tmp_suning_uos_patched/include/trace/events/xen.h

517 lines
16 KiB
C
Raw Normal View History

#undef TRACE_SYSTEM
#define TRACE_SYSTEM xen
#if !defined(_TRACE_XEN_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_XEN_H
#include <linux/tracepoint.h>
#include <asm/paravirt_types.h>
#include <asm/xen/trace_types.h>
xen/tracing: fix compile errors when tracing is disabled. When CONFIG_FUNCTION_TRACER is disabled, compilation fails as follows: CC arch/x86/xen/setup.o In file included from arch/x86/include/asm/xen/hypercall.h:42, from arch/x86/xen/setup.c:19: include/trace/events/xen.h:31: warning: 'struct multicall_entry' declared inside parameter list include/trace/events/xen.h:31: warning: its scope is only this definition or declaration, which is probably not what you want include/trace/events/xen.h:31: warning: 'struct multicall_entry' declared inside parameter list include/trace/events/xen.h:31: warning: 'struct multicall_entry' declared inside parameter list include/trace/events/xen.h:31: warning: 'struct multicall_entry' declared inside parameter list [...] arch/x86/xen/trace.c:5: error: '__HYPERVISOR_set_trap_table' undeclared here (not in a function) arch/x86/xen/trace.c:5: error: array index in initializer not of integer type arch/x86/xen/trace.c:5: error: (near initialization for 'xen_hypercall_names') arch/x86/xen/trace.c:6: error: '__HYPERVISOR_mmu_update' undeclared here (not in a function) arch/x86/xen/trace.c:6: error: array index in initializer not of integer type arch/x86/xen/trace.c:6: error: (near initialization for 'xen_hypercall_names') Fix this by making sure struct multicall_entry has a declaration in scope at all times, and don't bother compiling xen/trace.c when tracing is disabled. Reported-by: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
2011-07-26 06:51:02 +08:00
struct multicall_entry;
/* Multicalls */
DECLARE_EVENT_CLASS(xen_mc__batch,
TP_PROTO(enum paravirt_lazy_mode mode),
TP_ARGS(mode),
TP_STRUCT__entry(
__field(enum paravirt_lazy_mode, mode)
),
TP_fast_assign(__entry->mode = mode),
TP_printk("start batch LAZY_%s",
(__entry->mode == PARAVIRT_LAZY_MMU) ? "MMU" :
(__entry->mode == PARAVIRT_LAZY_CPU) ? "CPU" : "NONE")
);
#define DEFINE_XEN_MC_BATCH(name) \
DEFINE_EVENT(xen_mc__batch, name, \
TP_PROTO(enum paravirt_lazy_mode mode), \
TP_ARGS(mode))
DEFINE_XEN_MC_BATCH(xen_mc_batch);
DEFINE_XEN_MC_BATCH(xen_mc_issue);
TRACE_EVENT(xen_mc_entry,
TP_PROTO(struct multicall_entry *mc, unsigned nargs),
TP_ARGS(mc, nargs),
TP_STRUCT__entry(
__field(unsigned int, op)
__field(unsigned int, nargs)
__array(unsigned long, args, 6)
),
TP_fast_assign(__entry->op = mc->op;
__entry->nargs = nargs;
memcpy(__entry->args, mc->args, sizeof(unsigned long) * nargs);
memset(__entry->args + nargs, 0, sizeof(unsigned long) * (6 - nargs));
),
TP_printk("op %u%s args [%lx, %lx, %lx, %lx, %lx, %lx]",
__entry->op, xen_hypercall_name(__entry->op),
__entry->args[0], __entry->args[1], __entry->args[2],
__entry->args[3], __entry->args[4], __entry->args[5])
);
TRACE_EVENT(xen_mc_entry_alloc,
TP_PROTO(size_t args),
TP_ARGS(args),
TP_STRUCT__entry(
__field(size_t, args)
),
TP_fast_assign(__entry->args = args),
TP_printk("alloc entry %zu arg bytes", __entry->args)
);
TRACE_EVENT(xen_mc_callback,
TP_PROTO(xen_mc_callback_fn_t fn, void *data),
TP_ARGS(fn, data),
TP_STRUCT__entry(
__field(xen_mc_callback_fn_t, fn)
__field(void *, data)
),
TP_fast_assign(
__entry->fn = fn;
__entry->data = data;
),
TP_printk("callback %pf, data %p",
__entry->fn, __entry->data)
);
TRACE_EVENT(xen_mc_flush_reason,
TP_PROTO(enum xen_mc_flush_reason reason),
TP_ARGS(reason),
TP_STRUCT__entry(
__field(enum xen_mc_flush_reason, reason)
),
TP_fast_assign(__entry->reason = reason),
TP_printk("flush reason %s",
(__entry->reason == XEN_MC_FL_NONE) ? "NONE" :
(__entry->reason == XEN_MC_FL_BATCH) ? "BATCH" :
(__entry->reason == XEN_MC_FL_ARGS) ? "ARGS" :
(__entry->reason == XEN_MC_FL_CALLBACK) ? "CALLBACK" : "??")
