From: Guo Ren <[email protected]>
Reconstruct __setup_additional_pages() by appending vdso info
pointer argument to meet compat_vdso_info requirement. And change
vm_special_mapping *dm, *cm initialization into static.
Signed-off-by: Guo Ren <[email protected]>
Signed-off-by: Guo Ren <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Palmer Dabbelt <[email protected]>
---
arch/riscv/include/asm/elf.h | 5 ++
arch/riscv/include/asm/mmu.h | 1 +
arch/riscv/kernel/vdso.c | 104 +++++++++++++++++++++++++----------
3 files changed, 81 insertions(+), 29 deletions(-)
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 3a4293dc7229..d87d3bcc758d 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -134,5 +134,10 @@ do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
typedef compat_ulong_t compat_elf_greg_t;
typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG];
+extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+#define compat_arch_setup_additional_pages \
+ compat_arch_setup_additional_pages
+
#endif /* CONFIG_COMPAT */
#endif /* _ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 0099dc116168..cedcf8ea3c76 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -16,6 +16,7 @@ typedef struct {
atomic_long_t id;
#endif
void *vdso;
+ void *vdso_info;
#ifdef CONFIG_SMP
/* A local icache flush is needed before user execution can resume. */
cpumask_t icache_stale_mask;
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index a9436a65161a..deca69524799 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -23,6 +23,9 @@ struct vdso_data {
#endif
extern char vdso_start[], vdso_end[];
+#ifdef CONFIG_COMPAT
+extern char compat_vdso_start[], compat_vdso_end[];
+#endif
enum vvar_pages {
VVAR_DATA_PAGE_OFFSET,
@@ -30,6 +33,11 @@ enum vvar_pages {
VVAR_NR_PAGES,
};
+enum rv_vdso_map {
+ RV_VDSO_MAP_VVAR,
+ RV_VDSO_MAP_VDSO,
+};
+
#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
/*
@@ -52,12 +60,6 @@ struct __vdso_info {
struct vm_special_mapping *cm;
};
-static struct __vdso_info vdso_info __ro_after_init = {
- .name = "vdso",
- .vdso_code_start = vdso_start,
- .vdso_code_end = vdso_end,
-};
-
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
@@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
return 0;
}
-static int __init __vdso_init(void)
+static int __init __vdso_init(struct __vdso_info *vdso_info)
{
unsigned int i;
struct page **vdso_pagelist;
unsigned long pfn;
- if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
+ if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
return -EINVAL;
}
- vdso_info.vdso_pages = (
- vdso_info.vdso_code_end -
- vdso_info.vdso_code_start) >>
+ vdso_info->vdso_pages = (
+ vdso_info->vdso_code_end -
+ vdso_info->vdso_code_start) >>
PAGE_SHIFT;
- vdso_pagelist = kcalloc(vdso_info.vdso_pages,
+ vdso_pagelist = kcalloc(vdso_info->vdso_pages,
sizeof(struct page *),
GFP_KERNEL);
if (vdso_pagelist == NULL)
return -ENOMEM;
/* Grab the vDSO code pages. */
- pfn = sym_to_pfn(vdso_info.vdso_code_start);
+ pfn = sym_to_pfn(vdso_info->vdso_code_start);
- for (i = 0; i < vdso_info.vdso_pages; i++)
+ for (i = 0; i < vdso_info->vdso_pages; i++)
vdso_pagelist[i] = pfn_to_page(pfn + i);
- vdso_info.cm->pages = vdso_pagelist;
+ vdso_info->cm->pages = vdso_pagelist;
return 0;
}
@@ -116,13 +118,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
{
struct mm_struct *mm = task->mm;
struct vm_area_struct *vma;
+ struct __vdso_info *vdso_info = mm->context.vdso_info;
mmap_read_lock(mm);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
unsigned long size = vma->vm_end - vma->vm_start;
- if (vma_is_special_mapping(vma, vdso_info.dm))
+ if (vma_is_special_mapping(vma, vdso_info->dm))
zap_page_range(vma, vma->vm_start, size);
}
@@ -187,11 +190,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
return vmf_insert_pfn(vma, vmf->address, pfn);
}
-enum rv_vdso_map {
- RV_VDSO_MAP_VVAR,
- RV_VDSO_MAP_VDSO,
-};
-
static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
[RV_VDSO_MAP_VVAR] = {
.name = "[vvar]",
@@ -203,25 +201,53 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
},
};
+static struct __vdso_info vdso_info __ro_after_init = {
+ .name = "vdso",
+ .vdso_code_start = vdso_start,
+ .vdso_code_end = vdso_end,
