* [PATCH v4 1/2] mshv: refactor synic init and cleanup
From: Anirudh Rayabharam @ 2026-02-11 17:07 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, longli, linux-hyperv, linux-kernel; +Cc: anirudh
In-Reply-To: <20260211170728.3056226-1-anirudh@anirudhrb.com>
From: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
Rename mshv_synic_init() to mshv_synic_cpu_init() and
mshv_synic_cleanup() to mshv_synic_cpu_exit() to better reflect that
these functions handle per-cpu synic setup and teardown.
Use mshv_synic_init/cleanup() to perform init/cleanup that is not per-cpu.
Move all the synic related setup from mshv_parent_partition_init.
Move the reboot notifier to mshv_synic.c because it currently only
operates on the synic cpuhp state.
Move out synic_pages from the global mshv_root since it's use is now
completely local to mshv_synic.c.
This is in preparation for the next patch which will add more stuff to
mshv_synic_init().
No functional change.
Signed-off-by: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
---
drivers/hv/mshv_root.h | 5 ++-
drivers/hv/mshv_root_main.c | 59 +++++-------------------------
drivers/hv/mshv_synic.c | 71 +++++++++++++++++++++++++++++++++----
3 files changed, 75 insertions(+), 60 deletions(-)
diff --git a/drivers/hv/mshv_root.h b/drivers/hv/mshv_root.h
index 3c1d88b36741..26e0320c8097 100644
--- a/drivers/hv/mshv_root.h
+++ b/drivers/hv/mshv_root.h
@@ -183,7 +183,6 @@ struct hv_synic_pages {
};
struct mshv_root {
- struct hv_synic_pages __percpu *synic_pages;
spinlock_t pt_ht_lock;
DECLARE_HASHTABLE(pt_htable, MSHV_PARTITIONS_HASH_BITS);
struct hv_partition_property_vmm_capabilities vmm_caps;
@@ -242,8 +241,8 @@ int mshv_register_doorbell(u64 partition_id, doorbell_cb_t doorbell_cb,
void mshv_unregister_doorbell(u64 partition_id, int doorbell_portid);
void mshv_isr(void);
-int mshv_synic_init(unsigned int cpu);
-int mshv_synic_cleanup(unsigned int cpu);
+int mshv_synic_init(struct device *dev);
+void mshv_synic_cleanup(void);
static inline bool mshv_partition_encrypted(struct mshv_partition *partition)
{
diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 681b58154d5e..7c1666456e78 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -2035,7 +2035,6 @@ mshv_dev_release(struct inode *inode, struct file *filp)
return 0;
}
-static int mshv_cpuhp_online;
static int mshv_root_sched_online;
static const char *scheduler_type_to_string(enum hv_scheduler_type type)
@@ -2198,40 +2197,14 @@ root_scheduler_deinit(void)
free_percpu(root_scheduler_output);
}
-static int mshv_reboot_notify(struct notifier_block *nb,
- unsigned long code, void *unused)
-{
- cpuhp_remove_state(mshv_cpuhp_online);
- return 0;
-}
-
-struct notifier_block mshv_reboot_nb = {
- .notifier_call = mshv_reboot_notify,
-};
-
static void mshv_root_partition_exit(void)
{
- unregister_reboot_notifier(&mshv_reboot_nb);
root_scheduler_deinit();
}
static int __init mshv_root_partition_init(struct device *dev)
{
- int err;
-
- err = root_scheduler_init(dev);
- if (err)
- return err;
-
- err = register_reboot_notifier(&mshv_reboot_nb);
- if (err)
- goto root_sched_deinit;
-
- return 0;
-
-root_sched_deinit:
- root_scheduler_deinit();
- return err;
+ return root_scheduler_init(dev);
}
static void mshv_init_vmm_caps(struct device *dev)
@@ -2276,31 +2249,18 @@ static int __init mshv_parent_partition_init(void)
MSHV_HV_MAX_VERSION);
}
- mshv_root.synic_pages = alloc_percpu(struct hv_synic_pages);
- if (!mshv_root.synic_pages) {
- dev_err(dev, "Failed to allocate percpu synic page\n");
- ret = -ENOMEM;
+ ret = mshv_synic_init(dev);
+ if (ret)
goto device_deregister;
- }
-
- ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
- mshv_synic_init,
- mshv_synic_cleanup);
- if (ret < 0) {
- dev_err(dev, "Failed to setup cpu hotplug state: %i\n", ret);
- goto free_synic_pages;
- }
-
- mshv_cpuhp_online = ret;
ret = mshv_retrieve_scheduler_type(dev);
if (ret)
- goto remove_cpu_state;
+ goto synic_cleanup;
if (hv_root_partition())
ret = mshv_root_partition_init(dev);
if (ret)
- goto remove_cpu_state;
+ goto synic_cleanup;
mshv_init_vmm_caps(dev);
@@ -2318,10 +2278,8 @@ static int __init mshv_parent_partition_init(void)
exit_partition:
if (hv_root_partition())
mshv_root_partition_exit();
-remove_cpu_state:
- cpuhp_remove_state(mshv_cpuhp_online);
-free_synic_pages:
- free_percpu(mshv_root.synic_pages);
+synic_cleanup:
+ mshv_synic_cleanup();
device_deregister:
misc_deregister(&mshv_dev);
return ret;
@@ -2335,8 +2293,7 @@ static void __exit mshv_parent_partition_exit(void)
mshv_irqfd_wq_cleanup();
if (hv_root_partition())
mshv_root_partition_exit();
- cpuhp_remove_state(mshv_cpuhp_online);
- free_percpu(mshv_root.synic_pages);
+ mshv_synic_cleanup();
}
module_init(mshv_parent_partition_init);
diff --git a/drivers/hv/mshv_synic.c b/drivers/hv/mshv_synic.c
index f8b0337cdc82..074e37c48876 100644
--- a/drivers/hv/mshv_synic.c
+++ b/drivers/hv/mshv_synic.c
@@ -12,11 +12,16 @@
#include <linux/mm.h>
#include <linux/io.h>
#include <linux/random.h>
+#include <linux/cpuhotplug.h>
+#include <linux/reboot.h>
#include <asm/mshyperv.h>
#include "mshv_eventfd.h"
#include "mshv.h"
+static int synic_cpuhp_online;
+static struct hv_synic_pages __percpu *synic_pages;
+
static u32 synic_event_ring_get_queued_port(u32 sint_index)
{
struct hv_synic_event_ring_page **event_ring_page;
@@ -26,7 +31,7 @@ static u32 synic_event_ring_get_queued_port(u32 sint_index)
u32 message;
u8 tail;
- spages = this_cpu_ptr(mshv_root.synic_pages);
+ spages = this_cpu_ptr(synic_pages);
event_ring_page = &spages->synic_event_ring_page;
synic_eventring_tail = (u8 **)this_cpu_ptr(hv_synic_eventring_tail);
@@ -393,7 +398,7 @@ mshv_intercept_isr(struct hv_message *msg)
void mshv_isr(void)
{
- struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+ struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
struct hv_message *msg;
bool handled;
@@ -446,7 +451,7 @@ void mshv_isr(void)
}
}
-int mshv_synic_init(unsigned int cpu)
+static int mshv_synic_cpu_init(unsigned int cpu)
{
union hv_synic_simp simp;
union hv_synic_siefp siefp;
@@ -455,7 +460,7 @@ int mshv_synic_init(unsigned int cpu)
union hv_synic_sint sint;
#endif
union hv_synic_scontrol sctrl;
- struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+ struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
struct hv_synic_event_flags_page **event_flags_page =
&spages->synic_event_flags_page;
@@ -542,14 +547,14 @@ int mshv_synic_init(unsigned int cpu)
return -EFAULT;
}
-int mshv_synic_cleanup(unsigned int cpu)
+static int mshv_synic_cpu_exit(unsigned int cpu)
{
union hv_synic_sint sint;
union hv_synic_simp simp;
union hv_synic_siefp siefp;
union hv_synic_sirbp sirbp;
union hv_synic_scontrol sctrl;
- struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+ struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
struct hv_synic_event_flags_page **event_flags_page =
&spages->synic_event_flags_page;
@@ -663,3 +668,57 @@ mshv_unregister_doorbell(u64 partition_id, int doorbell_portid)
mshv_portid_free(doorbell_portid);
}
+
+static int mshv_synic_reboot_notify(struct notifier_block *nb,
+ unsigned long code, void *unused)
+{
+ if (!hv_root_partition())
+ return 0;
+
+ cpuhp_remove_state(synic_cpuhp_online);
+ return 0;
+}
+
