From patchwork Thu Nov 17 22:37:49 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexander Motin X-Patchwork-Id: 13047408 Received: from mail-qt1-f181.google.com (mail-qt1-f181.google.com [209.85.160.181]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 16C1B8F7B for ; Thu, 17 Nov 2022 22:38:39 +0000 (UTC) Received: by mail-qt1-f181.google.com with SMTP id z6so2106620qtv.5 for ; Thu, 17 Nov 2022 14:38:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ixsystems.com; s=google; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=zGuXVVPN/m5K4FKkj7oASxab4A65Q5i9aQDCiJUiKXI=; b=YHK+/jfYarj5IgKRdIloHToCkh58W0gvE6RUx+RZb6x7ws/VbTmTI7/+dGFk8+C0X0 o4nFwiCyZuZtadRs+CjtQqIjMHk1++zdFofN5ZAKHCCISznVAT6XmOZB8yKm20HcD4JL 6f//uHMtvCsKCxKAZx52Etrx0PehRKfBo0HuAp7FUt1ZI5JMc4NEQKusGt8c+KPV64EC MPhq4YTEH1vKIOs5eg2NVI6hanREz7yUaxRgAHW3XAuT2hIR5d5Lthttd8BkaSJFlHKF /cGGFV1wklM6i0DmuE3AuIaMezIcSffAF6If857U2AZte01+BQ5cJnDlZHTd9Ksil+tR 5KSw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=zGuXVVPN/m5K4FKkj7oASxab4A65Q5i9aQDCiJUiKXI=; b=d9kUYSQDBSVU8MKpqrXeaT/vR8wLMFranIf5cyMxuGhNGVaqpKcqilMdj7IPwQZHGJ jkpSXjwlMOy40D1sST70u7/fNMGclhwVaGCydylR4xp7TPKvf9EfOzvPIe3qtJLOuaKi nwgyopPk4XrXp7qaxy2sitDLRdYsYCeJmK5MrvI/IUe1c27G7oD6xG4U4xZSqyOn2xry zZfeM4VYtSmLUc4EeaKCk7VCCU8h46AYEuMW0Gkjm18tusIC3IXA2/yLgDVEcOLY6Evi l0c3VqCgQPZbm/pFqECdcHb2ujSboNLXJVGMkJ7QvQdjD+g/2hLmSZBlDkK52rFiqa3P bS6w== X-Gm-Message-State: ANoB5pkjV0d68HX5AKYFCTDf0Fwmb1cTPVGCr0P1RawDFMpUoA9cMrtO N77f/Lm9+B1mkMKOo0HdkzSZyYzIBcbIntqLdNJX4sjwm49g3oOEt/se+ygQZo+ZTvruJZMv561 M2Ai/jE9f+Y0b9+pCacLth/THlcRl+HW64Wv9d68kuoeQrzYc4KZWsFh4GQdlhkXong== X-Google-Smtp-Source: AA0mqf5KqmG0Sq88qSj7/BPLyPU0YvMbKZ5JLdLGt2SfuM7/sVXNwkkldV0BDiEzOxULloqT1yDoxg== X-Received: by 2002:ac8:4908:0:b0:3a5:faa7:35e7 with SMTP id e8-20020ac84908000000b003a5faa735e7mr4366879qtq.66.1668724718629; Thu, 17 Nov 2022 14:38:38 -0800 (PST) Received: from testm50.mav.ixsystems.net ([38.32.73.2]) by smtp.gmail.com with ESMTPSA id do52-20020a05620a2b3400b006fba0a389a4sm1272237qkb.88.2022.11.17.14.38.38 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 17 Nov 2022 14:38:38 -0800 (PST) From: Alexander Motin To: nvdimm@lists.linux.dev Cc: Alexander Motin Subject: [ndctl PATCH 1/2 v2] libndctl/msft: Cleanup the code Date: Thu, 17 Nov 2022 17:37:49 -0500 Message-Id: <20221117223749.6783-1-mav@ixsystems.com> X-Mailer: git-send-email 2.30.2 Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Clean up the code, making it more uniform with others and allowing more methods to be implemented later. Signed-off-by: Alexander Motin --- ndctl/lib/msft.c | 58 ++++++++++++++++++++++++++++++++++++++---------- ndctl/lib/msft.h | 13 ++++------- 2 files changed, 50 insertions(+), 21 