From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 27814A0548; Fri, 2 Apr 2021 11:27:08 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 0D9F2140EE4; Fri, 2 Apr 2021 11:27:08 +0200 (CEST) Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) by mails.dpdk.org (Postfix) with ESMTP id E4751140EE4 for ; Fri, 2 Apr 2021 11:27:06 +0200 (CEST) IronPort-SDR: 3VNoxYjZN6ZN2qTNI/1mFNajX/Lee0SSEaOBvYgPpc7RMkuZUHCnKuulsd4FrYB6PDn61ipVnv tzKsYXNgNP3w== X-IronPort-AV: E=McAfee;i="6000,8403,9941"; a="256414159" X-IronPort-AV: E=Sophos;i="5.81,299,1610438400"; d="scan'208";a="256414159" Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Apr 2021 02:27:05 -0700 IronPort-SDR: ucRleJTMBbeONPbKVwkxjgGbmx9ZyfYqSa6KsQ6x29LEsHKCadZNkOAtNUf2lnngnlQCTOXyUH d5E12lk3rYaA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.81,299,1610438400"; d="scan'208";a="517717857" Received: from silpixa00399498.ir.intel.com (HELO silpixa00399498.ger.corp.intel.com) ([10.237.222.97]) by fmsmga001.fm.intel.com with ESMTP; 02 Apr 2021 02:27:04 -0700 From: Anatoly Burakov To: dev@dpdk.org Date: Fri, 2 Apr 2021 09:27:01 +0000 Message-Id: <20210402092701.258316-1-anatoly.burakov@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210401150517.234085-1-anatoly.burakov@intel.com> References: <20210401150517.234085-1-anatoly.burakov@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: [dpdk-dev] [21.08 v2] power: refactor pstate sysfs handling X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Currently, pstate sysfs handling code is a bit of an unmaintainable mess, which has contributed to various errors leading to bugs. Refactor the code in a way that makes it more maintainable and less error prone. Signed-off-by: Anatoly Burakov --- lib/librte_power/meson.build | 7 + lib/librte_power/power_pstate_cpufreq.c | 355 +++++++++++++----------- 2 files changed, 193 insertions(+), 169 deletions(-) diff --git a/lib/librte_power/meson.build b/lib/librte_power/meson.build index 9a2dcbfc7a..fd408ffd4c 100644 --- a/lib/librte_power/meson.build +++ b/lib/librte_power/meson.build @@ -5,6 +5,13 @@ if not is_linux build = false reason = 'only supported on Linux' endif + +# we do some snprintf magic so silence format-nonliteral +flag_nonliteral = '-Wno-format-nonliteral' +if cc.has_argument(flag_nonliteral) + cflags += flag_nonliteral +endif + sources = files('rte_power.c', 'power_acpi_cpufreq.c', 'power_kvm_vm.c', 'guest_channel.c', 'rte_power_empty_poll.c', diff --git a/lib/librte_power/power_pstate_cpufreq.c b/lib/librte_power/power_pstate_cpufreq.c index 1cb0e4d917..db7856dadc 100644 --- a/lib/librte_power/power_pstate_cpufreq.c +++ b/lib/librte_power/power_pstate_cpufreq.c @@ -37,6 +37,13 @@ } \ } while (0) +#define FOPEN_OR_ERR_GOTO(f, label) do { \ + if ((f) == NULL) { \ + RTE_LOG(ERR, POWER, "File not opened\n"); \ + goto label; \ + } \ +} while (0) + #define