+ .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
+ .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
+};
+
+#ifdef CONFIG_COMPAT
+static struct __vdso_info compat_vdso_info __ro_after_init = {
+ .name = "compat_vdso",
+ .vdso_code_start = compat_vdso_start,
+ .vdso_code_end = compat_vdso_end,
+ .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
+ .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
+};
+#endif
+
static int __init vdso_init(void)
{
- vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR];
- vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO];
+ int ret;
+
+ ret = __vdso_init(&vdso_info);
+ if (ret)
+ goto out;
- return __vdso_init();
+#ifdef CONFIG_COMPAT
+ ret = __vdso_init(&compat_vdso_info);
+ if (ret)
+ goto out;
+#endif
+out:
+ return ret;
}
arch_initcall(vdso_init);
static int __setup_additional_pages(struct mm_struct *mm,
struct linux_binprm *bprm,
- int uses_interp)
+ int uses_interp,
+ struct __vdso_info *vdso_info)
{
unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
void *ret;
BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
- vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT;
+ vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
/* Be sure to map the data page */
vdso_mapping_len = vdso_text_len + VVAR_SIZE;
@@ -232,16 +258,18 @@ static int __setup_additional_pages(struct mm_struct *mm,
}
ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
- (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm);
+ (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm);
if (IS_ERR(ret))
goto up_fail;
vdso_base += VVAR_SIZE;
mm->context.vdso = (void *)vdso_base;
+ mm->context.vdso_info = (void *)vdso_info;
+
ret =
_install_special_mapping(mm, vdso_base, vdso_text_len,
(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
- vdso_info.cm);
+ vdso_info->cm);
if (IS_ERR(ret))
goto up_fail;
@@ -253,6 +281,24 @@ static int __setup_additional_pages(struct mm_struct *mm,
return PTR_ERR(ret);
}
+#ifdef CONFIG_COMPAT
+int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ int ret;
+
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
+ ret = __setup_additional_pages(mm, bprm, uses_interp,
+ &compat_vdso_info);
+ mmap_write_unlock(mm);
+
+ return ret;
+}
+#endif
+
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
@@ -261,7 +307,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (mmap_write_lock_killable(mm))
return -EINTR;
- ret = __setup_additional_pages(mm, bprm, uses_interp);
+ ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info);
mmap_write_unlock(mm);
return ret;
--
2.25.1
On Tue, 01 Feb 2022 07:05:41 PST (-0800), [email protected] wrote:
> From: Guo Ren <[email protected]>
>
> Reconstruct __setup_additional_pages() by appending vdso info
> pointer argument to meet compat_vdso_info requirement. And change
> vm_special_mapping *dm, *cm initialization into static.
>
> Signed-off-by: Guo Ren <[email protected]>
> Signed-off-by: Guo Ren <[email protected]>
> Cc: Arnd Bergmann <[email protected]>
> Cc: Palmer Dabbelt <[email protected]>
> ---
> arch/riscv/include/asm/elf.h | 5 ++
> arch/riscv/include/asm/mmu.h | 1 +
> arch/riscv/kernel/vdso.c | 104 +++++++++++++++++++++++++----------
> 3 files changed, 81 insertions(+), 29 deletions(-)
>
> diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
> index 3a4293dc7229..d87d3bcc758d 100644
> --- a/arch/riscv/include/asm/elf.h
> +++ b/arch/riscv/include/asm/elf.h
> @@ -134,5 +134,10 @@ do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
> typedef compat_ulong_t compat_elf_greg_t;
> typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG];
>
> +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> + int uses_interp);
> +#define compat_arch_setup_additional_pages \
> + compat_arch_setup_additional_pages
> +
> #endif /* CONFIG_COMPAT */
> #endif /* _ASM_RISCV_ELF_H */
> diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> index 0099dc116168..cedcf8ea3c76 100644
> --- a/arch/riscv/include/asm/mmu.h
> +++ b/arch/riscv/include/asm/mmu.h
> @@ -16,6 +16,7 @@ typedef struct {
> atomic_long_t id;
> #endif
> void *vdso;
> + void *vdso_info;
> #ifdef CONFIG_SMP
> /* A local icache flush is needed before user execution can resume. */
> cpumask_t icache_stale_mask;
> diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
> index a9436a65161a..deca69524799 100644
> --- a/arch/riscv/kernel/vdso.c
> +++ b/arch/riscv/kernel/vdso.c
> @@ -23,6 +23,9 @@ struct vdso_data {
> #endif
>
> extern char vdso_start[], vdso_end[];
> +#ifdef CONFIG_COMPAT
> +extern char compat_vdso_start[], compat_vdso_end[];
> +#endif
>
> enum vvar_pages {
> VVAR_DATA_PAGE_OFFSET,
> @@ -30,6 +33,11 @@ enum vvar_pages {
> VVAR_NR_PAGES,
> };
>
> +enum rv_vdso_map {
> + RV_VDSO_MAP_VVAR,
> + RV_VDSO_MAP_VDSO,
> +};
> +
> #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
>
> /*
> @@ -52,12 +60,6 @@ struct __vdso_info {
> struct vm_special_mapping *cm;
> };
>
> -static struct __vdso_info vdso_info __ro_after_init = {
> - .name = "vdso",
> - .vdso_code_start = vdso_start,
> - .vdso_code_end = vdso_end,
> -};
> -
> static int vdso_mremap(const struct vm_special_mapping *sm,
> struct vm_area_struct *new_vma)
> {
> @@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
> return 0;
> }
>
> -static int __init __vdso_init(void)
> +static int __init __vdso_init(struct __vdso_info *vdso_info)
> {
> unsigned int i;
> struct page **vdso_pagelist;
> unsigned long pfn;
>
> - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
> + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
> pr_err("vDSO is not a valid ELF object!\n");
> return -EINVAL;
> }
>
> - vdso_info.vdso_pages = (
> - vdso_info.vdso_code_end -
> - vdso_info.vdso_code_start) >>
> + vdso_info->vdso_pages = (
> + vdso_info->vdso_code_end -
> + vdso_info->vdso_code_start) >>
> PAGE_SHIFT;
>
> - vdso_pagelist = kcalloc(vdso_info.vdso_pages,
> + vdso_pagelist = kcalloc(vdso_info->vdso_pages,
> sizeof(struct page *),
> GFP_KERNEL);
> if (vdso_pagelist == NULL)
> return -ENOMEM;
>
> /* Grab the vDSO code pages. */
> - pfn = sym_to_pfn(vdso_info.vdso_code_start);
> + pfn = sym_to_pfn(vdso_info->vdso_code_start);
>
> - for (i = 0; i < vdso_info.vdso_pages; i++)
> + for (i = 0; i < vdso_info->vdso_pages; i++)
> vdso_pagelist[i] = pfn_to_page(pfn + i);
>
> - vdso_info.cm->pages = vdso_pagelist;
> + vdso_info->cm->pages = vdso_pagelist;
>
> return 0;
> }
> @@ -116,13 +118,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
> {
> struct mm_struct *mm = task->mm;
> struct vm_area_struct *vma;
> + struct __vdso_info *vdso_info = mm->context.vdso_info;
IIUC this is the only use for context.vdso_info? If that's the case,
can we just switch between VDSO targets based on __is_compat_task(task)?
That'd save an mm_struct pointer, which is always nice. It'd probably
be worth cleaning up the arm64 port too, which zaps both mappings.
>
> mmap_read_lock(mm);
>
> for (vma = mm->mmap; vma; vma = vma->vm_next) {
> unsigned long size = vma->vm_end - vma->vm_start;
>
> - if (vma_is_special_mapping(vma, vdso_info.dm))
> + if (vma_is_special_mapping(vma, vdso_info->dm))
> zap_page_range(vma, vma->vm_start, size);
> }
>
> @@ -187,11 +190,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
> return vmf_insert_pfn(vma, vmf->address, pfn);
> }
>
> -enum rv_vdso_map {
> - RV_VDSO_MAP_VVAR,
> - RV_VDSO_MAP_VDSO,
> -};
> -
> static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> [RV_VDSO_MAP_VVAR] = {
> .name = "[vvar]",
> @@ -203,25 +201,53 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> },
> };
>
> +static struct __vdso_info vdso_info __ro_after_init = {
> + .name = "vdso",
> + .vdso_code_start = vdso_start,
> + .vdso_code_end = vdso_end,
> + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> +};
> +
> +#ifdef CONFIG_COMPAT
> +static struct __vdso_info compat_vdso_info __ro_after_init = {
> + .name = "compat_vdso",
> + .vdso_code_start = compat_vdso_start,
> + .vdso_code_end = compat_vdso_end,
> + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> +};
> +#endif
> +
> static int __init vdso_init(void)
> {
> - vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR];
> - vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO];
> + int ret;
> +
> + ret = __vdso_init(&vdso_info);
> + if (ret)
> + goto out;
>
> - return __vdso_init();
> +#ifdef CONFIG_COMPAT
> + ret = __vdso_init(&compat_vdso_info);
> + if (ret)
> + goto out;
It's a bit pedantic (we're just going to crash anyway), but this is
mising the cleanup for the first __vdso_init().
