WSL2-Linux-Kernel/include/linux/hardirq.h

199 строки
5.5 KiB
C
Исходник Обычный вид История

#ifndef LINUX_HARDIRQ_H
#define LINUX_HARDIRQ_H
#include <linux/preempt.h>
#include <linux/smp_lock.h>
[PATCH] lockdep: core Do 'make oldconfig' and accept all the defaults for new config options - reboot into the kernel and if everything goes well it should boot up fine and you should have /proc/lockdep and /proc/lockdep_stats files. Typically if the lock validator finds some problem it will print out voluminous debug output that begins with "BUG: ..." and which syslog output can be used by kernel developers to figure out the precise locking scenario. What does the lock validator do? It "observes" and maps all locking rules as they occur dynamically (as triggered by the kernel's natural use of spinlocks, rwlocks, mutexes and rwsems). Whenever the lock validator subsystem detects a new locking scenario, it validates this new rule against the existing set of rules. If this new rule is consistent with the existing set of rules then the new rule is added transparently and the kernel continues as normal. If the new rule could create a deadlock scenario then this condition is printed out. When determining validity of locking, all possible "deadlock scenarios" are considered: assuming arbitrary number of CPUs, arbitrary irq context and task context constellations, running arbitrary combinations of all the existing locking scenarios. In a typical system this means millions of separate scenarios. This is why we call it a "locking correctness" validator - for all rules that are observed the lock validator proves it with mathematical certainty that a deadlock could not occur (assuming that the lock validator implementation itself is correct and its internal data structures are not corrupted by some other kernel subsystem). [see more details and conditionals of this statement in include/linux/lockdep.h and Documentation/lockdep-design.txt] Furthermore, this "all possible scenarios" property of the validator also enables the finding of complex, highly unlikely multi-CPU multi-context races via single single-context rules, increasing the likelyhood of finding bugs drastically. In practical terms: the lock validator already found a bug in the upstream kernel that could only occur on systems with 3 or more CPUs, and which needed 3 very unlikely code sequences to occur at once on the 3 CPUs. That bug was found and reported on a single-CPU system (!). So in essence a race will be found "piecemail-wise", triggering all the necessary components for the race, without having to reproduce the race scenario itself! In its short existence the lock validator found and reported many bugs before they actually caused a real deadlock. To further increase the efficiency of the validator, the mapping is not per "lock instance", but per "lock-class". For example, all struct inode objects in the kernel have inode->inotify_mutex. If there are 10,000 inodes cached, then there are 10,000 lock objects. But ->inotify_mutex is a single "lock type", and all locking activities that occur against ->inotify_mutex are "unified" into this single lock-class. The advantage of the lock-class approach is that all historical ->inotify_mutex uses are mapped into a single (and as narrow as possible) set of locking rules - regardless of how many different tasks or inode structures it took to build this set of rules. The set of rules persist during the lifetime of the kernel. To see the rough magnitude of checking that the lock validator does, here's a portion of /proc/lockdep_stats, fresh after bootup: lock-classes: 694 [max: 2048] direct dependencies: 1598 [max: 8192] indirect dependencies: 17896 all direct dependencies: 16206 dependency chains: 1910 [max: 8192] in-hardirq chains: 17 in-softirq chains: 105 in-process chains: 1065 stack-trace entries: 38761 [max: 131072] combined max dependencies: 2033928 hardirq-safe locks: 24 hardirq-unsafe locks: 176 softirq-safe locks: 53 softirq-unsafe locks: 137 irq-safe locks: 59 irq-unsafe locks: 176 The lock validator has observed 1598 actual single-thread locking patterns, and has validated all possible 2033928 distinct locking scenarios. More details about the design of the lock validator can be found in Documentation/lockdep-design.txt, which can also found at: http://redhat.com/~mingo/lockdep-patches/lockdep-design.txt [bunk@stusta.de: cleanups] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-03 11:24:50 +04:00
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
#include <asm/hardirq.h>
#include <asm/system.h>
/*
* We put the hardirq and softirq counter into the preemption
* counter. The bitmask has the following meaning:
*
* - bits 0-7 are the preemption count (max preemption depth: 256)
* - bits 8-15 are the softirq count (max # of softirqs: 256)
*
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
* The hardirq count can in theory reach the same as NR_IRQS.
* In reality, the number of nested IRQS is limited to the stack
* size as well. For archs with over 1000 IRQS it is not practical
* to expect that they will all nest. We give a max of 10 bits for
* hardirq nesting. An arch may choose to give less than 10 bits.
* m68k expects it to be 8.
*
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
* - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
* - bit 26 is the NMI_MASK
* - bit 28 is the PREEMPT_ACTIVE flag
*
* PREEMPT_MASK: 0x000000ff
* SOFTIRQ_MASK: 0x0000ff00
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
* HARDIRQ_MASK: 0x03ff0000
* NMI_MASK: 0x04000000
*/
#define PREEMPT_BITS 8
#define SOFTIRQ_BITS 8
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define NMI_BITS 1
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define MAX_HARDIRQ_BITS 10
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#ifndef HARDIRQ_BITS
# define HARDIRQ_BITS MAX_HARDIRQ_BITS
#endif
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
#error HARDIRQ_BITS too high!
