---

yaml
---
r: 147761
b: refs/heads/master
c: 3bb66d7
h: refs/heads/master
i:
  147759: 38654aa
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: a092ee20fd33d2df0990dcbf2235afc181612818
+refs/heads/master: 3bb66d7f8cc31537a3170c9bb82b38e538b984c5

trunk/Documentation/kernel-parameters.txt

@@ -1083,6 +1083,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
+	kmemleak=	[KNL] Boot-time kmemleak enable/disable
+			Valid arguments: on, off
+			Default: on
+
 	kstack=N	[X86] Print N words from the kernel stack
 			in oops dumps.
 

trunk/Documentation/kmemleak.txt

@@ -0,0 +1,142 @@
+Kernel Memory Leak Detector
+===========================
+
+Introduction
+------------
+
+Kmemleak provides a way of detecting possible kernel memory leaks in a
+way similar to a tracing garbage collector
+(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+with the difference that the orphan objects are not freed but only
+reported via /sys/kernel/debug/kmemleak. A similar method is used by the
+Valgrind tool (memcheck --leak-check) to detect the memory leaks in
+user-space applications.
+
+Usage
+-----
+
+CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
+thread scans the memory every 10 minutes (by default) and prints any new
+unreferenced objects found. To trigger an intermediate scan and display
+all the possible memory leaks:
+
+  # mount -t debugfs nodev /sys/kernel/debug/
+  # cat /sys/kernel/debug/kmemleak
+
+Note that the orphan objects are listed in the order they were allocated
+and one object at the beginning of the list may cause other subsequent
+objects to be reported as orphan.
+
+Memory scanning parameters can be modified at run-time by writing to the
+/sys/kernel/debug/kmemleak file. The following parameters are supported:
+
+  off		- disable kmemleak (irreversible)
+  stack=on	- enable the task stacks scanning
+  stack=off	- disable the tasks stacks scanning
+  scan=on	- start the automatic memory scanning thread
+  scan=off	- stop the automatic memory scanning thread
+  scan=<secs>	- set the automatic memory scanning period in seconds (0
+		  to disable it)
+
+Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
+the kernel command line.
+
+Basic Algorithm
+---------------
+
+The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and
+friends are traced and the pointers, together with additional
+information like size and stack trace, are stored in a prio search tree.
+The corresponding freeing function calls are tracked and the pointers
+removed from the kmemleak data structures.
+
+An allocated block of memory is considered orphan if no pointer to its
+start address or to any location inside the block can be found by
+scanning the memory (including saved registers). This means that there
+might be no way for the kernel to pass the address of the allocated
+block to a freeing function and therefore the block is considered a
+memory leak.
+
+The scanning algorithm steps:
+
+  1. mark all objects as white (remaining white objects will later be
+     considered orphan)
+  2. scan the memory starting with the data section and stacks, checking
+     the values against the addresses stored in the prio search tree. If
+     a pointer to a white object is found, the object is added to the
+     gray list
+  3. scan the gray objects for matching addresses (some white objects
+     can become gray and added at the end of the gray list) until the
+     gray set is finished
+  4. the remaining white objects are considered orphan and reported via
+     /sys/kernel/debug/kmemleak
+
+Some allocated memory blocks have pointers stored in the kernel's
+internal data structures and they cannot be detected as orphans. To
+avoid this, kmemleak can also store the number of values pointing to an
+address inside the block address range that need to be found so that the
+block is not considered a leak. One example is __vmalloc().
+
+Kmemleak API
+------------
+
+See the include/linux/kmemleak.h header for the functions prototype.
+
+kmemleak_init		 - initialize kmemleak
+kmemleak_alloc		 - notify of a memory block allocation
+kmemleak_free		 - notify of a memory block freeing
+kmemleak_not_leak	 - mark an object as not a leak
+kmemleak_ignore		 - do not scan or report an object as leak
+kmemleak_scan_area	 - add scan areas inside a memory block
+kmemleak_no_scan	 - do not scan a memory block
+kmemleak_erase		 - erase an old value in a pointer variable
+kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness
+kmemleak_free_recursive	 - as kmemleak_free but checks the recursiveness
+
+Dealing with false positives/negatives
+--------------------------------------
+
+The false negatives are real memory leaks (orphan objects) but not
+reported by kmemleak because values found during the memory scanning
+point to such objects. To reduce the number of false negatives, kmemleak
+provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and
+kmemleak_erase functions (see above). The task stacks also increase the
+amount of false negatives and their scanning is not enabled by default.
+
+The false positives are objects wrongly reported as being memory leaks
+(orphan). For objects known not to be leaks, kmemleak provides the
+kmemleak_not_leak function. The kmemleak_ignore could also be used if
+the memory block is known not to contain other pointers and it will no
+longer be scanned.
+
+Some of the reported leaks are only transient, especially on SMP
+systems, because of pointers temporarily stored in CPU registers or
+stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing
+the minimum age of an object to be reported as a memory leak.
+
+Limitations and Drawbacks
+-------------------------
+
+The main drawback is the reduced performance of memory allocation and
+freeing. To avoid other penalties, the memory scanning is only performed
+when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is
+intended for debugging purposes where the performance might not be the
+most important requirement.
+
+To keep the algorithm simple, kmemleak scans for values pointing to any
+address inside a block's address range. This may lead to an increased
+number of false negatives. However, it is likely that a real memory leak
+will eventually become visible.
+
+Another source of false negatives is the data stored in non-pointer
+values. In a future version, kmemleak could only scan the pointer
+members in the allocated structures. This feature would solve many of
+the false negative cases described above.
+
+The tool can report false positives. These are cases where an allocated
+block doesn't need to be freed (some cases in the init_call functions),
+the pointer is calculated by other methods than the usual container_of
+macro or the pointer is stored in a location not scanned by kmemleak.
+
+Page allocations and ioremap are not tracked. Only the ARM and x86
+architectures are currently supported.