> +#endif
> +out:
> + return ret;
> }
> arch_initcall(vdso_init);
>
> static int __setup_additional_pages(struct mm_struct *mm,
> struct linux_binprm *bprm,
> - int uses_interp)
> + int uses_interp,
> + struct __vdso_info *vdso_info)
> {
> unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
> void *ret;
>
> BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
>
> - vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT;
> + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
> /* Be sure to map the data page */
> vdso_mapping_len = vdso_text_len + VVAR_SIZE;
>
> @@ -232,16 +258,18 @@ static int __setup_additional_pages(struct mm_struct *mm,
> }
>
> ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
> - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm);
> + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm);
> if (IS_ERR(ret))
> goto up_fail;
>
> vdso_base += VVAR_SIZE;
> mm->context.vdso = (void *)vdso_base;
> + mm->context.vdso_info = (void *)vdso_info;
> +
> ret =
> _install_special_mapping(mm, vdso_base, vdso_text_len,
> (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
> - vdso_info.cm);
> + vdso_info->cm);
>
> if (IS_ERR(ret))
> goto up_fail;
> @@ -253,6 +281,24 @@ static int __setup_additional_pages(struct mm_struct *mm,
> return PTR_ERR(ret);
> }
>
> +#ifdef CONFIG_COMPAT
> +int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> + int uses_interp)
> +{
> + struct mm_struct *mm = current->mm;
> + int ret;
> +
> + if (mmap_write_lock_killable(mm))
> + return -EINTR;
> +
> + ret = __setup_additional_pages(mm, bprm, uses_interp,
> + &compat_vdso_info);
> + mmap_write_unlock(mm);
> +
> + return ret;
> +}
> +#endif
> +
> int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> {
> struct mm_struct *mm = current->mm;
> @@ -261,7 +307,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> if (mmap_write_lock_killable(mm))
> return -EINTR;
>
> - ret = __setup_additional_pages(mm, bprm, uses_interp);
> + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info);
> mmap_write_unlock(mm);
>
> return ret;
Reviewed-by: Palmer Dabbelt <[email protected]>
As I don't think either of these are big enough of a deal to keep from merging
this.
On Wed, Feb 23, 2022 at 9:42 AM Palmer Dabbelt <[email protected]> wrote:
>
> On Tue, 01 Feb 2022 07:05:41 PST (-0800), [email protected] wrote:
> > From: Guo Ren <[email protected]>
> >
> > Reconstruct __setup_additional_pages() by appending vdso info
> > pointer argument to meet compat_vdso_info requirement. And change
> > vm_special_mapping *dm, *cm initialization into static.
> >
> > Signed-off-by: Guo Ren <[email protected]>
> > Signed-off-by: Guo Ren <[email protected]>
> > Cc: Arnd Bergmann <[email protected]>
> > Cc: Palmer Dabbelt <[email protected]>
> > ---
> > arch/riscv/include/asm/elf.h | 5 ++
> > arch/riscv/include/asm/mmu.h | 1 +
> > arch/riscv/kernel/vdso.c | 104 +++++++++++++++++++++++++----------
> > 3 files changed, 81 insertions(+), 29 deletions(-)
> >
> > diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
> > index 3a4293dc7229..d87d3bcc758d 100644
> > --- a/arch/riscv/include/asm/elf.h
> > +++ b/arch/riscv/include/asm/elf.h
> > @@ -134,5 +134,10 @@ do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
> > typedef compat_ulong_t compat_elf_greg_t;
> > typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG];
> >
> > +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> > + int uses_interp);
> > +#define compat_arch_setup_additional_pages \
> > + compat_arch_setup_additional_pages
> > +
> > #endif /* CONFIG_COMPAT */
> > #endif /* _ASM_RISCV_ELF_H */
> > diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> > index 0099dc116168..cedcf8ea3c76 100644
> > --- a/arch/riscv/include/asm/mmu.h
> > +++ b/arch/riscv/include/asm/mmu.h
> > @@ -16,6 +16,7 @@ typedef struct {
> > atomic_long_t id;
> > #endif
> > void *vdso;
> > + void *vdso_info;
> > #ifdef CONFIG_SMP
> > /* A local icache flush is needed before user execution can resume. */
> > cpumask_t icache_stale_mask;
> > diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
> > index a9436a65161a..deca69524799 100644
> > --- a/arch/riscv/kernel/vdso.c
> > +++ b/arch/riscv/kernel/vdso.c
> > @@ -23,6 +23,9 @@ struct vdso_data {
> > #endif
> >
> > extern char vdso_start[], vdso_end[];
> > +#ifdef CONFIG_COMPAT
> > +extern char compat_vdso_start[], compat_vdso_end[];
> > +#endif
> >
> > enum vvar_pages {
