The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix: arch/x86/xen/built-in.o: In function `set_page_prot': enlighten.c:(.text+0x111d): undefined reference to `xen_raw_printk' arch/x86/xen/built-in.o: In function `xen_start_kernel': : undefined reference to `xen_raw_console_write' arch/x86/xen/built-in.o: In function `xen_start_kernel': : undefined reference to `xen_raw_console_write' Signed-off-by: Ingo Molnar <mingo@elte.hu>
Copy 64-bit definitions of various interface structures into place. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Stephen Tweedie <sct@redhat.com> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Mark McLoughlin <markmc@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
add xen_timer_resume() hook. Timer resume should be done after event channel is resumed. add xen_arch_resume() hook when ipi becomes usable after resume. After resume, some cpu specific resource must be reinitialized on ia64 that can't be set by another cpu. However available hooks is run once on only one cpu so that ipi has to be used. During stop_machine_run() ipi can't be used because interrupt is masked. So add another hook after stop_machine_run(). Another approach might be use resume hook which is run by device_resume(). However device_resume() may be executed on suspend error recovery path. So it is necessary to determine whether it is executed on real resume path or error recovery path. Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp> Cc: Stephen Tweedie <sct@redhat.com> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Mark McLoughlin <markmc@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Xen has a pte update function which will update a pte while preserving its accessed and dirty bits. This means that ptep_modify_prot_start() can be implemented as a simple read of the pte value. The hardware may update the pte in the meantime, but ptep_modify_prot_commit() updates it while preserving any changes that may have happened in the meantime. The updates in ptep_modify_prot_commit() are batched if we're currently in lazy mmu mode. The mmu_update hypercall can take a batch of updates to perform, but this code doesn't make particular use of that feature, in favour of using generic multicall batching to get them all into the hypervisor. The net effect of this is that each mprotect pte update turns from two expensive trap-and-emulate faults into they hypervisor into a single hypercall whose cost is amortized in a batched multicall. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Conflicts: arch/x86/xen/enlighten.c arch/x86/xen/mmu.c Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch updates the xen guest to use the pvclock structs and helper functions. Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Avi Kivity <avi@qumranet.com>
Define recently added XEN_ELFNOTEs, and use them appropriately. Most significantly, this enables domain checkpointing (xm save -c). Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-tip testing found the following build breakage: drivers/built-in.o: In function `xen_suspend': manage.c:(.text+0x4390f): undefined reference to `xen_console_resume' with this config: http://redhat.com/~mingo/misc/config-Thu_May_29_09_23_16_CEST_2008.bad i have bisected it down to: | commit 0e91398f2a5d4eb6b07df8115917d0d1cf3e9b58 | Author: Jeremy Fitzhardinge <jeremy@goop.org> | Date: Mon May 26 23:31:27 2008 +0100 | | xen: implement save/restore the problem is that drivers/xen/manage.c is built unconditionally if CONFIG_XEN is enabled and makes use of xen_suspend(), but drivers/char/hvc_xen.c, where the xen_suspend() method is implemented, is only build if CONFIG_HVC_XEN=y as well. i have solved this by providing a NOP implementation for xen_suspend() in the !CONFIG_HVC_XEN case. Signed-off-by: Ingo Molnar <mingo@elte.hu>
Hook into the device model to make sure that timekeeping's resume handler is called. This deals with our clocksource's non-monotonicity over the save/restore. Explicitly call clock_has_changed() to make sure that all the timers get retriggered properly. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>