Merge tag 'powerpc-4.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:
   - PowerNV PCI hotplug support.
   - Lots more Power9 support.
   - eBPF JIT support on ppc64le.
   - Lots of cxl updates.
   - Boot code consolidation.

  Bug fixes:
   - Fix spin_unlock_wait() from Boqun Feng
   - Fix stack pointer corruption in __tm_recheckpoint() from Michael
     Neuling
   - Fix multiple bugs in memory_hotplug_max() from Bharata B Rao
   - mm: Ensure "special" zones are empty from Oliver O'Halloran
   - ftrace: Separate the heuristics for checking call sites from
     Michael Ellerman
   - modules: Never restore r2 for a mprofile-kernel style mcount() call
     from Michael Ellerman
   - Fix endianness when reading TCEs from Alexey Kardashevskiy
   - start rtasd before PCI probing from Greg Kurz
   - PCI: rpaphp: Fix slot registration for multiple slots under a PHB
     from Tyrel Datwyler
   - powerpc/mm: Add memory barrier in __hugepte_alloc() from Sukadev
     Bhattiprolu

  Cleanups & fixes:
   - Drop support for MPIC in pseries from Rashmica Gupta
   - Define and use PPC64_ELF_ABI_v2/v1 from Michael Ellerman
   - Remove unused symbols in asm-offsets.c from Rashmica Gupta
   - Fix SRIOV not building without EEH enabled from Russell Currey
   - Remove kretprobe_trampoline_holder from Thiago Jung Bauermann
   - Reduce log level of PCI I/O space warning from Benjamin
     Herrenschmidt
   - Add array bounds checking to crash_shutdown_handlers from Suraj
     Jitindar Singh
   - Avoid -maltivec when using clang integrated assembler from Anton
     Blanchard
   - Fix array overrun in ppc_rtas() syscall from Andrew Donnellan
   - Fix error return value in cmm_mem_going_offline() from Rasmus
     Villemoes
   - export cpu_to_core_id() from Mauricio Faria de Oliveira
   - Remove old symbols from defconfigs from Andrew Donnellan
   - Update obsolete comments in setup_32.c about entry conditions from
     Benjamin Herrenschmidt
   - Add comment explaining the purpose of setup_kdump_trampoline() from
     Benjamin Herrenschmidt
   - Merge the RELOCATABLE config entries for ppc32 and ppc64 from Kevin
     Hao
   - Remove RELOCATABLE_PPC32 from Kevin Hao
   - Fix .long's in tlb-radix.c to more meaningful from Balbir Singh

  Minor cleanups & fixes:
   - Andrew Donnellan, Anna-Maria Gleixner, Anton Blanchard, Benjamin
     Herrenschmidt, Bharata B Rao, Christophe Leroy, Colin Ian King,
     Geliang Tang, Greg Kurz, Madhavan Srinivasan, Michael Ellerman,
     Michael Ellerman, Stephen Rothwell, Stewart Smith.

  Freescale updates from Scott:
   - "Highlights include more 8xx optimizations, device tree updates,
     and MVME7100 support."

  PowerNV PCI hotplug from Gavin Shan:
   - PCI: Add pcibios_setup_bridge()
   - Override pcibios_setup_bridge()
   - Remove PCI_RESET_DELAY_US
   - Move pnv_pci_ioda_setup_opal_tce_kill() around
   - Increase PE# capacity
   - Allocate PE# in reverse order
   - Create PEs in pcibios_setup_bridge()
   - Setup PE for root bus
   - Extend PCI bridge resources
   - Make pnv_ioda_deconfigure_pe() visible
   - Dynamically release PE
   - Update bridge windows on PCI plug
   - Delay populating pdn
   - Support PCI slot ID
   - Use PCI slot reset infrastructure
   - Introduce pnv_pci_get_slot_id()
   - Functions to get/set PCI slot state
   - PCI/hotplug: PowerPC PowerNV PCI hotplug driver
   - Print correct PHB type names

  Power9 idle support from Shreyas B. Prabhu:
   - set power_save func after the idle states are initialized
   - Use PNV_THREAD_WINKLE macro while requesting for winkle
   - make hypervisor state restore a function
   - Rename idle_power7.S to idle_book3s.S
   - Rename reusable idle functions to hardware agnostic names
   - Make pnv_powersave_common more generic
   - abstraction for saving SPRs before entering deep idle states
   - Add platform support for stop instruction
   - cpuidle/powernv: Use CPUIDLE_STATE_MAX instead of MAX_POWERNV_IDLE_STATES
   - cpuidle/powernv: cleanup cpuidle-powernv.c
   - cpuidle/powernv: Add support for POWER ISA v3 idle states
   - Use deepest stop state when cpu is offlined

