From nobody Wed Dec 17 08:57:20 2025 Received: from mail-pl1-f182.google.com (mail-pl1-f182.google.com [209.85.214.182]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 616E8224B01 for ; Thu, 20 Mar 2025 17:29:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.182 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491777; cv=none; b=nqJRxST2/yBXc79HLW4b4juLoQLG1BL33uWIUWeC7tHQ9u5SpZmu1gDZfzgDVsJ8U1x5SutCqkdH30LEnQXpJXOTfk72qyqpj1Kup9pJiZkbvLpBnsPUc9QP+z32icghqZdKY1KIpRilHf2kfcNH0cPhNWOW2NxYVnTYnnJX4C0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491777; c=relaxed/simple; bh=gaq/v9YuAdYAHAPq6G2li6XLwEhlQb1rcc0R86FQKSc=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=hkoJ1h6wouOyPGYvIXbtAxjh8Tt1nqJaJyk0eo26/WiJavAtO5yNnnCsVmrkYiY8B4BPL2Z/OlZtblEk9tBR3VbzHQCwTyC8Y7sp+tj24jVuBKavFJ32wi4dYTRoI+y2GCeEQzZIPebm6QdPoX3verwt/IddRp2YFXSoqYVSsNw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com; spf=pass smtp.mailfrom=rivosinc.com; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b=rpaaOI3P; arc=none smtp.client-ip=209.85.214.182 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b="rpaaOI3P" Received: by mail-pl1-f182.google.com with SMTP id d9443c01a7336-225b5448519so21384245ad.0 for ; Thu, 20 Mar 2025 10:29:36 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1742491775; x=1743096575; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=R3jS1rl0NyPiPtBrV6gbvaKvWtHD4LTe2LvNMOIdkhU=; b=rpaaOI3PySM22HZ/pfAmiO9vYBmaR5C4g7VXFdDqyhOTfiBcdYcBdglbiVuYCk6DOn MxqA5x64kZr4+jpc1rki4DGPTh1zNUDNMohQs0Q7Pfn34dlslrc0bzh1jGriGZjWl7RD WM0Dgr8aQ1UQipBIXNkPStCCHwgN95KgXqpsa6HHsVLSoE+GUDDyDKsDinqCXDlczfmj 66Dxla/YkCcOcS0Jls26gb4zyYY9OM60BOFw+PasL58D0gb4fjMkAisse5JAzuWkXTcf nKp56wmukvp5q3Ln9TI6e6GZo5vAn07dMrGgFUEaxf6HmxBmOCGjJ0qWb9bk7oNA3A5a FkCw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742491775; x=1743096575; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=R3jS1rl0NyPiPtBrV6gbvaKvWtHD4LTe2LvNMOIdkhU=; b=Kk78ysSDqwwjP2iDF7UwlSGBRufF9xomwOULAvPusHw157GLeMtrjpmsQgDzlM3d+u YwiyOYGNTcipVbJsBbJXI2zG+9M4rHXFrk8gsTbi/OrgbN0hcY0wMr0fR0dg492oddJf w3GBQ/H4D1DNIl2PcHZyyAuM2LDdVTj8goRmlSYobX5E2aqAXrNPVVtEzZgLIdEx0N1b nnKMHYpWVClcupezdyBw6C/Op1ntaG4iyPhOyfC3z+tjHlk4Q1yv/AZr+sFR1O3tyg/c F4FEXZMZsLJzX0EIzplYq9Kmyoxe7uVrkvn+yTI9uATXrJQulxbhqWLmsw8wXovFEsjz 7mhA== X-Forwarded-Encrypted: i=1; AJvYcCX1hLIc2jtW9piYdOOf7h6K3GlMRChsoLW3dEQ1Unv9a0ZPlRjxnC9BpFh40Vyd5c71mbARvKuEUoS2Krs=@vger.kernel.org X-Gm-Message-State: AOJu0YxOlNtrg27D7Y8JfelhtHO2wBaApMUV4xoKEVPAxuDY67IsHc/w Rwy+n6OMtUgBdLO+DdX8QQ8kPCeUrMl8jy+iQM/dMkCdHneEOetzK6K48uL0YzI= X-Gm-Gg: ASbGncswC4zhEykAzEVDNTEkkh/B20JErejOu592gShzq335hTkxx11ja5aHDVBUDZY uk5hNjHCbPH82BD0qKHbBAiur91CSA7BY5Gy5Z651NMOHMH1+lKmfCr16sw8ts6SDW6Qmgo1XIf e/T4PJ90blmqu86sOFXEZ4Ok3dk3Uex4UYvTKwOnfkQAsmUeOLSPLDmVX9BNTiUMw450pLolkGb lzja1B0mQJaZW6WpcS5KK7l6dP2++D0gkvs0NRTYc/Dbubk8cIq9/Ujy1VNRydRwFhfSnS2oyFD 0apTIW0tNLZIvxR2/K2GPioqZxvAakB20pooHIo/dC0/XDvjbYsOLE8q+NPn X-Google-Smtp-Source: AGHT+IEQ1hA26C98UYsq0v49utf4d+ujVyRXt/fsHRytInopHwMDFgd1YulOL9OtsGProEAKKBvvhw== X-Received: by 2002:a17:902:ea07:b0:224:76f:9e59 with SMTP id d9443c01a7336-22780c54d2cmr4749885ad.10.1742491775625; Thu, 20 Mar 2025 10:29:35 -0700 (PDT) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-22780f45994sm554075ad.81.2025.03.20.10.29.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 20 Mar 2025 10:29:34 -0700 (PDT) From: Charlie Jenkins Date: Thu, 20 Mar 2025 10:29:21 -0700 Subject: [PATCH v6 1/4] riscv: entry: Convert ret_from_fork() to C Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250320-riscv_optimize_entry-v6-1-63e187e26041@rivosinc.com> References: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> In-Reply-To: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Huacai Chen , WANG Xuerui , Thomas Gleixner , Peter Zijlstra , Andy Lutomirski , Alexandre Ghiti , Arnd Bergmann , Albert Ou , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, loongarch@lists.linux.dev, Charlie Jenkins X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=3515; i=charlie@rivosinc.com; h=from:subject:message-id; bh=gaq/v9YuAdYAHAPq6G2li6XLwEhlQb1rcc0R86FQKSc=; b=kA0DAAoWjgFid219CPYByyZiAGfcUHrImYiZNCS0BmPPKWSpiEX0ghY/Of3RasTrPX9qN5AB8 4h1BAAWCgAdFiEEDNaAA4XcL3bFFXaQjgFid219CPYFAmfcUHoACgkQjgFid219CPbRkwEAtPKv Ku03MbxplfH795hgrIKj97bZxGVqLUQ7QpkrN6QBAMINRMdaKpxJoDyr+sPeH8RagpPD/EteNBB ZeabOyrgN X-Developer-Key: i=charlie@rivosinc.com; a=openpgp; fpr=7D834FF11B1D8387E61C776FFB10D1F27D6B1354 Move the main section of ret_from_fork() to C to allow inlining of syscall_exit_to_user_mode(). Signed-off-by: Charlie Jenkins Reviewed-by: Alexandre Ghiti --- arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/kernel/entry.S | 15 ++++++--------- arch/riscv/kernel/process.c | 14 ++++++++++++-- 3 files changed, 19 insertions(+), 11 deletions(-) diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/a= sm/asm-prototypes.h index cd627ec289f163a630b73dd03dd52a6b28692997..733ff609778797001006c33bba9= e3cc5b1f15387 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -52,6 +52,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); =20 +asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_r= egs *regs); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 33a5a9f2a0d4e1eeccfb3621b9e518b88e1b0704..b2dc5e7c7b3a843fa4aa02eba2a= 911eb3ce31d1f 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -319,17 +319,14 @@ SYM_CODE_END(handle_kernel_stack_overflow) ASM_NOKPROBE(handle_kernel_stack_overflow) #endif =20 -SYM_CODE_START(ret_from_fork) +SYM_CODE_START(ret_from_fork_asm) call schedule_tail - beqz s0, 1f /* not from kernel thread */ - /* Call fn(arg) */ - move a0, s1 - jalr s0 -1: - move a0, sp /* pt_regs */ - call syscall_exit_to_user_mode + move a0, s1 /* fn_arg */ + move a1, s0 /* fn */ + move a2, sp /* pt_regs */ + call ret_from_fork j ret_from_exception -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_asm) =20 #ifdef CONFIG_IRQ_STACKS /* diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 7c244de7718008947075357ea4502d56419d507c..7b0a0bfe29aec896c2bdd8976d8= 55dd390de88d7 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -17,7 +17,9 @@ #include #include #include +#include =20 +#include #include #include #include @@ -36,7 +38,7 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif =20 -extern asmlinkage void ret_from_fork(void); +extern asmlinkage void ret_from_fork_asm(void); =20 void noinstr arch_cpu_idle(void) { @@ -206,6 +208,14 @@ int arch_dup_task_struct(struct task_struct *dst, stru= ct task_struct *src) return 0; } =20 +asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_r= egs *regs) +{ + if (unlikely(fn)) + fn(fn_arg); + + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *arg= s) { unsigned long clone_flags =3D args->flags; @@ -242,7 +252,7 @@ int copy_thread(struct task_struct *p, const struct ker= nel_clone_args *args) p->thread.riscv_v_flags =3D 0; if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); - p->thread.ra =3D (unsigned long)ret_from_fork; + p->thread.ra =3D (unsigned long)ret_from_fork_asm; p->thread.sp =3D (unsigned long)childregs; /* kernel sp */ return 0; } --=20 2.43.0 From nobody Wed Dec 17 08:57:20 2025 Received: from mail-pl1-f172.google.com (mail-pl1-f172.google.com [209.85.214.172]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 298D42253E1 for ; Thu, 20 Mar 2025 17:29:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491780; cv=none; b=egOc6ypkcNlzvlXXcEg0AQdY0Ui4zTLgfkAOsHZXG9hwqWYwcd1L7yB7wpIyT0TjqaTswP+NuubSKOwtS1IKmslSLpaSQg++EHOuKNwIso0t7GfY+NN7QNL3x/MdaM+CEMTQKEHJ4ceO5VBBKy+sx6f3+Gwa/i0VDkAhN8LoPoo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491780; c=relaxed/simple; bh=LoTSopBOka5A9kpDiPFFurbF+1mjOb81UBycxnBlNbA=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=OzfoIpEiCfxeoj2HNfLsyD1fz4LhcfQZhjSopkt4FupKbcGOt/MZ9YYMZryWtYg8nsEIe8iA5TA2QMhycLTdCYDY5XZswA5VDxbQb1SLYeA4ZXULDTGKzd0hiVBsuL0ssm6OAmgHYks0ANBLPpYrYZDix/RAoBwpBlYAzVJ1UGY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com; spf=pass smtp.mailfrom=rivosinc.com; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b=n9yTv+zU; arc=none smtp.client-ip=209.85.214.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b="n9yTv+zU" Received: by mail-pl1-f172.google.com with SMTP id d9443c01a7336-224100e9a5cso21626785ad.2 for ; Thu, 20 Mar 2025 10:29:37 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1742491777; x=1743096577; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=ehMUm3J1yyvZGiQlan49h9651rjeLktXjDjteQa4YzI=; b=n9yTv+zUXUjrw/BEhsHnIUuQn2/5RoCS3QS5qGbbbFeJy6LiMZD18lFZpv4WNq93NF XkErMFhwf+HX24u7Lm/t1ixbRdHTx7k4wDMrawfYzeSzPlVHrR1z2l65Fn37cpqpz5pH bjs5qCn0A1AV5TJQYftmc/nD0luhKjIBBV54dktOKgfCdau77fK+oX7BUG8uBBRQRmoY kzKsWCsMf2XErLl8EiptMAQeh+POAD5Zcjzf1bgnbtEjui1oJnyT+DsV85z91QYcpmVp i9hCR3s5jxeY/i96XVQC39TaIklXfqNVwHHC3K9Opl/WnZSZVahdACUPo1DLwHCzhV55 7qYg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742491777; x=1743096577; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=ehMUm3J1yyvZGiQlan49h9651rjeLktXjDjteQa4YzI=; b=OeVAiR0/FxXAV/dKugRRdMuk4syooshIk1tA8//o/wWEgLtqNPO0kr++SRze4o+cCv UNEF0FPLAr5PVwyFU6+LFW2OsL4ivdsIjXoMdd6VTO8AAblEQ+2tFETbt+//YmmCptht 3upN8d7PIh+65t47qnTVX93Lc2pFddBWtQbLqvySTJH44CU21pf2dvJAJC54fOUI02Uh ylFq57yGiVJSe65V7V/pVcnNqsqvh3sNy46vgwrlpGYyJiPrlmf+FBWF3FC+/DQ+BVpE MNcK1c0O0BsaA044A1DpzViEZSozUOlQmm8uRz/RhJJqk3WIyV3+aA8iEtLsoA/VsHM1 zoWQ== X-Forwarded-Encrypted: i=1; AJvYcCUvFLGvEsgVOeiilOlyHGsUkWBvOlO5H8HLwROT2c+m0nX7wEfTspdfDVNnaDwDAWWGZnYSB+pQ4RRISdU=@vger.kernel.org X-Gm-Message-State: AOJu0YxeIb5C+WwBQ/3+F5aTiT1MBChjbRSZzDzdfxTo6z8RpmKITaNQ WS0T5EYCzAMDYAu1a2PNywvpo858LCf+j7DP1CaNnUx61GTM2SBY7STCPFV2rWI= X-Gm-Gg: ASbGncuMtUABbCZaWAUPHOsS/bYOT1qSnsltS8e4vzVAEbGJ6P7eRHQRuhzl1g1BJW2 nQKJLA+R0IbYbz5jVg+dAwnprdogDz2R0cexHQ1gloMyekBn0qoj3kANciOq0Plr7ZJzrYfeA0Y Pee6sZeBGq/Cs0TncDAfzm0rZQ/hMhzBIOJWtoOvUuEvU67kE0yY7jEuIMuM/BFcgwtNpLqH36o br1CToDKAqQloB4e8yOgnZigHNMwZt4rDw+kxWofBiBVQqThgYoNrTiOl4ET6FSxDk3EkdjFTu6 YFjrICE+P2Y/tKwcYLSb9OPlkpnB/JlguENBAx1OGibGAE7PBXK6Pbk4L8QW X-Google-Smtp-Source: AGHT+IHosJQQFvVMIroy5HqFrhcvWEZzb29pVdZNHAFlNJkZE8gGcxmxyZzEuwUqug8vYxa+GU6q9w== X-Received: by 2002:a17:902:d4c5:b0:221:7e36:b13e with SMTP id d9443c01a7336-22780c7a32dmr3719635ad.12.1742491777384; Thu, 20 Mar 2025 10:29:37 -0700 (PDT) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-22780f45994sm554075ad.81.2025.03.20.10.29.35 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 20 Mar 2025 10:29:36 -0700 (PDT) From: Charlie Jenkins Date: Thu, 20 Mar 2025 10:29:22 -0700 Subject: [PATCH v6 2/4] riscv: entry: Split ret_from_fork() into user and kernel Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250320-riscv_optimize_entry-v6-2-63e187e26041@rivosinc.com> References: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> In-Reply-To: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Huacai Chen , WANG Xuerui , Thomas Gleixner , Peter Zijlstra , Andy Lutomirski , Alexandre Ghiti , Arnd Bergmann , Albert Ou , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, loongarch@lists.linux.dev, Charlie Jenkins X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=4464; i=charlie@rivosinc.com; h=from:subject:message-id; bh=LoTSopBOka5A9kpDiPFFurbF+1mjOb81UBycxnBlNbA=; b=owGbwMvMwCXWx5hUnlvL8Y3xtFoSQ/qdgKoixkOt4od/iEifL9zYlhO5zOWE7Vw5m4ApZ998y O14lMvdUcrCIMbFICumyMJzrYG59Y5+2VHRsgkwc1iZQIYwcHEKwEQ2pDL8d4p6u1r9XZ/p36Ph jJrvuJPnX6/4mvmoWWO2f7i9ULmTNcNfuVlX/l06sK2ofs2Kdtmgf/l/nq4y9epjOXvN4/StFeu UuAA= X-Developer-Key: i=charlie@rivosinc.com; a=openpgp; fpr=7D834FF11B1D8387E61C776FFB10D1F27D6B1354 This function was unified into a single function in commit ab9164dae273 ("riscv: entry: Consolidate ret_from_kernel_thread into ret_from_fork"). However that imposed a performance degradation. Partially reverting this commit to have ret_from_fork() split again results in a 1% increase on the number of times fork is able to be called per second. Signed-off-by: Charlie Jenkins Acked-by: Alexandre Ghiti --- arch/riscv/include/asm/asm-prototypes.h | 3 ++- arch/riscv/kernel/entry.S | 13 ++++++++++--- arch/riscv/kernel/process.c | 17 +++++++++++------ 3 files changed, 23 insertions(+), 10 deletions(-) diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/a= sm/asm-prototypes.h index 733ff609778797001006c33bba9e3cc5b1f15387..bfc8ea5f9319b19449ec59493b4= 5b926df888832 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -52,7 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); =20 -asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_r= egs *regs); +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), stru= ct pt_regs *regs); +asmlinkage void ret_from_fork_user(struct pt_regs *regs); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index b2dc5e7c7b3a843fa4aa02eba2a911eb3ce31d1f..0fb338000c6dc0358742cd03497= fa54b9e9d1aec 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -319,14 +319,21 @@ SYM_CODE_END(handle_kernel_stack_overflow) ASM_NOKPROBE(handle_kernel_stack_overflow) #endif =20 -SYM_CODE_START(ret_from_fork_asm) +SYM_CODE_START(ret_from_fork_kernel_asm) call schedule_tail move a0, s1 /* fn_arg */ move a1, s0 /* fn */ move a2, sp /* pt_regs */ - call ret_from_fork + call ret_from_fork_kernel j ret_from_exception -SYM_CODE_END(ret_from_fork_asm) +SYM_CODE_END(ret_from_fork_kernel_asm) + +SYM_CODE_START(ret_from_fork_user_asm) + call schedule_tail + move a0, sp /* pt_regs */ + call ret_from_fork_user + j ret_from_exception +SYM_CODE_END(ret_from_fork_user_asm) =20 #ifdef CONFIG_IRQ_STACKS /* diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 7b0a0bfe29aec896c2bdd8976d855dd390de88d7..485ec7a80a56097e8905cd6395a= f29633846b5c8 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -38,7 +38,8 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif =20 -extern asmlinkage void ret_from_fork_asm(void); +extern asmlinkage void ret_from_fork_kernel_asm(void); +extern asmlinkage void ret_from_fork_user_asm(void); =20 void noinstr arch_cpu_idle(void) { @@ -208,14 +209,18 @@ int arch_dup_task_struct(struct task_struct *dst, str= uct task_struct *src) return 0; } =20 -asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_r= egs *regs) +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), stru= ct pt_regs *regs) { - if (unlikely(fn)) - fn(fn_arg); + fn(fn_arg); =20 syscall_exit_to_user_mode(regs); } =20 +asmlinkage void ret_from_fork_user(struct pt_regs *regs) +{ + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *arg= s) { unsigned long clone_flags =3D args->flags; @@ -238,6 +243,7 @@ int copy_thread(struct task_struct *p, const struct ker= nel_clone_args *args) =20 p->thread.s[0] =3D (unsigned long)args->fn; p->thread.s[1] =3D (unsigned long)args->fn_arg; + p->thread.ra =3D (unsigned long)ret_from_fork_kernel_asm; } else { *childregs =3D *(current_pt_regs()); /* Turn off status.VS */ @@ -247,12 +253,11 @@ int copy_thread(struct task_struct *p, const struct k= ernel_clone_args *args) if (clone_flags & CLONE_SETTLS) childregs->tp =3D tls; childregs->a0 =3D 0; /* Return value of fork() */ - p->thread.s[0] =3D 0; + p->thread.ra =3D (unsigned long)ret_from_fork_user_asm; } p->thread.riscv_v_flags =3D 0; if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); - p->thread.ra =3D (unsigned long)ret_from_fork_asm; p->thread.sp =3D (unsigned long)childregs; /* kernel sp */ return 0; } --=20 2.43.0 From nobody Wed Dec 17 08:57:20 2025 Received: from mail-pl1-f175.google.com (mail-pl1-f175.google.com [209.85.214.175]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1C963225775 for ; Thu, 20 Mar 2025 17:29:39 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.175 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491781; cv=none; b=P6BnKof3BCNC9g730AWDeFUKuH1ZvFf+VOJ0FWZHCjExzBvHQNzkzAnd+CJkDo8P8JnSzUTOJ1alnH/UkFGJ46yUthoyDMaG5IGFQh9us0OSIHqomnFWzgKJrPVJxhyPWZ9Jl+S98WNy2PqSdJ6EOJ+rqRCEu9UG4q+oKCLgwPs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491781; c=relaxed/simple; bh=ji6jPR39ZKDby+guv8CCAiBLyKbpGz9Kynms9BH9fJU=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=YOMWUCchRL4M2LcWUkQzjzbccqKrQJpYerkySeuM0OWtBmSFrotIUKJBh2uSrVohBc+MkTBoKoxKWUn04uwexrIljzOgOn1GdDHCCvbpLoQBEVwaKmrS9NwRoVl3WMkWrFx8W9yTH4pMbutw/kd7ldK+ri7LLG+TqXUpG70cncY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com; spf=pass smtp.mailfrom=rivosinc.com; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b=sm0N5w6h; arc=none smtp.client-ip=209.85.214.175 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b="sm0N5w6h" Received: by mail-pl1-f175.google.com with SMTP id d9443c01a7336-2255003f4c6so22075775ad.0 for ; Thu, 20 Mar 2025 10:29:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1742491779; x=1743096579; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=a+zSCWqqyKc551VynXTcxotuXwo5gv9XFD/e4PnRFpw=; b=sm0N5w6ho495F3awvJLqAIfRMq12XyV1VBDIBlfx3ijPTZ9/0cnFYtmFgDjfTvjZ0Z FabbmGHci051nKAS/xxXDvsGDCSE2iOsRoWs0VPW3SsLeE8IkDR59NyiE0os1H8dTpbg temTef3vFjdsPKDvE6gdFAENL2n93XveIowo3fjND8K/qZNMfBRauoCzXoCNzr473pgZ +ed4f3pMYuM+aUoMxK8+XVpItQmaONaYqxc/xJOIdvVa4r/81l+hOgRj17xusJIw01fm tvNC29c2wRMpoNESid7t5DhI6IT20e2cfmk3HSpDaLkoHGw3R8wYccQLCFEL+a+3hnEI