Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20150923.0' into staging

VFIO updates 2015-09-23

 - Tracing improvements to use common prefixes for functional areas
 - Quirks overhaul:
   - Split PCI quirks to separate file
   - Make them understandable and more extensible
   - Improve use of MemoryRegions and eliminate use of target pagesize
 - Eliminate build-time debugging, everything migrated to runtime opts

# gpg: Signature made Wed 23 Sep 2015 21:09:05 BST using RSA key ID 3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg:                 aka "Alex Williamson <alex@shazbot.org>"
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>"
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>"

* remotes/awilliam/tags/vfio-update-20150923.0:
  vfio/pci: Add emulated PCI IDs
  vfio/pci: Cache vendor and device ID
  vfio/pci: Move AMD device specific reset to quirks
  vfio/pci: Remove old config window and mirror quirks
  vfio/pci: Config mirror quirk
  vfio/pci: Config window quirks
  vfio/pci: Rework RTL8168 quirk
  vfio/pci: Cleanup Nvidia 0x3d0 quirk
  vfio/pci: Cleanup ATI 0x3c3 quirk
  vfio/pci: Foundation for new quirk structure
  vfio/pci: Cleanup ROM blacklist quirk
  vfio/pci: Split quirks to a separate file
  vfio/pci: Extract PCI structures to a separate header
  vfio: Change polarity of our no-mmap option
  vfio/pci: Make interrupt bypass runtime configurable
  vfio/pci: Rename MSI/X functions for easier tracing
  vfio/pci: Rename INTx functions for easier tracing
  vfio/pci: Cleanup vfio_early_setup_msix() error path
  vfio/pci: Cleanup RTL8168 quirk and tracing

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

hw/vfio/Makefile.objs

 ifeq ($(CONFIG_LINUX), y)
 obj-$(CONFIG_SOFTMMU) += common.o
-obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_PCI) += pci.o pci-quirks.o
 obj-$(CONFIG_SOFTMMU) += platform.o
 obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
 endif

hw/vfio/common.c

@@ -496,7 +496,7 @@ int vfio_mmap_region(Object *obj, VFIORegion *region,
     int ret = 0;
     VFIODevice *vbasedev = region->vbasedev;
 
-    if (vbasedev->allow_mmap && size && region->flags &
+    if (!vbasedev->no_mmap && size && region->flags &
         VFIO_REGION_INFO_FLAG_MMAP) {
         int prot = 0;
 

