Merge branch 'linux_next' of git://git.kernel.org/pub/scm/linux/kerne…

…l/git/mchehab/i7core

* 'linux_next' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/i7core: (83 commits)
  i7core_edac: Better describe the supported devices
  Add support for Westmere to i7core_edac driver
  i7core_edac: don't free on success
  i7core_edac: Add support for X5670
  Always call i7core_[ur]dimm_check_mc_ecc_err
  i7core_edac: fix memory leak of i7core_dev
  EDAC: add __init to i7core_xeon_pci_fixup
  i7core_edac: Fix wrong device id for channel 1 devices
  i7core: add support for Lynnfield alternate address
  i7core_edac: Add initial support for Lynnfield
  i7core_edac: do not export static functions
  edac: fix i7core build
  edac: i7core_edac produces undefined behaviour on 32bit
  i7core_edac: Use a more generic approach for probing PCI devices
  i7core_edac: PCI device is called NONCORE, instead of NOCORE
  i7core_edac: Fix ringbuffer maxsize
  i7core_edac: First store, then increment
  i7core_edac: Better parse "any" addrmask
  i7core_edac: Use a lockless ringbuffer
  edac: Create an unique instance for each kobj
  ...

Documentation/edac.txt

@@ -6,6 +6,8 @@ Written by Doug Thompson <dougthompson@xmission.com>
 7 Dec 2005
 17 Jul 2007	Updated
 
+(c) Mauro Carvalho Chehab <mchehab@redhat.com>
+05 Aug 2009	Nehalem interface
 
 EDAC is maintained and written by:
 
@@ -717,3 +719,153 @@ unique drivers for their hardware systems.
 The 'test_device_edac' sample driver is located at the
 bluesmoke.sourceforge.net project site for EDAC.
 
+=======================================================================
+NEHALEM USAGE OF EDAC APIs
+
+This chapter documents some EXPERIMENTAL mappings for EDAC API to handle
+Nehalem EDAC driver. They will likely be changed on future versions
+of the driver.
+
+Due to the way Nehalem exports Memory Controller data, some adjustments
+were done at i7core_edac driver. This chapter will cover those differences
+
+1) On Nehalem, there are one Memory Controller per Quick Patch Interconnect
+   (QPI). At the driver, the term "socket" means one QPI. This is
+   associated with a physical CPU socket.
+
+   Each MC have 3 physical read channels, 3 physical write channels and
+   3 logic channels. The driver currenty sees it as just 3 channels.
+   Each channel can have up to 3 DIMMs.
+
+   The minimum known unity is DIMMs. There are no information about csrows.
+   As EDAC API maps the minimum unity is csrows, the driver sequencially
+   maps channel/dimm into different csrows.
+
+   For example, suposing the following layout:
+	Ch0 phy rd0, wr0 (0x063f4031): 2 ranks, UDIMMs
+	  dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400
+	  dimm 1 1024 Mb offset: 4, bank: 8, rank: 1, row: 0x4000, col: 0x400
+        Ch1 phy rd1, wr1 (0x063f4031): 2 ranks, UDIMMs
+	  dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400
+	Ch2 phy rd3, wr3 (0x063f4031): 2 ranks, UDIMMs
+	  dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400
+   The driver will map it as:
+	csrow0: channel 0, dimm0
+	csrow1: channel 0, dimm1
+	csrow2: channel 1, dimm0
+	csrow3: channel 2, dimm0
+
+exports one
+   DIMM per csrow.
+
+   Each QPI is exported as a different memory controller.
+
+2) Nehalem MC has the hability to generate errors. The driver implements this
+   functionality via some error injection nodes:
+
+   For injecting a memory error, there are some sysfs nodes, under
+   /sys/devices/system/edac/mc/mc?/:
+
+   inject_addrmatch/*:
+      Controls the error injection mask register. It is possible to specify
+      several characteristics of the address to match an error code:
+         dimm = the affected dimm. Numbers are relative to a channel;
+         rank = the memory rank;
+         channel = the channel that will generate an error;
+         bank = the affected bank;
+         page = the page address;
+         column (or col) = the address column.
+      each of the above values can be set to "any" to match any valid value.
+
+      At driver init, all values are set to any.
+
+      For example, to generate an error at rank 1 of dimm 2, for any channel,
+      any bank, any page, any column:
+		echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm
+		echo 1 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank
+
+	To return to the default behaviour of matching any, you can do:
+		echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm
+		echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank
+
+   inject_eccmask:
+       specifies what bits will have troubles,
+
+   inject_section:
+       specifies what ECC cache section will get the error:
+		3 for both
+		2 for the highest
+		1 for the lowest
+
+   inject_type:
+       specifies the type of error, being a combination of the following bits:
+		bit 0 - repeat
+		bit 1 - ecc
+		bit 2 - parity
+
+       inject_enable starts the error generation when something different
+       than 0 is written.
+
+   All inject vars can be read. root permission is needed for write.
+
+   Datasheet states that the error will only be generated after a write on an
+   address that matches inject_addrmatch. It seems, however, that reading will
+   also produce an error.
+
+   For example, the following code will generate an error for any write access
+   at socket 0, on any DIMM/address on channel 2:
+
+   echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/channel
+   echo 2 >/sys/devices/system/edac/mc/mc0/inject_type
+   echo 64 >/sys/devices/system/edac/mc/mc0/inject_eccmask
+   echo 3 >/sys/devices/system/edac/mc/mc0/inject_section
+   echo 1 >/sys/devices/system/edac/mc/mc0/inject_enable
+   dd if=/dev/mem of=/dev/null seek=16k bs=4k count=1 >& /dev/null
+
+   For socket 1, it is needed to replace "mc0" by "mc1" at the above
+   commands.
+
+   The generated error message will look like:
+
+   EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error))
+
+3) Nehalem specific Corrected Error memory counters
+
+   Nehalem have some registers to count memory errors. The driver uses those
+   registers to report Corrected Errors on devices with Registered Dimms.
+
+   However, those counters don't work with Unregistered Dimms. As the chipset
+   offers some counters that also work with UDIMMS (but with a worse level of
+   granularity than the default ones), the driver exposes those registers for
+   UDIMM memories.
+
+   They can be read by looking at the contents of all_channel_counts/
+
+   $ for i in /sys/devices/system/edac/mc/mc0/all_channel_counts/*; do echo $i; cat $i; done
+	/sys/devices/system/edac/mc/mc0/all_channel_counts/udimm0
+	0
+	/sys/devices/system/edac/mc/mc0/all_channel_counts/udimm1
+	0
+	/sys/devices/system/edac/mc/mc0/all_channel_counts/udimm2
+	0
+
+   What happens here is that errors on different csrows, but at the same
+   dimm number will increment the same counter.
+   So, in this memory mapping:
+	csrow0: channel 0, dimm0
+	csrow1: channel 0, dimm1
+	csrow2: channel 1, dimm0
+	csrow3: channel 2, dimm0
+   The hardware will increment udimm0 for an error at the first dimm at either
+	csrow0, csrow2  or csrow3;
+   The hardware will increment udimm1 for an error at the second dimm at either
+	csrow0, csrow2  or csrow3;
+   The hardware will increment udimm2 for an error at the third dimm at either
+	csrow0, csrow2  or csrow3;
+
+4) Standard error counters
+
+   The standard error counters are generated when an mcelog error is received
+   by the driver. Since, with udimm, this is counted by software, it is
+   possible that some errors could be lost. With rdimm's, they displays the
+   contents of the registers

