powerpc/perf_counter: Add support for PPC970 family

This adds the back-end for the PMU on the PPC970 family.

The PPC970 allows events from the ISU to be selected in two different
ways.  Rather than use alternative event codes to express this, we
instead use a single encoding for ISU events and express the
resulting constraint (that you can't select events from all three
of FPU/IFU/VPU, ISU and IDU/STS at the same time, since they all come
in through only 2 multiplexers) using a NAND constraint field, and
work out which multiplexer is used for ISU events at compute_mmcr
time.

Signed-off-by: Paul Mackerras <paulus@samba.org>

3 files changed, 389 insertions, 1 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index fde190bbb2bd..45798f6fb137 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -94,7 +94,7 @@ obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)           += compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
-obj-$(CONFIG_PERF_COUNTERS)     += perf_counter.o
+obj-$(CONFIG_PERF_COUNTERS)     += perf_counter.o ppc970-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index c7d4c2966a5c..5561ecb02a4b 100644
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -741,13 +741,26 @@ static void perf_counter_interrupt(struct pt_regs *regs)
         }
 }
 
+extern struct power_pmu ppc970_pmu;
+
 static int init_perf_counters(void)
 {
+        unsigned long pvr;
+
         if (reserve_pmc_hardware(perf_counter_interrupt)) {
                 printk(KERN_ERR "Couldn't init performance monitor subsystem\n");
                 return -EBUSY;
         }
 
+        /* XXX should get this from cputable */
+        pvr = mfspr(SPRN_PVR);
+        switch (PVR_VER(pvr)) {
+        case PV_970:
+        case PV_970FX:
+        case PV_970MP:
+                ppmu = &ppc970_pmu;
+                break;
+        }
         return 0;
 }
 