#endif
#define PREEMPT_SHIFT 0
#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
#define __IRQ_MASK(x) ((1UL << (x))-1)
#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define NMI_OFFSET (1UL << NMI_SHIFT)
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
#error PREEMPT_ACTIVE is too low!
#endif
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
| NMI_MASK))
/*
* Are we doing bottom half or hardware interrupt processing?
* Are we in a softirq context? Interrupt context?
*/
#define in_irq() (hardirq_count())
#define in_softirq() (softirq_count())
#define in_interrupt() (irq_count())
/*
* Are we in NMI context?
*/
preempt-count: force hardirq-count to max of 10 To add a bit in the preempt_count to be set when in NMI context, we found that some archs did not have enough bits to spare. This is due to the hardirq_count being a mask that can hold NR_IRQS. Some archs allow for over 16000 IRQs, and that would require a mask of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask is also 8 bits. The PREEMP_ACTIVE bit is bit 30, and bit 31 would make the preempt_count (which is type int) a negative number. A negative preempt_count is a sign of failure. Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit. But the hardirq_count is to track the number of nested IRQs, not the number of total IRQs. This originally took the paranoid approach of setting the max nesting to NR_IRQS. But when we have archs with over 1000 IRQs, it is not practical to think they will ever all nest on a single CPU. Not to mention that this would most definitely cause a stack overflow. This patch sets a max of 10 bits to be used for IRQ nesting. I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and HARDIRQ_MASK, and found that making it a max of 10 would not hurt anyone. I did find that the m68k expected it to be 8 bits, so I allow for the archs to set the number to be less than 10. I removed the setting of HARDIRQ_BITS from the archs that set it to more than 10. This includes ALPHA, ia64 and avr32. This will always allow room for the NMI bit, and if we need to allow for NMI nesting, we have 4 bits to play with. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 18:53:37 +03:00
#define in_nmi() (preempt_count() & NMI_MASK)
BKL: revert back to the old spinlock implementation The generic semaphore rewrite had a huge performance regression on AIM7 (and potentially other BKL-heavy benchmarks) because the generic semaphores had been rewritten to be simple to understand and fair. The latter, in particular, turns a semaphore-based BKL implementation into a mess of scheduling. The attempt to fix the performance regression failed miserably (see the previous commit 00b41ec2611dc98f87f30753ee00a53db648d662 'Revert "semaphore: fix"'), and so for now the simple and sane approach is to instead just go back to the old spinlock-based BKL implementation that never had any issues like this. This patch also has the advantage of being reported to fix the regression completely according to Yanmin Zhang, unlike the semaphore hack which still left a couple percentage point regression. As a spinlock, the BKL obviously has the potential to be a latency issue, but it's not really any different from any other spinlock in that respect. We do want to get rid of the BKL asap, but that has been the plan for several years. These days, the biggest users are in the tty layer (open/release in particular) and Alan holds out some hope: "tty release is probably a few months away from getting cured - I'm afraid it will almost certainly be the very last user of the BKL in tty to get fixed as it depends on everything else being sanely locked." so while we're not there yet, we do have a plan of action. Tested-by: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alexander Viro <viro@ftp.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-11 07:58:02 +04:00
#if defined(CONFIG_PREEMPT)
# define PREEMPT_INATOMIC_BASE kernel_locked()
# define PREEMPT_CHECK_OFFSET 1
#else
# define PREEMPT_INATOMIC_BASE 0
# define PREEMPT_CHECK_OFFSET 0
#endif
/*
* Are we running in atomic context? WARNING: this macro cannot
* always detect atomic context; in particular, it cannot know about
* held spinlocks in non-preemptible kernels. Thus it should not be
* used in the general case to determine whether sleeping is possible.
* Do not use in_atomic() in driver code.
