From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from [87.239.111.99] (localhost [127.0.0.1]) by dev.tarantool.org (Postfix) with ESMTP id B48C06ECE8; Wed, 6 Apr 2022 15:50:16 +0300 (MSK) DKIM-Filter: OpenDKIM Filter v2.11.0 dev.tarantool.org B48C06ECE8 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=tarantool.org; s=dev; t=1649249416; bh=V5aOznNIAiqBFcQfUD07L88Y1795pZRRkUpDtSLU5c0=; h=To:Date:In-Reply-To:References:Subject:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To: From; b=B/Rn4JqBnA2UlK2Hcswb66/U9u93b+KgYFDrZgHuRvPaer4+TBSSl99QRqAI9wUbq 2pLyFyVh98QBUNxxlEAWhvQgN6AkgIUeBNmpgCxwfbVSKFwJXIbx6LoLelZp1Gm9/E iUQcvWGFZRFeAeROJKd3n/QmpJhMC0kgYeO+E20E= Received: from mail-lf1-f47.google.com (mail-lf1-f47.google.com [209.85.167.47]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by dev.tarantool.org (Postfix) with ESMTPS id 3EBBF6ECE8 for ; Wed, 6 Apr 2022 15:49:47 +0300 (MSK) DKIM-Filter: OpenDKIM Filter v2.11.0 dev.tarantool.org 3EBBF6ECE8 Received: by mail-lf1-f47.google.com with SMTP id h7so3939466lfl.2 for ; Wed, 06 Apr 2022 05:49:47 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=dobhLzqSiCkI1fNGZcoAUaIzAtldmSMUpHATj4Aviio=; b=SvMqDGfEx7n4WlvW2w46WkFrPz1ABVn5BqF1vqFhh7QeMPYq2aRzx1hy5g8GM2hoqU W0mN+ZmKJUdFRNGPa0twvIULF4dyKq+TQov8DCUe1LjUSgJk8JYt6RA6rpIZGan3shzC T3D33cpUw0xzNC9N11qEtygdl91HhqI3IGe8e+m6HLeafWDgvWCLUwq9KfEalHvF3bzf Ux2vT5WnSAWPYEObGeRIZfXIjOcOvpLw6rOPyQ4CdIfcuPhwf5awyvm+Ot5mqdg7b7Fm kUTmevgYaitlttY/qRQCmNQcnJryXhHYBfMLU+aSw3kzEsmEBqCZzijilZ4d76a5D9nD z/vA== X-Gm-Message-State: AOAM532iJoD2gpXQMvfXu/N6pgmFIRoXSC14sKO5w6YPlcswxwWMOqLc iM0v6PTzwPpGXOHliH+8/gU0IoCflbRCtQ== X-Google-Smtp-Source: ABdhPJwXH2Kz5e35rRqv1BHAsaxf62vs4g/Y5pDKOhOKHTVqhp9209aCR8NXr4DrMuG7GabxaF0TzQ== X-Received: by 2002:a05:6512:318a:b0:44a:be25:7082 with SMTP id i10-20020a056512318a00b0044abe257082mr6043591lfe.439.1649249385962; Wed, 06 Apr 2022 05:49:45 -0700 (PDT) Received: from localhost.localdomain ([93.175.28.20]) by smtp.gmail.com with ESMTPSA id i25-20020a0565123e1900b0044a2908b040sm1821375lfv.115.2022.04.06.05.49.45 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 06 Apr 2022 05:49:45 -0700 (PDT) X-Google-Original-From: Maxim Kokryashkin To: tarantool-patches@dev.tarantool.org, imun@tarantool.org, skaplun@tarantool.org Date: Wed, 6 Apr 2022 15:49:33 +0300 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: [Tarantool-patches] [PATCH luajit v3 1/7] vm: save topframe info into global_State X-BeenThere: tarantool-patches@dev.tarantool.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: Tarantool development patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , From: Maxim Kokryashkin via Tarantool-patches Reply-To: Maxim Kokryashkin Errors-To: tarantool-patches-bounces@dev.tarantool.org Sender: "Tarantool-patches" From: Mikhail Shishatskiy Since commit 111d377d524e54e02187148a1832683291d620b2 ('vm: introduce VM states for Lua and fast functions') the VM has LFUNC and FFUNC states. The upcoming sampling profiler uses these vmstates to determine if the guest stack is valid or not. So, we need to provide a There is an inconsistent behavior of the VM when the Lua stack is not valid, but the state is set to LFUNC. This patch is just a gross hack with which the profiler works fine. The problem is to be investigated more deeply :( --- src/lj_obj.h | 12 ++++++++++++ src/vm_x64.dasc | 52 +++++++++++++++++++++++++++++++++++++++---------- src/vm_x86.dasc | 52 +++++++++++++++++++++++++++++++++++++++---------- 3 files changed, 96 insertions(+), 20 deletions(-) diff --git a/src/lj_obj.h