OpenCloudOS-Kernel/arch/powerpc/kernel/asm-offsets.c

775 lines
36 KiB
C
Raw Normal View History

/*
* This program is used to generate definitions needed by
* assembly language modules.
*
* We use the technique used in the OSF Mach kernel code:
* generate asm statements containing #defines,
* compile this file to assembler, and then extract the
* #defines from the assembly-language output.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/hrtimer.h>
#ifdef CONFIG_PPC64
#include <linux/time.h>
#include <linux/hardirq.h>
#endif
#include <linux/kbuild.h>
#include <asm/io.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/rtas.h>
#include <asm/vdso_datapage.h>
#include <asm/dbell.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/lppaca.h>
#include <asm/cache.h>
#include <asm/compat.h>
#include <asm/mmu.h>
#include <asm/hvcall.h>
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per core), whenever a CPU goes idle, we have to pull all the other hardware threads in the core out of the guest, because the H_CEDE hcall is handled in the kernel. This is inefficient. This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall in real mode. When a guest vcpu does an H_CEDE hcall, we now only exit to the kernel if all the other vcpus in the same core are also idle. Otherwise we mark this vcpu as napping, save state that could be lost in nap mode (mainly GPRs and FPRs), and execute the nap instruction. When the thread wakes up, because of a decrementer or external interrupt, we come back in at kvm_start_guest (from the system reset interrupt vector), find the `napping' flag set in the paca, and go to the resume path. This has some other ramifications. First, when starting a core, we now start all the threads, both those that are immediately runnable and those that are idle. This is so that we don't have to pull all the threads out of the guest when an idle thread gets a decrementer interrupt and wants to start running. In fact the idle threads will all start with the H_CEDE hcall returning; being idle they will just do another H_CEDE immediately and go to nap mode. This required some changes to kvmppc_run_core() and kvmppc_run_vcpu(). These functions have been restructured to make them simpler and clearer. We introduce a level of indirection in the wait queue that gets woken when external and decrementer interrupts get generated for a vcpu, so that we can have the 4 vcpus in a vcore using the same wait queue. We need this because the 4 vcpus are being handled by one thread. Secondly, when we need to exit from the guest to the kernel, we now have to generate an IPI for any napping threads, because an HDEC interrupt doesn't wake up a napping thread. Thirdly, we now need to be able to handle virtual external interrupts and decrementer interrupts becoming pending while a thread is napping, and deliver those interrupts to the guest when the thread wakes. This is done in kvmppc_cede_reentry, just before fast_guest_return. Finally, since we are not using the generic kvm_vcpu_block for book3s_hv, and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef from kvm_arch_vcpu_runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:42:46 +08:00
#include <asm/xics.h>
#endif
#ifdef CONFIG_PPC_POWERNV
#include <asm/opal.h>
#endif
#if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST)
#include <linux/kvm_host.h>
#endif
#if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
#include <asm/kvm_book3s.h>
#include <asm/kvm_ppc.h>
#endif
#ifdef CONFIG_PPC32
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
#include "head_booke.h"
#endif
#endif
#if defined(CONFIG_PPC_FSL_BOOK3E)
#include "../mm/mmu_decl.h"
#endif
int main(void)
{
DEFINE(THREAD, offsetof(struct task_struct, thread));
DEFINE(MM, offsetof(struct task_struct, mm));
DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
#ifdef CONFIG_PPC64
DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
powerpc: Allow perf_counters to access user memory at interrupt time This provides a mechanism to allow the perf_counters code to access user memory in a PMU interrupt routine. Such an access can cause various kinds of interrupt: SLB miss, MMU hash table miss, segment table miss, or TLB miss, depending on the processor. This commit only deals with 64-bit classic/server processors, which use an MMU hash table. 32-bit processors are already able to access user memory at interrupt time. Since we don't soft-disable on 32-bit, we avoid the possibility of reentering hash_page or the TLB miss handlers, since they run with interrupts disabled. On 64-bit processors, an SLB miss interrupt on a user address will update the slb_cache and slb_cache_ptr fields in the paca. This is OK except in the case where a PMU interrupt occurs in switch_slb, which also accesses those fields. To prevent this, we hard-disable interrupts in switch_slb. Interrupts are already soft-disabled at this point, and will get hard-enabled when they get soft-enabled later. This also reworks slb_flush_and_rebolt: to avoid hard-disabling twice, and to make sure that it clears the slb_cache_ptr when called from other callers than switch_slb, the existing routine is renamed to __slb_flush_and_rebolt, which is called by switch_slb and the new version of slb_flush_and_rebolt. Similarly, switch_stab (used on POWER3 and RS64 processors) gets a hard_irq_disable() to protect the per-cpu variables used there and in ste_allocate. If a MMU hashtable miss interrupt occurs, normally we would call hash_page to look up the Linux PTE for the address and create a HPTE. However, hash_page is fairly complex and takes some locks, so to avoid the possibility of deadlock, we check the preemption count to see if we are in a (pseudo-)NMI handler, and if so, we don't call hash_page but instead treat it like a bad access that will get reported up through the exception table mechanism. An interrupt whose handler runs even though the interrupt occurred when soft-disabled (such as the PMU interrupt) is considered a pseudo-NMI handler, which should use nmi_enter()/nmi_exit() rather than irq_enter()/irq_exit(). Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 13:17:54 +08:00
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
#else
rename thread_info to stack This finally renames the thread_info field in task structure to stack, so that the assumptions about this field are gone and archs have more freedom about placing the thread_info structure. Nonbroken archs which have a proper thread pointer can do the access to both current thread and task structure via a single pointer. It'll allow for a few more cleanups of the fork code, from which e.g. ia64 could benefit. Signed-off-by: Roman Zippel <zippel@linux-m68k.org> [akpm@linux-foundation.org: build fix] Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Andi Kleen <ak@muc.de> Cc: Chris Zankel <chris@zankel.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:35:17 +08:00
DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
#endif /* CONFIG_PPC64 */
DEFINE(KSP, offsetof(struct thread_struct, ksp));
DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
#ifdef CONFIG_BOOKE
DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
#endif
DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state));
DEFINE(THREAD_FPSAVEAREA, offsetof(struct thread_struct, fp_save_area));
DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr));
#ifdef CONFIG_ALTIVEC
DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state));
DEFINE(THREAD_VRSAVEAREA, offsetof(struct thread_struct, vr_save_area));
DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr));
#endif /* CONFIG_ALTIVEC */
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 12:07:18 +08:00
#ifdef CONFIG_VSX
DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr));
#endif /* CONFIG_VSX */
#ifdef CONFIG_PPC64
DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
#else /* CONFIG_PPC64 */
DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
#ifdef CONFIG_SPE
DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
DEFINE(THREAD_SPEFSCR, offsetof(struct thread_struct, spefscr));
DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
#endif /* CONFIG_SPE */
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, debug.dbcr0));
#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
#endif
#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
#endif
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct,
transact_vr));
DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
transact_vrsave));
DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct,
transact_fp));
/* Local pt_regs on stack for Transactional Memory funcs. */
DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
sizeof(struct pt_regs) + 16);
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
DEFINE(TI_TASK, offsetof(struct thread_info, task));
DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
#ifdef CONFIG_PPC64
DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size));
DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size));
DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page));
DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size));
DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size));
DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
/* paca */
DEFINE(PACA_SIZE, sizeof(struct paca_struct));
KVM: PPC: book3s_hv: Add support for PPC970-family processors This adds support for running KVM guests in supervisor mode on those PPC970 processors that have a usable hypervisor mode. Unfortunately, Apple G5 machines have supervisor mode disabled (MSR[HV] is forced to 1), but the YDL PowerStation does have a usable hypervisor mode. There are several differences between the PPC970 and POWER7 in how guests are managed. These differences are accommodated using the CPU_FTR_ARCH_201 (PPC970) and CPU_FTR_ARCH_206 (POWER7) CPU feature bits. Notably, on PPC970: * The LPCR, LPID or RMOR registers don't exist, and the functions of those registers are provided by bits in HID4 and one bit in HID0. * External interrupts can be directed to the hypervisor, but unlike POWER7 they are masked by MSR[EE] in non-hypervisor modes and use SRR0/1 not HSRR0/1. * There is no virtual RMA (VRMA) mode; the guest must use an RMO (real mode offset) area. * The TLB entries are not tagged with the LPID, so it is necessary to flush the whole TLB on partition switch. Furthermore, when switching partitions we have to ensure that no other CPU is executing the tlbie or tlbsync instructions in either the old or the new partition, otherwise undefined behaviour can occur. * The PMU has 8 counters (PMC registers) rather than 6. * The DSCR, PURR, SPURR, AMR, AMOR, UAMOR registers don't exist. * The SLB has 64 entries rather than 32. * There is no mediated external interrupt facility, so if we switch to a guest that has a virtual external interrupt pending but the guest has MSR[EE] = 0, we have to arrange to have an interrupt pending for it so that we can get control back once it re-enables interrupts. We do that by sending ourselves an IPI with smp_send_reschedule after hard-disabling interrupts. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:40:08 +08:00
DEFINE(PACA_LOCK_TOKEN, offsetof(struct paca_struct, lock_token));
DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start));
DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
DEFINE(PACACURRENT, offsetof(struct paca_struct, __current));
DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr));
DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
powerpc: Make it possible to move the interrupt handlers away from the kernel This changes the way that the exception prologs transfer control to the handlers in 64-bit kernels with the aim of making it possible to have the prologs separate from the main body of the kernel. Now, instead of computing the address of the handler by taking the top 32 bits of the paca address (to get the 0xc0000000........ part) and ORing in something in the bottom 16 bits, we get the base address of the kernel by doing a load from the paca and add an offset. This also replaces an mfmsr and an ori to compute the MSR value for the handler with a load from the paca. That makes it unnecessary to have a separate version of EXCEPTION_PROLOG_PSERIES that forces 64-bit mode. We can no longer use a direct branches in the exception prolog code, which means that the SLB miss handlers can't branch directly to .slb_miss_realmode any more. Instead we have to compute the address and do an indirect branch. This is conditional on CONFIG_RELOCATABLE; for non-relocatable kernels we use a direct branch as before. (A later change will allow CONFIG_RELOCATABLE to be set on 64-bit powerpc.) Since the secondary CPUs on pSeries start execution in the first 0x100 bytes of real memory and then have to get to wherever the kernel is, we can't use a direct branch to get there. Instead this changes __secondary_hold_spinloop from a flag to a function pointer. When it is set to a non-NULL value, the secondary CPUs jump to the function pointed to by that value. Finally this eliminates one code difference between 32-bit and 64-bit by making __secondary_hold be the text address of the secondary CPU spinloop rather than a function descriptor for it. Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-08-30 09:40:24 +08:00
DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase));
DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 15:27:59 +08:00
DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
[POWERPC] Introduce address space "slices" The basic issue is to be able to do what hugetlbfs does but with different page sizes for some other special filesystems; more specifically, my need is: - Huge pages - SPE local store mappings using 64K pages on a 4K base page size kernel on Cell - Some special 4K segments in 64K-page kernels for mapping a dodgy type of powerpc-specific infiniband hardware that requires 4K MMU mappings for various reasons I won't explain here. The main issues are: - To maintain/keep track of the page size per "segment" (as we can only have one page size per segment on powerpc, which are 256MB divisions of the address space). - To make sure special mappings stay within their allotted "segments" (including MAP_FIXED crap) - To make sure everybody else doesn't mmap/brk/grow_stack into a "segment" that is used for a special mapping Some of the necessary mechanisms to handle that were present in the hugetlbfs code, but mostly in ways not suitable for anything else. The patch relies on some changes to the generic get_unmapped_area() that just got merged. It still hijacks hugetlb callbacks here or there as the generic code hasn't been entirely cleaned up yet but that shouldn't be a problem. So what is a slice ? Well, I re-used the mechanism used formerly by our hugetlbfs implementation which divides the address space in "meta-segments" which I called "slices". The division is done using 256MB slices below 4G, and 1T slices above. Thus the address space is divided currently into 16 "low" slices and 16 "high" slices. (Special case: high slice 0 is the area between 4G and 1T). Doing so simplifies significantly the tracking of segments and avoids having to keep track of all the 256MB segments in the address space. While I used the "concepts" of hugetlbfs, I mostly re-implemented everything in a more generic way and "ported" hugetlbfs to it. Slices can have an associated page size, which is encoded in the mmu context and used by the SLB miss handler to set the segment sizes. The hash code currently doesn't care, it has a specific check for hugepages, though I might add a mechanism to provide per-slice hash mapping functions in the future. The slice code provide a pair of "generic" get_unmapped_area() (bottomup and topdown) functions that should work with any slice size. There is some trickiness here so I would appreciate people to have a look at the implementation of these and let me know if I got something wrong. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-05-08 14:27:27 +08:00
#ifdef CONFIG_PPC_MM_SLICES
DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
context.low_slices_psize));
DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
context.high_slices_psize));
DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
#endif /* CONFIG_PPC_MM_SLICES */
#ifdef CONFIG_PPC_BOOK3E
DEFINE(PACAPGD, offsetof(struct paca_struct, pgd));
DEFINE(PACA_KERNELPGD, offsetof(struct paca_struct, kernel_pgd));
DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
DEFINE(PACA_EXTLB, offsetof(struct paca_struct, extlb));
DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
DEFINE(PACA_EXCRIT, offsetof(struct paca_struct, excrit));
DEFINE(PACA_EXDBG, offsetof(struct paca_struct, exdbg));
DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack));
DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack));
DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack));
DEFINE(PACA_TCD_PTR, offsetof(struct paca_struct, tcd_ptr));
DEFINE(TCD_ESEL_NEXT,
offsetof(struct tlb_core_data, esel_next));
DEFINE(TCD_ESEL_MAX,
offsetof(struct tlb_core_data, esel_max));
DEFINE(TCD_ESEL_FIRST,
offsetof(struct tlb_core_data, esel_first));
#endif /* CONFIG_PPC_BOOK3E */
#ifdef CONFIG_PPC_STD_MMU_64
DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
#ifdef CONFIG_PPC_MM_SLICES
[POWERPC] Introduce address space "slices" The basic issue is to be able to do what hugetlbfs does but with different page sizes for some other special filesystems; more specifically, my need is: - Huge pages - SPE local store mappings using 64K pages on a 4K base page size kernel on Cell - Some special 4K segments in 64K-page kernels for mapping a dodgy type of powerpc-specific infiniband hardware that requires 4K MMU mappings for various reasons I won't explain here. The main issues are: - To maintain/keep track of the page size per "segment" (as we can only have one page size per segment on powerpc, which are 256MB divisions of the address space). - To make sure special mappings stay within their allotted "segments" (including MAP_FIXED crap) - To make sure everybody else doesn't mmap/brk/grow_stack into a "segment" that is used for a special mapping Some of the necessary mechanisms to handle that were present in the hugetlbfs code, but mostly in ways not suitable for anything else. The patch relies on some changes to the generic get_unmapped_area() that just got merged. It still hijacks hugetlb callbacks here or there as the generic code hasn't been entirely cleaned up yet but that shouldn't be a problem. So what is a slice ? Well, I re-used the mechanism used formerly by our hugetlbfs implementation which divides the address space in "meta-segments" which I called "slices". The division is done using 256MB slices below 4G, and 1T slices above. Thus the address space is divided currently into 16 "low" slices and 16 "high" slices. (Special case: high slice 0 is the area between 4G and 1T). Doing so simplifies significantly the tracking of segments and avoids having to keep track of all the 256MB segments in the address space. While I used the "concepts" of hugetlbfs, I mostly re-implemented everything in a more generic way and "ported" hugetlbfs to it. Slices can have an associated page size, which is encoded in the mmu context and used by the SLB miss handler to set the segment sizes. The hash code currently doesn't care, it has a specific check for hugepages, though I might add a mechanism to provide per-slice hash mapping functions in the future. The slice code provide a pair of "generic" get_unmapped_area() (bottomup and topdown) functions that should work with any slice size. There is some trickiness here so I would appreciate people to have a look at the implementation of these and let me know if I got something wrong. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-05-08 14:27:27 +08:00
DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
#else
DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
#endif /* CONFIG_PPC_MM_SLICES */
DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb));
DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
DEFINE(PACA_SLBSHADOWPTR, offsetof(struct paca_struct, slb_shadow_ptr));
DEFINE(SLBSHADOW_STACKVSID,
offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid));
DEFINE(SLBSHADOW_STACKESID,
offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid));
powerpc: Account time using timebase rather than PURR Currently, when CONFIG_VIRT_CPU_ACCOUNTING is enabled, we use the PURR register for measuring the user and system time used by processes, as well as other related times such as hardirq and softirq times. This turns out to be quite confusing for users because it means that a program will often be measured as taking less time when run on a multi-threaded processor (SMT2 or SMT4 mode) than it does when run on a single-threaded processor (ST mode), even though the program takes longer to finish. The discrepancy is accounted for as stolen time, which is also confusing, particularly when there are no other partitions running. This changes the accounting to use the timebase instead, meaning that the reported user and system times are the actual number of real-time seconds that the program was executing on the processor thread, regardless of which SMT mode the processor is in. Thus a program will generally show greater user and system times when run on a multi-threaded processor than on a single-threaded processor. On pSeries systems on POWER5 or later processors, we measure the stolen time (time when this partition wasn't running) using the hypervisor dispatch trace log. We check for new entries in the log on every entry from user mode and on every transition from kernel process context to soft or hard IRQ context (i.e. when account_system_vtime() gets called). So that we can correctly distinguish time stolen from user time and time stolen from system time, without having to check the log on every exit to user mode, we store separate timestamps for exit to user mode and entry from user mode. On systems that have a SPURR (POWER6 and POWER7), we read the SPURR in account_system_vtime() (as before), and then apportion the SPURR ticks since the last time we read it between scaled user time and scaled system time according to the relative proportions of user time and system time over the same interval. This avoids having to read the SPURR on every kernel entry and exit. On systems that have PURR but not SPURR (i.e., POWER5), we do the same using the PURR rather than the SPURR. This disables the DTL user interface in /sys/debug/kernel/powerpc/dtl for now since it conflicts with the use of the dispatch trace log by the time accounting code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-27 03:56:43 +08:00
DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
powerpc: Account time using timebase rather than PURR Currently, when CONFIG_VIRT_CPU_ACCOUNTING is enabled, we use the PURR register for measuring the user and system time used by processes, as well as other related times such as hardirq and softirq times. This turns out to be quite confusing for users because it means that a program will often be measured as taking less time when run on a multi-threaded processor (SMT2 or SMT4 mode) than it does when run on a single-threaded processor (ST mode), even though the program takes longer to finish. The discrepancy is accounted for as stolen time, which is also confusing, particularly when there are no other partitions running. This changes the accounting to use the timebase instead, meaning that the reported user and system times are the actual number of real-time seconds that the program was executing on the processor thread, regardless of which SMT mode the processor is in. Thus a program will generally show greater user and system times when run on a multi-threaded processor than on a single-threaded processor. On pSeries systems on POWER5 or later processors, we measure the stolen time (time when this partition wasn't running) using the hypervisor dispatch trace log. We check for new entries in the log on every entry from user mode and on every transition from kernel process context to soft or hard IRQ context (i.e. when account_system_vtime() gets called). So that we can correctly distinguish time stolen from user time and time stolen from system time, without having to check the log on every exit to user mode, we store separate timestamps for exit to user mode and entry from user mode. On systems that have a SPURR (POWER6 and POWER7), we read the SPURR in account_system_vtime() (as before), and then apportion the SPURR ticks since the last time we read it between scaled user time and scaled system time according to the relative proportions of user time and system time over the same interval. This avoids having to read the SPURR on every kernel entry and exit. On systems that have PURR but not SPURR (i.e., POWER5), we do the same using the PURR rather than the SPURR. This disables the DTL user interface in /sys/debug/kernel/powerpc/dtl for now since it conflicts with the use of the dispatch trace log by the time accounting code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-27 03:56:43 +08:00
DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
KVM: PPC: Handle some PAPR hcalls in the kernel This adds the infrastructure for handling PAPR hcalls in the kernel, either early in the guest exit path while we are still in real mode, or later once the MMU has been turned back on and we are in the full kernel context. The advantage of handling hcalls in real mode if possible is that we avoid two partition switches -- and this will become more important when we support SMT4 guests, since a partition switch means we have to pull all of the threads in the core out of the guest. The disadvantage is that we can only access the kernel linear mapping, not anything vmalloced or ioremapped, since the MMU is off. This also adds code to handle the following hcalls in real mode: H_ENTER Add an HPTE to the hashed page table H_REMOVE Remove an HPTE from the hashed page table H_READ Read HPTEs from the hashed page table H_PROTECT Change the protection bits in an HPTE H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table H_SET_DABR Set the data address breakpoint register Plus code to handle the following hcalls in the kernel: H_CEDE Idle the vcpu until an interrupt or H_PROD hcall arrives H_PROD Wake up a ceded vcpu H_REGISTER_VPA Register a virtual processor area (VPA) The code that runs in real mode has to be in the base kernel, not in the module, if KVM is compiled as a module. The real-mode code can only access the kernel linear mapping, not vmalloc or ioremap space. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:22:05 +08:00
DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count));
powerpc: Account time using timebase rather than PURR Currently, when CONFIG_VIRT_CPU_ACCOUNTING is enabled, we use the PURR register for measuring the user and system time used by processes, as well as other related times such as hardirq and softirq times. This turns out to be quite confusing for users because it means that a program will often be measured as taking less time when run on a multi-threaded processor (SMT2 or SMT4 mode) than it does when run on a single-threaded processor (ST mode), even though the program takes longer to finish. The discrepancy is accounted for as stolen time, which is also confusing, particularly when there are no other partitions running. This changes the accounting to use the timebase instead, meaning that the reported user and system times are the actual number of real-time seconds that the program was executing on the processor thread, regardless of which SMT mode the processor is in. Thus a program will generally show greater user and system times when run on a multi-threaded processor than on a single-threaded processor. On pSeries systems on POWER5 or later processors, we measure the stolen time (time when this partition wasn't running) using the hypervisor dispatch trace log. We check for new entries in the log on every entry from user mode and on every transition from kernel process context to soft or hard IRQ context (i.e. when account_system_vtime() gets called). So that we can correctly distinguish time stolen from user time and time stolen from system time, without having to check the log on every exit to user mode, we store separate timestamps for exit to user mode and entry from user mode. On systems that have a SPURR (POWER6 and POWER7), we read the SPURR in account_system_vtime() (as before), and then apportion the SPURR ticks since the last time we read it between scaled user time and scaled system time according to the relative proportions of user time and system time over the same interval. This avoids having to read the SPURR on every kernel entry and exit. On systems that have PURR but not SPURR (i.e., POWER5), we do the same using the PURR rather than the SPURR. This disables the DTL user interface in /sys/debug/kernel/powerpc/dtl for now since it conflicts with the use of the dispatch trace log by the time accounting code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-27 03:56:43 +08:00
DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
#endif /* CONFIG_PPC_STD_MMU_64 */
DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
powerpc/book3s: handle machine check in Linux host. Move machine check entry point into Linux. So far we were dependent on firmware to decode MCE error details and handover the high level info to OS. This patch introduces early machine check routine that saves the MCE information (srr1, srr0, dar and dsisr) to the emergency stack. We allocate stack frame on emergency stack and set the r1 accordingly. This allows us to be prepared to take another exception without loosing context. One thing to note here that, if we get another machine check while ME bit is off then we risk a checkstop. Hence we restrict ourselves to save only MCE information and register saved on PACA_EXMC save are before we turn the ME bit on. We use paca->in_mce flag to differentiate between first entry and nested machine check entry which helps proper use of emergency stack. We increment paca->in_mce every time we enter in early machine check handler and decrement it while leaving. When we enter machine check early handler first time (paca->in_mce == 0), we are sure nobody is using MC emergency stack and allocate a stack frame at the start of the emergency stack. During subsequent entry (paca->in_mce > 0), we know that r1 points inside emergency stack and we allocate separate stack frame accordingly. This prevents us from clobbering MCE information during nested machine checks. The early machine check handler changes are placed under CPU_FTR_HVMODE section. This makes sure that the early machine check handler will get executed only in hypervisor kernel. This is the code flow: Machine Check Interrupt | V 0x200 vector ME=0, IR=0, DR=0 | V +-----------------------------------------------+ |machine_check_pSeries_early: | ME=0, IR=0, DR=0 | Alloc frame on emergency stack | | Save srr1, srr0, dar and dsisr on stack | +-----------------------------------------------+ | (ME=1, IR=0, DR=0, RFID) | V machine_check_handle_early ME=1, IR=0, DR=0 | V +-----------------------------------------------+ | machine_check_early (r3=pt_regs) | ME=1, IR=0, DR=0 | Things to do: (in next patches) | | Flush SLB for SLB errors | | Flush TLB for TLB errors | | Decode and save MCE info | +-----------------------------------------------+ | (Fall through existing exception handler routine.) | V machine_check_pSerie ME=1, IR=0, DR=0 | (ME=1, IR=1, DR=1, RFID) | V machine_check_common ME=1, IR=1, DR=1 . . . Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-10-30 22:34:08 +08:00
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp));
DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce));
#endif
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default));
powerpc: Account time using timebase rather than PURR Currently, when CONFIG_VIRT_CPU_ACCOUNTING is enabled, we use the PURR register for measuring the user and system time used by processes, as well as other related times such as hardirq and softirq times. This turns out to be quite confusing for users because it means that a program will often be measured as taking less time when run on a multi-threaded processor (SMT2 or SMT4 mode) than it does when run on a single-threaded processor (ST mode), even though the program takes longer to finish. The discrepancy is accounted for as stolen time, which is also confusing, particularly when there are no other partitions running. This changes the accounting to use the timebase instead, meaning that the reported user and system times are the actual number of real-time seconds that the program was executing on the processor thread, regardless of which SMT mode the processor is in. Thus a program will generally show greater user and system times when run on a multi-threaded processor than on a single-threaded processor. On pSeries systems on POWER5 or later processors, we measure the stolen time (time when this partition wasn't running) using the hypervisor dispatch trace log. We check for new entries in the log on every entry from user mode and on every transition from kernel process context to soft or hard IRQ context (i.e. when account_system_vtime() gets called). So that we can correctly distinguish time stolen from user time and time stolen from system time, without having to check the log on every exit to user mode, we store separate timestamps for exit to user mode and entry from user mode. On systems that have a SPURR (POWER6 and POWER7), we read the SPURR in account_system_vtime() (as before), and then apportion the SPURR ticks since the last time we read it between scaled user time and scaled system time according to the relative proportions of user time and system time over the same interval. This avoids having to read the SPURR on every kernel entry and exit. On systems that have PURR but not SPURR (i.e., POWER5), we do the same using the PURR rather than the SPURR. This disables the DTL user interface in /sys/debug/kernel/powerpc/dtl for now since it conflicts with the use of the dispatch trace log by the time accounting code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-27 03:56:43 +08:00
DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
powerpc/booke64: Use SPRG7 for VDSO Previously SPRG3 was marked for use by both VDSO and critical interrupts (though critical interrupts were not fully implemented). In commit 8b64a9dfb091f1eca8b7e58da82f1e7d1d5fe0ad ("powerpc/booke64: Use SPRG0/3 scratch for bolted TLB miss & crit int"), Mihai Caraman made an attempt to resolve this conflict by restoring the VDSO value early in the critical interrupt, but this has some issues: - It's incompatible with EXCEPTION_COMMON which restores r13 from the by-then-overwritten scratch (this cost me some debugging time). - It forces critical exceptions to be a special case handled differently from even machine check and debug level exceptions. - It didn't occur to me that it was possible to make this work at all (by doing a final "ld r13, PACA_EXCRIT+EX_R13(r13)") until after I made (most of) this patch. :-) It might be worth investigating using a load rather than SPRG on return from all exceptions (except TLB misses where the scratch never leaves the SPRG) -- it could save a few cycles. Until then, let's stick with SPRG for all exceptions. Since we cannot use SPRG4-7 for scratch without corrupting the state of a KVM guest, move VDSO to SPRG7 on book3e. Since neither SPRG4-7 nor critical interrupts exist on book3s, SPRG3 is still used for VDSO there. Signed-off-by: Scott Wood <scottwood@freescale.com> Cc: Mihai Caraman <mihai.caraman@freescale.com> Cc: Anton Blanchard <anton@samba.org> Cc: Paul Mackerras <paulus@samba.org> Cc: kvm-ppc@vger.kernel.org
2014-03-11 06:29:38 +08:00
DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
#endif /* CONFIG_PPC64 */
/* RTAS */
DEFINE(RTASBASE, offsetof(struct rtas_t, base));
DEFINE(RTASENTRY, offsetof(struct rtas_t, entry));
/* Interrupt register frame */
DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
#ifdef CONFIG_PPC64
/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
/* hcall statistics */
DEFINE(HCALL_STAT_SIZE, sizeof(struct hcall_stats));
DEFINE(HCALL_STAT_CALLS, offsetof(struct hcall_stats, num_calls));
DEFINE(HCALL_STAT_TB, offsetof(struct hcall_stats, tb_total));
DEFINE(HCALL_STAT_PURR, offsetof(struct hcall_stats, purr_total));
#endif /* CONFIG_PPC64 */
DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0]));
DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1]));
DEFINE(GPR2, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[2]));
DEFINE(GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[3]));
DEFINE(GPR4, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[4]));
DEFINE(GPR5, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[5]));
DEFINE(GPR6, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[6]));
DEFINE(GPR7, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[7]));
DEFINE(GPR8, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[8]));
DEFINE(GPR9, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[9]));
DEFINE(GPR10, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[10]));
DEFINE(GPR11, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[11]));
DEFINE(GPR12, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[12]));
DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13]));
#ifndef CONFIG_PPC64
DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14]));
DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15]));
DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16]));
DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17]));
DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18]));
DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19]));
DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20]));
DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21]));
DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22]));
DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23]));
DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24]));
DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25]));
DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26]));
DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27]));
DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28]));
DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29]));
DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30]));
DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31]));
#endif /* CONFIG_PPC64 */
/*
* Note: these symbols include _ because they overlap with special
* register names
*/
DEFINE(_NIP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, nip));
DEFINE(_MSR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, msr));
DEFINE(_CTR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ctr));
DEFINE(_LINK, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, link));
DEFINE(_CCR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ccr));
DEFINE(_XER, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, xer));
DEFINE(_DAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
DEFINE(_DSISR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
DEFINE(ORIG_GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, orig_gpr3));
DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result));
DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap));
#ifndef CONFIG_PPC64
DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq));
/*
* The PowerPC 400-class & Book-E processors have neither the DAR
* nor the DSISR SPRs. Hence, we overload them to hold the similar
* DEAR and ESR SPRs for such processors. For critical interrupts
* we use them to hold SRR0 and SRR1.
