From 8feb8e896d77439146d2e2ab3d0ab55bb5baf5fc Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 29 May 2012 15:16:05 +0800 Subject: smp: Remove ipi_call_lock[_irq]()/ipi_call_unlock[_irq]() There is no user of those APIs anymore, just remove it. Signed-off-by: Yong Zhang Cc: ralf@linux-mips.org Cc: sshtylyov@mvista.com Cc: david.daney@cavium.com Cc: nikunj@linux.vnet.ibm.com Cc: paulmck@linux.vnet.ibm.com Cc: axboe@kernel.dk Cc: Andrew Morton Link: http://lkml.kernel.org/r/1338275765-3217-11-git-send-email-yong.zhang0@gmail.com Acked-by: Srivatsa S. Bhat Acked-by: Peter Zijlstra Signed-off-by: Thomas Gleixner --- kernel/smp.c | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'kernel') diff --git a/kernel/smp.c b/kernel/smp.c index d0ae5b24875e..29dd40a9f2f4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -581,26 +581,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait) return 0; } EXPORT_SYMBOL(smp_call_function); - -void ipi_call_lock(void) -{ - raw_spin_lock(&call_function.lock); -} - -void ipi_call_unlock(void) -{ - raw_spin_unlock(&call_function.lock); -} - -void ipi_call_lock_irq(void) -{ - raw_spin_lock_irq(&call_function.lock); -} - -void ipi_call_unlock_irq(void) -{ - raw_spin_unlock_irq(&call_function.lock); -} #endif /* USE_GENERIC_SMP_HELPERS */ /* Setup configured maximum number of CPUs to activate */ -- cgit v1.2.3 From c00b275043adc14d668f36266b890f0c53d46640 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:27:44 +0200 Subject: uprobes: Optimize is_swbp_at_addr() for current->mm Change is_swbp_at_addr() to try to avoid the costly read_opcode() if mm == current->mm, __copy_from_user_inatomic() should succeed in the likely case. Currently this optimization is not important, but we are going to add more is_swbp_at_addr(current->mm) callers. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192744.GA8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 985be4d80fe8..d0f5ec0dcdea 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -333,10 +333,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) uprobe_opcode_t opcode; int result; + if (current->mm == mm) { + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + } + result = read_opcode(mm, vaddr, &opcode); if (result) return result; - +out: if (is_swbp_insn(&opcode)) return 1; -- cgit v1.2.3 From a3d7bb47937b3a40b9f0c75655e97b3bb6407cbe Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:27:59 +0200 Subject: uprobes: Change read_opcode() to use FOLL_FORCE set_orig_insn()->read_opcode() should not fail if the probed task did mprotect() after uprobe_register(), change it to use FOLL_FORCE. Without FOLL_WRITE this doesn't have any "side" effect but allows to read the !VM_READ memory. There is another reason for this change, we are going to use is_swbp_at_addr() from handle_swbp() which can race with another thread doing mprotect(). Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192759.GB8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d0f5ec0dcdea..a0dbc87a2ec6 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -312,7 +312,7 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_ void *vaddr_new; int ret; - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (ret <= 0) return ret; -- cgit v1.2.3 From 3a9ea0520f38def4a3915b91f82455b749f07d88 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:28:57 +0200 Subject: uprobes: Introduce find_active_uprobe() helper No functional changes. Move the "find uprobe" code from handle_swbp() to the new helper, find_active_uprobe(). Note: with or without this change, the find-active-uprobe logic is not exactly right. We can race with another thread which unmaps the memory with the valid uprobe before we take mm->mmap_sem. We can't find this uprobe simply because find_vma() fails. In this case we wrongly assume that this trap was not caused by uprobe and send the erroneous SIGTRAP. See the next changes. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192857.GC8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 47 ++++++++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a0dbc87a2ec6..eaf4d55fd424 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1489,38 +1489,47 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } -/* - * Run handler and ask thread to singlestep. - * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. - */ -static void handle_swbp(struct pt_regs *regs) +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr) { + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; struct vm_area_struct *vma; - struct uprobe_task *utask; - struct uprobe *uprobe; - struct mm_struct *mm; - unsigned long bp_vaddr; - uprobe = NULL; - bp_vaddr = uprobe_get_swbp_addr(regs); - mm = current->mm; down_read(&mm->mmap_sem); vma = find_vma(mm, bp_vaddr); - if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) { - struct inode *inode; - loff_t offset; + if (vma && vma->vm_start <= bp_vaddr) { + if (valid_vma(vma, false)) { + struct inode *inode; + loff_t offset; - inode = vma->vm_file->f_mapping->host; - offset = bp_vaddr - vma->vm_start; - offset += (vma->vm_pgoff << PAGE_SHIFT); - uprobe = find_uprobe(inode, offset); + inode = vma->vm_file->f_mapping->host; + offset = bp_vaddr - vma->vm_start; + offset += (vma->vm_pgoff << PAGE_SHIFT); + uprobe = find_uprobe(inode, offset); + } } srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); current->uprobe_srcu_id = -1; up_read(&mm->mmap_sem); + return uprobe; +} + +/* + * Run handler and ask thread to singlestep. + * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. + */ +static void handle_swbp(struct pt_regs *regs) +{ + struct uprobe_task *utask; + struct uprobe *uprobe; + unsigned long bp_vaddr; + + bp_vaddr = uprobe_get_swbp_addr(regs); + uprobe = find_active_uprobe(bp_vaddr); + if (!uprobe) { /* No matching uprobe; signal SIGTRAP. */ send_sig(SIGTRAP, current, 0); -- cgit v1.2.3 From d790d34653ab20c74034902f5f0889bba807949a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:29:14 +0200 Subject: uprobes: Teach find_active_uprobe() to provide the "is_swbp" info A separate patch to simplify the review, and for the documentation. The patch adds another "int *is_swbp" argument to find_active_uprobe(), so far its only caller doesn't use this info. With this patch find_active_uprobe() additionally does: - if find_vma() + ->vm_start check fails, *is_swbp = -EFAULT - otherwise, if valid_vma() + find_uprobe() fails, it holds the result of is_swbp_at_addr(), can be negative too. The latter is only possible if we raced with another thread which did munmap/etc after we hit this bp. IOW. If find_active_uprobe(&is_swbp) returns NULL, the caller can look at is_swbp to figure out whether the current insn is bp or not, or detect the race with another thread if it is negative. Note: I think that performance-wise this change is fine. This adds is_swbp_at_addr(), but only if we raced with uprobe_unregister() or if we hit the "normal" int3 but this mm has uprobes as well. And even in this case the slow read_opcode() path is very unlikely, this insn recently triggered do_int3(), __copy_from_user_inatomic() shouldn't fail in the likely case. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192914.GD8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index eaf4d55fd424..ee3df704e78a 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1489,7 +1489,7 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } -static struct uprobe *find_active_uprobe(unsigned long bp_vaddr) +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; struct uprobe *uprobe = NULL; @@ -1497,7 +1497,6 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr) down_read(&mm->mmap_sem); vma = find_vma(mm, bp_vaddr); - if (vma && vma->vm_start <= bp_vaddr) { if (valid_vma(vma, false)) { struct inode *inode; @@ -1508,6 +1507,11 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr) offset += (vma->vm_pgoff << PAGE_SHIFT); uprobe = find_uprobe(inode, offset); } + + if (!uprobe) + *is_swbp = is_swbp_at_addr(mm, bp_vaddr); + } else { + *is_swbp = -EFAULT; } srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); @@ -1526,9 +1530,10 @@ static void handle_swbp(struct pt_regs *regs) struct uprobe_task *utask; struct uprobe *uprobe; unsigned long bp_vaddr; + int is_swbp; bp_vaddr = uprobe_get_swbp_addr(regs); - uprobe = find_active_uprobe(bp_vaddr); + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { /* No matching uprobe; signal SIGTRAP. */ -- cgit v1.2.3 From 77fc4af1b59d12ab3b1467adf0a5204806853123 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:29:28 +0200 Subject: uprobes: Change register_for_each_vma() to take mm->mmap_sem for writing Change register_for_each_vma() to take mm->mmap_sem for writing. This is a bit unfortunate but hopefully not too bad, this is the slow path anyway. This is needed to ensure that find_active_uprobe() can not race with uprobe_register() which adds the new bp at the same bp_vaddr, after find_uprobe() fails and before is_swbp_at_addr_fast() checks the memory. IOW, this is needed to ensure that if find_active_uprobe() returns NULL but is_swbp == true, we can safely assume that it was the "normal" int3 and we should send SIGTRAP. There is another reason for this change. We are going to replace uprobes_state->count with MMF_ flags set by register/unregister and cleared by find_active_uprobe(), and set/clear shouldn't race with each other. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192928.GE8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ee3df704e78a..a2ed82b4808c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -853,12 +853,12 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) } mm = vi->mm; - down_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); vma = find_vma(mm, (unsigned long)vi->vaddr); if (!vma || !valid_vma(vma, is_register)) { list_del(&vi->probe_list); kfree(vi); - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); mmput(mm); continue; } @@ -867,7 +867,7 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) vaddr != vi->vaddr) { list_del(&vi->probe_list); kfree(vi); - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); mmput(mm); continue; } @@ -877,7 +877,7 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) else remove_breakpoint(uprobe, mm, vi->vaddr); - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); mmput(mm); if (is_register) { if (ret && ret == -EEXIST) -- cgit v1.2.3 From 56bb4cf6475d702d2fb00fc641aa6441097c0330 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:29:47 +0200 Subject: uprobes: Teach handle_swbp() to rely on "is_swbp" rather than uprobes_srcu Currently handle_swbp() assumes that it can't race with unregister, so it roughly does: if (find_uprobe(vaddr)) process_uprobe(); else send_sig(SIGTRAP); This relies on the not-really-working uprobes_srcu code we are going to remove, see the next patch. With this patch we rely on the result of is_swbp_at_addr(bp_vaddr) if find_uprobe() fails. If is_swbp == 1, then we hit the normal int3, we should send SIGTRAP. If is_swbp == 0, we raced with uprobe_unregister(), we simply restart this insn again. The "difficult" case is is_swbp == -EFAULT, when we can't read this memory. In this case I think we should restart too, and this is more correct compared to the current code which sends SIGTRAP. Ignoring ENOMEM/etc from get_user_pages(), this can only happen if another thread unmaps this memory before find_active_uprobe() takes mmap_sem. It would be better to pretend it was unmapped before this insn was executed, restart, and get SIGSEGV. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529192947.GF8057@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a2ed82b4808c..1f02e3bbfc1d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1530,14 +1530,26 @@ static void handle_swbp(struct pt_regs *regs) struct uprobe_task *utask; struct uprobe *uprobe; unsigned long bp_vaddr; - int is_swbp; + int uninitialized_var(is_swbp); bp_vaddr = uprobe_get_swbp_addr(regs); uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { - /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + if (is_swbp > 0) { + /* No matching uprobe; signal SIGTRAP. */ + send_sig(SIGTRAP, current, 0); + } else { + /* + * Either we raced with uprobe_unregister() or we can't + * access this memory. The latter is only possible if + * another thread plays with our ->mm. In both cases + * we can simply restart. If this vma was unmapped we + * can pretend this insn was not executed yet and get + * the (correct) SIGSEGV after restart. + */ + instruction_pointer_set(regs, bp_vaddr); + } return; } -- cgit v1.2.3 From 778b032d96909690c19d84f8d17c13be65ed6f8e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:30:08 +0200 Subject: uprobes: Kill uprobes_srcu/uprobe_srcu_id Kill the no longer needed uprobes_srcu/uprobe_srcu_id code. It doesn't really work anyway. synchronize_srcu() can only synchronize with the code "inside" the srcu_read_lock/srcu_read_unlock section, while uprobe_pre_sstep_notifier() does srcu_read_lock() _after_ we already hit the breakpoint. I guess this probably works "in practice". synchronize_srcu() is slow and it implies synchronize_sched(), and the probed task enters the non- preemptible section at the start of exception handler. Still this is not right at least in theory, and task->uprobe_srcu_id blows task_struct. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529193008.GG8057@redhat.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/events/uprobes.c | 22 +++------------------- 2 files changed, 3 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6029d8c54476..6bd19655c1a7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1569,7 +1569,6 @@ struct task_struct { #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; - int uprobe_srcu_id; #endif }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 1f02e3bbfc1d..8c5e043cd309 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -38,7 +38,6 @@ #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE -static struct srcu_struct uprobes_srcu; static struct rb_root uprobes_tree = RB_ROOT; static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ @@ -738,20 +737,14 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr) } /* - * There could be threads that have hit the breakpoint and are entering the - * notifier code and trying to acquire the uprobes_treelock. The thread - * calling delete_uprobe() that is removing the uprobe from the rb_tree can - * race with these threads and might acquire the uprobes_treelock compared - * to some of the breakpoint hit threads. In such a case, the breakpoint - * hit threads will not find the uprobe. The current unregistering thread - * waits till all other threads have hit a breakpoint, to acquire the - * uprobes_treelock before the uprobe is removed from the rbtree. + * There could be threads that have already hit the breakpoint. They + * will recheck the current insn and restart if find_uprobe() fails. + * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { unsigned long flags; - synchronize_srcu(&uprobes_srcu); spin_lock_irqsave(&uprobes_treelock, flags); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock_irqrestore(&uprobes_treelock, flags); @@ -1388,9 +1381,6 @@ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; - if (t->uprobe_srcu_id != -1) - srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id); - if (!utask) return; @@ -1408,7 +1398,6 @@ void uprobe_free_utask(struct task_struct *t) void uprobe_copy_process(struct task_struct *t) { t->utask = NULL; - t->uprobe_srcu_id = -1; } /* @@ -1513,9 +1502,6 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) } else { *is_swbp = -EFAULT; } - - srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); - current->uprobe_srcu_id = -1; up_read(&mm->mmap_sem); return uprobe; @@ -1656,7 +1642,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) utask->state = UTASK_BP_HIT; set_thread_flag(TIF_UPROBE); - current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu); return 1; } @@ -1691,7 +1676,6 @@ static int __init init_uprobes(void) mutex_init(&uprobes_mutex[i]); mutex_init(&uprobes_mmap_mutex[i]); } - init_srcu_struct(&uprobes_srcu); return register_die_notifier(&uprobe_exception_nb); } -- cgit v1.2.3 From 7eb9ba5ed312ec6ed9d22259c5da1acb7cf4bd29 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Fri, 8 Jun 2012 15:02:57 +0530 Subject: uprobes: Pass probed vaddr to arch_uprobe_analyze_insn() On RISC architectures like powerpc, instructions are fixed size. Instruction analysis on such platforms is just a matter of (insn % 4). Pass the vaddr at which the uprobe is to be inserted so that arch_uprobe_analyze_insn() can flag misaligned registration requests. Signed-off-by: Ananth N Mavinakaynahalli Cc: michael@ellerman.id.au Cc: antonb@thinktux.localdomain Cc: Paul Mackerras Cc: benh@kernel.crashing.org Cc: peterz@infradead.org Cc: Srikar Dronamraju Cc: Jim Keniston Cc: oleg@redhat.com Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20120608093257.GG13409@in.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/uprobes.h | 2 +- arch/x86/kernel/uprobes.c | 3 ++- kernel/events/uprobes.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 1e9bed14f7ae..f3971bbcd1de 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -48,7 +48,7 @@ struct arch_uprobe_task { #endif }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm); +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index dc4e910a7d96..36fd42091fa7 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -409,9 +409,10 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. * @mm: the probed address space. * @arch_uprobe: the probepoint information. + * @addr: virtual address at which to install the probepoint * Return 0 on success or a -ve number on error. */ -int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm) +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) { int ret; struct insn insn; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 8c5e043cd309..b52376d02332 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -706,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) return -EEXIST; - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm); + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, addr); if (ret) return ret; -- cgit v1.2.3 From b871a42b6091b720e82ddff237659534c525c25b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 11 Jun 2012 15:07:08 +0200 Subject: smpboot: Remove leftover declaration Signed-off-by: Thomas Gleixner --- kernel/smpboot.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 80c0acfb8472..6ef9433e1c70 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -3,8 +3,6 @@ struct task_struct; -int smpboot_prepare(unsigned int cpu); - #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD struct task_struct *idle_thread_get(unsigned int cpu); void idle_thread_set_boot_cpu(void); -- cgit v1.2.3 From 8d240dd88cca33b704adf3fe281aa64b5aac2dd8 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 29 Mar 2012 19:11:40 +0200 Subject: ftrace: Remove a superfluous check register_ftrace_function() checks ftrace_disabled and calls __register_ftrace_function which does it again. Drop the first check and add the unlikely hint to the second one. Also, drop the label as John correctly notices. No functional change. Link: http://lkml.kernel.org/r/20120329171140.GE6409@aftab Cc: Borislav Petkov Cc: John Kacur Signed-off-by: Borislav Petkov Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a008663d86c8..b4f20fba09fc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -312,7 +312,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { - if (ftrace_disabled) + if (unlikely(ftrace_disabled)) return -ENODEV; if (FTRACE_WARN_ON(ops == &global_ops)) @@ -4299,16 +4299,12 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); - if (unlikely(ftrace_disabled)) - goto out_unlock; - ret = __register_ftrace_function(ops); if (!ret) ret = ftrace_startup(ops, 0); - - out_unlock: mutex_unlock(&ftrace_lock); + return ret; } EXPORT_SYMBOL_GPL(register_ftrace_function); -- cgit v1.2.3 From 7374e82771c6d5a9af2080be46f64a5826c7efb1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 31 May 2012 21:40:05 -0400 Subject: tracing: Register the ftrace internal events during early boot All trace events including ftrace internel events (like trace_printk and function tracing), register functions that describe how to print their output. The events may be recorded as soon as the ring buffer is allocated, but they are just raw binary in the buffer. The mapping of event ids to how to print them are held within a structure that is registered on system boot. If a crash happens in boot up before these functions are registered then their output (via ftrace_dump_on_oops) will be useless: Dumping ftrace buffer: --------------------------------- <...>-1 0.... 319705us : Unknown type 6 --------------------------------- This can be quite frustrating for a kernel developer trying to see what is going wrong. There's no reason to register them so late in the boot up process. They can be registered by early_initcall(). Reported-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- kernel/trace/trace_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index df611a0e76c5..123b189c732c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1325,4 +1325,4 @@ __init static int init_events(void) return 0; } -device_initcall(init_events); +early_initcall(init_events); -- cgit v1.2.3 From ea131377148cdfe90641b42ae9aa5a6b3a4fa327 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:22 +0200 Subject: uprobes: Valid_vma() should reject VM_HUGETLB __replace_page() obviously can't work with the hugetlbfs mappings, uprobe_register() will likely crash the kernel. Change valid_vma() to check VM_HUGETLB as well. As for PageTransHuge() no need to worry, vma->vm_file != NULL. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154322.GA9561@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index b52376d02332..f0d04530af63 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -99,7 +99,8 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register) if (!is_register) return true; - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) + if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) + == (VM_READ|VM_EXEC)) return true; return false; -- cgit v1.2.3 From cc359d180fa9c25a4c1819f17e07a422d788353d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:25 +0200 Subject: uprobes: __copy_insn() should ensure a_ops->readpage != NULL __copy_insn() blindly calls read_mapping_page(), this will crash the kernel if ->readpage == NULL, add the necessary check. For example, hugetlbfs_aops->readpage is NULL. Perhaps we should change read_mapping_page() instead. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154325.GA9568@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index f0d04530af63..604930bf9c92 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -610,6 +610,9 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins if (!filp) return -EINVAL; + if (!mapping->a_ops->readpage) + return -EIO; + idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); off1 = offset &= ~PAGE_MASK; -- cgit v1.2.3 From 5323ce71e4b4e1f188ebbc0cc7776885ea6c75fb Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:28 +0200 Subject: uprobes: Write_opcode()->__replace_page() can race with try_to_unmap() write_opcode() gets old_page via get_user_pages() and then calls __replace_page() which assumes that this old_page is still mapped after pte_offset_map_lock(). This is not true if this old_page was already try_to_unmap()'ed, and in this case everything __replace_page() does with old_page is wrong. Just for example, put_page() is not balanced. I think it is possible to teach __replace_page() to handle this unlikely case correctly, but this patch simply changes it to use page_check_address() and return -EAGAIN if it fails. The caller should notice this error code and retry. Note: write_opcode() asks for the cleanups, I'll try to do this in a separate patch. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154328.GA9571@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 41 +++++++++++++---------------------------- 1 file changed, 13 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 604930bf9c92..3ccdb29ee8d6 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -129,33 +129,17 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - spinlock_t *ptl; unsigned long addr; - int err = -EFAULT; + spinlock_t *ptl; + pte_t *ptep; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) - goto out; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - goto out; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - goto out; + return -EFAULT; - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - goto out; - - ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) - goto out; + return -EAGAIN; get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr); @@ -174,10 +158,8 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct try_to_free_swap(page); put_page(page); pte_unmap_unlock(ptep, ptl); - err = 0; -out: - return err; + return 0; } /** @@ -222,9 +204,10 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; struct uprobe *uprobe; + unsigned long pgoff; loff_t addr; int ret; - +retry: /* Read the page with vaddr into memory */ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); if (ret <= 0) @@ -269,9 +252,9 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, memcpy(vaddr_new, vaddr_old, PAGE_SIZE); /* poke the new insn in, ASSUMES we don't cross page boundary */ - vaddr &= ~PAGE_MASK; - BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + pgoff = (vaddr & ~PAGE_MASK); + BUG_ON(pgoff + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + memcpy(vaddr_new + pgoff, &opcode, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); kunmap_atomic(vaddr_old); @@ -291,6 +274,8 @@ unlock_out: put_out: put_page(old_page); + if (unlikely(ret == -EAGAIN)) + goto retry; return ret; } -- cgit v1.2.3 From c1914a0936f79ed0236f670122e06e36e4d332ee Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:31 +0200 Subject: uprobes: Install_breakpoint() should fail if is_swbp_insn() == T install_breakpoint() returns -EEXIST if is_swbp_insn(orig_insn) == T, the caller treats this code as success. This is doubly wrong. The successful return should set UPROBE_COPY_INSN, but the real problem is that it shouldn't succeed. If the probed insn is int3 the application should get SIGTRAP, this won't happen with uprobe. Probably we can fix this, we can add the UPROBE_SHARED_BP flag and teach handle_swbp/set_orig_insn to handle this case correctly. But this needs some complications and we have other insns which can't be probed, lets make a simple fix for now. I think this needs a cleanup. UPROBE_COPY_INSN should die, copy_insn() should be called by alloc_uprobe(). arch_uprobe_analyze_insn() depends on ->mm (ia32_compat) but it is called only once. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154331.GA9578@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3ccdb29ee8d6..ec78152e32e9 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -693,7 +693,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, return ret; if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) - return -EEXIST; + return -ENOTSUPP; ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, addr); if (ret) -- cgit v1.2.3 From 268720903f87e0b84b161626c4447b81671b5d18 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:33 +0200 Subject: uprobes: Rework register_for_each_vma() to make it O(n) Currently register_for_each_vma() is O(n ** 2) + O(n ** 3), every time find_next_vma_info() "restarts" the vma_prio_tree_foreach() loop and each iteration rechecks the whole try_list. This also means that try_list can grow "indefinitely" if register/unregister races with munmap/mmap activity even if the number of mapping is bounded at any time. With this patch register_for_each_vma() builds the list of mm/vaddr structures only once and does install_breakpoint() for each entry. We do not care about the new mappings which can be created after build_map_info() drops mapping->i_mmap_mutex, uprobe_mmap() should do its work. Note that we do not allocate map_info under i_mmap_mutex, this can deadlock with page reclaim (but see the next patch). So we use 2 lists, "curr" which we are going to return, and "prev" which holds the already allocated memory. The main loop deques the entry from "prev" (initially it is empty), and if "prev" becomes empty again it counts the number of entries we need to pre-allocate outside of i_mmap_mutex. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Link: http://lkml.kernel.org/r/20120615154333.GA9581@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 199 +++++++++++++++++++++--------------------------- 1 file changed, 86 insertions(+), 113 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ec78152e32e9..4e0db3496d70 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -60,17 +60,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; */ static atomic_t uprobe_events = ATOMIC_INIT(0); -/* - * Maintain a temporary per vma info that can be used to search if a vma - * has already been handled. This structure is introduced since extending - * vm_area_struct wasnt recommended. - */ -struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; -}; - struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; @@ -742,139 +731,123 @@ static void delete_uprobe(struct uprobe *uprobe) atomic_dec(&uprobe_events); } -static struct vma_info * -__find_next_vma_info(struct address_space *mapping, struct list_head *head, - struct vma_info *vi, loff_t offset, bool is_register) +struct map_info { + struct map_info *next; + struct mm_struct *mm; + loff_t vaddr; +}; + +static inline struct map_info *free_map_info(struct map_info *info) { + struct map_info *next = info->next; + kfree(info); + return next; +} + +static struct map_info * +build_map_info(struct address_space *mapping, loff_t offset, bool is_register) +{ + unsigned long pgoff = offset >> PAGE_SHIFT; struct prio_tree_iter iter; struct vm_area_struct *vma; - struct vma_info *tmpvi; - unsigned long pgoff; - int existing_vma; - loff_t vaddr; - - pgoff = offset >> PAGE_SHIFT; + struct map_info *curr = NULL; + struct map_info *prev = NULL; + struct map_info *info; + int more = 0; + again: + mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; - existing_vma = 0; - vaddr = vma_address(vma, offset); - - list_for_each_entry(tmpvi, head, probe_list) { - if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { - existing_vma = 1; - break; - } - } - - /* - * Another vma needs a probe to be installed. However skip - * installing the probe if the vma is about to be unlinked. - */ - if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { - vi->mm = vma->vm_mm; - vi->vaddr = vaddr; - list_add(&vi->probe_list, head); - - return vi; + if (!prev) { + more++; + continue; } - } - - return NULL; -} -/* - * Iterate in the rmap prio tree and find a vma where a probe has not - * yet been inserted. - */ -static struct vma_info * -find_next_vma_info(struct address_space *mapping, struct list_head *head, - loff_t offset, bool is_register) -{ - struct vma_info *vi, *retvi; + if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + continue; - vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); - if (!vi) - return ERR_PTR(-ENOMEM); + info = prev; + prev = prev->next; + info->next = curr; + curr = info; - mutex_lock(&mapping->i_mmap_mutex); - retvi = __find_next_vma_info(mapping, head, vi, offset, is_register); + info->mm = vma->vm_mm; + info->vaddr = vma_address(vma, offset); + } mutex_unlock(&mapping->i_mmap_mutex); - if (!retvi) - kfree(vi); + if (!more) + goto out; + + prev = curr; + while (curr) { + mmput(curr->mm); + curr = curr->next; + } - return retvi; + do { + info = kmalloc(sizeof(struct map_info), GFP_KERNEL); + if (!info) { + curr = ERR_PTR(-ENOMEM); + goto out; + } + info->next = prev; + prev = info; + } while (--more); + + goto again; + out: + while (prev) + prev = free_map_info(prev); + return curr; } static int register_for_each_vma(struct uprobe *uprobe, bool is_register) { - struct list_head try_list; - struct vm_area_struct *vma; - struct address_space *mapping; - struct vma_info *vi, *tmpvi; - struct mm_struct *mm; - loff_t vaddr; - int ret; + struct map_info *info; + int err = 0; - mapping = uprobe->inode->i_mapping; - INIT_LIST_HEAD(&try_list); - - ret = 0; + info = build_map_info(uprobe->inode->i_mapping, + uprobe->offset, is_register); + if (IS_ERR(info)) + return PTR_ERR(info); - for (;;) { - vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register); - if (!vi) - break; + while (info) { + struct mm_struct *mm = info->mm; + struct vm_area_struct *vma; + loff_t vaddr; - if (IS_ERR(vi)) { - ret = PTR_ERR(vi); - break; - } + if (err) + goto free; - mm = vi->mm; down_write(&mm->mmap_sem); - vma = find_vma(mm, (unsigned long)vi->vaddr); - if (!vma || !valid_vma(vma, is_register)) { - list_del(&vi->probe_list); - kfree(vi); - up_write(&mm->mmap_sem); - mmput(mm); - continue; - } + vma = find_vma(mm, (unsigned long)info->vaddr); + if (!vma || !valid_vma(vma, is_register)) + goto unlock; + vaddr = vma_address(vma, uprobe->offset); if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != vi->vaddr) { - list_del(&vi->probe_list); - kfree(vi); - up_write(&mm->mmap_sem); - mmput(mm); - continue; - } + vaddr != info->vaddr) + goto unlock; - if (is_register) - ret = install_breakpoint(uprobe, mm, vma, vi->vaddr); - else - remove_breakpoint(uprobe, mm, vi->vaddr); - - up_write(&mm->mmap_sem); - mmput(mm); if (is_register) { - if (ret && ret == -EEXIST) - ret = 0; - if (ret) - break; + err = install_breakpoint(uprobe, mm, vma, info->vaddr); + if (err == -EEXIST) + err = 0; + } else { + remove_breakpoint(uprobe, mm, info->vaddr); } + unlock: + up_write(&mm->mmap_sem); + free: + mmput(mm); + info = free_map_info(info); } - list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { - list_del(&vi->probe_list); - kfree(vi); - } - - return ret; + return err; } static int __uprobe_register(struct uprobe *uprobe) -- cgit v1.2.3 From 7a5bfb66b07f22d2429db776da7bb8b57bfb5cff Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:36 +0200 Subject: uprobes: Change build_map_info() to try kmalloc(GFP_NOWAIT) first build_map_info() doesn't allocate the memory under i_mmap_mutex to avoid the deadlock with page reclaim. But it can try GFP_NOWAIT first, it should work in the likely case and thus we almost never need the pre-alloc-and-retry path. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Link: http://lkml.kernel.org/r/20120615154336.GA9588@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e0db3496d70..897417dbca8e 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -761,6 +761,16 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register) if (!valid_vma(vma, is_register)) continue; + if (!prev && !more) { + /* + * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through + * reclaim. This is optimistic, no harm done if it fails. + */ + prev = kmalloc(sizeof(struct map_info), + GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (prev) + prev->next = NULL; + } if (!prev) { more++; continue; -- cgit v1.2.3 From c5784de2b351fe871bb57487878f7fc7ec5b075c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 Jun 2012 17:43:39 +0200 Subject: uprobes: Document uprobe_register() vs uprobe_mmap() race Because the mind is treacherous and makes us forget we need to write stuff down. Signed-off-by: Peter Zijlstra Signed-off-by: Oleg Nesterov Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Cc: Srikar Dronamraju Link: http://lkml.kernel.org/r/20120615154339.GA9591@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 897417dbca8e..2671d9ad49be 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -44,6 +44,23 @@ static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 +/* + * We need separate register/unregister and mmap/munmap lock hashes because + * of mmap_sem nesting. + * + * uprobe_register() needs to install probes on (potentially) all processes + * and thus needs to acquire multiple mmap_sems (consequtively, not + * concurrently), whereas uprobe_mmap() is called while holding mmap_sem + * for the particular process doing the mmap. + * + * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem + * because of lock order against i_mmap_mutex. This means there's a hole in + * the register vma iteration where a mmap() can happen. + * + * Thus uprobe_register() can race with uprobe_mmap() and we can try and + * install a probe where one is already installed. + */ + /* serialize (un)register */ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; @@ -339,7 +356,9 @@ out: int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { int result; - + /* + * See the comment near uprobes_hash(). + */ result = is_swbp_at_addr(mm, vaddr); if (result == 1) return -EEXIST; @@ -845,6 +864,10 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) if (is_register) { err = install_breakpoint(uprobe, mm, vma, info->vaddr); + /* + * We can race against uprobe_mmap(), see the + * comment near uprobe_hash(). + */ if (err == -EEXIST) err = 0; } else { @@ -1054,8 +1077,10 @@ int uprobe_mmap(struct vm_area_struct *vma) } ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - - /* Ignore double add: */ + /* + * We can race against uprobe_register(), see the + * comment near uprobe_hash(). + */ if (ret == -EEXIST) { ret = 0; -- cgit v1.2.3 From d436615e60c386095dac4a9bf72b08868d2a7564 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:42 +0200 Subject: uprobes: Copy_insn() shouldn't depend on mm/vma/vaddr 1. copy_insn() doesn't need "addr", it can use uprobe->offset. Remove this argument. 2. Change copy_insn/__copy_insn to accept "struct file*" instead of vma. copy_insn() is called only once and mm/vma/vaddr are random, it shouldn't depend on them. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154342.GA9598@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2671d9ad49be..08ef566da763 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -591,10 +591,9 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) } static int -__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn, +__copy_insn(struct address_space *mapping, struct file *filp, char *insn, unsigned long nbytes, unsigned long offset) { - struct file *filp = vma->vm_file; struct page *page; void *vaddr; unsigned long off1; @@ -625,15 +624,13 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins return 0; } -static int -copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) +static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping; unsigned long nbytes; int bytes; - addr &= ~PAGE_MASK; - nbytes = PAGE_SIZE - addr; + nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK); mapping = uprobe->inode->i_mapping; /* Instruction at end of binary; copy only available bytes */ @@ -644,13 +641,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) /* Instruction at the page-boundary; copy bytes in second page */ if (nbytes < bytes) { - if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes, + if (__copy_insn(mapping, filp, uprobe->arch.insn + nbytes, bytes - nbytes, uprobe->offset + nbytes)) return -ENOMEM; bytes = nbytes; } - return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset); + return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); } /* @@ -696,7 +693,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, addr = (unsigned long)vaddr; if (!(uprobe->flags & UPROBE_COPY_INSN)) { - ret = copy_insn(uprobe, vma, addr); + ret = copy_insn(uprobe, vma->vm_file); if (ret) return ret; -- cgit v1.2.3 From fc36f59565861af2e897225bc3782479a26c5d5a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:44 +0200 Subject: uprobes: Copy_insn() should not return -ENOMEM if __copy_insn() fails copy_insn() returns -ENOMEM if the first __copy_insn() fails, it should return the correct error code. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154344.GA9601@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 08ef566da763..2db1d94d7dfc 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -641,10 +641,10 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp) /* Instruction at the page-boundary; copy bytes in second page */ if (nbytes < bytes) { - if (__copy_insn(mapping, filp, uprobe->arch.insn + nbytes, - bytes - nbytes, uprobe->offset + nbytes)) - return -ENOMEM; - + int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes, + bytes - nbytes, uprobe->offset + nbytes); + if (err) + return err; bytes = nbytes; } return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); -- cgit v1.2.3 From eb2bf57bee42c7565032f93adaa211e2c9fcc52c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:47 +0200 Subject: uprobes: No need to re-check vma_address() in write_opcode() write_opcode() is called by register_for_each_vma() and uprobe_mmap() paths. In both cases the caller has already verified this vaddr under mmap_sem, no need to re-check. Note also that this check is wrong anyway, we should not truncate loff_t returned by vma_address() if we do not trust this mapping. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154347.GA9604@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2db1d94d7dfc..14c71a2aadad 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -211,7 +211,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, struct vm_area_struct *vma; struct uprobe *uprobe; unsigned long pgoff; - loff_t addr; int ret; retry: /* Read the page with vaddr into memory */ @@ -235,10 +234,6 @@ retry: if (mapping != vma->vm_file->f_mapping) goto put_out; - addr = vma_address(vma, uprobe->offset); - if (vaddr != (unsigned long)addr) - goto put_out; - ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) -- cgit v1.2.3 From d9c4a30e82614d43b55893a73f31e7284007ce82 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:50 +0200 Subject: uprobes: Move BUG_ON(UPROBE_SWBP_INSN_SIZE) from write_opcode() to install_breakpoint() write_opcode() ensures that UPROBE_SWBP_INSN doesn't cross the page boundary. This looks a bit confusing, the check does not depend on vaddr and it is enough to do it only once right after install_breakpoint()->arch_uprobe_analyze_insn(). Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154350.GA9611@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 14c71a2aadad..b9c61bda9029 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -210,7 +210,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; struct uprobe *uprobe; - unsigned long pgoff; int ret; retry: /* Read the page with vaddr into memory */ @@ -251,11 +250,7 @@ retry: vaddr_new = kmap_atomic(new_page); memcpy(vaddr_new, vaddr_old, PAGE_SIZE); - - /* poke the new insn in, ASSUMES we don't cross page boundary */ - pgoff = (vaddr & ~PAGE_MASK); - BUG_ON(pgoff + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - memcpy(vaddr_new + pgoff, &opcode, UPROBE_SWBP_INSN_SIZE); + memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); kunmap_atomic(vaddr_old); @@ -699,6 +694,10 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (ret) return ret; + /* write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + uprobe->flags |= UPROBE_COPY_INSN; } -- cgit v1.2.3 From 449d0d7c9fb87277175db34c009c70cb348004a8 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:53 +0200 Subject: uprobes: Simplify the usage of uprobe->pending_list uprobe->pending_list is only used to create the temporary list, it has no meaning after we drop uprobes_mmap_hash(inode). No need to initialize this node or remove it from tmp_list, and we can use list_for_each_entry(). Signed-off-by: Oleg Nesterov Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Cc: Srikar Dronamraju Link: http://lkml.kernel.org/r/20120615154353.GA9614@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index b9c61bda9029..7d5c78f063ae 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -513,7 +513,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; init_rwsem(&uprobe->consumer_rwsem); - INIT_LIST_HEAD(&uprobe->pending_list); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -1037,7 +1036,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head) int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; int ret, count; @@ -1055,10 +1054,9 @@ int uprobe_mmap(struct vm_area_struct *vma) ret = 0; count = 0; - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { + list_for_each_entry(uprobe, &tmp_list, pending_list) { loff_t vaddr; - list_del(&uprobe->pending_list); if (!ret) { vaddr = vma_address(vma, uprobe->offset); @@ -1106,7 +1104,7 @@ int uprobe_mmap(struct vm_area_struct *vma) void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) @@ -1123,12 +1121,10 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, &tmp_list); - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { + list_for_each_entry(uprobe, &tmp_list, pending_list) { loff_t vaddr; - list_del(&uprobe->pending_list); vaddr = vma_address(vma, uprobe->offset); - if (vaddr >= start && vaddr < end) { /* * An unregister could have removed the probe before -- cgit v1.2.3 From 816c03fbabe64fa09f66fbb64e932081af381415 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:55 +0200 Subject: uprobes: Don't use loff_t for the valid virtual address loff_t looks confusing when it is used for the virtual address. Change map_info and install_breakpoint/remove_breakpoint paths to use "unsigned long". The patch doesn't change vma_address(), it can't return "long" because it is used to verify the mapping. But probably this needs some cleanups too. Signed-off-by: Oleg Nesterov Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154355.GA9622@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 7d5c78f063ae..4df84b76dd48 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -664,9 +664,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp) */ static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, - struct vm_area_struct *vma, loff_t vaddr) + struct vm_area_struct *vma, unsigned long vaddr) { - unsigned long addr; int ret; /* @@ -679,8 +678,6 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (!uprobe->consumers) return -EEXIST; - addr = (unsigned long)vaddr; - if (!(uprobe->flags & UPROBE_COPY_INSN)) { ret = copy_insn(uprobe, vma->vm_file); if (ret) @@ -689,7 +686,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) return -ENOTSUPP; - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, addr); + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) return ret; @@ -709,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence increment before and decrement on failure. */ atomic_inc(&mm->uprobes_state.count); - ret = set_swbp(&uprobe->arch, mm, addr); + ret = set_swbp(&uprobe->arch, mm, vaddr); if (ret) atomic_dec(&mm->uprobes_state.count); @@ -717,9 +714,9 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, } static void -remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr) +remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true)) + if (!set_orig_insn(&uprobe->arch, mm, vaddr, true)) atomic_dec(&mm->uprobes_state.count); } @@ -743,7 +740,7 @@ static void delete_uprobe(struct uprobe *uprobe) struct map_info { struct map_info *next; struct mm_struct *mm; - loff_t vaddr; + unsigned long vaddr; }; static inline struct map_info *free_map_info(struct map_info *info) @@ -837,7 +834,6 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) while (info) { struct mm_struct *mm = info->mm; struct vm_area_struct *vma; - loff_t vaddr; if (err) goto free; @@ -847,9 +843,8 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) if (!vma || !valid_vma(vma, is_register)) goto unlock; - vaddr = vma_address(vma, uprobe->offset); if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != info->vaddr) + vma_address(vma, uprobe->offset) != info->vaddr) goto unlock; if (is_register) { @@ -1055,10 +1050,8 @@ int uprobe_mmap(struct vm_area_struct *vma) count = 0; list_for_each_entry(uprobe, &tmp_list, pending_list) { - loff_t vaddr; - if (!ret) { - vaddr = vma_address(vma, uprobe->offset); + loff_t vaddr = vma_address(vma, uprobe->offset); if (vaddr < vma->vm_start || vaddr >= vma->vm_end) { put_uprobe(uprobe); @@ -1122,9 +1115,8 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon build_probe_list(inode, &tmp_list); list_for_each_entry(uprobe, &tmp_list, pending_list) { - loff_t vaddr; + loff_t vaddr = vma_address(vma, uprobe->offset); - vaddr = vma_address(vma, uprobe->offset); if (vaddr >= start && vaddr < end) { /* * An unregister could have removed the probe before -- cgit v1.2.3 From 593609a59600c8377f311b300f14deacb155b9a4 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:43:59 +0200 Subject: uprobes: __copy_insn() needs "loff_t offset" 1. __copy_insn() needs "loff_t offset", not "unsigned long", to read the file. 2. use pgoff_t for "idx" and remove the unnecessary typecast. 3. fix the typo, "&=" is not what we want 4. can't resist, rename off1 to off. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Acked-by: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120615154359.GA9625@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4df84b76dd48..d1b2eeb80837 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -581,12 +581,12 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) static int __copy_insn(struct address_space *mapping, struct file *filp, char *insn, - unsigned long nbytes, unsigned long offset) + unsigned long nbytes, loff_t offset) { struct page *page; void *vaddr; - unsigned long off1; - unsigned long idx; + unsigned long off; + pgoff_t idx; if (!filp) return -EINVAL; @@ -594,8 +594,8 @@ __copy_insn(struct address_space *mapping, struct file *filp, char *insn, if (!mapping->a_ops->readpage) return -EIO; - idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); - off1 = offset &= ~PAGE_MASK; + idx = offset >> PAGE_CACHE_SHIFT; + off = offset & ~PAGE_MASK; /* * Ensure that the page that has the original instruction is @@ -606,7 +606,7 @@ __copy_insn(struct address_space *mapping, struct file *filp, char *insn, return PTR_ERR(page); vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off1, nbytes); + memcpy(insn, vaddr + off, nbytes); kunmap_atomic(vaddr); page_cache_release(page); -- cgit v1.2.3 From e227051b13956b8f71c0abecc41ad351e64671c8 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 15 Jun 2012 17:44:01 +0200 Subject: uprobes: Remove the unnecessary initialization in add_utask() Trivial cleanup. No need to nullify ->active_uprobe after kzalloc(). Signed-off-by: Oleg Nesterov Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Peter Zijlstra Cc: Srikar Dronamraju Link: http://lkml.kernel.org/r/20120615154401.GA9633@redhat.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d1b2eeb80837..f93532748bca 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1392,7 +1392,6 @@ static struct uprobe_task *add_utask(void) if (unlikely(!utask)) return NULL; - utask->active_uprobe = NULL; current->utask = utask; return utask; } -- cgit v1.2.3 From fbfc623f8231c8d8c78aab5841e9c6e5811ab638 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 15 Jun 2012 14:31:31 +0800 Subject: perf: Avoid race between cpu hotplug and installing event perf_event_open() requires the cpu on which to install event is online, but the cpu can go offline after perf_event_open checks that. Add a get_online_cpus()/put_online_cpus() pair to avoid the race. Signed-off-by: Zheng Yan Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1339741902-8449-3-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index d7d71d6ec972..31d182e01549 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6252,6 +6252,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + get_online_cpus(); + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL, NULL); if (IS_ERR(event)) { @@ -6391,6 +6393,8 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); + put_online_cpus(); + event->owner = current; mutex_lock(¤t->perf_event_mutex); @@ -6419,6 +6423,7 @@ err_context: err_alloc: free_event(event); err_task: + put_online_cpus(); if (task) put_task_struct(task); err_group_fd: -- cgit v1.2.3 From e2d37cd213dcc0aeb3db4b37b9bd1710fe36fbf7 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 15 Jun 2012 14:31:32 +0800 Subject: perf: Allow the PMU driver to choose the CPU on which to install events Allow the pmu->event_init callback to change event->cpu, so the PMU driver can choose the CPU on which to install events. Signed-off-by: Zheng Yan Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1339741902-8449-4-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 31d182e01549..fa36a39e8bb7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6306,7 +6306,7 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, cpu); + ctx = find_get_context(pmu, task, event->cpu); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; @@ -6379,16 +6379,16 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&ctx->mutex); if (move_group) { - perf_install_in_context(ctx, group_leader, cpu); + perf_install_in_context(ctx, group_leader, event->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, cpu); + perf_install_in_context(ctx, sibling, event->cpu); get_ctx(ctx); } } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); ++ctx->generation; perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); -- cgit v1.2.3 From 0cda4c023132aa93f2dd94811061f812e88daf4c Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 15 Jun 2012 14:31:33 +0800 Subject: perf: Introduce perf_pmu_migrate_context() Originally from Peter Zijlstra. The helper migrates perf events from one cpu to another cpu. Signed-off-by: Zheng Yan Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1339741902-8449-5-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 ++ kernel/events/core.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'kernel') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1ce887abcc5c..76c5c8b724a7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1107,6 +1107,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, struct task_struct *task, perf_overflow_handler_t callback, void *context); +extern void perf_pmu_migrate_context(struct pmu *pmu, + int src_cpu, int dst_cpu); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); diff --git a/kernel/events/core.c b/kernel/events/core.c index fa36a39e8bb7..f1cf0edeb39a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1645,6 +1645,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); event->ctx = ctx; + if (event->cpu != -1) + event->cpu = cpu; if (!task) { /* @@ -6379,6 +6381,7 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&ctx->mutex); if (move_group) { + synchronize_rcu(); perf_install_in_context(ctx, group_leader, event->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, @@ -6484,6 +6487,39 @@ err: } EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) +{ + struct perf_event_context *src_ctx; + struct perf_event_context *dst_ctx; + struct perf_event *event, *tmp; + LIST_HEAD(events); + + src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; + dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; + + mutex_lock(&src_ctx->mutex); + list_for_each_entry_safe(event, tmp, &src_ctx->event_list, + event_entry) { + perf_remove_from_context(event); + put_ctx(src_ctx); + list_add(&event->event_entry, &events); + } + mutex_unlock(&src_ctx->mutex); + + synchronize_rcu(); + + mutex_lock(&dst_ctx->mutex); + list_for_each_entry_safe(event, tmp, &events, event_entry) { + list_del(&event->event_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + mutex_unlock(&dst_ctx->mutex); +} +EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); + static void sync_child_event(struct perf_event *child_event, struct task_struct *child) { -- cgit v1.2.3 From 0be61ebc18b919dddbdbcd1c4f42513c310ecf59 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 18 Jun 2012 09:28:16 -0400 Subject: tracing/selftest: Add a WARN_ON() if a tracer test fails Add a WARN_ON() output on test failures so that they are easier to detect in automated tests. Although, the WARN_ON() will not print if the test causes the system to crash, obviously. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 49249c28690d..748f6401edf6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -830,6 +830,8 @@ int register_tracer(struct tracer *type) current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ -- cgit v1.2.3 From 6d158a813efcd09661c23f16ddf7e2ff834cb20c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 27 Jun 2012 20:46:14 -0400 Subject: tracing: Remove NR_CPUS array from trace_iterator Replace the NR_CPUS array of buffer_iter from the trace_iterator with an allocated array. This will just create an array of possible CPUS instead of the max number specified. The use of NR_CPUS in that array caused allocation failures for machines that were tight on memory. This did not cause any failures to the system itself (no crashes), but caused unnecessary failures for reading the trace files. Added a helper function called 'trace_buffer_iter()' that returns the buffer_iter item or NULL if it is not defined or the array was not allocated. Some routines do not require the array (tracing_open_pipe() for one). Reported-by: Dave Jones Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- kernel/trace/trace.c | 27 ++++++++++++++++++--------- kernel/trace/trace.h | 8 ++++++++ kernel/trace/trace_functions_graph.c | 2 +- 4 files changed, 28 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 1aff18346c71..af961d6f7ab1 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -65,7 +65,7 @@ struct trace_iterator { void *private; int cpu_file; struct mutex mutex; - struct ring_buffer_iter *buffer_iter[NR_CPUS]; + struct ring_buffer_iter **buffer_iter; unsigned long iter_flags; /* trace_seq for __print_flags() and __print_symbolic() etc. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 748f6401edf6..b2af14e94c28 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1710,9 +1710,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); + iter->idx++; - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + if (buf_iter) + ring_buffer_read(buf_iter, NULL); } static struct trace_entry * @@ -1720,7 +1722,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; - struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); @@ -1858,10 +1860,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) tr->data[cpu]->skipped_entries = 0; - if (!iter->buffer_iter[cpu]) + buf_iter = trace_buffer_iter(iter, cpu); + if (!buf_iter) return; - buf_iter = iter->buffer_iter[cpu]; ring_buffer_iter_reset(buf_iter); /* @@ -2207,13 +2209,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) int trace_empty(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { cpu = iter->cpu_file; - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2223,8 +2227,9 @@ int trace_empty(struct trace_iterator *iter) } for_each_tracing_cpu(cpu) { - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2383,6 +2388,8 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter) return ERR_PTR(-ENOMEM); + iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), + GFP_KERNEL); /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -2443,6 +2450,7 @@ __tracing_open(struct inode *inode, struct file *file) fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); + kfree(iter->buffer_iter); seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } @@ -2483,6 +2491,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); + kfree(iter->buffer_iter); seq_release_private(inode, file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5aec220d2de0..55e1f7f0db12 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -317,6 +317,14 @@ struct tracer { #define TRACE_PIPE_ALL_CPU -1 +static inline struct ring_buffer_iter * +trace_buffer_iter(struct trace_iterator *iter, int cpu) +{ + if (iter->buffer_iter && iter->buffer_iter[cpu]) + return iter->buffer_iter[cpu]; + return NULL; +} + int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void trace_wake_up(void); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a7d2a4c653d8..ce27c8ba8d31 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -538,7 +538,7 @@ get_return_for_leaf(struct trace_iterator *iter, next = &data->ret; } else { - ring_iter = iter->buffer_iter[iter->cpu]; + ring_iter = trace_buffer_iter(iter, iter->cpu); /* First peek to compare current entry and the next one */ if (ring_iter) -- cgit v1.2.3 From a5fb833172eca69136e9ee1ada778e404086ab8a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 28 Jun 2012 13:35:04 -0400 Subject: ring-buffer: Fix uninitialized read_stamp The ring buffer reader page is used to swap a page from the writable ring buffer. If the writer happens to be on that page, it ends up on the reader page, but will simply move off of it, back into the writable ring buffer as writes are added. The time stamp passed back to the readers is stored in the cpu_buffer per CPU descriptor. This stamp is updated when a swap of the reader page takes place, and it reads the current stamp from the page taken from the writable ring buffer. Everytime a writer goes to a new page, it updates the time stamp of that page. The problem happens if a reader reads a page from an empty per CPU ring buffer. If the buffer is empty, the swap still takes place, placing the writer at the start of the reader page. If at a later time, a write happens, it updates the page's time stamp and continues. But the problem is that the read_stamp does not get updated, because the page was already swapped. The solution to this was to not swap the page if the ring buffer happens to be empty. This also removes the side effect that the writes on the reader page will not get updated because the writer never gets back on the reader page without a swap. That is, if a read happens on an empty buffer, but then no reads happen for a while. If a swap took place, and the writer were to start writing a lot of data (function tracer), it will start overflowing the ring buffer and overwrite the older data. But because the writer never goes back onto the reader page, the data left on the reader page never gets overwritten. This causes the reader to see really old data, followed by a jump to newer data. Link: http://lkml.kernel.org/r/1340060577-9112-1-git-send-email-dhsharp@google.com Google-Bug-Id: 6410455 Reported-by: David Sharp tested-by: David Sharp Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1d0f6a8a0e5e..82a3e0c56b1d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) if (cpu_buffer->commit_page == cpu_buffer->reader_page) goto out; + /* Don't bother swapping if the ring buffer is empty */ + if (rb_num_of_entries(cpu_buffer) == 0) + goto out; + /* * Reset the reader page to size zero. */ -- cgit v1.2.3 From f885b7f2b2de70be266d2cecc476f773a1e2ca5d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 23 Apr 2012 15:52:53 -0700 Subject: rcu: Control RCU_FANOUT_LEAF from boot-time parameter Although making RCU_FANOUT_LEAF a kernel configuration parameter rather than a fixed constant makes it easier for people to decrease cache-miss overhead for large systems, it is of little help for people who must run a single pre-built kernel binary. This commit therefore allows the value of RCU_FANOUT_LEAF to be increased (but not decreased!) via a boot-time parameter named rcutree.rcu_fanout_leaf. Reported-by: Mike Galbraith Signed-off-by: Paul E. McKenney --- Documentation/kernel-parameters.txt | 5 ++ kernel/rcutree.c | 97 +++++++++++++++++++++++++++++++------ kernel/rcutree.h | 23 +++++---- kernel/rcutree_plugin.h | 2 + kernel/rcutree_trace.c | 2 +- 5 files changed, 104 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a92c5ebf373e..12783fa833c3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2367,6 +2367,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Set maximum number of finished RCU callbacks to process in one batch. + rcutree.fanout_leaf= [KNL,BOOT] + Increase the number of CPUs assigned to each + leaf rcu_node structure. Useful for very large + systems. + rcutree.qhimark= [KNL,BOOT] Set threshold of queued RCU callbacks over which batch limiting is disabled. diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4b97bba7396e..a4c592b66e10 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -60,17 +60,10 @@ /* Data structures. */ -static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; +static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; #define RCU_STATE_INITIALIZER(structname) { \ .level = { &structname##_state.node[0] }, \ - .levelcnt = { \ - NUM_RCU_LVL_0, /* root of