linux-stable/arch/powerpc/include/asm/lppaca.h

197 lines
5.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* lppaca.h
* Copyright (C) 2001 Mike Corrigan IBM Corporation
*/
#ifndef _ASM_POWERPC_LPPACA_H
#define _ASM_POWERPC_LPPACA_H
/*
* The below VPHN macros are outside the __KERNEL__ check since these are
* used for compiling the vphn selftest in userspace
*/
/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */
#define VPHN_REGISTER_COUNT 6
/*
* 6 64-bit registers unpacked into up to 24 be32 associativity values. To
* form the complete property we have to add the length in the first cell.
*/
#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1)
/*
* The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags:
* 1 for retrieving associativity information for a guest cpu
* 2 for retrieving associativity information for a host/hypervisor cpu
*/
#define VPHN_FLAG_VCPU 1
#define VPHN_FLAG_PCPU 2
#ifdef __KERNEL__
/*
* These definitions relate to hypervisors that only exist when using
* a server type processor
*/
#ifdef CONFIG_PPC_BOOK3S
/*
* This control block contains the data that is shared between the
* hypervisor and the OS.
*/
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/spinlock_types.h>
#include <asm/types.h>
#include <asm/mmu.h>
#include <asm/firmware.h>
/*
* The lppaca is the "virtual processor area" registered with the hypervisor,
* H_REGISTER_VPA etc.
*
* According to PAPR, the structure is 640 bytes long, must be L1 cache line
* aligned, and must not cross a 4kB boundary. Its size field must be at
* least 640 bytes (but may be more).
*
* Pre-v4.14 KVM hypervisors reject the VPA if its size field is smaller than
* 1kB, so we dynamically allocate 1kB and advertise size as 1kB, but keep
* this structure as the canonical 640 byte size.
*/
struct lppaca {
/* cacheline 1 contains read-only data */
__be32 desc; /* Eye catcher 0xD397D781 */
__be16 size; /* Size of this struct */
u8 reserved1[3];
u8 __old_status; /* Old status, including shared proc */
u8 reserved3[14];
volatile __be32 dyn_hw_node_id; /* Dynamic hardware node id */
volatile __be32 dyn_hw_proc_id; /* Dynamic hardware proc id */
u8 reserved4[56];
volatile u8 vphn_assoc_counts[8]; /* Virtual processor home node */
/* associativity change counters */
u8 reserved5[32];
/* cacheline 2 contains local read-write data */
u8 reserved6[48];
u8 cede_latency_hint;
u8 ebb_regs_in_use;
u8 reserved7[6];
u8 dtl_enable_mask; /* Dispatch Trace Log mask */
u8 donate_dedicated_cpu; /* Donate dedicated CPU cycles */
u8 fpregs_in_use;
u8 pmcregs_in_use;
u8 reserved8[28];
__be64 wait_state_cycles; /* Wait cycles for this proc */
u8 reserved9[28];
__be16 slb_count; /* # of SLBs to maintain */
u8 idle; /* Indicate OS is idle */
u8 vmxregs_in_use;
/* cacheline 3 is shared with other processors */
/*
* This is the yield_count. An "odd" value (low bit on) means that
* the processor is yielded (either because of an OS yield or a
* hypervisor preempt). An even value implies that the processor is
* currently executing.
* NOTE: Even dedicated processor partitions can yield so this
* field cannot be used to determine if we are shared or dedicated.
*/
volatile __be32 yield_count;
volatile __be32 dispersion_count; /* dispatch changed physical cpu */
volatile __be64 cmo_faults; /* CMO page fault count */
volatile __be64 cmo_fault_time; /* CMO page fault time */
u8 reserved10[104];
/* cacheline 4-5 */
__be32 page_ins; /* CMO Hint - # page ins by OS */
u8 reserved11[148];
volatile __be64 dtl_idx; /* Dispatch Trace Log head index */
u8 reserved12[96];
} ____cacheline_aligned;
#define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr)
/*
* We are using a non architected field to determine if a partition is
* shared or dedicated. This currently works on both KVM and PHYP, but
* we will have to transition to something better.
*/
#define LPPACA_OLD_SHARED_PROC 2
static inline bool lppaca_shared_proc(struct lppaca *l)
{
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return false;
return !!(l->__old_status & LPPACA_OLD_SHARED_PROC);
}
/*
* SLB shadow buffer structure as defined in the PAPR. The save_area
* contains adjacent ESID and VSID pairs for each shadowed SLB. The
* ESID is stored in the lower 64bits, then the VSID.
*/
struct slb_shadow {
__be32 persistent; /* Number of persistent SLBs */
__be32 buffer_length; /* Total shadow buffer length */
__be64 reserved;
struct {
__be64 esid;
__be64 vsid;
} save_area[SLB_NUM_BOLTED];
} ____cacheline_aligned;
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>
2010-08-26 19:56:43 +00:00
/*
* Layout of entries in the hypervisor's dispatch trace log buffer.
*/
struct dtl_entry {
u8 dispatch_reason;
u8 preempt_reason;
__be16 processor_id;
__be32 enqueue_to_dispatch_time;
__be32 ready_to_enqueue_time;
__be32 waiting_to_ready_time;
__be64 timebase;
__be64 fault_addr;
__be64 srr0;
__be64 srr1;
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>
2010-08-26 19:56:43 +00:00
};
#define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */
#define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
/*
* Dispatch trace log event enable mask:
* 0x1: voluntary virtual processor waits
* 0x2: time-slice preempts
* 0x4: virtual partition memory page faults
*/
#define DTL_LOG_CEDE 0x1
#define DTL_LOG_PREEMPT 0x2
#define DTL_LOG_FAULT 0x4
#define DTL_LOG_ALL (DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
extern struct kmem_cache *dtl_cache;
extern rwlock_t dtl_access_lock;
/*
cputime: Generic on-demand virtual cputime accounting If we want to stop the tick further idle, we need to be able to account the cputime without using the tick. Virtual based cputime accounting solves that problem by hooking into kernel/user boundaries. However implementing CONFIG_VIRT_CPU_ACCOUNTING require low level hooks and involves more overhead. But we already have a generic context tracking subsystem that is required for RCU needs by archs which plan to shut down the tick outside idle. This patch implements a generic virtual based cputime accounting that relies on these generic kernel/user hooks. There are some upsides of doing this: - This requires no arch code to implement CONFIG_VIRT_CPU_ACCOUNTING if context tracking is already built (already necessary for RCU in full tickless mode). - We can rely on the generic context tracking subsystem to dynamically (de)activate the hooks, so that we can switch anytime between virtual and tick based accounting. This way we don't have the overhead of the virtual accounting when the tick is running periodically. And one downside: - There is probably more overhead than a native virtual based cputime accounting. But this relies on hooks that are already set anyway. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-07-25 05:56:04 +00:00
* When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
* reading from the dispatch trace log. If other code wants to consume
* DTL entries, it can set this pointer to a function that will get
* called once for each DTL entry that gets processed.
*/
extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
extern void register_dtl_buffer(int cpu);
extern void alloc_dtl_buffers(unsigned long *time_limit);
extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
#endif /* CONFIG_PPC_BOOK3S */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_LPPACA_H */