linux_old1/arch/powerpc/include/asm/paca.h

174 lines
5.7 KiB
C
Raw Normal View History

/*
* This control block defines the PACA which defines the processor
* specific data for each logical processor on the system.
* There are some pointers defined that are utilized by PLIC.
*
* C 2001 PPC 64 Team, IBM Corp
*
* 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.
*/
#ifndef _ASM_POWERPC_PACA_H
#define _ASM_POWERPC_PACA_H
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
#include <linux/init.h>
#include <asm/types.h>
#include <asm/lppaca.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/exception-64e.h>
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#include <asm/kvm_book3s_asm.h>
#endif
register struct paca_struct *local_paca asm("r13");
#if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
/*
* Add standard checks that preemption cannot occur when using get_paca():
* otherwise the paca_struct it points to may be the wrong one just after.
*/
#define get_paca() ((void) debug_smp_processor_id(), local_paca)
#else
#define get_paca() local_paca
#endif
#define get_lppaca() (get_paca()->lppaca_ptr)
#define get_slb_shadow() (get_paca()->slb_shadow_ptr)
struct task_struct;
/*
* Defines the layout of the paca.
*
* This structure is not directly accessed by firmware or the service
* processor.
*/
struct paca_struct {
#ifdef CONFIG_PPC_BOOK3S
/*
* Because hw_cpu_id, unlike other paca fields, is accessed
* routinely from other CPUs (from the IRQ code), we stick to
* read-only (after boot) fields in the first cacheline to
* avoid cacheline bouncing.
*/
struct lppaca *lppaca_ptr; /* Pointer to LpPaca for PLIC */
#endif /* CONFIG_PPC_BOOK3S */
/*
* MAGIC: the spinlock functions in arch/powerpc/lib/locks.c
* load lock_token and paca_index with a single lwz
* instruction. They must travel together and be properly
* aligned.
*/
u16 lock_token; /* Constant 0x8000, used in locks */
u16 paca_index; /* Logical processor number */
u64 kernel_toc; /* Kernel TOC address */
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
u64 kernelbase; /* Base address of kernel */
u64 kernel_msr; /* MSR while running in kernel */
#ifdef CONFIG_PPC_STD_MMU_64
u64 stab_real; /* Absolute address of segment table */
u64 stab_addr; /* Virtual address of segment table */
#endif /* CONFIG_PPC_STD_MMU_64 */
void *emergency_sp; /* pointer to emergency stack */
[PATCH] powerpc/64: per cpu data optimisations The current ppc64 per cpu data implementation is quite slow. eg: lhz 11,18(13) /* smp_processor_id() */ ld 9,.LC63-.LCTOC1(30) /* per_cpu__variable_name */ ld 8,.LC61-.LCTOC1(30) /* __per_cpu_offset */ sldi 11,11,3 /* form index into __per_cpu_offset */ mr 10,9 ldx 9,11,8 /* __per_cpu_offset[smp_processor_id()] */ ldx 0,10,9 /* load per cpu data */ 5 loads for something that is supposed to be fast, pretty awful. One reason for the large number of loads is that we have to synthesize 2 64bit constants (per_cpu__variable_name and __per_cpu_offset). By putting __per_cpu_offset into the paca we can avoid the 2 loads associated with it: ld 11,56(13) /* paca->data_offset */ ld 9,.LC59-.LCTOC1(30) /* per_cpu__variable_name */ ldx 0,9,11 /* load per cpu data Longer term we can should be able to do even better than 3 loads. If per_cpu__variable_name wasnt a 64bit constant and paca->data_offset was in a register we could cut it down to one load. A suggestion from Rusty is to use gcc's __thread extension here. In order to do this we would need to free up r13 (the __thread register and where the paca currently is). So far Ive had a few unsuccessful attempts at doing that :) The patch also allocates per cpu memory node local on NUMA machines. This patch from Rusty has been sitting in my queue _forever_ but stalled when I hit the compiler bug. Sorry about that. Finally I also only allocate per cpu data for possible cpus, which comes straight out of the x86-64 port. On a pseries kernel (with NR_CPUS == 128) and 4 possible cpus we see some nice gains: total used free shared buffers cached Mem: 4012228 212860 3799368 0 0 162424 total used free shared buffers cached Mem: 4016200 212984 3803216 0 0 162424 A saving of 3.75MB. Quite nice for smaller machines. Note: we now have to be careful of per cpu users that touch data for !possible cpus. At this stage it might be worth making the NUMA and possible cpu optimisations generic, but per cpu init is done so early we have to be careful that all architectures have their possible map setup correctly. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-01-11 10:16:44 +08:00
u64 data_offset; /* per cpu data offset */
s16 hw_cpu_id; /* Physical processor number */
u8 cpu_start; /* At startup, processor spins until */
/* this becomes non-zero. */
u8 kexec_state; /* set when kexec down has irqs off */
#ifdef CONFIG_PPC_STD_MMU_64
struct slb_shadow *slb_shadow_ptr;
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
struct dtl_entry *dispatch_log;
struct dtl_entry *dispatch_log_end;
