diff mbox series

[v16,05/16] arm64: untag user pointers passed to memory syscalls

Message ID 045a94326401693e015bf80c444a4d946a5c68ed.1559580831.git.andreyknvl@google.com (mailing list archive)
State New
Headers show
Series arm64: untag user pointers passed to the kernel | expand

Commit Message

Andrey Konovalov June 3, 2019, 4:55 p.m. UTC
This patch is a part of a series that extends arm64 kernel ABI to allow to
pass tagged user pointers (with the top byte set to something else other
than 0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
mremap, msync, munlock.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
---
 mm/madvise.c   | 2 ++
 mm/mempolicy.c | 3 +++
 mm/mincore.c   | 2 ++
 mm/mlock.c     | 4 ++++
 mm/mprotect.c  | 2 ++
 mm/mremap.c    | 2 ++
 mm/msync.c     | 2 ++
 7 files changed, 17 insertions(+)

Comments

Kees Cook June 8, 2019, 3:51 a.m. UTC | #1
On Mon, Jun 03, 2019 at 06:55:07PM +0200, Andrey Konovalov wrote:
> This patch is a part of a series that extends arm64 kernel ABI to allow to
> pass tagged user pointers (with the top byte set to something else other
> than 0x00) as syscall arguments.
> 
> This patch allows tagged pointers to be passed to the following memory
> syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
> mremap, msync, munlock.
> 
> Signed-off-by: Andrey Konovalov <andreyknvl@google.com>

Reviewed-by: Kees Cook <keescook@chromium.org>

-Kees

> ---
>  mm/madvise.c   | 2 ++
>  mm/mempolicy.c | 3 +++
>  mm/mincore.c   | 2 ++
>  mm/mlock.c     | 4 ++++
>  mm/mprotect.c  | 2 ++
>  mm/mremap.c    | 2 ++
>  mm/msync.c     | 2 ++
>  7 files changed, 17 insertions(+)
> 
> diff --git a/mm/madvise.c b/mm/madvise.c
> index 628022e674a7..39b82f8a698f 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -810,6 +810,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
>  	size_t len;
>  	struct blk_plug plug;
>  
> +	start = untagged_addr(start);
> +
>  	if (!madvise_behavior_valid(behavior))
>  		return error;
>  
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 01600d80ae01..78e0a88b2680 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1360,6 +1360,7 @@ static long kernel_mbind(unsigned long start, unsigned long len,
>  	int err;
>  	unsigned short mode_flags;
>  
> +	start = untagged_addr(start);
>  	mode_flags = mode & MPOL_MODE_FLAGS;
>  	mode &= ~MPOL_MODE_FLAGS;
>  	if (mode >= MPOL_MAX)
> @@ -1517,6 +1518,8 @@ static int kernel_get_mempolicy(int __user *policy,
>  	int uninitialized_var(pval);
>  	nodemask_t nodes;
>  
> +	addr = untagged_addr(addr);
> +
>  	if (nmask != NULL && maxnode < nr_node_ids)
>  		return -EINVAL;
>  
> diff --git a/mm/mincore.c b/mm/mincore.c
> index c3f058bd0faf..64c322ed845c 100644
> --- a/mm/mincore.c
> +++ b/mm/mincore.c
> @@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
>  	unsigned long pages;
>  	unsigned char *tmp;
>  
> +	start = untagged_addr(start);
> +
>  	/* Check the start address: needs to be page-aligned.. */
>  	if (start & ~PAGE_MASK)
>  		return -EINVAL;
> diff --git a/mm/mlock.c b/mm/mlock.c
> index 080f3b36415b..e82609eaa428 100644
> --- a/mm/mlock.c
> +++ b/mm/mlock.c
> @@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
>  	unsigned long lock_limit;
>  	int error = -ENOMEM;
>  
> +	start = untagged_addr(start);
> +
>  	if (!can_do_mlock())
>  		return -EPERM;
>  
> @@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
>  {
>  	int ret;
>  
> +	start = untagged_addr(start);
> +
>  	len = PAGE_ALIGN(len + (offset_in_page(start)));
>  	start &= PAGE_MASK;
>  
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index bf38dfbbb4b4..19f981b733bc 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -465,6 +465,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
>  	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
>  				(prot & PROT_READ);
>  
> +	start = untagged_addr(start);
> +
>  	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
>  	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
>  		return -EINVAL;
> diff --git a/mm/mremap.c b/mm/mremap.c
> index fc241d23cd97..1d98281f7204 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -606,6 +606,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
>  	LIST_HEAD(uf_unmap_early);
>  	LIST_HEAD(uf_unmap);
>  
> +	addr = untagged_addr(addr);
> +
>  	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
>  		return ret;
>  
> diff --git a/mm/msync.c b/mm/msync.c
> index ef30a429623a..c3bd3e75f687 100644
> --- a/mm/msync.c
> +++ b/mm/msync.c
> @@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
>  	int unmapped_error = 0;
>  	int error = -EINVAL;
>  
> +	start = untagged_addr(start);
> +
>  	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
>  		goto out;
>  	if (offset_in_page(start))
> -- 
> 2.22.0.rc1.311.g5d7573a151-goog
>
Catalin Marinas June 10, 2019, 2:28 p.m. UTC | #2
On Mon, Jun 03, 2019 at 06:55:07PM +0200, Andrey Konovalov wrote:
> This patch is a part of a series that extends arm64 kernel ABI to allow to
> pass tagged user pointers (with the top byte set to something else other
> than 0x00) as syscall arguments.
> 
> This patch allows tagged pointers to be passed to the following memory
> syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
> mremap, msync, munlock.
> 
> Signed-off-by: Andrey Konovalov <andreyknvl@google.com>

