linux/arch/x86/pci/xen.c

577 lines
14 KiB
C
Raw Normal View History

/*
* Xen PCI - handle PCI (INTx) and MSI infrastructure calls for PV, HVM and
* initial domain support. We also handle the DSDT _PRT callbacks for GSI's
* used in HVM and initial domain mode (PV does not parse ACPI, so it has no
* concept of GSIs). Under PV we hook under the pnbbios API for IRQs and
* 0xcf8 PCI configuration read/write.
*
* Author: Ryan Wilson <hap9@epoch.ncsc.mil>
* Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
* Stefano Stabellini <stefano.stabellini@eu.citrix.com>
*/
x86: Audit and remove any remaining unnecessary uses of module.h Historically a lot of these existed because we did not have a distinction between what was modular code and what was providing support to modules via EXPORT_SYMBOL and friends. That changed when we forked out support for the latter into the export.h file. This means we should be able to reduce the usage of module.h in code that is obj-y Makefile or bool Kconfig. In the case of some of these which are modular, we can extend that to also include files that are building basic support functionality but not related to loading or registering the final module; such files also have no need whatsoever for module.h The advantage in removing such instances is that module.h itself sources about 15 other headers; adding significantly to what we feed cpp, and it can obscure what headers we are effectively using. Since module.h was the source for init.h (for __init) and for export.h (for EXPORT_SYMBOL) we consider each instance for the presence of either and replace as needed. In the case of crypto/glue_helper.c we delete a redundant instance of MODULE_LICENSE in order to delete module.h -- the license info is already present at the top of the file. The uncore change warrants a mention too; it is uncore.c that uses module.h and not uncore.h; hence the relocation done there. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20160714001901.31603-9-paul.gortmaker@windriver.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-14 08:19:01 +08:00
#include <linux/export.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <asm/io_apic.h>
#include <asm/pci_x86.h>
#include <asm/xen/hypervisor.h>
#include <xen/features.h>
#include <xen/events.h>
#include <asm/xen/pci.h>
#include <asm/xen/cpuid.h>
#include <asm/apic.h>
#include <asm/i8259.h>
static int xen_pcifront_enable_irq(struct pci_dev *dev)
{
int rc;
int share = 1;
int pirq;
u8 gsi;
rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
if (rc < 0) {
dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
rc);
return rc;
}
/* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
pirq = gsi;
if (gsi < nr_legacy_irqs())
share = 0;
rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront");
if (rc < 0) {
dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n",
gsi, pirq, rc);
return rc;
}
dev->irq = rc;
dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq);
return 0;
}
#ifdef CONFIG_ACPI
static int xen_register_pirq(u32 gsi, int gsi_override, int triggering,
bool set_pirq)
{
int rc, pirq = -1, irq = -1;
struct physdev_map_pirq map_irq;
int shareable = 0;
char *name;
irq = xen_irq_from_gsi(gsi);
if (irq > 0)
return irq;
if (set_pirq)
pirq = gsi;
map_irq.domid = DOMID_SELF;
map_irq.type = MAP_PIRQ_TYPE_GSI;
map_irq.index = gsi;
map_irq.pirq = pirq;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
if (rc) {
printk(KERN_WARNING "xen map irq failed %d\n", rc);
return -1;
}
if (triggering == ACPI_EDGE_SENSITIVE) {
shareable = 0;
name = "ioapic-edge";
} else {
shareable = 1;
name = "ioapic-level";
}
if (gsi_override >= 0)
gsi = gsi_override;
irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name);
if (irq < 0)
goto out;
printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d (gsi=%d)\n", map_irq.pirq, irq, gsi);
out:
return irq;
}
static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
int trigger, int polarity)
{
if (!xen_hvm_domain())
return -1;
return xen_register_pirq(gsi, -1 /* no GSI override */, trigger,
false /* no mapping of GSI to PIRQ */);
}
#ifdef CONFIG_XEN_DOM0
static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polarity)
{
int rc, irq;
struct physdev_setup_gsi setup_gsi;
if (!xen_pv_domain())
return -1;
printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
gsi, triggering, polarity);
irq = xen_register_pirq(gsi, gsi_override, triggering, true);
setup_gsi.gsi = gsi;
setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1);
setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi);
if (rc == -EEXIST)
printk(KERN_INFO "Already setup the GSI :%d\n", gsi);
else if (rc) {
printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n",
gsi, rc);
}
return irq;
}
static int acpi_register_gsi_xen(struct device *dev, u32 gsi,
int trigger, int polarity)
{
return xen_register_gsi(gsi, -1 /* no GSI override */, trigger, polarity);
}
#endif
#endif
#if defined(CONFIG_PCI_MSI)
#include <linux/msi.h>
#include <asm/msidef.h>
struct xen_pci_frontend_ops *xen_pci_frontend;
EXPORT_SYMBOL_GPL(xen_pci_frontend);
static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
int irq, ret, i;
struct msi_desc *msidesc;
int *v;
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
v = kcalloc(max(1, nvec), sizeof(int), GFP_KERNEL);
if (!v)
return -ENOMEM;
if (type == PCI_CAP_ID_MSIX)
ret = xen_pci_frontend_enable_msix(dev, v, nvec);
else
ret = xen_pci_frontend_enable_msi(dev, v);
if (ret)
goto error;
i = 0;
for_each_pci_msi_entry(msidesc, dev) {
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
(type == PCI_CAP_ID_MSI) ? nvec : 1,
(type == PCI_CAP_ID_MSIX) ?
