diff options
Diffstat (limited to 'arch/mips/kernel')
48 files changed, 2452 insertions, 698 deletions
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 80884983270..83bba332bbf 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_CPU_TX39XX) += r2300_fpu.o r2300_switch.o obj-$(CONFIG_CPU_TX49XX) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_VR41XX) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_CAVIUM_OCTEON) += octeon_switch.o +obj-$(CONFIG_CPU_XLR) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SMP_UP) += smp-up.o @@ -95,6 +96,7 @@ obj-$(CONFIG_GPIO_TXX9) += gpio_txx9.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_SPINLOCK_TEST) += spinlock_test.o +obj-$(CONFIG_MIPS_MACHINE) += mips_machine.o obj-$(CONFIG_OF) += prom.o @@ -104,4 +106,8 @@ obj-$(CONFIG_HAVE_STD_PC_SERIAL_PORT) += 8250-platform.o obj-$(CONFIG_MIPS_CPUFREQ) += cpufreq/ +obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o + +obj-$(CONFIG_JUMP_LABEL) += jump_label.o + CPPFLAGS_vmlinux.lds := $(KBUILD_CFLAGS) diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 2f4d7a99bcc..98c5a9737c1 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -32,7 +32,7 @@ static int mips_next_event(unsigned long delta, cnt = read_c0_count(); cnt += delta; write_c0_compare(cnt); - res = ((int)(read_c0_count() - cnt) > 0) ? -ETIME : 0; + res = ((int)(read_c0_count() - cnt) >= 0) ? -ETIME : 0; return res; } diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c index 0b7377361e2..f0ab92a1b05 100644 --- a/arch/mips/kernel/cevt-txx9.c +++ b/arch/mips/kernel/cevt-txx9.c @@ -51,8 +51,7 @@ void __init txx9_clocksource_init(unsigned long baseaddr, { struct txx9_tmr_reg __iomem *tmrptr; - clocksource_set_clock(&txx9_clocksource.cs, TIMER_CLK(imbusclk)); - clocksource_register(&txx9_clocksource.cs); + clocksource_register_hz(&txx9_clocksource.cs, TIMER_CLK(imbusclk)); tmrptr = ioremap(baseaddr, sizeof(struct txx9_tmr_reg)); __raw_writel(TCR_BASE, &tmrptr->tcr); diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index b8bb8ba6086..f305ca14351 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -73,7 +73,7 @@ static inline void mult_sh_align_mod(long *v1, long *v2, long *w, : "0" (5), "1" (8), "2" (5)); align_mod(align, mod); /* - * The trailing nop is needed to fullfill the two-instruction + * The trailing nop is needed to fulfill the two-instruction * requirement between reading hi/lo and staring a mult/div. * Leaving it out may cause gas insert a nop itself breaking * the desired alignment of the next chunk. diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index b1b304ea212..bb133d10b14 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -25,6 +25,8 @@ #include <asm/system.h> #include <asm/watch.h> #include <asm/spram.h> +#include <asm/uaccess.h> + /* * Not all of the MIPS CPUs have the "wait" instruction available. Moreover, * the implementation of the "wait" feature differs between CPU families. This @@ -181,12 +183,13 @@ void __init check_wait(void) case CPU_5KC: case CPU_25KF: case CPU_PR4450: - case CPU_BCM3302: - case CPU_BCM6338: - case CPU_BCM6348: - case CPU_BCM6358: + case CPU_BMIPS3300: + case CPU_BMIPS4350: + case CPU_BMIPS4380: + case CPU_BMIPS5000: case CPU_CAVIUM_OCTEON: case CPU_CAVIUM_OCTEON_PLUS: + case CPU_CAVIUM_OCTEON2: case CPU_JZRISC: cpu_wait = r4k_wait; break; @@ -288,6 +291,12 @@ static inline int cpu_has_confreg(void) #endif } +static inline void set_elf_platform(int cpu, const char *plat) +{ + if (cpu == 0) + __elf_platform = plat; +} + /* * Get the FPU Implementation/Revision. */ @@ -611,6 +620,16 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) case PRID_IMP_LOONGSON2: c->cputype = CPU_LOONGSON2; __cpu_name[cpu] = "ICT Loongson-2"; + + switch (c->processor_id & PRID_REV_MASK) { + case PRID_REV_LOONGSON2E: + set_elf_platform(cpu, "loongson2e"); + break; + case PRID_REV_LOONGSON2F: + set_elf_platform(cpu, "loongson2f"); + break; + } + c->isa_level = MIPS_CPU_ISA_III; c->options = R4K_OPTS | MIPS_CPU_FPU | MIPS_CPU_LLSC | @@ -736,6 +755,8 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c) && cpu_has_tlb) c->tlbsize += (config4 & MIPS_CONF4_MMUSIZEEXT) * 0x40; + c->kscratch_mask = (config4 >> 16) & 0xff; + return config4 & MIPS_CONF_M; } @@ -902,35 +923,41 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu) { decode_configs(c); switch (c->processor_id & 0xff00) { - case PRID_IMP_BCM3302: - /* same as PRID_IMP_BCM6338 */ - c->cputype = CPU_BCM3302; - __cpu_name[cpu] = "Broadcom BCM3302"; - break; - case PRID_IMP_BCM4710: - c->cputype = CPU_BCM4710; - __cpu_name[cpu] = "Broadcom BCM4710"; - break; - case PRID_IMP_BCM6345: - c->cputype = CPU_BCM6345; - __cpu_name[cpu] = "Broadcom BCM6345"; - break; - case PRID_IMP_BCM6348: - c->cputype = CPU_BCM6348; - __cpu_name[cpu] = "Broadcom BCM6348"; - break; - case PRID_IMP_BCM4350: - switch (c->processor_id & 0xf0) { - case PRID_REV_BCM6358: - c->cputype = CPU_BCM6358; - __cpu_name[cpu] = "Broadcom BCM6358"; - break; - default: - c->cputype = CPU_UNKNOWN; - break; + case PRID_IMP_BMIPS32_REV4: + case PRID_IMP_BMIPS32_REV8: + c->cputype = CPU_BMIPS32; + __cpu_name[cpu] = "Broadcom BMIPS32"; + set_elf_platform(cpu, "bmips32"); + break; + case PRID_IMP_BMIPS3300: + case PRID_IMP_BMIPS3300_ALT: + case PRID_IMP_BMIPS3300_BUG: + c->cputype = CPU_BMIPS3300; + __cpu_name[cpu] = "Broadcom BMIPS3300"; + set_elf_platform(cpu, "bmips3300"); + break; + case PRID_IMP_BMIPS43XX: { + int rev = c->processor_id & 0xff; + + if (rev >= PRID_REV_BMIPS4380_LO && + rev <= PRID_REV_BMIPS4380_HI) { + c->cputype = CPU_BMIPS4380; + __cpu_name[cpu] = "Broadcom BMIPS4380"; + set_elf_platform(cpu, "bmips4380"); + } else { + c->cputype = CPU_BMIPS4350; + __cpu_name[cpu] = "Broadcom BMIPS4350"; + set_elf_platform(cpu, "bmips4350"); } break; } + case PRID_IMP_BMIPS5000: + c->cputype = CPU_BMIPS5000; + __cpu_name[cpu] = "Broadcom BMIPS5000"; + set_elf_platform(cpu, "bmips5000"); + c->options |= MIPS_CPU_ULRI; + break; + } } static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu) @@ -950,8 +977,12 @@ static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_CAVIUM_OCTEON_PLUS; __cpu_name[cpu] = "Cavium Octeon+"; platform: - if (cpu == 0) - __elf_platform = "octeon"; + set_elf_platform(cpu, "octeon"); + break; + case PRID_IMP_CAVIUM_CN63XX: + c->cputype = CPU_CAVIUM_OCTEON2; + __cpu_name[cpu] = "Cavium Octeon II"; + set_elf_platform(cpu, "octeon2"); break; default: printk(KERN_INFO "Unknown Octeon chip!\n"); @@ -976,6 +1007,65 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) } } +static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu) +{ + decode_configs(c); + + c->options = (MIPS_CPU_TLB | + MIPS_CPU_4KEX | + MIPS_CPU_COUNTER | + MIPS_CPU_DIVEC | + MIPS_CPU_WATCH | + MIPS_CPU_EJTAG | + MIPS_CPU_LLSC); + + switch (c->processor_id & 0xff00) { + case PRID_IMP_NETLOGIC_XLR732: + case PRID_IMP_NETLOGIC_XLR716: + case PRID_IMP_NETLOGIC_XLR532: + case PRID_IMP_NETLOGIC_XLR308: + case PRID_IMP_NETLOGIC_XLR532C: + case PRID_IMP_NETLOGIC_XLR516C: + case PRID_IMP_NETLOGIC_XLR508C: + case PRID_IMP_NETLOGIC_XLR308C: + c->cputype = CPU_XLR; + __cpu_name[cpu] = "Netlogic XLR"; + break; + + case PRID_IMP_NETLOGIC_XLS608: + case PRID_IMP_NETLOGIC_XLS408: + case PRID_IMP_NETLOGIC_XLS404: + case PRID_IMP_NETLOGIC_XLS208: + case PRID_IMP_NETLOGIC_XLS204: + case PRID_IMP_NETLOGIC_XLS108: + case PRID_IMP_NETLOGIC_XLS104: + case PRID_IMP_NETLOGIC_XLS616B: + case PRID_IMP_NETLOGIC_XLS608B: + case PRID_IMP_NETLOGIC_XLS416B: + case PRID_IMP_NETLOGIC_XLS412B: + case PRID_IMP_NETLOGIC_XLS408B: + case PRID_IMP_NETLOGIC_XLS404B: + c->cputype = CPU_XLR; + __cpu_name[cpu] = "Netlogic XLS"; + break; + + default: + printk(KERN_INFO "Unknown Netlogic chip id [%02x]!\n", + c->processor_id); + c->cputype = CPU_XLR; + break; + } + + c->isa_level = MIPS_CPU_ISA_M64R1; + c->tlbsize = ((read_c0_config1() >> 25) & 0x3f) + 1; +} + +#ifdef CONFIG_64BIT +/* For use by uaccess.h */ +u64 __ua_limit; +EXPORT_SYMBOL(__ua_limit); +#endif + const char *__cpu_name[NR_CPUS]; const char *__elf_platform; @@ -1017,6 +1107,9 @@ __cpuinit void cpu_probe(void) case PRID_COMP_INGENIC: cpu_probe_ingenic(c, cpu); break; + case PRID_COMP_NETLOGIC: + cpu_probe_netlogic(c, cpu); + break; } BUG_ON(!__cpu_name[cpu]); @@ -1053,6 +1146,11 @@ __cpuinit void cpu_probe(void) c->srsets = 1; cpu_probe_vmbits(c); + +#ifdef CONFIG_64BIT + if (cpu == 0) + __ua_limit = ~((1ull << cpu_vmbits) - 1); +#endif } __cpuinit void cpu_report(void) diff --git a/arch/mips/kernel/csrc-bcm1480.c b/arch/mips/kernel/csrc-bcm1480.c index 51489f8a825..f96f99c794a 100644 --- a/arch/mips/kernel/csrc-bcm1480.c +++ b/arch/mips/kernel/csrc-bcm1480.c @@ -49,6 +49,5 @@ void __init sb1480_clocksource_init(void) plldiv = G_BCM1480_SYS_PLL_DIV(__raw_readq(IOADDR(A_SCD_SYSTEM_CFG))); zbbus = ((plldiv >> 1) * 50000000) + ((plldiv & 1) * 25000000); - clocksource_set_clock(cs, zbbus); - clocksource_register(cs); + clocksource_register_hz(cs, zbbus); } diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c index 23da108506b..46bd7fa98d6 100644 --- a/arch/mips/kernel/csrc-ioasic.c +++ b/arch/mips/kernel/csrc-ioasic.c @@ -59,7 +59,5 @@ void __init dec_ioasic_clocksource_init(void) printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq); clocksource_dec.rating = 200 + freq / 10000000; - clocksource_set_clock(&clocksource_dec, freq); - - clocksource_register(&clocksource_dec); + clocksource_register_hz(&clocksource_dec, freq); } diff --git a/arch/mips/kernel/csrc-powertv.c b/arch/mips/kernel/csrc-powertv.c index a27c16c8690..2e7c5232da8 100644 --- a/arch/mips/kernel/csrc-powertv.c +++ b/arch/mips/kernel/csrc-powertv.c @@ -78,9 +78,7 @@ static void __init powertv_c0_hpt_clocksource_init(void) clocksource_mips.rating = 200 + mips_hpt_frequency / 10000000; - clocksource_set_clock(&clocksource_mips, mips_hpt_frequency); - - clocksource_register(&clocksource_mips); + clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); } /** @@ -130,43 +128,16 @@ static struct clocksource clocksource_tim_c = { /** * powertv_tim_c_clocksource_init - set up a clock source for the TIM_C clock * - * The hard part here is coming up with a constant k and shift s such that - * the 48-bit TIM_C value multiplied by k doesn't overflow and that value, - * when shifted right by s, yields the corresponding number of nanoseconds. * We know that TIM_C counts at 27 MHz/8, so each cycle corresponds to - * 1 / (27,000,000/8) seconds. Multiply that by a billion and you get the - * number of nanoseconds. Since the TIM_C value has 48 bits and the math is - * done in 64 bits, avoiding an overflow means that k must be less than - * 64 - 48 = 16 bits. + * 1 / (27,000,000/8) seconds. */ static void __init powertv_tim_c_clocksource_init(void) { - int prescale; - unsigned long dividend; - unsigned long k; - int s; - const int max_k_bits = (64 - 48) - 1; - const unsigned long billion = 1000000000; const unsigned long counts_per_second = 27000000 / 8; - prescale = BITS_PER_LONG - ilog2(billion) - 1; - dividend = billion << prescale; - k = dividend / counts_per_second; - s = ilog2(k) - max_k_bits; - - if (s < 0) - s = prescale; - - else { - k >>= s; - s += prescale; - } - - clocksource_tim_c.mult = k; - clocksource_tim_c.shift = s; clocksource_tim_c.rating = 200; - clocksource_register(&clocksource_tim_c); + clocksource_register_hz(&clocksource_tim_c, counts_per_second); tim_c = (struct tim_c *) asic_reg_addr(tim_ch); } diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index e95a3cd48ee..decd1fa38d5 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -30,9 +30,7 @@ int __init init_r4k_clocksource(void) /* Calculate a somewhat reasonable rating value */ clocksource_mips.rating = 200 + mips_hpt_frequency / 10000000; - clocksource_set_clock(&clocksource_mips, mips_hpt_frequency); - - clocksource_register(&clocksource_mips); + clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); return 0; } diff --git a/arch/mips/kernel/csrc-sb1250.c b/arch/mips/kernel/csrc-sb1250.c index d14d3d1907f..e9606d90768 100644 --- a/arch/mips/kernel/csrc-sb1250.c +++ b/arch/mips/kernel/csrc-sb1250.c @@ -65,6 +65,5 @@ void __init sb1250_clocksource_init(void) IOADDR(A_SCD_TIMER_REGISTER(SB1250_HPT_NUM, R_SCD_TIMER_CFG))); - clocksource_set_clock(cs, V_SCD_TIMER_FREQ); - clocksource_register(cs); + clocksource_register_hz(cs, V_SCD_TIMER_FREQ); } diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index ffa331029e0..37acfa036d4 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -167,14 +167,13 @@ work_notifysig: # deal with pending signals and FEXPORT(syscall_exit_work_partial) SAVE_STATIC syscall_exit_work: - li t0, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT + li t0, _TIF_WORK_SYSCALL_EXIT and t0, a2 # a2 is preloaded with TI_FLAGS beqz t0, work_pending # trace bit set? - local_irq_enable # could let do_syscall_trace() + local_irq_enable # could let syscall_trace_leave() # call schedule() instead move a0, sp - li a1, 1 - jal do_syscall_trace + jal syscall_trace_leave b resume_userspace #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT) diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 5a84a1f1123..feb8021a305 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -17,29 +17,14 @@ #include <asm/cacheflush.h> #include <asm/uasm.h> -/* - * If the Instruction Pointer is in module space (0xc0000000), return true; - * otherwise, it is in kernel space (0x80000000), return false. - * - * FIXME: This will not work when the kernel space and module space are the - * same. If they are the same, we need to modify scripts/recordmcount.pl, - * ftrace_make_nop/call() and the other related parts to ensure the - * enabling/disabling of the calling site to _mcount is right for both kernel - * and module. - */ - -static inline int in_module(unsigned long ip) -{ - return ip & 0x40000000; -} +#include <asm-generic/sections.h> #ifdef CONFIG_DYNAMIC_FTRACE #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ #define ADDR_MASK 0x03ffffff /* op_code|addr : 31...26|25 ....0 */ +#define JUMP_RANGE_MASK ((1UL << 28) - 1) -#define INSN_B_1F_4 0x10000004 /* b 1f; offset = 4 */ -#define INSN_B_1F_5 0x10000005 /* b 1f; offset = 5 */ #define INSN_NOP 0x00000000 /* nop */ #define INSN_JAL(addr) \ ((unsigned int)(JAL | (((addr) >> 2) & ADDR_MASK))) @@ -60,15 +45,29 @@ static inline void ftrace_dyn_arch_init_insns(void) /* jal (ftrace_caller + 8), jump over the first two instruction */ buf = (u32 *)&insn_jal_ftrace_caller; - uasm_i_jal(&buf, (FTRACE_ADDR + 8)); + uasm_i_jal(&buf, (FTRACE_ADDR + 8) & JUMP_RANGE_MASK); #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* j ftrace_graph_caller */ buf = (u32 *)&insn_j_ftrace_graph_caller; - uasm_i_j(&buf, (unsigned long)ftrace_graph_caller); + uasm_i_j(&buf, (unsigned long)ftrace_graph_caller & JUMP_RANGE_MASK); #endif } +/* + * Check if the address is in kernel space + * + * Clone core_kernel_text() from kernel/extable.c, but doesn't call + * init_kernel_text() for Ftrace doesn't trace functions in init sections. + */ +static inline int in_kernel_space(unsigned long ip) +{ + if (ip >= (unsigned long)_stext && + ip <= (unsigned long)_etext) + return 1; + return 0; +} + static int ftrace_modify_code(unsigned long ip, unsigned int new_code) { int faulted; @@ -84,6 +83,42 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code) return 0; } +/* + * The details about the calling site of mcount on MIPS + * + * 1. For kernel: + * + * move at, ra + * jal _mcount --> nop + * + * 2. For modules: + * + * 2.1 For KBUILD_MCOUNT_RA_ADDRESS and CONFIG_32BIT + * + * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005) + * addiu v1, v1, low_16bit_of_mcount + * move at, ra + * move $12, ra_address + * jalr v1 + * sub sp, sp, 8 + * 1: offset = 5 instructions + * 2.2 For the Other situations + * + * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004) + * addiu v1, v1, low_16bit_of_mcount + * move at, ra + * jalr v1 + * nop | move $12, ra_address | sub sp, sp, 8 + * 1: offset = 4 instructions + */ + +#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) +#define MCOUNT_OFFSET_INSNS 5 +#else +#define MCOUNT_OFFSET_INSNS 4 +#endif +#define INSN_B_1F (0x10000000 | MCOUNT_OFFSET_INSNS) + int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { @@ -91,39 +126,11 @@ int ftrace_make_nop(struct module *mod, unsigned long ip = rec->ip; /* - * We have compiled module with -mlong-calls, but compiled the kernel - * without it, we need to cope with them respectively. + * If ip is in kernel space, no long call, otherwise, long call is + * needed. */ - if (in_module(ip)) { -#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) - /* - * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005) - * addiu v1, v1, low_16bit_of_mcount - * move at, ra - * move $12, ra_address - * jalr v1 - * sub sp, sp, 8 - * 1: offset = 5 instructions - */ - new = INSN_B_1F_5; -#else - /* - * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004) - * addiu v1, v1, low_16bit_of_mcount - * move at, ra - * jalr v1 - * nop | move $12, ra_address | sub sp, sp, 8 - * 1: offset = 4 instructions - */ - new = INSN_B_1F_4; -#endif - } else { - /* - * move at, ra - * jal _mcount --> nop - */ - new = INSN_NOP; - } + new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F; + return ftrace_modify_code(ip, new); } @@ -132,8 +139,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) unsigned int new; unsigned long ip = rec->ip; - /* ip, module: 0xc0000000, kernel: 0x80000000 */ - new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller; + new = in_kernel_space(ip) ? insn_jal_ftrace_caller : + insn_lui_v1_hi16_mcount; return ftrace_modify_code(ip, new); } @@ -190,29 +197,25 @@ int ftrace_disable_ftrace_graph_caller(void) #define S_R_SP (0xafb0 << 16) /* s{d,w} R, offset(sp) */ #define OFFSET_MASK 0xffff /* stack offset range: 0 ~ PT_SIZE */ -unsigned long ftrace_get_parent_addr(unsigned long self_addr, - unsigned long parent, - unsigned long parent_addr, - unsigned long fp) +unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long + old_parent_ra, unsigned long parent_ra_addr, unsigned long fp) { - unsigned long sp, ip, ra; + unsigned long sp, ip, tmp; unsigned int code; int faulted; /* - * For module, move the ip from calling site of mcount to the - * instruction "lui v1, hi_16bit_of_mcount"(offset is 20), but for - * kernel, move to the instruction "move ra, at"(offset is 12) + * For module, move the ip from the return address after the + * instruction "lui v1, hi_16bit_of_mcount"(offset is 24), but for + * kernel, move after the instruction "move ra, at"(offset is 16) */ - ip = self_addr - (in_module(self_addr) ? 20 : 12); + ip = self_ra - (in_kernel_space(self_ra) ? 16 : 24); /* * search the text until finding the non-store instruction or "s{d,w} * ra, offset(sp)" instruction */ do { - ip -= 4; - /* get the code at "ip": code = *(unsigned int *)ip; */ safe_load_code(code, ip, faulted); @@ -224,18 +227,20 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr, * store the ra on the stack */ if ((code & S_R_SP) != S_R_SP) - return parent_addr; + return parent_ra_addr; - } while (((code & S_RA_SP) != S_RA_SP)); + /* Move to the next instruction */ + ip -= 4; + } while ((code & S_RA_SP) != S_RA_SP); sp = fp + (code & OFFSET_MASK); - /* ra = *(unsigned long *)sp; */ - safe_load_stack(ra, sp, faulted); + /* tmp = *(unsigned long *)sp; */ + safe_load_stack(tmp, sp, faulted); if (unlikely(faulted)) return 0; - if (ra == parent) + if (tmp == old_parent_ra) return sp; return 0; } @@ -246,21 +251,21 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr, * Hook the return address and push it in the stack of return addrs * in current thread info. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, +void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, unsigned long fp) { - unsigned long old; + unsigned long old_parent_ra; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; - int faulted; + int faulted, insns; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; /* - * "parent" is the stack address saved the return address of the caller - * of _mcount. + * "parent_ra_addr" is the stack address saved the return address of + * the caller of _mcount. * * if the gcc < 4.5, a leaf function does not save the return address * in the stack address, so, we "emulate" one in _mcount's stack space, @@ -275,37 +280,44 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, * do it in ftrace_graph_caller of mcount.S. */ - /* old = *parent; */ - safe_load_stack(old, parent, faulted); + /* old_parent_ra = *parent_ra_addr; */ + safe_load_stack(old_parent_ra, parent_ra_addr, faulted); if (unlikely(faulted)) goto out; #ifndef KBUILD_MCOUNT_RA_ADDRESS - parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old, - (unsigned long)parent, fp); + parent_ra_addr = (unsigned long *)ftrace_get_parent_ra_addr(self_ra, + old_parent_ra, (unsigned long)parent_ra_addr, fp); /* * If fails when getting the stack address of the non-leaf function's * ra, stop function graph tracer and return */ - if (parent == 0) + if (parent_ra_addr == 0) goto out; #endif - /* *parent = return_hooker; */ - safe_store_stack(return_hooker, parent, faulted); + /* *parent_ra_addr = return_hooker; */ + safe_store_stack(return_hooker, parent_ra_addr, faulted); if (unlikely(faulted)) goto out; - if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) == - -EBUSY) { - *parent = old; + if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp) + == -EBUSY) { + *parent_ra_addr = old_parent_ra; return; } - trace.func = self_addr; + /* + * Get the recorded ip of the current mcount calling site in the + * __mcount_loc section, which will be used to filter the function + * entries configured through the tracing/set_graph_function interface. + */ + + insns = in_kernel_space(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; + trace.func = self_ra - (MCOUNT_INSN_SIZE * insns); /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) { current->curr_ret_stack--; - *parent = old; + *parent_ra_addr = old_parent_ra; } return; out: diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 2392a7a296d..391221b6a6a 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -125,87 +125,11 @@ void __init setup_pit_timer(void) setup_irq(0, &irq0); } -/* - * Since the PIT overflows every tick, its not very useful - * to just read by itself. So use jiffies to emulate a free - * running counter: - */ -static cycle_t pit_read(struct clocksource *cs) -{ - unsigned long flags; - int count; - u32 jifs; - static int old_count; - static u32 old_jifs; - - raw_spin_lock_irqsave(&i8253_lock, flags); - /* - * Although our caller may have the read side of xtime_lock, - * this is now a seqlock, and we are cheating in this routine - * by having side effects on state that we cannot undo if - * there is a collision on the seqlock and our caller has to - * retry. (Namely, old_jifs and old_count.) So we must treat - * jiffies as volatile despite the lock. We read jiffies - * before latching the timer count to guarantee that although - * the jiffies value might be older than the count (that is, - * the counter may underflow between the last point where - * jiffies was incremented and the point where we latch the - * count), it cannot be newer. - */ - jifs = jiffies; - outb_p(0x00, PIT_MODE); /* latch the count ASAP */ - count = inb_p(PIT_CH0); /* read the latched count */ - count |= inb_p(PIT_CH0) << 8; - - /* VIA686a test code... reset the latch if count > max + 1 */ - if (count > LATCH) { - outb_p(0x34, PIT_MODE); - outb_p(LATCH & 0xff, PIT_CH0); - outb(LATCH >> 8, PIT_CH0); - count = LATCH - 1; - } - - /* - * It's possible for count to appear to go the wrong way for a - * couple of reasons: - * - * 1. The timer counter underflows, but we haven't handled the - * resulting interrupt and incremented jiffies yet. - * 2. Hardware problem with the timer, not giving us continuous time, - * the counter does small "jumps" upwards on some Pentium systems, - * (see c't 95/10 page 335 for Neptun bug.) - * - * Previous attempts to handle these cases intelligently were - * buggy, so we just do the simple thing now. - */ - if (count > old_count && jifs == old_jifs) { - count = old_count; - } - old_count = count; - old_jifs = jifs; - - raw_spin_unlock_irqrestore(&i8253_lock, flags); - - count = (LATCH - 1) - count; - - return (cycle_t)(jifs * LATCH) + count; -} - -static struct clocksource clocksource_pit = { - .name = "pit", - .rating = 110, - .read = pit_read, - .mask = CLOCKSOURCE_MASK(32), - .mult = 0, - .shift = 20, -}; - static int __init init_pit_clocksource(void) { if (num_possible_cpus() > 1) /* PIT does not scale! */ return 0; - clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20); - return clocksource_register(&clocksource_pit); + return clocksource_i8253_init(); } arch_initcall(init_pit_clocksource); diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index c58176cc796..c018696765d 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -31,19 +31,19 @@ static int i8259A_auto_eoi = -1; DEFINE_RAW_SPINLOCK(i8259A_lock); -static void disable_8259A_irq(unsigned int irq); -static void enable_8259A_irq(unsigned int irq); -static void mask_and_ack_8259A(unsigned int irq); +static void disable_8259A_irq(struct irq_data *d); +static void enable_8259A_irq(struct irq_data *d); +static void mask_and_ack_8259A(struct irq_data *d); static void init_8259A(int auto_eoi); static struct irq_chip i8259A_chip = { - .name = "XT-PIC", - .mask = disable_8259A_irq, - .disable = disable_8259A_irq, - .unmask = enable_8259A_irq, - .mask_ack = mask_and_ack_8259A, + .name = "XT-PIC", + .irq_mask = disable_8259A_irq, + .irq_disable = disable_8259A_irq, + .irq_unmask = enable_8259A_irq, + .irq_mask_ack = mask_and_ack_8259A, #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF - .set_affinity = plat_set_irq_affinity, + .irq_set_affinity = plat_set_irq_affinity, #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ }; @@ -59,12 +59,11 @@ static unsigned int cached_irq_mask = 0xffff; #define cached_master_mask (cached_irq_mask) #define cached_slave_mask (cached_irq_mask >> 8) -static void disable_8259A_irq(unsigned int irq) +static void disable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; mask = 1 << irq; raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask |= mask; @@ -75,12 +74,11 @@ static void disable_8259A_irq(unsigned int irq) raw_spin_unlock_irqrestore(&i8259A_lock, flags); } -static void enable_8259A_irq(unsigned int irq) +static void enable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; mask = ~(1 << irq); raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask &= mask; @@ -112,7 +110,7 @@ int i8259A_irq_pending(unsigned int irq) void make_8259A_irq(unsigned int irq) { disable_irq_nosync(irq); - set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); enable_irq(irq); } @@ -145,12 +143,11 @@ static inline int i8259A_irq_real(unsigned int irq) * first, _then_ send the EOI, and the order of EOI * to the two 8259s is important! */ -static void mask_and_ack_8259A(unsigned int irq) +static void mask_and_ack_8259A(struct irq_data *d) { - unsigned int irqmask; + unsigned int irqmask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; irqmask = 1 << irq; raw_spin_lock_irqsave(&i8259A_lock, flags); /* @@ -290,9 +287,9 @@ static void init_8259A(int auto_eoi) * In AEOI mode we just have to mask the interrupt * when acking. */ - i8259A_chip.mask_ack = disable_8259A_irq; + i8259A_chip.irq_mask_ack = disable_8259A_irq; else - i8259A_chip.mask_ack = mask_and_ack_8259A; + i8259A_chip.irq_mask_ack = mask_and_ack_8259A; udelay(100); /* wait for 8259A to initialize */ @@ -339,8 +336,8 @@ void __init init_i8259_irqs(void) init_8259A(0); for (i = I8259A_IRQ_BASE; i < I8259A_IRQ_BASE + 16; i++) { - set_irq_chip_and_handler(i, &i8259A_chip, handle_level_irq); - set_irq_probe(i); + irq_set_chip_and_handler(i, &i8259A_chip, handle_level_irq); + irq_set_probe(i); } setup_irq(I8259A_IRQ_BASE + PIC_CASCADE_IR, &irq2); diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 1774271af84..0c527f65219 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -87,17 +87,10 @@ unsigned int gic_get_int(void) return i; } -static unsigned int gic_irq_startup(unsigned int irq) +static void gic_irq_ack(struct irq_data *d) { - irq -= _irqbase; - pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); - GIC_SET_INTR_MASK(irq); - return 0; -} + unsigned int irq = d->irq - _irqbase; -static void gic_irq_ack(unsigned int irq) -{ - irq -= _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_CLR_INTR_MASK(irq); @@ -105,16 +98,16 @@ static void gic_irq_ack(unsigned int irq) GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), irq); } -static void gic_mask_irq(unsigned int irq) +static void gic_mask_irq(struct irq_data *d) { - irq -= _irqbase; + unsigned int irq = d->irq - _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_CLR_INTR_MASK(irq); } -static void gic_unmask_irq(unsigned int irq) +static void gic_unmask_irq(struct irq_data *d) { - irq -= _irqbase; + unsigned int irq = d->irq - _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_SET_INTR_MASK(irq); } @@ -123,13 +116,14 @@ static void gic_unmask_irq(unsigned int irq) static DEFINE_SPINLOCK(gic_lock); -static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, + bool force) { + unsigned int irq = d->irq - _irqbase; cpumask_t tmp = CPU_MASK_NONE; unsigned long flags; int i; - irq -= _irqbase; pr_debug("%s(%d) called\n", __func__, irq); cpumask_and(&tmp, cpumask, cpu_online_mask); if (cpus_empty(tmp)) @@ -147,23 +141,22 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask); } - cpumask_copy(irq_desc[irq].affinity, cpumask); + cpumask_copy(d->affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } #endif static struct irq_chip gic_irq_controller = { - .name = "MIPS GIC", - .startup = gic_irq_startup, - .ack = gic_irq_ack, - .mask = gic_mask_irq, - .mask_ack = gic_mask_irq, - .unmask = gic_unmask_irq, - .eoi = gic_unmask_irq, + .name = "MIPS GIC", + .irq_ack = gic_irq_ack, + .irq_mask = gic_mask_irq, + .irq_mask_ack = gic_mask_irq, + .irq_unmask = gic_unmask_irq, + .irq_eoi = gic_unmask_irq, #ifdef CONFIG_SMP - .set_affinity = gic_set_affinity, + .irq_set_affinity = gic_set_affinity, #endif }; @@ -236,7 +229,7 @@ static void __init gic_basic_init(int numintrs, int numvpes, vpe_local_setup(numvpes); for (i = _irqbase; i < (_irqbase + numintrs); i++) - set_irq_chip(i, &gic_irq_controller); + irq_set_chip(i, &gic_irq_controller); } void __init