  Power9 PMU from Madhavan Srinivasan:
   - factor out power8 pmu macros and defines
   - factor out power8 pmu functions
   - factor out power8 __init_pmu code
   - Add power9 event list macros for generic and cache events
   - Power9 PMU support
   - Export Power9 generic and cache events to sysfs

  Power9 preliminary interrupt & PCI support from Benjamin Herrenschmidt:
   - Add XICS emulation APIs
   - Move a few exception common handlers to make room
   - Add support for HV virtualization interrupts
   - Add mechanism to force a replay of interrupts
   - Add ICP OPAL backend
   - Discover IODA3 PHBs
   - pci: Remove obsolete SW invalidate
   - opal: Add real mode call wrappers
   - Rename TCE invalidation calls
   - Remove SWINV constants and obsolete TCE code
   - Rework accessing the TCE invalidate register
   - Fallback to OPAL for TCE invalidations
   - Use the device-tree to get available range of M64's
   - Check status of a PHB before using it
   - pci: Don't try to allocate resources that will be reassigned

  Other Power9:
   - Send SIGBUS on unaligned copy and paste from Chris Smart
   - Large Decrementer support from Oliver O'Halloran
   - Load Monitor Register Support from Jack Miller

  Performance improvements from Anton Blanchard:
   - Avoid load hit store in __giveup_fpu() and __giveup_altivec()
   - Avoid load hit store in setup_sigcontext()
   - Remove assembly versions of strcpy, strcat, strlen and strcmp
   - Align hot loops of some string functions

  eBPF JIT from Naveen N. Rao:
   - Fix/enhance 32-bit Load Immediate implementation
   - Optimize 64-bit Immediate loads
   - Introduce rotate immediate instructions
   - A few cleanups
   - Isolate classic BPF JIT specifics into a separate header
   - Implement JIT compiler for extended BPF

  Operator Panel driver from Suraj Jitindar Singh:
   - devicetree/bindings: Add binding for operator panel on FSP machines
   - Add inline function to get rc from an ASYNC_COMP opal_msg
   - Add driver for operator panel on FSP machines

  Sparse fixes from Daniel Axtens:
   - make some things static
   - Introduce asm-prototypes.h
   - Include headers containing prototypes
   - Use #ifdef __BIG_ENDIAN__ #else for REG_BYTE
   - kvm: Clarify __user annotations
   - Pass endianness to sparse
   - Make ppc_md.{halt, restart} __noreturn

  MM fixes & cleanups from Aneesh Kumar K.V:
   - radix: Update LPCR HR bit as per ISA
   - use _raw variant of page table accessors
   - Compile out radix related functions if RADIX_MMU is disabled
   - Clear top 16 bits of va only on older cpus
   - Print formation regarding the the MMU mode
   - hash: Update SDR1 size encoding as documented in ISA 3.0
   - radix: Update PID switch sequence
   - radix: Update machine call back to support new HCALL.
   - radix: Add LPID based tlb flush helpers
   - radix: Add a kernel command line to disable radix
   - Cleanup LPCR defines

  Boot code consolidation from Benjamin Herrenschmidt:
   - Move epapr_paravirt_early_init() to early_init_devtree()
   - cell: Don't use flat device-tree after boot
   - ge_imp3a: Don't use the flat device-tree after boot
   - mpc85xx_ds: Don't use the flat device-tree after boot
   - mpc85xx_rdb: Don't use the flat device-tree after boot
   - Don't test for machine type in rtas_initialize()
   - Don't test for machine type in smp_setup_cpu_maps()
   - dt: Add of_device_compatible_match()
   - Factor do_feature_fixup calls
   - Move 64-bit feature fixup earlier
   - Move 64-bit memory reserves to setup_arch()
   - Use a cachable DART
   - Move FW feature probing out of pseries probe()
   - Put exception configuration in a common place
   - Remove early allocation of the SMU command buffer
   - Move MMU backend selection out of platform code
   - pasemi: Remove IOBMAP allocation from platform probe()
   - mm/hash: Don't use machine_is() early during boot
   - Don't test for machine type to detect HEA special case
   - pmac: Remove spurrious machine type test
   - Move hash table ops to a separate structure
   - Ensure that ppc_md is empty before probing for machine type
   - Move 64-bit probe_machine() to later in the boot process
   - Move 32-bit probe() machine to later in the boot process
   - Get rid of ppc_md.init_early()
   - Move the boot time info banner to a separate function
   - Move setting of {i,d}cache_bsize to initialize_cache_info()
   - Move the content of setup_system() to setup_arch()
   - Move cache info inits to a separate function
   - Re-order the call to smp_setup_cpu_maps()
   - Re-order setup_panic()
   - Make a few boot functions __init
   - Merge 32-bit and 64-bit setup_arch()