arch/x86/include/asm/pci_x86.h

@@ -53,6 +53,8 @@ extern int pcibios_last_bus;
 extern struct pci_bus *pci_root_bus;
 extern struct pci_ops pci_root_ops;
 
+void pcibios_scan_specific_bus(int busn);
+
 /* pci-irq.c */
 
 struct irq_info {

arch/x86/kernel/cpu/mcheck/mce.c

@@ -36,6 +36,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/edac_mce.h>
 
 #include <asm/processor.h>
 #include <asm/hw_irq.h>
@@ -168,6 +169,15 @@ void mce_log(struct mce *mce)
 	for (;;) {
 		entry = rcu_dereference_check_mce(mcelog.next);
 		for (;;) {
+			/*
+			 * If edac_mce is enabled, it will check the error type
+			 * and will process it, if it is a known error.
+			 * Otherwise, the error will be sent through mcelog
+			 * interface
+			 */
+			if (edac_mce_parse(mce))
+				return;
+
 			/*
 			 * When the buffer fills up discard new entries.
 			 * Assume that the earlier errors are the more

arch/x86/pci/legacy.c

@@ -11,28 +11,14 @@
  */
 static void __devinit pcibios_fixup_peer_bridges(void)
 {
-	int n, devfn;
-	long node;
+	int n;
 
 	if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff)
 		return;
 	DBG("PCI: Peer bridge fixup\n");
 
-	for (n=0; n <= pcibios_last_bus; n++) {
-		u32 l;
-		if (pci_find_bus(0, n))
-			continue;
-		node = get_mp_bus_to_node(n);
-		for (devfn = 0; devfn < 256; devfn += 8) {
-			if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
-			    l != 0x0000 && l != 0xffff) {
-				DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
-				printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
-				pci_scan_bus_on_node(n, &pci_root_ops, node);
-				break;
-			}
-		}
-	}
+	for (n=0; n <= pcibios_last_bus; n++)
+		pcibios_scan_specific_bus(n);
 }
 
 int __init pci_legacy_init(void)
@@ -50,6 +36,28 @@ int __init pci_legacy_init(void)
 	return 0;
 }
 
