similar to: [PATCH v3 03/18] x86/tsc/paravirt: Remove the read_tsc and read_tscp paravirt hooks

plain text document attachment (xx-paravirt-core.patch) Paravirt Ops core files. Signed-off-by: Steven Rostedt srostedt@redhat.com Signed-off-by: Glauber de Oliveira Costa <gcosta@redhat.com> Index: clean-start/arch/x86_64/kernel/paravirt.c =================================================================== --- /dev/null +++ clean-start/arch/x86_64/kernel/paravirt.c @@ -0,0 +1,504 @@ +/*

plain text document attachment (xx-paravirt-core.patch) Paravirt Ops core files. Signed-off-by: Steven Rostedt srostedt@redhat.com Signed-off-by: Glauber de Oliveira Costa <gcosta@redhat.com> Index: clean-start/arch/x86_64/kernel/paravirt.c =================================================================== --- /dev/null +++ clean-start/arch/x86_64/kernel/paravirt.c @@ -0,0 +1,504 @@ +/*

Hello all, Here's a new version of the paravirt_ops x86_64 patch. With this message, I'm sending an incremental patch. The complete patches can be found , from now on, at http://et.redhat.com/~gcosta/paravirt_ops/ The main aim of this new update, is to fix a critical bug, namely, Rusty's name. However, I took the opportunity to write some new less important pieces of code,

Hello all, Here's a new version of the paravirt_ops x86_64 patch. With this message, I'm sending an incremental patch. The complete patches can be found , from now on, at http://et.redhat.com/~gcosta/paravirt_ops/ The main aim of this new update, is to fix a critical bug, namely, Rusty's name. However, I took the opportunity to write some new less important pieces of code,

[ I think this is a straight repost this patch, which addresses all the previous comments. I'd like to submit this for .24 as the basis for a unified paravirt_ops. Any objections? ] This patch refactors the paravirt_ops structure into groups of functionally related ops: pv_info - random info, rather than function entrypoints pv_init_ops - functions used at boot time (some for module_init

[ I think this is a straight repost this patch, which addresses all the previous comments. I'd like to submit this for .24 as the basis for a unified paravirt_ops. Any objections? ] This patch refactors the paravirt_ops structure into groups of functionally related ops: pv_info - random info, rather than function entrypoints pv_init_ops - functions used at boot time (some for module_init

This patch refactors the paravirt_ops structure into groups of functionally related ops: pv_info - random info, rather than function entrypoints pv_init_ops - functions used at boot time (some for module_init too) pv_misc_ops - lazy mode, which didn't fit well anywhere else pv_time_ops - time-related functions pv_cpu_ops - various privileged instruction ops pv_irq_ops - operations for

This patch refactors the paravirt_ops structure into groups of functionally related ops: pv_info - random info, rather than function entrypoints pv_init_ops - functions used at boot time (some for module_init too) pv_misc_ops - lazy mode, which didn't fit well anywhere else pv_time_ops - time-related functions pv_cpu_ops - various privileged instruction ops pv_irq_ops - operations for

Here's a first attempt at splitting up paravirt_ops into more specific chunks. Its pretty clunky and chunky; mostly just a lot of replacement. The grouping of ops is very first cut; I'm open to suggestions about what groups should exist and what ops they each should contain. The only slightly subtle part is that I've kept the structures wrapped in a paravirt_ops structure,

Here's a first attempt at splitting up paravirt_ops into more specific chunks. Its pretty clunky and chunky; mostly just a lot of replacement. The grouping of ops is very first cut; I'm open to suggestions about what groups should exist and what ops they each should contain. The only slightly subtle part is that I've kept the structures wrapped in a paravirt_ops structure,

Implement the paravirt qspinlock for x86-kvm. We use the regular paravirt call patching to switch between: native_queue_spin_lock_slowpath() __pv_queue_spin_lock_slowpath() native_queue_spin_unlock() __pv_queue_spin_unlock() We use a callee saved call for the unlock function which reduces the i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions again. We further

Implement the paravirt qspinlock for x86-kvm. We use the regular paravirt call patching to switch between: native_queue_spin_lock_slowpath() __pv_queue_spin_lock_slowpath() native_queue_spin_unlock() __pv_queue_spin_unlock() We use a callee saved call for the unlock function which reduces the i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions again. We further

In order to share the common code in tsc.c which does CPU Khz calibration, we need to make an accurate value of CPU speed available to the tsc.c code. This value loses a lot of precision in a VM because of the timing differences with real hardware, but we need it to be as precise as possible so the guest can make accurate time calculations with the cycle counters. Signed-off-by: Zachary Amsden

In order to share the common code in tsc.c which does CPU Khz calibration, we need to make an accurate value of CPU speed available to the tsc.c code. This value loses a lot of precision in a VM because of the timing differences with real hardware, but we need it to be as precise as possible so the guest can make accurate time calculations with the cycle counters. Signed-off-by: Zachary Amsden

Add minimal paravirt support. The code aims for minimal impact on the native case. On the lock side we add one jump label (asm_goto) and 4 paravirt callee saved calls that default to NOPs. The only effects are the extra NOPs and some pointless MOVs to accomodate the calling convention. No register spills happen because of this (x86_64). On the unlock side we have one paravirt callee saved call,

The custom_sched_clock hook is broken. The result from sched_clock needs to be in nanoseconds, not in CPU cycles. The TSC is insufficient for this purpose, because TSC is poorly defined in a virtual environment, and mostly represents real world time instead of scheduled process time (which can be interrupted without notice when a virtual machine is descheduled). To make the scheduler

The custom_sched_clock hook is broken. The result from sched_clock needs to be in nanoseconds, not in CPU cycles. The TSC is insufficient for this purpose, because TSC is poorly defined in a virtual environment, and mostly represents real world time instead of scheduled process time (which can be interrupted without notice when a virtual machine is descheduled). To make the scheduler

Subject: Add a sched_clock paravirt_op The tsc-based get_scheduled_cycles interface is not a good match for Xen's runstate accounting, which reports everything in nanoseconds. This patch replaces this interface with a sched_clock interface, which matches both Xen and VMI's requirements. In order to do this, we: 1. replace get_scheduled_cycles with sched_clock 2. hoist cycles_2_ns

Subject: Add a sched_clock paravirt_op The tsc-based get_scheduled_cycles interface is not a good match for Xen's runstate accounting, which reports everything in nanoseconds. This patch replaces this interface with a sched_clock interface, which matches both Xen and VMI's requirements. In order to do this, we: 1. replace get_scheduled_cycles with sched_clock 2. hoist cycles_2_ns

To speed up paravirtualized spinlock handling when running on bare metal introduce a new pvops function "spin_unlock". This is a simple add instruction (possibly with lock prefix) when the kernel is running on bare metal. As the patched instruction includes a lock prefix in some configurations annotate this location to be subject to lock prefix patching. This is working even if