deletions(-) diff --git a/ndctl/lib/msft.c b/ndctl/lib/msft.c index 3112799..efc7fe1 100644 --- a/ndctl/lib/msft.c +++ b/ndctl/lib/msft.c @@ -2,6 +2,7 @@ // Copyright (C) 2016-2017 Dell, Inc. // Copyright (C) 2016 Hewlett Packard Enterprise Development LP // Copyright (C) 2016-2020, Intel Corporation. +/* Copyright (C) 2022 iXsystems, Inc. */ #include #include #include @@ -12,12 +13,39 @@ #define CMD_MSFT(_c) ((_c)->msft) #define CMD_MSFT_SMART(_c) (CMD_MSFT(_c)->u.smart.data) +static const char *msft_cmd_desc(int fn) +{ + static const char * const descs[] = { + [NDN_MSFT_CMD_CHEALTH] = "critical_health", + [NDN_MSFT_CMD_NHEALTH] = "nvdimm_health", + [NDN_MSFT_CMD_EHEALTH] = "es_health", + }; + const char *desc; + + if (fn >= (int) ARRAY_SIZE(descs)) + return "unknown"; + desc = descs[fn]; + if (!desc) + return "unknown"; + return desc; +} + +static bool msft_cmd_is_supported(struct ndctl_dimm *dimm, int cmd) +{ + /* Handle this separately to support monitor mode */ + if (cmd == ND_CMD_SMART) + return true; + + return !!(dimm->cmd_mask & (1ULL << cmd)); +} + static u32 msft_get_firmware_status(struct ndctl_cmd *cmd) { return cmd->msft->u.smart.status; } -static struct ndctl_cmd *msft_dimm_cmd_new_smart(struct ndctl_dimm *dimm) +static struct ndctl_cmd *alloc_msft_cmd(struct ndctl_dimm *dimm, + unsigned int func, size_t in_size, size_t out_size) { struct ndctl_bus *bus = ndctl_dimm_get_bus(dimm); struct ndctl_ctx *ctx = ndctl_bus_get_ctx(bus); @@ -30,12 +58,12 @@ static struct ndctl_cmd *msft_dimm_cmd_new_smart(struct ndctl_dimm *dimm) return NULL; } - if (test_dimm_dsm(dimm, NDN_MSFT_CMD_SMART) == DIMM_DSM_UNSUPPORTED) { + if (test_dimm_dsm(dimm, func) == DIMM_DSM_UNSUPPORTED) { dbg(ctx, "unsupported function\n"); return NULL; } - size = sizeof(*cmd) + sizeof(struct ndn_pkg_msft); + size = sizeof(*cmd) + sizeof(struct nd_cmd_pkg) + in_size + out_size; cmd = calloc(1, size); if (!cmd) return NULL; @@ -45,25 +73,30 @@ static struct ndctl_cmd *msft_dimm_cmd_new_smart(struct ndctl_dimm *dimm) cmd->type = ND_CMD_CALL; cmd->size = size; cmd->status = 1; + cmd->get_firmware_status = msft_get_firmware_status; msft = CMD_MSFT(cmd); msft->gen.nd_family = NVDIMM_FAMILY_MSFT; - msft->gen.nd_command = NDN_MSFT_CMD_SMART; + msft->gen.nd_command = func; msft->gen.nd_fw_size = 0; - msft->gen.nd_size_in = offsetof(struct ndn_msft_smart, status); - msft->gen.nd_size_out = sizeof(msft->u.smart); + msft->gen.nd_size_in = in_size; + msft->gen.nd_size_out = out_size; msft->u.smart.status = 0; - cmd->get_firmware_status = msft_get_firmware_status; return cmd; } +static struct ndctl_cmd *msft_dimm_cmd_new_smart(struct ndctl_dimm *dimm) +{ + return (alloc_msft_cmd(dimm, NDN_MSFT_CMD_NHEALTH, + 