From patchwork Thu Feb 10 06:41:07 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Song Liu X-Patchwork-Id: 12741435 X-Patchwork-Delegate: bpf@iogearbox.net 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B7D09C433EF for ; Thu, 10 Feb 2022 06:41:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235372AbiBJGl1 convert rfc822-to-8bit (ORCPT ); Thu, 10 Feb 2022 01:41:27 -0500 Received: from mxb-00190b01.gslb.pphosted.com ([23.128.96.19]:49920 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229901AbiBJGl0 (ORCPT ); Thu, 10 Feb 2022 01:41:26 -0500 Received: from mx0a-00082601.pphosted.com (mx0b-00082601.pphosted.com [67.231.153.30]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9061010A7 for ; Wed, 9 Feb 2022 22:41:28 -0800 (PST) Received: from pps.filterd (m0089730.ppops.net [127.0.0.1]) by m0089730.ppops.net (8.16.1.2/8.16.1.2) with ESMTP id 219NYHAk002462 for ; Wed, 9 Feb 2022 22:41:26 -0800 Received: from maileast.thefacebook.com ([163.114.130.16]) by m0089730.ppops.net (PPS) with ESMTPS id 3e4ha0cp0n-2 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Wed, 09 Feb 2022 22:41:26 -0800 Received: from twshared22811.39.frc1.facebook.com (2620:10d:c0a8:1b::d) by mail.thefacebook.com (2620:10d:c0a8:83::4) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.21; Wed, 9 Feb 2022 22:41:25 -0800 Received: by devbig006.ftw2.facebook.com (Postfix, from userid 4523) id 42D8229D423BF; Wed, 9 Feb 2022 22:41:19 -0800 (PST) From: Song Liu To: , , CC: , , , , , , Song Liu Subject: [PATCH bpf-next 1/2] vmalloc: expose vmap_allow_huge via get_vmap_allow_huge() Date: Wed, 9 Feb 2022 22:41:07 -0800 Message-ID: <20220210064108.1095847-2-song@kernel.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20220210064108.1095847-1-song@kernel.org> References: <20220210064108.1095847-1-song@kernel.org> MIME-Version: 1.0 X-FB-Internal: Safe X-Proofpoint-ORIG-GUID: Rj27020c0hsBVnTXgRrfCqNs8nak3MFi X-Proofpoint-GUID: Rj27020c0hsBVnTXgRrfCqNs8nak3MFi X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.816,Hydra:6.0.425,FMLib:17.11.62.513 definitions=2022-02-10_02,2022-02-09_01,2021-12-02_01 X-Proofpoint-Spam-Details: rule=fb_outbound_notspam policy=fb_outbound score=0 lowpriorityscore=0 adultscore=0 priorityscore=1501 spamscore=0 malwarescore=0 mlxscore=0 suspectscore=0 impostorscore=0 clxscore=1015 mlxlogscore=999 phishscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2201110000 definitions=main-2202100034 X-FB-Internal: deliver Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Users can use get_vmap_allow_huge() to predict the behavior of vmalloc (or its variations). Specifically, if get_vmap_allow_huge() == false, vmalloc will never return huge pages. Signed-off-by: Song Liu --- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 880227b9f044..22acfcd2d0d1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -256,6 +256,7 @@ extern long vread(char *buf, char *addr, unsigned long count); extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); +extern bool get_vmap_allow_huge(void); #ifdef CONFIG_SMP # ifdef CONFIG_MMU diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4165304d3547..895ac81b6bb4 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -72,6 +72,11 @@ early_param("nohugevmalloc", set_nohugevmalloc); static const bool vmap_allow_huge = false; #endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ +bool get_vmap_allow_huge(void) +{ + return vmap_allow_huge; +} + bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)x; From patchwork Thu Feb 10 06:41:08 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Song Liu X-Patchwork-Id: 12741436 X-Patchwork-Delegate: bpf@iogearbox.net 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 21EC6C433EF for ; Thu, 10 Feb 2022 06:41:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235388AbiBJGlf convert rfc822-to-8bit (ORCPT ); Thu, 10 Feb 2022 01:41:35 -0500 Received: from mxb-00190b01.gslb.pphosted.com ([23.128.96.19]:50000 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235383AbiBJGle (ORCPT ); Thu, 10 Feb 2022 01:41:34 -0500 Received: from mx0b-00082601.pphosted.com (mx0b-00082601.pphosted.com [67.231.153.30]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4DDD510AD for ; Wed, 9 Feb 2022 22:41:32 -0800 (PST) Received: from pps.filterd (m0109331.ppops.net [127.0.0.1]) by mx0a-00082601.pphosted.com (8.16.1.2/8.16.1.2) with ESMTP id 21A1nQ3Q032027 for ; Wed, 9 Feb 2022 22:41:31 -0800 Received: from maileast.thefacebook.com ([163.114.130.16]) by mx0a-00082601.pphosted.com (PPS) with ESMTPS id 3e4sckh48x-3 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Wed, 09 Feb 2022 22:41:31 -0800 Received: from twshared14630.35.frc1.facebook.com (2620:10d:c0a8:1b::d) by mail.thefacebook.com (2620:10d:c0a8:83::4) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.21; Wed, 9 Feb 2022 22:41:30 -0800 Received: by devbig006.ftw2.facebook.com (Postfix, from userid 4523) id 9B7AC29D423C9; Wed, 9 Feb 2022 22:41:21 -0800 (PST) From: Song Liu To: , , CC: , , , , , , Song Liu Subject: [PATCH bpf-next 2/2] bpf: flexible size for bpf_prog_pack Date: Wed, 9 Feb 2022 22:41:08 -0800 Message-ID: <20220210064108.1095847-3-song@kernel.