[v6,08/10] x86: avoid W^X being broken during modules loading
diff mbox series

Message ID 20181120203545.34928-9-namit@vmware.com
State New
Headers show
Series
  • x86/alternative: text_poke() fixes
Related show

Commit Message

Nadav Amit Nov. 20, 2018, 8:35 p.m. UTC
When modules and BPF filters are loaded, there is a time window in
which some memory is both writable and executable. An attacker that has
already found another vulnerability (e.g., a dangling pointer) might be
able to exploit this behavior to overwrite kernel code. This patch
prevents having writable executable PTEs in this stage.

In addition, avoiding having R+X mappings can also slightly simplify the
patching of modules code on initialization (e.g., by alternatives and
static-key), as would be done in the next patch.

To avoid having W+X mappings, set them initially as RW (NX) and after
they are set as RO set them as X as well. Setting them as executable is
done as a separate step to avoid one core in which the old PTE is cached
(hence writable), and another which sees the updated PTE (executable),
which would break the W^X protection.

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++-------
 arch/x86/kernel/module.c      |  2 +-
 include/linux/filter.h        |  6 ++++++
 kernel/module.c               | 10 ++++++++++
 4 files changed, 38 insertions(+), 8 deletions(-)

Comments

Nadav Amit Nov. 28, 2018, 6:59 p.m. UTC | #1
> On Nov 20, 2018, at 12:35 PM, Nadav Amit <namit@vmware.com> wrote:
> 
> When modules and BPF filters are loaded, there is a time window in
> which some memory is both writable and executable. An attacker that has
> already found another vulnerability (e.g., a dangling pointer) might be
> able to exploit this behavior to overwrite kernel code. This patch
> prevents having writable executable PTEs in this stage.
> 
> In addition, avoiding having R+X mappings can also slightly simplify the
> patching of modules code on initialization (e.g., by alternatives and
> static-key), as would be done in the next patch.
> 
> To avoid having W+X mappings, set them initially as RW (NX) and after
> they are set as RO set them as X as well. Setting them as executable is
> done as a separate step to avoid one core in which the old PTE is cached
> (hence writable), and another which sees the updated PTE (executable),
> which would break the W^X protection.
> 
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: Kees Cook <keescook@chromium.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Dave Hansen <dave.hansen@intel.com>
> Cc: Masami Hiramatsu <mhiramat@kernel.org>
> Suggested-by: Thomas Gleixner <tglx@linutronix.de>
> Suggested-by: Andy Lutomirski <luto@amacapital.net>
> Signed-off-by: Nadav Amit <namit@vmware.com>
> ---
> arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++-------
> arch/x86/kernel/module.c      |  2 +-
> include/linux/filter.h        |  6 ++++++
> kernel/module.c               | 10 ++++++++++
> 4 files changed, 38 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
> index 8fc4685f3117..18415e3b6000 100644
> --- a/arch/x86/kernel/alternative.c
> +++ b/arch/x86/kernel/alternative.c
> @@ -667,15 +667,29 @@ void __init alternative_instructions(void)
>  * handlers seeing an inconsistent instruction while you patch.
>  */
> void *__init_or_module text_poke_early(void *addr, const void *opcode,
> -					      size_t len)
> +				       size_t len)
> {
> 	unsigned long flags;
> -	local_irq_save(flags);
> -	memcpy(addr, opcode, len);
> -	local_irq_restore(flags);
> -	sync_core();
> -	/* Could also do a CLFLUSH here to speed up CPU recovery; but
> -	   that causes hangs on some VIA CPUs. */
> +
> +	if (static_cpu_has(X86_FEATURE_NX) &&
> +	    is_module_text_address((unsigned long)addr)) {
> +		/*
> +		 * Modules text is marked initially as non-executable, so the
> +		 * code cannot be running and speculative code-fetches are
> +		 * prevented. We can just change the code.
> +		 */
> +		memcpy(addr, opcode, len);
> +	} else {
> +		local_irq_save(flags);
> +		memcpy(addr, opcode, len);
> +		local_irq_restore(flags);
> +		sync_core();
> +
> +		/*
> +		 * Could also do a CLFLUSH here to speed up CPU recovery; but
> +		 * that causes hangs on some VIA CPUs.
> +		 */
> +	}
> 	return addr;
> }
> 
> diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
> index b052e883dd8c..cfa3106faee4 100644
> --- a/arch/x86/kernel/module.c
> +++ b/arch/x86/kernel/module.c
> @@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
> 	p = __vmalloc_node_range(size, MODULE_ALIGN,
> 				    MODULES_VADDR + get_module_load_offset(),
> 				    MODULES_END, GFP_KERNEL,
> -				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
> +				    PAGE_KERNEL, 0, NUMA_NO_NODE,
> 				    __builtin_return_address(0));
> 	if (p && (kasan_module_alloc(p, size) < 0)) {
> 		vfree(p);
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index de629b706d1d..ee9ae03c5f56 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -704,7 +704,13 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
> 
> static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
> {
> +	/*
> +	 * Perform mapping changes in two stages to avoid opening a time-window
> +	 * in which a PTE is cached in any TLB as writable, but marked as
> +	 * executable in the memory-resident mappings (e.g., page-tables).
> +	 */
> 	set_memory_ro((unsigned long)hdr, hdr->pages);
> +	set_memory_x((unsigned long)hdr, hdr->pages);
> }
> 
> static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
> diff --git a/kernel/module.c b/kernel/module.c
> index 49a405891587..7cb207249437 100644
> --- a/kernel/module.c
> +++ b/kernel/module.c
> @@ -1946,9 +1946,19 @@ void module_enable_ro(const struct module *mod, bool after_init)
> 	if (!rodata_enabled)
> 		return;
> 
> +	/*
> +	 * Perform mapping changes in two stages to avoid opening a time-window
> +	 * in which a PTE is cached in any TLB as writable, but marked as
> +	 * executable in the memory-resident mappings (e.g., page-tables).
> +	 */
> 	frob_text(&mod->core_layout, set_memory_ro);
> +	frob_text(&mod->core_layout, set_memory_x);
> +
> 	frob_rodata(&mod->core_layout, set_memory_ro);
> +
> 	frob_text(&mod->init_layout, set_memory_ro);
> +	frob_text(&mod->init_layout, set_memory_x);
> +
> 	frob_rodata(&mod->init_layout, set_memory_ro);
> 
> 	if (after_init)
> -- 
> 2.17.1

