From patchwork Wed Sep 30 22:21:18 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kalesh Singh X-Patchwork-Id: 11810395 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0344D112C for ; Wed, 30 Sep 2020 22:21:48 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id D3A7E21481 for ; Wed, 30 Sep 2020 22:21:47 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="P+s7piSR" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730977AbgI3WVr (ORCPT ); Wed, 30 Sep 2020 18:21:47 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49752 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727210AbgI3WVr (ORCPT ); Wed, 30 Sep 2020 18:21:47 -0400 Received: from mail-qt1-x84a.google.com (mail-qt1-x84a.google.com [IPv6:2607:f8b0:4864:20::84a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 19AB7C061755 for ; Wed, 30 Sep 2020 15:21:47 -0700 (PDT) Received: by mail-qt1-x84a.google.com with SMTP id w3so2224999qtn.16 for ; Wed, 30 Sep 2020 15:21:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=sender:date:in-reply-to:message-id:mime-version:references:subject :from:cc; bh=XbvI12WaHJN29uXJhtZ+EOB9wipW/gZZ4hVhoy3A3pk=; b=P+s7piSRTOYlMasrhJ2oHEQPHoelb8iyusd1TAd6av+DBZjV3mCsezsGb0aM8Cbq8F wcWniTz7nt0cgEMZzRfuoQ9pfRQazas3/PsqYjDs/NBqewHVQbn3A9FR3YF5x8RLQ+yX jcg16G459PC61aytMKkZj8myAxNaZIkOeqF5C6gBGdEB4NIfzn9r9+I4XIjXfWBQTRL9 nS21h4UueeuQ2VbqCnuA3kMG+4TjoDJl/gd2FxnZTiVHWLNyDBQ+8gxZZrGH2WQCMMeD XR49bF8yCpSjBarMyiS0KGX73IcaryYShv5dSNVrdWlHauwdqr5/O7le3VC/vIKhaCKe Hxzg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:in-reply-to:message-id:mime-version :references:subject:from:cc; bh=XbvI12WaHJN29uXJhtZ+EOB9wipW/gZZ4hVhoy3A3pk=; b=Kg9uIx5OC4RrirbmmmSC5rNqTqbpVBXO5KRVbUYjowg8mZ4w2JJHaiazkKN/1WRFuU LlDzDkLCKtOQzSkGwI74/tJbwVxtbpvD5247xRNbNgC8elgxsa6BROmkQHuem9RIBlfo TgzJsSMzH0ibZD+rmpdmhax58EujCV4h2yY47dmDSSP2lvi4f0Yfr+Jko7/+qV6/t/bR SBlnidmVFleNMwgYbA4GN4y3+D/nDj0B4s7fOmKJ50gtUEi45aPoZEr44ZzDAKab7PA+ zm1vUoYXVqZ4Oq6x1f0ohmULmzEv/Ebx8txVSxbp12KYGH5IyTMompvi9vPpfxGUNG91 BBOQ== X-Gm-Message-State: AOAM530FqcZgZitWrWrDbw+sZRgdHjBaOI+9uIMVn2AzFzstI0bT8CGo hUWs4u4QXgcWUEUB+haPRu4cgALjXQmmvJfEmQ== X-Google-Smtp-Source: ABdhPJwwSEexZldCHo9VW8lyUDwdXeRxfa1mYE1k7wqr1xRB7FpnAJwFMYg556it3BiSNrrerzkgakSQGznEqtJ0mQ== Sender: "kaleshsingh via sendgmr" X-Received: from kaleshsingh.c.googlers.com ([fda3:e722:ac3:10:14:4d90:c0a8:2145]) (user=kaleshsingh job=sendgmr) by 2002:a0c:9d03:: with SMTP id m3mr4759136qvf.54.1601504506102; Wed, 30 Sep 2020 15:21:46 -0700 (PDT) Date: Wed, 30 Sep 2020 22:21:18 +0000 In-Reply-To: <20200930222130.4175584-1-kaleshsingh@google.com> Message-Id: <20200930222130.4175584-2-kaleshsingh@google.com> Mime-Version: 1.0 References: <20200930222130.4175584-1-kaleshsingh@google.com> X-Mailer: git-send-email 2.28.0.709.gb0816b6eb0-goog Subject: [PATCH 1/5] kselftests: vm: Add mremap tests From: Kalesh Singh Cc: surenb@google.com, minchan@google.com, joelaf@google.com, lokeshgidra@google.com, kaleshsingh@google.com, kernel-team@android.com, Catalin Marinas , Will Deacon , Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" , Andrew Morton , Shuah Khan , "Aneesh Kumar K.V" , Kees Cook , Peter Zijlstra , Sami Tolvanen , Arnd Bergmann , Masahiro Yamada , Frederic Weisbecker , Krzysztof Kozlowski , Hassan Naveed , Christian Brauner , Mark Rutland , Mike Rapoport , Gavin Shan , Dave Martin , Jia He , Zhenyu Ye , John Hubbard , Jason Gunthorpe , Zi Yan , Mina Almasry , "Kirill A. Shutemov" , Ram Pai , Sandipan Das , Dave Hansen , Ralph Campbell , Brian Geffon , Masami Hiramatsu , Ira Weiny , SeongJae Park , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org To: unlisted-recipients:; (no To-header on input) Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org Test mremap on regions of various sizes and alignments and validate data after remapping. Also provide total time for remapping the region which is useful for performance comparison of the mremap optimizations that move pages at the PMD/PUD levels if HAVE_MOVE_PMD and/or HAVE_MOVE_PUD are enabled. Signed-off-by: Kalesh Singh --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/vm/mremap_test.c | 243 +++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests | 11 + 4 files changed, 256 insertions(+) create mode 100644 tools/testing/selftests/vm/mremap_test.c diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 849e8226395a..b3a183c36cb5 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -8,6 +8,7 @@ thuge-gen compaction_test mlock2-tests mremap_dontunmap +mremap_test on-fault-limit transhuge-stress protection_keys diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index a9026706d597..f044808b45fa 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -16,6 +16,7 @@ TEST_GEN_FILES += map_populate TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mremap_dontunmap +TEST_GEN_FILES += mremap_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c new file mode 100644 index 000000000000..09dc9a1ef81f --- /dev/null +++ b/tools/testing/selftests/vm/mremap_test.