Wkyg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742491779; x=1743096579; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=a+zSCWqqyKc551VynXTcxotuXwo5gv9XFD/e4PnRFpw=; b=LVndzqXg8kiD+v26+Zrkg53a8+5VYP4mGyZLXrDl9X/1hGfmKaRgw5al/P46f3Qs0O Ms5PuCTeDFzRl9vbfC3GHTRJL0kqGU6jl8suU5tvVoj5LpZr80Dty3unIiI9iyePMn7D D8GWiPY0+rsM+dF/WZ7CdttPUgQrD1RLxosf6b+hryyD/ZYGxLubKdcaqY+ZlR3wU0GT UHod082GDMvH0qo/bkJPNWTKEuc/qaoQiLLHqJEej2Y0DUyXDQKwc2eqyZ06jNp+swNc JeO7reGF9VUan8RIjycSUD9mIpRtfQ62LwGL8sMS5X2sdLK7VENkU2CvBEVTEkN1ki8O QGdQ== X-Forwarded-Encrypted: i=1; AJvYcCWx4hu60KU2E8y3AxKcziU00yrrzaLbS13flZGHEdIZzk9QeTjnv0RGDqP4Ch4d/Pesfz1TsFNWlx9a6hc=@vger.kernel.org X-Gm-Message-State: AOJu0Yyo82rwOupSFLX3TLpNr1XM3xOeg+LRqphhC09EiAY/NYiXk338 eGlf1D1DoUyYEx+cTooqzmezfyAb5OTyVNwMcTuywbzT4ytZKOau0nHGmtDOdEI= X-Gm-Gg: ASbGnctc6Hd3Ig5oPw1MyuiyxugzLnIRmpcbL54uPNKnvWoYoHfHNmzqm0RfCRaibaf fL1FS5rWKRgg3DPiy4lVd1yeP8UFQbykUSog/G2646VBhuOhQbK4gkU0EiKWWug1ebBYUhpI5sS t/umsZf67e6ilIXFICoRlBz0ebydoJz6eR+7FnXZFiH9RnY43IBqmg+N0HHqMiJs9g+K6MkUFpS 3MvodAem5YDnqRHpvK0OtsDm4n0bfnblJ3uM5VCyY7z+NrX/vKuUydbrit4rjVY/NyafQMuii8i XlV+CfnmQ0NoyU9P9V/qNMNr9nTKTjNYnS0LRfTEAheh1SPpKmpPWIXQI+s6 X-Google-Smtp-Source: AGHT+IFgzXwvWfdEvhnXyB7FqFqJoH2L77sDPXSbxso5gHzs8FqkCZv0zxAIf/4AajBrO5cX5nE4Pg== X-Received: by 2002:a17:902:d4ca:b0:223:4537:65b1 with SMTP id d9443c01a7336-22780e10a22mr3120205ad.36.1742491779220; Thu, 20 Mar 2025 10:29:39 -0700 (PDT) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-22780f45994sm554075ad.81.2025.03.20.10.29.37 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 20 Mar 2025 10:29:38 -0700 (PDT) From: Charlie Jenkins Date: Thu, 20 Mar 2025 10:29:23 -0700 Subject: [PATCH v6 3/4] LoongArch: entry: Migrate ret_from_fork() to C Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250320-riscv_optimize_entry-v6-3-63e187e26041@rivosinc.com> References: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> In-Reply-To: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Huacai Chen , WANG Xuerui , Thomas Gleixner , Peter Zijlstra , Andy Lutomirski , Alexandre Ghiti , Arnd Bergmann , Albert Ou , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, loongarch@lists.linux.dev, Charlie Jenkins X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=5547; i=charlie@rivosinc.com; h=from:subject:message-id; bh=ji6jPR39ZKDby+guv8CCAiBLyKbpGz9Kynms9BH9fJU=; b=owGbwMvMwCXWx5hUnlvL8Y3xtFoSQ/qdgOoXfxklWmUeR7VW8t5XaC5xnzvj6V8j4yka7OLlO tGi2tM6SlkYxLgYZMUUWXiuNTC33tEvOypaNgFmDisTyBAGLk4BmMiXUwx/5S/H2FwUSSl/Ne3W 8hjV4+nM3tVSUfPCTp9f7xxsL/qviZFh27yj6fsXnfmS+/d+s8uPTS2iK39NPycqaBbEabPDIjK dFwA= X-Developer-Key: i=charlie@rivosinc.com; a=openpgp; fpr=7D834FF11B1D8387E61C776FFB10D1F27D6B1354 LoongArch is the only architecture that calls syscall_exit_to_user_mode() from asm. Move the call into C so that this function can be inlined across all architectures. Signed-off-by: Charlie Jenkins --- arch/loongarch/include/asm/asm-prototypes.h | 8 +++++++ arch/loongarch/kernel/entry.S | 22 +++++++++---------- arch/loongarch/kernel/process.c | 33 +++++++++++++++++++++++--= ---- 3 files changed, 45 insertions(+), 18 deletions(-) diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/i= nclude/asm/asm-prototypes.h index 51f224bcfc654228ae423e9a066b25b35102a5b9..704066b4f7368be15be960fadbc= d6c2574bbf6c0 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -12,3 +12,11 @@ __int128_t __ashlti3(__int128_t a, int b); __int128_t __ashrti3(__int128_t a, int b); __int128_t __lshrti3(__int128_t a, int b); #endif + +asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_str= uct *prev, + struct pt_regs *regs); + +asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct= task_struct *prev, + struct pt_regs *regs, + int (*fn)(void *), + void *fn_arg); diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index 48e7e34e355e83eae8165957ba2eac05a8bf17df..2abc29e573810e000f2fef4646d= dca0dbb80eabe 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -77,24 +77,22 @@ SYM_CODE_START(handle_syscall) SYM_CODE_END(handle_syscall) _ASM_NOKPROBE(handle_syscall) =20 -SYM_CODE_START(ret_from_fork) +SYM_CODE_START(ret_from_fork_asm) UNWIND_HINT_REGS - bl schedule_tail # a0 =3D struct task_struct *prev - move a0, sp - bl syscall_exit_to_user_mode + move a1, sp + bl