hw/vfio/pci.h

+/*
+ * vfio based device assignment support - PCI devices
+ *
+ * Copyright Red Hat, Inc. 2012-2015
+ *
+ * Authors:
+ *  Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+#ifndef HW_VFIO_VFIO_PCI_H
+#define HW_VFIO_VFIO_PCI_H
+
+#include "qemu-common.h"
+#include "exec/memory.h"
+#include "hw/pci/pci.h"
+#include "hw/vfio/vfio-common.h"
+#include "qemu/event_notifier.h"
+#include "qemu/queue.h"
+#include "qemu/timer.h"
+
+#define PCI_ANY_ID (~0)
+
+struct VFIOPCIDevice;
+
+typedef struct VFIOQuirk {
+    QLIST_ENTRY(VFIOQuirk) next;
+    void *data;
+    int nr_mem;
+    MemoryRegion *mem;
+} VFIOQuirk;
+
+typedef struct VFIOBAR {
+    VFIORegion region;
+    bool ioport;
+    bool mem64;
+    QLIST_HEAD(, VFIOQuirk) quirks;
+} VFIOBAR;
+
+typedef struct VFIOVGARegion {
+    MemoryRegion mem;
+    off_t offset;
+    int nr;
+    QLIST_HEAD(, VFIOQuirk) quirks;
+} VFIOVGARegion;
+
+typedef struct VFIOVGA {
+    off_t fd_offset;
+    int fd;
+    VFIOVGARegion region[QEMU_PCI_VGA_NUM_REGIONS];
+} VFIOVGA;
+
+typedef struct VFIOINTx {
+    bool pending; /* interrupt pending */
+    bool kvm_accel; /* set when QEMU bypass through KVM enabled */
+    uint8_t pin; /* which pin to pull for qemu_set_irq */
+    EventNotifier interrupt; /* eventfd triggered on interrupt */
+    EventNotifier unmask; /* eventfd for unmask on QEMU bypass */
+    PCIINTxRoute route; /* routing info for QEMU bypass */
+    uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */
+    QEMUTimer *mmap_timer; /* enable mmaps after periods w/o interrupts */
+} VFIOINTx;
+
+typedef struct VFIOMSIVector {
+    /*
+     * Two interrupt paths are configured per vector.  The first, is only used
+     * for interrupts injected via QEMU.  This is typically the non-accel path,
+     * but may also be used when we want QEMU to handle masking and pending
+     * bits.  The KVM path bypasses QEMU and is therefore higher performance,
+     * but requires masking at the device.  virq is used to track the MSI route
+     * through KVM, thus kvm_interrupt is only available when virq is set to a
+     * valid (>= 0) value.
+     */
+    EventNotifier interrupt;
+    EventNotifier kvm_interrupt;
+    struct VFIOPCIDevice *vdev; /* back pointer to device */
+    int virq;
+    bool use;
+} VFIOMSIVector;
+
+enum {
+    VFIO_INT_NONE = 0,
+    VFIO_INT_INTx = 1,
+    VFIO_INT_MSI  = 2,
+    VFIO_INT_MSIX = 3,
+};
+
+/* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */
+typedef struct VFIOMSIXInfo {
+    uint8_t table_bar;
+    uint8_t pba_bar;
+    uint16_t entries;
+    uint32_t table_offset;
+    uint32_t pba_offset;
+    MemoryRegion mmap_mem;
+    void *mmap;
+} VFIOMSIXInfo;
+
+typedef struct VFIOPCIDevice {
+    PCIDevice pdev;
+    VFIODevice vbasedev;
+    VFIOINTx intx;
+    unsigned int config_size;
+    uint8_t *emulated_config_bits; /* QEMU emulated bits, little-endian */
+    off_t config_offset; /* Offset of config space region within device fd */
+    unsigned int rom_size;
+    off_t rom_offset; /* Offset of ROM region within device fd */
+    void *rom;
+    int msi_cap_size;
+    VFIOMSIVector *msi_vectors;
+    VFIOMSIXInfo *msix;
+    int nr_vectors; /* Number of MSI/MSIX vectors currently in use */
+    int interrupt; /* Current interrupt type */
+    VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */
+    VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */
+    PCIHostDeviceAddress host;
+    EventNotifier err_notifier;
+    EventNotifier req_notifier;
+    int (*resetfn)(struct VFIOPCIDevice *);
+    uint32_t vendor_id;
+    uint32_t device_id;
+    uint32_t sub_vendor_id;
+    uint32_t sub_device_id;
+    uint32_t features;
+#define VFIO_FEATURE_ENABLE_VGA_BIT 0
+#define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT)
+#define VFIO_FEATURE_ENABLE_REQ_BIT 1
+#define VFIO_FEATURE_ENABLE_REQ (1 << VFIO_FEATURE_ENABLE_REQ_BIT)
+    int32_t bootindex;
+    uint8_t pm_cap;
+    bool has_vga;
+    bool pci_aer;
+    bool req_enabled;
+    bool has_flr;
+    bool has_pm_reset;
+    bool rom_read_failed;
+    bool no_kvm_intx;
+    bool no_kvm_msi;
+    bool no_kvm_msix;
+} VFIOPCIDevice;
+
+uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
+void vfio_pci_write_config(PCIDevice *pdev,
+                           uint32_t addr, uint32_t val, int len);
+
+uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
+void vfio_vga_write(void *opaque, hwaddr addr, uint64_t data, unsigned size);
+
+bool vfio_blacklist_opt_rom(VFIOPCIDevice *vdev);
+void vfio_vga_quirk_setup(VFIOPCIDevice *vdev);
+void vfio_vga_quirk_teardown(VFIOPCIDevice *vdev);
+void vfio_vga_quirk_free(VFIOPCIDevice *vdev);
+void vfio_bar_quirk_setup(VFIOPCIDevice *vdev, int nr);
+void vfio_bar_quirk_teardown(VFIOPCIDevice *vdev, int nr);
+void vfio_bar_quirk_free(VFIOPCIDevice *vdev, int nr);
+void vfio_setup_resetfn_quirk(VFIOPCIDevice *vdev);
+
+#endif /* HW_VFIO_VFIO_PCI_H */

