Merge branches 'oprofile-v2' and 'timers/hpet' into x86/core-v4

Author: Ingo Molnar

Documentation/00-INDEX

@@ -159,8 +159,6 @@ hayes-esp.txt
 	- info on using the Hayes ESP serial driver.
 highuid.txt
 	- notes on the change from 16 bit to 32 bit user/group IDs.
-hpet.txt
-	- High Precision Event Timer Driver for Linux.
 timers/
 	- info on the timer related topics
 hw_random.txt

Documentation/timers/00-INDEX

@@ -0,0 +1,10 @@
+00-INDEX
+	- this file
+highres.txt
+	- High resolution timers and dynamic ticks design notes
+hpet.txt
+	- High Precision Event Timer Driver for Linux
+hrtimers.txt
+	- subsystem for high-resolution kernel timers
+timer_stats.txt
+	- timer usage statistics

Documentation/hpet.txt renamed to Documentation/timers/hpet.txt

@@ -1,21 +1,32 @@
 		High Precision Event Timer Driver for Linux
 
-The High Precision Event Timer (HPET) hardware is the future replacement
-for the 8254 and Real Time Clock (RTC) periodic timer functionality.
-Each HPET can have up to 32 timers.  It is possible to configure the
-first two timers as legacy replacements for 8254 and RTC periodic timers.
-A specification done by Intel and Microsoft can be found at
-<http://www.intel.com/technology/architecture/hpetspec.htm>.
+The High Precision Event Timer (HPET) hardware follows a specification
+by Intel and Microsoft which can be found at
+
+	http://www.intel.com/technology/architecture/hpetspec.htm
+
+Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
+and up to 32 comparators.  Normally three or more comparators are provided,
+each of which can generate oneshot interupts and at least one of which has
+additional hardware to support periodic interrupts.  The comparators are
+also called "timers", which can be misleading since usually timers are
+independent of each other ... these share a counter, complicating resets.
+
+HPET devices can support two interrupt routing modes.  In one mode, the
+comparators are additional interrupt sources with no particular system
+role.  Many x86 BIOS writers don't route HPET interrupts at all, which
+prevents use of that mode.  They support the other "legacy replacement"
+mode where the first two comparators block interrupts from 8254 timers
+and from the RTC.
 
 The driver supports detection of HPET driver allocation and initialization
 of the HPET before the driver module_init routine is called.  This enables
 platform code which uses timer 0 or 1 as the main timer to intercept HPET
 initialization.  An example of this initialization can be found in
-arch/i386/kernel/time_hpet.c.
+arch/x86/kernel/hpet.c.
 
-The driver provides two APIs which are very similar to the API found in
-the rtc.c driver.  There is a user space API and a kernel space API.
-An example user space program is provided below.
+The driver provides a userspace API which resembles the API found in the
+RTC driver framework.  An example user space program is provided below.
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -286,15 +297,3 @@ out:
 
 	return;
 }
-
-The kernel API has three interfaces exported from the driver:
-
-	hpet_register(struct hpet_task *tp, int periodic)
-	hpet_unregister(struct hpet_task *tp)
-	hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg)
-
-The kernel module using this interface fills in the ht_func and ht_data
-members of the hpet_task structure before calling hpet_register.
-hpet_control simply vectors to the hpet_ioctl routine and has the same
-commands and respective arguments as the user API.  hpet_unregister
-is used to terminate usage of the HPET timer reserved by hpet_register.

arch/Kconfig

@@ -13,6 +13,20 @@ config OPROFILE
 
 	  If unsure, say N.
 
+config OPROFILE_IBS
+	bool "OProfile AMD IBS support (EXPERIMENTAL)"
+	default n
+	depends on OPROFILE && SMP && X86
+	help
+          Instruction-Based Sampling (IBS) is a new profiling
+          technique that provides rich, precise program performance
+          information. IBS is introduced by AMD Family10h processors
+          (AMD Opteron Quad-Core processor “Barcelona”) to overcome
+          the limitations of conventional performance counter
+          sampling.
+
+	  If unsure, say N.
+
 config HAVE_OPROFILE
 	def_bool n
 

arch/x86/kernel/apic_32.c

@@ -295,6 +295,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
  *
  * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
  * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ *
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
  */
 
 #define APIC_EILVT_LVTOFF_MCE 0
@@ -319,6 +322,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
 	setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
 	return APIC_EILVT_LVTOFF_IBS;
 }
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
 
 /*
  * Program the next event, relative to now

arch/x86/kernel/apic_64.c

@@ -307,6 +307,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
  *
  * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
  * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ *
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
  */
 
 #define APIC_EILVT_LVTOFF_MCE 0
@@ -331,6 +334,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
 	setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
 	return APIC_EILVT_LVTOFF_IBS;
 }
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
 
 /*
  * Program the next event, relative to now

arch/x86/kernel/hpet.c

@@ -115,13 +115,17 @@ static void hpet_reserve_platform_timers(unsigned long id)
 	hd.hd_phys_address = hpet_address;
 	hd.hd_address = hpet;
 	hd.hd_nirqs = nrtimers;
-	hd.hd_flags = HPET_DATA_PLATFORM;
 	hpet_reserve_timer(&hd, 0);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 	hpet_reserve_timer(&hd, 1);
 #endif
 