gic_init(unsigned long gic_base_addr, diff --git a/arch/mips/kernel/irq-gt641xx.c b/arch/mips/kernel/irq-gt641xx.c index 42ef81461bf..883fc6cead3 100644 --- a/arch/mips/kernel/irq-gt641xx.c +++ b/arch/mips/kernel/irq-gt641xx.c @@ -29,64 +29,64 @@ static DEFINE_RAW_SPINLOCK(gt641xx_irq_lock); -static void ack_gt641xx_irq(unsigned int irq) +static void ack_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 cause; raw_spin_lock_irqsave(>641xx_irq_lock, flags); cause = GT_READ(GT_INTRCAUSE_OFS); - cause &= ~GT641XX_IRQ_TO_BIT(irq); + cause &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRCAUSE_OFS, cause); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void mask_gt641xx_irq(unsigned int irq) +static void mask_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask &= ~GT641XX_IRQ_TO_BIT(irq); + mask &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void mask_ack_gt641xx_irq(unsigned int irq) +static void mask_ack_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 cause, mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask &= ~GT641XX_IRQ_TO_BIT(irq); + mask &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); cause = GT_READ(GT_INTRCAUSE_OFS); - cause &= ~GT641XX_IRQ_TO_BIT(irq); + cause &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRCAUSE_OFS, cause); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void unmask_gt641xx_irq(unsigned int irq) +static void unmask_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask |= GT641XX_IRQ_TO_BIT(irq); + mask |= GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } static struct irq_chip gt641xx_irq_chip = { .name = "GT641xx", - .ack = ack_gt641xx_irq, - .mask = mask_gt641xx_irq, - .mask_ack = mask_ack_gt641xx_irq, - .unmask = unmask_gt641xx_irq, + .irq_ack = ack_gt641xx_irq, + .irq_mask = mask_gt641xx_irq, + .irq_mask_ack = mask_ack_gt641xx_irq, + .irq_unmask = unmask_gt641xx_irq, }; void gt641xx_irq_dispatch(void) @@ -126,6 +126,6 @@ void __init gt641xx_irq_init(void) * bit31: logical or of bits[25:1]. */ for (i = 1; i < 30; i++) - set_irq_chip_and_handler(GT641XX_IRQ_BASE + i, - >641xx_irq_chip, handle_level_irq); + irq_set_chip_and_handler(GT641XX_IRQ_BASE + i, + >641xx_irq_chip, handle_level_irq); } diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c index 6a8cd28133d..0c6afeed89d 100644 --- a/arch/mips/kernel/irq-msc01.c +++ b/arch/mips/kernel/irq-msc01.c @@ -28,8 +28,10 @@ static unsigned long _icctrl_msc; static unsigned int irq_base; /* mask off an interrupt */ -static inline void mask_msc_irq(unsigned int irq) +static inline void mask_msc_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < (irq_base + 32)) MSCIC_WRITE(MSC01_IC_DISL, 1<<(irq - irq_base)); else @@ -37,8 +39,10 @@ static inline void mask_msc_irq(unsigned int irq) } /* unmask an interrupt */ -static inline void unmask_msc_irq(unsigned int irq) +static inline void unmask_msc_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < (irq_base + 32)) MSCIC_WRITE(MSC01_IC_ENAL, 1<<(irq - irq_base)); else @@ -48,9 +52,11 @@ static inline void unmask_msc_irq(unsigned int irq) /* * Masks and ACKs an IRQ */ -static void level_mask_and_ack_msc_irq(unsigned int irq) +static void level_mask_and_ack_msc_irq(struct irq_data *d) { - mask_msc_irq(irq); + unsigned int irq = d->irq; + + mask_msc_irq(d); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); /* This actually needs to be a call into platform code */ @@ -60,9 +66,11 @@ static void level_mask_and_ack_msc_irq(unsigned int irq) /* * Masks and ACKs an IRQ */ -static void edge_mask_and_ack_msc_irq(unsigned int irq) +static void edge_mask_and_ack_msc_irq(struct irq_data *d) { - mask_msc_irq(irq); + unsigned int irq = d->irq; + + mask_msc_irq(d); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); else { @@ -75,15 +83,6 @@ static void edge_mask_and_ack_msc_irq(unsigned int irq) } /* - * End IRQ processing - */ -static void end_msc_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - unmask_msc_irq(irq); -} - -/* * Interrupt handler for interrupts coming from SOC-it. */ void ll_msc_irq(void) @@ -107,22 +106,20 @@ static void msc_bind_eic_interrupt(int irq, int set) static struct irq_chip msc_levelirq_type = { .name = "SOC-it-Level", - .ack = level_mask_and_ack_msc_irq, - .mask = mask_msc_irq, - .mask_ack = level_mask_and_ack_msc_irq, - .unmask = unmask_msc_irq, - .eoi = unmask_msc_irq, - .end = end_msc_irq, + .irq_ack = level_mask_and_ack_msc_irq, + .irq_mask = mask_msc_irq, + .irq_mask_ack = level_mask_and_ack_msc_irq, + .irq_unmask = unmask_msc_irq, + .irq_eoi = unmask_msc_irq, }; static struct irq_chip msc_edgeirq_type = { .name = "SOC-it-Edge", - .ack = edge_mask_and_ack_msc_irq, - .mask = mask_msc_irq, - .mask_ack = edge_mask_and_ack_msc_irq, - .unmask = unmask_msc_irq, - .eoi = unmask_msc_irq, - .end = end_msc_irq, + .irq_ack = edge_mask_and_ack_msc_irq, + .irq_mask = mask_msc_irq, + .irq_mask_ack = edge_mask_and_ack_msc_irq, + .irq_unmask = unmask_msc_irq, + .irq_eoi = unmask_msc_irq, }; @@ -140,16 +137,20 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma switch (imp->im_type) { case MSC01_IRQ_EDGE: - set_irq_chip_and_handler_name(irqbase + n, - &msc_edgeirq_type, handle_edge_irq, "edge"); + irq_set_chip_and_handler_name(irqbase + n, + &msc_edgeirq_type, + handle_edge_irq, + "edge"); if (cpu_has_veic) MSCIC_WRITE(MSC01_IC_SUP+n*8, MSC01_IC_SUP_EDGE_BIT); else MSCIC_WRITE(MSC01_IC_SUP+n*8, MSC01_IC_SUP_EDGE_BIT | imp->im_lvl); break; case MSC01_IRQ_LEVEL: - set_irq_chip_and_handler_name(irqbase+n, - &msc_levelirq_type, handle_level_irq, "level"); + irq_set_chip_and_handler_name(irqbase + n, + &msc_levelirq_type, + handle_level_irq, + "level"); if (cpu_has_veic) MSCIC_WRITE(MSC01_IC_SUP+n*8, 0); else diff --git a/arch/mips/kernel/irq-rm7000.c b/arch/mips/kernel/irq-rm7000.c index 9731e8b4786..a8a8977d588 100644 --- a/arch/mips/kernel/irq-rm7000.c +++ b/arch/mips/kernel/irq-rm7000.c @@ -18,23 +18,23 @@ #include <asm/mipsregs.h> #include <asm/system.h> -static inline void unmask_rm7k_irq(unsigned int irq) +static inline void unmask_rm7k_irq(struct irq_data *d) { - set_c0_intcontrol(0x100 << (irq - RM7K_CPU_IRQ_BASE)); + set_c0_intcontrol(0x100 << (d->irq - RM7K_CPU_IRQ_BASE)); } -static inline void mask_rm7k_irq(unsigned int irq) +static inline void mask_rm7k_irq(struct irq_data *d) { - clear_c0_intcontrol(0x100 << (irq - RM7K_CPU_IRQ_BASE)); + clear_c0_intcontrol(0x100 << (d->irq - RM7K_CPU_IRQ_BASE)); } static struct irq_chip rm7k_irq_controller = { .name = "RM7000", - .ack = mask_rm7k_irq, - .mask = mask_rm7k_irq, - .mask_ack = mask_rm7k_irq, - .unmask = unmask_rm7k_irq, - .eoi = unmask_rm7k_irq + .irq_ack = mask_rm7k_irq, + .irq_mask = mask_rm7k_irq, + .irq_mask_ack = mask_rm7k_irq, + .irq_unmask = unmask_rm7k_irq, + .irq_eoi = unmask_rm7k_irq }; void __init rm7k_cpu_irq_init(void) @@ -45,6 +45,6 @@ void __init rm7k_cpu_irq_init(void) clear_c0_intcontrol(0x00000f00); /* Mask all */ for (i = base; i < base + 4; i++) - set_irq_chip_and_handler(i, &rm7k_irq_controller, + irq_set_chip_and_handler(i, &rm7k_irq_controller, handle_percpu_irq); } diff --git a/arch/mips/kernel/irq-rm9000.c b/arch/mips/kernel/irq-rm9000.c index b7e4025b58a..38874a4b925 100644 --- a/arch/mips/kernel/irq-rm9000.c +++ b/arch/mips/kernel/irq-rm9000.c @@ -19,22 +19,22 @@ #include <asm/mipsregs.h> #include <asm/system.h> -static inline void unmask_rm9k_irq(unsigned int irq) +static inline void unmask_rm9k_irq(struct irq_data *d) { - set_c0_intcontrol(0x1000 << (irq - RM9K_CPU_IRQ_BASE)); + set_c0_intcontrol(0x1000 << (d->irq - RM9K_CPU_IRQ_BASE)); } -static inline void mask_rm9k_irq(unsigned int irq) +static inline void mask_rm9k_irq(struct irq_data *d) { - clear_c0_intcontrol(0x1000 << (irq - RM9K_CPU_IRQ_BASE)); + clear_c0_intcontrol(0x1000 << (d->irq - RM9K_CPU_IRQ_BASE)); } -static inline void rm9k_cpu_irq_enable(unsigned int irq) +static inline void rm9k_cpu_irq_enable(struct irq_data *d) { unsigned long flags; local_irq_save(flags); - unmask_rm9k_irq(irq); + unmask_rm9k_irq(d); local_irq_restore(flags); } @@ -43,50 +43,47 @@ static inline void rm9k_cpu_irq_enable(unsigned int irq) */ static void local_rm9k_perfcounter_irq_startup(void *args) { - unsigned int irq = (unsigned int) args; - - rm9k_cpu_irq_enable(irq); + rm9k_cpu_irq_enable(args); } -static unsigned int rm9k_perfcounter_irq_startup(unsigned int irq) +static unsigned int rm9k_perfcounter_irq_startup(struct irq_data *d) { - on_each_cpu(local_rm9k_perfcounter_irq_startup, (void *) irq, 1); + on_each_cpu(local_rm9k_perfcounter_irq_startup, d, 1); return 0; } static void local_rm9k_perfcounter_irq_shutdown(void *args) { - unsigned int irq = (unsigned int) args; unsigned long flags; local_irq_save(flags); - mask_rm9k_irq(irq); + mask_rm9k_irq(args); local_irq_restore(flags); } -static void rm9k_perfcounter_irq_shutdown(unsigned int irq) +static void rm9k_perfcounter_irq_shutdown(struct irq_data *d) { - on_each_cpu(local_rm9k_perfcounter_irq_shutdown, (void *) irq, 1); + on_each_cpu(local_rm9k_perfcounter_irq_shutdown, d, 1); } static struct irq_chip rm9k_irq_controller = { .name = "RM9000", - .ack = mask_rm9k_irq, - .mask = mask_rm9k_irq, - .mask_ack = mask_rm9k_irq, - .unmask = unmask_rm9k_irq, - .eoi = unmask_rm9k_irq + .irq_ack = mask_rm9k_irq, + .irq_mask = mask_rm9k_irq, + .irq_mask_ack = mask_rm9k_irq, + .irq_unmask = unmask_rm9k_irq, + .irq_eoi = unmask_rm9k_irq }; static struct irq_chip rm9k_perfcounter_irq = { .name = "RM9000", - .startup = rm9k_perfcounter_irq_startup, - .shutdown = rm9k_perfcounter_irq_shutdown, - .ack = mask_rm9k_irq, - .mask = mask_rm9k_irq, - .mask_ack = mask_rm9k_irq, - .unmask = unmask_rm9k_irq, + .irq_startup = rm9k_perfcounter_irq_startup, + .irq_shutdown = rm9k_perfcounter_irq_shutdown, + .irq_ack = mask_rm9k_irq, + .irq_mask = mask_rm9k_irq, + .irq_mask_ack = mask_rm9k_irq, + .irq_unmask = unmask_rm9k_irq, }; unsigned int rm9000_perfcount_irq; @@ -101,10 +98,10 @@ void __init rm9k_cpu_irq_init(void) clear_c0_intcontrol(0x0000f000); /* Mask all */ for (i = base; i < base + 4; i++) - set_irq_chip_and_handler(i, &rm9k_irq_controller, + irq_set_chip_and_handler(i, &rm9k_irq_controller, handle_level_irq); rm9000_perfcount_irq = base + 1; - set_irq_chip_and_handler(rm9000_perfcount_irq, &rm9k_perfcounter_irq, + irq_set_chip_and_handler(rm9000_perfcount_irq, &rm9k_perfcounter_irq, handle_percpu_irq); } diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index c6345f579a8..9b734d74ae8 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -81,48 +81,9 @@ void ack_bad_irq(unsigned int irq) atomic_t irq_err_count; -/* - * Generic, controller-independent functions: - */ - -int show_interrupts(struct seq_file *p, void *v) +int arch_show_interrupts(struct seq_file *p, int prec) { - int i = *(loff_t *) v, j; - struct irqaction * action; - unsigned long flags; - - if (i == 0) { - seq_printf(p, " "); - for_each_online_cpu(j) - seq_printf(p, "CPU%d ", j); - seq_putc(p, '\n'); - } - - if (i < NR_IRQS) { - raw_spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; - if (!action) - goto skip; - seq_printf(p, "%3d: ", i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else - for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); -#endif - seq_printf(p, " %14s", irq_desc[i].chip->name); - seq_printf(p, " %s", action->name); - - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); - - seq_putc(p, '\n'); -skip: - raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == NR_IRQS) { - seq_putc(p, '\n'); - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); - } + seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); return 0; } @@ -141,7 +102,7 @@ void __init init_IRQ(void) #endif for (i = 0; i < NR_IRQS; i++) - set_irq_noprobe(i); + irq_set_noprobe(i); arch_init_irq(); @@ -151,6 +112,29 @@ void __init init_IRQ(void) #endif } +#ifdef DEBUG_STACKOVERFLOW +static inline void check_stack_overflow(void) +{ + unsigned long sp; + + __asm__ __volatile__("move %0, $sp" : "=r" (sp)); + sp &= THREAD_MASK; + + /* + * Check for stack overflow: is there less than STACK_WARN free? + * STACK_WARN is defined as 1/8 of THREAD_SIZE by default. + */ + if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) { + printk("do_IRQ: stack overflow: %ld\n", + sp - sizeof(struct thread_info)); + dump_stack(); + } +} +#else +static inline void check_stack_overflow(void) {} +#endif + + /* * do_IRQ handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific @@ -159,8 +143,9 @@ void __init init_IRQ(void) void __irq_entry do_IRQ(unsigned int irq) { irq_enter(); - __DO_IRQ_SMTC_HOOK(irq); - generic_handle_irq(irq); + check_stack_overflow(); + if (!smtc_handle_on_other_cpu(irq)) + generic_handle_irq(irq); irq_exit(); } @@ -173,7 +158,7 @@ void __irq_entry do_IRQ(unsigned int irq) void __irq_entry do_IRQ_no_affinity(unsigned int irq) { irq_enter(); - __NO_AFFINITY_IRQ_SMTC_HOOK(irq); + smtc_im_backstop(irq); generic_handle_irq(irq); irq_exit(); } diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c index 0262abe0912..6e71b284f6c 100644 --- a/arch/mips/kernel/irq_cpu.c +++ b/arch/mips/kernel/irq_cpu.c @@ -37,42 +37,38 @@ #include <asm/mipsmtregs.h> #include <asm/system.h> -static inline void unmask_mips_irq(unsigned int irq) +static inline void unmask_mips_irq(struct irq_data *d) { - set_c0_status(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); irq_enable_hazard(); } -static inline void mask_mips_irq(unsigned int irq) +static inline void mask_mips_irq(struct irq_data *d) { - clear_c0_status(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); irq_disable_hazard(); } static struct irq_chip mips_cpu_irq_controller = { .name = "MIPS", - .ack = mask_mips_irq, - .mask = mask_mips_irq, - .mask_ack = mask_mips_irq, - .unmask = unmask_mips_irq, - .eoi = unmask_mips_irq, + .irq_ack = mask_mips_irq, + .irq_mask = mask_mips_irq, + .irq_mask_ack = mask_mips_irq, + .irq_unmask = unmask_mips_irq, + .irq_eoi = unmask_mips_irq, }; /* * Basically the same as above but taking care of all the MT stuff */ -#define unmask_mips_mt_irq unmask_mips_irq -#define mask_mips_mt_irq mask_mips_irq - -static unsigned int mips_mt_cpu_irq_startup(unsigned int irq) +static unsigned int mips_mt_cpu_irq_startup(struct irq_data *d) { unsigned int vpflags = dvpe(); - clear_c0_cause(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_cause(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); evpe(vpflags); - unmask_mips_mt_irq(irq); - + unmask_mips_irq(d); return 0; } @@ -80,22 +76,22 @@ static unsigned int mips_mt_cpu_irq_startup(unsigned int irq) * While we ack the interrupt interrupts are disabled and thus we don't need * to deal with concurrency issues. Same for mips_cpu_irq_end. */ -static void mips_mt_cpu_irq_ack(unsigned int irq) +static void mips_mt_cpu_irq_ack(struct irq_data *d) { unsigned int vpflags = dvpe(); - clear_c0_cause(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_cause(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); evpe(vpflags); - mask_mips_mt_irq(irq); + mask_mips_irq(d); } static struct irq_chip mips_mt_cpu_irq_controller = { .name = "MIPS", - .startup = mips_mt_cpu_irq_startup, - .ack = mips_mt_cpu_irq_ack, - .mask = mask_mips_mt_irq, - .mask_ack = mips_mt_cpu_irq_ack, - .unmask = unmask_mips_mt_irq, - .eoi = unmask_mips_mt_irq, + .irq_startup = mips_mt_cpu_irq_startup, + .irq_ack = mips_mt_cpu_irq_ack, + .irq_mask = mask_mips_irq, + .irq_mask_ack = mips_mt_cpu_irq_ack, + .irq_unmask = unmask_mips_irq, + .irq_eoi = unmask_mips_irq, }; void __init mips_cpu_irq_init(void) @@ -113,10 +109,10 @@ void __init mips_cpu_irq_init(void) */ if (cpu_has_mipsmt) for (i = irq_base; i < irq_base + 2; i++) - set_irq_chip_and_handler(i, &mips_mt_cpu_irq_controller, + irq_set_chip_and_handler(i, &mips_mt_cpu_irq_controller, handle_percpu_irq); for (i = irq_base + 2; i < irq_base + 8; i++) - set_irq_chip_and_handler(i, &mips_cpu_irq_controller, + irq_set_chip_and_handler(i, &mips_cpu_irq_controller, handle_percpu_irq); } diff --git a/arch/mips/kernel/irq_txx9.c b/arch/mips/kernel/irq_txx9.c index 95a96f69172..b0c55b50218 100644 --- a/arch/mips/kernel/irq_txx9.c +++ b/arch/mips/kernel/irq_txx9.c @@ -63,9 +63,9 @@ static struct { unsigned char mode; } txx9irq[TXx9_MAX_IR] __read_mostly; -static void txx9_irq_unmask(unsigned int irq) +static void txx9_irq_unmask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *ilrp = &txx9_ircptr->ilr[(irq_nr % 16 ) / 2]; int ofs = irq_nr / 16 * 16 + (irq_nr & 1) * 8; @@ -79,9 +79,9 @@ static void txx9_irq_unmask(unsigned int irq) #endif } -static inline void txx9_irq_mask(unsigned int irq) +static inline void txx9_irq_mask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *ilrp = &txx9_ircptr->ilr[(irq_nr % 16) / 2]; int ofs = irq_nr / 16 * 16 + (irq_nr & 1) * 8; @@ -99,19 +99,19 @@ static inline void txx9_irq_mask(unsigned int irq) #endif } -static void txx9_irq_mask_ack(unsigned int irq) +static void txx9_irq_mask_ack(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; - txx9_irq_mask(irq); + txx9_irq_mask(d); /* clear edge detection */ if (unlikely(TXx9_IRCR_EDGE(txx9irq[irq_nr].mode))) __raw_writel(TXx9_IRSCR_EIClrE | irq_nr, &txx9_ircptr->scr); } -static int txx9_irq_set_type(unsigned int irq, unsigned int flow_type) +static int txx9_irq_set_type(struct irq_data *d, unsigned int flow_type) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 cr; u32 __iomem *crp; int ofs; @@ -139,11 +139,11 @@ static int txx9_irq_set_type(unsigned int irq, unsigned int flow_type) static struct irq_chip txx9_irq_chip = { .name = "TXX9", - .ack = txx9_irq_mask_ack, - .mask = txx9_irq_mask, - .mask_ack = txx9_irq_mask_ack, - .unmask = txx9_irq_unmask, - .set_type = txx9_irq_set_type, + .irq_ack = txx9_irq_mask_ack, + .irq_mask = txx9_irq_mask, + .irq_mask_ack = txx9_irq_mask_ack, + .irq_unmask = txx9_irq_unmask, + .irq_set_type = txx9_irq_set_type, }; void __init txx9_irq_init(unsigned long baseaddr) @@ -154,8 +154,8 @@ void __init txx9_irq_init(unsigned long baseaddr) for (i = 0; i < TXx9_MAX_IR; i++) { txx9irq[i].level = 4; /* middle level */ txx9irq[i].mode = TXx9_IRCR_LOW; - set_irq_chip_and_handler(TXX9_IRQ_BASE + i, - &txx9_irq_chip, handle_level_irq); + irq_set_chip_and_handler(TXX9_IRQ_BASE + i, &txx9_irq_chip, + handle_level_irq); } /* mask all IRC interrupts */ diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c new file mode 100644 index 00000000000..6001610cfe5 --- /dev/null +++ b/arch/mips/kernel/jump_label.c @@ -0,0 +1,54 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2010 Cavium Networks, Inc. + */ + +#include <linux/jump_label.h> +#include <linux/kernel.h> +#include <linux/memory.h> +#include <linux/mutex.h> +#include <linux/types.h> +#include <linux/cpu.h> + +#include <asm/cacheflush.h> +#include <asm/inst.h> + +#ifdef HAVE_JUMP_LABEL + +#define J_RANGE_MASK ((1ul << 28) - 1) + +void arch_jump_label_transform(struct jump_entry *e, + enum jump_label_type type) +{ + union mips_instruction insn; + union mips_instruction *insn_p = + (union mips_instruction *)(unsigned long)e->code; + + /* Jump only works within a 256MB aligned region. */ + BUG_ON((e->target & ~J_RANGE_MASK) != (e->code & ~J_RANGE_MASK)); + + /* Target must have 4 byte alignment. */ + BUG_ON((e->target & 3) != 0); + + if (type == JUMP_LABEL_ENABLE) { + insn.j_format.opcode = j_op; + insn.j_format.target = (e->target & J_RANGE_MASK) >> 2; + } else { + insn.word = 0; /* nop */ + } + + get_online_cpus(); + mutex_lock(&text_mutex); + *insn_p = insn; + + flush_icache_range((unsigned long)insn_p, + (unsigned long)insn_p + sizeof(*insn_p)); + + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +#endif /* HAVE_JUMP_LABEL */ diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 6343b4a5b83..876a75cc376 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -251,14 +251,15 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz, SYSCALL_DEFINE1(32_personality, unsigned long, personality) { + unsigned int p = personality & 0xffffffff; int ret; - personality &= 0xffffffff; + if (personality(current->personality) == PER_LINUX32 && - personality == PER_LINUX) - personality = PER_LINUX32; - ret = sys_personality(personality); - if (ret == PER_LINUX32) - ret = PER_LINUX; + personality(p) == PER_LINUX) + p = (p & ~PER_MASK) | PER_LINUX32; + ret = sys_personality(p); + if (ret != -1 && personality(ret) == PER_LINUX32) + ret = (ret & ~PER_MASK) | PER_LINUX; return ret; } diff --git a/arch/mips/kernel/mips_machine.c b/arch/mips/kernel/mips_machine.c new file mode 100644 index 00000000000..411a058d2c5 --- /dev/null +++ b/arch/mips/kernel/mips_machine.c @@ -0,0 +1,86 @@ +/* + * Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + */ +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/slab.h> + +#include <asm/mips_machine.h> + +static struct mips_machine *mips_machine __initdata; +static char *mips_machine_name = "Unknown"; + +#define for_each_machine(mach) \ + for ((mach) = (struct mips_machine *)&__mips_machines_start; \ + (mach) && \ + (unsigned long)(mach) < (unsigned long)&__mips_machines_end; \ + (mach)++) + +__init void mips_set_machine_name(const char *name) +{ + char *p; + + if (name == NULL) + return; + + p = kstrdup(name, GFP_KERNEL); + if (!p) + pr_err("MIPS: no memory for machine_name\n"); + + mips_machine_name = p; +} + +char *mips_get_machine_name(void) +{ + return mips_machine_name; +} + +__init int mips_machtype_setup(char *id) +{ + struct mips_machine *mach; + + for_each_machine(mach) { + if (mach->mach_id == NULL) + continue; + + if (strcmp(mach->mach_id, id) == 0) { + mips_machtype = mach->mach_type; + return 0; + } + } + + pr_err("MIPS: no machine found for id '%s', supported machines:\n", id); + pr_err("%-24s %s\n", "id", "name"); + for_each_machine(mach) + pr_err("%-24s %s\n", mach->mach_id, mach->mach_name); + + return 1; +} + +__setup("machtype=", mips_machtype_setup); + +__init void mips_machine_setup(void) +{ + struct mips_machine *mach; + + for_each_machine(mach) { + if (mips_machtype == mach->mach_type) { + mips_machine = mach; + break; + } + } + + if (!mips_machine) + return; + + mips_set_machine_name(mips_machine->mach_name); + pr_info("MIPS: machine is %s\n", mips_machine_name); + + if (mips_machine->mach_setup) + mips_machine->mach_setup(); +} diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 6f51dda87fc..dd940b70196 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -30,6 +30,8 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> +#include <linux/jump_label.h> + #include <asm/pgtable.h> /* MODULE_START */ struct mips_hi16 { @@ -46,17 +48,9 @@ static DEFINE_SPINLOCK(dbe_lock); void *module_alloc(unsigned long size) { #ifdef MODULE_START - struct vm_struct *area; - - size = PAGE_ALIGN(size); - if (!size) - return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULE_START, MODULE_END); - if (!area) - return NULL; - - return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL); + return __vmalloc_node_range(size, 1, MODULE_START, MODULE_END, + GFP_KERNEL, PAGE_KERNEL, -1, + __builtin_return_address(0)); #else if (size == 0) return NULL; @@ -390,6 +384,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *s; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + /* Make jump label nops. */ + jump_label_apply_nops(me); + INIT_LIST_HEAD(&me->arch.dbe_list); for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { if (strcmp("__dbe_table", secstrings + s->sh_name) != 0) diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c new file mode 100644 index 00000000000..a8244854d3d --- /dev/null +++ b/arch/mips/kernel/perf_event.c @@ -0,0 +1,588 @@ +/* + * Linux performance counter support for MIPS. + * + * Copyright (C) 2010 MIPS Technologies, Inc. + * Author: Deng-Cheng Zhu + * + * This code is based on the implementation for ARM, which is in turn + * based on the sparc64 perf event code and the x86 code. Performance + * counter access is based on the MIPS Oprofile code. And the callchain + * support references the code of MIPS stacktrace.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/cpumask.h> +#include <linux/interrupt.h> +#include <linux/smp.h> +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/uaccess.h> + +#include <asm/irq.h> +#include <asm/irq_regs.h> +#include <asm/stacktrace.h> +#include <asm/time.h> /* For perf_irq */ + +/* These are for 32bit counters. For 64bit ones, define them accordingly. */ +#define MAX_PERIOD ((1ULL << 32) - 1) +#define VALID_COUNT 0x7fffffff +#define TOTAL_BITS 32 +#define HIGHEST_BIT 31 + +#define MIPS_MAX_HWEVENTS 4 + +struct cpu_hw_events { + /* Array of events on this cpu. */ + struct perf_event *events[MIPS_MAX_HWEVENTS]; + + /* + * Set the bit (indexed by the counter number) when the counter + * is used for an event. + */ + unsigned long used_mask[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)]; + + /* + * The borrowed MSB for the performance counter. A MIPS performance + * counter uses its bit 31 (for 32bit counters) or bit 63 (for 64bit + * counters) as a factor of determining whether a counter overflow + * should be signaled. So here we use a separate MSB for each + * counter to make things easy. + */ + unsigned long msbs[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)]; + + /* + * Software copy of the control register for each performance counter. + * MIPS CPUs vary in performance counters. They use this differently, + * and even may not use it. + */ + unsigned int saved_ctrl[MIPS_MAX_HWEVENTS]; +}; +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { + .saved_ctrl = {0}, +}; + +/* The description of MIPS performance events. */ +struct mips_perf_event { + unsigned int event_id; + /* + * MIPS performance counters are indexed starting from 0. + * CNTR_EVEN indicates the indexes of the counters to be used are + * even numbers. + */ + unsigned int cntr_mask; + #define CNTR_EVEN 0x55555555 + #define CNTR_ODD 0xaaaaaaaa +#ifdef CONFIG_MIPS_MT_SMP + enum { + T = 0, + V = 1, + P = 2, + } range; +#else + #define T + #define V + #define P +#endif +}; + +static struct mips_perf_event raw_event; +static DEFINE_MUTEX(raw_event_mutex); + +#define UNSUPPORTED_PERF_EVENT_ID 0xffffffff +#define C(x) PERF_COUNT_HW_CACHE_##x + +struct mips_pmu { + const char *name; + int irq; + irqreturn_t (*handle_irq)(int irq, void *dev); + int (*handle_shared_irq)(void); + void (*start)(void); + void (*stop)(void); + int (*alloc_counter)(struct cpu_hw_events *cpuc, + struct hw_perf_event *hwc); + u64 (*read_counter)(unsigned int idx); + void (*write_counter)(unsigned int idx, u64 val); + void (*enable_event)(struct hw_perf_event *evt, int idx); + void (*disable_event)(int idx); + const struct mips_perf_event *(*map_raw_event)(u64 config); + const struct mips_perf_event (*general_event_map)[PERF_COUNT_HW_MAX]; + const struct mips_perf_event (*cache_event_map) + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; + unsigned int num_counters; +}; + +static const struct mips_pmu *mipspmu; + +static int +mipspmu_event_set_period(struct perf_event *event, + struct hw_perf_event *hwc, + int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + s64 left = local64_read(&hwc->period_left); + s64 period = hwc->sample_period; + int ret = 0; + u64 uleft; + unsigned long flags; + + if (unlikely(left <= -period)) { + left = period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + ret = 1; + } + + if (unlikely(left <= 0)) { + left += period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + ret = 1; + } + + if (left > (s64)MAX_PERIOD) + left = MAX_PERIOD; + + local64_set(&hwc->prev_count, (u64)-left); + + local_irq_save(flags); + uleft = (u64)(-left) & MAX_PERIOD; + uleft > VALID_COUNT ? + set_bit(idx, cpuc->msbs) : clear_bit(idx, cpuc->msbs); + mipspmu->write_counter(idx, (u64)(-left) & VALID_COUNT); + local_irq_restore(flags); + + perf_event_update_userpage(event); + + return ret; +} + +static void mipspmu_event_update(struct perf_event *event, + struct hw_perf_event *hwc, + int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long flags; + int shift = 64 - TOTAL_BITS; + s64 prev_raw_count, new_raw_count; + u64 delta; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + local_irq_save(flags); + /* Make the counter value be a "real" one. */ + new_raw_count = mipspmu->read_counter(idx); + if (new_raw_count & (test_bit(idx, cpuc->msbs) << HIGHEST_BIT)) { + new_raw_count &= VALID_COUNT; + clear_bit(idx, cpuc->msbs); + } else + new_raw_count |= (test_bit(idx, cpuc->msbs) << HIGHEST_BIT); + local_irq_restore(flags); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + goto again; + + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); + + return; +} + +static void mipspmu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!mipspmu) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + + hwc->state = 0; + + /* Set the period for the event. */ + mipspmu_event_set_period(event, hwc, hwc->idx); + + /* Enable the event. */ + mipspmu->enable_event(hwc, hwc->idx); +} + +static void mipspmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!mipspmu) + return; + + if (!(hwc->state & PERF_HES_STOPPED)) { + /* We are working on a local event. */ + mipspmu->disable_event(hwc->idx); + barrier(); + mipspmu_event_update(event, hwc, hwc->idx); + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + } +} + +static int mipspmu_add(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx; + int err = 0; + + perf_pmu_disable(event->pmu); + + /* To look for a free counter for this event. */ + idx = mipspmu->alloc_counter(cpuc, hwc); + if (idx < 0) { + err = idx; + goto out; + } + + /* + * If there is an event in the counter we are going to use then + * make sure it is disabled. + */ + event->hw.idx = idx; + mipspmu->disable_event(idx); + cpuc->events[idx] = event; + + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + if (flags & PERF_EF_START) + mipspmu_start(event, PERF_EF_RELOAD); + + /* Propagate our changes to the userspace mapping. */ + perf_event_update_userpage(event); + +out: + perf_pmu_enable(event->pmu); + return err; +} + +static void mipspmu_del(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + WARN_ON(idx < 0 || idx >= mipspmu->num_counters); + + mipspmu_stop(event, PERF_EF_UPDATE); + cpuc->events[idx] = NULL; + clear_bit(idx, cpuc->used_mask); + + perf_event_update_userpage(event); +} + +static void mipspmu_read(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* Don't read disabled counters! */ + if (hwc->idx < 0) + return; + + mipspmu_event_update(event, hwc, hwc->idx); +} + +static void mipspmu_enable(struct pmu *pmu) +{ + if (mipspmu) + mipspmu->start(); +} + +static void mipspmu_disable(struct pmu *pmu) +{ + if (mipspmu) + mipspmu->stop(); +} + +static atomic_t active_events = ATOMIC_INIT(0); +static DEFINE_MUTEX(pmu_reserve_mutex); +static int (*save_perf_irq)(void); + +static int mipspmu_get_irq(void) +{ + int err; + + if (mipspmu->irq >= 0) { + /* Request my own irq handler. */ + err = request_irq(mipspmu->irq, mipspmu->handle_irq, + IRQF_DISABLED | IRQF_NOBALANCING, + "mips_perf_pmu", NULL); + if (err) { + pr_warning("Unable to request IRQ%d for MIPS " + "performance counters!