+static struct notifier_block mshv_synic_reboot_nb = {
+ .notifier_call = mshv_synic_reboot_notify,
+};
+
+int __init mshv_synic_init(struct device *dev)
+{
+ int ret = 0;
+
+ synic_pages = alloc_percpu(struct hv_synic_pages);
+ if (!synic_pages) {
+ dev_err(dev, "Failed to allocate percpu synic page\n");
+ return -ENOMEM;
+ }
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
+ mshv_synic_cpu_init,
+ mshv_synic_cpu_exit);
+ if (ret < 0) {
+ dev_err(dev, "Failed to setup cpu hotplug state: %i\n", ret);
+ goto free_synic_pages;
+ }
+
+ synic_cpuhp_online = ret;
+
+ ret = register_reboot_notifier(&mshv_synic_reboot_nb);
+ if (ret)
+ goto remove_cpuhp_state;
+
+ return 0;
+
+remove_cpuhp_state:
+ cpuhp_remove_state(synic_cpuhp_online);
+free_synic_pages:
+ free_percpu(synic_pages);
+ return ret;
+}
+
+void mshv_synic_cleanup(void)
+{
+ unregister_reboot_notifier(&mshv_synic_reboot_nb);
+ cpuhp_remove_state(synic_cpuhp_online);
+ free_percpu(synic_pages);
+}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 0/2] ARM64 support for doorbell and intercept SINTs
From: Anirudh Rayabharam @ 2026-02-11 17:07 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, longli, linux-hyperv, linux-kernel; +Cc: anirudh
From: "Anirudh Rayabharam (Microsoft)" <anirudh@anirudhrb.com>
On x86, the HYPERVISOR_CALLBACK_VECTOR is used to receive synthetic
interrupts (SINTs) from the hypervisor for doorbells and intercepts.
There is no such vector reserved for arm64.
On arm64, the hypervisor exposes a synthetic register that can be read
to find the INTID that should be used for SINTs. This INTID is in the
PPI range.
Changes in v4:
- Hypervisor now exposes a synthetic register to read the SINT vector
instead of using an ACPI platform device. So make changes to accomodate that.
Changes in v3:
- Moved the hv_root_partition() check into the reboot notifier
to avoid doing it multiple times.
v2: https://lore.kernel.org/linux-hyperv/20260202182706.648192-1-anirudh@anirudhrb.com/
Changes in v2:
Addressed review comments:
- Moved more stuff into mshv_synic.c
- Code simplifications
- Removed unnecessary debug prints
v1: https://lore.kernel.org/linux-hyperv/20260128160437.3342167-1-anirudh@anirudhrb.com/
Anirudh Rayabharam (Microsoft) (2):
mshv: refactor synic init and cleanup
mshv: add arm64 support for doorbell & intercept SINTs
drivers/hv/mshv_root.h | 5 +-
drivers/hv/mshv_root_main.c | 59 ++----------
drivers/hv/mshv_synic.c | 181 +++++++++++++++++++++++++++++++++---
include/hyperv/hvgdk_mini.h | 2 +
4 files changed, 181 insertions(+), 66 deletions(-)
--
2.34.1
^ permalink raw reply
* [PATCH net-next v3] net: mana: Add MAC address to vPort logs and clarify error messages
From: Erni Sri Satya Vennela @ 2026-02-11 5:43 UTC (permalink / raw)
To: ernis, kys, haiyangz, wei.liu, decui, longli, andrew+netdev,
davem, edumazet, kuba, pabeni, dipayanroy, ernis, shradhagupta,
shirazsaleem, gargaditya, linux-hyperv, netdev, linux-kernel
Add MAC address to vPort configuration success message and update error
message to be more specific about HWC message errors in
mana_send_request and mana_hwc_send_request.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
---
Changes in v3:
* Remove the changes from v2 and Update commit message.
* Use "Enabled vPort ..." instead of "Configured vPort" in
mana_cfg_vport.
* Update error logs in mana_hwc_send_request.
Changes in v2:
* Update commit message.
* Use "Enabled vPort ..." instead of "Configured vPort" in
mana_cfg_vport.
* Add info log in mana_uncfg_vport, mana_gd_verify_vf_version,
mana_gd_query_max_resources, mana_query_device_cfg and
mana_query_vport_cfg.
---
.../net/ethernet/microsoft/mana/hw_channel.c | 19 +++++++++++--------
drivers/net/ethernet/microsoft/mana/mana_en.c | 8 ++++----
2 files changed, 15 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index aa4e2731e2ba..d4fd513dc1d6 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -853,6 +853,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
struct hwc_caller_ctx *ctx;
u32 dest_vrcq = 0;
u32 dest_vrq = 0;
+ u32 command;
u16 msg_id;
int err;
@@ -861,8 +862,8 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
tx_wr = &txq->msg_buf->reqs[msg_id];
if (req_len > tx_wr->buf_len) {
- dev_err(hwc->dev, "HWC: req msg size: %d > %d\n", req_len,
- tx_wr->buf_len);
+ dev_err(hwc->dev, "%s:%d: req msg size: %d > %d\n",
+ __func__, __LINE__, req_len, tx_wr->buf_len);
err = -EINVAL;
goto out;
}
@@ -878,6 +879,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
req_msg->req.hwc_msg_id = msg_id;
tx_wr->msg_size = req_len;
+ command = req_msg->req.msg_type;
if (gc->is_pf) {
dest_vrq = hwc->pf_dest_vrq_id;
@@ -886,15 +888,16 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
err = mana_hwc_post_tx_wqe(txq, tx_wr, dest_vrq, dest_vrcq, false);
if (err) {
- dev_err(hwc->dev, "HWC: Failed to post send WQE: %d\n", err);
+ dev_err(hwc->dev, "%s:%d: Failed to post send WQE: %d\n",
+ __func__, __LINE__, err);
goto out;
}
if (!wait_for_completion_timeout(&ctx->comp_event,
(msecs_to_jiffies(hwc->hwc_timeout)))) {
if (hwc->hwc_timeout != 0)
- dev_err(hwc->dev, "HWC: Request timed out: %u ms\n",
- hwc->hwc_timeout);
+ dev_err(hwc->dev, "%s:%d: Command 0x%x timed out: %u ms\n",
+ __func__, __LINE__, command, hwc->hwc_timeout);
/* Reduce further waiting if HWC no response */
if (hwc->hwc_timeout > 1)
@@ -914,9 +917,9 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
err = -EOPNOTSUPP;
goto out;
}
- if (req_msg->req.msg_type != MANA_QUERY_PHY_STAT)
- dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
- ctx->status_code);
+ if (command != MANA_QUERY_PHY_STAT)
+ dev_err(hwc->dev, "%s:%d: Command 0x%x failed with status: 0x%x\n",
+ __func__, __LINE__, command, ctx->status_code);
err = -EPROTO;
goto out;
}
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9b5a72ada5c4..53f24244de75 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1023,8 +1023,8 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
if (req->req.msg_type != MANA_QUERY_PHY_STAT &&
mana_need_log(gc, err))
- dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
- err, resp->status);
+ dev_err(dev, "Command 0x%x failed with status: 0x%x, err: %d\n",
+ req->req.msg_type, resp->status, err);
return err ? err : -EPROTO;
}
@@ -1337,8 +1337,8 @@ int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
apc->tx_shortform_allowed = resp.short_form_allowed;
apc->tx_vp_offset = resp.tx_vport_offset;
- netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n",
- apc->port_handle, protection_dom_id, doorbell_pg_id);
+ netdev_info(apc->ndev, "Enabled vPort %llu PD %u DB %u MAC %pM\n",
+ apc->port_handle, protection_dom_id, doorbell_pg_id, apc->mac_addr);
out:
if (err)
mana_uncfg_vport(apc);
--
2.34.1
^ permalink raw reply related
* Re: [PATCH net-next v2] net: mana: Improve diagnostic logging for better debuggability
From: Erni Sri Satya Vennela @ 2026-02-11 5:20 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Jakub Kicinski, kys, haiyangz, wei.liu, decui, longli,
andrew+netdev, davem, edumazet, pabeni, kotaranov, shradhagupta,
yury.norov, dipayanroy, shirazsaleem, ssengar, gargaditya,
linux-hyperv, netdev, linux-kernel
In-Reply-To: <20260126195850.GO13967@unreal>
Hi Jakub, Leon,
Thankyou for your comments.
