From nobody Sat Jun 13 06:20:41 2026 Received: from mail-pf1-f177.google.com (mail-pf1-f177.google.com [209.85.210.177]) (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 ADC72389E05 for ; Sat, 9 May 2026 13:10:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.177 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332225; cv=none; b=op6b2PCMSsjCW86X90G42ZQIDz0KTscG7jvhRy1SjTJhCKTCDNNoeXVXcovyecERtB0aFd+xzzqhupYm98GI4oyWBRk+NR1VgCgQcNq2WyOpomnUOVtGm6b3Y5WTGk0FmqCT1Dge2UKmgrxNewW9XFquvIqtCQqm0sJEttV1ZS0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332225; c=relaxed/simple; bh=uZrd32wUvX5SDEU1PWqvgQ3qjQJm8e+VexqImi1d9vM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=FTPF6fe0BUlfPhxQlfisJm79XM+CJzLh6YI/t3aekAhDOMgseINCuWaQq0J8ptmca4bqbXNQW04Vm/n/GwNLKVyzi3Z5PTtV/2tZhPbXWZdW72tMNEAZzcnR/AR3nogqZJXP5z9sBuXgmAqY9Ul9hZ0wLhsEUEGF/yeTvVxvPmI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=BBL6CInP; arc=none smtp.client-ip=209.85.210.177 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="BBL6CInP" Received: by mail-pf1-f177.google.com with SMTP id d2e1a72fcca58-83d5bbef760so630450b3a.1 for ; Sat, 09 May 2026 06:10:23 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1778332223; x=1778937023; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=PAkSYkxsqqTOgdXkwd1wAt3CxX5zO5z0PreuHh3BJZA=; b=BBL6CInPOQv5BnrbcLeRqeSq1XBZF5dcFz4z1kbOPcBoPOFpXgcw4KkwlTGH4evp9U 8VHWC7E0v+gzq1YHAU1YpEMNV+kBkrvq0K2g30MuHFakzc1RRJufgp5RgvvlocIJMwoP VEq/JW0SKNY6acywbRlZZ0mhtQdpxbSW/XhXFfqiMnIyVEDcyhAqczgGJxn8GAZqTtfR 4tm8dgNapGqYKWY7esRqHf34K9NPMvuP2389Kd+u3Qu2OtcZno+j4P1MMS537n+nwPy2 ZPaoRaSXdGVvU6jtkq9vMqvjZa4FqM1YYYTRS7D6zGrLwmIEjalkWPhgVbxC93ccg8gw wvBg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778332223; x=1778937023; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=PAkSYkxsqqTOgdXkwd1wAt3CxX5zO5z0PreuHh3BJZA=; b=DmhodfZL3Cs4jkCcw6QGbRZQLC1Ckvl3KMWy57goVM23zXSIngFcnJ8QXEdEFSmnLJ mD47Ruw9sfhyxnJIWPpojhh/rJh+FTdyJB4JFL2699gOnmvhyUrlm+rkIZKhNh2GxZ36 Z5o4+5O8+k20ZCI7ErEbADg1txch4YK2qL5gv1HdKw0Q/dnEOmFYp38pE8i30SAL0mUy EeR/qQm00PuZUVKv4WESCDjtkpEaJ62p+vbirPL0S7RJL2dsljFEAA88ilkNEaD2KWvA xtFUC7Eg5frCjSS8PG9q0EVmswQ+byqy35FU2eK8Myitup9cDLqva3wwM4avZ0WXmRuQ 4rrw== X-Gm-Message-State: AOJu0YwVIzqpLhwYZWkhV9/EuNQzwZq4xioBeOtFZmVVNr5cN4SZvoch LvZocpet7cRI9LUqj/SYXyAFOalTMGq/fZkwNkTo4IzWWA7tTc5vmWdhFIGfKvlwfX8= X-Gm-Gg: Acq92OGl+KvmrHo5kPJX0K3YdahAi8ZKY+8FnduyuFdAHzjUP2gYyFX13pGK/Bhb9TO TnnqFOmpLb4KQd+iA1yZ74dBAK44g3ACMJ1WHMK/7XIumrqO7cv986Q40NGh4xWZmwmGvscoUFB KMDYbIeW7U/ZWi++l73mB8Yg5y/DiMeUa6nJHQZjXEdw5SYYDjj3yiZaB2qGTIN2zGIZ6TUCjTS QdACZovxNDtxIXv042srfi2lJm8c9A6ZTGa8dEaOCzSViAX+7goqWR3oH+r3Np7rIsHJkNlH3Li kPrYJMz3BFtVz4BPVdjabZVbMPlFz4MYsZTTfH8j8N6LqTPr41pyZ1UGRCpIUq8OHlSxOtA8xnp DhrAig1gJR8CXYmIclClwxwtt5a2YSVqNJTyuG87CiRQcnGisD3R2cD5ZwN6KjaBiF+tQiS7Exe 3hfwTT1VMpD7FCEbaUPAm0a+5WuK6w40x9tGg45fkelKQlpn/rHVbjMqGYU7kVDDvAVZUhu1bUX cn6iQ== X-Received: by 2002:a05:6a00:8018:b0:82c:249e:a85b with SMTP id d2e1a72fcca58-83a5b7cd0famr17299719b3a.13.1778332222817; Sat, 09 May 2026 06:10:22 -0700 (PDT) Received: from FJ7FR2JRQ3.bytedance.net ([155.117.34.6]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-839679c86b3sm18552855b3a.28.2026.05.09.06.10.15 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Sat, 09 May 2026 06:10:22 -0700 (PDT) From: Zhanpeng Zhang To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, linux-kselftest@vger.kernel.org, kvm@vger.kernel.org, kvm-riscv@lists.infradead.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexandre Ghiti , Conor Dooley , =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= , Himanshu Chauhan , Will Deacon , Mark Rutland , Atish Patra , Anup Patel , Shuah Khan , Yunhui Cui , Zhu Yuan , Zhanpeng Zhang Subject: [PATCH v9 1/5] riscv: add SBI SSE extension definitions Date: Sat, 9 May 2026 21:09:58 +0800 Message-ID: <2a8913d680ccf162d5d697fde1a125c48b2f1d0a.1778331862.1.git.zhangzhanpeng.jasper@bytedance.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: References: 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 From: Cl=C3=A9ment L=C3=A9ger Add needed definitions for SBI Supervisor Software Events extension [1]. This extension enables the SBI to inject events into supervisor software much like ARM SDEI. [1] https://lists.riscv.org/g/tech-prs/message/515 Signed-off-by: Cl=C3=A9ment L=C3=A9ger Co-developed-by: Zhanpeng Zhang Signed-off-by: Zhanpeng Zhang --- arch/riscv/include/asm/sbi.h | 61 ++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 5725e0ca4dda..3403b0f706b4 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -38,6 +38,7 @@ enum sbi_ext_id { SBI_EXT_FWFT =3D 0x46574654, SBI_EXT_MPXY =3D 0x4D505859, SBI_EXT_DBTR =3D 0x44425452, + SBI_EXT_SSE =3D 0x535345, =20 /* Experimentals extensions must lie within this range */ SBI_EXT_EXPERIMENTAL_START =3D 0x08000000, @@ -506,6 +507,66 @@ enum sbi_mpxy_rpmi_attribute_id { #define SBI_MPXY_CHAN_CAP_SEND_WITHOUT_RESP BIT(4) #define SBI_MPXY_CHAN_CAP_GET_NOTIFICATIONS BIT(5) =20 +enum sbi_ext_sse_fid { + SBI_SSE_EVENT_ATTR_READ =3D 0, + SBI_SSE_EVENT_ATTR_WRITE, + SBI_SSE_EVENT_REGISTER, + SBI_SSE_EVENT_UNREGISTER, + SBI_SSE_EVENT_ENABLE, + SBI_SSE_EVENT_DISABLE, + SBI_SSE_EVENT_COMPLETE, + SBI_SSE_EVENT_INJECT, + SBI_SSE_HART_UNMASK, + SBI_SSE_HART_MASK, +}; + +enum sbi_sse_state { + SBI_SSE_STATE_UNUSED =3D 0, + SBI_SSE_STATE_REGISTERED =3D 1, + SBI_SSE_STATE_ENABLED =3D 2, + SBI_SSE_STATE_RUNNING =3D 3, +}; + +/* SBI SSE Event Attributes. */ +enum sbi_sse_attr_id { + SBI_SSE_ATTR_STATUS =3D 0x00000000, + SBI_SSE_ATTR_PRIO =3D 0x00000001, + SBI_SSE_ATTR_CONFIG =3D 0x00000002, + SBI_SSE_ATTR_PREFERRED_HART =3D 0x00000003, + SBI_SSE_ATTR_ENTRY_PC =3D 0x00000004, + SBI_SSE_ATTR_ENTRY_ARG =3D 0x00000005, + SBI_SSE_ATTR_INTERRUPTED_SEPC =3D 0x00000006, + SBI_SSE_ATTR_INTERRUPTED_FLAGS =3D 0x00000007, + SBI_SSE_ATTR_INTERRUPTED_A6 =3D 0x00000008, + SBI_SSE_ATTR_INTERRUPTED_A7 =3D 0x00000009, + + SBI_SSE_ATTR_MAX =3D 0x0000000A +}; + +#define SBI_SSE_ATTR_STATUS_STATE_OFFSET 0 +#define SBI_SSE_ATTR_STATUS_STATE_MASK 0x3 +#define SBI_SSE_ATTR_STATUS_PENDING_OFFSET 2 +#define SBI_SSE_ATTR_STATUS_INJECT_OFFSET 3 + +#define SBI_SSE_ATTR_CONFIG_ONESHOT BIT(0) + +#define SBI_SSE_ATTR_INTERRUPTED_FLAGS_SSTATUS_SPP BIT(0) +#define SBI_SSE_ATTR_INTERRUPTED_FLAGS_SSTATUS_SPIE BIT(1) +#define SBI_SSE_ATTR_INTERRUPTED_FLAGS_HSTATUS_SPV BIT(2) +#define SBI_SSE_ATTR_INTERRUPTED_FLAGS_HSTATUS_SPVP BIT(3) + +#define SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS 0x00000000 +#define SBI_SSE_EVENT_LOCAL_DOUBLE_TRAP 0x00000001 +#define SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS 0x00008000 +#define SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW 0x00010000 +#define SBI_SSE_EVENT_LOCAL_LOW_PRIO_RAS 0x00100000 +#define SBI_SSE_EVENT_GLOBAL_LOW_PRIO_RAS 0x00108000 +#define SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED 0xffff0000 +#define SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED 0xffff8000 + +#define SBI_SSE_EVENT_PLATFORM BIT(14) +#define SBI_SSE_EVENT_GLOBAL BIT(15) + /* SBI debug triggers function IDs */ enum sbi_ext_dbtr_fid { SBI_EXT_DBTR_NUM_TRIGGERS =3D 0, --=20 2.50.1 (Apple Git-155) From nobody Sat Jun 13 06:20:41 2026 Received: from mail-pf1-f172.google.com (mail-pf1-f172.google.com [209.85.210.172]) (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 492343890EF for ; Sat, 9 May 2026 13:10:31 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332233; cv=none; b=KUYOi1YRmkur2hIxldlPGUTSGHPjRjk5x0nwZm/DgsRRq0vvZ5OIprAAnGnHblwipz7W/n7Bnrvhm7RWsd51F182SBQGF1ZnE24k+cur4QwYojuXGX2U3uj6VMHqxUePcJDGACSZmoi8nVH5X/IwrRLnsBhQZxd++4DwWchacPc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332233; c=relaxed/simple; bh=rAtNQA3NLFdkTgHvVKbL6xaj96tlQeVQTf59SruURfI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=Q0FrRyHras+1/C76mJd1Sn3OWbQQClXEE6akISxcmAlOuzIjsXXo6XRdjm2LjZgg5P8JkRRuN0T2k74UT9PtebAF+FbyKQEnohBqnRVX0vQtnpS9sPg2S3dkBJDhzq0PBuWzSdxGOsEoqPHXL/3LzkFbR7na+PiAWWgd5L3pXzQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=H18SYHuu; arc=none smtp.client-ip=209.85.210.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="H18SYHuu" Received: by mail-pf1-f172.google.com with SMTP id d2e1a72fcca58-82fa8d6425bso1439329b3a.0 for ; Sat, 09 May 2026 06:10:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1778332231; x=1778937031; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=ecXwhyzNCnuMJatbT5+39kE5N68ADeHEmu4fmlvfWjg=; b=H18SYHuuVqkG3fUX5G6ymsLCfxOA/B+GPf2q4z1Fih+t5+EHKivOcjROBPhMAlsCIq SqEmqoIH5a+2F2AU2U/pXyunz8loOanMUnUMIZMVxiac5oetrkMVGcfjmO480TR4NwzF UEv7lrAMDq8hYUbY6O52siZt1zJ5QQRlVO9svj8cHuKkipBPXzRNqtUh1xiV6rMvBhz5 C32VcWYchT4WVTLfUth9m8TqiAxty8W4aGXUDXXI5rpPa0tGciz3FIFfM+e3alhMVZt7 xACuImZYPjeRE7BIqLZ9h7HJpSqCaGNhvmmrBrFuE9APOoJQT5Yq73ksNErcd0OqQGVl 2c0A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778332231; x=1778937031; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=ecXwhyzNCnuMJatbT5+39kE5N68ADeHEmu4fmlvfWjg=; b=n2uWNKfEQu47/4rx4uIXPMOpHUWNW4HVfZE+WhA7aFVWoxVjxnExTnpSdGd0GZV4/z 4wbshmBY2fv0GfSko1ixha6TIIia08clMfzCGWfQmBMYU2mavfUthmxfUjoAp6yhs/Vz 8MWbgEblw/m88G+XxRc9QKdFPnoBshT/Bi+3WbJXPjZJyuGJAF6N76bK1ywurgRQdXMf wFemjryULDkbHriXgt9imeaW+Ikf+KSb/nMrDLLw84jOT/k1TeKuKvwdOEjSDKmXAGKZ zd2H1vuhHRSQORzIj7movvQaI5rx0beMBSRKnqKmqpTGzOhymk49WlKMEJWUsagaf6Uo aI8g== X-Gm-Message-State: AOJu0Yz4NjV17FFQi/zUnDyYL5rd/SzI2B+RBekt8kz6eGpyoGHKwhN7 BAiXrk5asuSBsYmfLcCuoZKsQteL9VTPgP2SWvA50O1N9Vh4AjFPkqxUncGNvAAdJ+8= X-Gm-Gg: Acq92OEreu0/V2VOXEbDRzKsPNfq/GuCrT1m195LWTkJT9WA8invLadFNM81DXxS1O/ BshEf/vaoOTmlEpo8UEzcg4FeLb5OqPZp8ZRAMGPPomAzqhuLFO0DxWoGCJ+gQPvg0aSP5U53SY vLahk9+pXzY926s7U3HLM8rrQHp0MlWMQIdescIoEesvyMVLmPOs6MnJAQ+IKKHvO0x8U5rtOpt NlgY07W1vFU4W2JaK2eDIgOXwbfdpgqgxS8X2ZNjooSKsWnqeDNS1Tg9QM0KaGxRF/TI71zi2Tb rTEfQYX/JoJSln+53A9ZFDYYFjkMrIrNb0M9PA4Mmmnn52AMkz0Ls+XEGsNoQHMaEGRn6+eJXzu ukCgAX0JTc68nlwaJYNULQIDgbOA/lCEzSCfwWU/zMXtCuqvWnmyKMlB6nkY5yX/MHuIBA3Nr88 UoXfwIYRQGWJ9Wh5zL3krxGSnk7jW9FneZwwUITmUd8B+f3x+0bjqpFdUGp3im7Hu9JeY= X-Received: by 2002:a05:6a00:850e:b0:83c:928:6e5a with SMTP id d2e1a72fcca58-83c09288c28mr7837335b3a.13.1778332230428; Sat, 09 May 2026 06:10:30 -0700 (PDT) Received: from FJ7FR2JRQ3.bytedance.net ([155.117.34.6]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-839679c86b3sm18552855b3a.28.2026.05.09.06.10.23 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Sat, 09 May 2026 06:10:29 -0700 (PDT) From: Zhanpeng Zhang To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, linux-kselftest@vger.kernel.org, kvm@vger.kernel.org, kvm-riscv@lists.infradead.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexandre Ghiti , Conor Dooley , =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= , Himanshu Chauhan , Will Deacon , Mark Rutland , Atish Patra , Anup Patel , Shuah Khan , Yunhui Cui , Zhu Yuan , Zhanpeng Zhang Subject: [PATCH v9 2/5] riscv: add support for SBI Supervisor Software Events extension Date: Sat, 9 May 2026 21:09:59 +0800 Message-ID: <45918ddc68df98ec25ac93c0bbab7da90a4ecbf9.1778331862.2.git.zhangzhanpeng.jasper@bytedance.