"pcifront-msi-x" :
"pcifront-msi",
DOMID_SELF);
if (irq < 0) {
ret = irq;
goto free;
}
i++;
}
kfree(v);
return 0;
error:
if (ret == -ENOSYS)
dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
else if (ret)
dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret);
free:
kfree(v);
return ret;
}
#define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \
MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0))
static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
struct msi_msg *msg)
{
/* We set vector == 0 to tell the hypervisor we don't care about it,
* but we want a pirq setup instead.
* We use the dest_id field to pass the pirq that we want. */
msg->address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(pirq);
msg->address_lo =
MSI_ADDR_BASE_LO |
MSI_ADDR_DEST_MODE_PHYSICAL |
MSI_ADDR_REDIRECTION_CPU |
MSI_ADDR_DEST_ID(pirq);
msg->data = XEN_PIRQ_MSI_DATA;
}
static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
int irq, pirq;
struct msi_desc *msidesc;
struct msi_msg msg;
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
for_each_pci_msi_entry(msidesc, dev) {
xen: do not re-use pirq number cached in pci device msi msg data Revert the main part of commit: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests") That commit introduced reading the pci device's msi message data to see if a pirq was previously configured for the device's msi/msix, and re-use that pirq. At the time, that was the correct behavior. However, a later change to Qemu caused it to call into the Xen hypervisor to unmap all pirqs for a pci device, when the pci device disables its MSI/MSIX vectors; specifically the Qemu commit: c976437c7dba9c7444fb41df45468968aaa326ad ("qemu-xen: free all the pirqs for msi/msix when driver unload") Once Qemu added this pirq unmapping, it was no longer correct for the kernel to re-use the pirq number cached in the pci device msi message data. All Qemu releases since 2.1.0 contain the patch that unmaps the pirqs when the pci device disables its MSI/MSIX vectors. This bug is causing failures to initialize multiple NVMe controllers under Xen, because the NVMe driver sets up a single MSIX vector for each controller (concurrently), and then after using that to talk to the controller for some configuration data, it disables the single MSIX vector and re-configures all the MSIX vectors it needs. So the MSIX setup code tries to re-use the cached pirq from the first vector for each controller, but the hypervisor has already given away that pirq to another controller, and its initialization fails. This is discussed in more detail at: https://lists.xen.org/archives/html/xen-devel/2017-01/msg00447.html Fixes: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests") Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Reviewed-by: Stefano Stabellini <sstabellini@kernel.org> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2017-01-14 04:07:51 +08:00
pirq = xen_allocate_pirq_msi(dev, msidesc);
if (pirq < 0) {
irq = -ENODEV;
goto error;
}
xen: do not re-use pirq number cached in pci device msi msg data Revert the main part of commit: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests") That commit introduced reading the pci device's msi message data to see if a pirq was previously configured for the device's msi/msix, and re-use that pirq. At the time, that was the correct behavior. However, a later change to Qemu caused it to call into the Xen hypervisor to unmap all pirqs for a pci device, when the pci device disables its MSI/MSIX vectors; specifically the Qemu commit: c976437c7dba9c7444fb41df45468968aaa326ad ("qemu-xen: free all the pirqs for msi/msix when driver unload") Once Qemu added this pirq unmapping, it was no longer correct for the kernel to re-use the pirq number cached in the pci device msi message data. All Qemu releases since 2.1.0 contain the patch that unmaps the pirqs when the pci device disables its MSI/MSIX vectors. This bug is causing failures to initialize multiple NVMe controllers under Xen, because the NVMe driver sets up a single MSIX vector for each controller (concurrently), and then after using that to talk to the controller for some configuration data, it disables the single MSIX vector and re-configures all the MSIX vectors it needs. So the MSIX setup code tries to re-use the cached pirq from the first vector for each controller, but the hypervisor has already given away that pirq to another controller, and its initialization fails. This is discussed in more detail at: https://lists.xen.org/archives/html/xen-devel/2017-01/msg00447.html Fixes: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests") Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Reviewed-by: Stefano Stabellini <sstabellini@kernel.org> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2017-01-14 04:07:51 +08:00
xen_msi_compose_msg(dev, pirq, &msg);
__pci_write_msi_msg(msidesc, &msg);
dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
(type == PCI_CAP_ID_MSI) ? nvec : 1,
(type == PCI_CAP_ID_MSIX) ?
