| 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: <20260107175548.1792-4-guojinhui.liam@bytedance.com>
Date: Thu, 8 Jan 2026 01:55:48 +0800
From: "Jinhui Guo" <guojinhui.liam@...edance.com>
To: <dakr@...nel.org>, <alexander.h.duyck@...ux.intel.com>,
<alexanderduyck@...com>, <bhelgaas@...gle.com>, <bvanassche@....org>,
<dan.j.williams@...el.com>, <gregkh@...uxfoundation.org>,
<helgaas@...nel.org>, <rafael@...nel.org>, <tj@...nel.org>
Cc: <guojinhui.liam@...edance.com>, <linux-kernel@...r.kernel.org>,
<linux-pci@...r.kernel.org>
Subject: [PATCH 3/3] PCI: Clean up NUMA-node awareness in pci_bus_type probe
With NUMA-node-aware probing now handled by the driver core,
the equivalent code in the PCI driver is redundant and can
be removed.
Dropping it speeds up asynchronous probe by 35%; the gain
comes from eliminating the work_on_cpu() call in pci_call_probe()
that previously pinned every worker to the same CPU, forcing
serial probe of devices on the same NUMA node.
Testing three NVMe devices on the same NUMA node of an AMD
EPYC 9A64 2.4 GHz processor shows a 35% probe-time improvement
with the patch:
Before (all on CPU 0):
nvme 0000:01:00.0: CPU: 0, COMM: kworker/0:1, cost: 52266334ns
nvme 0000:02:00.0: CPU: 0, COMM: kworker/0:0, cost: 50787194ns
nvme 0000:03:00.0: CPU: 0, COMM: kworker/0:2, cost: 50541584ns
After (spread across CPUs 1, 2, 4):
nvme 0000:01:00.0: CPU: 1, COMM: kworker/u1025:2, cost: 35399608ns
nvme 0000:02:00.0: CPU: 2, COMM: kworker/u1025:3, cost: 35156157ns
nvme 0000:03:00.0: CPU: 4, COMM: kworker/u1025:0, cost: 35322116ns
The improvement grows with more PCI devices because fewer probes
contend for the same CPU.
Signed-off-by: Jinhui Guo <guojinhui.liam@...edance.com>
---
drivers/pci/pci-driver.c | 83 ++++------------------------------------
include/linux/pci.h | 1 -
2 files changed, 8 insertions(+), 76 deletions(-)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 7c2d9d596258..683bc682e750 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -296,18 +296,9 @@ static struct attribute *pci_drv_attrs[] = {
};
ATTRIBUTE_GROUPS(pci_drv);
-struct drv_dev_and_id {
- struct pci_driver *drv;
- struct pci_dev *dev;
- const struct pci_device_id *id;
-};
-
-static long local_pci_probe(void *_ddi)
+static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
+ const struct pci_device_id *id)
{
- struct drv_dev_and_id *ddi = _ddi;
- struct pci_dev *pci_dev = ddi->dev;
- struct pci_driver *pci_drv = ddi->drv;
- struct device *dev = &pci_dev->dev;
int rc;
/*
@@ -319,83 +310,25 @@ static long local_pci_probe(void *_ddi)
* count, in its probe routine and pm_runtime_get_noresume() in
* its remove routine.
*/
- pm_runtime_get_sync(dev);
- pci_dev->driver = pci_drv;
- rc = pci_drv->probe(pci_dev, ddi->id);
+ pm_runtime_get_sync(&dev->dev);
+ dev->driver = drv;
+ rc = drv->probe(dev, id);
if (!rc)
return rc;
if (rc < 0) {
- pci_dev->driver = NULL;
- pm_runtime_put_sync(dev);
+ dev->driver = NULL;
+ pm_runtime_put_sync(&dev->dev);
return rc;
}
/*
* Probe function should return < 0 for failure, 0 for success
* Treat values > 0 as success, but warn.
*/
- pci_warn(pci_dev, "Driver probe function unexpectedly returned %d\n",
+ pci_warn(dev, "Driver probe function unexpectedly returned %d\n",
rc);
return 0;
}
-static bool pci_physfn_is_probed(struct pci_dev *dev)
-{
-#ifdef CONFIG_PCI_IOV
- return dev->is_virtfn && dev->physfn->is_probed;
-#else
- return false;
-#endif
-}
-
-static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
- const struct pci_device_id *id)
-{
- int error, node, cpu;
- struct drv_dev_and_id ddi = { drv, dev, id };
-
- /*
- * Execute driver initialization on node where the device is
- * attached. This way the driver likely allocates its local memory
- * on the right node.
- */
- node = dev_to_node(&dev->dev);
- dev->is_probed = 1;
-
- cpu_hotplug_disable();
-
- /*
- * Prevent nesting work_on_cpu() for the case where a Virtual Function
- * device is probed from work_on_cpu() of the Physical device.
- */
- if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
- pci_physfn_is_probed(dev)) {
- cpu = nr_cpu_ids;
- } else {
- cpumask_var_t wq_domain_mask;
-
- if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) {
- error = -ENOMEM;
- goto out;
- }
- cpumask_and(wq_domain_mask,
- housekeeping_cpumask(HK_TYPE_WQ),
- housekeeping_cpumask(HK_TYPE_DOMAIN));
-
- cpu = cpumask_any_and(cpumask_of_node(node),
- wq_domain_mask);
- free_cpumask_var(wq_domain_mask);
- }
-
- if (cpu < nr_cpu_ids)
- error = work_on_cpu(cpu, local_pci_probe, &ddi);
- else
- error = local_pci_probe(&ddi);
-out:
- dev->is_probed = 0;
- cpu_hotplug_enable();
- return error;
-}
-
/**
* __pci_device_probe - check if a driver wants to claim a specific PCI device
* @drv: driver to call to check if it wants the PCI device
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 864775651c6f..cbc0db2f2b84 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -481,7 +481,6 @@ struct pci_dev {
unsigned int io_window_1k:1; /* Intel bridge 1K I/O windows */
unsigned int irq_managed:1;
unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */
- unsigned int is_probed:1; /* Device probing in progress */
unsigned int link_active_reporting:1;/* Device capable of reporting link active */
unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */
unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */
--
2.20.1
Powered by blists - more mailing lists