Merge remote-tracking branch 'mst/tags/for_anthony' into staging

pci: add pci test device

This adds a new device that we can use for testing PCI PIO and MMIO, with and
without ioeventfd in different configurations.  FAST_MMIO will be added if/when
kvm supports it.  Also included are minor cleanups in kvm APIs that it needs.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon 15 Apr 2013 05:42:24 PM CDT using RSA key ID D28D5469
# gpg: Can't check signature: public key not found

# By Michael S. Tsirkin
# Via Michael S. Tsirkin
* mst/tags/for_anthony:
  pci: add pci test device
  kvm: support non datamatch ioeventfd
  kvm: support any size for pio eventfd
  kvm: remove unused APIs

Message-id: cover.1366272004.git.mst@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

8 files changed, 422 insertions, 79 deletions

diff --git a/default-configs/pci.mak b/default-configs/pci.mak
index f5f100ecb0..b608f31c9a 100644
--- a/default-configs/pci.mak
+++ b/default-configs/pci.mak
@@ -24,3 +24,4 @@ CONFIG_SERIAL=y
 CONFIG_SERIAL_PCI=y
 CONFIG_IPACK=y
 CONFIG_WDT_IB6300ESB=y
+CONFIG_PCI_TESTDEV=y
diff --git a/docs/specs/pci-testdev.txt b/docs/specs/pci-testdev.txt
new file mode 100644
index 0000000000..128ae222ef
--- /dev/null
+++ b/docs/specs/pci-testdev.txt
@@ -0,0 +1,26 @@
+pci-test is a device used for testing low level IO
+
+device implements up to two BARs: BAR0 and BAR1.
+Each BAR can be memory or IO. Guests must detect
+BAR type and act accordingly.
+
+Each BAR size is up to 4K bytes.
+Each BAR starts with the following header:
+
+typedef struct PCITestDevHdr {
+    uint8_t test;  <- write-only, starts a given test number
+    uint8_t width_type; <- read-only, type and width of access for a given test.
+                           1,2,4 for byte,word or long write.
+                           any other value if test not supported on this BAR
+    uint8_t pad0[2];
+    uint32_t offset; <- read-only, offset in this BAR for a given test
+    uint32_t data;    <- read-only, data to use for a given test
+    uint32_t count;  <- for debugging. number of writes detected.
+    uint8_t name[]; <- for debugging. 0-terminated ASCII string.
+} PCITestDevHdr;
+
+All registers are little endian.
+
+device is expected to always implement tests 0 to N on each BAR, and to add new
+tests with higher numbers.  In this way a guest can scan test numbers until it
+detects an access type that it does not support on this BAR, then stop.
diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs
index 03699c3365..11b18a4196 100644
--- a/hw/misc/Makefile.objs
+++ b/hw/misc/Makefile.objs
@@ -4,6 +4,7 @@ common-obj-$(CONFIG_TMP105) += tmp105.o
 common-obj-$(CONFIG_ISA_DEBUG) += debugexit.o
 common-obj-$(CONFIG_SGA) += sga.o
 common-obj-$(CONFIG_ISA_TESTDEV) += pc-testdev.o
+common-obj-$(CONFIG_PCI_TESTDEV) += pci-testdev.o
 