*/
BKL: revert back to the old spinlock implementation The generic semaphore rewrite had a huge performance regression on AIM7 (and potentially other BKL-heavy benchmarks) because the generic semaphores had been rewritten to be simple to understand and fair. The latter, in particular, turns a semaphore-based BKL implementation into a mess of scheduling. The attempt to fix the performance regression failed miserably (see the previous commit 00b41ec2611dc98f87f30753ee00a53db648d662 'Revert "semaphore: fix"'), and so for now the simple and sane approach is to instead just go back to the old spinlock-based BKL implementation that never had any issues like this. This patch also has the advantage of being reported to fix the regression completely according to Yanmin Zhang, unlike the semaphore hack which still left a couple percentage point regression. As a spinlock, the BKL obviously has the potential to be a latency issue, but it's not really any different from any other spinlock in that respect. We do want to get rid of the BKL asap, but that has been the plan for several years. These days, the biggest users are in the tty layer (open/release in particular) and Alan holds out some hope: "tty release is probably a few months away from getting cured - I'm afraid it will almost certainly be the very last user of the BKL in tty to get fixed as it depends on everything else being sanely locked." so while we're not there yet, we do have a plan of action. Tested-by: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alexander Viro <viro@ftp.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-11 07:58:02 +04:00
#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_INATOMIC_BASE)
/*
* Check whether we were atomic before we did preempt_disable():
BKL: revert back to the old spinlock implementation The generic semaphore rewrite had a huge performance regression on AIM7 (and potentially other BKL-heavy benchmarks) because the generic semaphores had been rewritten to be simple to understand and fair. The latter, in particular, turns a semaphore-based BKL implementation into a mess of scheduling. The attempt to fix the performance regression failed miserably (see the previous commit 00b41ec2611dc98f87f30753ee00a53db648d662 'Revert "semaphore: fix"'), and so for now the simple and sane approach is to instead just go back to the old spinlock-based BKL implementation that never had any issues like this. This patch also has the advantage of being reported to fix the regression completely according to Yanmin Zhang, unlike the semaphore hack which still left a couple percentage point regression. As a spinlock, the BKL obviously has the potential to be a latency issue, but it's not really any different from any other spinlock in that respect. We do want to get rid of the BKL asap, but that has been the plan for several years. These days, the biggest users are in the tty layer (open/release in particular) and Alan holds out some hope: "tty release is probably a few months away from getting cured - I'm afraid it will almost certainly be the very last user of the BKL in tty to get fixed as it depends on everything else being sanely locked." so while we're not there yet, we do have a plan of action. Tested-by: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Alexander Viro <viro@ftp.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-11 07:58:02 +04:00
* (used by the scheduler, *after* releasing the kernel lock)
*/
#define in_atomic_preempt_off() \
((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
#ifdef CONFIG_PREEMPT
# define preemptible() (preempt_count() == 0 && !irqs_disabled())
# define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1)
#else
# define preemptible() 0
# define IRQ_EXIT_OFFSET HARDIRQ_OFFSET
#endif
#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS)
extern void synchronize_irq(unsigned int irq);
#else
# define synchronize_irq(irq) barrier()
#endif
struct task_struct;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
static inline void account_system_vtime(struct task_struct *tsk)
{
}
#endif
"Tree RCU": scalable classic RCU implementation This patch fixes a long-standing performance bug in classic RCU that results in massive internal-to-RCU lock contention on systems with more than a few hundred CPUs. Although this patch creates a separate flavor of RCU for ease of review and patch maintenance, it is intended to replace classic RCU. This patch still handles stress better than does mainline, so I am still calling it ready for inclusion. This patch is against the -tip tree. Nevertheless, experience on an actual 1000+ CPU machine would still be most welcome. Most of the changes noted below were found while creating an rcutiny (which should permit ejecting the current rcuclassic) and while doing detailed line-by-line documentation. Updates from v9 (http://lkml.org/lkml/2008/12/2/334): o Fixes from remainder of line-by-line code walkthrough, including comment spelling, initialization, undesirable narrowing due to type conversion, removing redundant memory barriers, removing redundant local-variable initialization, and removing redundant local variables. I do not believe that any of these fixes address the CPU-hotplug issues that Andi Kleen was seeing, but please do give it a whirl in case the machine is smarter than I am. A writeup from the walkthrough may be found at the following URL, in case you are suffering from terminal insomnia or masochism: http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf o Made rcutree tracing use seq_file, as suggested some time ago by Lai Jiangshan. o Added a .csv variant of the rcudata debugfs trace file, to allow people having thousands of CPUs to drop the data into a spreadsheet. Tested with oocalc and gnumeric. Updated documentation to suit. Updates from v8 (http://lkml.org/lkml/2008/11/15/139): o Fix a theoretical race between grace-period initialization and force_quiescent_state() that could occur if more than three jiffies were required to carry out the grace-period initialization. Which it might, if you had enough CPUs. o Apply Ingo's printk-standardization patch. o Substitute local variables for repeated accesses to global variables. o Fix comment misspellings and redundant (but harmless) increments of ->n_rcu_pending (this latter after having explicitly added it). o Apply checkpatch fixes. Updates from v7 (http://lkml.org/lkml/2008/10/10/291): o Fixed a number of problems noted by Gautham Shenoy, including the