0, sizeof(struct ndn_msft_smart))); +} + static int msft_smart_valid(struct ndctl_cmd *cmd) { if (cmd->type != ND_CMD_CALL || - cmd->size != sizeof(*cmd) + sizeof(struct ndn_pkg_msft) || CMD_MSFT(cmd)->gen.nd_family != NVDIMM_FAMILY_MSFT || - CMD_MSFT(cmd)->gen.nd_command != NDN_MSFT_CMD_SMART || + CMD_MSFT(cmd)->gen.nd_command != NDN_MSFT_CMD_NHEALTH || cmd->status != 0) return cmd->status < 0 ? cmd->status : -EINVAL; return 0; @@ -80,9 +113,8 @@ static unsigned int msft_cmd_smart_get_flags(struct ndctl_cmd *cmd) } /* below health data can be retrieved via MSFT _DSM function 11 */ - return NDN_MSFT_SMART_HEALTH_VALID | - NDN_MSFT_SMART_TEMP_VALID | - NDN_MSFT_SMART_USED_VALID; + return ND_SMART_HEALTH_VALID | ND_SMART_TEMP_VALID | + ND_SMART_USED_VALID; } static unsigned int num_set_bit_health(__u16 num) @@ -171,6 +203,8 @@ static int msft_cmd_xlat_firmware_status(struct ndctl_cmd *cmd) } struct ndctl_dimm_ops * const msft_dimm_ops = &(struct ndctl_dimm_ops) { + .cmd_desc = msft_cmd_desc, + .cmd_is_supported = msft_cmd_is_supported, .new_smart = msft_dimm_cmd_new_smart, .smart_get_flags = msft_cmd_smart_get_flags, .smart_get_health = msft_cmd_smart_get_health, diff --git a/ndctl/lib/msft.h b/ndctl/lib/msft.h index 978cc11..8d246a5 100644 --- a/ndctl/lib/msft.h +++ b/ndctl/lib/msft.h @@ -2,21 +2,16 @@ /* Copyright (C) 2016-2017 Dell, Inc. */ /* Copyright (C) 2016 Hewlett Packard Enterprise Development LP */ /* Copyright (C) 2014-2020, Intel Corporation. */ +/* Copyright (C) 2022 iXsystems, Inc. */ #ifndef __NDCTL_MSFT_H__ #define __NDCTL_MSFT_H__ enum { - NDN_MSFT_CMD_QUERY = 0, - - /* non-root commands */ - NDN_MSFT_CMD_SMART = 11, + NDN_MSFT_CMD_CHEALTH = 10, + NDN_MSFT_CMD_NHEALTH = 11, + NDN_MSFT_CMD_EHEALTH = 12, }; -/* NDN_MSFT_CMD_SMART */ -#define NDN_MSFT_SMART_HEALTH_VALID ND_SMART_HEALTH_VALID -#define NDN_MSFT_SMART_TEMP_VALID ND_SMART_TEMP_VALID -#define NDN_MSFT_SMART_USED_VALID ND_SMART_USED_VALID - /* * This is actually function 11 data, * This is the closest I can find to match smart From patchwork Thu Nov 17 22:37:51 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexander Motin X-Patchwork-Id: 13047409 Received: from mail-qt1-f171.google.com (mail-qt1-f171.google.com [209.85.160.171]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5A3C3A464 for ; Thu, 17 Nov 2022 22:38:59 +0000 (UTC) Received: by mail-qt1-f171.google.com with SMTP id e15so2122203qts.1 for ; Thu, 17 Nov 2022 14:38:59 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ixsystems.com; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=/sakPxkdhefEPhxq3cq6e29lQC77134wJ/YGMkb/Hak=; b=H5T9uUrVcMsNlW3j5pU4Pi4tZdL3GPeJbX5bipqUzsb3AzPvj058P6CTCYlkBWiQfV dB+YPm4dr85XTGC+mKDKrB5njM57eKANJKTEccinWBcxQlbDT+NoiM/CaUXQcHZp/GLl