+void pcibios_scan_specific_bus(int busn)
+{
+	int devfn;
+	long node;
+	u32 l;
+
+	if (pci_find_bus(0, busn))
+		return;
+
+	node = get_mp_bus_to_node(busn);
+	for (devfn = 0; devfn < 256; devfn += 8) {
+		if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) &&
+		    l != 0x0000 && l != 0xffff) {
+			DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l);
+			printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn);
+			pci_scan_bus_on_node(busn, &pci_root_ops, node);
+			return;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus);
+
 int __init pci_subsys_init(void)
 {
 	/*

drivers/edac/Kconfig

@@ -69,6 +69,9 @@ config EDAC_MM_EDAC
 	  occurred so that a particular failing memory module can be
 	  replaced.  If unsure, select 'Y'.
 
+config EDAC_MCE
+	bool
+
 config EDAC_AMD64
 	tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
 	depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE
@@ -166,6 +169,16 @@ config EDAC_I5400
 	  Support for error detection and correction the Intel
 	  i5400 MCH chipset (Seaburg).
 
+config EDAC_I7CORE
+	tristate "Intel i7 Core (Nehalem) processors"
+	depends on EDAC_MM_EDAC && PCI && X86
+	select EDAC_MCE
+	help
+	  Support for error detection and correction the Intel
+	  i7 Core (Nehalem) Integrated Memory Controller that exists on
+	  newer processors like i7 Core, i7 Core Extreme, Xeon 35xx
+	  and Xeon 55xx processors.
+
 config EDAC_I82860
 	tristate "Intel 82860"
 	depends on EDAC_MM_EDAC && PCI && X86_32

drivers/edac/Makefile

@@ -8,6 +8,7 @@
 
 obj-$(CONFIG_EDAC)			:= edac_stub.o
 obj-$(CONFIG_EDAC_MM_EDAC)		+= edac_core.o
+obj-$(CONFIG_EDAC_MCE)			+= edac_mce.o
 
 edac_core-objs	:= edac_mc.o edac_device.o edac_mc_sysfs.o edac_pci_sysfs.o
 edac_core-objs	+= edac_module.o edac_device_sysfs.o
@@ -23,6 +24,7 @@ obj-$(CONFIG_EDAC_CPC925)		+= cpc925_edac.o
 obj-$(CONFIG_EDAC_I5000)		+= i5000_edac.o
 obj-$(CONFIG_EDAC_I5100)		+= i5100_edac.o
 obj-$(CONFIG_EDAC_I5400)		+= i5400_edac.o
+obj-$(CONFIG_EDAC_I7CORE)		+= i7core_edac.o
 obj-$(CONFIG_EDAC_E7XXX)		+= e7xxx_edac.o
 obj-$(CONFIG_EDAC_E752X)		+= e752x_edac.o
 obj-$(CONFIG_EDAC_I82443BXGX)		+= i82443bxgx_edac.o

drivers/edac/edac_core.h

@@ -341,12 +341,30 @@ struct csrow_info {
 	struct channel_info *channels;
 };
 
+struct mcidev_sysfs_group {
+	const char *name;				/* group name */
+	struct mcidev_sysfs_attribute *mcidev_attr;	/* group attributes */
+};
+
+struct mcidev_sysfs_group_kobj {
+	struct list_head list;		/* list for all instances within a mc */
+
+	struct kobject kobj;		/* kobj for the group */
+
+	struct mcidev_sysfs_group *grp;	/* group description table */
+	struct mem_ctl_info *mci;	/* the parent */
+};
+
 /* mcidev_sysfs_attribute structure
  *	used for driver sysfs attributes and in mem_ctl_info
  * 	sysfs top level entries
  */
 struct mcidev_sysfs_attribute {
-        struct attribute attr;
+	/* It should use either attr or grp */
+	struct attribute attr;
+	struct mcidev_sysfs_group *grp;	/* Points to a group of attributes */
+
+	/* Ops for show/store values at the attribute - not used on group */
         ssize_t (*show)(struct mem_ctl_info *,char *);
         ssize_t (*store)(struct mem_ctl_info *, const char *,size_t);
 };
@@ -424,6 +442,9 @@ struct mem_ctl_info {
 	/* edac sysfs device control */
 	struct kobject edac_mci_kobj;
 
+	/* list for all grp instances within a mc */
+	struct list_head grp_kobj_list;
+
 	/* Additional top controller level attributes, but specified
 	 * by the low level driver.
 	 *