powerpc/pseries: Fix partition migration hang under load

While testing partition migration with heavy CPU load using
shared processors, it was observed that sometimes the migration
would never complete and would appear to hang. Currently, the
migration code assumes that if H_SUCCESS is returned from the H_JOIN
then the migration is complete and the processor is waking up on
the target system. If there was an outstanding PROD to the processor
when the H_JOIN is called, however, it will return H_SUCCESS on the source
system, causing the migration to hang, or in some scenarios cause
the kernel to crash on the complete call waking the caller
of rtas_percpu_suspend_me. Fix this by calling H_JOIN multiple times
if necessary during the migration.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index fdfe14c..ee4c760 100644 (file)
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -46,6 +46,7 @@ EXPORT_SYMBOL(rtas);
 
 struct rtas_suspend_me_data {
        atomic_t working; /* number of cpus accessing this struct */
+       atomic_t done;
        int token; /* ibm,suspend-me */
        int error;
        struct completion *complete; /* wait on this until working == 0 */
@@ -689,7 +690,7 @@ static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
 static void rtas_percpu_suspend_me(void *info)
 {
-       long rc;
+       long rc = H_SUCCESS;
        unsigned long msr_save;
        int cpu;
        struct rtas_suspend_me_data *data =
@@ -701,7 +702,8 @@ static void rtas_percpu_suspend_me(void *info)
        msr_save = mfmsr();
        mtmsr(msr_save & ~(MSR_EE));
 
-       rc = plpar_hcall_norets(H_JOIN);
+       while (rc == H_SUCCESS && !atomic_read(&data->done))
+               rc = plpar_hcall_norets(H_JOIN);
 
        mtmsr(msr_save);
 
@@ -724,6 +726,9 @@ static void rtas_percpu_suspend_me(void *info)
                       smp_processor_id(), rc);
                data->error = rc;
        }
+
+       atomic_set(&data->done, 1);
+
        /* This cpu did the suspend or got an error; in either case,
         * we need to prod all other other cpus out of join state.
         * Extra prods are harmless.
@@ -766,6 +771,7 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
        }
 
        atomic_set(&data.working, 0);
+       atomic_set(&data.done, 0);
        data.token = rtas_token("ibm,suspend-me");
        data.error = 0;
        data.complete = &done;