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2020 Google LLC + */ +#define _GNU_SOURCE + +#include +#include +#include +#include + +#include "../kselftest.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +struct config { + unsigned long long src_alignment; + unsigned long long dest_alignment; + unsigned long long region_size; + int overlapping; +}; + +struct test { + const char *name; + struct config config; + int expect_failure; +}; + +enum { + _1KB = 1ULL << 10, /* 1KB -> not page aligned */ + _4KB = 4ULL << 10, + _8KB = 8ULL << 10, + _1MB = 1ULL << 20, + _2MB = 2ULL << 20, + _4MB = 4ULL << 20, + _1GB = 1ULL << 30, + _2GB = 2ULL << 30, + PTE = _4KB, + PMD = _2MB, + PUD = _1GB, +}; + +#define MAKE_TEST(source_align, destination_align, size, \ + overlaps, should_fail, test_name) \ +{ \ + .name = test_name, \ + .config = { \ + .src_alignment = source_align, \ + .dest_alignment = destination_align, \ + .region_size = size, \ + .overlapping = overlaps, \ + }, \ + .expect_failure = should_fail \ +} + +#define MAKE_SIMPLE_TEST(source_align, destination_align, size) \ + MAKE_TEST(source_align, destination_align, size, 0, 0, \ + #size " mremap - Source " #source_align \ + " aligned, Destination " #destination_align \ + " aligned") + +/* + * Returns the start address of the mapping on success, else returns + * NULL on failure. + */ +static void *get_source_mapping(struct config c) +{ + unsigned long long addr = 0ULL; + void *src_addr = NULL; +retry: + addr += c.src_alignment; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0); + if (src_addr == MAP_FAILED) { + if (errno == EPERM) + goto retry; + goto error; + } + /* + * Check that the address is aligned to the specified alignment. Addresses + * which have alignments that are multiples of that specified are not considered + * valid. For instance, 1GB address is 2MB-aligned, however it will not be + * considered valid for a requested alignment of 2MB. This is done to + * reduce coincidental alignment in the tests. + */ + if (((unsigned long long) src_addr & (c.src_alignment - 1)) || + !((unsigned long long) src_addr & c.src_alignment)) + goto retry; + + if (!src_addr) + goto error; + + return src_addr; +error: + ksft_print_msg("Failed to map source region: %s\n", + strerror(errno)); + return NULL; +} + +/* Returns the time taken for the remap on success else returns -1. */ +static long long remap_region(struct config c) +{ + void *addr, *src_addr, *dest_addr; + int i, j; + struct timespec t_start = {0, 0}, t_end = {0, 0}; + long long start_ns, end_ns, align_mask, ret, offset; + char pattern[] = {0xa8, 0xcd, 0xfe}; + int pattern_size = ARRAY_SIZE(pattern); + + src_addr = get_source_mapping(c); + if (!src_addr) { + ret = -1; + goto out; + } + + /* Set byte pattern */ + for (i = 0; i < c.region_size; i++) { + for (j = 0; i+j < c.region_size && j < pattern_size; j++) + memset((char *) src_addr + i+j, pattern[j], 1); + i += pattern_size-1; + } + + align_mask = ~(c.dest_alignment - 1); + offset = (c.overlapping) ? -c.dest_alignment : c.dest_alignment; + addr = (void *) (((unsigned long long) src_addr + c.region_size + offset) + & align_mask); + + /* See comment in get_source_mapping() */ + if (!((unsigned long long) addr & c.dest_alignment)) + addr = (void *) ((unsigned long long) addr | c.dest_alignment); + + clock_gettime(CLOCK_MONOTONIC, &t_start); + dest_addr = mremap(src_addr, c.region_size, c.region_size, + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + clock_gettime(CLOCK_MONOTONIC, &t_end); + + if (dest_addr == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + ret = -1; + goto clean_up_src; + } + + /* Verify byte pattern after remapping */ + for (i = 0; i < c.region_size; i++) { + for (j = 0; i+j < c.region_size && j < pattern_size; j++) { + if (((char *) dest_addr)[i+j] != (char) pattern[j]) { + ksft_print_msg("Data after remap doesn't match at offset %d\n", + i+j); + ksft_print_msg("Expected: %#x\t Got: %#x\n", pattern[j] & 0xff, + ((char *) dest_addr)[i+j] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + i += pattern_size-1; + } + + start_ns = t_start.tv_sec * 1000000000ULL + t_start.tv_nsec; + end_ns = t_end.tv_sec * 1000000000ULL + t_end.tv_nsec; + ret = end_ns - start_ns; + +/* + * Since the destination address is specified using MREMAP_FIXED, subsequent mremap will unmap any + * previous mapping at the address range specified by dest_addr and region_size. This significantly + * affects the remap time of subsequent tests. So we clean up mappings after each test. + */ +clean_up_dest: + munmap(dest_addr, c.region_size); +clean_up_src: + munmap(src_addr, c.region_size); +out: + return ret; +} + +static void run_mremap_test_case(struct