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
new file mode 100644
index 000000000000..c3256580be1a
--- /dev/null
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -0,0 +1,375 @@
+/*
+ * Performance counter support for PPC970-family processors.
+ *
+ * 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/string.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for PPC970
+ */
+#define PM_PMC_SH       12      /* PMC number (1-based) for direct events */
+#define PM_PMC_MSK      0xf
+#define PM_UNIT_SH      8       /* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK     0xf
+#define PM_BYTE_SH      4       /* Byte number of event bus to use */
+#define PM_BYTE_MSK     3
+#define PM_PMCSEL_MSK   0xf
+
+/* Values in PM_UNIT field */
+#define PM_NONE         0
+#define PM_FPU          1
+#define PM_VPU          2
+#define PM_ISU          3
+#define PM_IFU          4
+#define PM_IDU          5
+#define PM_STS          6
+#define PM_LSU0         7
+#define PM_LSU1U        8
+#define PM_LSU1L        9
+#define PM_LASTUNIT     9
+
+/*
+ * Bits in MMCR0 for PPC970
+ */
+#define MMCR0_PMC1SEL_SH        8
+#define MMCR0_PMC2SEL_SH        1
+#define MMCR_PMCSEL_MSK         0x1f
+
+/*
+ * Bits in MMCR1 for PPC970
+ */
+#define MMCR1_TTM0SEL_SH        62
+#define MMCR1_TTM1SEL_SH        59
+#define MMCR1_TTM3SEL_SH        53
+#define MMCR1_TTMSEL_MSK        3
+#define MMCR1_TD_CP_DBG0SEL_SH  50
+#define MMCR1_TD_CP_DBG1SEL_SH  48
+#define MMCR1_TD_CP_DBG2SEL_SH  46
+#define MMCR1_TD_CP_DBG3SEL_SH  44
+#define MMCR1_PMC1_ADDER_SEL_SH 39
+#define MMCR1_PMC2_ADDER_SEL_SH 38
+#define MMCR1_PMC6_ADDER_SEL_SH 37
+#define MMCR1_PMC5_ADDER_SEL_SH 36
+#define MMCR1_PMC8_ADDER_SEL_SH 35
+#define MMCR1_PMC7_ADDER_SEL_SH 34
+#define MMCR1_PMC3_ADDER_SEL_SH 33
+#define MMCR1_PMC4_ADDER_SEL_SH 32
+#define MMCR1_PMC3SEL_SH        27
+#define MMCR1_PMC4SEL_SH        22
+#define MMCR1_PMC5SEL_SH        17
+#define MMCR1_PMC6SEL_SH        12
+#define MMCR1_PMC7SEL_SH        7
+#define MMCR1_PMC8SEL_SH        2
+
+static short mmcr1_adder_bits[8] = {
+        MMCR1_PMC1_ADDER_SEL_SH,
+        MMCR1_PMC2_ADDER_SEL_SH,
+        MMCR1_PMC3_ADDER_SEL_SH,
+        MMCR1_PMC4_ADDER_SEL_SH,
+        MMCR1_PMC5_ADDER_SEL_SH,
+        MMCR1_PMC6_ADDER_SEL_SH,
+        MMCR1_PMC7_ADDER_SEL_SH,
+        MMCR1_PMC8_ADDER_SEL_SH
+};
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *                 <><>[  >[  >[  ><  ><  ><  ><  ><><><><><><><><>
+ *                 T0T1 UC  PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
+ *
+ * T0 - TTM0 constraint
+ *     46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS
+ *     43: UC3 error 0x0800_0000_0000
+ *     42: FPU|IFU|VPU events needed 0x0400_0000_0000
+ *     41: ISU events needed 0x0200_0000_0000
+ *     40: IDU|STS events needed 0x0100_0000_0000
+ *
+ * PS1
+ *     39: PS1 error 0x0080_0000_0000
+ *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
+ *
+ * PS2
+ *     35: PS2 error 0x0008_0000_0000
+ *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
+ *
+ * B0
+ *     28-31: Byte 0 event source 0xf000_0000
+ *            Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
+ *
+ * P1
+ *     15: P1 error 0x8000
+ *     14-15: Count of events needing PMC1
+ *
+ * P2..P8
+ *     0-13: Count of events needing PMC2..PMC8
+ */
+
+/* Masks and values for using events from the various units */
+static u64 unit_cons[PM_LASTUNIT+1][2] = {
+        [PM_FPU] =   { 0xc80000000000ull, 0x040000000000ull },
+        [PM_VPU] =   { 0xc80000000000ull, 0xc40000000000ull },
+        [PM_ISU] =   { 0x080000000000ull, 0x020000000000ull },
+        [PM_IFU] =   { 0xc80000000000ull, 0x840000000000ull },
+        [PM_IDU] =   { 0x380000000000ull, 0x010000000000ull },
+        [PM_STS] =   { 0x380000000000ull, 0x310000000000ull },
+};
+
+static int p970_get_constraint(unsigned int event, u64 *maskp, u64 *valp)
+{
+        int pmc, byte, unit, sh;
+        u64 mask = 0, value = 0;
+        int grp = -1;
+
+        pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+        if (pmc) {
+                if (pmc > 8)
+                        return -1;
+                sh = (pmc - 1) * 2;
+                mask |= 2 << sh;
+                value |= 1 << sh;
+                grp = ((pmc - 1) >> 1) & 1;
+        }
+        unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+        if (unit) {
+                if (unit > PM_LASTUNIT)
+                        return -1;
+                mask |= unit_cons[unit][0];
+                value |= unit_cons[unit][1];
+                byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+                /*
+                 * Bus events on bytes 0 and 2 can be counted
+                 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
+                 */
+                if (!pmc)
+                        grp = byte & 1;
+                /* Set byte lane select field */
+                mask  |= 0xfULL << (28 - 4 * byte);
+                value |= (u64)unit << (28 - 4 * byte);
+        }
+        if (grp == 0) {
+                /* increment PMC1/2/5/6 field */
+                mask  |= 0x8000000000ull;
+                value |= 0x1000000000ull;
+        } else if (grp == 1) {
+                /* increment PMC3/4/7/8 field */
+                mask  |= 0x800000000ull;
+                value |= 0x100000000ull;
+        }
+        *maskp = mask;
+        *valp = value;
+        return 0;
+}
+
+static int p970_get_alternatives(unsigned int event, unsigned int alt[])
+{
+        alt[0] = event;
+
+        /* 2 alternatives for LSU empty */
+        if (event == 0x2002 || event == 0x3002) {
+                alt[1] = event ^ 0x1000;
+                return 2;
+        }
+                
+        return 1;
+}
+
+static int p970_compute_mmcr(unsigned int event[], int n_ev,
+                             unsigned int hwc[], u64 mmcr[])
+{
+        u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+        unsigned int pmc, unit, byte, psel;
+        unsigned int ttm, grp;
+        unsigned int pmc_inuse = 0;
+        unsigned int pmc_grp_use[2];
+        unsigned char busbyte[4];
+        unsigned char unituse[16];
+        unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 };
+        unsigned char ttmuse[2];
+        unsigned char pmcsel[8];
+        int i;
+
+        if (n_ev > 8)
+                return -1;
+
+        /* First pass to count resource use */
+        pmc_grp_use[0] = pmc_grp_use[1] = 0;
