[PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[Michael Ellerman]

The STF (store-to-load forwarding) barrier mitigation can be
enabled/disabled at runtime via a debugfs file (stf_barrier), which
causes the kernel to patch itself to enable/disable the relevant
mitigations.

However depending on which mitigation we're using, it may not be safe to
do that patching while other CPUs are active. For example the following
crash:

  User access of kernel address (c00000003fff5af0) - exploit attempt? (uid: 0)
  segfault (11) at c00000003fff5af0 nip 7fff8ad12198 lr 7fff8ad121f8 code 1
  code: 40820128 e93c00d0 e9290058 7c292840 40810058 38600000 4bfd9a81 e8410018
  code: 2c030006 41810154 3860ffb6 e9210098 <e94d8ff0> 7d295279 39400000 40820a3c

Shows that we returned to userspace without restoring the user r13
value, due to executing the partially patched STF exit code.

Fix it by doing the patching under stop machine. The CPUs that aren't
doing the patching will be spinning in the core of the stop machine
logic. That is currently sufficient for our purposes, because none of
the patching we do is to that code or anywhere in the vicinity.

Fixes: a048a07d7f45 ("powerpc/64s: Add support for a store forwarding barrier at kernel entry/exit")
Cc: stable@vger.kernel.org # v4.17+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/lib/feature-fixups.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 1fd31b4b0e13..8f8c8c98a6ac 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/sched/mm.h>
+#include <linux/stop_machine.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
 #include <asm/page.h>
@@ -227,11 +228,25 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
 		                                           : "unknown");
 }
 
-
-void do_stf_barrier_fixups(enum stf_barrier_type types)
+static int __do_stf_barrier_fixups(void *data)
 {
+	enum stf_barrier_type types = (enum stf_barrier_type)data;
+
 	do_stf_entry_barrier_fixups(types);
 	do_stf_exit_barrier_fixups(types);
+
+	return 0;
+}
+
+void do_stf_barrier_fixups(enum stf_barrier_type types)
+{
+	/*
+	 * The call to the fallback entry flush, and the fallback/sync-ori exit
+	 * flush can not be safely patched in/out while other CPUs are executing
+	 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
+	 * spin in the stop machine core with interrupts hard disabled.
+	 */
+	stop_machine_cpuslocked(__do_stf_barrier_fixups, (void *)types, NULL);
 }
 
 void do_uaccess_flush_fixups(enum l1d_flush_type types)
-- 
2.25.1

[PATCH 2/2] powerpc/64s: Fix crashes when toggling entry flush barrier

[Michael Ellerman]

The entry flush mitigation can be enabled/disabled at runtime via a
debugfs file (entry_flush), which causes the kernel to patch itself to
enable/disable the relevant mitigations.

However depending on which mitigation we're using, it may not be safe to
do that patching while other CPUs are active. For example the following
crash:

  sleeper[15639]: segfault (11) at c000000000004c20 nip c000000000004c20 lr c000000000004c20

Shows that we returned to userspace with a corrupted LR that points into
the kernel, due to executing the partially patched call to the fallback
entry flush (ie. we missed the LR restore).

Fix it by doing the patching under stop machine. The CPUs that aren't
doing the patching will be spinning in the core of the stop machine
logic. That is currently sufficient for our purposes, because none of
the patching we do is to that code or anywhere in the vicinity.

Fixes: f79643787e0a ("powerpc/64s: flush L1D on kernel entry")
Cc: stable@vger.kernel.org # v5.10+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/lib/feature-fixups.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 8f8c8c98a6ac..679833564e19 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -299,8 +299,9 @@ void do_uaccess_flush_fixups(enum l1d_flush_type types)
 						: "unknown");
 }
 
-void do_entry_flush_fixups(enum l1d_flush_type types)
+static int __do_entry_flush_fixups(void *data)
 {
+	enum l1d_flush_type types = (enum l1d_flush_type)data;
 	unsigned int instrs[3], *dest;
 	long *start, *end;
 	int i;
@@ -369,6 +370,19 @@ void do_entry_flush_fixups(enum l1d_flush_type types)
 							: "ori type" :
 		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
 						: "unknown");
+
+	return 0;
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+	/*
+	 * The call to the fallback flush can not be safely patched in/out while
+	 * other CPUs are executing it. So call __do_entry_flush_fixups() on one
+	 * CPU while all other CPUs spin in the stop machine core with interrupts
+	 * hard disabled.
+	 */
+	stop_machine_cpuslocked(__do_entry_flush_fixups, (void *)types, NULL);
 }
 
 void do_rfi_flush_fixups(enum l1d_flush_type types)
-- 
2.25.1

Re: [PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[Nathan Lynch]