FOPS_OR_NULL_GOTO(ret, label) do { \ if ((ret) == NULL) { \ RTE_LOG(ERR, POWER, "fgets returns nothing\n"); \ @@ -148,93 +155,147 @@ out: close(fd); return ret; } +static int +open_core_sysfs_file(const char *template, unsigned int core, const char *mode, + FILE **f) +{ + char fullpath[PATH_MAX]; + FILE *tmpf; + + /* silenced -Wformat-nonliteral here */ + snprintf(fullpath, sizeof(fullpath), template, core); + tmpf = fopen(fullpath, mode); + if (tmpf == NULL) + return -1; + *f = tmpf; + + return 0; +} + +static int +read_core_sysfs_u32(FILE *f, uint32_t *val) +{ + char buf[BUFSIZ]; + uint32_t fval; + char *s; + + s = fgets(buf, sizeof(buf), f); + if (s == NULL) + return -1; + + /* fgets puts null terminator in, but do this just in case */ + buf[BUFSIZ - 1] = '\0'; + + /* strip off any terminating newlines */ + if (strlen(buf)) + strtok(buf, "\n"); + + fval = strtoul(buf, NULL, POWER_CONVERT_TO_DECIMAL); + + /* write the value */ + *val = fval; + + return 0; +} + +static int +read_core_sysfs_s(FILE *f, char *buf, unsigned int len) +{ + char *s; + + s = fgets(buf, len, f); + if (s == NULL) + return -1; + + /* fgets puts null terminator in, but do this just in case */ + buf[len - 1] = '\0'; + + /* strip off any terminating newlines */ + if (strlen(buf)) + strtok(buf, "\n"); + + return 0; +} + +static int +write_core_sysfs_s(FILE *f, const char *str) +{ + int ret; + + ret = fseek(f, 0, SEEK_SET); + if (ret != 0) + return -1; + + ret = fputs(str, f); + if (ret != 0) + return -1; + + /* flush the output */ + ret = fflush(f); + if (ret != 0) + return -1; + + return 0; +} + /** * It is to fopen the sys file for the future setting the lcore frequency. */ static int power_init_for_setting_freq(struct pstate_power_info *pi) { - FILE *f_min, *f_max, *f_base = NULL, *f_base_max; - char fullpath_min[PATH_MAX]; - char fullpath_max[PATH_MAX]; - char fullpath_base[PATH_MAX]; - char fullpath_base_max[PATH_MAX]; - char buf_base[BUFSIZ]; - char *s_base; - char *s_base_max; - uint32_t base_ratio = 0; - uint32_t base_max_ratio = 0; - uint64_t max_non_turbo = 0; - int ret_val = 0; - - snprintf(fullpath_base_max, - sizeof(fullpath_base_max), - POWER_SYSFILE_BASE_MAX_FREQ, - pi->lcore_id); - f_base_max = fopen(fullpath_base_max, "r"); - FOPEN_OR_ERR_RET(f_base_max, -1); - if (f_base_max != NULL) { - s_base_max = fgets(buf_base, sizeof(buf_base), f_base_max); - FOPS_OR_NULL_GOTO(s_base_max, out); - - buf_base[BUFSIZ-1] = '\0'; - if (strlen(buf_base)) - /* Strip off terminating '\n' */ - strtok(buf_base, "\n"); - - base_max_ratio = - strtoul(buf_base, NULL, POWER_CONVERT_TO_DECIMAL) - / BUS_FREQ; - } - - snprintf(fullpath_min, sizeof(fullpath_min), POWER_SYSFILE_MIN_FREQ, - pi->lcore_id); - f_min = fopen(fullpath_min, "rw+"); - FOPEN_OR_ERR_RET(f_min, -1); - - snprintf(fullpath_max, sizeof(fullpath_max), POWER_SYSFILE_MAX_FREQ, - pi->lcore_id); - f_max = fopen(fullpath_max, "rw+"); - if (f_max == NULL) - fclose(f_min); - FOPEN_OR_ERR_RET(f_max, -1); - - pi->f_cur_min = f_min; - pi->f_cur_max = f_max; - - snprintf(fullpath_base, sizeof(fullpath_base), POWER_SYSFILE_BASE_FREQ, - pi->lcore_id); - - f_base = fopen(fullpath_base, "r"); - if (f_base == NULL) { - /* No sysfs base_frequency, that's OK, continue without */ - base_ratio = 0; + FILE *f_base = NULL, *f_base_max = NULL, *f_min = NULL, *f_max = NULL; + uint32_t base_ratio, base_max_ratio; + uint64_t max_non_turbo; + int ret; + + /* open all files we expect to have open */ + open_core_sysfs_file(POWER_SYSFILE_BASE_MAX_FREQ, pi->lcore_id, "r", + &f_base_max); + FOPEN_OR_ERR_GOTO(f_base_max, err); + + open_core_sysfs_file(POWER_SYSFILE_MIN_FREQ, pi->lcore_id, "rw+", + &f_min); + FOPEN_OR_ERR_GOTO(f_min, err); + + open_core_sysfs_file(POWER_SYSFILE_MAX_FREQ, pi->lcore_id, "rw+", + &f_max); + FOPEN_OR_ERR_GOTO(f_max, err); + + open_core_sysfs_file(POWER_SYSFILE_BASE_FREQ, pi->lcore_id, "r", + &f_base); + /* base ratio file may not exist in some kernels, so no error check */ + + /* read base max ratio */ + ret = read_core_sysfs_u32(f_base_max, &base_max_ratio); + FOPS_OR_ERR_GOTO(ret, err); + + /* base ratio may not exist */ + if (f_base != NULL) { + ret = read_core_sysfs_u32(f_base, &base_ratio); + FOPS_OR_ERR_GOTO(ret, err); } else { - s_base = fgets(buf_base, sizeof(buf_base), f_base); - FOPS_OR_NULL_GOTO(s_base, out); - - buf_base[BUFSIZ-1] = '\0'; - if (strlen(buf_base)) - /* Strip off terminating '\n' */ - strtok(buf_base, "\n"); - - base_ratio = strtoul(buf_base, NULL, POWER_CONVERT_TO_DECIMAL) - / BUS_FREQ; - fclose(f_base); + base_ratio = 0; } /* Add MSR read to detect turbo status */ + if (power_rdmsr(PLATFORM_INFO, &max_non_turbo, pi->lcore_id) < 0) + goto err; + /* no errors after this point */ - if (power_rdmsr(PLATFORM_INFO, &max_non_turbo, pi->lcore_id) < 0) { - ret_val = -1; - goto out; - } + /* convert ratios to bins */ + base_max_ratio /= BUS_FREQ; + base_ratio /= BUS_FREQ; + + /* assign file handles */ + pi->f_cur_min = f_min; + pi->f_cur_max = f_max; max_non_turbo = (max_non_turbo&NON_TURBO_MASK)>>NON_TURBO_OFFSET; POWER_DEBUG_TRACE("no turbo perf %"PRIu64"\n", max_non_turbo); - pi->non_turbo_max_ratio = max_non_turbo; + pi->non_turbo_max_ratio = (uint32_t)max_non_turbo; /* * If base_frequency is reported as greater than the maximum @@ -260,7 +321,20 @@ power_init_for_setting_freq(struct pstate_power_info *pi) out: if (f_base != NULL) fclose(f_base); - return ret_val; + fclose(f_base_max); + /* f_min and f_max are stored, no need to close */ + return 0; + +err: + if (f_base != NULL) + fclose(f_base); + if (f_base_max != NULL) + fclose(f_base_max); + if (f_min != NULL) + fclose(f_min); + if (f_max != NULL) + fclose(f_max); + return -1; } static int @@ -365,22 +439,16 @@ set_freq_internal(struct pstate_power_info *pi, uint32_t idx) static