From nobody Wed Dec 24 21:50:36 2025 Received: from mail-pj1-f52.google.com (mail-pj1-f52.google.com [209.85.216.52]) (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 8EEC855C30 for ; Tue, 23 Jan 2024 23:31:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.52 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706052685; cv=none; b=fYIOjM4hIAaLbzBhYZzbm81Lebzt0oPQSChycTjsoXCAqB+1YMxentsfIWRVgwwnMq+tYrU+sswK0S4DIsc5uPR1qMwj3btEvLmRiKlxMERW34HqADzIUMhDoWhBvI02JXF0RFAMHx0+JpTOg05g9q+UdvnqaE8FeSqnohjezsU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706052685; c=relaxed/simple; bh=TgPJhtuS5elB9x3qkOYRijPzfqXeMZFnxGkigghx8VE=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=eZn37dziNT1CtuJGFvbuZfzQYRfhr02/D354oQmn08wiHk/ZwPGRnH6MW9gYgU76km4sfvJHWXJHHLP/zZV4+6LT7WBv02PItjyKBa5vddmy70oJNzjN5uyHjohRWcfk3GPlpW8pU7zRhKhtHLRLMq1PzSW3+BvlhtjFYCBe72s= 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=Pt0PsWys; arc=none smtp.client-ip=209.85.216.52 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="Pt0PsWys" Received: by mail-pj1-f52.google.com with SMTP id 98e67ed59e1d1-290449c30d4so2183895a91.2 for ; Tue, 23 Jan 2024 15:31:23 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1706052683; x=1706657483; 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=MFBy5Jhev5nWWdDTHxl/l5SJEKa5TSeb5KKT2dQQAj4=; b=Pt0PsWysWfHvtNw1HIU/m2ayy3skQtoJaKh63X9d8hkPxrTzwmZel7q5jbDGF+BIax nfI8HM6aYyyOsdTAgDz4bYRuBb77mT0OziYUE286NkDLCGIg2Xj5S9e93bqJr1PXLcmh NKNfuN3sIHsI9r4RQCJ4P16315VnpRvRS2UwRc70fuWYWHrvvRZIkTPKFSzLz34UeaSJ y6bY5ecxQThUiOj64IG5hdqbMSi3Cq+g/Uo9u9eRscdLyftHmJuaIAI602Cx/iAsiZwk x4RK4XFi0VSZVYIRIGOnVOgXfnwrcrhVgPu8PLAInFTzd0M0YzDXh5j5LEeL86jWi+JG DmeQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1706052683; x=1706657483; 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=MFBy5Jhev5nWWdDTHxl/l5SJEKa5TSeb5KKT2dQQAj4=; b=C/tsg3Z5xox0DsCLYAqYHPWQnub8CUsBpGC3jjnVrb8elHIooqtnLEQCP41uYse5UN 64be8hU7zm6EkbK1gMqaw2Pm7c1RtoOpQGey5vrci2u74Pau6WAh3Km5vEnzxwU4B69d p6SCthzg66iRJM9VmE6YrEvIi/YjDcu3L5cAtwoBKh7Z/M4vhj7mDMuwb2pHhLC5JeQz jRtCGql5NKysOiJaiYLkN0iD4VgWQdzpSsH9iiAmhO6xLDE44nBKnQzIe1tiTT95/IYD UAzBJUsGXWZP9AYL3XbyrLVzfZJ8avmW5N56ZHp7Ob47Wuska28rJ+Os0ZPwULnd5VFk XpIA== X-Gm-Message-State: AOJu0YxA/7ZR0yI1T2DwFDZOUa19TfUoAEssML6WOnNnTohYyNOEhW66 q+rSXMKcU6ZHFzY+NtjOv0tQvlcVY3J13f6K0oi8DQa0N53fQdwwe/dd67/97qEvp5m+j+/i659 3 X-Google-Smtp-Source: AGHT+IEi37Pa/gG7czUf85R7YXWtq6tKYHXwQ5zNNZ7Tfn61NcbfM5AiSRDOlUtQgCW4kytOLIzsXQ== X-Received: by 2002:a17:90b:153:b0:28e:8c11:e042 with SMTP id em19-20020a17090b015300b0028e8c11e042mr3142760pjb.56.1706052682945; Tue, 23 Jan 2024 15:31:22 -0800 (PST) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id eu15-20020a17090af94f00b0028d19ddb1afsm12150698pjb.33.2024.01.23.15.31.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 23 Jan 2024 15:31:22 -0800 (PST) From: Charlie Jenkins Date: Tue, 23 Jan 2024 15:29:51 -0800 Subject: [PATCH v9 1/2] riscv: Include riscv_set_icache_flush_ctx prctl 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: <20240123-fencei-v9-1-71411bfe8d71@rivosinc.com> References: <20240123-fencei-v9-0-71411bfe8d71@rivosinc.com> In-Reply-To: <20240123-fencei-v9-0-71411bfe8d71@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Albert Ou , Jonathan Corbet , Conor Dooley , =?utf-8?q?Cl=C3=A9ment_L=C3=A9ger?= , Atish Patra , Randy Dunlap , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, Charlie Jenkins , Atish Patra X-Mailer: b4 0.12.3 X-Developer-Signature: v=1; a=ed25519-sha256; t=1706052680; l=9638; i=charlie@rivosinc.com; s=20231120; h=from:subject:message-id; bh=TgPJhtuS5elB9x3qkOYRijPzfqXeMZFnxGkigghx8VE=; b=H+VOHsPIUKHl1VzT+mYCChtEjWh5nkPnxepWSSs8XNMkqozEj3RkHTI/IFCW6O/cSWgzrAW2d rfDaQBhPCcuBkkcAm/i/+8HxKJM6aBTDA66Dh2ciyvJvLSerQheAyMo X-Developer-Key: i=charlie@rivosinc.com; a=ed25519; pk=t4RSWpMV1q5lf/NWIeR9z58bcje60/dbtxxmoSfBEcs= Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable optimization of cross modifying code. This prctl enables userspace code to use icache flushing instructions such as fence.i with the guarantee that the icache will continue to be clean after thread migration. Signed-off-by: Charlie Jenkins Reviewed-by: Atish Patra --- arch/riscv/include/asm/mmu.h | 2 ++ arch/riscv/include/asm/processor.h | 7 ++++ arch/riscv/include/asm/switch_to.h | 13 ++++++++ arch/riscv/mm/cacheflush.c | 67 ++++++++++++++++++++++++++++++++++= ++++ arch/riscv/mm/context.c | 14 ++++++-- include/uapi/linux/prctl.h | 6 ++++ kernel/sys.c | 6 ++++ 7 files changed, 112 insertions(+), 3 deletions(-) diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 355504b37f8e..60be458e94da 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -19,6 +19,8 @@ typedef struct { #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; + /* Force local icache flush on all migrations. */ + bool force_icache_flush; #endif #ifdef CONFIG_BINFMT_ELF_FDPIC unsigned long exec_fdpic_loadmap; diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/pr= ocessor.h index f19f861cda54..1cad05f579ad 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -84,6 +84,10 @@ struct thread_struct { unsigned long vstate_ctrl; struct __riscv_v_ext_state vstate; unsigned long align_ctl; +#ifdef CONFIG_SMP + bool force_icache_flush; + unsigned int prev_cpu; +#endif }; =20 /* Whitelist the fstate from the task_struct for hardened usercopy */ @@ -145,6 +149,9 @@ extern int set_unalign_ctl(struct task_struct *tsk, uns= igned int val); #define GET_UNALIGN_CTL(tsk, addr) get_unalign_ctl((tsk), (addr)) #define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val)) =20 +#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2) riscv_set_icache_flush_ctx(= arg1, arg2) +extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per= _thread); + #endif /* __ASSEMBLY__ */ =20 #endif /* _ASM_RISCV_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/sw= itch_to.h index f90d8e42f3c7..72c032d4277e 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -8,6 +8,7 @@ =20 #include #include +#include #include #include #include @@ -73,6 +74,15 @@ static __always_inline bool has_fpu(void) { return false= ; } extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *); =20 +static inline bool switch_to_should_flush_icache(struct task_struct *task) +{ + bool stale_mm =3D task->mm && (task->mm->context.force_icache_flush); + bool stale_thread =3D task->thread.force_icache_flush && + (smp_processor_id() !