diff options
Diffstat (limited to 'arch/alpha/kernel')
-rw-r--r-- | arch/alpha/kernel/Makefile | 1 | ||||
-rw-r--r-- | arch/alpha/kernel/core_t2.c | 11 | ||||
-rw-r--r-- | arch/alpha/kernel/entry.S | 81 | ||||
-rw-r--r-- | arch/alpha/kernel/err_ev6.c | 12 | ||||
-rw-r--r-- | arch/alpha/kernel/err_marvel.c | 39 | ||||
-rw-r--r-- | arch/alpha/kernel/err_titan.c | 35 | ||||
-rw-r--r-- | arch/alpha/kernel/irq.c | 7 | ||||
-rw-r--r-- | arch/alpha/kernel/irq_alpha.c | 3 | ||||
-rw-r--r-- | arch/alpha/kernel/machvec_impl.h | 3 | ||||
-rw-r--r-- | arch/alpha/kernel/osf_sys.c | 23 | ||||
-rw-r--r-- | arch/alpha/kernel/pci-sysfs.c | 2 | ||||
-rw-r--r-- | arch/alpha/kernel/pci_iommu.c | 4 | ||||
-rw-r--r-- | arch/alpha/kernel/perf_event.c | 886 | ||||
-rw-r--r-- | arch/alpha/kernel/process.c | 7 | ||||
-rw-r--r-- | arch/alpha/kernel/proto.h | 3 | ||||
-rw-r--r-- | arch/alpha/kernel/ptrace.c | 7 | ||||
-rw-r--r-- | arch/alpha/kernel/signal.c | 97 | ||||
-rw-r--r-- | arch/alpha/kernel/srm_env.c | 2 | ||||
-rw-r--r-- | arch/alpha/kernel/sys_cabriolet.c | 19 | ||||
-rw-r--r-- | arch/alpha/kernel/sys_takara.c | 11 | ||||
-rw-r--r-- | arch/alpha/kernel/systbls.S | 5 | ||||
-rw-r--r-- | arch/alpha/kernel/time.c | 26 | ||||
-rw-r--r-- | arch/alpha/kernel/traps.c | 3 |
23 files changed, 1076 insertions, 211 deletions
diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile index 5a62fb46ef20..1ee9b5b629b8 100644 --- a/arch/alpha/kernel/Makefile +++ b/arch/alpha/kernel/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci_iommu.o pci-sysfs.o obj-$(CONFIG_SRM_ENV) += srm_env.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_ALPHA_GENERIC diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c index e6d90568b65d..2f770e994289 100644 --- a/arch/alpha/kernel/core_t2.c +++ b/arch/alpha/kernel/core_t2.c @@ -74,8 +74,6 @@ # define DBG(args) #endif -DEFINE_RAW_SPINLOCK(t2_hae_lock); - static volatile unsigned int t2_mcheck_any_expected; static volatile unsigned int t2_mcheck_last_taken; @@ -406,6 +404,7 @@ void __init t2_init_arch(void) { struct pci_controller *hose; + struct resource *hae_mem; unsigned long temp; unsigned int i; @@ -433,7 +432,13 @@ t2_init_arch(void) */ pci_isa_hose = hose = alloc_pci_controller(); hose->io_space = &ioport_resource; - hose->mem_space = &iomem_resource; + hae_mem = alloc_resource(); + hae_mem->start = 0; + hae_mem->end = T2_MEM_R1_MASK; + hae_mem->name = pci_hae0_name; + if (request_resource(&iomem_resource, hae_mem) < 0) + printk(KERN_ERR "Failed to request HAE_MEM\n"); + hose->mem_space = hae_mem; hose->index = 0; hose->sparse_mem_base = T2_SPARSE_MEM - IDENT_ADDR; diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index b45d913a51c3..6d159cee5f2f 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -73,8 +73,6 @@ ldq $20, HAE_REG($19); \ stq $21, HAE_CACHE($19); \ stq $21, 0($20); \ - ldq $0, 0($sp); \ - ldq $1, 8($sp); \ 99:; \ ldq $19, 72($sp); \ ldq $20, 80($sp); \ @@ -316,19 +314,24 @@ ret_from_sys_call: cmovne $26, 0, $19 /* $19 = 0 => non-restartable */ ldq $0, SP_OFF($sp) and $0, 8, $0 - beq $0, restore_all -ret_from_reschedule: + beq $0, ret_to_kernel +ret_to_user: /* Make sure need_resched and sigpending don't change between sampling and the rti. */ lda $16, 7 call_pal PAL_swpipl ldl $5, TI_FLAGS($8) and $5, _TIF_WORK_MASK, $2 - bne $5, work_pending + bne $2, work_pending restore_all: RESTORE_ALL call_pal PAL_rti +ret_to_kernel: + lda $16, 7 + call_pal PAL_swpipl + br restore_all + .align 3 $syscall_error: /* @@ -363,7 +366,7 @@ $ret_success: * $8: current. * $19: The old syscall number, or zero if this is not a return * from a syscall that errored and is possibly restartable. - * $20: Error indication. + * $20: The old a3 value */ .align 4 @@ -392,12 +395,18 @@ $work_resched: $work_notifysig: mov $sp, $16 - br $1, do_switch_stack + bsr $1, do_switch_stack mov $sp, $17 mov $5, $18 + mov $19, $9 /* save old syscall number */ + mov $20, $10 /* save old a3 */ + and $5, _TIF_SIGPENDING, $2 + cmovne $2, 0, $9 /* we don't want double syscall restarts */ jsr $26, do_notify_resume + mov $9, $19 + mov $10, $20 bsr $1, undo_switch_stack - br restore_all + br ret_to_user .end work_pending /* @@ -430,6 +439,7 @@ strace: beq $1, 1f ldq $27, 0($2) 1: jsr $26, ($27), sys_gettimeofday +ret_from_straced: ldgp $gp, 0($26) /* check return.. */ @@ -650,7 +660,7 @@ kernel_thread: /* We don't actually care for a3 success widgetry in the kernel. Not for positive errno values. */ stq $0, 0($sp) /* $0 */ - br restore_all + br ret_to_kernel .end kernel_thread /* @@ -757,11 +767,15 @@ sys_vfork: .ent sys_sigreturn sys_sigreturn: .prologue 0 + lda $9, ret_from_straced + cmpult $26, $9, $9 mov $sp, $17 lda $18, -SWITCH_STACK_SIZE($sp) lda $sp, -SWITCH_STACK_SIZE($sp) jsr $26, do_sigreturn - br $1, undo_switch_stack + bne $9, 1f + jsr $26, syscall_trace +1: br $1, undo_switch_stack br ret_from_sys_call .end sys_sigreturn @@ -770,47 +784,19 @@ sys_sigreturn: .ent sys_rt_sigreturn sys_rt_sigreturn: .prologue 0 + lda $9, ret_from_straced + cmpult $26, $9, $9 mov $sp, $17 lda $18, -SWITCH_STACK_SIZE($sp) lda $sp, -SWITCH_STACK_SIZE($sp) jsr $26, do_rt_sigreturn - br $1, undo_switch_stack + bne $9, 1f + jsr $26, syscall_trace +1: br $1, undo_switch_stack br ret_from_sys_call .end sys_rt_sigreturn .align 4 - .globl sys_sigsuspend - .ent sys_sigsuspend -sys_sigsuspend: - .prologue 0 - mov $sp, $17 - br $1, do_switch_stack - mov $sp, $18 - subq $sp, 16, $sp - stq $26, 0($sp) - jsr $26, do_sigsuspend - ldq $26, 0($sp) - lda $sp, SWITCH_STACK_SIZE+16($sp) - ret -.end sys_sigsuspend - - .align 4 - .globl sys_rt_sigsuspend - .ent sys_rt_sigsuspend -sys_rt_sigsuspend: - .prologue 0 - mov $sp, $18 - br $1, do_switch_stack - mov $sp, $19 - subq $sp, 16, $sp - stq $26, 0($sp) - jsr $26, do_rt_sigsuspend - ldq $26, 0($sp) - lda $sp, SWITCH_STACK_SIZE+16($sp) - ret -.end sys_rt_sigsuspend - - .align 4 .globl sys_sethae .ent sys_sethae sys_sethae: @@ -929,15 +915,6 @@ sys_execve: .end sys_execve .align 4 - .globl osf_sigprocmask - .ent osf_sigprocmask -osf_sigprocmask: - .prologue 0 - mov $sp, $18 - jmp $31, sys_osf_sigprocmask -.end osf_sigprocmask - - .align 4 .globl alpha_ni_syscall .ent alpha_ni_syscall alpha_ni_syscall: diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c index 8ca6345bf131..253cf1a87481 100644 --- a/arch/alpha/kernel/err_ev6.c +++ b/arch/alpha/kernel/err_ev6.c @@ -90,11 +90,13 @@ static int ev6_parse_cbox(u64 c_addr, u64 c1_syn, u64 c2_syn, u64 c_stat, u64 c_sts, int print) { - char *sourcename[] = { "UNKNOWN", "UNKNOWN", "UNKNOWN", - "MEMORY", "BCACHE", "DCACHE", - "BCACHE PROBE", "BCACHE PROBE" }; - char *streamname[] = { "D", "I" }; - char *bitsname[] = { "SINGLE", "DOUBLE" }; + static const char * const sourcename[] = { + "UNKNOWN", "UNKNOWN", "UNKNOWN", + "MEMORY", "BCACHE", "DCACHE", + "BCACHE PROBE", "BCACHE PROBE" + }; + static const char * const streamname[] = { "D", "I" }; + static const char * const bitsname[] = { "SINGLE", "DOUBLE" }; int status = MCHK_DISPOSITION_REPORT; int source = -1, stream = -1, bits = -1; diff --git a/arch/alpha/kernel/err_marvel.c b/arch/alpha/kernel/err_marvel.c index 52a79dfc13c6..648ae88aeb8a 100644 --- a/arch/alpha/kernel/err_marvel.c +++ b/arch/alpha/kernel/err_marvel.c @@ -109,7 +109,7 @@ marvel_print_err_cyc(u64 err_cyc) #define IO7__ERR_CYC__CYCLE__M (0x7) printk("%s Packet In Error: %s\n" - "%s Error in %s, cycle %ld%s%s\n", + "%s Error in %s, cycle %lld%s%s\n", err_print_prefix, packet_desc[EXTRACT(err_cyc, IO7__ERR_CYC__PACKET)], err_print_prefix, @@ -313,7 +313,7 @@ marvel_print_po7_ugbge_sym(u64 ugbge_sym) } printk("%s Up Hose Garbage Symptom:\n" - "%s Source Port: %ld - Dest PID: %ld - OpCode: %s\n", + "%s Source Port: %lld - Dest PID: %lld - OpCode: %s\n", err_print_prefix, err_print_prefix, EXTRACT(ugbge_sym, IO7__PO7_UGBGE_SYM__UPH_SRC_PORT), @@ -552,7 +552,7 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt) #define IO7__POX_SPLCMPLT__REM_BYTE_COUNT__M (0xfff) printk("%s Split Completion Error:\n" - "%s Source (Bus:Dev:Func): %ld:%ld:%ld\n", + "%s Source (Bus:Dev:Func): %lld:%lld:%lld\n", err_print_prefix, err_print_prefix, EXTRACT(spl_cmplt, IO7__POX_SPLCMPLT__SOURCE_BUS), @@ -589,22 +589,23 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt) static void marvel_print_pox_trans_sum(u64 trans_sum) { - char *pcix_cmd[] = { "Interrupt Acknowledge", - "Special Cycle", - "I/O Read", - "I/O Write", - "Reserved", - "Reserved / Device ID Message", - "Memory Read", - "Memory Write", - "Reserved / Alias to Memory Read Block", - "Reserved / Alias to Memory Write Block", - "Configuration Read", - "Configuration Write", - "Memory Read Multiple / Split Completion", - "Dual Address Cycle", - "Memory Read Line / Memory Read Block", - "Memory Write and Invalidate / Memory Write Block" + static const char * const pcix_cmd[] = { + "Interrupt Acknowledge", + "Special Cycle", + "I/O Read", + "I/O Write", + "Reserved", + "Reserved / Device ID Message", + "Memory Read", + "Memory Write", + "Reserved / Alias to Memory Read Block", + "Reserved / Alias to Memory Write Block", + "Configuration Read", + "Configuration Write", + "Memory Read Multiple / Split Completion", + "Dual Address Cycle", + "Memory Read Line / Memory Read Block", + "Memory Write and Invalidate / Memory Write Block" }; #define IO7__POX_TRANSUM__PCI_ADDR__S (0) diff --git a/arch/alpha/kernel/err_titan.c b/arch/alpha/kernel/err_titan.c index f7ed97ce0dfd..c3b3781a03de 100644 --- a/arch/alpha/kernel/err_titan.c +++ b/arch/alpha/kernel/err_titan.c @@ -75,8 +75,12 @@ titan_parse_p_serror(int which, u64 serror, int print) int status = MCHK_DISPOSITION_REPORT; #ifdef CONFIG_VERBOSE_MCHECK - char *serror_src[] = {"GPCI", "APCI", "AGP HP", "AGP LP"}; - char *serror_cmd[] = {"DMA Read", "DMA RMW", "SGTE Read", "Reserved"}; + static const char * const serror_src[] = { + "GPCI", "APCI", "AGP HP", "AGP LP" + }; + static const char * const serror_cmd[] = { + "DMA Read", "DMA RMW", "SGTE Read", "Reserved" + }; #endif /* CONFIG_VERBOSE_MCHECK */ #define TITAN__PCHIP_SERROR__LOST_UECC (1UL << 0) @@ -140,14 +144,15 @@ titan_parse_p_perror(int which, int port, u64 perror, int print) int status = MCHK_DISPOSITION_REPORT; #ifdef CONFIG_VERBOSE_MCHECK - char *perror_cmd[] = { "Interrupt Acknowledge", "Special Cycle", - "I/O Read", "I/O Write", - "Reserved", "Reserved", - "Memory Read", "Memory Write", - "Reserved", "Reserved", - "Configuration Read", "Configuration Write", - "Memory Read Multiple", "Dual Address Cycle", - "Memory Read Line","Memory Write and Invalidate" + static const char * const perror_cmd[] = { + "Interrupt Acknowledge", "Special Cycle", + "I/O Read", "I/O Write", + "Reserved", "Reserved", + "Memory Read", "Memory Write", + "Reserved", "Reserved", + "Configuration Read", "Configuration Write", + "Memory Read Multiple", "Dual Address Cycle", + "Memory Read Line", "Memory Write and Invalidate" }; #endif /* CONFIG_VERBOSE_MCHECK */ @@ -273,11 +278,11 @@ titan_parse_p_agperror(int which, u64 agperror, int print) int cmd, len; unsigned long addr; - char *agperror_cmd[] = { "Read (low-priority)", "Read (high-priority)", - "Write (low-priority)", - "Write (high-priority)", - "Reserved", "Reserved", - "Flush", "Fence" + static const char * const agperror_cmd[] = { + "Read (low-priority)", "Read (high-priority)", + "Write (low-priority)", "Write (high-priority)", + "Reserved", "Reserved", + "Flush", "Fence" }; #endif /* CONFIG_VERBOSE_MCHECK */ diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 7f912ba3d9ad..fe912984d9b1 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -31,6 +31,7 @@ #include <asm/uaccess.h> volatile unsigned long irq_err_count; +DEFINE_PER_CPU(unsigned long, irq_pmi_count); void ack_bad_irq(unsigned int irq) { @@ -63,9 +64,7 @@ int irq_select_affinity(unsigned int irq) int show_interrupts(struct seq_file *p, void *v) { -#ifdef CONFIG_SMP int j; -#endif int irq = *(loff_t *) v; struct irqaction * action; unsigned long flags; @@ -112,6 +111,10 @@ unlock: seq_printf(p, "%10lu ", cpu_data[j].ipi_count); seq_putc(p, '\n'); #endif + seq_puts(p, "PMI: "); + for_each_online_cpu(j) + seq_printf(p, "%10lu ", per_cpu(irq_pmi_count, j)); + seq_puts(p, " Performance Monitoring\n"); seq_printf(p, "ERR: %10lu\n", irq_err_count); } return 0; diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index cfde865b78e0..5f77afb88e89 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -10,6 +10,7 @@ #include <asm/machvec.h> #include <asm/dma.h> +#include <asm/perf_event.h> #include "proto.h" #include "irq_impl.h" @@ -111,6 +112,8 @@ init_IRQ(void) wrent(entInt, 0); alpha_mv.init_irq(); + + init_hw_perf_events(); } /* diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h index 512685f78097..7fa62488bd16 100644 --- a/arch/alpha/kernel/machvec_impl.h +++ b/arch/alpha/kernel/machvec_impl.h @@ -25,6 +25,9 @@ #ifdef MCPCIA_ONE_HAE_WINDOW #define MCPCIA_HAE_ADDRESS (&alpha_mv.hae_cache) #endif +#ifdef T2_ONE_HAE_WINDOW +#define T2_HAE_ADDRESS (&alpha_mv.hae_cache) +#endif /* Only a few systems don't define IACK_SC, handling all interrupts through the SRM console. But splitting out that one case from IO() below diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index de9d39717808..547e8b84b2f7 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -15,7 +15,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/syscalls.h> #include <linux/unistd.h> @@ -69,7 +68,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start, { struct mm_struct *mm; - lock_kernel(); mm = current->mm; mm->end_code = bss_start + bss_len; mm->start_brk = bss_start + bss_len; @@ -78,7 +76,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start, printk("set_program_attributes(%lx %lx %lx %lx)\n", text_start, text_len, bss_start, bss_len); #endif - unlock_kernel(); return 0; } @@ -234,17 +231,17 @@ linux_to_osf_statfs(struct kstatfs *linux_stat, struct osf_statfs __user *osf_st } static int -do_osf_statfs(struct dentry * dentry, struct osf_statfs __user *buffer, +do_osf_statfs(struct path *path, struct osf_statfs __user *buffer, unsigned long bufsiz) { struct kstatfs linux_stat; - int error = vfs_statfs(dentry, &linux_stat); + int error = vfs_statfs(path, &linux_stat); if (!error) error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz); return error; } -SYSCALL_DEFINE3(osf_statfs, char __user *, pathname, +SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname, struct osf_statfs __user *, buffer, unsigned long, bufsiz) { struct path path; @@ -252,7 +249,7 @@ SYSCALL_DEFINE3(osf_statfs, char __user *, pathname, retval = user_path(pathname, &path); if (!retval) { - retval = do_osf_statfs(path.dentry, buffer, bufsiz); + retval = do_osf_statfs(&path, buffer, bufsiz); path_put(&path); } return retval; @@ -267,7 +264,7 @@ SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd, retval = -EBADF; file = fget(fd); if (file) { - retval = do_osf_statfs(file->f_path.dentry, buffer, bufsiz); + retval = do_osf_statfs(&file->f_path, buffer, bufsiz); fput(file); } return retval; @@ -358,7 +355,7 @@ osf_procfs_mount(char *dirname, struct procfs_args __user *args, int flags) return do_mount("", dirname, "proc", flags, NULL); } -SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, +SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path, int, flag, void __user *, data) { int retval; @@ -517,7 +514,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code, long error; int __user *min_buf_size_ptr; - lock_kernel(); switch (code) { case PL_SET: if (get_user(error, &args->set.nbytes)) @@ -547,7 +543,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code, error = -EOPNOTSUPP; break; }; - unlock_kernel(); return error; } @@ -594,7 +589,7 @@ SYSCALL_DEFINE2(osf_sigstack, struct sigstack __user *, uss, SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) { - char *sysinfo_table[] = { + const char *sysinfo_table[] = { utsname()->sysname, utsname()->nodename, utsname()->release, @@ -606,7 +601,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) "dummy", /* secure RPC domain */ }; unsigned long offset; - char *res; + const char *res; long len, err = -EINVAL; offset = command-1; @@ -932,7 +927,7 @@ SYSCALL_DEFINE3(osf_setitimer, int, which, struct itimerval32 __user *, in, } -SYSCALL_DEFINE2(osf_utimes, char __user *, filename, +SYSCALL_DEFINE2(osf_utimes, const char __user *, filename, struct timeval32 __user *, tvs) { struct timespec tv[2]; diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index 738fc824e2ea..b899e95f79fd 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -66,7 +66,7 @@ static int pci_mmap_resource(struct kobject *kobj, { struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj)); - struct resource *res = (struct resource *)attr->private; + struct resource *res = attr->private; enum pci_mmap_state mmap_type; struct pci_bus_region bar; int i; diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index d1dbd9acd1df..022c2748fa41 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -223,7 +223,7 @@ iommu_arena_free(struct pci_iommu_arena *arena, long ofs, long n) */ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask) { - dma64_addr_t dac_offset = alpha_mv.pci_dac_offset; + dma_addr_t dac_offset = alpha_mv.pci_dac_offset; int ok = 1; /* If this is not set, the machine doesn't support DAC at all. */ @@ -756,7 +756,7 @@ static void alpha_pci_unmap_sg(struct device *dev, struct scatterlist *sg, spin_lock_irqsave(&arena->lock, flags); for (end = sg + nents; sg < end; ++sg) { - dma64_addr_t addr; + dma_addr_t addr; size_t size; long npages, ofs; dma_addr_t tend; diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c new file mode 100644 index 000000000000..1cc49683fb69 --- /dev/null +++ b/arch/alpha/kernel/perf_event.c @@ -0,0 +1,886 @@ +/* + * Hardware performance events for the Alpha. + * + * We implement HW counts on the EV67 and subsequent CPUs only. + * + * (C) 2010 Michael J. Cree + * + * Somewhat based on the Sparc code, and to a lesser extent the PowerPC and + * ARM code, which are copyright by their respective authors. + */ + +#include <linux/perf_event.h> +#include <linux/kprobes.h> +#include <linux/kernel.h> +#include <linux/kdebug.h> +#include <linux/mutex.h> + +#include <asm/hwrpb.h> +#include <asm/atomic.h> +#include <asm/irq.h> +#include <asm/irq_regs.h> +#include <asm/pal.h> +#include <asm/wrperfmon.h> +#include <asm/hw_irq.h> + + +/* The maximum number of PMCs on any Alpha CPU whatsoever. */ +#define MAX_HWEVENTS 3 +#define PMC_NO_INDEX -1 + +/* For tracking PMCs and the hw events they monitor on each CPU. */ +struct cpu_hw_events { + int enabled; + /* Number of events scheduled; also number entries valid in arrays below. */ + int n_events; + /* Number events added since last hw_perf_disable(). */ + int n_added; + /* Events currently scheduled. */ + struct perf_event *event[MAX_HWEVENTS]; + /* Event type of each scheduled event. */ + unsigned long evtype[MAX_HWEVENTS]; + /* Current index of each scheduled event; if not yet determined + * contains PMC_NO_INDEX. + */ + int current_idx[MAX_HWEVENTS]; + /* The active PMCs' config for easy use with wrperfmon(). */ + unsigned long config; + /* The active counters' indices for easy use with wrperfmon(). */ + unsigned long idx_mask; +}; +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + + + +/* + * A structure to hold the description of the PMCs available on a particular + * type of Alpha CPU. + */ +struct alpha_pmu_t { + /* Mapping of the perf system hw event types to indigenous event types */ + const int *event_map; + /* The number of entries in the event_map */ + int max_events; + /* The number of PMCs on this Alpha */ + int num_pmcs; + /* + * All PMC counters reside in the IBOX register PCTR. This is the + * LSB of the counter. + */ + int pmc_count_shift[MAX_HWEVENTS]; + /* + * The mask that isolates the PMC bits when the LSB of the counter + * is shifted to bit 0. + */ + unsigned long pmc_count_mask[MAX_HWEVENTS]; + /* The maximum period the PMC can count. */ + unsigned long pmc_max_period[MAX_HWEVENTS]; + /* + * The maximum value that may be written to the counter due to + * hardware restrictions is pmc_max_period - pmc_left. + */ + long pmc_left[3]; + /* Subroutine for allocation of PMCs. Enforces constraints. */ + int (*check_constraints)(struct perf_event **, unsigned long *, int); +}; + +/* + * The Alpha CPU PMU description currently in operation. This is set during + * the boot process to the specific CPU of the machine. + */ +static const struct alpha_pmu_t *alpha_pmu; + + +#define HW_OP_UNSUPPORTED -1 + +/* + * The hardware description of the EV67, EV68, EV69, EV7 and EV79 PMUs + * follow. Since they are identical we refer to them collectively as the + * EV67 henceforth. + */ + +/* + * EV67 PMC event types + * + * There is no one-to-one mapping of the possible hw event types to the + * actual codes that are used to program the PMCs hence we introduce our + * own hw event type identifiers. + */ +enum ev67_pmc_event_type { + EV67_CYCLES = 1, + EV67_INSTRUCTIONS, + EV67_BCACHEMISS, + EV67_MBOXREPLAY, + EV67_LAST_ET +}; +#define EV67_NUM_EVENT_TYPES (EV67_LAST_ET-EV67_CYCLES) + + +/* Mapping of the hw event types to the perf tool interface */ +static const int ev67_perfmon_event_map[] = { + [PERF_COUNT_HW_CPU_CYCLES] = EV67_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = EV67_INSTRUCTIONS, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = EV67_BCACHEMISS, +}; + +struct ev67_mapping_t { + int config; + int idx; +}; + +/* + * The mapping used for one event only - these must be in same order as enum + * ev67_pmc_event_type definition. + */ +static const struct ev67_mapping_t ev67_mapping[] = { + {EV67_PCTR_INSTR_CYCLES, 1}, /* EV67_CYCLES, */ + {EV67_PCTR_INSTR_CYCLES, 0}, /* EV67_INSTRUCTIONS */ + {EV67_PCTR_INSTR_BCACHEMISS, 1}, /* EV67_BCACHEMISS */ + {EV67_PCTR_CYCLES_MBOX, 1} /* EV67_MBOXREPLAY */ +}; + + +/* + * Check that a group of events can be simultaneously scheduled on to the + * EV67 PMU. Also allocate counter indices and config. + */ +static int ev67_check_constraints(struct perf_event **event, + unsigned long *evtype, int n_ev) +{ + int idx0; + unsigned long config; + + idx0 = ev67_mapping[evtype[0]-1].idx; + config = ev67_mapping[evtype[0]-1].config; + if (n_ev == 1) + goto success; + + BUG_ON(n_ev != 2); + + if (evtype[0] == EV67_MBOXREPLAY || evtype[1] == EV67_MBOXREPLAY) { + /* MBOX replay traps must be on PMC 1 */ + idx0 = (evtype[0] == EV67_MBOXREPLAY) ? 1 : 0; + /* Only cycles can accompany MBOX replay traps */ + if (evtype[idx0] == EV67_CYCLES) { + config = EV67_PCTR_CYCLES_MBOX; + goto success; + } + } + + if (evtype[0] == EV67_BCACHEMISS || evtype[1] == EV67_BCACHEMISS) { + /* Bcache misses must be on PMC 1 */ + idx0 = (evtype[0] == EV67_BCACHEMISS) ? 1 : 0; + /* Only instructions can accompany Bcache misses */ + if (evtype[idx0] == EV67_INSTRUCTIONS) { + config = EV67_PCTR_INSTR_BCACHEMISS; + goto success; + } + } + + if (evtype[0] == EV67_INSTRUCTIONS || evtype[1] == EV67_INSTRUCTIONS) { + /* Instructions must be on PMC 0 */ + idx0 = (evtype[0] == EV67_INSTRUCTIONS) ? 0 : 1; + /* By this point only cycles can accompany instructions */ + if (evtype[idx0^1] == EV67_CYCLES) { + config = EV67_PCTR_INSTR_CYCLES; + goto success; + } + } + + /* Otherwise, darn it, there is a conflict. */ + return -1; + +success: + event[0]->hw.idx = idx0; + event[0]->hw.config_base = config; + if (n_ev == 2) { + event[1]->hw.idx = idx0 ^ 1; + event[1]->hw.config_base = config; + } + return 0; +} + + +static const struct alpha_pmu_t ev67_pmu = { + .event_map = ev67_perfmon_event_map, + .max_events = ARRAY_SIZE(ev67_perfmon_event_map), + .num_pmcs = 2, + .pmc_count_shift = {EV67_PCTR_0_COUNT_SHIFT, EV67_PCTR_1_COUNT_SHIFT, 0}, + .pmc_count_mask = {EV67_PCTR_0_COUNT_MASK, EV67_PCTR_1_COUNT_MASK, 0}, + .pmc_max_period = {(1UL<<20) - 1, (1UL<<20) - 1, 0}, + .pmc_left = {16, 4, 0}, + .check_constraints = ev67_check_constraints +}; + + + +/* + * Helper routines to ensure that we read/write only the correct PMC bits + * when calling the wrperfmon PALcall. + */ +static inline void alpha_write_pmc(int idx, unsigned long val) +{ + val &= alpha_pmu->pmc_count_mask[idx]; + val <<= alpha_pmu->pmc_count_shift[idx]; + val |= (1<<idx); + wrperfmon(PERFMON_CMD_WRITE, val); +} + +static inline unsigned long alpha_read_pmc(int idx) +{ + unsigned long val; + + val = wrperfmon(PERFMON_CMD_READ, 0); + val >>= alpha_pmu->pmc_count_shift[idx]; + val &= alpha_pmu->pmc_count_mask[idx]; + return val; +} + +/* Set a new period to sample over */ +static int alpha_perf_event_set_period(struct perf_event *event, + struct hw_perf_event *hwc, int idx) +{ + long left = local64_read(&hwc->period_left); + long period = hwc->sample_period; + int ret = 0; + + 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; + } + + /* + * Hardware restrictions require that the counters must not be + * written with values that are too close to the maximum period. + */ + if (unlikely(left < alpha_pmu->pmc_left[idx])) + left = alpha_pmu->pmc_left[idx]; + + if (left > (long)alpha_pmu->pmc_max_period[idx]) + left = alpha_pmu->pmc_max_period[idx]; + + local64_set(&hwc->prev_count, (unsigned long)(-left)); + + alpha_write_pmc(idx, (unsigned long)(-left)); + + perf_event_update_userpage(event); + + return ret; +} + + +/* + * Calculates the count (the 'delta') since the last time the PMC was read. + * + * As the PMCs' full period can easily be exceeded within the perf system + * sampling period we cannot use any high order bits as a guard bit in the + * PMCs to detect overflow as is done by other architectures. The code here + * calculates the delta on the basis that there is no overflow when ovf is + * zero. The value passed via ovf by the interrupt handler corrects for + * overflow. + * + * This can be racey on rare occasions -- a call to this routine can occur + * with an overflowed counter just before the PMI service routine is called. + * The check for delta negative hopefully always rectifies this situation. + */ +static unsigned long alpha_perf_event_update(struct perf_event *event, + struct hw_perf_event *hwc, int idx, long ovf) +{ + long prev_raw_count, new_raw_count; + long delta; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + new_raw_count = alpha_read_pmc(idx); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + goto again; + + delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf; + + /* It is possible on very rare occasions that the PMC has overflowed + * but the interrupt is yet to come. Detect and fix this situation. + */ + if (unlikely(delta < 0)) { + delta += alpha_pmu->pmc_max_period[idx] + 1; + } + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); + + return new_raw_count; +} + + +/* + * Collect all HW events into the array event[]. + */ +static int collect_events(struct perf_event *group, int max_count, + struct perf_event *event[], unsigned long *evtype, + int *current_idx) +{ + struct perf_event *pe; + int n = 0; + + if (!is_software_event(group)) { + if (n >= max_count) + return -1; + event[n] = group; + evtype[n] = group->hw.event_base; + current_idx[n++] = PMC_NO_INDEX; + } + list_for_each_entry(pe, &group->sibling_list, group_entry) { + if (!is_software_event(pe) && pe->state != PERF_EVENT_STATE_OFF) { + if (n >= max_count) + return -1; + event[n] = pe; + evtype[n] = pe->hw.event_base; + current_idx[n++] = PMC_NO_INDEX; + } + } + return n; +} + + + +/* + * Check that a group of events can be simultaneously scheduled on to the PMU. + */ +static int alpha_check_constraints(struct perf_event **events, + unsigned long *evtypes, int n_ev) +{ + + /* No HW events is possible from hw_perf_group_sched_in(). */ + if (n_ev == 0) + return 0; + + if (n_ev > alpha_pmu->num_pmcs) + return -1; + + return alpha_pmu->check_constraints(events, evtypes, n_ev); +} + + +/* + * If new events have been scheduled then update cpuc with the new + * configuration. This may involve shifting cycle counts from one PMC to + * another. + */ +static void maybe_change_configuration(struct cpu_hw_events *cpuc) +{ + int j; + + if (cpuc->n_added == 0) + return; + + /* Find counters that are moving to another PMC and update */ + for (j = 0; j < cpuc->n_events; j++) { + struct perf_event *pe = cpuc->event[j]; + + if (cpuc->current_idx[j] != PMC_NO_INDEX && + cpuc->current_idx[j] != pe->hw.idx) { + alpha_perf_event_update(pe, &pe->hw, cpuc->current_idx[j], 0); + cpuc->current_idx[j] = PMC_NO_INDEX; + } + } + + /* Assign to counters all unassigned events. */ + cpuc->idx_mask = 0; + for (j = 0; j < cpuc->n_events; j++) { + struct perf_event *pe = cpuc->event[j]; + struct hw_perf_event *hwc = &pe->hw; + int idx = hwc->idx; + + if (cpuc->current_idx[j] == PMC_NO_INDEX) { + alpha_perf_event_set_period(pe, hwc, idx); + cpuc->current_idx[j] = idx; + } + + if (!(hwc->state & PERF_HES_STOPPED)) + cpuc->idx_mask |= (1<<cpuc->current_idx[j]); + } + cpuc->config = cpuc->event[0]->hw.config_base; +} + + + +/* Schedule perf HW event on to PMU. + * - this function is called from outside this module via the pmu struct + * returned from perf event initialisation. + */ +static int alpha_pmu_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 n0; + int ret; + unsigned long irq_flags; + + /* + * The Sparc code has the IRQ disable first followed by the perf + * disable, however this can lead to an overflowed counter with the + * PMI disabled on rare occasions. The alpha_perf_event_update() + * routine should detect this situation by noting a negative delta, + * nevertheless we disable the PMCs first to enable a potential + * final PMI to occur before we disable interrupts. + */ + perf_pmu_disable(event->pmu); + local_irq_save(irq_flags); + + /* Default to error to be returned */ + ret = -EAGAIN; + + /* Insert event on to PMU and if successful modify ret to valid return */ + n0 = cpuc->n_events; + if (n0 < alpha_pmu->num_pmcs) { + cpuc->event[n0] = event; + cpuc->evtype[n0] = event->hw.event_base; + cpuc->current_idx[n0] = PMC_NO_INDEX; + + if (!alpha_check_constraints(cpuc->event, cpuc->evtype, n0+1)) { + cpuc->n_events++; + cpuc->n_added++; + ret = 0; + } + } + + hwc->state = PERF_HES_UPTODATE; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_STOPPED; + + local_irq_restore(irq_flags); + perf_pmu_enable(event->pmu); + + return ret; +} + + + +/* Disable performance monitoring unit + * - this function is called from outside this module via the pmu struct + * returned from perf event initialisation. + */ +static void alpha_pmu_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; + unsigned long irq_flags; + int j; + + perf_pmu_disable(event->pmu); + local_irq_save(irq_flags); + + for (j = 0; j < cpuc->n_events; j++) { + if (event == cpuc->event[j]) { + int idx = cpuc->current_idx[j]; + + /* Shift remaining entries down into the existing + * slot. + */ + while (++j < cpuc->n_events) { + cpuc->event[j - 1] = cpuc->event[j]; + cpuc->evtype[j - 1] = cpuc->evtype[j]; + cpuc->current_idx[j - 1] = + cpuc->current_idx[j]; + } + + /* Absorb the final count and turn off the event. */ + alpha_perf_event_update(event, hwc, idx, 0); + perf_event_update_userpage(event); + + cpuc->idx_mask &= ~(1UL<<idx); + cpuc->n_events--; + break; + } + } + + local_irq_restore(irq_flags); + perf_pmu_enable(event->pmu); +} + + +static void alpha_pmu_read(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + alpha_perf_event_update(event, hwc, hwc->idx, 0); +} + + +static void alpha_pmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!