vlriTSbMchPqMeLwjRHsIr2kzrNmhZHQiOt4yyVOO2puUuAuATby7Gg+SSENoB/q2bVn k3+UM19cfgfbrZR1RdnTiCHI7vCeh7JLkKHAcOTKNvhbWliqGmOXiSx+mzwulMXbZmEO mXAaUaRHtDQ7eX27+IAerDm+XZbc0lm+TCEmVl4j+ugN6TOVpYIMcW4PW6d8nLagQfsy NZ7Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=/sakPxkdhefEPhxq3cq6e29lQC77134wJ/YGMkb/Hak=; b=GKZe4xi6Q/xuF6BgtZeXZkB6hddcWlQ4GYdmDGOnJXgfR6Jq/DV+Z2LEPVIl1DxbtB T6fRvzNeThp1cayAbqJY758Xp9RhyNnOBmLC710n6/CtYcGcM25KA2KbA/zUfcnJFGTq R1VMm/n4fuouf5l+SPCm9eAdCX380BJ9D3UIBDoXvtBtC8y9fLfRiDsXGFOLqJJs4GiC f91KtHcJkBn1uSUsF8SsNGJv2on/gFiVhwjMlHqAO3TDoEGhJSebygrNCPYWAx/9ur16 ODqxFabjwRP/ae298lp3S0cH2GJyOaQgSl1JEqTv+KfkB2gbyQ754M25c1SmmSWAwJZt eSMg== X-Gm-Message-State: ANoB5plKk+4xAppQbiFvK4/hkhM3c7Ru5RXmvDo1KUL5K1WtoJIrIqBk FBRJ8mXzccjtvezVx6JzdgipAsDP6iTz/vo0SnqBix9A8BD25qBiIMTSQrWE4frSM5H1N6Dfa/m zpZPCBKfM0szz8YKYPAoIfAf3gySDrLlxU1ZYDhV4f6kbHbrUflt0bXgdvR/cmyl9KA== X-Google-Smtp-Source: AA0mqf5M+SBmplXomz9eCcrbOPGtNqE1R3vUPf6JJ8OG8Fwo1Sb7IeOCp5/PzzkiMIxpvdLJPgMuFQ== X-Received: by 2002:ac8:6688:0:b0:3a5:3e8c:6130 with SMTP id d8-20020ac86688000000b003a53e8c6130mr4209352qtp.259.1668724738061; Thu, 17 Nov 2022 14:38:58 -0800 (PST) Received: from testm50.mav.ixsystems.net ([38.32.73.2]) by smtp.gmail.com with ESMTPSA id do52-20020a05620a2b3400b006fba0a389a4sm1272237qkb.88.2022.11.17.14.38.57 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 17 Nov 2022 14:38:57 -0800 (PST) From: Alexander Motin To: nvdimm@lists.linux.dev Cc: Alexander Motin Subject: [ndctl PATCH 2/2 v2] libndctl/msft: Improve "smart" state reporting Date: Thu, 17 Nov 2022 17:37:51 -0500 Message-Id: <20221117223749.6783-2-mav@ixsystems.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20221117223749.6783-1-mav@ixsystems.com> References: <20221117223749.6783-1-mav@ixsystems.com> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Previous code reported "smart" state based on number of bits set in the module health field. But actually any single bit set there already means critical failure. Rework the logic according to specification, properly reporting non-critical state in case of warning threshold reached, critical in case of any module health bit set or error threshold reached and fatal if NVDIMM exhausted its life time. In attempt to report the cause of failure in absence of better methods, report reached thresholds as more or less matching alarms. Signed-off-by: Alexander Motin --- ndctl/lib/msft.c | 55 ++++++++++++++++++++++++++---------------------- 1 file changed, 30 insertions(+), 25 deletions(-) diff --git a/ndctl/lib/msft.c b/ndctl/lib/msft.c index efc7fe1..8f66c97 100644 --- a/ndctl/lib/msft.c +++ b/ndctl/lib/msft.c @@ -114,26 +114,32 @@ static unsigned int