=3D task->thread.prev_cpu); + + return stale_mm || stale_thread; +} + #define switch_to(prev, next, last) \ do { \ struct task_struct *__prev =3D (prev); \ @@ -81,7 +91,10 @@ do { \ __switch_to_fpu(__prev, __next); \ if (has_vector()) \ __switch_to_vector(__prev, __next); \ + if (switch_to_should_flush_icache(__next)) \ + local_flush_icache_all(); \ ((last) =3D __switch_to(__prev, __next)); \ + __next->thread.prev_cpu =3D smp_processor_id(); \ } while (0) =20 #endif /* _ASM_RISCV_SWITCH_TO_H */ diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 55a34f2020a8..ff545f19f07a 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -5,6 +5,7 @@ =20 #include #include +#include #include #include =20 @@ -152,3 +153,69 @@ void __init riscv_init_cbo_blocksizes(void) if (cboz_block_size) riscv_cboz_block_size =3D cboz_block_size; } + +/** + * riscv_set_icache_flush_ctx() - Enable/disable icache flushing instructi= ons in + * userspace. + * @ctx: Set the type of icache flushing instructions permitted/prohibited= in + * userspace. Supported values described below. + * + * Supported values for ctx: + * + * * %PR_RISCV_CTX_SW_FENCEI_ON: Allow fence.i in userspace. + * + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``sc= ope =3D=3D + * PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a proce= ss. + * Therefore, caution must be taken -- only use this flag when you can + * guarantee that no thread in the process will emit fence.i from this p= oint + * onward. + * + * @scope: Set scope of where icache flushing instructions are allowed to = be + * emitted. Supported values described below. + * + * Supported values for scope: + * + * * PR_RISCV_SCOPE_PER_PROCESS: Ensure the icache of any thread in this p= rocess + * is coherent with instruction storage upon + * migration. + * + * * PR_RISCV_SCOPE_PER_THREAD: Ensure the icache of the current thread is + * coherent with instruction storage upon + * migration. + * + * When ``scope =3D=3D PR_RISCV_SCOPE_PER_PROCESS``, all threads in the pr= ocess are + * permitted to emit icache flushing instructions. Whenever any thread in = the + * process is migrated, the corresponding hart's icache will be guaranteed= to be + * consistent with instruction storage. Note this does not enforce any + * guarantees outside of migration. If a thread modifies an instruction th= at + * another thread may attempt to execute, the other thread must still emit= an + * icache flushing instruction before attempting to execute the potentially + * modified instruction. This must be performed by the userspace program. + * + * In per-thread context (eg. ``scope =3D=3D PR_RISCV_SCOPE_PER_THREAD``),= only the + * thread calling this function is permitted to emit icache flushing + * instructions. When the thread is migrated, the corresponding hart's ica= che + * will be guaranteed to be consistent with instruction storage. + * + * On kernels configured without SMP, this function is a nop as migrations + * across harts will not occur. + */ +int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope) +{ +#ifdef CONFIG_SMP + switch (ctx) { + case PR_RISCV_CTX_SW_FENCEI_ON: + switch (scope) { + case PR_RISCV_SCOPE_PER_PROCESS: + current->mm->context.force_icache_flush =3D true; + break; + case PR_RISCV_SCOPE_PER_THREAD: + current->thread.force_icache_flush =3D true; + break; + default: + return -EINVAL; + } + } +#endif + return 0; +} diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 217fd4de6134..b059dc0fae91 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -15,6 +15,7 @@ #include #include #include +#include =20 #ifdef CONFIG_MMU =20 @@ -297,19 +298,26 @@ static inline void set_mm(struct mm_struct *prev, * * The "cpu" argument must be the current local CPU number. */ -static inline void flush_icache_deferred(struct mm_struct *mm, unsigned in= t cpu) +static inline void flush_icache_deferred(struct mm_struct *mm, unsigned in= t cpu, + struct task_struct *task) { #ifdef CONFIG_SMP cpumask_t *mask =3D &mm->context.icache_stale_mask; =20 if (cpumask_test_cpu(cpu, mask)) { cpumask_clear_cpu(cpu, mask); + /* * Ensure the remote hart's writes are visible to this hart. * This pairs with a barrier in flush_icache_mm. */ smp_mb(); - local_flush_icache_all(); + + /* + * If cache will be flushed in switch_to, no need to flush here. + */ + if (!(task && switch_to_should_flush_icache(task))) + local_flush_icache_all(); } =20 #endif @@ -332,5 +340,5 @@ void switch_mm(struct mm_struct *prev, struct mm_struct= *next, =20 set_mm(prev, next, cpu); =20 - flush_icache_deferred(next, cpu); + flush_icache_deferred(next, cpu, task); } diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 370ed14b1ae0..524d546d697b 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -306,4 +306,10 @@ struct prctl_mm_map { # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc # define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f =20 +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 420d9cb9cc8e..e806a8a67c36 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -146,6 +146,9 @@ #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif +#ifndef RISCV_SET_ICACHE_FLUSH_CTX +# define RISCV_SET_ICACHE_FLUSH_CTX(a, b) (-EINVAL) +#endif =20 /* * this is where the system-wide overflow UID and GID are defined, for @@ -2739,6 +2742,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, ar= g2, unsigned long, arg3, case PR_RISCV_V_GET_CONTROL: error =3D RISCV_V_GET_CONTROL(); break; + case PR_RISCV_SET_ICACHE_FLUSH_CTX: + error =3D RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); + break; default: error =3D -EINVAL; break; --=20 2.43.0 From nobody Wed Dec 24 21:50:36 2025 Received: from mail-pj1-f52.google.com (mail-pj1-f52.google.com [209.85.216.52]) (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 AA9C15466F for ; Tue, 23 Jan 2024 23:31:24 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.52 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706052686; cv=none; b=NRTN0ZcGEZHMjPhzQEUUvt9H552LL3PzSjXbAc4UCSSARmEwU0KrOvytaiaedjpTabfP2JDGSSycipzeS66xw7B5ojy0+5+GFsw7HH/7AVb30l6Wq5RYJ7S/jARjU2Yt/jl31Kc5/eJGPABCaBWAwQHc2hztAhAOnkLhMs0e5Xc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706052686; c=relaxed/simple; bh=s1vPZ9pBqnCgTaBmMZz76e14UF6RK2nnhmaQL0fr1PM=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=EQO4FWMGLCc/9onmGs1YApg0jv5KUtDLkhdPQ4+Wf0aY+SRm9H6+8cq4AboG8fGt0/B4qH59nj6C2j1oXJ/bnzltBG3famTEq5XaEkeUxY5acpkW409TkBjFwXDBab6XmMB95Wg1lAivNTkhmWpWojGZJ4TpkhjRuMVvCgoVmbo= 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=1hkWzx9y; arc=none smtp.client-ip=209.85.216.52 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="1hkWzx9y" Received: by mail-pj1-f52.google.com with SMTP id 98e67ed59e1d1-290b1e19101so1697213a91.0 for ; Tue, 23 Jan 2024 15:31:24 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1706052684; x=1706657484; 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=ypj/UfIhrHcfkXvw9Dauu4SlRhzY7WsoxY+bpEphFSM=; b=1hkWzx9yfbFvtu2kbt79azyWxGP5klJuNLd8LpolL8auuYdNQ9QIO/kxRipHEuG49H