 obj-$(CONFIG_VMPORT) += vmport.o
 
diff --git a/hw/misc/pci-testdev.c b/hw/misc/pci-testdev.c
new file mode 100644
index 0000000000..71ce5a3e08
--- /dev/null
+++ b/hw/misc/pci-testdev.c
@@ -0,0 +1,325 @@
+/*
+ * QEMU PCI test device
+ *
+ * Copyright (c) 2012 Red Hat Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#include "hw/hw.h"
+#include "hw/pci/pci.h"
+#include "qemu/event_notifier.h"
+#include "qemu/osdep.h"
+
+typedef struct PCITestDevHdr {
+    uint8_t test;
+    uint8_t width;
+    uint8_t pad0[2];
+    uint32_t offset;
+    uint8_t data;
+    uint8_t pad1[3];
+    uint32_t count;
+    uint8_t name[];
+} PCITestDevHdr;
+
+typedef struct IOTest {
+    MemoryRegion *mr;
+    EventNotifier notifier;
+    bool hasnotifier;
+    unsigned size;
+    bool match_data;
+    PCITestDevHdr *hdr;
+    unsigned bufsize;
+} IOTest;
+
+#define IOTEST_DATAMATCH 0xFA
+#define IOTEST_NOMATCH   0xCE
+
+#define IOTEST_IOSIZE 128
+#define IOTEST_MEMSIZE 2048
+
+static const char *iotest_test[] = {
+    "no-eventfd",
+    "wildcard-eventfd",
+    "datamatch-eventfd"
+};
+
+static const char *iotest_type[] = {
+    "mmio",
+    "portio"
+};
+
+#define IOTEST_TEST(i) (iotest_test[((i) % ARRAY_SIZE(iotest_test))])
+#define IOTEST_TYPE(i) (iotest_type[((i) / ARRAY_SIZE(iotest_test))])
+#define IOTEST_MAX_TEST (ARRAY_SIZE(iotest_test))
+#define IOTEST_MAX_TYPE (ARRAY_SIZE(iotest_type))
+#define IOTEST_MAX (IOTEST_MAX_TEST * IOTEST_MAX_TYPE)
+
+enum {
+    IOTEST_ACCESS_NAME,
+    IOTEST_ACCESS_DATA,
+    IOTEST_ACCESS_MAX,
+};
+
+#define IOTEST_ACCESS_TYPE uint8_t
+#define IOTEST_ACCESS_WIDTH (sizeof(uint8_t))
+
+typedef struct PCITestDevState {
+    PCIDevice dev;
+    MemoryRegion mmio;
+    MemoryRegion portio;
+    IOTest *tests;
+    int current;
+} PCITestDevState;
+
+#define IOTEST_IS_MEM(i) (strcmp(IOTEST_TYPE(i), "portio"))
+#define IOTEST_REGION(d, i) (IOTEST_IS_MEM(i) ?  &(d)->mmio : &(d)->portio)
+#define IOTEST_SIZE(i) (IOTEST_IS_MEM(i) ? IOTEST_MEMSIZE : IOTEST_IOSIZE)
+#define IOTEST_PCI_BAR(i) (IOTEST_IS_MEM(i) ? PCI_BASE_ADDRESS_SPACE_MEMORY : \
+                           PCI_BASE_ADDRESS_SPACE_IO)
+
+static int pci_testdev_start(IOTest *test)
+{
+    test->hdr->count = 0;
+    if (!test->hasnotifier) {
+        return 0;
+    }
+    event_notifier_test_and_clear(&test->notifier);
+    memory_region_add_eventfd(test->mr,
+                              le32_to_cpu(test->hdr->offset),
+                              test->size,
+                              test->match_data,
+                              test->hdr->data,
+                              &test->notifier);
+    return 0;
+}
+
+static void pci_testdev_stop(IOTest *test)
+{
+    if (!test->hasnotifier) {
+        return;
+    }
+    memory_region_del_eventfd(test->mr,
+                              le32_to_cpu(test->hdr->offset),
+                              test->size,
+                              test->match_data,
+                              test->hdr->data,
