Linux-EDAC Archive on lore.kernel.org
 help / color / Atom feed
From: Robert Richter <rrichter@marvell.com>
To: Borislav Petkov <bp@alien8.de>, Tony Luck <tony.luck@intel.com>,
	"James Morse" <james.morse@arm.com>,
	Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: "linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Robert Richter <rrichter@marvell.com>
Subject: [PATCH 14/21] EDAC, ghes: Extract numa node information for each dimm
Date: Wed, 29 May 2019 08:44:35 +0000
Message-ID: <20190529084344.28562-15-rrichter@marvell.com> (raw)
In-Reply-To: <20190529084344.28562-1-rrichter@marvell.com>

In a later patch we want to have one mc device per node. This patch
extracts the numa node information for each dimm. This is done by
collecting the physical address ranges from the DMI table (Memory
Array Mapped Address - Type 19 of SMBIOS spec). The node information
for a physical address is already know to a numa aware system (e.g. by
using the ACPI _PXM method or the ACPI SRAT table), so based on the PA
we can assign the node id to the dimms.

A fallback that disables numa is implemented in case the node
information is inconsistent.

E.g., on a ThunderX2 system the following node mappings are found
based on the DMI table:

EDAC DEBUG: mem_info_setup: DIMM0: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM1: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM2: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM3: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM4: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM5: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM6: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM7: Found mem range [0x0000008800000000-0x0000009ffcffffff] on node 0
EDAC DEBUG: mem_info_setup: DIMM8: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM9: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM10: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM11: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM12: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM13: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM14: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1
EDAC DEBUG: mem_info_setup: DIMM15: Found mem range [0x0000009ffd000000-0x000000bffcffffff] on node 1

Signed-off-by: Robert Richter <rrichter@marvell.com>
---
 drivers/edac/ghes_edac.c | 104 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 103 insertions(+), 1 deletion(-)

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 50f4ee36b755..083452a48b42 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -67,14 +67,34 @@ struct memdev_dmi_entry {
 	u16 conf_mem_clk_speed;
 } __attribute__((__packed__));
 
+/* Memory Array Mapped Address - Type 19 of SMBIOS spec */
+struct memarr_dmi_entry {
+	u8		type;
+	u8		length;
+	u16		handle;
+	u32		start;
+	u32		end;
+	u16		phys_mem_array_handle;
+	u8		partition_width;
+	u64		ext_start;
+	u64		ext_end;
+} __attribute__((__packed__));
+
 struct ghes_dimm_info {
 	struct dimm_info dimm_info;
 	int		idx;
+	int		numa_node;
+	phys_addr_t	start;
+	phys_addr_t	end;
+	u16		phys_handle;
 };
 
 struct ghes_mem_info {
-	int num_dimm;
+	int		num_dimm;
 	struct ghes_dimm_info *dimms;
+	int		num_nodes;
+	int		num_per_node[MAX_NUMNODES];
+	bool		enable_numa;
 };
 
 struct ghes_mem_info mem_info;
@@ -97,10 +117,50 @@ static void ghes_dimm_info_init(void)
 
 	for_each_dimm(dimm) {
 		dimm->idx	= idx;
+		dimm->numa_node	= NUMA_NO_NODE;
 		idx++;
 	}
 }
 
+static void ghes_edac_set_nid(const struct dmi_header *dh, void *arg)
+{
+	struct memarr_dmi_entry *entry = (struct memarr_dmi_entry *)dh;
+	struct ghes_dimm_info *dimm;
+	phys_addr_t start, end;
+	int nid;
+
+	if (dh->type != DMI_ENTRY_MEM_ARRAY_MAPPED_ADDR)
+		return;
+
+	/* only support SMBIOS 2.7+ */
+	if (entry->length < sizeof(*entry))
+		return;
+
+	if (entry->start == 0xffffffff)
+		start = entry->ext_start;
+	else
+		start = entry->start;
+	if (entry->end == 0xffffffff)
+		end = entry->ext_end;
+	else
+		end = entry->end;
+
+	if (!pfn_valid(PHYS_PFN(start)))
+		return;
+
+	nid = pfn_to_nid(PHYS_PFN(start));
+	if (nid < 0 || nid >= MAX_NUMNODES || !node_possible(nid))
+		nid = NUMA_NO_NODE;
+
+	for_each_dimm(dimm) {
+		if (entry->phys_mem_array_handle == dimm->phys_handle) {
+			dimm->numa_node	= nid;
+			dimm->start	= start;
+			dimm->end	= end;
+		}
+	}
+}
+
 static int get_dimm_smbios_index(u16 handle)
 {
 	struct mem_ctl_info *mci = ghes_pvt->mci;
@@ -213,8 +273,25 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 	}
 }
 
+static void mem_info_disable_numa(void)
+{
+	struct ghes_dimm_info *dimm;
+
+	for_each_dimm(dimm) {
+		if (dimm->numa_node != NUMA_NO_NODE)
+			mem_info.num_per_node[dimm->numa_node] = 0;
+		dimm->numa_node = 0;
+	}
+
+	mem_info.num_per_node[0] = mem_info.num_dimm;
+	mem_info.num_nodes = 1;
+	mem_info.enable_numa = false;
+}
+
 static int mem_info_setup(void)
 {
+	struct ghes_dimm_info *dimm;
+	bool enable_numa = true;
 	int idx = 0;
 
 	memset(&mem_info, 0, sizeof(mem_info));
@@ -231,6 +308,29 @@ static int mem_info_setup(void)
 
