The following changes since commit 97c81ef4b8e203d9620fd46e7eb77004563e3675:

Merge tag 'pull-9p-20230706' of https://github.com/cschoenebeck/qemu into staging (2023-07-06 18:19:42 +0100)

for you to fetch changes up to da9f7f7769e8e65f6423095e978f9a375e33515c:

igb: Remove obsolete workaround for Windows (2023-07-07 16:35:12 +0800)

Akihiko Odaki (2):

e1000e: Add ICR clearing by corresponding IMS bit

igb: Remove obsolete workaround for Windows

Bin Meng (9):

hw/net: e1000: Remove the logic of padding short frames in the receive path

hw/net: vmxnet3: Remove the logic of padding short frames in the receive path

hw/net: i82596: Remove the logic of padding short frames in the receive path

hw/net: ne2000: Remove the logic of padding short frames in the receive path

hw/net: pcnet: Remove the logic of padding short frames in the receive path

hw/net: rtl8139: Remove the logic of padding short frames in the receive path

hw/net: sungem: Remove the logic of padding short frames in the receive path

hw/net: sunhme: Remove the logic of padding short frames in the receive path

hw/net: ftgmac100: Drop the small packet check in the receive path

Laurent Vivier (4):

virtio-net: correctly report maximum tx_queue_size value

net: socket: prepare to cleanup net_init_socket()

net: socket: move fd type checking to its own function

net: socket: remove net_init_socket()

hw/net/e1000.c | 11 +----------

hw/net/e1000e_core.c | 38 +++++++++++++++++++++++++++++++------

hw/net/ftgmac100.c | 8 --------

hw/net/i82596.c | 18 ------------------

hw/net/igb_core.c | 7 +------

hw/net/ne2000.c | 12 ------------

hw/net/pcnet.c | 9 ---------

hw/net/rtl8139.c | 12 ------------

hw/net/sungem.c | 14 --------------

hw/net/sunhme.c | 11 -----------

hw/net/trace-events | 1 +

hw/net/virtio-net.c | 4 ++--

hw/net/vmxnet3.c | 10 ----------

net/socket.c | 53 +++++++++++++++++++++++++++-------------------------

14 files changed, 65 insertions(+), 143 deletions(-)

From: Bin Meng <bmeng@tinylab.org>

Now that we have implemented unified short frames padding in the

QEMU networking codes, remove the same logic in the NIC codes.

Signed-off-by: Bin Meng <bmeng@tinylab.org>

hw/net/ne2000.c | 12 ------------

1 file changed, 12 deletions(-)

diff --git a/hw/net/ne2000.c b/hw/net/ne2000.c

--- a/hw/net/ne2000.c

+++ b/hw/net/ne2000.c

@@ -XXX,XX +XXX,XX @@ static int ne2000_buffer_full(NE2000State *s)

-#define MIN_BUF_SIZE 60

-

ssize_t ne2000_receive(NetClientState *nc, const uint8_t *buf, size_t size_)

NE2000State *s = qemu_get_nic_opaque(nc);

size_t size = size_;

uint8_t *p;

unsigned int total_len, next, avail, len, index, mcast_idx;

- uint8_t buf1[60];

static const uint8_t broadcast_macaddr[6] =

{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };

@@ -XXX,XX +XXX,XX @@ ssize_t ne2000_receive(NetClientState *nc, const uint8_t *buf, size_t size_)

}

- /* if too small buffer, then expand it */

- if (size < MIN_BUF_SIZE) {

- memcpy(buf1, buf, size);

- memset(buf1 + size, 0, MIN_BUF_SIZE - size);

- buf = buf1;

- size = MIN_BUF_SIZE;

- }

index = s->curpag << 8;

if (index >= NE2000_PMEM_END) {

index = s->start;

From: Bin Meng <bmeng@tinylab.org>

Now that we have implemented unified short frames padding in the

QEMU networking codes, remove the same logic in the NIC codes.