+                              &test->notifier);
+}
+
+static void
+pci_testdev_reset(PCITestDevState *d)
+{
+    if (d->current == -1) {
+        return;
+    }
+    pci_testdev_stop(&d->tests[d->current]);
+    d->current = -1;
+}
+
+static void pci_testdev_inc(IOTest *test, unsigned inc)
+{
+    uint32_t c = le32_to_cpu(test->hdr->count);
+    test->hdr->count = cpu_to_le32(c + inc);
+}
+
+static void
+pci_testdev_write(void *opaque, hwaddr addr, uint64_t val,
+                  unsigned size, int type)
+{
+    PCITestDevState *d = opaque;
+    IOTest *test;
+    int t, r;
+
+    if (addr == offsetof(PCITestDevHdr, test)) {
+        pci_testdev_reset(d);
+        if (val >= IOTEST_MAX_TEST) {
+            return;
+        }
+        t = type * IOTEST_MAX_TEST + val;
+        r = pci_testdev_start(&d->tests[t]);
+        if (r < 0) {
+            return;
+        }
+        d->current = t;
+        return;
+    }
+    if (d->current < 0) {
+        return;
+    }
+    test = &d->tests[d->current];
+    if (addr != le32_to_cpu(test->hdr->offset)) {
+        return;
+    }
+    if (test->match_data && test->size != size) {
+        return;
+    }
+    if (test->match_data && val != test->hdr->data) {
+        return;
+    }
+    pci_testdev_inc(test, 1);
+}
+
+static uint64_t
+pci_testdev_read(void *opaque, hwaddr addr, unsigned size)
+{
+    PCITestDevState *d = opaque;
+    const char *buf;
+    IOTest *test;
+    if (d->current < 0) {
+        return 0;
+    }
+    test = &d->tests[d->current];
+    buf = (const char *)test->hdr;
+    if (addr + size >= test->bufsize) {
+        return 0;
+    }
+    if (test->hasnotifier) {
+        event_notifier_test_and_clear(&test->notifier);
+    }
+    return buf[addr];
+}
+
+static void
+pci_testdev_mmio_write(void *opaque, hwaddr addr, uint64_t val,
+                       unsigned size)
+{
+    pci_testdev_write(opaque, addr, val, size, 0);
+}
+
+static void
+pci_testdev_pio_write(void *opaque, hwaddr addr, uint64_t val,
+                       unsigned size)
+{
+    pci_testdev_write(opaque, addr, val, size, 1);
+}
+
+static const MemoryRegionOps pci_testdev_mmio_ops = {
+    .read = pci_testdev_read,
+    .write = pci_testdev_mmio_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+};
+
+static const MemoryRegionOps pci_testdev_pio_ops = {
+    .read = pci_testdev_read,
+    .write = pci_testdev_pio_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+};
+
+static int pci_testdev_init(PCIDevice *pci_dev)
+{
+    PCITestDevState *d = DO_UPCAST(PCITestDevState, dev, pci_dev);
+    uint8_t *pci_conf;
+    char *name;
+    int r, i;
+
+    pci_conf = d->dev.config;
+
+    pci_conf[PCI_INTERRUPT_PIN] = 0; /* no interrupt pin */
+
+    memory_region_init_io(&d->mmio, &pci_testdev_mmio_ops, d,
+                          "pci-testdev-mmio", IOTEST_MEMSIZE * 2);
+    memory_region_init_io(&d->portio, &pci_testdev_pio_ops, d,
+                          "pci-testdev-portio", IOTEST_IOSIZE * 2);
+    pci_register_bar(&d->dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
+    pci_register_bar(&d->dev, 1, PCI_BASE_ADDRESS_SPACE_IO, &d->portio);
+
+    d->current = -1;
+    d->tests = g_malloc0(IOTEST_MAX * sizeof *d->tests);
+    for (i = 0; i < IOTEST_MAX; ++i) {
+        IOTest *test = &d->tests[i];
+        name = g_strdup_printf("%s-%s", IOTEST_TYPE(i), IOTEST_TEST(i));
+        test->bufsize = sizeof(PCITestDevHdr) + strlen(name) + 1;
+        test->hdr = g_malloc0(test->bufsize);
+        memcpy(test->hdr->name, name, strlen(name) + 1);
+        g_free(name);
+        test->hdr->offset = cpu_to_le32(IOTEST_SIZE(i) + i * IOTEST_ACCESS_WIDTH);
+        test->size = IOTEST_ACCESS_WIDTH;
+        test->match_data = strcmp(IOTEST_TEST(i), "wildcard-eventfd");
+        test->hdr->test = i;
+        test->hdr->data = test->match_data ? IOTEST_DATAMATCH : IOTEST_NOMATCH;
+        test->hdr->width = IOTEST_ACCESS_WIDTH;
+        test->mr = IOTEST_REGION(d, i);
+        if (!strcmp(IOTEST_TEST(i), "no-eventfd")) {
+            test->hasnotifier = false;
+            continue;
+        }
+        r = event_notifier_init(&test->notifier, 0);
+        assert(r >= 0);
+        test->hasnotifier = true;
+    }
+
+    return 0;
+}
+
+static void
+pci_testdev_uninit(PCIDevice *dev)
+{
+    PCITestDevState *d = DO_UPCAST(PCITestDevState, dev, dev);
+    int i;
+
+    pci_testdev_reset(d);
+    for (i = 0; i < IOTEST_MAX; ++i) {
+        if (d->tests[i].hasnotifier) {
+            event_notifier_cleanup(&d->tests[i].notifier);
+        }
+        g_free(d->tests[i].hdr);
+    }
+    g_free(d->tests);
+    memory_region_destroy(&d->mmio);
+    memory_region_destroy(&d->portio);
+}
+
+static void qdev_pci_testdev_reset(DeviceState *dev)
+{
+    PCITestDevState *d = DO_UPCAST(PCITestDevState, dev.qdev, dev);
+    pci_testdev_reset(d);
+}
+
+static void pci_testdev_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = pci_testdev_init;
+    k->exit = pci_testdev_uninit;
+    k->vendor_id = PCI_VENDOR_ID_REDHAT;
+    k->device_id = PCI_DEVICE_ID_REDHAT_TEST;
+    k->revision = 0x00;
+    k->class_id = PCI_CLASS_OTHERS;
+    dc->desc = "PCI Test Device";
+    dc->reset = qdev_pci_testdev_reset;
+}
+
+static const TypeInfo pci_testdev_info = {
+    .name          = "pci-testdev",
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCITestDevState),
+    .class_init    = pci_testdev_class_init,
+};
+
+static void pci_testdev_register_types(void)
+{
+    type_register_static(&pci_testdev_info);
+}
+
+type_init(pci_testdev_register_types)
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 05315c0475..7053d5bb4b 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -85,6 +85,7 @@
 #define PCI_DEVICE_ID_REDHAT_SERIAL      0x0002
 #define PCI_DEVICE_ID_REDHAT_SERIAL2     0x0003
 #define PCI_DEVICE_ID_REDHAT_SERIAL4     0x0004
+#define PCI_DEVICE_ID_REDHAT_TEST        0x0005
 #define PCI_DEVICE_ID_REDHAT_QXL         0x0100
 
 #define FMT_PCIBUS                      PRIx64
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 495e6f8dbd..75bd7d9934 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -283,10 +283,6 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram_addr,
 #endif
 
 #endif
-int kvm_set_ioeventfd_mmio(int fd, uint32_t adr, uint32_t val, bool assign,
-                           uint32_t size);
-
-int kvm_set_ioeventfd_pio_word(int fd, uint16_t adr, uint16_t val, bool assign);
 
 int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg);
 int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg);
diff --git a/kvm-all.c b/kvm-all.c
index fc4e17c8bb..2d927217bd 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -500,6 +500,66 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
     return ret;
 }
 
+static int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val,
+                                  bool assign, uint32_t size, bool datamatch)
+{
+    int ret;
+    struct kvm_ioeventfd iofd;
+
+    iofd.datamatch = datamatch ? val : 0;
+    iofd.addr = addr;
+    iofd.len = size;
+    iofd.flags = 0;
+    iofd.fd = fd;
+
+    if (!kvm_enabled()) {
+        return -ENOSYS;
+    }
+
+    if (datamatch) {
+        iofd.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+    }
+    if (!assign) {
+        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    }
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
+
+    if (ret < 0) {
+        return -errno;
+    }
+
+    return 0;
+}
+
+static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
+                                 bool assign, uint32_t size, bool datamatch)
+{
+    struct kvm_ioeventfd kick = {
+        .datamatch = datamatch ? val : 0,
+        .addr = addr,
+        .flags = KVM_IOEVENTFD_FLAG_PIO,
+        .len = size,
+        .fd = fd,
+    };
+    int r;
+    if (!kvm_enabled()) {
+        return -ENOSYS;
+    }
+    if (datamatch) {
+        kick.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+    }
+    if (!assign) {
+        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    }
+    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
+    if (r < 0) {
+        return r;
+    }
+    return 0;
+}
+
+
 static int kvm_check_many_ioeventfds(void)
 {
     /* Userspace can use ioeventfd for io notification.  This requires a host
@@ -517,7 +577,7 @@ static int kvm_check_many_ioeventfds(void)
         if (ioeventfds[i] < 0) {
             break;
         }
-        ret = kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, true);
+        ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true);
         if (ret < 0) {
             close(ioeventfds[i]);
             break;
@@ -528,7 +588,7 @@ static int kvm_check_many_ioeventfds(void)
     ret = i == ARRAY_SIZE(ioeventfds);
 
     while (i-- > 0) {
-        kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, false);
+        kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true);
         close(ioeventfds[i]);
     }
     return ret;
@@ -748,10 +808,8 @@ static void kvm_mem_ioeventfd_add(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    assert(match_data && section->size <= 8);
-
     r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
-                               data, true, section->size);
+                               data, true, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -766,7 +824,7 @@ static void kvm_mem_ioeventfd_del(MemoryListener *listener,
     int r;
 
     r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
-                               data, false, section->size);
+                               data, false, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -780,10 +838,8 @@ static void kvm_io_ioeventfd_add(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    assert(match_data && section->size == 2);
-
-    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
-                                   data, true);
+    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+                              data, true, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -798,8 +854,8 @@ static void kvm_io_ioeventfd_del(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
-                                   data, false);
+    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+                              data, false, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -1967,59 +2023,6 @@ int kvm_set_signal_mask(CPUArchState *env, const sigset_t *sigset)
 
     return r;
 }
-
-int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val, bool assign,
-                           uint32_t size)
-{
-    int ret;
-    struct kvm_ioeventfd iofd;
-
-    iofd.datamatch = val;
-    iofd.addr = addr;
-    iofd.len = size;
-    iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
-    iofd.fd = fd;
-
-    if (!kvm_enabled()) {
-        return -ENOSYS;
-    }
-
-    if (!assign) {
-        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
-    }
-
-    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
-
-    if (ret < 0) {
-        return -errno;
-    }
-
-    return 0;
-}
-
-int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
-{
-    struct kvm_ioeventfd kick = {
-        .datamatch = val,
-        .addr = addr,
-        .len = 2,
-        .flags = KVM_IOEVENTFD_FLAG_DATAMATCH | KVM_IOEVENTFD_FLAG_PIO,
-        .fd = fd,
-    };
-    int r;
-    if (!kvm_enabled()) {
-        return -ENOSYS;
-    }
-    if (!assign) {
-        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
-    }
-    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
-    if (r < 0) {
-        return r;
-    }
-    return 0;
-}
-
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
 {
     return kvm_arch_on_sigbus_vcpu(cpu, code, addr);
diff --git a/kvm-stub.c b/kvm-stub.c
index 723a813735..5f52186ae7 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -101,16 +101,6 @@ int kvm_set_signal_mask(CPUArchState *env, const sigset_t *sigset)
 }
 #endif
 
-int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
-{
-    return -ENOSYS;
-}
-
-int kvm_set_ioeventfd_mmio(int fd, uint32_t adr, uint32_t val, bool assign, uint32_t len)
-{
-    return -ENOSYS;
-}
-
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
 {
     return 1;