* [PATCH net-next v5 3/4] test/vsock: Add retry mechanism to ioctl wrapper
From: Xuewei Niu @ 2025-07-06 4:36 UTC (permalink / raw)
To: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman
Cc: linux-hyperv, virtualization, netdev, linux-kernel, Xuewei Niu,
fupan.lfp
In-Reply-To: <20250706-siocinq-v5-0-8d0b96a87465@antgroup.com>
Wrap the ioctl in `ioctl_int()`, which takes a pointer to the actual
int value and an expected int value. The function will not return until
either the ioctl returns the expected value or a timeout occurs, thus
avoiding immediate failure.
Signed-off-by: Xuewei Niu <niuxuewei.nxw@antgroup.com>
---
tools/testing/vsock/util.c | 30 +++++++++++++++++++++---------
tools/testing/vsock/util.h | 1 +
2 files changed, 22 insertions(+), 9 deletions(-)
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 803f1e075b62228c25f9dffa1eff131b8072a06a..1e65c5abd85b8bcf5886272de15437d7be13eb89 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -17,6 +17,7 @@
#include <unistd.h>
#include <assert.h>
#include <sys/epoll.h>
+#include <sys/ioctl.h>
#include <sys/mman.h>
#include <linux/sockios.h>
@@ -101,28 +102,39 @@ void vsock_wait_remote_close(int fd)
close(epollfd);
}
-/* Wait until transport reports no data left to be sent.
- * Return false if transport does not implement the unsent_bytes() callback.
+/* Wait until ioctl gives an expected int value.
+ * Return false if the op is not supported.
*/
-bool vsock_wait_sent(int fd)
+bool vsock_ioctl_int(int fd, unsigned long op, int expected)
{
- int ret, sock_bytes_unsent;
+ int actual, ret;
+ char name[32];
+
+ snprintf(name, sizeof(name), "ioctl(%lu)", op);
timeout_begin(TIMEOUT);
do {
- ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+ ret = ioctl(fd, op, &actual);
if (ret < 0) {
if (errno == EOPNOTSUPP)
break;
- perror("ioctl(SIOCOUTQ)");
+ perror(name);
exit(EXIT_FAILURE);
}
- timeout_check("SIOCOUTQ");
- } while (sock_bytes_unsent != 0);
+ timeout_check(name);
+ } while (actual != expected);
timeout_end();
- return !ret;
+ return ret >= 0;
+}
+
+/* Wait until transport reports no data left to be sent.
+ * Return false if transport does not implement the unsent_bytes() callback.
+ */
+bool vsock_wait_sent(int fd)
+{
+ return vsock_ioctl_int(fd, SIOCOUTQ, 0);
}
/* Create socket <type>, bind to <cid, port>.
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fdd4649fe2d49f57c93c4aa5dfbb37b710c65918..142c02a6834acb7117aca485b661332b73754b63 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -87,6 +87,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port);
int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp);
void vsock_wait_remote_close(int fd);
+bool vsock_ioctl_int(int fd, unsigned long op, int expected);
bool vsock_wait_sent(int fd);
void send_buf(int fd, const void *buf, size_t len, int flags,
ssize_t expected_ret);
--
2.34.1
^ permalink raw reply related
* [PATCH net-next v5 4/4] test/vsock: Add ioctl SIOCINQ tests
From: Xuewei Niu @ 2025-07-06 4:36 UTC (permalink / raw)
To: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman
Cc: linux-hyperv, virtualization, netdev, linux-kernel, Xuewei Niu,
fupan.lfp
In-Reply-To: <20250706-siocinq-v5-0-8d0b96a87465@antgroup.com>
Add SIOCINQ ioctl tests for both SOCK_STREAM and SOCK_SEQPACKET.
The client waits for the server to send data, and checks if the SIOCINQ
ioctl value matches the data size. After consuming the data, the client
checks if the SIOCINQ value is 0.
Signed-off-by: Xuewei Niu <niuxuewei.nxw@antgroup.com>
---
tools/testing/vsock/vsock_test.c | 79 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 79 insertions(+)
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index be6ce764f69480c0f9c3e2288fc19cd2e74be148..a66d2360133dd0e36940a5907679aeacc8af7714 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -24,6 +24,7 @@
#include <linux/time64.h>
#include <pthread.h>
#include <fcntl.h>
+#include <linux/sockios.h>
#include "vsock_test_zerocopy.h"
#include "timeout.h"
@@ -1307,6 +1308,54 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
close(fd);
}
+static void test_unread_bytes_server(const struct test_opts *opts, int type)
+{
+ unsigned char buf[MSG_BUF_IOCTL_LEN];
+ int client_fd;
+
+ client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type);
+ if (client_fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ for (int i = 0; i < sizeof(buf); i++)
+ buf[i] = rand() & 0xFF;
+
+ send_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf));
+ control_writeln("SENT");
+
+ close(client_fd);
+}
+
+static void test_unread_bytes_client(const struct test_opts *opts, int type)
+{
+ unsigned char buf[MSG_BUF_IOCTL_LEN];
+ int fd;
+
+ fd = vsock_connect(opts->peer_cid, opts->peer_port, type);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ control_expectln("SENT");
+ /* The data has arrived but has not been read. The expected is
+ * MSG_BUF_IOCTL_LEN.
+ */
+ if (!vsock_ioctl_int(fd, SIOCINQ, MSG_BUF_IOCTL_LEN)) {
+ fprintf(stderr, "Test skipped, SIOCINQ not supported.\n");
+ goto out;
+ }
+
+ recv_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
+ /* All data has been consumed, so the expected is 0. */
+ vsock_ioctl_int(fd, SIOCINQ, 0);
+
+out:
+ close(fd);
+}
+
static void test_stream_unsent_bytes_client(const struct test_opts *opts)
{
test_unsent_bytes_client(opts, SOCK_STREAM);
@@ -1327,6 +1376,26 @@ static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts)
test_unsent_bytes_server(opts, SOCK_SEQPACKET);
}
+static void test_stream_unread_bytes_client(const struct test_opts *opts)
+{
+ test_unread_bytes_client(opts, SOCK_STREAM);
+}
+
+static void test_stream_unread_bytes_server(const struct test_opts *opts)
+{
+ test_unread_bytes_server(opts, SOCK_STREAM);
+}
+
+static void test_seqpacket_unread_bytes_client(const struct test_opts *opts)
+{
+ test_unread_bytes_client(opts, SOCK_SEQPACKET);
+}
+
+static void test_seqpacket_unread_bytes_server(const struct test_opts *opts)
+{
+ test_unread_bytes_server(opts, SOCK_SEQPACKET);
+}
+
#define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128)
/* This define is the same as in 'include/linux/virtio_vsock.h':
* it is used to decide when to send credit update message during
@@ -2276,6 +2345,16 @@ static struct test_case test_cases[] = {
.run_client = test_stream_transport_change_client,
.run_server = test_stream_transport_change_server,
},
+ {
+ .name = "SOCK_STREAM ioctl(SIOCINQ) functionality",
+ .run_client = test_stream_unread_bytes_client,
+ .run_server = test_stream_unread_bytes_server,
+ },
+ {
+ .name = "SOCK_SEQPACKET ioctl(SIOCINQ) functionality",
+ .run_client = test_seqpacket_unread_bytes_client,
+ .run_server = test_seqpacket_unread_bytes_server,
+ },
{},
};
--
2.34.1
^ permalink raw reply related
* Re: [PATCH] irqdomain: Export irq_domain_free_irqs_top()
From: Thomas Gleixner @ 2025-07-06 10:01 UTC (permalink / raw)
To: Nam Cao, K . Y . Srinivasan, Michael Kelley, Bjorn Helgaas,
Haiyang Zhang, Wei Liu, Dexuan Cui, linux-hyperv
Cc: Nam Cao
In-Reply-To: <20250703212054.2561551-1-namcao@linutronix.de>
On Thu, Jul 03 2025 at 23:20, Nam Cao wrote:
> Export irq_domain_free_irqs_top(), making it usable for drivers compiled as
> modules.
>
> Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
This should go with the fixed-up HV driver.
^ permalink raw reply
* RE: [PATCH v2 1/6] PCI: hv: Don't load the driver for baremetal root partition
From: Michael Kelley @ 2025-07-07 3:12 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-2-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> From: Mukesh Rathor <mrathor@linux.microsoft.com>
>
> The root partition only uses VMBus when running nested.
>
> When running on baremetal the Hyper-V PCI driver is not needed,
> so do not initialize it.
>
> Signed-off-by: Mukesh Rathor <mrathor@linux.microsoft.com>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
> ---
> drivers/pci/controller/pci-hyperv.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index b4f29ee75848..4d25754dfe2f 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -4150,6 +4150,9 @@ static int __init init_hv_pci_drv(void)
> if (!hv_is_hyperv_initialized())
> return -ENODEV;
>
> + if (hv_root_partition() && !hv_nested)
> + return -ENODEV;
> +
> ret = hv_pci_irqchip_init();
> if (ret)
> return ret;
> --
> 2.34.1
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
^ permalink raw reply
* RE: [PATCH v2 2/6] Drivers: hv: Use nested hypercall for post message and signal event
From: Michael Kelley @ 2025-07-07 3:13 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-3-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> When running nested, these hypercalls must be sent to the L0 hypervisor
> or VMBus will fail.
>
> Remove hv_do_nested_hypercall() and hv_do_fast_nested_hypercall8()
> altogether and open-code these cases, since there are only 2 and all
> they do is add the nested bit.
