+static int copy_vdso(struct vdso_image **vdso_dst, const struct vdso_image 
*vdso_src)
 {
-       const struct vdso_image *vdso_src = &vdso_image_64;
        struct vdso_image *vdso;
        void *vdso_data;
 
-       if (ve->vdso_64)
+       if (*vdso_dst)
                return 0;
 
        vdso = kmemdup(vdso_src, sizeof(*vdso), GFP_KERNEL);
@@ -563,10 +563,22 @@ static int copy_vdso(struct ve_struct *ve)
 
        vdso->data = vdso_data;
 
-       ve->vdso_64 = vdso;
+       *vdso_dst = vdso;
        return 0;
 }
 
+static void ve_free_vdso(struct ve_struct *ve)
+{
+       if (ve->vdso_64 && ve->vdso_64 != &vdso_image_64) {
+               kfree(ve->vdso_64->data);
+               kfree(ve->vdso_64);
+       }
+       if (ve->vdso_32 && ve->vdso_32 != &vdso_image_32) {
+               kfree(ve->vdso_32->data);
+               kfree(ve->vdso_32);
+       }
+}
+
 static struct cgroup_subsys_state *ve_create(struct cgroup_subsys_state 
*parent_css)
 {
        struct ve_struct *ve = &ve0;
@@ -592,7 +604,10 @@ static struct cgroup_subsys_state *ve_create(struct 
cgroup_subsys_state *parent_
        if (err)
                goto err_log;
 
-       if (copy_vdso(ve))
+       if (copy_vdso(&ve->vdso_64, &vdso_image_64))
+               goto err_vdso;
+
+       if (copy_vdso(&ve->vdso_32, &vdso_image_32))
                goto err_vdso;
 
        ve->features = VE_FEATURES_DEF;
@@ -619,6 +634,7 @@ static struct cgroup_subsys_state *ve_create(struct 
cgroup_subsys_state *parent_
        return &ve->css;
 
 err_vdso:
+       ve_free_vdso(ve);
        ve_log_destroy(ve);
 err_log:
        free_percpu(ve->sched_lat_ve.cur);
@@ -658,15 +674,6 @@ static void ve_offline(struct cgroup_subsys_state *css)
        ve->ve_name = NULL;
 }
 
-static void ve_free_vdso(struct ve_struct *ve)
-{
-       if (ve->vdso_64 == &vdso_image_64)
-               return;
-
-       kfree(ve->vdso_64->data);
-       kfree(ve->vdso_64);
-}
-
 static void ve_destroy(struct cgroup_subsys_state *css)
 {
        struct ve_struct *ve = css_to_ve(css);
-- 
2.26.2

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel

Reply via email to