trunk/MAINTAINERS

@@ -3372,6 +3372,12 @@ F:	Documentation/trace/kmemtrace.txt
 F:	include/trace/kmemtrace.h
 F:	kernel/trace/kmemtrace.c
 
+KMEMLEAK
+P:	Catalin Marinas
+M:	catalin.marinas@arm.com
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+
 KPROBES
 P:	Ananth N Mavinakayanahalli
 M:	ananth@in.ibm.com
@@ -4405,6 +4411,16 @@ S:	Maintained
 F:	include/linux/delayacct.h
 F:	kernel/delayacct.c
 
+PERFORMANCE COUNTER SUBSYSTEM
+P:	Peter Zijlstra
+M:	a.p.zijlstra@chello.nl
+P:	Paul Mackerras
+M:	paulus@samba.org
+P:	Ingo Molnar
+M:	mingo@elte.hu
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+
 PERSONALITY HANDLING
 P:	Christoph Hellwig
 M:	hch@infradead.org

trunk/arch/powerpc/include/asm/hw_irq.h

@@ -131,5 +131,44 @@ static inline int irqs_disabled_flags(unsigned long flags)
  */
 struct irq_chip;
 
+#ifdef CONFIG_PERF_COUNTERS
+static inline unsigned long test_perf_counter_pending(void)
+{
+	unsigned long x;
+
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, perf_counter_pending)));
+	return x;
+}
+
+static inline void set_perf_counter_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (1),
+		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+}
+
+static inline void clear_perf_counter_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (0),
+		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+}
+
+extern void perf_counter_do_pending(void);
+
+#else
+
+static inline unsigned long test_perf_counter_pending(void)
+{
+	return 0;
+}
+
+static inline void set_perf_counter_pending(void) {}
+static inline void clear_perf_counter_pending(void) {}
+static inline void perf_counter_do_pending(void) {}
+#endif /* CONFIG_PERF_COUNTERS */
+
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_HW_IRQ_H */

trunk/arch/powerpc/include/asm/paca.h

@@ -99,6 +99,7 @@ struct paca_struct {
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
+	u8 perf_counter_pending;	/* PM interrupt while soft-disabled */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */

trunk/arch/powerpc/include/asm/perf_counter.h

@@ -0,0 +1,98 @@
+/*
+ * Performance counter support - PowerPC-specific definitions.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/types.h>
+
+#define MAX_HWCOUNTERS		8
+#define MAX_EVENT_ALTERNATIVES	8
+#define MAX_LIMITED_HWCOUNTERS	2
+
+/*
+ * This struct provides the constants and functions needed to
+ * describe the PMU on a particular POWER-family CPU.
+ */
+struct power_pmu {
+	int	n_counter;
+	int	max_alternatives;
+	u64	add_fields;
+	u64	test_adder;
+	int	(*compute_mmcr)(u64 events[], int n_ev,
+				unsigned int hwc[], u64 mmcr[]);
+	int	(*get_constraint)(u64 event, u64 *mskp, u64 *valp);
+	int	(*get_alternatives)(u64 event, unsigned int flags,
+				    u64 alt[]);
+	void	(*disable_pmc)(unsigned int pmc, u64 mmcr[]);
+	int	(*limited_pmc_event)(u64 event);
+	u32	flags;
+	int	n_generic;
+	int	*generic_events;
+	int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+			       [PERF_COUNT_HW_CACHE_OP_MAX]
+			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+extern struct power_pmu *ppmu;
+
+/*
+ * Values for power_pmu.flags
+ */
+#define PPMU_LIMITED_PMC5_6	1	/* PMC5/6 have limited function */
+#define PPMU_ALT_SIPR		2	/* uses alternate posn for SIPR/HV */
+
+/*
+ * Values for flags to get_alternatives()
+ */
+#define PPMU_LIMITED_PMC_OK	1	/* can put this on a limited PMC */
+#define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
+#define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
+
+struct pt_regs;
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+
+/*
+ * The power_pmu.get_constraint function returns a 64-bit value and
+ * a 64-bit mask that express the constraints between this event and
+ * other events.
+ *
+ * The value and mask are divided up into (non-overlapping) bitfields
+ * of three different types:
+ *
+ * Select field: this expresses the constraint that some set of bits
+ * in MMCR* needs to be set to a specific value for this event.  For a
+ * select field, the mask contains 1s in every bit of the field, and
+ * the value contains a unique value for each possible setting of the
+ * MMCR* bits.  The constraint checking code will ensure that two events
+ * that set the same field in their masks have the same value in their
+ * value dwords.
+ *
+ * Add field: this expresses the constraint that there can be at most
+ * N events in a particular class.  A field of k bits can be used for
+ * N <= 2^(k-1) - 1.  The mask has the most significant bit of the field
+ * set (and the other bits 0), and the value has only the least significant
+ * bit of the field set.  In addition, the 'add_fields' and 'test_adder'
+ * in the struct power_pmu for this processor come into play.  The
+ * add_fields value contains 1 in the LSB of the field, and the
+ * test_adder contains 2^(k-1) - 1 - N in the field.
+ *
+ * NAND field: this expresses the constraint that you may not have events
+ * in all of a set of classes.  (For example, on PPC970, you can't select
+ * events from the FPU, ISU and IDU simultaneously, although any two are
+ * possible.)  For N classes, the field is N+1 bits wide, and each class
+ * is assigned one bit from the least-significant N bits.  The mask has
+ * only the most-significant bit set, and the value has only the bit
+ * for the event's class set.  The test_adder has the least significant
+ * bit set in the field.
+ *
+ * If an event is not subject to the constraint expressed by a particular
+ * field, then it will have 0 in both the mask and value for that field.
+ */

trunk/arch/powerpc/include/asm/reg.h

@@ -492,11 +492,13 @@
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
+#define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */
 #define   MMCRA_SLOT_SHIFT	24
 #define   MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */
+#define   POWER6_MMCRA_SDSYNC 0x0000080000000000ULL	/* SDAR/SIAR synced */
 #define   POWER6_MMCRA_SIHV   0x0000040000000000ULL
 #define   POWER6_MMCRA_SIPR   0x0000020000000000ULL
 #define   POWER6_MMCRA_THRM	0x00000020UL

trunk/arch/powerpc/include/asm/systbl.h

@@ -322,6 +322,6 @@ SYSCALL_SPU(epoll_create1)
 SYSCALL_SPU(dup3)
 SYSCALL_SPU(pipe2)
 SYSCALL(inotify_init1)
-SYSCALL(ni_syscall)
+SYSCALL_SPU(perf_counter_open)
 COMPAT_SYS_SPU(preadv)
 COMPAT_SYS_SPU(pwritev)

trunk/arch/powerpc/include/asm/unistd.h

@@ -341,6 +341,7 @@
 #define __NR_dup3		316
 #define __NR_pipe2		317
 #define __NR_inotify_init1	318
+#define __NR_perf_counter_open	319
 #define __NR_preadv		320
 #define __NR_pwritev		321
 

trunk/arch/powerpc/kernel/Makefile

@@ -94,6 +94,9 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_PERF_COUNTERS)	+= perf_counter.o power4-pmu.o ppc970-pmu.o \
+				   power5-pmu.o power5+-pmu.o power6-pmu.o \
+				   power7-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 

trunk/arch/powerpc/kernel/asm-offsets.c

@@ -131,6 +131,7 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
+	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
 	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
 	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));