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: References: 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 From: Cl=C3=A9ment L=C3=A9ger The SBI SSE extension allows the supervisor software to be notified by the SBI of specific events that are not maskable. The context switch is handled partially by the firmware which will save registers a6 and a7. When entering kernel we can rely on these 2 registers to setup the stack and save all the registers. Since SSE events can be delivered at any time to the kernel, including during exception handling, we need a way to locate the current_task for context tracking. On RISC-V, it is stored in scratch when in user space or tp when in kernel space (in which case SSCRATCH is zero). But at the beginning of exception handling, SSCRATCH is used to swap tp and check the origin of the exception. If interrupted at that point, then, there is no way to reliably know where is located the current task_struct. Even checking the interruption location won't work as SSE event can be nested on top of each other so the original interruption site might be lost at some point. In order to retrieve it reliably, store the current task in an additional __sse_entry_task per_cpu array. This array is then used to retrieve the current task based on the hart ID that is passed to the SSE event handler in a6. That being said, the way the current task struct is stored should probably be reworked to find a better reliable alternative. Since each event (and each CPU for local events) have their own context and can preempt each other, allocate a stack (and a shadow stack if needed) for each of them (and for each cpu for local events). The SSE handler runs as a synthetic handler episode, but completion must resume the context that was interrupted by the SSE event. Preserve stvec and, when the hypervisor extension is present, hstatus across do_sse() so the handler episode does not leak trap-vector or virtualization state into the interrupted context. When completing the event, if we were coming from kernel with interrupts disabled, simply return there. If coming from userspace or kernel with interrupts enabled, simulate an interrupt exception by setting IE_SIE in CSR_IP to allow delivery of signals to user task. For instance this can happen when a RAS event has been generated by a user application and a SIGBUS has been sent to a task. Signed-off-by: Cl=C3=A9ment L=C3=A9ger Co-developed-by: Zhanpeng Zhang Signed-off-by: Zhanpeng Zhang --- arch/riscv/include/asm/asm.h | 14 +- arch/riscv/include/asm/scs.h | 7 + arch/riscv/include/asm/sse.h | 47 +++++++ arch/riscv/include/asm/switch_to.h | 14 ++ arch/riscv/include/asm/thread_info.h | 1 + arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/asm-offsets.c | 14 ++ arch/riscv/kernel/sbi_sse.c | 162 +++++++++++++++++++++++ arch/riscv/kernel/sbi_sse_entry.S | 187 +++++++++++++++++++++++++++ 9 files changed, 444 insertions(+), 3 deletions(-) create mode 100644 arch/riscv/include/asm/sse.h create mode 100644 arch/riscv/kernel/sbi_sse.c create mode 100644 arch/riscv/kernel/sbi_sse_entry.S diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index e9e8ba83e632..50bace00053c 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -90,16 +90,24 @@ .endm =20 #ifdef CONFIG_SMP -.macro asm_per_cpu dst sym tmp - lw \tmp, TASK_TI_CPU_NUM(tp) - slli \tmp, \tmp, RISCV_LGPTR +.macro asm_per_cpu_with_cpu dst sym tmp cpu + slli \tmp, \cpu, RISCV_LGPTR la \dst, __per_cpu_offset add \dst, \dst, \tmp REG_L \tmp, 0(\dst) la \dst, \sym add \dst, \dst, \tmp .endm + +.macro asm_per_cpu dst sym tmp + lw \tmp, TASK_TI_CPU_NUM(tp) + asm_per_cpu_with_cpu \dst \sym \tmp \tmp +.endm #else /* CONFIG_SMP */ +.macro asm_per_cpu_with_cpu dst sym tmp cpu + la \dst, \sym +.endm + .macro asm_per_cpu dst sym tmp la \dst, \sym .endm diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h index 023a412fe38d..0d70a35bc01a 100644 --- a/arch/riscv/include/asm/scs.h +++ b/arch/riscv/include/asm/scs.h @@ -17,6 +17,11 @@ load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp .endm =20 +/* Load the per-CPU IRQ shadow call stack to gp. */ +.macro scs_load_sse_stack reg_evt + REG_L gp, SSE_REG_EVT_SHADOW_STACK(\reg_evt) +.endm + /* Load task_scs_sp(current) to gp. */ .macro scs_load_current REG_L gp, TASK_TI_SCS_SP(tp) @@ -40,6 +45,8 @@ .endm .macro scs_load_irq_stack tmp .endm +.macro scs_load_sse_stack reg_evt +.endm .macro scs_load_current .endm .macro scs_load_current_if_task_changed prev diff --git a/arch/riscv/include/asm/sse.h b/arch/riscv/include/asm/sse.h new file mode 100644 index 000000000000..d3ce8c2b5221 --- /dev/null +++ b/arch/riscv/include/asm/sse.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Rivos Inc. + */ +#ifndef __ASM_SSE_H +#define __ASM_SSE_H + +#include + +#ifdef CONFIG_RISCV_SBI_SSE + +struct sse_event_interrupted_state { + unsigned long a6; + unsigned long a7; +}; + +struct sse_event_arch_data { + void *stack; + void *shadow_stack; + unsigned long tmp; + struct sse_event_interrupted_state interrupted; + unsigned long interrupted_phys; + u32 evt_id; + unsigned int hart_id; + unsigned int cpu_id; +}; + +static inline bool sse_event_is_global(u32 evt) +{ + return !!(evt & SBI_SSE_EVENT_GLOBAL); +} + +void arch_sse_event_update_cpu(struct sse_event_arch_data *arch_evt, int c= pu); +int arch_sse_init_event(struct sse_event_arch_data *arch_evt, u32 evt_id, + int cpu); +void arch_sse_free_event(struct sse_event_arch_data *arch_evt); +int arch_sse_register_event(struct sse_event_arch_data *arch_evt); + +void sse_handle_event(struct sse_event_arch_data *arch_evt, + struct pt_regs *regs); +asmlinkage void handle_sse(void); +asmlinkage void do_sse(struct sse_event_arch_data *arch_evt, + struct pt_regs *reg); + +#endif + +#endif diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/sw= itch_to.h index 0e71eb82f920..ded8dc440b12 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -88,6 +88,19 @@ static inline void __switch_to_envcfg(struct task_struct= *next) :: "r" (next->thread.envcfg) : "memory"); } =20 +#ifdef CONFIG_RISCV_SBI_SSE +DECLARE_PER_CPU(struct task_struct *, __sbi_sse_entry_task); + +static inline void __switch_sbi_sse_entry_task(struct task_struct *next) +{ + __this_cpu_write(__sbi_sse_entry_task, next); +} +#else +static inline void __switch_sbi_sse_entry_task(struct task_struct *next) +{ +} +#endif + extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *); =20 @@ -122,6 +135,7 @@ do { \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ __switch_to_envcfg(__next); \ + __switch_sbi_sse_entry_task(__next); \ ((last) =3D __switch_to(__prev, __next)); \ } while (0) =20 diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/= thread_info.h index 55019fdfa9ec..d14b45610c73 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -36,6 +36,7 @@ #define OVERFLOW_STACK_SIZE SZ_4K =20 #define IRQ_STACK_SIZE THREAD_SIZE +#define SSE_STACK_SIZE THREAD_SIZE =20 #ifndef __ASSEMBLER__ =20 diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index cabb99cadfb6..8d4aed6368a6 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -101,6 +101,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE) +=3D mcount-dyn.o obj-$(CONFIG_PERF_EVENTS) +=3D perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) +=3D perf_regs.o obj-$(CONFIG_RISCV_SBI) +=3D sbi.o sbi_ecall.o +obj-$(CONFIG_RISCV_SBI_SSE) +=3D sbi_sse.o sbi_sse_entry.o ifeq ($(CONFIG_RISCV_SBI), y) obj-$(CONFIG_SMP) +=3D sbi-ipi.o obj-$(CONFIG_SMP) +=3D cpu_ops_sbi.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offset= s.c index af827448a609..7cc03f5a0673 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -15,6 +15,8 @@ #include #include #include +#include +#include #include =20 void asm_offsets(void); @@ -533,6 +535,18 @@ void asm_offsets(void) DEFINE(FREGS_A6, offsetof(struct __arch_ftrace_regs, a6)); DEFINE(FREGS_A7, offsetof(struct __arch_ftrace_regs, a7)); #endif + +#ifdef CONFIG_RISCV_SBI_SSE + OFFSET(SSE_REG_EVT_STACK, sse_event_arch_data, stack); + OFFSET(SSE_REG_EVT_SHADOW_STACK, sse_event_arch_data, shadow_stack); + OFFSET(SSE_REG_EVT_TMP, sse_event_arch_data, tmp); + OFFSET(SSE_REG_HART_ID, sse_event_arch_data, hart_id); + OFFSET(SSE_REG_CPU_ID, sse_event_arch_data, cpu_id); + + DEFINE(SBI_EXT_SSE, SBI_EXT_SSE); + DEFINE(SBI_SSE_EVENT_COMPLETE, SBI_SSE_EVENT_COMPLETE); + DEFINE(ASM_NR_CPUS, CONFIG_NR_CPUS); +#endif #ifdef CONFIG_RISCV_SBI DEFINE(SBI_EXT_FWFT, SBI_EXT_FWFT); DEFINE(SBI_EXT_FWFT_SET, SBI_EXT_FWFT_SET); diff --git a/arch/riscv/kernel/sbi_sse.c b/arch/riscv/kernel/sbi_sse.c new file mode 100644 index 000000000000..f30ae9ff77c9 --- /dev/null +++ b/arch/riscv/kernel/sbi_sse.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2025 Rivos Inc. + */ +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +DEFINE_PER_CPU(struct task_struct *, __sbi_sse_entry_task); + +void __weak sse_handle_event(struct sse_event_arch_data *arch_evt, struct = pt_regs *regs) +{ +} + +void do_sse(struct sse_event_arch_data *arch_evt, struct pt_regs *regs) +{ + nmi_enter(); + + /* Retrieve missing GPRs from SBI */ + sbi_ecall(SBI_EXT_SSE, SBI_SSE_EVENT_ATTR_READ, arch_evt->evt_id, + SBI_SSE_ATTR_INTERRUPTED_A6, + (SBI_SSE_ATTR_INTERRUPTED_A7 - SBI_SSE_ATTR_INTERRUPTED_A6) + 1, + arch_evt->interrupted_phys, 0, 0); + + memcpy(®s->a6, &arch_evt->interrupted, sizeof(arch_evt->interrupted)); + + sse_handle_event(arch_evt, regs); + + nmi_exit(); +} + +static void *alloc_to_stack_pointer(void *alloc) +{ + return alloc ? alloc + SSE_STACK_SIZE : NULL; +} + +static void *stack_pointer_to_alloc(void *stack) +{ + return stack - SSE_STACK_SIZE; +} + +#ifdef CONFIG_VMAP_STACK +static void *sse_stack_alloc(unsigned int cpu) +{ + void *stack =3D arch_alloc_vmap_stack(SSE_STACK_SIZE, cpu_to_node(cpu)); + + return alloc_to_stack_pointer(stack); +} + +static void sse_stack_free(void *stack) +{ + vfree(stack_pointer_to_alloc(stack)); +} + +static void arch_sse_stack_cpu_sync(struct sse_event_arch_data *arch_evt) +{ + void *p_stack =3D arch_evt->stack; + unsigned long stack =3D (unsigned long)stack_pointer_to_alloc(p_stack); + unsigned long stack_end =3D stack + SSE_STACK_SIZE; + + /* + * Flush the tlb to avoid taking any exception when accessing the + * vmapped stack inside the SSE handler + */ + if (sse_event_is_global(arch_evt->evt_id)) + flush_tlb_kernel_range(stack, stack_end); + else + local_flush_tlb_kernel_range(stack, stack_end); +} +#else /* CONFIG_VMAP_STACK */ +static void *sse_stack_alloc(unsigned int cpu) +{ + void *stack =3D kmalloc(SSE_STACK_SIZE, GFP_KERNEL); + + return alloc_to_stack_pointer(stack); +} + +static void sse_stack_free(void *stack) +{ + kfree(stack_pointer_to_alloc(stack)); +} + +static void arch_sse_stack_cpu_sync(struct sse_event_arch_data *arch_evt) = {} +#endif /* CONFIG_VMAP_STACK */ + +static int sse_init_scs(int cpu, struct sse_event_arch_data *arch_evt) +{ + void *stack; + + if (!scs_is_enabled()) + return 0; + + stack =3D scs_alloc(cpu_to_node(cpu)); + if (!stack) + return -ENOMEM; + + arch_evt->shadow_stack =3D stack; + + return 0; +} + +void arch_sse_event_update_cpu(struct sse_event_arch_data *arch_evt, int c= pu) +{ + arch_evt->cpu_id =3D cpu; + arch_evt->hart_id =3D cpuid_to_hartid_map(cpu); +} + +int arch_sse_init_event(struct sse_event_arch_data *arch_evt, u32 evt_id, + int cpu) +{ + void *stack; + + arch_evt->evt_id =3D evt_id; + stack =3D sse_stack_alloc(cpu); + if (!stack) + return -ENOMEM; + + arch_evt->stack =3D stack; + + if (sse_init_scs(cpu, arch_evt)) { + sse_stack_free(arch_evt->stack); + return -ENOMEM; + } + + if (sse_event_is_global(evt_id)) { + arch_evt->interrupted_phys =3D + virt_to_phys(&arch_evt->interrupted); + } else { + arch_evt->interrupted_phys =3D + per_cpu_ptr_to_phys(&arch_evt->interrupted); + } + + arch_sse_event_update_cpu(arch_evt, cpu); + + return 0; +} + +void arch_sse_free_event(struct sse_event_arch_data *arch_evt) +{ + scs_free(arch_evt->shadow_stack); + sse_stack_free(arch_evt->stack); +} + +int arch_sse_register_event(struct sse_event_arch_data *arch_evt) +{ + struct sbiret sret; + + arch_sse_stack_cpu_sync(arch_evt); + + sret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_EVENT_REGISTER, arch_evt->evt_id, + (unsigned