>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
> ---
> arch/x86/include/asm/mshyperv.h | 20 --------------------
> drivers/hv/connection.c | 7 +++++--
> drivers/hv/hv.c | 6 ++++--
> 3 files changed, 9 insertions(+), 24 deletions(-)
>
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 5ec92e3e2e37..e00a8431ef8e 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -111,12 +111,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input,
> void *output)
> return hv_status;
> }
>
> -/* Hypercall to the L0 hypervisor */
> -static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
> -{
> - return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
> -}
> -
> /* Fast hypercall with 8 bytes of input and no output */
> static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
> {
> @@ -164,13 +158,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
> return _hv_do_fast_hypercall8(control, input1);
> }
>
> -static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
> -{
> - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
> -
> - return _hv_do_fast_hypercall8(control, input1);
> -}
> -
> /* Fast hypercall with 16 bytes of input */
> static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
> {
> @@ -222,13 +209,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
> return _hv_do_fast_hypercall16(control, input1, input2);
> }
>
> -static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
> -{
> - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
> -
> - return _hv_do_fast_hypercall16(control, input1, input2);
> -}
> -
> extern struct hv_vp_assist_page **hv_vp_assist_page;
>
> static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
> index be490c598785..47c93cee1ef6 100644
> --- a/drivers/hv/connection.c
> +++ b/drivers/hv/connection.c
> @@ -518,8 +518,11 @@ void vmbus_set_event(struct vmbus_channel *channel)
> channel->sig_event, 0);
> else
> WARN_ON_ONCE(1);
> - } else {
> - hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
> + } else if (hv_nested) {
As coded, this won't make any hypercall for the non-nested case.
The "else if (hv_nested)" should be just "else".
Michael
> + u64 control = HVCALL_SIGNAL_EVENT;
> +
> + control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
> + hv_do_fast_hypercall8(control, channel->sig_event);
> }
> }
> EXPORT_SYMBOL_GPL(vmbus_set_event);
> diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
> index 308c8f279df8..b14c5f9e0ef2 100644
> --- a/drivers/hv/hv.c
> +++ b/drivers/hv/hv.c
> @@ -85,8 +85,10 @@ int hv_post_message(union hv_connection_id connection_id,
> else
> status = HV_STATUS_INVALID_PARAMETER;
> } else {
> - status = hv_do_hypercall(HVCALL_POST_MESSAGE,
> - aligned_msg, NULL);
> + u64 control = HVCALL_POST_MESSAGE;
> +
> + control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
> + status = hv_do_hypercall(control, aligned_msg, NULL);
> }
>
> local_irq_restore(flags);
> --
> 2.34.1
^ permalink raw reply
* RE: [PATCH v2 3/6] x86/hyperv: Fix usage of cpu_online_mask to get valid cpu
From: Michael Kelley @ 2025-07-07 3:13 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-4-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> Accessing cpu_online_mask here is problematic because the cpus read lock
> is not held in this context.
>
> However, cpu_online_mask isn't needed here since the effective affinity
> mask is guaranteed to be valid in this callback. So, just use
> cpumask_first() to get the cpu instead of ANDing it with cpus_online_mask
> unnecessarily.
>
> Fixes: e39397d1fd68 ("x86/hyperv: implement an MSI domain for root partition")
> Reported-by: Michael Kelley <mhklinux@outlook.com>
> Closes: https://lore.kernel.org/linux-hyperv/SN6PR02MB4157639630F8AD2D8FD8F52FD475A@SN6PR02MB4157.namprd02.prod.outlook.com/
> Suggested-by: Thomas Gleixner <tglx@linutronix.de>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> ---
> arch/x86/hyperv/irqdomain.c | 4 +---
> 1 file changed, 1 insertion(+), 3 deletions(-)
>
> diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
> index 31f0d29cbc5e..e28c317ac9e8 100644
> --- a/arch/x86/hyperv/irqdomain.c
> +++ b/arch/x86/hyperv/irqdomain.c
> @@ -192,7 +192,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> struct pci_dev *dev;
> struct hv_interrupt_entry out_entry, *stored_entry;
> struct irq_cfg *cfg = irqd_cfg(data);
> - const cpumask_t *affinity;
> int cpu;
> u64 status;
>
> @@ -204,8 +203,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> return;
> }
>
> - affinity = irq_data_get_effective_affinity_mask(data);
> - cpu = cpumask_first_and(affinity, cpu_online_mask);
> + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
>
> if (data->chip_data) {
> /*
> --
> 2.34.1
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
^ permalink raw reply
* RE: [PATCH v2 4/6] x86/hyperv: Clean up hv_map/unmap_interrupt() return values
From: Michael Kelley @ 2025-07-07 3:14 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-5-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> Fix the return values of these hypercall helpers so they return
> a negated errno either directly or via hv_result_to_errno().
>
> Update the callers to check for errno instead of using
> hv_status_success(), and remove redundant error printing.
>
> While at it, rearrange some variable declarations to adhere to style
> guidelines i.e. "reverse fir tree order".
>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> ---
> arch/x86/hyperv/irqdomain.c | 32 ++++++++++++++------------------
> drivers/iommu/hyperv-iommu.c | 33 ++++++++++++---------------------
> 2 files changed, 26 insertions(+), 39 deletions(-)
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
^ permalink raw reply
* RE: [PATCH v2 5/6] x86: hyperv: Expose hv_map_msi_interrupt function
From: Michael Kelley @ 2025-07-07 3:14 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-6-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
>
> This patch moves a part of currently internal logic into the
> hv_map_msi_interrupt function and makes it globally available helper
> function, which will be used to map PCI interrupts in case of root
> partition.
Commit message still has "this patch". See suggested wording
in my comment on v1 of this patch.
>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
> ---
> arch/x86/hyperv/irqdomain.c | 38 +++++++++++++++++++++++----------
> arch/x86/include/asm/mshyperv.h | 2 ++
> 2 files changed, 29 insertions(+), 11 deletions(-)
>
> diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
> index 75b25724b045..eca015563420 100644
> --- a/arch/x86/hyperv/irqdomain.c
> +++ b/arch/x86/hyperv/irqdomain.c
> @@ -172,13 +172,32 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
> return dev_id;
> }
>
> -static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
> - struct hv_interrupt_entry *entry)
> +/**
> + * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
> + * @data: Describes the IRQ
> + * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
Also document the return value? At least to say that success returns 0,
while a failure returns a negative errno.
> + *
> + * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
> + */
> +int hv_map_msi_interrupt(struct irq_data *data,
> + struct hv_interrupt_entry *out_entry)
> {
> - union hv_device_id device_id = hv_build_pci_dev_id(dev);
> + struct irq_cfg *cfg = irqd_cfg(data);
> + struct hv_interrupt_entry dummy;
> + union hv_device_id device_id;
> + struct msi_desc *msidesc;
> + struct pci_dev *dev;
> + int cpu;
>
> - return hv_map_interrupt(device_id, false, cpu, vector, entry);
> + msidesc = irq_data_get_msi_desc(data);
> + dev = msi_desc_to_pci_dev(msidesc);
> + device_id = hv_build_pci_dev_id(dev);
> + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
> +
> + return hv_map_interrupt(device_id, false, cpu, cfg->vector,
> + out_entry ? out_entry : &dummy);
> }
> +EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
>
> static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
> {
> @@ -191,11 +210,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
> static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
> static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> {
> - struct hv_interrupt_entry out_entry, *stored_entry;
> + struct hv_interrupt_entry *stored_entry;
> struct irq_cfg *cfg = irqd_cfg(data);
> struct msi_desc *msidesc;
> struct pci_dev *dev;
> - int cpu, ret;
> + int ret;
>
> msidesc = irq_data_get_msi_desc(data);
> dev = msi_desc_to_pci_dev(msidesc);
> @@ -205,8 +224,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> return;
> }
>
> - cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
> -
> if (data->chip_data) {
> /*
> * This interrupt is already mapped. Let's unmap first.
> @@ -233,15 +250,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> return;
> }
>
> - ret = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
> + ret = hv_map_msi_interrupt(data, stored_entry);
> if (ret) {
> kfree(stored_entry);
> return;
> }
>
> - *stored_entry = out_entry;
> data->chip_data = stored_entry;
> - entry_to_msi_msg(&out_entry, msg);
> + entry_to_msi_msg(data->chip_data, msg);
>
> return;
> }
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index e00a8431ef8e..42ea9c68f8c8 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -241,6 +241,8 @@ static inline void hv_apic_init(void) {}
>
> struct irq_domain *hv_create_pci_msi_domain(void);
>
> +int hv_map_msi_interrupt(struct irq_data *data,
> + struct hv_interrupt_entry *out_entry);
> int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
> struct hv_interrupt_entry *entry);
> int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
> --
> 2.34.1
^ permalink raw reply
* RE: [PATCH v2 6/6] PCI: hv: Use the correct hypercall for unmasking interrupts on nested
From: Michael Kelley @ 2025-07-07 3:15 UTC (permalink / raw)
To: Nuno Das Neves, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <1751582677-30930-7-git-send-email-nunodasneves@linux.microsoft.com>
From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>
> From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
>
> Running as nested root on MSHV imposes a different requirement
> for the pci-hyperv controller.
>
> In this setup, the interrupt will first come to the L1 (nested) hypervisor,
> which will deliver it to the appropriate root CPU. Instead of issuing the
> RETARGET hypercall, issue the MAP_DEVICE_INTERRUPT hypercall to L1 to
> complete the setup.
>
> Rename hv_arch_irq_unmask() to hv_irq_retarget_interrupt().
>
> Co-developed-by: Jinank Jain <jinankjain@linux.microsoft.com>
> Signed-off-by: Jinank Jain <jinankjain@linux.microsoft.com>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
> ---
> drivers/pci/controller/pci-hyperv.c | 18 ++++++++++++++++--
> 1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 4d25754dfe2f..9a8cba39ea6b 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -600,7 +600,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data
> *data)
> #define hv_msi_prepare pci_msi_prepare
>
> /**
> - * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current
> + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current
> * affinity.
> * @data: Describes the IRQ
> *
> @@ -609,7 +609,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data
> *data)
> * is built out of this PCI bus's instance GUID and the function
> * number of the device.