Michael Ellerman <mpe@ellerman.id.au> writes:
> -void do_stf_barrier_fixups(enum stf_barrier_type types)
> +static int __do_stf_barrier_fixups(void *data)
>  {
> +	enum stf_barrier_type types = (enum stf_barrier_type)data;
> +
>  	do_stf_entry_barrier_fixups(types);
>  	do_stf_exit_barrier_fixups(types);
> +
> +	return 0;
> +}
> +
> +void do_stf_barrier_fixups(enum stf_barrier_type types)
> +{
> +	/*
> +	 * The call to the fallback entry flush, and the fallback/sync-ori exit
> +	 * flush can not be safely patched in/out while other CPUs are executing
> +	 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
> +	 * spin in the stop machine core with interrupts hard disabled.
> +	 */
> +	stop_machine_cpuslocked(__do_stf_barrier_fixups, (void *)types, NULL);

Would it be preferable to avoid the explicit casts:

	stop_machine_cpuslocked(__do_stf_barrier_fixups, &types, NULL);

...

static int __do_stf_barrier_fixups(void *data)
{
	enum stf_barrier_type *types = data;

 	do_stf_entry_barrier_fixups(*types);
 	do_stf_exit_barrier_fixups(*types);

?

post_mobility_fixup() does cpus_read_unlock() before calling
pseries_setup_security_mitigations(), I think that will need to be
changed?

Re: [PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[Michael Ellerman]

Nathan Lynch <nathanl@linux.ibm.com> writes:
> Michael Ellerman <mpe@ellerman.id.au> writes:
>> -void do_stf_barrier_fixups(enum stf_barrier_type types)
>> +static int __do_stf_barrier_fixups(void *data)
>>  {
>> +	enum stf_barrier_type types = (enum stf_barrier_type)data;
>> +
>>  	do_stf_entry_barrier_fixups(types);
>>  	do_stf_exit_barrier_fixups(types);
>> +
>> +	return 0;
>> +}
>> +
>> +void do_stf_barrier_fixups(enum stf_barrier_type types)
>> +{
>> +	/*
>> +	 * The call to the fallback entry flush, and the fallback/sync-ori exit
>> +	 * flush can not be safely patched in/out while other CPUs are executing
>> +	 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
>> +	 * spin in the stop machine core with interrupts hard disabled.
>> +	 */
>> +	stop_machine_cpuslocked(__do_stf_barrier_fixups, (void *)types, NULL);
>
> Would it be preferable to avoid the explicit casts:
>
> 	stop_machine_cpuslocked(__do_stf_barrier_fixups, &types, NULL);
>
> ...
>
> static int __do_stf_barrier_fixups(void *data)
> {
> 	enum stf_barrier_type *types = data;
>
>  	do_stf_entry_barrier_fixups(*types);
>  	do_stf_exit_barrier_fixups(*types);
>
> ?

Yes.

That will also avoid the pesky issue of undefined behaviour :facepalm:

> post_mobility_fixup() does cpus_read_unlock() before calling
> pseries_setup_security_mitigations(), I think that will need to be
> changed?

I don't think so.

I'm using stop_machine_cpuslocked() but that's because I'm a goose and
forgot to switch to stop_machine() after I reworked the code to not take
cpus_read_lock() by hand. I really shouldn't send patches after 11pm.

I don't think it's important to keep the cpus lock held from where we
take it in post_mobility_fixup(). If some CPUs come or go between there
and here that's fine.

I'll send a v2.

cheers

Re: [PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[Nathan Lynch]

Michael Ellerman <mpe@ellerman.id.au> writes:
> Nathan Lynch <nathanl@linux.ibm.com> writes:
>> post_mobility_fixup() does cpus_read_unlock() before calling
>> pseries_setup_security_mitigations(), I think that will need to be
>> changed?
>
> I don't think so.
>
> I'm using stop_machine_cpuslocked() but that's because I'm a goose and
> forgot to switch to stop_machine() after I reworked the code to not take
> cpus_read_lock() by hand. I really shouldn't send patches after 11pm.
>
> I don't think it's important to keep the cpus lock held from where we
> take it in post_mobility_fixup(). If some CPUs come or go between there
> and here that's fine.