cpu-stall-detection bug that he was having difficulty convincing me was real. ;-) o Changed cpu-stall detection to wait for ten seconds rather than three in order to reduce false positive, as suggested by Ingo Molnar. o Produced a design document (http://lwn.net/Articles/305782/). The act of writing this document uncovered a number of both theoretical and "here and now" bugs as noted below. o Fix dynticks_nesting accounting confusion, simplify WARN_ON() condition, fix kerneldoc comments, and add memory barriers in dynticks interface functions. o Add more data to tracing. o Remove unused "rcu_barrier" field from rcu_data structure. o Count calls to rcu_pending() from scheduling-clock interrupt to use as a surrogate timebase should jiffies stop counting. o Fix a theoretical race between force_quiescent_state() and grace-period initialization. Yes, initialization does have to go on for some jiffies for this race to occur, but given enough CPUs... Updates from v6 (http://lkml.org/lkml/2008/9/23/448): o Fix a number of checkpatch.pl complaints. o Apply review comments from Ingo Molnar and Lai Jiangshan on the stall-detection code. o Fix several bugs in !CONFIG_SMP builds. o Fix a misspelled config-parameter name so that RCU now announces at boot time if stall detection is configured. o Run tests on numerous combinations of configurations parameters, which after the fixes above, now build and run correctly. Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line): o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a changeset some time ago, and finally got around to retesting this option). o Fix some tracing bugs in rcupreempt that caused incorrect totals to be printed. o I now test with a more brutal random-selection online/offline script (attached). Probably more brutal than it needs to be on the people reading it as well, but so it goes. o A number of optimizations and usability improvements: o Make rcu_pending() ignore the grace-period timeout when there is no grace period in progress. o Make force_quiescent_state() avoid going for a global lock in the case where there is no grace period in progress. o Rearrange struct fields to improve struct layout. o Make call_rcu() initiate a grace period if RCU was idle, rather than waiting for the next scheduling clock interrupt. o Invoke rcu_irq_enter() and rcu_irq_exit() only when idle, as suggested by Andi Kleen. I still don't completely trust this change, and might back it out. o Make CONFIG_RCU_TRACE be the single config variable manipulated for all forms of RCU, instead of the prior confusion. o Document tracing files and formats for both rcupreempt and rcutree. Updates from v4 for those missing v5 given its bad subject line: o Separated dynticks interface so that NMIs and irqs call separate functions, greatly simplifying it. In particular, this code no longer requires a proof of correctness. ;-) o Separated dynticks state out into its own per-CPU structure, avoiding the duplicated accounting. o The case where a dynticks-idle CPU runs an irq handler that invokes call_rcu() is now correctly handled, forcing that CPU out of dynticks-idle mode. o Review comments have been applied (thank you all!!!). For but one example, fixed the dynticks-ordering issue that Manfred pointed out, saving me much debugging. ;-) o Adjusted rcuclassic and rcupreempt to handle dynticks changes. Attached is an updated patch to Classic RCU that applies a hierarchy, greatly reducing the contention on the top-level lock for large machines. This passes 10-hour concurrent rcutorture and online-offline testing on 128-CPU ppc64 without dynticks enabled, and exposes some timekeeping bugs in presence of dynticks (exciting working on a system where "sleep 1" hangs until interrupted...), which were fixed in the 2.6.27 kernel. It is getting more reliable than mainline by some measures, so the next version will be against -tip for inclusion. See also Manfred Spraul's recent patches (or his earlier work from 2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2). We will converge onto a common patch in the fullness of time, but are currently exploring different regions of the design space. That said, I have already gratefully stolen quite a few of Manfred's ideas. This patch provides CONFIG_RCU_FANOUT, which controls the bushiness of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on 64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT, there is no hierarchy. By default, the RCU initialization code will adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable this balancing, allowing the hierarchy to be exactly aligned to the underlying hardware. Up to two levels of hierarchy are permitted (in addition to the root node), allowing up to 16,384 CPUs on 32-bit systems and up to 262,144 CPUs on 64-bit systems. I just know that I am going to regret saying this, but this seems more than sufficient for the foreseeable future. (Some architectures might wish to set CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs. If this becomes a real problem, additional levels can be added, but I doubt that it will make a significant difference on real hardware.) In the common case, a given CPU will manipulate its private rcu_data structure and the rcu_node structure that it shares with its immediate neighbors. This can reduce both lock and memory contention by multiple orders of magnitude, which should eliminate the need for the strange manipulations that are reported to be required when running Linux on very large systems. Some shortcomings: o More bugs will probably surface as a result of an ongoing line-by-line code inspection. Patches will be provided as required. o There are probably hangs, rcutorture failures, &c. Seems quite stable on a 128-CPU machine, but that is kind of small compared to 4096 CPUs. However, seems to do better than mainline. Patches will be provided as required. o The memory footprint of this version is several KB larger than rcuclassic. A separate UP-only rcutiny patch will be provided, which will reduce the memory footprint significantly, even compared to the old rcuclassic. One such patch passes light testing, and has a memory footprint smaller even than rcuclassic. Initial reaction from various embedded guys was "it is not worth it", so am putting it aside. Credits: o Manfred Spraul for ideas, review comments, and bugs spotted, as well as some good friendly competition. ;-) o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers, Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton for reviews and comments. o Thomas Gleixner for much-needed help with some timer issues (see patches below). o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos, Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines alive despite my heavy abuse^Wtesting. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 23:55:32 +03:00