> */
> -static void hv_arch_irq_unmask(struct irq_data *data)
> +static void hv_irq_retarget_interrupt(struct irq_data *data)
> {
> struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
> struct hv_retarget_device_interrupt *params;
> @@ -714,6 +714,20 @@ static void hv_arch_irq_unmask(struct irq_data *data)
> dev_err(&hbus->hdev->device,
> "%s() failed: %#llx", __func__, res);
> }
> +
> +static void hv_arch_irq_unmask(struct irq_data *data)
> +{
> + if (hv_root_partition())
> + /*
> + * In case of the nested root partition, the nested hypervisor
> + * is taking care of interrupt remapping and thus the
> + * MAP_DEVICE_INTERRUPT hypercall is required instead of
> + * RETARGET_INTERRUPT.
> + */
> + (void)hv_map_msi_interrupt(data, NULL);
> + else
> + hv_irq_retarget_interrupt(data);
> +}
> #elif defined(CONFIG_ARM64)
> /*
> * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit
> --
> 2.34.1
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
^ permalink raw reply
* Re: [PATCH 00/16] PCI: MSI parent domain conversion
From: Manivannan Sadhasivam @ 2025-07-07 6:20 UTC (permalink / raw)
To: Nam Cao
Cc: Bjorn Helgaas, Marc Zyngier, Thomas Gleixner, Lorenzo Pieralisi,
Krzysztof Wilczyński, Rob Herring, Bjorn Helgaas, linux-pci,
linux-kernel, Karthikeyan Mitran, Hou Zhiqiang, Thomas Petazzoni,
Pali Rohár, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Joyce Ooi, Jim Quinlan, Nicolas Saenz Julienne,
Florian Fainelli, Broadcom internal kernel review list, Ray Jui,
Scott Branden, Ryder Lee, Jianjun Wang, Marek Vasut,
Yoshihiro Shimoda, Michal Simek, Daire McNamara, Nirmal Patel,
Jonathan Derrick, Matthias Brugger, AngeloGioacchino Del Regno,
linux-arm-kernel, linux-hyperv, linux-rpi-kernel, linux-mediatek,
linux-renesas-soc
In-Reply-To: <20250704044806.7wtcOlGB@linutronix.de>
On Fri, Jul 04, 2025 at 06:48:06AM GMT, Nam Cao wrote:
> On Thu, Jul 03, 2025 at 12:28:01PM -0500, Bjorn Helgaas wrote:
> > On Thu, Jun 26, 2025 at 04:47:50PM +0200, Nam Cao wrote:
> > > The initial implementation of PCI/MSI interrupt domains in the hierarchical
> > > interrupt domain model used a shortcut by providing a global PCI/MSI
> > > domain.
> > >
> > > This works because the PCI/MSI[X] hardware is standardized and uniform, but
> > > it violates the basic design principle of hierarchical interrupt domains:
> > > Each hardware block involved in the interrupt delivery chain should have a
> > > separate interrupt domain.
> > >
> > > For PCI/MSI[X], the interrupt controller is per PCI device and not a global
> > > made-up entity.
> > >
> > > Unsurprisingly, the shortcut turned out to have downsides as it does not
> > > allow dynamic allocation of interrupt vectors after initialization and it
> > > prevents supporting IMS on PCI. For further details, see:
> > >
> > > https://lore.kernel.org/lkml/20221111120501.026511281@linutronix.de/
> > >
> > > The solution is implementing per device MSI domains, this means the
> > > entities which provide global PCI/MSI domain so far have to implement MSI
> > > parent domain functionality instead.
> > >
> > > This series converts the PCI controller drivers to implement MSI parent
> > > domain.
> > >
> > > drivers/pci/Kconfig | 1 +
> > > drivers/pci/controller/Kconfig | 11 +
> > > drivers/pci/controller/dwc/Kconfig | 1 +
> > > .../pci/controller/dwc/pcie-designware-host.c | 68 ++----
> > > drivers/pci/controller/dwc/pcie-designware.h | 1 -
> > > drivers/pci/controller/mobiveil/Kconfig | 1 +
> > > .../controller/mobiveil/pcie-mobiveil-host.c | 42 ++--
> > > .../pci/controller/mobiveil/pcie-mobiveil.h | 1 -
> > > drivers/pci/controller/pci-aardvark.c | 59 ++---
> > > drivers/pci/controller/pci-hyperv.c | 98 ++++++--
> > > drivers/pci/controller/pcie-altera-msi.c | 44 ++--
> > > drivers/pci/controller/pcie-brcmstb.c | 44 ++--
> > > drivers/pci/controller/pcie-iproc-msi.c | 45 ++--
> > > drivers/pci/controller/pcie-mediatek-gen3.c | 67 ++---
> > > drivers/pci/controller/pcie-mediatek.c | 46 ++--
> > > drivers/pci/controller/pcie-rcar-host.c | 69 ++----
> > > drivers/pci/controller/pcie-xilinx-dma-pl.c | 48 ++--
> > > drivers/pci/controller/pcie-xilinx-nwl.c | 45 ++--
> > > drivers/pci/controller/pcie-xilinx.c | 55 +++--
> > > drivers/pci/controller/plda/Kconfig | 1 +
> > > drivers/pci/controller/plda/pcie-plda-host.c | 44 ++--
> > > drivers/pci/controller/plda/pcie-plda.h | 1 -
> > > drivers/pci/controller/vmd.c | 229 +++++++++---------
> > > 23 files changed, 504 insertions(+), 517 deletions(-)
> >
> > Looks good to me, thanks! I think Mani will probably pick this up.
> >
> > I might have included the specific "legacy MSI domain" thing you're
> > replacing. It looks like you're replacing pci_msi_create_irq_domain()
> > with msi_create_parent_irq_domain()?
>
> Yes, pci_msi_create_irq_domain() is legacy. We will delete it once
> everything is converted.
>
I'll amend the commit message to include pci_msi_create_irq_domain().
> > Minor merge conflict in pcie-mediatek-gen3.c with dcbea1c7e94e ("PCI:
> > mediatek-gen3: Use dev_fwnode() for irq_domain_create_linear()"). No
> > problem, we can easily fix that up.
>
> Thanks!
>
> > The "++i" in vmd.c stuck out to me since "i++" is so much more common.
>
> I always do "++i", maybe I'm the weird one..
>
Just for the sake of uniformity, I'll do 's/++i/i++' while applying.
And based on the discussion on patch 14/16, I'll drop it to be applied through
netdev and apply the rest of the series through PCI tree.
- Mani
--
மணிவண்ணன் சதாசிவம்
^ permalink raw reply
* Re: [PATCH 00/16] PCI: MSI parent domain conversion
From: Manivannan Sadhasivam @ 2025-07-07 7:43 UTC (permalink / raw)
To: Nam Cao
Cc: Marc Zyngier, Thomas Gleixner, Lorenzo Pieralisi,
Krzysztof Wilczyński, Rob Herring, Bjorn Helgaas, linux-pci,
linux-kernel, Karthikeyan Mitran, Hou Zhiqiang, Thomas Petazzoni,
Pali Rohár, K . Y . Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Joyce Ooi, Jim Quinlan, Nicolas Saenz Julienne,
Florian Fainelli, Broadcom internal kernel review list, Ray Jui,
Scott Branden, Ryder Lee, Jianjun Wang, Marek Vasut,
Yoshihiro Shimoda, Michal Simek, Daire McNamara, Nirmal Patel,
Jonathan Derrick, Matthias Brugger, AngeloGioacchino Del Regno,
linux-arm-kernel, linux-hyperv, linux-rpi-kernel, linux-mediatek,
linux-renesas-soc
In-Reply-To: <cover.1750858083.git.namcao@linutronix.de>
On Thu, Jun 26, 2025 at 04:47:50PM GMT, Nam Cao wrote:
> The initial implementation of PCI/MSI interrupt domains in the hierarchical
> interrupt domain model used a shortcut by providing a global PCI/MSI
> domain.
>
> This works because the PCI/MSI[X] hardware is standardized and uniform, but
> it violates the basic design principle of hierarchical interrupt domains:
> Each hardware block involved in the interrupt delivery chain should have a
> separate interrupt domain.
>
> For PCI/MSI[X], the interrupt controller is per PCI device and not a global
> made-up entity.
>
> Unsurprisingly, the shortcut turned out to have downsides as it does not
> allow dynamic allocation of interrupt vectors after initialization and it
> prevents supporting IMS on PCI. For further details, see:
>
> https://lore.kernel.org/lkml/20221111120501.026511281@linutronix.de/
>
> The solution is implementing per device MSI domains, this means the
> entities which provide global PCI/MSI domain so far have to implement MSI
> parent domain functionality instead.
>
> This series converts the PCI controller drivers to implement MSI parent
> domain.
>
Applied the series except patch 14/16 to pci/controller/msi-parent, thanks!
- Mani
> drivers/pci/Kconfig | 1 +
> drivers/pci/controller/Kconfig | 11 +
> drivers/pci/controller/dwc/Kconfig | 1 +
> .../pci/controller/dwc/pcie-designware-host.c | 68 ++----
> drivers/pci/controller/dwc/pcie-designware.h | 1 -
> drivers/pci/controller/mobiveil/Kconfig | 1 +
> .../controller/mobiveil/pcie-mobiveil-host.c | 42 ++--
> .../pci/controller/mobiveil/pcie-mobiveil.h | 1 -
> drivers/pci/controller/pci-aardvark.c | 59 ++---
> drivers/pci/controller/pci-hyperv.c | 98 ++++++--
> drivers/pci/controller/pcie-altera-msi.c | 44 ++--
> drivers/pci/controller/pcie-brcmstb.c | 44 ++--
> drivers/pci/controller/pcie-iproc-msi.c | 45 ++--
> drivers/pci/controller/pcie-mediatek-gen3.c | 67 ++---
> drivers/pci/controller/pcie-mediatek.c | 46 ++--
> drivers/pci/controller/pcie-rcar-host.c | 69 ++----
> drivers/pci/controller/pcie-xilinx-dma-pl.c | 48 ++--
> drivers/pci/controller/pcie-xilinx-nwl.c | 45 ++--
> drivers/pci/controller/pcie-xilinx.c | 55 +++--
> drivers/pci/controller/plda/Kconfig | 1 +
> drivers/pci/controller/plda/pcie-plda-host.c | 44 ++--
> drivers/pci/controller/plda/pcie-plda.h | 1 -
> drivers/pci/controller/vmd.c | 229 +++++++++---------
> 23 files changed, 504 insertions(+), 517 deletions(-)
>
> --
> 2.39.5
>
--
மணிவண்ணன் சதாசிவம்
^ permalink raw reply
* [PATCH] Drivers: hv: Fix the check for HYPERVISOR_CALLBACK_VECTOR
From: Naman Jain @ 2025-07-07 8:43 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Michael Kelley, Roman Kisel
Cc: linux-hyperv, linux-kernel, stable, namjain
__is_defined(HYPERVISOR_CALLBACK_VECTOR) would return 1, only if
HYPERVISOR_CALLBACK_VECTOR macro is defined as 1. However its value is
0xf3 and this leads to __is_defined() returning 0. The expectation
was to just check whether this MACRO is defined or not and get 1 if
it's defined. Replace __is_defined with #ifdef blocks instead to
fix it.