long)handle_sse, (unsigned long)arch_evt, 0, + 0, 0); + + return sbi_err_map_linux_errno(sret.error); +} diff --git a/arch/riscv/kernel/sbi_sse_entry.S b/arch/riscv/kernel/sbi_sse_= entry.S new file mode 100644 index 000000000000..6086751e6644 --- /dev/null +++ b/arch/riscv/kernel/sbi_sse_entry.S @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2025 Rivos Inc. + */ + +#include +#include + +#include +#include +#include +#include +#include + +/* When entering handle_sse, the following registers are set: + * a6: contains the hartid + * a7: contains a sse_event_arch_data struct pointer + */ +SYM_CODE_START(handle_sse) + /* Save stack temporarily */ + REG_S sp, SSE_REG_EVT_TMP(a7) + /* Set entry stack */ + REG_L sp, SSE_REG_EVT_STACK(a7) + + addi sp, sp, -(PT_SIZE_ON_STACK) + REG_S ra, PT_RA(sp) + REG_S s0, PT_S0(sp) + REG_S s1, PT_S1(sp) + REG_S s2, PT_S2(sp) + REG_S s3, PT_S3(sp) + REG_S s4, PT_S4(sp) + REG_S s5, PT_S5(sp) + REG_S s6, PT_S6(sp) + REG_S s7, PT_S7(sp) + REG_S s8, PT_S8(sp) + REG_S s9, PT_S9(sp) + REG_S s10, PT_S10(sp) + REG_S s11, PT_S11(sp) + REG_S tp, PT_TP(sp) + REG_S t0, PT_T0(sp) + REG_S t1, PT_T1(sp) + REG_S t2, PT_T2(sp) + REG_S t3, PT_T3(sp) + REG_S t4, PT_T4(sp) + REG_S t5, PT_T5(sp) + REG_S t6, PT_T6(sp) + REG_S gp, PT_GP(sp) + REG_S a0, PT_A0(sp) + REG_S a1, PT_A1(sp) + REG_S a2, PT_A2(sp) + REG_S a3, PT_A3(sp) + REG_S a4, PT_A4(sp) + REG_S a5, PT_A5(sp) + + /* Retrieve entry sp */ + REG_L a4, SSE_REG_EVT_TMP(a7) + /* Save CSRs */ + csrr a0, CSR_EPC + csrr a1, CSR_SSTATUS + csrr a2, CSR_STVAL + csrr a3, CSR_SCAUSE + + REG_S a0, PT_EPC(sp) + REG_S a1, PT_STATUS(sp) + REG_S a2, PT_BADADDR(sp) + REG_S a3, PT_CAUSE(sp) + REG_S a4, PT_SP(sp) + + /* Disable user memory access and floating/vector computing */ + li t0, SR_SUM | SR_FS_VS + csrc CSR_STATUS, t0 + + load_global_pointer + scs_load_sse_stack a7 + +#ifdef CONFIG_SMP + lw t4, SSE_REG_HART_ID(a7) + lw t3, SSE_REG_CPU_ID(a7) + + bne t4, a6, .Lfind_hart_id_slowpath + +.Lcpu_id_found: +#else + mv t3, zero +#endif + + asm_per_cpu_with_cpu t2 __sbi_sse_entry_task t1 t3 + REG_L tp, 0(t2) + + mv a1, sp /* pt_regs on stack */ + + /* + * Run the SSE handler with the normal exception vector, but restore the + * interrupted stvec before completing the event. SSE can arrive while + * the kernel is using a temporary trap vector in a sensitive entry path. + */ + csrr s3, CSR_STVEC + la t0, handle_exception + csrw CSR_STVEC, t0 + + /* + * Preserve the full HS-mode virtualization state across the handler. + * hstatus is live supervisor state rather than an SSE interrupted + * attribute, and OpenSBI consumes hstatus.SPV during event completion. + * Saving the whole CSR keeps the handler episode transparent to KVM and + * avoids having to infer which hstatus bits may matter to a guest resume. + */ + ALTERNATIVE("nop", "csrr s5, hstatus", 0, RISCV_ISA_EXT_h, 1) + + /* + * Save sscratch for restoration since we might have interrupted the + * kernel in early exception path and thus, we don't know the content of + * sscratch. + */ + csrrw s4, CSR_SSCRATCH, x0 + + mv a0, a7 + + call do_sse + + csrw CSR_SSCRATCH, s4 + ALTERNATIVE("nop", "csrw hstatus, s5", 0, RISCV_ISA_EXT_h, 1) + csrw CSR_STVEC, s3 + + REG_L a0, PT_STATUS(sp) + REG_L a1, PT_EPC(sp) + REG_L a2, PT_BADADDR(sp) + REG_L a3, PT_CAUSE(sp) + csrw CSR_SSTATUS, a0 + csrw CSR_EPC, a1 + csrw CSR_STVAL, a2 + csrw CSR_SCAUSE, a3 + + REG_L ra, PT_RA(sp) + REG_L s0, PT_S0(sp) + REG_L s1, PT_S1(sp) + REG_L s2, PT_S2(sp) + REG_L s3, PT_S3(sp) + REG_L s4, PT_S4(sp) + REG_L s5, PT_S5(sp) + REG_L s6, PT_S6(sp) + REG_L s7, PT_S7(sp) + REG_L s8, PT_S8(sp) + REG_L s9, PT_S9(sp) + REG_L s10, PT_S10(sp) + REG_L s11, PT_S11(sp) + REG_L tp, PT_TP(sp) + REG_L t0, PT_T0(sp) + REG_L t1, PT_T1(sp) + REG_L t2, PT_T2(sp) + REG_L t3, PT_T3(sp) + REG_L t4, PT_T4(sp) + REG_L t5, PT_T5(sp) + REG_L t6, PT_T6(sp) + REG_L gp, PT_GP(sp) + REG_L a0, PT_A0(sp) + REG_L a1, PT_A1(sp) + REG_L a2, PT_A2(sp) + REG_L a3, PT_A3(sp) + REG_L a4, PT_A4(sp) + REG_L a5, PT_A5(sp) + + REG_L sp, PT_SP(sp) + + li a7, SBI_EXT_SSE + li a6, SBI_SSE_EVENT_COMPLETE + ecall + +#ifdef CONFIG_SMP +.Lfind_hart_id_slowpath: + + /* Restore current task struct from __sbi_sse_entry_task */ + li t1, ASM_NR_CPUS + /* Slowpath to find the CPU id associated to the hart id */ + la t0, __cpuid_to_hartid_map + +.Lhart_id_loop: + REG_L t2, 0(t0) + beq t2, a6, .Lcpu_id_found + + /* Increment pointer and CPU number */ + addi t3, t3, 1 + addi t0, t0, RISCV_SZPTR + bltu t3, t1, .Lhart_id_loop + + /* + * This should never happen since we expect the hart_id to match one + * of our CPU, but better be safe than sorry + */ + la tp, init_task + la a0, sse_hart_id_panic_string + la t0, panic + jalr t0 +#endif + +SYM_CODE_END(handle_sse) + +SYM_DATA_START_LOCAL(sse_hart_id_panic_string) + .ascii "Unable to match hart_id with cpu\0" +SYM_DATA_END(sse_hart_id_panic_string) --=20 2.50.1 (Apple Git-155) From nobody Sat Jun 13 06:20:41 2026 Received: from mail-pg1-f180.google.com (mail-pg1-f180.google.com [209.85.215.180]) (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 EAD69389DE6 for ; Sat, 9 May 2026 13:10:39 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.215.180 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332242; cv=none; b=TOuT45ipIojk8+EGytGlsU6VEa48uh7xwgYZKScCdk99x59xlJnFHYTAKGs8CqNDDzisNFztgo9eOabCUSbjpuSPR6MJ0bYdpGUx/JhcA5mlUK58cVjKNlmjDElxzGlzxRWpkt5mb2+DTirPVDxuDAb3ytHWsYYJ3lcPef/qlXo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332242; c=relaxed/simple; bh=7dqz4segQ/MalpRZ9Ya0yjpSu+KiCILfAeaCem3tceQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=rZnA1LBo1SVJELvV5Jp2jDCQ+p0Cq3xavgusOt2m0AG8zjQEDyqTGWbN2dgXle78+e4tQByKA3vp0dAOorol0LrGN4yH5W7RUMjAicDVRFhDWxZiJ4Jsysqm208enyGMs1QHXpXxv97QinUruJEUfl56BTMsEaZkb9jvuM4gByg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=LhBROx4G; arc=none smtp.client-ip=209.85.215.180 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="LhBROx4G" Received: by mail-pg1-f180.google.com with SMTP id 41be03b00d2f7-c8025aecc40so1325636a12.0 for ; Sat, 09 May 2026 06:10:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1778332239; x=1778937039; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=8Q4dh0CdjTPEi5DSD0op3QJu9CGHQvyYzAsp+GsL6pc=; b=LhBROx4Galci6bBPyC7i37+JkW7o8CYC6JSXZVxkrAwPXrx72b3EP5rukqNwbMbE0q qV2oNzUG3fcIB/tvOt/lreEfsLPx5OdqlaaTonPM2agbLxNIr8f+lPXJHaMQvPMWM+gc Wh6r/Gn7jVmf9FqHQuLd+N9aSIyHcId3qAZ4wadky1uAV2AvFbRiRCcF3PHJ3b6xT+F4 aq9meFA0796vb6VppkBMhOICiqIaWIZMenSCmlsbhm6+CKYO4w04qrJNgT5iYawpSe2+ 5xTh62nu7Q2rYY3JxE84PjsJZf/83eu7WCCsSl7PnYJMMA/NS+mqauQ46VC8vZ7NtOSs m8yw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778332239; x=1778937039; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=8Q4dh0CdjTPEi5DSD0op3QJu9CGHQvyYzAsp+GsL6pc=; b=VdDVR6WkGPltcuG5ZSPWNAb54c9YH0ZMjvYpSJpDeKieS77KVZakiXytA37WfJ5J9C gzDF7UypNGMNuNQ5OVr453pr/OVyWv1HKBiGKY6EkRJ623awMSEXjsZ2AigL+wdXfX9j dxAV8P1kvhH2LscPc0FTHNeWQc2NU1uVto+7SqDgQWWRw/tnlcZCAoKWHkVPu5Z/vYD1 rEazd15q7/kooMyjGjeoGlWDUfhEmvbOLqNt1JJM7nSp8ZzyHeriGeLvroZ+0ta+LRTS zxFDRUssLPFoRAMHjmcKw5PI0JQzm6vwC+Yw1lZw2l+hhD/a4Q/2ZzukTZ7yahu1e9Wt 7u4w== X-Gm-Message-State: AOJu0YzGMKfsm/hz8MGEGBoPr4K2UFyFa15z5E1s6RsQCwm/eb9j54Ka qNJlShqYIIZcx3fBUP7fPUcZrbrc9/vLGg3gBlI+Tv4zq9yjb73Qiz1duFEfQ6GeBnI= X-Gm-Gg: Acq92OHpZ6rDRhuXAb/8IjNlsSUt4YmWHLbXytT9jptgkgPoi4kxwTLbRgadVF16dv6 yLZG/4R9KWfyijy3+o9gh8Cvd9oEb61t8qTQzbiIcPhcq4TIcZnJNxH/OEbq49BqaO4mBoA7AN0 OE0Tdlu9aQFgu2ky+A2KbUnmCytzUVjdL9VaiyCv5SkCTPnzz8LIReAEEAsYky+C1T8eHlSABLK AsN3NhEpLuy4Pu7GFKA3+CAw0axcBrUWmUaJjUkRXi8+icmt8lSxSjlQ1psucjeAl1lgjeGkxpl F4iixBZiWVIYHiDWAL1dFCZGYOlI+hp1DuBt1ZPI3N7eykNABhA07PXEpHTzRVoSPxoaRrgidfn yINnc5sJuNy3poa9fn0Xjst3mJFx8/GZC9JSI6cDyTbDGDTaTYOhCOvKvMXoqniweoxljGoyYyA ZeRHPtsV6cvu5BLjxLcEQJIww9AQ+6zSYwdvNjuQT1UPCpTn0uFB2MNmUBgLzDKc6uFbc= X-Received: by 2002:a05:6a20:12c6:b0:3a2:c9a1:2c22 with SMTP id adf61e73a8af0-3aa8be1d28bmr9696923637.6.1778332239111; Sat, 09 May 2026 06:10:39 -0700 (PDT) Received: from FJ7FR2JRQ3.bytedance.net ([155.117.34.6]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-839679c86b3sm18552855b3a.28.2026.05.09.06.10.30 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Sat, 09 May 2026 06:10:38 -0700 (PDT) From: Zhanpeng Zhang To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, linux-kselftest@vger.kernel.org, kvm@vger.kernel.org, kvm-riscv@lists.infradead.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexandre Ghiti , Conor Dooley , =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= , Himanshu Chauhan , Will Deacon , Mark Rutland , Atish Patra , Anup Patel , Shuah Khan , Yunhui Cui , Zhu Yuan , Himanshu Chauhan , Zhanpeng Zhang , Conor Dooley Subject: [PATCH v9 3/5] drivers: firmware: add riscv SSE support Date: Sat, 9 May 2026 21:10:00 +0800 Message-ID: <7d86cbd47688700fbdfc27e530e824a6bec0548c.1778331862.3.git.zhangzhanpeng.jasper@bytedance.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: References: 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 From: Cl=C3=A9ment L=C3=A9ger Add a driver-level interface for RISC-V SSE support. The interface lets Linux clients register handlers and enable, disable and complete SSE events. It will be used by PMU and GHES drivers. Co-developed-by: Himanshu Chauhan Signed-off-by: Himanshu Chauhan Signed-off-by: Cl=C3=A9ment L=C3=A9ger Co-developed-by: Zhanpeng Zhang Signed-off-by: Zhanpeng Zhang Acked-by: Conor Dooley --- MAINTAINERS | 16 + drivers/firmware/Kconfig | 1 + drivers/firmware/Makefile | 1 + drivers/firmware/riscv/Kconfig | 15 + drivers/firmware/riscv/Makefile | 3 + drivers/firmware/riscv/riscv_sbi_sse.c | 694 +++++++++++++++++++++++++ include/linux/riscv_sbi_sse.h | 57 ++ 7 files changed, 787 insertions(+) create mode 100644 drivers/firmware/riscv/Kconfig create mode 100644 drivers/firmware/riscv/Makefile create mode 100644 drivers/firmware/riscv/riscv_sbi_sse.c create mode 100644 include/linux/riscv_sbi_sse.h diff --git a/MAINTAINERS b/MAINTAINERS index 2fb1c75afd16..c247acc56d1c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22914,6 +22914,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/g= it/iommu/linux.git F: Documentation/devicetree/bindings/iommu/riscv,iommu.yaml F: drivers/iommu/riscv/ =20 +RISC-V FIRMWARE DRIVERS +M: Conor Dooley +L: linux-riscv@lists.infradead.