ret_from_fork RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_asm) =20 -SYM_CODE_START(ret_from_kernel_thread) +SYM_CODE_START(ret_from_kernel_thread_asm) UNWIND_HINT_REGS - bl schedule_tail # a0 =3D struct task_struct *prev - move a0, s1 - jirl ra, s0, 0 - move a0, sp - bl syscall_exit_to_user_mode + move a1, sp + move a2, s0 + move a3, s1 + bl ret_from_kernel_thread RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET -SYM_CODE_END(ret_from_kernel_thread) +SYM_CODE_END(ret_from_kernel_thread_asm) diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/proces= s.c index 6e58f65455c7ca3eae2e88ed852c8655a6701e5c..98bc60d7c550fcc0225e8452f81= a7d6cd7888015 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -33,6 +34,7 @@ #include #include =20 +#include #include #include #include @@ -47,6 +49,7 @@ #include #include #include +#include #include #include =20 @@ -63,8 +66,9 @@ EXPORT_SYMBOL(__stack_chk_guard); unsigned long boot_option_idle_override =3D IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); =20 -asmlinkage void ret_from_fork(void); -asmlinkage void ret_from_kernel_thread(void); +asmlinkage void restore_and_ret(void); +asmlinkage void ret_from_fork_asm(void); +asmlinkage void ret_from_kernel_thread_asm(void); =20 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -138,6 +142,23 @@ int arch_dup_task_struct(struct task_struct *dst, stru= ct task_struct *src) return 0; } =20 +asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_str= uct *prev, + struct pt_regs *regs) +{ + schedule_tail(prev); + syscall_exit_to_user_mode(regs); +} + +asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct= task_struct *prev, + struct pt_regs *regs, + int (*fn)(void *), + void *fn_arg) +{ + schedule_tail(prev); + fn(fn_arg); + syscall_exit_to_user_mode(regs); +} + /* * Copy architecture-specific thread state */ @@ -165,8 +186,8 @@ int copy_thread(struct task_struct *p, const struct ker= nel_clone_args *args) p->thread.reg03 =3D childksp; p->thread.reg23 =3D (unsigned long)args->fn; p->thread.reg24 =3D (unsigned long)args->fn_arg; - p->thread.reg01 =3D (unsigned long)ret_from_kernel_thread; - p->thread.sched_ra =3D (unsigned long)ret_from_kernel_thread; + p->thread.reg01 =3D (unsigned long)ret_from_kernel_thread_asm; + p->thread.sched_ra =3D (unsigned long)ret_from_kernel_thread_asm; memset(childregs, 0, sizeof(struct pt_regs)); childregs->csr_euen =3D p->thread.csr_euen; childregs->csr_crmd =3D p->thread.csr_crmd; @@ -182,8 +203,8 @@ int copy_thread(struct task_struct *p, const struct ker= nel_clone_args *args) childregs->regs[3] =3D usp; =20 p->thread.reg03 =3D (unsigned long) childregs; - p->thread.reg01 =3D (unsigned long) ret_from_fork; - p->thread.sched_ra =3D (unsigned long) ret_from_fork; + p->thread.reg01 =3D (unsigned long) ret_from_fork_asm; + p->thread.sched_ra =3D (unsigned long) ret_from_fork_asm; =20 /* * New tasks lose permission to use the fpu. This accelerates context --=20 2.43.0 From nobody Wed Dec 17 08:57:20 2025 Received: from mail-pl1-f176.google.com (mail-pl1-f176.google.com [209.85.214.176]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id BA272225795 for ; Thu, 20 Mar 2025 17:29:41 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.176 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491783; cv=none; b=FI4XxVNC263+YPKSPTy8y5mfDURdouQOhjVfjhZCUEpzjZrEKfGLuQM5ZyCinaPgvMUxW1NXiudltc2mUjAi5b8kUqcM+oD0PmLvXH8WEn8BiRV7P9PxyjT/Gj3Cn3oNzAQlVYnjO7q8kC3MIcs+ldsl1WypxD7mIvrGeRgqU64= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742491783; c=relaxed/simple; bh=hwgP0eJzDOrIufwWh6p9CUUm5a7+Fj7HYXiMVVUL4i0=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=FOyIv70oOuYF5z+D95CA9Ws50iaZcVsbZyfEVQyfFNw8J/OJVs9Ijn8zlOdSFfHvymKMhRZwfwXnOL+PRYtPtVTr2r/rSlJ9bf4uqct2DK/loKnJB1sPNG2ZsS6CgaYmZepBzLrLyNsQEx7tRDzB7/alyBBZPENQV1nycywaWjo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com; spf=pass smtp.mailfrom=rivosinc.com; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b=xXICdZrj; arc=none smtp.client-ip=209.85.214.176 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b="xXICdZrj" Received: by mail-pl1-f176.google.com with SMTP id d9443c01a7336-2260c91576aso20298085ad.3 for ; Thu, 20 Mar 2025 