From: Vikash Bansal <bvikas@xxxxxxxxxx>
In the current implementation, the PCI capability list is parsed from
the beginning to find each capability, which results in a large number
of redundant PCI reads.
Instead, we can parse the complete list just once, store it in the
pci_dev structure, and get the offset of each capability directly from
the pci_dev structure.
This implementation improves pci devices initialization time by ~2-3%
(from 270ms to 261ms) in case of bare metal and 7-8% (From 201ms to 184ms)
in case of VM running on ESXi.
It also adds a memory overhead of 20bytes (value of PCI_CAP_ID_MAX) per
PCI device.
Ran pahole for pci_dev structure. This patch is not adding any padding
bytes.
Signed-off-by: Vikash Bansal <bvikas@xxxxxxxxxx>
Signed-off-by: Ajay Kaher <akaher@xxxxxxxxxx>
---
Changes in v3:
- Added check before access cap_off from pci_find_capability().
- Moved declaration of pci_find_all_capabilities() to drivers/pci/pci.h.
Changes in v2:
- Ran pahole tool.
- Modified comments to add "clock time".
- Removed comments before call to pci_find_all_capabilities.
---
drivers/pci/pci.c | 44 +++++++++++++++++++++++++++++++++++++-------
drivers/pci/pci.h | 1 +
drivers/pci/probe.c | 1 +
include/linux/pci.h | 1 +
4 files changed, 40 insertions(+), 7 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 3d2fb39..cf54811 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -469,6 +469,40 @@ static u8 __pci_bus_find_cap_start(struct pci_bus *bus,
}
/**
+ * pci_find_all_capabilities - Read all capabilities
+ * @dev: the PCI device
+ *
+ * Read all capabilities and store offsets in cap_off
+ * array in pci_dev structure.
+ */
+void pci_find_all_capabilities(struct pci_dev *dev)
+{
+ int ttl = PCI_FIND_CAP_TTL;
+ u16 ent;
+ u8 pos;
+ u8 id;
+
+ pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
+ if (!pos)
+ return;
+ pci_bus_read_config_byte(dev->bus, dev->devfn, pos, &pos);
+ while (ttl--) {
+ if (pos < 0x40)
+ break;
+ pos &= ~3;
+ pci_bus_read_config_word(dev->bus, dev->devfn, pos, &ent);
+ id = ent & 0xff;
+ if (id == 0xff)
+ break;
+
+ /* Read first instance of capability */
+ if (!(dev->cap_off[id]))
+ dev->cap_off[id] = pos;
+ pos = (ent >> 8);
+ }
+}
+
+/**
* pci_find_capability - query for devices' capabilities
* @dev: PCI device to query
* @cap: capability code
@@ -489,13 +523,9 @@ static u8 __pci_bus_find_cap_start(struct pci_bus *bus,
*/
u8 pci_find_capability(struct pci_dev *dev, int cap)
{
- u8 pos;
-
- pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
- if (pos)
- pos = __pci_find_next_cap(dev->bus, dev->devfn, pos, cap);
-
- return pos;
+ if(cap >= PCI_CAP_ID_MAX)
+ return 0;
+ return dev->cap_off[cap];
}
EXPORT_SYMBOL(pci_find_capability);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 3d60cab..3cb70d5 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -87,6 +87,7 @@ bool pci_bridge_d3_possible(struct pci_dev *dev);
void pci_bridge_d3_update(struct pci_dev *dev);
void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev);
void pci_bridge_reconfigure_ltr(struct pci_dev *dev);
+void pci_find_all_capabilities(struct pci_dev *dev);
static inline void pci_wakeup_event(struct pci_dev *dev)
{
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 087d365..d75e1fa 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1839,6 +1839,7 @@ int pci_setup_device(struct pci_dev *dev)
dev->hdr_type = hdr_type & 0x7f;
dev->multifunction = !!(hdr_type & 0x80);
dev->error_state = pci_channel_io_normal;
+ pci_find_all_capabilities(dev);
set_pcie_port_type(dev);
pci_set_of_node(dev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 18a75c8..bd61cee 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -326,6 +326,7 @@ struct pci_dev {
unsigned int class; /* 3 bytes: (base,sub,prog-if) */
u8 revision; /* PCI revision, low byte of class word */
u8 hdr_type; /* PCI header type (`multi' flag masked out) */
+ u8 cap_off[PCI_CAP_ID_MAX]; /* Offsets of all pci capabilities */
#ifdef CONFIG_PCIEAER
u16 aer_cap; /* AER capability offset */
struct aer_stats *aer_stats; /* AER stats for this device */
--
2.7.4
