1
0
Files
Greg Kroah-Hartman 14cea4ffd7 Merge 4.9.215 into android-4.9-q
Changes in 4.9.215
	x86/vdso: Use RDPID in preference to LSL when available
	KVM: x86: emulate RDPID
	ALSA: hda: Use scnprintf() for printing texts for sysfs/procfs
	ecryptfs: fix a memory leak bug in parse_tag_1_packet()
	ecryptfs: fix a memory leak bug in ecryptfs_init_messaging()
	ALSA: usb-audio: Apply sample rate quirk for Audioengine D1
	ext4: don't assume that mmp_nodename/bdevname have NUL
	ext4: fix checksum errors with indexed dirs
	ext4: improve explanation of a mount failure caused by a misconfigured kernel
	Btrfs: fix race between using extent maps and merging them
	btrfs: log message when rw remount is attempted with unclean tree-log
	perf/x86/amd: Add missing L2 misses event spec to AMD Family 17h's event map
	padata: Remove broken queue flushing
	s390/time: Fix clk type in get_tod_clock
	perf/x86/intel: Fix inaccurate period in context switch for auto-reload
	hwmon: (pmbus/ltc2978) Fix PMBus polling of MFR_COMMON definitions.
	jbd2: move the clearing of b_modified flag to the journal_unmap_buffer()
	jbd2: do not clear the BH_Mapped flag when forgetting a metadata buffer
	btrfs: print message when tree-log replay starts
	scsi: qla2xxx: fix a potential NULL pointer dereference
	Revert "KVM: VMX: Add non-canonical check on writes to RTIT address MSRs"
	drm/gma500: Fixup fbdev stolen size usage evaluation
	cpu/hotplug, stop_machine: Fix stop_machine vs hotplug order
	brcmfmac: Fix use after free in brcmf_sdio_readframes()
	gianfar: Fix TX timestamping with a stacked DSA driver
	pinctrl: sh-pfc: sh7264: Fix CAN function GPIOs
	pxa168fb: Fix the function used to release some memory in an error handling path
	media: i2c: mt9v032: fix enum mbus codes and frame sizes
	powerpc/powernv/iov: Ensure the pdn for VFs always contains a valid PE number
	gpio: gpio-grgpio: fix possible sleep-in-atomic-context bugs in grgpio_irq_map/unmap()
	media: sti: bdisp: fix a possible sleep-in-atomic-context bug in bdisp_device_run()
	pinctrl: baytrail: Do not clear IRQ flags on direct-irq enabled pins
	efi/x86: Map the entire EFI vendor string before copying it
	MIPS: Loongson: Fix potential NULL dereference in loongson3_platform_init()
	sparc: Add .exit.data section.
	uio: fix a sleep-in-atomic-context bug in uio_dmem_genirq_irqcontrol()
	usb: gadget: udc: fix possible sleep-in-atomic-context bugs in gr_probe()
	jbd2: clear JBD2_ABORT flag before journal_reset to update log tail info when load journal
	x86/sysfb: Fix check for bad VRAM size
	tracing: Fix tracing_stat return values in error handling paths
	tracing: Fix very unlikely race of registering two stat tracers
	ext4, jbd2: ensure panic when aborting with zero errno
	kconfig: fix broken dependency in randconfig-generated .config
	clk: qcom: rcg2: Don't crash if our parent can't be found; return an error
	drm/amdgpu: remove 4 set but not used variable in amdgpu_atombios_get_connector_info_from_object_table
	regulator: rk808: Lower log level on optional GPIOs being not available
	net/wan/fsl_ucc_hdlc: reject muram offsets above 64K
	PCI/IOV: Fix memory leak in pci_iov_add_virtfn()
	NFC: port100: Convert cpu_to_le16(le16_to_cpu(E1) + E2) to use le16_add_cpu().