test test_case, int *failures) +{ + long long remap_time = remap_region(test_case.config); + + if (remap_time < 0) { + if (test_case.expect_failure) + ksft_test_result_pass("%s\n\tExpected mremap failure\n", test_case.name); + else { + ksft_test_result_fail("%s\n", test_case.name); + *failures += 1; + } + } else + ksft_test_result_pass("%s\n\tmremap time: %12lldns\n", test_case.name, remap_time); +} + +int main(int argc, char *argv[]) +{ + int failures = 0; + int i; + + struct test test_cases[] = { + /* Expected mremap failures */ + MAKE_TEST(_4KB, _4KB, _4KB, 1 /* overlaps */, 1 /* fails */, + "mremap - Source and Destination Regions Overlapping"), + MAKE_TEST(_4KB, _1KB, _4KB, 0 /* overlaps */, 1 /* fails */, + "mremap - Destination Address Misaligned (1KB-aligned)"), + MAKE_TEST(_1KB, _4KB, _4KB, 0 /* overlaps */, 1 /* fails */, + "mremap - Source Address Misaligned (1KB-aligned)"), + + /* Src addr PTE aligned */ + MAKE_SIMPLE_TEST(PTE, PTE, _8KB), + + /* Src addr 1MB aligned */ + MAKE_SIMPLE_TEST(_1MB, PTE, _2MB), + MAKE_SIMPLE_TEST(_1MB, _1MB, _2MB), + + /* Src addr PMD aligned */ + MAKE_SIMPLE_TEST(PMD, PTE, _4MB), + MAKE_SIMPLE_TEST(PMD, _1MB, _4MB), + MAKE_SIMPLE_TEST(PMD, PMD, _4MB), + + /* Src addr PUD aligned */ + MAKE_SIMPLE_TEST(PUD, PTE, _2GB), + MAKE_SIMPLE_TEST(PUD, _1MB, _2GB), + MAKE_SIMPLE_TEST(PUD, PMD, _2GB), + MAKE_SIMPLE_TEST(PUD, PUD, _2GB), + }; + + struct test perf_test_cases[] = { + /* mremap 1GB region - Page table level aligned time comparison */ + MAKE_SIMPLE_TEST(PTE, PTE, _1GB), + MAKE_SIMPLE_TEST(PMD, PMD, _1GB), + MAKE_SIMPLE_TEST(PUD, PUD, _1GB), + }; + + ksft_set_plan(ARRAY_SIZE(test_cases) + ARRAY_SIZE(perf_test_cases)); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_mremap_test_case(test_cases[i], &failures); + + ksft_print_msg("\nmremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:\n"); + for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++) + run_mremap_test_case(perf_test_cases[i], &failures); + + if (failures > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a3f4f30f0a2e..d578ad831813 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -241,6 +241,17 @@ else echo "[PASS]" fi +echo "-------------------" +echo "running mremap_test" +echo "-------------------" +./mremap_test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-----------------" echo "running thuge-gen" echo "-----------------" From patchwork Wed Sep 30 22:21:19 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kalesh Singh X-Patchwork-Id: 11810403 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 5DBED112C for ; Wed, 30 Sep 2020 22:22:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3E7292075F for ; Wed, 30 Sep 2020 22:22:01 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="boDpHG4Y" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731449AbgI3WV6 (ORCPT ); Wed, 30 Sep 2020 18:21:58 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49784 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731259AbgI3WV6 (ORCPT ); Wed, 30 Sep 2020 18:21:58 -0400 Received: from mail-yb1-xb49.google.com (mail-yb1-xb49.google.com [IPv6:2607:f8b0:4864:20::b49]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DDB42C0613D0 for ; Wed, 30 Sep 2020 15:21:57 -0700 (PDT) Received: by mail-yb1-xb49.google.com with SMTP id e190so3174050ybf.18 for ; Wed, 30 Sep 2020 15:21:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=sender:date:in-reply-to:message-id:mime-version:references:subject :from:cc; bh=M0Jnd5wDs989jegufD80A647gOObA9k7fcoXOfGIBiI=; b=boDpHG4YKr/2sBYi+LXa7BYu2zahi8BWNiXF87MohJyyIman1YZgh2emp0eq+ALxVF N8Rorega2dCLqmupg5pggd4PEd0bioiDmLQNT/uayIfQYI/mK9sOXXXaXnkfAPLGDmJx /Co7dHpFXUZPb6JhgzEuOs4vsL7nB/ouZzo9v6V4300dN5vLptrbHO4vapViZXwBudAh Ek2t7vH58qT4ABFOsGeFw8dE9HSppt8Cv93fwPd7G3MmAMn3Em8oG/bsv6UWDPJ3jGbg m/Zl/8FLGMadTgwwz/0FCcE3Bg5lmumAkFDQr0+kGeF1/sPrtYOu+Lj4tH/9bYQCLPbI YrzA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:in-reply-to:message-id:mime-version :references:subject:from:cc; bh=M0Jnd5wDs989jegufD80A647gOObA9k7fcoXOfGIBiI=; b=D+Mw3j7FoCB8bSQfuzT5TzZSTQ7DJKtshJJz9CvczSDAyfYGOXAfLhrhYEbqBekgNS z/NvqNBsJgGsXgw8N50Ds3oHUWOXimvxvANdEdNXiu6tX2e3Riuy4C9oR+vXflKfMf28 Boz2vFd4AnawDbt3BlrU7hZXNMGy9AAHwDQ8waFm6eMRfCg/t/znh0bH9n4AfV2/BZlA CkQxbH7+FXfG5qD3qqtR9+YzhpKX0Y2KmmJA9x8Puq336P0Ks7XDzQPjO/1Bd1z+Ss2q +7QrGiC2aA9lmoNxygcAwqlH/eLXnE+dA0tE2pB5RDWzrKOROWZsE79igRsXNOuS+mkX WJNw== X-Gm-Message-State: AOAM532PGzjgcJrSKrqB0pF2RXx+f+sKzhBWNZ8i2ItiNubjeNVESh4p twoaPP8XeRCdlfyF0X7c0YXdjYuf9Ofoy5Ih8g== X-Google-Smtp-Source: ABdhPJzpG054ym1h9s82GZx0gEkFQHO8lOnhV52qK7oqfRRBlQ4XabfPxVWgnQguS08M76s/iC40L0YtMGRjB+Vw+Q== Sender: "kaleshsingh via sendgmr" X-Received: from kaleshsingh.c.googlers.com ([fda3:e722:ac3:10:14:4d90:c0a8:2145]) (user=kaleshsingh job=sendgmr) by 2002:a25:ae9f:: with SMTP id b31mr6084827ybj.437.1601504516920; Wed, 30 Sep 2020 15:21:56 -0700 (PDT) Date: Wed, 30 Sep 2020 22:21:19 +0000 In-Reply-To: <20200930222130.4175584-1-kaleshsingh@google.com> Message-Id: <20200930222130.4175584-3-kaleshsingh@google.com> Mime-Version: 1.0 References: <20200930222130.4175584-1-kaleshsingh@google.com> X-Mailer: git-send-email 2.28.0.709.gb0816b6eb0-goog Subject: [PATCH 2/5] arm64: mremap speedup - Enable HAVE_MOVE_PMD From: Kalesh Singh Cc: surenb@google.com, minchan@google.com, joelaf@google.com, lokeshgidra@google.com, kaleshsingh@google.com, kernel-team@android.com, Catalin Marinas , Will Deacon , Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" , Andrew Morton , Shuah Khan , Kees Cook , "Aneesh Kumar K.V" , Peter Zijlstra , Sami Tolvanen , Arnd Bergmann , Masahiro Yamada , Krzysztof Kozlowski , Frederic Weisbecker , Hassan Naveed , Christian Brauner , Mark Rutland , Mike Rapoport , Gavin Shan , Mark Brown , Jia He , Zhenyu Ye , John Hubbard , Dave Hansen , Sandipan Das , Ralph Campbell , "Kirill A. Shutemov" , Ram Pai , Mina Almasry , Colin Ian King , Masami Hiramatsu , SeongJae Park , Brian Geffon , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org To: unlisted-recipients:; (no To-header on input) Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org HAVE_MOVE_PMD enables remapping pages at the PMD level if both the source and destination addresses are PMD-aligned. HAVE_MOVE_PMD is already enabled on x86. The original patch [1] that introduced this config did not enable it on arm64 at the time because of performance issues with flushing the TLB on every PMD move. These issues have since been addressed in more recent releases with improvements to the arm64 TLB invalidation and core mmu_gather code as Will Deacon mentioned in [2]. From the data below, it can be inferred that there is approximately 8x improvement in performance when HAVE_MOVE_PMD is enabled on arm64. --------- Test Results ---------- The following results were obtained on an arm64 device running a 5.4 kernel, by remapping a PMD-aligned, 1GB sized region to a PMD-aligned destination. The results from 10 iterations of the test are given below. All times are in nanoseconds. Control HAVE_MOVE_PMD 9220833 1247761 9002552 1219896 9254115 1094792 8725885 1227760 9308646 1043698 9001667 1101771 8793385 1159896 8774636 1143594 9553125 1025833 9374010 1078125 9100885.4 1134312.6 <-- Mean Time in nanoseconds Total mremap time for a 1GB sized PMD-aligned region drops from ~9.1 milliseconds to ~1.1 milliseconds. (~8x speedup). [1] https://lore.kernel.org/r/20181108181201.88826-3-joelaf@google.com [2] https://www.mail-archive.com/linuxppc-dev@lists.ozlabs.org/msg140837.html Signed-off-by: Kalesh Singh --- arch/arm64/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6d232837cbee..844d089668e3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -121,6 +121,7 @@ config ARM64 select GENERIC_VDSO_TIME_NS select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND + select HAVE_MOVE_PMD select HAVE_PCI select HAVE_ACPI_APEI if (ACPI && EFI) select HAVE_ALIGNED_STRUCT_PAGE if SLUB From patchwork Wed Sep 30 22:21:20 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Kalesh Singh X-Patchwork-Id: 11810409 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id B70BD112C for ; Wed, 30 Sep 2020 22:22:10 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 9081E2076A for ; Wed, 30 Sep 2020 22:22:10 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="uc1lC+BR" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731440AbgI3WWK (ORCPT ); Wed, 30 Sep 2020 18:22:10 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49816 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727210AbgI3WWJ (ORCPT ); Wed, 30 Sep 2020 18:22:09 -0400 Received: from mail-yb1-xb4a.google.com (mail-yb1-xb4a.google.com [IPv6:2607:f8b0:4864:20::b4a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1CC28C061755 for ; Wed, 30 Sep 2020 15:22:08 -0700 (PDT) Received: by mail-yb1-xb4a.google.com with SMTP id e2so3172866ybc.17 for ; Wed, 30 Sep 2020 15:22:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=sender:date:in-reply-to:message-id:mime-version:references:subject :from:cc:content-transfer-encoding; bh=5bHwRAkIFgRUKgngW4gcP068wEdPRj/cA85ER5ge5+w=; b=uc1lC+BRciNCCenfHEg9UpdZN5PsHA6dts/eMegcTHFRbNmxAt+14yp2sd85qBnhWS /iQ6LFsh4BgYcnuYARjFzrcEz/ZOnAaRHA8vceh6iMmgL2CcCA1ShQXN6A0EkeRzto87 XP2ahfz3G1rWtHeMk2Iie02Bh5Bh0tv3f3+acB7crNXPg47WZEE6HxKCeN+Ddv1yICAG sReM4qnVO2nhs3CV0JpJOlQduy3bOPn+tHSdXaPjkP+C6Geq901I1kmdC3Y2kNiZU8q4 1q6YqqR+HGbk++rIzTfi4ZkgncraaFN0QqjeC/1v+W4BQT1+gF6vukHux4c1ngvQ68DW nFBg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:in-reply-to:message-id:mime-version :references:subject:from:cc:content-transfer-encoding; bh=5bHwRAkIFgRUKgngW4gcP068wEdPRj/cA85ER5ge5+w=; b=Gb4eGsGQA9FWvS+vR//F8rrx0TXyBIN++ItGk/sDaD4fzTKXpMIUocCI4g6M73DQSi rH8ZxEuySf8gXaqahszIR9qAMGCWyUYo7RXL8UiRllNrZfZQJJVW3CLXhUd42XDdk+yt Lamz/lo2LB2QbRBfEMIFGJsDUVJSOGTmdATB4CoOQ1kCIX5yj9dYglngJcuUXCUo5hXW 9LoOTMYE9b48q0T3rbpl9fkQcqWqcn65fV7JC/bMRxOB5wGLEVza318oi7ljG9tTyZH5 hnRPHYzIAryk+TCjoc91MoG1Ec9T7R2FYksm8E/jvGe7ZXFara/ZR9uaxSoEex3Qa30Q iIpA== X-Gm-Message-State: AOAM533YqiMJ80M8KhNZ/N3JsMtJIhfffZdlfNi8sHjb0fJRHHQXpN/K MNt1F1bUH4/Dbf8S4WMlYg7jQz9tg0sPqYkmdQ== X-Google-Smtp-Source: ABdhPJwBYpAmlRALKHYyir3OblZbIEhsgUn0acpHu8aRfQEb5kag4nDCQqATpwKZEagaltStuNxSB3SptnIGiDEZdw== Sender: "kaleshsingh via sendgmr" X-Received: from kaleshsingh.c.googlers.com ([fda3:e722:ac3:10:14:4d90:c0a8:2145]) (user=kaleshsingh job=sendgmr) by 2002:a25:5d8:: with SMTP id 207mr6822598ybf.444.1601504527236; Wed, 30 Sep 2020 15:22:07 -0700 (PDT) Date: Wed, 30 Sep 2020 22:21:20 +0000 In-Reply-To: <20200930222130.4175584-1-kaleshsingh@google.com> Message-Id: <20200930222130.4175584-4-kaleshsingh@google.com> Mime-Version: 1.0 References: <20200930222130.4175584-1-kaleshsingh@google.com> X-Mailer: git-send-email 2.28.0.709.gb0816b6eb0-goog Subject: [PATCH 3/5] mm: Speedup mremap on 1GB or larger regions From: Kalesh Singh Cc: surenb@google.com, minchan@google.com, joelaf@google.com, lokeshgidra@google.com, kaleshsingh@google.com, kernel-team@android.com, Catalin Marinas , Will Deacon , Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" , Andrew Morton , Shuah Khan , Kees Cook , "Aneesh Kumar K.V" , Peter Zijlstra , Arnd Bergmann , Sami Tolvanen , Masahiro Yamada , Frederic Weisbecker , Krzysztof Kozlowski , Hassan Naveed , Christian Brauner , Stephen Boyd , Mark Rutland , Mark Brown , Mike Rapoport , Gavin Shan , Chris von Recklinghausen , Jia He , Zhenyu Ye , John Hubbard , Sandipan Das , Dave Hansen , Ralph Campbell , Ram Pai , "Kirill A. Shutemov" , William Kucharski , Brian Geffon , Mina Almasry , Masami Hiramatsu , SeongJae Park , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org To: unlisted-recipients:; (no To-header on input) Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org Android needs to move large memory regions for garbage collection. Optimize mremap for >= 1GB-sized regions by moving at the PUD/PGD level if the source and destination addresses are PUD-aligned. For CONFIG_PGTABLE_LEVELS == 3, moving at the PUD level in effect moves PGD entries, since the PUD entry is “folded back” onto the PGD entry. Add HAVE_MOVE_PUD so that architectures where moving at the PUD level isn't supported/tested can turn this off by not selecting the config. Signed-off-by: Kalesh Singh --- arch/Kconfig | 7 + arch/arm64/include/asm/pgtable.h | 1 + mm/mremap.c | 211 ++++++++++++++++++++++++++----- 3 files changed, 189 insertions(+), 30 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index af14a567b493..5eabaa00bf9b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -602,6 +602,13 @@ config HAVE_IRQ_TIME_ACCOUNTING Archs need to ensure they use a high enough resolution clock to support irq time accounting and then call enable_sched_clock_irqtime(). +config HAVE_MOVE_PUD + bool + help + Architectures that select this are able to move page tables at the + PUD level. If there are only 3 page table levels, the move effectively + happens at the PGD level. + config HAVE_MOVE_PMD bool help diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index d5d3fbe73953..8848125e3024 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -415,6 +415,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) +#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)) #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) diff --git a/mm/mremap.c b/mm/mremap.c index 138abbae4f75..a5a1440bd366 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -249,14 +249,167 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, return true; } +#else +static inline bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) +{ + return false; +} #endif +#ifdef CONFIG_HAVE_MOVE_PUD +static pud_t *get_old_pud(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset(mm, addr); + if (pgd_none_or_clear_bad(pgd)) + return NULL; + + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); + if (pud_none_or_clear_bad(pud)) + return NULL; + + return pud; +} + +static pud_t *alloc_new_pud(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + + return pud; +} + +static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pud_t *old_pud, pud_t *new_pud) +{ + spinlock_t *old_ptl, *new_ptl; + struct mm_struct *mm = vma->vm_mm; + pud_t pud; + + /* + * The destination pud shouldn't be established, free_pgtables() + * should have released it. + */ + if (WARN_ON_ONCE(!pud_none(*new_pud))) + return false; + + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_lock prevents deadlock. + */ + old_ptl = pud_lock(vma->vm_mm, old_pud); + new_ptl = pud_lockptr(mm, new_pud); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + + /* Clear the pud */ + pud = *old_pud; + pud_clear(old_pud); + + VM_BUG_ON(!pud_none(*new_pud)); + + /* Set the new pud */ + set_pud_at(mm, new_addr, new_pud, pud); + flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); + + return true; +} +#else +static inline bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pud_t *old_pud, pud_t *new_pud) +{ + return false; +} +#endif + +enum pgt_entry { + NORMAL_PMD, + HPAGE_PMD, + NORMAL_PUD, +}; + +/* + * Returns an extent of the corresponding size for the pgt_entry specified if valid. + * Else returns a smaller extent bounded by the end of the source and destination + * pgt_entry. Returns 0 if an invalid pgt_entry is specified. + */ +static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr, + unsigned long old_end, unsigned long new_addr) +{ + unsigned long next, extent, mask, size; + + if (entry == NORMAL_PMD || entry == HPAGE_PMD) { + mask = PMD_MASK; + size = PMD_SIZE; + } else if (entry == NORMAL_PUD) { + mask = PUD_MASK; + size = PUD_SIZE; + } else + return 0; + + next = (old_addr + size) & mask; + /* even if next overflowed, extent below will be ok */ + extent = (next > old_end) ? old_end - old_addr : next - old_addr; + next = (new_addr + size) & mask; + if (extent > next - new_addr) + extent = next - new_addr; + return extent; +} + +/* + * Attempts to speedup the move by moving entry at the level corresponding to + * pgt_entry. Returns true if the move was successful, else false. + */ +static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma, + unsigned long old_addr, unsigned long new_addr, void *old_entry, + void *new_entry, bool need_rmap_locks) +{ + bool moved = false; + + /* See comment in move_ptes() */ + if (need_rmap_locks) + take_rmap_locks(vma); + if (entry == NORMAL_PMD) + moved = move_normal_pmd(vma, old_addr, new_addr, old_entry, new_entry); + else if (entry == NORMAL_PUD) + moved = move_normal_pud(vma, old_addr, new_addr, old_entry, new_entry); + else if (entry == HPAGE_PMD) + moved = move_huge_pmd(vma, old_addr, new_addr, old_entry, new_entry); + else + WARN_ON_ONCE(1); + if (need_rmap_locks) + drop_rmap_locks(vma); + + return moved; +} + unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks) { - unsigned long extent, next, old_end; + unsigned long extent, old_end; struct mmu_notifier_range range; pmd_t *old_pmd, *new_pmd; @@ -269,14 +422,27 @@ unsigned long move_page_tables(struct vm_area_struct *vma, for (; old_addr < old_end; old_addr += extent, new_addr += extent) { cond_resched(); - next = (old_addr + PMD_SIZE) & PMD_MASK; - /* even if next overflowed, extent below will be ok */ - extent = next - old_addr; - if (extent > old_end - old_addr) - extent = old_end - old_addr; - next = (new_addr + PMD_SIZE) & PMD_MASK; - if (extent > next - new_addr) - extent = next - new_addr; +#ifdef CONFIG_HAVE_MOVE_PUD + /* + * If extent is PUD-sized try to speed up the move by moving at the + * PUD level if possible. + */ + extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr); + if (extent == PUD_SIZE) { + pud_t *old_pud, *new_pud; + + old_pud = get_old_pud(vma->vm_mm, old_addr); + if (!old_pud) + continue; + new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr); + if (!new_pud) + break; + if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr, + old_pud, new_pud, need_rmap_locks)) + continue; + } +#endif + extent = get_extent(NORMAL_PMD, old_addr, old_end, new_addr); old_pmd = get_old_pmd(vma->vm_mm, old_addr); if (!old_pmd) continue; @@ -284,18 +450,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (!new_pmd) break; if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) { - if (extent == HPAGE_PMD_SIZE) { - bool moved; - /* See comment in move_ptes() */ - if (need_rmap_locks) - take_rmap_locks(vma); - moved = move_huge_pmd(vma, old_addr, new_addr, - old_pmd, new_pmd); - if (need_rmap_locks) - drop_rmap_locks(vma); - if (moved) - continue; - } + if (extent == HPAGE_PMD_SIZE && + move_pgt_entry(HPAGE_PMD, vma, old_addr, new_addr, old_pmd, + new_pmd, need_rmap_locks)) + continue; split_huge_pmd(vma, old_pmd, old_addr); if (pmd_trans_unstable(old_pmd)) continue; @@ -305,15 +463,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma, * If the extent is PMD-sized, try to speed the move by * moving at the PMD level if possible. */ - bool moved; - - if (need_rmap_locks) - take_rmap_locks(vma); - moved = move_normal_pmd(vma, old_addr, new_addr, - old_pmd, new_pmd); - if (need_rmap_locks) - drop_rmap_locks(vma); - if (moved) + if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr, old_pmd, + new_pmd, need_rmap_locks)) continue; #endif } From patchwork Wed Sep 30 22:21:21 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kalesh Singh X-Patchwork-Id: 11810413 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 770F2112C for ; Wed, 30 Sep 2020 22:22:19 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 55D1B2075F for ; Wed, 30 Sep 2020 22:22:19 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="W1iWTcIg" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731255AbgI3WWS (ORCPT ); Wed, 30 Sep 2020 18:22:18 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49848 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1730201AbgI3WWS (ORCPT ); Wed, 30 Sep 2020 18:22:18 -0400 Received: from mail-qt1-x849.google.com (mail-qt1-x849.google.com [IPv6:2607:f8b0:4864:20::849]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7A43BC0613D0 for ; Wed, 30 Sep 2020 15:22:18 -0700 (PDT) Received: by mail-qt1-x849.google.com with SMTP id w92so2245665qte.19 for ; Wed, 30 Sep 2020 15:22:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=sender:date:in-reply-to:message-id:mime-version:references:subject :from:cc; bh=r9i4rFwlO0Ri1Z8TnSbsRvxZfWKWakVdyJrZ8aN7lSY=; b=W1iWTcIgxIUy2UVtGwKg/FWOAbFwxj1yZWmUPz5Pi/125KT5znQ+tf41yAd1LXtU3d Uib3iflcCUIsFkmFwF65SPdIo0tOd05bt6iEjAmwvgkuxVugygP1L5ds1Ja8WufaiuMV xz81lcY5xrAL+nyfM3Z0hdPj/tJ43t16HfcFkrJ+MxmieS3E1BV/xbXh8PvXr1ROpI8b rCKYtMByUOGystQtiQJjncYyQgIpF3rGdUXr5N8/ZwBTqs43v+RaP/0IRmqIv5X0KeCw wjabq5p+HsWNPVNiSZT1vRrkK3OoQqkBQQ+qiqurkNU1dwg9e3kAqbptm+mdcIc9xW87 dADg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:in-reply-to:message-id:mime-version :references:subject:from:cc; bh=r9i4rFwlO0Ri1Z8TnSbsRvxZfWKWakVdyJrZ8aN7lSY=; b=iNvB5JSprU4uklO1HZJykVZgm2wrP6uWvfRy6Hj6r3AaDT+lh3zs/7lMqecY7sPfDT GXJH0pehd/Xx3bJH4XlqFsDQdFKG3K7K1b2ui71shtrX+mouf7KUDFBVATyTmaDoC00B EPodeq7Rgs+LPnmRdbWRD+DiWfe1I3lpHPR11El1NnO5TCNq5oNQdv7kqj8iXOaGGikL T8f7FYhYZicUzAHr6LQaV6eX3Jy5qnH0EhqAHoZhQzRkTIiurU8kyrit4pXN+p6CZdg7 ExLMOXemfzdenS/HLq4S2AwlNUdYJNanQHwxgmJ9LTNvvRv3sRZu3soDIU/sAUfftfFZ Bo1A== X-Gm-Message-State: AOAM533nHMNCj0rAWxaaN4OfCKoiOQXw3LCIfzRtvrK+F5fva5gB3IpM MxdKTD8MnkaeVn4fZbWtznELlTzvGZ9OQ7C6Cw== X-Google-Smtp-Source: ABdhPJw/sR64l5kK5cZN6wHaMabXV7sFr12f7agBjeiB0rYDcGu7AUGvx40hqtjxrcgjvKmLH0L0Diy+P9Slii6SiQ== Sender: "kaleshsingh via sendgmr" X-Received: from kaleshsingh.c.googlers.com ([fda3:e722:ac3:10:14:4d90:c0a8:2145]) (user=kaleshsingh job=sendgmr) by 2002:ad4:58e3:: with SMTP id di3mr4707465qvb.54.1601504537414; Wed, 30 Sep 2020 15:22:17 -0700 (PDT) Date: Wed, 30 Sep 2020 22:21:21 +0000 In-Reply-To: <20200930222130.4175584-1-kaleshsingh@google.com> Message-Id: <20200930222130.4175584-5-kaleshsingh@google.com> Mime-Version: 1.0 References: <20200930222130.4175584-1-kaleshsingh@google.com> X-Mailer: git-send-email 2.28.0.709.gb0816b6eb0-goog Subject: [PATCH 4/5] arm64: mremap speedup - Enable HAVE_MOVE_PUD From: Kalesh Singh Cc: surenb@google.com, minchan@google.com, joelaf@google.com, lokeshgidra@google.com, kaleshsingh@google.com, kernel-team@android.com, Catalin Marinas , Will Deacon , Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" , Andrew Morton , Shuah Khan , Kees Cook , "Aneesh Kumar K.V" , Peter Zijlstra , Arnd Bergmann , Masahiro Yamada , Sami Tolvanen , Krzysztof Kozlowski , Frederic Weisbecker , Hassan Naveed , Christian Brauner , Mark Rutland , Mark Brown , Mike Rapoport , Gavin Shan , Dave Martin , Jia He , Zhenyu Ye , John Hubbard , Jason Gunthorpe , Zi Yan , Dave Hansen , "Kirill A. Shutemov" , Ralph Campbell , Ram Pai , Mina Almasry , Sandipan Das , Brian Geffon , Masami Hiramatsu , Kamalesh Babulal , SeongJae Park , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org To: unlisted-recipients:; (no To-header on input) Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org HAVE_MOVE_PUD enables remapping pages at the PUD level if both the source and destination addresses are PUD-aligned. With HAVE_MOVE_PUD enabled it can be inferred that there is approximately a 19x improvement in performance on arm64. (See data below). ------- Test Results --------- The following results were obtained using a 5.4 kernel, by remapping a PUD-aligned, 1GB sized region to a PUD-aligned destination. The results from 10 iterations of the test are given below: Total mremap times for 1GB data on arm64. All times are in nanoseconds. Control HAVE_MOVE_PUD 1247761 74271 1219896 46771 1094792 59687 1227760 48385 1043698 76666 1101771 50365 1159896 52500 1143594 75261 1025833 61354 1078125 48697 1134312.6 59395.7 <-- Mean time in nanoseconds A 1GB mremap completion time drops from ~1.1 milliseconds to ~59 microseconds on arm64. (~19x speed up). Signed-off-by: Kalesh Singh --- arch/arm64/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 844d089668e3..4d521f0a5863 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -122,6 +122,7 @@ config ARM64 select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_MOVE_PMD + select HAVE_MOVE_PUD select HAVE_PCI select HAVE_ACPI_APEI if (ACPI && EFI) select HAVE_ALIGNED_STRUCT_PAGE if SLUB From patchwork Wed Sep 30 22:21:22 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kalesh