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git +F: drivers/firmware/riscv/ + RISC-V MICROCHIP SUPPORT M: Conor Dooley M: Daire McNamara @@ -22999,6 +23006,15 @@ F: arch/riscv/boot/dts/spacemit/ N: spacemit K: spacemit =20 +RISC-V SSE DRIVER +M: Zhanpeng Zhang +R: Himanshu Chauhan +R: Yunhui Cui +L: linux-riscv@lists.infradead.org +S: Maintained +F: drivers/firmware/riscv/riscv_sbi_sse.c +F: include/linux/riscv_sbi_sse.h + RISC-V TENSTORRENT SoC SUPPORT M: Drew Fustini M: Joel Stanley diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index bbd2155d8483..1894df87b08e 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -294,6 +294,7 @@ source "drivers/firmware/meson/Kconfig" source "drivers/firmware/microchip/Kconfig" source "drivers/firmware/psci/Kconfig" source "drivers/firmware/qcom/Kconfig" +source "drivers/firmware/riscv/Kconfig" source "drivers/firmware/samsung/Kconfig" source "drivers/firmware/smccc/Kconfig" source "drivers/firmware/tegra/Kconfig" diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 4ddec2820c96..6cdd84570ea7 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -34,6 +34,7 @@ obj-y +=3D efi/ obj-y +=3D imx/ obj-y +=3D psci/ obj-y +=3D qcom/ +obj-y +=3D riscv/ obj-y +=3D samsung/ obj-y +=3D smccc/ obj-y +=3D tegra/ diff --git a/drivers/firmware/riscv/Kconfig b/drivers/firmware/riscv/Kconfig new file mode 100644 index 000000000000..ed5b663ac5f9 --- /dev/null +++ b/drivers/firmware/riscv/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "Risc-V Specific firmware drivers" +depends on RISCV + +config RISCV_SBI_SSE + bool "Enable SBI Supervisor Software Events support" + depends on RISCV_SBI + default y + help + The Supervisor Software Events support allows the SBI to deliver + NMI-like notifications to the supervisor mode software. When enabled, + this option provides support to register callbacks on specific SSE + events. + +endmenu diff --git a/drivers/firmware/riscv/Makefile b/drivers/firmware/riscv/Makef= ile new file mode 100644 index 000000000000..c8795d4bbb2e --- /dev/null +++ b/drivers/firmware/riscv/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_RISCV_SBI_SSE) +=3D riscv_sbi_sse.o diff --git a/drivers/firmware/riscv/riscv_sbi_sse.c b/drivers/firmware/risc= v/riscv_sbi_sse.c new file mode 100644 index 000000000000..830011ddd33f --- /dev/null +++ b/drivers/firmware/riscv/riscv_sbi_sse.c @@ -0,0 +1,694 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2025 Rivos Inc. + */ + +#define pr_fmt(fmt) "sse: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +struct sse_event { + struct list_head list; + u32 evt_id; + u32 priority; + sse_event_handler_fn *handler; + void *handler_arg; + /* Only valid for global events */ + unsigned int cpu; + + union { + struct sse_registered_event *global; + struct sse_registered_event __percpu *local; + }; +}; + +static int sse_hp_state; +static bool sse_available __ro_after_init; +static DEFINE_SPINLOCK(events_list_lock); +static LIST_HEAD(events); +static DEFINE_MUTEX(sse_mutex); + +struct sse_registered_event { + struct sse_event_arch_data arch; + struct sse_event *event; + unsigned long attr; + bool is_enabled; +}; + +void sse_handle_event(struct sse_event_arch_data *arch_event, + struct pt_regs *regs) +{ + int ret; + struct sse_registered_event *reg_evt =3D + container_of(arch_event, struct sse_registered_event, arch); + struct sse_event *evt =3D reg_evt->event; + + ret =3D evt->handler(evt->evt_id, evt->handler_arg, regs); + if (ret) + pr_warn("event %x handler failed with error %d\n", evt->evt_id, ret); +} + +static struct sse_event *sse_event_get(u32 evt) +{ + struct sse_event *event =3D NULL; + + scoped_guard(spinlock, &events_list_lock) { + list_for_each_entry(event, &events, list) { + if (event->evt_id =3D=3D evt) + return event; + } + } + + return NULL; +} + +static phys_addr_t sse_event_get_attr_phys(struct sse_registered_event *re= g_evt) +{ + phys_addr_t phys; + void *addr =3D ®_evt->attr; + + if (sse_event_is_global(reg_evt->event->evt_id)) + phys =3D virt_to_phys(addr); + else + phys =3D per_cpu_ptr_to_phys(addr); + + return phys; +} + +static struct sse_registered_event *sse_get_reg_evt(struct sse_event *even= t) +{ + if (sse_event_is_global(event->evt_id)) + return event->global; + else + return per_cpu_ptr(event->local, smp_processor_id()); +} + +static int sse_sbi_event_func(struct sse_event *event, unsigned long func) +{ + struct sbiret ret; + u32 evt =3D event->evt_id; + struct sse_registered_event *reg_evt =3D sse_get_reg_evt(event); + + ret =3D sbi_ecall(SBI_EXT_SSE, func, evt, 0, 0, 0, 0, 0); + if (ret.error) { + pr_warn("Failed to execute func %lx, event %x, error %ld\n", + func, evt, ret.error); + return sbi_err_map_linux_errno(ret.error); + } + + if (func =3D=3D SBI_SSE_EVENT_DISABLE) + reg_evt->is_enabled =3D false; + else if (func =3D=3D SBI_SSE_EVENT_ENABLE) + reg_evt->is_enabled =3D true; + + return 0; +} + +int sse_event_disable_local(struct sse_event *event) +{ + return sse_sbi_event_func(event, SBI_SSE_EVENT_DISABLE); +} +EXPORT_SYMBOL_GPL(sse_event_disable_local); + +int sse_event_enable_local(struct sse_event *event) +{ + return sse_sbi_event_func(event, SBI_SSE_EVENT_ENABLE); +} +EXPORT_SYMBOL_GPL(sse_event_enable_local); + +static int sse_event_attr_get_no_lock(struct sse_registered_event *reg_evt, + unsigned long attr_id, unsigned long *val) +{ + struct sbiret sret; + u32 evt =3D reg_evt->event->evt_id; + unsigned long phys; + + phys =3D sse_event_get_attr_phys(reg_evt); + + sret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_EVENT_ATTR_READ, evt, attr_id, 1, + phys, 0, 0); + if (sret.error) { + pr_debug("Failed to get event %x attr %lx, error %ld\n", evt, + attr_id, sret.error); + return sbi_err_map_linux_errno(sret.error); + } + + *val =3D reg_evt->attr; + + return 0; +} + +static int sse_event_attr_set_nolock(struct sse_registered_event *reg_evt, + unsigned long attr_id, unsigned long val) +{ + struct sbiret sret; + u32 evt =3D reg_evt->event->evt_id; + unsigned long phys; + + reg_evt->attr =3D val; + phys =3D sse_event_get_attr_phys(reg_evt); + + sret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_EVENT_ATTR_WRITE, evt, attr_id, 1, + phys, 0, 0); + if (sret.error) + pr_debug("Failed to set event %x attr %lx, error %ld\n", evt, + attr_id, sret.error); + + return sbi_err_map_linux_errno(sret.error); +} + +static void sse_global_event_update_cpu(struct sse_event *event, + unsigned int cpu) +{ + struct sse_registered_event *reg_evt =3D event->global; + + event->cpu =3D cpu; + arch_sse_event_update_cpu(®_evt->arch, cpu); +} + +static int sse_event_set_target_cpu_nolock(struct sse_event *event, + unsigned int cpu) +{ + unsigned long hart_id =3D cpuid_to_hartid_map(cpu); + struct sse_registered_event *reg_evt =3D event->global; + u32 evt =3D event->evt_id; + bool was_enabled; + int ret; + + if (!sse_event_is_global(evt)) + return -EINVAL; + + was_enabled =3D reg_evt->is_enabled; + if (was_enabled) + sse_event_disable_local(event); + + ret =3D sse_event_attr_set_nolock(reg_evt, SBI_SSE_ATTR_PREFERRED_HART, + hart_id); + if (ret =3D=3D 0) + sse_global_event_update_cpu(event, cpu); + + if (was_enabled) + sse_event_enable_local(event); + + return 0; +} + +int sse_event_set_target_cpu(struct sse_event *event, unsigned int cpu) +{ + int ret; + + scoped_guard(mutex, &sse_mutex) { + scoped_guard(cpus_read_lock) { + if (!cpu_online(cpu)) + return -EINVAL; + + ret =3D sse_event_set_target_cpu_nolock(event, cpu); + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(sse_event_set_target_cpu); + +static int sse_event_init_registered(unsigned int cpu, + struct sse_registered_event *reg_evt, + struct sse_event *event) +{ + reg_evt->event =3D event; + + return arch_sse_init_event(®_evt->arch, event->evt_id, cpu); +} + +static void sse_event_free_registered(struct sse_registered_event *reg_evt) +{ + arch_sse_free_event(®_evt->arch); +} + +static int sse_event_alloc_global(struct sse_event *event) +{ + int err; + struct sse_registered_event *reg_evt; + + reg_evt =3D kzalloc_obj(*reg_evt, GFP_KERNEL); + if (!reg_evt) + return -ENOMEM; + + event->global =3D reg_evt; + err =3D sse_event_init_registered(smp_processor_id(), reg_evt, event); + if (err) + kfree(reg_evt); + + return err; +} + +static int sse_event_alloc_local(struct sse_event *event) +{ + int err; + unsigned int cpu, err_cpu; + struct sse_registered_event *reg_evt; + struct sse_registered_event __percpu *reg_evts; + + reg_evts =3D alloc_percpu(struct sse_registered_event); + if (!reg_evts) + return -ENOMEM; + + event->local =3D reg_evts; + + for_each_possible_cpu(cpu) { + reg_evt =3D per_cpu_ptr(reg_evts, cpu); + err =3D sse_event_init_registered(cpu, reg_evt, event); + if (err) { + err_cpu =3D cpu; + goto err_free_per_cpu; + } + } + + return 0; + +err_free_per_cpu: + for_each_possible_cpu(cpu) { + if (cpu =3D=3D err_cpu) + break; + reg_evt =3D per_cpu_ptr(reg_evts, cpu); + sse_event_free_registered(reg_evt); + } + + free_percpu(reg_evts); + + return err; +} + +static struct sse_event *sse_event_alloc(u32 evt, u32 priority, + sse_event_handler_fn *handler, + void *arg) +{ + int err; + struct sse_event *event; + + event =3D kzalloc_obj(*event, GFP_KERNEL); + if (!event) + return ERR_PTR(-ENOMEM); + + event->evt_id =3D evt; + event->priority =3D priority; + event->handler_arg =3D arg; + event->handler =3D handler; + + if (sse_event_is_global(evt)) + err =3D sse_event_alloc_global(event); + else + err =3D sse_event_alloc_local(event); + + if (err) { + kfree(event); + return ERR_PTR(err); + } + + return event; +} + +static int sse_sbi_register_event(struct sse_event *event, + struct sse_registered_event *reg_evt) +{ + int ret; + + ret =3D sse_event_attr_set_nolock(reg_evt, SBI_SSE_ATTR_PRIO, + event->priority); + if (ret) + return ret; + + return arch_sse_register_event(®_evt->arch); +} + +static int sse_event_register_local(struct sse_event *event) +{ + int ret; + struct sse_registered_event *reg_evt; + + reg_evt =3D per_cpu_ptr(event->local, smp_processor_id()); + ret =3D sse_sbi_register_event(event, reg_evt); + if (ret) + pr_debug("Failed to register event %x: err %d\n", event->evt_id, + ret); + + return ret; +} + +static int sse_sbi_unregister_event(struct sse_event *event) +{ + return sse_sbi_event_func(event, SBI_SSE_EVENT_UNREGISTER); +} + +struct sse_per_cpu_evt { + struct sse_event *event; + unsigned long func; + cpumask_t error; +}; + +static void sse_event_per_cpu_func(void *info) +{ + int ret; + struct sse_per_cpu_evt *cpu_evt =3D info; + + if (cpu_evt->func =3D=3D SBI_SSE_EVENT_REGISTER) + ret =3D sse_event_register_local(cpu_evt->event); + else + ret =3D sse_sbi_event_func(cpu_evt->event, cpu_evt->func); + + if (ret) + cpumask_set_cpu(smp_processor_id(), &cpu_evt->error); +} + +static void sse_event_free(struct sse_event *event) +{ + unsigned int cpu; + struct sse_registered_event *reg_evt; + + if (sse_event_is_global(event->evt_id)) { + sse_event_free_registered(event->global); + kfree(event->global); + } else { + for_each_possible_cpu(cpu) { + reg_evt =3D per_cpu_ptr(event->local, cpu); + sse_event_free_registered(reg_evt); + } + free_percpu(event->local); + } + + kfree(event); +} + +static int sse_on_each_cpu(struct sse_event *event, unsigned long func, + unsigned long revert_func) +{ + struct sse_per_cpu_evt cpu_evt; + + cpu_evt.event =3D event; + cpumask_clear(&cpu_evt.error); + cpu_evt.func =3D func; + on_each_cpu(sse_event_per_cpu_func, &cpu_evt, 1); + /* + * If there are some error reported by CPUs, revert event state on the + * other ones + */ + if (!cpumask_empty(&cpu_evt.error)) { + cpumask_t revert; + + cpumask_andnot(&revert, cpu_online_mask, &cpu_evt.error); + cpu_evt.func =3D revert_func; + on_each_cpu_mask(&revert, sse_event_per_cpu_func, &cpu_evt, 1); + + return -EIO; + } + + return 0; +} + +int sse_event_enable(struct sse_event *event) +{ + int ret =3D 0; + + scoped_guard(mutex, &sse_mutex) { + scoped_guard(cpus_read_lock) { + if (sse_event_is_global(event->evt_id)) { + ret =3D sse_event_enable_local(event); + } else { + ret =3D sse_on_each_cpu(event, + SBI_SSE_EVENT_ENABLE, + SBI_SSE_EVENT_DISABLE); + } + } + } + return ret; +} +EXPORT_SYMBOL_GPL(sse_event_enable); + +static int sse_events_mask(void) +{ + struct sbiret ret; + + ret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_HART_MASK, 0, 0, 0, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +static int sse_events_unmask(void) +{ + struct sbiret ret; + + ret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_HART_UNMASK, 0, 0, 0, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +static void sse_event_disable_nolock(struct sse_event *event) +{ + struct sse_per_cpu_evt cpu_evt; + + if (sse_event_is_global(event->evt_id)) { + sse_event_disable_local(event); + } else { + cpu_evt.event =3D event; + cpu_evt.func =3D SBI_SSE_EVENT_DISABLE; + on_each_cpu(sse_event_per_cpu_func, &cpu_evt, 1); + } +} + +void sse_event_disable(struct