int power_set_governor_performance(struct pstate_power_info *pi) { - FILE *f; + FILE *f_governor = NULL; int ret = -1; char buf[BUFSIZ]; - char fullpath[PATH_MAX]; - char *s; - int val; - snprintf(fullpath, sizeof(fullpath), POWER_SYSFILE_GOVERNOR, - pi->lcore_id); - f = fopen(fullpath, "rw+"); - FOPEN_OR_ERR_RET(f, ret); + open_core_sysfs_file(POWER_SYSFILE_GOVERNOR, pi->lcore_id, "rw+", + &f_governor); + FOPEN_OR_ERR_GOTO(f_governor, out); - s = fgets(buf, sizeof(buf), f); - FOPS_OR_NULL_GOTO(s, out); - /* Strip off terminating '\n' */ - strtok(buf, "\n"); + ret = read_core_sysfs_s(f_governor, buf, sizeof(buf)); + FOPS_OR_ERR_GOTO(ret, out); /* Save the original governor */ rte_strscpy(pi->governor_ori, buf, sizeof(pi->governor_ori)); @@ -395,21 +463,15 @@ power_set_governor_performance(struct pstate_power_info *pi) } /* Write 'performance' to the governor */ - val = fseek(f, 0, SEEK_SET); - FOPS_OR_ERR_GOTO(val, out); - - val = fputs(POWER_GOVERNOR_PERF, f); - FOPS_OR_ERR_GOTO(val, out); - - /* We need to flush to see if the fputs succeeds */ - val = fflush(f); - FOPS_OR_ERR_GOTO(val, out); + ret = write_core_sysfs_s(f_governor, POWER_GOVERNOR_PERF); + FOPS_OR_ERR_GOTO(ret, out); ret = 0; RTE_LOG(INFO, POWER, "Power management governor of lcore %u has been " "set to performance successfully\n", pi->lcore_id); out: - fclose(f); + if (f_governor != NULL) + fclose(f_governor); return ret; } @@ -421,20 +483,16 @@ power_set_governor_performance(struct pstate_power_info *pi) static int power_set_governor_original(struct pstate_power_info *pi) { - FILE *f; + FILE *f_governor = NULL; int ret = -1; char buf[BUFSIZ]; - char fullpath[PATH_MAX]; - char *s; - int val; - snprintf(fullpath, sizeof(fullpath), POWER_SYSFILE_GOVERNOR, - pi->lcore_id); - f = fopen(fullpath, "rw+"); - FOPEN_OR_ERR_RET(f, ret); + open_core_sysfs_file(POWER_SYSFILE_GOVERNOR, pi->lcore_id, "rw+", + &f_governor); + FOPEN_OR_ERR_GOTO(f_governor, out); - s = fgets(buf, sizeof(buf), f); - FOPS_OR_NULL_GOTO(s, out); + ret = read_core_sysfs_s(f_governor, buf, sizeof(buf)); + FOPS_OR_ERR_GOTO(ret, out); /* Check if the governor to be set is the same as current */ if (strncmp(buf, pi->governor_ori, sizeof(pi->governor_ori)) == 0) { @@ -446,19 +504,16 @@ power_set_governor_original(struct pstate_power_info *pi) } /* Write back the original governor */ - val = fseek(f, 0, SEEK_SET); - FOPS_OR_ERR_GOTO(val, out); - - val = fputs(pi->governor_ori, f); - FOPS_OR_ERR_GOTO(val, out); + ret = write_core_sysfs_s(f_governor, pi->governor_ori); + FOPS_OR_ERR_GOTO(ret, out); ret = 0; RTE_LOG(INFO, POWER, "Power management governor of lcore %u " "has been set back to %s successfully\n", pi->lcore_id, pi->governor_ori); out: - fclose(f); - + if (f_governor != NULL) + fclose(f_governor); return ret; } @@ -469,51 +524,26 @@ power_set_governor_original(struct pstate_power_info *pi) static int