Yes, agreed.

Re: [PATCH 1/2] powerpc/64s: Fix crashes when toggling stf barrier

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 2473 bytes --]

Hi Michael,

I love your patch! Perhaps something to improve:

[auto build test WARNING on powerpc/next]
[also build test WARNING on linus/master v5.12 next-20210505]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Michael-Ellerman/powerpc-64s-Fix-crashes-when-toggling-stf-barrier/20210504-214718
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-randconfig-r022-20210505 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 8f5a2a5836cc8e4c1def2bdeb022e7b496623439)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install powerpc cross compiling tool for clang build
        # apt-get install binutils-powerpc-linux-gnu
        # https://github.com/0day-ci/linux/commit/da6ffcce096961322b6eef8bea33bb1e4c4d1bbf
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Michael-Ellerman/powerpc-64s-Fix-crashes-when-toggling-stf-barrier/20210504-214718
        git checkout da6ffcce096961322b6eef8bea33bb1e4c4d1bbf
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=powerpc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

>> arch/powerpc/lib/feature-fixups.c:233:32: warning: cast to smaller integer type 'enum stf_barrier_type' from 'void *' [-Wvoid-pointer-to-enum-cast]
           enum stf_barrier_type types = (enum stf_barrier_type)data;
                                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~
   1 warning generated.


vim +233 arch/powerpc/lib/feature-fixups.c

   230	
   231	static int __do_stf_barrier_fixups(void *data)
   232	{
 > 233		enum stf_barrier_type types = (enum stf_barrier_type)data;
   234	
   235		do_stf_entry_barrier_fixups(types);
   236		do_stf_exit_barrier_fixups(types);
   237	
   238		return 0;
   239	}
   240	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org

[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 37716 bytes --]

Re: [PATCH 2/2] powerpc/64s: Fix crashes when toggling entry flush barrier

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 8086 bytes --]

Hi Michael,

I love your patch! Perhaps something to improve:

[auto build test WARNING on powerpc/next]
[also build test WARNING on linus/master v5.12 next-20210505]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Michael-Ellerman/powerpc-64s-Fix-crashes-when-toggling-stf-barrier/20210504-214718
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-randconfig-r022-20210505 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 8f5a2a5836cc8e4c1def2bdeb022e7b496623439)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install powerpc cross compiling tool for clang build
        # apt-get install binutils-powerpc-linux-gnu
        # https://github.com/0day-ci/linux/commit/416c4a71342ea7c46c85d8c415489f75635785f1
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Michael-Ellerman/powerpc-64s-Fix-crashes-when-toggling-stf-barrier/20210504-214718
        git checkout 416c4a71342ea7c46c85d8c415489f75635785f1
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=powerpc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   arch/powerpc/lib/feature-fixups.c:233:32: warning: cast to smaller integer type 'enum stf_barrier_type' from 'void *' [-Wvoid-pointer-to-enum-cast]
           enum stf_barrier_type types = (enum stf_barrier_type)data;
                                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~
>> arch/powerpc/lib/feature-fixups.c:304:30: warning: cast to smaller integer type 'enum l1d_flush_type' from 'void *' [-Wvoid-pointer-to-enum-cast]
           enum l1d_flush_type types = (enum l1d_flush_type)data;
                                       ^~~~~~~~~~~~~~~~~~~~~~~~~
   2 warnings generated.


