[S390] Fix reboot hang on LPARs

Reboot hangs on LPARs without diag308 support. The reason for this is,
that before the reboot is done, the channel subsystem is shut down.
During the reset on each possible subchannel a "store subchannel" is
done. This operation can end in a program check interruption, if the
specified subchannel set is not implemented by the hardware. During
the reset, currently we do not have a program check handler, which
leads to the described kernel bug. We install now a new program check
handler for the reboot code to fix this problem.

Signed-off-by: Michael Holzheu <holzheu@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index a36bea1..d2e6a0a 100644 (file)
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1037,13 +1037,15 @@ static void do_reset_calls(void)
 }
 
 extern void reset_mcck_handler(void);
+extern void reset_pgm_handler(void);
 
 void s390_reset_system(void)
 {
        struct _lowcore *lc;
 
-       /* Stack for interrupt/machine check handler */
        lc = (struct _lowcore *)(unsigned long) store_prefix();
+
+       /* Stack for interrupt/machine check handler */
        lc->panic_stack = S390_lowcore.panic_stack;
 
        /* Disable prefixing */
@@ -1056,5 +1058,11 @@ void s390_reset_system(void)
        S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_MCHECK;
        S390_lowcore.mcck_new_psw.addr =
                PSW_ADDR_AMODE | (unsigned long) &reset_mcck_handler;
+
+       /* Set new program check handler */
+       S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_MCHECK;
+       S390_lowcore.program_new_psw.addr =
+               PSW_ADDR_AMODE | (unsigned long) &reset_pgm_handler;
+
        do_reset_calls();
 }

diff --git a/arch/s390/kernel/reset.S b/arch/s390/kernel/reset.S
index be8688c..8a87355 100644 (file)
--- a/arch/s390/kernel/reset.S
+++ b/arch/s390/kernel/reset.S
@@ -3,6 +3,7 @@
  *
  *    Copyright (C) IBM Corp. 2006
  *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ *              Michael Holzheu <holzheu@de.ibm.com>
  */
 
 #include <asm/ptrace.h>
@@ -27,6 +28,26 @@ reset_mcck_handler:
 s390_reset_mcck_handler:
        .quad   0
 
+       .globl  reset_pgm_handler
+reset_pgm_handler:
+       stmg    %r0,%r15,__LC_SAVE_AREA
+       basr    %r13,0
+0:     lg      %r15,__LC_PANIC_STACK   # load panic stack
+       aghi    %r15,-STACK_FRAME_OVERHEAD
+       lg      %r1,s390_reset_pgm_handler-0b(%r13)
+       ltgr    %r1,%r1
+       jz      1f
+       basr    %r14,%r1
+       lmg     %r0,%r15,__LC_SAVE_AREA
+       lpswe   __LC_PGM_OLD_PSW
+1:     lpswe   disabled_wait_psw-0b(%r13)
+       .globl s390_reset_pgm_handler
+s390_reset_pgm_handler:
+       .quad   0
+       .align  8
+disabled_wait_psw:
+       .quad   0x0002000180000000,0x0000000000000000 + reset_pgm_handler
+
 #else /* CONFIG_64BIT */
 
        .globl  reset_mcck_handler
@@ -45,4 +66,25 @@ reset_mcck_handler:
 s390_reset_mcck_handler:
        .long   0
 
+       .globl  reset_pgm_handler
+reset_pgm_handler:
+       stm     %r0,%r15,__LC_SAVE_AREA
+       basr    %r13,0
+0:     l       %r15,__LC_PANIC_STACK   # load panic stack
+       ahi     %r15,-STACK_FRAME_OVERHEAD
+       l       %r1,s390_reset_pgm_handler-0b(%r13)
+       ltr     %r1,%r1
+       jz      1f
+       basr    %r14,%r1
+       lm      %r0,%r15,__LC_SAVE_AREA
+       lpsw    __LC_PGM_OLD_PSW
+
+1:     lpsw    disabled_wait_psw-0b(%r13)
+       .globl  s390_reset_pgm_handler
+s390_reset_pgm_handler:
+       .long   0
+disabled_wait_psw:
+       .align 8
+       .long   0x000a0000,0x00000000 + reset_pgm_handler
+
 #endif /* CONFIG_64BIT */

diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 7835a71..3a403f1 100644 (file)
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -871,11 +871,32 @@ __clear_subchannel_easy(struct subchannel_id schid)
        return -EBUSY;
 }
 
+static int pgm_check_occured;
+
+static void cio_reset_pgm_check_handler(void)
+{
+       pgm_check_occured = 1;
+}
+
+static int stsch_reset(struct subchannel_id schid, volatile struct schib *addr)
+{
+       int rc;
+
+       pgm_check_occured = 0;
+       s390_reset_pgm_handler = cio_reset_pgm_check_handler;
+       rc = stsch(schid, addr);
+       s390_reset_pgm_handler = NULL;
+       if (pgm_check_occured)
+               return -EIO;
+       else
+               return rc;
+}
+
 static int __shutdown_subchannel_easy(struct subchannel_id schid, void *data)
 {
        struct schib schib;
 
-       if (stsch_err(schid, &schib))
+       if (stsch_reset(schid, &schib))
                return -ENXIO;
        if (!schib.pmcw.ena)
                return 0;
@@ -972,7 +993,7 @@ static int __reipl_subchannel_match(struct subchannel_id schid, void *data)
        struct schib schib;
        struct sch_match_id *match_id = data;
 
-       if (stsch_err(schid, &schib))
+       if (stsch_reset(schid, &schib))
                return -ENXIO;
        if (schib.pmcw.dnv &&
            (schib.pmcw.dev == match_id->devid.devno) &&

diff --git a/include/asm-s390/reset.h b/include/asm-s390/reset.h
index 9b439cf..532e65a 100644 (file)
--- a/include/asm-s390/reset.h
+++ b/include/asm-s390/reset.h
@@ -19,5 +19,6 @@ extern void register_reset_call(struct reset_call *reset);
 extern void unregister_reset_call(struct reset_call *reset);
 extern void s390_reset_system(void);
 extern void (*s390_reset_mcck_handler)(void);
+extern void (*s390_reset_pgm_handler)(void);
 
 #endif /* _ASM_S390_RESET_H */