	media: v4l2-device.h: Explicitly compare grp{id,mask} to zero in v4l2_device macros
	reiserfs: Fix spurious unlock in reiserfs_fill_super() error handling
	ALSA: usx2y: Adjust indentation in snd_usX2Y_hwdep_dsp_status
	b43legacy: Fix -Wcast-function-type
	ipw2x00: Fix -Wcast-function-type
	iwlegacy: Fix -Wcast-function-type
	rtlwifi: rtl_pci: Fix -Wcast-function-type
	orinoco: avoid assertion in case of NULL pointer
	ACPICA: Disassembler: create buffer fields in ACPI_PARSE_LOAD_PASS1
	scsi: aic7xxx: Adjust indentation in ahc_find_syncrate
	drm/mediatek: handle events when enabling/disabling crtc
	ARM: dts: r8a7779: Add device node for ARM global timer
	x86/vdso: Provide missing include file
	PM / devfreq: rk3399_dmc: Add COMPILE_TEST and HAVE_ARM_SMCCC dependency
	pinctrl: sh-pfc: sh7269: Fix CAN function GPIOs
	RDMA/rxe: Fix error type of mmap_offset
	ALSA: sh: Fix compile warning wrt const
	tools lib api fs: Fix gcc9 stringop-truncation compilation error
	usbip: Fix unsafe unaligned pointer usage
	udf: Fix free space reporting for metadata and virtual partitions
	soc/tegra: fuse: Correct straps' address for older Tegra124 device trees
	rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls
	Input: edt-ft5x06 - work around first register access error
	wan: ixp4xx_hss: fix compile-testing on 64-bit
	ASoC: atmel: fix build error with CONFIG_SND_ATMEL_SOC_DMA=m
	tty: synclinkmp: Adjust indentation in several functions
	tty: synclink_gt: Adjust indentation in several functions
	driver core: platform: Prevent resouce overflow from causing infinite loops
	driver core: Print device when resources present in really_probe()
	vme: bridges: reduce stack usage
	drm/nouveau/gr/gk20a,gm200-: add terminators to method lists read from fw
	drm/nouveau: Fix copy-paste error in nouveau_fence_wait_uevent_handler
	drm/vmwgfx: prevent memory leak in vmw_cmdbuf_res_add
	usb: musb: omap2430: Get rid of musb .set_vbus for omap2430 glue
	iommu/arm-smmu-v3: Use WRITE_ONCE() when changing validity of an STE
	scsi: iscsi: Don't destroy session if there are outstanding connections
	arm64: fix alternatives with LLVM's integrated assembler
	pwm: omap-dmtimer: Remove PWM chip in .remove before making it unfunctional
	cmd64x: potential buffer overflow in cmd64x_program_timings()
	ide: serverworks: potential overflow in svwks_set_pio_mode()
	remoteproc: Initialize rproc_class before use
	x86/decoder: Add TEST opcode to Group3-2
	s390/ftrace: generate traced function stack frame
	driver core: platform: fix u32 greater or equal to zero comparison
	ALSA: hda - Add docking station support for Lenovo Thinkpad T420s
	powerpc/sriov: Remove VF eeh_dev state when disabling SR-IOV
	jbd2: switch to use jbd2_journal_abort() when failed to submit the commit record
	ARM: 8951/1: Fix Kexec compilation issue.
	hostap: Adjust indentation in prism2_hostapd_add_sta
	iwlegacy: ensure loop counter addr does not wrap and cause an infinite loop
	cifs: fix NULL dereference in match_prepath
	irqchip/gic-v3: Only provision redistributors that are enabled in ACPI
	drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
	ftrace: fpid_next() should increase position index
	trigger_next should increase position index
	radeon: insert 10ms sleep in dce5_crtc_load_lut
	ocfs2: fix a NULL pointer dereference when call ocfs2_update_inode_fsync_trans()
	lib/scatterlist.c: adjust indentation in __sg_alloc_table
	reiserfs: prevent NULL pointer dereference in reiserfs_insert_item()
	bcache: explicity type cast in bset_bkey_last()
	irqchip/gic-v3-its: Reference to its_invall_cmd descriptor when building INVALL
	iwlwifi: mvm: Fix thermal zone registration
	microblaze: Prevent the overflow of the start
	brd: check and limit max_part par
	help_next should increase position index
	selinux: ensure we cleanup the internal AVC counters on error in avc_update()
	enic: prevent waking up stopped tx queues over watchdog reset
	net/sched: matchall: add missing validation of TCA_MATCHALL_FLAGS
	net/sched: flower: add missing validation of TCA_FLOWER_FLAGS
	floppy: check FDC index for errors before assigning it
	vt: selection, handle pending signals in paste_selection
	staging: android: ashmem: Disallow ashmem memory from being remapped
	staging: vt6656: fix sign of rx_dbm to bb_pre_ed_rssi.