I would add in the commit log (and possibly in the code with a comment)
that mremap() and mmap() do not currently accept tagged hint addresses.
Architectures may interpret the hint tag as a background colour for the
corresponding vma. With this:

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Andrey Konovalov June 11, 2019, 3:35 p.m. UTC | #3
On Mon, Jun 10, 2019 at 4:28 PM Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Mon, Jun 03, 2019 at 06:55:07PM +0200, Andrey Konovalov wrote:
> > This patch is a part of a series that extends arm64 kernel ABI to allow to
> > pass tagged user pointers (with the top byte set to something else other
> > than 0x00) as syscall arguments.
> >
> > This patch allows tagged pointers to be passed to the following memory
> > syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
> > mremap, msync, munlock.
> >
> > Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
>
> I would add in the commit log (and possibly in the code with a comment)
> that mremap() and mmap() do not currently accept tagged hint addresses.
> Architectures may interpret the hint tag as a background colour for the
> corresponding vma. With this:

I'll change the commit log. Where do you you think I should put this
comment? Before mmap and mremap definitions in mm/?

Thanks!

>
> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
>
> --
> Catalin
Catalin Marinas June 11, 2019, 5:44 p.m. UTC | #4
On Tue, Jun 11, 2019 at 05:35:31PM +0200, Andrey Konovalov wrote:
> On Mon, Jun 10, 2019 at 4:28 PM Catalin Marinas <catalin.marinas@arm.com> wrote:
> > On Mon, Jun 03, 2019 at 06:55:07PM +0200, Andrey Konovalov wrote:
> > > This patch is a part of a series that extends arm64 kernel ABI to allow to
> > > pass tagged user pointers (with the top byte set to something else other
> > > than 0x00) as syscall arguments.
> > >
> > > This patch allows tagged pointers to be passed to the following memory
> > > syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
> > > mremap, msync, munlock.
> > >
> > > Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
> >
> > I would add in the commit log (and possibly in the code with a comment)
> > that mremap() and mmap() do not currently accept tagged hint addresses.
> > Architectures may interpret the hint tag as a background colour for the
> > corresponding vma. With this:
> 
> I'll change the commit log. Where do you you think I should put this
> comment? Before mmap and mremap definitions in mm/?