#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
extern void rcu_irq_enter(void);
extern void rcu_irq_exit(void);
"Tree RCU": scalable classic RCU implementation This patch fixes a long-standing performance bug in classic RCU that results in massive internal-to-RCU lock contention on systems with more than a few hundred CPUs. Although this patch creates a separate flavor of RCU for ease of review and patch maintenance, it is intended to replace classic RCU. This patch still handles stress better than does mainline, so I am still calling it ready for inclusion. This patch is against the -tip tree. Nevertheless, experience on an actual 1000+ CPU machine would still be most welcome. Most of the changes noted below were found while creating an rcutiny (which should permit ejecting the current rcuclassic) and while doing detailed line-by-line documentation. Updates from v9 (http://lkml.org/lkml/2008/12/2/334): o Fixes from remainder of line-by-line code walkthrough, including comment spelling, initialization, undesirable narrowing due to type conversion, removing redundant memory barriers, removing redundant local-variable initialization, and removing redundant local variables. I do not believe that any of these fixes address the CPU-hotplug issues that Andi Kleen was seeing, but please do give it a whirl in case the machine is smarter than I am. A writeup from the walkthrough may be found at the following URL, in case you are suffering from terminal insomnia or masochism: http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf o Made rcutree tracing use seq_file, as suggested some time ago by Lai Jiangshan. o Added a .csv variant of the rcudata debugfs trace file, to allow people having thousands of CPUs to drop the data into a spreadsheet. Tested with oocalc and gnumeric. Updated documentation to suit. Updates from v8 (http://lkml.org/lkml/2008/11/15/139): o Fix a theoretical race between grace-period initialization and force_quiescent_state() that could occur if more than three jiffies were required to carry out the grace-period initialization. Which it might, if you had enough CPUs. o Apply Ingo's printk-standardization patch. o Substitute local variables for repeated accesses to global variables. o Fix comment misspellings and redundant (but harmless) increments of ->n_rcu_pending (this latter after having explicitly added it). o Apply checkpatch fixes. Updates from v7 (http://lkml.org/lkml/2008/10/10/291): o Fixed a number of problems noted by Gautham Shenoy, including the cpu-stall-detection bug that he was having difficulty convincing me was real. ;-) o Changed cpu-stall detection to wait for ten seconds rather than three in order to reduce false positive, as suggested by Ingo Molnar. o Produced a design document (http://lwn.net/Articles/305782/). The act of writing this document uncovered a number of both theoretical and "here and now" bugs as noted below. o Fix dynticks_nesting accounting confusion, simplify WARN_ON() condition, fix kerneldoc comments, and add memory barriers in dynticks interface functions. o Add more data to tracing. o Remove unused "rcu_barrier" field from rcu_data structure. o Count calls to rcu_pending() from scheduling-clock interrupt to use as a surrogate timebase should jiffies stop counting. o Fix a theoretical race between force_quiescent_state() and grace-period initialization. Yes, initialization does have to go on for some jiffies for this race to occur, but given enough CPUs... Updates from v6 (http://lkml.org/lkml/2008/9/23/448): o Fix a number of checkpatch.pl complaints. o Apply review comments from Ingo Molnar and Lai Jiangshan on the stall-detection code. o Fix several bugs in !CONFIG_SMP builds. o Fix a misspelled config-parameter name so that RCU now announces at boot time if stall detection is configured. o Run tests on numerous combinations of configurations parameters, which after the fixes above, now build and run correctly. Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line): o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a changeset some time ago, and finally got around to retesting this option). o Fix some tracing bugs in rcupreempt that caused incorrect totals to be printed. o I now test with a more brutal random-selection online/offline script (attached). Probably more brutal than it needs to be on the people reading it as well, but so it goes. o A number of optimizations and usability improvements: o Make rcu_pending() ignore the grace-period timeout when there is no grace period in progress. o Make force_quiescent_state() avoid going for a global lock in the case where there is no grace period in progress. o Rearrange struct fields to improve struct layout. o Make call_rcu() initiate a grace period if RCU was idle, rather than waiting for the next scheduling clock interrupt. o Invoke rcu_irq_enter() and rcu_irq_exit() only when idle, as suggested by Andi Kleen. I still don't completely trust this change, and might back it out. o Make CONFIG_RCU_TRACE be the single config variable manipulated for all forms of RCU, instead of the prior confusion. o Document tracing files and formats for both rcupreempt and rcutree. Updates from v4 for those missing v5 given its bad subject line: o Separated dynticks interface so that NMIs and irqs call separate functions, greatly simplifying it. In particular, this code no longer requires a proof of correctness. ;-) o Separated dynticks state out into its own per-CPU structure, avoiding the duplicated accounting. o The case where a dynticks-idle CPU runs an irq handler that invokes call_rcu() is now correctly handled, forcing that CPU out of dynticks-idle mode. o Review comments have been applied (thank you all!!!). For but one example, fixed the dynticks-ordering issue that Manfred pointed out, saving me much debugging. ;-) o Adjusted rcuclassic and rcupreempt to handle dynticks changes. Attached is an updated patch to Classic RCU that applies a hierarchy, greatly reducing the contention on the top-level lock for large machines. This passes 10-hour concurrent rcutorture and online-offline testing on 128-CPU