*/
DEFINE(_DEAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
DEFINE(_ESR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
#else /* CONFIG_PPC64 */
DEFINE(SOFTE, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, softe));
/* These _only_ to be used with {PROM,RTAS}_FRAME_SIZE!!! */
DEFINE(_SRR0, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs));
DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_PPC32)
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
/* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */
DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1));
DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2));
DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3));
DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6));
DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7));
DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0));
DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1));
DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0));
DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1));
DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0));
DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1));
DEFINE(SAVED_KSP_LIMIT, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, saved_ksp_limit));
#endif
#endif
DEFINE(CLONE_VM, CLONE_VM);
DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);
#ifndef CONFIG_PPC64
DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
#endif /* ! CONFIG_PPC64 */
/* About the CPU features table */
DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore));
DEFINE(pbe_address, offsetof(struct pbe, address));
DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
DEFINE(pbe_next, offsetof(struct pbe, next));
#ifndef CONFIG_PPC64
DEFINE(TASK_SIZE, TASK_SIZE);
DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
#endif /* ! CONFIG_PPC64 */
/* datapage offsets for use by vdso */
DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp));
DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec));
DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs));
DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec));
DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count));
DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest));
DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime));
DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
powerpc: Rework VDSO gettimeofday to prevent time going backwards Currently it is possible for userspace to see the result of gettimeofday() going backwards by 1 microsecond, assuming that userspace is using the gettimeofday() in the VDSO. The VDSO gettimeofday() algorithm computes the time in "xsecs", which are units of 2^-20 seconds, or approximately 0.954 microseconds, using the algorithm now = (timebase - tb_orig_stamp) * tb_to_xs + stamp_xsec and then converts the time in xsecs to seconds and microseconds. The kernel updates the tb_orig_stamp and stamp_xsec values every tick in update_vsyscall(). If the length of the tick is not an integer number of xsecs, then some precision is lost in converting the current time to xsecs. For example, with CONFIG_HZ=1000, the tick is 1ms long, which is 1048.576 xsecs. That means that stamp_xsec will advance by either 1048 or 1049 on each tick. With the right conditions, it is possible for userspace to get (timebase - tb_orig_stamp) * tb_to_xs being 1049 if the kernel is slightly late in updating the vdso_datapage, and then for stamp_xsec to advance by 1048 when the kernel does update it, and for userspace to then see (timebase - tb_orig_stamp) * tb_to_xs being zero due to integer truncation. The result is that time appears to go backwards by 1 microsecond. To fix this we change the VDSO gettimeofday to use a new field in the VDSO datapage which stores the nanoseconds part of the time as a fractional number of seconds in a 0.32 binary fraction format. (Or put another way, as a 32-bit number in units of 0.23283 ns.) This is convenient because we can use the mulhwu instruction to convert it to either microseconds or nanoseconds. Since it turns out that computing the time of day using this new field is simpler than either using stamp_xsec (as gettimeofday does) or stamp_xtime.tv_nsec (as clock_gettime does), this converts both gettimeofday and clock_gettime to use the new field. The existing __do_get_tspec function is converted to use the new field and take a parameter in r7 that indicates the desired resolution, 1,000,000 for microseconds or 1,000,000,000 for nanoseconds. The __do_get_xsec function is then unused and is deleted. The new algorithm is now = ((timebase - tb_orig_stamp) << 12) * tb_to_xs + (stamp_xtime_seconds << 32) + stamp_sec_fraction with 'now' in units of 2^-32 seconds. That is then converted to seconds and either microseconds or nanoseconds with seconds = now >> 32 partseconds = ((now & 0xffffffff) * resolution) >> 32 The 32-bit VDSO code also makes a further simplification: it ignores the bottom 32 bits of the tb_to_xs value, which is a 0.64 format binary fraction. Doing so gets rid of 4 multiply instructions. Assuming a timebase frequency of 1GHz or less and an update interval of no more than 10ms, the upper 32 bits of tb_to_xs will be at least 4503599, so the error from ignoring the low 32 bits will be at most 2.2ns, which is more than an order of magnitude less than the time taken to do gettimeofday or clock_gettime on our fastest processors, so there is no possibility of seeing inconsistent values due to this. This also moves update_gtod() down next to its only caller, and makes update_vsyscall use the time passed in via the wall_time argument rather than accessing xtime directly. At present, wall_time always points to xtime, but that could change in future. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-06-21 03:03:08 +08:00
DEFINE(STAMP_SEC_FRAC, offsetof(struct vdso_data, stamp_sec_fraction));
DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
DEFINE(CFG_DCACHE_LOGBLOCKSZ, offsetof(struct vdso_data, dcache_log_block_size));
#ifdef CONFIG_PPC64
DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64));
DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));
DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec));
DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec));
DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec));
DEFINE(TSPC64_TV_SEC, offsetof(struct timespec, tv_sec));
DEFINE(TSPC64_TV_NSEC, offsetof(struct timespec, tv_nsec));
DEFINE(TSPC32_TV_SEC, offsetof(struct compat_timespec, tv_sec));
DEFINE(TSPC32_TV_NSEC, offsetof(struct compat_timespec, tv_nsec));
#else
DEFINE(TVAL32_TV_SEC, offsetof(struct timeval, tv_sec));
DEFINE(TVAL32_TV_USEC, offsetof(struct timeval, tv_usec));
DEFINE(TSPC32_TV_SEC, offsetof(struct timespec, tv_sec));
DEFINE(TSPC32_TV_NSEC, offsetof(struct timespec, tv_nsec));
#endif
/* timeval/timezone offsets for use by vdso */
DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
/* Other bits used by the vdso */
DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
#ifdef CONFIG_BUG
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
#endif
DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
DEFINE(PTE_SIZE, sizeof(pte_t));
#ifdef CONFIG_KVM
DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid));
DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fp.fpr));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#ifdef CONFIG_ALTIVEC
DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr.vr));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#endif
DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
#ifdef CONFIG_PPC_BOOK3S
DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar));
#endif
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr));
DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0));
DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1));
DEFINE(VCPU_SPRG0, offsetof(struct kvm_vcpu, arch.shregs.sprg0));
DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
KVM: PPC: Book3S HV: Accumulate timing information for real-mode code This reads the timebase at various points in the real-mode guest entry/exit code and uses that to accumulate total, minimum and maximum time spent in those parts of the code. Currently these times are accumulated per vcpu in 5 parts of the code: * rm_entry - time taken from the start of kvmppc_hv_entry() until just before entering the guest. * rm_intr - time from when we take a hypervisor interrupt in the guest until we either re-enter the guest or decide to exit to the host. This includes time spent handling hcalls in real mode. * rm_exit - time from when we decide to exit the guest until the return from kvmppc_hv_entry(). * guest - time spend in the guest * cede - time spent napping in real mode due to an H_CEDE hcall while other threads in the same vcore are active. These times are exposed in debugfs in a directory per vcpu that contains a file called "timings". This file contains one line for each of the 5 timings above, with the name followed by a colon and 4 numbers, which are the count (number of times the code has been executed), the total time, the minimum time, and the maximum time, all in nanoseconds. The overhead of the extra code amounts to about 30ns for an hcall that is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since production environments may not wish to incur this overhead, the new code is conditional on a new config symbol, CONFIG_KVM_BOOK3S_HV_EXIT_TIMING. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 11:21:02 +08:00
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#endif
DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
DEFINE(VCPU_SHARED_SPRG7, offsetof(struct kvm_vcpu_arch_shared, sprg7));
DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1));
DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
DEFINE(VCPU_SHAREDBE, offsetof(struct kvm_vcpu, arch.shared_big_endian));
#endif
DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0));
DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1));
DEFINE(VCPU_SHARED_MAS2, offsetof(struct kvm_vcpu_arch_shared, mas2));
DEFINE(VCPU_SHARED_MAS7_3, offsetof(struct kvm_vcpu_arch_shared, mas7_3));
DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
/* book3s */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations When we change or remove a HPT (hashed page table) entry, we can do either a global TLB invalidation (tlbie) that works across the whole machine, or a local invalidation (tlbiel) that only affects this core. Currently we do local invalidations if the VM has only one vcpu or if the guest requests it with the H_LOCAL flag, though the guest Linux kernel currently doesn't ever use H_LOCAL. Then, to cope with the possibility that vcpus moving around to different physical cores might expose stale TLB entries, there is some code in kvmppc_hv_entry to flush the whole TLB of entries for this VM if either this vcpu is now running on a different physical core from where it last ran, or if this physical core last ran a different vcpu. There are a number of problems on POWER7 with this as it stands: - The TLB invalidation is done per thread, whereas it only needs to be done per core, since the TLB is shared between the threads. - With the possibility of the host paging out guest pages, the use of H_LOCAL by an SMP guest is dangerous since the guest could possibly retain and use a stale TLB entry pointing to a page that had been removed from the guest. - The TLB invalidations that we do when a vcpu moves from one physical core to another are unnecessary in the case of an SMP guest that isn't using H_LOCAL. - The optimization of using local invalidations rather than global should apply to guests with one virtual core, not just one vcpu. (None of this applies on PPC970, since there we always have to invalidate the whole TLB when entering and leaving the guest, and we can't support paging out guest memory.) To fix these problems and simplify the code, we now maintain a simple cpumask of which cpus need to flush the TLB on entry to the guest. (This is indexed by cpu, though we only ever use the bits for thread 0 of each core.) Whenever we do a local TLB invalidation, we set the bits for every cpu except the bit for thread 0 of the core that we're currently running on. Whenever we enter a guest, we test and clear the bit for our core, and flush the TLB if it was set. On initial startup of the VM, and when resetting the HPT, we set all the bits in the need_tlb_flush cpumask, since any core could potentially have stale TLB entries from the previous VM to use the same LPID, or the previous contents of the HPT. Then, we maintain a count of the number of online virtual cores, and use that when deciding whether to use a local invalidation rather than the number of online vcpus. The code to make that decision is extracted out into a new function, global_invalidates(). For multi-core guests on POWER7 (i.e. when we are using mmu notifiers), we now never do local invalidations regardless of the H_LOCAL flag. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2012-11-22 07:28:08 +08:00