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20220210064108.1095847-1-song@kernel.org> References: <20220210064108.1095847-1-song@kernel.org> MIME-Version: 1.0 X-FB-Internal: Safe X-Proofpoint-ORIG-GUID: 7N-72YumpeA3UUBArK3hRwlBI809_Sel X-Proofpoint-GUID: 7N-72YumpeA3UUBArK3hRwlBI809_Sel X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.816,Hydra:6.0.425,FMLib:17.11.62.513 definitions=2022-02-10_02,2022-02-09_01,2021-12-02_01 X-Proofpoint-Spam-Details: rule=fb_outbound_notspam policy=fb_outbound score=0 malwarescore=0 mlxlogscore=999 clxscore=1015 impostorscore=0 bulkscore=0 spamscore=0 phishscore=0 priorityscore=1501 suspectscore=0 mlxscore=0 lowpriorityscore=0 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2201110000 definitions=main-2202100034 X-FB-Internal: deliver Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net bpf_prog_pack uses huge pages to reduce pressue on instruction TLB. To guarantee allocating huge pages for bpf_prog_pack, it is necessary to allocate memory of size PMD_SIZE * num_online_nodes(). On the other hand, if the system doesn't support huge pages, it is more efficient to allocate PAGE_SIZE bpf_prog_pack. Address different scenarios with more flexible bpf_prog_pack_size(). Signed-off-by: Song Liu --- kernel/bpf/core.c | 47 +++++++++++++++++++++++++++-------------------- 1 file changed, 27 insertions(+), 20 deletions(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 42d96549a804..d961a1f07a13 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -814,46 +814,53 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) * to host BPF programs. */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define BPF_PROG_PACK_SIZE HPAGE_PMD_SIZE -#else -#define BPF_PROG_PACK_SIZE PAGE_SIZE -#endif #define BPF_PROG_CHUNK_SHIFT 6 #define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT) #define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1)) -#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE) struct bpf_prog_pack { struct list_head list; void *ptr; - unsigned long bitmap[BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)]; + unsigned long bitmap[]; }; -#define BPF_PROG_MAX_PACK_PROG_SIZE BPF_PROG_PACK_SIZE #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) static DEFINE_MUTEX(pack_mutex); static LIST_HEAD(pack_list); +static inline int bpf_prog_pack_size(void) +{ + /* If vmap_allow_huge == true, use pack size of the smallest + * possible vmalloc huge page: PMD_SIZE * num_online_nodes(). + * Otherwise, use pack size of PAGE_SIZE. + */ + return get_vmap_allow_huge() ? PMD_SIZE * num_online_nodes() : PAGE_SIZE; +} + +static inline int bpf_prog_chunk_count(void) +{ + return bpf_prog_pack_size() / BPF_PROG_CHUNK_SIZE; +} + static struct bpf_prog_pack *alloc_new_pack(void) { struct bpf_prog_pack *pack; - pack = kzalloc(sizeof(*pack), GFP_KERNEL); + pack = kzalloc(sizeof(*pack) + BITS_TO_BYTES(bpf_prog_chunk_count()), GFP_KERNEL); if (!pack) return NULL; - pack->ptr = module_alloc(BPF_PROG_PACK_SIZE); + pack->ptr = module_alloc(bpf_prog_pack_size()); if (!pack->ptr) { kfree(pack); return NULL; } - bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); + bitmap_zero(pack->bitmap, bpf_prog_pack_size() / BPF_PROG_CHUNK_SIZE); list_add_tail(&pack->list, &pack_list); set_vm_flush_reset_perms(pack->ptr); - set_memory_ro((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); - set_memory_x((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + set_memory_ro((unsigned long)pack->ptr, bpf_prog_pack_size() / PAGE_SIZE); + set_memory_x((unsigned long)pack->ptr, bpf_prog_pack_size() / PAGE_SIZE); return pack; } @@ -864,7 +871,7 @@ static void *bpf_prog_pack_alloc(u32 size) unsigned long pos; void *ptr = NULL; - if (size > BPF_PROG_MAX_PACK_PROG_SIZE) { + if (size > bpf_prog_pack_size()) { size = round_up(size, PAGE_SIZE); ptr = module_alloc(size); if (ptr) { @@ -876,9 +883,9 @@ static void *bpf_prog_pack_alloc(u32 size) } mutex_lock(&pack_mutex); list_for_each_entry(pack, &pack_list, list) { - pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, + pos = bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0, nbits, 0); - if (pos < BPF_PROG_CHUNK_COUNT) + if (pos < bpf_prog_chunk_count()) goto found_free_area; } @@ -904,12 +911,12 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr) unsigned long pos; void *pack_ptr; - if (hdr->size > BPF_PROG_MAX_PACK_PROG_SIZE) { + if (hdr->size > bpf_prog_pack_size()) { module_memfree(hdr); return; } - pack_ptr = (void *)((unsigned long)hdr & ~(BPF_PROG_PACK_SIZE - 1)); + pack_ptr = (void *)((unsigned long)hdr & ~(bpf_prog_pack_size() - 1)); mutex_lock(&pack_mutex); list_for_each_entry(tmp, &pack_list, list) { @@ -926,8 +933,8 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr) pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT; bitmap_clear(pack->bitmap, pos, nbits); - if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, - BPF_PROG_CHUNK_COUNT, 0) == 0) { + if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0, + bpf_prog_chunk_count(), 0) == 0) { list_del(&pack->list); module_memfree(pack->ptr); kfree(pack);