Commit 74f4d227 authored by Anthony Liguori's avatar Anthony Liguori
Browse files

Merge remote-tracking branch 'qemu-kvm/uq/master' into staging 

* qemu-kvm/uq/master:
  virtio/vhost: Add support for KVM in-kernel MSI injection
  msix: Add msix_nr_vectors_allocated
  kvm: Enable use of kvm_irqchip_in_kernel in hwlib code
  kvm: Introduce kvm_irqchip_add/remove_irqfd
  kvm: Make kvm_irqchip_commit_routes an internal service
  kvm: Publicize kvm_irqchip_release_virq
  kvm: Introduce kvm_irqchip_add_msi_route
  kvm: Rename kvm_irqchip_add_route to kvm_irqchip_add_irq_route
  msix: Introduce vector notifiers
  msix: Invoke msix_handle_mask_update on msix_mask_all
  msix: Factor out msix_get_message
  kvm: update vmxcap for EPT A/D, INVPCID, RDRAND, VMFUNC
  kvm: Enable in-kernel irqchip support by default
  kvm: Add support for direct MSI injections
  kvm: Update kernel headers
  kvm: x86: Wire up MSI support for in-kernel irqchip
  pc: Enable MSI support at APIC level
  kvm: Introduce basic MSI support for in-kernel irqchips
  Introduce MSIMessage structure
  kvm: Refactor KVMState::max_gsi to gsi_count
parents 2eb02f28 7d37d351

hw/apic.c

+3 −0
Original line number Diff line number Diff line
@@ -19,6 +19,7 @@ 
#include "apic_internal.h"

#include "apic.h"

#include "ioapic.h"

#include "msi.h"

#include "host-utils.h"

#include "trace.h"

#include "pc.h"
@@ -862,6 +863,8 @@ static void apic_init(APICCommonState *s) 


    s->timer = qemu_new_timer_ns(vm_clock, apic_timer, s);

    local_apics[s->idx] = s;



    msi_supported = true;

}



static void apic_class_init(ObjectClass *klass, void *data)

hw/kvm/apic.c

+32 −2
Original line number Diff line number Diff line
@@ -10,6 +10,7 @@ 
 * See the COPYING file in the top-level directory.

 */

#include "hw/apic_internal.h"

#include "hw/msi.h"

#include "kvm.h"



static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic,
@@ -145,10 +146,39 @@ static void kvm_apic_external_nmi(APICCommonState *s) 
    run_on_cpu(s->cpu_env, do_inject_external_nmi, s);

}



static uint64_t kvm_apic_mem_read(void *opaque, target_phys_addr_t addr,

                                  unsigned size)

{

    return ~(uint64_t)0;

}



static void kvm_apic_mem_write(void *opaque, target_phys_addr_t addr,

                               uint64_t data, unsigned size)

{

    MSIMessage msg = { .address = addr, .data = data };

    int ret;



    ret = kvm_irqchip_send_msi(kvm_state, msg);

    if (ret < 0) {

        fprintf(stderr, "KVM: injection failed, MSI lost (%s)\n",

                strerror(-ret));

    }

}



static const MemoryRegionOps kvm_apic_io_ops = {

    .read = kvm_apic_mem_read,

    .write = kvm_apic_mem_write,

    .endianness = DEVICE_NATIVE_ENDIAN,

};



static void kvm_apic_init(APICCommonState *s)

{

    memory_region_init_reservation(&s->io_memory, "kvm-apic-msi",

    memory_region_init_io(&s->io_memory, &kvm_apic_io_ops, s, "kvm-apic-msi",

                          MSI_SPACE_SIZE);



    if (kvm_has_gsi_routing()) {

        msi_supported = true;

    }

}



static void kvm_apic_class_init(ObjectClass *klass, void *data)

hw/msi.h

+5 −0
Original line number Diff line number Diff line
@@ -24,6 +24,11 @@ 
#include "qemu-common.h"

#include "pci.h"



struct MSIMessage {

    uint64_t address;

    uint32_t data;

};



extern bool msi_supported;



bool msi_enabled(const PCIDevice *dev);

hw/msix.c

+115 −6
Original line number Diff line number Diff line
@@ -35,6 +35,15 @@ 
#define MSIX_PAGE_PENDING (MSIX_PAGE_SIZE / 2)

#define MSIX_MAX_ENTRIES 32



static MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)

{

    uint8_t *table_entry = dev->msix_table_page + vector * PCI_MSIX_ENTRY_SIZE;

    MSIMessage msg;



    msg.address = pci_get_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR);

    msg.data = pci_get_long(table_entry + PCI_MSIX_ENTRY_DATA);

    return msg;

}



/* Add MSI-X capability to the config space for the device. */

/* Given a bar and its size, add MSI-X table on top of it
@@ -130,13 +139,34 @@ static bool msix_is_masked(PCIDevice *dev, int vector) 
    return msix_vector_masked(dev, vector, dev->msix_function_masked);

}



static void msix_fire_vector_notifier(PCIDevice *dev,

                                      unsigned int vector, bool is_masked)

{

    MSIMessage msg;

    int ret;



    if (!dev->msix_vector_use_notifier) {

        return;

    }

    if (is_masked) {

        dev->msix_vector_release_notifier(dev, vector);

    } else {

        msg = msix_get_message(dev, vector);

        ret = dev->msix_vector_use_notifier(dev, vector, msg);

        assert(ret >= 0);

    }

}



static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)

