From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
To: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>,
        viresh.kumar@linaro.org, rjw@rjwysocki.net, huntbag@linux.vnet.ibm.com,
        akshay.adiga@linux.vnet.ibm.com, Michael Ellerman <mpe@ellerman.id.au>,
        Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org,
        "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>, <stable@vger.kernel.org>
Subject: [v2 PATCH] cpufreq: powernv: Correctly parse the sign of pstates on POWER8 vs POWER9
Date: Thu,  7 Dec 2017 11:29:25 +0530
Message-Id: <1512626365-22845-1-git-send-email-ego@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 4900
Lines: 134

From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>

On POWERNV platform, Pstates are 8-bit values. On POWER8 they are
negatively numbered while on POWER9 they are positively
numbered. Thus, on POWER9, the maximum number of pstates could be as
high as 256.

The current code interprets pstates as a signed 8-bit value. This
causes a problem on POWER9 platforms which have more than 128 pstates.
On such systems, on a CPU that is in a lower pstate whose number is
greater than 128, querying the current pstate returns a "pstate X is
out of bound" error message and the current pstate is reported as the
nominal pstate.

This patch fixes the aforementioned issue by correctly differentiating
the sign whenever a pstate value read, depending on whether the
pstates are positively numbered or negatively numbered.

Fixes: commit 09ca4c9b5958 ("cpufreq: powernv: Replacing pstate_id with frequency table index")
Cc: <stable@vger.kernel.org> #v4.8
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Tested-and-reviewed-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/powernv-cpufreq.c | 43 ++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index b6d7c4c..bb7586e 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -41,11 +41,14 @@
 #define POWERNV_MAX_PSTATES	256
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
-#define PMSR_MAX(x)		((x >> 32) & 0xFF)
+#define EXTRACT_BYTE(x, shift)	(((x) >> shift) & 0xFF)
+#define MAX_SHIFT		32
 #define LPSTATE_SHIFT		48
 #define GPSTATE_SHIFT		56
-#define GET_LPSTATE(x)		(((x) >> LPSTATE_SHIFT) & 0xFF)
-#define GET_GPSTATE(x)		(((x) >> GPSTATE_SHIFT) & 0xFF)
+#define GET_PMSR_MAX(x)		EXTRACT_BYTE(x, MAX_SHIFT)
+#define GET_LPSTATE(x)		EXTRACT_BYTE(x, LPSTATE_SHIFT)
+#define GET_GPSTATE(x)		EXTRACT_BYTE(x, GPSTATE_SHIFT)
+
 
 #define MAX_RAMP_DOWN_TIME				5120
 /*
@@ -64,6 +67,12 @@
 
 /* Interval after which the timer is queued to bring down global pstate */
 #define GPSTATE_TIMER_INTERVAL				2000
+/*
+ * On POWER8 the pstates are negatively numbered. On POWER9, they are
+ * positively numbered.  Use this flag to track whether we have
+ * positive or negative numbered pstates.
+ */
+static bool pos_pstates;
 
 /**
  * struct global_pstate_info -	Per policy data structure to maintain history of
@@ -164,7 +173,7 @@ static inline unsigned int pstate_to_idx(int pstate)
 	int min = powernv_freqs[powernv_pstate_info.min].driver_data;
 	int max = powernv_freqs[powernv_pstate_info.max].driver_data;
 
-	if (min > 0) {
+	if (pos_pstates) {
 		if (unlikely((pstate < max) || (pstate > min))) {
 			pr_warn_once("pstate %d is out of bound\n", pstate);
 			return powernv_pstate_info.nominal;
@@ -301,6 +310,9 @@ static int init_powernv_pstates(void)
 		}
 	}
 
+	if ((int)pstate_min > 0)
+		pos_pstates = true;
+
 	/* End of list marker entry */
 	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;
 	return 0;
@@ -438,7 +450,6 @@ struct powernv_smp_call_data {
 static void powernv_read_cpu_freq(void *arg)
 {
 	unsigned long pmspr_val;
-	s8 local_pstate_id;
 	struct powernv_smp_call_data *freq_data = arg;
 
 	pmspr_val = get_pmspr(SPRN_PMSR);
@@ -447,8 +458,11 @@ static void powernv_read_cpu_freq(void *arg)
 	 * The local pstate id corresponds bits 48..55 in the PMSR.
 	 * Note: Watch out for the sign!
 	 */
-	local_pstate_id = (pmspr_val >> 48) & 0xFF;
-	freq_data->pstate_id = local_pstate_id;
+	if (pos_pstates)
+		freq_data->pstate_id = (u8)GET_LPSTATE(pmspr_val);
+	else
+		freq_data->pstate_id = (s8)GET_LPSTATE(pmspr_val);
+
 	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);
 
 	pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n",
@@ -522,7 +536,10 @@ static void powernv_cpufreq_throttle_check(void *data)
 	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
-	pmsr_pmax = (s8)PMSR_MAX(pmsr);
+	if (pos_pstates)
+		pmsr_pmax = (u8)GET_PMSR_MAX(pmsr);
+	else
+		pmsr_pmax = (s8)GET_PMSR_MAX(pmsr);
 	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
 	if (pmsr_pmax_idx != powernv_pstate_info.max) {
 		if (chip->throttled)
@@ -645,8 +662,14 @@ void gpstate_timer_handler(struct timer_list *t)
 	 * value. Hence, read from PMCR to get correct data.
 	 */
 	val = get_pmspr(SPRN_PMCR);
-	freq_data.gpstate_id = (s8)GET_GPSTATE(val);
-	freq_data.pstate_id = (s8)GET_LPSTATE(val);
+	if (pos_pstates) {
+		freq_data.gpstate_id = (u8)GET_GPSTATE(val);
+		freq_data.pstate_id = (u8)GET_LPSTATE(val);
+	} else {
+		freq_data.gpstate_id = (s8)GET_GPSTATE(val);
+		freq_data.pstate_id = (s8)GET_LPSTATE(val);
+	}
+
 	if (freq_data.gpstate_id  == freq_data.pstate_id) {
 		reset_gpstates(policy);
 		spin_unlock(&gpstates->gpstate_lock);
-- 
1.8.3.1