);
TRACE_EVENT(xen_mc_flush,
TP_PROTO(unsigned mcidx, unsigned argidx, unsigned cbidx),
TP_ARGS(mcidx, argidx, cbidx),
TP_STRUCT__entry(
__field(unsigned, mcidx)
__field(unsigned, argidx)
__field(unsigned, cbidx)
),
TP_fast_assign(__entry->mcidx = mcidx;
__entry->argidx = argidx;
__entry->cbidx = cbidx),
TP_printk("flushing %u hypercalls, %u arg bytes, %u callbacks",
__entry->mcidx, __entry->argidx, __entry->cbidx)
);
TRACE_EVENT(xen_mc_extend_args,
TP_PROTO(unsigned long op, size_t args, enum xen_mc_extend_args res),
TP_ARGS(op, args, res),
TP_STRUCT__entry(
__field(unsigned int, op)
__field(size_t, args)
__field(enum xen_mc_extend_args, res)
),
TP_fast_assign(__entry->op = op;
__entry->args = args;
__entry->res = res),
TP_printk("extending op %u%s by %zu bytes res %s",
__entry->op, xen_hypercall_name(__entry->op),
__entry->args,
__entry->res == XEN_MC_XE_OK ? "OK" :
__entry->res == XEN_MC_XE_BAD_OP ? "BAD_OP" :
__entry->res == XEN_MC_XE_NO_SPACE ? "NO_SPACE" : "???")
);
/* mmu */
DECLARE_EVENT_CLASS(xen_mmu__set_pte,
TP_PROTO(pte_t *ptep, pte_t pteval),
TP_ARGS(ptep, pteval),
TP_STRUCT__entry(
__field(pte_t *, ptep)
__field(pteval_t, pteval)
),
TP_fast_assign(__entry->ptep = ptep;
__entry->pteval = pteval.pte),
TP_printk("ptep %p pteval %0*llx (raw %0*llx)",
__entry->ptep,
(int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
(int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
);
#define DEFINE_XEN_MMU_SET_PTE(name) \
DEFINE_EVENT(xen_mmu__set_pte, name, \
TP_PROTO(pte_t *ptep, pte_t pteval), \
TP_ARGS(ptep, pteval))
DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte);
DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte_atomic);
TRACE_EVENT(xen_mmu_set_domain_pte,
TP_PROTO(pte_t *ptep, pte_t pteval, unsigned domid),
TP_ARGS(ptep, pteval, domid),
TP_STRUCT__entry(
__field(pte_t *, ptep)
__field(pteval_t, pteval)
__field(unsigned, domid)
),
TP_fast_assign(__entry->ptep = ptep;
__entry->pteval = pteval.pte;
__entry->domid = domid),
TP_printk("ptep %p pteval %0*llx (raw %0*llx) domid %u",
__entry->ptep,
(int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
(int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval,
__entry->domid)
);
TRACE_EVENT(xen_mmu_set_pte_at,
TP_PROTO(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval),
TP_ARGS(mm, addr, ptep, pteval),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
__field(unsigned long, addr)
__field(pte_t *, ptep)
__field(pteval_t, pteval)
),
TP_fast_assign(__entry->mm = mm;
__entry->addr = addr;
__entry->ptep = ptep;
__entry->pteval = pteval.pte),
TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)",
__entry->mm, __entry->addr, __entry->ptep,
(int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
(int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
);
TRACE_EVENT(xen_mmu_pte_clear,
TP_PROTO(struct mm_struct *mm, unsigned long addr, pte_t *ptep),
TP_ARGS(mm, addr, ptep),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
__field(unsigned long, addr)
__field(pte_t *, ptep)
),
TP_fast_assign(__entry->mm = mm;
__entry->addr = addr;
__entry->ptep = ptep),
TP_printk("mm %p addr %lx ptep %p",
__entry->mm, __entry->addr, __entry->ptep)
);
TRACE_EVENT(xen_mmu_set_pmd,
TP_PROTO(pmd_t *pmdp, pmd_t pmdval),
TP_ARGS(pmdp, pmdval),
TP_STRUCT__entry(
__field(pmd_t *, pmdp)
__field(pmdval_t, pmdval)
),
TP_fast_assign(__entry->pmdp = pmdp;
__entry->pmdval = pmdval.pmd),
TP_printk("pmdp %p pmdval %0*llx (raw %0*llx)",
__entry->pmdp,
(int)sizeof(pmdval_t) * 2, (unsigned long long)pmd_val(native_make_pmd(__entry->pmdval)),
