By default the retry timeout is 1 second.  Allow that to be modified,
primarily for slow operations, like firmware writes.

Also, the timeout was driven by a 1 second timer, so 1 second really
meant between 0 and 1 second.  Set the default to 2 seconds so it
means between 1 and 2 seconds.

Also allow the time the interface automatically stays in mainenance
mode to be modified from it's default 30 seconds.

Also consolidate some of the timeout and retry setup.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

more

And get rid of the license text that is no longer necessary.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Alistair Popple <alistair@popple.id.au>
Cc: Jeremy Kerr <jk@ozlabs.org>
Cc: Joel Stanley <joel@jms.id.au>
Cc: Rocky Craig <rocky.craig@hp.com>

Convert DEVICE_ATTR uses to DEVICE_ATTR_RO where possible.

Done with perl script:

$ git grep -w --name-only DEVICE_ATTR | \
  xargs perl -i -e 'local $/; while (<>) { s/\bDEVICE_ATTR\s*\(\s*(\w+)\s*,\s*\(?(?:\s*S_IRUGO\s*|\s*0444\s*)\)?\s*,\s*\1_show\s*,\s*NULL\s*\)/DEVICE_ATTR_RO(\1)/g; print;}'
Signed-off-by: NJoe Perches <joe@perches.com>
Acked-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: NRobert Jarzmik <robert.jarzmik@free.fr>
Acked-by: NSagi Grimberg <sagi@grimberg.me>
Acked-by: NZhang Rui <rui.zhang@intel.com>
Acked-by: NHarald Freudenberger <freude@linux.vnet.ibm.com>
Acked-by: NJani Nikula <jani.nikula@intel.com>
Acked-by: NCorey Minyard <cminyard@mvista.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

gcc-8 reports

drivers/char/ipmi/ipmi_msghandler.c: In function
'panic_op_write_handler':
./include/linux/string.h:245:9: warning: '__builtin_strncpy' specified
bound 16 equals destination size [-Wstringop-truncation]

drivers/char/ipmi/ipmi_watchdog.c: In function 'set_param_str':
./include/linux/string.h:245:9: warning: '__builtin_strncpy' specified
bound 16 equals destination size [-Wstringop-truncation]

We need one less byte or call strlcpy() to make it a nul-terminated
string.
Signed-off-by: NXiongfeng Wang <xiongfeng.wang@linaro.org>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

This converts all remaining cases of the old setup_timer() API into using
timer_setup(), where the callback argument is the structure already
holding the struct timer_list. These should have no behavioral changes,
since they just change which pointer is passed into the callback with
the same available pointers after conversion. It handles the following
examples, in addition to some other variations.

Casting from unsigned long:

    void my_callback(unsigned long data)
    {
        struct something *ptr = (struct something *)data;
    ...
    }
    ...
    setup_timer(&ptr->my_timer, my_callback, ptr);

and forced object casts:

    void my_callback(struct something *ptr)
    {
    ...
    }
    ...
    setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr);

become:

    void my_callback(struct timer_list *t)
    {
        struct something *ptr = from_timer(ptr, t, my_timer);
    ...
    }
    ...
    timer_setup(&ptr->my_timer, my_callback, 0);

Direct function assignments:

    void my_callback(unsigned long data)
    {
        struct something *ptr = (struct something *)data;
    ...
    }
    ...
    ptr->my_timer.function = my_callback;

have a temporary cast added, along with converting the args:

    void my_callback(struct timer_list *t)
    {
        struct something *ptr = from_timer(ptr, t, my_timer);
    ...
    }
    ...
    ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback;

And finally, callbacks without a data assignment:

    void my_callback(unsigned long data)
    {
    ...
    }
    ...
    setup_timer(&ptr->my_timer, my_callback, 0);

have their argument renamed to verify they're unused during conversion:

    void my_callback(struct timer_list *unused)
    {
    ...
    }
    ...
    timer_setup(&ptr->my_timer, my_callback, 0);

The conversion is done with the following Coccinelle script:

spatch --very-quiet --all-includes --include-headers \
	-I ./arch/x86/include -I ./arch/x86/include/generated \
	-I ./include -I ./arch/x86/include/uapi \
	-I ./arch/x86/include/generated/uapi -I ./include/uapi \
	-I ./include/generated/uapi --include ./include/linux/kconfig.h \
	--dir . \
	--cocci-file ~/src/data/timer_setup.cocci

@fix_address_of@
expression e;
@@

 setup_timer(
-&(e)
+&e
 , ...)