sse_event *event) +{ + scoped_guard(mutex, &sse_mutex) { + scoped_guard(cpus_read_lock) { + sse_event_disable_nolock(event); + } + } +} +EXPORT_SYMBOL_GPL(sse_event_disable); + +struct sse_event *sse_event_register(u32 evt, u32 priority, + sse_event_handler_fn *handler, void *arg) +{ + struct sse_event *event; + int cpu; + int ret =3D 0; + + if (!sse_available) + return ERR_PTR(-EOPNOTSUPP); + + guard(mutex)(&sse_mutex); + if (sse_event_get(evt)) + return ERR_PTR(-EEXIST); + + event =3D sse_event_alloc(evt, priority, handler, arg); + if (IS_ERR(event)) + return event; + + scoped_guard(cpus_read_lock) { + if (sse_event_is_global(evt)) { + unsigned long preferred_hart; + + ret =3D sse_event_attr_get_no_lock(event->global, + SBI_SSE_ATTR_PREFERRED_HART, + &preferred_hart); + if (ret) + goto err_event_free; + + cpu =3D riscv_hartid_to_cpuid(preferred_hart); + sse_global_event_update_cpu(event, cpu); + + ret =3D sse_sbi_register_event(event, event->global); + if (ret) + goto err_event_free; + + } else { + ret =3D sse_on_each_cpu(event, SBI_SSE_EVENT_REGISTER, + SBI_SSE_EVENT_DISABLE); + if (ret) + goto err_event_free; + } + } + + scoped_guard(spinlock, &events_list_lock) + list_add(&event->list, &events); + + return event; + +err_event_free: + sse_event_free(event); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(sse_event_register); + +static void sse_event_unregister_nolock(struct sse_event *event) +{ + struct sse_per_cpu_evt cpu_evt; + + if (sse_event_is_global(event->evt_id)) { + sse_sbi_unregister_event(event); + } else { + cpu_evt.event =3D event; + cpu_evt.func =3D SBI_SSE_EVENT_UNREGISTER; + on_each_cpu(sse_event_per_cpu_func, &cpu_evt, 1); + } +} + +void sse_event_unregister(struct sse_event *event) +{ + scoped_guard(mutex, &sse_mutex) { + scoped_guard(cpus_read_lock) + sse_event_unregister_nolock(event); + + scoped_guard(spinlock, &events_list_lock) + list_del(&event->list); + + sse_event_free(event); + } +} +EXPORT_SYMBOL_GPL(sse_event_unregister); + +static int sse_cpu_online(unsigned int cpu) +{ + struct sse_event *event; + + scoped_guard(spinlock, &events_list_lock) { + list_for_each_entry(event, &events, list) { + if (sse_event_is_global(event->evt_id)) + continue; + + sse_event_register_local(event); + if (sse_get_reg_evt(event)) + sse_event_enable_local(event); + } + } + + /* Ready to handle events. Unmask SSE. */ + return sse_events_unmask(); +} + +static int sse_cpu_teardown(unsigned int cpu) +{ + int ret =3D 0; + unsigned int next_cpu; + struct sse_event *event; + struct sse_registered_event *reg_evt; + + /* Mask the sse events */ + ret =3D sse_events_mask(); + if (ret) + return ret; + + scoped_guard(spinlock, &events_list_lock) { + list_for_each_entry(event, &events, list) { + /* Disable local event on current cpu */ + if (!sse_event_is_global(event->evt_id)) { + reg_evt =3D sse_get_reg_evt(event); + if (reg_evt->is_enabled) + sse_event_disable_local(event); + + sse_sbi_unregister_event(event); + continue; + } + + if (event->cpu !=3D smp_processor_id()) + continue; + + /* Update destination hart for global event */ + next_cpu =3D cpumask_any_but(cpu_online_mask, cpu); + ret =3D sse_event_set_target_cpu_nolock(event, next_cpu); + } + } + + return ret; +} + +static int sse_pm_notifier(struct notifier_block *nb, unsigned long action, + void *data) +{ + WARN_ON_ONCE(preemptible()); + + switch (action) { + case CPU_PM_ENTER: + sse_events_mask(); + break; + case CPU_PM_EXIT: + case CPU_PM_ENTER_FAILED: + sse_events_unmask(); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block sse_pm_nb =3D { + .notifier_call =3D sse_pm_notifier, +}; + +/* + * Mask all CPUs and unregister all events on panic, reboot or kexec. + */ +static int sse_reboot_notifier(struct notifier_block *nb, unsigned long ac= tion, + void *data) +{ + cpuhp_remove_state(sse_hp_state); + + return NOTIFY_OK; +} + +static struct notifier_block sse_reboot_nb =3D { + .notifier_call =3D sse_reboot_notifier, +}; + +static int __init sse_init(void) +{ + int ret; + + if (sbi_probe_extension(SBI_EXT_SSE) <=3D 0) { + pr_info("Missing SBI SSE extension\n"); + return -EOPNOTSUPP; + } + pr_info("SBI SSE extension detected\n"); + + ret =3D cpu_pm_register_notifier(&sse_pm_nb); + if (ret) { + pr_warn("Failed to register CPU PM notifier...\n"); + return ret; + } + + ret =3D register_reboot_notifier(&sse_reboot_nb); + if (ret) { + pr_warn("Failed to register reboot notifier...\n"); + goto remove_cpupm; + } + + ret =3D cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/sse:online", + sse_cpu_online, sse_cpu_teardown); + if (ret < 0) + goto remove_reboot; + + sse_hp_state =3D ret; + sse_available =3D true; + + return 0; + +remove_reboot: + unregister_reboot_notifier(&sse_reboot_nb); + +remove_cpupm: + cpu_pm_unregister_notifier(&sse_pm_nb); + + return ret; +} +arch_initcall(sse_init); diff --git a/include/linux/riscv_sbi_sse.h b/include/linux/riscv_sbi_sse.h new file mode 100644 index 000000000000..84165cb5f2d0 --- /dev/null +++ b/include/linux/riscv_sbi_sse.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2025 Rivos Inc. + */ + +#ifndef __LINUX_RISCV_SBI_SSE_H +#define __LINUX_RISCV_SBI_SSE_H + +#include +#include + +struct sse_event; +struct pt_regs; + +typedef int (sse_event_handler_fn)(u32 event_num, void *arg, + struct pt_regs *regs); + +#ifdef CONFIG_RISCV_SBI_SSE + +struct sse_event *sse_event_register(u32 event_num, u32 priority, + sse_event_handler_fn *handler, void *arg); + +void sse_event_unregister(struct sse_event *evt); + +int sse_event_set_target_cpu(struct sse_event *sse_evt, unsigned int cpu); + +int sse_event_enable(struct sse_event *sse_evt); + +void sse_event_disable(struct sse_event *sse_evt); + +int sse_event_enable_local(struct sse_event *sse_evt); +int sse_event_disable_local(struct sse_event *sse_evt); + +#else +static inline struct sse_event *sse_event_register(u32 event_num, u32 prio= rity, + sse_event_handler_fn *handler, + void *arg) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void sse_event_unregister(struct sse_event *evt) {} + +static inline int sse_event_set_target_cpu(struct sse_event *sse_evt, + unsigned int cpu) +{ + return -EOPNOTSUPP; +} + +static inline int sse_event_enable(struct sse_event *sse_evt) +{ + return -EOPNOTSUPP; +} + +static inline void sse_event_disable(struct sse_event *sse_evt) {} +#endif +#endif /* __LINUX_RISCV_SBI_SSE_H */ --=20 2.50.1 (Apple Git-155) From nobody Sat Jun 13 06:20:41 2026 Received: from mail-pf1-f178.google.com (mail-pf1-f178.google.com [209.85.210.178]) (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 3F0603890EA for ; Sat, 9 May 2026 13:10:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.178 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332250; cv=none; b=Q+FcwM9e2bz6V5CwzTU6j3cw2frIDW4B3hr/LTYzzJ48yTkqcB50l0fIBIMJtoX8z1/t9g1IgTPnbmfPtWEwoteiZAIv/aRL/V0FnK62JdOFHvHAFmdrFzwjKFxcTreBHpIkroVgPsuHHkOadXmFYd2R9mxcPPvy+PXOoebQjac= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332250; c=relaxed/simple; bh=AxS2hiTvXQ1L7djlfRb8J2l+dnwjjt9GL4eayf9IsPw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=acioagtUM879DSylX3za2UgncRl92KGvaa/pRKT0mRZ0Tbu2huQE/mZj8h2s3bsYg4rVylX01Vxz0K+Cs2nVuV2oNmPdRIZ3BJOMFmizHCxNe/xtAK9vsV8dM1KAttRH4tmxtM2jj7SeNZQ1HJIDPR2u2mx5dJ6+LBgHnGcVLkk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=WJU2Rmwu; arc=none smtp.client-ip=209.85.210.178 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="WJU2Rmwu" Received: by mail-pf1-f178.google.com with SMTP id d2e1a72fcca58-82fbf5d4dc2so2040542b3a.1 for ; Sat, 09 May 2026 06:10:48 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1778332247; x=1778937047; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=35mLlYC50YSAZkc9pjH9mUHgKfH5WzPcTbiF8fQMNpQ=; b=WJU2Rmwu8RPCx21zB1KpFgEul80NwqjZBoRpWcMK+5jp76l0xH+jxuCRvHx6XgjoZq GAmQozcbVV5iYHUO4hnsXsIbwzBPLnulcIfCRNeSPxtVT7phP69DDyIhaFw/dMfwTx6W o6B9bBDcnQ492gAI6ArNI0IKdPtYg3CJNoVUiew+jBZVBb5dM2M+gk7NjyiAj7pMTx6L zt3TBfiCNSx9RgGs13JJprU2UntFbUKHO3FDnzDOdz3o6SYnrhqlLOCFpVMJX31srBAZ KlzxN7XsfkRnLIZqTcWK6hGBrqEI7lGmJ1rfrdtNGwHdAcCIWxLdIZfyW5GJnwe78JT4 IPvA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778332247; x=1778937047; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=35mLlYC50YSAZkc9pjH9mUHgKfH5WzPcTbiF8fQMNpQ=; b=D2qNJQqYdxMHndrPAV+WjAmwnb77kTTJ2bujFa6DAKkwPVUm4gfT9OPZ5Wm8t3TPaW MHYFnXXV3EdznIvbrcgxUSbrpdz6pBgD2nmiEKdrCBSvbyfJgzNr4BGGv4qaGx62aExi f+fGVOEuJmdfxFUnLiV6NsLCGxD7KZeZUn2ZdAGHzJyw0SZ4dfKPNF10fNmuhuqQcvd3 kGnzRR7I3mN/6zTa5nAyIDl9x4QGs3hnfCENwWt1ijtE0y29qbeZ/9jg+Fb/7aMMqMc2 GCSyQTA3orptwx9pHP/gheE5L9hO4U+HDCpzUQCXHBdKZT3ofxQi6F6qKX3Y4E+3cKoY OCpQ== X-Gm-Message-State: AOJu0Ywue70h6PLOlB6gAjUsq1DMtKZdYXPHgJfrmvG3f3/rx7ODbWb2 2qJ6GkMYXwUWgfwK3VWSA8+rsR+l/+ZmQRghvtC0HUCsejpjwCAK6o0Zwnk6lNYn3VM= X-Gm-Gg: Acq92OHITHXafrPPdhUIahX7QSUfcvEF0CAgRA1vDEbIKuA7X0QXiD77yJOUcc22llw b+A1pSb4b0A7Xw9A88I9d3PNb03qMZ904qyOl1eR+Ds/fxgyxHX2VGceYWct3DvTh3z9NqSWpLW a8agvCaM47iKxm9/cwZC8QH7INgW5Zt9jRKf/xCZcjd/qM+iA7a5QCv4tvcuOZlOeYYQWIj5AXJ dv1ZrCry8fBFI4TWEe5P2J8cse0IcrB+oMVLE9rV7k+9IuZ+1/arLMrWiE+zu94Cate8OkbuGsV rTJC6iECv4JzKHYReHAbpzaetIOvYdUxrD5DNecshwnMmjhkUF7Ur2ND/YhUdSyQzLSNKgWmIo0 YKfmxQiq4VTXApnpPFaXupKvqSwSodQIjBsDnSufYismWmFOHxAEAAxRBVABIJfVn5D+29POkow jymt7FVTrYfXaTuBKm7sZivZILrRlovNB0i/e3mNeJsqubWZn2jLs5rCmySGNEMpHwxDs= X-Received: by 2002:a05:6a00:acd:b0:835:405a:7e69 with SMTP id d2e1a72fcca58-83a5c2be5c4mr16061517b3a.16.1778332247317; Sat, 09 May 2026 06:10:47 -0700 (PDT) Received: from FJ7FR2JRQ3.bytedance.net ([155.117.34.6]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-839679c86b3sm18552855b3a.28.2026.05.09.06.10.39 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Sat, 09 May 2026 06:10:46 -0700 (PDT) From: Zhanpeng Zhang To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, linux-kselftest@vger.kernel.org, kvm@vger.kernel.org, kvm-riscv@lists.infradead.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexandre Ghiti , Conor Dooley , =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= , Himanshu Chauhan , Will Deacon , Mark Rutland , Atish Patra , Anup Patel , Shuah Khan , Yunhui Cui , Zhu Yuan , Zhanpeng Zhang Subject: [PATCH v9 4/5] perf: RISC-V: add support for SSE event Date: Sat, 9 May 2026 21:10:01 +0800 Message-ID: <7989b7338b7480164bda55131fb7537bd9416591.1778331862.4.git.zhangzhanpeng.jasper@bytedance.