(int)sizeof(pmdval_t) * 2, (unsigned long long)__entry->pmdval)
);
TRACE_EVENT(xen_mmu_pmd_clear,
TP_PROTO(pmd_t *pmdp),
TP_ARGS(pmdp),
TP_STRUCT__entry(
__field(pmd_t *, pmdp)
),
TP_fast_assign(__entry->pmdp = pmdp),
TP_printk("pmdp %p", __entry->pmdp)
);
#if CONFIG_PGTABLE_LEVELS >= 4
TRACE_EVENT(xen_mmu_set_pud,
TP_PROTO(pud_t *pudp, pud_t pudval),
TP_ARGS(pudp, pudval),
TP_STRUCT__entry(
__field(pud_t *, pudp)
__field(pudval_t, pudval)
),
TP_fast_assign(__entry->pudp = pudp;
__entry->pudval = native_pud_val(pudval)),
TP_printk("pudp %p pudval %0*llx (raw %0*llx)",
__entry->pudp,
(int)sizeof(pudval_t) * 2, (unsigned long long)pud_val(native_make_pud(__entry->pudval)),
(int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
);
TRACE_EVENT(xen_mmu_set_pgd,
TP_PROTO(pgd_t *pgdp, pgd_t *user_pgdp, pgd_t pgdval),
TP_ARGS(pgdp, user_pgdp, pgdval),
TP_STRUCT__entry(
__field(pgd_t *, pgdp)
__field(pgd_t *, user_pgdp)
__field(pgdval_t, pgdval)
),
TP_fast_assign(__entry->pgdp = pgdp;
__entry->user_pgdp = user_pgdp;
__entry->pgdval = pgdval.pgd),
TP_printk("pgdp %p user_pgdp %p pgdval %0*llx (raw %0*llx)",
__entry->pgdp, __entry->user_pgdp,
(int)sizeof(pgdval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pgdval)),
(int)sizeof(pgdval_t) * 2, (unsigned long long)__entry->pgdval)
);
TRACE_EVENT(xen_mmu_pud_clear,
TP_PROTO(pud_t *pudp),
TP_ARGS(pudp),
TP_STRUCT__entry(
__field(pud_t *, pudp)
),
TP_fast_assign(__entry->pudp = pudp),
TP_printk("pudp %p", __entry->pudp)
);
#else
TRACE_EVENT(xen_mmu_set_pud,
TP_PROTO(pud_t *pudp, pud_t pudval),
TP_ARGS(pudp, pudval),
TP_STRUCT__entry(
__field(pud_t *, pudp)
__field(pudval_t, pudval)
),
TP_fast_assign(__entry->pudp = pudp;
__entry->pudval = native_pud_val(pudval)),
TP_printk("pudp %p pudval %0*llx (raw %0*llx)",
__entry->pudp,
(int)sizeof(pudval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pudval)),
(int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
);
#endif
TRACE_EVENT(xen_mmu_pgd_clear,
TP_PROTO(pgd_t *pgdp),
TP_ARGS(pgdp),
TP_STRUCT__entry(
__field(pgd_t *, pgdp)
),
TP_fast_assign(__entry->pgdp = pgdp),
TP_printk("pgdp %p", __entry->pgdp)
);
DECLARE_EVENT_CLASS(xen_mmu_ptep_modify_prot,
TP_PROTO(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval),
TP_ARGS(mm, addr, ptep, pteval),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
__field(unsigned long, addr)
__field(pte_t *, ptep)
__field(pteval_t, pteval)
),
TP_fast_assign(__entry->mm = mm;
__entry->addr = addr;
__entry->ptep = ptep;
__entry->pteval = pteval.pte),
TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)",
__entry->mm, __entry->addr, __entry->ptep,
(int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
(int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
);
#define DEFINE_XEN_MMU_PTEP_MODIFY_PROT(name) \
DEFINE_EVENT(xen_mmu_ptep_modify_prot, name, \
TP_PROTO(struct mm_struct *mm, unsigned long addr, \
pte_t *ptep, pte_t pteval), \
TP_ARGS(mm, addr, ptep, pteval))
DEFINE_XEN_MMU_PTEP_MODIFY_PROT(xen_mmu_ptep_modify_prot_start);
DEFINE_XEN_MMU_PTEP_MODIFY_PROT(xen_mmu_ptep_modify_prot_commit);
TRACE_EVENT(xen_mmu_alloc_ptpage,
TP_PROTO(struct mm_struct *mm, unsigned long pfn, unsigned level, bool pinned),
TP_ARGS(mm, pfn, level, pinned),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
__field(unsigned long, pfn)
__field(unsigned, level)
__field(bool, pinned)
),
TP_fast_assign(__entry->mm = mm;
__entry->pfn = pfn;
__entry->level = level;
__entry->pinned = pinned),
TP_printk("mm %p pfn %lx level %d %spinned",
__entry->mm, __entry->pfn, __entry->level,
__entry->pinned ? "" : "un")
);