Fixes: 1dc5df133b98 ("Drivers: hv: vmbus: Get the IRQ number from DeviceTree")
Cc: stable@kernel.org
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/hv/vmbus_drv.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 33b524b4eb5e..2ed5a1e89d69 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2509,7 +2509,7 @@ static int vmbus_acpi_add(struct platform_device *pdev)
return 0;
}
#endif
-
+#ifndef HYPERVISOR_CALLBACK_VECTOR
static int vmbus_set_irq(struct platform_device *pdev)
{
struct irq_data *data;
@@ -2534,6 +2534,7 @@ static int vmbus_set_irq(struct platform_device *pdev)
return 0;
}
+#endif
static int vmbus_device_add(struct platform_device *pdev)
{
@@ -2549,11 +2550,11 @@ static int vmbus_device_add(struct platform_device *pdev)
if (ret)
return ret;
- if (!__is_defined(HYPERVISOR_CALLBACK_VECTOR))
- ret = vmbus_set_irq(pdev);
+#ifndef HYPERVISOR_CALLBACK_VECTOR
+ ret = vmbus_set_irq(pdev);
if (ret)
return ret;
-
+#endif
for_each_of_range(&parser, &range) {
struct resource *res;
base-commit: 26ffb3d6f02cd0935fb9fa3db897767beee1cb2a
--
2.34.1
^ permalink raw reply related
* Re: [PATCH net-next v5 1/4] hv_sock: Return the readable bytes in hvs_stream_has_data()
From: Stefano Garzarella @ 2025-07-07 13:40 UTC (permalink / raw)
To: Xuewei Niu
Cc: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, linux-hyperv, virtualization, netdev, linux-kernel,
Xuewei Niu, fupan.lfp
In-Reply-To: <20250706-siocinq-v5-1-8d0b96a87465@antgroup.com>
On Sun, Jul 06, 2025 at 12:36:29PM +0800, Xuewei Niu wrote:
Again, this patch should have `From: Dexuan Cui <decui@microsoft.com>`
on first line, and this is done automatically by `git format-patch` (or
others tools) if the author is the right one in your branch.
I'm not sure what is going on on your side, but you should avoid to
reset the original author.
Applying this patch we will have:
commit ed36075e04ecbb1dd02a3d8eba5bfac6469d73e4
Author: Xuewei Niu <niuxuewei97@gmail.com>
Date: Sun Jul 6 12:36:29 2025 +0800
hv_sock: Return the readable bytes in hvs_stream_has_data()
This is not what we want, right?
>When hv_sock was originally added, __vsock_stream_recvmsg() and
>vsock_stream_has_data() actually only needed to know whether there
>is any readable data or not, so hvs_stream_has_data() was written to
>return 1 or 0 for simplicity.
>
>However, now hvs_stream_has_data() should return the readable bytes
>because vsock_data_ready() -> vsock_stream_has_data() needs to know the
>actual bytes rather than a boolean value of 1 or 0.
>
>The SIOCINQ ioctl support also needs hvs_stream_has_data() to return
>the readable bytes.
>
>Let hvs_stream_has_data() return the readable bytes of the payload in
>the next host-to-guest VMBus hv_sock packet.
>
>Note: there may be multpile incoming hv_sock packets pending in the
>VMBus channel's ringbuffer, but so far there is not a VMBus API that
>allows us to know all the readable bytes in total without reading and
>caching the payload of the multiple packets, so let's just return the
>readable bytes of the next single packet. In the future, we'll either
>add a VMBus API that allows us to know the total readable bytes without
>touching the data in the ringbuffer, or the hv_sock driver needs to
>understand the VMBus packet format and parse the packets directly.
>
>Signed-off-by: Dexuan Cui <decui@microsoft.com>
Your S-o-b was fine here, I was talking about the author.
Thanks,
Stefano
>---
> net/vmw_vsock/hyperv_transport.c | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
>diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>index 31342ab502b4fc35feb812d2c94e0e35ded73771..432fcbbd14d4f44bd2550be8376e42ce65122758 100644
>--- a/net/vmw_vsock/hyperv_transport.c
>+++ b/net/vmw_vsock/hyperv_transport.c
>@@ -694,15 +694,26 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
> static s64 hvs_stream_has_data(struct vsock_sock *vsk)
> {
> struct hvsock *hvs = vsk->trans;
>+ bool need_refill;
> s64 ret;
>
> if (hvs->recv_data_len > 0)
>- return 1;
>+ return hvs->recv_data_len;
>
> switch (hvs_channel_readable_payload(hvs->chan)) {
> case 1:
>- ret = 1;
>- break;
>+ need_refill = !hvs->recv_desc;
>+ if (!need_refill)
>+ return -EIO;
>+
>+ hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
>+ if (!hvs->recv_desc)
>+ return -ENOBUFS;
>+
>+ ret = hvs_update_recv_data(hvs);
>+ if (ret)
>+ return ret;
>+ return hvs->recv_data_len;
> case 0:
> vsk->peer_shutdown |= SEND_SHUTDOWN;
> ret = 0;
>
>--
>2.34.1
>
^ permalink raw reply
* Re: [PATCH net-next v5 1/4] hv_sock: Return the readable bytes in hvs_stream_has_data()
From: Stefano Garzarella @ 2025-07-07 13:42 UTC (permalink / raw)
To: Xuewei Niu
Cc: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, linux-hyperv, virtualization, netdev, linux-kernel,
Xuewei Niu, fupan.lfp
In-Reply-To: <20250706-siocinq-v5-1-8d0b96a87465@antgroup.com>
On Sun, Jul 06, 2025 at 12:36:29PM +0800, Xuewei Niu wrote:
>When hv_sock was originally added, __vsock_stream_recvmsg() and
>vsock_stream_has_data() actually only needed to know whether there
>is any readable data or not, so hvs_stream_has_data() was written to
>return 1 or 0 for simplicity.
>
>However, now hvs_stream_has_data() should return the readable bytes
>because vsock_data_ready() -> vsock_stream_has_data() needs to know the
>actual bytes rather than a boolean value of 1 or 0.
>
>The SIOCINQ ioctl support also needs hvs_stream_has_data() to return
>the readable bytes.
>
>Let hvs_stream_has_data() return the readable bytes of the payload in
>the next host-to-guest VMBus hv_sock packet.
>
>Note: there may be multpile incoming hv_sock packets pending in the
s/multpile/multiple
>VMBus channel's ringbuffer, but so far there is not a VMBus API that
>allows us to know all the readable bytes in total without reading and
>caching the payload of the multiple packets, so let's just return the
>readable bytes of the next single packet. In the future, we'll either
>add a VMBus API that allows us to know the total readable bytes without
>touching the data in the ringbuffer, or the hv_sock driver needs to
>understand the VMBus packet format and parse the packets directly.
>
>Signed-off-by: Dexuan Cui <decui@microsoft.com>
>---
> net/vmw_vsock/hyperv_transport.c | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
>diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>index 31342ab502b4fc35feb812d2c94e0e35ded73771..432fcbbd14d4f44bd2550be8376e42ce65122758 100644
>--- a/net/vmw_vsock/hyperv_transport.c
>+++ b/net/vmw_vsock/hyperv_transport.c
>@@ -694,15 +694,26 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
> static s64 hvs_stream_has_data(struct vsock_sock *vsk)
> {
> struct hvsock *hvs = vsk->trans;
>+ bool need_refill;
> s64 ret;
>
> if (hvs->recv_data_len > 0)
>- return 1;
>+ return hvs->recv_data_len;
>
> switch (hvs_channel_readable_payload(hvs->chan)) {
> case 1:
>- ret = 1;
>- break;
>+ need_refill = !hvs->recv_desc;
>+ if (!need_refill)
>+ return -EIO;
>+
>+ hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
>+ if (!hvs->recv_desc)
>+ return -ENOBUFS;
>+
>+ ret = hvs_update_recv_data(hvs);
>+ if (ret)
>+ return ret;
>+ return hvs->recv_data_len;
> case 0:
> vsk->peer_shutdown |= SEND_SHUTDOWN;
> ret = 0;
>
>--
>2.34.1
>
^ permalink raw reply
* Re: [PATCH net-next v5 0/4] vsock: Introduce SIOCINQ ioctl support
From: Stefano Garzarella @ 2025-07-07 13:44 UTC (permalink / raw)
To: Xuewei Niu
Cc: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, linux-hyperv, virtualization, netdev, linux-kernel,
Xuewei Niu, fupan.lfp
In-Reply-To: <20250706-siocinq-v5-0-8d0b96a87465@antgroup.com>
On Sun, Jul 06, 2025 at 12:36:28PM +0800, Xuewei Niu wrote:
>Introduce SIOCINQ ioctl support for vsock, indicating the length of unread
>bytes.
