From patchwork Tue Apr 25 07:56:50 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Henry Wang X-Patchwork-Id: 13222994 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from lists.xenproject.org (lists.xenproject.org [192.237.175.120]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 37E88C6FD18 for ; Tue, 25 Apr 2023 07:59:20 +0000 (UTC) Received: from list by lists.xenproject.org with outflank-mailman.525798.817281 (Exim 4.92) (envelope-from ) id 1prDZu-0002zq-Bx; Tue, 25 Apr 2023 07:59:10 +0000 X-Outflank-Mailman: Message body and most headers restored to incoming version Received: by outflank-mailman (output) from mailman id 525798.817281; Tue, 25 Apr 2023 07:59:10 +0000 Received: from localhost ([127.0.0.1] helo=lists.xenproject.org) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1prDZu-0002xu-2V; Tue, 25 Apr 2023 07:59:10 +0000 Received: by outflank-mailman (input) for mailman id 525798; Tue, 25 Apr 2023 07:59:08 +0000 Received: from se1-gles-flk1-in.inumbo.com ([94.247.172.50] helo=se1-gles-flk1.inumbo.com) by lists.xenproject.org with esmtp (Exim 4.92) (envelope-from ) id 1prDYe-0005uB-Si for xen-devel@lists.xenproject.org; Tue, 25 Apr 2023 07:57:52 +0000 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by se1-gles-flk1.inumbo.com (Halon) with ESMTP id e0211fc5-e33e-11ed-8611-37d641c3527e; Tue, 25 Apr 2023 09:57:50 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 23EC4FEC; Tue, 25 Apr 2023 00:58:34 -0700 (PDT) Received: from a015966.shanghai.arm.com (a015966.shanghai.arm.com [10.169.190.5]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id CE20E3F587; Tue, 25 Apr 2023 00:57:47 -0700 (PDT) X-BeenThere: xen-devel@lists.xenproject.org List-Id: Xen developer discussion List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" X-Inumbo-ID: e0211fc5-e33e-11ed-8611-37d641c3527e From: Henry Wang To: xen-devel@lists.xenproject.org Cc: Wei Chen , Stefano Stabellini , Julien Grall , Bertrand Marquis , Volodymyr Babchuk , Henry Wang Subject: [PATCH v4 12/17] xen/arm: enable device tree based NUMA in system init Date: Tue, 25 Apr 2023 15:56:50 +0800 Message-Id: <20230425075655.4037980-13-Henry.Wang@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230425075655.4037980-1-Henry.Wang@arm.com> References: <20230425075655.4037980-1-Henry.Wang@arm.com> MIME-Version: 1.0 From: Wei Chen In this patch, we can start to create NUMA system that is based on device tree. Signed-off-by: Wei Chen Signed-off-by: Henry Wang --- v3 -> v4: 1. No change. v2 -> v3: 1. No change. v1 -> v2: 1. replace ~0 by INVALID_PADDR. 2. only print error messages for invalid dtb data. 3. remove unnecessary return. 4. remove the parameter of numa_init. --- xen/arch/arm/include/asm/numa.h | 5 +++ xen/arch/arm/numa.c | 57 +++++++++++++++++++++++++++++++++ xen/arch/arm/setup.c | 7 ++++ 3 files changed, 69 insertions(+) diff --git a/xen/arch/arm/include/asm/numa.h b/xen/arch/arm/include/asm/numa.h index 15308f5a36..55ac4665db 100644 --- a/xen/arch/arm/include/asm/numa.h +++ b/xen/arch/arm/include/asm/numa.h @@ -45,6 +45,7 @@ extern void numa_set_distance(nodeid_t from, nodeid_t to, unsigned int distance); extern void numa_detect_cpu_node(unsigned int cpu); extern int numa_device_tree_init(const void *fdt); +extern void numa_init(void); #else @@ -90,6 +91,10 @@ static inline void numa_detect_cpu_node(unsigned int cpu) { } +static inline void numa_init(void) +{ +} + #endif #define arch_want_default_dmazone() (false) diff --git a/xen/arch/arm/numa.c b/xen/arch/arm/numa.c index b953c2574a..f4635e0277 100644 --- a/xen/arch/arm/numa.c +++ b/xen/arch/arm/numa.c @@ -18,7 +18,11 @@ * */ #include +#include +#include #include +#include +#include enum dt_numa_status __ro_after_init device_tree_numa = DT_NUMA_DEFAULT; @@ -108,6 +112,59 @@ unsigned char __node_distance(nodeid_t from, nodeid_t to) return node_distance_map[from][to]; } +void __init numa_init(void) +{ + unsigned int idx; + paddr_t ram_start = INVALID_PADDR; + paddr_t ram_size = 0; + paddr_t ram_end = 0; + + /* NUMA has been turned off through Xen parameters */ + if ( numa_off ) + goto mem_init; + + /* Initialize NUMA from device tree when system is not ACPI booted */ + if ( acpi_disabled ) + { + int ret = numa_device_tree_init(device_tree_flattened); + if ( ret ) + { + numa_off = true; + if ( ret == -EINVAL ) + printk(XENLOG_WARNING + "Init NUMA from device tree failed, ret=%d\n", ret); + } + } + else + { + /* We don't support NUMA for ACPI boot currently */ + printk(XENLOG_WARNING + "ACPI NUMA has not been supported yet, NUMA off!\n"); + numa_off = true; + } + +mem_init: + /* + * Find the minimal and maximum address of RAM, NUMA will + * build a memory to node mapping table for the whole range. + */ + ram_start = bootinfo.mem.bank[0].start; + ram_size = bootinfo.mem.bank[0].size; + ram_end = ram_start + ram_size; + for ( idx = 1 ; idx < bootinfo.mem.nr_banks; idx++ ) + { + paddr_t bank_start = bootinfo.mem.bank[idx].start; + paddr_t bank_size = bootinfo.mem.bank[idx].size; + paddr_t bank_end = bank_start + bank_size; + + ram_size = ram_size + bank_size; + ram_start = min(ram_start, bank_start); + ram_end = max(ram_end, bank_end); + } + + numa_initmem_init(PFN_UP(ram_start), PFN_DOWN(ram_end)); +} + int __init arch_get_ram_range(unsigned int idx, paddr_t *start, paddr_t *end) { if ( idx >= bootinfo.mem.nr_banks ) diff --git a/xen/arch/arm/setup.c b/xen/arch/arm/setup.c index 09e18d32df..f05e233f3a 100644 --- a/xen/arch/arm/setup.c +++ b/xen/arch/arm/setup.c @@ -1121,6 +1121,13 @@ void __init start_xen(unsigned long boot_phys_offset, /* Parse the ACPI tables for possible boot-time configuration */ acpi_boot_table_init(); + /* + * Try to initialize NUMA system, if failed, the system will + * fallback to uniform system which means system has only 1 + * NUMA node. + */ + numa_init(); + end_boot_allocator(); /*