Rick pointed out that I screwed up ftrace and kprobes.

For kprobes, I think I need to add set_memory_x() to alloc_insn_page() and
change arch_ftrace_update_trampoline().

For arch_ftrace_update_trampoline(), I think I should remove not use
set_memory_rw() when patching in __probe_kernel_write() should be done
through text_poke().

I’ll give it another look and send another version later.

Regards,
Nadav
Masami Hiramatsu Nov. 30, 2018, 2:32 a.m. UTC | #2
On Wed, 28 Nov 2018 18:59:30 +0000
Nadav Amit <namit@vmware.com> wrote:

> > On Nov 20, 2018, at 12:35 PM, Nadav Amit <namit@vmware.com> wrote:
> > 
> > When modules and BPF filters are loaded, there is a time window in
> > which some memory is both writable and executable. An attacker that has
> > already found another vulnerability (e.g., a dangling pointer) might be
> > able to exploit this behavior to overwrite kernel code. This patch
> > prevents having writable executable PTEs in this stage.
> > 
> > In addition, avoiding having R+X mappings can also slightly simplify the
> > patching of modules code on initialization (e.g., by alternatives and
> > static-key), as would be done in the next patch.
> > 
> > To avoid having W+X mappings, set them initially as RW (NX) and after
> > they are set as RO set them as X as well. Setting them as executable is
> > done as a separate step to avoid one core in which the old PTE is cached
> > (hence writable), and another which sees the updated PTE (executable),
> > which would break the W^X protection.
> > 
> > Cc: Andy Lutomirski <luto@kernel.org>
> > Cc: Kees Cook <keescook@chromium.org>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Dave Hansen <dave.hansen@intel.com>
> > Cc: Masami Hiramatsu <mhiramat@kernel.org>
> > Suggested-by: Thomas Gleixner <tglx@linutronix.de>
> > Suggested-by: Andy Lutomirski <luto@amacapital.net>
> > Signed-off-by: Nadav Amit <namit@vmware.com>
> > ---
> > arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++-------
> > arch/x86/kernel/module.c      |  2 +-
> > include/linux/filter.h        |  6 ++++++
> > kernel/module.c               | 10 ++++++++++
> > 4 files changed, 38 insertions(+), 8 deletions(-)
> > 
> > diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
> > index 8fc4685f3117..18415e3b6000 100644
> > --- a/arch/x86/kernel/alternative.c
> > +++ b/arch/x86/kernel/alternative.c
> > @@ -667,15 +667,29 @@ void __init alternative_instructions(void)
> >  * handlers seeing an inconsistent instruction while you patch.
> >  */
> > void *__init_or_module text_poke_early(void *addr, const void *opcode,
> > -					      size_t len)
> > +				       size_t len)
> > {
> > 	unsigned long flags;
> > -	local_irq_save(flags);
> > -	memcpy(addr, opcode, len);
> > -	local_irq_restore(flags);
> > -	sync_core();
> > -	/* Could also do a CLFLUSH here to speed up CPU recovery; but
> > -	   that causes hangs on some VIA CPUs. */
> > +
> > +	if (static_cpu_has(X86_FEATURE_NX) &&
> > +	    is_module_text_address((unsigned long)addr)) {