\n", mipspmu->irq); + } + } else if (cp0_perfcount_irq < 0) { + /* + * We are sharing the irq number with the timer interrupt. + */ + save_perf_irq = perf_irq; + perf_irq = mipspmu->handle_shared_irq; + err = 0; + } else { + pr_warning("The platform hasn't properly defined its " + "interrupt controller.\n"); + err = -ENOENT; + } + + return err; +} + +static void mipspmu_free_irq(void) +{ + if (mipspmu->irq >= 0) + free_irq(mipspmu->irq, NULL); + else if (cp0_perfcount_irq < 0) + perf_irq = save_perf_irq; +} + +/* + * mipsxx/rm9000/loongson2 have different performance counters, they have + * specific low-level init routines. + */ +static void reset_counters(void *arg); +static int __hw_perf_event_init(struct perf_event *event); + +static void hw_perf_event_destroy(struct perf_event *event) +{ + if (atomic_dec_and_mutex_lock(&active_events, + &pmu_reserve_mutex)) { + /* + * We must not call the destroy function with interrupts + * disabled. + */ + on_each_cpu(reset_counters, + (void *)(long)mipspmu->num_counters, 1); + mipspmu_free_irq(); + mutex_unlock(&pmu_reserve_mutex); + } +} + +static int mipspmu_event_init(struct perf_event *event) +{ + int err = 0; + + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + + if (!mipspmu || event->cpu >= nr_cpumask_bits || + (event->cpu >= 0 && !cpu_online(event->cpu))) + return -ENODEV; + + if (!atomic_inc_not_zero(&active_events)) { + if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) { + atomic_dec(&active_events); + return -ENOSPC; + } + + mutex_lock(&pmu_reserve_mutex); + if (atomic_read(&active_events) == 0) + err = mipspmu_get_irq(); + + if (!err) + atomic_inc(&active_events); + mutex_unlock(&pmu_reserve_mutex); + } + + if (err) + return err; + + err = __hw_perf_event_init(event); + if (err) + hw_perf_event_destroy(event); + + return err; +} + +static struct pmu pmu = { + .pmu_enable = mipspmu_enable, + .pmu_disable = mipspmu_disable, + .event_init = mipspmu_event_init, + .add = mipspmu_add, + .del = mipspmu_del, + .start = mipspmu_start, + .stop = mipspmu_stop, + .read = mipspmu_read, +}; + +static inline unsigned int +mipspmu_perf_event_encode(const struct mips_perf_event *pev) +{ +/* + * Top 8 bits for range, next 16 bits for cntr_mask, lowest 8 bits for + * event_id. + */ +#ifdef CONFIG_MIPS_MT_SMP + return ((unsigned int)pev->range << 24) | + (pev->cntr_mask & 0xffff00) | + (pev->event_id & 0xff); +#else + return (pev->cntr_mask & 0xffff00) | + (pev->event_id & 0xff); +#endif +} + +static const struct mips_perf_event * +mipspmu_map_general_event(int idx) +{ + const struct mips_perf_event *pev; + + pev = ((*mipspmu->general_event_map)[idx].event_id == + UNSUPPORTED_PERF_EVENT_ID ? ERR_PTR(-EOPNOTSUPP) : + &(*mipspmu->general_event_map)[idx]); + + return pev; +} + +static const struct mips_perf_event * +mipspmu_map_cache_event(u64 config) +{ + unsigned int cache_type, cache_op, cache_result; + const struct mips_perf_event *pev; + + cache_type = (config >> 0) & 0xff; + if (cache_type >= PERF_COUNT_HW_CACHE_MAX) + return ERR_PTR(-EINVAL); + + cache_op = (config >> 8) & 0xff; + if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) + return ERR_PTR(-EINVAL); + + cache_result = (config >> 16) & 0xff; + if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return ERR_PTR(-EINVAL); + + pev = &((*mipspmu->cache_event_map) + [cache_type] + [cache_op] + [cache_result]); + + if (pev->event_id == UNSUPPORTED_PERF_EVENT_ID) + return ERR_PTR(-EOPNOTSUPP); + + return pev; + +} + +static int validate_event(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event fake_hwc = event->hw; + + /* Allow mixed event group. So return 1 to pass validation. */ + if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF) + return 1; + + return mipspmu->alloc_counter(cpuc, &fake_hwc) >= 0; +} + +static int validate_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct cpu_hw_events fake_cpuc; + + memset(&fake_cpuc, 0, sizeof(fake_cpuc)); + + if (!validate_event(&fake_cpuc, leader)) + return -ENOSPC; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (!validate_event(&fake_cpuc, sibling)) + return -ENOSPC; + } + + if (!validate_event(&fake_cpuc, event)) + return -ENOSPC; + + return 0; +} + +/* This is needed by specific irq handlers in perf_event_*.c */ +static void +handle_associated_event(struct cpu_hw_events *cpuc, + int idx, struct perf_sample_data *data, struct pt_regs *regs) +{ + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc = &event->hw; + + mipspmu_event_update(event, hwc, idx); + data->period = event->hw.last_period; + if (!mipspmu_event_set_period(event, hwc, idx)) + return; + + if (perf_event_overflow(event, 0, data, regs)) + mipspmu->disable_event(idx); +} + +#include "perf_event_mipsxx.c" + +/* Callchain handling code. */ + +/* + * Leave userspace callchain empty for now. When we find a way to trace + * the user stack callchains, we add here. + */ +void perf_callchain_user(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ +} + +static void save_raw_perf_callchain(struct perf_callchain_entry *entry, + unsigned long reg29) +{ + unsigned long *sp = (unsigned long *)reg29; + unsigned long addr; + + while (!kstack_end(sp)) { + addr = *sp++; + if (__kernel_text_address(addr)) { + perf_callchain_store(entry, addr); + if (entry->nr >= PERF_MAX_STACK_DEPTH) + break; + } + } +} + +void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ + unsigned long sp = regs->regs[29]; +#ifdef CONFIG_KALLSYMS + unsigned long ra = regs->regs[31]; + unsigned long pc = regs->cp0_epc; + + if (raw_show_trace || !__kernel_text_address(pc)) { + unsigned long stack_page = + (unsigned long)task_stack_page(current); + if (stack_page && sp >= stack_page && + sp <= stack_page + THREAD_SIZE - 32) + save_raw_perf_callchain(entry, sp); + return; + } + do { + perf_callchain_store(entry, pc); + if (entry->nr >= PERF_MAX_STACK_DEPTH) + break; + pc = unwind_stack(current, &sp, pc, &ra); + } while (pc); +#else + save_raw_perf_callchain(entry, sp); +#endif +} diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c new file mode 100644 index 00000000000..75266ff4cc3 --- /dev/null +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -0,0 +1,1054 @@ +#if defined(CONFIG_CPU_MIPS32) || defined(CONFIG_CPU_MIPS64) || \ + defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_SB1) + +#define M_CONFIG1_PC (1 << 4) + +#define M_PERFCTL_EXL (1UL << 0) +#define M_PERFCTL_KERNEL (1UL << 1) +#define M_PERFCTL_SUPERVISOR (1UL << 2) +#define M_PERFCTL_USER (1UL << 3) +#define M_PERFCTL_INTERRUPT_ENABLE (1UL << 4) +#define M_PERFCTL_EVENT(event) (((event) & 0x3ff) << 5) +#define M_PERFCTL_VPEID(vpe) ((vpe) << 16) +#define M_PERFCTL_MT_EN(filter) ((filter) << 20) +#define M_TC_EN_ALL M_PERFCTL_MT_EN(0) +#define M_TC_EN_VPE M_PERFCTL_MT_EN(1) +#define M_TC_EN_TC M_PERFCTL_MT_EN(2) +#define M_PERFCTL_TCID(tcid) ((tcid) << 22) +#define M_PERFCTL_WIDE (1UL << 30) +#define M_PERFCTL_MORE (1UL << 31) + +#define M_PERFCTL_COUNT_EVENT_WHENEVER (M_PERFCTL_EXL | \ + M_PERFCTL_KERNEL | \ + M_PERFCTL_USER | \ + M_PERFCTL_SUPERVISOR | \ + M_PERFCTL_INTERRUPT_ENABLE) + +#ifdef CONFIG_MIPS_MT_SMP +#define M_PERFCTL_CONFIG_MASK 0x3fff801f +#else +#define M_PERFCTL_CONFIG_MASK 0x1f +#endif +#define M_PERFCTL_EVENT_MASK 0xfe0 + +#define M_COUNTER_OVERFLOW (1UL << 31) + +#ifdef CONFIG_MIPS_MT_SMP +static int cpu_has_mipsmt_pertccounters; + +/* + * FIXME: For VSMP, vpe_id() is redefined for Perf-events, because + * cpu_data[cpuid].vpe_id reports 0 for _both_ CPUs. + */ +#if defined(CONFIG_HW_PERF_EVENTS) +#define vpe_id() (cpu_has_mipsmt_pertccounters ? \ + 0 : smp_processor_id()) +#else +#define vpe_id() (cpu_has_mipsmt_pertccounters ? \ + 0 : cpu_data[smp_processor_id()].vpe_id) +#endif + +/* Copied from op_model_mipsxx.c */ +static inline unsigned int vpe_shift(void) +{ + if (num_possible_cpus() > 1) + return 1; + + return 0; +} +#else /* !CONFIG_MIPS_MT_SMP */ +#define vpe_id() 0 + +static inline unsigned int vpe_shift(void) +{ + return 0; +} +#endif /* CONFIG_MIPS_MT_SMP */ + +static inline unsigned int +counters_total_to_per_cpu(unsigned int counters) +{ + return counters >> vpe_shift(); +} + +static inline unsigned int +counters_per_cpu_to_total(unsigned int counters) +{ + return counters << vpe_shift(); +} + +#define __define_perf_accessors(r, n, np) \ + \ +static inline unsigned int r_c0_ ## r ## n(void) \ +{ \ + unsigned int cpu = vpe_id(); \ + \ + switch (cpu) { \ + case 0: \ + return read_c0_ ## r ## n(); \ + case 1: \ + return read_c0_ ## r ## np(); \ + default: \ + BUG(); \ + } \ + return 0; \ +} \ + \ +static inline void w_c0_ ## r ## n(unsigned int value) \ +{ \ + unsigned int cpu = vpe_id(); \ + \ + switch (cpu) { \ + case 0: \ + write_c0_ ## r ## n(value); \ + return; \ + case 1: \ + write_c0_ ## r ## np(value); \ + return; \ + default: \ + BUG(); \ + } \ + return; \ +} \ + +__define_perf_accessors(perfcntr, 0, 2) +__define_perf_accessors(perfcntr, 1, 3) +__define_perf_accessors(perfcntr, 2, 0) +__define_perf_accessors(perfcntr, 3, 1) + +__define_perf_accessors(perfctrl, 0, 2) +__define_perf_accessors(perfctrl, 1, 3) +__define_perf_accessors(perfctrl, 2, 0) +__define_perf_accessors(perfctrl, 3, 1) + +static inline int __n_counters(void) +{ + if (!(read_c0_config1() & M_CONFIG1_PC)) + return 0; + if (!(read_c0_perfctrl0() & M_PERFCTL_MORE)) + return 1; + if (!(read_c0_perfctrl1() & M_PERFCTL_MORE)) + return 2; + if (!(read_c0_perfctrl2() & M_PERFCTL_MORE)) + return 3; + + return 4; +} + +static inline int n_counters(void) +{ + int counters; + + switch (current_cpu_type()) { + case CPU_R10000: + counters = 2; + break; + + case CPU_R12000: + case CPU_R14000: + counters = 4; + break; + + default: + counters = __n_counters(); + } + + return counters; +} + +static void reset_counters(void *arg) +{ + int counters = (int)(long)arg; + switch (counters) { + case 4: + w_c0_perfctrl3(0); + w_c0_perfcntr3(0); + case 3: + w_c0_perfctrl2(0); + w_c0_perfcntr2(0); + case 2: + w_c0_perfctrl1(0); + w_c0_perfcntr1(0); + case 1: + w_c0_perfctrl0(0); + w_c0_perfcntr0(0); + } +} + +static inline u64 +mipsxx_pmu_read_counter(unsigned int idx) +{ + switch (idx) { + case 0: + return r_c0_perfcntr0(); + case 1: + return r_c0_perfcntr1(); + case 2: + return r_c0_perfcntr2(); + case 3: + return r_c0_perfcntr3(); + default: + WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx); + return 0; + } +} + +static inline void +mipsxx_pmu_write_counter(unsigned int idx, u64 val) +{ + switch (idx) { + case 0: + w_c0_perfcntr0(val); + return; + case 1: + w_c0_perfcntr1(val); + return; + case 2: + w_c0_perfcntr2(val); + return; + case 3: + w_c0_perfcntr3(val); + return; + } +} + +static inline unsigned int +mipsxx_pmu_read_control(unsigned int idx) +{ + switch (idx) { + case 0: + return r_c0_perfctrl0(); + case 1: + return r_c0_perfctrl1(); + case 2: + return r_c0_perfctrl2(); + case 3: + return r_c0_perfctrl3(); + default: + WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx); + return 0; + } +} + +static inline void +mipsxx_pmu_write_control(unsigned int idx, unsigned int val) +{ + switch (idx) { + case 0: + w_c0_perfctrl0(val); + return; + case 1: + w_c0_perfctrl1(val); + return; + case 2: + w_c0_perfctrl2(val); + return; + case 3: + w_c0_perfctrl3(val); + return; + } +} + +#ifdef CONFIG_MIPS_MT_SMP +static DEFINE_RWLOCK(pmuint_rwlock); +#endif + +/* 24K/34K/1004K cores can share the same event map. */ +static const struct mips_perf_event mipsxxcore_event_map + [PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD, P }, + [PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD, T }, + [PERF_COUNT_HW_CACHE_REFERENCES] = { UNSUPPORTED_PERF_EVENT_ID }, + [PERF_COUNT_HW_CACHE_MISSES] = { UNSUPPORTED_PERF_EVENT_ID }, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x02, CNTR_EVEN, T }, + [PERF_COUNT_HW_BRANCH_MISSES] = { 0x02, CNTR_ODD, T }, + [PERF_COUNT_HW_BUS_CYCLES] = { UNSUPPORTED_PERF_EVENT_ID }, +}; + +/* 74K core has different branch event code. */ +static const struct mips_perf_event mipsxx74Kcore_event_map + [PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD, P }, + [PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD, T }, + [PERF_COUNT_HW_CACHE_REFERENCES] = { UNSUPPORTED_PERF_EVENT_ID }, + [PERF_COUNT_HW_CACHE_MISSES] = { UNSUPPORTED_PERF_EVENT_ID }, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x27, CNTR_EVEN, T }, + [PERF_COUNT_HW_BRANCH_MISSES] = { 0x27, CNTR_ODD, T }, + [PERF_COUNT_HW_BUS_CYCLES] = { UNSUPPORTED_PERF_EVENT_ID }, +}; + +/* 24K/34K/1004K cores can share the same cache event map. */ +static const struct mips_perf_event mipsxxcore_cache_map + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { +[C(L1D)] = { + /* + * Like some other architectures (e.g. ARM), the performance + * counters don't differentiate between read and write + * accesses/misses, so this isn't strictly correct, but it's the + * best we can do. Writes and reads get combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x0a, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x0b, CNTR_EVEN | CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x0a, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x0b, CNTR_EVEN | CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x09, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x09, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x09, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x09, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { 0x14, CNTR_EVEN, T }, + /* + * Note that MIPS has only "hit" events countable for + * the prefetch operation. + */ + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x15, CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x16, CNTR_EVEN, P }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x15, CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x16, CNTR_EVEN, P }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x06, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x06, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x06, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x06, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x05, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x05, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x05, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x05, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(BPU)] = { + /* Using the same code for *HW_BRANCH* */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x02, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x02, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x02, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x02, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +}; + +/* 74K core has completely different cache event map. */ +static const struct mips_perf_event mipsxx74Kcore_cache_map + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { +[C(L1D)] = { + /* + * Like some other architectures (e.g. ARM), the performance + * counters don't differentiate between read and write + * accesses/misses, so this isn't strictly correct, but it's the + * best we can do. Writes and reads get combined. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x17, CNTR_ODD, T }, + [C(RESULT_MISS)] = { 0x18, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x17, CNTR_ODD, T }, + [C(RESULT_MISS)] = { 0x18, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x06, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x06, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x06, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x06, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { 0x34, CNTR_EVEN, T }, + /* + * Note that MIPS has only "hit" events countable for + * the prefetch operation. + */ + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x1c, CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN | CNTR_ODD, P }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x1c, CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN | CNTR_ODD, P }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(DTLB)] = { + /* 74K core does not have specific DTLB events. */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x04, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x04, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x04, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x04, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +[C(BPU)] = { + /* Using the same code for *HW_BRANCH* */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { 0x27, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x27, CNTR_ODD, T }, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = { 0x27, CNTR_EVEN, T }, + [C(RESULT_MISS)] = { 0x27, CNTR_ODD, T }, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID }, + [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID }, + }, +}, +}; + +#ifdef CONFIG_MIPS_MT_SMP +static void +check_and_calc_range(struct perf_event *event, + const struct mips_perf_event *pev) +{ + struct hw_perf_event *hwc = &event->hw; + + if (event->cpu >= 0) { + if (pev->range > V) { + /* + * The user selected an event that is processor + * wide, while expecting it to be VPE wide. + */ + hwc->config_base |= M_TC_EN_ALL; + } else { + /* + * FIXME: cpu_data[event->cpu].vpe_id reports 0 + * for both CPUs. + */ + hwc->config_base |= M_PERFCTL_VPEID(event->cpu); + hwc->config_base |= M_TC_EN_VPE; + } + } else + hwc->config_base |= M_TC_EN_ALL; +} +#else +static void +check_and_calc_range(struct perf_event *event, + const struct mips_perf_event *pev) +{ +} +#endif + +static int __hw_perf_event_init(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + const struct mips_perf_event *pev; + int err; + + /* Returning MIPS event descriptor for generic perf event. */ + if (PERF_TYPE_HARDWARE == event->attr.type) { + if (event->attr.config >= PERF_COUNT_HW_MAX) + return -EINVAL; + pev = mipspmu_map_general_event(event->attr.config); + } else if (PERF_TYPE_HW_CACHE == event->attr.type) { + pev = mipspmu_map_cache_event(event->attr.config); + } else if (PERF_TYPE_RAW == event->attr.type) { + /* We are working on the global raw event. */ + mutex_lock(&raw_event_mutex); + pev = mipspmu->map_raw_event(event->attr.config); + } else { + /* The event type is not (yet) supported. */ + return -EOPNOTSUPP; + } + + if (IS_ERR(pev)) { + if (PERF_TYPE_RAW == event->attr.type) + mutex_unlock(&raw_event_mutex); + return PTR_ERR(pev); + } + + /* + * We allow max flexibility on how each individual counter shared + * by the single CPU operates (the mode exclusion and the range). + */ + hwc->config_base = M_PERFCTL_INTERRUPT_ENABLE; + + /* Calculate range bits and validate it. */ + if (num_possible_cpus() > 1) + check_and_calc_range(event, pev); + + hwc->event_base = mipspmu_perf_event_encode(pev); + if (PERF_TYPE_RAW == event->attr.type) + mutex_unlock(&raw_event_mutex); + + if (!attr->exclude_user) + hwc->config_base |= M_PERFCTL_USER; + if (!attr->exclude_kernel) { + hwc->config_base |= M_PERFCTL_KERNEL; + /* MIPS kernel mode: KSU == 00b || EXL == 1 || ERL == 1 */ + hwc->config_base |= M_PERFCTL_EXL; + } + if (!attr->exclude_hv) + hwc->config_base |= M_PERFCTL_SUPERVISOR; + + hwc->config_base &= M_PERFCTL_CONFIG_MASK; + /* + * The event can belong to another cpu. We do not assign a local + * counter for it for now. + */ + hwc->idx = -1; + hwc->config = 0; + + if (!hwc->sample_period) { + hwc->sample_period = MAX_PERIOD; + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + } + + err = 0; + if (event->group_leader != event) { + err = validate_group(event); + if (err) + return -EINVAL; + } + + event->destroy = hw_perf_event_destroy; + + return err; +} + +static void pause_local_counters(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int counters = mipspmu->num_counters; + unsigned long flags; + + local_irq_save(flags); + switch (counters) { + case 4: + cpuc->saved_ctrl[3] = r_c0_perfctrl3(); + w_c0_perfctrl3(cpuc->saved_ctrl[3] & + ~M_PERFCTL_COUNT_EVENT_WHENEVER); + case 3: + cpuc->saved_ctrl[2] = r_c0_perfctrl2(); + w_c0_perfctrl2(cpuc->saved_ctrl[2] & + ~M_PERFCTL_COUNT_EVENT_WHENEVER); + case 2: + cpuc->saved_ctrl[1] = r_c0_perfctrl1(); + w_c0_perfctrl1(cpuc->saved_ctrl[1] & + ~M_PERFCTL_COUNT_EVENT_WHENEVER); + case 1: + cpuc->saved_ctrl[0] = r_c0_perfctrl0(); + w_c0_perfctrl0(cpuc->saved_ctrl[0] & + ~M_PERFCTL_COUNT_EVENT_WHENEVER); + } + local_irq_restore(flags); +} + +static void resume_local_counters(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int counters = mipspmu->num_counters; + unsigned long flags; + + local_irq_save(flags); + switch (counters) { + case 4: + w_c0_perfctrl3(cpuc->saved_ctrl[3]); + case 3: + w_c0_perfctrl2(cpuc->saved_ctrl[2]); + case 2: + w_c0_perfctrl1(cpuc->saved_ctrl[1]); + case 1: + w_c0_perfctrl0(cpuc->saved_ctrl[0]); + } + local_irq_restore(flags); +} + +static int mipsxx_pmu_handle_shared_irq(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct perf_sample_data data; + unsigned int counters = mipspmu->num_counters; + unsigned int counter; + int handled = IRQ_NONE; + struct pt_regs *regs; + + if (cpu_has_mips_r2 && !(read_c0_cause() & (1 << 26))) + return handled; + + /* + * First we pause the local counters, so that when we are locked + * here, the counters are all paused. When it gets locked due to + * perf_disable(), the timer interrupt handler will be delayed. + * + * See also mipsxx_pmu_start(). + */ + pause_local_counters(); +#ifdef CONFIG_MIPS_MT_SMP + read_lock(&pmuint_rwlock); +#endif + + regs = get_irq_regs(); + + perf_sample_data_init(&data, 0); + + switch (counters) { +#define HANDLE_COUNTER(n) \ + case n + 1: \ + if (test_bit(n, cpuc->used_mask)) { \ + counter = r_c0_perfcntr ## n(); \ + if (counter & M_COUNTER_OVERFLOW) { \ + w_c0_perfcntr ## n(counter & \ + VALID_COUNT); \ + if (test_and_change_bit(n, cpuc->msbs)) \ + handle_associated_event(cpuc, \ + n, &data, regs); \ + handled = IRQ_HANDLED; \ + } \ + } + HANDLE_COUNTER(3) + HANDLE_COUNTER(2) + HANDLE_COUNTER(1) + HANDLE_COUNTER(0) + } + + /* + * Do all the work for the pending perf events. We can do this + * in here because the performance counter interrupt is a regular + * interrupt, not NMI. + */ + if (handled == IRQ_HANDLED) + irq_work_run(); + +#ifdef CONFIG_MIPS_MT_SMP + read_unlock(&pmuint_rwlock); +#endif + resume_local_counters(); + return handled; +} + +static irqreturn_t +mipsxx_pmu_handle_irq(int irq, void *dev) +{ + return mipsxx_pmu_handle_shared_irq(); +} + +static void mipsxx_pmu_start(void) +{ +#ifdef CONFIG_MIPS_MT_SMP + write_unlock(&pmuint_rwlock); +#endif + resume_local_counters(); +} + +/* + * MIPS performance counters can be per-TC. The control registers can + * not be directly accessed across CPUs. Hence if we want to do global + * control, we need cross CPU calls. on_each_cpu() can help us, but we + * can not make sure this function is called with interrupts enabled. So + * here we pause local counters and then grab a rwlock and leave the + * counters on other CPUs alone. If any counter interrupt raises while + * we own the write lock, simply pause local counters on that CPU and + * spin in the handler. Also we know we won't be switched to another + * CPU after pausing local counters and before grabbing the lock. + */ +static void mipsxx_pmu_stop(void) +{ + pause_local_counters(); +#ifdef CONFIG_MIPS_MT_SMP + write_lock(&pmuint_rwlock); +#endif +} + +static int +mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc, + struct hw_perf_event *hwc) +{ + int i; + + /* + * We only need to care the counter mask. The range has been + * checked definitely. + */ + unsigned long cntr_mask = (hwc->event_base >> 8) & 0xffff; + + for (i = mipspmu->num_counters - 1; i >= 0; i--) { + /* + * Note that some MIPS perf events can be counted by both + * even and odd counters, wheresas many other are only by + * even _or_ odd counters. This introduces an issue that + * when the former kind of event takes the counter the + * latter kind of event wants to use, then the "counter + * allocation" for the latter event will fail. In fact if + * they can be dynamically swapped, they both feel happy. + * But here we leave this issue alone for now. + */ + if (test_bit(i, &cntr_mask) && + !test_and_set_bit(i, cpuc->used_mask)) + return i; + } + + return -EAGAIN; +} + +static void +mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long flags; + + WARN_ON(idx < 0 || idx >= mipspmu->num_counters); + + local_irq_save(flags); + cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) | + (evt->config_base & M_PERFCTL_CONFIG_MASK) | + /* Make sure interrupt enabled. */ + M_PERFCTL_INTERRUPT_ENABLE; + /* + * We do not actually let the counter run. Leave it until start(). + */ + local_irq_restore(flags); +} + +static void +mipsxx_pmu_disable_event(int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long flags; + + WARN_ON(idx < 0 || idx >= mipspmu->num_counters); + + local_irq_save(flags); + cpuc->saved_ctrl[idx] = mipsxx_pmu_read_control(idx) & + ~M_PERFCTL_COUNT_EVENT_WHENEVER; + mipsxx_pmu_write_control(idx, cpuc->saved_ctrl[idx]); + local_irq_restore(flags); +} + +/* 24K */ +#define IS_UNSUPPORTED_24K_EVENT(r, b) \ + ((b) == 12 || (r) == 151 || (r) == 152 || (b) == 26 || \ + (b) == 27 || (r) == 28 || (r) == 158 || (b) == 31 || \ + (b) == 32 || (b) == 34 || (b) == 36 || (r) == 168 || \ + (r) == 172 || (b) == 47 || ((b) >= 56 && (b) <= 63) || \ + ((b) >= 68 && (b) <= 127)) +#define IS_BOTH_COUNTERS_24K_EVENT(b) \ + ((b) == 0 || (b) == 1 || (b) == 11) + +/* 34K */ +#define IS_UNSUPPORTED_34K_EVENT(r, b) \ + ((b) == 12 || (r) == 27 || (r) == 158 || (b) == 36 || \ + (b) == 38 || (r) == 175 || ((b) >= 56 && (b) <= 63) || \ + ((b) >= 68 && (b) <= 127)) +#define IS_BOTH_COUNTERS_34K_EVENT(b) \ + ((b) == 0 || (b) == 1 || (b) == 11) +#ifdef CONFIG_MIPS_MT_SMP +#define IS_RANGE_P_34K_EVENT(r, b) \ + ((b) == 0 || (r) == 18 || (b) == 21 || (b) == 22 || \ + (b) == 25 || (b) == 39 || (r) == 44 || (r) == 174 || \ + (r) == 176 || ((b) >= 50 && (b) <= 55) || \ + ((b) >= 64 && (b) <= 67)) +#define IS_RANGE_V_34K_EVENT(r) ((r) == 47) +#endif + +/* 74K */ +#define IS_UNSUPPORTED_74K_EVENT(r, b) \ + ((r) == 5 || ((r) >= 135 && (r) <= 137) || \ + ((b) >= 10 && (b) <= 12) || (b) == 22 || (b) == 27 || \ + (b) == 33 || (b) == 34 || ((b) >= 47 && (b) <= 49) || \ + (r) == 178 || (b) == 55 || (b) == 57 || (b) == 60 || \ + (b) == 61 || (r) == 62 || (r) == 191 || \ + ((b) >= 64 && (b) <= 127)) +#define IS_BOTH_COUNTERS_74K_EVENT(b) \ + ((b) == 0 || (b) == 1) + +/* 1004K */ +#define IS_UNSUPPORTED_1004K_EVENT(r, b) \ + ((b) == 12 || (r) == 27 || (r) == 158 || (b) == 38 || \ + (r) == 175 || (b) == 63 || ((b) >= 68 && (b) <= 127)) +#define IS_BOTH_COUNTERS_1004K_EVENT(b) \ + ((b) == 0 || (b) == 1 || (b) == 11) +#ifdef CONFIG_MIPS_MT_SMP +#define IS_RANGE_P_1004K_EVENT(r, b) \ + ((b) == 0 || (r) == 18 || (b) == 21 || (b) == 22 || \ + (b) == 25 || (b) == 36 || (b) == 39 || (r) == 44 || \ + (r) == 174 || (r) == 176 || ((b) >= 50 && (b) <= 59) || \ + (r) == 188 || (b) == 61 || (b) == 62 || \ + ((b) >= 64 && (b) <= 67)) +#define IS_RANGE_V_1004K_EVENT(r) ((r) == 47) +#endif + +/* + * User can use 0-255 raw events, where 0-127 for the events of even + * counters, and 128-255 for odd counters. Note that bit 7 is used to + * indicate the parity. So, for example, when user wants to take the + * Event Num of 15 for odd counters (by referring to the user manual), + * then 128 needs to be added to 15 as the input for the event config, + * i.e., 143 (0x8F) to be used. + */ +static const struct mips_perf_event * +mipsxx_pmu_map_raw_event(u64 config) +{ + unsigned int raw_id = config & 0xff; + unsigned int base_id = raw_id & 0x7f; + + switch (current_cpu_type()) { + case CPU_24K: + if (IS_UNSUPPORTED_24K_EVENT(raw_id, base_id)) + return ERR_PTR(-EOPNOTSUPP); + raw_event.event_id = base_id; + if (IS_BOTH_COUNTERS_24K_EVENT(base_id)) + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + else + raw_event.cntr_mask = + raw_id > 127 ? CNTR_ODD : CNTR_EVEN; +#ifdef CONFIG_MIPS_MT_SMP + /* + * This is actually doing nothing. Non-multithreading + * CPUs will not check and calculate the range. + */ + raw_event.range = P; +#endif + break; + case CPU_34K: + if (IS_UNSUPPORTED_34K_EVENT(raw_id, base_id)) + return ERR_PTR(-EOPNOTSUPP); + raw_event.event_id = base_id; + if (IS_BOTH_COUNTERS_34K_EVENT(base_id)) + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + else + raw_event.cntr_mask = + raw_id > 127 ? CNTR_ODD : CNTR_EVEN; +#ifdef CONFIG_MIPS_MT_SMP + if (IS_RANGE_P_34K_EVENT(raw_id, base_id)) + raw_event.range = P; + else if (unlikely(IS_RANGE_V_34K_EVENT(raw_id))) + raw_event.range = V; + else + raw_event.range = T; +#endif + break; + case CPU_74K: + if (IS_UNSUPPORTED_74K_EVENT(raw_id, base_id)) + return ERR_PTR(-EOPNOTSUPP); + raw_event.event_id = base_id; + if (IS_BOTH_COUNTERS_74K_EVENT(base_id)) + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + else + raw_event.cntr_mask = + raw_id > 127 ? CNTR_ODD : CNTR_EVEN; +#ifdef CONFIG_MIPS_MT_SMP + raw_event.range = P; +#endif + break; + case CPU_1004K: + if (IS_UNSUPPORTED_1004K_EVENT(raw_id, base_id)) + return ERR_PTR(-EOPNOTSUPP); + raw_event.event_id = base_id; + if (IS_BOTH_COUNTERS_1004K_EVENT(base_id)) + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + else + raw_event.cntr_mask = + raw_id > 127 ? CNTR_ODD : CNTR_EVEN; +#ifdef CONFIG_MIPS_MT_SMP + if (IS_RANGE_P_1004K_EVENT(raw_id, base_id)) + raw_event.range = P; + else if (unlikely(IS_RANGE_V_1004K_EVENT(raw_id))) + raw_event.range = V; + else + raw_event.range = T; +#endif + break; + } + + return &raw_event; +} + +static struct mips_pmu mipsxxcore_pmu = { + .handle_irq = mipsxx_pmu_handle_irq, + .handle_shared_irq = mipsxx_pmu_handle_shared_irq, + .start = mipsxx_pmu_start, + .stop = mipsxx_pmu_stop, + .alloc_counter = mipsxx_pmu_alloc_counter, + .read_counter = mipsxx_pmu_read_counter, + .write_counter = mipsxx_pmu_write_counter, + .enable_event = mipsxx_pmu_enable_event, + .disable_event = mipsxx_pmu_disable_event, + .map_raw_event = mipsxx_pmu_map_raw_event, + .general_event_map = &mipsxxcore_event_map, + .cache_event_map = &mipsxxcore_cache_map, +}; + +static struct mips_pmu mipsxx74Kcore_pmu = { + .handle_irq = mipsxx_pmu_handle_irq, + .handle_shared_irq = mipsxx_pmu_handle_shared_irq, + .start = mipsxx_pmu_start, + .stop = mipsxx_pmu_stop, + .alloc_counter = mipsxx_pmu_alloc_counter, + .read_counter = mipsxx_pmu_read_counter, + .write_counter = mipsxx_pmu_write_counter, + .enable_event = mipsxx_pmu_enable_event, + .disable_event = mipsxx_pmu_disable_event, + .map_raw_event = mipsxx_pmu_map_raw_event, + .general_event_map = &mipsxx74Kcore_event_map, + .cache_event_map = &mipsxx74Kcore_cache_map, +}; + +static int __init +init_hw_perf_events(void) +{ + int counters, irq; + + pr_info("Performance counters: "); + + counters = n_counters(); + if (counters == 0) { + pr_cont("No available PMU.\n"); + return -ENODEV; + } + +#ifdef CONFIG_MIPS_MT_SMP + cpu_has_mipsmt_pertccounters = read_c0_config7() & (1<<19); + if (!cpu_has_mipsmt_pertccounters) + counters = counters_total_to_per_cpu(counters); +#endif + +#ifdef MSC01E_INT_BASE + if (cpu_has_veic) { + /* + * Using platform specific interrupt controller defines. + */ + irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR; + } else { +#endif + if (cp0_perfcount_irq >= 0) + irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq; + else + irq = -1; +#ifdef MSC01E_INT_BASE + } +#endif + + on_each_cpu(reset_counters, (void *)(long)counters, 1); + + switch (current_cpu_type()) { + case CPU_24K: + mipsxxcore_pmu.name = "mips/24K"; + mipsxxcore_pmu.num_counters = counters; + mipsxxcore_pmu.irq = irq; + mipspmu = &mipsxxcore_pmu; + break; + case CPU_34K: + mipsxxcore_pmu.name = "mips/34K"; + mipsxxcore_pmu.num_counters = counters; + mipsxxcore_pmu.irq = irq; + mipspmu = &mipsxxcore_pmu; + break; + case CPU_74K: + mipsxx74Kcore_pmu.name = "mips/74K"; + mipsxx74Kcore_pmu.num_counters = counters; + mipsxx74Kcore_pmu.irq = irq; + mipspmu = &mipsxx74Kcore_pmu; + break; + case CPU_1004K: + mipsxxcore_pmu.name = "mips/1004K"; + mipsxxcore_pmu.num_counters = counters; + mipsxxcore_pmu.irq = irq; + mipspmu = &mipsxxcore_pmu; + break; + default: + pr_cont("Either hardware does not support performance " + "counters, or not yet implemented.\n"); + return -ENODEV; + } + + if (mipspmu) + pr_cont("%s PMU enabled, %d counters available to each " + "CPU, irq %d%s\n", mipspmu->name, counters, irq, + irq < 0 ? " (share with timer interrupt)" : ""); + + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); + + return 0; +} +early_initcall(init_hw_perf_events); + +#endif /* defined(CONFIG_CPU_MIPS32)... */ diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 26109c4d517..e309665b6c8 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -12,6 +12,7 @@ #include <asm/cpu-features.h> #include <asm/mipsregs.h> #include <asm/processor.h> +#include <asm/mips_machine.h> unsigned int vced_count, vcei_count; @@ -31,8 +32,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* * For the first processor also print the system type */ - if (n == 0) + if (n == 0) { seq_printf(m, "system type\t\t: %s\n", get_system_type()); + if (mips_get_machine_name()) + seq_printf(m, "machine\t\t\t: %s\n", + mips_get_machine_name()); + } seq_printf(m, "processor\t\t: %ld\n", n); sprintf(fmt, "cpu model\t\t: %%s V%%d.%%d%s\n", @@ -69,6 +74,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) ); seq_printf(m, "shadow register sets\t: %d\n", cpu_data[n].srsets); + seq_printf(m, "kscratch registers\t: %d\n", + hweight8(cpu_data[n].kscratch_mask)); seq_printf(m, "core\t\t\t: %d\n", cpu_data[n].core); sprintf(fmt, "VCE%%c exceptions\t\t: %s\n", diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 99960940d4a..d2112d3cf11 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -142,7 +142,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs->regs[7] = 0; /* Clear error flag */ childregs->regs[2] = 0; /* Child gets zero as return value */ - regs->regs[2] = p->pid; if (childregs->cp0_status & ST0_CU0) { childregs->regs[28] = (unsigned long) ti; @@ -411,7 +410,7 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, if (!kallsyms_lookup_size_offset(pc, &size, &ofs)) return 0; /* - * Return ra if an exception occured at the first instruction + * Return ra if an exception occurred at the first instruction */ if (unlikely(ofs == 0)) { pc = *ra; diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index e000b278f02..a19811e98a4 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -45,11 +45,9 @@ void __init free_mem_mach(unsigned long addr, unsigned long size) return free_bootmem(addr, size); } -u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align) +void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - return virt_to_phys( - __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)) - ); + return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } #ifdef CONFIG_BLK_DEV_INITRD @@ -100,7 +98,7 @@ void __init device_tree_init(void) return; base = virt_to_phys((void *)initial_boot_params); - size = initial_boot_params->totalsize; + size = be32_to_cpu(initial_boot_params->totalsize); /* Before we do anything, lets reserve the dt blob */ reserve_mem_mach(base, size); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index c8777333e19..4e6ea1ffad4 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -255,9 +255,13 @@ int ptrace_set_watch_regs(struct task_struct *child, return 0; } -long arch_ptrace(struct task_struct *child, long request, long addr, long data) +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) { int ret; + void __user *addrp = (void __user *) addr; + void __user *datavp = (void __user *) data; + unsigned long __user *datalp = (void __user *) data; switch (request) { /* when I and D space are separate, these will need to be fixed. */ @@ -386,7 +390,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = -EIO; goto out; } - ret = put_user(tmp, (unsigned long __user *) data); + ret = put_user(tmp, datalp); break; } @@ -478,34 +482,31 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } case PTRACE_GETREGS: - ret = ptrace_getregs(child, (__s64 __user *) data); + ret = ptrace_getregs(child, datavp); break; case PTRACE_SETREGS: - ret = ptrace_setregs(child, (__s64 __user *) data); + ret = ptrace_setregs(child, datavp); break; case PTRACE_GETFPREGS: - ret = ptrace_getfpregs(child, (__u32 __user *) data); + ret = ptrace_getfpregs(child, datavp); break; case PTRACE_SETFPREGS: - ret = ptrace_setfpregs(child, (__u32 __user *) data); + ret = ptrace_setfpregs(child, datavp); break; case PTRACE_GET_THREAD_AREA: - ret = put_user(task_thread_info(child)->tp_value, - (unsigned long __user *) data); + ret = put_user(task_thread_info(child)->tp_value, datalp); break; case PTRACE_GET_WATCH_REGS: - ret = ptrace_get_watch_regs(child, - (struct pt_watch_regs __user *) addr); + ret = ptrace_get_watch_regs(child, addrp); break; case PTRACE_SET_WATCH_REGS: - ret = ptrace_set_watch_regs(child, - (struct pt_watch_regs __user *) addr); + ret = ptrace_set_watch_regs(child, addrp); break; default: @@ -532,15 +533,10 @@ static inline int audit_arch(void) * Notification of system call entry/exit * - triggered by current->work.syscall_trace */ -asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) +asmlinkage void syscall_trace_enter(struct pt_regs *regs) { /* do the secure computing check first */ - if (!entryexit) - secure_computing(regs->regs[2]); - - if (unlikely(current->audit_context) && entryexit) - audit_syscall_exit(AUDITSC_RESULT(regs->regs[2]), - regs->regs[2]); + secure_computing(regs->regs[2]); if (!(current->ptrace & PT_PTRACED)) goto out; @@ -564,8 +560,40 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) } out: - if (unlikely(current->audit_context) && !entryexit) + if (unlikely(current->audit_context)) audit_syscall_entry(audit_arch(), regs->regs[2], regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); } + +/* + * Notification of system call entry/exit + * - triggered by current->work.syscall_trace + */ +asmlinkage void syscall_trace_leave(struct pt_regs *regs) +{ + if (unlikely(current->audit_context)) + audit_syscall_exit(AUDITSC_RESULT(regs->regs[7]), + -regs->regs[2]); + + if (!(current->ptrace & PT_PTRACED)) + return; + + if (!test_thread_flag(TIF_SYSCALL_TRACE)) + return; + + /* The 0x80 provides a way for the tracing parent to distinguish + between a syscall stop and SIGTRAP delivery */ + ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? + 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } +} diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index fbaabad0e6e..7a8e1dd7f6f 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -88,8 +88,7 @@ syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - li a1, 0 - jal do_syscall_trace + jal syscall_trace_enter move t0, s0 RESTORE_STATIC @@ -565,7 +564,7 @@ einval: li v0, -ENOSYS sys sys_ioprio_get 2 /* 4315 */ sys sys_utimensat 4 sys sys_signalfd 3 - sys sys_ni_syscall 0 + sys sys_ni_syscall 0 /* was timerfd */ sys sys_eventfd 1 sys sys_fallocate 6 /* 4320 */ sys sys_timerfd_create 2 @@ -586,6 +585,10 @@ einval: li v0, -ENOSYS sys sys_fanotify_init 2 sys sys_fanotify_mark 6 sys sys_prlimit64 4 + sys sys_name_to_handle_at 5 + sys sys_open_by_handle_at 3 /* 4340 */ + sys sys_clock_adjtime 2 + sys sys_syncfs 1 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 3f417928320..2d31c83224f 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -91,8 +91,7 @@ syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - li a1, 0 - jal do_syscall_trace + jal syscall_trace_enter move t0, s0 RESTORE_STATIC @@ -404,7 +403,7 @@ sys_call_table: PTR sys_ioprio_get PTR sys_utimensat /* 5275 */ PTR sys_signalfd - PTR sys_ni_syscall + PTR sys_ni_syscall /* was timerfd */ PTR sys_eventfd PTR sys_fallocate PTR sys_timerfd_create /* 5280 */ @@ -425,4 +424,8 @@ sys_call_table: PTR sys_fanotify_init /* 5295 */ PTR sys_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR sys_open_by_handle_at + PTR sys_clock_adjtime /* 5300 */ + PTR sys_syncfs .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f08ece6d8ac..38a0503b9a4 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -89,8 +89,7 @@ n32_syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - li a1, 0 - jal do_syscall_trace + jal syscall_trace_enter move t0, s0 RESTORE_STATIC @@ -403,7 +402,7 @@ EXPORT(sysn32_call_table) PTR sys_ioprio_get PTR compat_sys_utimensat PTR compat_sys_signalfd /* 6280 */ - PTR sys_ni_syscall + PTR sys_ni_syscall /* was timerfd */ PTR sys_eventfd PTR sys_fallocate PTR sys_timerfd_create @@ -425,4 +424,8 @@ EXPORT(sysn32_call_table) PTR sys_fanotify_init /* 6300 */ PTR sys_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR sys_open_by_handle_at + PTR compat_sys_clock_adjtime /* 6305 */ + PTR sys_syncfs .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 78d768a3e19..91ea5e4041d 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -123,8 +123,7 @@ trace_a_syscall: move s0, t2 # Save syscall pointer move a0, sp - li a1, 0 - jal do_syscall_trace + jal syscall_trace_enter move t0, s0 RESTORE_STATIC @@ -522,7 +521,7 @@ sys_call_table: PTR sys_ioprio_get /* 4315 */ PTR compat_sys_utimensat PTR compat_sys_signalfd - PTR sys_ni_syscall + PTR sys_ni_syscall /* was timerfd */ PTR sys_eventfd PTR sys32_fallocate /* 4320 */ PTR sys_timerfd_create @@ -543,4 +542,8 @@ sys_call_table: PTR sys_fanotify_init PTR sys_32_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR compat_sys_open_by_handle_at /* 4340 */ + PTR compat_sys_clock_adjtime + PTR sys_syncfs .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index a6b900f2962..8ad1d5679f1 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -70,7 +70,7 @@ static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; * mips_io_port_base is the begin of the address space to which x86 style * I/O ports are mapped. */ -const unsigned long mips_io_port_base __read_mostly = -1; +const unsigned long mips_io_port_base = -1; EXPORT_SYMBOL(mips_io_port_base); static struct resource code_resource = { .name = "Kernel code", }; @@ -490,6 +490,7 @@ static void __init arch_mem_init(char **cmdline_p) bootmem_init(); device_tree_init(); sparse_init(); + plat_swiotlb_setup(); paging_init(); } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 5922342bca3..dbbe0ce48d8 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -84,7 +84,7 @@ static int protected_save_fp_context(struct sigcontext __user *sc) static int protected_restore_fp_context(struct sigcontext __user *sc) { - int err, tmp; + int err, tmp __maybe_unused; while (1) { lock_fpu_owner(); own_fpu_inatomic(0); diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index a0ed0e052b2..aae98661379 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -115,7 +115,7 @@ static int protected_save_fp_context32(struct sigcontext32 __user *sc) static int protected_restore_fp_context32(struct sigcontext32 __user *sc) { - int err, tmp; + int err, tmp __maybe_unused; while (1) { lock_fpu_owner(); own_fpu_inatomic(0); diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index 43e7cdc5ded..1ec56e635d0 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -120,7 +120,7 @@ static void vsmp_send_ipi_single(int cpu, unsigned int action) local_irq_save(flags); - vpflags = dvpe(); /* cant access the other CPU's registers whilst MVPE enabled */ + vpflags = dvpe(); /* can't access the other CPU's registers whilst MVPE enabled */ switch (action) { case SMP_CALL_FUNCTION: @@ -153,7 +153,7 @@ static void __cpuinit vsmp_init_secondary(void) { extern int gic_present; - /* This is Malta specific: IPI,performance and timer inetrrupts */ + /* This is Malta specific: IPI,performance and timer interrupts */ if (gic_present) change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 | STATUSF_IP7); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 383aeb95cb4..32a25610108 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -193,6 +193,22 @@ void __devinit smp_prepare_boot_cpu(void) */ static struct task_struct *cpu_idle_thread[NR_CPUS]; +struct create_idle { + struct work_struct work; + struct task_struct *idle; + struct completion done; + int cpu; +}; + +static void __cpuinit do_fork_idle(struct work_struct *work) +{ + struct create_idle *c_idle = + container_of(work, struct create_idle, work); + + c_idle->idle = fork_idle(c_idle->cpu); + complete(&c_idle->done); +} + int __cpuinit __cpu_up(unsigned int cpu) { struct task_struct *idle; @@ -203,8 +219,19 @@ int __cpuinit __cpu_up(unsigned int cpu) * Linux can schedule processes on this slave. */ if (!cpu_idle_thread[cpu]) { - idle = fork_idle(cpu); - cpu_idle_thread[cpu] = idle; + /* + * Schedule work item to avoid forking user task + * Ported from arch/x86/kernel/smpboot.c + */ + struct create_idle c_idle = { + .cpu = cpu, + .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), + }; + + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); + schedule_work(&c_idle.work); + wait_for_completion(&c_idle.done); + idle = cpu_idle_thread[cpu] = c_idle.idle; if (IS_ERR(idle)) panic(KERN_ERR "Fork failed for CPU %d", cpu); diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 39c08254b0f..cedac463374 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -677,8 +677,9 @@ void smtc_set_irq_affinity(unsigned int irq, cpumask_t affinity) */ } -void smtc_forward_irq(unsigned int irq) +void smtc_forward_irq(struct irq_data *d) { + unsigned int irq = d->irq; int target; /* @@ -692,7 +693,7 @@ void smtc_forward_irq(unsigned int irq) * and efficiency, we just pick the easiest one to find. */ - target = cpumask_first(irq_desc[irq].affinity); + target = cpumask_first(d->affinity); /* * We depend on the platform code to have correctly processed @@ -707,12 +708,10 @@ void smtc_forward_irq(unsigned int irq) */ /* If no one is eligible, service locally */ - if (target >= NR_CPUS) { + if (target >= NR_CPUS) do_IRQ_no_affinity(irq); - return; - } - - smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq); + else + smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq); } #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ @@ -930,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) static void ipi_resched_interrupt(void) { - /* Return from interrupt should be enough to cause scheduler check */ + scheduler_ipi(); } static void ipi_call_interrupt(void) @@ -1147,7 +1146,7 @@ static void setup_cross_vpe_interrupts(unsigned int nvpe) setup_irq_smtc(cpu_ipi_irq, &irq_ipi, (0x100 << MIPS_CPU_IPI_IRQ)); - set_irq_handler(cpu_ipi_irq, handle_percpu_irq); + irq_set_handler(cpu_ipi_irq, handle_percpu_irq); } /* diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 1dc6edff45e..d02765708dd 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -10,12 +10,9 @@ #include <linux/capability.h> #include <linux/errno.h> #include <linux/linkage.h> -#include <linux/mm.h> #include <linux/fs.h> #include <linux/smp.h> -#include <linux/mman.h> #include <linux/ptrace.h> -#include <linux/sched.h> #include <linux/string.h> #include <linux/syscalls.h> #include <linux/file.h> @@ -25,11 +22,9 @@ #include <linux/msg.h> #include <linux/shm.h> #include <linux/compiler.h> -#include <linux/module.h> #include <linux/ipc.h> #include <linux/uaccess.h> #include <linux/slab.h> -#include <linux/random.h> #include <linux/elf.h> #include <asm/asm.h> @@ -66,121 +61,6 @@ out: return res; } -unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */ - -EXPORT_SYMBOL(shm_align_mask); - -#define COLOUR_ALIGN(addr,pgoff) \ - ((((addr) + shm_align_mask) & ~shm_align_mask) + \ - (((pgoff) << PAGE_SHIFT) & shm_align_mask)) - -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct vm_area_struct * vmm; - int do_color_align; - unsigned long task_size; - -#ifdef CONFIG_32BIT - task_size = TASK_SIZE; -#else /* Must be CONFIG_64BIT*/ - task_size = test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE; -#endif - - if (len > task_size) - return -ENOMEM; - - if (flags & MAP_FIXED) { - /* Even MAP_FIXED mappings must reside within task_size. */ - if (task_size - len < addr) - return -EINVAL; - - /* - * We do not accept a shared mapping if it would violate - * cache aliasing constraints. - */ - if ((flags & MAP_SHARED) && - ((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask)) - return -EINVAL; - return addr; - } - - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = 1; - if (addr) { - if (do_color_align) - addr = COLOUR_ALIGN(addr, pgoff); - else - addr = PAGE_ALIGN(addr); - vmm = find_vma(current->mm, addr); - if (task_size - len >= addr && - (!vmm || addr + len <= vmm->vm_start)) - return addr; - } - addr = current->mm->mmap_base; - if (do_color_align) - addr = COLOUR_ALIGN(addr, pgoff); - else - addr = PAGE_ALIGN(addr); - - for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) { - /* At this point: (!vmm || addr < vmm->vm_end). */ - if (task_size - len < addr) - return -ENOMEM; - if (!vmm || addr + len <= vmm->vm_start) - return addr; - addr = vmm->vm_end; - if (do_color_align) - addr = COLOUR_ALIGN(addr, pgoff); - } -} - -void arch_pick_mmap_layout(struct mm_struct *mm) -{ - unsigned long random_factor = 0UL; - - if (current->flags & PF_RANDOMIZE) { - random_factor = get_random_int(); - random_factor = random_factor << PAGE_SHIFT; - if (TASK_IS_32BIT_ADDR) - random_factor &= 0xfffffful; - else - random_factor &= 0xffffffful; - } - - mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; -} - -static inline unsigned long brk_rnd(void) -{ - unsigned long rnd = get_random_int(); - - rnd = rnd << PAGE_SHIFT; - /* 8MB for 32bit, 256MB for 64bit */ - if (TASK_IS_32BIT_ADDR) - rnd = rnd & 0x7ffffful; - else - rnd = rnd & 0xffffffful; - - return rnd; -} - -unsigned long arch_randomize_brk(struct mm_struct *mm) -{ - unsigned long base = mm->brk; - unsigned long ret; - - ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < mm->brk) - return mm->brk; - - return ret; -} - SYSCALL_DEFINE6(mips_mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -383,12 +263,11 @@ save_static_function(sys_sysmips); static int __used noinline _sys_sysmips(nabi_no_regargs struct pt_regs regs) { - long cmd, arg1, arg2, arg3; + long cmd, arg1, arg2; cmd = regs.regs[4]; arg1 = regs.regs[5]; arg2 = regs.regs[6]; - arg3 = regs.regs[7]; switch (cmd) { case MIPS_ATOMIC_SET: @@ -405,7 +284,7 @@ _sys_sysmips(nabi_no_regargs struct pt_regs regs) if (arg1 & 2) set_thread_flag(TIF_LOGADE); else - clear_thread_flag(TIF_FIXADE); + clear_thread_flag(TIF_LOGADE); return 0; diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index fb749740551..1083ad4e101 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -102,7 +102,7 @@ static __init int cpu_has_mfc0_count_bug(void) case CPU_R4400SC: case CPU_R4400MC: /* - * The published errata for the R4400 upto 3.0 say the CPU + * The published errata for the R4400 up to 3.0 say the CPU * has the mfc0 from count bug. */ if ((current_cpu_data.processor_id & 0xff) <= 0x30) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index d053bf4759e..e9b3af27d84 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -29,6 +29,7 @@ #include <linux/notifier.h> #include <linux/kdb.h> #include <linux/irq.h> +#include <linux/perf_event.h> #include <asm/bootinfo.h> #include <asm/branch.h> @@ -82,7 +83,8 @@ extern asmlinkage void handle_mcheck(void); extern asmlinkage void handle_reserved(void); extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, - struct mips_fpu_struct *ctx, int has_fpu); + struct mips_fpu_struct *ctx, int has_fpu, + void *__user *fault_addr); void (*board_be_init)(void); int (*board_be_handler)(struct pt_regs *regs, int is_fixup); @@ -372,7 +374,8 @@ void __noreturn die(const char *str, struct pt_regs *regs) unsigned long dvpret = dvpe(); #endif /* CONFIG_MIPS_MT_SMTC */ - notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV); + if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV) == NOTIFY_STOP) + sig = 0; console_verbose(); spin_lock_irq(&die_lock); @@ -381,9 +384,6 @@ void __noreturn die(const char *str, struct pt_regs *regs) mips_mt_regdump(dvpret); #endif /* CONFIG_MIPS_MT_SMTC */ - if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV) == NOTIFY_STOP) - sig = 0; - printk("%s[#%d]:\n", str, ++die_counter); show_registers(regs); add_taint(TAINT_DIE); @@ -576,10 +576,16 @@ static inline int simulate_sc(struct pt_regs *regs, unsigned int opcode) */ static int simulate_llsc(struct pt_regs *regs, unsigned int opcode) { - if ((opcode & OPCODE) == LL) + if ((opcode & OPCODE) == LL) { + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, + 1, 0, regs, 0); return simulate_ll(regs, opcode); - if ((opcode & OPCODE) == SC) + } + if ((opcode & OPCODE) == SC) { + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, + 1, 0, regs, 0); return simulate_sc(regs, opcode); + } return -1; /* Must be something else ... */ } @@ -595,6 +601,8 @@ static int simulate_rdhwr(struct pt_regs *regs, unsigned int opcode) if ((opcode & OPCODE) == SPEC3 && (opcode & FUNC) == RDHWR) { int rd = (opcode & RD) >> 11; int rt = (opcode & RT) >> 16; + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, + 1, 0, regs, 0); switch (rd) { case 0: /* CPU number */ regs->regs[rt] = smp_processor_id(); @@ -630,8 +638,11 @@ static int simulate_rdhwr(struct pt_regs *regs, unsigned int opcode) static int simulate_sync(struct pt_regs *regs, unsigned int opcode) { - if ((opcode & OPCODE) == SPEC0 && (opcode & FUNC) == SYNC) + if ((opcode & OPCODE) == SPEC0 && (opcode & FUNC) == SYNC) { + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, + 1, 0, regs, 0); return 0; + } return -1; /* Must be something else ... */ } @@ -649,12 +660,36 @@ asmlinkage void do_ov(struct pt_regs *regs) force_sig_info(SIGFPE, &info, current); } +static int process_fpemu_return(int sig, void __user *fault_addr) +{ + if (sig == SIGSEGV || sig == SIGBUS) { + struct siginfo si = {0}; + si.si_addr = fault_addr; + si.si_signo = sig; + if (sig == SIGSEGV) { + if (find_vma(current->mm, (unsigned long)fault_addr)) + si.si_code = SEGV_ACCERR; + else + si.si_code = SEGV_MAPERR; + } else { + si.si_code = BUS_ADRERR; + } + force_sig_info(sig, &si, current); + return 1; + } else if (sig) { + force_sig(sig, current); + return 1; + } else { + return 0; + } +} + /* * XXX Delayed fp exceptions when doing a lazy ctx switch XXX */ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) { - siginfo_t info; + siginfo_t info = {0}; if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) @@ -663,6 +698,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) if (fcr31 & FPU_CSR_UNI_X) { int sig; + void __user *fault_addr = NULL; /* * Unimplemented operation exception. If we've got the full @@ -678,7 +714,8 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) lose_fpu(1); /* Run the emulator */ - sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1); + sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, + &fault_addr); /* * We can't allow the emulated instruction to leave any of @@ -690,8 +727,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) own_fpu(1); /* Using the FPU again. */ /* If something went wrong, signal */ - if (sig) - force_sig(sig, current); + process_fpemu_return(sig, fault_addr); return; } else if (fcr31 & FPU_CSR_INV_X) @@ -984,11 +1020,11 @@ asmlinkage void do_cpu(struct pt_regs *regs) if (!raw_cpu_has_fpu) { int sig; + void __user *fault_addr = NULL; sig = fpu_emulator_cop1Handler(regs, - ¤t->thread.fpu, 0); - if (sig) - force_sig(sig, current); - else + ¤t->thread.fpu, + 0, &fault_addr); + if (!process_fpemu_return(sig, fault_addr)) mt_ase_fp_affinity(); } @@ -1469,6 +1505,7 @@ void __cpuinit per_cpu_trap_init(void) { unsigned int cpu = smp_processor_id(); unsigned int status_set = ST0_CU0; + unsigned int hwrena = cpu_hwrena_impl_bits; #ifdef CONFIG_MIPS_MT_SMTC int secondaryTC = 0; int bootTC = (cpu == 0); @@ -1501,14 +1538,14 @@ void __cpuinit per_cpu_trap_init(void) change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX, status_set); - if (cpu_has_mips_r2) { - unsigned int enable = 0x0000000f | cpu_hwrena_impl_bits; + if (cpu_has_mips_r2) + hwrena |= 0x0000000f; - if (!noulri && cpu_has_userlocal) - enable |= (1 << 29); + if (!noulri && cpu_has_userlocal) + hwrena |= (1 << 29); - write_c0_hwrena(enable); - } + if (hwrena) + write_c0_hwrena(hwrena); #ifdef CONFIG_MIPS_MT_SMTC if (!secondaryTC) { @@ -1553,7 +1590,6 @@ void __cpuinit per_cpu_trap_init(void) #endif /* CONFIG_MIPS_MT_SMTC */ cpu_data[cpu].asid_cache = ASID_FIRST_VERSION; - TLBMISS_HANDLER_SETUP(); atomic_inc(&init_mm.mm_count); current->active_mm = &init_mm; @@ -1575,6 +1611,7 @@ void __cpuinit per_cpu_trap_init(void) write_c0_wired(0); } #endif /* CONFIG_MIPS_MT_SMTC */ + TLBMISS_HANDLER_SETUP(); } /* Install CPU exception handler */ diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 33d5a5ce4a2..cfea1adfa15 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -78,6 +78,8 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/debugfs.h> +#include <linux/perf_event.h> + #include <asm/asm.h> #include <asm/branch.h> #include <asm/byteorder.h> @@ -109,6 +111,9 @@ static void emulate_load_store_insn(struct pt_regs *regs, unsigned long value; unsigned int res; + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, + 1, 0, regs, 0); + /* * This load never faults. */ @@ -511,6 +516,8 @@ asmlinkage void do_ade(struct pt_regs *regs) unsigned int __user *pc; mm_segment_t seg; + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, + 1, 0, regs, regs->cp0_badvaddr); /* * Did we catch a fault trying to load an instruction? * Or are we running in MIPS16 mode? diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index f25df73db92..01af3876cf9 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -65,15 +65,18 @@ SECTIONS NOTES :text :note .dummy : { *(.dummy) } :text + _sdata = .; /* Start of data section */ RODATA /* writeable */ + _sdata = .; /* Start of data section */ .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ INIT_TASK_DATA(PAGE_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) + READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) DATA_DATA CONSTRUCTORS } @@ -98,6 +101,13 @@ SECTIONS INIT_TEXT_SECTION(PAGE_SIZE) INIT_DATA_SECTION(16) + . = ALIGN(4); + .mips.machines.init : AT(ADDR(.mips.machines.init) - LOAD_OFFSET) { + __mips_machines_start = .; + *(.mips.machines.init) + __mips_machines_end = .; + } + /* .exit.text is discarded at runtime, not link time, to deal with * references from .rodata */ @@ -108,7 +118,7 @@ SECTIONS EXIT_DATA } - PERCPU(PAGE_SIZE) + PERCPU(1 << CONFIG_MIPS_L1_CACHE_SHIFT, PAGE_SIZE) . = ALIGN(PAGE_SIZE); __init_end = .; /* freed after init ends here */ diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 3eb3cde2f66..dbb6b408f00 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -19,7 +19,7 @@ * VPE support module * * Provides support for loading a MIPS SP program on VPE1. - * The SP enviroment is rather simple, no tlb's. It needs to be relocatable + * The SP environment is rather simple, no tlb's. It needs to be relocatable * (or partially linked). You should initialise your stack in the startup * code. This loader looks for the symbol __start and sets up * execution to resume from there. The MIPS SDE kit contains suitable examples. @@ -148,9 +148,9 @@ struct { spinlock_t tc_list_lock; struct list_head tc_list; /* Thread contexts */ } vpecontrol = { - .vpe_list_lock = SPIN_LOCK_UNLOCKED, + .vpe_list_lock = __SPIN_LOCK_UNLOCKED(vpe_list_lock), .vpe_list = LIST_HEAD_INIT(vpecontrol.vpe_list), - .tc_list_lock = SPIN_LOCK_UNLOCKED, + .tc_list_lock = __SPIN_LOCK_UNLOCKED(tc_list_lock), .tc_list = LIST_HEAD_INIT(vpecontrol.tc_list) }; @@ -1092,6 +1092,10 @@ static int vpe_open(struct inode *inode, struct file *filp) /* this of-course trashes what was there before... */ v->pbuffer = vmalloc(P_SIZE); + if (!v->pbuffer) { + pr_warning("VPE loader: unable to allocate memory\n"); + return -ENOMEM; + } v->plen = P_SIZE; v->load_addr = NULL; v->len = 0; @@ -1149,10 +1153,9 @@ static int vpe_release(struct inode *inode, struct file *filp) if (ret < 0) v->shared_ptr = NULL; - // cleanup any temp buffers - if (v->pbuffer) - vfree(v->pbuffer); + vfree(v->pbuffer); v->plen = 0; + return ret; } @@ -1169,11 +1172,6 @@ static ssize_t vpe_write(struct file *file, const char __user * buffer, if (v == NULL) return -ENODEV; - if (v->pbuffer == NULL) { - printk(KERN_ERR "VPE loader: no buffer for program\n"); - return -ENOMEM; - } - if ((count + v->len) > v->plen) { printk(KERN_WARNING "VPE loader: elf size too big. Perhaps strip uneeded symbols\n"); |