(hwc->state & PERF_HES_STOPPED)) { + cpuc->idx_mask &= ~(1UL<<hwc->idx); + hwc->state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + alpha_perf_event_update(event, hwc, hwc->idx, 0); + hwc->state |= PERF_HES_UPTODATE; + } + + if (cpuc->enabled) + wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx)); +} + + +static void alpha_pmu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + alpha_perf_event_set_period(event, hwc, hwc->idx); + } + + hwc->state = 0; + + cpuc->idx_mask |= 1UL<<hwc->idx; + if (cpuc->enabled) + wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx)); +} + + +/* + * Check that CPU performance counters are supported. + * - currently support EV67 and later CPUs. + * - actually some later revisions of the EV6 have the same PMC model as the + * EV67 but we don't do suffiently deep CPU detection to detect them. + * Bad luck to the very few people who might have one, I guess. + */ +static int supported_cpu(void) +{ + struct percpu_struct *cpu; + unsigned long cputype; + + /* Get cpu type from HW */ + cpu = (struct percpu_struct *)((char *)hwrpb + hwrpb->processor_offset); + cputype = cpu->type & 0xffffffff; + /* Include all of EV67, EV68, EV7, EV79 and EV69 as supported. */ + return (cputype >= EV67_CPU) && (cputype <= EV69_CPU); +} + + + +static void hw_perf_event_destroy(struct perf_event *event) +{ + /* Nothing to be done! */ + return; +} + + + +static int __hw_perf_event_init(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + struct perf_event *evts[MAX_HWEVENTS]; + unsigned long evtypes[MAX_HWEVENTS]; + int idx_rubbish_bin[MAX_HWEVENTS]; + int ev; + int n; + + /* We only support a limited range of HARDWARE event types with one + * only programmable via a RAW event type. + */ + if (attr->type == PERF_TYPE_HARDWARE) { + if (attr->config >= alpha_pmu->max_events) + return -EINVAL; + ev = alpha_pmu->event_map[attr->config]; + } else if (attr->type == PERF_TYPE_HW_CACHE) { + return -EOPNOTSUPP; + } else if (attr->type == PERF_TYPE_RAW) { + ev = attr->config & 0xff; + } else { + return -EOPNOTSUPP; + } + + if (ev < 0) { + return ev; + } + + /* The EV67 does not support mode exclusion */ + if (attr->exclude_kernel || attr->exclude_user + || attr->exclude_hv || attr->exclude_idle) { + return -EPERM; + } + + /* + * We place the event type in event_base here and leave calculation + * of the codes to programme the PMU for alpha_pmu_enable() because + * it is only then we will know what HW events are actually + * scheduled on to the PMU. At that point the code to programme the + * PMU is put into config_base and the PMC to use is placed into + * idx. We initialise idx (below) to PMC_NO_INDEX to indicate that + * it is yet to be determined. + */ + hwc->event_base = ev; + + /* Collect events in a group together suitable for calling + * alpha_check_constraints() to verify that the group as a whole can + * be scheduled on to the PMU. + */ + n = 0; + if (event->group_leader != event) { + n = collect_events(event->group_leader, + alpha_pmu->num_pmcs - 1, + evts, evtypes, idx_rubbish_bin); + if (n < 0) + return -EINVAL; + } + evtypes[n] = hwc->event_base; + evts[n] = event; + + if (alpha_check_constraints(evts, evtypes, n + 1)) + return -EINVAL; + + /* Indicate that PMU config and idx are yet to be determined. */ + hwc->config_base = 0; + hwc->idx = PMC_NO_INDEX; + + event->destroy = hw_perf_event_destroy; + + /* + * Most architectures reserve the PMU for their use at this point. + * As there is no existing mechanism to arbitrate usage and there + * appears to be no other user of the Alpha PMU we just assume + * that we can just use it, hence a NO-OP here. + * + * Maybe an alpha_reserve_pmu() routine should be implemented but is + * anything else ever going to use it? + */ + + if (!hwc->sample_period) { + hwc->sample_period = alpha_pmu->pmc_max_period[0]; + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + } + + return 0; +} + +/* + * Main entry point to initialise a HW performance event. + */ +static int alpha_pmu_event_init(struct perf_event *event) +{ + int err; + + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + + if (!alpha_pmu) + return -ENODEV; + + /* Do the real initialisation work. */ + err = __hw_perf_event_init(event); + + return err; +} + +/* + * Main entry point - enable HW performance counters. + */ +static void alpha_pmu_enable(struct pmu *pmu) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->enabled) + return; + + cpuc->enabled = 1; + barrier(); + + if (cpuc->n_events > 0) { + /* Update cpuc with information from any new scheduled events. */ + maybe_change_configuration(cpuc); + + /* Start counting the desired events. */ + wrperfmon(PERFMON_CMD_LOGGING_OPTIONS, EV67_PCTR_MODE_AGGREGATE); + wrperfmon(PERFMON_CMD_DESIRED_EVENTS, cpuc->config); + wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); + } +} + + +/* + * Main entry point - disable HW performance counters. + */ + +static void alpha_pmu_disable(struct pmu *pmu) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!cpuc->enabled) + return; + + cpuc->enabled = 0; + cpuc->n_added = 0; + + wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask); +} + +static struct pmu pmu = { + .pmu_enable = alpha_pmu_enable, + .pmu_disable = alpha_pmu_disable, + .event_init = alpha_pmu_event_init, + .add = alpha_pmu_add, + .del = alpha_pmu_del, + .start = alpha_pmu_start, + .stop = alpha_pmu_stop, + .read = alpha_pmu_read, +}; + + +/* + * Main entry point - don't know when this is called but it + * obviously dumps debug info. + */ +void perf_event_print_debug(void) +{ + unsigned long flags; + unsigned long pcr; + int pcr0, pcr1; + int cpu; + + if (!supported_cpu()) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + + pcr = wrperfmon(PERFMON_CMD_READ, 0); + pcr0 = (pcr >> alpha_pmu->pmc_count_shift[0]) & alpha_pmu->pmc_count_mask[0]; + pcr1 = (pcr >> alpha_pmu->pmc_count_shift[1]) & alpha_pmu->pmc_count_mask[1]; + + pr_info("CPU#%d: PCTR0[%06x] PCTR1[%06x]\n", cpu, pcr0, pcr1); + + local_irq_restore(flags); +} + + +/* + * Performance