I will be sending the next version with updated error logs only
with MAC address reporting in Vport Config.
Additional information will be added into debugfs in a different patch.
^ permalink raw reply
* Re: [PATCH v2 3/3] x86/hyperv: Remove ASM_CALL_CONSTRAINT with VMMCALL insn
From: H. Peter Anvin @ 2026-02-10 22:52 UTC (permalink / raw)
To: Uros Bizjak
Cc: linux-hyperv, x86, linux-kernel, Michael Kelley, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen
In-Reply-To: <CAFULd4ZaRGENKVYXZiaPO0heT+1bpGrVBGzA+Wz9VS1NG6trAQ@mail.gmail.com>
On 2025-11-22 01:33, Uros Bizjak wrote:
>>
>> I think it would be good to have a comment at the point where ASM_CALL_CONSTRAINT is defined explaining its proper use.
>>
>> Specifically, instructions like syscall, vmcall, vmfunc, vmmcall, int xx and VM-specific escape instructions are not "calls" because they either don't modify the stack or create an exception frame (kernel) or signal frame (user space) which is completely special.
>
> The existing comment already mentions CALL instruction only:
>
> /*
> * This output constraint should be used for any inline asm which has a "call"
> * instruction. Otherwise the asm may be inserted before the frame pointer
> * gets set up by the containing function. If you forget to do this, objtool
> * may print a "call without frame pointer save/setup" warning.
> */
>
Yes. Some people seem to have misunderstood it to mean any instruction with
"CALL" in the name.
-hpa
^ permalink raw reply
* RE: [PATCH v2 2/3] x86/hyperv: Use savesegment() instead of inline asm() to save segment registers
From: Michael Kelley @ 2026-02-10 22:40 UTC (permalink / raw)
To: Uros Bizjak, linux-hyperv@vger.kernel.org, x86@kernel.org,
linux-kernel@vger.kernel.org, Wei Liu
Cc: K. Y. Srinivasan, Haiyang Zhang, Dexuan Cui, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, H. Peter Anvin
In-Reply-To: <20251121141437.205481-2-ubizjak@gmail.com>
From: Uros Bizjak <ubizjak@gmail.com> Sent: Friday, November 21, 2025 6:14 AM
>
> Use standard savesegment() utility macro to save segment registers.
Patch 1 of this series was included in the tip tree. But this patch (Patch 2) and
Patch 3 have not been picked up anywhere.
Wei Liu -- could you pick these two up in the hyperv tree?
Michael
>
> Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
> Acked-by: Wei Liu <wei.liu@kernel.org>
> Tested-by: Michael Kelley <mhklinux@outlook.com>
> Cc: "K. Y. Srinivasan" <kys@microsoft.com>
> Cc: Haiyang Zhang <haiyangz@microsoft.com>
> Cc: Dexuan Cui <decui@microsoft.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> ---
> arch/x86/hyperv/ivm.c | 9 +++++----
> 1 file changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
> index 651771534cae..7365d8f43181 100644
> --- a/arch/x86/hyperv/ivm.c
> +++ b/arch/x86/hyperv/ivm.c
> @@ -25,6 +25,7 @@
> #include <asm/e820/api.h>
> #include <asm/desc.h>
> #include <asm/msr.h>
> +#include <asm/segment.h>
> #include <uapi/asm/vmx.h>
>
> #ifdef CONFIG_AMD_MEM_ENCRYPT
> @@ -315,16 +316,16 @@ int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip,
> unsigned int cpu)
> vmsa->gdtr.base = gdtr.address;
> vmsa->gdtr.limit = gdtr.size;
>
> - asm volatile("movl %%es, %%eax;" : "=a" (vmsa->es.selector));
> + savesegment(es, vmsa->es.selector);
> hv_populate_vmcb_seg(vmsa->es, vmsa->gdtr.base);
>
> - asm volatile("movl %%cs, %%eax;" : "=a" (vmsa->cs.selector));
> + savesegment(cs, vmsa->cs.selector);
> hv_populate_vmcb_seg(vmsa->cs, vmsa->gdtr.base);
>
> - asm volatile("movl %%ss, %%eax;" : "=a" (vmsa->ss.selector));
> + savesegment(ss, vmsa->ss.selector);
> hv_populate_vmcb_seg(vmsa->ss, vmsa->gdtr.base);
>
> - asm volatile("movl %%ds, %%eax;" : "=a" (vmsa->ds.selector));
> + savesegment(ds, vmsa->ds.selector);
> hv_populate_vmcb_seg(vmsa->ds, vmsa->gdtr.base);
>
> vmsa->efer = native_read_msr(MSR_EFER);
> --
> 2.51.1
^ permalink raw reply
* Re: [PATCH v1] x86/hyperv: Reserve 3 interrupt vectors used exclusively by mshv
From: Thomas Gleixner @ 2026-02-10 21:23 UTC (permalink / raw)
To: Mukesh Rathor, linux-hyperv, linux-kernel
Cc: kys, haiyangz, wei.liu, decui, longli, mingo, bp, dave.hansen,
x86, hpa
In-Reply-To: <20260102220208.862818-1-mrathor@linux.microsoft.com>
On Fri, Jan 02 2026 at 14:02, Mukesh Rathor wrote:
>
> +#ifndef CONFIG_X86_FRED
This #ifndef is broken. A FRED enabled kernel is no guarantee that the
CPU has FRED. So this has to be unconditional.
> + * Reserve vectors hard coded in the hypervisor. If used outside, the hypervisor
> + * will crash or hang or break into debugger.
> + */
> +static void hv_reserve_irq_vectors(void)
> +{
> + #define HYPERV_DBG_FASTFAIL_VECTOR 0x29
> + #define HYPERV_DBG_ASSERT_VECTOR 0x2C
> + #define HYPERV_DBG_SERVICE_VECTOR 0x2D
As FRED does not need this bit fiddling you want:
if (cpu_feature_enabled(X86_FEATURE_FRED))
return;
right here.
