aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/include
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@samba.org>2009-04-29 08:38:51 -0400
committerIngo Molnar <mingo@elte.hu>2009-04-29 08:58:35 -0400
commitab7ef2e50a557af92f4f90689f51fadadafc16b2 (patch)
tree71ef1cbc279e5d2ad96b6c701617ac60ff36c363 /arch/powerpc/include
parent98144511427c192e4249ff66a3f9debc55c59411 (diff)
perf_counter: powerpc: allow use of limited-function counters
POWER5+ and POWER6 have two hardware counters with limited functionality: PMC5 counts instructions completed in run state and PMC6 counts cycles in run state. (Run state is the state when a hardware RUN bit is 1; the idle task clears RUN while waiting for work to do and sets it when there is work to do.) These counters can't be written to by the kernel, can't generate interrupts, and don't obey the freeze conditions. That means we can only use them for per-task counters (where we know we'll always be in run state; we can't put a per-task counter on an idle task), and only if we don't want interrupts and we do want to count in all processor modes. Obviously some counters can't go on a limited hardware counter, but there are also situations where we can only put a counter on a limited hardware counter - if there are already counters on that exclude some processor modes and we want to put on a per-task cycle or instruction counter that doesn't exclude any processor mode, it could go on if it can use a limited hardware counter. To keep track of these constraints, this adds a flags argument to the processor-specific get_alternatives() functions, with three bits defined: one to say that we can accept alternative event codes that go on limited counters, one to say we only want alternatives on limited counters, and one to say that this is a per-task counter and therefore events that are gated by run state are equivalent to those that aren't (e.g. a "cycles" event is equivalent to a "cycles in run state" event). These flags are computed for each counter and stored in the counter->hw.counter_base field (slightly wonky name for what it does, but it was an existing unused field). Since the limited counters don't freeze when we freeze the other counters, we need some special handling to avoid getting skew between things counted on the limited counters and those counted on normal counters. To minimize this skew, if we are using any limited counters, we read PMC5 and PMC6 immediately after setting and clearing the freeze bit. This is done in a single asm in the new write_mmcr0() function. The code here is specific to PMC5 and PMC6 being the limited hardware counters. Being more general (e.g. having a bitmap of limited hardware counter numbers) would have meant more complex code to read the limited counters when freezing and unfreezing the normal counters, with conditional branches, which would have increased the skew. Since it isn't necessary for the code to be more general at this stage, it isn't. This also extends the back-ends for POWER5+ and POWER6 to be able to handle up to 6 counters rather than the 4 they previously handled. Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <18936.19035.163066.892208@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/powerpc/include')
-rw-r--r--arch/powerpc/include/asm/perf_counter.h13
1 files changed, 12 insertions, 1 deletions
diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h
index 9d7ff6d7fb56..56d66c38143b 100644
--- a/arch/powerpc/include/asm/perf_counter.h
+++ b/arch/powerpc/include/asm/perf_counter.h
@@ -12,6 +12,7 @@
12 12
13#define MAX_HWCOUNTERS 8 13#define MAX_HWCOUNTERS 8
14#define MAX_EVENT_ALTERNATIVES 8 14#define MAX_EVENT_ALTERNATIVES 8
15#define MAX_LIMITED_HWCOUNTERS 2
15 16
16/* 17/*
17 * This struct provides the constants and functions needed to 18 * This struct provides the constants and functions needed to
@@ -25,8 +26,11 @@ struct power_pmu {
25 int (*compute_mmcr)(unsigned int events[], int n_ev, 26 int (*compute_mmcr)(unsigned int events[], int n_ev,
26 unsigned int hwc[], u64 mmcr[]); 27 unsigned int hwc[], u64 mmcr[]);
27 int (*get_constraint)(unsigned int event, u64 *mskp, u64 *valp); 28 int (*get_constraint)(unsigned int event, u64 *mskp, u64 *valp);
28 int (*get_alternatives)(unsigned int event, unsigned int alt[]); 29 int (*get_alternatives)(unsigned int event, unsigned int flags,
30 unsigned int alt[]);
29 void (*disable_pmc)(unsigned int pmc, u64 mmcr[]); 31 void (*disable_pmc)(unsigned int pmc, u64 mmcr[]);
32 int (*limited_pmc_event)(unsigned int event);
33 int limited_pmc5_6; /* PMC5 and PMC6 have limited function */
30 int n_generic; 34 int n_generic;
31 int *generic_events; 35 int *generic_events;
32}; 36};
@@ -34,6 +38,13 @@ struct power_pmu {
34extern struct power_pmu *ppmu; 38extern struct power_pmu *ppmu;
35 39
36/* 40/*
41 * Values for flags to get_alternatives()
42 */
43#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */
44#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */
45#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */
46
47/*
37 * The power_pmu.get_constraint function returns a 64-bit value and 48 * The power_pmu.get_constraint function returns a 64-bit value and
38 * a 64-bit mask that express the constraints between this event and 49 * a 64-bit mask that express the constraints between this event and
39 * other events. 50 * other events.