b4ddfd6167
The only current purpose of the pvh lock was explained there On Wed, Jan 09, 2013 at 11:46:13PM -0600, Alan Cox wrote: > Let me lay out one example for you in detail. Suppose that we have > three processors and two of these processors are actively using the same > pmap. Now, one of the two processors sharing the pmap performs a > pmap_remove(). Suppose that one of the removed mappings is to a > physical page P. Moreover, suppose that the other processor sharing > that pmap has this mapping cached with write access in its TLB. Here's > where the trouble might begin. As you might expect, the processor > performing the pmap_remove() will acquire the fine-grained lock on the > PV list for page P before destroying the mapping to page P. Moreover, > this processor will ensure that the vm_page's dirty field is updated > before releasing that PV list lock. However, the TLB shootdown for this > mapping may not be initiated until after the PV list lock is released. > The processor performing the pmap_remove() is not problematic, because > the code being executed by that processor won't presume that the mapping > is destroyed until the TLB shootdown has completed and pmap_remove() has > returned. However, the other processor sharing the pmap could be > problematic. Specifically, suppose that the third processor is > executing the page daemon and concurrently trying to reclaim page P. > This processor performs a pmap_remove_all() on page P in preparation for > reclaiming the page. At this instant, the PV list for page P may > already be empty but our second processor still has a stale TLB entry > mapping page P. So, changes might still occur to the page after the > page daemon believes that all mappings have been destroyed. (If the PV > entry had still existed, then the pmap lock would have ensured that the > TLB shootdown completed before the pmap_remove_all() finished.) Note, > however, the page daemon will know that the page is dirty. It can't > possibly mistake a dirty page for a clean one. However, without the > current pvh global locking, I don't think anything is stopping the page > daemon from starting the laundering process before the TLB shootdown has > completed. > > I believe that a similar example could be constructed with a clean page > P' and a stale read-only TLB entry. In this case, the page P' could be > "cached" in the cache/free queues and recycled before the stale TLB > entry is flushed. TLBs for addresses with updated PTEs are always flushed before pmap lock is unlocked. On the other hand, amd64 pmap code does not always flushes TLBs before PV list locks are unlocked, if previously PTEs were cleared and PV entries removed. To handle the situations where a thread might notice empty PV list but third thread still having access to the page due to TLB invalidation not finished yet, introduce delayed invalidation. Comparing with the pvh_global_lock, DI does not block entered thread when pmap_remove_all() or pmap_remove_write() (callers of pmap_delayed_invl_wait()) are executed in parallel. But _invl_wait() callers are blocked until all previously noted DI blocks are leaved, thus ensuring that neccessary TLB invalidations were performed before returning from pmap_remove_all() or pmap_remove_write(). See comments for detailed description of the mechanism, and also for the explanations why several pmap methods, most important pmap_enter(), do not need DI protection. Reviewed by: alc, jhb (turnstile KPI usage) Tested by: pho (previous version) Sponsored by: The FreeBSD Foundation Differential revision: https://reviews.freebsd.org/D5747
105 lines
3.2 KiB
C
105 lines
3.2 KiB
C
/*-
|
|
* Copyright (c) 1991 Regents of the University of California.
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
* 4. Neither the name of the University nor the names of its contributors
|
|
* may be used to endorse or promote products derived from this software
|
|
* without specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*
|
|
* from: @(#)proc.h 7.1 (Berkeley) 5/15/91
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
#ifndef _MACHINE_PROC_H_
|
|
#define _MACHINE_PROC_H_
|
|
|
|
#include <sys/queue.h>
|
|
#include <machine/segments.h>
|
|
|
|
/*
|
|
* List of locks
|
|
* k - only accessed by curthread
|
|
* pp - pmap.c:invl_gen_mtx
|
|
*/
|
|
|
|
struct proc_ldt {
|
|
caddr_t ldt_base;
|
|
int ldt_refcnt;
|
|
};
|
|
|
|
struct pmap_invl_gen {
|
|
u_long gen; /* (k) */
|
|
LIST_ENTRY(pmap_invl_gen) link; /* (pp) */
|
|
};
|
|
|
|
/*
|
|
* Machine-dependent part of the proc structure for AMD64.
|
|
*/
|
|
struct mdthread {
|
|
int md_spinlock_count; /* (k) */
|
|
register_t md_saved_flags; /* (k) */
|
|
register_t md_spurflt_addr; /* (k) Spurious page fault address. */
|
|
struct pmap_invl_gen md_invl_gen;
|
|
};
|
|
|
|
struct mdproc {
|
|
struct proc_ldt *md_ldt; /* (t) per-process ldt */
|
|
struct system_segment_descriptor md_ldt_sd;
|
|
};
|
|
|
|
#define KINFO_PROC_SIZE 1088
|
|
#define KINFO_PROC32_SIZE 768
|
|
|
|
#ifdef _KERNEL
|
|
|
|
/* Get the current kernel thread stack usage. */
|
|
#define GET_STACK_USAGE(total, used) do { \
|
|
struct thread *td = curthread; \
|
|
(total) = td->td_kstack_pages * PAGE_SIZE; \
|
|
(used) = (char *)td->td_kstack + \
|
|
td->td_kstack_pages * PAGE_SIZE - \
|
|
(char *)&td; \
|
|
} while (0)
|
|
|
|
void set_user_ldt(struct mdproc *);
|
|
struct proc_ldt *user_ldt_alloc(struct proc *, int);
|
|
void user_ldt_free(struct thread *);
|
|
void user_ldt_deref(struct proc_ldt *);
|
|
struct sysarch_args;
|
|
int sysarch_ldt(struct thread *td, struct sysarch_args *uap, int uap_space);
|
|
int amd64_set_ldt_data(struct thread *td, int start, int num,
|
|
struct user_segment_descriptor *descs);
|
|
|
|
extern struct mtx dt_lock;
|
|
extern int max_ldt_segment;
|
|
|
|
struct syscall_args {
|
|
u_int code;
|
|
struct sysent *callp;
|
|
register_t args[8];
|
|
int narg;
|
|
};
|
|
#endif /* _KERNEL */
|
|
|
|
#endif /* !_MACHINE_PROC_H_ */
|