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling This provides a way for userspace controls which sPAPR hcalls get handled in the kernel. Each hcall can be individually enabled or disabled for in-kernel handling, except for H_RTAS. The exception for H_RTAS is because userspace can already control whether individual RTAS functions are handled in-kernel or not via the KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for H_RTAS is out of the normal sequence of hcall numbers. Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM. The args field of the struct kvm_enable_cap specifies the hcall number in args[0] and the enable/disable flag in args[1]; 0 means disable in-kernel handling (so that the hcall will always cause an exit to userspace) and 1 means enable. Enabling or disabling in-kernel handling of an hcall is effective across the whole VM. The ability for KVM_ENABLE_CAP to be used on a VM file descriptor on PowerPC is new, added by this commit. The KVM_CAP_ENABLE_CAP_VM capability advertises that this ability exists. When a VM is created, an initial set of hcalls are enabled for in-kernel handling. The set that is enabled is the set that have an in-kernel implementation at this point. Any new hcall implementations from this point onwards should not be added to the default set without a good reason. No distinction is made between real-mode and virtual-mode hcall implementations; the one setting controls them both. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-06-02 09:02:59 +08:00
DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests This adds infrastructure which will be needed to allow book3s_hv KVM to run on older POWER processors, including PPC970, which don't support the Virtual Real Mode Area (VRMA) facility, but only the Real Mode Offset (RMO) facility. These processors require a physically contiguous, aligned area of memory for each guest. When the guest does an access in real mode (MMU off), the address is compared against a limit value, and if it is lower, the address is ORed with an offset value (from the Real Mode Offset Register (RMOR)) and the result becomes the real address for the access. The size of the RMA has to be one of a set of supported values, which usually includes 64MB, 128MB, 256MB and some larger powers of 2. Since we are unlikely to be able to allocate 64MB or more of physically contiguous memory after the kernel has been running for a while, we allocate a pool of RMAs at boot time using the bootmem allocator. The size and number of the RMAs can be set using the kvm_rma_size=xx and kvm_rma_count=xx kernel command line options. KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability of the pool of preallocated RMAs. The capability value is 1 if the processor can use an RMA but doesn't require one (because it supports the VRMA facility), or 2 if the processor requires an RMA for each guest. This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the pool and returns a file descriptor which can be used to map the RMA. It also returns the size of the RMA in the argument structure. Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION ioctl calls from userspace. To cope with this, we now preallocate the kvm->arch.ram_pginfo array when the VM is created with a size sufficient for up to 64GB of guest memory. Subsequently we will get rid of this array and use memory associated with each memslot instead. This moves most of the code that translates the user addresses into host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level to kvmppc_core_prepare_memory_region. Also, instead of having to look up the VMA for each page in order to check the page size, we now check that the pages we get are compound pages of 16MB. However, if we are adding memory that is mapped to an RMA, we don't bother with calling get_user_pages_fast and instead just offset from the base pfn for the RMA. Typically the RMA gets added after vcpus are created, which makes it inconvenient to have the LPCR (logical partition control register) value in the vcpu->arch struct, since the LPCR controls whether the processor uses RMA or VRMA for the guest. This moves the LPCR value into the kvm->arch struct and arranges for the MER (mediated external request) bit, which is the only bit that varies between vcpus, to be set in assembly code when going into the guest if there is a pending external interrupt request. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:25:44 +08:00
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications done by the host to the virtual processor areas (VPAs) and dispatch trace logs (DTLs) registered by the guest. This is because those modifications are done either in real mode or in the host kernel context, and in neither case does the access go through the guest's HPT, and thus no change (C) bit gets set in the guest's HPT. However, the changes done by the host do need to be tracked so that the modified pages get transferred when doing live migration. In order to track these modifications, this adds a dirty flag to the struct representing the VPA/DTL areas, and arranges to set the flag when the VPA/DTL gets modified by the host. Then, when we are collecting the dirty log, we also check the dirty flags for the VPA and DTL for each vcpu and set the relevant bit in the dirty log if necessary. Doing this also means we now need to keep track of the guest physical address of the VPA/DTL areas. So as not to lose track of modifications to a VPA/DTL area when it gets unregistered, or when a new area gets registered in its place, we need to transfer the dirty state to the rmap chain. This adds code to kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify that code, we now require that all VPA, DTL and SLB shadow buffer areas fit within a single host page. Guests already comply with this requirement because pHyp requires that these areas not cross a 4k boundary. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-04-19 03:51:04 +08:00
DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
DEFINE(VCPU_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst));
KVM: PPC: Book3S HV: Make use of unused threads when running guests When running a virtual core of a guest that is configured with fewer threads per core than the physical cores have, the extra physical threads are currently unused. This makes it possible to use them to run one or more other virtual cores from the same guest when certain conditions are met. This applies on POWER7, and on POWER8 to guests with one thread per virtual core. (It doesn't apply to POWER8 guests with multiple threads per vcore because they require a 1-1 virtual to physical thread mapping in order to be able to use msgsndp and the TIR.) The idea is that we maintain a list of preempted vcores for each physical cpu (i.e. each core, since the host runs single-threaded). Then, when a vcore is about to run, it checks to see if there are any vcores on the list for its physical cpu that could be piggybacked onto this vcore's execution. If so, those additional vcores are put into state VCORE_PIGGYBACK and their runnable VCPU threads are started as well as the original vcore, which is called the master vcore. After the vcores have exited the guest, the extra ones are put back onto the preempted list if any of their VCPUs are still runnable and not idle. This means that vcpu->arch.ptid is no longer necessarily the same as the physical thread that the vcpu runs on. In order to make it easier for code that wants to send an IPI to know which CPU to target, we now store that in a new field in struct vcpu_arch, called thread_cpu. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Tested-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2015-06-24 19:18:03 +08:00
DEFINE(VCPU_CPU, offsetof(struct kvm_vcpu, cpu));
DEFINE(VCPU_THREAD_CPU, offsetof(struct kvm_vcpu, arch.thread_cpu));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#endif
#ifdef CONFIG_PPC_BOOK3S
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
DEFINE(VCPU_IAMR, offsetof(struct kvm_vcpu, arch.iamr));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
KVM: PPC: Book3S HV: Add support for DABRX register on POWER7 The DABRX (DABR extension) register on POWER7 processors provides finer control over which accesses cause a data breakpoint interrupt. It contains 3 bits which indicate whether to enable accesses in user, kernel and hypervisor modes respectively to cause data breakpoint interrupts, plus one bit that enables both real mode and virtual mode accesses to cause interrupts. Currently, KVM sets DABRX to allow both kernel and user accesses to cause interrupts while in the guest. This adds support for the guest to specify other values for DABRX. PAPR defines a H_SET_XDABR hcall to allow the guest to set both DABR and DABRX with one call. This adds a real-mode implementation of H_SET_XDABR, which shares most of its code with the existing H_SET_DABR implementation. To support this, we add a per-vcpu field to store the DABRX value plus code to get and set it via the ONE_REG interface. For Linux guests to use this new hcall, userspace needs to add "hcall-xdabr" to the set of strings in the /chosen/hypertas-functions property in the device tree. If userspace does this and then migrates the guest to a host where the kernel doesn't include this patch, then userspace will need to implement H_SET_XDABR by writing the specified DABR value to the DABR using the ONE_REG interface. In that case, the old kernel will set DABRX to DABRX_USER | DABRX_KERNEL. That should still work correctly, at least for Linux guests, since Linux guests cope with getting data breakpoint interrupts in modes that weren't requested by just ignoring the interrupt, and Linux guests never set DABRX_BTI. The other thing this does is to make H_SET_DABR and H_SET_XDABR work on POWER8, which has the DAWR and DAWRX instead of DABR/X. Guests that know about POWER8 should use H_SET_MODE rather than H_SET_[X]DABR, but guests running in POWER7 compatibility mode will still use H_SET_[X]DABR. For them, this adds the logic to convert DABR/X values into DAWR/X values on POWER8. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 18:25:29 +08:00
DEFINE(VCPU_DABRX, offsetof(struct kvm_vcpu, arch.dabrx));
DEFINE(VCPU_DAWR, offsetof(struct kvm_vcpu, arch.dawr));
DEFINE(VCPU_DAWRX, offsetof(struct kvm_vcpu, arch.dawrx));
DEFINE(VCPU_CIABR, offsetof(struct kvm_vcpu, arch.ciabr));
DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests This adds infrastructure which will be needed to allow book3s_hv KVM to run on older POWER processors, including PPC970, which don't support the Virtual Real Mode Area (VRMA) facility, but only the Real Mode Offset (RMO) facility. These processors require a physically contiguous, aligned area of memory for each guest. When the guest does an access in real mode (MMU off), the address is compared against a limit value, and if it is lower, the address is ORed with an offset value (from the Real Mode Offset Register (RMOR)) and the result becomes the real address for the access. The size of the RMA has to be one of a set of supported values, which usually includes 64MB, 128MB, 256MB and some larger powers of 2. Since we are unlikely to be able to allocate 64MB or more of physically contiguous memory after the kernel has been running for a while, we allocate a pool of RMAs at boot time using the bootmem allocator. The size and number of the RMAs can be set using the kvm_rma_size=xx and kvm_rma_count=xx kernel command line options. KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability of the pool of preallocated RMAs. The capability value is 1 if the processor can use an RMA but doesn't require one (because it supports the VRMA facility), or 2 if the processor requires an RMA for each guest. This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the pool and returns a file descriptor which can be used to map the RMA. It also returns the size of the RMA in the argument structure. Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION ioctl calls from userspace. To cope with this, we now preallocate the kvm->arch.ram_pginfo array when the VM is created with a size sufficient for up to 64GB of guest memory. Subsequently we will get rid of this array and use memory associated with each memslot instead. This moves most of the code that translates the user addresses into host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level to kvmppc_core_prepare_memory_region. Also, instead of having to look up the VMA for each page in order to check the page size, we now check that the pages we get are compound pages of 16MB. However, if we are adding memory that is mapped to an RMA, we don't bother with calling get_user_pages_fast and instead just offset from the base pfn for the RMA. Typically the RMA gets added after vcpus are created, which makes it inconvenient to have the LPCR (logical partition control register) value in the vcpu->arch struct, since the LPCR controls whether the processor uses RMA or VRMA for the guest. This moves the LPCR value into the kvm->arch struct and arranges for the MER (mediated external request) bit, which is the only bit that varies between vcpus, to be set in assembly code when going into the guest if there is a pending external interrupt request. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:25:44 +08:00
DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per core), whenever a CPU goes idle, we have to pull all the other hardware threads in the core out of the guest, because the H_CEDE hcall is handled in the kernel. This is inefficient. This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall in real mode. When a guest vcpu does an H_CEDE hcall, we now only exit to the kernel if all the other vcpus in the same core are also idle. Otherwise we mark this vcpu as napping, save state that could be lost in nap mode (mainly GPRs and FPRs), and execute the nap instruction. When the thread wakes up, because of a decrementer or external interrupt, we come back in at kvm_start_guest (from the system reset interrupt vector), find the `napping' flag set in the paca, and go to the resume path. This has some other ramifications. First, when starting a core, we now start all the threads, both those that are immediately runnable and those that are idle. This is so that we don't have to pull all the threads out of the guest when an idle thread gets a decrementer interrupt and wants to start running. In fact the idle threads will all start with the H_CEDE hcall returning; being idle they will just do another H_CEDE immediately and go to nap mode. This required some changes to kvmppc_run_core() and kvmppc_run_vcpu(). These functions have been restructured to make them simpler and clearer. We introduce a level of indirection in the wait queue that gets woken when external and decrementer interrupts get generated for a vcpu, so that we can have the 4 vcpus in a vcore using the same wait queue. We need this because the 4 vcpus are being handled by one thread. Secondly, when we need to exit from the guest to the kernel, we now have to generate an IPI for any napping threads, because an HDEC interrupt doesn't wake up a napping thread. Thirdly, we now need to be able to handle virtual external interrupts and decrementer interrupts becoming pending while a thread is napping, and deliver those interrupts to the guest when the thread wakes. This is done in kvmppc_cede_reentry, just before fast_guest_return. Finally, since we are not using the generic kvm_vcpu_block for book3s_hv, and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef from kvm_arch_vcpu_runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:42:46 +08:00
DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded));
DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
DEFINE(VCPU_SPMC, offsetof(struct kvm_vcpu, arch.spmc));
DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar));
DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar));
DEFINE(VCPU_SIER, offsetof(struct kvm_vcpu, arch.sier));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr));
DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
DEFINE(VCPU_BESCR, offsetof(struct kvm_vcpu, arch.bescr));
DEFINE(VCPU_CSIGR, offsetof(struct kvm_vcpu, arch.csigr));
DEFINE(VCPU_TACR, offsetof(struct kvm_vcpu, arch.tacr));
DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
KVM: PPC: Book3S PR: Keep volatile reg values in vcpu rather than shadow_vcpu Currently PR-style KVM keeps the volatile guest register values (R0 - R13, CR, LR, CTR, XER, PC) in a shadow_vcpu struct rather than the main kvm_vcpu struct. For 64-bit, the shadow_vcpu exists in two places, a kmalloc'd struct and in the PACA, and it gets copied back and forth in kvmppc_core_vcpu_load/put(), because the real-mode code can't rely on being able to access the kmalloc'd struct. This changes the code to copy the volatile values into the shadow_vcpu as one of the last things done before entering the guest. Similarly the values are copied back out of the shadow_vcpu to the kvm_vcpu immediately after exiting the guest. We arrange for interrupts to be still disabled at this point so that we can't get preempted on 64-bit and end up copying values from the wrong PACA. This means that the accessor functions in kvm_book3s.h for these registers are greatly simplified, and are same between PR and HV KVM. In places where accesses to shadow_vcpu fields are now replaced by accesses to the kvm_vcpu, we can also remove the svcpu_get/put pairs. Finally, on 64-bit, we don't need the kmalloc'd struct at all any more. With this, the time to read the PVR one million times in a loop went from 567.7ms to 575.5ms (averages of 6 values), an increase of about 1.4% for this worse-case test for guest entries and exits. The standard deviation of the measurements is about 11ms, so the difference is only marginally significant statistically. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:43 +08:00
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
KVM: PPC: Allow book3s_hv guests to use SMT processor modes This lifts the restriction that book3s_hv guests can only run one hardware thread per core, and allows them to use up to 4 threads per core on POWER7. The host still has to run single-threaded. This capability is advertised to qemu through a new KVM_CAP_PPC_SMT capability. The return value of the ioctl querying this capability is the number of vcpus per virtual CPU core (vcore), currently 4. To use this, the host kernel should be booted with all threads active, and then all the secondary threads should be offlined. This will put the secondary threads into nap mode. KVM will then wake them from nap mode and use them for running guest code (while they are still offline). To wake the secondary threads, we send them an IPI using a new xics_wake_cpu() function, implemented in arch/powerpc/sysdev/xics/icp-native.c. In other words, at this stage we assume that the platform has a XICS interrupt controller and we are using icp-native.c to drive it. Since the woken thread will need to acknowledge and clear the IPI, we also export the base physical address of the XICS registers using kvmppc_set_xics_phys() for use in the low-level KVM book3s code. When a vcpu is created, it is assigned to a virtual CPU core. The vcore number is obtained by dividing the vcpu number by the number of threads per core in the host. This number is exported to userspace via the KVM_CAP_PPC_SMT capability. If qemu wishes to run the guest in single-threaded mode, it should make all vcpu numbers be multiples of the number of threads per core. We distinguish three states of a vcpu: runnable (i.e., ready to execute the guest), blocked (that is, idle), and busy in host. We currently implement a policy that the vcore can run only when all its threads are runnable or blocked. This way, if a vcpu needs to execute elsewhere in the kernel or in qemu, it can do so without being starved of CPU by the other vcpus. When a vcore starts to run, it executes in the context of one of the vcpu threads. The other vcpu threads all go to sleep and stay asleep until something happens requiring the vcpu thread to return to qemu, or to wake up to run the vcore (this can happen when another vcpu thread goes from busy in host state to blocked). It can happen that a vcpu goes from blocked to runnable state (e.g. because of an interrupt), and the vcore it belongs to is already running. In that case it can start to run immediately as long as the none of the vcpus in the vcore have started to exit the guest. We send the next free thread in the vcore an IPI to get it to start to execute the guest. It synchronizes with the other threads via the vcore->entry_exit_count field to make sure that it doesn't go into the guest if the other vcpus are exiting by the time that it is ready to actually enter the guest. Note that there is no fixed relationship between the hardware thread number and the vcpu number. Hardware threads are assigned to vcpus as they become runnable, so we will always use the lower-numbered hardware threads in preference to higher-numbered threads if not all the vcpus in the vcore are runnable, regardless of which vcpus are runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:23:08 +08:00
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per core), whenever a CPU goes idle, we have to pull all the other hardware threads in the core out of the guest, because the H_CEDE hcall is handled in the kernel. This is inefficient. This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall in real mode. When a guest vcpu does an H_CEDE hcall, we now only exit to the kernel if all the other vcpus in the same core are also idle. Otherwise we mark this vcpu as napping, save state that could be lost in nap mode (mainly GPRs and FPRs), and execute the nap instruction. When the thread wakes up, because of a decrementer or external interrupt, we come back in at kvm_start_guest (from the system reset interrupt vector), find the `napping' flag set in the paca, and go to the resume path. This has some other ramifications. First, when starting a core, we now start all the threads, both those that are immediately runnable and those that are idle. This is so that we don't have to pull all the threads out of the guest when an idle thread gets a decrementer interrupt and wants to start running. In fact the idle threads will all start with the H_CEDE hcall returning; being idle they will just do another H_CEDE immediately and go to nap mode. This required some changes to kvmppc_run_core() and kvmppc_run_vcpu(). These functions have been restructured to make them simpler and clearer. We introduce a level of indirection in the wait queue that gets woken when external and decrementer interrupts get generated for a vcpu, so that we can have the 4 vcpus in a vcore using the same wait queue. We need this because the 4 vcpus are being handled by one thread. Secondly, when we need to exit from the guest to the kernel, we now have to generate an IPI for any napping threads, because an HDEC interrupt doesn't wake up a napping thread. Thirdly, we now need to be able to handle virtual external interrupts and decrementer interrupts becoming pending while a thread is napping, and deliver those interrupts to the guest when the thread wakes. This is done in kvmppc_cede_reentry, just before fast_guest_return. Finally, since we are not using the generic kvm_vcpu_block for book3s_hv, and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef from kvm_arch_vcpu_runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:42:46 +08:00
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers On a threaded processor such as POWER7, we group VCPUs into virtual cores and arrange that the VCPUs in a virtual core run on the same physical core. Currently we don't enforce any correspondence between virtual thread numbers within a virtual core and physical thread numbers. Physical threads are allocated starting at 0 on a first-come first-served basis to runnable virtual threads (VCPUs). POWER8 implements a new "msgsndp" instruction which guest kernels can use to interrupt other threads in the same core or sub-core. Since the instruction takes the destination physical thread ID as a parameter, it becomes necessary to align the physical thread IDs with the virtual thread IDs, that is, to make sure virtual thread N within a virtual core always runs on physical thread N. This means that it's possible that thread 0, which is where we call __kvmppc_vcore_entry, may end up running some other vcpu than the one whose task called kvmppc_run_core(), or it may end up running no vcpu at all, if for example thread 0 of the virtual core is currently executing in userspace. However, we do need thread 0 to be responsible for switching the MMU -- a previous version of this patch that had other threads switching the MMU was found to be responsible for occasional memory corruption and machine check interrupts in the guest on POWER7 machines. To accommodate this, we no longer pass the vcpu pointer to __kvmppc_vcore_entry, but instead let the assembly code load it from the PACA. Since the assembly code will need to know the kvm pointer and the thread ID for threads which don't have a vcpu, we move the thread ID into the PACA and we add a kvm pointer to the virtual core structure. In the case where thread 0 has no vcpu to run, it still calls into kvmppc_hv_entry in order to do the MMU switch, and then naps until either its vcpu is ready to run in the guest, or some other thread needs to exit the guest. In the latter case, thread 0 jumps to the code that switches the MMU back to the host. This control flow means that now we switch the MMU before loading any guest vcpu state. Similarly, on guest exit we now save all the guest vcpu state before switching the MMU back to the host. This has required substantial code movement, making the diff rather large. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 18:25:20 +08:00
DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
KVM: PPC: Book3S HV: Implement timebase offset for guests This allows guests to have a different timebase origin from the host. This is needed for migration, where a guest can migrate from one host to another and the two hosts might have a different timebase origin. However, the timebase seen by the guest must not go backwards, and should go forwards only by a small amount corresponding to the time taken for the migration. Therefore this provides a new per-vcpu value accessed via the one_reg interface using the new KVM_REG_PPC_TB_OFFSET identifier. This value defaults to 0 and is not modified by KVM. On entering the guest, this value is added onto the timebase, and on exiting the guest, it is subtracted from the timebase. This is only supported for recent POWER hardware which has the TBU40 (timebase upper 40 bits) register. Writing to the TBU40 register only alters the upper 40 bits of the timebase, leaving the lower 24 bits unchanged. This provides a way to modify the timebase for guest migration without disturbing the synchronization of the timebase registers across CPU cores. The kernel rounds up the value given to a multiple of 2^24. Timebase values stored in KVM structures (struct kvm_vcpu, struct kvmppc_vcore, etc.) are stored as host timebase values. The timebase values in the dispatch trace log need to be guest timebase values, however, since that is read directly by the guest. This moves the setting of vcpu->arch.dec_expires on guest exit to a point after we have restored the host timebase so that vcpu->arch.dec_expires is a host timebase value. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-06 11:17:46 +08:00
DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes));
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
DEFINE(VCPU_TFHAR, offsetof(struct kvm_vcpu, arch.tfhar));
