Merge tag 'powerpc-4.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for direct mapped LPC on POWER9, giving Linux direct access
     to devices that may be on there such as a UART.

   - Memory hotplug support for the Power9 Radix MMU.

   - Add new AUX vectors describing the processor's cache geometry, to
     be used by glibc.

   - The ability for a guest to ask the hypervisor to resize the guest's
     hash table, and in addition support for doing so automatically when
     memory is hotplugged into/out-of the guest. This allows the hash
     table to be sized based on the current memory usage of the guest,
     rather than the maximum possible memory usage.

   - Implementation of optprobes (kprobe optimisation) for powerpc.

  In addition there's the topic branch shared with the KVM tree, which
  includes support for guests to use the Radix MMU on Power9.

  Thanks to:
    Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju T, Anton
    Blanchard, Benjamin Herrenschmidt, Chris Packham, Daniel Axtens,
    Daniel Borkmann, David Gibson, Finn Thain, Gautham R. Shenoy, Gavin
    Shan, Greg Kurz, Joel Stanley, John Allen, Madhavan Srinivasan,
    Mahesh Salgaonkar, Markus Elfring, Michael Neuling, Nathan Fontenot,
    Naveen N. Rao, Nicholas Piggin, Paul Mackerras, Ravi Bangoria, Reza
    Arbab, Shailendra Singh, Vaibhav Jain, Wei Yongjun"

* tag 'powerpc-4.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (129 commits)
  powerpc/mm/radix: Skip ptesync in pte update helpers
  powerpc/mm/radix: Use ptep_get_and_clear_full when clearing pte for full mm
  powerpc/mm/radix: Update pte update sequence for pte clear case
  powerpc/mm: Update PROTFAULT handling in the page fault path
  powerpc/xmon: Fix data-breakpoint
  powerpc/mm: Fix build break with BOOK3S_64=n and MEMORY_HOTPLUG=y
  powerpc/mm: Fix build break when CMA=n && SPAPR_TCE_IOMMU=y
  powerpc/mm: Fix build break with RADIX=y & HUGETLBFS=n
  powerpc/pseries: Fix typo in parameter description
  powerpc/kprobes: Remove kprobe_exceptions_notify()
  kprobes: Introduce weak variant of kprobe_exceptions_notify()
  powerpc/ftrace: Fix confusing help text for DISABLE_MPROFILE_KERNEL
  powerpc/powernv: Fix opal_exit tracepoint opcode
  powerpc: Add a prototype for mcount() so it can be versioned
  powerpc: Drop GPL from of_node_to_nid() export to match other arches
  powerpc/kprobes: Optimize kprobe in kretprobe_trampoline()
  powerpc/kprobes: Implement Optprobes
  powerpc/kprobes: Fixes for kprobe_lookup_name() on BE
  powerpc: Add helper to check if offset is within relative branch range
  powerpc/bpf: Introduce __PPC_SH64()
  ...

1 files changed, 88 insertions, 41 deletions

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 0835a37..3705930 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -19,7 +19,12 @@
 #include <asm/firmware.h>
 #include <asm/opal.h>
 #include <asm/runlatch.h>
+#include <asm/cpuidle.h>
 
+/*
+ * Expose only those Hardware idle states via the cpuidle framework
+ * that have latency value below POWERNV_THRESHOLD_LATENCY_NS.
+ */
 #define POWERNV_THRESHOLD_LATENCY_NS 200000
 
 static struct cpuidle_driver powernv_idle_driver = {
@@ -30,7 +35,12 @@ static struct cpuidle_driver powernv_idle_driver = {
 static int max_idle_state;
 static struct cpuidle_state *cpuidle_state_table;
 
-static u64 stop_psscr_table[CPUIDLE_STATE_MAX];
+struct stop_psscr_table {
+	u64 val;
+	u64 mask;
+};
+
+static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX];
 
 static u64 snooze_timeout;
 static bool snooze_timeout_en;
@@ -102,7 +112,8 @@ static int stop_loop(struct cpuidle_device *dev,
 		     int index)
 {
 	ppc64_runlatch_off();
-	power9_idle_stop(stop_psscr_table[index]);
+	power9_idle_stop(stop_psscr_table[index].val,
+			 stop_psscr_table[index].mask);
 	ppc64_runlatch_on();
 	return index;
 }
@@ -167,6 +178,25 @@ static int powernv_cpuidle_driver_init(void)
 	return 0;
 }
 
+static inline void add_powernv_state(int index, const char *name,
+				     unsigned int flags,
+				     int (*idle_fn)(struct cpuidle_device *,
+						    struct cpuidle_driver *,
+						    int),
+				     unsigned int target_residency,
+				     unsigned int exit_latency,
+				     u64 psscr_val, u64 psscr_mask)
+{
+	strlcpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN);
+	strlcpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN);
+	powernv_states[index].flags = flags;
+	powernv_states[index].target_residency = target_residency;
+	powernv_states[index].exit_latency = exit_latency;
+	powernv_states[index].enter = idle_fn;
+	stop_psscr_table[index].val = psscr_val;
+	stop_psscr_table[index].mask = psscr_mask;
+}
+
 static int powernv_add_idle_states(void)
 {
 	struct device_node *power_mgt;
@@ -176,7 +206,9 @@ static int powernv_add_idle_states(void)
 	u32 residency_ns[CPUIDLE_STATE_MAX];
 	u32 flags[CPUIDLE_STATE_MAX];
 	u64 psscr_val[CPUIDLE_STATE_MAX];
+	u64 psscr_mask[CPUIDLE_STATE_MAX];
 	const char *names[CPUIDLE_STATE_MAX];
+	u32 has_stop_states = 0;
 	int i, rc;
 