  Other new features:
   - tty/hvc: Use IRQF_SHARED for OPAL hvc consoles from Sam Mendoza-Jonas
   - tty/hvc: Use opal irqchip interface if available from Sam Mendoza-Jonas
   - powerpc: Add module autoloading based on CPU features from Alastair D'Silva
   - crypto: vmx - Convert to CPU feature based module autoloading from Alastair D'Silva
   - Wake up kopald polling thread before waiting for events from Benjamin Herrenschmidt
   - xmon: Dump ISA 2.06 SPRs from Michael Ellerman
   - xmon: Dump ISA 2.07 SPRs from Michael Ellerman
   - Add a parameter to disable 1TB segs from Oliver O'Halloran
   - powerpc/boot: Add OPAL console to epapr wrappers from Oliver O'Halloran
   - Assign fixed PHB number based on device-tree properties from Guilherme G. Piccoli
   - pseries: Add pseries hotplug workqueue from John Allen
   - pseries: Add support for hotplug interrupt source from John Allen
   - pseries: Use kernel hotplug queue for PowerVM hotplug events from John Allen
   - pseries: Move property cloning into its own routine from Nathan Fontenot
   - pseries: Dynamic add entires to associativity lookup array from Nathan Fontenot
   - pseries: Auto-online hotplugged memory from Nathan Fontenot
   - pseries: Remove call to memblock_add() from Nathan Fontenot

  cxl:
   - Add set and get private data to context struct from Michael Neuling
   - make base more explicitly non-modular from Paul Gortmaker
   - Use for_each_compatible_node() macro from Wei Yongjun
   - Frederic Barrat
   - Abstract the differences between the PSL and XSL
   - Make vPHB device node match adapter's
   - Philippe Bergheaud
   - Add mechanism for delivering AFU driver specific events
   - Ignore CAPI adapters misplaced in switched slots
   - Refine slice error debug messages
   - Andrew Donnellan
   - static-ify variables to fix sparse warnings
   - PCI/hotplug: pnv_php: export symbols and move struct types needed by cxl
   - PCI/hotplug: pnv_php: handle OPAL_PCI_SLOT_OFFLINE power state
   - Add cxl_check_and_switch_mode() API to switch bi-modal cards
   - remove dead Kconfig options
   - fix potential NULL dereference in free_adapter()
   - Ian Munsie
   - Update process element after allocating interrupts
   - Add support for CAPP DMA mode
   - Fix allowing bogus AFU descriptors with 0 maximum processes
   - Fix allocating a minimum of 2 pages for the SPA
   - Fix bug where AFU disable operation had no effect
   - Workaround XSL bug that does not clear the RA bit after a reset
   - Fix NULL pointer dereference on kernel contexts with no AFU interrupts
   - powerpc/powernv: Split cxl code out into a separate file
   - Add cxl_slot_is_supported API
   - Enable bus mastering for devices using CAPP DMA mode
   - Move cxl_afu_get / cxl_afu_put to base
   - Allow a default context to be associated with an external pci_dev
   - Do not create vPHB if there are no AFU configuration records
   - powerpc/powernv: Add support for the cxl kernel api on the real phb
   - Add support for using the kernel API with a real PHB
   - Add kernel APIs to get & set the max irqs per context
   - Add preliminary workaround for CX4 interrupt limitation
   - Add support for interrupts on the Mellanox CX4
   - Workaround PE=0 hardware limitation in Mellanox CX4
   - powerpc/powernv: Fix pci-cxl.c build when CONFIG_MODULES=n

  selftests:
   - Test unaligned copy and paste from Chris Smart
   - Load Monitor Register Tests from Jack Miller
   - Cyril Bur
   - exec() with suspended transaction
   - Use signed long to read perf_event_paranoid
   - Fix usage message in context_switch
   - Fix generation of vector instructions/types in context_switch
   - Michael Ellerman
   - Use "Delta" rather than "Error" in normal output
   - Import Anton's mmap & futex micro benchmarks
   - Add a test for PROT_SAO"

