Implement rtas_call_reentrant() for reentrant rtas-calls:
"ibm,int-on", "ibm,int-off",ibm,get-xive" and "ibm,set-xive".
On LoPAPR Version 1.1 (March 24, 2016), from 7.3.10.1 to 7.3.10.4,
items 2 and 3 say:
2 - For the PowerPC External Interrupt option: The * call must be
reentrant to the number of processors on the platform.
3 - For the PowerPC External Interrupt option: The * argument call
buffer for each simultaneous call must be physically unique.
So, these rtas-calls can be called in a lockless way, if using
a different buffer for each call.
This can be useful to avoid deadlocks in crashing, where rtas-calls are
needed, but some other thread crashed holding the rtas.lock.
This is an example backtrace of deadlock noticed:
#0 arch_spin_lock
#1 lock_rtas ()
#2 rtas_call (token=8204, nargs=1, nret=1, outputs=0x0)
#3 ics_rtas_mask_real_irq (hw_irq=4100)
#4 machine_kexec_mask_interrupts
#5 default_machine_crash_shutdown
#6 machine_crash_shutdown
#7 __crash_kexec
#8 crash_kexec
#9 oops_end
Signed-off-by: Leonardo Bras
---
Changes since v1:
- Moved buffer from stack to PACA (as suggested by Paul Mackerras)
- Added missing output bits
- Improve documentation following kernel-doc format (as suggested by
Nathan Lynch)
---
arch/powerpc/include/asm/paca.h | 2 ++
arch/powerpc/include/asm/rtas.h | 1 +
arch/powerpc/kernel/rtas.c | 42 +
arch/powerpc/sysdev/xics/ics-rtas.c | 22 +++
4 files changed, 56 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index e3cc9eb9204d..5a76ba50b40f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -29,6 +29,7 @@
#include
#include
#include
+#include
#include
@@ -270,6 +271,7 @@ struct paca_struct {
#ifdef CONFIG_MMIOWB
struct mmiowb_state mmiowb_state;
#endif
+ struct rtas_args reentrant_args;
} cacheline_aligned;
extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index c35c5350b7e4..fa7509c85881 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -236,6 +236,7 @@ extern struct rtas_t rtas;
extern int rtas_token(const char *service);
extern int rtas_service_present(const char *service);
extern int rtas_call(int token, int, int, int *, ...);
+int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...);
void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
int nret, ...);
extern void __noreturn rtas_restart(char *cmd);
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index c5fa251b8950..d426b5c4856c 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -41,6 +41,7 @@
#include
#include
#include
+#include
/* This is here deliberately so it's only used in this file */
void enter_rtas(unsigned long);
@@ -483,6 +484,47 @@ int rtas_call(int token, int nargs, int nret, int
*outputs, ...)
}
EXPORT_SYMBOL(rtas_call);
+/**
+ * rtas_call_reentrant() - Used for reentrant rtas calls
+ * @token: Token for desired reentrant RTAS call
+ * @nargs: Number of Input Parameters
+ * @nret: Number of Output Parameters
+ * @outputs: Array of outputs
+ * @...: Inputs for desired RTAS call
+ *
+ * According to LoPAR documentation, only "ibm,int-on", "ibm,int-off",
+ * "ibm,get-xive" and "ibm,set-xive" are currently reentrant.
+ * Reentrant calls need their own rtas_args buffer, so not using rtas.args, but
+ * PACA one instead.
+ *
+ * Return: -1 on error,
+ * First output value of RTAS call if (nret > 0),
+ * 0 otherwise,
+ */
+
+int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
+{
+ va_list list;
+ struct rtas_args *args;
+ int i;
+
+ if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
+ return -1;
+
+ /* We use the per-cpu (PACA) rtas args buffer */
+ args = &local_paca->reentrant_args;
+
+ va_start(list, outputs);
+ va_rtas_call_unlocked(args, token, nargs, nret, list);
+ va_end(list);
+
+ if (nret > 1 && outputs)
+ for (i = 0; i < nret - 1; ++i)
+ outputs[i] = be32_to_cpu(args->rets[i + 1]);
+
+ return (nret > 0) ? be32_to_cpu(args->rets[0]) : 0;
+}
+
/* For RTAS_BUSY (-2), delay for 1 millisecond. For an extended busy status
* code of 990n, perform the hinted delay of 10^n (last digit) milliseconds.
*/
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c
b/arch/powerpc/sysdev/xics/ics-rtas.c
index 6aabc74688a6..4cf18000f07c 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -50,8 +50,8 @@ static void ics_rtas_unmask_irq(struct irq_data *d)
server = xics_get_irq_server(d->irq, irq_data_get_affinity_mask(d)