> > +		/*
> > +		 * Modules text is marked initially as non-executable, so the
> > +		 * code cannot be running and speculative code-fetches are
> > +		 * prevented. We can just change the code.
> > +		 */
> > +		memcpy(addr, opcode, len);
> > +	} else {
> > +		local_irq_save(flags);
> > +		memcpy(addr, opcode, len);
> > +		local_irq_restore(flags);
> > +		sync_core();
> > +
> > +		/*
> > +		 * Could also do a CLFLUSH here to speed up CPU recovery; but
> > +		 * that causes hangs on some VIA CPUs.
> > +		 */
> > +	}
> > 	return addr;
> > }
> > 
> > diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
> > index b052e883dd8c..cfa3106faee4 100644
> > --- a/arch/x86/kernel/module.c
> > +++ b/arch/x86/kernel/module.c
> > @@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
> > 	p = __vmalloc_node_range(size, MODULE_ALIGN,
> > 				    MODULES_VADDR + get_module_load_offset(),
> > 				    MODULES_END, GFP_KERNEL,
> > -				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
> > +				    PAGE_KERNEL, 0, NUMA_NO_NODE,
> > 				    __builtin_return_address(0));
> > 	if (p && (kasan_module_alloc(p, size) < 0)) {
> > 		vfree(p);
> > diff --git a/include/linux/filter.h b/include/linux/filter.h
> > index de629b706d1d..ee9ae03c5f56 100644
> > --- a/include/linux/filter.h
> > +++ b/include/linux/filter.h
> > @@ -704,7 +704,13 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
> > 
> > static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
> > {
> > +	/*
> > +	 * Perform mapping changes in two stages to avoid opening a time-window
> > +	 * in which a PTE is cached in any TLB as writable, but marked as
> > +	 * executable in the memory-resident mappings (e.g., page-tables).
> > +	 */
> > 	set_memory_ro((unsigned long)hdr, hdr->pages);
> > +	set_memory_x((unsigned long)hdr, hdr->pages);
> > }
> > 
> > static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
> > diff --git a/kernel/module.c b/kernel/module.c
> > index 49a405891587..7cb207249437 100644
> > --- a/kernel/module.c
> > +++ b/kernel/module.c
> > @@ -1946,9 +1946,19 @@ void module_enable_ro(const struct module *mod, bool after_init)
> > 	if (!rodata_enabled)
> > 		return;
> > 
> > +	/*
> > +	 * Perform mapping changes in two stages to avoid opening a time-window
> > +	 * in which a PTE is cached in any TLB as writable, but marked as
> > +	 * executable in the memory-resident mappings (e.g., page-tables).
> > +	 */
> > 	frob_text(&mod->core_layout, set_memory_ro);
> > +	frob_text(&mod->core_layout, set_memory_x);
> > +
> > 	frob_rodata(&mod->core_layout, set_memory_ro);
> > +
> > 	frob_text(&mod->init_layout, set_memory_ro);
> > +	frob_text(&mod->init_layout, set_memory_x);
> > +
> > 	frob_rodata(&mod->init_layout, set_memory_ro);
> > 
> > 	if (after_init)
> > -- 
> > 2.17.1
> 
> Rick pointed out that I screwed up ftrace and kprobes.
> 
> For kprobes, I think I need to add set_memory_x() to alloc_insn_page() and
> change arch_ftrace_update_trampoline().