> > VVAR_DATA_PAGE_OFFSET,
> > @@ -30,6 +33,11 @@ enum vvar_pages {
> > VVAR_NR_PAGES,
> > };
> >
> > +enum rv_vdso_map {
> > + RV_VDSO_MAP_VVAR,
> > + RV_VDSO_MAP_VDSO,
> > +};
> > +
> > #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
> >
> > /*
> > @@ -52,12 +60,6 @@ struct __vdso_info {
> > struct vm_special_mapping *cm;
> > };
> >
> > -static struct __vdso_info vdso_info __ro_after_init = {
> > - .name = "vdso",
> > - .vdso_code_start = vdso_start,
> > - .vdso_code_end = vdso_end,
> > -};
> > -
> > static int vdso_mremap(const struct vm_special_mapping *sm,
> > struct vm_area_struct *new_vma)
> > {
> > @@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
> > return 0;
> > }
> >
> > -static int __init __vdso_init(void)
> > +static int __init __vdso_init(struct __vdso_info *vdso_info)
> > {
> > unsigned int i;
> > struct page **vdso_pagelist;
> > unsigned long pfn;
> >
> > - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
> > + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
> > pr_err("vDSO is not a valid ELF object!\n");
> > return -EINVAL;
> > }
> >
> > - vdso_info.vdso_pages = (
> > - vdso_info.vdso_code_end -
> > - vdso_info.vdso_code_start) >>
> > + vdso_info->vdso_pages = (
> > + vdso_info->vdso_code_end -
> > + vdso_info->vdso_code_start) >>
> > PAGE_SHIFT;
> >
> > - vdso_pagelist = kcalloc(vdso_info.vdso_pages,
> > + vdso_pagelist = kcalloc(vdso_info->vdso_pages,
> > sizeof(struct page *),
> > GFP_KERNEL);
> > if (vdso_pagelist == NULL)
> > return -ENOMEM;
> >
> > /* Grab the vDSO code pages. */
> > - pfn = sym_to_pfn(vdso_info.vdso_code_start);
> > + pfn = sym_to_pfn(vdso_info->vdso_code_start);
> >
> > - for (i = 0; i < vdso_info.vdso_pages; i++)
> > + for (i = 0; i < vdso_info->vdso_pages; i++)
> > vdso_pagelist[i] = pfn_to_page(pfn + i);
> >
> > - vdso_info.cm->pages = vdso_pagelist;
> > + vdso_info->cm->pages = vdso_pagelist;
> >
> > return 0;
> > }
> > @@ -116,13 +118,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
> > {
> > struct mm_struct *mm = task->mm;
> > struct vm_area_struct *vma;
> > + struct __vdso_info *vdso_info = mm->context.vdso_info;
>
> IIUC this is the only use for context.vdso_info? If that's the case,
> can we just switch between VDSO targets based on __is_compat_task(task)?
> That'd save an mm_struct pointer, which is always nice. It'd probably
> be worth cleaning up the arm64 port too, which zaps both mappings.
>
> >
> > mmap_read_lock(mm);
> >
> > for (vma = mm->mmap; vma; vma = vma->vm_next) {
> > unsigned long size = vma->vm_end - vma->vm_start;
> >
> > - if (vma_is_special_mapping(vma, vdso_info.dm))
> > + if (vma_is_special_mapping(vma, vdso_info->dm))
> > zap_page_range(vma, vma->vm_start, size);
> > }
> >
> > @@ -187,11 +190,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
> > return vmf_insert_pfn(vma, vmf->address, pfn);
> > }
> >
> > -enum rv_vdso_map {
> > - RV_VDSO_MAP_VVAR,
> > - RV_VDSO_MAP_VDSO,
> > -};
> > -
> > static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> > [RV_VDSO_MAP_VVAR] = {
> > .name = "[vvar]",
> > @@ -203,25 +201,53 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> > },
> > };
> >
> > +static struct __vdso_info vdso_info __ro_after_init = {
> > + .name = "vdso",
> > + .vdso_code_start = vdso_start,
> > + .vdso_code_end = vdso_end,
> > + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> > + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> > +};
> > +
> > +#ifdef CONFIG_COMPAT
> > +static struct __vdso_info compat_vdso_info __ro_after_init = {
> > + .name = "compat_vdso",
> > + .vdso_code_start = compat_vdso_start,
> > + .vdso_code_end = compat_vdso_end,
> > + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> > + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> > +};
> > +#endif
> > +
> > static int __init vdso_init(void)
> > {
> > - vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR];
> > - vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO];
> > + int ret;
> > +
> > + ret = __vdso_init(&vdso_info);
> > + if (ret)
> > + goto out;
> >
> > - return __vdso_init();
> > +#ifdef CONFIG_COMPAT
> > + ret = __vdso_init(&compat_vdso_info);
> > + if (ret)
> > + goto out;
>
> It's a bit pedantic (we're just going to crash anyway), but this is
> mising the cleanup for the first __vdso_init().
I would use panic in __vdso_init:
static void __init __vdso_init(struct __vdso_info *vdso_info)
{
...