ppc64 without dynticks enabled, and exposes some timekeeping bugs in presence of dynticks (exciting working on a system where "sleep 1" hangs until interrupted...), which were fixed in the 2.6.27 kernel. It is getting more reliable than mainline by some measures, so the next version will be against -tip for inclusion. See also Manfred Spraul's recent patches (or his earlier work from 2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2). We will converge onto a common patch in the fullness of time, but are currently exploring different regions of the design space. That said, I have already gratefully stolen quite a few of Manfred's ideas. This patch provides CONFIG_RCU_FANOUT, which controls the bushiness of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on 64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT, there is no hierarchy. By default, the RCU initialization code will adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable this balancing, allowing the hierarchy to be exactly aligned to the underlying hardware. Up to two levels of hierarchy are permitted (in addition to the root node), allowing up to 16,384 CPUs on 32-bit systems and up to 262,144 CPUs on 64-bit systems. I just know that I am going to regret saying this, but this seems more than sufficient for the foreseeable future. (Some architectures might wish to set CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs. If this becomes a real problem, additional levels can be added, but I doubt that it will make a significant difference on real hardware.) In the common case, a given CPU will manipulate its private rcu_data structure and the rcu_node structure that it shares with its immediate neighbors. This can reduce both lock and memory contention by multiple orders of magnitude, which should eliminate the need for the strange manipulations that are reported to be required when running Linux on very large systems. Some shortcomings: o More bugs will probably surface as a result of an ongoing line-by-line code inspection. Patches will be provided as required. o There are probably hangs, rcutorture failures, &c. Seems quite stable on a 128-CPU machine, but that is kind of small compared to 4096 CPUs. However, seems to do better than mainline. Patches will be provided as required. o The memory footprint of this version is several KB larger than rcuclassic. A separate UP-only rcutiny patch will be provided, which will reduce the memory footprint significantly, even compared to the old rcuclassic. One such patch passes light testing, and has a memory footprint smaller even than rcuclassic. Initial reaction from various embedded guys was "it is not worth it", so am putting it aside. Credits: o Manfred Spraul for ideas, review comments, and bugs spotted, as well as some good friendly competition. ;-) o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers, Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton for reviews and comments. o Thomas Gleixner for much-needed help with some timer issues (see patches below). o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos, Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines alive despite my heavy abuse^Wtesting. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 23:55:32 +03:00
extern void rcu_nmi_enter(void);
extern void rcu_nmi_exit(void);
#else
# define rcu_irq_enter() do { } while (0)
# define rcu_irq_exit() do { } while (0)
"Tree RCU": scalable classic RCU implementation This patch fixes a long-standing performance bug in classic RCU that results in massive internal-to-RCU lock contention on systems with more than a few hundred CPUs. Although this patch creates a separate flavor of RCU for ease of review and patch maintenance, it is intended to replace classic RCU. This patch still handles stress better than does mainline, so I am still calling it ready for inclusion. This patch is against the -tip tree. Nevertheless, experience on an actual 1000+ CPU machine would still be most welcome. Most of the changes noted below were found while creating an rcutiny (which should permit ejecting the current rcuclassic) and while doing detailed line-by-line documentation. Updates from v9 (http://lkml.org/lkml/2008/12/2/334): o Fixes from remainder of line-by-line code walkthrough, including comment spelling, initialization, undesirable narrowing due to type conversion, removing redundant memory barriers, removing redundant local-variable initialization, and removing redundant local variables. I do not believe that any of these fixes address the CPU-hotplug issues that Andi Kleen was seeing, but please do give it a whirl in case the machine is smarter than I am. A writeup from the walkthrough may be found at the following URL, in case you are suffering from terminal insomnia or masochism: http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf o Made rcutree tracing use seq_file, as suggested some time ago by Lai Jiangshan. o Added a .csv variant of the rcudata debugfs trace file, to allow people having thousands of CPUs to drop the data into a spreadsheet. Tested with oocalc and gnumeric. Updated documentation to suit. Updates from v8 (http://lkml.org/lkml/2008/11/15/139): o Fix a theoretical race between grace-period initialization and force_quiescent_state() that could occur if more than three jiffies were required to carry out the grace-period initialization. Which it might, if you had enough CPUs. o Apply Ingo's printk-standardization patch. o Substitute local variables for repeated accesses to global variables. o Fix comment misspellings and redundant (but harmless) increments of ->n_rcu_pending (this latter after having explicitly added it). o Apply checkpatch fixes. Updates from v7 (http://lkml.org/lkml/2008/10/10/291): o Fixed a number of problems noted by Gautham Shenoy, including the cpu-stall-detection bug that he was having difficulty convincing me was real. ;-) o Changed cpu-stall detection to wait for ten seconds rather than three in order to reduce false positive, as suggested by Ingo Molnar. o Produced a design document (http://lwn.net/Articles/305782/). The act of writing this document uncovered a number of both theoretical and "here and now" bugs as noted below. o Fix dynticks_nesting accounting confusion, simplify WARN_ON() condition, fix kerneldoc comments, and add memory barriers in dynticks interface functions. o Add more data to tracing. o Remove unused "rcu_barrier" field from rcu_data structure. o Count calls to rcu_pending() from scheduling-clock interrupt to use as a surrogate timebase should jiffies stop counting. o Fix a theoretical race between force_quiescent_state() and grace-period initialization. Yes, initialization does have to go on for some jiffies for this race to occur, but given enough CPUs... Updates from v6 (http://lkml.org/lkml/2008/9/23/448): o Fix a number of checkpatch.pl complaints. o Apply review comments from Ingo Molnar and Lai Jiangshan on the stall-detection code. o Fix several bugs in !CONFIG_SMP builds. o Fix a misspelled config-parameter name so that RCU now announces at boot time if stall detection is configured. o Run tests on numerous combinations of configurations parameters, which after the fixes above, now build and run correctly. Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line): o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a changeset some time ago, and finally got around to retesting this option). o Fix some tracing bugs in rcupreempt that caused incorrect totals to be printed. o I now test with a more brutal random-selection online/offline script (attached). Probably more brutal than it needs to be on the people reading it as well, but so it goes. o A number of optimizations and usability improvements: o Make rcu_pending() ignore the grace-period timeout when there is no grace period in progress. o Make force_quiescent_state() avoid going for a global lock in the case where there is no grace period in progress. o Rearrange struct fields to improve struct layout. o Make call_rcu() initiate a grace period if RCU was idle, rather than waiting for the next scheduling clock interrupt. o Invoke rcu_irq_enter() and rcu_irq_exit() only when idle, as suggested by Andi Kleen. I still don't completely trust this change, and might back it out. o Make CONFIG_RCU_TRACE be the single config variable manipulated for all forms of RCU, instead of the prior confusion. o Document tracing files and formats for both rcupreempt and rcutree. Updates from v4 for those missing v5 given its bad subject line: o Separated dynticks interface so that NMIs and irqs call separate functions, greatly simplifying it. In particular, this code no longer requires a proof of correctness. ;-) o Separated dynticks state out into its own per-CPU structure, avoiding the duplicated accounting. o The case where a dynticks-idle CPU runs an irq handler that invokes call_rcu() is now correctly handled, forcing that CPU out of dynticks-idle mode. o Review comments have been applied (thank you all!!!). For but one example, fixed the dynticks-ordering issue that Manfred pointed out, saving me much debugging. ;-) o Adjusted rcuclassic and rcupreempt to handle dynticks changes. Attached is an updated patch to Classic RCU that applies a hierarchy, greatly reducing the contention on the top-level lock for large machines. This passes 10-hour concurrent rcutorture and online-offline testing on 128-CPU ppc64 without dynticks enabled, and exposes some timekeeping bugs in presence of dynticks (exciting working on a system where "sleep 1" hangs until interrupted...), which were fixed in the 2.6.27 kernel. It is getting more reliable than mainline by some measures, so the next version will be against -tip for inclusion. See also Manfred Spraul's recent patches (or his earlier work from 2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2). We will converge onto a common patch in the fullness of time, but are currently exploring different regions of the design space. That said, I have already gratefully stolen quite a few of Manfred's ideas. This patch provides CONFIG_RCU_FANOUT, which controls the bushiness of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on 64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT, there is no hierarchy. By default, the RCU initialization code will adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable this balancing, allowing the hierarchy to be exactly aligned to the underlying hardware. Up to two levels of hierarchy are permitted (in addition to the root node), allowing up to 16,384 CPUs on 32-bit systems and up to 262,144 CPUs on 64-bit systems. I just know that I am going to regret saying this, but this seems more than sufficient for the foreseeable future. (Some architectures might wish to set CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs. If this becomes a real problem, additional levels can be added, but I doubt that it will make a significant difference on real hardware.) In the common case, a given CPU will manipulate its private rcu_data structure and the rcu_node structure that it shares with its immediate neighbors. This can reduce both lock and memory contention by multiple orders of magnitude, which should eliminate the need for the strange manipulations that are reported to be required when running Linux on very large systems. Some shortcomings: o More bugs will probably surface as a result of an ongoing line-by-line code inspection. Patches will be provided as required. o There are probably hangs, rcutorture failures, &c. Seems quite stable on a 128-CPU machine, but that is kind of small compared to 4096 CPUs. However, seems to do better than mainline. Patches will be provided as required. o The memory footprint of this version is several KB larger than rcuclassic. A separate UP-only rcutiny patch will be provided, which will reduce the memory footprint significantly, even compared to the old rcuclassic. One such patch passes light testing, and has a memory footprint smaller even than rcuclassic. Initial reaction from various embedded guys was "it is not worth it", so am putting it aside. Credits: o Manfred Spraul for ideas, review comments, and bugs spotted, as well as some good friendly competition. ;-) o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers, Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton for reviews and comments. o Thomas Gleixner for much-needed help with some timer issues (see patches below). o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos, Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines alive despite my heavy abuse^Wtesting. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 23:55:32 +03:00
# define rcu_nmi_enter() do { } while (0)
# define rcu_nmi_exit() do { } while (0)
#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
* because NMI handlers may not preempt and the ops are
* always balanced, so the interrupted value of ->hardirq_context
* will always be restored.