msft_cmd_smart_get_flags(struct ndctl_cmd *cmd) /* below health data can be retrieved via MSFT _DSM function 11 */ return ND_SMART_HEALTH_VALID | ND_SMART_TEMP_VALID | - ND_SMART_USED_VALID; + ND_SMART_USED_VALID | ND_SMART_ALARM_VALID; } -static unsigned int num_set_bit_health(__u16 num) +static unsigned int msft_cmd_smart_get_health(struct ndctl_cmd *cmd) { - int i; - __u16 n = num & 0x7FFF; - unsigned int count = 0; + unsigned int health = 0; + int rc; - for (i = 0; i < 15; i++) - if (!!(n & (1 << i))) - count++; + rc = msft_smart_valid(cmd); + if (rc < 0) { + errno = -rc; + return UINT_MAX; + } - return count; + if (CMD_MSFT_SMART(cmd)->nvm_lifetime == 0) + health |= ND_SMART_FATAL_HEALTH; + if (CMD_MSFT_SMART(cmd)->health != 0 || + CMD_MSFT_SMART(cmd)->err_thresh_stat != 0) + health |= ND_SMART_CRITICAL_HEALTH; + if (CMD_MSFT_SMART(cmd)->warn_thresh_stat != 0) + health |= ND_SMART_NON_CRITICAL_HEALTH; + return health; } -static unsigned int msft_cmd_smart_get_health(struct ndctl_cmd *cmd) +static unsigned int msft_cmd_smart_get_media_temperature(struct ndctl_cmd *cmd) { - unsigned int health; - unsigned int num; int rc; rc = msft_smart_valid(cmd); @@ -142,21 +148,13 @@ static unsigned int msft_cmd_smart_get_health(struct ndctl_cmd *cmd) return UINT_MAX; } - num = num_set_bit_health(CMD_MSFT_SMART(cmd)->health); - if (num == 0) - health = 0; - else if (num < 2) - health = ND_SMART_NON_CRITICAL_HEALTH; - else if (num < 3) - health = ND_SMART_CRITICAL_HEALTH; - else - health = ND_SMART_FATAL_HEALTH; - - return health; + return CMD_MSFT_SMART(cmd)->temp * 16; } -static unsigned int msft_cmd_smart_get_media_temperature(struct ndctl_cmd *cmd) +static unsigned int msft_cmd_smart_get_alarm_flags(struct ndctl_cmd *cmd) { + __u8 stat; + unsigned int flags = 0; int rc; rc = msft_smart_valid(cmd); @@ -165,7 +163,13 @@ static unsigned int msft_cmd_smart_get_media_temperature(struct ndctl_cmd *cmd) return UINT_MAX; } - return CMD_MSFT_SMART(cmd)->temp * 16; + stat = CMD_MSFT_SMART(cmd)->err_thresh_stat | + CMD_MSFT_SMART(cmd)->warn_thresh_stat; + if (stat & 3) /* NVM_LIFETIME/ES_LIFETIME */ + flags |= ND_SMART_SPARE_TRIP; + if (stat & 4) /* ES_TEMP */ + flags |= ND_SMART_CTEMP_TRIP; + return flags; } static unsigned int msft_cmd_smart_get_life_used(struct ndctl_cmd *cmd) @@ -209,6 +213,7 @@ struct ndctl_dimm_ops * const msft_dimm_ops = &(struct ndctl_dimm_ops) { .smart_get_flags = msft_cmd_smart_get_flags, .smart_get_health = msft_cmd_smart_get_health, .smart_get_media_temperature = msft_cmd_smart_get_media_temperature, + .smart_get_alarm_flags = msft_cmd_smart_get_alarm_flags, .smart_get_life_used = msft_cmd_smart_get_life_used, .xlat_firmware_status = msft_cmd_xlat_firmware_status, };