[PATCH] pci: Store more data about VFs into the SRIOV struct

From: KarimAllah Ahmed
Date: Wed Jan 17 2018 - 12:44:59 EST


... to avoid reading them from the config space of all the PCI VFs. This is
specially a useful optimization when bringing up thousands of VFs.

Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Cc: linux-pci@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: KarimAllah Ahmed <karahmed@xxxxxxxxx>
---
drivers/pci/iov.c | 20 ++++++++++++++++++--
drivers/pci/pci.h | 6 +++++-
drivers/pci/probe.c | 42 ++++++++++++++++++++++++++++++++----------
3 files changed, 55 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 168328a..78e9595 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -129,7 +129,7 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
if (!dev->is_physfn)
return 0;

- return dev->sriov->barsz[resno - PCI_IOV_RESOURCES];
+ return dev->sriov->vf_barsz[resno - PCI_IOV_RESOURCES];
}

int batch_pci_iov_add_virtfn(struct pci_dev *dev, struct pci_bus **bus,
@@ -325,6 +325,20 @@ static void pci_iov_wq_fn(struct work_struct *work)
kfree(req);
}

+static void pci_read_vf_config_common(struct pci_bus *bus,
+ struct pci_dev *dev)
+{
+ int devfn = pci_iov_virtfn_devfn(dev, 0);
+
+ pci_bus_read_config_dword(bus, devfn, PCI_CLASS_REVISION,
+ &dev->sriov->vf_class);
+ pci_bus_read_config_word(bus, devfn, PCI_SUBSYSTEM_ID,
+ &dev->sriov->vf_subsystem_device);
+ pci_bus_read_config_word(bus, devfn, PCI_SUBSYSTEM_VENDOR_ID,
+ &dev->sriov->vf_subsystem_vendor);
+ pci_bus_read_config_byte(bus, devfn, PCI_HEADER_TYPE, &dev->sriov->vf_hdr_type);
+}
+
static struct workqueue_struct *pci_iov_wq;

static int __init init_pci_iov_wq(void)
@@ -361,6 +375,8 @@ static int enable_vfs(struct pci_dev *dev, int nr_vfs)
goto add_bus_fail;
}

+ pci_read_vf_config_common(bus[0], dev);
+
while (remaining_vfs > 0) {
bool ret;
struct pci_iov_wq_item *req;
@@ -617,7 +633,7 @@ static int sriov_init(struct pci_dev *dev, int pos)
rc = -EIO;
goto failed;
}
- iov->barsz[i] = resource_size(res);
+ iov->vf_barsz[i] = resource_size(res);
res->end = res->start + resource_size(res) * total - 1;
dev_info(&dev->dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n",
i, res, i, total);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index f6b58b3..3264c9e 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -271,7 +271,11 @@ struct pci_sriov {
u16 driver_max_VFs; /* max num VFs driver supports */
struct pci_dev *dev; /* lowest numbered PF */
struct pci_dev *self; /* this PF */
- resource_size_t barsz[PCI_SRIOV_NUM_BARS]; /* VF BAR size */
+ u8 vf_hdr_type; /* VF header type */
+ u32 vf_class; /* VF device */
+ u16 vf_subsystem_vendor; /* VF subsystem vendor */
+ u16 vf_subsystem_device; /* VF subsystem device */
+ resource_size_t vf_barsz[PCI_SRIOV_NUM_BARS]; /* VF BAR size */
bool drivers_autoprobe; /* auto probing of VFs by driver */
};

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 14e0ea1..65099d0 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -175,6 +175,7 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar)
int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
struct resource *res, unsigned int pos)
{
+ int bar = res - dev->resource;
u32 l = 0, sz = 0, mask;
u64 l64, sz64, mask64;
u16 orig_cmd;
@@ -194,9 +195,13 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
res->name = pci_name(dev);

pci_read_config_dword(dev, pos, &l);
- pci_write_config_dword(dev, pos, l | mask);
- pci_read_config_dword(dev, pos, &sz);
- pci_write_config_dword(dev, pos, l);
+ if (dev->is_virtfn) {
+ sz = dev->physfn->sriov->vf_barsz[bar] & 0xffffffff;
+ } else {
+ pci_write_config_dword(dev, pos, l | mask);
+ pci_read_config_dword(dev, pos, &sz);
+ pci_write_config_dword(dev, pos, l);
+ }

/*
* All bits set in sz means the device isn't working properly.
@@ -236,9 +241,14 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,

if (res->flags & IORESOURCE_MEM_64) {
pci_read_config_dword(dev, pos + 4, &l);
- pci_write_config_dword(dev, pos + 4, ~0);
- pci_read_config_dword(dev, pos + 4, &sz);
- pci_write_config_dword(dev, pos + 4, l);
+
+ if (dev->is_virtfn) {
+ sz = (dev->physfn->sriov->vf_barsz[bar] >> 32) & 0xffffffff;
+ } else {
+ pci_write_config_dword(dev, pos + 4, ~0);
+ pci_read_config_dword(dev, pos + 4, &sz);
+ pci_write_config_dword(dev, pos + 4, l);
+ }

l64 |= ((u64)l << 32);
sz64 |= ((u64)sz << 32);
@@ -327,6 +337,8 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
for (pos = 0; pos < howmany; pos++) {
struct resource *res = &dev->resource[pos];
reg = PCI_BASE_ADDRESS_0 + (pos << 2);
+ if (dev->is_virtfn && dev->physfn->sriov->vf_barsz[pos] == 0)
+ continue;
pos += __pci_read_base(dev, pci_bar_unknown, res, reg);
}

@@ -1444,7 +1456,9 @@ int pci_setup_device(struct pci_dev *dev)
struct pci_bus_region region;
struct resource *res;

- if (pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type))
+ if (dev->is_virtfn)
+ hdr_type = dev->physfn->sriov->vf_hdr_type;
+ else if (pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type))
return -EIO;

dev->sysdata = dev->bus->sysdata;
@@ -1464,7 +1478,10 @@ int pci_setup_device(struct pci_dev *dev)
dev->bus->number, PCI_SLOT(dev->devfn),
PCI_FUNC(dev->devfn));

- pci_read_config_dword(dev, PCI_CLASS_REVISION, &class);
+ if (dev->is_virtfn)
+ class = dev->physfn->sriov->vf_class;
+ else
+ pci_read_config_dword(dev, PCI_CLASS_REVISION, &class);
dev->revision = class & 0xff;
dev->class = class >> 8; /* upper 3 bytes */

@@ -1503,8 +1520,13 @@ int pci_setup_device(struct pci_dev *dev)
goto bad;
pci_read_irq(dev);
pci_read_bases(dev, 6, PCI_ROM_ADDRESS);
- pci_read_config_word(dev, PCI_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
- pci_read_config_word(dev, PCI_SUBSYSTEM_ID, &dev->subsystem_device);
+ if (dev->is_virtfn) {
+ dev->subsystem_vendor = dev->physfn->sriov->vf_subsystem_vendor;
+ dev->subsystem_device = dev->physfn->sriov->vf_subsystem_device;
+ } else {
+ pci_read_config_word(dev, PCI_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
+ pci_read_config_word(dev, PCI_SUBSYSTEM_ID, &dev->subsystem_device);
+ }

/*
* Do the ugly legacy mode stuff here rather than broken chip
--
2.7.4