	xhci: Force Maximum Packet size for Full-speed bulk devices to valid range.
	usb: uas: fix a plug & unplug racing
	USB: Fix novation SourceControl XL after suspend
	USB: hub: Don't record a connect-change event during reset-resume
	staging: rtl8188eu: Fix potential security hole
	staging: rtl8188eu: Fix potential overuse of kernel memory
	x86/mce/amd: Publish the bank pointer only after setup has succeeded
	x86/mce/amd: Fix kobject lifetime
	tty/serial: atmel: manage shutdown in case of RS485 or ISO7816 mode
	tty: serial: imx: setup the correct sg entry for tx dma
	Revert "ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()"
	xhci: apply XHCI_PME_STUCK_QUIRK to Intel Comet Lake platforms
	KVM: x86: don't notify userspace IOAPIC on edge-triggered interrupt EOI
	VT_RESIZEX: get rid of field-by-field copyin
	vt: vt_ioctl: fix race in VT_RESIZEX
	lib/stackdepot.c: fix global out-of-bounds in stack_slabs
	KVM: nVMX: Don't emulate instructions in guest mode
	netfilter: xt_bpf: add overflow checks
	ext4: fix a data race in EXT4_I(inode)->i_disksize
	ext4: add cond_resched() to __ext4_find_entry()
	ext4: fix mount failure with quota configured as module
	ext4: rename s_journal_flag_rwsem to s_writepages_rwsem
	ext4: fix race between writepages and enabling EXT4_EXTENTS_FL
	KVM: nVMX: Refactor IO bitmap checks into helper function
	KVM: nVMX: Check IO instruction VM-exit conditions
	KVM: apic: avoid calculating pending eoi from an uninitialized val
	Btrfs: fix btrfs_wait_ordered_range() so that it waits for all ordered extents
	scsi: Revert "RDMA/isert: Fix a recently introduced regression related to logout"
	scsi: Revert "target: iscsi: Wait for all commands to finish before freeing a session"
	usb: gadget: composite: Fix bMaxPower for SuperSpeedPlus
	staging: greybus: use after free in gb_audio_manager_remove_all()
	ecryptfs: replace BUG_ON with error handling code
	ALSA: rawmidi: Avoid bit fields for state flags
	ALSA: seq: Avoid concurrent access to queue flags
	ALSA: seq: Fix concurrent access to queue current tick/time
	netfilter: xt_hashlimit: limit the max size of hashtable
	ata: ahci: Add shutdown to freeze hardware resources of ahci
	xen: Enable interrupts when calling _cond_resched()
	s390/mm: Explicitly compare PAGE_DEFAULT_KEY against zero in storage_key_init_range
	Linux 4.9.215

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I4c663321dde48cd2a324e59acb70c99f75f9344e
2020-03-02 17:01:42 +03:00

807 lines
19 KiB
C

/*
* drivers/pci/iov.c
*
* Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com>
*
* PCI Express I/O Virtualization (IOV) support.
* Single Root IOV 1.0
* Address Translation Service 1.0
*/
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/export.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/pci-ats.h>
#include "pci.h"
#define VIRTFN_ID_LEN 16
int pci_iov_virtfn_bus(struct pci_dev *dev, int vf_id)
{
if (!dev->is_physfn)
return -EINVAL;
return dev->bus->number + ((dev->devfn + dev->sriov->offset +
dev->sriov->stride * vf_id) >> 8);
}
int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id)
{
if (!dev->is_physfn)
return -EINVAL;
return (dev->devfn + dev->sriov->offset +
dev->sriov->stride * vf_id) & 0xff;
}
/*
* Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may
* change when NumVFs changes.