if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
- pr_err("vDSO is not a valid ELF object!\n");
- return -EINVAL;
+ panic("vDSO is not a valid ELF object!\n");
}
>
> > +#endif
> > +out:
> > + return ret;
> > }
> > arch_initcall(vdso_init);
> >
> > static int __setup_additional_pages(struct mm_struct *mm,
> > struct linux_binprm *bprm,
> > - int uses_interp)
> > + int uses_interp,
> > + struct __vdso_info *vdso_info)
> > {
> > unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
> > void *ret;
> >
> > BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
> >
> > - vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT;
> > + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
> > /* Be sure to map the data page */
> > vdso_mapping_len = vdso_text_len + VVAR_SIZE;
> >
> > @@ -232,16 +258,18 @@ static int __setup_additional_pages(struct mm_struct *mm,
> > }
> >
> > ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
> > - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm);
> > + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm);
> > if (IS_ERR(ret))
> > goto up_fail;
> >
> > vdso_base += VVAR_SIZE;
> > mm->context.vdso = (void *)vdso_base;
> > + mm->context.vdso_info = (void *)vdso_info;
> > +
> > ret =
> > _install_special_mapping(mm, vdso_base, vdso_text_len,
> > (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
> > - vdso_info.cm);
> > + vdso_info->cm);
> >
> > if (IS_ERR(ret))
> > goto up_fail;
> > @@ -253,6 +281,24 @@ static int __setup_additional_pages(struct mm_struct *mm,
> > return PTR_ERR(ret);
> > }
> >
> > +#ifdef CONFIG_COMPAT
> > +int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> > + int uses_interp)
> > +{
> > + struct mm_struct *mm = current->mm;
> > + int ret;
> > +
> > + if (mmap_write_lock_killable(mm))
> > + return -EINTR;
> > +
> > + ret = __setup_additional_pages(mm, bprm, uses_interp,
> > + &compat_vdso_info);
> > + mmap_write_unlock(mm);
> > +
> > + return ret;
> > +}
> > +#endif
> > +
> > int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> > {
> > struct mm_struct *mm = current->mm;
> > @@ -261,7 +307,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> > if (mmap_write_lock_killable(mm))
> > return -EINTR;
> >
> > - ret = __setup_additional_pages(mm, bprm, uses_interp);
> > + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info);
> > mmap_write_unlock(mm);
> >
> > return ret;
>
> Reviewed-by: Palmer Dabbelt <[email protected]>
>
> As I don't think either of these are big enough of a deal to keep from merging
> this.
--
Best Regards
Guo Ren
ML: https://lore.kernel.org/linux-csky/
On Wed, Feb 23, 2022 at 8:19 PM Rolf Eike Beer <[email protected]> wrote:
>
> > @@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping
> > *sm, return 0;
> > }
> >
> > -static int __init __vdso_init(void)
> > +static int __init __vdso_init(struct __vdso_info *vdso_info)
> > {
> > unsigned int i;
> > struct page **vdso_pagelist;
> > unsigned long pfn;
> >
> > - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
> > + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
> > pr_err("vDSO is not a valid ELF object!\n");
> > return -EINVAL;
> > }
> >
>
> Does anyone actually guarantee that this is at least this 4 bytes long?
You can ref:
arch/arm64/kernel/vdso.c
arch/arm/kernel/vdso.c
arch/nds32/kernel/vdso.c
and in arch/powerpc/boot/elf.h:
arch/powerpc/kernel/fadump.c: memcpy(elf->e_ident, ELFMAG, SELFMAG);
arch/powerpc/boot/elf.h:#define ELFMAG0 0x7f /* EI_MAG */
arch/powerpc/boot/elf.h:#define ELFMAG1 'E'
arch/powerpc/boot/elf.h:#define ELFMAG2 'L'
arch/powerpc/boot/elf.h:#define ELFMAG3 'F'
arch/powerpc/boot/elf.h:#define ELFMAG "\177ELF"
arch/powerpc/boot/elf.h:#define SELFMAG 4
>
> Eike
> --
> Rolf Eike Beer, emlix GmbH, https://www.emlix.com
> Fon +49 551 30664-0, Fax +49 551 30664-11
> Gothaer Platz 3, 37083 Göttingen, Germany
> Sitz der Gesellschaft: Göttingen, Amtsgericht Göttingen HR B 3160
> Geschäftsführung: Heike Jordan, Dr. Uwe Kracke – Ust-IdNr.: DE 205 198 055
>
> emlix - smart embedded open source
--
Best Regards
Guo Ren
ML: https://lore.kernel.org/linux-csky/
> @@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping
> *sm, return 0;
> }
>
> -static int __init __vdso_init(void)
> +static int __init __vdso_init(struct __vdso_info *vdso_info)
> {
> unsigned int i;
> struct page **vdso_pagelist;
> unsigned long pfn;
>
> - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
> + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
> pr_err("vDSO is not a valid ELF object!\n");
> return -EINVAL;
> }
>
Does anyone actually guarantee that this is at least this 4 bytes long?
Eike
--
Rolf Eike Beer, emlix GmbH, https://www.emlix.com
Fon +49 551 30664-0, Fax +49 551 30664-11
Gothaer Platz 3, 37083 Göttingen, Germany
Sitz der Gesellschaft: Göttingen, Amtsgericht Göttingen HR B 3160
Geschäftsführung: Heike Jordan, Dr. Uwe Kracke – Ust-IdNr.: DE 205 198 055
emlix - smart embedded open source
On Wed, Feb 23, 2022 at 9:42 AM Palmer Dabbelt <[email protected]> wrote:
>
> On Tue, 01 Feb 2022 07:05:41 PST (-0800), [email protected] wrote:
> > From: Guo Ren <[email protected]>
> >
> > Reconstruct __setup_additional_pages() by appending vdso info
> > pointer argument to meet compat_vdso_info requirement. And change
> > vm_special_mapping *dm, *cm initialization into static.