/*
* Now, starting in cacheline 2, the exception save areas
*/
/* used for most interrupts/exceptions */
u64 exgen[11] __attribute__((aligned(0x80)));
u64 exmc[11]; /* used for machine checks */
u64 exslb[11]; /* used for SLB/segment table misses
* on the linear mapping */
/* SLB related definitions */
powerpc: Use 64k pages without needing cache-inhibited large pages Some POWER5+ machines can do 64k hardware pages for normal memory but not for cache-inhibited pages. This patch lets us use 64k hardware pages for most user processes on such machines (assuming the kernel has been configured with CONFIG_PPC_64K_PAGES=y). User processes start out using 64k pages and get switched to 4k pages if they use any non-cacheable mappings. With this, we use 64k pages for the vmalloc region and 4k pages for the imalloc region. If anything creates a non-cacheable mapping in the vmalloc region, the vmalloc region will get switched to 4k pages. I don't know of any driver other than the DRM that would do this, though, and these machines don't have AGP. When a region gets switched from 64k pages to 4k pages, we do not have to clear out all the 64k HPTEs from the hash table immediately. We use the _PAGE_COMBO bit in the Linux PTE to indicate whether the page was hashed in as a 64k page or a set of 4k pages. If hash_page is trying to insert a 4k page for a Linux PTE and it sees that it has already been inserted as a 64k page, it first invalidates the 64k HPTE before inserting the 4k HPTE. The hash invalidation routines also use the _PAGE_COMBO bit, to determine whether to look for a 64k HPTE or a set of 4k HPTEs to remove. With those two changes, we can tolerate a mix of 4k and 64k HPTEs in the hash table, and they will all get removed when the address space is torn down. Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-06-15 08:45:18 +08:00
u16 vmalloc_sllp;
u16 slb_cache_ptr;
[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
u16 slb_cache[SLB_CACHE_ENTRIES];
#endif /* CONFIG_PPC_STD_MMU_64 */
#ifdef CONFIG_PPC_BOOK3E
pgd_t *pgd; /* Current PGD */
pgd_t *kernel_pgd; /* Kernel PGD */
u64 exgen[8] __attribute__((aligned(0x80)));
/* We can have up to 3 levels of reentrancy in the TLB miss handler */
u64 extlb[3][EX_TLB_SIZE / sizeof(u64)] __attribute__((aligned(0x80)));
u64 exmc[8]; /* used for machine checks */
u64 excrit[8]; /* used for crit interrupts */
u64 exdbg[8]; /* used for debug interrupts */
/* Kernel stack pointers for use by special exceptions */
void *mc_kstack;
void *crit_kstack;
void *dbg_kstack;
#endif /* CONFIG_PPC_BOOK3E */
mm_context_t context;
/*
* then miscellaneous read-write fields
*/
struct task_struct *__current; /* Pointer to current */
u64 kstack; /* Saved Kernel stack addr */
u64 stab_rr; /* stab/slb round-robin counter */
u64 saved_r1; /* r1 save for RTAS calls or PM */
u64 saved_msr; /* MSR saved here by enter_rtas */
u16 trap_save; /* Used when bad stack is encountered */
u8 soft_enabled; /* irq soft-enable flag */
u8 hard_enabled; /* set if irqs are enabled in MSR */
u8 io_sync; /* writel() needs spin_unlock sync */
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
powerpc: Implement accurate task and CPU time accounting This implements accurate task and cpu time accounting for 64-bit powerpc kernels. Instead of accounting a whole jiffy of time to a task on a timer interrupt because that task happened to be running at the time, we now account time in units of timebase ticks according to the actual time spent by the task in user mode and kernel mode. We also count the time spent processing hardware and software interrupts accurately. This is conditional on CONFIG_VIRT_CPU_ACCOUNTING. If that is not set, we do tick-based approximate accounting as before. To get this accurate information, we read either the PURR (processor utilization of resources register) on POWER5 machines, or the timebase on other machines on * each entry to the kernel from usermode * each exit to usermode * transitions between process context, hard irq context and soft irq context in kernel mode * context switches. On POWER5 systems with shared-processor logical partitioning we also read both the PURR and the timebase at each timer interrupt and context switch in order to determine how much time has been taken by the hypervisor to run other partitions ("steal" time). Unfortunately, since we need values of the PURR on both threads at the same time to accurately calculate the steal time, and since we can only calculate steal time on a per-core basis, the apportioning of the steal time between idle time (time which we ceded to the hypervisor in the idle loop) and actual stolen time is somewhat approximate at the moment. This is all based quite heavily on what s390 does, and it uses the generic interfaces that were added by the s390 developers, i.e. account_system_time(), account_user_time(), etc. This patch doesn't add any new interfaces between the kernel and userspace, and doesn't change the units in which time is reported to userspace by things such as /proc/stat, /proc/<pid>/stat, getrusage(), times(), etc. Internally the various task and cpu times are stored in timebase units, but they are converted to USER_HZ units (1/100th of a second) when reported to userspace. Some precision is therefore lost but there should not be any accumulating error, since the internal accumulation is at full precision. Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-02-24 07:06:59 +08:00
