diff options
30 files changed, 322 insertions, 233 deletions
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index de1dfa18d0a1..21dbe6bdb8ed 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1122,7 +1122,7 @@ ENDPROC(fast_syscall_spill_registers) * a3: exctable, original value in excsave1 */ -fast_syscall_spill_registers_fixup: +ENTRY(fast_syscall_spill_registers_fixup) rsr a2, windowbase # get current windowbase (a2 is saved) xsr a0, depc # restore depc and a0 @@ -1134,22 +1134,26 @@ fast_syscall_spill_registers_fixup: */ xsr a3, excsave1 # get spill-mask - slli a2, a3, 1 # shift left by one + slli a3, a3, 1 # shift left by one - slli a3, a2, 32-WSBITS - src a2, a2, a3 # a1 = xxwww1yyxxxwww1yy...... + slli a2, a3, 32-WSBITS + src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy...... wsr a2, windowstart # set corrected windowstart - rsr a3, excsave1 - l32i a2, a3, EXC_TABLE_DOUBLE_SAVE # restore a2 - l32i a3, a3, EXC_TABLE_PARAM # original WB (in user task) + srli a3, a3, 1 + rsr a2, excsave1 + l32i a2, a2, EXC_TABLE_DOUBLE_SAVE # restore a2 + xsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE # save a3 + l32i a3, a2, EXC_TABLE_PARAM # original WB (in user task) + xsr a2, excsave1 /* Return to the original (user task) WINDOWBASE. * We leave the following frame behind: * a0, a1, a2 same - * a3: trashed (saved in excsave_1) + * a3: trashed (saved in EXC_TABLE_DOUBLE_SAVE) * depc: depc (we have to return to that address) - * excsave_1: a3 + * excsave_1: exctable */ wsr a3, windowbase @@ -1159,9 +1163,9 @@ fast_syscall_spill_registers_fixup: * a0: return address * a1: used, stack pointer * a2: kernel stack pointer - * a3: available, saved in EXCSAVE_1 + * a3: available * depc: exception address - * excsave: a3 + * excsave: exctable * Note: This frame might be the same as above. */ @@ -1181,9 +1185,12 @@ fast_syscall_spill_registers_fixup: rsr a0, exccause addx4 a0, a0, a3 # find entry in table l32i a0, a0, EXC_TABLE_FAST_USER # load handler + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE jx a0 -fast_syscall_spill_registers_fixup_return: +ENDPROC(fast_syscall_spill_registers_fixup) + +ENTRY(fast_syscall_spill_registers_fixup_return) /* When we return here, all registers have been restored (a2: DEPC) */ @@ -1191,13 +1198,13 @@ fast_syscall_spill_registers_fixup_return: /* Restore fixup handler. */ - xsr a3, excsave1 - movi a2, fast_syscall_spill_registers_fixup - s32i a2, a3, EXC_TABLE_FIXUP - s32i a0, a3, EXC_TABLE_DOUBLE_SAVE - rsr a2, windowbase - s32i a2, a3, EXC_TABLE_PARAM - l32i a2, a3, EXC_TABLE_KSTK + rsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE + movi a3, fast_syscall_spill_registers_fixup + s32i a3, a2, EXC_TABLE_FIXUP + rsr a3, windowbase + s32i a3, a2, EXC_TABLE_PARAM + l32i a2, a2, EXC_TABLE_KSTK /* Load WB at the time the exception occurred. */ @@ -1206,8 +1213,12 @@ fast_syscall_spill_registers_fixup_return: wsr a3, windowbase rsync + rsr a3, excsave1 + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE + rfde +ENDPROC(fast_syscall_spill_registers_fixup_return) /* * spill all registers. diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 718eca1850bd..98b67d5f1514 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -341,7 +341,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sp = regs->areg[1]; - if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && ! on_sig_stack(sp)) { + if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; } diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 56f88b7afe2f..e9e1aad8c271 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -737,7 +737,8 @@ static int __init iss_net_setup(char *str) return 1; } - if ((new = alloc_bootmem(sizeof new)) == NULL) { + new = alloc_bootmem(sizeof(*new)); + if (new == NULL) { printk("Alloc_bootmem failed\n"); return 1; } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 5cbc4bb1b395..df5e961484e1 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -105,8 +105,11 @@ static int scatter_elem_sz_prev = SG_SCATTER_SZ; static int sg_add(struct device *, struct class_interface *); static void sg_remove(struct device *, struct class_interface *); +static DEFINE_SPINLOCK(sg_open_exclusive_lock); + static DEFINE_IDR(sg_index_idr); -static DEFINE_RWLOCK(sg_index_lock); +static DEFINE_RWLOCK(sg_index_lock); /* Also used to lock + file descriptor list for device */ static struct class_interface sg_interface = { .add_dev = sg_add, @@ -143,7 +146,8 @@ typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ } Sg_request; typedef struct sg_fd { /* holds the state of a file descriptor */ - struct list_head sfd_siblings; /* protected by sfd_lock of device */ + /* sfd_siblings is protected by sg_index_lock */ + struct list_head sfd_siblings; struct sg_device *parentdp; /* owning device */ wait_queue_head_t read_wait; /* queue read until command done */ rwlock_t rq_list_lock; /* protect access to list in req_arr */ @@ -166,12 +170,13 @@ typedef struct sg_fd { /* holds the state of a file descriptor */ typedef struct sg_device { /* holds the state of each scsi generic device */ struct scsi_device *device; + wait_queue_head_t o_excl_wait; /* queue open() when O_EXCL in use */ int sg_tablesize; /* adapter's max scatter-gather table size */ u32 index; /* device index number */ - spinlock_t sfd_lock; /* protect file descriptor list for device */ + /* sfds is protected by sg_index_lock */ struct list_head sfds; - struct rw_semaphore o_sem; /* exclude open should hold this rwsem */ volatile char detached; /* 0->attached, 1->detached pending removal */ + /* exclude protected by sg_open_exclusive_lock */ char exclude; /* opened for exclusive access */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ struct gendisk *disk; @@ -220,14 +225,35 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd) return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE); } +static int get_exclude(Sg_device *sdp) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&sg_open_exclusive_lock, flags); + ret = sdp->exclude; + spin_unlock_irqrestore(&sg_open_exclusive_lock, flags); + return ret; +} + +static int set_exclude(Sg_device *sdp, char val) +{ + unsigned long flags; + + spin_lock_irqsave(&sg_open_exclusive_lock, flags); + sdp->exclude = val; + spin_unlock_irqrestore(&sg_open_exclusive_lock, flags); + return val; +} + static int sfds_list_empty(Sg_device *sdp) { unsigned long flags; int ret; - spin_lock_irqsave(&sdp->sfd_lock, flags); + read_lock_irqsave(&sg_index_lock, flags); ret = list_empty(&sdp->sfds); - spin_unlock_irqrestore(&sdp->sfd_lock, flags); + read_unlock_irqrestore(&sg_index_lock, flags); return ret; } @@ -239,6 +265,7 @@ sg_open(struct inode *inode, struct file *filp) struct request_queue *q; Sg_device *sdp; Sg_fd *sfp; + int res; int retval; nonseekable_open(inode, filp); @@ -267,52 +294,54 @@ sg_open(struct inode *inode, struct file *filp) goto error_out; } - if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE))) { - retval = -EPERM; /* Can't lock it with read only access */ - goto error_out; - } - if (flags & O_NONBLOCK) { - if (flags & O_EXCL) { - if (!down_write_trylock(&sdp->o_sem)) { - retval = -EBUSY; - goto error_out; - } - } else { - if (!down_read_trylock(&sdp->o_sem)) { - retval = -EBUSY; - goto error_out; - } + if (flags & O_EXCL) { + if (O_RDONLY == (flags & O_ACCMODE)) { + retval = -EPERM; /* Can't lock it with read only access */ + goto error_out; + } + if (!sfds_list_empty(sdp) && (flags & O_NONBLOCK)) { + retval = -EBUSY; + goto error_out; + } + res = wait_event_interruptible(sdp->o_excl_wait, + ((!sfds_list_empty(sdp) || get_exclude(sdp)) ? 0 : set_exclude(sdp, 1))); + if (res) { + retval = res; /* -ERESTARTSYS because signal hit process */ + goto error_out; + } + } else if (get_exclude(sdp)) { /* some other fd has an exclusive lock on dev */ + if (flags & O_NONBLOCK) { + retval = -EBUSY; + goto error_out; + } + res = wait_event_interruptible(sdp->o_excl_wait, !get_exclude(sdp)); + if (res) { + retval = res; /* -ERESTARTSYS because signal hit process */ + goto error_out; } - } else { - if (flags & O_EXCL) - down_write(&sdp->o_sem); - else - down_read(&sdp->o_sem); } - /* Since write lock is held, no need to check sfd_list */ - if (flags & O_EXCL) - sdp->exclude = 1; /* used by release lock */ - + if (sdp->detached) { + retval = -ENODEV; + goto error_out; + } if (sfds_list_empty(sdp)) { /* no existing opens on this device */ sdp->sgdebug = 0; q = sdp->device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } - sfp = sg_add_sfp(sdp, dev); - if (!IS_ERR(sfp)) + if ((sfp = sg_add_sfp(sdp, dev))) filp->private_data = sfp; - /* retval is already provably zero at this point because of the - * check after retval = scsi_autopm_get_device(sdp->device)) - */ else { - retval = PTR_ERR(sfp); - if (flags & O_EXCL) { - sdp->exclude = 0; /* undo if error */ - up_write(&sdp->o_sem); - } else - up_read(&sdp->o_sem); + set_exclude(sdp, 0); /* undo if error */ + wake_up_interruptible(&sdp->o_excl_wait); + } + retval = -ENOMEM; + goto error_out; + } + retval = 0; error_out: + if (retval) { scsi_autopm_put_device(sdp->device); sdp_put: scsi_device_put(sdp->device); @@ -329,18 +358,13 @@ sg_release(struct inode *inode, struct file *filp) { Sg_device *sdp; Sg_fd *sfp; - int excl; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_release: %s\n", sdp->disk->disk_name)); - excl = sdp->exclude; - sdp->exclude = 0; - if (excl) - up_write(&sdp->o_sem); - else - up_read(&sdp->o_sem); + set_exclude(sdp, 0); + wake_up_interruptible(&sdp->o_excl_wait); scsi_autopm_put_device(sdp->device); kref_put(&sfp->f_ref, sg_remove_sfp); @@ -1391,9 +1415,8 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) disk->first_minor = k; sdp->disk = disk; sdp->device = scsidp; - spin_lock_init(&sdp->sfd_lock); INIT_LIST_HEAD(&sdp->sfds); - init_rwsem(&sdp->o_sem); + init_waitqueue_head(&sdp->o_excl_wait); sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); @@ -1526,13 +1549,11 @@ static void sg_remove(struct device *cl_dev, struct class_interface *cl_intf) /* Need a write lock to set sdp->detached. */ write_lock_irqsave(&sg_index_lock, iflags); - spin_lock(&sdp->sfd_lock); sdp->detached = 1; list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) { wake_up_interruptible(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP); } - spin_unlock(&sdp->sfd_lock); write_unlock_irqrestore(&sg_index_lock, iflags); sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic"); @@ -2043,7 +2064,7 @@ sg_add_sfp(Sg_device * sdp, int dev) sfp = kzalloc(sizeof(*sfp), GFP_ATOMIC | __GFP_NOWARN); if (!sfp) - return ERR_PTR(-ENOMEM); + return NULL; init_waitqueue_head(&sfp->read_wait); rwlock_init(&sfp->rq_list_lock); @@ -2057,13 +2078,9 @@ sg_add_sfp(Sg_device * sdp, int dev) sfp->cmd_q = SG_DEF_COMMAND_Q; sfp->keep_orphan = SG_DEF_KEEP_ORPHAN; sfp->parentdp = sdp; - spin_lock_irqsave(&sdp->sfd_lock, iflags); - if (sdp->detached) { - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); - return ERR_PTR(-ENODEV); - } + write_lock_irqsave(&sg_index_lock, iflags); list_add_tail(&sfp->sfd_siblings, &sdp->sfds); - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); + write_unlock_irqrestore(&sg_index_lock, iflags); SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp: sfp=0x%p\n", sfp)); if (unlikely(sg_big_buff != def_reserved_size)) sg_big_buff = def_reserved_size; @@ -2113,9 +2130,10 @@ static void sg_remove_sfp(struct kref *kref) struct sg_device *sdp = sfp->parentdp; unsigned long iflags; - spin_lock_irqsave(&sdp->sfd_lock, iflags); + write_lock_irqsave(&sg_index_lock, iflags); list_del(&sfp->sfd_siblings); - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); + write_unlock_irqrestore(&sg_index_lock, iflags); + wake_up_interruptible(&sdp->o_excl_wait); INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext); schedule_work(&sfp->ew.work); @@ -2502,7 +2520,7 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v) return 0; } -/* must be called while holding sg_index_lock and sfd_lock */ +/* must be called while holding sg_index_lock */ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) { int k, m, new_interface, blen, usg; @@ -2587,26 +2605,22 @@ static int sg_proc_seq_show_debug(struct seq_file *s, void *v) read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; - if (sdp) { - spin_lock(&sdp->sfd_lock); - if (!list_empty(&sdp->sfds)) { - struct scsi_device *scsidp = sdp->device; + if (sdp && !list_empty(&sdp->sfds)) { + struct scsi_device *scsidp = sdp->device; - seq_printf(s, " >>> device=%s ", sdp->disk->disk_name); - if (sdp->detached) - seq_printf(s, "detached pending close "); - else - seq_printf - (s, "scsi%d chan=%d id=%d lun=%d em=%d", - scsidp->host->host_no, - scsidp->channel, scsidp->id, - scsidp->lun, - scsidp->host->hostt->emulated); - seq_printf(s, " sg_tablesize=%d excl=%d\n", - sdp->sg_tablesize, sdp->exclude); - sg_proc_debug_helper(s, sdp); - } - spin_unlock(&sdp->sfd_lock); + seq_printf(s, " >>> device=%s ", sdp->disk->disk_name); + if (sdp->detached) + seq_printf(s, "detached pending close "); + else + seq_printf + (s, "scsi%d chan=%d id=%d lun=%d em=%d", + scsidp->host->host_no, + scsidp->channel, scsidp->id, + scsidp->lun, + scsidp->host->hostt->emulated); + seq_printf(s, " sg_tablesize=%d excl=%d\n", + sdp->sg_tablesize, get_exclude(sdp)); + sg_proc_debug_helper(s, sdp); } read_unlock_irqrestore(&sg_index_lock, iflags); return 0; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index ba475632c5fa..0e808cf91d97 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -642,16 +642,29 @@ static int uio_mmap_physical(struct vm_area_struct *vma) { struct uio_device *idev = vma->vm_private_data; int mi = uio_find_mem_index(vma); + struct uio_mem *mem; if (mi < 0) return -EINVAL; + mem = idev->info->mem + mi; - vma->vm_ops = &uio_physical_vm_ops; + if (vma->vm_end - vma->vm_start > mem->size) + return -EINVAL; + vma->vm_ops = &uio_physical_vm_ops; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + /* + * We cannot use the vm_iomap_memory() helper here, + * because vma->vm_pgoff is the map index we looked + * up above in