Merge tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add support for (optionally) using queued spinlocks & rwlocks.

 - Support for a new faster system call ABI using the scv instruction on
   Power9 or later.

 - Drop support for the PROT_SAO mmap/mprotect flag as it will be
   unsupported on Power10 and future processors, leaving us with no way
   to implement the functionality it requests. This risks breaking
   userspace, though we believe it is unused in practice.

 - A bug fix for, and then the removal of, our custom stack expansion
   checking. We now allow stack expansion up to the rlimit, like other
   architectures.

 - Remove the remnants of our (previously disabled) topology update
   code, which tried to react to NUMA layout changes on virtualised
   systems, but was prone to crashes and other problems.

 - Add PMU support for Power10 CPUs.

 - A change to our signal trampoline so that we don't unbalance the link
   stack (branch return predictor) in the signal delivery path.

 - Lots of other cleanups, refactorings, smaller features and so on as
   usual.

Thanks to: Abhishek Goel, Alastair D'Silva, Alexander A. Klimov, Alexey
Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju
T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Balamuruhan
S, Bharata B Rao, Bill Wendling, Bin Meng, Cédric Le Goater, Chris
Packham, Christophe Leroy, Christoph Hellwig, Daniel Axtens, Dan
Williams, David Lamparter, Desnes A. Nunes do Rosario, Erhard F., Finn
Thain, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geoff Levand,
Greg Kurz, Gustavo A. R. Silva, Hari Bathini, Harish, Imre Kaloz, Joel
Stanley, Joe Perches, John Crispin, Jordan Niethe, Kajol Jain, Kamalesh
Babulal, Kees Cook, Laurent Dufour, Leonardo Bras, Li RongQing, Madhavan
Srinivasan, Mahesh Salgaonkar, Mark Cave-Ayland, Michal Suchanek, Milton
Miller, Mimi Zohar, Murilo Opsfelder Araujo, Nathan Chancellor, Nathan
Lynch, Naveen N. Rao, Nayna Jain, Nicholas Piggin, Oliver O'Halloran,
Palmer Dabbelt, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud,
Pingfan Liu, Pratik Rajesh Sampat, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sam Bobroff, Sandipan Das, Santosh
Sivaraj, Satheesh Rajendran, Shirisha Ganta, Sourabh Jain, Srikar
Dronamraju, Stan Johnson, Stephen Rothwell, Thadeu Lima de Souza
Cascardo, Thiago Jung Bauermann, Tom Lane, Vaibhav Jain, Vladis Dronov,
Wei Yongjun, Wen Xiong, YueHaibing.

* tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (337 commits)
  selftests/powerpc: Fix pkey syscall redefinitions
  powerpc: Fix circular dependency between percpu.h and mmu.h
  powerpc/powernv/sriov: Fix use of uninitialised variable
  selftests/powerpc: Skip vmx/vsx/tar/etc tests on older CPUs
  powerpc/40x: Fix assembler warning about r0
  powerpc/papr_scm: Add support for fetching nvdimm 'fuel-gauge' metric
  powerpc/papr_scm: Fetch nvdimm performance stats from PHYP
  cpuidle: pseries: Fixup exit latency for CEDE(0)
  cpuidle: pseries: Add function to parse extended CEDE records
  cpuidle: pseries: Set the latency-hint before entering CEDE
  selftests/powerpc: Fix online CPU selection
  powerpc/perf: Consolidate perf_callchain_user_[64|32]()
  powerpc/pseries/hotplug-cpu: Remove double free in error path
  powerpc/pseries/mobility: Add pr_debug() for device tree changes
  powerpc/pseries/mobility: Set pr_fmt()
  powerpc/cacheinfo: Warn if cache object chain becomes unordered
  powerpc/cacheinfo: Improve diagnostics about malformed cache lists
  powerpc/cacheinfo: Use name@unit instead of full DT path in debug messages
  powerpc/cacheinfo: Set pr_fmt()
  powerpc: fix function annotations to avoid section mismatch warnings with gcc-10
  ...

2 files changed, 184 insertions, 17 deletions

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 1b299e801f74..addaa6e6718b 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -244,20 +244,6 @@ static inline void add_powernv_state(int index, const char *name,
 	stop_psscr_table[index].mask = psscr_mask;
 }
 
-/*
- * Returns 0 if prop1_len == prop2_len. Else returns -1
- */
-static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
-					 const char *prop2, int prop2_len)
-{
-	if (prop1_len == prop2_len)
-		return 0;
-
-	pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
-		prop1, prop2);
-	return -1;
-}
-
 extern u32 pnv_get_supported_cpuidle_states(void);
 static int powernv_add_idle_states(void)
 {
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 6513ef2af66a..ff6d99e923a4 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -21,8 +21,9 @@
 #include <asm/runlatch.h>
 #include <asm/idle.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/rtas.h>
 
-struct cpuidle_driver pseries_idle_driver = {
+static struct cpuidle_driver pseries_idle_driver = {
 	.name             = "pseries_idle",
 	.owner            = THIS_MODULE,
 };
@@ -86,19 +87,150 @@ static void check_and_cede_processor(void)
 	}
 }
 
+/*
+ * XCEDE: Extended CEDE states discovered through the
+ *        "ibm,get-systems-parameter" RTAS call with the token
+ *        CEDE_LATENCY_TOKEN
+ */
+
+/*
+ * Section 7.3.16 System Parameters Option of PAPR version 2.8.1 has a
+ * table with all the parameters to ibm,get-system-parameters.
+ * CEDE_LATENCY_TOKEN corresponds to the token value for Cede Latency
+ * Settings Information.
+ */
+#define CEDE_LATENCY_TOKEN	45
+
+/*
+ * If the platform supports the cede latency settings information system
+ * parameter it must provide the following information in the NULL terminated
+ * parameter string:
+ *
+ * a. The first byte is the length “N” of each cede latency setting record minus
+ *    one (zero indicates a length of 1 byte).
+ *
+ * b. For each supported cede latency setting a cede latency setting record
+ *    consisting of the first “N” bytes as per the following table.
+ *
+ *    -----------------------------
+ *    | Field           | Field   |
+ *    | Name            | Length  |
+ *    -----------------------------
+ *    | Cede Latency    | 1 Byte  |
+ *    | Specifier Value |         |
+ *    -----------------------------
+ *    | Maximum wakeup  |         |
+ *    | latency in      | 8 Bytes |
+ *    | tb-ticks        |         |
+ *    -----------------------------
+ *    | Responsive to   |         |
+ *    | external        | 1 Byte  |
+ *    | interrupts      |         |
+ *    -----------------------------
+ *
+ * This version has cede latency record size = 10.
+ *
+ * The structure xcede_latency_payload represents a) and b) with
+ * xcede_latency_record representing the table in b).
+ *
+ * xcede_latency_parameter is what gets returned by
+ * ibm,get-systems-parameter RTAS call when made with
+ * CEDE_LATENCY_TOKEN.
+ *
+ * These structures are only used to represent the data obtained by the RTAS
+ * call. The data is in big-endian.
+ */
+struct xcede_latency_record {
+	u8	hint;
+	__be64	latency_ticks;
+	u8	wake_on_irqs;
+} __packed;
+
+// Make space for 16 records, which "should be enough".
+struct xcede_latency_payload {
+	u8     record_size;
+	struct xcede_latency_record records[16];
+} __packed;
+
+struct xcede_latency_parameter {
+	__be16  payload_size;
+	struct xcede_latency_payload payload;
+	u8 null_char;
+} __packed;
+
+static unsigned int nr_xcede_records;
+static struct xcede_latency_parameter xcede_latency_parameter __initdata;
+
+static int __init parse_cede_parameters(void)
+{
+	struct xcede_latency_payload *payload;
+	u32 total_xcede_records_size;
+	u8 xcede_record_size;
+	u16 payload_size;
+	int ret, i;
+
+	ret = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+			NULL, CEDE_LATENCY_TOKEN, __pa(&xcede_latency_parameter),
+			sizeof(xcede_latency_parameter));
+	if (ret) {
+		pr_err("xcede: Error parsing CEDE_LATENCY_TOKEN\n");
+		return ret;
+	}
+
+	payload_size = be16_to_cpu(xcede_latency_parameter.payload_size);
+	payload = &xcede_latency_parameter.payload;
+
+	xcede_record_size = payload->record_size + 1;
+
+	if (xcede_record_size != sizeof(struct xcede_latency_record)) {
+		pr_err("xcede: Expected record-size %lu. Observed size %u.\n",
+		       sizeof(struct xcede_latency_record), xcede_record_size);
+		return -EINVAL;
+	}
+
+	pr_info("xcede: xcede_record_size = %d\n", xcede_record_size);
+
+	/*
+	 * Since the payload_size includes the last NULL byte and the
+	 * xcede_record_size, the remaining bytes correspond to array of all
+	 * cede_latency settings.
+	 */
+	total_xcede_records_size = payload_size - 2;
+	nr_xcede_records = total_xcede_records_size / xcede_record_size;
+
+	for (i = 0; i < nr_xcede_records; i++) {
+		struct xcede_latency_record *record = &payload->records[i];
+		u64 latency_ticks = be64_to_cpu(record->latency_ticks);
+		u8 wake_on_irqs = record->wake_on_irqs;
+		u8 hint = record->hint;
+
+		pr_info("xcede: Record %d : hint = %u, latency = 0x%llx tb ticks, Wake-on-irq = %u\n",
+			i, hint, latency_ticks, wake_on_irqs);
+	}
+
+	return 0;
+}
+
+#define NR_DEDICATED_STATES	2 /* snooze, CEDE */
+static u8 cede_latency_hint[NR_DEDICATED_STATES];
+
 static int dedicated_cede_loop(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
 {
+	u8 old_latency_hint;
 