// Update any raw setup_timer() usages that have a NULL callback, but
// would otherwise match change_timer_function_usage, since the latter
// will update all function assignments done in the face of a NULL
// function initialization in setup_timer().
@change_timer_function_usage_NULL@
expression _E;
identifier _timer;
type _cast_data;
@@

(
-setup_timer(&_E->_timer, NULL, _E);
+timer_setup(&_E->_timer, NULL, 0);
|
-setup_timer(&_E->_timer, NULL, (_cast_data)_E);
+timer_setup(&_E->_timer, NULL, 0);
|
-setup_timer(&_E._timer, NULL, &_E);
+timer_setup(&_E._timer, NULL, 0);
|
-setup_timer(&_E._timer, NULL, (_cast_data)&_E);
+timer_setup(&_E._timer, NULL, 0);
)

@change_timer_function_usage@
expression _E;
identifier _timer;
struct timer_list _stl;
identifier _callback;
type _cast_func, _cast_data;
@@

(
-setup_timer(&_E->_timer, _callback, _E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, &_callback, _E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, _callback, (_cast_data)_E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, &_callback, (_cast_data)_E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, (_cast_func)_callback, _E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, (_cast_func)&_callback, _E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E._timer, _callback, (_cast_data)_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, _callback, (_cast_data)&_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, &_callback, (_cast_data)_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, &_callback, (_cast_data)&_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E);
+timer_setup(&_E._timer, _callback, 0);
|
 _E->_timer@_stl.function = _callback;
|
 _E->_timer@_stl.function = &_callback;
|
 _E->_timer@_stl.function = (_cast_func)_callback;
|
 _E->_timer@_stl.function = (_cast_func)&_callback;
|
 _E._timer@_stl.function = _callback;
|
 _E._timer@_stl.function = &_callback;
|
 _E._timer@_stl.function = (_cast_func)_callback;
|
 _E._timer@_stl.function = (_cast_func)&_callback;
)

// callback(unsigned long arg)
@change_callback_handle_cast
 depends on change_timer_function_usage@
identifier change_timer_function_usage._callback;
identifier change_timer_function_usage._timer;
type _origtype;
identifier _origarg;
type _handletype;
identifier _handle;
@@

 void _callback(
-_origtype _origarg
+struct timer_list *t
 )
 {
(
	... when != _origarg
	_handletype *_handle =
-(_handletype *)_origarg;
+from_timer(_handle, t, _timer);
	... when != _origarg
|
	... when != _origarg
	_handletype *_handle =
-(void *)_origarg;
+from_timer(_handle, t, _timer);
	... when != _origarg
|
	... when != _origarg
	_handletype *_handle;
	... when != _handle
	_handle =
-(_handletype *)_origarg;
+from_timer(_handle, t, _timer);
	... when != _origarg
|
	... when != _origarg
	_handletype *_handle;
	... when != _handle
	_handle =
-(void *)_origarg;
+from_timer(_handle, t, _timer);
	... when != _origarg
)
 }

// callback(unsigned long arg) without existing variable
@change_callback_handle_cast_no_arg
 depends on change_timer_function_usage &&
                     !change_callback_handle_cast@
identifier change_timer_function_usage._callback;
identifier change_timer_function_usage._timer;
type _origtype;
identifier _origarg;
type _handletype;
@@

 void _callback(
-_origtype _origarg
+struct timer_list *t
 )
 {
+	_handletype *_origarg = from_timer(_origarg, t, _timer);
+
	... when != _origarg
-	(_handletype *)_origarg
+	_origarg
	... when != _origarg
 }