Monitoring Interrupt Service Routine called when a PMC + * overflows. The PMC that overflowed is passed in la_ptr. + */ +static void alpha_perf_event_irq_handler(unsigned long la_ptr, + struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc; + struct perf_sample_data data; + struct perf_event *event; + struct hw_perf_event *hwc; + int idx, j; + + __get_cpu_var(irq_pmi_count)++; + cpuc = &__get_cpu_var(cpu_hw_events); + + /* Completely counting through the PMC's period to trigger a new PMC + * overflow interrupt while in this interrupt routine is utterly + * disastrous! The EV6 and EV67 counters are sufficiently large to + * prevent this but to be really sure disable the PMCs. + */ + wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask); + + /* la_ptr is the counter that overflowed. */ + if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) { + /* This should never occur! */ + irq_err_count++; + pr_warning("PMI: silly index %ld\n", la_ptr); + wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); + return; + } + + idx = la_ptr; + + perf_sample_data_init(&data, 0); + for (j = 0; j < cpuc->n_events; j++) { + if (cpuc->current_idx[j] == idx) + break; + } + + if (unlikely(j == cpuc->n_events)) { + /* This can occur if the event is disabled right on a PMC overflow. */ + wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); + return; + } + + event = cpuc->event[j]; + + if (unlikely(!event)) { + /* This should never occur! */ + irq_err_count++; + pr_warning("PMI: No event at index %d!\n", idx); + wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); + return; + } + + hwc = &event->hw; + alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1); + data.period = event->hw.last_period; + + if (alpha_perf_event_set_period(event, hwc, idx)) { + if (perf_event_overflow(event, 1, &data, regs)) { + /* Interrupts coming too quickly; "throttle" the + * counter, i.e., disable it for a little while. + */ + alpha_pmu_stop(event, 0); + } + } + wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); + + return; +} + + + +/* + * Init call to initialise performance events at kernel startup. + */ +void __init init_hw_perf_events(void) +{ + pr_info("Performance events: "); + + if (!supported_cpu()) { + pr_cont("No support for your CPU.\n"); + return; + } + + pr_cont("Supported CPU type!\n"); + + /* Override performance counter IRQ vector */ + + perf_irq = alpha_perf_event_irq_handler; + + /* And set up PMU specification */ + alpha_pmu = &ev67_pmu; + + perf_pmu_register(&pmu); +} + diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 395a464353b8..3ec35066f1dc 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -356,7 +356,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti) dest[27] = pt->r27; dest[28] = pt->r28; dest[29] = pt->gp; - dest[30] = rdusp(); + dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp; dest[31] = pt->pc; /* Once upon a time this was the PS value. Which is stupid @@ -387,8 +387,9 @@ EXPORT_SYMBOL(dump_elf_task_fp); * sys_execve() executes a new program. */ asmlinkage int -do_sys_execve(char __user *ufilename, char __user * __user *argv, - char __user * __user *envp, struct pt_regs *regs) +do_sys_execve(const char __user *ufilename, + const char __user *const __user *argv, + const char __user *const __user *envp, struct pt_regs *regs) { int error; char *filename; diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 3d2627ec9860..d3e52d3fd592 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -156,9 +156,6 @@ extern void SMC669_Init(int); /* es1888.c */ extern void es1888_init(void); -/* ns87312.c */ -extern void ns87312_enable_ide(long ide_base); - /* ../lib/fpreg.c */ extern void alpha_write_fp_reg (unsigned long reg, unsigned long val); extern unsigned long alpha_read_fp_reg (unsigned long reg); diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c index baa903602f6a..e2af5eb59bb4 100644 --- a/arch/alpha/kernel/ptrace.c +++ b/arch/alpha/kernel/ptrace.c @@ -269,7 +269,8 @@ void ptrace_disable(struct task_struct *child) user_disable_single_step(child); } -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) { unsigned long tmp; size_t copied; @@ -292,7 +293,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case PTRACE_PEEKUSR: force_successful_syscall_return(); ret = get_reg(child, addr); - DBG(DBG_MEM, ("peek $%ld->%#lx\n", addr, ret)); + DBG(DBG_MEM, ("peek $%lu->%#lx\n", addr, ret)); break; /* When I and D space are separate, this will have to be fixed. */ @@ -302,7 +303,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; case PTRACE_POKEUSR: /* write the specified register */ - DBG(DBG_MEM, ("poke $%ld<-%#lx\n", addr, data)); + DBG(DBG_MEM, ("poke $%lu<-%#lx\n", addr, data)); ret = put_reg(child, addr, data); break; default: diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 0932dbb1ef8e..6f7feb5db271 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *, /* * The OSF/1 sigprocmask calling sequence is different from the * C sigprocmask() sequence.. - * - * how: - * 1 - SIG_BLOCK - * 2 - SIG_UNBLOCK - * 3 - SIG_SETMASK - * - * We change the range to -1 .. 1 in order to let gcc easily - * use the conditional move instructions. - * - * Note that we don't need to acquire the kernel lock for SMP - * operation, as all of this is local to this thread. */ -SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask, - struct pt_regs *, regs) +SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask) { - unsigned long oldmask = -EINVAL; - - if ((unsigned long)how-1 <= 2) { - long sign = how-2; /* -1 .. 