Signed-off-by: Bin Meng <bmeng@tinylab.org>

hw/net/rtl8139.c | 12 ------------

1 file changed, 12 deletions(-)

diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c

--- a/hw/net/rtl8139.c

+++ b/hw/net/rtl8139.c

@@ -XXX,XX +XXX,XX @@ static ssize_t rtl8139_do_receive(NetClientState *nc, const uint8_t *buf, size_t

uint32_t packet_header = 0;

- uint8_t buf1[MIN_BUF_SIZE + VLAN_HLEN];

static const uint8_t broadcast_macaddr[6] =

{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };

@@ -XXX,XX +XXX,XX @@ static ssize_t rtl8139_do_receive(NetClientState *nc, const uint8_t *buf, size_t

From: Bin Meng <bmeng@tinylab.org>

Now that we have implemented unified short frames padding in the

QEMU networking codes, the small packet check logic in the receive

path is no longer needed.

Suggested-by: Cédric Le Goater <clg@kaod.org>

Reviewed-by: Cédric Le Goater <clg@kaod.org>

Signed-off-by: Bin Meng <bmeng@tinylab.org>

hw/net/ftgmac100.c | 8 --------

1 file changed, 8 deletions(-)

diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c

--- a/hw/net/ftgmac100.c

+++ b/hw/net/ftgmac100.c

@@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf,

return -1;

}

- /* TODO : Pad to minimum Ethernet frame length */

- /* handle small packets. */

- if (size < 10) {

- qemu_log_mask(LOG_GUEST_ERROR, "%s: dropped frame of %zd bytes\n",

- __func__, size);

- return size;

- }

-

if (!ftgmac100_filter(s, buf, size)) {

return size;

}

From: Laurent Vivier <lvivier@redhat.com>

Move the file descriptor type checking before doing anything with it.

If it's not usable, don't close it as it could be in use by another

part of QEMU, only fail and report an error.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

Signed-off-by: Laurent Vivier <lvivier@redhat.com>

net/socket.c | 43 +++++++++++++++++--------------------------

1 file changed, 17 insertions(+), 26 deletions(-)

diff --git a/net/socket.c b/net/socket.c

--- a/net/socket.c

+++ b/net/socket.c

@@ -XXX,XX +XXX,XX @@ static int net_socket_fd_check(int fd, Error **errp)

return so_type;

}

-static NetSocketState *net_socket_fd_init(NetClientState *peer,

- const char *model, const char *name,

- int fd, int is_connected,

- const char *mc, Error **errp)

-{

- int so_type;

-

- so_type = net_socket_fd_check(fd, errp);

- if (so_type < 0) {

- close(fd);

- return NULL;

- }

- switch(so_type) {

- case SOCK_DGRAM:

- return net_socket_fd_init_dgram(peer, model, name, fd, is_connected,

- mc, errp);

- case SOCK_STREAM:

- return net_socket_fd_init_stream(peer, model, name, fd, is_connected);

- }

- return NULL;

-}

-

static void net_socket_accept(void *opaque)

{

NetSocketState *s = opaque;

@@ -XXX,XX +XXX,XX @@ int net_init_socket(const Netdev *netdev, const char *name,

}

if (sock->fd) {

- int fd, ret;

+ int fd, ret, so_type;

fd = monitor_fd_param(monitor_cur(), sock->fd, errp);

if (fd == -1) {

return -1;

}

+ so_type = net_socket_fd_check(fd, errp);

+ if (so_type < 0) {

+ return -1;

+ }

ret = qemu_socket_try_set_nonblock(fd);

- if (!net_socket_fd_init(peer, "socket", name, fd, 1, sock->mcast,

- errp)) {

- return -1;

+ switch (so_type) {

+ case SOCK_DGRAM:

+ if (!net_socket_fd_init_dgram(peer, "socket", name, fd, 1,

+ sock->mcast, errp)) {

+ return -1;

+ }

+ break;

+ case SOCK_STREAM:

+ if (!net_socket_fd_init_stream(peer, "socket", name, fd, 1)) {

+ return -1;

+ }

+ break;

return 0;

}

From: Akihiko Odaki <akihiko.odaki@daynix.com>

The datasheet does not say what happens when interrupt was asserted

(ICR.INT_ASSERT=1) and auto mask is *not* active.

However, section of 13.3.27 the PCIe* GbE Controllers Open Source

Software Developer’s Manual, which were written for older devices,

namely 631xESB/632xESB, 82563EB/82564EB, 82571EB/82572EI &

82573E/82573V/82573L, does say:

> If IMS = 0b, then the ICR register is always clear-on-read. If IMS is

> not 0b, but some ICR bit is set where the corresponding IMS bit is not

> set, then a read does not clear the ICR register. For example, if

> IMS = 10101010b and ICR = 01010101b, then a read to the ICR register

> does not clear it. If IMS = 10101010b and ICR = 0101011b, then a read

> to the ICR register clears it entirely (ICR.INT_ASSERTED = 1b).

