| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20241016105832.GSZw-cWDOFweQMWRgZ@fat_crate.local>
Date: Wed, 16 Oct 2024 12:58:32 +0200
From: Borislav Petkov <bp@...en8.de>
To: shiju.jose@...wei.com
Cc: linux-edac@...r.kernel.org, linux-cxl@...r.kernel.org,
linux-acpi@...r.kernel.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, tony.luck@...el.com,
rafael@...nel.org, lenb@...nel.org, mchehab@...nel.org,
dan.j.williams@...el.com, dave@...olabs.net,
jonathan.cameron@...wei.com, dave.jiang@...el.com,
alison.schofield@...el.com, vishal.l.verma@...el.com,
ira.weiny@...el.com, david@...hat.com, Vilas.Sridharan@....com,
leo.duran@....com, Yazen.Ghannam@....com, rientjes@...gle.com,
jiaqiyan@...gle.com, Jon.Grimm@....com, dave.hansen@...ux.intel.com,
naoya.horiguchi@....com, james.morse@....com, jthoughton@...gle.com,
somasundaram.a@....com, erdemaktas@...gle.com, pgonda@...gle.com,
duenwen@...gle.com, gthelen@...gle.com,
wschwartz@...erecomputing.com, dferguson@...erecomputing.com,
wbs@...amperecomputing.com, nifan.cxl@...il.com,
tanxiaofei@...wei.com, prime.zeng@...ilicon.com,
roberto.sassu@...wei.com, kangkang.shen@...urewei.com,
wanghuiqiang@...wei.com, linuxarm@...wei.com
Subject: Re: [PATCH v13 01/18] EDAC: Add support for EDAC device features
control
On Wed, Oct 09, 2024 at 01:41:02PM +0100, shiju.jose@...wei.com wrote:
> From: Shiju Jose <shiju.jose@...wei.com>
>
> Add generic EDAC device features control supports registering
> RAS features supported in the system. Driver exposes features
> control attributes to userspace in
> /sys/bus/edac/devices/<dev-name>/<ras-feature>/
Chatgpt prompt:
| Please check the grammar in this English text: "Add generic EDAC device
| features control supports registering RAS features supported in the system.
| Driver exposes features control attributes to userspace in
| /sys/bus/edac/devices/<dev-name>/<ras-"feature>/
Response:
| Here’s a corrected version of the text:
|
| "Add generic EDAC device feature control support for registering RAS features
| supported in the system. The driver exposes feature control attributes to
| userspace in /sys/bus/edac/devices/<dev-name>/<ras-feature>/."
|
| Changes made:
|
| * "features control" was changed to "feature control" for consistency and
| clarity.
|
| * "supports registering" was changed to "support for registering" to match the
| structure of the sentence.
|
| * Added "The" at the beginning of the second sentence for better flow.
|
| * Corrected the syntax around the file path to ensure clarity and proper
| * punctuation.
Please run all your commit text through some LLM AI as they're apparently good
enough now to help me in correcting grammar.
> Co-developed-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
> Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
> ---
> drivers/edac/edac_device.c | 105 +++++++++++++++++++++++++++++++++++++
> include/linux/edac.h | 32 +++++++++++
> 2 files changed, 137 insertions(+)
>
> diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
> index 621dc2a5d034..0b8aa8150239 100644
> --- a/drivers/edac/edac_device.c
> +++ b/drivers/edac/edac_device.c
> @@ -570,3 +570,108 @@ void edac_device_handle_ue_count(struct edac_device_ctl_info *edac_dev,
> block ? block->name : "N/A", count, msg);
> }
> EXPORT_SYMBOL_GPL(edac_device_handle_ue_count);
> +
> +/* EDAC device feature */
> +static void edac_dev_release(struct device *dev)
> +{
> + struct edac_dev_feat_ctx *ctx = container_of(dev, struct edac_dev_feat_ctx, dev);
> +
> + kfree(ctx->dev.groups);
> + kfree(ctx);
> +}
> +
> +const struct device_type edac_dev_type = {
> + .name = "edac_dev",
> + .release = edac_dev_release,
> +};
> +
> +static void edac_dev_unreg(void *data)
> +{
> + device_unregister(data);
> +}
> +
> +/**
> + * edac_dev_register - register device for RAS features with EDAC
> + * @parent: client device.
If this is a client device, why is the variable called "parent" and not
"client"?
I.e.,
struct device *client;
For clarity and simplicity.
Or call it "parent" because you do:
ctx->dev.parent = parent;
and forget "client" altogether.
> + * @name: client device's name.
> + * @private: parent driver's data to store in the context if any.
> + * @num_features: number of RAS features to register.
> + * @ras_features: list of RAS features to register.
> + *
> + * Return:
> + * * %0 - Success.
> + * * %-EINVAL - Invalid parameters passed.
> + * * %-ENOMEM - Dynamic memory allocation failed.
> + *
> + * The new edac_dev_feat_ctx would be freed automatically.
Why is this important to call out here?
It is a common coding pattern of freeing resources in the release function...
> + */
> +int edac_dev_register(struct device *parent, char *name,
> + void *private, int num_features,
> + const struct edac_dev_feature *ras_features)
> +{
> + const struct attribute_group **ras_attr_groups;
> + struct edac_dev_feat_ctx *ctx;
> + int attr_gcnt = 0;
> + int ret, feat;
> +
> + if (!parent || !name || !num_features || !ras_features)
> + return -EINVAL;
> +
> + /* Double parse to make space for attributes */
> + for (feat = 0; feat < num_features; feat++) {
> + switch (ras_features[feat].ft_type) {
> + /* Add feature specific code */
> + default:
> + return -EINVAL;
> + }
> + }
> +
> + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
> + if (!ctx)
> + return -ENOMEM;
> +
> + ctx->dev.parent = parent;
> + ctx->private = private;
> +
> + ras_attr_groups = kcalloc(attr_gcnt + 1, sizeof(*ras_attr_groups), GFP_KERNEL);
> + if (!ras_attr_groups) {
> + ret = -ENOMEM;
> + goto ctx_free;
> + }
> +
> + attr_gcnt = 0;
> + for (feat = 0; feat < num_features; feat++, ras_features++) {
> + switch (ras_features->ft_type) {
> + /* Add feature specific code */
> + default:
> + ret = -EINVAL;
> + goto groups_free;
> + }
> + }
> +
> + ras_attr_groups[attr_gcnt] = NULL;
> + ctx->dev.bus = edac_get_sysfs_subsys();
> + ctx->dev.type = &edac_dev_type;
> + ctx->dev.groups = ras_attr_groups;
> + dev_set_drvdata(&ctx->dev, ctx);
> +
> + ret = dev_set_name(&ctx->dev, name);
> + if (ret)
> + goto groups_free;
> +
> + ret = device_register(&ctx->dev);
> + if (ret) {
> + put_device(&ctx->dev);
> + goto groups_free;
> + return ret;
^^^^^^^^^^
Come again?!
There's code after a "goto"?
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
Powered by blists - more mailing lists