uio_find_mem_index(), rather than an + * actual page offset into the mmap. + * + * So we just do the physical mmap without a page + * offset. + */ return remap_pfn_range(vma, vma->vm_start, - idev->info->mem[mi].addr >> PAGE_SHIFT, + mem->addr >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot); } diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c index a54ccdc4d661..22ad85242e5b 100644 --- a/drivers/video/au1100fb.c +++ b/drivers/video/au1100fb.c @@ -361,37 +361,13 @@ void au1100fb_fb_rotate(struct fb_info *fbi, int angle) int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma) { struct au1100fb_device *fbdev; - unsigned int len; - unsigned long start=0, off; fbdev = to_au1100fb_device(fbi); - if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) { - return -EINVAL; - } - - start = fbdev->fb_phys & PAGE_MASK; - len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len); - - off = vma->vm_pgoff << PAGE_SHIFT; - - if ((vma->vm_end - vma->vm_start + off) > len) { - return -EINVAL; - } - - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6 - if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) { - return -EAGAIN; - } - - return 0; + return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len); } static struct fb_ops au1100fb_ops = diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c index 301224ecc950..1d02897d17f2 100644 --- a/drivers/video/au1200fb.c +++ b/drivers/video/au1200fb.c @@ -1233,34 +1233,13 @@ static int au1200fb_fb_blank(int blank_mode, struct fb_info *fbi) * method mainly to allow the use of the TLB streaming flag (CCA=6) */ static int au1200fb_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) - { - unsigned int len; - unsigned long start=0, off; struct au1200fb_device *fbdev = info->par; - if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) { - return -EINVAL; - } - - start = fbdev->fb_phys & PAGE_MASK; - len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len); - - off = vma->vm_pgoff << PAGE_SHIFT; - - if ((vma->vm_end - vma->vm_start + off) > len) { - return -EINVAL; - } - - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); pgprot_val(vma->vm_page_prot) |= _CACHE_MASK; /* CCA=7 */ - return io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); + return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len); } static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 06344d986eb9..094f3152ec2b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -983,7 +983,7 @@ config DEBUG_KOBJECT config DEBUG_KOBJECT_RELEASE bool "kobject release debugging" - depends on DEBUG_KERNEL + depends on DEBUG_OBJECTS_TIMERS help kobjects are reference counted objects. This means that their last reference count put is not predictable, and the kobject can diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e297b74471b8..ca0d3d9f4bac 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -90,8 +90,20 @@ OPTIONS Number of mmap data pages. Must be a power of two. -g:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Do call-graph (stack chain/backtrace) recording. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -g. + + Allows specifying "fp" (frame pointer) or "dwarf" + (DWARF's CFI - Call Frame Information) as the method to collect + the information used to show the call graphs. + + In some systems, where binaries are build with gcc + --fomit-frame-pointer, using the "fp" method will produce bogus + call graphs, using "dwarf", if available (perf tools linked to + the libunwind library) should be used instead. -q:: --quiet:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 58d6598a9686..6a118e71d003 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -140,20 +140,12 @@ Default is to monitor all CPUS. --asm-raw:: Show raw instruction encoding of assembly instructions. --G [type,min,order]:: +-G:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Display call chains using type, min percent threshold and order. - type can be either: - - flat: single column, linear exposure of call chains. - - graph: use a graph tree, displaying absolute overhead rates. - - fractal: like graph, but displays relative rates. Each branch of - the tree is considered as a new profiled object. - - order can be either: - - callee: callee based call graph. - - caller: inverted caller based call graph. - - Default: fractal,0.5,callee. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -G. --ignore-callees=<regex>:: Ignore callees of the function(s) matching the given regex. diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 935d52216c89..fbc2888d6495 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -888,11 +888,18 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) { err = perf_evlist__parse_sample(kvm->evlist, event, &sample); if (err) { + perf_evlist__mmap_consume(kvm->evlist, idx); pr_err("Failed to parse sample\n"); return -1; } err = perf_session_queue_event(kvm->session, event, &sample, 0); + /* + * FIXME: Here we can't consume the event, as perf_session_queue_event will + * point to it, and it'll get possibly overwritten by the kernel. + */ + perf_evlist__mmap_consume(kvm->evlist, idx); + if (err) { pr_err("Failed to enqueue sample: %d\n", err); return -1; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a41ac41546c9..d04651484640 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -712,21 +712,12 @@ static int get_stack_size(char *str, unsigned long *_size) } #endif /* LIBUNWIND_SUPPORT */ -int record_parse_callchain_opt(const struct option *opt, - const char *arg, int unset) +int record_parse_callchain(const char *arg, struct perf_record_opts *opts) { - struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; - /* --no-call-graph */ - if (unset) - return 0; - - /* We specified default option if none is provided. */ - BUG_ON(!arg); - /* We need buffer that we know we can write to. */ buf = malloc(strlen(arg) + 1); if (!buf) @@ -764,13 +755,9 @@ int record_parse_callchain_opt(const struct option *opt, ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } - - if (!ret) - pr_debug("callchain: stack dump size %d\n", - opts->stack_dump_size); #endif /* LIBUNWIND_SUPPORT */ } else { - pr_err("callchain: Unknown -g option " + pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); break; } @@ -778,13 +765,52 @@ int record_parse_callchain_opt(const struct option *opt, } while (0); free(buf); + return ret; +} + +static void callchain_debug(struct perf_record_opts *opts) +{ + pr_debug("callchain: type %d\n", opts->call_graph); + if (opts->call_graph == CALLCHAIN_DWARF) + pr_debug("callchain: stack dump size %d\n", + opts->stack_dump_size); +} + +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + struct perf_record_opts *opts = opt->value; + int ret; + + /* --no-call-graph */ + if (unset) { + opts->call_graph = CALLCHAIN_NONE; + pr_debug("callchain: disabled\n"); + return 0; + } + + ret = record_parse_callchain(arg, opts); if (!ret) - pr_debug("callchain: type %d\n", opts->call_graph); + callchain_debug(opts); return ret; } +int record_callchain_opt(const struct option *opt, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + struct perf_record_opts *opts = opt->value; + + if (opts->call_graph == CALLCHAIN_NONE) + opts->call_graph = CALLCHAIN_FP; + + callchain_debug(opts); + return 0; +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -813,12 +839,12 @@ static struct perf_record record = { }, }; -#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " +#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " #ifdef LIBUNWIND_SUPPORT -const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else -const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp"; #endif /* @@ -858,9 +884,12 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, - "mode[,dump_size]", record_callchain_help, - &record_parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('g', NULL, &record.opts, + NULL, "enables call-graph recording" , + &record_callchain_opt), + OPT_CALLBACK(0, "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 212214162bb2..5a11f13e56f9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -810,7 +810,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ret = perf_evlist__parse_sample(top->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - continue; + goto next_event; } evsel = perf_evlist__id2evsel(session->evlist, sample.id); @@ -825,13 +825,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) case PERF_RECORD_MISC_USER: ++top->us_samples; if (top->hide_user_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: @@ -847,7 +847,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) */ /* Fall thru */ default: - continue; + goto next_event; } @@ -859,6 +859,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) machine__process_event(machine, event); } else ++session->stats.nr_unknown_events; +next_event: + perf_evlist__mmap_consume(top->evlist, idx); } } @@ -1016,16 +1018,16 @@ out_delete: } static int -parse_callchain_opt(const struct option *opt, const char *arg, int unset) +callchain_opt(const struct option *opt, const char *arg, int unset) { - /* - * --no-call-graph - */ - if (unset) - return 0; - symbol_conf.use_callchain = true; + return record_callchain_opt(opt, arg, unset); +} +static int +parse_callchain_opt(const struct option *opt, const char *arg, int unset) +{ + symbol_conf.use_callchain = true; return record_parse_callchain_opt(opt, arg, unset); } @@ -1106,9 +1108,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, - "mode[,dump_size]", record_callchain_help, - &parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts, + NULL, "enables call-graph recording", + &callchain_opt), + OPT_CALLBACK(0, "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 71aa3e35406b..99c8d9ad6729 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -987,7 +987,7 @@ again: err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); - continue; + goto next_event; } if (trace->base_time == 0) @@ -1001,18 +1001,20 @@ again: evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - continue; + goto next_event; } if (sample.raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); - continue; + goto next_event; } handler = evsel->handler.func; handler(trace, evsel, &sample); +next_event: + perf_evlist__mmap_consume(evlist, i); if (done) goto out_unmap_evlist; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 6fb781d5586c..e3fedfa2906e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -290,6 +290,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist, for (i = 0; i < evlist->nr_mmaps; i++) { while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { ret = process_event(machine, evlist, event, state); + perf_evlist__mmap_consume(evlist, i); if (ret < 0) return ret; } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index d444ea2c47d9..376c35608534 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -36,6 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) (pid_t)event->comm.tid == getpid() && strcmp(event->comm.comm, comm) == 0) found += 1; + perf_evlist__mmap_consume(evlist, i); } } return found; diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index c4185b9aeb80..a7232c204eb9 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -122,6 +122,7 @@ int test__basic_mmap(void) goto out_munmap; } nr_events[evsel->idx]++; + perf_evlist__mmap_consume(evlist, 0); } err = 0; diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index fc5b9fca8b47..524b221b829b 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void) ++nr_events; - if (type != PERF_RECORD_SAMPLE) + if (type != PERF_RECORD_SAMPLE) { + perf_evlist__mmap_consume(evlist, i); continue; + } err = perf_evsel__parse_sample(evsel, event, &sample); if (err) { diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index b8a7056519ac..7923b06ffc91 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -263,6 +263,8 @@ int test__PERF_RECORD(void) type); ++errs; } + + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 0ab61b1f408e..4ca1b938f6a6 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -122,7 +122,7 @@ int test__perf_time_to_tsc(void) if (event->header.type != PERF_RECORD_COMM || (pid_t)event->comm.pid != getpid() || (pid_t)event->comm.tid != getpid()) - continue; + goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { CHECK__(perf_evsel__parse_sample(evsel, event, @@ -134,6 +134,8 @@ int test__perf_time_to_tsc(void) &sample)); comm2_time = sample.time; } +next_event: + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 2e41e2d32ccc..6e2b44ec0749 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) - continue; + goto next_event; err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { @@ -88,6 +88,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) total_periods += sample.period; nr_samples++; +next_event: + perf_evlist__mmap_consume(evlist, 0); } if ((u64) nr_samples == total_periods) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 28fe5894b061..a3e64876e940 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -96,10 +96,10 @@ int test__task_exit(void) retry: while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { - if (event->header.type != PERF_RECORD_EXIT) - continue; + if (event->header.type == PERF_RECORD_EXIT) + nr_exit++; - nr_exit++; + perf_evlist__mmap_consume(evlist, 0); } if (!exited || !nr_exit) { diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 194e2f42ff5d..6c152686e837 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -315,8 +315,7 @@ static inline void advance_hpp(struct perf_hpp *hpp, int inc) } static int hist_entry__period_snprintf(struct perf_hpp *hpp, - struct hist_entry *he, - bool color) + struct hist_entry *he) { const char *sep = symbol_conf.field_sep; struct perf_hpp_fmt *fmt; @@ -338,7 +337,7 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp, } else first = false; - if (color && fmt->color) + if (perf_hpp__use_color() && fmt->color) ret = fmt->color(fmt, hpp, he); else ret = fmt->entry(fmt, hpp, he); @@ -358,12 +357,11 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, .buf = bf, .size = size, }; - bool color = !symbol_conf.field_sep; if (size == 0 || size > bfsz) size = hpp.size = bfsz; - ret = hist_entry__period_snprintf(&hpp, he, color); + ret = hist_entry__period_snprintf(&hpp, he); hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); ret = fprintf(fp, "%s\n", bf); @@ -482,6 +480,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, print_entries: linesz = hists__sort_list_width(hists) + 3 + 1; + linesz += perf_hpp__color_overhead(); line = malloc(linesz); if (line == NULL) { ret = -1; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 2b585bc308cf..9e99060408ae 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -147,6 +147,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; +int record_parse_callchain(const char *arg, struct perf_record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 63df031fc9c7..49096ea58a15 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -213,7 +213,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, &event->mmap.pgoff, execname); - if (n != 8) + if (n != 5) continue; if (prot[2] != 'x') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f9f77bee0b1b..e584cd30b0f2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -545,12 +545,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) md->prev = old; - if (!evlist->overwrite) - perf_mmap__write_tail(md, old); - return event; } +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + if (!evlist->overwrite) { + struct perf_mmap *md = &evlist->mmap[idx]; + unsigned int old = md->prev; + + perf_mmap__write_tail(md, old); + } +} + static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) { if (evlist->mmap[idx].base != NULL) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 880d7139d2fb..206d09339306 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -89,6 +89,8 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); + int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1329b6b6ffe6..ce8dc61ce2c3 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -5,6 +5,7 @@ #include <pthread.h> #include "callchain.h" #include "header.h" +#include "color.h" extern struct callchain_param callchain_param; @@ -175,6 +176,18 @@ void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +static inline size_t perf_hpp__use_color(void) +{ + return !symbol_conf.field_sep; +} + +static inline size_t perf_hpp__color_overhead(void) +{ + return perf_hpp__use_color() ? + (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX + : 0; +} + struct perf_evlist; struct hist_browser_timer { diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 71b5412bbbb9..2ac4bc92bb1f 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -822,6 +822,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + perf_evlist__mmap_consume(evlist, cpu); + if (pyevent == NULL) return PyErr_NoMemory(); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cc75a3cef388..95d91a0b23af 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name) Py_FatalError("problem in Python trace event handler"); } +/* + * Insert val into into the dictionary and decrement the reference counter. + * This is necessary for dictionaries since PyDict_SetItemString() does not + * steal a reference, as opposed to PyTuple_SetItem(). + */ +static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) +{ + PyDict_SetItemString(dict, key, val); + Py_DECREF(val); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); } else { - PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu)); - PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s)); - PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns)); - PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid)); - PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); + pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); + pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); + pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); + pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event if (handler) PyTuple_SetItem(t, n++, obj); else - PyDict_SetItemString(dict, field->name, obj); + pydict_set_item_string_decref(dict, field->name, obj); } if (!handler) @@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event if (!handler || !PyCallable_Check(handler)) goto exit; - PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( (const char *)sample, sizeof(*sample))); - PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); - PyDict_SetItemString(dict, "comm", + pydict_set_item_string_decref(dict, "comm", PyString_FromString(thread->comm)); if (al->map) { - PyDict_SetItemString(dict, "dso", + pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); } if (al->sym) { - PyDict_SetItemString(dict, "symbol", + pydict_set_item_string_decref(dict, "symbol", PyString_FromString(al->sym->name)); } |