On arm64 we use our own sys_mmap(). I'd say just add a comment on the
generic mremap() just before the untagged_addr() along the lines that
new_address is not untagged for preserving similar behaviour to mmap().
Andrey Konovalov June 12, 2019, 11:13 a.m. UTC | #5
On Tue, Jun 11, 2019 at 7:45 PM Catalin Marinas <catalin.marinas@arm.com> wrote:
>
> On Tue, Jun 11, 2019 at 05:35:31PM +0200, Andrey Konovalov wrote:
> > On Mon, Jun 10, 2019 at 4:28 PM Catalin Marinas <catalin.marinas@arm.com> wrote:
> > > On Mon, Jun 03, 2019 at 06:55:07PM +0200, Andrey Konovalov wrote:
> > > > This patch is a part of a series that extends arm64 kernel ABI to allow to
> > > > pass tagged user pointers (with the top byte set to something else other
> > > > than 0x00) as syscall arguments.
> > > >
> > > > This patch allows tagged pointers to be passed to the following memory
> > > > syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
> > > > mremap, msync, munlock.
> > > >
> > > > Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
> > >
> > > I would add in the commit log (and possibly in the code with a comment)
> > > that mremap() and mmap() do not currently accept tagged hint addresses.
> > > Architectures may interpret the hint tag as a background colour for the
> > > corresponding vma. With this:
> >
> > I'll change the commit log. Where do you you think I should put this
> > comment? Before mmap and mremap definitions in mm/?
>
> On arm64 we use our own sys_mmap(). I'd say just add a comment on the
> generic mremap() just before the untagged_addr() along the lines that
> new_address is not untagged for preserving similar behaviour to mmap().

Will do in v17, thanks!

>
> --
> Catalin
diff mbox series

Patch

diff --git a/mm/madvise.c b/mm/madvise.c
index 628022e674a7..39b82f8a698f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -810,6 +810,8 @@  SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;
 	struct blk_plug plug;
 
+	start = untagged_addr(start);
+
 	if (!madvise_behavior_valid(behavior))
 		return error;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 01600d80ae01..78e0a88b2680 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1360,6 +1360,7 @@  static long kernel_mbind(unsigned long start, unsigned long len,
 	int err;
 	unsigned short mode_flags;
 
+	start = untagged_addr(start);
 	mode_flags = mode & MPOL_MODE_FLAGS;
 	mode &= ~MPOL_MODE_FLAGS;
 	if (mode >= MPOL_MAX)
@@ -1517,6 +1518,8 @@  static int kernel_get_mempolicy(int __user *policy,
 	int uninitialized_var(pval);
 	nodemask_t nodes;
 
+	addr = untagged_addr(addr);
+
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 
diff --git a/mm/mincore.c b/mm/mincore.c
index c3f058bd0faf..64c322ed845c 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -249,6 +249,8 @@  SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 	unsigned long pages;
 	unsigned char *tmp;
 
+	start = untagged_addr(start);
+
 	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_MASK)
 		return -EINVAL;
diff --git a/mm/mlock.c b/mm/mlock.c
index 080f3b36415b..e82609eaa428 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -674,6 +674,8 @@  static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
 	unsigned long lock_limit;
 	int error = -ENOMEM;
 
+	start = untagged_addr(start);
+
 	if (!can_do_mlock())
 		return -EPERM;
 
@@ -735,6 +737,8 @@  SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
+	start = untagged_addr(start);
+
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index bf38dfbbb4b4..19f981b733bc 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -465,6 +465,8 @@  static int do_mprotect_pkey(unsigned long start, size_t len,
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
 
+	start = untagged_addr(start);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;
diff --git a/mm/mremap.c b/mm/mremap.c
index fc241d23cd97..1d98281f7204 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -606,6 +606,8 @@  SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	addr = untagged_addr(addr);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
 
diff --git a/mm/msync.c b/mm/msync.c
index ef30a429623a..c3bd3e75f687 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -37,6 +37,8 @@  SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 	int unmapped_error = 0;
 	int error = -EINVAL;
 
+	start = untagged_addr(start);
+
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (offset_in_page(start))