/* Stuff for accurate time accounting */
u64 user_time; /* accumulated usermode TB ticks */
u64 system_time; /* accumulated system TB ticks */
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
u64 user_time_scaled; /* accumulated usermode SPURR ticks */
u64 starttime; /* TB value snapshot */
u64 starttime_user; /* TB value on exit to usermode */
powerpc: add scaled time accounting This adds POWERPC specific hooks for scaled time accounting. POWER6 includes a SPURR register. The SPURR is based off the PURR register but is scaled based on CPU frequency and issue rates. This gives a more accurate account of the instructions used per task. The PURR and timebase will be constant relative to the wall clock, irrespective of the CPU frequency. This implementation reads the SPURR register in account_system_vtime which is only call called on context witch and hard and soft irq entry and exit. The percentage of user and system time is then estimated using the ratio of these accounted by the PURR. If the SPURR is not present, the PURR read. An earlier implementation of this patch read the SPURR whenever the PURR was read, which included the system call entry and exit path. Unfortunately this showed a performance regression on lmbench runs, so was re-implemented. I've included the lmbench results here when run bare metal on POWER6. 1st column is the unpatch results. 2nd column is the results using the below patch and the 3rd is the % diff of these results from the base. 4th and 5th columns are the results and % differnce from the base using the older patch (SPURR read in syscall entry/exit path). Base Scaled-Acct SPURR-in-syscall Result Result % diff Result % diff Simple syscall: 0.3086 0.3086 0.0000 0.3452 11.8600 Simple read: 0.4591 0.4671 1.7425 0.5044 9.86713 Simple write: 0.4364 0.4366 0.0458 0.4731 8.40971 Simple stat: 2.0055 2.0295 1.1967 2.0669 3.06158 Simple fstat: 0.5962 0.5876 -1.442 0.6368 6.80979 Simple open/close: 3.1283 3.1009 -0.875 3.2088 2.57328 Select on 10 fd's: 0.8554 0.8457 -1.133 0.8667 1.32101 Select on 100 fd's: 3.5292 3.6329 2.9383 3.6664 3.88756 Select on 250 fd's: 7.9097 8.1881 3.5197 8.2242 3.97613 Select on 500 fd's: 15.2659 15.836 3.7357 15.873 3.97814 Select on 10 tcp fd's: 0.9576 0.9416 -1.670 0.9752 1.83792 Select on 100 tcp fd's: 7.248 7.2254 -0.311 7.2685 0.28283 Select on 250 tcp fd's: 17.7742 17.707 -0.375 17.749 -0.1406 Select on 500 tcp fd's: 35.4258 35.25 -0.496 35.286 -0.3929 Signal handler installation: 0.6131 0.6075 -0.913 0.647 5.52927 Signal handler overhead: 2.0919 2.1078 0.7600 2.1831 4.35967 Protection fault: 0.7345 0.7478 1.8107 0.8031 9.33968 Pipe latency: 33.006 16.398 -50.31 33.475 1.42368 AF_UNIX sock stream latency: 14.5093 30.910 113.03 30.715 111.692 Process fork+exit: 219.8 222.8 1.3648 229.37 4.35623 Process fork+execve: 876.14 873.28 -0.32 868.66 -0.8533 Process fork+/bin/sh -c: 2830 2876.5 1.6431 2958 4.52296 File /var/tmp/XXX write bw: 1193497 1195536 0.1708 118657 -0.5799 Pagefaults on /var/tmp/XXX: 3.1272 3.2117 2.7020 3.2521 3.99398 Also, kernel compile times show no difference with this patch applied. [pbadari@us.ibm.com: Avoid unnecessary PURR reading] Signed-off-by: Michael Neuling <mikey@neuling.org> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Jay Lan <jlan@engr.sgi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:06:37 +08:00
u64 startspurr; /* SPURR value snapshot */
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
u64 utime_sspurr; /* ->user_time when ->startspurr set */
u64 stolen_time; /* TB ticks taken by hypervisor */
u64 dtl_ridx; /* read index in dispatch log */
struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */
#ifdef CONFIG_KVM_BOOK3S_HANDLER
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_KVM_BOOK3S_PR
/* We use this to store guest state in */
struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
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
struct kvmppc_host_state kvm_hstate;
#endif
};
extern struct paca_struct *paca;
extern __initdata struct paca_struct boot_paca;
extern void initialise_paca(struct paca_struct *new_paca, int cpu);
extern void setup_paca(struct paca_struct *new_paca);
extern void allocate_pacas(void);
extern void free_unused_pacas(void);
#else /* CONFIG_PPC64 */
static inline void allocate_pacas(void) { };
static inline void free_unused_pacas(void) { };
#endif /* CONFIG_PPC64 */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PACA_H */