[WATCHDOG] iTCO_wdt: Fix ICH7+ reboot issue.

Bugzilla: 9868 & 10195.
There seems to be a bug into the SMM code that handles TCO Timeout SMI.
Andriy Gapon found that the code on his DG33TL system does the following:
> The handler is quite simple - it tests value in TCO1_CNT against 0x800, i.e.
> checks TCO_TMR_HLT. If the bit is set the handler goes into an infinite loop,
> apparently to allow the second timeout and reboot. Otherwise it simply clears
> TIMEOUT bit in TCO1_STS and that's it.
> So the logic seems to be reversed, because it is hard to see how TIMEOUT can
> get set to 1 and SMI generated when TCO_TMR_HLT is set (other than a
> transitional effect).

The only trick we have is to bypass the SMM code by turning of the generation
of the SMI#. The trick can only be enabled by setting the vendorsupport module
parameter to 911. This trick doesn't work well on laptop's.

Note: this is a dirty hack. Please handle with care. The only real fix is that
the bug in the SMM bios code get's fixed.

Signed-off-by: Wim Van Sebroeck <wim@iguana.be>

diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c
index 843ef626bc501239c2c104a40c24ba4f3af4a8cc..5133bca5ccbea69ea8ea0a9af367db4c085fcb06 100644 (file)
--- a/drivers/watchdog/iTCO_vendor_support.c
+++ b/drivers/watchdog/iTCO_vendor_support.c
@@ -19,7 +19,7 @@
 
 /* Module and version information */
 #define DRV_NAME       "iTCO_vendor_support"
-#define DRV_VERSION    "1.03"
+#define DRV_VERSION    "1.04"
 #define PFX            DRV_NAME ": "
 
 /* Includes */
@@ -44,11 +44,14 @@
 #define SUPERMICRO_OLD_BOARD   1
 /* SuperMicro Pentium 4 / Xeon 4 / EMT64T Era Systems */
 #define SUPERMICRO_NEW_BOARD   2
+/* Broken BIOS */
+#define BROKEN_BIOS            911
 
 static int vendorsupport;
 module_param(vendorsupport, int, 0);
 MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default="
-                       "0 (none), 1=SuperMicro Pent3, 2=SuperMicro Pent4+");
+                       "0 (none), 1=SuperMicro Pent3, 2=SuperMicro Pent4+, "
+                                                       "911=Broken SMI BIOS");
 
 /*
  *     Vendor Specific Support
@@ -242,6 +245,59 @@ static void supermicro_new_pre_set_heartbeat(unsigned int heartbeat)
        supermicro_new_lock_watchdog();
 }
 
+/*
+ *     Vendor Support: 911
+ *     Board: Some Intel ICHx based motherboards
+ *     iTCO chipset: ICH7+
+ *
+ *     Some Intel motherboards have a broken BIOS implementation: i.e.
+ *     the SMI handler clear's the TIMEOUT bit in the TC01_STS register
+ *     and does not reload the time. Thus the TCO watchdog does not reboot
+ *     the system.
+ *
+ *     These are the conclusions of Andriy Gapon <avg@icyb.net.ua> after
+ *     debugging: the SMI handler is quite simple - it tests value in
+ *     TCO1_CNT against 0x800, i.e. checks TCO_TMR_HLT. If the bit is set
+ *     the handler goes into an infinite loop, apparently to allow the
+ *     second timeout and reboot. Otherwise it simply clears TIMEOUT bit
+ *     in TCO1_STS and that's it.
+ *     So the logic seems to be reversed, because it is hard to see how
+ *     TIMEOUT can get set to 1 and SMI generated when TCO_TMR_HLT is set
+ *     (other than a transitional effect).
+ *
+ *     The only fix found to get the motherboard(s) to reboot is to put
+ *     the glb_smi_en bit to 0. This is a dirty hack that bypasses the
+ *     broken code by disabling Global SMI.
+ *
+ *     WARNING: globally disabling SMI could possibly lead to dramatic
+ *     problems, especially on laptops! I.e. various ACPI things where
+ *     SMI is used for communication between OS and firmware.
+ *
+ *     Don't use this fix if you don't need to!!!
+ */
+
+static void broken_bios_start(unsigned long acpibase)
+{
+       unsigned long val32;
+
+       val32 = inl(SMI_EN);
+       /* Bit 13: TCO_EN     -> 0 = Disables TCO logic generating an SMI#
+          Bit  0: GBL_SMI_EN -> 0 = No SMI# will be generated by ICH. */
+       val32 &= 0xffffdffe;
+       outl(val32, SMI_EN);
+}
+
+static void broken_bios_stop(unsigned long acpibase)
+{
+       unsigned long val32;
+
+       val32 = inl(SMI_EN);
+       /* Bit 13: TCO_EN     -> 1 = Enables TCO logic generating an SMI#
+          Bit  0: GBL_SMI_EN -> 1 = Turn global SMI on again. */
+       val32 |= 0x00002001;
+       outl(val32, SMI_EN);
+}
+
 /*
  *     Generic Support Functions
  */
@@ -249,19 +305,33 @@ static void supermicro_new_pre_set_heartbeat(unsigned int heartbeat)
 void iTCO_vendor_pre_start(unsigned long acpibase,
                           unsigned int heartbeat)
 {
-       if (vendorsupport == SUPERMICRO_OLD_BOARD)
+       switch (vendorsupport) {
+       case SUPERMICRO_OLD_BOARD:
                supermicro_old_pre_start(acpibase);
-       else if (vendorsupport == SUPERMICRO_NEW_BOARD)
+               break;
+       case SUPERMICRO_NEW_BOARD:
                supermicro_new_pre_start(heartbeat);
+               break;
+       case BROKEN_BIOS:
+               broken_bios_start(acpibase);
+               break;
+       }
 }
 EXPORT_SYMBOL(iTCO_vendor_pre_start);
 
 void iTCO_vendor_pre_stop(unsigned long acpibase)
 {
-       if (vendorsupport == SUPERMICRO_OLD_BOARD)
+       switch (vendorsupport) {
+       case SUPERMICRO_OLD_BOARD:
                supermicro_old_pre_stop(acpibase);
-       else if (vendorsupport == SUPERMICRO_NEW_BOARD)
+               break;
+       case SUPERMICRO_NEW_BOARD:
                supermicro_new_pre_stop();
+               break;
+       case BROKEN_BIOS:
+               broken_bios_stop(acpibase);
+               break;
+       }
 }
 EXPORT_SYMBOL(iTCO_vendor_pre_stop);