>
>Similar with SIOCOUTQ ioctl, the information is transport-dependent.
>
>The first patch adds SIOCINQ ioctl support in AF_VSOCK.
>
>Thanks to @dexuan, the second patch is to fix the issue where hyper-v
>`hvs_stream_has_data()` doesn't return the readable bytes.
>
>The third patch wraps the ioctl into `ioctl_int()`, which implements a
>retry mechanism to prevent immediate failure.
>
>The last one adds two test cases to check the functionality. The changes
>have been tested, and the results are as expected.
>
>Signed-off-by: Xuewei Niu <niuxuewei.nxw@antgroup.com>
>
>--
>
>v1->v2:
>https://lore.kernel.org/lkml/20250519070649.3063874-1-niuxuewei.nxw@antgroup.com/
>- Use net-next tree.
>- Reuse `rx_bytes` to count unread bytes.
>- Wrap ioctl syscall with an int pointer argument to implement a retry
> mechanism.
>
>v2->v3:
>https://lore.kernel.org/netdev/20250613031152.1076725-1-niuxuewei.nxw@antgroup.com/
>- Update commit messages following the guidelines
>- Remove `unread_bytes` callback and reuse `vsock_stream_has_data()`
>- Move the tests to the end of array
>- Split the refactoring patch
>- Include <sys/ioctl.h> in the util.c
>
>v3->v4:
>https://lore.kernel.org/netdev/20250617045347.1233128-1-niuxuewei.nxw@antgroup.com/
>- Hyper-v `hvs_stream_has_data()` returns the readable bytes
>- Skip testing the null value for `actual` (int pointer)
>- Rename `ioctl_int()` to `vsock_ioctl_int()`
>- Fix a typo and a format issue in comments
>- Remove the `RECEIVED` barrier.
>- The return type of `vsock_ioctl_int()` has been changed to bool
>
>v4->v5:
>https://lore.kernel.org/netdev/20250630075727.210462-1-niuxuewei.nxw@antgroup.com/
>- Put the hyper-v fix before the SIOCINQ ioctl implementation.
>- Remove my SOB from the hyper-v fix patch.
Has I mentioned, that was not the issue, but the wrong Author.
There are also other issue, not sure how you're sending them, but I
guess there are some issues with you `git format-patch` configuration:
$ ./scripts/checkpatch.pl -g net-next..HEAD --codespell
-----------------------------------------------------------------------------------
Commit ed36075e04ec ("hv_sock: Return the readable bytes in hvs_stream_has_data()")
-----------------------------------------------------------------------------------
WARNING: 'multpile' may be misspelled - perhaps 'multiple'?
#23:
Note: there may be multpile incoming hv_sock packets pending in the
^^^^^^^^
ERROR: Missing Signed-off-by: line by nominal patch author 'Xuewei Niu <niuxuewei97@gmail.com>'
total: 1 errors, 1 warnings, 0 checks, 29 lines checked
NOTE: For some of the reported defects, checkpatch may be able to
mechanically convert to the typical style using --fix or --fix-inplace.
Commit ed36075e04ec ("hv_sock: Return the readable bytes in hvs_stream_has_data()") has style problems, please review.
------------------------------------------------------------
Commit 4e5c39e373fa ("vsock: Add support for SIOCINQ ioctl")
------------------------------------------------------------
WARNING: From:/Signed-off-by: email address mismatch: 'From: Xuewei Niu <niuxuewei97@gmail.com>' != 'Signed-off-by: Xuewei Niu <niuxuewei.nxw@antgroup.com>'
total: 0 errors, 1 warnings, 0 checks, 28 lines checked
NOTE: For some of the reported defects, checkpatch may be able to
mechanically convert to the typical style using --fix or --fix-inplace.
Commit 4e5c39e373fa ("vsock: Add support for SIOCINQ ioctl") has style problems, please review.
------------------------------------------------------------------------
Commit 3eb323b2d9f4 ("test/vsock: Add retry mechanism to ioctl wrapper")
------------------------------------------------------------------------
WARNING: From:/Signed-off-by: email address mismatch: 'From: Xuewei Niu <niuxuewei97@gmail.com>' != 'Signed-off-by: Xuewei Niu <niuxuewei.nxw@antgroup.com>'
total: 0 errors, 1 warnings, 62 lines checked
NOTE: For some of the reported defects, checkpatch may be able to
mechanically convert to the typical style using --fix or --fix-inplace.
Commit 3eb323b2d9f4 ("test/vsock: Add retry mechanism to ioctl wrapper") has style problems, please review.
NOTE: If any of the errors are false positives, please report
them to the maintainer, see CHECKPATCH in MAINTAINERS.
>- Move the `need_refill` initialization into the `case 1` block.
>- Remove the `actual` argument from `vsock_ioctl_int()`.
>- Replace `TIOCINQ` with `SIOCINQ`.
>
>---
>Xuewei Niu (4):
> hv_sock: Return the readable bytes in hvs_stream_has_data()
> vsock: Add support for SIOCINQ ioctl
> test/vsock: Add retry mechanism to ioctl wrapper
> test/vsock: Add ioctl SIOCINQ tests
>
> net/vmw_vsock/af_vsock.c | 22 +++++++++++
> net/vmw_vsock/hyperv_transport.c | 17 +++++++--
> tools/testing/vsock/util.c | 30 ++++++++++-----
> tools/testing/vsock/util.h | 1 +
> tools/testing/vsock/vsock_test.c | 79 ++++++++++++++++++++++++++++++++++++++++
> 5 files changed, 137 insertions(+), 12 deletions(-)
>---
>base-commit: 5f712c3877f99d5b5e4d011955c6467ae0e535a6
>change-id: 20250703-siocinq-9e2907939806
>
>Best regards,
>--
>Xuewei Niu <niuxuewei.nxw@antgroup.com>
>
^ permalink raw reply
* Re: [PATCH v2 1/6] PCI: hv: Don't load the driver for baremetal root partition
From: Bjorn Helgaas @ 2025-07-07 16:04 UTC (permalink / raw)
To: Nuno Das Neves
Cc: linux-hyperv, linux-arm-kernel, linux-kernel, linux-pci, mhklinux,
tglx, bhelgaas, romank, kys, haiyangz, wei.liu, decui,
catalin.marinas, will, mingo, bp, dave.hansen, hpa, lpieralisi,
kw, robh, jinankjain, skinsburskii, mrathor, x86
In-Reply-To: <1751582677-30930-2-git-send-email-nunodasneves@linux.microsoft.com>
On Thu, Jul 03, 2025 at 03:44:32PM -0700, Nuno Das Neves wrote:
> From: Mukesh Rathor <mrathor@linux.microsoft.com>
>
> The root partition only uses VMBus when running nested.
>
> When running on baremetal the Hyper-V PCI driver is not needed,
> so do not initialize it.
>
> Signed-off-by: Mukesh Rathor <mrathor@linux.microsoft.com>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
I assume this series will be merged elsewhere.
> ---
> drivers/pci/controller/pci-hyperv.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index b4f29ee75848..4d25754dfe2f 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -4150,6 +4150,9 @@ static int __init init_hv_pci_drv(void)
> if (!hv_is_hyperv_initialized())
> return -ENODEV;
>
> + if (hv_root_partition() && !hv_nested)
> + return -ENODEV;
> +
> ret = hv_pci_irqchip_init();
> if (ret)
> return ret;
> --
> 2.34.1
>
^ permalink raw reply
* Re: [PATCH v2 6/6] PCI: hv: Use the correct hypercall for unmasking interrupts on nested
From: Bjorn Helgaas @ 2025-07-07 16:05 UTC (permalink / raw)
To: Nuno Das Neves
Cc: linux-hyperv, linux-arm-kernel, linux-kernel, linux-pci, mhklinux,
tglx, bhelgaas, romank, kys, haiyangz, wei.liu, decui,
catalin.marinas, will, mingo, bp, dave.hansen, hpa, lpieralisi,
kw, robh, jinankjain, skinsburskii, mrathor, x86
In-Reply-To: <1751582677-30930-7-git-send-email-nunodasneves@linux.microsoft.com>
On Thu, Jul 03, 2025 at 03:44:37PM -0700, Nuno Das Neves wrote:
> From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
>
> Running as nested root on MSHV imposes a different requirement
> for the pci-hyperv controller.
>
> In this setup, the interrupt will first come to the L1 (nested) hypervisor,
> which will deliver it to the appropriate root CPU. Instead of issuing the
> RETARGET hypercall, issue the MAP_DEVICE_INTERRUPT hypercall to L1 to
> complete the setup.
>
> Rename hv_arch_irq_unmask() to hv_irq_retarget_interrupt().
>
> Co-developed-by: Jinank Jain <jinankjain@linux.microsoft.com>
> Signed-off-by: Jinank Jain <jinankjain@linux.microsoft.com>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
> ---
> drivers/pci/controller/pci-hyperv.c | 18 ++++++++++++++++--
> 1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 4d25754dfe2f..9a8cba39ea6b 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -600,7 +600,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data)
> #define hv_msi_prepare pci_msi_prepare
>
> /**
> - * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current
> + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current
> * affinity.
> * @data: Describes the IRQ
> *
> @@ -609,7 +609,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data)
> * is built out of this PCI bus's instance GUID and the function
> * number of the device.
> */
> -static void hv_arch_irq_unmask(struct irq_data *data)
> +static void hv_irq_retarget_interrupt(struct irq_data *data)
> {
> struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
> struct hv_retarget_device_interrupt *params;
> @@ -714,6 +714,20 @@ static void hv_arch_irq_unmask(struct irq_data *data)
> dev_err(&hbus->hdev->device,
> "%s() failed: %#llx", __func__, res);
> }
> +
> +static void hv_arch_irq_unmask(struct irq_data *data)
> +{
> + if (hv_root_partition())
> + /*
> + * In case of the nested root partition, the nested hypervisor
> + * is taking care of interrupt remapping and thus the
> + * MAP_DEVICE_INTERRUPT hypercall is required instead of
> + * RETARGET_INTERRUPT.