> + if (test_and_set_bit(HYPERV_DBG_ASSERT_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_SERVICE_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_FASTFAIL_VECTOR, system_vectors))
> + BUG();
> +
Thanks,
tglx
^ permalink raw reply
* Re: [PATCH v1] x86/hyperv: Reserve 3 interrupt vectors used exclusively by mshv
From: H. Peter Anvin @ 2026-02-10 20:33 UTC (permalink / raw)
To: Mukesh Rathor, linux-hyperv, linux-kernel
Cc: kys, haiyangz, wei.liu, decui, longli, tglx, mingo, bp,
dave.hansen, x86
In-Reply-To: <20260102220208.862818-1-mrathor@linux.microsoft.com>
On 2026-01-02 14:02, Mukesh Rathor wrote:
>
> v1: Add ifndef CONFIG_X86_FRED (thanks hpa)
>
It just clicked in my brain.
This must be cpu_feature_enabled() not a static #ifndef. Just because the
kernel is compiled with FRED support doesn't mean that it is *using* FRED!
-hpa
> arch/x86/kernel/cpu/mshyperv.c | 26 ++++++++++++++++++++++++++
> 1 file changed, 26 insertions(+)
>
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index 579fb2c64cfd..8ef4ca6733ac 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -478,6 +478,27 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
> }
> EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
>
> +#ifndef CONFIG_X86_FRED
> +/*
> + * Reserve vectors hard coded in the hypervisor. If used outside, the hypervisor
> + * will crash or hang or break into debugger.
> + */
> +static void hv_reserve_irq_vectors(void)
> +{
> + #define HYPERV_DBG_FASTFAIL_VECTOR 0x29
> + #define HYPERV_DBG_ASSERT_VECTOR 0x2C
> + #define HYPERV_DBG_SERVICE_VECTOR 0x2D
> +
> + if (test_and_set_bit(HYPERV_DBG_ASSERT_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_SERVICE_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_FASTFAIL_VECTOR, system_vectors))
> + BUG();
> +
> + pr_info("Hyper-V:reserve vectors: %d %d %d\n", HYPERV_DBG_ASSERT_VECTOR,
> + HYPERV_DBG_SERVICE_VECTOR, HYPERV_DBG_FASTFAIL_VECTOR);
> +}
> +#endif /* CONFIG_X86_FRED */
> +
> static void __init ms_hyperv_init_platform(void)
> {
> int hv_max_functions_eax, eax;
> @@ -510,6 +531,11 @@ static void __init ms_hyperv_init_platform(void)
>
> hv_identify_partition_type();
>
> +#ifndef CONFIG_X86_FRED
> + if (hv_root_partition())
> + hv_reserve_irq_vectors();
> +#endif /* CONFIG_X86_FRED */
> +
> if (cc_platform_has(CC_ATTR_SNP_SECURE_AVIC))
> ms_hyperv.hints |= HV_DEPRECATING_AEOI_RECOMMENDED;
>
^ permalink raw reply
* Re: [PATCH v1] x86/hyperv: Reserve 3 interrupt vectors used exclusively by mshv
From: H. Peter Anvin @ 2026-02-10 19:41 UTC (permalink / raw)
To: Wei Liu, Mukesh Rathor
Cc: linux-hyperv, linux-kernel, kys, haiyangz, decui, longli, tglx,
mingo, bp, dave.hansen, x86
In-Reply-To: <20260115072509.GF3557088@liuwe-devbox-debian-v2.local>
On 2026-01-14 23:25, Wei Liu wrote:
>
> I briefly looked up FRED and checked the code. I understand that once it
> is enabled, Linux kernel doesn't setup the IDT anymore (code in
> arch/x86/kernel/traps.c).
>
> My question is, do we need to do anything when FRED is enabled?
>
Assuming you don't need them handled in any specific way, then you don't. INT
instructions are treated completely separately from hardware interrupts in
FRED, and so they cannot be confused.
By default they will emulate a #GP(0) just as if an INT instruction had been
executed in user space with the DPL of the corresponding interrupt gate < 3;
this is currently the case for interrupt vectors other than 3, 4, and 0x80
(which are handled in fred_intx).
Any INT instruction in kernel space will end up in fred_bad_type().
-hpa
^ permalink raw reply
* Re: [PATCH v1] x86/hyperv: Reserve 3 interrupt vectors used exclusively by mshv
From: Mukesh R @ 2026-02-10 19:12 UTC (permalink / raw)
To: linux-hyperv, linux-kernel
Cc: kys, haiyangz, wei.liu, decui, longli, tglx, mingo, bp,
dave.hansen, x86, hpa
In-Reply-To: <20260102220208.862818-1-mrathor@linux.microsoft.com>
On 1/2/26 14:02, Mukesh Rathor wrote:
> MSVC compiler, used to compile the Microsoft Hyper-V hypervisor currently,
> has an assert intrinsic that uses interrupt vector 0x29 to create an
> exception. This will cause hypervisor to then crash and collect core. As
> such, if this interrupt number is assigned to a device by linux and the
> device generates it, hypervisor will crash. There are two other such
> vectors hard coded in the hypervisor, 0x2C and 0x2D for debug purposes.
> Fortunately, the three vectors are part of the kernel driver space and
> that makes it feasible to reserve them early so they are not assigned
> later.
>
> Signed-off-by: Mukesh Rathor <mrathor@linux.microsoft.com>
> ---
>
> v1: Add ifndef CONFIG_X86_FRED (thanks hpa)
>
> arch/x86/kernel/cpu/mshyperv.c | 26 ++++++++++++++++++++++++++
> 1 file changed, 26 insertions(+)
>
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index 579fb2c64cfd..8ef4ca6733ac 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -478,6 +478,27 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
> }
> EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
>
> +#ifndef CONFIG_X86_FRED
> +/*
> + * Reserve vectors hard coded in the hypervisor. If used outside, the hypervisor
> + * will crash or hang or break into debugger.
> + */
> +static void hv_reserve_irq_vectors(void)
> +{
> + #define HYPERV_DBG_FASTFAIL_VECTOR 0x29
> + #define HYPERV_DBG_ASSERT_VECTOR 0x2C
> + #define HYPERV_DBG_SERVICE_VECTOR 0x2D
> +
> + if (test_and_set_bit(HYPERV_DBG_ASSERT_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_SERVICE_VECTOR, system_vectors) ||
> + test_and_set_bit(HYPERV_DBG_FASTFAIL_VECTOR, system_vectors))
> + BUG();
> +
> + pr_info("Hyper-V:reserve vectors: %d %d %d\n", HYPERV_DBG_ASSERT_VECTOR,
> + HYPERV_DBG_SERVICE_VECTOR, HYPERV_DBG_FASTFAIL_VECTOR);
> +}
> +#endif /* CONFIG_X86_FRED */
> +
> static void __init ms_hyperv_init_platform(void)
> {
> int hv_max_functions_eax, eax;
> @@ -510,6 +531,11 @@ static void __init ms_hyperv_init_platform(void)
>
> hv_identify_partition_type();
>
> +#ifndef CONFIG_X86_FRED
> + if (hv_root_partition())
> + hv_reserve_irq_vectors();
> +#endif /* CONFIG_X86_FRED */
> +
> if (cc_platform_has(CC_ATTR_SNP_SECURE_AVIC))
> ms_hyperv.hints |= HV_DEPRECATING_AEOI_RECOMMENDED;
>
Hi Wei,
Ping on this one... this is show stopper. Are we waiting for an ack
from someone else on x86 side? If so, pl lmk if you know best person
to ping.