 	ghes_dimm_info_init();
 	dmi_walk(ghes_edac_dmidecode, &idx);
+	dmi_walk(ghes_edac_set_nid, NULL);
+
+	for_each_dimm(dimm) {
+		if (dimm->numa_node == NUMA_NO_NODE) {
+			enable_numa = false;
+		} else {
+			if (!mem_info.num_per_node[dimm->numa_node])
+				mem_info.num_nodes++;
+			mem_info.num_per_node[dimm->numa_node]++;
+		}
+
+		edac_dbg(1, "DIMM%i: Found mem range [%pa-%pa] on node %d\n",
+			dimm->idx, &dimm->start, &dimm->end, dimm->numa_node);
+	}
+
+	mem_info.enable_numa = enable_numa;
+	if (enable_numa)
+		return 0;
+
+	/* something went wrong, disable numa */
+	if (num_possible_nodes() > 1)
+		pr_warn("Can't get numa info, disabling numa\n");
+	mem_info_disable_numa();
 
 	return 0;
 }
@@ -258,6 +358,8 @@ static int mem_info_setup_fake(void)
 	dimm->dtype = DEV_UNKNOWN;
 	dimm->edac_mode = EDAC_SECDED;
 
+	mem_info_disable_numa();
+
 	return 0;
 }
 
-- 
2.20.1


  parent reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-29  8:44 [PATCH 00/21] EDAC, mc, ghes: Fixes and updates to improve memory error reporting Robert Richter
2019-05-29  8:44 ` [PATCH 01/21] EDAC, mc: Fix edac_mc_find() in case no device is found Robert Richter
2019-05-29  8:44 ` [PATCH 02/21] EDAC: Fixes to use put_device() after device_add() errors Robert Richter
2019-06-11 17:28   ` Borislav Petkov
2019-06-12 17:17     ` Robert Richter
2019-05-29  8:44 ` [PATCH 03/21] EDAC: Kill EDAC_DIMM_PTR() macro Robert Richter
2019-05-29  8:44 ` [PATCH 04/21] EDAC: Kill EDAC_DIMM_OFF() macro Robert Richter
2019-05-29  8:44 ` [PATCH 05/21] EDAC: Introduce mci_for_each_dimm() iterator Robert Richter
2019-05-29  8:44 ` [PATCH 06/21] EDAC, mc: Cleanup _edac_mc_free() code Robert Richter
2019-05-29  8:44 ` [PATCH 07/21] EDAC, mc: Remove per layer counters Robert Richter
2019-05-29  8:44 ` [PATCH 08/21] EDAC, mc: Rework edac_raw_mc_handle_error() to use struct dimm_info Robert Richter
2019-05-29  8:44 ` [PATCH 09/21] EDAC, ghes: Use standard kernel macros for page calculations Robert Richter
2019-05-29 15:13   ` James Morse
2019-05-29  8:44 ` [PATCH 10/21] EDAC, ghes: Remove pvt->detail_location string Robert Richter
2019-05-29 15:13   ` James Morse
2019-06-12 18:13     ` Robert Richter
2019-05-29  8:44 ` [PATCH 11/21] EDAC, ghes: Unify trace_mc_event() code with edac_mc driver Robert Richter
2019-05-29 15:12   ` James Morse
2019-06-03 13:10     ` Robert Richter
2019-06-04 17:15       ` James Morse
2019-06-13 22:23         ` Robert Richter
2019-05-29  8:44 ` [PATCH 12/21] EDAC, ghes: Add support for legacy API counters Robert Richter
2019-05-29 15:13   ` James Morse
2019-06-12 18:41     ` Robert Richter
2019-06-19 17:22       ` James Morse
2019-06-20  6:55         ` Robert Richter
2019-06-26  9:33           ` James Morse
2019-06-26 10:27             ` Robert Richter
2019-05-29  8:44 ` [PATCH 13/21] EDAC, ghes: Rework memory hierarchy detection Robert Richter
2019-05-29 15:06   ` James Morse
2019-05-31 13:41     ` Robert Richter
2019-05-29  8:44 ` Robert Richter [this message]
2019-05-29 17:51   ` [PATCH 14/21] EDAC, ghes: Extract numa node information for each dimm James Morse
2019-06-13 20:52     ` Robert Richter
2019-05-29  8:44 ` [PATCH 15/21] EDAC, ghes: Moving code around ghes_edac_register() Robert Richter
2019-05-29  8:44 ` [PATCH 16/21] EDAC, ghes: Create one memory controller device per node Robert Richter
2019-05-29  8:44 ` [PATCH 17/21] EDAC, ghes: Fill sysfs with the DMI DIMM label information Robert Richter
2019-05-29  8:44 ` [PATCH 18/21] EDAC, mc: Introduce edac_mc_alloc_by_dimm() for per dimm allocation Robert Richter
2019-05-29  8:44 ` [PATCH 19/21] EDAC, ghes: Identify dimm by node, card, module and handle Robert Richter
2019-05-29  8:44 ` [PATCH 20/21] EDAC, ghes: Enable per-layer reporting based on card/module Robert Richter
2019-05-29  8:44 ` [PATCH 21/21] EDAC, Documentation: Describe CPER module definition and DIMM ranks Robert Richter
2019-05-29 14:54 ` [PATCH 00/21] EDAC, mc, ghes: Fixes and updates to improve memory error reporting Borislav Petkov
2019-05-31 14:48   ` Robert Richter

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190529084344.28562-15-rrichter@marvell.com \
    --to=rrichter@marvell.com \
    --cc=bp@alien8.de \
    --cc=james.morse@arm.com \
    --cc=linux-edac@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mchehab@kernel.org \
    --cc=tony.luck@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-EDAC Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-edac/0 linux-edac/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-edac linux-edac/ https://lore.kernel.org/linux-edac \
		linux-edac@vger.kernel.org
	public-inbox-index linux-edac

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-edac


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git