From: Peter Zijlstra <peterz@infradead.org> To: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@elte.hu>, Steven Rostedt <rostedt@goodmis.org>, Linux-mm <linux-mm@kvack.org>, Arnaldo Carvalho de Melo <acme@infradead.org>, Linus Torvalds <torvalds@linux-foundation.org>, Jonathan Corbet <corbet@lwn.net>, Christoph Hellwig <hch@infradead.org>, Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>, Thomas Gleixner <tglx@linutronix.de>, Ananth N Mavinakayanahalli <ananth@in.ibm.com>, Oleg Nesterov <oleg@redhat.com>, Andrew Morton <akpm@linux-foundation.org>, SystemTap <systemtap@sources.redhat.com>, Jim Keniston <jkenisto@linux.vnet.ibm.com>, Roland McGrath <roland@hack.frob.com>, Andi Kleen <andi@firstfloor.org>, LKML <linux-kernel@vger.kernel.org> Subject: Re: [PATCH v3 2.6.39-rc1-tip 12/26] 12: uprobes: slot allocation for uprobes Date: Mon, 18 Apr 2011 18:46:11 +0200 [thread overview] Message-ID: <1303145171.32491.886.camel@twins> (raw) In-Reply-To: <20110401143457.15455.64839.sendpatchset@localhost6.localdomain6> On Fri, 2011-04-01 at 20:04 +0530, Srikar Dronamraju wrote: > Every task is allocated a fixed slot. When a probe is hit, the original > instruction corresponding to the probe hit is copied to per-task fixed > slot. Currently we allocate one page of slots for each mm. Bitmaps are > used to know which slots are free. Each slot is made of 128 bytes so > that its cache aligned. > > TODO: On massively threaded processes (or if a huge number of processes > share the same mm), there is a possiblilty of running out of slots. > One alternative could be to extend the slots as when slots are required. As long as you're single stepping things and not using boosted probes you can fully serialize the slot usage. Claim a slot on trap and release the slot on finish. Claiming can wait on a free slot since you already have the whole SLEEPY thing. > +static int xol_add_vma(struct uprobes_xol_area *area) > +{ > + struct vm_area_struct *vma; > + struct mm_struct *mm; > + struct file *file; > + unsigned long addr; > + int ret = -ENOMEM; > + > + mm = get_task_mm(current); > + if (!mm) > + return -ESRCH; > + > + down_write(&mm->mmap_sem); > + if (mm->uprobes_xol_area) { > + ret = -EALREADY; > + goto fail; > + } > + > + /* > + * Find the end of the top mapping and skip a page. > + * If there is no space for PAGE_SIZE above > + * that, mmap will ignore our address hint. > + * > + * We allocate a "fake" unlinked shmem file because > + * anonymous memory might not be granted execute > + * permission when the selinux security hooks have > + * their way. > + */ That just annoys me, so we're working around some stupid sekurity crap, executable anonymous maps are perfectly fine, also what do JITs do? > + vma = rb_entry(rb_last(&mm->mm_rb), struct vm_area_struct, vm_rb); > + addr = vma->vm_end + PAGE_SIZE; > + file = shmem_file_setup("uprobes/xol", PAGE_SIZE, VM_NORESERVE); > + if (!file) { > + printk(KERN_ERR "uprobes_xol failed to setup shmem_file " > + "while allocating vma for pid/tgid %d/%d for " > + "single-stepping out of line.