Thanks,
-Mukesh
^ permalink raw reply
* RE: [PATCH] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT
From: Michael Kelley @ 2026-02-09 18:25 UTC (permalink / raw)
To: Florian Bezdeka, Jan Kiszka, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Long Li, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86@kernel.org
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org, RT,
Mitchell Levy, skinsburskii@linux.microsoft.com,
mrathor@linux.microsoft.com, anirudh@anirudhrb.com,
schakrabarti@linux.microsoft.com, ssengar@linux.microsoft.com
In-Reply-To: <1b569fcf3d096066aeb011e21f9c1fe21f7df9b5.camel@siemens.com>
From: Florian Bezdeka <florian.bezdeka@siemens.com> Sent: Monday, February 9, 2026 2:35 AM
>
> On Sat, 2026-02-07 at 01:30 +0000, Michael Kelley wrote:
>
> [snip]
> >
> > I've run your suggested experiment on an arm64 VM in the Azure cloud. My
> > kernel was linux-next 20260128. I set CONFIG_PREEMPT_RT=y and
> > CONFIG_PROVE_LOCKING=y, but did not add either of your two patches
> > (neither the storvsc driver patch nor the x86 VMBus interrupt handling patch).
> > The VM comes up and runs, but with this warning during boot:
> >
> > [ 3.075604] hv_utils: Registering HyperV Utility Driver
> > [ 3.075636] hv_vmbus: registering driver hv_utils
> > [ 3.085920] =============================
> > [ 3.088128] hv_vmbus: registering driver hv_netvsc
> > [ 3.091180] [ BUG: Invalid wait context ]
> > [ 3.093544] 6.19.0-rc7-next-20260128+ #3 Tainted: G E
> > [ 3.097582] -----------------------------
> > [ 3.099899] systemd-udevd/284 is trying to lock:
> > [ 3.102568] ffff000100e24490 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
> > [ 3.108208] other info that might help us debug this:
> > [ 3.111454] context-{2:2}
> > [ 3.112987] 1 lock held by systemd-udevd/284:
> > [ 3.115626] #0: ffffd5cfc20bcc80 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0xcc/0x3b8 [hv_vmbus]
> > [ 3.121224] stack backtrace:
> > [ 3.122897] CPU: 0 UID: 0 PID: 284 Comm: systemd-udevd Tainted: G E 6.19.0-rc7-next-20260128+ #3 PREEMPT_RT
> > [ 3.129631] Tainted: [E]=UNSIGNED_MODULE
> > [ 3.131946] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 06/10/2025
> > [ 3.138553] Call trace:
> > [ 3.140015] show_stack+0x20/0x38 (C)
> > [ 3.142137] dump_stack_lvl+0x9c/0x158
> > [ 3.144340] dump_stack+0x18/0x28
> > [ 3.146290] __lock_acquire+0x488/0x1e20
> > [ 3.148569] lock_acquire+0x11c/0x388
> > [ 3.150703] rt_spin_lock+0x54/0x230
> > [ 3.152785] vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
> > [ 3.155611] vmbus_isr+0x34/0x80 [hv_vmbus]
> > [ 3.158093] vmbus_percpu_isr+0x18/0x30 [hv_vmbus]
> > [ 3.160848] handle_percpu_devid_irq+0xdc/0x348
> > [ 3.163495] handle_irq_desc+0x48/0x68
> > [ 3.165851] generic_handle_domain_irq+0x20/0x38
> > [ 3.168664] gic_handle_irq+0x1dc/0x430
> > [ 3.170868] call_on_irq_stack+0x30/0x70
> > [ 3.173161] do_interrupt_handler+0x88/0xa0
> > [ 3.175724] el1_interrupt+0x4c/0xb0
> > [ 3.177855] el1h_64_irq_handler+0x18/0x28
> > [ 3.180332] el1h_64_irq+0x84/0x88
> > [ 3.182378] _raw_spin_unlock_irqrestore+0x4c/0xb0 (P)
> > [ 3.185493] rt_mutex_slowunlock+0x404/0x440
> > [ 3.187951] rt_spin_unlock+0xb8/0x178
> > [ 3.190394] kmem_cache_alloc_noprof+0xf0/0x4f8
> > [ 3.193100] alloc_empty_file+0x64/0x148
> > [ 3.195461] path_openat+0x58/0xaa0
> > [ 3.197658] do_file_open+0xa0/0x140
> > [ 3.199752] do_sys_openat2+0x190/0x278
> > [ 3.202124] do_sys_open+0x60/0xb8
> > [ 3.204047] __arm64_sys_openat+0x2c/0x48
> > [ 3.206433] invoke_syscall+0x6c/0xf8
> > [ 3.208519] el0_svc_common.constprop.0+0x48/0xf0
> > [ 3.211050] do_el0_svc+0x24/0x38
> > [ 3.212990] el0_svc+0x164/0x3c8
> > [ 3.214842] el0t_64_sync_handler+0xd0/0xe8
> > [ 3.217251] el0t_64_sync+0x1b0/0x1b8
> > [ 3.219450] hv_utils: Heartbeat IC version 3.0
> > [ 3.219471] hv_utils: Shutdown IC version 3.2
> > [ 3.219844] hv_utils: TimeSync IC version 4.0
>
> That matches with my expectation that the same problem exists on arm64.
> The patch from Jan addresses that issue for x86 (only, so far) as we do
> not have a working test environment for arm64 yet.
OK. I had understood Jan's earlier comments to mean that the VMBus
interrupt problem was implicitly solved on arm64 because of VMBus using
a standard Linux IRQ on arm64. But evidently that's not the case. So my
earlier comment stands: The code changes should go into the architecture
independent portion of the VMBus driver, and not under arch/x86. I
can probably work with you to test on arm64 if need be.
>
> >
> > I don't see an indication that vmbus_isr() has been offloaded from
> > interrupt level onto a thread. The stack starting with el1h_64_irq()
> > and going forward is the stack for normal per-cpu interrupt handling.
> > Maybe arm64 with PREEMPT_RT does the offload to a thread only
> > for SPIs and LPIs, but not for PPIs? I haven't looked at the source code
> > for how PREEMPT_RT affects arm64 interrupt handling.
> >
> > Also, I had expected to see a problem with storvsc because I did
> > not apply your storvsc patch. But there was no such problem, even
> > with some disk I/O load (read only). arm64 VMs in Azure use exactly
> > the same virtual SCSI devices that are used with x86 VMs in Azure or
> > on local Hyper-V. I don't have an explanation. Will think about it.
> >
>
> Running the --iomix stressor provided by stress-ng was able to trigger
> the SCSI problem within 2 minutes. The result was a completely frozen
> system. For completeness the complete stress-ng command line:
>
> # stress-ng --cpu 2 --iomix 8 --vm 2 --vm-bytes 128M --fork 4
>
Thanks!
Yes, that command line reproduced the storvsc problem on arm64. And
then applying the storvsc patch made the problem go away. FWIW, on
arm64 Linux recovered and kept running after hitting the storvsc
problem.
Michael
^ permalink raw reply
* Re: [PATCH] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT
From: Florian Bezdeka @ 2026-02-09 10:35 UTC (permalink / raw)
To: Michael Kelley, Jan Kiszka, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Long Li, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86@kernel.org
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org, RT,
Mitchell Levy, skinsburskii@linux.microsoft.com,
mrathor@linux.microsoft.com, anirudh@anirudhrb.com,
schakrabarti@linux.microsoft.com, ssengar@linux.microsoft.com
In-Reply-To: <SN6PR02MB41579F60E39CA2A3CA8A5A75D467A@SN6PR02MB4157.namprd02.prod.outlook.com>
On Sat, 2026-02-07 at 01:30 +0000, Michael Kelley wrote:
[snip]
>
> I've run your suggested experiment on an arm64 VM in the Azure cloud. My
> kernel was linux-next 20260128. I set CONFIG_PREEMPT_RT=y and
> CONFIG_PROVE_LOCKING=y, but did not add either of your two patches
> (neither the storvsc driver patch nor the x86 VMBus interrupt handling patch).