*
* Update iov->offset and iov->stride when NumVFs is written.
*/
static inline void pci_iov_set_numvfs(struct pci_dev *dev, int nr_virtfn)
{
struct pci_sriov *iov = dev->sriov;
pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, nr_virtfn);
pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_OFFSET, &iov->offset);
pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_STRIDE, &iov->stride);
}
/*
* The PF consumes one bus number. NumVFs, First VF Offset, and VF Stride
* determine how many additional bus numbers will be consumed by VFs.
*
* Iterate over all valid NumVFs, validate offset and stride, and calculate
* the maximum number of bus numbers that could ever be required.
*/
static int compute_max_vf_buses(struct pci_dev *dev)
{
struct pci_sriov *iov = dev->sriov;
int nr_virtfn, busnr, rc = 0;
for (nr_virtfn = iov->total_VFs; nr_virtfn; nr_virtfn--) {
pci_iov_set_numvfs(dev, nr_virtfn);
if (!iov->offset || (nr_virtfn > 1 && !iov->stride)) {
rc = -EIO;
goto out;
}
busnr = pci_iov_virtfn_bus(dev, nr_virtfn - 1);
if (busnr > iov->max_VF_buses)
iov->max_VF_buses = busnr;
}
out:
pci_iov_set_numvfs(dev, 0);
return rc;
}
static struct pci_bus *virtfn_add_bus(struct pci_bus *bus, int busnr)
{
struct pci_bus *child;
if (bus->number == busnr)
return bus;
child = pci_find_bus(pci_domain_nr(bus), busnr);
if (child)
return child;
child = pci_add_new_bus(bus, NULL, busnr);
if (!child)
return NULL;
pci_bus_insert_busn_res(child, busnr, busnr);
return child;
}
static void virtfn_remove_bus(struct pci_bus *physbus, struct pci_bus *virtbus)
{
if (physbus != virtbus && list_empty(&virtbus->devices))
pci_remove_bus(virtbus);
}
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];
}
int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
{
int i;
int rc = -ENOMEM;
u64 size;
char buf[VIRTFN_ID_LEN];
struct pci_dev *virtfn;
struct resource *res;
struct pci_sriov *iov = dev->sriov;
struct pci_bus *bus;
mutex_lock(&iov->dev->sriov->lock);
bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id));
if (!bus)
goto failed;
virtfn = pci_alloc_dev(bus);
if (!virtfn)
goto failed0;
virtfn->devfn = pci_iov_virtfn_devfn(dev, id);
virtfn->vendor = dev->vendor;
pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device);
rc = pci_setup_device(virtfn);
if (rc)
goto failed0;
virtfn->dev.parent = dev->dev.parent;
virtfn->physfn = pci_dev_get(dev);
virtfn->is_virtfn = 1;
virtfn->multifunction = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &dev->resource[i + PCI_IOV_RESOURCES];
if (!res->parent)
continue;
virtfn->resource[i].name = pci_name(virtfn);
virtfn->resource[i].flags = res->flags;
size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
virtfn->resource[i].start = res->start + size * id;
virtfn->resource[i].end = virtfn->resource[i].start + size - 1;
rc = request_resource(res, &virtfn->resource[i]);
BUG_ON(rc);
}
if (reset)
__pci_reset_function(virtfn);
pci_device_add(virtfn, virtfn->bus);
mutex_unlock(&iov->dev->sriov->lock);
sprintf(buf, "virtfn%u", id);
rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
if (rc)
goto failed1;
rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn");
if (rc)
goto failed2;
kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
pci_bus_add_device(virtfn);
return 0;
failed2:
sysfs_remove_link(&dev->dev.kobj, buf);
failed1:
pci_stop_and_remove_bus_device(virtfn);
pci_dev_put(dev);
mutex_lock(&iov->dev->sriov->lock);
pci_stop_and_remove_bus_device(virtfn);
failed0:
virtfn_remove_bus(dev->bus, bus);
failed:
mutex_unlock(&iov->dev->sriov->lock);
return rc;
}
void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset)
{
char buf[VIRTFN_ID_LEN];
struct pci_dev *virtfn;
struct pci_sriov *iov = dev->sriov;
virtfn = pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
pci_iov_virtfn_bus(dev, id),
pci_iov_virtfn_devfn(dev, id));
if (!virtfn)
return;
if (reset) {
device_release_driver(&virtfn->dev);
__pci_reset_function(virtfn);
}
sprintf(buf, "virtfn%u", id);
sysfs_remove_link(&dev->dev.kobj, buf);
/*
* pci_stop_dev() could have been called for this virtfn already,
* so the directory for the virtfn may have been removed before.