+	/*
+	 * NOTE that hd_irq[] reflects IOAPIC input pins (LEGACY_8254
+	 * is wrong for i8259!) not the output IRQ.  Many BIOS writers
+	 * don't bother configuring *any* comparator interrupts.
+	 */
 	hd.hd_irq[0] = HPET_LEGACY_8254;
 	hd.hd_irq[1] = HPET_LEGACY_RTC;
 

arch/x86/kernel/quirks.c

@@ -354,9 +354,27 @@ static void ati_force_hpet_resume(void)
 	printk(KERN_DEBUG "Force enabled HPET at resume\n");
 }
 
+static u32 ati_ixp4x0_rev(struct pci_dev *dev)
+{
+	u32 d;
+	u8  b;
+
+	pci_read_config_byte(dev, 0xac, &b);
+	b &= ~(1<<5);
+	pci_write_config_byte(dev, 0xac, b);
+	pci_read_config_dword(dev, 0x70, &d);
+	d |= 1<<8;
+	pci_write_config_dword(dev, 0x70, d);
+	pci_read_config_dword(dev, 0x8, &d);
+	d &= 0xff;
+	dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d);
+	return d;
+}
+
 static void ati_force_enable_hpet(struct pci_dev *dev)
 {
-	u32 uninitialized_var(val);
+	u32 d, val;
+	u8  b;
 
 	if (hpet_address || force_hpet_address)
 		return;
@@ -366,14 +384,33 @@ static void ati_force_enable_hpet(struct pci_dev *dev)
 		return;
 	}
 
+	d = ati_ixp4x0_rev(dev);
+	if (d  < 0x82)
+		return;
+
+	/* base address */
 	pci_write_config_dword(dev, 0x14, 0xfed00000);
 	pci_read_config_dword(dev, 0x14, &val);
+
+	/* enable interrupt */
+	outb(0x72, 0xcd6); b = inb(0xcd7);
+	b |= 0x1;
+	outb(0x72, 0xcd6); outb(b, 0xcd7);
+	outb(0x72, 0xcd6); b = inb(0xcd7);
+	if (!(b & 0x1))
+		return;
+	pci_read_config_dword(dev, 0x64, &d);
+	d |= (1<<10);
+	pci_write_config_dword(dev, 0x64, d);
+	pci_read_config_dword(dev, 0x64, &d);
+	if (!(d & (1<<10)))
+		return;
+
 	force_hpet_address = val;
 	force_hpet_resume_type = ATI_FORCE_HPET_RESUME;
 	dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n",
 		   force_hpet_address);
 	cached_dev = dev;
-	return;
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS,
 			 ati_force_enable_hpet);

arch/x86/oprofile/Makefile

@@ -7,6 +7,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		timer_int.o )
 
 oprofile-y				:= $(DRIVER_OBJS) init.o backtrace.o
-oprofile-$(CONFIG_X86_LOCAL_APIC) 	+= nmi_int.o op_model_athlon.o \
+oprofile-$(CONFIG_X86_LOCAL_APIC) 	+= nmi_int.o op_model_amd.o \
 					   op_model_ppro.o op_model_p4.o
 oprofile-$(CONFIG_X86_IO_APIC)		+= nmi_timer_int.o

arch/x86/oprofile/nmi_int.c

@@ -1,10 +1,11 @@
 /**
  * @file nmi_int.c
  *
- * @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2002-2008 OProfile authors
  * @remark Read the file COPYING
  *
  * @author John Levon <[email protected]>
+ * @author Robert Richter <[email protected]>
  */
 
 #include <linux/init.h>
@@ -439,6 +440,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	__u8 vendor = boot_cpu_data.x86_vendor;
 	__u8 family = boot_cpu_data.x86;
 	char *cpu_type;
+	int ret = 0;
 
 	if (!cpu_has_apic)
 		return -ENODEV;
@@ -451,19 +453,23 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		default:
 			return -ENODEV;
 		case 6:
-			model = &op_athlon_spec;
+			model = &op_amd_spec;
 			cpu_type = "i386/athlon";
 			break;
 		case 0xf:
-			model = &op_athlon_spec;
+			model = &op_amd_spec;
 			/* Actually it could be i386/hammer too, but give
 			 user space an consistent name. */
 			cpu_type = "x86-64/hammer";
 			break;
 		case 0x10:
-			model = &op_athlon_spec;
+			model = &op_amd_spec;
 			cpu_type = "x86-64/family10";
 			break;
+		case 0x11:
+			model = &op_amd_spec;
+			cpu_type = "x86-64/family11h";
+			break;
 		}
 		break;
 
@@ -490,17 +496,24 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		return -ENODEV;
 	}
 
-	init_sysfs();
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&oprofile_cpu_nb);
 #endif
-	using_nmi = 1;
+	/* default values, can be overwritten by model */
 	ops->create_files = nmi_create_files;
 	ops->setup = nmi_setup;
 	ops->shutdown = nmi_shutdown;
 	ops->start = nmi_start;
 	ops->stop = nmi_stop;
 	ops->cpu_type = cpu_type;
+
+	if (model->init)
+		ret = model->init(ops);
+	if (ret)
+		return ret;
+
+	init_sysfs();
+	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
 }
@@ -513,4 +526,6 @@ void op_nmi_exit(void)
 		unregister_cpu_notifier(&oprofile_cpu_nb);
 #endif
 	}
+	if (model->exit)
+		model->exit();
 }