> The VM comes up and runs, but with this warning during boot:
>
> [ 3.075604] hv_utils: Registering HyperV Utility Driver
> [ 3.075636] hv_vmbus: registering driver hv_utils
> [ 3.085920] =============================
> [ 3.088128] hv_vmbus: registering driver hv_netvsc
> [ 3.091180] [ BUG: Invalid wait context ]
> [ 3.093544] 6.19.0-rc7-next-20260128+ #3 Tainted: G E
> [ 3.097582] -----------------------------
> [ 3.099899] systemd-udevd/284 is trying to lock:
> [ 3.102568] ffff000100e24490 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
> [ 3.108208] other info that might help us debug this:
> [ 3.111454] context-{2:2}
> [ 3.112987] 1 lock held by systemd-udevd/284:
> [ 3.115626] #0: ffffd5cfc20bcc80 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0xcc/0x3b8 [hv_vmbus]
> [ 3.121224] stack backtrace:
> [ 3.122897] CPU: 0 UID: 0 PID: 284 Comm: systemd-udevd Tainted: G E 6.19.0-rc7-next-20260128+ #3 PREEMPT_RT
> [ 3.129631] Tainted: [E]=UNSIGNED_MODULE
> [ 3.131946] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 06/10/2025
> [ 3.138553] Call trace:
> [ 3.140015] show_stack+0x20/0x38 (C)
> [ 3.142137] dump_stack_lvl+0x9c/0x158
> [ 3.144340] dump_stack+0x18/0x28
> [ 3.146290] __lock_acquire+0x488/0x1e20
> [ 3.148569] lock_acquire+0x11c/0x388
> [ 3.150703] rt_spin_lock+0x54/0x230
> [ 3.152785] vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
> [ 3.155611] vmbus_isr+0x34/0x80 [hv_vmbus]
> [ 3.158093] vmbus_percpu_isr+0x18/0x30 [hv_vmbus]
> [ 3.160848] handle_percpu_devid_irq+0xdc/0x348
> [ 3.163495] handle_irq_desc+0x48/0x68
> [ 3.165851] generic_handle_domain_irq+0x20/0x38
> [ 3.168664] gic_handle_irq+0x1dc/0x430
> [ 3.170868] call_on_irq_stack+0x30/0x70
> [ 3.173161] do_interrupt_handler+0x88/0xa0
> [ 3.175724] el1_interrupt+0x4c/0xb0
> [ 3.177855] el1h_64_irq_handler+0x18/0x28
> [ 3.180332] el1h_64_irq+0x84/0x88
> [ 3.182378] _raw_spin_unlock_irqrestore+0x4c/0xb0 (P)
> [ 3.185493] rt_mutex_slowunlock+0x404/0x440
> [ 3.187951] rt_spin_unlock+0xb8/0x178
> [ 3.190394] kmem_cache_alloc_noprof+0xf0/0x4f8
> [ 3.193100] alloc_empty_file+0x64/0x148
> [ 3.195461] path_openat+0x58/0xaa0
> [ 3.197658] do_file_open+0xa0/0x140
> [ 3.199752] do_sys_openat2+0x190/0x278
> [ 3.202124] do_sys_open+0x60/0xb8
> [ 3.204047] __arm64_sys_openat+0x2c/0x48
> [ 3.206433] invoke_syscall+0x6c/0xf8
> [ 3.208519] el0_svc_common.constprop.0+0x48/0xf0
> [ 3.211050] do_el0_svc+0x24/0x38
> [ 3.212990] el0_svc+0x164/0x3c8
> [ 3.214842] el0t_64_sync_handler+0xd0/0xe8
> [ 3.217251] el0t_64_sync+0x1b0/0x1b8
> [ 3.219450] hv_utils: Heartbeat IC version 3.0
> [ 3.219471] hv_utils: Shutdown IC version 3.2
> [ 3.219844] hv_utils: TimeSync IC version 4.0
That matches with my expectation that the same problem exists on arm64.
The patch from Jan addresses that issue for x86 (only, so far) as we do
not have a working test environment for arm64 yet.
>
> I don't see an indication that vmbus_isr() has been offloaded from
> interrupt level onto a thread. The stack starting with el1h_64_irq()
> and going forward is the stack for normal per-cpu interrupt handling.
> Maybe arm64 with PREEMPT_RT does the offload to a thread only
> for SPIs and LPIs, but not for PPIs? I haven't looked at the source code
> for how PREEMPT_RT affects arm64 interrupt handling.
>
> Also, I had expected to see a problem with storvsc because I did
> not apply your storvsc patch. But there was no such problem, even
> with some disk I/O load (read only). arm64 VMs in Azure use exactly
> the same virtual SCSI devices that are used with x86 VMs in Azure or
> on local Hyper-V. I don't have an explanation. Will think about it.
>
Running the --iomix stressor provided by stress-ng was able to trigger
the SCSI problem within 2 minutes. The result was a completely frozen
system. For completeness the complete stress-ng command line:
# stress-ng --cpu 2 --iomix 8 --vm 2 --vm-bytes 128M --fork 4
Best regards,
Florian
^ permalink raw reply
* [PATCH 2/2] drm/hyperv: During panic do VMBus unload after frame buffer is flushed
From: mhkelley58 @ 2026-02-09 7:02 UTC (permalink / raw)
To: drawat.floss, maarten.lankhorst, mripard, tzimmermann, airlied,
simona, kys, haiyangz, wei.liu, decui, longli, ryasuoka, jfalempe
Cc: dri-devel, linux-kernel, linux-hyperv, stable
In-Reply-To: <20260209070201.1492-1-mhklinux@outlook.com>
From: Michael Kelley <mhklinux@outlook.com>
In a VM, Linux panic information (reason for the panic, stack trace,
etc.) may be written to a serial console and/or a virtual frame buffer
for a graphics console. The latter may need to be flushed back to the
host hypervisor for display.
The current Hyper-V DRM driver for the frame buffer does the flushing
*after* the VMBus connection has been unloaded, such that panic messages
are not displayed on the graphics console. A user with a Hyper-V graphics
console is left with just a hung empty screen after a panic. The enhanced
control that DRM provides over the panic display in the graphics console
is similarly non-functional.
Commit 3671f3777758 ("drm/hyperv: Add support for drm_panic") added
the Hyper-V DRM driver support to flush the virtual frame buffer. It
provided necessary functionality but did not handle the sequencing
problem with VMBus unload.
Fix the full problem by using VMBus functions to suppress the VMBus
unload that is normally done by the VMBus driver in the panic path. Then
after the frame buffer has been flushed, do the VMBus unload so that a
kdump kernel can start cleanly. As expected, CONFIG_DRM_PANIC must be
selected for these changes to have effect. As a side benefit, the
enhanced features of the DRM panic path are also functional.
