nvme: add support for dynamic quirk configuration via module parameter

Introduce support for enabling or disabling specific NVMe quirks at module
load time through the `quirks` module parameter.
This mechanism allows users to apply known quirks dynamically based on the
device's PCI vendor and device IDs, without requiring to add hardcoded
entries in the driver and recompiling the kernel.

While the generic PCI new_id sysfs interface exists for dynamic
configuration, it is insufficient for scenarios where the system fails
to boot (for example, this has been reported to happen because of the
bogus_nid quirk). The new_id attribute is writable only after the system
has booted and sysfs is mounted.

The `quirks` parameter accepts a list of quirk specifications separated by
a '-' character in the following format:

<VID>:<DID>:<quirk_names>[-<VID>:<DID>:<quirk_names>-..]

Each quirk is represented by its name and can be prefixed with `^` to
indicate that the quirk should be disabled; quirk names are separated by
a ',' character.

Example: enable BOGUS_NID and BROKEN_MSI, disable DEALLOCATE_ZEROES:

   $ modprobe nvme quirks=7170:2210:bogus_nid,broken_msi,^deallocate_zeroes

Tested-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>

Author: maurizio-lombardi

Documentation/admin-guide/kernel-parameters.txt

@@ -74,6 +74,7 @@
 	TPM	TPM drivers are enabled.
 	UMS	USB Mass Storage support is enabled.
 	USB	USB support is enabled.
+	NVME	NVMe support is enabled
 	USBHID	USB Human Interface Device support is enabled.
 	V4L	Video For Linux support is enabled.
 	VGA	The VGA console has been enabled.
@@ -4671,6 +4672,18 @@ Kernel parameters
 			This can be set from sysctl after boot.
 			See Documentation/admin-guide/sysctl/vm.rst for details.
 
+	nvme.quirks=    [NVME] A list of quirk entries to augment the built-in
+			nvme quirk list. List entries are separated by a
+			'-' character.
+			Each entry has the form VendorID:ProductID:quirk_names.
+			The IDs are 4-digits hex numbers and quirk_names is a
+			list of quirk names separated by commas. A quirk name
+			can be prefixed by '^', meaning that the specified
+			quirk must be disabled.
+
+			Example:
+			nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi
+
 	ohci1394_dma=early	[HW,EARLY] enable debugging via the ohci1394 driver.
 			See Documentation/core-api/debugging-via-ohci1394.rst for more
 			info.

drivers/nvme/host/pci.c

@@ -72,6 +72,13 @@
 static_assert(MAX_PRP_RANGE / NVME_CTRL_PAGE_SIZE <=
 	(1 /* prp1 */ + NVME_MAX_NR_DESCRIPTORS * PRPS_PER_PAGE));
 
+struct quirk_entry {
+	u16 vendor_id;
+	u16 dev_id;
+	u32 enabled_quirks;
+	u32 disabled_quirks;
+};
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0444);
 
@@ -102,6 +109,142 @@ static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096");
 
+static struct quirk_entry *nvme_pci_quirk_list;
+static unsigned int nvme_pci_quirk_count;
+
+/* Helper to parse individual quirk names */
+static int nvme_parse_quirk_names(char *quirk_str, struct quirk_entry *entry)
+{
+	int i;
+	size_t field_len;
+	bool disabled, found;
+	char *p = quirk_str, *field;
+
+	while ((field = strsep(&p, ",")) && *field) {
+		disabled = false;
+		found = false;
+
+		if (*field == '^') {
+			/* Skip the '^' character */
+			disabled = true;
+			field++;
+		}
+
+		field_len = strlen(field);
+		for (i = 0; i < 32; i++) {
+			unsigned int bit = 1U << i;
+			char *q_name = nvme_quirk_name(bit);
+			size_t q_len = strlen(q_name);
+
+			if (!strcmp(q_name, "unknown"))
+				break;
+
+			if (!strcmp(q_name, field) &&
+				    q_len == field_len) {
+				if (disabled)
+					entry->disabled_quirks |= bit;
+				else
+					entry->enabled_quirks |= bit;
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			pr_err("nvme: unrecognized quirk %s\n", field);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+/* Helper to parse a single VID:DID:quirk_names entry */
+static int nvme_parse_quirk_entry(char *s, struct quirk_entry *entry)
+{
+	char *field;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->vendor_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->dev_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field)
+		return -EINVAL;
+
+	return nvme_parse_quirk_names(field, entry);
+}
+
+static int quirks_param_set(const char *value, const struct kernel_param *kp)
+{
+	int count, err, i;
+	struct quirk_entry *qlist;
+	char *field, *val, *sep_ptr;
+
+	err = param_set_copystring(value, kp);
+	if (err)
+		return err;
+
+	val = kstrdup(value, GFP_KERNEL);
+	if (!val)
+		return -ENOMEM;
+
+	if (!*val)
+		goto out_free_val;
+
+	count = 1;
+	for (i = 0; val[i]; i++) {
+		if (val[i] == '-')
+			count++;
+	}
+
+	qlist = kcalloc(count, sizeof(*qlist), GFP_KERNEL);
+	if (!qlist) {
+		err = -ENOMEM;
+		goto out_free_val;
+	}
+
+	i = 0;
+	sep_ptr = val;
+	while ((field = strsep(&sep_ptr, "-"))) {
+		if (nvme_parse_quirk_entry(field, &qlist[i])) {
+			pr_err("nvme: failed to parse quirk string %s\n",
+				value);
+			goto out_free_qlist;
+		}
+
+		i++;
+	}
+
+	nvme_pci_quirk_count = count;
+	nvme_pci_quirk_list  = qlist;
+	goto out_free_val;
+
+out_free_qlist:
+	kfree(qlist);
+out_free_val:
+	kfree(val);
+	return err;
+}
+
+static char quirks_param[128];
+static const struct kernel_param_ops quirks_param_ops = {
+	.set = quirks_param_set,
+	.get = param_get_string,
+};
+
+static struct kparam_string quirks_param_string = {
+	.maxlen = sizeof(quirks_param),
+	.string = quirks_param,
+};
+
+module_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0444);
+MODULE_PARM_DESC(quirks, "Enable/disable NVMe quirks by specifying "
+						"quirks=VID:DID:quirk_names");
+
 static int io_queue_count_set(const char *val, const struct kernel_param *kp)
 {
 	unsigned int n;
@@ -3439,12 +3582,25 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 	return 0;
 }
 
+static struct quirk_entry *detect_dynamic_quirks(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < nvme_pci_quirk_count; i++)
+		if (pdev->vendor == nvme_pci_quirk_list[i].vendor_id &&
+		    pdev->device == nvme_pci_quirk_list[i].dev_id)
+			return &nvme_pci_quirk_list[i];
+
+	return NULL;
+}
+
 static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 		const struct pci_device_id *id)
 {
 	unsigned long quirks = id->driver_data;
 	int node = dev_to_node(&pdev->dev);
 	struct nvme_dev *dev;
+	struct quirk_entry *qentry;
 	int ret = -ENOMEM;
 
 	dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids),
@@ -3476,6 +3632,11 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 			 "platform quirk: setting simple suspend\n");
 		quirks |= NVME_QUIRK_SIMPLE_SUSPEND;
 	}
+	qentry = detect_dynamic_quirks(pdev);
+	if (qentry) {
+		quirks |= qentry->enabled_quirks;
+		quirks &= ~qentry->disabled_quirks;
+	}
 	ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
 			     quirks);
 	if (ret)
@@ -4074,6 +4235,7 @@ static int __init nvme_init(void)
 
 static void __exit nvme_exit(void)
 {
+	kfree(nvme_pci_quirk_list);
 	pci_unregister_driver(&nvme_driver);
 	flush_workqueue(nvme_wq);
 }