PgMJfuRzF5oitkGew1wIvbyusHpZ+fzayK5Rar9iXRxJjlJAo01OvaNXHm+BPvYNtop0 jtexfPvct+ouwZ2Guj/1A1G4o8ddgXKXVnRx/YGscnjq+nGawFUj6eIgEiVjuoHVTRqr z9ObsVAqsW4o3QwjJAjnBErocLVLYeg6QlpYfCF+VzT2VtUlndVXQsya0/wRIC/bP5Sk riVZdJXVP7ELAo5woX34Oj1iRPlmnafieTLDtULHSQY31skZpWbyzt8FqMURWI7S4dgt SzMw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1706052684; x=1706657484; 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=ypj/UfIhrHcfkXvw9Dauu4SlRhzY7WsoxY+bpEphFSM=; b=ckmENAPNeOoD9oEiZ3bMkAKOZ4R8EFjGhMrXU+l0V9se64QdMdcIOrwtKesW0YyzRJ LAZjrr+VBTS8C+DqaNe92nDDBYWO2x1U13gzeGihSQ/mwhxRVdWSoYfdvWa/r2yRfKtW bE+U6xowMCV+RrTAxCtwo0qncWZPa5y43kJu8RexHkUm9uWV6xJoXj7hoP6vacr6YoZn 44dLL9OlFdUDbEwSoJGliqlzHChzCGgJlbJ48Z1/yR+h0kDVbViXN8ZHrzG35N+2OYJ+ UF3PDJc8zeq/TX1uFu5RV+lAtdQ0wP+gnAdzaIBcEahQq6G+SQDD0s8KuQVnPixBaQAD J9mQ== X-Gm-Message-State: AOJu0YysC/EHJ/jwN47j/96MxGB1phsUBKx3JNQzpXc2duWfDQD91sIu kCiFFPiXkm2lgA1FqcNZpn/osL12Gxd8WbzqeQvMD53hwqCBFh1uhQ0zzQZFV4I= X-Google-Smtp-Source: AGHT+IHToLOk9K0v/hNzUDffZhy+RECx2WTKxjTAijS0JAdyRvVF5awESDE1uNYxsm2LWaQ36Vie/g== X-Received: by 2002:a17:90a:4b4c:b0:28d:1581:29e6 with SMTP id o12-20020a17090a4b4c00b0028d158129e6mr432143pjl.13.1706052684090; Tue, 23 Jan 2024 15:31:24 -0800 (PST) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id eu15-20020a17090af94f00b0028d19ddb1afsm12150698pjb.33.2024.01.23.15.31.23 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 23 Jan 2024 15:31:23 -0800 (PST) From: Charlie Jenkins Date: Tue, 23 Jan 2024 15:29:52 -0800 Subject: [PATCH v9 2/2] documentation: Document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl 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: <20240123-fencei-v9-2-71411bfe8d71@rivosinc.com> References: <20240123-fencei-v9-0-71411bfe8d71@rivosinc.com> In-Reply-To: <20240123-fencei-v9-0-71411bfe8d71@rivosinc.com> To: Paul Walmsley , Palmer Dabbelt , Albert Ou , Jonathan Corbet , Conor Dooley , =?utf-8?q?Cl=C3=A9ment_L=C3=A9ger?= , Atish Patra , Randy Dunlap , Alexandre Ghiti Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, Charlie Jenkins , Atish Patra X-Mailer: b4 0.12.3 X-Developer-Signature: v=1; a=ed25519-sha256; t=1706052680; l=4373; i=charlie@rivosinc.com; s=20231120; h=from:subject:message-id; bh=s1vPZ9pBqnCgTaBmMZz76e14UF6RK2nnhmaQL0fr1PM=; b=Ur9C/GYjVRc9cfGP6lbfdLcd5+hrocoQQ3dJe0KO4KsYN3HCUO6zjvu2mV8SSw3XAXQTLvrtX FAcuM9z45lnCp+iAcp2yvi2SBh+OuWVcEO/LKKTp8kBQdt/sOG6QIjp X-Developer-Key: i=charlie@rivosinc.com; a=ed25519; pk=t4RSWpMV1q5lf/NWIeR9z58bcje60/dbtxxmoSfBEcs= Provide documentation that explains how to properly do CMODX in riscv. Signed-off-by: Charlie Jenkins Reviewed-by: Atish Patra --- Documentation/arch/riscv/cmodx.rst | 96 ++++++++++++++++++++++++++++++++++= ++++ Documentation/arch/riscv/index.rst | 1 + 2 files changed, 97 insertions(+) diff --git a/Documentation/arch/riscv/cmodx.rst b/Documentation/arch/riscv/= cmodx.rst new file mode 100644 index 000000000000..2ad46129d812 --- /dev/null +++ b/Documentation/arch/riscv/cmodx.rst @@ -0,0 +1,96 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D +Concurrent Modification and Execution of Instructions (CMODX) for RISC-V L= inux +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D + +CMODX is a programming technique where a program executes instructions tha= t were +modified by the program itself. Instruction storage and the instruction ca= che +(icache) are not guaranteed to be synchronized on RISC-V hardware. Therefo= re, the +program must enforce its own synchronization with the unprivileged fence.i +instruction. + +However, the default Linux ABI prohibits the use of fence.i in userspace +applications. At any point the scheduler may migrate a task onto a new har= t. If +migration occurs after the userspace synchronized the icache and instructi= on +storage with fence.i, the icache will no longer be clean. This is due to t= he +behavior of fence.i only affecting the hart that it is called on. Thus, th= e hart +that the task has been migrated to may not have synchronized instruction s= torage +and icache. + +There are two ways to solve this problem: use the riscv_flush_icache() sys= call, +or use the ``PR_RISCV_SET_ICACHE_FLUSH_CTX`` prctl() and emit fence.i in +userspace. The syscall performs a one-off icache flushing operation. The p= rctl +changes the Linux ABI to allow userspace to emit icache flushing operation= s. + +As an aside, "deferred" icache flushes can sometimes be triggered in the k= ernel. +At the time of writing, this only occurs during the riscv_flush_icache() s= yscall +and when the kernel uses copy_to_user_page(). These deferred flushes happe= n only +when the memory map being used by a hart changes. If the prctl() context c= aused +an icache flush, this deferred icache flush will be skipped as it is redun= dant. +Therefore, there will be no additional flush when using the riscv_flush_ic= ache() +syscall inside of the prctl() context. + +prctl() Interface +--------------------- + +Call prctl() with ``PR_RISCV_SET_ICACHE_FLUSH_CTX`` as the first argument.= The +remaining arguments will be delegated to the riscv_set_icache_flush_ctx +function detailed below. + +.. kernel-doc:: arch/riscv/mm/cacheflush.c + :identifiers: riscv_set_icache_flush_ctx + +Example usage: + +The following files are meant to be compiled and linked with each other. T= he +modify_instruction() function replaces an add with 0 with an add with one, +causing the instruction sequence in get_value() to change from returning a= zero +to returning a one. + +cmodx.c:: + + #include + #include + + extern int get_value(); + extern void modify_instruction(); + + int main() + { + int value =3D get_value(); + printf("Value before cmodx: %d\n", value); + + // Call prctl before first fence.i is called inside modify_instruction + prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_ON, PR_RISCV_CTX_SW_FENCEI, PR_RISCV= _SCOPE_PER_PROCESS); + modify_instruction(); + + value =3D get_value(); + printf("Value after cmodx: %d\n", value); + return 0; + } + +cmodx.S:: + + .option norvc + + .text + .global modify_instruction + modify_instruction: + lw a0, new_insn + lui a5,%hi(old_insn) + sw a0,%lo(old_insn)(a5) + fence.i + ret + + .section modifiable, "awx" + .global get_value + get_value: + li a0, 0 + old_insn: + addi a0, a0, 0 + ret + + .data + new_insn: + addi a0, a0, 1 diff --git a/Documentation/arch/riscv/index.rst b/Documentation/arch/riscv/= index.rst index 4dab0cb4b900..eecf347ce849 100644 --- a/Documentation/arch/riscv/index.rst +++ b/Documentation/arch/riscv/index.rst @@ -13,6 +13,7 @@ RISC-V architecture patch-acceptance uabi vector + cmodx =20 features =20 --=20 2.43.0