Oops, right. It should be easy to fix for kprobe :) what you need is below.

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index c33b06f..51818f3 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -431,8 +431,10 @@ void *alloc_insn_page(void)
        void *page;
 
        page = module_alloc(PAGE_SIZE);
-       if (page)
+       if (page) {
                set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+               set_memory_x((unsigned long)page & PAGE_MASK, 1);
+       }
 
        return page;
 }


> 
> For arch_ftrace_update_trampoline(), I think I should remove not use
> set_memory_rw() when patching in __probe_kernel_write() should be done
> through text_poke().

right.

> 
> I’ll give it another look and send another version later.

Thank you,

> 
> Regards,
> Nadav
> 
>

Patch
diff mbox series

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8fc4685f3117..18415e3b6000 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -667,15 +667,29 @@  void __init alternative_instructions(void)
  * handlers seeing an inconsistent instruction while you patch.
  */
 void *__init_or_module text_poke_early(void *addr, const void *opcode,
-					      size_t len)
+				       size_t len)
 {
 	unsigned long flags;
-	local_irq_save(flags);
-	memcpy(addr, opcode, len);
-	local_irq_restore(flags);
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
+
+	if (static_cpu_has(X86_FEATURE_NX) &&
+	    is_module_text_address((unsigned long)addr)) {
+		/*
+		 * Modules text is marked initially as non-executable, so the
+		 * code cannot be running and speculative code-fetches are
+		 * prevented. We can just change the code.
+		 */
+		memcpy(addr, opcode, len);
+	} else {
+		local_irq_save(flags);
+		memcpy(addr, opcode, len);
+		local_irq_restore(flags);
+		sync_core();
+
+		/*
+		 * Could also do a CLFLUSH here to speed up CPU recovery; but
+		 * that causes hangs on some VIA CPUs.
+		 */
+	}
 	return addr;
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b052e883dd8c..cfa3106faee4 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -87,7 +87,7 @@  void *module_alloc(unsigned long size)
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 	if (p && (kasan_module_alloc(p, size) < 0)) {
 		vfree(p);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index de629b706d1d..ee9ae03c5f56 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -704,7 +704,13 @@  static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
+	/*
+	 * Perform mapping changes in two stages to avoid opening a time-window
+	 * in which a PTE is cached in any TLB as writable, but marked as
+	 * executable in the memory-resident mappings (e.g., page-tables).
+	 */
 	set_memory_ro((unsigned long)hdr, hdr->pages);
+	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
diff --git a/kernel/module.c b/kernel/module.c
index 49a405891587..7cb207249437 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1946,9 +1946,19 @@  void module_enable_ro(const struct module *mod, bool after_init)
 	if (!rodata_enabled)
 		return;
 
+	/*
+	 * Perform mapping changes in two stages to avoid opening a time-window
+	 * in which a PTE is cached in any TLB as writable, but marked as
+	 * executable in the memory-resident mappings (e.g., page-tables).
+	 */
 	frob_text(&mod->core_layout, set_memory_ro);
+	frob_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)