hw/vfio/platform.c

@@ -678,7 +678,7 @@ static const VMStateDescription vfio_platform_vmstate = {
 
 static Property vfio_platform_dev_properties[] = {
     DEFINE_PROP_STRING("host", VFIOPlatformDevice, vbasedev.name),
-    DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true),
+    DEFINE_PROP_BOOL("x-no-mmap", VFIOPlatformDevice, vbasedev.no_mmap, false),
     DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice,
                        mmap_timeout, 1100),
     DEFINE_PROP_BOOL("x-irqfd", VFIOPlatformDevice, irqfd_allowed, true),

include/hw/vfio/vfio-common.h

@@ -35,11 +35,6 @@
     do { } while (0)
 #endif
 
-/* Extra debugging, trap acceleration paths for more logging */
-#define VFIO_ALLOW_KVM_INTX 1
-#define VFIO_ALLOW_KVM_MSI 1
-#define VFIO_ALLOW_KVM_MSIX 1
-
 enum {
     VFIO_DEVICE_TYPE_PCI = 0,
     VFIO_DEVICE_TYPE_PLATFORM = 1,
@@ -102,7 +97,7 @@ typedef struct VFIODevice {
     int type;
     bool reset_works;
     bool needs_reset;
-    bool allow_mmap;
+    bool no_mmap;
     VFIODeviceOps *ops;
     unsigned int num_irqs;
     unsigned int num_regions;

trace-events

@@ -1522,56 +1522,30 @@ xen_pv_mmio_write(uint64_t addr) "WARNING: write to Xen PV Device MMIO space (ad
 pci_cfg_read(const char *dev, unsigned devid, unsigned fnid, unsigned offs, unsigned val) "%s %02u:%u @0x%x -> 0x%x"
 pci_cfg_write(const char *dev, unsigned devid, unsigned fnid, unsigned offs, unsigned val) "%s %02u:%u @0x%x <- 0x%x"
 