Fixes: 3671f3777758 ("drm/hyperv: Add support for drm_panic")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
---
drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 4 ++++
drivers/gpu/drm/hyperv/hyperv_drm_modeset.c | 15 ++++++++-------
2 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index 06b5d96e6eaf..79e51643be67 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -150,6 +150,9 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
goto err_free_mmio;
}
+ /* If DRM panic path is stubbed out VMBus code must do the unload */
+ if (IS_ENABLED(CONFIG_DRM_PANIC) && IS_ENABLED(CONFIG_PRINTK))
+ vmbus_set_skip_unload(true);
drm_client_setup(dev, NULL);
return 0;
@@ -169,6 +172,7 @@ static void hyperv_vmbus_remove(struct hv_device *hdev)
struct drm_device *dev = hv_get_drvdata(hdev);
struct hyperv_drm_device *hv = to_hv(dev);
+ vmbus_set_skip_unload(false);
drm_dev_unplug(dev);
drm_atomic_helper_shutdown(dev);
vmbus_close(hdev->channel);
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
index 7978f8c8108c..d48ca6c23b7c 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
@@ -212,15 +212,16 @@ static void hyperv_plane_panic_flush(struct drm_plane *plane)
struct hyperv_drm_device *hv = to_hv(plane->dev);
struct drm_rect rect;
- if (!plane->state || !plane->state->fb)
- return;
+ if (plane->state && plane->state->fb) {
+ rect.x1 = 0;
+ rect.y1 = 0;
+ rect.x2 = plane->state->fb->width;
+ rect.y2 = plane->state->fb->height;
- rect.x1 = 0;
- rect.y1 = 0;
- rect.x2 = plane->state->fb->width;
- rect.y2 = plane->state->fb->height;
+ hyperv_update_dirt(hv->hdev, &rect);
+ }
- hyperv_update_dirt(hv->hdev, &rect);
+ vmbus_initiate_unload(true);
}
static const struct drm_plane_helper_funcs hyperv_plane_helper_funcs = {
--
2.25.1
^ permalink raw reply related
* [PATCH 1/2] Drivers: hv: vmbus: Provide option to skip VMBus unload on panic
From: mhkelley58 @ 2026-02-09 7:02 UTC (permalink / raw)
To: drawat.floss, maarten.lankhorst, mripard, tzimmermann, airlied,
simona, kys, haiyangz, wei.liu, decui, longli, ryasuoka, jfalempe
Cc: dri-devel, linux-kernel, linux-hyperv, stable
From: Michael Kelley <mhklinux@outlook.com>
Currently, VMBus code initiates a VMBus unload in the panic path so
that if a kdump kernel is loaded, it can start fresh in setting up its
own VMBus connection. However, a driver for the VMBus virtual frame
buffer may need to flush dirty portions of the frame buffer back to
the Hyper-V host so that panic information is visible in the graphics
console. To support such flushing, provide exported functions for the
frame buffer driver to specify that the VMBus unload should not be
done by the VMBus driver, and to initiate the VMBus unload itself.
Together these allow a frame buffer driver to delay the VMBus unload
until after it has completed the flush.
Ideally, the VMBus driver could use its own panic-path callback to do
the unload after all frame buffer drivers have finished. But DRM frame
buffer drivers use the kmsg dump callback, and there are no callbacks
after that in the panic path. Hence this somewhat messy approach to
properly sequencing the frame buffer flush and the VMBus unload.
Fixes: 3671f3777758 ("drm/hyperv: Add support for drm_panic")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
---
drivers/hv/channel_mgmt.c | 1 +
drivers/hv/hyperv_vmbus.h | 1 -
drivers/hv/vmbus_drv.c | 25 ++++++++++++++++++-------
include/linux/hyperv.h | 3 +++
4 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 74fed2c073d4..5de83676dbad 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -944,6 +944,7 @@ void vmbus_initiate_unload(bool crash)
else
vmbus_wait_for_unload();
}
+EXPORT_SYMBOL_GPL(vmbus_initiate_unload);
static void vmbus_setup_channel_state(struct vmbus_channel *channel,
struct vmbus_channel_offer_channel *offer)
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index cdbc5f5c3215..5d3944fc93ae 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -440,7 +440,6 @@ void hv_vss_deinit(void);
int hv_vss_pre_suspend(void);
int hv_vss_pre_resume(void);
void hv_vss_onchannelcallback(void *context);
-void vmbus_initiate_unload(bool crash);
static inline void hv_poll_channel(struct vmbus_channel *channel,
void (*cb)(void *))
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 6785ad63a9cb..97dfa529d250 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -69,19 +69,29 @@ bool vmbus_is_confidential(void)
}
EXPORT_SYMBOL_GPL(vmbus_is_confidential);
+static bool skip_vmbus_unload;
+
+/*
+ * Allow a VMBus framebuffer driver to specify that in the case of a panic,
+ * it will do the VMbus unload operation once it has flushed any dirty
+ * portions of the framebuffer to the Hyper-V host.
+ */
+void vmbus_set_skip_unload(bool skip)
+{
+ skip_vmbus_unload = skip;
+}
+EXPORT_SYMBOL_GPL(vmbus_set_skip_unload);
+
/*
* The panic notifier below is responsible solely for unloading the
* vmbus connection, which is necessary in a panic event.
- *
- * Notice an intrincate relation of this notifier with Hyper-V
- * framebuffer panic notifier exists - we need vmbus connection alive
- * there in order to succeed, so we need to order both with each other
- * [see hvfb_on_panic()] - this is done using notifiers' priorities.
*/
static int hv_panic_vmbus_unload(struct notifier_block *nb, unsigned long val,
void *args)
{
- vmbus_initiate_unload(true);
+ if (!skip_vmbus_unload)
+ vmbus_initiate_unload(true);
+
return NOTIFY_DONE;
}
static struct notifier_block hyperv_panic_vmbus_unload_block = {
@@ -2848,7 +2858,8 @@ static void hv_crash_handler(struct pt_regs *regs)
{
int cpu;
- vmbus_initiate_unload(true);
+ if (!skip_vmbus_unload)
+ vmbus_initiate_unload(true);
/*
* In crash handler we can't schedule synic cleanup for all CPUs,
* doing the cleanup for current CPU only. This should be sufficient
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index dfc516c1c719..b0502a336eb3 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1334,6 +1334,9 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
bool fb_overlap_ok);
void vmbus_free_mmio(resource_size_t start, resource_size_t size);
+void vmbus_initiate_unload(bool crash);
+void vmbus_set_skip_unload(bool skip);
+
/*
* GUID definitions of various offer types - services offered to the guest.
*/
--
2.25.1
^ permalink raw reply related
* Re: [PATCH] PCI: hv: Allocate MMIO from above 4GB for the config window
From: Krister Johansen @ 2026-02-07 1:42 UTC (permalink / raw)
To: Matthew Ruffell, Michael Kelley
Cc: DECUI@microsoft.com, bhelgaas@google.com, haiyangz@microsoft.com,
jakeo@microsoft.com, kwilczynski@kernel.org, kys@microsoft.com,
linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-pci@vger.kernel.org, longli@microsoft.com,
lpieralisi@kernel.org, mani@kernel.org, robh@kernel.org,
stable@vger.kernel.org, wei.liu@kernel.org
In-Reply-To: <SN6PR02MB41573CD2EA6CD82A0C238F66D494A@SN6PR02MB4157.namprd02.prod.outlook.com>
Hi Matthew and Michael,
On Fri, Jan 23, 2026 at 06:39:24AM +0000, Michael Kelley wrote:
> From: Matthew Ruffell <matthew.ruffell@canonical.com> Sent: Thursday, January 22, 2026 9:39 PM
> > > > There's a parameter to the kexec() command that governs whether it uses the
> > > > kexec_file_load() system call or the kexec_load() system call.
> > > > I wonder if that parameter makes a difference in the problem described for this
> > > > patch.
> >
> > Yes, it does indeed make a difference. I have been debugging this the past few
> > days, and my colleague Melissa noticed that the problem reproduces when secure
> > boot is disabled, but it does not reproduce when secure boot is enabled.
> > Additionally, it reproduces on jammy, but not noble. It turns out that
> > kexec-tools on jammy defaults to kexec_load() when secure boot is disabled,
> > and when enabled, it instead uses kexec_file_load(). On noble, it defaults to
> > first trying kexec_file_load() before falling back to kexec_load(), so the
> > issue does not reproduce.
>
> This is good info, and definitely a clue. So to be clear, the problem repros
> only when kexec_load() is used. With kexec_file_load(), it does not repro. Is that
> right? I saw a similar distinction when working on commit 304386373007,
> though in the opposite direction!