vim +304 arch/powerpc/lib/feature-fixups.c

   230	
   231	static int __do_stf_barrier_fixups(void *data)
   232	{
 > 233		enum stf_barrier_type types = (enum stf_barrier_type)data;
   234	
   235		do_stf_entry_barrier_fixups(types);
   236		do_stf_exit_barrier_fixups(types);
   237	
   238		return 0;
   239	}
   240	
   241	void do_stf_barrier_fixups(enum stf_barrier_type types)
   242	{
   243		/*
   244		 * The call to the fallback entry flush, and the fallback/sync-ori exit
   245		 * flush can not be safely patched in/out while other CPUs are executing
   246		 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
   247		 * spin in the stop machine core with interrupts hard disabled.
   248		 */
   249		stop_machine_cpuslocked(__do_stf_barrier_fixups, (void *)types, NULL);
   250	}
   251	
   252	void do_uaccess_flush_fixups(enum l1d_flush_type types)
   253	{
   254		unsigned int instrs[4], *dest;
   255		long *start, *end;
   256		int i;
   257	
   258		start = PTRRELOC(&__start___uaccess_flush_fixup);
   259		end = PTRRELOC(&__stop___uaccess_flush_fixup);
   260	
   261		instrs[0] = 0x60000000; /* nop */
   262		instrs[1] = 0x60000000; /* nop */
   263		instrs[2] = 0x60000000; /* nop */
   264		instrs[3] = 0x4e800020; /* blr */
   265	
   266		i = 0;
   267		if (types == L1D_FLUSH_FALLBACK) {
   268			instrs[3] = 0x60000000; /* nop */
   269			/* fallthrough to fallback flush */
   270		}
   271	
   272		if (types & L1D_FLUSH_ORI) {
   273			instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
   274			instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
   275		}
   276	
   277		if (types & L1D_FLUSH_MTTRIG)
   278			instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
   279	
   280		for (i = 0; start < end; start++, i++) {
   281			dest = (void *)start + *start;
   282	
   283			pr_devel("patching dest %lx\n", (unsigned long)dest);
   284	
   285			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
   286	
   287			patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
   288			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
   289			patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3]));
   290		}
   291	
   292		printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
   293			(types == L1D_FLUSH_NONE)       ? "no" :
   294			(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
   295			(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
   296								? "ori+mttrig type"
   297								: "ori type" :
   298			(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
   299							: "unknown");
   300	}
   301	
   302	static int __do_entry_flush_fixups(void *data)
   303	{
 > 304		enum l1d_flush_type types = (enum l1d_flush_type)data;
   305		unsigned int instrs[3], *dest;
   306		long *start, *end;
   307		int i;
   308	
   309		instrs[0] = 0x60000000; /* nop */
   310		instrs[1] = 0x60000000; /* nop */
   311		instrs[2] = 0x60000000; /* nop */
   312	
   313		i = 0;
   314		if (types == L1D_FLUSH_FALLBACK) {
   315			instrs[i++] = 0x7d4802a6; /* mflr r10		*/
   316			instrs[i++] = 0x60000000; /* branch patched below */
   317			instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
   318		}
   319	
   320		if (types & L1D_FLUSH_ORI) {
   321			instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
   322			instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
   323		}
   324	
   325		if (types & L1D_FLUSH_MTTRIG)
   326			instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
   327	
   328		start = PTRRELOC(&__start___entry_flush_fixup);
   329		end = PTRRELOC(&__stop___entry_flush_fixup);
   330		for (i = 0; start < end; start++, i++) {
   331			dest = (void *)start + *start;
   332	
   333			pr_devel("patching dest %lx\n", (unsigned long)dest);
   334	
   335			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
   336	
   337			if (types == L1D_FLUSH_FALLBACK)
   338				patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback,
   339					     BRANCH_SET_LINK);
   340			else
   341				patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
   342	
   343			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
   344		}
   345	
   346		start = PTRRELOC(&__start___scv_entry_flush_fixup);
   347		end = PTRRELOC(&__stop___scv_entry_flush_fixup);
   348		for (; start < end; start++, i++) {
   349			dest = (void *)start + *start;
   350	
   351			pr_devel("patching dest %lx\n", (unsigned long)dest);
   352	
   353			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
   354	
   355			if (types == L1D_FLUSH_FALLBACK)
   356				patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback,
   357					     BRANCH_SET_LINK);
   358			else
   359				patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
   360	
   361			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
   362		}
   363	
   364	
   365		printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
   366			(types == L1D_FLUSH_NONE)       ? "no" :
   367			(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
   368			(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
   369								? "ori+mttrig type"
   370								: "ori type" :
   371			(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
   372							: "unknown");
   373	
   374		return 0;
   375	}
   376	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org

[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 37716 bytes --]