Linux does no longer activate auto mask since commit

0a8047ac68e50e4ccbadcfc6b6b070805b976885 and the real hardware clears

ICR even in such a case so we also should do so.

Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1707441

Signed-off-by: Andrew Melnychenko <andrew@daynix.com>

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>

hw/net/e1000e_core.c | 38 ++++++++++++++++++++++++++++++++------

hw/net/trace-events | 1 +

2 files changed, 33 insertions(+), 6 deletions(-)

@@ -XXX,XX +XXX,XX @@ e1000e_mac_icr_read(E1000ECore *core, int index)

e1000e_lower_interrupts(core, ICR, 0xffffffff);

}

- if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&

- (core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {

- trace_e1000e_irq_icr_clear_iame();

- e1000e_lower_interrupts(core, ICR, 0xffffffff);

- trace_e1000e_irq_icr_process_iame();

- e1000e_lower_interrupts(core, IMS, core->mac[IAM]);

+ if (core->mac[ICR] & E1000_ICR_ASSERTED) {

+ if (core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME) {

+ trace_e1000e_irq_icr_clear_iame();

+ e1000e_lower_interrupts(core, ICR, 0xffffffff);

+ trace_e1000e_irq_icr_process_iame();

+ e1000e_lower_interrupts(core, IMS, core->mac[IAM]);

+

+ /*

+ * The datasheet does not say what happens when interrupt was asserted

+ * (ICR.INT_ASSERT=1) and auto mask is *not* active.

+ * However, section of 13.3.27 the PCIe* GbE Controllers Open Source

+ * Software Developer’s Manual, which were written for older devices,

+ * namely 631xESB/632xESB, 82563EB/82564EB, 82571EB/82572EI &

+ * 82573E/82573V/82573L, does say:

+ * > If IMS = 0b, then the ICR register is always clear-on-read. If IMS

+ * > is not 0b, but some ICR bit is set where the corresponding IMS bit

+ * > is not set, then a read does not clear the ICR register. For

+ * > example, if IMS = 10101010b and ICR = 01010101b, then a read to the

+ * > ICR register does not clear it. If IMS = 10101010b and

+ * > ICR = 0101011b, then a read to the ICR register clears it entirely

+ * > (ICR.INT_ASSERTED = 1b).

+ *

+ * Linux does no longer activate auto mask since commit

+ * 0a8047ac68e50e4ccbadcfc6b6b070805b976885 and the real hardware

+ * clears ICR even in such a case so we also should do so.

+ */

+ if (core->mac[ICR] & core->mac[IMS]) {

+ trace_e1000e_irq_icr_clear_icr_bit_ims(core->mac[ICR],

+ core->mac[IMS]);

+ e1000e_lower_interrupts(core, ICR, 0xffffffff);

+ }

}

return ret;

diff --git a/hw/net/trace-events b/hw/net/trace-events

index XXXXXXX..XXXXXXX 100644

--- a/hw/net/trace-events

+++ b/hw/net/trace-events

@@ -XXX,XX +XXX,XX @@ e1000e_irq_read_ims(uint32_t ims) "Current IMS: 0x%x"

e1000e_irq_icr_clear_nonmsix_icr_read(void) "Clearing ICR on read due to non MSI-X int"

e1000e_irq_icr_clear_zero_ims(void) "Clearing ICR on read due to zero IMS"

e1000e_irq_icr_clear_iame(void) "Clearing ICR on read due to IAME"

+e1000e_irq_icr_clear_icr_bit_ims(uint32_t icr, uint32_t ims) "Clearing ICR on read due corresponding IMS bit: 0x%x & 0x%x"

e1000e_irq_iam_clear_eiame(uint32_t iam, uint32_t cause) "Clearing IMS due to EIAME, IAM: 0x%X, cause: 0x%X"

e1000e_irq_icr_clear_eiac(uint32_t icr, uint32_t eiac) "Clearing ICR bits due to EIAC, ICR: 0x%X, EIAC: 0x%X"

e1000e_irq_ims_clear_set_imc(uint32_t val) "Clearing IMS bits due to IMC write 0x%x"