arm64/vdso: Add time namespace page

Allocate the time namespace page among VVAR pages.  Provide
__arch_get_timens_vdso_data() helper for VDSO code to get the
code-relative position of VVARs on that special page.

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.

The time-namespace page isn't allocated on !CONFIG_TIME_NAMESPACE, but
vma is the same size, which simplifies criu/vdso migration between
different kernel configs.

Signed-off-by: Andrei Vagin <[email protected]>
Reviewed-by: Vincenzo Frascino <[email protected]>
Reviewed-by: Dmitry Safonov <[email protected]>
Cc: Mark Rutland <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: avagin

arch/arm64/include/asm/vdso.h

@@ -12,6 +12,8 @@
  */
 #define VDSO_LBASE	0x0
 
+#define __VVAR_PAGES    2
+
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -152,6 +152,18 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
 	return ret;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	const struct vdso_data *ret;
+
+	/* See __arch_get_vdso_data(). */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
+
+	return ret;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -96,6 +96,14 @@ const struct vdso_data *__arch_get_vdso_data(void)
 	return _vdso_data;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return _timens_data;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/kernel/vdso.c

@@ -40,6 +40,12 @@ enum vdso_abi {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
@@ -125,6 +131,11 @@ static int __vdso_init(enum vdso_abi abi)
 }
 
 #ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
 /*
  * The vvar mapping contains data for a specific time namespace, so when a task
  * changes namespace we must unmap its vvar data for the old namespace.
@@ -173,17 +184,19 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
 		ret = ERR_PTR(vdso_base);
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
+	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
 				       VM_READ|VM_MAYREAD|VM_PFNMAP,
 				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
@@ -192,7 +205,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += PAGE_SIZE;
+	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|

arch/arm64/kernel/vdso/vdso.lds.S

@@ -17,7 +17,10 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - PAGE_SIZE);
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

arch/arm64/kernel/vdso32/vdso.lds.S

@@ -17,7 +17,10 @@ OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

include/vdso/datapage.h

@@ -109,6 +109,7 @@ struct vdso_data {
  * relocation, and this is what we need.
  */
 extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
 
 /*
  * The generic vDSO implementation requires that gettimeofday.h