\n", > + current->pid, current->tgid); > + goto fail; > + } > + addr = do_mmap_pgoff(file, addr, PAGE_SIZE, PROT_EXEC, MAP_PRIVATE, 0); > + fput(file); > + > + if (addr & ~PAGE_MASK) { > + printk(KERN_ERR "uprobes_xol failed to allocate a vma for " > + "pid/tgid %d/%d for single-stepping out of " > + "line.\n", current->pid, current->tgid); > + goto fail; > + } > + vma = find_vma(mm, addr); > + > + /* Don't expand vma on mremap(). */ > + vma->vm_flags |= VM_DONTEXPAND | VM_DONTCOPY; > + area->vaddr = vma->vm_start; > + if (get_user_pages(current, mm, area->vaddr, 1, 1, 1, &area->page, > + &vma) > 0) > + ret = 0; > + > +fail: > + up_write(&mm->mmap_sem); > + mmput(mm); > + return ret; > +}
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org> To: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@elte.hu>, Steven Rostedt <rostedt@goodmis.org>, Linux-mm <linux-mm@kvack.org>, Arnaldo Carvalho de Melo <acme@infradead.org>, Linus Torvalds <torvalds@linux-foundation.org>, Jonathan Corbet <corbet@lwn.net>, Christoph Hellwig <hch@infradead.org>, Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>, Thomas Gleixner <tglx@linutronix.de>, Ananth N Mavinakayanahalli <ananth@in.ibm.com>, Oleg Nesterov <oleg@redhat.com>, Andrew Morton <akpm@linux-foundation.org>, SystemTap <systemtap@sources.redhat.com>, Jim Keniston <jkenisto@linux.vnet.ibm.com>, Roland McGrath <roland@hack.frob.com>, Andi Kleen <andi@firstfloor.org>, LKML <linux-kernel@vger.kernel.org> Subject: Re: [PATCH v3 2.6.39-rc1-tip 12/26] 12: uprobes: slot allocation for uprobes Date: Mon, 18 Apr 2011 18:46:11 +0200 [thread overview] Message-ID: <1303145171.32491.886.camel@twins> (raw) In-Reply-To: <20110401143457.15455.64839.sendpatchset@localhost6.localdomain6> On Fri, 2011-04-01 at 20:04 +0530, Srikar Dronamraju wrote: > Every task is allocated a fixed slot. When a probe is hit, the original > instruction corresponding to the probe hit is copied to per-task fixed > slot. Currently we allocate one page of slots for each mm. Bitmaps are > used to know which slots are free. Each slot is made of 128 bytes so > that its cache aligned. > > TODO: On massively threaded processes (or if a huge number of processes > share the same mm), there is a possiblilty of running out of slots. > One alternative could be to extend the slots as when slots are required. As long as you're single stepping things and not using boosted probes you can fully serialize the slot usage. Claim a slot on trap and release the slot on finish. Claiming can wait on a free slot since you already have the whole SLEEPY thing. > +static int xol_add_vma(struct uprobes_xol_area *area) > +{ > + struct vm_area_struct *vma; > + struct mm_struct *mm; > + struct file *file; > + unsigned long addr; > + int ret = -ENOMEM; > + > + mm = get_task_mm(current); > + if (!mm) > + return -ESRCH; > + > + down_write(&mm->mmap_sem); > + if (mm->uprobes_xol_area) { > + ret = -EALREADY; > + goto fail; > + } > + > + /* > + * Find the end of the top mapping and skip a page. > + * If there is no space for PAGE_SIZE above > + * that, mmap will ignore our address hint. > + * > + * We allocate a "fake" unlinked shmem file because > + * anonymous memory might not be granted execute > + * permission when