* Double check to avoid spurious sysfs warnings.
*/
if (virtfn->dev.kobj.sd)
sysfs_remove_link(&virtfn->dev.kobj, "physfn");
mutex_lock(&iov->dev->sriov->lock);
pci_stop_and_remove_bus_device(virtfn);
virtfn_remove_bus(dev->bus, virtfn->bus);
mutex_unlock(&iov->dev->sriov->lock);
/* balance pci_get_domain_bus_and_slot() */
pci_dev_put(virtfn);
pci_dev_put(dev);
}
int __weak pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
{
return 0;
}
int __weak pcibios_sriov_disable(struct pci_dev *pdev)
{
return 0;
}
static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
{
int rc;
int i;
int nres;
u16 initial;
struct resource *res;
struct pci_dev *pdev;
struct pci_sriov *iov = dev->sriov;
int bars = 0;
int bus;
if (!nr_virtfn)
return 0;
if (iov->num_VFs)
return -EINVAL;
pci_read_config_word(dev, iov->pos + PCI_SRIOV_INITIAL_VF, &initial);
if (initial > iov->total_VFs ||
(!(iov->cap & PCI_SRIOV_CAP_VFM) && (initial != iov->total_VFs)))
return -EIO;
if (nr_virtfn < 0 || nr_virtfn > iov->total_VFs ||
(!(iov->cap & PCI_SRIOV_CAP_VFM) && (nr_virtfn > initial)))
return -EINVAL;
nres = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
bars |= (1 << (i + PCI_IOV_RESOURCES));
res = &dev->resource[i + PCI_IOV_RESOURCES];
if (res->parent)
nres++;
}
if (nres != iov->nres) {
dev_err(&dev->dev, "not enough MMIO resources for SR-IOV\n");
return -ENOMEM;
}
bus = pci_iov_virtfn_bus(dev, nr_virtfn - 1);
if (bus > dev->bus->busn_res.end) {
dev_err(&dev->dev, "can't enable %d VFs (bus %02x out of range of %pR)\n",
nr_virtfn, bus, &dev->bus->busn_res);
return -ENOMEM;
}
if (pci_enable_resources(dev, bars)) {
dev_err(&dev->dev, "SR-IOV: IOV BARS not allocated\n");
return -ENOMEM;
}
if (iov->link != dev->devfn) {
pdev = pci_get_slot(dev->bus, iov->link);
if (!pdev)
return -ENODEV;
if (!pdev->is_physfn) {
pci_dev_put(pdev);
return -ENOSYS;
}
rc = sysfs_create_link(&dev->dev.kobj,
&pdev->dev.kobj, "dep_link");
pci_dev_put(pdev);
if (rc)
return rc;
}
iov->initial_VFs = initial;
if (nr_virtfn < initial)
initial = nr_virtfn;
rc = pcibios_sriov_enable(dev, initial);
if (rc) {
dev_err(&dev->dev, "failure %d from pcibios_sriov_enable()\n", rc);
goto err_pcibios;
}
pci_iov_set_numvfs(dev, nr_virtfn);
iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
pci_cfg_access_lock(dev);
pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
msleep(100);
pci_cfg_access_unlock(dev);
for (i = 0; i < initial; i++) {
rc = pci_iov_add_virtfn(dev, i, 0);
if (rc)
goto failed;
}
kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE);
iov->num_VFs = nr_virtfn;
return 0;
failed:
while (i--)
pci_iov_remove_virtfn(dev, i, 0);
pcibios_sriov_disable(dev);
err_pcibios:
iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
pci_cfg_access_lock(dev);
pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
ssleep(1);
pci_cfg_access_unlock(dev);
if (iov->link != dev->devfn)
sysfs_remove_link(&dev->dev.kobj, "dep_link");
pci_iov_set_numvfs(dev, 0);
return rc;
}
static void sriov_disable(struct pci_dev *dev)
{
int i;
struct pci_sriov *iov = dev->sriov;
if (!iov->num_VFs)
return;
for (i = 0; i < iov->num_VFs; i++)
pci_iov_remove_virtfn(dev, i, 0);
pcibios_sriov_disable(dev);
iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
pci_cfg_access_lock(dev);
pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
ssleep(1);
pci_cfg_access_unlock(dev);
if (iov->link != dev->devfn)
sysfs_remove_link(&dev->dev.kobj, "dep_link");
iov->num_VFs = 0;
pci_iov_set_numvfs(dev, 0);
}
static int sriov_init(struct pci_dev *dev, int pos)
{
int i, bar64;
int rc;
int nres;
u32 pgsz;
u16 ctrl, total;
struct pci_sriov *iov;
struct resource *res;
struct pci_dev *pdev;
pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
if (ctrl & PCI_SRIOV_CTRL_VFE) {
pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, 0);
ssleep(1);
}
ctrl = 0;
list_for_each_entry(pdev, &dev->bus->devices, bus_list)
if (pdev->is_physfn)
goto found;
pdev = NULL;
if (pci_ari_enabled(dev->bus))
ctrl |= PCI_SRIOV_CTRL_ARI;
found:
pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, ctrl);
pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total);
if (!total)
return 0;
pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &pgsz);
i = PAGE_SHIFT > 12 ? PAGE_SHIFT - 12 : 0;
pgsz &= ~((1 << i) - 1);
if (!pgsz)
return -EIO;
pgsz &= ~(pgsz - 1);
pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz);
iov = kzalloc(sizeof(*iov), GFP_KERNEL);
if (!iov)
return -ENOMEM;
nres = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &dev->resource[i + PCI_IOV_RESOURCES];
/*
* If it is already FIXED, don't change it, something
* (perhaps EA or header fixups) wants it this way.
*/
if (res->flags & IORESOURCE_PCI_FIXED)
bar64 = (res->flags & IORESOURCE_MEM_64) ? 1 : 0;
else
bar64 = __pci_read_base(dev, pci_bar_unknown, res,
pos + PCI_SRIOV_BAR + i * 4);
if (!res->flags)
continue;
if (resource_size(res) & (PAGE_SIZE - 1)) {
rc = -EIO;
goto failed;
}
iov->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);
i += bar64;
nres++;
}
iov->pos = pos;
iov->nres = nres;
iov->ctrl = ctrl;
iov->total_VFs = total;
iov->pgsz = pgsz;
iov->self = dev;
pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)
iov->link = PCI_DEVFN(PCI_SLOT(dev->devfn), iov->link);
if (pdev)
iov->dev = pci_dev_get(pdev);
else
iov->dev = dev;
mutex_init(&iov->lock);
dev->sriov = iov;
dev->is_physfn = 1;
rc = compute_max_vf_buses(dev);
if (rc)
goto fail_max_buses;
return 0;
fail_max_buses:
dev->sriov = NULL;
dev->is_physfn = 0;
failed:
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &dev->resource[i + PCI_IOV_RESOURCES];
res->flags = 0;
}
kfree(iov);
return rc;
}
static void sriov_release(struct pci_dev *dev)
{
BUG_ON(dev->sriov->num_VFs);
if (dev != dev->sriov->dev)
pci_dev_put(dev->sriov->dev);
mutex_destroy(&dev->sriov->lock);
kfree(dev->sriov);
dev->sriov = NULL;
}
static void sriov_restore_state(struct pci_dev *dev)
{
int i;
u16 ctrl;
struct pci_sriov *iov = dev->sriov;
pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &ctrl);
if (ctrl & PCI_SRIOV_CTRL_VFE)
return;
for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++)
pci_update_resource(dev, i);
pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz);
pci_iov_set_numvfs(dev, iov->num_VFs);
pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
if (iov->ctrl & PCI_SRIOV_CTRL_VFE)
msleep(100);
}
/**
* pci_iov_init - initialize the IOV capability
* @dev: the PCI device
*
* Returns 0 on success, or negative on failure.
*/
int pci_iov_init(struct pci_dev *dev)
{
int pos;
if (!pci_is_pcie(dev))
return -ENODEV;
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
if (pos)
return sriov_init(dev, pos);
return -ENODEV;
}
/**
* pci_iov_release - release resources used by the IOV capability
* @dev: the PCI device
*/
void pci_iov_release(struct pci_dev *dev)
{
if (dev->is_physfn)
sriov_release(dev);
}
/**
* pci_iov_update_resource - update a VF BAR
* @dev: the PCI device
* @resno: the resource number
*
* Update a VF BAR in the SR-IOV capability of a PF.
*/
void pci_iov_update_resource(struct pci_dev *dev, int resno)
{
struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL;
struct resource *res = dev->resource + resno;
int vf_bar = resno - PCI_IOV_RESOURCES;
struct pci_bus_region region;
u16 cmd;
u32 new;
int reg;
/*
* The generic pci_restore_bars() path calls this for all devices,
* including VFs and non-SR-IOV devices. If this is not a PF, we
* have nothing to do.
*/
if (!iov)
return;
pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &cmd);
if ((cmd & PCI_SRIOV_CTRL_VFE) && (cmd & PCI_SRIOV_CTRL_MSE)) {
dev_WARN(&dev->dev, "can't update enabled VF BAR%d %pR\n",
vf_bar, res);
return;
}
/*
* Ignore unimplemented BARs, unused resource slots for 64-bit
* BARs, and non-movable resources, e.g., those described via
* Enhanced Allocation.
*/
if (!res->flags)
return;
if (res->flags & IORESOURCE_UNSET)
return;
if (res->flags & IORESOURCE_PCI_FIXED)
return;
pcibios_resource_to_bus(dev->bus, &region, res);
new = region.start;
new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK;
reg = iov->pos + PCI_SRIOV_BAR + 4 * vf_bar;
pci_write_config_dword(dev, reg, new);
if (res->flags & IORESOURCE_MEM_64) {
new = region.start >> 16 >> 16;
pci_write_config_dword(dev, reg + 4, new);
}
}
resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev,
int resno)
{
return pci_iov_resource_size(dev, resno);
}
/**
* pci_sriov_resource_alignment - get resource alignment for VF BAR
* @dev: the PCI device
* @resno: the resource number
*
* Returns the alignment of the VF BAR found in the SR-IOV capability.
* This is not the same as the resource size which is defined as
* the VF BAR size multiplied by the number of VFs. The alignment
* is just the VF BAR size.
*/
resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
{
return pcibios_iov_resource_alignment(dev, resno);
}
/**
* pci_restore_iov_state - restore the state of the IOV capability
* @dev: the PCI device
*/
void pci_restore_iov_state(struct pci_dev *dev)
{
if (dev->is_physfn)
sriov_restore_state(dev);
}
/**
* pci_iov_bus_range - find bus range used by Virtual Function
* @bus: the PCI bus
*
* Returns max number of buses (exclude current one) used by Virtual
* Functions.
*/
int pci_iov_bus_range(struct pci_bus *bus)
{
int max = 0;
struct pci_dev *dev;
list_for_each_entry(dev, &bus->devices, bus_list) {
if (!dev->is_physfn)
continue;
if (dev->sriov->max_VF_buses > max)
max = dev->sriov->max_VF_buses;
}
return max ? max - bus->number : 0;
}
/**
* pci_enable_sriov - enable the SR-IOV capability
* @dev: the PCI device
* @nr_virtfn: number of virtual functions to enable
*
* Returns 0 on success, or negative on failure.
*/
int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
{
might_sleep();
if (!dev->is_physfn)
return -ENOSYS;
return sriov_enable(dev, nr_virtfn);
}
EXPORT_SYMBOL_GPL(pci_enable_sriov);
/**
* pci_disable_sriov - disable the SR-IOV capability
* @dev: the PCI device
*/
void pci_disable_sriov(struct pci_dev *dev)
{
might_sleep();
if (!dev->is_physfn)
return;
sriov_disable(dev);
}
EXPORT_SYMBOL_GPL(pci_disable_sriov);
/**
* pci_num_vf - return number of VFs associated with a PF device_release_driver
* @dev: the PCI device
*
* Returns number of VFs, or 0 if SR-IOV is not enabled.
*/
int pci_num_vf(struct pci_dev *dev)
{
if (!dev->is_physfn)
return 0;
return dev->sriov->num_VFs;
}
EXPORT_SYMBOL_GPL(pci_num_vf);
/**
* pci_vfs_assigned - returns number of VFs are assigned to a guest
* @dev: the PCI device
*
* Returns number of VFs belonging to this device that are assigned to a guest.
* If device is not a physical function returns 0.
*/
int pci_vfs_assigned(struct pci_dev *dev)
{
struct pci_dev *vfdev;
unsigned int vfs_assigned = 0;
unsigned short dev_id;
/* only search if we are a PF */
if (!dev->is_physfn)
return 0;
/*
* determine the device ID for the VFs, the vendor ID will be the
* same as the PF so there is no need to check for that one
*/
pci_read_config_word(dev, dev->sriov->pos + PCI_SRIOV_VF_DID, &dev_id);
/* loop through all the VFs to see if we own any that are assigned */
vfdev = pci_get_device(dev->vendor, dev_id, NULL);
while (vfdev) {
/*
* It is considered assigned if it is a virtual function with
* our dev as the physical function and the assigned bit is set
*/
if (vfdev->is_virtfn && (vfdev->physfn == dev) &&
pci_is_dev_assigned(vfdev))
vfs_assigned++;
vfdev = pci_get_device(dev->vendor, dev_id, vfdev);
}
return vfs_assigned;
}
EXPORT_SYMBOL_GPL(pci_vfs_assigned);
/**
* pci_sriov_set_totalvfs -- reduce the TotalVFs available
* @dev: the PCI PF device
* @numvfs: number that should be used for TotalVFs supported
*
* Should be called from PF driver's probe routine with
* device's mutex held.
*
* Returns 0 if PF is an SRIOV-capable device and
* value of numvfs valid. If not a PF return -ENOSYS;
* if numvfs is invalid return -EINVAL;
* if VFs already enabled, return -EBUSY.
*/
int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
{
if (!dev->is_physfn)
return -ENOSYS;
if (numvfs > dev->sriov->total_VFs)
return -EINVAL;
/* Shouldn't change if VFs already enabled */
if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
return -EBUSY;
else
dev->sriov->driver_max_VFs = numvfs;
return 0;
}
EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
/**
* pci_sriov_get_totalvfs -- get total VFs supported on this device
* @dev: the PCI PF device
*
* For a PCIe device with SRIOV support, return the PCIe
* SRIOV capability value of TotalVFs or the value of driver_max_VFs
* if the driver reduced it. Otherwise 0.
*/
int pci_sriov_get_totalvfs(struct pci_dev *dev)
{
if (!dev->is_physfn)
return 0;
if (dev->sriov->driver_max_VFs)
return dev->sriov->driver_max_VFs;
return dev->sriov->total_VFs;
}
EXPORT_SYMBOL_GPL(pci_sriov_get_totalvfs);