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: References: 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 From: Cl=C3=A9ment L=C3=A9ger In order to use SSE within PMU drivers, register an SSE handler for the local PMU event. Reuse the existing overflow IRQ handler and pass appropriate pt_regs. Add a config option RISCV_PMU_SBI_SSE to select event delivery via SSE events. When the SSE path is used, also honor the return value from perf_event_overflow(). If perf core throttles or disables an event, do not immediately restart the overflowed counters from the SSE handler. Signed-off-by: Cl=C3=A9ment L=C3=A9ger Co-developed-by: Zhanpeng Zhang Signed-off-by: Zhanpeng Zhang --- drivers/perf/Kconfig | 10 +++++ drivers/perf/riscv_pmu.c | 23 +++++++++++ drivers/perf/riscv_pmu_sbi.c | 78 ++++++++++++++++++++++++++++++++----- include/linux/perf/riscv_pmu.h | 5 +++ 4 files changed, 104 insertions(+), 12 deletions(-) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index ab90932fc2d0..b6c58475091c 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -105,6 +105,16 @@ config RISCV_PMU_SBI full perf feature support i.e. counter overflow, privilege mode filtering, counter configuration. =20 +config RISCV_PMU_SBI_SSE + depends on RISCV_PMU && RISCV_SBI_SSE + bool "RISC-V PMU SSE events" + default n + help + Say y if you want to use SSE events to deliver PMU interrupts. This + provides a way to profile the kernel at any level by using NMI-like + SSE events. Since SSE events can be intrusive, this option allows + selecting them only when needed. + config STARFIVE_STARLINK_PMU depends on ARCH_STARFIVE || COMPILE_TEST depends on 64BIT diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 8e3cd0f35336..a48e286d9394 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include =20 @@ -254,6 +255,24 @@ void riscv_pmu_start(struct perf_event *event, int fla= gs) perf_event_update_userpage(event); } =20 +#ifdef CONFIG_RISCV_PMU_SBI_SSE +static void riscv_pmu_disable(struct pmu *pmu) +{ + struct riscv_pmu *rvpmu =3D to_riscv_pmu(pmu); + + if (rvpmu->sse_evt) + sse_event_disable_local(rvpmu->sse_evt); +} + +static void riscv_pmu_enable(struct pmu *pmu) +{ + struct riscv_pmu *rvpmu =3D to_riscv_pmu(pmu); + + if (rvpmu->sse_evt) + sse_event_enable_local(rvpmu->sse_evt); +} +#endif + static int riscv_pmu_add(struct perf_event *event, int flags) { struct riscv_pmu *rvpmu =3D to_riscv_pmu(event->pmu); @@ -411,6 +430,10 @@ struct riscv_pmu *riscv_pmu_alloc(void) .event_mapped =3D riscv_pmu_event_mapped, .event_unmapped =3D riscv_pmu_event_unmapped, .event_idx =3D riscv_pmu_event_idx, +#ifdef CONFIG_RISCV_PMU_SBI_SSE + .pmu_enable =3D riscv_pmu_enable, + .pmu_disable =3D riscv_pmu_disable, +#endif .add =3D riscv_pmu_add, .del =3D riscv_pmu_del, .start =3D riscv_pmu_start, diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 385af5e6e6d0..ac10ebd73c7c 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -1038,10 +1039,10 @@ static void pmu_sbi_start_overflow_mask(struct risc= v_pmu *pmu, pmu_sbi_start_ovf_ctrs_sbi(cpu_hw_evt, ctr_ovf_mask); } =20 -static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) +static irqreturn_t pmu_sbi_ovf_handler(struct cpu_hw_events *cpu_hw_evt, + struct pt_regs *regs, bool from_sse) { struct perf_sample_data data; - struct pt_regs *regs; struct hw_perf_event *hw_evt; union sbi_pmu_ctr_info *info; int lidx, hidx, fidx; @@ -1049,7 +1050,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void = *dev) struct perf_event *event; + int ev_overflow =3D 0; u64 overflow; u64 overflowed_ctrs =3D 0; - struct cpu_hw_events *cpu_hw_evt =3D dev; u64 start_clock =3D sched_clock(); struct riscv_pmu_snapshot_data *sdata =3D cpu_hw_evt->snapshot_addr; =20 @@ -1059,13 +1059,15 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, voi= d *dev) /* Firmware counter don't support overflow yet */ fidx =3D find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS); if (fidx =3D=3D RISCV_MAX_COUNTERS) { - csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); + if (!from_sse) + csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); return IRQ_NONE; } =20 event =3D cpu_hw_evt->events[fidx]; if (!event) { - ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); + if (!from_sse) + ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); return IRQ_NONE; } =20 @@ -1080,16 +1082,16 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, voi= d *dev) =20 /* * Overflow interrupt pending bit should only be cleared after stopping - * all the counters to avoid any race condition. + * all the counters to avoid any race condition. When using SSE, + * interrupt is cleared when stopping counters. */ - ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); + if (!from_sse) + ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); =20 /* No overflow bit is set */ if (!overflow) return IRQ_NONE; =20 - regs =3D get_irq_regs(); - for_each_set_bit(lidx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) { struct perf_event *event =3D cpu_hw_evt->events[lidx]; =20 @@ -1133,18 +1136,65 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, voi= d *dev) * TODO: We will need to stop the guest counters once * virtualization support is added. */ - perf_event_overflow(event, &data, regs); + ev_overflow |=3D perf_event_overflow(event, &data, regs); } /* Reset the state as we are going to start the counter after the loop */ hw_evt->state =3D 0; } =20 - pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); + if (!ev_overflow || !from_sse) + pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); + perf_sample_event_took(sched_clock() - start_clock); =20 return IRQ_HANDLED; } =20 +static irqreturn_t pmu_sbi_ovf_irq_handler(int irq, void *dev) +{ + return pmu_sbi_ovf_handler(dev, get_irq_regs(), false); +} + +#ifdef CONFIG_RISCV_PMU_SBI_SSE +static int pmu_sbi_ovf_sse_handler(u32 evt, void *arg, struct pt_regs *reg= s) +{ + struct cpu_hw_events __percpu *hw_events =3D arg; + struct cpu_hw_events *hw_event =3D raw_cpu_ptr(hw_events); + + pmu_sbi_ovf_handler(hw_event, regs, true); + + return 0; +} + +static int pmu_sbi_setup_sse(struct riscv_pmu *pmu) +{ + int ret; + struct sse_event *evt; + struct cpu_hw_events __percpu *hw_events =3D pmu->hw_events; + + evt =3D sse_event_register(SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW, 0, + pmu_sbi_ovf_sse_handler, hw_events); + if (IS_ERR(evt)) + return PTR_ERR(evt); + + ret =3D sse_event_enable(evt); + if (ret) { + sse_event_unregister(evt); + return ret; + } + + pr_info("using SSE for PMU event delivery\n"); + pmu->sse_evt =3D evt; + + return ret; +} +#else +static int pmu_sbi_setup_sse(struct riscv_pmu *pmu) +{ + return -EOPNOTSUPP; +} +#endif + static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) { struct riscv_pmu *pmu =3D hlist_entry_safe(node, struct riscv_pmu, node); @@ -1195,6 +1242,10 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu,= struct platform_device *pde struct cpu_hw_events __percpu *hw_events =3D pmu->hw_events; struct irq_domain *domain =3D NULL; =20 + ret =3D pmu_sbi_setup_sse(pmu); + if (!ret) + return 0; + if (riscv_isa_extension_available(NULL, SSCOFPMF)) { riscv_pmu_irq_num =3D RV_IRQ_PMU; riscv_pmu_use_irq =3D true; @@ -1229,7 +1280,7 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, = struct platform_device *pde return -ENODEV; } =20 - ret =3D request_percpu_irq(riscv_pmu_irq, pmu_sbi_ovf_handler, "riscv-pmu= ", hw_events); + ret =3D request_percpu_irq(riscv_pmu_irq, pmu_sbi_ovf_irq_handler, "riscv= -pmu", hw_events); if (ret) { pr_err("registering percpu irq failed [%d]\n", ret); return ret; diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index f82a28040594..08fdcf6baf4e 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -28,6 +28,8 @@ =20 #define RISCV_PMU_CONFIG1_GUEST_EVENTS 0x1 =20 +struct sse_event; + struct cpu_hw_events { /* currently enabled events */ int n_events; @@ -54,6 +56,9 @@ struct riscv_pmu { char *name; =20 irqreturn_t (*handle_irq)(int irq_num, void *dev); +#ifdef CONFIG_RISCV_PMU_SBI_SSE + struct sse_event *sse_evt; +#endif =20 unsigned long cmask; u64 (*ctr_read)(struct perf_event *event); --=20 2.50.1 (Apple Git-155) From nobody Sat Jun 13 06:20:41 2026 Received: from mail-pf1-f175.google.com (mail-pf1-f175.google.com [209.85.210.175]) (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 557D7388E5E for ; Sat, 9 May 2026 13:10:56 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.175 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332258; cv=none; b=sm21KssrdMGJNT1KFg5fB/sANAliuNJSYBPUCAvZkPKFymiSLARu/VWJzceDWAEIP9HxZEhyJ5oPEDF7peIhxmL8megw50cahWe+pqWC4k/scmUeUn+icRiofPVe7BqJiuaih7MrIBdVybqHFgRrOMMVaerlMLOWDQwLLhUAV3I= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778332258; c=relaxed/simple; bh=ebCvpVlXYudCqk2oDUSNFMiqT9vZTUFFH6ipMm2gON8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=EbrGlDD5kz+fUM2sPWfzOWGXn0i9AO7fSLfPiMBQ6yTdi7VRPMdIV2sjmyYoSSUFhlgemKyugY3/nv+tqvbgdbBF6uyuwrskarrKrQfeVXC8B67QLpzCpbx+kLqNR5SM87bZQHcOvPyTyYI8XBBr6xwOLzrgy4GFLHektJvqaOA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=Ye9RrcB3; arc=none smtp.client-ip=209.85.210.175 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="Ye9RrcB3" Received: by mail-pf1-f175.google.com with SMTP id d2e1a72fcca58-8367df48711so1315681b3a.1 for ; Sat, 09 May 2026 06:10:56 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1778332256; x=1778937056; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=fXfPGCZUlYh3ML2E5Z35byh0hcud282pgOoFG2gFoW4=; b=Ye9RrcB36JAb76tmG1WfKVjY6nS+oKFIC2uJqy6/gxJVCoPr5DppXkKxbukzgoZSJE 6QkdE3euYR61OzKRP0U9kJwRtnVU5t+OpxDZ48iXs2Gh9vmbcPzWKSwXpcbtN7gzDaxa Iu9NO225wVRNBA+izptc0VRMuXu1348xDybml5csdzoXFEtkLmCVAq9efqM9DI4Ay4Xd ruQST9SXUrJlD5NWjkOsJevVWd/nt2tu/Izvoiq7/OxRlk7FSiouU+MDzgBZUw1jkn9o +PXNpoOwnGW6RlS3wJwjTX7IsN9RuZ0PxdlwAZ1xXzEK65vkDMdPlpo7Auf7KI4Fiu0Y EQsg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778332256; x=1778937056; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=fXfPGCZUlYh3ML2E5Z35byh0hcud282pgOoFG2gFoW4=; b=aJdQrhEZ+M1cNMdH1rFSQ0GL88Wh5EMs2UfPFaGEGII3z+JGAWQv+4RS+fsgQ+5QvQ +3L4bzJqx5OpYBntw8q9bpf8V+TckbuQUZs4++CH7L8+I1YT+ePIlpLYYuXmskQnk35Y Ow3OVFanUxqLXnijoyw2B9fF20K2PyFLwFX0iamarn/g1KNfQ06gaml2o0ZyJZEYdosE 3KisBshpYyOwfXTE71+mVKNSj9UedUNCyYd/bxjSISTk461HfYdoQboP4cCXZCTqF2Nl dm1X2GpGEg0ZAkZJBs+T6dzuuPSoW3gk0OfZSAEdkljk3xd8A5Z0OLGSk/rS8HKFovFX oQKQ== X-Gm-Message-State: AOJu0Yyl9xTFR8CzookewBWTfWjhJ0vDWHXuZCuDMi1tbgmFP3qYyQDJ BpK5HpJHQvx8LJTHZhlI2ZjYl+Aw2aZ+h1p+PJukdiIriHxhmM2Xa6RHZ4Wch4K9bpA= X-Gm-Gg: Acq92OF0F5wDWyQecKSbQ5r8Q6iM7M+/UHePB+xbROZa92nb9UvbuVLJccUHDSmtPVI qhP2kKACfiRJjJpnBuJLxxjSz3vIXX2SVEogiPfBInCwyXSebaaiL5qd4I5XlW2QoKfbJopOnNc OEm61zApBkWLRYXSq/j2gi0xdpu85I/Szb6R5yEnfwc/G9vuwI5g6gcog+mjU0R/krj+91m9uPD Xc5jF/d5p6m/re8BqvwNTXbtm+UqSPi/QqrV0rQF/QC68J+9vG1KuiRpHXNuzjada0vMlSgmeWk ZvK+aSZuncaWmg4EC4Hx+2A0XoP3KonaLPkq3/4WS4J69Jgm3mHr3NJJlkZ76us9A5M3OBLHnl2 cGM839AB59B2WdUV+1EFY45narCxYTIkBw0LAq8kEEGVNMGlWPH0mRaQyCME/S7FWe5OQmfH+8b kgUuDzDapyR+HQqd2hEV/5n5mjmSlTpzbdpJcYjj1q5BSRSwru+HXZkX9pyVQpuoPeMTs= X-Received: by 2002:a05:6a00:1411:b0:838:c01a:7a50 with SMTP id d2e1a72fcca58-83a5d68134fmr15695879b3a.30.1778332255468; Sat, 09 May 2026 06:10:55 -0700 (PDT) Received: from FJ7FR2JRQ3.bytedance.net ([155.117.34.6]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-839679c86b3sm18552855b3a.28.2026.05.09.06.10.47 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Sat, 09 May 2026 06:10:54 -0700 (PDT) From: Zhanpeng Zhang To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, linux-kselftest@vger.kernel.org, kvm@vger.kernel.org, kvm-riscv@lists.infradead.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexandre Ghiti , Conor Dooley , =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= , Himanshu Chauhan , Will Deacon , Mark Rutland , Atish Patra , Anup Patel , Shuah Khan , Yunhui Cui , Zhu Yuan , Zhanpeng Zhang Subject: [PATCH v9 5/5] selftests/riscv: add SSE test module Date: Sat, 9 May 2026 21:10:02 +0800 Message-ID: <1f66bfb775e8b6658c6f2f2f48aa4f668f911db5.1778331862.5.git.zhangzhanpeng.jasper@bytedance.