 	/* Currently we have snooze statically defined */
@@ -223,19 +255,30 @@ static int powernv_add_idle_states(void)
 
 	/*
 	 * If the idle states use stop instruction, probe for psscr values
-	 * which are necessary to specify required stop level.
+	 * and psscr mask which are necessary to specify required stop level.
 	 */
-	if (flags[0] & (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP))
+	has_stop_states = (flags[0] &
+			   (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
+	if (has_stop_states) {
 		if (of_property_read_u64_array(power_mgt,
 		    "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
-			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n");
+			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
+			goto out;
+		}
+
+		if (of_property_read_u64_array(power_mgt,
+					       "ibm,cpu-idle-state-psscr-mask",
+						psscr_mask, dt_idle_states)) {
+			pr_warn("cpuidle-powernv:Missing ibm,cpu-idle-state-psscr-mask in DT\n");
 			goto out;
 		}
+	}
 
 	rc = of_property_read_u32_array(power_mgt,
 		"ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states);
 
 	for (i = 0; i < dt_idle_states; i++) {
+		unsigned int exit_latency, target_residency;
 		/*
 		 * If an idle state has exit latency beyond
 		 * POWERNV_THRESHOLD_LATENCY_NS then don't use it
@@ -243,28 +286,43 @@ static int powernv_add_idle_states(void)
 		 */
 		if (latency_ns[i] > POWERNV_THRESHOLD_LATENCY_NS)
 			continue;
+		/*
+		 * Firmware passes residency and latency values in ns.
+		 * cpuidle expects it in us.
+		 */
+		exit_latency = latency_ns[i] / 1000;
+		if (!rc)
+			target_residency = residency_ns[i] / 1000;
+		else
+			target_residency = 0;
+
+		if (has_stop_states) {
+			int err = validate_psscr_val_mask(&psscr_val[i],
+							  &psscr_mask[i],
+							  flags[i]);
+			if (err) {
+				report_invalid_psscr_val(psscr_val[i], err);
+				continue;
+			}
+		}
 
 		/*
-		 * Cpuidle accepts exit_latency and target_residency in us.
-		 * Use default target_residency values if f/w does not expose it.
+		 * For nap and fastsleep, use default target_residency
+		 * values if f/w does not expose it.
 		 */
 		if (flags[i] & OPAL_PM_NAP_ENABLED) {
+			if (!rc)
+				target_residency = 100;
 			/* Add NAP state */
-			strcpy(powernv_states[nr_idle_states].name, "Nap");
-			strcpy(powernv_states[nr_idle_states].desc, "Nap");
-			powernv_states[nr_idle_states].flags = 0;
-			powernv_states[nr_idle_states].target_residency = 100;
-			powernv_states[nr_idle_states].enter = nap_loop;
+			add_powernv_state(nr_idle_states, "Nap",
+					  CPUIDLE_FLAG_NONE, nap_loop,
+					  target_residency, exit_latency, 0, 0);
 		} else if ((flags[i] & OPAL_PM_STOP_INST_FAST) &&
 				!(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
-			strncpy(powernv_states[nr_idle_states].name,
-				names[i], CPUIDLE_NAME_LEN);
-			strncpy(powernv_states[nr_idle_states].desc,
-				names[i], CPUIDLE_NAME_LEN);
-			powernv_states[nr_idle_states].flags = 0;
-
-			powernv_states[nr_idle_states].enter = stop_loop;
-			stop_psscr_table[nr_idle_states] = psscr_val[i];
+			add_powernv_state(nr_idle_states, names[i],
+					  CPUIDLE_FLAG_NONE, stop_loop,
+					  target_residency, exit_latency,
+					  psscr_val[i], psscr_mask[i]);
 		}
 
 		/*
@@ -274,32 +332,21 @@ static int powernv_add_idle_states(void)
 #ifdef CONFIG_TICK_ONESHOT
 		if (flags[i] & OPAL_PM_SLEEP_ENABLED ||
 			flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) {
+			if (!rc)
+				target_residency = 300000;
 			/* Add FASTSLEEP state */
-			strcpy(powernv_states[nr_idle_states].name, "FastSleep");
-			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
-			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIMER_STOP;
-			powernv_states[nr_idle_states].target_residency = 300000;
-			powernv_states[nr_idle_states].enter = fastsleep_loop;
+			add_powernv_state(nr_idle_states, "FastSleep",
+					  CPUIDLE_FLAG_TIMER_STOP,
+					  fastsleep_loop,
+					  target_residency, exit_latency, 0, 0);
 		} else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) &&
 				(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
-			strncpy(powernv_states[nr_idle_states].name,
-				names[i], CPUIDLE_NAME_LEN);
-			strncpy(powernv_states[nr_idle_states].desc,
-				names[i], CPUIDLE_NAME_LEN);
-
-			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIMER_STOP;
-			powernv_states[nr_idle_states].enter = stop_loop;
-			stop_psscr_table[nr_idle_states] = psscr_val[i];
+			add_powernv_state(nr_idle_states, names[i],
+					  CPUIDLE_FLAG_TIMER_STOP, stop_loop,
+					  target_residency, exit_latency,
+					  psscr_val[i], psscr_mask[i]);
 		}
 #endif
-		powernv_states[nr_idle_states].exit_latency =
-				((unsigned int)latency_ns[i]) / 1000;
-
-		if (!rc) {
-			powernv_states[nr_idle_states].target_residency =
-				((unsigned int)residency_ns[i]) / 1000;
-		}
-
 		nr_idle_states++;
 	}
 out: