From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CBBC780632 for ; Fri, 26 Apr 2024 04:01:56 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714104116; cv=none; b=r/jcW2ZKAmWkWcPhD16x5AD44OMySoIRyg+6I6CyyzjxrZpeyb5Y53UbG/X8QoFIlKNpG6h6is3mc6LorpvTaYyXgvwvzvtfKkXNvm40l2Gfi5R9XCT0aJX2wc8t9O/x9I5ap5lb1uPHPTPiOeQx3IAPFVQpzRdSH3yPGqSCRIg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714104116; c=relaxed/simple; bh=37c1KdxDKi2RXzRUl1mGgO0/2giMDyVE6jVmwnmiX5k=; h=Date:To:From:Subject:Message-Id; b=s68qUgwt/7IyCLk2Ii0oNoz23aMyQmCIsN48jktxBb2c1fxahKBYsZj22CkAKXiieoLCARvrHoxDlFeXCdxCXyzH8fzvP5HudxKWQ8Iy8CObYElBcUv14jYVEW8elP7NCOmLy1DMEPs4H+hYBGTnEjwPBiLs2ykv6Cm4Izb5l3U= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=zurWQJ3k; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="zurWQJ3k" Received: by smtp.kernel.org (Postfix) with ESMTPSA id A0DB1C113CD; Fri, 26 Apr 2024 04:01:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1714104116; bh=37c1KdxDKi2RXzRUl1mGgO0/2giMDyVE6jVmwnmiX5k=; h=Date:To:From:Subject:From; b=zurWQJ3knY2r4FmXVKUdTU+QhJQ1wdXApRU8dtBYcnTcn0z/7x62L3phwebct/FH+ QMDvRmbzDG/VR2SgNFdZzPiWa1+L7cDYQT3QSecJVE2Lb40W1IUAysxLw1CeNN8M1U xKd/xT/iYcxYKCa5SyzBDq2lAvHAG6G3soSmaAqs= Date: Thu, 25 Apr 2024 21:01:56 -0700 To: mm-commits@vger.kernel.org,shuah@kernel.org,kaleshsingh@google.com,jhubbard@nvidia.com,anshuman.khandual@arm.com,dev.jain@arm.com,akpm@linux-foundation.org From: Andrew Morton Subject: [merged mm-stable] selftests-mm-mremap_test-optimize-execution-time-from-minutes-to-seconds-using-chunkwise-memcmp.patch removed from -mm tree Message-Id: <20240426040156.A0DB1C113CD@smtp.kernel.org> Precedence: bulk X-Mailing-List: mm-commits@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: The quilt patch titled Subject: selftests/mm: mremap_test: optimize execution time from minutes to seconds using chunkwise memcmp has been removed from the -mm tree. Its filename was selftests-mm-mremap_test-optimize-execution-time-from-minutes-to-seconds-using-chunkwise-memcmp.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Dev Jain Subject: selftests/mm: mremap_test: optimize execution time from minutes to seconds using chunkwise memcmp Date: Sat, 30 Mar 2024 23:05:56 +0530 Mismatch index is currently being checked by a brute force iteration over the buffer. Instead, break the comparison into O(sqrt(n)) number of chunks, with the chunk size of this order only, where n is the size of the buffer. Do a brute-force iteration to print to stdout only when the highly optimized memcmp() library function returns a mismatch in the chunk. The time complexity of this algorithm is O(sqrt(n)) * t, where t is the time taken by memcmp(); for our test conditions, it is safe to assume t to be small. Link: https://lkml.kernel.org/r/20240330173557.2697684-3-dev.jain@arm.com Signed-off-by: Dev Jain Cc: Anshuman Khandual Cc: John Hubbard Cc: Kalesh Singh Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/mremap_test.c | 112 +++++++++++++++++---- 1 file changed, 91 insertions(+), 21 deletions(-) --- a/tools/testing/selftests/mm/mremap_test.c~selftests-mm-mremap_test-optimize-execution-time-from-minutes-to-seconds-using-chunkwise-memcmp +++ a/tools/testing/selftests/mm/mremap_test.c @@ -70,6 +70,27 @@ enum { .expect_failure = should_fail \ } +/* compute square root using binary search */ +static unsigned long get_sqrt(unsigned long val) +{ + unsigned long low = 1; + + /* assuming rand_size is less than 1TB */ + unsigned long high = (1UL << 20); + + while (low <= high) { + unsigned long mid = low + (high - low) / 2; + unsigned long temp = mid * mid; + + if (temp == val) + return mid; + if (temp < val) + low = mid + 1; + high = mid - 1; + } + return low; +} + /* * Returns false if the requested remap region overlaps with an * existing mapping (e.g text, stack) else returns true. @@ -355,14 +376,14 @@ out: /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, - unsigned int pattern_seed, char *rand_addr) + char *rand_addr) { void *addr, *src_addr, *dest_addr, *dest_preamble_addr; - int d; - unsigned long long t; + unsigned long long t, d; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; unsigned long long threshold; + unsigned long num_chunks; if (threshold_mb == VALIDATION_NO_THRESHOLD) threshold = c.region_size; @@ -430,15 +451,42 @@ static long long remap_region(struct con goto clean_up_dest_preamble; } - /* Verify byte pattern after remapping */ - srand(pattern_seed); - for (t = 0; t < threshold; t++) { - char c = (char) rand(); + /* + * Verify byte pattern after remapping. Employ an algorithm with a + * square root time complexity in threshold: divide the range into + * chunks, if memcmp() returns non-zero, only then perform an + * iteration in that chunk to find the mismatch index. + */ + num_chunks = get_sqrt(threshold); + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = threshold / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_addr + shift, rand_addr + shift, chunk_size)) + continue; + + /* brute force iteration only over mismatch segment */ + for (t = shift; t < shift + chunk_size; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { + ksft_print_msg("Data after remap doesn't match at offset %llu\n", + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, + ((char *) dest_addr)[t] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + } - if (((char *) dest_addr)[t] != c) { + /* + * if threshold is not divisible by num_chunks, then check the + * last chunk + */ + for (t = num_chunks * (threshold / num_chunks); t < threshold; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { ksft_print_msg("Data after remap doesn't match at offset %llu\n", - t); - ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, ((char *) dest_addr)[t] & 0xff); ret = -1; goto clean_up_dest; @@ -446,22 +494,44 @@ static long long remap_region(struct con } /* Verify the dest preamble byte pattern after remapping */ - if (c.dest_preamble_size) { - srand(pattern_seed); - for (d = 0; d < c.dest_preamble_size; d++) { - char c = (char) rand(); - - if (((char *) dest_preamble_addr)[d] != c) { - ksft_print_msg("Preamble data after remap doesn't match at offset %d\n", - d); - ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_preamble_addr)[d] & 0xff); + if (!c.dest_preamble_size) + goto no_preamble; + + num_chunks = get_sqrt(c.dest_preamble_size); + + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = c.dest_preamble_size / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_preamble_addr + shift, rand_addr + shift, + chunk_size)) + continue; + + /* brute force iteration only over mismatched segment */ + for (d = shift; d < shift + chunk_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); ret = -1; goto clean_up_dest; } } } + for (d = num_chunks * (c.dest_preamble_size / num_chunks); d < c.dest_preamble_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + +no_preamble: start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; ret = end_ns - start_ns; @@ -563,7 +633,7 @@ static void run_mremap_test_case(struct unsigned int pattern_seed, char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, - pattern_seed, rand_addr); + rand_addr); if (remap_time < 0) { if (test_case.expect_failure) _ Patches currently in -mm which might be from dev.jain@arm.com are