> + */
> + (void)hv_map_msi_interrupt(data, NULL);
> + else
> + hv_irq_retarget_interrupt(data);
> +}
> #elif defined(CONFIG_ARM64)
> /*
> * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit
> --
> 2.34.1
>
^ permalink raw reply
* Re: [PATCH] Drivers: hv: Fix the check for HYPERVISOR_CALLBACK_VECTOR
From: Roman Kisel @ 2025-07-07 17:58 UTC (permalink / raw)
To: Naman Jain
Cc: linux-hyperv, linux-kernel, stable, namjain, K . Y . Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Michael Kelley
In-Reply-To: <20250707084322.1763-1-namjain@linux.microsoft.com>
On 7/7/2025 1:43 AM, Naman Jain wrote:
> __is_defined(HYPERVISOR_CALLBACK_VECTOR) would return 1, only if
> HYPERVISOR_CALLBACK_VECTOR macro is defined as 1. However its value is
> 0xf3 and this leads to __is_defined() returning 0. The expectation
> was to just check whether this MACRO is defined or not and get 1 if
> it's defined. Replace __is_defined with #ifdef blocks instead to
> fix it.
>
> Fixes: 1dc5df133b98 ("Drivers: hv: vmbus: Get the IRQ number from DeviceTree")
> Cc: stable@kernel.org
> Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
> ---
[...]
Appreciate fixing that! From what I learned from you, x86 was broken.
Very likely I did a smoke test there only while focusing on arm64. Sorry
about that, thanks again!!
LGTM.
Reviewed-by: Roman Kisel <romank@linux.microsoft.com
>
>
> base-commit: 26ffb3d6f02cd0935fb9fa3db897767beee1cb2a
--
Thank you,
Roman
^ permalink raw reply
* Re: [PATCH 1/1] Drivers: hv: Select CONFIG_SYSFB only if EFI is enabled
From: Roman Kisel @ 2025-07-07 17:59 UTC (permalink / raw)
To: mhklinux
Cc: linux-kernel, linux-hyperv, stable, kys, haiyangz, wei.liu, decui,
deller, javierm, arnd
In-Reply-To: <20250613230059.380483-1-mhklinux@outlook.com>
On 6/13/2025 4:00 PM, mhkelley58@gmail.com wrote:
> From: Michael Kelley <mhklinux@outlook.com>
>
> Commit 96959283a58d ("Drivers: hv: Always select CONFIG_SYSFB
> for Hyper-V guests") selects CONFIG_SYSFB for Hyper-V guests
> so that screen_info is available to the VMBus driver to get
> the location of the framebuffer in Generation 2 VMs. However,
> if CONFIG_HYPERV is enabled but CONFIG_EFI is not, a kernel
> link error results in ARM64 builds because screen_info is
> provided by the EFI firmware interface. While configuring
> an ARM64 Hyper-V guest without EFI isn't useful since EFI is
> required to boot, the configuration is still possible and
> the link error should be prevented.
>
> Fix this by making the selection of CONFIG_SYSFB conditional
> on CONFIG_EFI being defined. For Generation 1 VMs on x86/x64,
> which don't use EFI, the additional condition is OK because
> such VMs get the framebuffer information via a mechanism
> that doesn't use screen_info.
>
[...]
LGTM.
Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
--
Thank you,
Roman
^ permalink raw reply
* Re: [PATCH v2 2/6] Drivers: hv: Use nested hypercall for post message and signal event
From: Nuno Das Neves @ 2025-07-07 18:19 UTC (permalink / raw)
To: Michael Kelley, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <SN6PR02MB41576CBCA98ECA4C77BCC2D7D44FA@SN6PR02MB4157.namprd02.prod.outlook.com>
On 7/6/2025 8:13 PM, Michael Kelley wrote:
> From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>>
>> When running nested, these hypercalls must be sent to the L0 hypervisor
>> or VMBus will fail.
>>
>> Remove hv_do_nested_hypercall() and hv_do_fast_nested_hypercall8()
>> altogether and open-code these cases, since there are only 2 and all
>> they do is add the nested bit.
>>
>> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
>> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
>> ---
>> arch/x86/include/asm/mshyperv.h | 20 --------------------
>> drivers/hv/connection.c | 7 +++++--
>> drivers/hv/hv.c | 6 ++++--
>> 3 files changed, 9 insertions(+), 24 deletions(-)
>>
>> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
>> index 5ec92e3e2e37..e00a8431ef8e 100644
>> --- a/arch/x86/include/asm/mshyperv.h
>> +++ b/arch/x86/include/asm/mshyperv.h
>> @@ -111,12 +111,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input,
>> void *output)
>> return hv_status;
>> }
>>
>> -/* Hypercall to the L0 hypervisor */
>> -static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
>> -{
>> - return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
>> -}
>> -
>> /* Fast hypercall with 8 bytes of input and no output */
>> static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
>> {
>> @@ -164,13 +158,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
>> return _hv_do_fast_hypercall8(control, input1);
>> }
>>
>> -static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
>> -{
>> - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
>> -
>> - return _hv_do_fast_hypercall8(control, input1);
>> -}
>> -
>> /* Fast hypercall with 16 bytes of input */
>> static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
>> {
>> @@ -222,13 +209,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
>> return _hv_do_fast_hypercall16(control, input1, input2);
>> }
>>
>> -static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
>> -{
>> - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
>> -
>> - return _hv_do_fast_hypercall16(control, input1, input2);
>> -}
>> -
>> extern struct hv_vp_assist_page **hv_vp_assist_page;
>>
>> static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
>> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
>> index be490c598785..47c93cee1ef6 100644
>> --- a/drivers/hv/connection.c
>> +++ b/drivers/hv/connection.c
>> @@ -518,8 +518,11 @@ void vmbus_set_event(struct vmbus_channel *channel)
>> channel->sig_event, 0);
>> else
>> WARN_ON_ONCE(1);
>> - } else {
>> - hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
>> + } else if (hv_nested) {
>
> As coded, this won't make any hypercall for the non-nested case.
> The "else if (hv_nested)" should be just "else".
Ah, forgot to change this line. Thank you for catching it
Nuno
>
> Michael
>
>> + u64 control = HVCALL_SIGNAL_EVENT;
>> +
>> + control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
>> + hv_do_fast_hypercall8(control, channel->sig_event);
>> }
>> }
>> EXPORT_SYMBOL_GPL(vmbus_set_event);
>> diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
>> index 308c8f279df8..b14c5f9e0ef2 100644
>> --- a/drivers/hv/hv.c
>> +++ b/drivers/hv/hv.c
>> @@ -85,8 +85,10 @@ int hv_post_message(union hv_connection_id connection_id,
>> else
>> status = HV_STATUS_INVALID_PARAMETER;
>> } else {
>> - status = hv_do_hypercall(HVCALL_POST_MESSAGE,
>> - aligned_msg, NULL);
>> + u64 control = HVCALL_POST_MESSAGE;
>> +
>> + control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
>> + status = hv_do_hypercall(control, aligned_msg, NULL);
>> }
>>
>> local_irq_restore(flags);
>> --
>> 2.34.1
^ permalink raw reply
* Re: [PATCH v2 5/6] x86: hyperv: Expose hv_map_msi_interrupt function
From: Nuno Das Neves @ 2025-07-07 18:23 UTC (permalink / raw)
To: Michael Kelley, linux-hyperv@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, bhelgaas@google.com,
romank@linux.microsoft.com
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, catalin.marinas@arm.com, will@kernel.org,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
hpa@zytor.com, lpieralisi@kernel.org, kw@linux.com,
robh@kernel.org, jinankjain@linux.microsoft.com,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
x86@kernel.org
In-Reply-To: <SN6PR02MB4157AAF735DD432EED00C945D44FA@SN6PR02MB4157.namprd02.prod.outlook.com>
On 7/6/2025 8:14 PM, Michael Kelley wrote:
> From: Nuno Das Neves <nunodasneves@linux.microsoft.com> Sent: Thursday, July 3, 2025 3:45 PM
>>
>> From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
>>
>> This patch moves a part of currently internal logic into the
>> hv_map_msi_interrupt function and makes it globally available helper
>> function, which will be used to map PCI interrupts in case of root
>> partition.
>
> Commit message still has "this patch". See suggested wording
> in my comment on v1 of this patch.
>
Ah, indeed, I missed the change somehow :(
>>
>> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
>> Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
>> Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
>> ---
>> arch/x86/hyperv/irqdomain.c | 38 +++++++++++++++++++++++----------
>> arch/x86/include/asm/mshyperv.h | 2 ++
>> 2 files changed, 29 insertions(+), 11 deletions(-)
>>
>> diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
>> index 75b25724b045..eca015563420 100644
>> --- a/arch/x86/hyperv/irqdomain.c
>> +++ b/arch/x86/hyperv/irqdomain.c
>> @@ -172,13 +172,32 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
>> return dev_id;
>> }
>>
>> -static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
>> - struct hv_interrupt_entry *entry)
>> +/**
>> + * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
>> + * @data: Describes the IRQ
>> + * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
>
> Also document the return value? At least to say that success returns 0,
> while a failure returns a negative errno.