 	pseries_idle_prolog();
 	get_lppaca()->donate_dedicated_cpu = 1;
+	old_latency_hint = get_lppaca()->cede_latency_hint;
+	get_lppaca()->cede_latency_hint = cede_latency_hint[index];
 
 	HMT_medium();
 	check_and_cede_processor();
 
 	local_irq_disable();
 	get_lppaca()->donate_dedicated_cpu = 0;
+	get_lppaca()->cede_latency_hint = old_latency_hint;
 
 	pseries_idle_epilog();
 
@@ -130,7 +262,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 /*
  * States for dedicated partition case.
  */
-static struct cpuidle_state dedicated_states[] = {
+static struct cpuidle_state dedicated_states[NR_DEDICATED_STATES] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
@@ -211,6 +343,54 @@ static int pseries_cpuidle_driver_init(void)
 	return 0;
 }
 
+static void __init fixup_cede0_latency(void)
+{
+	struct xcede_latency_payload *payload;
+	u64 min_latency_us;
+	int i;
+
+	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
+
+	if (parse_cede_parameters())
+		return;
+
+	pr_info("cpuidle: Skipping the %d Extended CEDE idle states\n",
+		nr_xcede_records);
+
+	payload = &xcede_latency_parameter.payload;
+	for (i = 0; i < nr_xcede_records; i++) {
+		struct xcede_latency_record *record = &payload->records[i];
+		u64 latency_tb = be64_to_cpu(record->latency_ticks);
+		u64 latency_us = tb_to_ns(latency_tb) / NSEC_PER_USEC;
+
+		if (latency_us < min_latency_us)
+			min_latency_us = latency_us;
+	}
+
+	/*
+	 * By default, we assume that CEDE(0) has exit latency 10us,
+	 * since there is no way for us to query from the platform.
+	 *
+	 * However, if the wakeup latency of an Extended CEDE state is
+	 * smaller than 10us, then we can be sure that CEDE(0)
+	 * requires no more than that.
+	 *
+	 * Perform the fix-up.
+	 */
+	if (min_latency_us < dedicated_states[1].exit_latency) {
+		u64 cede0_latency = min_latency_us - 1;
+
+		if (cede0_latency <= 0)
+			cede0_latency = min_latency_us;
+
+		dedicated_states[1].exit_latency = cede0_latency;
+		dedicated_states[1].target_residency = 10 * (cede0_latency);
+		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
+			cede0_latency);
+	}
+
+}
+
 /*
  * pseries_idle_probe()
  * Choose state table for shared versus dedicated partition
@@ -232,8 +412,9 @@ static int pseries_idle_probe(void)
 			cpuidle_state_table = shared_states;
 			max_idle_state = ARRAY_SIZE(shared_states);
 		} else {
+			fixup_cede0_latency();
 			cpuidle_state_table = dedicated_states;
-			max_idle_state = ARRAY_SIZE(dedicated_states);
+			max_idle_state = NR_DEDICATED_STATES;
 		}
 	} else
 		return -ENODEV;