*/
#define __irq_enter() \
do { \
account_system_vtime(current); \
add_preempt_count(HARDIRQ_OFFSET); \
trace_hardirq_enter(); \
} while (0)
/*
* Enter irq context (on NO_HZ, update jiffies):
*/
extern void irq_enter(void);
/*
* Exit irq context without processing softirqs:
*/
#define __irq_exit() \
do { \
trace_hardirq_exit(); \
account_system_vtime(current); \
sub_preempt_count(HARDIRQ_OFFSET); \
} while (0)
/*
* Exit irq context and process softirqs if needed:
*/
extern void irq_exit(void);
#define nmi_enter() \
do { \
ftrace_nmi_enter(); \
BUG_ON(in_nmi()); \
add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \
lockdep_off(); \
rcu_nmi_enter(); \
trace_hardirq_enter(); \
ftrace: nmi safe code modification Impact: fix crashes that can occur in NMI handlers, if their code is modified Modifying code is something that needs special care. On SMP boxes, if code that is being modified is also being executed on another CPU, that CPU will have undefined results. The dynamic ftrace uses kstop_machine to make the system act like a uniprocessor system. But this does not address NMIs, that can still run on other CPUs. One approach to handle this is to make all code that are used by NMIs not be traced. But NMIs can call notifiers that spread throughout the kernel and this will be very hard to maintain, and the chance of missing a function is very high. The approach that this patch takes is to have the NMIs modify the code if the modification is taking place. The way this works is that just writing to code executing on another CPU is not harmful if what is written is the same as what exists. Two buffers are used: an IP buffer and a "code" buffer. The steps that the patcher takes are: 1) Put in the instruction pointer into the IP buffer and the new code into the "code" buffer. 2) Set a flag that says we are modifying code 3) Wait for any running NMIs to finish. 4) Write the code 5) clear the flag. 6) Wait for any running NMIs to finish. If an NMI is executed, it will also write the pending code. Multiple writes are OK, because what is being written is the same. Then the patcher must wait for all running NMIs to finish before going to the next line that must be patched. This is basically the RCU approach to code modification. Thanks to Ingo Molnar for suggesting the idea, and to Arjan van de Ven for his guidence on what is safe and what is not. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-10-30 23:08:32 +03:00
} while (0)
#define nmi_exit() \
do { \
trace_hardirq_exit(); \
rcu_nmi_exit(); \
lockdep_on(); \
BUG_ON(!in_nmi()); \
sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \
ftrace_nmi_exit(); \
ftrace: nmi safe code modification Impact: fix crashes that can occur in NMI handlers, if their code is modified Modifying code is something that needs special care. On SMP boxes, if code that is being modified is also being executed on another CPU, that CPU will have undefined results. The dynamic ftrace uses kstop_machine to make the system act like a uniprocessor system. But this does not address NMIs, that can still run on other CPUs. One approach to handle this is to make all code that are used by NMIs not be traced. But NMIs can call notifiers that spread throughout the kernel and this will be very hard to maintain, and the chance of missing a function is very high. The approach that this patch takes is to have the NMIs modify the code if the modification is taking place. The way this works is that just writing to code executing on another CPU is not harmful if what is written is the same as what exists. Two buffers are used: an IP buffer and a "code" buffer. The steps that the patcher takes are: 1) Put in the instruction pointer into the IP buffer and the new code into the "code" buffer. 2) Set a flag that says we are modifying code 3) Wait for any running NMIs to finish. 4) Write the code 5) clear the flag. 6) Wait for any running NMIs to finish. If an NMI is executed, it will also write the pending code. Multiple writes are OK, because what is being written is the same. Then the patcher must wait for all running NMIs to finish before going to the next line that must be patched. This is basically the RCU approach to code modification. Thanks to Ingo Molnar for suggesting the idea, and to Arjan van de Ven for his guidence on what is safe and what is not. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-10-30 23:08:32 +03:00
} while (0)
#endif /* LINUX_HARDIRQ_H */