DEFINE(VCPU_TFIAR, offsetof(struct kvm_vcpu, arch.tfiar));
DEFINE(VCPU_TEXASR, offsetof(struct kvm_vcpu, arch.texasr));
DEFINE(VCPU_GPR_TM, offsetof(struct kvm_vcpu, arch.gpr_tm));
DEFINE(VCPU_FPRS_TM, offsetof(struct kvm_vcpu, arch.fp_tm.fpr));
DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));
DEFINE(VCPU_PPR_TM, offsetof(struct kvm_vcpu, arch.ppr_tm));
DEFINE(VCPU_DSCR_TM, offsetof(struct kvm_vcpu, arch.dscr_tm));
DEFINE(VCPU_TAR_TM, offsetof(struct kvm_vcpu, arch.tar_tm));
#endif
#ifdef CONFIG_PPC_BOOK3S_64
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
KVM: PPC: Book3S PR: Keep volatile reg values in vcpu rather than shadow_vcpu Currently PR-style KVM keeps the volatile guest register values (R0 - R13, CR, LR, CTR, XER, PC) in a shadow_vcpu struct rather than the main kvm_vcpu struct. For 64-bit, the shadow_vcpu exists in two places, a kmalloc'd struct and in the PACA, and it gets copied back and forth in kvmppc_core_vcpu_load/put(), because the real-mode code can't rely on being able to access the kmalloc'd struct. This changes the code to copy the volatile values into the shadow_vcpu as one of the last things done before entering the guest. Similarly the values are copied back out of the shadow_vcpu to the kvm_vcpu immediately after exiting the guest. We arrange for interrupts to be still disabled at this point so that we can't get preempted on 64-bit and end up copying values from the wrong PACA. This means that the accessor functions in kvm_book3s.h for these registers are greatly simplified, and are same between PR and HV KVM. In places where accesses to shadow_vcpu fields are now replaced by accesses to the kvm_vcpu, we can also remove the svcpu_get/put pairs. Finally, on 64-bit, we don't need the kmalloc'd struct at all any more. With this, the time to read the PVR one million times in a loop went from 567.7ms to 575.5ms (averages of 6 values), an increase of about 1.4% for this worse-case test for guest entries and exits. The standard deviation of the measurements is about 11ms, so the difference is only marginally significant statistically. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:43 +08:00
DEFINE(PACA_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#else
# define SVCPU_FIELD(x, f)
#endif
# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
#else /* 32-bit */
# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f))
#endif
SVCPU_FIELD(SVCPU_CR, cr);
SVCPU_FIELD(SVCPU_XER, xer);
SVCPU_FIELD(SVCPU_CTR, ctr);
SVCPU_FIELD(SVCPU_LR, lr);
SVCPU_FIELD(SVCPU_PC, pc);
SVCPU_FIELD(SVCPU_R0, gpr[0]);
SVCPU_FIELD(SVCPU_R1, gpr[1]);
SVCPU_FIELD(SVCPU_R2, gpr[2]);
SVCPU_FIELD(SVCPU_R3, gpr[3]);
SVCPU_FIELD(SVCPU_R4, gpr[4]);
SVCPU_FIELD(SVCPU_R5, gpr[5]);
SVCPU_FIELD(SVCPU_R6, gpr[6]);
SVCPU_FIELD(SVCPU_R7, gpr[7]);
SVCPU_FIELD(SVCPU_R8, gpr[8]);
SVCPU_FIELD(SVCPU_R9, gpr[9]);
SVCPU_FIELD(SVCPU_R10, gpr[10]);
SVCPU_FIELD(SVCPU_R11, gpr[11]);
SVCPU_FIELD(SVCPU_R12, gpr[12]);
SVCPU_FIELD(SVCPU_R13, gpr[13]);
SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr);
SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar);
SVCPU_FIELD(SVCPU_LAST_INST, last_inst);
SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1);
#ifdef CONFIG_PPC_BOOK3S_32
SVCPU_FIELD(SVCPU_SR, sr);
#endif
#ifdef CONFIG_PPC64
SVCPU_FIELD(SVCPU_SLB, slb);
SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
SVCPU_FIELD(SVCPU_SHADOW_FSCR, shadow_fscr);
#endif
HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
HSTATE_FIELD(HSTATE_HOST_R2, host_r2);
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
HSTATE_FIELD(HSTATE_HOST_MSR, host_msr);
HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
KVM: PPC: book3s_pr: Simplify transitions between virtual and real mode This simplifies the way that the book3s_pr makes the transition to real mode when entering the guest. We now call kvmppc_entry_trampoline (renamed from kvmppc_rmcall) in the base kernel using a normal function call instead of doing an indirect call through a pointer in the vcpu. If kvm is a module, the module loader takes care of generating a trampoline as it does for other calls to functions outside the module. kvmppc_entry_trampoline then disables interrupts and jumps to kvmppc_handler_trampoline_enter in real mode using an rfi[d]. That then uses the link register as the address to return to (potentially in module space) when the guest exits. This also simplifies the way that we call the Linux interrupt handler when we exit the guest due to an external, decrementer or performance monitor interrupt. Instead of turning on the MMU, then deciding that we need to call the Linux handler and turning the MMU back off again, we now go straight to the handler at the point where we would turn the MMU on. The handler will then return to the virtual-mode code (potentially in the module). Along the way, this moves the setting and clearing of the HID5 DCBZ32 bit into real-mode interrupts-off code, and also makes sure that we clear the MSR[RI] bit before loading values into SRR0/1. The net result is that we no longer need any code addresses to be stored in vcpu->arch. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:41:44 +08:00
HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per core), whenever a CPU goes idle, we have to pull all the other hardware threads in the core out of the guest, because the H_CEDE hcall is handled in the kernel. This is inefficient. This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall in real mode. When a guest vcpu does an H_CEDE hcall, we now only exit to the kernel if all the other vcpus in the same core are also idle. Otherwise we mark this vcpu as napping, save state that could be lost in nap mode (mainly GPRs and FPRs), and execute the nap instruction. When the thread wakes up, because of a decrementer or external interrupt, we come back in at kvm_start_guest (from the system reset interrupt vector), find the `napping' flag set in the paca, and go to the resume path. This has some other ramifications. First, when starting a core, we now start all the threads, both those that are immediately runnable and those that are idle. This is so that we don't have to pull all the threads out of the guest when an idle thread gets a decrementer interrupt and wants to start running. In fact the idle threads will all start with the H_CEDE hcall returning; being idle they will just do another H_CEDE immediately and go to nap mode. This required some changes to kvmppc_run_core() and kvmppc_run_vcpu(). These functions have been restructured to make them simpler and clearer. We introduce a level of indirection in the wait queue that gets woken when external and decrementer interrupts get generated for a vcpu, so that we can have the 4 vcpus in a vcore using the same wait queue. We need this because the 4 vcpus are being handled by one thread. Secondly, when we need to exit from the guest to the kernel, we now have to generate an IPI for any napping threads, because an HDEC interrupt doesn't wake up a napping thread. Thirdly, we now need to be able to handle virtual external interrupts and decrementer interrupts becoming pending while a thread is napping, and deliver those interrupts to the guest when the thread wakes. This is done in kvmppc_cede_reentry, just before fast_guest_return. Finally, since we are not using the generic kvm_vcpu_block for book3s_hv, and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef from kvm_arch_vcpu_runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:42:46 +08:00
HSTATE_FIELD(HSTATE_NAPPING, napping);
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req);
HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
KVM: PPC: Allow book3s_hv guests to use SMT processor modes This lifts the restriction that book3s_hv guests can only run one hardware thread per core, and allows them to use up to 4 threads per core on POWER7. The host still has to run single-threaded. This capability is advertised to qemu through a new KVM_CAP_PPC_SMT capability. The return value of the ioctl querying this capability is the number of vcpus per virtual CPU core (vcore), currently 4. To use this, the host kernel should be booted with all threads active, and then all the secondary threads should be offlined. This will put the secondary threads into nap mode. KVM will then wake them from nap mode and use them for running guest code (while they are still offline). To wake the secondary threads, we send them an IPI using a new xics_wake_cpu() function, implemented in arch/powerpc/sysdev/xics/icp-native.c. In other words, at this stage we assume that the platform has a XICS interrupt controller and we are using icp-native.c to drive it. Since the woken thread will need to acknowledge and clear the IPI, we also export the base physical address of the XICS registers using kvmppc_set_xics_phys() for use in the low-level KVM book3s code. When a vcpu is created, it is assigned to a virtual CPU core. The vcore number is obtained by dividing the vcpu number by the number of threads per core in the host. This number is exported to userspace via the KVM_CAP_PPC_SMT capability. If qemu wishes to run the guest in single-threaded mode, it should make all vcpu numbers be multiples of the number of threads per core. We distinguish three states of a vcpu: runnable (i.e., ready to execute the guest), blocked (that is, idle), and busy in host. We currently implement a policy that the vcore can run only when all its threads are runnable or blocked. This way, if a vcpu needs to execute elsewhere in the kernel or in qemu, it can do so without being starved of CPU by the other vcpus. When a vcore starts to run, it executes in the context of one of the vcpu threads. The other vcpu threads all go to sleep and stay asleep until something happens requiring the vcpu thread to return to qemu, or to wake up to run the vcore (this can happen when another vcpu thread goes from busy in host state to blocked). It can happen that a vcpu goes from blocked to runnable state (e.g. because of an interrupt), and the vcore it belongs to is already running. In that case it can start to run immediately as long as the none of the vcpus in the vcore have started to exit the guest. We send the next free thread in the vcore an IPI to get it to start to execute the guest. It synchronizes with the other threads via the vcore->entry_exit_count field to make sure that it doesn't go into the guest if the other vcpus are exiting by the time that it is ready to actually enter the guest. Note that there is no fixed relationship between the hardware thread number and the vcpu number. Hardware threads are assigned to vcpus as they become runnable, so we will always use the lower-numbered hardware threads in preference to higher-numbered threads if not all the vcpus in the vcore are runnable, regardless of which vcpus are runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:23:08 +08:00
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers On a threaded processor such as POWER7, we group VCPUs into virtual cores and arrange that the VCPUs in a virtual core run on the same physical core. Currently we don't enforce any correspondence between virtual thread numbers within a virtual core and physical thread numbers. Physical threads are allocated starting at 0 on a first-come first-served basis to runnable virtual threads (VCPUs). POWER8 implements a new "msgsndp" instruction which guest kernels can use to interrupt other threads in the same core or sub-core. Since the instruction takes the destination physical thread ID as a parameter, it becomes necessary to align the physical thread IDs with the virtual thread IDs, that is, to make sure virtual thread N within a virtual core always runs on physical thread N. This means that it's possible that thread 0, which is where we call __kvmppc_vcore_entry, may end up running some other vcpu than the one whose task called kvmppc_run_core(), or it may end up running no vcpu at all, if for example thread 0 of the virtual core is currently executing in userspace. However, we do need thread 0 to be responsible for switching the MMU -- a previous version of this patch that had other threads switching the MMU was found to be responsible for occasional memory corruption and machine check interrupts in the guest on POWER7 machines. To accommodate this, we no longer pass the vcpu pointer to __kvmppc_vcore_entry, but instead let the assembly code load it from the PACA. Since the assembly code will need to know the kvm pointer and the thread ID for threads which don't have a vcpu, we move the thread ID into the PACA and we add a kvm pointer to the virtual core structure. In the case where thread 0 has no vcpu to run, it still calls into kvmppc_hv_entry in order to do the MMU switch, and then naps until either its vcpu is ready to run in the guest, or some other thread needs to exit the guest. In the latter case, thread 0 jumps to the code that switches the MMU back to the host. This control flow means that now we switch the MMU before loading any guest vcpu state. Similarly, on guest exit we now save all the guest vcpu state before switching the MMU back to the host. This has required substantial code movement, making the diff rather large. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2014-01-08 18:25:20 +08:00
HSTATE_FIELD(HSTATE_PTID, ptid);
HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]);
HSTATE_FIELD(HSTATE_SIAR, host_mmcr[3]);
HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
HSTATE_FIELD(HSTATE_PMC4, host_pmc[3]);
HSTATE_FIELD(HSTATE_PMC5, host_pmc[4]);
HSTATE_FIELD(HSTATE_PMC6, host_pmc[5]);
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
HSTATE_FIELD(HSTATE_PURR, host_purr);