b/src/lj_obj.h index d26e60be..b76c3155 100644 --- a/src/lj_obj.h +++ b/src/lj_obj.h @@ -514,6 +514,17 @@ typedef struct GCtab { #define setfreetop(t, n, v) (setmref((n)->freetop, (v))) #endif +/* -- Misc objects -------------------------------------------------------- */ + +struct lj_sysprof_topframe { + uint8_t ffid; /* FFUNC: fast function id. */ + union { + uint64_t raw; /* Raw value for context save/restore. */ + TValue *interp_base; /* LFUNC: Base of the executed coroutine. */ + lua_CFunction cf; /* CFUNC: Address of the C function. */ + } guesttop; +}; + /* -- State objects ------------------------------------------------------- */ /* VM states. */ @@ -674,6 +685,7 @@ typedef struct global_State { MRef jit_base; /* Current JIT code L->base or NULL. */ MRef ctype_state; /* Pointer to C type state. */ GCRef gcroot[GCROOT_MAX]; /* GC roots. */ + struct lj_sysprof_topframe top_frame; /* Top frame for sysprof */ } global_State; #define mainthread(g) (&gcref(g->mainthref)->th) diff --git a/src/vm_x64.dasc b/src/vm_x64.dasc index 974047d3..c4beb5e7 100644 --- a/src/vm_x64.dasc +++ b/src/vm_x64.dasc @@ -345,6 +345,35 @@ | mov dword [DISPATCH+DISPATCH_GL(vmstate)], ~LJ_VMST_..st |.endmacro | +|// Stash interpreter's internal base and enter LFUNC VM state. +|// PROFILER: Each time profiler sees LFUNC state, it will inspect [BASE-1] +|// expecting to see a valid framelink there. So enter this state only when +|// BASE is stable and slots are not moved on the stack. +|.macro set_vmstate_lfunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], BASE +| set_vmstate LFUNC +|.endmacro +| +|// Stash ID of the fast function about to be executed and enter FFUNC VM state. +|// PROFILER: Each time profiler sees FFUNC state, it will write ffid +|// to the profile stream. +|.macro set_vmstate_ffunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov XCHGd, dword [BASE-8] +| mov dword [DISPATCH+DISPATCH_GL(top_frame.ffid)], XCHGd +| set_vmstate FFUNC +|.endmacro +| +|// Stash address of the C function about to be executed and enter CFUNC VM state. +|// PROFILER: Each time profiler sees CFUNC state, it will write this address +|// to the profile stream. +|.macro set_vmstate_cfunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], BASE +| set_vmstate CFUNC +|.endmacro +| |// Uses TMPRd (r10d). |.macro save_vmstate |.if not WIN @@ -435,7 +464,7 @@ static void build_subroutines(BuildCtx *ctx) | jnz ->vm_returnp | | // Return to C. - | set_vmstate CFUNC + | set_vmstate_cfunc | and PC, -8 | sub PC, BASE | neg PC // Previous base = BASE - delta. @@ -467,6 +496,9 @@ static void build_subroutines(BuildCtx *ctx) | xor eax, eax // Ok return status for vm_pcall. | |->vm_leave_unw: + | set_vmstate INTERP // Guard for non-atomic VM context restoration + | mov XCHGd, L:RBa->base + | mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], XCHGd | // DISPATCH required to set properly. | restore_vmstate // Caveat: uses TMPRd (r10d). | restoreregs @@ -725,7 +757,7 @@ static void build_subroutines(BuildCtx *ctx) | cleartp LFUNC:KBASE | mov KBASE, LFUNC:KBASE->pc | mov KBASE, [KBASE+PC2PROTO(k)] - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | // BASE = base, RC = result, RB = meta base | jmp RA // Jump to continuation. | @@ -1166,7 +1198,7 @@ static void build_subroutines(BuildCtx *ctx) | |.macro .ffunc, name |->ff_ .. name: - | set_vmstate FFUNC + | set_vmstate_ffunc |.endmacro | |.macro .ffunc_1, name @@ -1748,7 +1780,7 @@ static void build_subroutines(BuildCtx *ctx) | movzx RAd, PC_RA | neg RA | lea BASE, [BASE+RA*8-16] // base = base - (RA+2)*8 - | set_vmstate LFUNC // LFUNC state after BASE restoration. + | set_vmstate_lfunc // LFUNC state after BASE restoration. | ins_next | |6: // Fill up results with nil. @@ -2513,7 +2545,7 @@ static void build_subroutines(BuildCtx *ctx) | mov KBASE, [KBASE+PC2PROTO(k)] | mov L:RB->base, BASE | mov qword [DISPATCH+DISPATCH_GL(jit_base)], 0 - | set_vmstate LFUNC // LFUNC after BASE & KBASE restoration. + | set_vmstate_lfunc // LFUNC after BASE & KBASE restoration. | // Modified copy of ins_next which handles function header dispatch, too. | mov RCd, [PC] | movzx RAd, RCH @@ -2730,7 +2762,7 @@ static void build_subroutines(BuildCtx *ctx) | call extern lj_ccallback_enter // (CTState *cts, void *cf) | // lua_State * returned in eax (RD). | mov BASE, L:RD->base - | set_vmstate LFUNC // LFUNC after BASE restoration. + | set_vmstate_lfunc // LFUNC after BASE restoration. | mov RD, L:RD->top | sub RD, BASE | mov LFUNC:RB, [BASE-16] @@ -4299,7 +4331,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | mov KBASE, LFUNC:KBASE->pc | mov KBASE, [KBASE+PC2PROTO(k)] | // LFUNC after the old BASE & KBASE is restored. - | set_vmstate LFUNC + | set_vmstate_lfunc | ins_next | |6: // Fill up results with nil. @@ -4591,7 +4623,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | ins_AD // BASE = new base, RA = framesize, RD = nargs+1 | mov KBASE, [PC-4+PC2PROTO(k)] | mov L:RB, SAVE_L - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | lea RA, [BASE+RA*8] // Top of frame. | cmp RA, L:RB->maxstack | ja ->vm_growstack_f @@ -4629,7 +4661,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | mov [RD-8], RB // Store delta + FRAME_VARG. | mov [RD-16], LFUNC:KBASE // Store copy of LFUNC. | mov L:RB, SAVE_L - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | lea RA, [RD+RA*8] | cmp RA, L:RB->maxstack | ja ->vm_growstack_v // Need to grow stack. @@ -4685,7 +4717,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | mov CARG1, L:RB // Caveat: CARG1 may be RA. } | ja ->vm_growstack_c // Need to grow stack. - | set_vmstate CFUNC // CFUNC before entering C function. + | set_vmstate_cfunc // CFUNC before entering C function. if (op == BC_FUNCC) { | call KBASE // (lua_State *L) } else { diff --git a/src/vm_x86.dasc b/src/vm_x86.dasc index ab8e6f27..222754fe 100644 --- a/src/vm_x86.dasc +++ b/src/vm_x86.dasc @@ -443,6 +443,35 @@ | mov dword [DISPATCH+DISPATCH_GL(vmstate)], ~LJ_VMST_..st |.endmacro | +|// Stash interpreter's internal base and enter LFUNC VM state. +|// PROFILER: Each time profiler sees LFUNC state, it will inspect [BASE-1] +|// expecting to see a valid framelink there. So enter this state only when +|// BASE is stable and slots are not moved on the stack. +|.macro set_vmstate_lfunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], BASE +| set_vmstate LFUNC +|.endmacro +| +|// Stash ID of the fast function about to be executed and enter FFUNC VM state. +|// PROFILER: Each time profiler sees FFUNC state, it will write ffid +|// to the profile stream. +|.macro set_vmstate_ffunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov XCHGd, dword [BASE-8] +| mov dword [DISPATCH+DISPATCH_GL(top_frame.ffid)], XCHGd +| set_vmstate FFUNC +|.endmacro +| +|// Stash address of the C function about to be executed and enter CFUNC VM state. +|// PROFILER: Each time profiler sees CFUNC state, it will write this address +|// to the profile stream. +|.macro set_vmstate_cfunc +| set_vmstate INTERP // Guard for non-atomic VM context restoration +| mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], BASE +| set_vmstate CFUNC +|.endmacro +| |// Uses spilled ecx on x86 or XCHGd (r11d) on x64. |.macro save_vmstate |.if not WIN @@ -560,7 +589,7 @@ static void build_subroutines(BuildCtx *ctx) | jnz ->vm_returnp | | // Return to C. - | set_vmstate CFUNC + | set_vmstate_cfunc | and PC, -8 | sub PC, BASE | neg PC // Previous base = BASE - delta. @@ -599,6 +628,9 @@ static void build_subroutines(BuildCtx *ctx) | xor eax, eax // Ok return status for vm_pcall. | |->vm_leave_unw: + | set_vmstate INTERP // Guard for non-atomic VM context restoration + | mov XCHGd, L:RBa->base + | mov dword [DISPATCH+DISPATCH_GL(top_frame.guesttop)], XCHGd | // DISPATCH required to set properly. | restore_vmstate // Caveat: on x64 uses XCHGd (r11d). | restoreregs @@ -934,7 +966,7 @@ static void build_subroutines(BuildCtx *ctx) | mov KBASE, LFUNC:KBASE->pc | mov KBASE, [KBASE+PC2PROTO(k)] | // BASE = base, RC = result, RB = meta base - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | jmp RAa // Jump to continuation. | |.if FFI @@ -1459,7 +1491,7 @@ static void build_subroutines(BuildCtx *ctx) | |.macro .ffunc, name |->ff_ .. name: - | set_vmstate FFUNC + | set_vmstate_ffunc |.endmacro | |.macro .ffunc_1, name @@ -2141,7 +2173,7 @@ static void build_subroutines(BuildCtx *ctx) | movzx RA, PC_RA | not RAa // Note: ~RA = -(RA+1) | lea BASE, [BASE+RA*8] // base = base - (RA+1)*8 - | set_vmstate LFUNC // LFUNC state after BASE restoration. + | set_vmstate_lfunc // LFUNC state after BASE restoration. | ins_next | |6: // Fill up results with nil. @@ -2986,7 +3018,7 @@ static void build_subroutines(BuildCtx *ctx) | mov KBASE, [KBASE+PC2PROTO(k)] | mov L:RB->base, BASE | mov dword [DISPATCH+DISPATCH_GL(jit_base)], 0 - | set_vmstate LFUNC // LFUNC after BASE & KBASE restoration. + | set_vmstate_lfunc // LFUNC after BASE & KBASE restoration. | // Modified copy of ins_next which handles function header dispatch, too. | mov RC, [PC] | movzx RA, RCH @@ -3257,7 +3289,7 @@ static void build_subroutines(BuildCtx *ctx) | call extern lj_ccallback_enter@8 // (CTState *cts, void *cf) | // lua_State * returned in eax (RD). | mov BASE, L:RD->base - | set_vmstate LFUNC // LFUNC after BASE restoration. + | set_vmstate_lfunc // LFUNC after BASE restoration. | mov RD, L:RD->top | sub RD, BASE | mov LFUNC:RB, [BASE-8] @@ -5103,7 +5135,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | mov KBASE, LFUNC:KBASE->pc | mov KBASE, [KBASE+PC2PROTO(k)] | // LFUNC after the old BASE & KBASE is restored. - | set_vmstate LFUNC + | set_vmstate_lfunc | ins_next | |6: // Fill up results with nil. @@ -5391,7 +5423,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | ins_AD // BASE = new base, RA = framesize, RD = nargs+1 | mov KBASE, [PC-4+PC2PROTO(k)] | mov L:RB, SAVE_L - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | lea RA, [BASE+RA*8] // Top of frame. | cmp RA, L:RB->maxstack | ja ->vm_growstack_f @@ -5429,7 +5461,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | mov [RD-4], RB // Store delta + FRAME_VARG. | mov [RD-8], LFUNC:KBASE // Store copy of LFUNC. | mov L:RB, SAVE_L - | set_vmstate LFUNC // LFUNC after KBASE restoration. + | set_vmstate_lfunc // LFUNC after KBASE restoration. | lea RA, [RD+RA*8] | cmp RA, L:RB->maxstack | ja ->vm_growstack_v // Need to grow stack. @@ -5494,7 +5526,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) |.endif } | ja ->vm_growstack_c // Need to grow stack. - | set_vmstate CFUNC // CFUNC before entering C function. + | set_vmstate_cfunc // CFUNC before entering C function. if (op == BC_FUNCC) { | call KBASEa // (lua_State *L) } else { -- 2.35.1