Singh X-Patchwork-Id: 11810417 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id C3D226CA for ; Wed, 30 Sep 2020 22:22:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A9D0521531 for ; Wed, 30 Sep 2020 22:22:29 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="jDIKOMNU" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731548AbgI3WW3 (ORCPT ); Wed, 30 Sep 2020 18:22:29 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49876 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731339AbgI3WW2 (ORCPT ); Wed, 30 Sep 2020 18:22:28 -0400 Received: from mail-qv1-xf49.google.com (mail-qv1-xf49.google.com [IPv6:2607:f8b0:4864:20::f49]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B16B3C0613D0 for ; Wed, 30 Sep 2020 15:22:28 -0700 (PDT) Received: by mail-qv1-xf49.google.com with SMTP id y2so1885859qvs.14 for ; Wed, 30 Sep 2020 15:22:28 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=sender:date:in-reply-to:message-id:mime-version:references:subject :from:cc; bh=Mra73tAqzotShWNgSXv1vhLyePg3f0HjrcFvwMDeq9o=; b=jDIKOMNUrsBzgzsboYR6brg4WOYp4kCRZqrCWAvAZbpkekxYpp5uwWu1VMa3jBM1D4 qePDAkhwPaS7ozmJhvpiPn8rqjAEru5rJyPx6RWU/8Ay/7inrR7CHVJ77p9zaJZ1IwI9 Dy5ixhsQoV7e7t6GjskB9KRoGi6vhUEOJIOmUECHIHMNA/6dx0Mfp5sk/qPevZgAIWJD dSDgUoz8vPO96wn0mRJrwb6JU+kn6sz1n4gmMp04q1wpnavCaWjLkLkQER3ZYnT7jxHz JbrMiGc+vRmaiWx7InwR9v7+c9MnvzgX9b4pL1qHoSDq+DWQYdeR0dkqLDkbjTEQELIk LT7A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:in-reply-to:message-id:mime-version :references:subject:from:cc; bh=Mra73tAqzotShWNgSXv1vhLyePg3f0HjrcFvwMDeq9o=; b=Nbg4A/v9qmuaPwe1ahSdm42837ykdhAAGjW3MSDzpktRCNkXM6+g/ES7RKL2daBbUx HPUB/WEv5NhDsIfTw8QBqKHK4y9FOO+HFKmsBh87ekP+7AUg5pv5VaqB4qv7eGQ1z3N9 6duZ22L7dakGYSs7efDO5l5mGjhgoM3JOFJTAeozcdVXNxv2J8/aqUwqpEpxJ6517Cev yILvYtQZuwxeN2oWhfRbuqkJTUqYHPP57t2FPzoLd71XoNkfUJ2Q5dFNXxEfh7OJEaf0 GpIdxyQ6n1gxK0ERvmvTTTbvANNjGdhJ9s6P+/lVKsg7vcZ6Ndcl3RKZs1CdoeR0qjcH Fr6Q== X-Gm-Message-State: AOAM530fPe8dj4Lk72wN7s3oriB6t1nN3NfTsCu8Hcp9+T/H0SVMPJzL AKRgLvqOXYeTFd+vr5LtJBT2M7PNV5jkSrqTPw== X-Google-Smtp-Source: ABdhPJyLR6MYlSTS4XQqoJzvYxjrHwSWIVNtfhqTdtx45lsRl3oJwBhgd7X3m6yDztZJ8ANUp7tpdCXWxqNC36OyAw== Sender: "kaleshsingh via sendgmr" X-Received: from kaleshsingh.c.googlers.com ([fda3:e722:ac3:10:14:4d90:c0a8:2145]) (user=kaleshsingh job=sendgmr) by 2002:a0c:b39a:: with SMTP id t26mr4865208qve.19.1601504547782; Wed, 30 Sep 2020 15:22:27 -0700 (PDT) Date: Wed, 30 Sep 2020 22:21:22 +0000 In-Reply-To: <20200930222130.4175584-1-kaleshsingh@google.com> Message-Id: <20200930222130.4175584-6-kaleshsingh@google.com> Mime-Version: 1.0 References: <20200930222130.4175584-1-kaleshsingh@google.com> X-Mailer: git-send-email 2.28.0.709.gb0816b6eb0-goog Subject: [PATCH 5/5] x86: mremap speedup - Enable HAVE_MOVE_PUD From: Kalesh Singh Cc: surenb@google.com, minchan@google.com, joelaf@google.com, lokeshgidra@google.com, kaleshsingh@google.com, kernel-team@android.com, Catalin Marinas , Will Deacon , Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" , Andrew Morton , Shuah Khan , Kees Cook , "Aneesh Kumar K.V" , Peter Zijlstra , Sami Tolvanen , Arnd Bergmann , Masahiro Yamada , Krzysztof Kozlowski , Frederic Weisbecker , Hassan Naveed , Christian Brauner , Mark Rutland , Mark Brown , Mike Rapoport , Gavin Shan , Steven Price , Zhenyu Ye , Jia He , John Hubbard , Ram Pai , "Kirill A. Shutemov" , Ralph Campbell , Mina Almasry , Sandipan Das , Dave Hansen , Brian Geffon , Masami Hiramatsu , SeongJae Park , linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org To: unlisted-recipients:; (no To-header on input) Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org HAVE_MOVE_PUD enables remapping pages at the PUD level if both the source and destination addresses are PUD-aligned. With HAVE_MOVE_PUD enabled it can be inferred that there is approximately a 13x improvement in performance on x86. (See data below). ------- Test Results --------- The following results were obtained using a 5.4 kernel, by remapping a PUD-aligned, 1GB sized region to a PUD-aligned destination. The results from 10 iterations of the test are given below: Total mremap times for 1GB data on x86. All times are in nanoseconds. Control HAVE_MOVE_PUD 180394 15089 235728 14056 238931 25741 187330 13838 241742 14187 177925 14778 182758 14728 160872 14418 205813 15107 245722 13998 205721.5 15594 <-- Mean time in nanoseconds A 1GB mremap completion time drops from ~205 microseconds to ~15 microseconds on x86. (~13x speed up). Signed-off-by: Kalesh Singh --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7101ac64bb20..ff6e2755cab8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -198,6 +198,7 @@ config X86 select HAVE_MIXED_BREAKPOINTS_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_MOVE_PMD + select HAVE_MOVE_PUD select HAVE_NMI select HAVE_OPROFILE select HAVE_OPTPROBES