-# hw/vfio/vfio-pci.c
+# hw/vfio/pci.c
 vfio_intx_interrupt(const char *name, char line) " (%s) Pin %c"
-vfio_eoi(const char *name) " (%s) EOI"
-vfio_enable_intx_kvm(const char *name) " (%s) KVM INTx accel enabled"
-vfio_disable_intx_kvm(const char *name) " (%s) KVM INTx accel disabled"
-vfio_update_irq(const char *name, int new_irq, int target_irq) " (%s) IRQ moved %d -> %d"
-vfio_enable_intx(const char *name) " (%s)"
-vfio_disable_intx(const char *name) " (%s)"
+vfio_intx_eoi(const char *name) " (%s) EOI"
+vfio_intx_enable_kvm(const char *name) " (%s) KVM INTx accel enabled"
+vfio_intx_disable_kvm(const char *name) " (%s) KVM INTx accel disabled"
+vfio_intx_update(const char *name, int new_irq, int target_irq) " (%s) IRQ moved %d -> %d"
+vfio_intx_enable(const char *name) " (%s)"
+vfio_intx_disable(const char *name) " (%s)"
 vfio_msi_interrupt(const char *name, int index, uint64_t addr, int data) " (%s) vector %d 0x%"PRIx64"/0x%x"
 vfio_msix_vector_do_use(const char *name, int index) " (%s) vector %d used"
 vfio_msix_vector_release(const char *name, int index) " (%s) vector %d released"
-vfio_enable_msix(const char *name) " (%s)"
-vfio_enable_msi(const char *name, int nr_vectors) " (%s) Enabled %d MSI vectors"
-vfio_disable_msix(const char *name) " (%s)"
-vfio_disable_msi(const char *name) " (%s)"
+vfio_msix_enable(const char *name) " (%s)"
+vfio_msix_disable(const char *name) " (%s)"
+vfio_msi_enable(const char *name, int nr_vectors) " (%s) Enabled %d MSI vectors"
+vfio_msi_disable(const char *name) " (%s)"
 vfio_pci_load_rom(const char *name, unsigned long size, unsigned long offset, unsigned long flags) "Device %s ROM:\n  size: 0x%lx, offset: 0x%lx, flags: 0x%lx"
 vfio_rom_read(const char *name, uint64_t addr, int size, uint64_t data) " (%s, 0x%"PRIx64", 0x%x) = 0x%"PRIx64
 vfio_pci_size_rom(const char *name, int size) "%s ROM size 0x%x"
 vfio_vga_write(uint64_t addr, uint64_t data, int size) " (0x%"PRIx64", 0x%"PRIx64", %d)"
 vfio_vga_read(uint64_t addr, int size, uint64_t data) " (0x%"PRIx64", %d) = 0x%"PRIx64
-# remove ) =
-vfio_generic_window_quirk_read(const char * region_name, const char *name, int index, uint64_t addr, int size, uint64_t data) "%s read(%s:BAR%d+0x%"PRIx64", %d = 0x%"PRIx64
-## remove )
-vfio_generic_window_quirk_write(const char * region_name, const char *name, int index, uint64_t addr, uint64_t data, int size) "%s write(%s:BAR%d+0x%"PRIx64", 0x%"PRIx64", %d"
-# remove ) =
-vfio_generic_quirk_read(const char * region_name, const char *name, int index, uint64_t addr, int size, uint64_t data) "%s read(%s:BAR%d+0x%"PRIx64", %d = 0x%"PRIx64
-# remove )
-vfio_generic_quirk_write(const char * region_name, const char *name, int index, uint64_t addr, uint64_t data, int size) "%s write(%s:BAR%d+0x%"PRIx64", 0x%"PRIx64", %d"
-vfio_ati_3c3_quirk_read(uint64_t data) " (0x3c3, 1) = 0x%"PRIx64
-vfio_vga_probe_ati_3c3_quirk(const char *name) "Enabled ATI/AMD quirk 0x3c3 BAR4for device %s"
-vfio_probe_ati_bar4_window_quirk(const char *name) "Enabled ATI/AMD BAR4 window quirk for device %s"
-#issue with )
-vfio_rtl8168_window_quirk_read_fake(const char *region_name, const char *name) "%s fake read(%s"
-vfio_rtl8168_window_quirk_read_table(const char *region_name, const char *name) "%s MSI-X table read(%s"
-vfio_rtl8168_window_quirk_read_direct(const char *region_name, const char *name) "%s direct read(%s"
-vfio_rtl8168_window_quirk_write_table(const char *region_name, const char *name) "%s MSI-X table write(%s"
-vfio_rtl8168_window_quirk_write_direct(const char *region_name, const char *name) "%s direct write(%s"
-vfio_probe_rtl8168_bar2_window_quirk(const char *name) "Enabled RTL8168 BAR2 window quirk for device %s"
-vfio_probe_ati_bar2_4000_quirk(const char *name) "Enabled ATI/AMD BAR2 0x4000 quirk for device %s"
-vfio_nvidia_3d0_quirk_read(int size, uint64_t data) " (0x3d0, %d) = 0x%"PRIx64
-vfio_nvidia_3d0_quirk_write(uint64_t data, int size) " (0x3d0, 0x%"PRIx64", %d)"
-vfio_vga_probe_nvidia_3d0_quirk(const char *name) "Enabled NVIDIA VGA 0x3d0 quirk for device %s"
-vfio_probe_nvidia_bar5_window_quirk(const char *name) "Enabled NVIDIA BAR5 window quirk for device %s"
-vfio_probe_nvidia_bar0_88000_quirk(const char *name) "Enabled NVIDIA BAR0 0x88000 quirk for device %s"
-vfio_probe_nvidia_bar0_1800_quirk_id(int id) "Nvidia NV%02x"
-vfio_probe_nvidia_bar0_1800_quirk(const char *name) "Enabled NVIDIA BAR0 0x1800 quirk for device %s"
 vfio_pci_read_config(const char *name, int addr, int len, int val) " (%s, @0x%x, len=0x%x) %x"
 vfio_pci_write_config(const char *name, int addr, int val, int len) " (%s, @0x%x, 0x%x, len=0x%x)"
-vfio_setup_msi(const char *name, int pos) "%s PCI MSI CAP @0x%x"
-vfio_early_setup_msix(const char *name, int pos, int table_bar, int offset, int entries) "%s PCI MSI-X CAP @0x%x, BAR %d, offset 0x%x, entries %d"
+vfio_msi_setup(const char *name, int pos) "%s PCI MSI CAP @0x%x"
+vfio_msix_early_setup(const char *name, int pos, int table_bar, int offset, int entries) "%s PCI MSI-X CAP @0x%x, BAR %d, offset 0x%x, entries %d"
 vfio_check_pcie_flr(const char *name) "%s Supports FLR via PCIe cap"
 vfio_check_pm_reset(const char *name) "%s Supports PM reset"
 vfio_check_af_flr(const char *name) "%s Supports FLR via AF cap"
@@ -1586,6 +1560,41 @@ vfio_initfn(const char *name, int group_id) " (%s) group %d"
 vfio_pci_reset(const char *name) " (%s)"
 vfio_pci_reset_flr(const char *name) "%s FLR/VFIO_DEVICE_RESET"
 vfio_pci_reset_pm(const char *name) "%s PCI PM Reset"
+vfio_pci_emulated_vendor_id(const char *name, uint16_t val) "%s %04x"
+vfio_pci_emulated_device_id(const char *name, uint16_t val) "%s %04x"
+vfio_pci_emulated_sub_vendor_id(const char *name, uint16_t val) "%s %04x"
+vfio_pci_emulated_sub_device_id(const char *name, uint16_t val) "%s %04x"
+
+# hw/vfio/pci-quirks.
+vfio_quirk_rom_blacklisted(const char *name, uint16_t vid, uint16_t did) "%s %04x:%04x"
+vfio_quirk_generic_window_address_write(const char *name, const char * region_name, uint64_t data) "%s %s 0x%"PRIx64
+vfio_quirk_generic_window_data_read(const char *name, const char * region_name, uint64_t data) "%s %s 0x%"PRIx64
+vfio_quirk_generic_window_data_write(const char *name, const char * region_name, uint64_t data) "%s %s 0x%"PRIx64
+vfio_quirk_generic_mirror_read(const char *name, const char * region_name, uint64_t addr, uint64_t data) "%s %s 0x%"PRIx64": 0x%"PRIx64
+vfio_quirk_generic_mirror_write(const char *name, const char * region_name, uint64_t addr, uint64_t data) "%s %s 0x%"PRIx64": 0x%"PRIx64
+vfio_quirk_ati_3c3_read(const char *name, uint64_t data) "%s 0x%"PRIx64
+vfio_quirk_ati_3c3_probe(const char *name) "%s"
+vfio_quirk_ati_bar4_probe(const char *name) "%s"
+vfio_quirk_ati_bar2_probe(const char *name) "%s"
+vfio_quirk_nvidia_3d0_state(const char *name, const char *state) "%s %s"
+vfio_quirk_nvidia_3d0_read(const char *name, uint8_t offset, unsigned size, uint64_t val) " (%s, @0x%x, len=0x%x) %"PRIx64
+vfio_quirk_nvidia_3d0_write(const char *name, uint8_t offset, uint64_t data, unsigned size) "(%s, @0x%x, 0x%"PRIx64", len=0x%x)"
+vfio_quirk_nvidia_3d0_probe(const char *name) "%s"
+vfio_quirk_nvidia_bar5_state(const char *name, const char *state) "%s %s"
+vfio_quirk_nvidia_bar5_probe(const char *name) "%s"
+vfio_quirk_nvidia_bar0_msi_ack(const char *name) "%s"
+vfio_quirk_nvidia_bar0_probe(const char *name) "%s"
+vfio_quirk_rtl8168_fake_latch(const char *name, uint64_t val) "%s 0x%"PRIx64
+vfio_quirk_rtl8168_msix_write(const char *name, uint16_t offset, uint64_t val) "%s MSI-X table write[0x%x]: 0x%"PRIx64
+vfio_quirk_rtl8168_msix_read(const char *name, uint16_t offset, uint64_t val) "%s MSI-X table read[0x%x]: 0x%"PRIx64
+vfio_quirk_rtl8168_probe(const char *name) "%s"
+
+vfio_quirk_ati_bonaire_reset_skipped(const char *name) "%s"
+vfio_quirk_ati_bonaire_reset_no_smc(const char *name) "%s"
+vfio_quirk_ati_bonaire_reset_timeout(const char *name) "%s"
+vfio_quirk_ati_bonaire_reset_done(const char *name) "%s"
+vfio_quirk_ati_bonaire_reset(const char *name) "%s"
+
 
 # hw/vfio/vfio-common.c
 vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)"