TRACE_EVENT(xen_mmu_release_ptpage,
TP_PROTO(unsigned long pfn, unsigned level, bool pinned),
TP_ARGS(pfn, level, pinned),
TP_STRUCT__entry(
__field(unsigned long, pfn)
__field(unsigned, level)
__field(bool, pinned)
),
TP_fast_assign(__entry->pfn = pfn;
__entry->level = level;
__entry->pinned = pinned),
TP_printk("pfn %lx level %d %spinned",
__entry->pfn, __entry->level,
__entry->pinned ? "" : "un")
);
DECLARE_EVENT_CLASS(xen_mmu_pgd,
TP_PROTO(struct mm_struct *mm, pgd_t *pgd),
TP_ARGS(mm, pgd),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
__field(pgd_t *, pgd)
),
TP_fast_assign(__entry->mm = mm;
__entry->pgd = pgd),
TP_printk("mm %p pgd %p", __entry->mm, __entry->pgd)
);
#define DEFINE_XEN_MMU_PGD_EVENT(name) \
DEFINE_EVENT(xen_mmu_pgd, name, \
TP_PROTO(struct mm_struct *mm, pgd_t *pgd), \
TP_ARGS(mm, pgd))
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
TRACE_EVENT(xen_mmu_flush_tlb_all,
TP_PROTO(int x),
TP_ARGS(x),
TP_STRUCT__entry(__array(char, x, 0)),
TP_fast_assign((void)x),
TP_printk("%s", "")
);
TRACE_EVENT(xen_mmu_flush_tlb,
TP_PROTO(int x),
TP_ARGS(x),
TP_STRUCT__entry(__array(char, x, 0)),
TP_fast_assign((void)x),
TP_printk("%s", "")
);
TRACE_EVENT(xen_mmu_flush_tlb_single,
TP_PROTO(unsigned long addr),
TP_ARGS(addr),
TP_STRUCT__entry(
__field(unsigned long, addr)
),
TP_fast_assign(__entry->addr = addr),
TP_printk("addr %lx", __entry->addr)
);
TRACE_EVENT(xen_mmu_flush_tlb_others,
TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm,
x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range x86 has no flush_tlb_range support in instruction level. Currently the flush_tlb_range just implemented by flushing all page table. That is not the best solution for all scenarios. In fact, if we just use 'invlpg' to flush few lines from TLB, we can get the performance gain from later remain TLB lines accessing. But the 'invlpg' instruction costs much of time. Its execution time can compete with cr3 rewriting, and even a bit more on SNB CPU. So, on a 512 4KB TLB entries CPU, the balance points is at: (512 - X) * 100ns(assumed TLB refill cost) = X(TLB flush entries) * 100ns(assumed invlpg cost) Here, X is 256, that is 1/2 of 512 entries. But with the mysterious CPU pre-fetcher and page miss handler Unit, the assumed TLB refill cost is far lower then 100ns in sequential access. And 2 HT siblings in one core makes the memory access more faster if they are accessing the same memory. So, in the patch, I just do the change when the target entries is less than 1/16 of whole active tlb entries. Actually, I have no data support for the percentage '1/16', so any suggestions are welcomed. As to hugetlb, guess due to smaller page table, and smaller active TLB entries, I didn't see benefit via my benchmark, so no optimizing now. My micro benchmark show in ideal scenarios, the performance improves 70 percent in reading. And in worst scenario, the reading/writing performance is similar with unpatched 3.4-rc4 kernel. Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP 'always': multi thread testing, '-t' paramter is thread number: with patch unpatched 3.4-rc4 ./mprotect -t 1 14ns 24ns ./mprotect -t 2 13ns 22ns ./mprotect -t 4 12ns 19ns ./mprotect -t 8 14ns 16ns ./mprotect -t 16 28ns 26ns ./mprotect -t 32 54ns 51ns ./mprotect -t 128 200ns 199ns Single process with sequencial flushing and memory accessing: with patch unpatched 3.4-rc4 ./mprotect 7ns 11ns ./mprotect -p 4096 -l 8 -n 10240 21ns 21ns [ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com has additional performance numbers. ] Signed-off-by: Alex Shi <alex.shi@intel.com> Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2012-06-28 09:02:17 +08:00