hierarchy. */ \ - NUM_RCU_LVL_1, \ - NUM_RCU_LVL_2, \ - NUM_RCU_LVL_3, \ - NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ - }, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ @@ -91,6 +84,19 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +module_param(rcu_fanout_leaf, int, 0); +int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; +static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ + NUM_RCU_LVL_0, + NUM_RCU_LVL_1, + NUM_RCU_LVL_2, + NUM_RCU_LVL_3, + NUM_RCU_LVL_4, +}; +int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ + /* * The rcu_scheduler_active variable transitions from zero to one just * before the first task is spawned. So when this variable is zero, RCU @@ -2574,9 +2580,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) { int i; - for (i = NUM_RCU_LVLS - 1; i > 0; i--) + for (i = rcu_num_lvls - 1; i > 0; i--) rsp->levelspread[i] = CONFIG_RCU_FANOUT; - rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF; + rsp->levelspread[0] = rcu_fanout_leaf; } #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) @@ -2586,7 +2592,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) int i; cprv = NR_CPUS; - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { ccur = rsp->levelcnt[i]; rsp->levelspread[i] = (cprv + ccur - 1) / ccur; cprv = ccur; @@ -2613,13 +2619,15 @@ static void __init rcu_init_one(struct rcu_state *rsp, /* Initialize the level-tracking arrays. */ - for (i = 1; i < NUM_RCU_LVLS; i++) + for (i = 0; i < rcu_num_lvls; i++) + rsp->levelcnt[i] = num_rcu_lvl[i]; + for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; rcu_init_levelspread(rsp); /* Initialize the elements themselves, starting from the leaves. */ - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= rsp->levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { @@ -2649,7 +2657,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - rnp = rsp->level[NUM_RCU_LVLS - 1]; + rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; @@ -2658,11 +2666,72 @@ static void __init rcu_init_one(struct rcu_state *rsp, } } +/* + * Compute the rcu_node tree geometry from kernel parameters. This cannot + * replace the definitions in rcutree.h because those are needed to size + * the ->node array in the rcu_state structure. + */ +static void __init rcu_init_geometry(void) +{ + int i; + int j; + int n = NR_CPUS; + int rcu_capacity[MAX_RCU_LVLS + 1]; + + /* If the compile-time values are accurate, just leave. */ + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF) + return; + + /* + * Compute number of nodes that can be handled an rcu_node tree + * with the given number of levels. Setting rcu_capacity[0] makes + * some of the arithmetic easier. + */ + rcu_capacity[0] = 1; + rcu_capacity[1] = rcu_fanout_leaf; + for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Finally, the tree must be able to accommodate + * the configured number of CPUs. Complain and fall back to the + * compile-time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8 || + n > rcu_capacity[MAX_RCU_LVLS]) { + WARN_ON(1); + return; + } + + /* Calculate the number of rcu_nodes at each level of the tree. */ + for (i = 1; i <= MAX_RCU_LVLS; i++) + if (n <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) + num_rcu_lvl[j] = + DIV_ROUND_UP(n, rcu_capacity[i - j]); + rcu_num_lvls = i; + for (j = i + 1; j <= MAX_RCU_LVLS; j++) + num_rcu_lvl[j] = 0; + break; + } + + /* Calculate the total number of rcu_node structures. */ + rcu_num_nodes = 0; + for (i = 0; i <= MAX_RCU_LVLS; i++) + rcu_num_nodes += num_rcu_lvl[i]; + rcu_num_nodes -= n; +} + void __init rcu_init(void) { int cpu; rcu_bootup_announce(); + rcu_init_geometry(); rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 19b61ac1079f..780a0195d35a 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -42,28 +42,28 @@ #define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT_1 -# define NUM_RCU_LVLS 1 +# define RCU_NUM_LVLS 1 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 (NR_CPUS) # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_2 -# define NUM_RCU_LVLS 2 +# define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_3 -# define NUM_RCU_LVLS 3 +# define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_3 (NR_CPUS) # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_4 -# define NUM_RCU_LVLS 4 +# define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) @@ -76,6 +76,9 @@ #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) +extern int rcu_num_lvls; +extern int rcu_num_nodes; + /* * Dynticks per-CPU state. */ @@ -206,7 +209,7 @@ struct rcu_node { */ #define rcu_for_each_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* * Do a breadth-first scan of the non-leaf rcu_node structures for the @@ -215,7 +218,7 @@ struct rcu_node { */ #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) /* * Scan the leaves of the rcu_node hierarchy for the specified rcu_state @@ -224,8 +227,8 @@ struct rcu_node { * It is still a leaf node, even if it is also the root node. */ #define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ @@ -357,9 +360,9 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */ + struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ - u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */ + u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ /* The following fields are guarded by the root rcu_node's lock. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3e4899459f3d..fb92b6dd9980 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -70,6 +70,8 @@ static void __init rcu_bootup_announce_oddness(void) #if NUM_RCU_LVL_4 != 0 printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); #endif + if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); } #ifdef CONFIG_TREE_PREEMPT_RCU diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index d4bc16ddd1d4..a3556a2d842c 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -278,7 +278,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); level = rnp->level; -- cgit v1.2.3 From cc5df65b0370fc6aa2bfe3bb19e0451d5cafb99f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 15 Jun 2012 18:16:00 -0700 Subject: rcu: Four-level hierarchy is no longer experimental Time to make the four-level-hierarchy setting less scary, so this commit removes "Experimental" from the boot-time message. Leave the message in order to get a heads-up on any possible need to expand to a five-level hierarchy. Signed-off-by: Paul E. McKenney --- kernel/rcutree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index fb92b6dd9980..70e0fd256cc6 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -68,7 +68,7 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 - printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); + printk(KERN_INFO "\tFour-level hierarchy is enabled.\n"); #endif if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); -- cgit v1.2.3 From cca6f3931920a7547d02e68adc2ca635bea5600c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 May 2012 21:00:28 -0700 Subject: rcu: Size rcu_node tree from nr_cpu_ids rather than NR_CPUS The rcu_node tree array is sized based on compile-time constants, including NR_CPUS. Although this approach has worked well in the past, the recent trend by many distros to define NR_CPUS=4096 results in excessive grace-period-initialization latencies. This commit therefore substitutes the run-time computed nr_cpu_ids for the compile-time NR_CPUS when building the tree. This can result in much of the compile-time-allocated rcu_node array being unused. If this is a major problem, you are in a specialized situation anyway, so you can manually adjust the NR_CPUS, RCU_FANOUT, and RCU_FANOUT_LEAF kernel config parameters. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 2 +- kernel/rcutree_plugin.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index a4c592b66e10..0fdbc5e07302 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -2675,7 +2675,7 @@ static void __init rcu_init_geometry(void) { int i; int j; - int n = NR_CPUS; + int n = nr_cpu_ids; int rcu_capacity[MAX_RCU_LVLS + 1]; /* If the compile-time values are accurate, just leave. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 70e0fd256cc6..ef2b5231afa4 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -72,6 +72,8 @@ static void __init rcu_bootup_announce_oddness(void) #endif if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + if (nr_cpu_ids != NR_CPUS) + printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); } #ifdef CONFIG_TREE_PREEMPT_RCU -- cgit v1.2.3 From 6c90cc7bf077f28144013e949ee0c122012d194a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 May 2012 19:41:41 -0700 Subject: rcu: Prevent excessive line length in RCU_STATE_INITIALIZER() Upcoming rcu_barrier() concurrency commits will result in line lengths greater than 80 characters in the RCU_STATE_INITIALIZER(), so this commit shortens the name of the macro's argument to prevent this. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 0fdbc5e07302..dd7fd96c90c5 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -62,18 +62,18 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; -#define RCU_STATE_INITIALIZER(structname) { \ - .level = { &structname##_state.node[0] }, \ +#define RCU_STATE_INITIALIZER(sname) { \ + .level = { &sname##_state.node[0] }, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ - .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ - .orphan_nxttail = &structname##_state.orphan_nxtlist, \ - .orphan_donetail = &structname##_state.orphan_donelist, \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \ + .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.onofflock), \ + .orphan_nxttail = &sname##_state.orphan_nxtlist, \ + .orphan_donetail = &sname##_state.orphan_donelist, \ + .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ .n_force_qs = 0, \ .n_force_qs_ngp = 0, \ - .name = #structname, \ + .name = #sname, \ } struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); -- cgit v1.2.3 From 037b64ed0bf2405a1a01542164d3418564b44fff Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 May 2012 23:26:01 -0700 Subject: rcu: Place pointer to call_rcu() in rcu_data structure This is a preparatory commit for increasing rcu_barrier()'s concurrency. It adds a pointer in the rcu_data structure to the corresponding call_rcu() function. This allows a pointer to the rcu_data structure to imply the function pointer, which allows _rcu_barrier() state to be placed in the rcu_state structure. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 27 ++++++++++++--------------- kernel/rcutree.h | 2 ++ kernel/rcutree_plugin.h | 5 +++-- 3 files changed, 17 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index dd7fd96c90c5..00c518fa34bb 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -62,8 +62,9 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; -#define RCU_STATE_INITIALIZER(sname) { \ +#define RCU_STATE_INITIALIZER(sname, cr) { \ .level = { &sname##_state.node[0] }, \ + .call = cr, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ @@ -76,10 +77,11 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; .name = #sname, \ } -struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); +struct rcu_state rcu_sched_state = + RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched); DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); -struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh); +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; @@ -2282,21 +2284,17 @@ static void rcu_barrier_func(void *type) { int cpu = smp_processor_id(); struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + struct rcu_state *rsp = type; atomic_inc(&rcu_barrier_cpu_count); - call_rcu_func = type; - call_rcu_func(head, rcu_barrier_callback); + rsp->call(head, rcu_barrier_callback); } /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. */ -static void _rcu_barrier(struct rcu_state *rsp, - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +static void _rcu_barrier(struct rcu_state *rsp) { int cpu; unsigned long flags; @@ -2348,8 +2346,7 @@ static void _rcu_barrier(struct rcu_state *rsp, while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) schedule_timeout_interruptible(1); } else if (ACCESS_ONCE(rdp->qlen)) { - smp_call_function_single(cpu, rcu_barrier_func, - (void *)call_rcu_func, 1); + smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); preempt_enable(); } else { preempt_enable(); @@ -2370,7 +2367,7 @@ static void _rcu_barrier(struct rcu_state *rsp, raw_spin_unlock_irqrestore(&rsp->onofflock, flags); atomic_inc(&rcu_barrier_cpu_count); smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - call_rcu_func(&rh, rcu_barrier_callback); + rsp->call(&rh, rcu_barrier_callback); /* * Now that we have an rcu_barrier_callback() callback on each @@ -2393,7 +2390,7 @@ static void _rcu_barrier(struct rcu_state *rsp, */ void rcu_barrier_bh(void) { - _rcu_barrier(&rcu_bh_state, call_rcu_bh); + _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); @@ -2402,7 +2399,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_bh); */ void rcu_barrier_sched(void) { - _rcu_barrier(&rcu_sched_state, call_rcu_sched); + _rcu_barrier(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_barrier_sched); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 780a0195d35a..049896a835d9 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -364,6 +364,8 @@ struct rcu_state { u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ + void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ + void (*func)(struct rcu_head *head)); /* The following fields are guarded by the root rcu_node's lock. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index ef2b5231afa4..9cb3a68819fa 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -78,7 +78,8 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_TREE_PREEMPT_RCU -struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); +struct rcu_state rcu_preempt_state = + RCU_STATE_INITIALIZER(rcu_preempt, call_rcu); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; @@ -944,7 +945,7 @@ static int rcu_preempt_cpu_has_callbacks(int cpu) */ void rcu_barrier(void) { - _rcu_barrier(&rcu_preempt_state, call_rcu); + _rcu_barrier(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_barrier); -- cgit v1.2.3 From 06668efa9180f4824fe846a8ff96338c18646bc7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 May 2012 23:57:46 -0700 Subject: rcu: Move _rcu_barrier()'s rcu_head structures to rcu_data structures In order for multiple flavors of RCU to each concurrently run one rcu_barrier(), each flavor needs its own per-CPU set of rcu_head structures. This commit therefore moves _rcu_barrier()'s set of per-CPU rcu_head structures from per-CPU variables to the existing per-CPU and per-RCU-flavor rcu_data structures. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 6 ++---- kernel/rcutree.h | 3 +++ 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 00c518fa34bb..1e552598b55d 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -157,7 +157,6 @@ unsigned long rcutorture_vernum; /* State information for rcu_barrier() and friends. */ -static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; @@ -2282,12 +2281,11 @@ static void rcu_barrier_callback(struct rcu_head *notused) */ static void rcu_barrier_func(void *type) { - int cpu = smp_processor_id(); - struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); struct rcu_state *rsp = type; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); atomic_inc(&rcu_barrier_cpu_count); - rsp->call(head, rcu_barrier_callback); + rsp->call(&rdp->barrier_head, rcu_barrier_callback); } /* diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 049896a835d9..586d93c978f2 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -314,6 +314,9 @@ struct rcu_data { unsigned long n_rp_need_fqs; unsigned long n_rp_need_nothing; + /* 6) _rcu_barrier() callback. */ + struct rcu_head barrier_head; + int cpu; struct rcu_state *rsp; }; -- cgit v1.2.3 From 24ebbca8ecdd5129d7f829a7cb5146aaeb531f77 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 May 2012 00:34:56 -0700 Subject: rcu: Move rcu_barrier_cpu_count to rcu_state structure In order to allow each RCU flavor to concurrently execute its rcu_barrier() function, it is necessary to move the relevant state to the rcu_state structure. This commit therefore moves the rcu_barrier_cpu_count global variable to a new ->barrier_cpu_count field in the rcu_state structure. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 25 ++++++++++++++----------- kernel/rcutree.h | 1 + 2 files changed, 15 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 1e552598b55d..5929b021666d 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -157,7 +157,6 @@ unsigned long rcutorture_vernum; /* State information for rcu_barrier() and friends. */ -static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; @@ -2270,9 +2269,12 @@ static int rcu_cpu_has_callbacks(int cpu) * RCU callback function for _rcu_barrier(). If we are last, wake * up the task executing _rcu_barrier(). */ -static void rcu_barrier_callback(struct rcu_head *notused) +static void rcu_barrier_callback(struct rcu_head *rhp) { - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); + struct rcu_state *rsp = rdp->rsp; + + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) complete(&rcu_barrier_completion); } @@ -2284,7 +2286,7 @@ static void rcu_barrier_func(void *type) struct rcu_state *rsp = type; struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - atomic_inc(&rcu_barrier_cpu_count); + atomic_inc(&rsp->barrier_cpu_count); rsp->call(&rdp->barrier_head, rcu_barrier_callback); } @@ -2297,9 +2299,9 @@ static void _rcu_barrier(struct rcu_state *rsp) int cpu; unsigned long flags; struct rcu_data *rdp; - struct rcu_head rh; + struct rcu_data rd; - init_rcu_head_on_stack(&rh); + init_rcu_head_on_stack(&rd.barrier_head); /* Take mutex to serialize concurrent rcu_barrier() requests. */ mutex_lock(&rcu_barrier_mutex); @@ -2324,7 +2326,7 @@ static void _rcu_barrier(struct rcu_state *rsp) * us -- but before CPU 1's orphaned callbacks are invoked!!! */ init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 1); + atomic_set(&rsp->barrier_cpu_count, 1); raw_spin_lock_irqsave(&rsp->onofflock, flags); rsp->rcu_barrier_in_progress = current; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); @@ -2363,15 +2365,16 @@ static void _rcu_barrier(struct rcu_state *rsp) rcu_adopt_orphan_cbs(rsp); rsp->rcu_barrier_in_progress = NULL; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - atomic_inc(&rcu_barrier_cpu_count); + atomic_inc(&rsp->barrier_cpu_count); smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - rsp->call(&rh, rcu_barrier_callback); + rd.rsp = rsp; + rsp->call(&rd.barrier_head, rcu_barrier_callback); /* * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) complete(&rcu_barrier_completion); /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ @@ -2380,7 +2383,7 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rcu_barrier_mutex); - destroy_rcu_head_on_stack(&rh); + destroy_rcu_head_on_stack(&rd.barrier_head); } /** diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 586d93c978f2..c57ef0b7f097 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -400,6 +400,7 @@ struct rcu_state { struct task_struct *rcu_barrier_in_progress; /* Task doing rcu_barrier(), */ /* or NULL if no barrier. */ + atomic_t barrier_cpu_count; /* # CPUs waiting on. */ raw_spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ -- cgit v1.2.3 From 7db74df88b52844f4e966901e2972bba725e6766 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 May 2012 03:03:37 -0700 Subject: rcu: Move rcu_barrier_completion to rcu_state structure In order to allow each RCU flavor to concurrently execute its rcu_barrier() function, it is necessary to move the relevant state to the rcu_state structure. This commit therefore moves the rcu_barrier_completion global variable to a new ->barrier_completion field in the rcu_state structure. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 9 ++++----- kernel/rcutree.h | 1 + 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 5929b021666d..ca7d1678ac79 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -158,7 +158,6 @@ unsigned long rcutorture_vernum; /* State information for rcu_barrier() and friends. */ static DEFINE_MUTEX(rcu_barrier_mutex); -static struct completion rcu_barrier_completion; /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s @@ -2275,7 +2274,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp) struct rcu_state *rsp = rdp->rsp; if (atomic_dec_and_test(&rsp->barrier_cpu_count)) - complete(&rcu_barrier_completion); + complete(&rsp->barrier_completion); } /* @@ -2325,7 +2324,7 @@ static void _rcu_barrier(struct rcu_state *rsp) * 6. Both rcu_barrier_callback() callbacks are invoked, awakening * us -- but before CPU 1's orphaned callbacks are invoked!!! */ - init_completion(&rcu_barrier_completion); + init_completion(&rsp->barrier_completion); atomic_set(&rsp->barrier_cpu_count, 1); raw_spin_lock_irqsave(&rsp->onofflock, flags); rsp->rcu_barrier_in_progress = current; @@ -2375,10 +2374,10 @@ static void _rcu_barrier(struct rcu_state *rsp) * CPU, and thus each counted, remove the initial count. */ if (atomic_dec_and_test(&rsp->barrier_cpu_count)) - complete(&rcu_barrier_completion); + complete(&rsp->barrier_completion); /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ - wait_for_completion(&rcu_barrier_completion); + wait_for_completion(&rsp->barrier_completion); /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rcu_barrier_mutex); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index c57ef0b7f097..d1ca4424122b 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -401,6 +401,7 @@ struct rcu_state { /* Task doing rcu_barrier(), */ /* or NULL if no barrier. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ + struct completion barrier_completion; /* Wake at barrier end. */ raw_spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ -- cgit v1.2.3 From 7be7f0be907224445acc62b3884c892f38b7ff40 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 May 2012 05:18:53 -0700 Subject: rcu: Move rcu_barrier_mutex to rcu_state structure In order to allow each RCU flavor to concurrently execute its rcu_barrier() function, it is necessary to move the relevant state to the rcu_state structure. This commit therefore moves the rcu_barrier_mutex global variable to a new ->barrier_mutex field in the rcu_state structure. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 9 +++------ kernel/rcutree.h | 1 + 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index ca7d1678ac79..ff992ac24e73 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -71,6 +71,7 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.onofflock), \ .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ + .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ .n_force_qs = 0, \ .n_force_qs_ngp = 0, \ @@ -155,10 +156,6 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); unsigned long rcutorture_testseq; unsigned long rcutorture_vernum; -/* State information for rcu_barrier() and friends. */ - -static DEFINE_MUTEX(rcu_barrier_mutex); - /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -2303,7 +2300,7 @@ static void _rcu_barrier(struct rcu_state *rsp) init_rcu_head_on_stack(&rd.barrier_head); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rcu_barrier_mutex); + mutex_lock(&rsp->barrier_mutex); smp_mb(); /* Prevent any prior operations from leaking in. */ @@ -2380,7 +2377,7 @@ static void _rcu_barrier(struct rcu_state *rsp) wait_for_completion(&rsp->barrier_completion); /* Other rcu_barrier() invocations can now safely proceed. */ - mutex_unlock(&rcu_barrier_mutex); + mutex_unlock(&rsp->barrier_mutex); destroy_rcu_head_on_stack(&rd.barrier_head); } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index d1ca4424122b..7641aec3e59c 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -400,6 +400,7 @@ struct rcu_state { struct task_struct *rcu_barrier_in_progress; /* Task doing rcu_barrier(), */ /* or NULL if no barrier. */ + struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ raw_spinlock_t fqslock; /* Only one task forcing */ -- cgit v1.2.3 From cfed0a85dad921c683e9c0d25b072bcc5745ede0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 15 Jun 2012 18:22:05 -0700 Subject: rcu: Remove needless initialization For global variables, C defaults all fields to zero. The initialization of the rcu_state structure's ->n_force_qs and ->n_force_qs_ngp fields is therefore redundant, so this commit removes these initializations. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index ff992ac24e73..44a8fda9be86 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -73,8 +73,6 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ - .n_force_qs = 0, \ - .n_force_qs_ngp = 0, \ .name = #sname, \ } -- cgit v1.2.3 From cf3a9c4842b1e097dbe0854933c471d43dd24f69 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 May 2012 14:56:46 -0700 Subject: rcu: Increase rcu_barrier() concurrency The traditional rcu_barrier() implementation has serialized all requests, regardless of RCU flavor, and also does not coalesce concurrent requests. In the past, this has been good and sufficient. However, systems are getting larger and use of rcu_barrier() has been increasing. This commit therefore introduces a counter-based scheme that allows _rcu_barrier() calls for the same flavor of RCU to take advantage of each others' work. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 36 +++++++++++++++++++++++++++++++++++- kernel/rcutree.h | 2 ++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 44a8fda9be86..6bb5d562253f 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -2294,13 +2294,41 @@ static void _rcu_barrier(struct rcu_state *rsp) unsigned long flags; struct rcu_data *rdp; struct rcu_data rd; + unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap_done; init_rcu_head_on_stack(&rd.barrier_head); /* Take mutex to serialize concurrent rcu_barrier() requests. */ mutex_lock(&rsp->barrier_mutex); - smp_mb(); /* Prevent any prior operations from leaking in. */ + /* + * Ensure that all prior references, including to ->n_barrier_done, + * are ordered before the _rcu_barrier() machinery. + */ + smp_mb(); /* See above block comment. */ + + /* + * Recheck ->n_barrier_done to see if others did our work for us. + * This means checking ->n_barrier_done for an even-to-odd-to-even + * transition. The "if" expression below therefore rounds the old + * value up to the next even number and adds two before comparing. + */ + snap_done = ACCESS_ONCE(rsp->n_barrier_done); + if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) { + smp_mb(); /* caller's subsequent code after above check. */ + mutex_unlock(&rsp->barrier_mutex); + return; + } + + /* + * Increment ->n_barrier_done to avoid duplicate work. Use + * ACCESS_ONCE() to prevent the compiler from speculating + * the increment to precede the early-exit check. + */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ /* * Initialize the count to one rather than to zero in order to @@ -2371,6 +2399,12 @@ static void _rcu_barrier(struct rcu_state *rsp) if (atomic_dec_and_test(&rsp->barrier_cpu_count)) complete(&rsp->barrier_completion); + /* Increment ->n_barrier_done to prevent duplicate work. */ + smp_mb(); /* Keep increment after above mechanism. */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + smp_mb(); /* Keep increment before caller's subsequent code. */ + /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ wait_for_completion(&rsp->barrier_completion); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 7641aec3e59c..be10286ad380 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -403,6 +403,8 @@ struct rcu_state { struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ + unsigned long n_barrier_done; /* ++ at start and end of */ + /* _rcu_barrier(). */ raw_spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ -- cgit v1.2.3 From a83eff0a82a7f3f14fea477fd41e6c082e7fc96a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 23 May 2012 18:47:05 -0700 Subject: rcu: Add tracing for _rcu_barrier() This commit adds event tracing for _rcu_barrier() execution. This is defined only if RCU_TRACE=y. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/trace/events/rcu.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ kernel/rcutree.c | 29 ++++++++++++++++++++++++++++- 2 files changed, 73 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d274734b2aa4..5bde94d8585b 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -541,6 +541,50 @@ TRACE_EVENT(rcu_torture_read, __entry->rcutorturename, __entry->rhp) ); +/* + * Tracepoint for _rcu_barrier() execution. The string "s" describes + * the _rcu_barrier phase: + * "Begin": rcu_barrier_callback() started. + * "Check": rcu_barrier_callback() checking for piggybacking. + * "EarlyExit": rcu_barrier_callback() piggybacked, thus early exit. + * "Inc1": rcu_barrier_callback() piggyback check counter incremented. + * "Offline": rcu_barrier_callback() found offline CPU + * "OnlineQ": rcu_barrier_callback() found online CPU with callbacks. + * "OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks. + * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. + * "CB": An rcu_barrier_callback() invoked a callback, not the last. + * "LastCB": An rcu_barrier_callback() invoked the last callback. + * "Inc2": rcu_barrier_callback() piggyback check counter incremented. + * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument + * is the count of remaining callbacks, and "done" is the piggybacking count. + */ +TRACE_EVENT(rcu_barrier, + + TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done), + + TP_ARGS(rcuname, s, cpu, cnt, done), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(char *, s) + __field(int, cpu) + __field(int, cnt) + __field(unsigned long, done) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->s = s; + __entry->cpu = cpu; + __entry->cnt = cnt; + __entry->done = done; + ), + + TP_printk("%s %s cpu %d remaining %d # %lu", + __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt, + __entry->done) +); + #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) @@ -564,6 +608,7 @@ TRACE_EVENT(rcu_torture_read, #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ do { } while (0) #define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0) #endif /* #else #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6bb5d562253f..dda43d826504 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -2259,6 +2259,17 @@ static int rcu_cpu_has_callbacks(int cpu) rcu_preempt_cpu_has_callbacks(cpu); } +/* + * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * the compiler is expected to optimize this away. + */ +static void _rcu_barrier_trace(struct rcu_state *rsp, char *s, + int cpu, unsigned long done) +{ + trace_rcu_barrier(rsp->name, s, cpu, + atomic_read(&rsp->barrier_cpu_count), done); +} + /* * RCU callback function for _rcu_barrier(). If we are last, wake * up the task executing _rcu_barrier(). @@ -2268,8 +2279,12 @@ static void rcu_barrier_callback(struct rcu_head *rhp) struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); struct rcu_state *rsp = rdp->rsp; - if (atomic_dec_and_test(&rsp->barrier_cpu_count)) + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); complete(&rsp->barrier_completion); + } else { + _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + } } /* @@ -2280,6 +2295,7 @@ static void rcu_barrier_func(void *type) struct rcu_state *rsp = type; struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); atomic_inc(&rsp->barrier_cpu_count); rsp->call(&rdp->barrier_head, rcu_barrier_callback); } @@ -2298,6 +2314,7 @@ static void _rcu_barrier(struct rcu_state *rsp) unsigned long snap_done; init_rcu_head_on_stack(&rd.barrier_head); + _rcu_barrier_trace(rsp, "Begin", -1, snap); /* Take mutex to serialize concurrent rcu_barrier() requests. */ mutex_lock(&rsp->barrier_mutex); @@ -2315,7 +2332,9 @@ static void _rcu_barrier(struct rcu_state *rsp) * value up to the next even number and adds two before comparing. */ snap_done = ACCESS_ONCE(rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "Check", -1, snap_done); if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); smp_mb(); /* caller's subsequent code after above check. */ mutex_unlock(&rsp->barrier_mutex); return; @@ -2328,6 +2347,7 @@ static void _rcu_barrier(struct rcu_state *rsp) */ ACCESS_ONCE(rsp->n_barrier_done)++; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ /* @@ -2364,13 +2384,19 @@ static void _rcu_barrier(struct rcu_state *rsp) preempt_disable(); rdp = per_cpu_ptr(rsp->rda, cpu); if (cpu_is_offline(cpu)) { + _rcu_barrier_trace(rsp, "Offline", cpu, + rsp->n_barrier_done); preempt_enable(); while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) schedule_timeout_interruptible(1); } else if (ACCESS_ONCE(rdp->qlen)) { + _rcu_barrier_trace(rsp, "OnlineQ", cpu, + rsp->n_barrier_done); smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); preempt_enable(); } else { + _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + rsp->n_barrier_done); preempt_enable(); } } @@ -2403,6 +2429,7 @@ static void _rcu_barrier(struct rcu_state *rsp) smp_mb(); /* Keep increment after above mechanism. */ ACCESS_ONCE(rsp->n_barrier_done)++; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); smp_mb(); /* Keep increment before caller's subsequent code. */ /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ -- cgit v1.2.3 From d7e187c8e9f30543f9cadfed094896ff414acb8f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 25 May 2012 11:49:15 -0700 Subject: rcu: Add rcu_barrier() statistics to debugfs tracing This commit adds an rcubarrier file to RCU's debugfs statistical tracing directory, providing diagnostic information on rcu_barrier(). Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree_trace.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'kernel') diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index a3556a2d842c..057408be6c3b 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,40 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +static void print_rcubarrier(struct seq_file *m, struct rcu_state *rsp) +{ + seq_printf(m, "%c bcc: %d nbd: %lu\n", + rsp->rcu_barrier_in_progress ? 'B' : '.', + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); +} + +static int show_rcubarrier(struct seq_file *m, void *unused) +{ +#ifdef CONFIG_TREE_PREEMPT_RCU + seq_puts(m, "rcu_preempt: "); + print_rcubarrier(m, &rcu_preempt_state); +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ + seq_puts(m, "rcu_sched: "); + print_rcubarrier(m, &rcu_sched_state); + seq_puts(m, "rcu_bh: "); + print_rcubarrier(m, &rcu_bh_state); + return 0; +} + +static int rcubarrier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcubarrier, NULL); +} + +static const struct file_operations rcubarrier_fops = { + .owner = THIS_MODULE, + .open = rcubarrier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + #ifdef CONFIG_RCU_BOOST static char convert_kthread_status(unsigned int kthread_status) @@ -453,6 +487,11 @@ static int __init rcutree_trace_init(void) if (!rcudir) goto free_out; + retval = debugfs_create_file("rcubarrier", 0444, rcudir, + NULL, &rcubarrier_fops); + if (!retval) + goto free_out; + retval = debugfs_create_file("rcudata", 0444, rcudir, NULL, &rcudata_fops); if (!retval) -- cgit v1.2.3 From 1bca8cf1a2c3c6683b12ad28a3e826ca7a834978 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Jun 2012 09:40:38 -0700 Subject: rcu: Remove unneeded __rcu_process_callbacks() argument With the advent of __this_cpu_ptr(), it is no longer necessary to pass both the rcu_state and rcu_data structures into __rcu_process_callbacks(). This commit therefore computes the rcu_data pointer from the rcu_state pointer within __rcu_process_callbacks() so that callers can pass in only the pointer to the rcu_state structure. This paves the way for linking the rcu_state structures together and iterating over them. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 8 ++++---- kernel/rcutree_plugin.h | 3 +-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index dda43d826504..5376a156be8a 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1788,9 +1788,10 @@ unlock_fqs_ret: * whom the rdp belongs. */ static void -__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +__rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); @@ -1827,9 +1828,8 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) static void rcu_process_callbacks(struct softirq_action *unused) { trace_rcu_utilization("Start RCU core"); - __rcu_process_callbacks(&rcu_sched_state, - &__get_cpu_var(rcu_sched_data)); - __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + __rcu_process_callbacks(&rcu_sched_state); + __rcu_process_callbacks(&rcu_bh_state); rcu_preempt_process_callbacks(); trace_rcu_utilization("End RCU core"); } diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 9cb3a68819fa..5a80cdd9a0a3 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -687,8 +687,7 @@ static void rcu_preempt_check_callbacks(int cpu) */ static void rcu_preempt_process_callbacks(void) { - __rcu_process_callbacks(&rcu_preempt_state, - &__get_cpu_var(rcu_preempt_data)); + __rcu_process_callbacks(&rcu_preempt_state); } #ifdef CONFIG_RCU_BOOST -- cgit v1.2.3 From 6ce75a2326e6f8b3bdfb60e1de7934b89858e87b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Jun 2012 11:01:13 -0700 Subject: rcu: Introduce for_each_rcu_flavor() and use it The arrival of TREE_PREEMPT_RCU some years back included some ugly code involving either #ifdef or #ifdef'ed wrapper functions to iterate over all non-SRCU flavors of RCU. This commit therefore introduces a for_each_rcu_flavor() iterator over the rcu_state structures for each flavor of RCU to clean up a bit of the ugliness. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 53 +++++++++++++--------- kernel/rcutree.h | 12 +++-- kernel/rcutree_plugin.h | 116 ------------------------------------------------ 3 files changed, 37 insertions(+), 144 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 5376a156be8a..b61c3ffc80e9 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -84,6 +84,7 @@ struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +LIST_HEAD(rcu_struct_flavors); /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; @@ -860,9 +861,10 @@ static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) */ void rcu_cpu_stall_reset(void) { - rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_preempt_stall_reset(); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rsp->jiffies_stall = jiffies + ULONG_MAX / 2; } static struct notifier_block rcu_panic_block = { @@ -1827,10 +1829,11 @@ __rcu_process_callbacks(struct rcu_state *rsp) */ static void rcu_process_callbacks(struct softirq_action *unused) { + struct rcu_state *rsp; + trace_rcu_utilization("Start RCU core"); - __rcu_process_callbacks(&rcu_sched_state); - __rcu_process_callbacks(&rcu_bh_state); - rcu_preempt_process_callbacks(); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); trace_rcu_utilization("End RCU core"); } @@ -2241,9 +2244,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) */ static int rcu_pending(int cpu) { - return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) || - __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) || - rcu_preempt_pending(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu))) + return 1; + return 0; } /* @@ -2253,10 +2259,13 @@ static int rcu_pending(int cpu) */ static int rcu_cpu_has_callbacks(int cpu) { + struct rcu_state *rsp; + /* RCU callbacks either ready or pending? */ - return per_cpu(rcu_sched_data, cpu).nxtlist || - per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_cpu_has_callbacks(cpu); + for_each_rcu_flavor(rsp) + if (per_cpu_ptr(rsp->rda, cpu)->nxtlist) + return 1; + return 0; } /* @@ -2551,9 +2560,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) static void __cpuinit rcu_prepare_cpu(int cpu) { - rcu_init_percpu_data(cpu, &rcu_sched_state, 0); - rcu_init_percpu_data(cpu, &rcu_bh_state, 0); - rcu_preempt_init_percpu_data(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_init_percpu_data(cpu, rsp, + strcmp(rsp->name, "rcu_preempt") == 0); } /* @@ -2565,6 +2576,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, long cpu = (long)hcpu; struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; + struct rcu_state *rsp; trace_rcu_utilization("Start CPU hotplug"); switch (action) { @@ -2589,18 +2601,16 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_cleanup_dying_cpu(&rcu_bh_state); - rcu_cleanup_dying_cpu(&rcu_sched_state); - rcu_preempt_cleanup_dying_cpu(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); - rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); - rcu_preempt_cleanup_dead_cpu(cpu); + for_each_rcu_flavor(rsp) + rcu_cleanup_dead_cpu(cpu, rsp); break; default: break; @@ -2717,6 +2727,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, per_cpu_ptr(rsp->rda, i)->mynode = rnp; rcu_boot_init_percpu_data(i, rsp); } + list_add(&rsp->flavors, &rcu_struct_flavors); } /* diff --git a/kernel/rcutree.h b/kernel/rcutree.h index be10286ad380..b92c4550a6e6 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -422,8 +422,13 @@ struct rcu_state { unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ char *name; /* Name of structure. */ + struct list_head flavors; /* List of RCU flavors. */ }; +extern struct list_head rcu_struct_flavors; +#define for_each_rcu_flavor(rsp) \ + list_for_each_entry((rsp), &rcu_struct_flavors, flavors) + /* Return values for rcu_preempt_offline_tasks(). */ #define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ @@ -466,25 +471,18 @@ static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); -static void rcu_preempt_stall_reset(void); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); -static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ -static int rcu_preempt_pending(int cpu); -static int rcu_preempt_cpu_has_callbacks(int cpu); -static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 5a80cdd9a0a3..d18b4d383afe 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -544,16 +544,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } -/* - * Suppress preemptible RCU's CPU stall warnings by pushing the - * time of the next stall-warning message comfortably far into the - * future. - */ -static void rcu_preempt_stall_reset(void) -{ - rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2; -} - /* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace @@ -654,14 +644,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -/* - * Do CPU-offline processing for preemptible RCU. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ - rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); -} - /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, @@ -682,14 +664,6 @@ static void rcu_preempt_check_callbacks(int cpu) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } -/* - * Process callbacks for preemptible RCU. - */ -static void rcu_preempt_process_callbacks(void) -{ - __rcu_process_callbacks(&rcu_preempt_state); -} - #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void) @@ -921,24 +895,6 @@ mb_ret: } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -/* - * Check to see if there is any immediate preemptible-RCU-related work - * to be done. - */ -static int rcu_preempt_pending(int cpu) -{ - return __rcu_pending(&rcu_preempt_state, - &per_cpu(rcu_preempt_data, cpu)); -} - -/* - * Does preemptible RCU have callbacks on this CPU? - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return !!per_cpu(rcu_preempt_data, cpu).nxtlist; -} - /** * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. */ @@ -948,23 +904,6 @@ void rcu_barrier(void) } EXPORT_SYMBOL_GPL(rcu_barrier); -/* - * Initialize preemptible RCU's per-CPU data. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ - rcu_init_percpu_data(cpu, &rcu_preempt_state, 1); -} - -/* - * Move preemptible RCU's callbacks from dying CPU to other online CPU - * and record a quiescent state. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ - rcu_cleanup_dying_cpu(&rcu_preempt_state); -} - /* * Initialize preemptible RCU's state structures. */ @@ -1049,14 +988,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return 0; } -/* - * Because preemptible RCU does not exist, there is no need to suppress - * its CPU stall warnings. - */ -static void rcu_preempt_stall_reset(void) -{ -} - /* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for @@ -1084,14 +1015,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -/* - * Because preemptible RCU does not exist, it never needs CPU-offline - * processing. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ -} - /* * Because preemptible RCU does not exist, it never has any callbacks * to check. @@ -1100,14 +1023,6 @@ static void rcu_preempt_check_callbacks(int cpu) { } -/* - * Because preemptible RCU does not exist, it never has any callbacks - * to process. - */ -static void rcu_preempt_process_callbacks(void) -{ -} - /* * Queue an RCU callback for lazy invocation after a grace period. * This will likely be later named something like "call_rcu_lazy()", @@ -1148,22 +1063,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -/* - * Because preemptible RCU does not exist, it never has any work to do. - */ -static int rcu_preempt_pending(int cpu) -{ - return 0; -} - -/* - * Because preemptible RCU does not exist, it never has callbacks - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return 0; -} - /* * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). @@ -1174,21 +1073,6 @@ void rcu_barrier(void) } EXPORT_SYMBOL_GPL(rcu_barrier); -/* - * Because preemptible RCU does not exist, there is no per-CPU - * data to initialize. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ -} - -/* - * Because there is no preemptible RCU, there is no cleanup to do. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ -} - /* * Because preemptible RCU does not exist, it need not be initialized. */ -- cgit v1.2.3 From c0cc962da3e7770feb3665f087ea3e23d8c15479 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Jun 2012 12:25:39 -0700 Subject: rcu: Use for_each_rcu_flavor() in TREE_RCU tracing This commit applies the new for_each_rcu_flavor() macro to the kernel/rcutree_trace.c file. Signed-off-by: Paul E. McKenney --- kernel/rcutree_trace.c | 116 ++++++++++++++++++------------------------------- 1 file changed, 43 insertions(+), 73 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 057408be6c3b..a16ddbd6fdc4 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,24 +46,15 @@ #define RCU_TREE_NONCORE #include "rcutree.h" -static void print_rcubarrier(struct seq_file *m, struct rcu_state *rsp) -{ - seq_printf(m, "%c bcc: %d nbd: %lu\n", - rsp->rcu_barrier_in_progress ? 'B' : '.', - atomic_read(&rsp->barrier_cpu_count), - rsp->n_barrier_done); -} - static int show_rcubarrier(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt: "); - print_rcubarrier(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched: "); - print_rcubarrier(m, &rcu_sched_state); - seq_puts(m, "rcu_bh: "); - print_rcubarrier(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + seq_printf(m, "%s: %c bcc: %d nbd: %lu\n", + rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.', + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); return 0; } @@ -129,24 +120,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } -#define PRINT_RCU_DATA(name, func, m) \ - do { \ - int _p_r_d_i; \ - \ - for_each_possible_cpu(_p_r_d_i) \ - func(m, &per_cpu(name, _p_r_d_i)); \ - } while (0) - static int show_rcudata(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m); - seq_puts(m, "rcu_bh:\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + int cpu; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -200,6 +183,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { + int cpu; + struct rcu_state *rsp; + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); @@ -207,14 +193,11 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "\"rcu_preempt:\"\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "\"rcu_sched:\"\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m); - seq_puts(m, "\"rcu_bh:\"\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + for_each_rcu_flavor(rsp) { + seq_printf(m, "\"%s:\"\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data_csv(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -304,9 +287,9 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; gpnum = rsp->gpnum; - seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x " + seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x " "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->completed, gpnum, rsp->fqs_state, + rsp->name, rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), (int)(jiffies & 0xffff), rsp->n_force_qs, rsp->n_force_qs_ngp, @@ -329,14 +312,10 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) static int show_rcuhier(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_one_rcu_state(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_one_rcu_state(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_one_rcu_state(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + print_one_rcu_state(m, rsp); return 0; } @@ -377,11 +356,10 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) static int show_rcugp(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - show_one_rcugp(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - show_one_rcugp(m, &rcu_sched_state); - show_one_rcugp(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + show_one_rcugp(m, rsp); return 0; } @@ -416,28 +394,20 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) rdp->n_rp_need_nothing); } -static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp) +static int show_rcu_pending(struct seq_file *m, void *unused) { int cpu; struct rcu_data *rdp; - - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rdp->beenonline) - print_one_rcu_pending(m, rdp); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->beenonline) + print_one_rcu_pending(m, rdp); + } } -} - -static int show_rcu_pending(struct seq_file *m, void *unused) -{ -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_rcu_pendings(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_rcu_pendings(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_rcu_pendings(m, &rcu_bh_state); return 0; } -- cgit v1.2.3 From ff015030c939f0bec68fa9b8898da3aaa7fe55ea Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Jun 2012 13:16:58 -0700 Subject: rcu: RCU_SAVE_DYNTICK code no longer ever dead Before RCU had unified idle, the RCU_SAVE_DYNTICK leg of the switch statement in force_quiescent_state() was dead code for CONFIG_NO_HZ=n kernel builds. With unified idle, the code is never dead. This commit therefore removes the "if" statement designed to make gcc aware of when the code was and was not dead. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b61c3ffc80e9..967b4bed2cf3 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1747,8 +1747,6 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) break; /* grace period idle or initializing, ignore. */ case RCU_SAVE_DYNTICK: - if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) - break; /* So gcc recognizes the dead code. */ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ -- cgit v1.2.3 From 751a68b2e46fe11a42450cb55a16e8065eddec7e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 7 May 2012 13:44:44 -0700 Subject: rcu: Rationalize ordering of torture_ops list Move the raw SRCU interfaces out of the middle of the normal SRCU interfaces. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutorture.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e66b34ab7555..9850479f319d 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -1908,8 +1908,8 @@ rcu_torture_init(void) static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_sync_ops, &srcu_raw_ops, - &srcu_raw_sync_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops, + &srcu_raw_ops, &srcu_raw_sync_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); -- cgit v1.2.3 From e3f8d3788ed7cf55946030dc9b76e73edb111602 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 May 2012 10:21:50 -0700 Subject: rcu: Test srcu_barrier() from rcutorture test suite SRCU now has a call_srcu() and an srcu_barrier(), but rcutorture does not test them. This commit adds the machinery to allow rcutorture's existing tests for call_rcu() and rcu_barrier() to apply to the SRCU equivalents. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutorture.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 9850479f319d..7b6935e0cee3 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -635,6 +635,17 @@ static void srcu_torture_synchronize(void) synchronize_srcu(&srcu_ctl); } +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + static int srcu_torture_stats(char *page) { int cnt = 0; @@ -661,8 +672,8 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, - .call = NULL, - .cb_barrier = NULL, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, .name = "srcu" }; -- cgit v1.2.3 From c6ebcbb60c8c68a88160fe54302e851700d1362c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 May 2012 19:21:41 -0700 Subject: rcu: Fix bug in rcu_barrier() torture test The child threads in the rcu_torture_barrier_cbs() are improperly synchronized, which can cause the rcu_barrier() tests to hang. The failure mode is as follows: 1. CPU 0 running in rcu_torture_barrier() sets barrier_cbs_count to n_barrier_cbs. 2. CPU 1 running in rcu_torture_barrier_cbs() wakes up, posts its RCU callback, and atomically decrements barrier_cbs_count. Because barrier_cbs_count is not zero, it does not do the wake_up(). 3. CPU 2 running in rcu_torture_barrier_cbs() wakes up, but finds that barrier_cbs_count is not equal to n_barrier_cbs, and so returns to sleep. 4. The value of barrier_cbs_count therefore never reaches zero, which causes the test to hang. This commit therefore uses a phase variable to coordinate the test, preventing this scenario from occurring. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutorture.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 7b6935e0cee3..f7fe73e59c9f 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -206,6 +206,7 @@ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static bool barrier_phase; /* Test phase. */ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); @@ -1642,6 +1643,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; + bool lastphase = 0; struct rcu_head rcu; init_rcu_head_on_stack(&rcu); @@ -1649,9 +1651,11 @@ static int rcu_torture_barrier_cbs(void *arg) set_user_nice(current, 19); do { wait_event(barrier_cbs_wq[myid], - atomic_read(&barrier_cbs_count) == n_barrier_cbs || + barrier_phase != lastphase || kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP); + lastphase = barrier_phase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); @@ -1676,7 +1680,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - /* wake_up() path contains the required barriers. */ + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, -- cgit v1.2.3 From 143aa672f4fc643420c8325ad09c379ed33a27cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 24 May 2012 18:17:48 -0700 Subject: rcu: Fix diagnostic-printk typo in rcutorture The rcu_torture_barrier() function has a copy-and-paste typo in the string passed to rcutorture_shutdown_absorb(), which this commit fixes. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutorture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index f7fe73e59c9f..045a3dc233ea 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -1700,7 +1700,7 @@ static int rcu_torture_barrier(void *arg) schedule_timeout_interruptible(HZ / 10); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + rcutorture_shutdown_absorb("rcu_torture_barrier"); while (!kthread_should_stop()) schedule_timeout_interruptible(1); return 0; -- cgit v1.2.3 From 72472a02a9c4507ef54d03d71bb253c26015f52c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 May 2012 17:50:51 -0700 Subject: rcu: Make rcutorture fakewriters invoke rcu_barrier() The current rcutorture rcu_barrier() testing never intentionally runs more than one instance of rcu_barrier() at a given time. This fails to test the the shiny new concurrency features of rcu_barrier(). This commit therefore modifies the rcutorture fakewriter kthread to randomly invoke rcu_barrier() rather than the usual synchronize_rcu(). Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutorture.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 045a3dc233ea..c279ee920947 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -1025,7 +1025,11 @@ rcu_torture_fakewriter(void *arg) do { schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); - cur_ops->sync(); + if (cur_ops->cb_barrier != NULL && + rcu_random(&rand) % (nfakewriters * 8) == 0) + cur_ops->cb_barrier(); + else + cur_ops->sync(); rcu_stutter_wait("rcu_torture_fakewriter"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); -- cgit v1.2.3 From 285fe29481d865ae381ad3924c80894e6968c2d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2012 08:45:12 -0700 Subject: rcu: Fix detection of abruptly-ending stall The code that attempts to identify stalls that end just as we detect them is broken by both flavors of initialization failure. This commit therefore properly initializes and computes the count of the number of reasons why the RCU grace period is stalled. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4b97bba7396e..dc8c5284fe06 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -733,7 +733,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; - int ndetected; + int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -774,7 +774,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) */ rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected = rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); print_cpu_stall_info_end(); -- cgit v1.2.3 From 3f5d3ea64f1783f0d4ea0d35890ae3297f045a8b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2012 15:39:56 -0700 Subject: rcu: Consolidate duplicate callback-list initialization There are a couple of open-coded initializations of the rcu_data structure's RCU callback list. This commit therefore consolidates them into a new init_callback_list() function. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index dc8c5284fe06..81e0394e46af 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -936,6 +936,18 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) return ret; } +/* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + /* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp @@ -1328,8 +1340,6 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; - /* * Orphan the callbacks. First adjust the counts. This is safe * because ->onofflock excludes _rcu_barrier()'s adoption of @@ -1369,9 +1379,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, } /* Finally, initialize the rcu_data structure's list to empty. */ - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); } /* @@ -2407,16 +2415,13 @@ static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - int i; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); rdp->qlen_lazy = 0; rdp->qlen = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); -- cgit v1.2.3 From 1d1fb395f6dbc07b36285bbedcf01a73b57f7cb5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2012 15:44:42 -0700 Subject: rcu: Add ACCESS_ONCE() to ->qlen accesses The _rcu_barrier() function accesses other CPUs' rcu_data structure's ->qlen field without benefit of locking. This commit therefore adds the required ACCESS_ONCE() wrappers around accesses and updates that need it. ACCESS_ONCE() is not needed when a CPU accesses its own ->qlen, or in code that cannot run while _rcu_barrier() is sampling ->qlen fields. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 81e0394e46af..89addada3e3a 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1350,7 +1350,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; } /* @@ -1600,7 +1600,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - rdp->qlen -= count; + ACCESS_ONCE(rdp->qlen) -= count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -1889,7 +1889,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ - rdp->qlen++; + ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; else @@ -2423,7 +2423,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); init_callback_list(rdp); rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); -- cgit v1.2.3 From 2a3fa843b555d202e682bf08c65ee1a4a93c79cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 21 May 2012 11:58:36 -0700 Subject: rcu: Consolidate tree/tiny __rcu_read_{,un}lock() implementations The CONFIG_TREE_PREEMPT_RCU and CONFIG_TINY_PREEMPT_RCU versions of __rcu_read_lock() and __rcu_read_unlock() are identical, so this commit consolidates them into kernel/rcupdate.h. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 1 + kernel/rcupdate.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ kernel/rcutiny_plugin.h | 47 +---------------------------------------------- kernel/rcutree_plugin.h | 47 +---------------------------------------------- 4 files changed, 47 insertions(+), 92 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index fb8e6db511d7..698555ebf49b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -147,6 +147,7 @@ extern void synchronize_sched(void); extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 95cba41ce1e9..4e6a61b15e86 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -53,6 +53,50 @@ #ifdef CONFIG_PREEMPT_RCU +/* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + /* * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d65100..a269b0da0eb6 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -526,24 +525,12 @@ void rcu_preempt_note_context_switch(void) local_irq_restore(flags); } -/* - * Tiny-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - /* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -626,38 +613,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) local_irq_restore(flags); } -/* - * Tiny-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3e4899459f3d..4b6b17cdf66b 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -78,7 +78,6 @@ struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -232,18 +231,6 @@ static void rcu_preempt_note_context_switch(int cpu) local_irq_restore(flags); } -/* - * Tree-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutree.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - /* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable @@ -310,7 +297,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -418,38 +405,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } } -/* - * Tree-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* -- cgit v1.2.3 From 62fde6edf12b60fddb13a3f0a779c8be0bb7447e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 22 May 2012 22:10:24 -0700 Subject: rcu: Make __call_rcu() handle invocation from idle Although __call_rcu() is handled correctly when called from a momentary non-idle period, if it is called on a CPU that RCU believes to be idle on RCU_FAST_NO_HZ kernels, the callback might be indefinitely postponed. This commit therefore ensures that RCU is aware of the new callback and has a chance to force the CPU out of dyntick-idle mode when a new callback is posted. Reported-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 13 ++++--------- kernel/rcutree.c | 15 +++++++++------ 2 files changed, 13 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 31568c734525..26f6417f0264 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -256,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) +extern int rcu_is_cpu_idle(void); +#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */ + #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ @@ -267,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#ifdef CONFIG_PROVE_RCU -extern int rcu_is_cpu_idle(void); -#else /* !CONFIG_PROVE_RCU */ -static inline int rcu_is_cpu_idle(void) -{ - return 0; -} -#endif /* else !CONFIG_PROVE_RCU */ - static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 89addada3e3a..a4a9c916ad36 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -585,8 +585,6 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } -#ifdef CONFIG_PROVE_RCU - /** * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * @@ -604,7 +602,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * Is the current CPU online? Disable preemption to avoid false positives @@ -645,9 +643,7 @@ bool rcu_lockdep_current_cpu_online(void) } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /** * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle @@ -1904,6 +1900,13 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), else trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (rcu_is_cpu_idle()) + invoke_rcu_core(); + /* If interrupts were disabled, don't dive into RCU core. */ if (irqs_disabled_flags(flags)) { local_irq_restore(flags); -- cgit v1.2.3 From a16b7a693430406dc229ab0c6b154f669a2031c5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 26 May 2012 08:56:01 -0700 Subject: rcu: Prevent __call_rcu() from invoking RCU core on offline CPUs The __call_rcu() function will invoke the RCU core, for example, if it detects that the current CPU has too many callbacks. However, this can happen on an offline CPU that is on its way to the idle loop, in which case it is an error to invoke the RCU core, and the excess callbacks will be adopted in any case. This commit therefore adds checks to __call_rcu() for running on an offline CPU, refraining from invoking the RCU core in this case. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index a4a9c916ad36..ceaa95923a87 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1904,11 +1904,11 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. */ - if (rcu_is_cpu_idle()) + if (rcu_is_cpu_idle() && cpu_online(smp_processor_id())) invoke_rcu_core(); - /* If interrupts were disabled, don't dive into RCU core. */ - if (irqs_disabled_flags(flags)) { + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) { local_irq_restore(flags); return; } -- cgit v1.2.3 From 29154c57e35a191c83b19c61b1935c9f21957662 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 30 May 2012 03:21:48 -0700 Subject: rcu: Split RCU core processing out of __call_rcu() The __call_rcu() function is a bit overweight, so this commit splits it into actual enqueuing of and accounting for the callback (__call_rcu()) and associated RCU-core processing (__call_rcu_core()). Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 90 ++++++++++++++++++++++++++++++-------------------------- 1 file changed, 49 insertions(+), 41 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index ceaa95923a87..70c4da7d2a97 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1861,45 +1861,12 @@ static void invoke_rcu_core(void) raise_softirq(RCU_SOFTIRQ); } -static void -__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), - struct rcu_state *rsp, bool lazy) +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) { - unsigned long flags; - struct rcu_data *rdp; - - WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ - debug_rcu_head_queue(head); - head->func = func; - head->next = NULL; - - smp_mb(); /* Ensure RCU update seen before callback registry. */ - - /* - * Opportunistically note grace-period endings and beginnings. - * Note that we might see a beginning right after we see an - * end, but never vice versa, since this CPU has to pass through - * a quiescent state betweentimes. - */ - local_irq_save(flags); - rdp = this_cpu_ptr(rsp->rda); - - /* Add the callback to our list. */ - ACCESS_ONCE(rdp->qlen)++; - if (lazy) - rdp->qlen_lazy++; - else - rcu_idle_count_callbacks_posted(); - smp_mb(); /* Count before adding callback for rcu_barrier(). */ - *rdp->nxttail[RCU_NEXT_TAIL] = head; - rdp->nxttail[RCU_NEXT_TAIL] = &head->next; - - if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, - rdp->qlen_lazy, rdp->qlen); - else - trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); - /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -1908,10 +1875,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), invoke_rcu_core(); /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ - if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) { - local_irq_restore(flags); + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) return; - } /* * Force the grace period if too many callbacks or too long waiting. @@ -1944,6 +1909,49 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), } } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) force_quiescent_state(rsp, 1); +} + +static void +__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), + struct rcu_state *rsp, bool lazy) +{ + unsigned long flags; + struct rcu_data *rdp; + + WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ + debug_rcu_head_queue(head); + head->func = func; + head->next = NULL; + + smp_mb(); /* Ensure RCU update seen before callback registry. */ + + /* + * Opportunistically note grace-period endings and beginnings. + * Note that we might see a beginning right after we see an + * end, but never vice versa, since this CPU has to pass through + * a quiescent state betweentimes. + */ + local_irq_save(flags); + rdp = this_cpu_ptr(rsp->rda); + + /* Add the callback to our list. */ + ACCESS_ONCE(rdp->qlen)++; + if (lazy) + rdp->qlen_lazy++; + else + rcu_idle_count_callbacks_posted(); + smp_mb(); /* Count before adding callback for rcu_barrier(). */ + *rdp->nxttail[RCU_NEXT_TAIL] = head; + rdp->nxttail[RCU_NEXT_TAIL] = &head->next; + + if (__is_kfree_rcu_offset((unsigned long)func)) + trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, + rdp->qlen_lazy, rdp->qlen); + else + trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); + + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); local_irq_restore(flags); } -- cgit v1.2.3 From d7118175cce7e76b3292b60832813ef1f28b6523 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 6 Jun 2012 07:12:43 -0700 Subject: rcu: Fix rcu_is_cpu_idle() #ifdef in TINY_RCU The rcu_is_cpu_idle() function is used if CONFIG_DEBUG_LOCK_ALLOC, but TINY_RCU defines it only when CONFIG_PROVE_RCU. This causes build failures when CONFIG_DEBUG_LOCK_ALLOC=y but CONFIG_PROVE_RCU=n. This commit therefore adjusts the #ifdefs for rcu_is_cpu_idle() so that it is defined when CONFIG_DEBUG_LOCK_ALLOC=y. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutiny.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 37a5444204d2..547b1fe5b052 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -172,7 +172,7 @@ void rcu_irq_enter(void) local_irq_restore(flags); } -#ifdef CONFIG_PROVE_RCU +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Test whether RCU thinks that the current CPU is idle. @@ -183,7 +183,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * Test whether the current CPU was interrupted from idle. Nested -- cgit v1.2.3 From 1c17e4d4437d8045a596d9f06c1558dc09e2b372 Mon Sep 17 00:00:00 2001 From: Carsten Emde Date: Tue, 19 Jun 2012 10:43:16 +0200 Subject: rcu: Prevent uninitialized string in RCU CPU stall info An uninitialized string may be displayed at the end of the rcu_preempt detected stall info such as 0: (1 GPs behind) idle=075/140000000000000/0 =8?^D=8?^D ^^^^^^^^^^ if CONFIG_RCU_FAST_NO_HZ is not defined. This trivial patch clears the string in this case. Signed-off-by: Carsten Emde Signed-off-by: Paul E. McKenney --- kernel/rcutree_plugin.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 4b6b17cdf66b..395cdd1e0634 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -2224,6 +2224,7 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { + *cp = '\0'; } #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ -- cgit v1.2.3 From 95f0c1de3e6ed4383cc4b5f52ce4ecfb21026b49 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 19 Jun 2012 11:58:27 -0700 Subject: rcu: Disable preemption in rcu_blocking_is_gp() It is time to optimize CONFIG_TREE_PREEMPT_RCU's synchronize_rcu() for uniprocessor optimization, which means that rcu_blocking_is_gp() can no longer rely on RCU read-side critical sections having disabled preemption. This commit therefore disables preemption across rcu_blocking_is_gp()'s scan of the cpu_online_mask. (Updated from previous version to fix embarrassing bug spotted by Wu Fengguang.) Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 70c4da7d2a97..e000a623e635 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1981,28 +1981,16 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * occasionally incorrectly indicate that there are multiple CPUs online * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. - * - * Of course, sampling num_online_cpus() with preemption enabled can - * give erroneous results if there are concurrent CPU-hotplug operations. - * For example, given a demonic sequence of preemptions in num_online_cpus() - * and CPU-hotplug operations, there could be two or more CPUs online at - * all times, but num_online_cpus() might well return one (or even zero). - * - * However, all such demonic sequences require at least one CPU-offline - * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer - * is only a problem if there is an RCU read-side critical section executing - * throughout. But RCU-sched and RCU-bh read-side critical sections - * disable either preemption or bh, which prevents a CPU from going offline. - * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return - * that there is only one CPU when in fact there was more than one throughout - * is when there were no RCU readers in the system. If there are no - * RCU readers, the grace period by definition can be of zero length, - * regardless of the number of online CPUs. */ static inline int rcu_blocking_is_gp(void) { + int ret; + might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() <= 1; + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; } /** -- cgit v1.2.3 From cf01537ecf192d9ff15c32a355db5d5af22bea4d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 21 Jun 2012 11:26:42 -0700 Subject: rcu: Add check for CPUs going offline with callbacks queued If a CPU goes offline with callbacks queued, those callbacks might be indefinitely postponed, which can result in a system hang. This commit therefore inserts warnings for this condition. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e000a623e635..95c7b61e77e4 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1509,6 +1509,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From bf1304e9cd755be7814ac8365834b7a1d0f06b58 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2012 15:55:39 -0700 Subject: rcu: Dump only the current CPU's buffers for idle-entry/exit warnings Problems in RCU idle entry and exit are almost always confined to the offending CPU. This commit therefore switches ftrace_dump() from DUMP_ALL to DUMP_ORIG. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Tested-by: Heiko Carstens Tested-by: Pascal Chapperon --- kernel/rcutree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4b97bba7396e..6eb48f13eeeb 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -358,7 +358,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -468,7 +468,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) trace_rcu_dyntick("Error on exit: not idle task", oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ -- cgit v1.2.3 From 28f8555364ef5b54b21251c5c8022109a70626e9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 10 May 2012 15:37:48 -0700 Subject: rcu: The rcu_needs_cpu() function is not a quiescent state The TINY_PREEMPT_RCU() function rcu_preempt_needs_cpu(), which is called from rcu_needs_cpu(), assumes that it is in a quiescent state with respect to the CPU. This is no longer the case. This commit therefore updates rcu_preempt_needs_cpu() to make it aware that it is not running in a quiescent state. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Tested-by: Heiko Carstens Tested-by: Pascal Chapperon --- kernel/rcutiny_plugin.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d65100..849ede51c12d 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -846,8 +846,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ int rcu_preempt_needs_cpu(void) { - if (!rcu_preempt_running_reader()) - rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } -- cgit v1.2.3 From e84c48ae3024ac2f14ed1c3671e5ea37c60fb838 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 4 Jun 2012 20:45:10 -0700 Subject: rcu: Round FAST_NO_HZ lazy timeout to nearest second Currently, if several CPUs in the same package have all lazy RCU callbacks, their wakeups will be uncorrelated. If all the CPUs are in the same power domain (as is often the case), this will result in unnecessary power-ups of the package. This commit therefore uses round_jiffies() to round the timeouts to a second boundary, increasing the odds that they can be coalesced with each other or with other timeouts. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutree_plugin.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3e4899459f3d..c28d25522a81 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1968,7 +1968,7 @@ static void rcu_idle_count_callbacks_posted(void) */ #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ -#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ /* @@ -2047,10 +2047,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) return 1; } /* Set up for the possibility that RCU will post a timer. */ - if (rcu_cpu_has_nonlazy_callbacks(cpu)) - *delta_jiffies = RCU_IDLE_GP_DELAY; - else - *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies, + RCU_IDLE_GP_DELAY) - jiffies; + } else { + *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY; + *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies; + } return 0; } @@ -2187,10 +2190,11 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_nonlazy_callbacks(cpu)) { trace_rcu_prep_idle("Dyntick with callbacks"); rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_GP_DELAY; + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); } else { rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_LAZY_GP_DELAY; + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); trace_rcu_prep_idle("Dyntick with lazy callbacks"); } tp = &rdtp->idle_gp_timer; -- cgit v1.2.3 From 9d2ad24306f2fafc3612e5a216aab31f9e56e879 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 24 Jun 2012 10:15:02 -0700 Subject: rcu: Make RCU_FAST_NO_HZ respect nohz= boot parameter If the nohz= boot parameter disables nohz, then RCU_FAST_NO_HZ needs to also disable itself. This commit therefore checks for tick_nohz_enabled being zero, disabling rcu_prepare_for_idle() if so. This commit assumes that tick_nohz_enabled can change at runtime: If this is not the case, then a simpler approach suffices. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- kernel/rcutree.h | 1 + kernel/rcutree_plugin.h | 15 +++++++++++++++ kernel/time/tick-sched.c | 2 +- 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 19b61ac1079f..e978845c6800 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -97,6 +97,7 @@ struct rcu_dynticks { /* # times non-lazy CBs posted to CPU. */ unsigned long nonlazy_posted_snap; /* idle-period nonlazy_posted snapshot. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ }; diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c28d25522a81..3508000e077d 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1971,6 +1971,8 @@ static void rcu_idle_count_callbacks_posted(void) #define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ +extern int tick_nohz_enabled; + /* * Does the specified flavor of RCU have non-lazy callbacks pending on * the specified CPU? Both RCU flavor and CPU are specified by the @@ -2112,6 +2114,7 @@ static void rcu_cleanup_after_idle(int cpu) del_timer(&rdtp->idle_gp_timer); trace_rcu_prep_idle("Cleanup after idle"); + rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled); } /* @@ -2137,6 +2140,18 @@ static void rcu_prepare_for_idle(int cpu) { struct timer_list *tp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_enabled); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(cpu)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; /* * If this is an idle re-entry, for example, due to use of diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 869997833928..66ff07f6184c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -105,7 +105,7 @@ static ktime_t tick_init_jiffy_update(void) /* * NO HZ enabled ? */ -static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_enabled __read_mostly = 1; /* * Enable / Disable tickless mode -- cgit v1.2.3 From cfca927972e31a5b3da49bf641c525732ff3c357 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 25 Jun 2012 12:54:17 -0700 Subject: rcu: Introduce check for callback list/count mismatch The recent bug that introduced the RCU callback list/count mismatch showed the need for a diagnostic to check for this, which this commit adds. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 95c7b61e77e4..4154c9567a6d 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1612,6 +1612,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->n_force_qs_snap = rsp->n_force_qs; } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); local_irq_restore(flags); -- cgit v1.2.3 From c701d5d9b384ff03ceb232ef21236364d784a411 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 28 Jun 2012 08:08:25 -0700 Subject: rcu: Fix code-style issues involving "else" The Linux kernel coding style says that single-statement blocks should omit curly braces unless the other leg of the "if" statement has multiple statements, in which case the curly braces should be included. This commit fixes RCU's violations of this rule. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutiny_plugin.h | 7 ++++--- kernel/rcutorture.c | 3 ++- kernel/rcutree.c | 7 ++++--- kernel/rcutree_plugin.h | 14 ++++++++------ 4 files changed, 18 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 116725b5edfb..918fd1e8509c 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -350,8 +350,9 @@ static int rcu_initiate_boost(void) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); - } else + } else { RCU_TRACE(rcu_initiate_boost_trace()); + } return 1; } @@ -778,9 +779,9 @@ void synchronize_rcu_expedited(void) rpcp->exp_tasks = NULL; /* Wait for tail of ->blkd_tasks list to drain. */ - if (!rcu_preempted_readers_exp()) + if (!rcu_preempted_readers_exp()) { local_irq_restore(flags); - else { + } else { rcu_initiate_boost(); local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index c279ee920947..155fb129b641 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -408,8 +408,9 @@ rcu_torture_cb(struct rcu_head *p) if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { rp->rtort_mbtest = 0; rcu_torture_free(rp); - } else + } else { cur_ops->deferred_free(rp); + } } static int rcu_no_completed(void) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 117218a43724..f280e542e3e9 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -892,8 +892,9 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct if (rnp->qsmask & rdp->grpmask) { rdp->qs_pending = 1; rdp->passed_quiesce = 0; - } else + } else { rdp->qs_pending = 0; + } zero_cpu_stall_ticks(rdp); } } @@ -2130,9 +2131,9 @@ void synchronize_sched_expedited(void) put_online_cpus(); /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_sched(); return; } diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index a9194d5606c4..7f3244c0df01 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -390,8 +390,9 @@ void rcu_read_unlock_special(struct task_struct *t) rnp->grphi, !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rnp, flags); - } else + } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); + } #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ @@ -757,9 +758,9 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) int must_wait = 0; raw_spin_lock_irqsave(&rnp->lock, flags); - if (list_empty(&rnp->blkd_tasks)) + if (list_empty(&rnp->blkd_tasks)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - else { + } else { rnp->exp_tasks = rnp->blkd_tasks.next; rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ must_wait = 1; @@ -803,9 +804,9 @@ void synchronize_rcu_expedited(void) * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_rcu(); return; } @@ -2093,8 +2094,9 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_callbacks(cpu)) { trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else + } else { trace_rcu_prep_idle("Callbacks drained"); + } } /* -- cgit v1.2.3 From 5cf05ad758c30d17ff23c2be346b5de982bc2121 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 17 May 2012 15:12:45 -0700 Subject: rcu: Fix broken strings in RCU's source code. Although the C language allows you to break strings across lines, doing this makes it hard for people to find the Linux kernel code corresponding to a given console message. This commit therefore fixes broken strings throughout RCU's source code. Suggested-by: Josh Triplett Suggested-by: Ingo Molnar Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 3 +-- kernel/rcutorture.c | 33 ++++++++++++++------------------- kernel/rcutree_trace.c | 25 ++++++++++++------------- lib/list_debug.c | 6 ++---- 4 files changed, 29 insertions(+), 38 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c2c0d86dd3ac..115ead2b5155 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -427,8 +427,7 @@ extern int rcu_my_thread_group_empty(void); static inline void rcu_preempt_sleep_check(void) { rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), - "Illegal context switch in RCU read-side " - "critical section"); + "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 155fb129b641..25b15033c61f 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -49,8 +49,7 @@ #include MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Paul E. McKenney and " - "Josh Triplett "); +MODULE_AUTHOR("Paul E. McKenney and Josh Triplett "); static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ @@ -1200,27 +1199,27 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d rtbke: %ld rtbre: %ld " - "rtbf: %ld rtb: %ld nt: %ld " - "onoff: %ld/%ld:%ld/%ld " - "barrier: %ld/%ld:%ld", + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), atomic_read(&n_rcu_torture_alloc), atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free), + atomic_read(&n_rcu_torture_free)); + cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ", atomic_read(&n_rcu_torture_mberror), n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror, + n_rcu_torture_boost_rterror); + cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers, + n_rcu_torture_timers); + cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ", n_online_successes, n_online_attempts, n_offline_successes, - n_offline_attempts, + n_offline_attempts); + cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, n_rcu_torture_barrier_error); @@ -1462,8 +1461,7 @@ rcu_torture_shutdown(void *arg) delta = shutdown_time - jiffies_snap; if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu " - "jiffies remaining\n", + "rcu_torture_shutdown task: %lu jiffies remaining\n", torture_type, delta); schedule_timeout_interruptible(delta); jiffies_snap = ACCESS_ONCE(jiffies); @@ -1515,8 +1513,7 @@ rcu_torture_onoff(void *arg) if (cpu_down(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "offlined %d\n", + "rcu_torture_onoff task: offlined %d\n", torture_type, cpu); n_offline_successes++; } @@ -1529,8 +1526,7 @@ rcu_torture_onoff(void *arg) if (cpu_up(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "onlined %d\n", + "rcu_torture_onoff task: onlined %d\n", torture_type, cpu); n_online_successes++; } @@ -1952,8 +1948,7 @@ rcu_torture_init(void) return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { - printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero " - "fqs_duration, fqs disabled.\n"); + printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index a16ddbd6fdc4..abffb486e94e 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -218,8 +218,7 @@ static const struct file_operations rcudata_csv_fops = { static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) { - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu " - "j=%04x bt=%04x\n", + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", rnp->grplo, rnp->grphi, "T."[list_empty(&rnp->blkd_tasks)], "N."[!rnp->gp_tasks], @@ -227,11 +226,11 @@ static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) "B."[!rnp->boost_tasks], convert_kthread_status(rnp->boost_kthread_status), rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts, + rnp->n_normal_boosts); + seq_printf(m, "j=%04x bt=%04x\n", (int)(jiffies & 0xffff), (int)(rnp->boost_time & 0xffff)); - seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - " balk", + seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", rnp->n_balk_blkd_tasks, rnp->n_balk_exp_gp_tasks, rnp->n_balk_boost_tasks, @@ -287,11 +286,11 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; gpnum = rsp->gpnum; - seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x " - "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", + seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x ", rsp->name, rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff), + (int)(jiffies & 0xffff)); + seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); @@ -378,16 +377,16 @@ static const struct file_operations rcugp_fops = { static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) { - seq_printf(m, "%3d%cnp=%ld " - "qsp=%ld rpq=%ld cbr=%ld cng=%ld " - "gpc=%ld gps=%ld nf=%ld nn=%ld\n", + seq_printf(m, "%3d%cnp=%ld ", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending, + rdp->n_rcu_pending); + seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", rdp->n_rp_qs_pending, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp, + rdp->n_rp_cpu_needs_gp); + seq_printf(m, "gpc=%ld gps=%ld nf=%ld nn=%ld\n", rdp->n_rp_gp_completed, rdp->n_rp_gp_started, rdp->n_rp_need_fqs, diff --git a/lib/list_debug.c b/lib/list_debug.c index 23a5e031cd8b..c24c2f7e296f 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -87,12 +87,10 @@ void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { WARN(next->prev != prev, - "list_add_rcu corruption. next->prev should be " - "prev (%p), but was %p. (next=%p).\n", + "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n", prev, next->prev, next); WARN(prev->next != next, - "list_add_rcu corruption. prev->next should be " - "next (%p), but was %p. (prev=%p).\n", + "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n", next, prev->next, prev); new->next = next; new->prev = prev; -- cgit v1.2.3 From 93574fcc5b50cc7b8834698acb2ce947e5b6a5dc Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 11 Jul 2012 09:35:08 +0300 Subject: tracing: Check for allocation failure in __tracing_open() Clean up and return -ENOMEM on if the kzalloc() fails. This also prevents a potential crash, as the pointer that failed to allocate would be later used. Link: http://lkml.kernel.org/r/20120711063507.GF11812@elgon.mountain Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Dan Carpenter Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 814ff306ae74..a120f98c4112 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2390,6 +2390,9 @@ __tracing_open(struct inode *inode, struct file *file) iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), GFP_KERNEL); + if (!iter->buffer_iter) + goto release; + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -2451,6 +2454,7 @@ __tracing_open(struct inode *inode, struct file *file) mutex_unlock(&trace_types_lock); kfree(iter->trace); kfree(iter->buffer_iter); +release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } -- cgit v1.2.3 From 3e997130bd2e8c6f5aaa49d6e3161d4d29b43ab0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 16 Jul 2012 12:50:42 -0400 Subject: timekeeping: Add missing update call in timekeeping_resume() The leap second rework unearthed another issue of inconsistent data. On timekeeping_resume() the timekeeper data is updated, but nothing calls timekeeping_update(), so now the update code in the timer interrupt sees stale values. This has been the case before those changes, but then the timer interrupt was using stale data as well so this went unnoticed for quite some time. Add the missing update call, so all the data is consistent everywhere. Reported-by: Andreas Schwab Reported-and-tested-by: "Rafael J. Wysocki" Reported-and-tested-by: Martin Steigerwald Cc: LKML Cc: Linux PM list Cc: John Stultz Cc: Ingo Molnar Cc: Peter Zijlstra , Cc: Prarit Bhargava Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz Signed-off-by: Linus Torvalds --- kernel/time/timekeeping.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 269b1fe5f2ae..3447cfaf11e7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -717,6 +717,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; + timekeeping_update(false); write_sequnlock_irqrestore(&timekeeper.lock, flags); touch_softlockup_watchdog(); -- cgit v1.2.3 From eea03c20ae38a55405c0865ed9adfccc400e4c8e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 18 Jul 2012 18:15:46 -0700 Subject: Make wait_for_device_probe() also do scsi_complete_async_scans() Commit a7a20d103994 ("sd: limit the scope of the async probe domain") make the SCSI device probing run device discovery in it's own async domain. However, as a result, the partition detection was no longer synchronized by async_synchronize_full() (which, despite the name, only synchronizes the global async space, not all of them). Which in turn meant that "wait_for_device_probe()" would not wait for the SCSI partitions to be parsed. And "wait_for_device_probe()" was what the boot time init code relied on for mounting the root filesystem. Now, most people never noticed this, because not only is it timing-dependent, but modern distributions all use initrd. So the root filesystem isn't actually on a disk at all. And then before they actually mount the final disk filesystem, they will have loaded the scsi-wait-scan module, which not only does the expected wait_for_device_probe(), but also does scsi_complete_async_scans(). [ Side note: scsi_complete_async_scans() had also been partially broken, but that was fixed in commit 43a8d39d0137 ("fix async probe regression"), so that same commit a7a20d103994 had actually broken setups even if you used scsi-wait-scan explicitly ] Solve this problem by just moving the scsi_complete_async_scans() call into wait_for_device_probe(). Everybody who wants to wait for device probing to finish really wants the SCSI probing to complete, so there's no reason not to do this. So now "wait_for_device_probe()" really does what the name implies, and properly waits for device probing to finish. This also removes the now unnecessary extra calls to scsi_complete_async_scans(). Reported-and-tested-by: Artem S. Tashkinov Cc: Dan Williams Cc: Alan Stern Cc: James Bottomley Cc: Borislav Petkov Cc: linux-scsi Signed-off-by: Linus Torvalds --- drivers/base/dd.c | 2 ++ drivers/scsi/scsi_wait_scan.c | 5 ----- include/linux/device.h | 2 -- kernel/power/hibernate.c | 8 -------- kernel/power/user.c | 2 -- 5 files changed, 2 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/drivers/base/dd.c b/drivers/base/dd.c index dcb8a6e48692..4b01ab3d2c24 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "base.h" #include "power/power.h" @@ -332,6 +333,7 @@ void wait_for_device_probe(void) /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); + scsi_complete_async_scans(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); diff --git a/drivers/scsi/scsi_wait_scan.c b/drivers/scsi/scsi_wait_scan.c index ae7814874618..072734538876 100644 --- a/drivers/scsi/scsi_wait_scan.c +++ b/drivers/scsi/scsi_wait_scan.c @@ -22,11 +22,6 @@ static int __init wait_scan_init(void) * and might not yet have reached the scsi async scanning */ wait_for_device_probe(); - /* - * and then we wait for the actual asynchronous scsi scan - * to finish. - */ - scsi_complete_async_scans(); return 0; } diff --git a/include/linux/device.h b/include/linux/device.h index 161d96241b1b..6de94151ff6f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -865,8 +865,6 @@ extern int (*platform_notify_remove)(struct device *dev); extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); -extern void wait_for_device_probe(void); - #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); extern int devtmpfs_delete_node(struct device *dev); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8b53db38a279..238025f5472e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -27,7 +27,6 @@ #include #include #include -#include #include "power.h" @@ -748,13 +747,6 @@ static int software_resume(void) async_synchronize_full(); } - /* - * We can't depend on SCSI devices being available after loading - * one of their modules until scsi_complete_async_scans() is - * called and the resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { error = -ENODEV; diff --git a/kernel/power/user.c b/kernel/power/user.c index 91b0fd021a95..4ed81e74f86f 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -24,7 +24,6 @@ #include #include #include -#include #include @@ -84,7 +83,6 @@ static int snapshot_open(struct inode *inode, struct file *filp) * appear. */ wait_for_device_probe(); - scsi_complete_async_scans(); data->swap = -1; data->mode = O_WRONLY; -- cgit v1.2.3 From bc792e612e78a24ae0b30cc5b85f2368379ba4d4 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 20 Jul 2012 17:27:37 -0700 Subject: kdb: Revive dmesg command The kgdb dmesg command is broken after the printk rework. The old logic in kdb code makes no sense in terms of current printk/logging storage format, and KDB simply hangs forever. This patch revives the command by switching to kmsg_dumper iterator. The code is now much more simpler and shorter. Signed-off-by: Anton Vorontsov Signed-off-by: Linus Torvalds --- kernel/debug/kdb/kdb_main.c | 91 ++++++++++++++++----------------------------- 1 file changed, 33 insertions(+), 58 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 67b847dfa2bb..df17c935d3c6 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -2040,8 +2041,15 @@ static int kdb_env(int argc, const char **argv) */ static int kdb_dmesg(int argc, const char **argv) { - char *syslog_data[4], *start, *end, c = '\0', *p; - int diag, logging, logsize, lines = 0, adjust = 0, n; + int diag; + int logging; + int lines = 0; + int adjust = 0; + int n = 0; + int skip = 0; + struct kmsg_dumper dumper = { .active = 1 }; + size_t len; + char buf[201]; if (argc > 2) return KDB_ARGCOUNT; @@ -2064,22 +2072,10 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - /* syslog_data[0,1] physical start, end+1. syslog_data[2,3] - * logical start, end+1. */ - kdb_syslog_data(syslog_data); - if (syslog_data[2] == syslog_data[3]) - return 0; - logsize = syslog_data[1] - syslog_data[0]; - start = syslog_data[2]; - end = syslog_data[3]; -#define KDB_WRAP(p) (((p - syslog_data[0]) % logsize) + syslog_data[0]) - for (n = 0, p = start; p < end; ++p) { - c = *KDB_WRAP(p); - if (c == '\n') - ++n; - } - if (c != '\n') - ++n; + kmsg_dump_rewind(&dumper); + while (kmsg_dump_get_line(&dumper, 1, NULL, 0, NULL)) + n++; + if (lines < 0) { if (adjust >= n) kdb_printf("buffer only contains %d lines, nothing " @@ -2087,21 +2083,11 @@ static int kdb_dmesg(int argc, const char **argv) else if (adjust - lines >= n) kdb_printf("buffer only contains %d lines, last %d " "lines printed\n", n, n - adjust); - if (adjust) { - for (; start < end && adjust; ++start) { - if (*KDB_WRAP(start) == '\n') - --adjust; - } - if (start < end) - ++start; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - ++lines; - } - end = p; + skip = adjust; + lines = abs(lines); } else if (lines > 0) { - int skip = n - (adjust + lines); + skip = n - lines - adjust; + lines = abs(lines); if (adjust >= n) { kdb_printf("buffer only contains %d lines, " "nothing printed\n", n); @@ -2112,35 +2098,24 @@ static int kdb_dmesg(int argc, const char **argv) kdb_printf("buffer only contains %d lines, first " "%d lines printed\n", n, lines); } - for (; start < end && skip; ++start) { - if (*KDB_WRAP(start) == '\n') - --skip; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - --lines; - } - end = p; + } else { + lines = n; } - /* Do a line at a time (max 200 chars) to reduce protocol overhead */ - c = '\n'; - while (start != end) { - char buf[201]; - p = buf; - if (KDB_FLAG(CMD_INTERRUPT)) - return 0; - while (start < end && (c = *KDB_WRAP(start)) && - (p - buf) < sizeof(buf)-1) { - ++start; - *p++ = c; - if (c == '\n') - break; + + if (skip >= n || skip < 0) + return 0; + + kmsg_dump_rewind(&dumper); + while (kmsg_dump_get_line(&dumper, 1, buf, sizeof(buf), &len)) { + if (skip) { + skip--; + continue; } - *p = '\0'; - kdb_printf("%s", buf); + if (!lines--) + break; + + kdb_printf("%.*s\n", (int)len - 1, buf); } - if (c != '\n') - kdb_printf("\n"); return 0; } -- cgit v1.2.3 From 1b499d05eecbe04969516717a8e15afb6ad80689 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 20 Jul 2012 17:27:54 -0700 Subject: printk: Remove kdb_syslog_data The function is no longer needed, so remove it. Signed-off-by: Anton Vorontsov Signed-off-by: Linus Torvalds --- kernel/debug/kdb/kdb_private.h | 1 - kernel/printk.c | 15 --------------- 2 files changed, 16 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 47c4e56e513b..392ec6a25844 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -205,7 +205,6 @@ extern char kdb_grep_string[]; extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; -extern void kdb_syslog_data(char *syslog_data[]); extern unsigned long kdb_task_state_string(const char *); extern char kdb_task_state_char (const struct task_struct *); extern unsigned long kdb_task_state(const struct task_struct *p, diff --git a/kernel/printk.c b/kernel/printk.c index 177fa49357a5..c8129678dfbf 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1192,21 +1192,6 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } -#ifdef CONFIG_KGDB_KDB -/* kdb dmesg command needs access to the syslog buffer. do_syslog() - * uses locks so it cannot be used during debugging. Just tell kdb - * where the start and end of the physical and logical logs are. This - * is equivalent to do_syslog(3). - */ -void kdb_syslog_data(char *syslog_data[4]) -{ - syslog_data[0] = log_buf; - syslog_data[1] = log_buf + log_buf_len; - syslog_data[2] = log_buf + log_first_idx; - syslog_data[3] = log_buf + log_next_idx; -} -#endif /* CONFIG_KGDB_KDB */ - static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) -- cgit v1.2.3 From 533827c921c34310f63e859e1d6d0feec439657d Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 20 Jul 2012 17:28:07 -0700 Subject: printk: Implement some unlocked kmsg_dump functions If used from KDB, the locked variants are prone to deadlocks (suppose we got to the debugger w/ the logbuf lock held). So, we have to implement a few routines that grab no logbuf lock. Yet we don't need these functions in modules, so we don't export them. Signed-off-by: Anton Vorontsov Signed-off-by: Linus Torvalds --- include/linux/kmsg_dump.h | 16 +++++++++++ kernel/printk.c | 68 ++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 71 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index d6bd50110ec2..2e7a1e032c71 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -55,12 +55,17 @@ struct kmsg_dumper { #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len); + bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len); bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len); +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper); + void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); @@ -71,6 +76,13 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } +static inline bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, + bool syslog, const char *line, + size_t size, size_t *len) +{ + return false; +} + static inline bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, const char *line, size_t size, size_t *len) { @@ -83,6 +95,10 @@ static inline bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, return false; } +static inline void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ +} + static inline void kmsg_dump_rewind(struct kmsg_dumper *dumper) { } diff --git a/kernel/printk.c b/kernel/printk.c index c8129678dfbf..ac4bc9e79465 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -2510,7 +2510,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) } /** - * kmsg_dump_get_line - retrieve one kmsg log line + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to @@ -2525,11 +2525,12 @@ void kmsg_dump(enum kmsg_dump_reason reason) * * A return value of FALSE indicates that there are no more records to * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) { - unsigned long flags; struct log *msg; size_t l = 0; bool ret = false; @@ -2537,7 +2538,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, if (!dumper->active) goto out; - raw_spin_lock_irqsave(&logbuf_lock, flags); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; @@ -2545,10 +2545,8 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, } /* last entry */ - if (dumper->cur_seq >= log_next_seq) { - raw_spin_unlock_irqrestore(&logbuf_lock, flags); + if (dumper->cur_seq >= log_next_seq) goto out; - } msg = log_from_idx(dumper->cur_idx); l = msg_print_text(msg, 0, syslog, line, size); @@ -2556,12 +2554,41 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, dumper->cur_idx = log_next(dumper->cur_idx); dumper->cur_seq++; ret = true; - raw_spin_unlock_irqrestore(&logbuf_lock, flags); out: if (len) *len = l; return ret; } + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** @@ -2663,6 +2690,24 @@ out: } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); +/** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + /** * kmsg_dump_rewind - reset the interator * @dumper: registered kmsg dumper @@ -2676,10 +2721,7 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper) unsigned long flags; raw_spin_lock_irqsave(&logbuf_lock, flags); - dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + kmsg_dump_rewind_nolock(dumper); raw_spin_unlock_irqrestore(&logbuf_lock, flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); -- cgit v1.2.3 From c064da47144b11be4697a4611f640086a663016a Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 20 Jul 2012 17:28:25 -0700 Subject: kdb: Switch to nolock variants of kmsg_dump functions The locked variants are prone to deadlocks (suppose we got to the debugger w/ the logbuf lock held), so let's switch to nolock variants. Signed-off-by: Anton Vorontsov Signed-off-by: Linus Torvalds --- kernel/debug/kdb/kdb_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index df17c935d3c6..1f91413edb87 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2072,8 +2072,8 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - kmsg_dump_rewind(&dumper); - while (kmsg_dump_get_line(&dumper, 1, NULL, 0, NULL)) + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) n++; if (lines < 0) { @@ -2105,8 +2105,8 @@ static int kdb_dmesg(int argc, const char **argv) if (skip >= n || skip < 0) return 0; - kmsg_dump_rewind(&dumper); - while (kmsg_dump_get_line(&dumper, 1, buf, sizeof(buf), &len)) { + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { if (skip) { skip--; continue; -- cgit v1.2.3