>
>> + *
>> + * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
>> + */
>> +int hv_map_msi_interrupt(struct irq_data *data,
>> + struct hv_interrupt_entry *out_entry)
>> {
>> - union hv_device_id device_id = hv_build_pci_dev_id(dev);
>> + struct irq_cfg *cfg = irqd_cfg(data);
>> + struct hv_interrupt_entry dummy;
>> + union hv_device_id device_id;
>> + struct msi_desc *msidesc;
>> + struct pci_dev *dev;
>> + int cpu;
>>
>> - return hv_map_interrupt(device_id, false, cpu, vector, entry);
>> + msidesc = irq_data_get_msi_desc(data);
>> + dev = msi_desc_to_pci_dev(msidesc);
>> + device_id = hv_build_pci_dev_id(dev);
>> + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
>> +
>> + return hv_map_interrupt(device_id, false, cpu, cfg->vector,
>> + out_entry ? out_entry : &dummy);
>> }
>> +EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
>>
>> static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
>> {
>> @@ -191,11 +210,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
>> static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
>> static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
>> {
>> - struct hv_interrupt_entry out_entry, *stored_entry;
>> + struct hv_interrupt_entry *stored_entry;
>> struct irq_cfg *cfg = irqd_cfg(data);
>> struct msi_desc *msidesc;
>> struct pci_dev *dev;
>> - int cpu, ret;
>> + int ret;
>>
>> msidesc = irq_data_get_msi_desc(data);
>> dev = msi_desc_to_pci_dev(msidesc);
>> @@ -205,8 +224,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
>> return;
>> }
>>
>> - cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
>> -
>> if (data->chip_data) {
>> /*
>> * This interrupt is already mapped. Let's unmap first.
>> @@ -233,15 +250,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
>> return;
>> }
>>
>> - ret = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
>> + ret = hv_map_msi_interrupt(data, stored_entry);
>> if (ret) {
>> kfree(stored_entry);
>> return;
>> }
>>
>> - *stored_entry = out_entry;
>> data->chip_data = stored_entry;
>> - entry_to_msi_msg(&out_entry, msg);
>> + entry_to_msi_msg(data->chip_data, msg);
>>
>> return;
>> }
>> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
>> index e00a8431ef8e..42ea9c68f8c8 100644
>> --- a/arch/x86/include/asm/mshyperv.h
>> +++ b/arch/x86/include/asm/mshyperv.h
>> @@ -241,6 +241,8 @@ static inline void hv_apic_init(void) {}
>>
>> struct irq_domain *hv_create_pci_msi_domain(void);
>>
>> +int hv_map_msi_interrupt(struct irq_data *data,
>> + struct hv_interrupt_entry *out_entry);
>> int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
>> struct hv_interrupt_entry *entry);
>> int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
>> --
>> 2.34.1
^ permalink raw reply
* RE: [PATCH for-netdev v2 2/2] PCI: hv: Switch to msi_create_parent_irq_domain()
From: Michael Kelley @ 2025-07-07 18:49 UTC (permalink / raw)
To: Nam Cao, Marc Zyngier, Thomas Gleixner, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Simon Horman,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
open list:Hyper-V/Azure CORE AND DRIVERS
Cc: Manivannan Sadhasivam, Bjorn Helgaas
In-Reply-To: <7b99cca47b41dacc9a82b96093935eab07cac43a.1751875853.git.namcao@linutronix.de>
From: Nam Cao <namcao@linutronix.de> Sent: Monday, July 7, 2025 1:20 AM
>
> Move away from the legacy MSI domain setup, switch to use
> msi_create_parent_irq_domain().
>
> While doing the conversion, I noticed that hv_compose_msi_msg() is doing
> more than it is supposed to (composing message). This function also
> allocates and populates struct tran_int_desc, which should be done in
> hv_pcie_domain_alloc() instead. It works, but it is not the correct design.
> However, I have no hardware to test such change, therefore I leave a TODO
> note.
>
> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
> Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
> Signed-off-by: Nam Cao <namcao@linutronix.de>
[Adding linux-hyperv@vger.kernel.org so that the Linux on Hyper-V folks
have visibility.]
This all looks good to me now. Thanks for the additional explanation of
the TODO. I understand what you are suggesting. Moving the interaction
with the Hyper-V host into hv_pcie_domain_alloc() has additional appeal
because it should eliminate the need for the ugly polling for a VMBus
response. However, I'm unlikely to be the person implementing the
TODO. hv_compose_msi_msg() is a real beast of a function, and I lack
access to hardware to fully test the move, particularly a device that
does multi MSI. I don't think such a device is available in a VM in the
Azure public cloud.
I've tested this patch in an Azure VM that has a MANA NIC. The MANA
driver has updates in linux-next to use MSIX dynamic allocation, and
that dynamic allocation appears to work correctly with this patch. My
testing included unbind and rebind the driver several times so that
the full round-trip is tested.
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
> ---
> v2:
> - rebase onto netdev/next
> - clarify the TODO note
> - fixup arm64
> - Add HV_MSI_CHIP_FLAGS macro and reduce the amount of #ifdef
> ---
> drivers/pci/Kconfig | 1 +
> drivers/pci/controller/pci-hyperv.c | 111 +++++++++++++++++++++-------
> 2 files changed, 84 insertions(+), 28 deletions(-)
>
> diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
> index 9c0e4aaf4e8c..9a249c65aedc 100644
> --- a/drivers/pci/Kconfig
> +++ b/drivers/pci/Kconfig
> @@ -223,6 +223,7 @@ config PCI_HYPERV
> tristate "Hyper-V PCI Frontend"
> depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && SYSFS
> select PCI_HYPERV_INTERFACE
> + select IRQ_MSI_LIB
> help
> The PCI device frontend driver allows the kernel to import arbitrary
> PCI devices from a PCI backend to support PCI driver domains.
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 86ca041bf74a..ebe39218479a 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -44,6 +44,7 @@
> #include <linux/delay.h>
> #include <linux/semaphore.h>
> #include <linux/irq.h>
> +#include <linux/irqchip/irq-msi-lib.h>
> #include <linux/msi.h>
> #include <linux/hyperv.h>
> #include <linux/refcount.h>
> @@ -508,7 +509,6 @@ struct hv_pcibus_device {
> struct list_head children;
> struct list_head dr_list;
>
> - struct msi_domain_info msi_info;
> struct irq_domain *irq_domain;
>
> struct workqueue_struct *wq;
> @@ -576,9 +576,8 @@ struct hv_pci_compl {
> static void hv_pci_onchannelcallback(void *context);
>
> #ifdef CONFIG_X86
> -#define DELIVERY_MODE APIC_DELIVERY_MODE_FIXED
> -#define FLOW_HANDLER handle_edge_irq
> -#define FLOW_NAME "edge"
> +#define DELIVERY_MODE APIC_DELIVERY_MODE_FIXED
> +#define HV_MSI_CHIP_FLAGS MSI_CHIP_FLAG_SET_ACK
>
> static int hv_pci_irqchip_init(void)
> {
> @@ -723,8 +722,7 @@ static void hv_arch_irq_unmask(struct irq_data *data)
> #define HV_PCI_MSI_SPI_START 64
> #define HV_PCI_MSI_SPI_NR (1020 - HV_PCI_MSI_SPI_START)
> #define DELIVERY_MODE 0
> -#define FLOW_HANDLER NULL
> -#define FLOW_NAME NULL
> +#define HV_MSI_CHIP_FLAGS MSI_CHIP_FLAG_SET_EOI
> #define hv_msi_prepare NULL
>
> struct hv_pci_chip_data {
> @@ -1687,7 +1685,7 @@ static void hv_msi_free(struct irq_domain *domain, struct
> msi_domain_info *info,
> struct msi_desc *msi = irq_data_get_msi_desc(irq_data);
>
> pdev = msi_desc_to_pci_dev(msi);
> - hbus = info->data;
> + hbus = domain->host_data;
> int_desc = irq_data_get_irq_chip_data(irq_data);
> if (!int_desc)
> return;
> @@ -1705,7 +1703,6 @@ static void hv_msi_free(struct irq_domain *domain, struct
> msi_domain_info *info,
>
> static void hv_irq_mask(struct irq_data *data)
> {
> - pci_msi_mask_irq(data);
> if (data->parent_data->chip->irq_mask)
> irq_chip_mask_parent(data);
> }
> @@ -1716,7 +1713,6 @@ static void hv_irq_unmask(struct irq_data *data)
>
> if (data->parent_data->chip->irq_unmask)
> irq_chip_unmask_parent(data);
> - pci_msi_unmask_irq(data);
> }
>
> struct compose_comp_ctxt {
> @@ -2101,25 +2097,87 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
> msg->data = 0;
> }
>
> +static bool hv_pcie_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
> + struct irq_domain *real_parent, struct msi_domain_info *info)
> +{
> + struct irq_chip *chip = info->chip;
> +
> + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
> + return false;
> +
> + info->ops->msi_prepare = hv_msi_prepare;
> +
> + chip->irq_set_affinity = irq_chip_set_affinity_parent;
> +
> + if (IS_ENABLED(CONFIG_X86))
> + chip->flags |= IRQCHIP_MOVE_DEFERRED;
> +
> + return true;
> +}
> +
> +#define HV_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \
> + MSI_FLAG_USE_DEF_CHIP_OPS | \
> + MSI_FLAG_PCI_MSI_MASK_PARENT)
> +#define HV_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \
> + MSI_FLAG_PCI_MSIX | \
> + MSI_FLAG_PCI_MSIX_ALLOC_DYN | \
> + MSI_GENERIC_FLAGS_MASK)
> +
> +static const struct msi_parent_ops hv_pcie_msi_parent_ops = {
> + .required_flags = HV_PCIE_MSI_FLAGS_REQUIRED,
> + .supported_flags = HV_PCIE_MSI_FLAGS_SUPPORTED,
> + .bus_select_token = DOMAIN_BUS_PCI_MSI,
> + .chip_flags = HV_MSI_CHIP_FLAGS,
> + .prefix = "HV-",
> + .init_dev_msi_info = hv_pcie_init_dev_msi_info,
> +};
> +
> /* HW Interrupt Chip Descriptor */
> static struct irq_chip hv_msi_irq_chip = {
> .name = "Hyper-V PCIe MSI",
> .irq_compose_msi_msg = hv_compose_msi_msg,
> .irq_set_affinity = irq_chip_set_affinity_parent,
> -#ifdef CONFIG_X86
> .irq_ack = irq_chip_ack_parent,
> - .flags = IRQCHIP_MOVE_DEFERRED,
> -#elif defined(CONFIG_ARM64)
> .irq_eoi = irq_chip_eoi_parent,
> -#endif
> .irq_mask = hv_irq_mask,
> .irq_unmask = hv_irq_unmask,
> };
>
> -static struct msi_domain_ops hv_msi_ops = {
> - .msi_prepare = hv_msi_prepare,
> - .msi_free = hv_msi_free,
> - .prepare_desc = pci_msix_prepare_desc,
> +static int hv_pcie_domain_alloc(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs,
> + void *arg)
> +{
> + /*
> + * TODO: Allocating and populating struct tran_int_desc in hv_compose_msi_msg()
> + * should be moved here.