unsigned long addr, unsigned long end),
TP_ARGS(cpus, mm, addr, end),
TP_STRUCT__entry(
__field(unsigned, ncpus)
__field(struct mm_struct *, mm)
__field(unsigned long, addr)
x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range x86 has no flush_tlb_range support in instruction level. Currently the flush_tlb_range just implemented by flushing all page table. That is not the best solution for all scenarios. In fact, if we just use 'invlpg' to flush few lines from TLB, we can get the performance gain from later remain TLB lines accessing. But the 'invlpg' instruction costs much of time. Its execution time can compete with cr3 rewriting, and even a bit more on SNB CPU. So, on a 512 4KB TLB entries CPU, the balance points is at: (512 - X) * 100ns(assumed TLB refill cost) = X(TLB flush entries) * 100ns(assumed invlpg cost) Here, X is 256, that is 1/2 of 512 entries. But with the mysterious CPU pre-fetcher and page miss handler Unit, the assumed TLB refill cost is far lower then 100ns in sequential access. And 2 HT siblings in one core makes the memory access more faster if they are accessing the same memory. So, in the patch, I just do the change when the target entries is less than 1/16 of whole active tlb entries. Actually, I have no data support for the percentage '1/16', so any suggestions are welcomed. As to hugetlb, guess due to smaller page table, and smaller active TLB entries, I didn't see benefit via my benchmark, so no optimizing now. My micro benchmark show in ideal scenarios, the performance improves 70 percent in reading. And in worst scenario, the reading/writing performance is similar with unpatched 3.4-rc4 kernel. Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP 'always': multi thread testing, '-t' paramter is thread number: with patch unpatched 3.4-rc4 ./mprotect -t 1 14ns 24ns ./mprotect -t 2 13ns 22ns ./mprotect -t 4 12ns 19ns ./mprotect -t 8 14ns 16ns ./mprotect -t 16 28ns 26ns ./mprotect -t 32 54ns 51ns ./mprotect -t 128 200ns 199ns Single process with sequencial flushing and memory accessing: with patch unpatched 3.4-rc4 ./mprotect 7ns 11ns ./mprotect -p 4096 -l 8 -n 10240 21ns 21ns [ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com has additional performance numbers. ] Signed-off-by: Alex Shi <alex.shi@intel.com> Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2012-06-28 09:02:17 +08:00
__field(unsigned long, end)
),
TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
__entry->mm = mm;
x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range x86 has no flush_tlb_range support in instruction level. Currently the flush_tlb_range just implemented by flushing all page table. That is not the best solution for all scenarios. In fact, if we just use 'invlpg' to flush few lines from TLB, we can get the performance gain from later remain TLB lines accessing. But the 'invlpg' instruction costs much of time. Its execution time can compete with cr3 rewriting, and even a bit more on SNB CPU. So, on a 512 4KB TLB entries CPU, the balance points is at: (512 - X) * 100ns(assumed TLB refill cost) = X(TLB flush entries) * 100ns(assumed invlpg cost) Here, X is 256, that is 1/2 of 512 entries. But with the mysterious CPU pre-fetcher and page miss handler Unit, the assumed TLB refill cost is far lower then 100ns in sequential access. And 2 HT siblings in one core makes the memory access more faster if they are accessing the same memory. So, in the patch, I just do the change when the target entries is less than 1/16 of whole active tlb entries. Actually, I have no data support for the percentage '1/16', so any suggestions are welcomed. As to hugetlb, guess due to smaller page table, and smaller active TLB entries, I didn't see benefit via my benchmark, so no optimizing now. My micro benchmark show in ideal scenarios, the performance improves 70 percent in reading. And in worst scenario, the reading/writing performance is similar with unpatched 3.4-rc4 kernel. Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP 'always': multi thread testing, '-t' paramter is thread number: with patch unpatched 3.4-rc4 ./mprotect -t 1 14ns 24ns ./mprotect -t 2 13ns 22ns ./mprotect -t 4 12ns 19ns ./mprotect -t 8 14ns 16ns ./mprotect -t 16 28ns 26ns ./mprotect -t 32 54ns 51ns ./mprotect -t 128 200ns 199ns Single process with sequencial flushing and memory accessing: with patch unpatched 3.4-rc4 ./mprotect 7ns 11ns ./mprotect -p 4096 -l 8 -n 10240 21ns 21ns [ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com has additional performance numbers. ] Signed-off-by: Alex Shi <alex.shi@intel.com> Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2012-06-28 09:02:17 +08:00
__entry->addr = addr,
__entry->end = end),
TP_printk("ncpus %d mm %p addr %lx, end %lx",
__entry->ncpus, __entry->mm, __entry->addr, __entry->end)
);
TRACE_EVENT(xen_mmu_write_cr3,
TP_PROTO(bool kernel, unsigned long cr3),
TP_ARGS(kernel, cr3),
TP_STRUCT__entry(
__field(bool, kernel)
__field(unsigned long, cr3)
),
TP_fast_assign(__entry->kernel = kernel;
__entry->cr3 = cr3),
TP_printk("%s cr3 %lx",
__entry->kernel ? "kernel" : "user", __entry->cr3)
);
/* CPU */
TRACE_EVENT(xen_cpu_write_ldt_entry,
TP_PROTO(struct desc_struct *dt, int entrynum, u64 desc),
TP_ARGS(dt, entrynum, desc),
TP_STRUCT__entry(
__field(struct desc_struct *, dt)
__field(int, entrynum)
__field(u64, desc)
),
TP_fast_assign(__entry->dt = dt;
__entry->entrynum = entrynum;
__entry->desc = desc;
),
TP_printk("dt %p entrynum %d entry %016llx",
__entry->dt, __entry->entrynum,
(unsigned long long)__entry->desc)
);
TRACE_EVENT(xen_cpu_write_idt_entry,
TP_PROTO(gate_desc *dt, int entrynum, const gate_desc *ent),
TP_ARGS(dt, entrynum, ent),
TP_STRUCT__entry(
__field(gate_desc *, dt)
__field(int, entrynum)
),
TP_fast_assign(__entry->dt = dt;
__entry->entrynum = entrynum;
),
TP_printk("dt %p entrynum %d",
__entry->dt, __entry->entrynum)
);
TRACE_EVENT(xen_cpu_load_idt,
TP_PROTO(const struct desc_ptr *desc),
TP_ARGS(desc),
TP_STRUCT__entry(
__field(unsigned long, addr)
),
TP_fast_assign(__entry->addr = desc->address),
TP_printk("addr %lx", __entry->addr)
);
TRACE_EVENT(xen_cpu_write_gdt_entry,
TP_PROTO(struct desc_struct *dt, int entrynum, const void *desc, int type),
TP_ARGS(dt, entrynum, desc, type),
TP_STRUCT__entry(
__field(u64, desc)
__field(struct desc_struct *, dt)
__field(int, entrynum)
__field(int, type)
),
TP_fast_assign(__entry->dt = dt;
__entry->entrynum = entrynum;
__entry->desc = *(u64 *)desc;
__entry->type = type;
),
TP_printk("dt %p entrynum %d type %d desc %016llx",
__entry->dt, __entry->entrynum, __entry->type,
(unsigned long long)__entry->desc)
);
TRACE_EVENT(xen_cpu_set_ldt,
TP_PROTO(const void *addr, unsigned entries),
TP_ARGS(addr, entries),
TP_STRUCT__entry(
__field(const void *, addr)
__field(unsigned, entries)
),
TP_fast_assign(__entry->addr = addr;
__entry->entries = entries),
TP_printk("addr %p entries %u",
__entry->addr, __entry->entries)
);
#endif /* _TRACE_XEN_H */
/* This part must be outside protection */
#include <trace/define_trace.h>