power_get_available_freqs(struct pstate_power_info *pi) { - FILE *f_min, *f_max; + FILE *f_min = NULL, *f_max = NULL; int ret = -1; - char *p_min, *p_max; - char buf_min[BUFSIZ]; - char buf_max[BUFSIZ]; - char fullpath_min[PATH_MAX]; - char fullpath_max[PATH_MAX]; - char *s_min, *s_max; uint32_t sys_min_freq = 0, sys_max_freq = 0, base_max_freq = 0; uint32_t i, num_freqs = 0; - snprintf(fullpath_max, sizeof(fullpath_max), - POWER_SYSFILE_BASE_MAX_FREQ, - pi->lcore_id); - snprintf(fullpath_min, sizeof(fullpath_min), - POWER_SYSFILE_BASE_MIN_FREQ, - pi->lcore_id); + /* open all files */ + open_core_sysfs_file(POWER_SYSFILE_BASE_MAX_FREQ, pi->lcore_id, "r", + &f_max); + FOPEN_OR_ERR_GOTO(f_max, out); - f_min = fopen(fullpath_min, "r"); - FOPEN_OR_ERR_RET(f_min, ret); + open_core_sysfs_file(POWER_SYSFILE_BASE_MIN_FREQ, pi->lcore_id, "r", + &f_min); + FOPEN_OR_ERR_GOTO(f_max, out); - f_max = fopen(fullpath_max, "r"); - if (f_max == NULL) - fclose(f_min); + /* read base ratios */ + ret = read_core_sysfs_u32(f_max, &sys_max_freq); + FOPS_OR_ERR_GOTO(ret, out); - FOPEN_OR_ERR_RET(f_max, ret); - - s_min = fgets(buf_min, sizeof(buf_min), f_min); - FOPS_OR_NULL_GOTO(s_min, out); - - s_max = fgets(buf_max, sizeof(buf_max), f_max); - FOPS_OR_NULL_GOTO(s_max, out); - - - /* Strip the line break if there is */ - p_min = strchr(buf_min, '\n'); - if (p_min != NULL) - *p_min = 0; - - p_max = strchr(buf_max, '\n'); - if (p_max != NULL) - *p_max = 0; - - sys_min_freq = strtoul(buf_min, &p_min, POWER_CONVERT_TO_DECIMAL); - sys_max_freq = strtoul(buf_max, &p_max, POWER_CONVERT_TO_DECIMAL); + ret = read_core_sysfs_u32(f_min, &sys_min_freq); + FOPS_OR_ERR_GOTO(ret, out); if (sys_max_freq < sys_min_freq) goto out; @@ -572,27 +602,14 @@ power_get_cur_idx(struct pstate_power_info *pi) { FILE *f_cur; int ret = -1; - char *p_cur; - char buf_cur[BUFSIZ]; - char fullpath_cur[PATH_MAX]; - char *s_cur; uint32_t sys_cur_freq = 0; unsigned int i; - snprintf(fullpath_cur, sizeof(fullpath_cur), - POWER_SYSFILE_CUR_FREQ, - pi->lcore_id); - f_cur = fopen(fullpath_cur, "r"); - FOPEN_OR_ERR_RET(f_cur, ret); + open_core_sysfs_file(POWER_SYSFILE_CUR_FREQ, pi->lcore_id, "r", &f_cur); + FOPEN_OR_ERR_GOTO(f_cur, fail); - /* initialize the cur_idx to matching current frequency freq index */ - s_cur = fgets(buf_cur, sizeof(buf_cur), f_cur); - FOPS_OR_NULL_GOTO(s_cur, fail); - - p_cur = strchr(buf_cur, '\n'); - if (p_cur != NULL) - *p_cur = 0; - sys_cur_freq = strtoul(buf_cur, &p_cur, POWER_CONVERT_TO_DECIMAL); + ret = read_core_sysfs_u32(f_cur, &sys_cur_freq); + FOPS_OR_ERR_GOTO(ret, fail); /* convert the frequency to nearest 100000 value * Ex: if sys_cur_freq=1396789 then freq_conv=1400000 @@ -611,10 +628,10 @@ power_get_cur_idx(struct pstate_power_info *pi) } } - fclose(f_cur); - return 0; + ret = 0; fail: - fclose(f_cur); + if (f_cur != NULL) + fclose(f_cur); return ret; } -- 2.25.1