{

    bool is_masked = msix_is_masked(dev, vector);



    if (is_masked == was_masked) {

        return;

    }



    msix_fire_vector_notifier(dev, vector, is_masked);



    if (!is_masked && msix_is_pending(dev, vector)) {

        msix_clr_pending(dev, vector);

        msix_notify(dev, vector);
@@ -222,10 +252,14 @@ static void msix_mmio_setup(PCIDevice *d, MemoryRegion *bar) 
static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)

{

    int vector;



    for (vector = 0; vector < nentries; ++vector) {

        unsigned offset =

            vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;

        bool was_masked = msix_is_masked(dev, vector);



        dev->msix_table_page[offset] |= PCI_MSIX_ENTRY_CTRL_MASKBIT;

        msix_handle_mask_update(dev, vector, was_masked);

    }

}
@@ -317,6 +351,7 @@ void msix_save(PCIDevice *dev, QEMUFile *f) 
void msix_load(PCIDevice *dev, QEMUFile *f)

{

    unsigned n = dev->msix_entries_nr;

    unsigned int vector;



    if (!(dev->cap_present & QEMU_PCI_CAP_MSIX)) {

        return;
@@ -326,6 +361,10 @@ void msix_load(PCIDevice *dev, QEMUFile *f) 
    qemu_get_buffer(f, dev->msix_table_page, n * PCI_MSIX_ENTRY_SIZE);

    qemu_get_buffer(f, dev->msix_table_page + MSIX_PAGE_PENDING, (n + 7) / 8);

    msix_update_function_masked(dev);



    for (vector = 0; vector < n; vector++) {

        msix_handle_mask_update(dev, vector, true);

    }

}



/* Does device support MSI-X? */
@@ -352,9 +391,7 @@ uint32_t msix_bar_size(PCIDevice *dev) 
/* Send an MSI-X message */

void msix_notify(PCIDevice *dev, unsigned vector)

{

    uint8_t *table_entry = dev->msix_table_page + vector * PCI_MSIX_ENTRY_SIZE;

    uint64_t address;

    uint32_t data;

    MSIMessage msg;



    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])

        return;
@@ -363,9 +400,9 @@ void msix_notify(PCIDevice *dev, unsigned vector) 
        return;

    }



    address = pci_get_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR);

    data = pci_get_long(table_entry + PCI_MSIX_ENTRY_DATA);

    stl_le_phys(address, data);

    msg = msix_get_message(dev, vector);



    stl_le_phys(msg.address, msg.data);

}



void msix_reset(PCIDevice *dev)
@@ -414,3 +451,75 @@ void msix_unuse_all_vectors(PCIDevice *dev) 
        return;

    msix_free_irq_entries(dev);

}



unsigned int msix_nr_vectors_allocated(const PCIDevice *dev)

{

    return dev->msix_entries_nr;

}



static int msix_set_notifier_for_vector(PCIDevice *dev, unsigned int vector)

{

    MSIMessage msg;



    if (msix_is_masked(dev, vector)) {

        return 0;

    }

    msg = msix_get_message(dev, vector);

    return dev->msix_vector_use_notifier(dev, vector, msg);

}



static void msix_unset_notifier_for_vector(PCIDevice *dev, unsigned int vector)

{

    if (msix_is_masked(dev, vector)) {

        return;

    }

    dev->msix_vector_release_notifier(dev, vector);

}



int msix_set_vector_notifiers(PCIDevice *dev,

                              MSIVectorUseNotifier use_notifier,

                              MSIVectorReleaseNotifier release_notifier)

{

    int vector, ret;



    assert(use_notifier && release_notifier);



    dev->msix_vector_use_notifier = use_notifier;

    dev->msix_vector_release_notifier = release_notifier;



    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &

        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {

        for (vector = 0; vector < dev->msix_entries_nr; vector++) {

            ret = msix_set_notifier_for_vector(dev, vector);

            if (ret < 0) {

                goto undo;

            }

        }

    }

    return 0;



undo:

    while (--vector >= 0) {

        msix_unset_notifier_for_vector(dev, vector);

    }

    dev->msix_vector_use_notifier = NULL;

    dev->msix_vector_release_notifier = NULL;

    return ret;

}



void msix_unset_vector_notifiers(PCIDevice *dev)

{

    int vector;



    assert(dev->msix_vector_use_notifier &&

           dev->msix_vector_release_notifier);



    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &

        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {

        for (vector = 0; vector < dev->msix_entries_nr; vector++) {

            msix_unset_notifier_for_vector(dev, vector);

        }

    }

    dev->msix_vector_use_notifier = NULL;

    dev->msix_vector_release_notifier = NULL;

}

hw/msix.h

+6 −0
Original line number Diff line number Diff line
@@ -13,6 +13,8 @@ void msix_write_config(PCIDevice *pci_dev, uint32_t address, 


int msix_uninit(PCIDevice *d, MemoryRegion *bar);



unsigned int msix_nr_vectors_allocated(const PCIDevice *dev);



void msix_save(PCIDevice *dev, QEMUFile *f);

void msix_load(PCIDevice *dev, QEMUFile *f);
@@ -29,4 +31,8 @@ void msix_notify(PCIDevice *dev, unsigned vector); 


void msix_reset(PCIDevice *dev);



int msix_set_vector_notifiers(PCIDevice *dev,

                              MSIVectorUseNotifier use_notifier,

                              MSIVectorReleaseNotifier release_notifier);

void msix_unset_vector_notifiers(PCIDevice *dev);

#endif