10:29:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1742491781; x=1743096581; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=3eCKaISwGTmHrKIN85ACd1M+I+peSRtvNHA2LnoFqyQ=; b=xXICdZrjWvULppfczpgiFxp217pTHxukpYPMzGIlXbKQwTG4gTE6SrjcIz2CEnVB+J /wjXgpivTY5jdowSKbxYr8Iup3nec+8jrLKHDlERvwomCDy2O2/UsGEN9nJrfaT1Ff29 4w9ednkTEDNrP/5p1bRbZP0/LEyfsm7bnt2+7hrRk2rmqdlRYUpPTVqaMUolr791cmzb /NoHNfYC9/xOyoR+QWxKE8IDT1tw8j4g/O4qzUNUNk52YS+PrtP157vC4tECbbm6uq+F gncdt5pZh1yKAIA6/SEPaEc7hGN0fVg2tXuC5t1wuOSHiAXnDstOYyLi5P0ar2KdQWTp ZGNQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742491781; x=1743096581; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=3eCKaISwGTmHrKIN85ACd1M+I+peSRtvNHA2LnoFqyQ=; b=dIeesbedNHaWurA/xMj9zaqJY17o9fdFNyjfNjxujJ23WNz8yw/KKIHHH4NLr2wodd OmigvgiRZ8DstKsC8eDHVhD1K4VJ6oNl69mhgWR1AJoQABzhGcsDyVf+MqjrawcDTh+X qdlSQDR4fQed4hEb4axrx7EmsO/SD0zVYhUGFNHEf6Qx4si6BAAoO60Mlni9Cfy7VY3+ QseQnlKSvt4T+mfXQFrDqeHS9pbWvM+5vIfmPC1trHfD0XEw2ZmygqzELEIbOWtw9qb9 R2jiVl5bueSNmJbtn6SpBC6C8CB+WPBHGSv6R2CeAreJeNkVuRGI7qM2C+lVdwtuE0CQ zY4Q== X-Forwarded-Encrypted: i=1; AJvYcCVjw0rH2cdGyQ8zcZIh2vxQTuy264lyGAcaiVr8R6hxpxH010JYmfI/VYR7a7xIktg5FerW8Ty1p8beRGo=@vger.kernel.org X-Gm-Message-State: AOJu0YyDZbG2Wq8cSdJN+RN02HagxY34ir0ngm2g895QWxenm36Tbh2F 5TUehfg9FYlcvCGYIvP+vrmWfVVC86fJFb4XcLfVi7QU3dwShWESTcGGjlxrA7U= X-Gm-Gg: ASbGncvAdeWEh6t6g8T5xGa2icqXriQ0iiJgeeVb5TuOAor3Ju5ZzkIZ+YMTJ9mkZWy jNNZAX1MwSfjz8my/m6FiF5i8v+K+cNOLSxh+drk867aC2B0C218tF93dHAj7RVguP0b/aPQxkH 0J9hNJeAoED56AGyT10wWjSEFoSwj5P26nel+EeUtCtNr/GssRkv8J7nn6G2xstuqUeux9oRNq8 m6eIxA5LWU+C17kbKm69dga3hU8HjDeuEV9vqqD7mjhJ5VqngaRh2ivjYRSGSHIBQJPSAbo2Qc8 VVTrKNvpYmPmQIrjgfgZ+cPDX/UpGFLEdvKLr1SSV5oNrEEnj+d6W4w1/l3c X-Google-Smtp-Source: AGHT+IEoiSAT3PG2OtWmoV8mEdtsEZlvOKiVq4y4a6hslPNxV+g32GTCCxsgFDxyvEafNQCPfwNFsA== X-Received: by 2002:a17:902:d511:b0:21f:61a9:be7d with SMTP id d9443c01a7336-22780e259c5mr2788735ad.49.1742491780987; Thu, 20 Mar 2025 10:29:40 -0700 (PDT) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-22780f45994sm554075ad.81.2025.03.20.10.29.39 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 20 Mar 2025 10:29:40 -0700 (PDT) From: Charlie Jenkins Date: Thu, 20 Mar 2025 10:29:24 -0700 Subject: [PATCH v6 4/4] entry: Inline syscall_exit_to_user_mode() Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250320-riscv_optimize_entry-v6-4-63e187e26041@rivosinc.com> References: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> In-Reply-To: <20250320-riscv_optimize_entry-v6-0-63e187e26041@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Huacai Chen , WANG Xuerui , Thomas Gleixner , Peter Zijlstra , Andy Lutomirski , Alexandre Ghiti , Arnd Bergmann , Albert Ou , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, loongarch@lists.linux.dev, Charlie Jenkins X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=5735; i=charlie@rivosinc.com; h=from:subject:message-id; bh=hwgP0eJzDOrIufwWh6p9CUUm5a7+Fj7HYXiMVVUL4i0=; b=owGbwMvMwCXWx5hUnlvL8Y3xtFoSQ/qdgGq/gwcSBbKN5p44aWIlPpmL3/weZ9XT/V/fHUmOf WD/Vr29o5SFQYyLQVZMkYXnWgNz6x39sqOiZRNg5rAygQxh4OIUgImEVDEyrBLd8GnjvikyV9/F i29z36Hy8PXSm5elT8rPVp7dM+fmBkZGhgnvBaQuX9uxPEsj9ztDn3DcJ3+Zs8yioUodqUxax45 PYgMA X-Developer-Key: i=charlie@rivosinc.com; a=openpgp; fpr=7D834FF11B1D8387E61C776FFB10D1F27D6B1354 Similar to commit 221a164035fd ("entry: Move syscall_enter_from_user_mode() to header file"), move syscall_exit_to_user_mode() to the header file as well. Testing was done with the byte-unixbench [1] syscall benchmark (which calls getpid) and QEMU. On riscv I measured a 7.09246% improvement, on x86 a 2.98843% improvement, on loongarch a 6.07954% improvement, and on s390 a 11.1328% improvement. The Intel bot also reported "kernel test robot noticed a 1.9% improvement of stress-ng.seek.ops_per_sec" [2] [1] https://github.com/kdlucas/byte-unixbench [2] https://lore.kernel.org/linux-riscv/202502051555.85ae6844-lkp@intel.com/ Signed-off-by: Charlie Jenkins Reviewed-by: Alexandre Ghiti --- include/linux/entry-common.h | 43 ++++++++++++++++++++++++++++++++++++-- kernel/entry/common.c | 49 +---------------------------------------= ---- 2 files changed, 42 insertions(+), 50 deletions(-) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index fc61d0205c97084acc89c8e45e088946f5e6d9b2..f94f3fdf15fc0091223cc9f7b82= 3970302e67312 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -14,6 +14,7 @@ #include =20 #include +#include =20 /* * Define dummy _TIF work flags if not defined by the architecture or for @@ -366,6 +367,15 @@ static __always_inline void exit_to_user_mode(void) lockdep_hardirqs_on(CALLER_ADDR0); } =20 +/** + * syscall_exit_work - Handle work before returning to user mode + * @regs: Pointer to current pt_regs + * @work: Current thread syscall work + * + * Do one-time syscall specific work. + */ +void syscall_exit_work(struct pt_regs *regs, unsigned long work); + /** * syscall_exit_to_user_mode_work - Handle work before returning to user m= ode * @regs: Pointer to currents pt_regs @@ -379,7 +389,30 @@ static __always_inline void exit_to_user_mode(void) * make the final state transitions. Interrupts must stay disabled between * return from this function and the invocation of exit_to_user_mode(). */ -void syscall_exit_to_user_mode_work(struct pt_regs *regs); +static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs = *regs) +{ + unsigned long work =3D READ_ONCE(current_thread_info()->syscall_work); + unsigned long nr =3D syscall_get_nr(current, regs); + + CT_WARN_ON(ct_state() !=3D CT_STATE_KERNEL); + + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { + if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr)) + local_irq_enable(); + } + + rseq_syscall(regs); + + /* + * Do one-time syscall specific work. If these work items are + * enabled, we want to run them exactly once per syscall exit with + * interrupts enabled. + */ + if (unlikely(work & SYSCALL_WORK_EXIT)) + syscall_exit_work(regs, work); + local_irq_disable_exit_to_user(); + exit_to_user_mode_prepare(regs); +} =20 /** * syscall_exit_to_user_mode - Handle work before returning to user mode @@ -410,7 +443,13 @@ void syscall_exit_to_user_mode_work(struct pt_regs *re= gs); * exit_to_user_mode(). This function is preferred unless there is a * compelling architectural reason to use the separate functions. */ -void syscall_exit_to_user_mode(struct pt_regs *regs); +static __always_inline void syscall_exit_to_user_mode(struct pt_regs *regs) +{ + instrumentation_begin(); + syscall_exit_to_user_mode_work(regs); + instrumentation_end(); + exit_to_user_mode(); +} =20 /** * irqentry_enter_from_user_mode - Establish state before invoking the irq= handler diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e33691d5adf7aab4af54cf2bf8e5ef5bd6ad1424..f55e421fb196dd5f9d4e34dd85a= e096c774cf879 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -146,7 +146,7 @@ static inline bool report_single_step(unsigned long wor= k) return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; } =20 -static void syscall_exit_work(struct pt_regs *regs, unsigned long work) +void syscall_exit_work(struct pt_regs *regs, unsigned long work) { bool step; =20 @@ -173,53 +173,6 @@ static void syscall_exit_work(struct pt_regs *regs, un= signed long work) ptrace_report_syscall_exit(regs, step); } =20 -/* - * Syscall specific exit to user mode preparation. Runs with interrupts - * enabled. - */ -static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) -{ - unsigned long work =3D READ_ONCE(current_thread_info()->syscall_work); - unsigned long nr =3D syscall_get_nr(current, regs); - - CT_WARN_ON(ct_state() !=3D CT_STATE_KERNEL); - - if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { - if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr)) - local_irq_enable(); - } - - rseq_syscall(regs); - - /* - * Do one-time syscall specific work. If these work items are - * enabled, we want to run them exactly once per syscall exit with - * interrupts enabled. - */ - if (unlikely(work & SYSCALL_WORK_EXIT)) - syscall_exit_work(regs, work); -} - -static __always_inline void __syscall_exit_to_user_mode_work(struct pt_reg= s *regs) -{ - syscall_exit_to_user_mode_prepare(regs); - local_irq_disable_exit_to_user(); - exit_to_user_mode_prepare(regs); -} - -void syscall_exit_to_user_mode_work(struct pt_regs *regs) -{ - __syscall_exit_to_user_mode_work(regs); -} - -__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs) -{ - instrumentation_begin(); - __syscall_exit_to_user_mode_work(regs); - instrumentation_end(); - exit_to_user_mode(); -} - noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs) { enter_from_user_mode(regs); --=20 2.43.0