> + */
> + int ret;
> +
> + ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, arg);
> + if (ret < 0)
> + return ret;
> +
> + for (int i = 0; i < nr_irqs; i++) {
> + irq_domain_set_hwirq_and_chip(d, virq + i, 0, &hv_msi_irq_chip, NULL);
> + if (IS_ENABLED(CONFIG_X86))
> + __irq_set_handler(virq + i, handle_edge_irq, 0, "edge");
> + }
> +
> + return 0;
> +}
> +
> +static void hv_pcie_domain_free(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs)
> +{
> + struct msi_domain_info *info = d->host_data;
> +
> + for (int i = 0; i < nr_irqs; i++)
> + hv_msi_free(d, info, virq + i);
> +
> + irq_domain_free_irqs_top(d, virq, nr_irqs);
> +}
> +
> +static const struct irq_domain_ops hv_pcie_domain_ops = {
> + .alloc = hv_pcie_domain_alloc,
> + .free = hv_pcie_domain_free,
> };
>
> /**
> @@ -2137,17 +2195,14 @@ static struct msi_domain_ops hv_msi_ops = {
> */
> static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
> {
> - hbus->msi_info.chip = &hv_msi_irq_chip;
> - hbus->msi_info.ops = &hv_msi_ops;
> - hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
> - MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
> - MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN);
> - hbus->msi_info.handler = FLOW_HANDLER;
> - hbus->msi_info.handler_name = FLOW_NAME;
> - hbus->msi_info.data = hbus;
> - hbus->irq_domain = pci_msi_create_irq_domain(hbus->fwnode,
> - &hbus->msi_info,
> - hv_pci_get_root_domain());
> + struct irq_domain_info info = {
> + .fwnode = hbus->fwnode,
> + .ops = &hv_pcie_domain_ops,
> + .host_data = hbus,
> + .parent = hv_pci_get_root_domain(),
> + };
> +
> + hbus->irq_domain = msi_create_parent_irq_domain(&info, &hv_pcie_msi_parent_ops);
> if (!hbus->irq_domain) {
> dev_err(&hbus->hdev->device,
> "Failed to build an MSI IRQ domain\n");
> --
> 2.39.5
^ permalink raw reply
* RE: [PATCH 14/16] PCI: hv: Switch to msi_create_parent_irq_domain()
From: Michael Kelley @ 2025-07-07 19:04 UTC (permalink / raw)
To: Nam Cao
Cc: Marc Zyngier, Thomas Gleixner, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org, Karthikeyan Mitran, Hou Zhiqiang,
Thomas Petazzoni, Pali Rohár, K . Y . Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Joyce Ooi, Jim Quinlan,
Nicolas Saenz Julienne, Florian Fainelli,
Broadcom internal kernel review list, Ray Jui, Scott Branden,
Ryder Lee, Jianjun Wang, Marek Vasut, Yoshihiro Shimoda,
Michal Simek, Daire McNamara, Nirmal Patel, Jonathan Derrick,
Matthias Brugger, AngeloGioacchino Del Regno,
linux-arm-kernel@lists.infradead.org,
linux-hyperv@vger.kernel.org,
linux-rpi-kernel@lists.infradead.org,
linux-mediatek@lists.infradead.org,
linux-renesas-soc@vger.kernel.org
In-Reply-To: <20250705100211.8Lcszko3@linutronix.de>
From: Nam Cao <namcao@linutronix.de> Sent: Saturday, July 5, 2025 3:02 AM
>
> On Sat, Jul 05, 2025 at 11:46:59AM +0200, Nam Cao wrote:
> > On Sat, Jul 05, 2025 at 03:51:48AM +0000, Michael Kelley wrote:
> > > From: Nam Cao <namcao@linutronix.de> Sent: Thursday, June 26, 2025 7:48 AM
> > > >
> > > > Move away from the legacy MSI domain setup, switch to use
> > > > msi_create_parent_irq_domain().
> > >
> > > With the additional tweak to this patch that you supplied separately,
> > > everything in my testing on both x86 and arm64 seems to work OK. So
> > > that's all good.
> >
> > Thanks so much for examining the patch,
>
> Btw, you probably would also be interested in
> https://lore.kernel.org/lkml/cover.1751277765.git.namcao@linutronix.de/
>
> which does a similar conversion for the other hyperv driver.
>
Thanks. I had seen this other small series for the driver used by Linux
when running as the root partition (i.e., "dom0") on the Hyper-V
hypervisor. Unfortunately, I have less familiarity with that configuration,
and I lack access to hardware needed to run and test it. Someone at
Microsoft would need to look at the patches and give them a basic smoke
test with Linux-as-root.
FWIW, I was a Microsoft employee for many years, working on Linux
guests on Hyper-V. But I retired about 2 years ago. Though I've kept my
hands in Linux kernel work, my access to hardware configs is more
limited than when I was an employee -- now it's guest VMs on my
personal laptop and Azure VMs.
Michael
^ permalink raw reply
* Re: [PATCH net-next v5 1/4] hv_sock: Return the readable bytes in hvs_stream_has_data()
From: Xuewei Niu @ 2025-07-08 5:17 UTC (permalink / raw)
To: Stefano Garzarella, Xuewei Niu
Cc: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, linux-hyperv, virtualization, netdev, linux-kernel,
fupan.lfp
In-Reply-To: <xphwpqqi42w5b3jug3vfooybrlft3z5ewravl7jvzci7ogs3nh@5i7yi66dg7fa>
On 2025/7/7 21:42, Stefano Garzarella wrote:
> On Sun, Jul 06, 2025 at 12:36:29PM +0800, Xuewei Niu wrote:
>> When hv_sock was originally added, __vsock_stream_recvmsg() and
>> vsock_stream_has_data() actually only needed to know whether there
>> is any readable data or not, so hvs_stream_has_data() was written to
>> return 1 or 0 for simplicity.
>>
>> However, now hvs_stream_has_data() should return the readable bytes
>> because vsock_data_ready() -> vsock_stream_has_data() needs to know the
>> actual bytes rather than a boolean value of 1 or 0.
>>
>> The SIOCINQ ioctl support also needs hvs_stream_has_data() to return
>> the readable bytes.
>>
>> Let hvs_stream_has_data() return the readable bytes of the payload in
>> the next host-to-guest VMBus hv_sock packet.
>>
>> Note: there may be multpile incoming hv_sock packets pending in the
>
> s/multpile/multiple
Will do.
Thanks,
Xuewei
>> VMBus channel's ringbuffer, but so far there is not a VMBus API that
>> allows us to know all the readable bytes in total without reading and
>> caching the payload of the multiple packets, so let's just return the
>> readable bytes of the next single packet. In the future, we'll either
>> add a VMBus API that allows us to know the total readable bytes without
>> touching the data in the ringbuffer, or the hv_sock driver needs to
>> understand the VMBus packet format and parse the packets directly.
>>
>> Signed-off-by: Dexuan Cui <decui@microsoft.com>
>> ---
>> net/vmw_vsock/hyperv_transport.c | 17 ++++++++++++++---
>> 1 file changed, 14 insertions(+), 3 deletions(-)
>>
>> diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>> index 31342ab502b4fc35feb812d2c94e0e35ded73771..432fcbbd14d4f44bd2550be8376e42ce65122758 100644
>> --- a/net/vmw_vsock/hyperv_transport.c
>> +++ b/net/vmw_vsock/hyperv_transport.c
>> @@ -694,15 +694,26 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
>> static s64 hvs_stream_has_data(struct vsock_sock *vsk)
>> {
>> struct hvsock *hvs = vsk->trans;
>> + bool need_refill;
>> s64 ret;
>>
>> if (hvs->recv_data_len > 0)
>> - return 1;
>> + return hvs->recv_data_len;
>>
>> switch (hvs_channel_readable_payload(hvs->chan)) {
>> case 1:
>> - ret = 1;
>> - break;
>> + need_refill = !hvs->recv_desc;
>> + if (!need_refill)
>> + return -EIO;
>> +
>> + hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
>> + if (!hvs->recv_desc)
>> + return -ENOBUFS;
>> +
>> + ret = hvs_update_recv_data(hvs);
>> + if (ret)
>> + return ret;
>> + return hvs->recv_data_len;
>> case 0:
>> vsk->peer_shutdown |= SEND_SHUTDOWN;
>> ret = 0;
>>
>> --
>> 2.34.1
>>
^ permalink raw reply
* [PATCH] PCI/MSI: Initialize the prepare descriptor by default
From: Naman Jain @ 2025-07-08 5:18 UTC (permalink / raw)
To: Bjorn Helgaas, Thomas Gleixner, Marc Zyngier, Lorenzo Pieralisi,
Shivamurthy Shastri, Shradha Gupta
Cc: Naman Jain, linux-pci, linux-kernel, linux-hyperv, Roman Kisel
Plug the default MSI-X prepare descriptor for non-implemented ops by
default to workaround the inability of Hyper-V vPCI module to setup
the MSI-X descriptors properly; especially for dynamically allocated
MSI-X.
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/pci/msi/irqdomain.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index 765312c92d9b..655e99b9c8cc 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -84,6 +84,8 @@ static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
} else {
if (ops->set_desc == NULL)
ops->set_desc = pci_msi_domain_set_desc;
+ if (ops->prepare_desc == NULL)
+ ops->prepare_desc = pci_msix_prepare_desc;
}
}
base-commit: 26ffb3d6f02cd0935fb9fa3db897767beee1cb2a
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox