Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

vhost, virtio, pci, pxe

Fixes all over the place.
New tests for pxe.

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

# gpg: Signature made Thu 18 Feb 2016 15:46:39 GMT using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream:
  tests/vhost-user-bridge: add scattering of incoming packets
  vhost-user interrupt management fixes
  rules: filter out irrelevant files
  change type of pci_bridge_initfn() to void
  dec: convert to realize()
  tests: add pxe e1000 and virtio-pci tests
  msix: fix msix_vector_masked
  virtio: optimize virtio_access_is_big_endian() for little-endian targets
  vhost: simplify vhost_needs_vring_endian()
  vhost: move virtio 1.0 check to cross-endian helper
  virtio: move cross-endian helper to vhost
  vhost-net: revert support of cross-endian vnet headers
  virtio-net: use the backend cross-endian capabilities

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

6 files changed, 285 insertions, 98 deletions

diff --git a/tests/Makefile b/tests/Makefile
index c1c605fc63..839d357d46 100644
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -173,6 +173,7 @@ check-qtest-i386-y += tests/hd-geo-test$(EXESUF)
 gcov-files-i386-y += hw/block/hd-geometry.c
 check-qtest-i386-y += tests/boot-order-test$(EXESUF)
 check-qtest-i386-y += tests/bios-tables-test$(EXESUF)
+check-qtest-i386-y += tests/pxe-test$(EXESUF)
 check-qtest-i386-y += tests/rtc-test$(EXESUF)
 check-qtest-i386-y += tests/ipmi-kcs-test$(EXESUF)
 check-qtest-i386-y += tests/ipmi-bt-test$(EXESUF)
@@ -518,7 +519,9 @@ tests/ipmi-kcs-test$(EXESUF): tests/ipmi-kcs-test.o
 tests/ipmi-bt-test$(EXESUF): tests/ipmi-bt-test.o
 tests/hd-geo-test$(EXESUF): tests/hd-geo-test.o
 tests/boot-order-test$(EXESUF): tests/boot-order-test.o $(libqos-obj-y)
-tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o $(libqos-obj-y)
+tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o \
+	tests/boot-sector.o $(libqos-obj-y)
+tests/pxe-test$(EXESUF): tests/pxe-test.o tests/boot-sector.o $(libqos-obj-y)
 tests/tmp105-test$(EXESUF): tests/tmp105-test.o $(libqos-omap-obj-y)
 tests/ds1338-test$(EXESUF): tests/ds1338-test.o $(libqos-imx-obj-y)
 tests/i440fx-test$(EXESUF): tests/i440fx-test.o $(libqos-pc-obj-y)
diff --git a/tests/bios-tables-test.c b/tests/bios-tables-test.c
index 7155fecdbf..0a80ddf04b 100644
--- a/tests/bios-tables-test.c
+++ b/tests/bios-tables-test.c
@@ -18,6 +18,7 @@
 #include "hw/acpi/acpi-defs.h"
 #include "hw/smbios/smbios.h"
 #include "qemu/bitmap.h"
+#include "boot-sector.h"
 
 #define MACHINE_PC "pc"
 #define MACHINE_Q35 "q35"
@@ -51,13 +52,6 @@ typedef struct {
     struct smbios_21_entry_point smbios_ep_table;
 } test_data;
 
-#define LOW(x) ((x) & 0xff)
-#define HIGH(x) ((x) >> 8)
-
-#define SIGNATURE 0xdead
-#define SIGNATURE_OFFSET 0x10
-#define BOOT_SECTOR_ADDRESS 0x7c00
-
 #define ACPI_READ_FIELD(field, addr)           \
     do {                                       \
         switch (sizeof(field)) {               \
@@ -117,35 +111,6 @@ typedef struct {
     g_assert_cmpstr(ACPI_ASSERT_CMP_str, ==, expected); \
 } while (0)
 
-/* Boot sector code: write SIGNATURE into memory,
- * then halt.
- * Q35 machine requires a minimum 0x7e000 bytes disk.
- * (bug or feature?)
- */
-static uint8_t boot_sector[0x7e000] = {
-    /* 7c00: mov $0xdead,%ax */
-    [0x00] = 0xb8,
-    [0x01] = LOW(SIGNATURE),
-    [0x02] = HIGH(SIGNATURE),
-    /* 7c03:  mov %ax,0x7c10 */
-    [0x03] = 0xa3,
-    [0x04] = LOW(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET),
-    [0x05] = HIGH(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET),
-    /* 7c06: cli */
-    [0x06] = 0xfa,
-    /* 7c07: hlt */
-    [0x07] = 0xf4,
-    /* 7c08: jmp 0x7c07=0x7c0a-3 */
-    [0x08] = 0xeb,
-    [0x09] = LOW(-3),
-    /* We mov 0xdead here: set value to make debugging easier */
-    [SIGNATURE_OFFSET] = LOW(0xface),
-    [SIGNATURE_OFFSET + 1] = HIGH(0xface),
-    /* End of boot sector marker */
-    [0x1FE] = 0x55,
-    [0x1FF] = 0xAA,
-};
-
 static const char *disk = "tests/acpi-test-disk.raw";
 static const char *data_dir = "tests/acpi-test-data";
 #ifdef CONFIG_IASL
@@ -737,10 +702,6 @@ static void test_smbios_structs(test_data *data)
 static void test_acpi_one(const char *params, test_data *data)
 {
     char *args;
-    uint8_t signature_low;
-    uint8_t signature_high;
-    uint16_t signature;
-    int i;
 
     args = g_strdup_printf("-net none -display none %s "
                            "-drive id=hd0,if=none,file=%s,format=raw "
@@ -749,24 +710,7 @@ static void test_acpi_one(const char *params, test_data *data)
 
     qtest_start(args);
 
-   /* Wait at most 1 minute */
-#define TEST_DELAY (1 * G_USEC_PER_SEC / 10)
-#define TEST_CYCLES MAX((60 * G_USEC_PER_SEC / TEST_DELAY), 1)
-
-    /* Poll until code has run and modified memory.  Once it has we know BIOS
-     * initialization is done.  TODO: check that IP reached the halt
-     * instruction.
-     */
-    for (i = 0; i < TEST_CYCLES; ++i) {
-        signature_low = readb(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET);
-        signature_high = readb(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET + 1);
-        signature = (signature_high << 8) | signature_low;
-        if (signature == SIGNATURE) {
-            break;
-        }
-        g_usleep(TEST_DELAY);
-    }
-    g_assert_cmphex(signature, ==, SIGNATURE);
+    boot_sector_test();
 
     test_acpi_rsdp_address(data);
     test_acpi_rsdp_table(data);
@@ -840,15 +784,11 @@ static void test_acpi_q35_tcg_bridge(void)
 int main(int argc, char *argv[])
 {
     const char *arch = qtest_get_arch();
-    FILE *f = fopen(disk, "w");
     int ret;
 
-    if (!f) {
-        fprintf(stderr, "Couldn't open \"%s\": %s", disk, strerror(errno));
-        return 1;
-    }
-    fwrite(boot_sector, 1, sizeof boot_sector, f);
-    fclose(f);
+    ret = boot_sector_init(disk);
+    if(ret)
+        return ret;
 
     g_test_init(&argc, &argv, NULL);
 
@@ -859,6 +799,6 @@ int main(int argc, char *argv[])
         qtest_add_func("acpi/q35/tcg/bridge", test_acpi_q35_tcg_bridge);
     }
     ret = g_test_run();
-    unlink(disk);
+    boot_sector_cleanup(disk);
     return ret;
 }
diff --git a/tests/boot-sector.c b/tests/boot-sector.c
new file mode 100644
index 0000000000..0b48bb34bf
--- /dev/null
+++ b/tests/boot-sector.c
@@ -0,0 +1,119 @@
+/*
+ * QEMU boot sector testing helpers.
+ *
+ * Copyright (c) 2016 Red Hat Inc.
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *  Victor Kaplansky <victork@redhat.com>    
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "boot-sector.h"
+#include <string.h>
+#include <stdio.h>
+#include "qemu-common.h"
+#include "libqtest.h"
+
+#define LOW(x) ((x) & 0xff)
+#define HIGH(x) ((x) >> 8)
+
+#define SIGNATURE 0xdead
+#define SIGNATURE_OFFSET 0x10
+#define BOOT_SECTOR_ADDRESS 0x7c00
+
+/* Boot sector code: write SIGNATURE into memory,
+ * then halt.
+ * Q35 machine requires a minimum 0x7e000 bytes disk.
+ * (bug or feature?)
+ */
+static uint8_t boot_sector[0x7e000] = {
+    /* The first sector will be placed at RAM address 00007C00, and
+     * the BIOS transfers control to 00007C00
+     */
+
+    /* Data Segment register should be initialized, since pxe
+     * boot loader can leave it dirty.
+     */
+
+    /* 7c00: move $0000,%ax */
+    [0x00] = 0xb8,
+    [0x01] = 0x00,
+    [0x02] = 0x00,
+    /* 7c03: move %ax,%ds */
+    [0x03] = 0x8e,
+    [0x04] = 0xd8,
+
+    /* 7c05: mov $0xdead,%ax */
+    [0x05] = 0xb8,
+    [0x06] = LOW(SIGNATURE),
+    [0x07] = HIGH(SIGNATURE),
+    /* 7c08:  mov %ax,0x7c10 */
+    [0x08] = 0xa3,
+    [0x09] = LOW(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET),
+    [0x0a] = HIGH(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET),
+
+    /* 7c0b cli */
+    [0x0b] = 0xfa,
+    /* 7c0c: hlt */
+    [0x0c] = 0xf4,
+    /* 7c0e: jmp 0x7c07=0x7c0f-3 */
+    [0x0d] = 0xeb,
+    [0x0e] = LOW(-3),
+    /* We mov 0xdead here: set value to make debugging easier */
+    [SIGNATURE_OFFSET] = LOW(0xface),
+    [SIGNATURE_OFFSET + 1] = HIGH(0xface),
+    /* End of boot sector marker */
+    [0x1FE] = 0x55,
+    [0x1FF] = 0xAA,
+};
+
+/* Create boot disk file.  */
+int boot_sector_init(const char *fname)
+{
+    FILE *f = fopen(fname, "w");
+
+    if (!f) {
+        fprintf(stderr, "Couldn't open \"%s\": %s", fname, strerror(errno));
+        return 1;
+    }
+    fwrite(boot_sector, 1, sizeof boot_sector, f);
+    fclose(f);
+    return 0;
+}
+
+/* Loop until signature in memory is OK.  */
+void boot_sector_test(void)
+{
+    uint8_t signature_low;
+    uint8_t signature_high;
+    uint16_t signature;
+    int i;
+
+   /* Wait at most 1 minute */
+#define TEST_DELAY (1 * G_USEC_PER_SEC / 10)
+#define TEST_CYCLES MAX((60 * G_USEC_PER_SEC / TEST_DELAY), 1)
+
+    /* Poll until code has run and modified memory.  Once it has we know BIOS
+     * initialization is done.  TODO: check that IP reached the halt
+     * instruction.
+     */
+    for (i = 0; i < TEST_CYCLES; ++i) {
+        signature_low = readb(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET);
+        signature_high = readb(BOOT_SECTOR_ADDRESS + SIGNATURE_OFFSET + 1);
+        signature = (signature_high << 8) | signature_low;
+        if (signature == SIGNATURE) {
+            break;
+        }
+        g_usleep(TEST_DELAY);
+    }
+
+    g_assert_cmphex(signature, ==, SIGNATURE);
+}
+
+/* unlink boot disk file.  */
+void boot_sector_cleanup(const char *fname)
+{
+    unlink(fname);
+}
diff --git a/tests/boot-sector.h b/tests/boot-sector.h
new file mode 100644
index 0000000000..38be0290e3
--- /dev/null
+++ b/tests/boot-sector.h
@@ -0,0 +1,26 @@
+/*
+ * QEMU boot sector testing helpers.
+ *
+ * Copyright (c) 2016 Red Hat Inc.
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *  Victor Kaplansky <victork@redhat.com>    
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef TEST_BOOT_SECTOR
+#define TEST_BOOT_SECTOR
+
+/* Create boot disk file.  */
+int boot_sector_init(const char *fname);
+
+/* Loop until signature in memory is OK.  */
+void boot_sector_test(void);
+
+/* unlink boot disk file.  */
+void boot_sector_cleanup(const char *fname);
+
+#endif /* TEST_BOOT_SECTOR */
diff --git a/tests/pxe-test.c b/tests/pxe-test.c
new file mode 100644
index 0000000000..fa430958ea
--- /dev/null
+++ b/tests/pxe-test.c
@@ -0,0 +1,69 @@
+/*
+ * PXE test cases.
+ *
+ * Copyright (c) 2016 Red Hat Inc.
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>,
+ *  Victor Kaplansky <victork@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <string.h>
+#include <stdio.h>
+#include <glib.h>
+#include <glib/gstdio.h>
+#include "qemu-common.h"
+#include "libqtest.h"
+#include "boot-sector.h"
+
+#define NETNAME "net0"
+
+static const char *disk = "tests/pxe-test-disk.raw";
+
+static void test_pxe_one(const char *params)
+{
+    char *args;
+
+    args = g_strdup_printf("-machine accel=tcg "
+                           "-netdev user,id=" NETNAME ",tftp=./,bootfile=%s "
+                           "%s ",
+                           disk, params);
+
+    qtest_start(args);
+    boot_sector_test();
+    qtest_quit(global_qtest);
+    g_free(args);
+}
+
+static void test_pxe_e1000(void)
+{
+    test_pxe_one("-device e1000,netdev=" NETNAME);
+}
+
+static void test_pxe_virtio_pci(void)
+{
+    test_pxe_one("-device virtio-net-pci,netdev=" NETNAME);
+}
+
+int main(int argc, char *argv[])
+{
+    int ret;
+    const char *arch = qtest_get_arch();
+
+    ret = boot_sector_init(disk);
+    if(ret)
+        return ret;
+
+    g_test_init(&argc, &argv, NULL);
+
+    if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) {
+        qtest_add_func("pxe/e1000", test_pxe_e1000);
+        qtest_add_func("pxe/virtio", test_pxe_virtio_pci);
+    }
+    ret = g_test_run();
+    boot_sector_cleanup(disk);
+    return ret;
+}
diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c
index 9a1ad5a1bb..f2b6c67e5b 100644
--- a/tests/vhost-user-bridge.c
+++ b/tests/vhost-user-bridge.c
@@ -37,6 +37,7 @@
 #include <sys/eventfd.h>
 #include <arpa/inet.h>
 #include <netdb.h>
+#include <qemu/osdep.h>
 
 #include <linux/vhost.h>
 
@@ -176,6 +177,8 @@ typedef struct VubrVirtq {
 
 #define VHOST_MEMORY_MAX_NREGIONS    8
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
+/* v1.0 compliant. */
+#define VIRTIO_F_VERSION_1		32
 
 #define VHOST_LOG_PAGE 4096
 
@@ -284,6 +287,7 @@ typedef struct VubrDev {
     struct sockaddr_in backend_udp_dest;
     int ready;
     uint64_t features;
+    int hdrlen;
 } VubrDev;
 
 static const char *vubr_request_str[] = {
@@ -474,7 +478,8 @@ vubr_backend_udp_recvbuf(VubrDev *dev, uint8_t *buf, size_t buflen)
 static void
 vubr_consume_raw_packet(VubrDev *dev, uint8_t *buf, uint32_t len)
 {
-    int hdrlen = sizeof(struct virtio_net_hdr_v1);
+    int hdrlen = dev->hdrlen;
+    DPRINT("    hdrlen = %d\n", dev->hdrlen);
 
     if (VHOST_USER_BRIDGE_DEBUG) {
         print_buffer(buf, len);
@@ -536,6 +541,7 @@ vubr_post_buffer(VubrDev *dev, VubrVirtq *vq, uint8_t *buf, int32_t len)
     struct vring_avail *avail = vq->avail;
     struct vring_used *used = vq->used;
     uint64_t log_guest_addr = vq->log_guest_addr;
+    int32_t remaining_len = len;
 
     unsigned int size = vq->size;
 
@@ -550,36 +556,49 @@ vubr_post_buffer(VubrDev *dev, VubrVirtq *vq, uint8_t *buf, int32_t len)
     uint16_t d_index = avail->ring[a_index];
 
     int i = d_index;
+    uint32_t written_len = 0;
 
-    DPRINT("Post packet to guest on vq:\n");
-    DPRINT("    size             = %d\n", vq->size);
-    DPRINT("    last_avail_index = %d\n", vq->last_avail_index);
-    DPRINT("    last_used_index  = %d\n", vq->last_used_index);
-    DPRINT("    a_index = %d\n", a_index);
-    DPRINT("    u_index = %d\n", u_index);
-    DPRINT("    d_index = %d\n", d_index);
-    DPRINT("    desc[%d].addr    = 0x%016"PRIx64"\n", i, desc[i].addr);
-    DPRINT("    desc[%d].len     = %d\n", i, desc[i].len);
-    DPRINT("    desc[%d].flags   = %d\n", i, desc[i].flags);
-    DPRINT("    avail->idx = %d\n", avail_index);
-    DPRINT("    used->idx  = %d\n", used->idx);
-
-    if (!(desc[i].flags & VRING_DESC_F_WRITE)) {
-        /* FIXME: we should find writable descriptor. */
-        fprintf(stderr, "Error: descriptor is not writable. Exiting.\n");
-        exit(1);
-    }
+    do {
+        DPRINT("Post packet to guest on vq:\n");
+        DPRINT("    size             = %d\n", vq->size);
+        DPRINT("    last_avail_index = %d\n", vq->last_avail_index);
+        DPRINT("    last_used_index  = %d\n", vq->last_used_index);
+        DPRINT("    a_index = %d\n", a_index);
+        DPRINT("    u_index = %d\n", u_index);
+        DPRINT("    d_index = %d\n", d_index);
+        DPRINT("    desc[%d].addr    = 0x%016"PRIx64"\n", i, desc[i].addr);
+        DPRINT("    desc[%d].len     = %d\n", i, desc[i].len);
+        DPRINT("    desc[%d].flags   = %d\n", i, desc[i].flags);
+        DPRINT("    avail->idx = %d\n", avail_index);
+        DPRINT("    used->idx  = %d\n", used->idx);
+
+        if (!(desc[i].flags & VRING_DESC_F_WRITE)) {
+            /* FIXME: we should find writable descriptor. */
+            fprintf(stderr, "Error: descriptor is not writable. Exiting.\n");
+            exit(1);
+        }
 
-    void *chunk_start = (void *)gpa_to_va(dev, desc[i].addr);
-    uint32_t chunk_len = desc[i].len;
+        void *chunk_start = (void *)gpa_to_va(dev, desc[i].addr);
+        uint32_t chunk_len = desc[i].len;
+        uint32_t chunk_write_len = MIN(remaining_len, chunk_len);
 
-    if (len <= chunk_len) {
-        memcpy(chunk_start, buf, len);
-        vubr_log_write(dev, desc[i].addr, len);
-    } else {
-        fprintf(stderr,
-                "Received too long packet from the backend. Dropping...\n");
-        return;
+        memcpy(chunk_start, buf + written_len, chunk_write_len);
+        vubr_log_write(dev, desc[i].addr, chunk_write_len);
+        remaining_len -= chunk_write_len;
+        written_len += chunk_write_len;
+
+        if ((remaining_len == 0) || !(desc[i].flags & VRING_DESC_F_NEXT)) {
+            break;
+        }
+
+        i = desc[i].next;
+    } while (1);
+
+    if (remaining_len > 0) {
+            fprintf(stderr,
+                    "Too long packet for RX, remaining_len = %d, Dropping...\n",
+                    remaining_len);
+            return;
     }
 
     /* Add descriptor to the used ring. */
@@ -687,7 +706,7 @@ vubr_backend_recv_cb(int sock, void *ctx)
     VubrVirtq *rx_vq = &dev->vq[0];
     uint8_t buf[4096];
     struct virtio_net_hdr_v1 *hdr = (struct virtio_net_hdr_v1 *)buf;
-    int hdrlen = sizeof(struct virtio_net_hdr_v1);
+    int hdrlen = dev->hdrlen;
     int buflen = sizeof(buf);
     int len;
 
@@ -696,6 +715,7 @@ vubr_backend_recv_cb(int sock, void *ctx)
     }
 
     DPRINT("\n\n   ***   IN UDP RECEIVE CALLBACK    ***\n\n");
+    DPRINT("    hdrlen = %d\n", hdrlen);
 
     uint16_t avail_index = atomic_mb_read(&rx_vq->avail->idx);
 
@@ -707,10 +727,12 @@ vubr_backend_recv_cb(int sock, void *ctx)
         return;
     }
 
+    memset(buf, 0, hdrlen);
+    /* TODO: support mergeable buffers. */
+    if (hdrlen == 12)
+        hdr->num_buffers = 1;
     len = vubr_backend_udp_recvbuf(dev, buf + hdrlen, buflen - hdrlen);
 
-    *hdr = (struct virtio_net_hdr_v1) { };
-    hdr->num_buffers = 1;
     vubr_post_buffer(dev, rx_vq, buf, len + hdrlen);
 }
 
@@ -758,7 +780,15 @@ static int
 vubr_set_features_exec(VubrDev *dev, VhostUserMsg *vmsg)
 {
     DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
+
     dev->features = vmsg->payload.u64;
+    if ((dev->features & (1ULL << VIRTIO_F_VERSION_1)) ||
+        (dev->features & (1ULL << VIRTIO_NET_F_MRG_RXBUF))) {
+        dev->hdrlen = 12;
+    } else {
+        dev->hdrlen = 10;
+    }
+
     return 0;
 }