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: References: 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 From: Cl=C3=A9ment L=C3=A9ger This module, once loaded, will execute a series of tests using the SSE framework. The provided script will check for any error reported by the test module. Add stress=3D{0,1,2} modes so the same module can cover repeated handler entry, SBI calls from a handler, PMU activity and re-injection. Also make the tests tolerate events that are already registered, and keep the attribute read buffer lifetime local to the SBI call. Signed-off-by: Cl=C3=A9ment L=C3=A9ger Co-developed-by: Zhanpeng Zhang Signed-off-by: Zhanpeng Zhang --- MAINTAINERS | 1 + tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/sse/Makefile | 5 + .../selftests/riscv/sse/module/Makefile | 16 + .../riscv/sse/module/riscv_sse_test.c | 769 ++++++++++++++++++ .../selftests/riscv/sse/run_sse_test.sh | 48 ++ 6 files changed, 840 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/riscv/sse/Makefile create mode 100644 tools/testing/selftests/riscv/sse/module/Makefile create mode 100644 tools/testing/selftests/riscv/sse/module/riscv_sse_test= .c create mode 100644 tools/testing/selftests/riscv/sse/run_sse_test.sh diff --git a/MAINTAINERS b/MAINTAINERS index c247acc56d1c..e4bb9b880c26 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22902,6 +22902,7 @@ C: irc://irc.libera.chat/riscv P: Documentation/arch/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ +F: tools/testing/selftests/riscv/ N: riscv K: riscv =20 diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftes= ts/riscv/Makefile index 5671b4405a12..43c7c8f97676 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?=3D $(shell uname -m 2>/dev/null || echo not) =20 ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?=3D abi hwprobe mm sigreturn vector cfi +RISCV_SUBTARGETS ?=3D abi hwprobe mm sigreturn vector cfi sse else RISCV_SUBTARGETS :=3D endif diff --git a/tools/testing/selftests/riscv/sse/Makefile b/tools/testing/sel= ftests/riscv/sse/Makefile new file mode 100644 index 000000000000..67eaee06f213 --- /dev/null +++ b/tools/testing/selftests/riscv/sse/Makefile @@ -0,0 +1,5 @@ +TEST_GEN_MODS_DIR :=3D module + +TEST_FILES :=3D run_sse_test.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/riscv/sse/module/Makefile b/tools/test= ing/selftests/riscv/sse/module/Makefile new file mode 100644 index 000000000000..02018f083456 --- /dev/null +++ b/tools/testing/selftests/riscv/sse/module/Makefile @@ -0,0 +1,16 @@ +TESTMODS_DIR :=3D $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))= )) +KDIR ?=3D /lib/modules/$(shell uname -r)/build + +obj-m +=3D riscv_sse_test.o + +# Ensure that KDIR exists, otherwise skip the compilation +modules: +ifneq ("$(wildcard $(KDIR))", "") + $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=3D$(TESTMODS_DIR) +endif + +# Ensure that KDIR exists, otherwise skip the clean target +clean: +ifneq ("$(wildcard $(KDIR))", "") + $(Q)$(MAKE) -C $(KDIR) clean KBUILD_EXTMOD=3D$(TESTMODS_DIR) +endif diff --git a/tools/testing/selftests/riscv/sse/module/riscv_sse_test.c b/to= ols/testing/selftests/riscv/sse/module/riscv_sse_test.c new file mode 100644 index 000000000000..c0efdfc5467c --- /dev/null +++ b/tools/testing/selftests/riscv/sse/module/riscv_sse_test.c @@ -0,0 +1,769 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2025 Rivos Inc. + */ + +#define pr_fmt(fmt) "riscv_sse_test: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define RUN_LOOP_COUNT 1000 +#define SSE_FAILED_PREFIX "FAILED: " +#define STRESS_DURATION_MS 3000 +#define STRESS_INJECT_NS 10000 +#define STRESS_REINJECT_DEPTH 10 +#define sse_err(...) pr_err(SSE_FAILED_PREFIX __VA_ARGS__) + +enum sse_stress_mode { + SSE_STRESS_OFF, + SSE_STRESS_AFTER_SMOKE, + SSE_STRESS_ONLY, +}; + +static int stress; +module_param(stress, int, 0444); +MODULE_PARM_DESC(stress, "Stress mode: 0=3Doff, 1=3Dafter smoke, 2=3Dstres= s only"); + +struct sse_event_desc { + u32 evt_id; + const char *name; + bool can_inject; +}; + +static struct sse_event_desc sse_event_descs[] =3D { + { + .evt_id =3D SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS, + .name =3D "local_high_prio_ras", + }, + { + .evt_id =3D SBI_SSE_EVENT_LOCAL_DOUBLE_TRAP, + .name =3D "local_double_trap", + }, + { + .evt_id =3D SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS, + .name =3D "global_high_prio_ras", + }, + { + .evt_id =3D SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW, + .name =3D "local_pmu_overflow", + }, + { + .evt_id =3D SBI_SSE_EVENT_LOCAL_LOW_PRIO_RAS, + .name =3D "local_low_prio_ras", + }, + { + .evt_id =3D SBI_SSE_EVENT_GLOBAL_LOW_PRIO_RAS, + .name =3D "global_low_prio_ras", + }, + { + .evt_id =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED, + .name =3D "local_software_injected", + }, + { + .evt_id =3D SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED, + .name =3D "global_software_injected", + } +}; + +static struct sse_event_desc *sse_get_evt_desc(u32 evt) +{ + int i; + + for (i =3D 0; i < ARRAY_SIZE(sse_event_descs); i++) { + if (sse_event_descs[i].evt_id =3D=3D evt) + return &sse_event_descs[i]; + } + + return NULL; +} + +static const char *sse_evt_name(u32 evt) +{ + struct sse_event_desc *desc =3D sse_get_evt_desc(evt); + + return desc ? desc->name : NULL; +} + +static bool sse_test_can_inject_event(u32 evt) +{ + struct sse_event_desc *desc =3D sse_get_evt_desc(evt); + + return desc ? desc->can_inject : false; +} + +static struct sbiret sbi_sse_ecall(int fid, unsigned long arg0, unsigned l= ong arg1) +{ + return sbi_ecall(SBI_EXT_SSE, fid, arg0, arg1, 0, 0, 0, 0); +} + +static int sse_event_attr_get(u32 evt, unsigned long attr_id, + unsigned long *val) +{ + struct sbiret sret; + unsigned long *attr_buf, phys; + + attr_buf =3D kmalloc_obj(*attr_buf, GFP_KERNEL); + if (!attr_buf) + return -ENOMEM; + + phys =3D virt_to_phys(attr_buf); + + sret =3D sbi_ecall(SBI_EXT_SSE, SBI_SSE_EVENT_ATTR_READ, evt, attr_id, 1, + phys, 0, 0); + if (sret.error) { + kfree(attr_buf); + return sbi_err_map_linux_errno(sret.error); + } + + *val =3D *attr_buf; + kfree(attr_buf); + + return 0; +} + +static int sse_test_signal(u32 evt, unsigned int cpu) +{ + unsigned int hart_id =3D cpuid_to_hartid_map(cpu); + struct sbiret ret; + + ret =3D sbi_sse_ecall(SBI_SSE_EVENT_INJECT, evt, hart_id); + if (ret.error) { + sse_err("Failed to signal event %x, error %ld\n", evt, ret.error); + return sbi_err_map_linux_errno(ret.error); + } + + return 0; +} + +static int sse_test_inject_event(struct sse_event *event, u32 evt, unsigne= d int cpu) +{ + int res; + unsigned long status; + + if (sse_event_is_global(evt)) { + /* + * Due to the fact the completion might happen faster than + * the call to SBI_SSE_COMPLETE in the handler, if the event was + * running on another CPU, we need to wait for the event status + * to be !RUNNING. + */ + do { + res =3D sse_event_attr_get(evt, SBI_SSE_ATTR_STATUS, &status); + if (res) { + sse_err("Failed to get status for evt %x, error %d\n", evt, res); + return res; + } + status =3D status & SBI_SSE_ATTR_STATUS_STATE_MASK; + } while (status =3D=3D SBI_SSE_STATE_RUNNING); + + res =3D sse_event_set_target_cpu(event, cpu); + if (res) { + sse_err("Failed to set cpu for evt %x, error %d\n", evt, res); + return res; + } + } + + return sse_test_signal(evt, cpu); +} + +struct fast_test_arg { + u32 evt; + int cpu; + bool completion; +}; + +static int sse_test_handler(u32 evt, void *arg, struct pt_regs *regs) +{ + int ret =3D 0; + struct fast_test_arg *targ =3D arg; + u32 test_evt =3D READ_ONCE(targ->evt); + int cpu =3D READ_ONCE(targ->cpu); + + if (evt !=3D test_evt) { + sse_err("Received SSE event id %x instead of %x\n", test_evt, evt); + ret =3D -EINVAL; + } + + if (cpu !=3D smp_processor_id()) { + sse_err("Received SSE event %d on CPU %d instead of %d\n", evt, smp_proc= essor_id(), + cpu); + ret =3D -EINVAL; + } + + WRITE_ONCE(targ->completion, true); + + return ret; +} + +static void sse_run_fast_test(struct fast_test_arg *test_arg, struct sse_e= vent *event, u32 evt) +{ + unsigned long timeout; + int ret, cpu; + + for_each_online_cpu(cpu) { + WRITE_ONCE(test_arg->completion, false); + WRITE_ONCE(test_arg->cpu, cpu); + /* Test arg is used on another CPU */ + smp_wmb(); + + ret =3D sse_test_inject_event(event, evt, cpu); + if (ret) { + sse_err("event %s injection failed, err %d\n", sse_evt_name(evt), ret); + return; + } + + timeout =3D jiffies + HZ / 100; + /* We can not use since they are not NMI safe */ + while (!READ_ONCE(test_arg->completion) && + time_before(jiffies, timeout)) { + cpu_relax(); + } + if (!time_before(jiffies, timeout)) { + sse_err("Failed to wait for event %s completion on CPU %d\n", + sse_evt_name(evt), cpu); + return; + } + } +} + +static void sse_test_injection_fast(void) +{ + int i, ret =3D 0, j; + u32 evt; + struct fast_test_arg test_arg; + struct sse_event *event; + + pr_info("Starting SSE test (fast)\n"); + + for (i =3D 0; i < ARRAY_SIZE(sse_event_descs); i++) { + evt =3D sse_event_descs[i].evt_id; + WRITE_ONCE(test_arg.evt, evt); + + if (!sse_event_descs[i].can_inject) + continue; + + event =3D sse_event_register(evt, 0, sse_test_handler, + (void *)&test_arg); + if (IS_ERR(event)) { + if (PTR_ERR(event) =3D=3D -EEXIST) { + pr_info("Event %s already registered, skipping\n", + sse_evt_name(evt)); + continue; + } + sse_err("Failed to register event %s, err %ld\n", sse_evt_name(evt), + PTR_ERR(event)); + continue; + } + + ret =3D sse_event_enable(event); + if (ret) { + sse_err("Failed to enable event %s, err %d\n", sse_evt_name(evt), ret); + goto err_unregister; + } + + pr_info("Starting testing event %s\n", sse_evt_name(evt)); + + for (j =3D 0; j < RUN_LOOP_COUNT; j++) + sse_run_fast_test(&test_arg, event, evt); + + pr_info("Finished testing event %s\n", sse_evt_name(evt)); + + sse_event_disable(event); +err_unregister: + sse_event_unregister(event); + } + pr_info("Finished SSE test (fast)\n"); +} + +struct priority_test_arg { + unsigned long evt; + struct sse_event *event; + bool called; + u32 prio; + struct priority_test_arg *next_evt_arg; + void (*check_func)(struct priority_test_arg *arg); +}; + +static int sse_hi_priority_test_handler(u32 evt, void *arg, + struct pt_regs *regs) +{ + struct priority_test_arg *targ =3D arg; + struct priority_test_arg *next =3D READ_ONCE(targ->next_evt_arg); + + WRITE_ONCE(targ->called, 1); + + if (next) { + sse_test_signal(next->evt, smp_processor_id()); + if (!READ_ONCE(next->called)) { + sse_err("Higher priority event %s was not handled %s\n", + sse_evt_name(next->evt), sse_evt_name(evt)); + } + } + + return 0; +} + +static int sse_low_priority_test_handler(u32 evt, void *arg, struct pt_reg= s *regs) +{ + struct priority_test_arg *targ =3D arg; + struct priority_test_arg *next =3D READ_ONCE(targ->next_evt_arg); + + WRITE_ONCE(targ->called, 1); + + if (next) { + sse_test_signal(next->evt, smp_processor_id()); + if (READ_ONCE(next->called)) { + sse_err("Lower priority event %s was handle before %s\n", + sse_evt_name(next->evt), sse_evt_name(evt)); + } + } + + return 0; +} + +static void sse_test_injection_priority_arg(struct priority_test_arg *args= , unsigned int args_size, + sse_event_handler_fn handler, const char *test_name) +{ + unsigned int i; + int ret; + struct sse_event *event; + struct priority_test_arg *arg, *first_arg =3D NULL, *prev_arg =3D NULL; + + pr_info("Starting SSE priority test (%s)\n", test_name); + for (i =3D 0; i < args_size; i++) { + arg =3D &args[i]; + + if (!sse_test_can_inject_event(arg->evt)) + continue; + + WRITE_ONCE(arg->called, false); + WRITE_ONCE(arg->next_evt_arg, NULL); + WRITE_ONCE(arg->event, NULL); + + event =3D sse_event_register(arg->evt, arg->prio, handler, (void *)arg); + if (IS_ERR(event)) { + if (PTR_ERR(event) =3D=3D -EEXIST) { + pr_info("Event %s already registered, skipping\n", + sse_evt_name(arg->evt)); + continue; + } + sse_err("Failed to register event %s, err %ld\n", sse_evt_name(arg->evt= ), + PTR_ERR(event)); + goto release_events; + } + arg->event =3D event; + + if (sse_event_is_global(arg->evt)) { + /* Target event at current CPU */ + ret =3D sse_event_set_target_cpu(event, smp_processor_id()); + if (ret) { + sse_err("Failed to set event %s target CPU, err %d\n", + sse_evt_name(arg->evt), ret); + goto release_events; + } + } + + ret =3D sse_event_enable(event); + if (ret) { + sse_err("Failed to enable event %s, err %d\n", sse_evt_name(arg->evt), = ret); + goto