the selinux security hooks have > + * their way. > + */ That just annoys me, so we're working around some stupid sekurity crap, executable anonymous maps are perfectly fine, also what do JITs do? > + vma = rb_entry(rb_last(&mm->mm_rb), struct vm_area_struct, vm_rb); > + addr = vma->vm_end + PAGE_SIZE; > + file = shmem_file_setup("uprobes/xol", PAGE_SIZE, VM_NORESERVE); > + if (!file) { > + printk(KERN_ERR "uprobes_xol failed to setup shmem_file " > + "while allocating vma for pid/tgid %d/%d for " > + "single-stepping out of line.\n", > + current->pid, current->tgid); > + goto fail; > + } > + addr = do_mmap_pgoff(file, addr, PAGE_SIZE, PROT_EXEC, MAP_PRIVATE, 0); > + fput(file); > + > + if (addr & ~PAGE_MASK) { > + printk(KERN_ERR "uprobes_xol failed to allocate a vma for " > + "pid/tgid %d/%d for single-stepping out of " > + "line.\n", current->pid, current->tgid); > + goto fail; > + } > + vma = find_vma(mm, addr); > + > + /* Don't expand vma on mremap(). */ > + vma->vm_flags |= VM_DONTEXPAND | VM_DONTCOPY; > + area->vaddr = vma->vm_start; > + if (get_user_pages(current, mm, area->vaddr, 1, 1, 1, &area->page, > + &vma) > 0) > + ret = 0; > + > +fail: > + up_write(&mm->mmap_sem); > + mmput(mm); > + return ret; > +} -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-04-18 16:46 UTC|newest] Thread overview: 150+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-04-01 14:32 [PATCH v3 2.6.39-rc1-tip 0/26] 0: Uprobes patchset with perf probe support Srikar Dronamraju 2011-04-01 14:32 ` Srikar Dronamraju 2011-04-01 14:32 ` [PATCH v3 2.6.39-rc1-tip 1/26] 1: mm: replace_page() loses static attribute Srikar Dronamraju 2011-04-01 14:32 ` Srikar Dronamraju 2011-04-01 14:32 ` [PATCH v3 2.6.39-rc1-tip 2/26] 2: mm: Move replace_page() to mm/memory.c Srikar Dronamraju 2011-04-01 14:32 ` Srikar Dronamraju 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 3/26] 3: X86 specific breakpoint definitions Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 4/26] 4: uprobes: Breakground page replacement Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-18 12:20 ` Peter Zijlstra 2011-04-18 12:20 ` Peter Zijlstra 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 5/26] 5: uprobes: Adding and remove a uprobe in a rb tree Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-18 12:20 ` Peter Zijlstra 2011-04-18 12:20 ` Peter Zijlstra 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 6/26] 6: Uprobes: register/unregister probes Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-02 0:26 ` Stephen Wilson 2011-04-02 0:26 ` Stephen Wilson 2011-04-02 0:53 ` Srikar Dronamraju 2011-04-02 0:53 ` Srikar Dronamraju 2011-04-02 1:29 ` Stephen Wilson 2011-04-02 1:29 ` Stephen Wilson 2011-04-18 12:20 ` Peter Zijlstra 2011-04-18 12:20 ` Peter Zijlstra 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 7/26] 7: x86: analyze instruction and determine fixups Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-19 13:29 ` Steven Rostedt 2011-04-19 13:29 ` Steven Rostedt 2011-04-21 17:31 ` Srikar Dronamraju 2011-04-21 17:31 ` Srikar Dronamraju 2011-04-21 17:52 ` Peter Zijlstra 2011-04-21 17:52 ` Peter Zijlstra 2011-04-01 14:33 ` [PATCH v3 2.6.39-rc1-tip 8/26] 8: uprobes: store/restore original instruction Srikar Dronamraju 2011-04-01 14:33 ` Srikar Dronamraju 2011-04-18 16:12 ` Peter Zijlstra 2011-04-18 16:12 ` Peter Zijlstra 2011-04-01 14:34 ` [PATCH v3 2.6.39-rc1-tip 9/26] 9: uprobes: mmap and fork hooks Srikar Dronamraju 2011-04-01 14:34 ` Srikar Dronamraju 2011-04-18 16:21 ` Peter Zijlstra 2011-04-18 16:21 ` Peter Zijlstra 2011-04-18 16:29 ` Peter Zijlstra 2011-04-18 16:29 ` Peter Zijlstra 2011-04-19 6:45 ` Srikar Dronamraju 2011-04-19 6:45 ` Srikar Dronamraju 2011-04-01 14:34 ` [PATCH v3 2.6.39-rc1-tip 10/26] 10: x86: architecture specific task information Srikar Dronamraju 2011-04-01 14:34 ` Srikar Dronamraju 2011-04-01 14:34 ` [PATCH v3 2.6.39-rc1-tip 11/26] 11: uprobes: task specific information Srikar Dronamraju 2011-04-01 14:34 ` Srikar Dronamraju 2011-04-01 14:34 ` [PATCH v3 2.6.39-rc1-tip 12/26] 12: uprobes: slot allocation for uprobes Srikar Dronamraju 2011-04-01 14:34 ` Srikar Dronamraju 2011-04-18 16:46 ` Peter Zijlstra [this message] 2011-04-18 16:46 ` Peter Zijlstra 2011-04-19 6:26 ` Srikar Dronamraju 2011-04-19 6:26 ` Srikar Dronamraju 2011-04-19 9:02 ` Peter Zijlstra 2011-04-19 9:02 ` Peter Zijlstra 2011-04-19 9:11 ` Peter Zijlstra 2011-04-19 9:11 ` Peter Zijlstra 2011-04-20 13:40 ` Eric Paris 2011-04-20 13:40 ` Eric Paris 2011-04-20 14:51 ` Frank Ch. Eigler 2011-04-20 14:51 ` Frank Ch. Eigler 2011-04-20 15:16 ` Stephen Smalley 2011-04-20 15:16 ` Stephen Smalley 2011-04-21 14:11 ` Srikar Dronamraju 2011-04-21 14:11 ` Srikar Dronamraju 2011-04-21 14:45 ` Eric Paris 2011-04-21 14:45 ` Eric Paris 2011-04-21 16:14 ` Roland McGrath 2011-04-21 16:14 ` Roland McGrath 2011-04-21 16:59 ` Srikar Dronamraju 2011-04-21 16:59 ` Srikar Dronamraju 2011-04-01 14:35 ` [PATCH v3 2.6.39-rc1-tip 13/26] 13: uprobes: get the breakpoint address Srikar Dronamraju 2011-04-01 14:35 ` Srikar Dronamraju 2011-04-18 16:47 ` Peter Zijlstra 2011-04-18 16:47 ` Peter Zijlstra 2011-04-01 14:35 ` [PATCH v3 2.6.39-rc1-tip 14/26] 14: x86: x86 specific probe handling Srikar Dronamraju 2011-04-01 14:35 ` Srikar Dronamraju 2011-04-18 16:55 ` Peter Zijlstra 2011-04-18 16:55 ` Peter Zijlstra 2011-04-19 5:43 ` Srikar Dronamraju 2011-04-19 5:43 ` Srikar Dronamraju 2011-04-18 16:57 ` Peter Zijlstra 2011-04-18 16:57 ` Peter Zijlstra 2011-04-01 14:35 ` [PATCH v3 2.6.39-rc1-tip 15/26] 15: uprobes: Handing int3 and singlestep exception Srikar Dronamraju 2011-04-01 14:35 ` Srikar Dronamraju 2011-04-19 13:03 ` Peter Zijlstra 2011-04-19 13:03 ` Peter Zijlstra 2011-04-19 13:12 ` Steven Rostedt 2011-04-19 13:12 ` Steven Rostedt 2011-04-21 17:10 ` Srikar Dronamraju 2011-04-21 17:10 ` Srikar Dronamraju 2011-04-21 17:41 ` Peter Zijlstra 2011-04-21 17:41 ` Peter Zijlstra 2011-04-19 13:39 ` Peter Zijlstra 2011-04-19 13:39 ` Peter Zijlstra 2011-04-21 17:03 ` Srikar Dronamraju 2011-04-21 17:03 ` Srikar Dronamraju 2011-04-01 14:35 ` [PATCH v3 2.6.39-rc1-tip 16/26] 16: x86: uprobes exception notifier for x86 Srikar Dronamraju 2011-04-01 14:35 ` Srikar Dronamraju 2011-04-01 14:35 ` [PATCH v3 2.6.39-rc1-tip 17/26] 17: uprobes: register a notifier for uprobes Srikar Dronamraju 2011-04-01 14:35 ` Srikar Dronamraju 2011-04-19 13:54 ` Peter Zijlstra 2011-04-19 13:54 ` Peter Zijlstra 2011-04-01 14:36 ` [PATCH v3 2.6.39-rc1-tip 18/26] 18: uprobes: commonly used filters Srikar Dronamraju 2011-04-01 14:36 ` Srikar Dronamraju 2011-04-05 1:26 ` Masami Hiramatsu 2011-04-05 1:26 ` Masami Hiramatsu 2011-04-19 13:57 ` Peter Zijlstra 2011-04-19 13:57 ` Peter Zijlstra 2011-04-21 11:09 ` Srikar Dronamraju 2011-04-21 11:09 ` Srikar Dronamraju 2011-04-21 11:37 ` Peter Zijlstra 2011-04-21 11:37 ` Peter Zijlstra 2011-04-21 11:49 ` Srikar Dronamraju 2011-04-21 11:49 ` Srikar Dronamraju 2011-04-01 14:36 ` [PATCH v3 2.6.39-rc1-tip 19/26] 19: tracing: Extract out common code for kprobes/uprobes traceevents Srikar Dronamraju 2011-04-01 14:36 ` Srikar Dronamraju 2011-04-01 14:36 ` [PATCH v3 2.6.39-rc1-tip 20/26] 20: tracing: uprobes trace_event interface Srikar Dronamraju 2011-04-01 14:36 ` Srikar Dronamraju 2011-04-01 14:36 ` [PATCH v3 2.6.39-rc1-tip 21/26] 21: Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Srikar Dronamraju 2011-04-01 14:36 ` Srikar Dronamraju 2011-04-01 14:47 ` [RESEND] [PATCH v3 2.6.39-rc1-tip 21/26] 21: Uprobe tracer documentation " Srikar Dronamraju 2011-04-01 14:47 ` Srikar Dronamraju 2011-04-01 14:36 ` [PATCH v3 2.6.39-rc1-tip 22/26] 22: perf: rename target_module to target Srikar Dronamraju 2011-04-01 14:36 ` Srikar Dronamraju 2011-04-04 10:06 ` Masami Hiramatsu 2011-04-04 10:06 ` Masami Hiramatsu 2011-04-06 23:46 ` Srikar Dronamraju 2011-04-06 23:46 ` Srikar Dronamraju 2011-04-01 14:37 ` [PATCH v3 2.6.39-rc1-tip 23/26] 23: perf: show possible probes in a given executable file or library Srikar Dronamraju 2011-04-01 14:37 ` Srikar Dronamraju 2011-04-04 10:15 ` Masami Hiramatsu 2011-04-04 10:15 ` Masami Hiramatsu 2011-04-06 22:50 ` Srikar Dronamraju 2011-04-06 22:50 ` Srikar Dronamraju 2011-04-01 14:37 ` [PATCH v3 2.6.39-rc1-tip 24/26] 24: perf: perf interface for uprobes Srikar Dronamraju 2011-04-01 14:37 ` Srikar Dronamraju 2011-04-01 14:37 ` [PATCH v3 2.6.39-rc1-tip 25/26] 25: perf: Documentation for perf uprobes Srikar Dronamraju 2011-04-01 14:37 ` Srikar Dronamraju 2011-04-01 14:37 ` [PATCH v3 2.6.39-rc1-tip 26/26] 26: uprobes: filter chain Srikar Dronamraju 2011-04-01 14:37 ` Srikar Dronamraju 2011-04-05 1:27 ` Masami Hiramatsu 2011-04-05 1:27 ` Masami Hiramatsu 2011-04-06 22:41 ` Srikar Dronamraju 2011-04-06 22:41 ` Srikar Dronamraju 2011-04-07 3:19 ` Masami Hiramatsu 2011-04-07 3:19 ` Masami Hiramatsu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1303145171.32491.886.camel@twins \ --to=peterz@infradead.org \ --cc=acme@infradead.org \ --cc=akpm@linux-foundation.org \ --cc=ananth@in.ibm.com \ --cc=andi@firstfloor.org \ --cc=corbet@lwn.net \ --cc=hch@infradead.org \ --cc=jkenisto@linux.vnet.ibm.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=masami.hiramatsu.pt@hitachi.com \ --cc=mingo@elte.hu \ --cc=oleg@redhat.com \ --cc=roland@hack.frob.com \ --cc=rostedt@goodmis.org \ --cc=srikar@linux.vnet.ibm.com \ --cc=systemtap@sources.redhat.com \ --cc=tglx@linutronix.de \ --cc=torvalds@linux-foundation.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.