> >
> > Signed-off-by: Guo Ren <[email protected]>
> > Signed-off-by: Guo Ren <[email protected]>
> > Cc: Arnd Bergmann <[email protected]>
> > Cc: Palmer Dabbelt <[email protected]>
> > ---
> > arch/riscv/include/asm/elf.h | 5 ++
> > arch/riscv/include/asm/mmu.h | 1 +
> > arch/riscv/kernel/vdso.c | 104 +++++++++++++++++++++++++----------
> > 3 files changed, 81 insertions(+), 29 deletions(-)
> >
> > diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
> > index 3a4293dc7229..d87d3bcc758d 100644
> > --- a/arch/riscv/include/asm/elf.h
> > +++ b/arch/riscv/include/asm/elf.h
> > @@ -134,5 +134,10 @@ do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
> > typedef compat_ulong_t compat_elf_greg_t;
> > typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG];
> >
> > +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> > + int uses_interp);
> > +#define compat_arch_setup_additional_pages \
> > + compat_arch_setup_additional_pages
> > +
> > #endif /* CONFIG_COMPAT */
> > #endif /* _ASM_RISCV_ELF_H */
> > diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> > index 0099dc116168..cedcf8ea3c76 100644
> > --- a/arch/riscv/include/asm/mmu.h
> > +++ b/arch/riscv/include/asm/mmu.h
> > @@ -16,6 +16,7 @@ typedef struct {
> > atomic_long_t id;
> > #endif
> > void *vdso;
> > + void *vdso_info;
> > #ifdef CONFIG_SMP
> > /* A local icache flush is needed before user execution can resume. */
> > cpumask_t icache_stale_mask;
> > diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
> > index a9436a65161a..deca69524799 100644
> > --- a/arch/riscv/kernel/vdso.c
> > +++ b/arch/riscv/kernel/vdso.c
> > @@ -23,6 +23,9 @@ struct vdso_data {
> > #endif
> >
> > extern char vdso_start[], vdso_end[];
> > +#ifdef CONFIG_COMPAT
> > +extern char compat_vdso_start[], compat_vdso_end[];
> > +#endif
> >
> > enum vvar_pages {
> > VVAR_DATA_PAGE_OFFSET,
> > @@ -30,6 +33,11 @@ enum vvar_pages {
> > VVAR_NR_PAGES,
> > };
> >
> > +enum rv_vdso_map {
> > + RV_VDSO_MAP_VVAR,
> > + RV_VDSO_MAP_VDSO,
> > +};
> > +
> > #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
> >
> > /*
> > @@ -52,12 +60,6 @@ struct __vdso_info {
> > struct vm_special_mapping *cm;
> > };
> >
> > -static struct __vdso_info vdso_info __ro_after_init = {
> > - .name = "vdso",
> > - .vdso_code_start = vdso_start,
> > - .vdso_code_end = vdso_end,
> > -};
> > -
> > static int vdso_mremap(const struct vm_special_mapping *sm,
> > struct vm_area_struct *new_vma)
> > {
> > @@ -66,35 +68,35 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
> > return 0;
> > }
> >
> > -static int __init __vdso_init(void)
> > +static int __init __vdso_init(struct __vdso_info *vdso_info)
> > {
> > unsigned int i;
> > struct page **vdso_pagelist;
> > unsigned long pfn;
> >
> > - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
> > + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) {
> > pr_err("vDSO is not a valid ELF object!\n");
> > return -EINVAL;
> > }
> >
> > - vdso_info.vdso_pages = (
> > - vdso_info.vdso_code_end -
> > - vdso_info.vdso_code_start) >>
> > + vdso_info->vdso_pages = (
> > + vdso_info->vdso_code_end -
> > + vdso_info->vdso_code_start) >>
> > PAGE_SHIFT;
> >
> > - vdso_pagelist = kcalloc(vdso_info.vdso_pages,
> > + vdso_pagelist = kcalloc(vdso_info->vdso_pages,
> > sizeof(struct page *),
> > GFP_KERNEL);
> > if (vdso_pagelist == NULL)
> > return -ENOMEM;
> >
> > /* Grab the vDSO code pages. */
> > - pfn = sym_to_pfn(vdso_info.vdso_code_start);
> > + pfn = sym_to_pfn(vdso_info->vdso_code_start);
> >
> > - for (i = 0; i < vdso_info.vdso_pages; i++)
> > + for (i = 0; i < vdso_info->vdso_pages; i++)
> > vdso_pagelist[i] = pfn_to_page(pfn + i);
> >
> > - vdso_info.cm->pages = vdso_pagelist;
> > + vdso_info->cm->pages = vdso_pagelist;
> >
> > return 0;
> > }
> > @@ -116,13 +118,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
> > {
> > struct mm_struct *mm = task->mm;
> > struct vm_area_struct *vma;
> > + struct __vdso_info *vdso_info = mm->context.vdso_info;
>
> IIUC this is the only use for context.vdso_info? If that's the case,
> can we just switch between VDSO targets based on __is_compat_task(task)?