* tag 'powerpc-4.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (263 commits)
  powerpc/mm: Parenthesise IS_ENABLED() in if condition
  tty/hvc: Use opal irqchip interface if available
  tty/hvc: Use IRQF_SHARED for OPAL hvc consoles
  selftests/powerpc: exec() with suspended transaction
  powerpc: Improve comment explaining why we modify VRSAVE
  powerpc/mm: Drop unused externs for hpte_init_beat[_v3]()
  powerpc/mm: Rename hpte_init_lpar() and move the fallback to a header
  powerpc/mm: Fix build break when PPC_NATIVE=n
  crypto: vmx - Convert to CPU feature based module autoloading
  powerpc: Add module autoloading based on CPU features
  powerpc/powernv/ioda: Fix endianness when reading TCEs
  powerpc/mm: Add memory barrier in __hugepte_alloc()
  powerpc/modules: Never restore r2 for a mprofile-kernel style mcount() call
  powerpc/ftrace: Separate the heuristics for checking call sites
  powerpc: Merge 32-bit and 64-bit setup_arch()
  powerpc/64: Make a few boot functions __init
  powerpc: Re-order setup_panic()
  powerpc: Re-order the call to smp_setup_cpu_maps()
  powerpc/32: Move cache info inits to a separate function
  powerpc/64: Move the content of setup_system() to setup_arch()
  ...

1 files changed, 159 insertions, 29 deletions

diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index fcc8b6861b63..479c25601612 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -27,9 +27,12 @@
 #include "powernv.h"
 #include "subcore.h"
 
+/* Power ISA 3.0 allows for stop states 0x0 - 0xF */
+#define MAX_STOP_STATE	0xF
+
 static u32 supported_cpuidle_states;
 
-int pnv_save_sprs_for_winkle(void)
+static int pnv_save_sprs_for_deep_states(void)
 {
 	int cpu;
 	int rc;
@@ -50,15 +53,19 @@ int pnv_save_sprs_for_winkle(void)
 		uint64_t pir = get_hard_smp_processor_id(cpu);
 		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
 
-		/*
-		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
-		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
-		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
-		 * can use this bit to distinguish between fastsleep and
-		 * deep winkle.
-		 */
-		hsprg0_val |= 1;
-
+		if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+			/*
+			 * HSPRG0 is used to store the cpu's pointer to paca.
+			 * Hence last 3 bits are guaranteed to be 0. Program
+			 * slw to restore HSPRG0 with 63rd bit set, so that
+			 * when a thread wakes up at 0x100 we can use this bit
+			 * to distinguish between fastsleep and deep winkle.
+			 * This is not necessary with stop/psscr since PLS
+			 * field of psscr indicates which state we are waking
+			 * up from.
+			 */
+			hsprg0_val |= 1;
+		}
 		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
 		if (rc != 0)
 			return rc;
@@ -130,8 +137,8 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
-		pnv_save_sprs_for_winkle();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
+		pnv_save_sprs_for_deep_states();
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -230,43 +237,162 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
 			show_fastsleep_workaround_applyonce,
 			store_fastsleep_workaround_applyonce);
 
-static int __init pnv_init_idle_states(void)
+
+/*
+ * Used for ppc_md.power_save which needs a function with no parameters
+ */
+static void power9_idle(void)
 {
-	struct device_node *power_mgt;
-	int dt_idle_states;
-	u32 *flags;
-	int i;
+	/* Requesting stop state 0 */
+	power9_idle_stop(0);
+}
+/*
+ * First deep stop state. Used to figure out when to save/restore
+ * hypervisor context.
+ */
+u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
 
-	supported_cpuidle_states = 0;
+/*
+ * Deepest stop idle state. Used when a cpu is offlined
+ */
+u64 pnv_deepest_stop_state;
 
-	if (cpuidle_disable != IDLE_NO_OVERRIDE)
-		goto out;
+/*
+ * Power ISA 3.0 idle initialization.
+ *
+ * POWER ISA 3.0 defines a new SPR Processor stop Status and Control
+ * Register (PSSCR) to control idle behavior.
+ *
+ * PSSCR layout:
+ * ----------------------------------------------------------
+ * | PLS | /// | SD | ESL | EC | PSLL | /// | TR | MTL | RL |
+ * ----------------------------------------------------------
+ * 0      4     41   42    43   44     48    54   56    60
+ *
+ * PSSCR key fields:
+ *	Bits 0:3  - Power-Saving Level Status (PLS). This field indicates the
+ *	lowest power-saving state the thread entered since stop instruction was
+ *	last executed.
+ *
+ *	Bit 41 - Status Disable(SD)
+ *	0 - Shows PLS entries
+ *	1 - PLS entries are all 0
+ *
+ *	Bit 42 - Enable State Loss
+ *	0 - No state is lost irrespective of other fields
+ *	1 - Allows state loss
+ *
+ *	Bit 43 - Exit Criterion
+ *	0 - Exit from power-save mode on any interrupt
+ *	1 - Exit from power-save mode controlled by LPCR's PECE bits
+ *
+ *	Bits 44:47 - Power-Saving Level Limit
+ *	This limits the power-saving level that can be entered into.
+ *
+ *	Bits 60:63 - Requested Level
+ *	Used to specify which power-saving level must be entered on executing
+ *	stop instruction
+ *
+ * @np: /ibm,opal/power-mgt device node
+ * @flags: cpu-idle-state-flags array
+ * @dt_idle_states: Number of idle state entries
+ * Returns 0 on success
+ */
+static int __init pnv_arch300_idle_init(struct device_node *np, u32 *flags,
+					int dt_idle_states)
+{
+	u64 *psscr_val = NULL;
+	int rc = 0, i;
 
-	if (!firmware_has_feature(FW_FEATURE_OPAL))
+	psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val),
+				GFP_KERNEL);
+	if (!psscr_val) {
+		rc = -1;
+		goto out;
+	}
+	if (of_property_read_u64_array(np,
+		"ibm,cpu-idle-state-psscr",
+		psscr_val, dt_idle_states)) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n");
+		rc = -1;
 		goto out;
+	}
 
-	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
-	if (!power_mgt) {
+	/*
+	 * Set pnv_first_deep_stop_state and pnv_deepest_stop_state.
+	 * pnv_first_deep_stop_state should be set to the first stop
+	 * level to cause hypervisor state loss.
+	 * pnv_deepest_stop_state should be set to the deepest stop
+	 * stop state.
+	 */
+	pnv_first_deep_stop_state = MAX_STOP_STATE;
+	for (i = 0; i < dt_idle_states; i++) {
+		u64 psscr_rl = psscr_val[i] & PSSCR_RL_MASK;
+
+		if ((flags[i] & OPAL_PM_LOSE_FULL_CONTEXT) &&
+		     (pnv_first_deep_stop_state > psscr_rl))
+			pnv_first_deep_stop_state = psscr_rl;
+
+		if (pnv_deepest_stop_state < psscr_rl)
+			pnv_deepest_stop_state = psscr_rl;
+	}
+
+out:
+	kfree(psscr_val);
+	return rc;
+}
+
+/*
+ * Probe device tree for supported idle states
+ */
+static void __init pnv_probe_idle_states(void)
+{
+	struct device_node *np;
+	int dt_idle_states;
+	u32 *flags = NULL;
+	int i;
+
+	np = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!np) {
 		pr_warn("opal: PowerMgmt Node not found\n");
 		goto out;
 	}
-	dt_idle_states = of_property_count_u32_elems(power_mgt,
+	dt_idle_states = of_property_count_u32_elems(np,
 			"ibm,cpu-idle-state-flags");
 	if (dt_idle_states < 0) {
 		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
 		goto out;
 	}
 
-	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
-	if (of_property_read_u32_array(power_mgt,
+	flags = kcalloc(dt_idle_states, sizeof(*flags),  GFP_KERNEL);
+
+	if (of_property_read_u32_array(np,
 			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
 		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
-		goto out_free;
+		goto out;
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (pnv_arch300_idle_init(np, flags, dt_idle_states))
+			goto out;
 	}
 
 	for (i = 0; i < dt_idle_states; i++)
 		supported_cpuidle_states |= flags[i];
 
+out:
+	kfree(flags);
+}
+static int __init pnv_init_idle_states(void)
+{
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		goto out;
+
+	pnv_probe_idle_states();
+
 	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
 		patch_instruction(
 			(unsigned int *)pnv_fastsleep_workaround_at_entry,
@@ -285,8 +411,12 @@ static int __init pnv_init_idle_states(void)
 	}
 
 	pnv_alloc_idle_core_states();
-out_free:
-	kfree(flags);
+
+	if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
+		ppc_md.power_save = power7_idle;
+	else if (supported_cpuidle_states & OPAL_PM_STOP_INST_FAST)
+		ppc_md.power_save = power9_idle;
+
 out:
 	return 0;
 }