release_events; + } + + if (prev_arg) + WRITE_ONCE(prev_arg->next_evt_arg, arg); + + prev_arg =3D arg; + + if (!first_arg) + first_arg =3D arg; + } + + if (!first_arg) { + pr_info("No injectable event available for %s priority test\n", + test_name); + return; + } + + /* Inject first event, handler should trigger the others in chain. */ + ret =3D sse_test_inject_event(first_arg->event, first_arg->evt, smp_proce= ssor_id()); + if (ret) { + sse_err("SSE event %s injection failed\n", sse_evt_name(first_arg->evt)); + goto release_events; + } + + /* + * Event are injected directly on the current CPU after calling sse_test_= inject_event() + * so that execution is preempted right away, no need to wait for timeout. + */ + arg =3D first_arg; + while (arg) { + if (!READ_ONCE(arg->called)) { + sse_err("Event %s handler was not called\n", + sse_evt_name(arg->evt)); + ret =3D -EINVAL; + } + + event =3D arg->event; + arg =3D READ_ONCE(arg->next_evt_arg); + } + +release_events: + + arg =3D first_arg; + while (arg) { + event =3D arg->event; + if (!event) + break; + + sse_event_disable(event); + sse_event_unregister(event); + arg =3D READ_ONCE(arg->next_evt_arg); + } + + pr_info("Finished SSE priority test (%s)\n", test_name); +} + +static void sse_test_injection_priority(void) +{ + struct priority_test_arg default_hi_prio_args[] =3D { + { .evt =3D SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED }, + { .evt =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_LOW_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_LOW_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_DOUBLE_TRAP }, + { .evt =3D SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS }, + }; + + struct priority_test_arg default_low_prio_args[] =3D { + { .evt =3D SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_DOUBLE_TRAP }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW }, + { .evt =3D SBI_SSE_EVENT_LOCAL_LOW_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_LOW_PRIO_RAS }, + { .evt =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED }, + + }; + struct priority_test_arg set_prio_args[] =3D { + { .evt =3D SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED, .prio =3D 5 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED, .prio =3D 10 }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_LOW_PRIO_RAS, .prio =3D 15 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_LOW_PRIO_RAS, .prio =3D 20 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW, .prio =3D 25 }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS, .prio =3D 30 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_DOUBLE_TRAP, .prio =3D 35 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS, .prio =3D 40 }, + }; + + struct priority_test_arg same_prio_args[] =3D { + { .evt =3D SBI_SSE_EVENT_LOCAL_PMU_OVERFLOW, .prio =3D 0 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_HIGH_PRIO_RAS, .prio =3D 10 }, + { .evt =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED, .prio =3D 10 }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_SOFTWARE_INJECTED, .prio =3D 10 }, + { .evt =3D SBI_SSE_EVENT_GLOBAL_HIGH_PRIO_RAS, .prio =3D 20 }, + }; + + sse_test_injection_priority_arg(default_hi_prio_args, ARRAY_SIZE(default_= hi_prio_args), + sse_hi_priority_test_handler, "high"); + + sse_test_injection_priority_arg(default_low_prio_args, ARRAY_SIZE(default= _low_prio_args), + sse_low_priority_test_handler, "low"); + + sse_test_injection_priority_arg(set_prio_args, ARRAY_SIZE(set_prio_args), + sse_low_priority_test_handler, "set"); + + sse_test_injection_priority_arg(same_prio_args, ARRAY_SIZE(same_prio_args= ), + sse_low_priority_test_handler, "same_prio_args"); +} + +static bool sse_get_inject_status(u32 evt) +{ + int ret; + unsigned long val; + + /* Check if injection is supported */ + ret =3D sse_event_attr_get(evt, SBI_SSE_ATTR_STATUS, &val); + if (ret) + return false; + + return !!(val & BIT(SBI_SSE_ATTR_STATUS_INJECT_OFFSET)); +} + +static void sse_init_events(void) +{ + int i; + + for (i =3D 0; i < ARRAY_SIZE(sse_event_descs); i++) { + struct sse_event_desc *desc =3D &sse_event_descs[i]; + + desc->can_inject =3D sse_get_inject_status(desc->evt_id); + if (!desc->can_inject) + pr_info("Can not inject event %s, tests using this event will be skippe= d\n", + desc->name); + } +} + +struct stress_test_ctx { + struct sse_event *event; + struct hrtimer timer; + struct hrtimer stop_timer; + struct task_struct *monitor_task; + wait_queue_head_t wait_q; + atomic_t inject_count; + atomic_t handler_count; + u32 evt_id; + int layer; + bool running; + bool test_done; +}; + +static struct stress_test_ctx stress_ctx; +static DEFINE_PER_CPU(int, stress_reinject_cpu_depth); + +static int stress_handler_empty(u32 evt, void *arg, struct pt_regs *regs) +{ + struct stress_test_ctx *ctx =3D arg; + + atomic_inc(&ctx->handler_count); + + return 0; +} + +static int stress_handler_ecall(u32 evt, void *arg, struct pt_regs *regs) +{ + struct stress_test_ctx *ctx =3D arg; + + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_NUM_COUNTERS, 0, 0, 0, 0, 0, 0); + atomic_inc(&ctx->handler_count); + + return 0; +} + +static int stress_handler_pmu(u32 evt, void *arg, struct pt_regs *regs) +{ + struct stress_test_ctx *ctx =3D arg; + + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, 3, 1, 0, 0, 0, 0); + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, 3, 1, 0, 0, 0, 0); + atomic_inc(&ctx->handler_count); + + return 0; +} + +static int stress_handler_reinject(u32 evt, void *arg, struct pt_regs *reg= s) +{ + struct stress_test_ctx *ctx =3D arg; + int *depth =3D this_cpu_ptr(&stress_reinject_cpu_depth); + + (*depth)++; + if (*depth < STRESS_REINJECT_DEPTH) + sse_test_signal(evt, smp_processor_id()); + else + *depth =3D 0; + + atomic_inc(&ctx->handler_count); + + return 0; +} + +static sse_event_handler_fn *stress_handlers[] =3D { + stress_handler_empty, + stress_handler_ecall, + stress_handler_pmu, + stress_handler_reinject, +}; + +static const char * const stress_layer_names[] =3D { + "empty handler", + "SBI ecall in handler", + "PMU stop/start in handler", + "self re-inject", +}; + +static enum hrtimer_restart stress_timer_callback(struct hrtimer *timer) +{ + struct stress_test_ctx *ctx =3D container_of(timer, struct stress_test_ct= x, timer); + + if (!READ_ONCE(ctx->running)) + return HRTIMER_NORESTART; + + sse_test_signal(ctx->evt_id, smp_processor_id()); + atomic_inc(&ctx->inject_count); + hrtimer_forward_now(timer, ns_to_ktime(STRESS_INJECT_NS)); + + return HRTIMER_RESTART; +} + +static enum hrtimer_restart stress_stop_timer_callback(struct hrtimer *tim= er) +{ + struct stress_test_ctx *ctx; + + ctx =3D container_of(timer, struct stress_test_ctx, stop_timer); + WRITE_ONCE(ctx->test_done, true); + wake_up(&ctx->wait_q); + + return HRTIMER_NORESTART; +} + +static int stress_monitor_thread(void *data) +{ + struct stress_test_ctx *ctx =3D data; + unsigned long last_inject =3D 0, last_handler =3D 0; + + while (!kthread_should_stop() && READ_ONCE(ctx->running)) { + unsigned long inject =3D atomic_read(&ctx->inject_count); + unsigned long handler =3D atomic_read(&ctx->handler_count); + + pr_info("stress layer %d: inject=3D%lu (+%lu), handler=3D%lu (+%lu)\n", + ctx->layer, inject, inject - last_inject, + handler, handler - last_handler); + + last_inject =3D inject; + last_handler =3D handler; + + schedule_timeout_interruptible(HZ); + } + + return 0; +} + +static int sse_stress_test_layer(int layer) +{ + struct sse_event *event; + int ret; + + if (layer < 0 || layer >=3D ARRAY_SIZE(stress_handlers)) + return -EINVAL; + + pr_info("Starting SSE stress layer %d (%s)\n", + layer, stress_layer_names[layer]); + + memset(&stress_ctx, 0, sizeof(stress_ctx)); + stress_ctx.evt_id =3D SBI_SSE_EVENT_LOCAL_SOFTWARE_INJECTED; + stress_ctx.layer =3D layer; + WRITE_ONCE(stress_ctx.running, true); + atomic_set(&stress_ctx.inject_count, 0); + atomic_set(&stress_ctx.handler_count, 0); + init_waitqueue_head(&stress_ctx.wait_q); + + event =3D sse_event_register(stress_ctx.evt_id, 0, + stress_handlers[layer], &stress_ctx); + if (IS_ERR(event)) { + sse_err("Failed to register stress event, err %ld\n", + PTR_ERR(event)); + return PTR_ERR(event); + } + + stress_ctx.event =3D event; + + ret =3D sse_event_enable(event); + if (ret) { + sse_err("Failed to enable stress event, err %d\n", ret); + goto err_unregister; + } + + stress_ctx.monitor_task =3D kthread_run(stress_monitor_thread, + &stress_ctx, "sse_stress_mon"); + if (IS_ERR(stress_ctx.monitor_task)) { + ret =3D PTR_ERR(stress_ctx.monitor_task); + sse_err("Failed to create stress monitor thread, err %d\n", ret); + goto err_disable; + } + + hrtimer_setup(&stress_ctx.timer, stress_timer_callback, + CLOCK_MONOTONIC, HRTIMER_MODE_PINNED); + hrtimer_start(&stress_ctx.timer, ns_to_ktime(STRESS_INJECT_NS), + HRTIMER_MODE_REL_PINNED); + + hrtimer_setup(&stress_ctx.stop_timer, stress_stop_timer_callback, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_start(&stress_ctx.stop_timer, ms_to_ktime(STRESS_DURATION_MS), + HRTIMER_MODE_REL); + + wait_event(stress_ctx.wait_q, READ_ONCE(stress_ctx.test_done)); + + WRITE_ONCE(stress_ctx.running, false); + hrtimer_cancel(&stress_ctx.timer); + hrtimer_cancel(&stress_ctx.stop_timer); + kthread_stop(stress_ctx.monitor_task); + + pr_info("Finished SSE stress layer %d (%s): inject=3D%d, handler=3D%d\n", + layer, stress_layer_names[layer], + atomic_read(&stress_ctx.inject_count), + atomic_read(&stress_ctx.handler_count)); + +err_disable: + sse_event_disable(event); +err_unregister: + sse_event_unregister(event); + + return ret; +} + +static void sse_stress_test_all_layers(void) +{ + int i, ret; + + pr_info("Starting SSE stress tests: duration=3D%d ms, interval=3D%d ns\n", + STRESS_DURATION_MS, STRESS_INJECT_NS); + + for (i =3D 0; i < ARRAY_SIZE(stress_handlers); i++) { + ret =3D sse_stress_test_layer(i); + if (ret) + sse_err("Stress layer %d failed, err %d\n", i, ret); + + msleep(100); + } + + pr_info("Finished SSE stress tests\n"); +} + +static int __init sse_test_init(void) +{ + if (stress < SSE_STRESS_OFF || stress > SSE_STRESS_ONLY) { + sse_err("Invalid stress mode %d\n", stress); + return -EINVAL; + } + + sse_init_events(); + + if (stress !=3D SSE_STRESS_ONLY) { + sse_test_injection_fast(); + sse_test_injection_priority(); + } + + if (stress !=3D SSE_STRESS_OFF) + sse_stress_test_all_layers(); + + return 0; +} + +static void __exit sse_test_exit(void) +{ +} + +module_init(sse_test_init); +module_exit(sse_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Cl=C3=A9ment L=C3=A9ger "); +MODULE_DESCRIPTION("Test module for SSE"); diff --git a/tools/testing/selftests/riscv/sse/run_sse_test.sh b/tools/test= ing/selftests/riscv/sse/run_sse_test.sh new file mode 100644 index 000000000000..c8eb1ce51682 --- /dev/null +++ b/tools/testing/selftests/riscv/sse/run_sse_test.sh @@ -0,0 +1,48 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2025 Rivos Inc. + +MODULE_NAME=3Driscv_sse_test +DRIVER=3D"./module/${MODULE_NAME}.ko" + +check_test_failed_prefix() { + if dmesg | grep -q "${MODULE_NAME}: FAILED:";then + echo "${MODULE_NAME} failed, please check dmesg" + exit 1 + fi +} + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=3D4 + +check_test_requirements() +{ + uid=3D$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile ${MODULE_NAME} module" + exit $ksft_skip + fi +} + +check_test_requirements + +if ! insmod $DRIVER "$@" > /dev/null 2>&1; then + echo "${MODULE_NAME}: failed to load, please check dmesg" + exit 1 +fi + +rmmod $MODULE_NAME +check_test_failed_prefix + +exit 0 --=20 2.50.1 (Apple Git-155)