"msi-x" : "msi",
DOMID_SELF);
if (irq < 0)
goto error;
dev_dbg(&dev->dev,
"xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
}
return 0;
error:
dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n",
type == PCI_CAP_ID_MSI ? "" : "-X", irq);
return irq;
}
#ifdef CONFIG_XEN_DOM0
static bool __read_mostly pci_seg_supported = true;
static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
int ret = 0;
struct msi_desc *msidesc;
for_each_pci_msi_entry(msidesc, dev) {
struct physdev_map_pirq map_irq;
domid_t domid;
domid = ret = xen_find_device_domain_owner(dev);
/* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED,
* hence check ret value for < 0. */
if (ret < 0)
domid = DOMID_SELF;
memset(&map_irq, 0, sizeof(map_irq));
map_irq.domid = domid;
map_irq.type = MAP_PIRQ_TYPE_MSI_SEG;
map_irq.index = -1;
map_irq.pirq = -1;
map_irq.bus = dev->bus->number |
(pci_domain_nr(dev->bus) << 16);
map_irq.devfn = dev->devfn;
if (type == PCI_CAP_ID_MSI && nvec > 1) {
map_irq.type = MAP_PIRQ_TYPE_MULTI_MSI;
map_irq.entry_nr = nvec;
} else if (type == PCI_CAP_ID_MSIX) {
int pos;
unsigned long flags;
u32 table_offset, bir;
pos = dev->msix_cap;
pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
&table_offset);
bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
flags = pci_resource_flags(dev, bir);
if (!flags || (flags & IORESOURCE_UNSET))
return -EINVAL;
map_irq.table_base = pci_resource_start(dev, bir);
map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
}
ret = -EINVAL;
if (pci_seg_supported)
ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq,
&map_irq);
if (type == PCI_CAP_ID_MSI && nvec > 1 && ret) {
/*
* If MAP_PIRQ_TYPE_MULTI_MSI is not available
* there's nothing else we can do in this case.
* Just set ret > 0 so driver can retry with
* single MSI.
*/
ret = 1;
goto out;
}
if (ret == -EINVAL && !pci_domain_nr(dev->bus)) {
map_irq.type = MAP_PIRQ_TYPE_MSI;
map_irq.index = -1;
map_irq.pirq = -1;
map_irq.bus = dev->bus->number;
ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq,
&map_irq);
if (ret != -EINVAL)
pci_seg_supported = false;
}
if (ret) {
dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n",
ret, domid);
goto out;
}
ret = xen_bind_pirq_msi_to_irq(dev, msidesc, map_irq.pirq,
(type == PCI_CAP_ID_MSI) ? nvec : 1,
(type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi",
domid);
if (ret < 0)
goto out;
}
ret = 0;
out:
return ret;
}
static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
{
int ret = 0;
if (pci_seg_supported) {
struct physdev_pci_device restore_ext;
restore_ext.seg = pci_domain_nr(dev->bus);
restore_ext.bus = dev->bus->number;
restore_ext.devfn = dev->devfn;
ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi_ext,
&restore_ext);
if (ret == -ENOSYS)
pci_seg_supported = false;
WARN(ret && ret != -ENOSYS, "restore_msi_ext -> %d\n", ret);
}
if (!pci_seg_supported) {
struct physdev_restore_msi restore;
restore.bus = dev->bus->number;
restore.devfn = dev->devfn;
ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore);
WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
}
}
#endif
static void xen_teardown_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *msidesc;
msidesc = first_pci_msi_entry(dev);
if (msidesc->msi_attrib.is_msix)
xen_pci_frontend_disable_msix(dev);
else
xen_pci_frontend_disable_msi(dev);
/* Free the IRQ's and the msidesc using the generic code. */
default_teardown_msi_irqs(dev);
}
static void xen_teardown_msi_irq(unsigned int irq)
{
xen_destroy_irq(irq);
}
#endif
int __init pci_xen_init(void)
{
if (!xen_pv_domain() || xen_initial_domain())
return -ENODEV;
printk(KERN_INFO "PCI: setting up Xen PCI frontend stub\n");
pcibios_set_cache_line_size();
pcibios_enable_irq = xen_pcifront_enable_irq;
pcibios_disable_irq = NULL;
/* Keep ACPI out of the picture */
acpi_noirq_set();
#ifdef CONFIG_PCI_MSI
x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
pci_msi_ignore_mask = 1;
#endif
return 0;
}
#ifdef CONFIG_PCI_MSI
void __init xen_msi_init(void)
{
if (!disable_apic) {
/*
* If hardware supports (x2)APIC virtualization (as indicated
* by hypervisor's leaf 4) then we don't need to use pirqs/
* event channels for MSI handling and instead use regular
* APIC processing
*/
uint32_t eax = cpuid_eax(xen_cpuid_base() + 4);
if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) ||
((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC)))
return;
}
x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
}
#endif
int __init pci_xen_hvm_init(void)
{
xen: Revert commits da72ff5bfcb0 and 72a9b186292d Recent discussion (http://marc.info/?l=xen-devel&m=149192184523741) established that commit 72a9b186292d ("xen: Remove event channel notification through Xen PCI platform device") (and thus commit da72ff5bfcb0 ("partially revert "xen: Remove event channel notification through Xen PCI platform device"")) are unnecessary and, in fact, prevent HVM guests from booting on Xen releases prior to 4.0 Therefore we revert both of those commits. The summary of that discussion is below: Here is the brief summary of the current situation: Before the offending commit (72a9b186292): 1) INTx does not work because of the reset_watches path. 2) The reset_watches path is only taken if you have Xen > 4.0 3) The Linux Kernel by default will use vector inject if the hypervisor support. So even INTx does not work no body running the kernel with Xen > 4.0 would notice. Unless he explicitly disabled this feature either in the kernel or in Xen (and this can only be disabled by modifying the code, not user-supported way to do it). After the offending commit (+ partial revert): 1) INTx is no longer support for HVM (only for PV guests). 2) Any HVM guest The kernel will not boot on Xen < 4.0 which does not have vector injection support. Since the only other mode supported is INTx which. So based on this summary, I think before commit (72a9b186292) we were in much better position from a user point of view. Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Reviewed-by: Juergen Gross <jgross@suse.com> Signed-off-by: Juergen Gross <jgross@suse.com>
2017-04-25 03:04:53 +08:00
if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
return 0;
#ifdef CONFIG_ACPI
/*
* We don't want to change the actual ACPI delivery model,
* just how GSIs get registered.
*/
__acpi_register_gsi = acpi_register_gsi_xen_hvm;
__acpi_unregister_gsi = NULL;
#endif
#ifdef CONFIG_PCI_MSI
/*
* We need to wait until after x2apic is initialized
* before we can set MSI IRQ ops.
*/
x86_platform.apic_post_init = xen_msi_init;
#endif
return 0;
}
#ifdef CONFIG_XEN_DOM0
int __init pci_xen_initial_domain(void)
{
int irq;
#ifdef CONFIG_PCI_MSI
x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
pci_msi_ignore_mask = 1;
#endif
__acpi_register_gsi = acpi_register_gsi_xen;
__acpi_unregister_gsi = NULL;
/*
* Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here
* because we don't have a PIC and thus nr_legacy_irqs() is zero.
*/
for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
int trigger, polarity;
if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
continue;
xen_register_pirq(irq, -1 /* no GSI override */,
trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
true /* Map GSI to PIRQ */);
}
if (0 == nr_ioapics) {
for (irq = 0; irq < nr_legacy_irqs(); irq++)
xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic");
}
return 0;
}
struct xen_device_domain_owner {
domid_t domain;
struct pci_dev *dev;
struct list_head list;
};
static DEFINE_SPINLOCK(dev_domain_list_spinlock);
static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
{
struct xen_device_domain_owner *owner;
list_for_each_entry(owner, &dev_domain_list, list) {
if (owner->dev == dev)
return owner;
}
return NULL;
}
int xen_find_device_domain_owner(struct pci_dev *dev)
{
struct xen_device_domain_owner *owner;
int domain = -ENODEV;
spin_lock(&dev_domain_list_spinlock);
owner = find_device(dev);
if (owner)
domain = owner->domain;
spin_unlock(&dev_domain_list_spinlock);
return domain;
}
EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
{
struct xen_device_domain_owner *owner;
owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
if (!owner)
return -ENODEV;
spin_lock(&dev_domain_list_spinlock);
if (find_device(dev)) {
spin_unlock(&dev_domain_list_spinlock);
kfree(owner);
return -EEXIST;
}
owner->domain = domain;
owner->dev = dev;
list_add_tail(&owner->list, &dev_domain_list);
spin_unlock(&dev_domain_list_spinlock);
return 0;
}
EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
int xen_unregister_device_domain_owner(struct pci_dev *dev)
{
struct xen_device_domain_owner *owner;
spin_lock(&dev_domain_list_spinlock);
owner = find_device(dev);
if (!owner) {
spin_unlock(&dev_domain_list_spinlock);
return -ENODEV;
}
list_del(&owner->list);
spin_unlock(&dev_domain_list_spinlock);
kfree(owner);
return 0;
}
EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
#endif