HSTATE_FIELD(HSTATE_SPURR, host_spurr);
HSTATE_FIELD(HSTATE_DSCR, host_dscr);
HSTATE_FIELD(HSTATE_DABR, dabr);
HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8 This builds on the ability to run more than one vcore on a physical core by using the micro-threading (split-core) modes of the POWER8 chip. Previously, only vcores from the same VM could be run together, and (on POWER8) only if they had just one thread per core. With the ability to split the core on guest entry and unsplit it on guest exit, we can run up to 8 vcpu threads from up to 4 different VMs, and we can run multiple vcores with 2 or 4 vcpus per vcore. Dynamic micro-threading is only available if the static configuration of the cores is whole-core mode (unsplit), and only on POWER8. To manage this, we introduce a new kvm_split_mode struct which is shared across all of the subcores in the core, with a pointer in the paca on each thread. In addition we extend the core_info struct to have information on each subcore. When deciding whether to add a vcore to the set already on the core, we now have two possibilities: (a) piggyback the vcore onto an existing subcore, or (b) start a new subcore. Currently, when any vcpu needs to exit the guest and switch to host virtual mode, we interrupt all the threads in all subcores and switch the core back to whole-core mode. It may be possible in future to allow some of the subcores to keep executing in the guest while subcore 0 switches to the host, but that is not implemented in this patch. This adds a module parameter called dynamic_mt_modes which controls which micro-threading (split-core) modes the code will consider, as a bitmap. In other words, if it is 0, no micro-threading mode is considered; if it is 2, only 2-way micro-threading is considered; if it is 4, only 4-way, and if it is 6, both 2-way and 4-way micro-threading mode will be considered. The default is 6. With this, we now have secondary threads which are the primary thread for their subcore and therefore need to do the MMU switch. These threads will need to be started even if they have no vcpu to run, so we use the vcore pointer in the PACA rather than the vcpu pointer to trigger them. It is now possible for thread 0 to find that an exit has been requested before it gets to switch the subcore state to the guest. In that case we haven't added the guest's timebase offset to the timebase, so we need to be careful not to subtract the offset in the guest exit path. In fact we just skip the whole path that switches back to host context, since we haven't switched to the guest context. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 18:38:16 +08:00
HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per core), whenever a CPU goes idle, we have to pull all the other hardware threads in the core out of the guest, because the H_CEDE hcall is handled in the kernel. This is inefficient. This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall in real mode. When a guest vcpu does an H_CEDE hcall, we now only exit to the kernel if all the other vcpus in the same core are also idle. Otherwise we mark this vcpu as napping, save state that could be lost in nap mode (mainly GPRs and FPRs), and execute the nap instruction. When the thread wakes up, because of a decrementer or external interrupt, we come back in at kvm_start_guest (from the system reset interrupt vector), find the `napping' flag set in the paca, and go to the resume path. This has some other ramifications. First, when starting a core, we now start all the threads, both those that are immediately runnable and those that are idle. This is so that we don't have to pull all the threads out of the guest when an idle thread gets a decrementer interrupt and wants to start running. In fact the idle threads will all start with the H_CEDE hcall returning; being idle they will just do another H_CEDE immediately and go to nap mode. This required some changes to kvmppc_run_core() and kvmppc_run_vcpu(). These functions have been restructured to make them simpler and clearer. We introduce a level of indirection in the wait queue that gets woken when external and decrementer interrupts get generated for a vcpu, so that we can have the 4 vcpus in a vcore using the same wait queue. We need this because the 4 vcpus are being handled by one thread. Secondly, when we need to exit from the guest to the kernel, we now have to generate an IPI for any napping threads, because an HDEC interrupt doesn't wake up a napping thread. Thirdly, we now need to be able to handle virtual external interrupts and decrementer interrupts becoming pending while a thread is napping, and deliver those interrupts to the guest when the thread wakes. This is done in kvmppc_cede_reentry, just before fast_guest_return. Finally, since we are not using the generic kvm_vcpu_block for book3s_hv, and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef from kvm_arch_vcpu_runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-07-23 15:42:46 +08:00
DEFINE(IPI_PRIORITY, IPI_PRIORITY);
KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8 This builds on the ability to run more than one vcore on a physical core by using the micro-threading (split-core) modes of the POWER8 chip. Previously, only vcores from the same VM could be run together, and (on POWER8) only if they had just one thread per core. With the ability to split the core on guest entry and unsplit it on guest exit, we can run up to 8 vcpu threads from up to 4 different VMs, and we can run multiple vcores with 2 or 4 vcpus per vcore. Dynamic micro-threading is only available if the static configuration of the cores is whole-core mode (unsplit), and only on POWER8. To manage this, we introduce a new kvm_split_mode struct which is shared across all of the subcores in the core, with a pointer in the paca on each thread. In addition we extend the core_info struct to have information on each subcore. When deciding whether to add a vcore to the set already on the core, we now have two possibilities: (a) piggyback the vcore onto an existing subcore, or (b) start a new subcore. Currently, when any vcpu needs to exit the guest and switch to host virtual mode, we interrupt all the threads in all subcores and switch the core back to whole-core mode. It may be possible in future to allow some of the subcores to keep executing in the guest while subcore 0 switches to the host, but that is not implemented in this patch. This adds a module parameter called dynamic_mt_modes which controls which micro-threading (split-core) modes the code will consider, as a bitmap. In other words, if it is 0, no micro-threading mode is considered; if it is 2, only 2-way micro-threading is considered; if it is 4, only 4-way, and if it is 6, both 2-way and 4-way micro-threading mode will be considered. The default is 6. With this, we now have secondary threads which are the primary thread for their subcore and therefore need to do the MMU switch. These threads will need to be started even if they have no vcpu to run, so we use the vcore pointer in the PACA rather than the vcpu pointer to trigger them. It is now possible for thread 0 to find that an exit has been requested before it gets to switch the subcore state to the guest. In that case we haven't added the guest's timebase offset to the timebase, so we need to be careful not to subtract the offset in the guest exit path. In fact we just skip the whole path that switches back to host context, since we haven't switched to the guest context. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2015-07-02 18:38:16 +08:00
DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
KVM: PPC: Add support for Book3S processors in hypervisor mode This adds support for KVM running on 64-bit Book 3S processors, specifically POWER7, in hypervisor mode. Using hypervisor mode means that the guest can use the processor's supervisor mode. That means that the guest can execute privileged instructions and access privileged registers itself without trapping to the host. This gives excellent performance, but does mean that KVM cannot emulate a processor architecture other than the one that the hardware implements. This code assumes that the guest is running paravirtualized using the PAPR (Power Architecture Platform Requirements) interface, which is the interface that IBM's PowerVM hypervisor uses. That means that existing Linux distributions that run on IBM pSeries machines will also run under KVM without modification. In order to communicate the PAPR hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code to include/linux/kvm.h. Currently the choice between book3s_hv support and book3s_pr support (i.e. the existing code, which runs the guest in user mode) has to be made at kernel configuration time, so a given kernel binary can only do one or the other. This new book3s_hv code doesn't support MMIO emulation at present. Since we are running paravirtualized guests, this isn't a serious restriction. With the guest running in supervisor mode, most exceptions go straight to the guest. We will never get data or instruction storage or segment interrupts, alignment interrupts, decrementer interrupts, program interrupts, single-step interrupts, etc., coming to the hypervisor from the guest. Therefore this introduces a new KVMTEST_NONHV macro for the exception entry path so that we don't have to do the KVM test on entry to those exception handlers. We do however get hypervisor decrementer, hypervisor data storage, hypervisor instruction storage, and hypervisor emulation assist interrupts, so we have to handle those. In hypervisor mode, real-mode accesses can access all of RAM, not just a limited amount. Therefore we put all the guest state in the vcpu.arch and use the shadow_vcpu in the PACA only for temporary scratch space. We allocate the vcpu with kzalloc rather than vzalloc, and we don't use anything in the kvmppc_vcpu_book3s struct, so we don't allocate it. We don't have a shared page with the guest, but we still need a kvm_vcpu_arch_shared struct to store the values of various registers, so we include one in the vcpu_arch struct. The POWER7 processor has a restriction that all threads in a core have to be in the same partition. MMU-on kernel code counts as a partition (partition 0), so we have to do a partition switch on every entry to and exit from the guest. At present we require the host and guest to run in single-thread mode because of this hardware restriction. This code allocates a hashed page table for the guest and initializes it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We require that the guest memory is allocated using 16MB huge pages, in order to simplify the low-level memory management. This also means that we can get away without tracking paging activity in the host for now, since huge pages can't be paged or swapped. This also adds a few new exports needed by the book3s_hv code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2011-06-29 08:21:34 +08:00
#ifdef CONFIG_PPC_BOOK3S_64
HSTATE_FIELD(HSTATE_CFAR, cfar);
HSTATE_FIELD(HSTATE_PPR, ppr);
HSTATE_FIELD(HSTATE_HOST_FSCR, host_fscr);
#endif /* CONFIG_PPC_BOOK3S_64 */
#else /* CONFIG_PPC_BOOK3S */
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
DEFINE(VCPU_SPRG9, offsetof(struct kvm_vcpu, arch.sprg9));
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
DEFINE(VCPU_CRIT_SAVE, offsetof(struct kvm_vcpu, arch.crit_save));
#endif /* CONFIG_PPC_BOOK3S */
#endif /* CONFIG_KVM */
#ifdef CONFIG_KVM_GUEST
DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared,
scratch1));
DEFINE(KVM_MAGIC_SCRATCH2, offsetof(struct kvm_vcpu_arch_shared,
scratch2));
DEFINE(KVM_MAGIC_SCRATCH3, offsetof(struct kvm_vcpu_arch_shared,
scratch3));
DEFINE(KVM_MAGIC_INT, offsetof(struct kvm_vcpu_arch_shared,
int_pending));
DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared,
critical));
DEFINE(KVM_MAGIC_SR, offsetof(struct kvm_vcpu_arch_shared, sr));
#endif
#ifdef CONFIG_44x
DEFINE(PGD_T_LOG2, PGD_T_LOG2);
DEFINE(PTE_T_LOG2, PTE_T_LOG2);
#endif
#ifdef CONFIG_PPC_FSL_BOOK3E
DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0));
DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1));
DEFINE(TLBCAM_MAS2, offsetof(struct tlbcam, MAS2));
DEFINE(TLBCAM_MAS3, offsetof(struct tlbcam, MAS3));
DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7));
#endif
#if defined(CONFIG_KVM) && defined(CONFIG_SPE)
DEFINE(VCPU_EVR, offsetof(struct kvm_vcpu, arch.evr[0]));
DEFINE(VCPU_ACC, offsetof(struct kvm_vcpu, arch.acc));
DEFINE(VCPU_SPEFSCR, offsetof(struct kvm_vcpu, arch.spefscr));
DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr));
#endif
#ifdef CONFIG_KVM_BOOKE_HV
DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4));
DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6));
DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc));
#endif
#ifdef CONFIG_KVM_EXIT_TIMING
DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
arch.timing_exit.tv32.tbu));
DEFINE(VCPU_TIMING_EXIT_TBL, offsetof(struct kvm_vcpu,
arch.timing_exit.tv32.tbl));
DEFINE(VCPU_TIMING_LAST_ENTER_TBU, offsetof(struct kvm_vcpu,
arch.timing_last_enter.tv32.tbu));
DEFINE(VCPU_TIMING_LAST_ENTER_TBL, offsetof(struct kvm_vcpu,
arch.timing_last_enter.tv32.tbl));
#endif
#ifdef CONFIG_PPC_POWERNV
DEFINE(PACA_CORE_IDLE_STATE_PTR,
offsetof(struct paca_struct, core_idle_state_ptr));
DEFINE(PACA_THREAD_IDLE_STATE,
offsetof(struct paca_struct, thread_idle_state));
DEFINE(PACA_THREAD_MASK,
offsetof(struct paca_struct, thread_mask));
DEFINE(PACA_SUBCORE_SIBLING_MASK,
offsetof(struct paca_struct, subcore_sibling_mask));
#endif
DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
return 0;
}