> That'd save an mm_struct pointer, which is always nice. It'd probably
> be worth cleaning up the arm64 port too, which zaps both mappings.
Do you want rv32 to support HAVE_GENERIC_VDSO_NS in the future?
>
> >
> > mmap_read_lock(mm);
> >
> > for (vma = mm->mmap; vma; vma = vma->vm_next) {
> > unsigned long size = vma->vm_end - vma->vm_start;
> >
> > - if (vma_is_special_mapping(vma, vdso_info.dm))
> > + if (vma_is_special_mapping(vma, vdso_info->dm))
> > zap_page_range(vma, vma->vm_start, size);
> > }
> >
> > @@ -187,11 +190,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
> > return vmf_insert_pfn(vma, vmf->address, pfn);
> > }
> >
> > -enum rv_vdso_map {
> > - RV_VDSO_MAP_VVAR,
> > - RV_VDSO_MAP_VDSO,
> > -};
> > -
> > static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> > [RV_VDSO_MAP_VVAR] = {
> > .name = "[vvar]",
> > @@ -203,25 +201,53 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
> > },
> > };
> >
> > +static struct __vdso_info vdso_info __ro_after_init = {
> > + .name = "vdso",
> > + .vdso_code_start = vdso_start,
> > + .vdso_code_end = vdso_end,
> > + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> > + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> > +};
> > +
> > +#ifdef CONFIG_COMPAT
> > +static struct __vdso_info compat_vdso_info __ro_after_init = {
> > + .name = "compat_vdso",
> > + .vdso_code_start = compat_vdso_start,
> > + .vdso_code_end = compat_vdso_end,
> > + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR],
> > + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO],
> > +};
> > +#endif
> > +
> > static int __init vdso_init(void)
> > {
> > - vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR];
> > - vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO];
> > + int ret;
> > +
> > + ret = __vdso_init(&vdso_info);
> > + if (ret)
> > + goto out;
> >
> > - return __vdso_init();
> > +#ifdef CONFIG_COMPAT
> > + ret = __vdso_init(&compat_vdso_info);
> > + if (ret)
> > + goto out;
>
> It's a bit pedantic (we're just going to crash anyway), but this is
> mising the cleanup for the first __vdso_init().
>
> > +#endif
> > +out:
> > + return ret;
> > }
> > arch_initcall(vdso_init);
> >
> > static int __setup_additional_pages(struct mm_struct *mm,
> > struct linux_binprm *bprm,
> > - int uses_interp)
> > + int uses_interp,
> > + struct __vdso_info *vdso_info)
> > {
> > unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
> > void *ret;
> >
> > BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
> >
> > - vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT;
> > + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
> > /* Be sure to map the data page */
> > vdso_mapping_len = vdso_text_len + VVAR_SIZE;
> >
> > @@ -232,16 +258,18 @@ static int __setup_additional_pages(struct mm_struct *mm,
> > }
> >
> > ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
> > - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm);
> > + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm);
> > if (IS_ERR(ret))
> > goto up_fail;
> >
> > vdso_base += VVAR_SIZE;
> > mm->context.vdso = (void *)vdso_base;
> > + mm->context.vdso_info = (void *)vdso_info;
> > +
> > ret =
> > _install_special_mapping(mm, vdso_base, vdso_text_len,
> > (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
> > - vdso_info.cm);
> > + vdso_info->cm);
> >
> > if (IS_ERR(ret))
> > goto up_fail;
> > @@ -253,6 +281,24 @@ static int __setup_additional_pages(struct mm_struct *mm,
> > return PTR_ERR(ret);
> > }
> >
> > +#ifdef CONFIG_COMPAT
> > +int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
> > + int uses_interp)
> > +{
> > + struct mm_struct *mm = current->mm;
> > + int ret;
> > +
> > + if (mmap_write_lock_killable(mm))
> > + return -EINTR;
> > +
> > + ret = __setup_additional_pages(mm, bprm, uses_interp,
> > + &compat_vdso_info);
> > + mmap_write_unlock(mm);
> > +
> > + return ret;
> > +}
> > +#endif
> > +
> > int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> > {
> > struct mm_struct *mm = current->mm;
> > @@ -261,7 +307,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
> > if (mmap_write_lock_killable(mm))
> > return -EINTR;
> >
> > - ret = __setup_additional_pages(mm, bprm, uses_interp);
> > + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info);
> > mmap_write_unlock(mm);
> >
> > return ret;
>
> Reviewed-by: Palmer Dabbelt <[email protected]>
>
> As I don't think either of these are big enough of a deal to keep from merging
> this.
--
Best Regards
Guo Ren
ML: https://lore.kernel.org/linux-csky/