+        memset(busbyte, 0, sizeof(busbyte));
+        memset(unituse, 0, sizeof(unituse));
+        for (i = 0; i < n_ev; ++i) {
+                pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+                if (pmc) {
+                        if (pmc_inuse & (1 << (pmc - 1)))
+                                return -1;
+                        pmc_inuse |= 1 << (pmc - 1);
+                        /* count 1/2/5/6 vs 3/4/7/8 use */
+                        ++pmc_grp_use[((pmc - 1) >> 1) & 1];
+                }
+                unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+                byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+                if (unit) {
+                        if (unit > PM_LASTUNIT)
+                                return -1;
+                        if (!pmc)
+                                ++pmc_grp_use[byte & 1];
+                        if (busbyte[byte] && busbyte[byte] != unit)
+                                return -1;
+                        busbyte[byte] = unit;
+                        unituse[unit] = 1;
+                }
+        }
+        if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
+                return -1;
+
+        /*
+         * Assign resources and set multiplexer selects.
+         *
+         * PM_ISU can go either on TTM0 or TTM1, but that's the only
+         * choice we have to deal with.
+         */
+        if (unituse[PM_ISU] &
+            (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU]))
+                unitmap[PM_ISU] = 2 | 4;        /* move ISU to TTM1 */
+        /* Set TTM[01]SEL fields. */
+        ttmuse[0] = ttmuse[1] = 0;
+        for (i = PM_FPU; i <= PM_STS; ++i) {
+                if (!unituse[i])
+                        continue;
+                ttm = unitmap[i];
+                ++ttmuse[(ttm >> 2) & 1];
+                mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH;
+        }
+        /* Check only one unit per TTMx */
+        if (ttmuse[0] > 1 || ttmuse[1] > 1)
+                return -1;
+
+        /* Set byte lane select fields and TTM3SEL. */
+        for (byte = 0; byte < 4; ++byte) {
+                unit = busbyte[byte];
+                if (!unit)
+                        continue;
+                if (unit <= PM_STS)
+                        ttm = (unitmap[unit] >> 2) & 1;
+                else if (unit == PM_LSU0)
+                        ttm = 2;
+                else {
+                        ttm = 3;
+                        if (unit == PM_LSU1L && byte >= 2)
+                                mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+                }
+                mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+        }
+
+        /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+        memset(pmcsel, 0x8, sizeof(pmcsel));    /* 8 means don't count */
+        for (i = 0; i < n_ev; ++i) {
+                pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+                unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+                byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+                psel = event[i] & PM_PMCSEL_MSK;
+                if (!pmc) {
+                        /* Bus event or any-PMC direct event */
+                        if (unit)
+                                psel |= 0x10 | ((byte & 2) << 2);
+                        else
+                                psel |= 8;
+                        for (pmc = 0; pmc < 8; ++pmc) {
+                                if (pmc_inuse & (1 << pmc))
+                                        continue;
+                                grp = (pmc >> 1) & 1;
+                                if (unit) {
+                                        if (grp == (byte & 1))
+                                                break;
+                                } else if (pmc_grp_use[grp] < 4) {
+                                        ++pmc_grp_use[grp];
+                                        break;
+                                }
+                        }
+                        pmc_inuse |= 1 << pmc;
+                } else {
+                        /* Direct event */
+                        --pmc;
+                        if (psel == 0 && (byte & 2))
+                                /* add events on higher-numbered bus */
+                                mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
+                }
+                pmcsel[pmc] = psel;
+                hwc[i] = pmc;
+        }
+        for (pmc = 0; pmc < 2; ++pmc)
+                mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc);
+        for (; pmc < 8; ++pmc)
+                mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+        if (pmc_inuse & 1)
+                mmcr0 |= MMCR0_PMC1CE;
+        if (pmc_inuse & 0xfe)
+                mmcr0 |= MMCR0_PMCjCE;
+
+        mmcra |= 0x2000;        /* mark only one IOP per PPC instruction */
+
+        /* Return MMCRx values */
+        mmcr[0] = mmcr0;
+        mmcr[1] = mmcr1;
+        mmcr[2] = mmcra;
+        return 0;
+}
+
+static void p970_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+        int shift, i;
+
+        if (pmc <= 1) {
+                shift = MMCR0_PMC1SEL_SH - 7 * pmc;
+                i = 0;
+        } else {
+                shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2);
+                i = 1;
+        }
+        /*
+         * Setting the PMCxSEL field to 0x08 disables PMC x.
+         */
+        mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift);
+}
+
+static int ppc970_generic_events[] = {
+        [PERF_COUNT_CPU_CYCLES] = 7,
+        [PERF_COUNT_INSTRUCTIONS] = 1,
+        [PERF_COUNT_CACHE_REFERENCES] = 0x8810,         /* PM_LD_REF_L1 */
+        [PERF_COUNT_CACHE_MISSES] = 0x3810,             /* PM_LD_MISS_L1 */
+        [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x431,       /* PM_BR_ISSUED */
+        [PERF_COUNT_BRANCH_MISSES] = 0x327,             /* PM_GRP_BR_MPRED */
+};
+
+struct power_pmu ppc970_pmu = {
+        .n_counter = 8,
+        .max_alternatives = 2,
+        .add_fields = 0x001100005555ull,
+        .test_adder = 0x013300000000ull,
+        .compute_mmcr = p970_compute_mmcr,
+        .get_constraint = p970_get_constraint,
+        .get_alternatives = p970_get_alternatives,
+        .disable_pmc = p970_disable_pmc,
+        .n_generic = ARRAY_SIZE(ppc970_generic_events),
+        .generic_events = ppc970_generic_events,
+};