From nobody Wed Nov 5 13:43:34 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zoho.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1498558153283419.27779201160354; Tue, 27 Jun 2017 03:09:13 -0700 (PDT) Received: from localhost ([::1]:51575 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dPnQl-0006ru-FX for importer@patchew.org; Tue, 27 Jun 2017 06:09:11 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:36918) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dPnPz-0006Zg-S8 for qemu-devel@nongnu.org; Tue, 27 Jun 2017 06:08:25 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1dPnPu-0001tA-Rj for qemu-devel@nongnu.org; Tue, 27 Jun 2017 06:08:23 -0400 Received: from roura.ac.upc.es ([147.83.33.10]:52333) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dPnPu-0001st-Aa for qemu-devel@nongnu.org; Tue, 27 Jun 2017 06:08:18 -0400 Received: from correu-2.ac.upc.es (correu-2.ac.upc.es [147.83.30.92]) by roura.ac.upc.es (8.13.8/8.13.8) with ESMTP id v5RA8EOV018036; Tue, 27 Jun 2017 12:08:14 +0200 Received: from localhost (unknown [132.68.53.125]) by correu-2.ac.upc.es (Postfix) with ESMTPSA id 1B7B64B0; Tue, 27 Jun 2017 12:08:08 +0200 (CEST) From: =?utf-8?b?TGx1w61z?= Vilanova To: qemu-devel@nongnu.org Date: Tue, 27 Jun 2017 13:08:08 +0300 Message-Id: <149855808784.4578.3124281738059937565.stgit@frigg.lan> X-Mailer: git-send-email 2.11.0 In-Reply-To: <149855711979.4578.11884555663631849051.stgit@frigg.lan> References: <149855711979.4578.11884555663631849051.stgit@frigg.lan> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-MIME-Autoconverted: from 8bit to quoted-printable by roura.ac.upc.es id v5RA8EOV018036 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6.x [fuzzy] X-Received-From: 147.83.33.10 Subject: [Qemu-devel] [PATCH v9 4/7] exec: [tcg] Use different TBs according to the vCPU's dynamic tracing state X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Eduardo Habkost , Peter Crosthwaite , "Emilio G. Cota" , Stefan Hajnoczi , Paolo Bonzini , Richard Henderson Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Every vCPU now uses a separate set of TBs for each set of dynamic tracing event state values. Each set of TBs can be used by any number of vCPUs to maximize TB reuse when vCPUs have the same tracing state. This feature is later used by tracetool to optimize tracing of guest code events. The maximum number of TB sets is defined as 2^E, where E is the number of events that have the 'vcpu' property (their state is stored in CPUState->trace_dstate). For this to work, a change on the dynamic tracing state of a vCPU will force it to flush its virtual TB cache (which is only indexed by address), and fall back to the physical TB cache (which now contains the vCPU's dynamic tracing state as part of the hashing function). Signed-off-by: Llu=C3=ADs Vilanova Reviewed-by: Richard Henderson --- accel/tcg/cpu-exec.c | 8 ++++++-- accel/tcg/translate-all.c | 11 +++++++++-- include/exec/exec-all.h | 6 ++++++ include/exec/tb-hash-xx.h | 7 +++++-- include/exec/tb-hash.h | 5 +++-- tcg/tcg-runtime.c | 3 ++- tests/qht-bench.c | 2 +- trace/control-target.c | 1 + trace/control.h | 3 +++ 9 files changed, 36 insertions(+), 10 deletions(-) diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index 3581618bc0..d84b01d1b8 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -280,6 +280,7 @@ struct tb_desc { CPUArchState *env; tb_page_addr_t phys_page1; uint32_t flags; + uint32_t trace_vcpu_dstate; }; =20 static bool tb_cmp(const void *p, const void *d) @@ -291,6 +292,7 @@ static bool tb_cmp(const void *p, const void *d) tb->page_addr[0] =3D=3D desc->phys_page1 && tb->cs_base =3D=3D desc->cs_base && tb->flags =3D=3D desc->flags && + tb->trace_vcpu_dstate =3D=3D desc->trace_vcpu_dstate && !atomic_read(&tb->invalid)) { /* check next page if needed */ if (tb->page_addr[1] =3D=3D -1) { @@ -319,10 +321,11 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, tar= get_ulong pc, desc.env =3D (CPUArchState *)cpu->env_ptr; desc.cs_base =3D cs_base; desc.flags =3D flags; + desc.trace_vcpu_dstate =3D *cpu->trace_dstate; desc.pc =3D pc; phys_pc =3D get_page_addr_code(desc.env, pc); desc.phys_page1 =3D phys_pc & TARGET_PAGE_MASK; - h =3D tb_hash_func(phys_pc, pc, flags); + h =3D tb_hash_func(phys_pc, pc, flags, *cpu->trace_dstate); return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h); } =20 @@ -342,7 +345,8 @@ static inline TranslationBlock *tb_find(CPUState *cpu, cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); tb =3D atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]); if (unlikely(!tb || tb->pc !=3D pc || tb->cs_base !=3D cs_base || - tb->flags !=3D flags)) { + tb->flags !=3D flags || + tb->trace_vcpu_dstate !=3D *cpu->trace_dstate)) { tb =3D tb_htable_lookup(cpu, pc, cs_base, flags); if (!tb) { =20 diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 03820e3aeb..71badaaa6b 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -54,6 +54,7 @@ #include "exec/tb-hash.h" #include "translate-all.h" #include "qemu/bitmap.h" +#include "qemu/error-report.h" #include "qemu/timer.h" #include "qemu/main-loop.h" #include "exec/log.h" @@ -112,6 +113,11 @@ typedef struct PageDesc { #define V_L2_BITS 10 #define V_L2_SIZE (1 << V_L2_BITS) =20 +/* Make sure all possible CPU event bits fit in tb->trace_ds */ +QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS > + sizeof(((TranslationBlock *)0)->trace_vcpu_dstate) + * BITS_PER_BYTE); + uintptr_t qemu_host_page_size; intptr_t qemu_host_page_mask; =20 @@ -1102,7 +1108,7 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page= _addr_t page_addr) =20 /* remove the TB from the hash list */ phys_pc =3D tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); - h =3D tb_hash_func(phys_pc, tb->pc, tb->flags); + h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->trace_vcpu_dstate); qht_remove(&tcg_ctx.tb_ctx.htable, tb, h); =20 /* remove the TB from the page list */ @@ -1247,7 +1253,7 @@ static void tb_link_page(TranslationBlock *tb, tb_pag= e_addr_t phys_pc, } =20 /* add in the hash table */ - h =3D tb_hash_func(phys_pc, tb->pc, tb->flags); + h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->trace_vcpu_dstate); qht_insert(&tcg_ctx.tb_ctx.htable, tb, h); =20 #ifdef DEBUG_TB_CHECK @@ -1293,6 +1299,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tb->cs_base =3D cs_base; tb->flags =3D flags; tb->cflags =3D cflags; + tb->trace_vcpu_dstate =3D *cpu->trace_dstate; tb->invalid =3D false; =20 #ifdef CONFIG_PROFILER diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index b0281b000f..d918410944 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -310,6 +310,10 @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced= (CPUState *cpu, #define USE_DIRECT_JUMP #endif =20 +/** + * TranslationBlock: + * @trace_vcpu_dstate: Per-vCPU dynamic tracing state used to generate thi= s TB. + */ struct TranslationBlock { target_ulong pc; /* simulated PC corresponding to this block (EIP + = CS base) */ target_ulong cs_base; /* CS base for this block */ @@ -324,6 +328,8 @@ struct TranslationBlock { #define CF_USE_ICOUNT 0x20000 #define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */ =20 + uint32_t trace_vcpu_dstate; + uint16_t invalid; =20 void *tc_ptr; /* pointer to the translated code */ diff --git a/include/exec/tb-hash-xx.h b/include/exec/tb-hash-xx.h index 2c40b5c466..6cd3022c07 100644 --- a/include/exec/tb-hash-xx.h +++ b/include/exec/tb-hash-xx.h @@ -49,7 +49,7 @@ * contiguous in memory. */ static inline -uint32_t tb_hash_func5(uint64_t a0, uint64_t b0, uint32_t e) +uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f) { uint32_t v1 =3D TB_HASH_XX_SEED + PRIME32_1 + PRIME32_2; uint32_t v2 =3D TB_HASH_XX_SEED + PRIME32_2; @@ -78,11 +78,14 @@ uint32_t tb_hash_func5(uint64_t a0, uint64_t b0, uint32= _t e) v4 *=3D PRIME32_1; =20 h32 =3D rol32(v1, 1) + rol32(v2, 7) + rol32(v3, 12) + rol32(v4, 18); - h32 +=3D 20; + h32 +=3D 24; =20 h32 +=3D e * PRIME32_3; h32 =3D rol32(h32, 17) * PRIME32_4; =20 + h32 +=3D f * PRIME32_3; + h32 =3D rol32(h32, 17) * PRIME32_4; + h32 ^=3D h32 >> 15; h32 *=3D PRIME32_2; h32 ^=3D h32 >> 13; diff --git a/include/exec/tb-hash.h b/include/exec/tb-hash.h index b1fe2d0161..17b5ee0edf 100644 --- a/include/exec/tb-hash.h +++ b/include/exec/tb-hash.h @@ -58,9 +58,10 @@ static inline unsigned int tb_jmp_cache_hash_func(target= _ulong pc) #endif /* CONFIG_SOFTMMU */ =20 static inline -uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc, uint32_t fl= ags) +uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc, uint32_t fl= ags, + uint32_t trace_vcpu_dstate) { - return tb_hash_func5(phys_pc, pc, flags); + return tb_hash_func6(phys_pc, pc, flags, trace_vcpu_dstate); } =20 #endif diff --git a/tcg/tcg-runtime.c b/tcg/tcg-runtime.c index ec3a34e461..3e23649dd7 100644 --- a/tcg/tcg-runtime.c +++ b/tcg/tcg-runtime.c @@ -158,7 +158,8 @@ void *HELPER(lookup_tb_ptr)(CPUArchState *env, target_u= long addr) if (unlikely(!(tb && tb->pc =3D=3D addr && tb->cs_base =3D=3D cs_base - && tb->flags =3D=3D flags))) { + && tb->flags =3D=3D flags + && tb->trace_vcpu_dstate =3D=3D *cpu->trace_dstate))) { tb =3D tb_htable_lookup(cpu, addr, cs_base, flags); if (!tb) { return tcg_ctx.code_gen_epilogue; diff --git a/tests/qht-bench.c b/tests/qht-bench.c index 2afa09d859..11c1cec766 100644 --- a/tests/qht-bench.c +++ b/tests/qht-bench.c @@ -103,7 +103,7 @@ static bool is_equal(const void *obj, const void *userp) =20 static inline uint32_t h(unsigned long v) { - return tb_hash_func5(v, 0, 0); + return tb_hash_func6(v, 0, 0, 0); } =20 /* diff --git a/trace/control-target.c b/trace/control-target.c index 9d44566c95..329127873e 100644 --- a/trace/control-target.c +++ b/trace/control-target.c @@ -62,6 +62,7 @@ static void trace_event_synchronize_vcpu_state_dynamic( { bitmap_copy(vcpu->trace_dstate, vcpu->trace_dstate_delayed, trace_get_vcpu_event_count()); + tb_flush_jmp_cache_all(vcpu); } =20 void trace_event_set_vcpu_state_dynamic(CPUState *vcpu, diff --git a/trace/control.h b/trace/control.h index 4ea53e2986..b931824d60 100644 --- a/trace/control.h +++ b/trace/control.h @@ -165,6 +165,9 @@ void trace_event_set_state_dynamic(TraceEvent *ev, bool= state); * Set the dynamic tracing state of an event for the given vCPU. * * Pre-condition: trace_event_get_vcpu_state_static(ev) =3D=3D true + * + * Note: Changes for execution-time events with the 'tcg' property will no= t be + * propagated until the next TB is executed (iff executing in TCG mo= de). */ void trace_event_set_vcpu_state_dynamic(CPUState *vcpu, TraceEvent *ev, bool state);