powerpc/vdso: Switch to generic storage implementation

The generic storage implementation provides the same features as the
custom one. However it can be shared between architectures, making
maintenance easier.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-14-13a4669dfc8c@linutronix.de

9 files changed, 30 insertions, 120 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7a390bd4f4af..b3048f6d3822 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -334,7 +334,6 @@ int main(void)
 #endif /* ! CONFIG_PPC64 */
 
 	/* datapage offsets for use by vdso */
-	OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
 	OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
 #ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0727332ad86f..15784c5c95c7 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -950,7 +950,7 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
 	}
 
-	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+	vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec;
 #ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
 #endif
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 43379365ce1b..219d67bcf747 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -17,7 +17,7 @@
 #include <linux/elf.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
@@ -32,6 +32,8 @@
 #include <asm/vdso_datapage.h>
 #include <asm/setup.h>
 
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
+
 /* The alignment of the vDSO */
 #define VDSO_ALIGNMENT	(1 << 16)
 
@@ -40,24 +42,6 @@ extern char vdso64_start, vdso64_end;
 
 long sys_ni_syscall(void);
 
-/*
- * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
- * Once the early boot kernel code no longer needs to muck around
- * with it, it will become dynamically allocated
- */
-static union {
-	struct vdso_arch_data	data;
-	u8			page[2 * PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_arch_data *vdso_data = &vdso_data_store.data;
-
-enum vvar_pages {
-	VVAR_BASE_PAGE_OFFSET,
-	VVAR_TIME_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
@@ -96,14 +80,6 @@ static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struc
 	mm->context.vdso = NULL;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf);
-
-static struct vm_special_mapping vvar_spec __ro_after_init = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso32_mremap,
@@ -116,73 +92,6 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.close = vdso_close,
 };
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return 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.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_spec))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_BASE_PAGE_OFFSET:
-		pfn = virt_to_pfn(vdso_data);
-		break;
-	case VVAR_TIME_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = virt_to_pfn(vdso_data->data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = virt_to_pfn(vdso_data->data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -191,7 +100,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 {
 	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
-	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+	unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
@@ -217,9 +126,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	/* Add required alignment. */
 	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
 
-	vma = _install_special_mapping(mm, vdso_base, vvar_size,
-				       VM_READ | VM_MAYREAD | VM_IO |
-				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+	vma = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -299,10 +206,10 @@ static void __init vdso_setup_syscall_map(void)
 
 	for (i = 0; i < NR_syscalls; i++) {
 		if (sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 		if (IS_ENABLED(CONFIG_COMPAT) &&
 		    compat_sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 	}
 }
 
@@ -352,10 +259,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
-	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
-	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
-	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+	vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size;
+	vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size;
+	vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+	vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
 #endif /* CONFIG_PPC64 */
 
 	vdso_setup_syscall_map();
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index 0085ae464dac..488d3ade11e6 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 #ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r10
+	get_datapage	r10 vdso_u_arch_data
 	mtlr	r12
   .cfi_restore	lr
 #endif
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f0166..d23b2e8e2a34 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr.	r4,r3
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 	mtlr	r12
 #ifdef __powerpc64__
 	addi	r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 #ifndef __powerpc64__
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 #endif
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index 5333848322ca..79c967212444 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -33,9 +33,9 @@
   .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
 	.ifeq	\call_time
-		get_datapage	r5 VDSO_DATA_OFFSET
+		get_datapage	r5 vdso_u_time_data
 	.else
-		get_datapage	r4 VDSO_DATA_OFFSET
+		get_datapage	r4 vdso_u_time_data
 	.endif
 	bl		CFUNC(DOTSYM(\funct))
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
index 1a1b0b6d681a..72a1012b8a20 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash          	: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
index e21b5506cad6..32102a05eaa7 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
index 55a287c9a736..6f5167d81af5 100644
--- a/arch/powerpc/kernel/vdso/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -7,43 +7,43 @@
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_data(vd, clock_id, res);
 }
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime32_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd)
+			       const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_time32_data(vd, clock_id, res);
 }
 #endif
 
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_gettimeofday_data(vd, tv, tz);
 }
 
-__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd)
 {
 	return __cvdso_time_data(vd, time);
 }