1 */ - unsigned long block, unblock; - - newmask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - oldmask = current->blocked.sig[0]; - - unblock = oldmask & ~newmask; - block = oldmask | newmask; - if (!sign) - block = unblock; - if (sign <= 0) - newmask = block; - if (_NSIG_WORDS > 1 && sign > 0) - sigemptyset(¤t->blocked); - current->blocked.sig[0] = newmask; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - regs->r0 = 0; /* special no error return */ + sigset_t oldmask; + sigset_t mask; + unsigned long res; + + siginitset(&mask, newmask & _BLOCKABLE); + res = sigprocmask(how, &mask, &oldmask); + if (!res) { + force_successful_syscall_return(); + res = oldmask.sig[0]; } - return oldmask; + return res; } SYSCALL_DEFINE3(osf_sigaction, int, sig, @@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, old_sigset_t mask; if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags)) + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); new_ka.ka_restorer = NULL; } @@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, if (!ret && oact) { if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags)) + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; @@ -144,8 +118,7 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act, /* * Atomically swap in the new signal mask, and wait for a signal. */ -asmlinkage int -do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw) +SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) { mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); @@ -154,41 +127,6 @@ do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw) recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - /* Indicate EINTR on return from any possible signal handler, - which will not come back through here, but via sigreturn. */ - regs->r0 = EINTR; - regs->r19 = 1; - - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - return -ERESTARTNOHAND; -} - -asmlinkage int -do_rt_sigsuspend(sigset_t __user *uset, size_t sigsetsize, - struct pt_regs *regs, struct switch_stack *sw) -{ - sigset_t set; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - if (copy_from_user(&set, uset, sizeof(set))) - return -EFAULT; - - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - /* Indicate EINTR on return from any possible signal handler, - which will not come back through here, but via sigreturn. */ - regs->r0 = EINTR; - regs->r19 = 1; - current->state = TASK_INTERRUPTIBLE; schedule(); set_thread_flag(TIF_RESTORE_SIGMASK); @@ -239,6 +177,8 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long usp; long i, err = __get_user(regs->pc, &sc->sc_pc); + current_thread_info()->restart_block.fn = do_no_restart_syscall; + sw->r26 = (unsigned long) ret_from_sys_call; err |= __get_user(regs->r0, sc->sc_regs+0); @@ -591,7 +531,6 @@ syscall_restart(unsigned long r0, unsigned long r19, regs->pc -= 4; break; case ERESTART_RESTARTBLOCK: - current_thread_info()->restart_block.fn = do_no_restart_syscall; regs->r0 = EINTR; break; } diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index 4afc1a1e2e5a..f0df3fbd8402 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -87,7 +87,7 @@ static int srm_env_proc_show(struct seq_file *m, void *v) srm_env_t *entry; char *page; - entry = (srm_env_t *)m->private; + entry = m->private; page = (char *)__get_free_page(GFP_USER); if (!page) return -ENOMEM; diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index affd0f3f25df..14c8898d19ec 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -33,7 +33,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask = ~0UL; @@ -236,17 +236,30 @@ cabriolet_map_irq(struct pci_dev *dev, u8 slot, u8 pin) } static inline void __init +cabriolet_enable_ide(void) +{ + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + + pc873xx_enable_ide(); + } +} + +static inline void __init cabriolet_init_pci(void) { common_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } static inline void __init cia_cab_init_pci(void) { cia_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } /* diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 230464885b5c..4da596b6adbb 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -29,7 +29,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask[2] = { -1, -1 }; @@ -264,7 +264,14 @@ takara_init_pci(void) alpha_mv.pci_map_irq = takara_map_irq_srm; cia_init_pci(); - ns87312_enable_ide(0x26e); + + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + pc873xx_enable_ide(); + } } diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 09acb786e72b..a6a1de9db16f 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -58,7 +58,7 @@ sys_call_table: .quad sys_open /* 45 */ .quad alpha_ni_syscall .quad sys_getxgid - .quad osf_sigprocmask + .quad sys_osf_sigprocmask .quad alpha_ni_syscall .quad alpha_ni_syscall /* 50 */ .quad sys_acct @@ -512,6 +512,9 @@ sys_call_table: .quad sys_pwritev .quad sys_rt_tgsigqueueinfo .quad sys_perf_event_open + .quad sys_fanotify_init + .quad sys_fanotify_mark /* 495 */ + .quad sys_prlimit64 .size sys_call_table, . - sys_call_table .type sys_call_table, @object diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index 1efbed82c0fd..0f1d8493cfca 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -41,6 +41,7 @@ #include <linux/init.h> #include <linux/bcd.h> #include <linux/profile.h> +#include <linux/irq_work.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -82,6 +83,26 @@ static struct { unsigned long est_cycle_freq; +#ifdef CONFIG_IRQ_WORK + +DEFINE_PER_CPU(u8, irq_work_pending); + +#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 +#define test_irq_work_pending() __get_cpu_var(irq_work_pending) +#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 + +void set_irq_work_pending(void) +{ + set_irq_work_pending_flag(); +} + +#else /* CONFIG_IRQ_WORK */ + +#define test_irq_work_pending() 0 +#define clear_irq_work_pending() + +#endif /* CONFIG_IRQ_WORK */ + static inline __u32 rpcc(void) { @@ -170,6 +191,11 @@ irqreturn_t timer_interrupt(int irq, void *dev) write_sequnlock(&xtime_lock); + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); + } + #ifndef CONFIG_SMP while (nticks--) update_process_times(user_mode(get_irq_regs())); diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index b14f015008ad..0414e021a91c 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -13,7 +13,6 @@ #include <linux/sched.h> #include <linux/tty.h> #include <linux/delay.h> -#include <linux/smp_lock.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kallsyms.h> @@ -623,7 +622,6 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, return; } - lock_kernel(); printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); do_exit(SIGSEGV); @@ -646,7 +644,6 @@ got_exception: * Yikes! No one to forward the exception to. * Since the registers are in a weird format, dump them ourselves. */ - lock_kernel(); printk("%s(%d): unhandled unaligned exception\n", current->comm, task_pid_nr(current)); |