// Avoid already converted callbacks.
@match_callback_converted
 depends on change_timer_function_usage &&
            !change_callback_handle_cast &&
	    !change_callback_handle_cast_no_arg@
identifier change_timer_function_usage._callback;
identifier t;
@@

 void _callback(struct timer_list *t)
 { ... }

// callback(struct something *handle)
@change_callback_handle_arg
 depends on change_timer_function_usage &&
	    !match_callback_converted &&
            !change_callback_handle_cast &&
            !change_callback_handle_cast_no_arg@
identifier change_timer_function_usage._callback;
identifier change_timer_function_usage._timer;
type _handletype;
identifier _handle;
@@

 void _callback(
-_handletype *_handle
+struct timer_list *t
 )
 {
+	_handletype *_handle = from_timer(_handle, t, _timer);
	...
 }

// If change_callback_handle_arg ran on an empty function, remove
// the added handler.
@unchange_callback_handle_arg
 depends on change_timer_function_usage &&
	    change_callback_handle_arg@
identifier change_timer_function_usage._callback;
identifier change_timer_function_usage._timer;
type _handletype;
identifier _handle;
identifier t;
@@

 void _callback(struct timer_list *t)
 {
-	_handletype *_handle = from_timer(_handle, t, _timer);
 }

// We only want to refactor the setup_timer() data argument if we've found
// the matching callback. This undoes changes in change_timer_function_usage.
@unchange_timer_function_usage
 depends on change_timer_function_usage &&
            !change_callback_handle_cast &&
            !change_callback_handle_cast_no_arg &&
	    !change_callback_handle_arg@
expression change_timer_function_usage._E;
identifier change_timer_function_usage._timer;
identifier change_timer_function_usage._callback;
type change_timer_function_usage._cast_data;
@@

(
-timer_setup(&_E->_timer, _callback, 0);
+setup_timer(&_E->_timer, _callback, (_cast_data)_E);
|
-timer_setup(&_E._timer, _callback, 0);
+setup_timer(&_E._timer, _callback, (_cast_data)&_E);
)

// If we fixed a callback from a .function assignment, fix the
// assignment cast now.
@change_timer_function_assignment
 depends on change_timer_function_usage &&
            (change_callback_handle_cast ||
             change_callback_handle_cast_no_arg ||
             change_callback_handle_arg)@
expression change_timer_function_usage._E;
identifier change_timer_function_usage._timer;
identifier change_timer_function_usage._callback;
type _cast_func;
typedef TIMER_FUNC_TYPE;
@@

(
 _E->_timer.function =
-_callback
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E->_timer.function =
-&_callback
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E->_timer.function =
-(_cast_func)_callback;
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E->_timer.function =
-(_cast_func)&_callback
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E._timer.function =
-_callback
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E._timer.function =
-&_callback;
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E._timer.function =
-(_cast_func)_callback
+(TIMER_FUNC_TYPE)_callback
 ;
|
 _E._timer.function =
-(_cast_func)&_callback
+(TIMER_FUNC_TYPE)_callback
 ;
)

// Sometimes timer functions are called directly. Replace matched args.
@change_timer_function_calls
 depends on change_timer_function_usage &&
            (change_callback_handle_cast ||
             change_callback_handle_cast_no_arg ||
             change_callback_handle_arg)@
expression _E;
identifier change_timer_function_usage._timer;
identifier change_timer_function_usage._callback;
type _cast_data;
@@

 _callback(
(
-(_cast_data)_E
+&_E->_timer
|
-(_cast_data)&_E
+&_E._timer
|
-_E
+&_E->_timer
)
 )

// If a timer has been configured without a data argument, it can be
// converted without regard to the callback argument, since it is unused.
@match_timer_function_unused_data@
expression _E;
identifier _timer;
identifier _callback;
@@

(
-setup_timer(&_E->_timer, _callback, 0);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, _callback, 0L);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E->_timer, _callback, 0UL);
+timer_setup(&_E->_timer, _callback, 0);
|
-setup_timer(&_E._timer, _callback, 0);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, _callback, 0L);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_E._timer, _callback, 0UL);
+timer_setup(&_E._timer, _callback, 0);
|
-setup_timer(&_timer, _callback, 0);
+timer_setup(&_timer, _callback, 0);
|
-setup_timer(&_timer, _callback, 0L);
+timer_setup(&_timer, _callback, 0);
|
-setup_timer(&_timer, _callback, 0UL);
+timer_setup(&_timer, _callback, 0);
|
-setup_timer(_timer, _callback, 0);
+timer_setup(_timer, _callback, 0);
|
-setup_timer(_timer, _callback, 0L);
+timer_setup(_timer, _callback, 0);
|
-setup_timer(_timer, _callback, 0UL);
+timer_setup(_timer, _callback, 0);
)

@change_callback_unused_data
 depends on match_timer_function_unused_data@
identifier match_timer_function_unused_data._callback;
type _origtype;
identifier _origarg;
@@

 void _callback(
-_origtype _origarg
+struct timer_list *unused
 )
 {
	... when != _origarg
 }
Signed-off-by: NKees Cook <keescook@chromium.org>

The pointer bmc is being initialized and this initialized value is
never being read, so this is assignment redundant and can be removed.
Cleans up clang warning:

warning: Value stored to 'bmc' during its initialization is never read
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Get rid of all printfs, using dev_xxx() if a device is available,
pr_xxx() otherwise, and format long strings properly.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Rework the DMI probe function to be a generic platform probe, and
then rework the DMI code (and a few other things) to use the more
generic information.  This is so other things can declare platform
IPMI devices.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

So we can remove it later.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Signed-off-by: NCorey Minyard <cminyard@mvista.com>

If the BMC changes versions or a change is otherwise detected,
rescan the channels on the BMC.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Put it in it's own struct, getting ready for channel information
being dynamically changed.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

If the BMC fails to register, just set up to retry periodically.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

A BMC's guid or device id info may change dynamically, this could
result in a different configuration that needs to be done.  Adjust
the BMCs dynamically.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

This is getting ready for the ability to redo the BMC if it's
information changes, we need a fallback mechanism.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

This will catch if the GUID changes.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

This is in preparation for making ipmi_get_device_id() dynamically
return the guid and device id.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

It's no longer used, dynamic device id handling is in place now.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Currently, it's up to the IPMI SMIs to provide the product & version
details of BMCs behind registered IPMI SMI interfaces. This device ID is
provided on SMI regsitration, and kept around for all future queries.

However, this version information isn't always static. For example, a
BMC may be upgraded at runtime, making the old version information
stale.

This change allows querying the BMC device ID & version information
dynamically. If no static device_id argument is provided to
ipmi_register_smi, then the IPMI core code will perform a Get Device ID
IPMI command to query the version information when needed. We keep a
short-term cache of this information so we don't need to re-query
for every attribute access.
Signed-off-by: NJeremy Kerr <jk@ozlabs.org>

I basically rewrote this, I fixed some locking issues and simplified
things.  Same functional change, though.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

There are a lot of bad things that a set of BMCs could do that
would really confuse the IPMI driver; it's possible for BMCs with
different GUIDs to have the same product/devid (though that's
not technically legal), which would result in platform device
namespace collisions.  Fixing it would involve either using
the GUID in the BMC name, which resulted in huge names, or
just using an ida for numbering the BMCs.  The latter approach
was chosen to avoid the huge names.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

In an upcoming change, we'll want to grab a reference to the ipmi_smi_t
from a struct bmc_device. This change adds a pointer to allow this.
Signed-off-by: NJeremy Kerr <jk@ozlabs.org>

Reworked to support multiple interfaces on a BMC.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

This makes getting the device id consistent, and make it possible
to add a function to fetch it dynamically later.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

It was just wrong.  Make it print according to the guid spec.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

There was a certain error case where the BMC wouldn't be deregistered
like it should be.  Rework the BMC registration to make calling
ipmi_bmc_unregister() ok even if it's not registered and to clean up
the error handling for ipmi_bmc_register().
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

BMC device refcounts were not being decremented after fetching from
driver_find_device().  Also, document the use of ipmidriver_mutex
and tighten it's span some by incrementing the BMC's usecount in
the BMC find routines and not later.  This will be important for
future changes where a long mutex hold area will complicate things.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Just an added safety check.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

No functional change, this is for a later change that uses the
bmc device type.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

It was off by one.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

They were set by config items, but people complained that they were
never turned on.  So have them always available and enabled by a
module parameter.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

When I set the timeout to a specific value such as 500ms, the timeout
event will not happen in time due to the overflow in function
check_msg_timeout:
...
	ent->timeout -= timeout_period;
	if (ent->timeout > 0)
		return;
...

The type of timeout_period is long, but ent->timeout is unsigned long.
This patch makes the type consistent.
Reported-by: NWeilong Chen <chenweilong@huawei.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>
Tested-by: NWeilong Chen <chenweilong@huawei.com>
Cc: <stable@vger.kernel.org> # 3.16.x

File size before:
   text	   data	    bss	    dec	    hex	filename
  25678	   1024	     92	  26794	   68aa	drivers/char/ipmi/ipmi_msghandler.o

File size After adding 'const':
   text	   data	    bss	    dec	    hex	filename
  25806	    896	     92	  26794	   68aa	drivers/char/ipmi/ipmi_msghandler.o
Signed-off-by: NArvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

A vendor with a system having more than 128 CPUs occasionally encounters
the following crash during shutdown. This is not an easily reproduceable
event, but the vendor was able to provide the following analysis of the
crash, which exhibits the same footprint each time.

crash> bt
PID: 0      TASK: ffff88017c70ce70  CPU: 5   COMMAND: "swapper/5"
 #0 [ffff88085c143ac8] machine_kexec at ffffffff81059c8b
 #1 [ffff88085c143b28] __crash_kexec at ffffffff811052e2
 #2 [ffff88085c143bf8] crash_kexec at ffffffff811053d0
 #3 [ffff88085c143c10] oops_end at ffffffff8168ef88
 #4 [ffff88085c143c38] no_context at ffffffff8167ebb3
 #5 [ffff88085c143c88] __bad_area_nosemaphore at ffffffff8167ec49
 #6 [ffff88085c143cd0] bad_area_nosemaphore at ffffffff8167edb3
 #7 [ffff88085c143ce0] __do_page_fault at ffffffff81691d1e
 #8 [ffff88085c143d40] do_page_fault at ffffffff81691ec5
 #9 [ffff88085c143d70] page_fault at ffffffff8168e188
    [exception RIP: unknown or invalid address]
    RIP: ffffffffa053c800  RSP: ffff88085c143e28  RFLAGS: 00010206
    RAX: ffff88017c72bfd8  RBX: ffff88017a8dc000  RCX: ffff8810588b5ac8
    RDX: ffff8810588b5a00  RSI: ffffffffa053c800  RDI: ffff8810588b5a00
    RBP: ffff88085c143e58   R8: ffff88017c70d408   R9: ffff88017a8dc000
    R10: 0000000000000002  R11: ffff88085c143da0  R12: ffff8810588b5ac8
    R13: 0000000000000100  R14: ffffffffa053c800  R15: ffff8810588b5a00
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
    <IRQ stack>
    [exception RIP: cpuidle_enter_state+82]
    RIP: ffffffff81514192  RSP: ffff88017c72be50  RFLAGS: 00000202
    RAX: 0000001e4c3c6f16  RBX: 000000000000f8a0  RCX: 0000000000000018
    RDX: 0000000225c17d03  RSI: ffff88017c72bfd8  RDI: 0000001e4c3c6f16
    RBP: ffff88017c72be78   R8: 000000000000237e   R9: 0000000000000018
    R10: 0000000000002494  R11: 0000000000000001  R12: ffff88017c72be20
    R13: ffff88085c14f8e0  R14: 0000000000000082  R15: 0000001e4c3bb400
    ORIG_RAX: ffffffffffffff10  CS: 0010  SS: 0018

This is the corresponding stack trace

It has crashed because the area pointed with RIP extracted from timer
element is already removed during a shutdown process.

The function is smi_timeout().

And we think ffff8810588b5a00 in RDX is a parameter struct smi_info

crash> rd ffff8810588b5a00 20
ffff8810588b5a00:  ffff8810588b6000 0000000000000000   .`.X............
ffff8810588b5a10:  ffff880853264400 ffffffffa05417e0   .D&S......T.....
ffff8810588b5a20:  24a024a000000000 0000000000000000   .....$.$........
ffff8810588b5a30:  0000000000000000 0000000000000000   ................
ffff8810588b5a30:  0000000000000000 0000000000000000   ................
ffff8810588b5a40:  ffffffffa053a040 ffffffffa053a060   @.S.....`.S.....
ffff8810588b5a50:  0000000000000000 0000000100000001   ................
ffff8810588b5a60:  0000000000000000 0000000000000e00   ................
ffff8810588b5a70:  ffffffffa053a580 ffffffffa053a6e0   ..S.......S.....
ffff8810588b5a80:  ffffffffa053a4a0 ffffffffa053a250   ..S.....P.S.....
ffff8810588b5a90:  0000000500000002 0000000000000000   ................

Unfortunately the top of this area is already detroyed by someone.
But because of two reasonns we think this is struct smi_info
 1) The address included in between  ffff8810588b5a70 and ffff8810588b5a80:
  are inside of ipmi_si_intf.c  see crash> module ffff88085779d2c0

 2) We've found the area which point this.
  It is offset 0x68 of  ffff880859df4000

crash> rd  ffff880859df4000 100
ffff880859df4000:  0000000000000000 0000000000000001   ................
ffff880859df4010:  ffffffffa0535290 dead000000000200   .RS.............
ffff880859df4020:  ffff880859df4020 ffff880859df4020    @.Y.... @.Y....
ffff880859df4030:  0000000000000002 0000000000100010   ................
ffff880859df4040:  ffff880859df4040 ffff880859df4040   @@.Y....@@.Y....
ffff880859df4050:  0000000000000000 0000000000000000   ................
ffff880859df4060:  0000000000000000 ffff8810588b5a00   .........Z.X....
ffff880859df4070:  0000000000000001 ffff880859df4078   ........x@.Y....

 If we regards it as struct ipmi_smi in shutdown process
 it looks consistent.

The remedy for this apparent race is affixed below.
Signed-off-by: NTony Camuso <tcamuso@redhat.com>
Cc: stable@vger.kernel.org # 3.19

This was first introduced in 7ea0ed2b ipmi: Make the
message handler easier to use for SMI interfaces
where some code was moved outside of the rcu_read_lock()
and the lock was not added.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

It's only function pointers.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

When a computer has an IPMI system interface, the device interface
is most probably also desired. Autoloading of ipmi_devintf currently
works only if ipmi_si has allocated a platform device. That doesn't
happen if the SI interface was detected e.g. via ACPI. But ACPI
detection is preferred these days, see e.g. kernel.org bug 46741.

This patch introduces a softdep in place of the existing modalias
for ipmi_devintf.
Signed-off-by: NMartin Wilck <mwilck@suse.com>
Suggested-by: NTakashi Iwai <tiwai@suse.com>

I moved this to ipmi_msghandler.c, so it works for all IPMI
interfaces.  Retested by Martin.
Tested-by: NMartin Wilck <mwilck@suse.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

The IPMI message handler uses a message id that the lower-layer
preserved to track the sequence number of the message.  The macros
that handled these sequence numbers were somewhat broken as they
could result in sequence number truncation and they were not
doing an "and" of the proper number of bits.

I think this actually is not a problem, because the truncation
should be harmless and the improper "and" didn't hurt anything
because sequence number generation used the same improper "and"
and wouldn't generate a sequence number that would get
truncated wrong.  However, it should be fixed.
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

I meet a crash, which could be reproduce:
1) while true; do cat /proc/ipmi/0/version; done
2) modprobe -rv ipmi_si ipmi_msghandler ipmi_devintf

[82761.021137] IPMI BT: req2rsp=5 secs retries=2
[82761.034524] ipmi device interface
[82761.222218] ipmi_si ipmi_si.0: Found new BMC (man_id: 0x0007db, prod_id: 0x0001, dev_id: 0x01)
[82761.222230] ipmi_si ipmi_si.0: IPMI bt interface initialized
[82903.922740] BUG: unable to handle kernel NULL pointer dereference at 00000000000002d4
[82903.930952] IP: [<ffffffffa030d9e8>] smi_version_proc_show+0x18/0x40 [ipmi_msghandler]
[82903.939220] PGD 86693a067 PUD 865304067 PMD 0
[82903.943893] Thread overran stack, or stack corrupted
[82903.949034] Oops: 0000 [#1] SMP
[82903.983091] Modules linked in: ipmi_si(-) ipmi_msghandler binfmt_misc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter
...
[82904.057285]  pps_core scsi_transport_sas dm_mod vfio_iommu_type1 vfio xt_sctp nf_conntrack_proto_sctp nf_nat_proto_sctp
                nf_nat nf_conntrack sctp libcrc32c [last unloaded: ipmi_devintf]
[82904.073169] CPU: 37 PID: 28089 Comm: cat Tainted: GF          O   ---- -------   3.10.0-327.28.3.el7.x86_64 #1
[82904.083373] Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 3.22 05/16/2016
[82904.090592] task: ffff880101cc2e00 ti: ffff880369c54000 task.ti: ffff880369c54000
[82904.098414] RIP: 0010:[<ffffffffa030d9e8>]  [<ffffffffa030d9e8>] smi_version_proc_show+0x18/0x40 [ipmi_msghandler]
[82904.109124] RSP: 0018:ffff880369c57e70  EFLAGS: 00010203
[82904.114608] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000024688470
[82904.121912] RDX: fffffffffffffff4 RSI: ffffffffa0313404 RDI: ffff8808670ce200
[82904.129218] RBP: ffff880369c57e70 R08: 0000000000019720 R09: ffffffff81204a27
[82904.136521] R10: ffff88046f803300 R11: 0000000000000246 R12: ffff880662399700
[82904.143828] R13: 0000000000000001 R14: ffff880369c57f48 R15: ffff8808670ce200
[82904.151128] FS:  00007fb70c9ca740(0000) GS:ffff88086e340000(0000) knlGS:0000000000000000
[82904.159557] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[82904.165473] CR2: 00000000000002d4 CR3: 0000000864c0c000 CR4: 00000000003407e0
[82904.172778] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[82904.180084] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[82904.187385] Stack:
[82904.189573]  ffff880369c57ee0 ffffffff81204f1a 00000000122a2427 0000000001426000
[82904.197392]  ffff8808670ce238 0000000000010000 0000000000000000 0000000000000fff
[82904.205198]  00000000122a2427 ffff880862079600 0000000001426000 ffff880369c57f48
[82904.212962] Call Trace:
[82904.219667]  [<ffffffff81204f1a>] seq_read+0xfa/0x3a0
[82904.224893]  [<ffffffff8124ce2d>] proc_reg_read+0x3d/0x80
[82904.230468]  [<ffffffff811e102c>] vfs_read+0x9c/0x170
[82904.235689]  [<ffffffff811e1b7f>] SyS_read+0x7f/0xe0
[82904.240816]  [<ffffffff81649209>] system_call_fastpath+0x16/0x1b
[82904.246991] Code: 30 a0 e8 0c 6f ef e0 5b 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f
               44 00 00 48 8b 47 78 55 48 c7 c6 04 34 31 a0 48 89 e5 48 8b 40 50 <0f>
	       b6 90 d4 02 00 00 31 c0 89 d1 83 e2 0f c0 e9 04 0f b6 c9 e8
[82904.267710] RIP  [<ffffffffa030d9e8>] smi_version_proc_show+0x18/0x40 [ipmi_msghandler]
[82904.276079]  RSP <ffff880369c57e70>
[82904.279734] CR2: 00000000000002d4
[82904.283731] ---[ end trace a69e4328b49dd7c4 ]---
[82904.328118] Kernel panic - not syncing: Fatal exception

Reading versin from /proc need bmc device struct available. So in this patch
we move add/remove_proc_entries between ipmi_bmc_register and ipmi_bmc_unregister.

Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: NXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Parameter trydefaults=1 causes the ipmi_init to initialize ipmi through
the legacy port io space that was designated for ipmi. Architectures
that do not map legacy port io can panic when trydefaults=1.

Rather than implement build-time conditional exceptions for each
architecture that does not map legacy port io, we have removed legacy
port io from the driver.

Parameter 'trydefaults' has been removed. Attempts to use it hereafter
will evoke the "Unknown symbol in module, or unknown parameter" message.

The patch was built against a number of architectures and tested for
regressions and functionality on x86_64 and ARM64.
Signed-off-by: NTony Camuso <tcamuso@redhat.com>

Removed the config entry and the address source entry for default,
since neither were used any more.
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Commit 7ea0ed2b ("ipmi: Make the message handler easier to use for
SMI interfaces") changed handle_new_recv_msgs() to call handle_one_recv_msg()
for a smi_msg while the smi_msg is still connected to waiting_rcv_msgs list.
That could lead to following list corruption problems:

1) low-level function treats smi_msg as not connected to list

  handle_one_recv_msg() could end up calling smi_send(), which
  assumes the msg is not connected to list.

  For example, the following sequence could corrupt list by
  doing list_add_tail() for the entry still connected to other list.

    handle_new_recv_msgs()
      msg = list_entry(waiting_rcv_msgs)
      handle_one_recv_msg(msg)
        handle_ipmb_get_msg_cmd(msg)
          smi_send(msg)
            spin_lock(xmit_msgs_lock)
            list_add_tail(msg)
            spin_unlock(xmit_msgs_lock)

2) race between multiple handle_new_recv_msgs() instances

  handle_new_recv_msgs() once releases waiting_rcv_msgs_lock before calling
  handle_one_recv_msg() then retakes the lock and list_del() it.

  If others call handle_new_recv_msgs() during the window shown below
  list_del() will be done twice for the same smi_msg.

  handle_new_recv_msgs()
    spin_lock(waiting_rcv_msgs_lock)
    msg = list_entry(waiting_rcv_msgs)
    spin_unlock(waiting_rcv_msgs_lock)
  |
  | handle_one_recv_msg(msg)
  |
    spin_lock(waiting_rcv_msgs_lock)
    list_del(msg)
    spin_unlock(waiting_rcv_msgs_lock)

Fixes: 7ea0ed2b ("ipmi: Make the message handler easier to use for SMI interfaces")
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
[Added a comment to describe why this works.]
Signed-off-by: NCorey Minyard <cminyard@mvista.com>
Cc: stable@vger.kernel.org # 3.19
Tested-by: NYe Feng <yefeng.yl@alibaba-inc.com>

Lots of char arrays could be set as const since they contain only literal
char arrays.
We could in the same time make const some struct members who are pointer
to those const char arrays.
Signed-off-by: NLABBE Corentin <clabbe.montjoie@gmail.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>

Received handlers defined as ipmi_recv_hndl member of struct
ipmi_user_hndl can take a spinlock.  This means that if the kernel
panics while holding the lock, a deadlock may happen on the lock
while flushing queued messages in the panic context.

Calling the receive handler doesn't make much meanings in the panic
context, simply skip it to avoid possible deadlocks.
Signed-off-by: NHidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Signed-off-by: NCorey Minyard <cminyard@mvista.com>