Just to muddy the waters here, I have a team on the Noble 6.8 kernel
train that's running into this issue on Standard_D#pds_v6 with secure
boot disabled. I've validated via strace(8) that kexec(8) is calling
kexec_file_load(2), but in this case the problem Dexuan describes in the
cover letter occurs but affects NIC attachment instead of the NVMe
storage device. (e.g. pci_hyperv attach of the NIC reports the
pass-through error instead of successfully attaching).
> > > > > /*
> > > > > * Set up a region of MMIO space to use for accessing configuration
> > > > > - * space.
> > > > > + * space. Use the high MMIO range to not conflict with the hyperv_drm
> > > > > + * driver (which normally gets MMIO from the low MMIO range) in the
> > > > > + * kdump kernel of a Gen2 VM, which fails to reserve the framebuffer
> > > > > + * MMIO range in vmbus_reserve_fb() due to screen_info.lfb_base being
> > > > > + * zero in the kdump kernel.
> > > > > */
> > > > > - ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, 0, -1,
> > > > > + ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, SZ_4G, -1,
> > > > > PCI_CONFIG_MMIO_LENGTH, 0x1000, false);
> > > > > if (ret)
> > > > > return ret;
> > > > > --
> >
> > Thank you for the patch Dexuan.
> >
> > This patch fixes the problem on Ubuntu 5.15, and 6.8 based kernels
> > booting V6 instance types on Azure with Gen 2 images.
>
> Are you seeing the problem on x86/64 or arm64 instances in Azure?
> "V6 instance types" could be either, I think, but I'm guessing you
> are on x86/64.
>
> And just to confirm: are you seeing the problem with the
> Hyper-V DRM driver, or the Hyper-V FB driver? This patch mentions
> the DRM driver, so I assume that's the problematic config.
It's been arm64 and not x86 for the case I've seen. They're currently
running with the hyperv_drm driver, but they've also tried swapping to
the fb driver without any change in results.
> > Tested-by: Matthew Ruffell <matthew.ruffell@canonical.com>
All of the above said, I also tested Dexuan's fix on these instances and
found that with the patch applied kdump did work again.
Tested-by: Krister Johansen <johansen@templeofstupid.com>
-K
^ permalink raw reply
* RE: [PATCH] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT
From: Michael Kelley @ 2026-02-07 1:30 UTC (permalink / raw)
To: Jan Kiszka, K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Long Li, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86@kernel.org
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
Florian Bezdeka, RT, Mitchell Levy,
skinsburskii@linux.microsoft.com, mrathor@linux.microsoft.com,
anirudh@anirudhrb.com, schakrabarti@linux.microsoft.com,
ssengar@linux.microsoft.com
In-Reply-To: <eb5debe8-b7d6-4076-b295-9a02271c2ee6@siemens.com>
From: Jan Kiszka <jan.kiszka@siemens.com> Sent: Thursday, February 5, 2026 10:41 PM
>
> On 05.02.26 19:55, Michael Kelley wrote:
> > From: Jan Kiszka <jan.kiszka@siemens.com> Sent: Tuesday, February 3, 2026 8:02 AM
> >>
> >> Resolves the following lockdep report when booting PREEMPT_RT on Hyper-V
> >> with related guest support enabled:
> >>
> >> [ 1.127941] hv_vmbus: registering driver hyperv_drm
> >>
> >> [ 1.132518] =============================
> >> [ 1.132519] [ BUG: Invalid wait context ]
> >> [ 1.132521] 6.19.0-rc8+ #9 Not tainted
> >> [ 1.132524] -----------------------------
> >> [ 1.132525] swapper/0/0 is trying to lock:
> >> [ 1.132526] ffff8b9381bb3c90 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0xc4/0x2b0
> >> [ 1.132543] other info that might help us debug this:
> >> [ 1.132544] context-{2:2}
> >> [ 1.132545] 1 lock held by swapper/0/0:
> >> [ 1.132547] #0: ffffffffa010c4c0 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0x31/0x2b0
> >> [ 1.132557] stack backtrace:
> >> [ 1.132560] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.19.0-rc8+ #9 PREEMPT_{RT,(lazy)}
> >> [ 1.132565] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/25/2025
> >> [ 1.132567] Call Trace:
> >> [ 1.132570] <IRQ>
> >> [ 1.132573] dump_stack_lvl+0x6e/0xa0
> >> [ 1.132581] __lock_acquire+0xee0/0x21b0
> >> [ 1.132592] lock_acquire+0xd5/0x2d0
> >> [ 1.132598] ? vmbus_chan_sched+0xc4/0x2b0
> >> [ 1.132606] ? lock_acquire+0xd5/0x2d0
> >> [ 1.132613] ? vmbus_chan_sched+0x31/0x2b0
> >> [ 1.132619] rt_spin_lock+0x3f/0x1f0
> >> [ 1.132623] ? vmbus_chan_sched+0xc4/0x2b0
> >> [ 1.132629] ? vmbus_chan_sched+0x31/0x2b0
> >> [ 1.132634] vmbus_chan_sched+0xc4/0x2b0
> >> [ 1.132641] vmbus_isr+0x2c/0x150
> >> [ 1.132648] __sysvec_hyperv_callback+0x5f/0xa0
> >> [ 1.132654] sysvec_hyperv_callback+0x88/0xb0
> >> [ 1.132658] </IRQ>
> >> [ 1.132659] <TASK>
> >> [ 1.132660] asm_sysvec_hyperv_callback+0x1a/0x20
> >>
> >> As code paths that handle vmbus IRQs use sleepy locks under PREEMPT_RT,
> >> the complete vmbus_handler execution needs to be moved into thread
> >> context. Open-coding this allows to skip the IPI that irq_work would
> >> additionally bring and which we do not need, being an IRQ, never an NMI.
> >>
> >> Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
> >> ---
[snip]
> >>
> >> arch/x86/kernel/cpu/mshyperv.c | 52 ++++++++++++++++++++++++++++++++--
> >
> > You've added this code under arch/x86. But isn't it architecture independent? I
> > think it should also work on arm64. If that's the case, the code should probably
> > be added to drivers/hv/vmbus_drv.c instead.
> >
>
> I checked that before: arm64 uses normal IRQs, not over-optimized APIC
> vectors. And those IRQs are auto-threaded.
Just to clarify, with CONFIG_PREEMPT_RT=y, you expect the normal Linux
IRQ handling mechanism to offload a per-CPU interrupt handler from interrupt
level onto a thread?
>
> That said, someone with an arm64 Hyper-V deployment should still try to
> run things there once (PREEMPT_RT + PROVE_LOCKING). I don't have such a
> setup.
>
I've run your suggested experiment on an arm64 VM in the Azure cloud. My
kernel was linux-next 20260128. I set CONFIG_PREEMPT_RT=y and
CONFIG_PROVE_LOCKING=y, but did not add either of your two patches
(neither the storvsc driver patch nor the x86 VMBus interrupt handling patch).
The VM comes up and runs, but with this warning during boot:
[ 3.075604] hv_utils: Registering HyperV Utility Driver
[ 3.075636] hv_vmbus: registering driver hv_utils
[ 3.085920] =============================
[ 3.088128] hv_vmbus: registering driver hv_netvsc
[ 3.091180] [ BUG: Invalid wait context ]
[ 3.093544] 6.19.0-rc7-next-20260128+ #3 Tainted: G E
[ 3.097582] -----------------------------
[ 3.099899] systemd-udevd/284 is trying to lock:
[ 3.102568] ffff000100e24490 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
[ 3.108208] other info that might help us debug this:
[ 3.111454] context-{2:2}
[ 3.112987] 1 lock held by systemd-udevd/284:
[ 3.115626] #0: ffffd5cfc20bcc80 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0xcc/0x3b8 [hv_vmbus]
[ 3.121224] stack backtrace:
[ 3.122897] CPU: 0 UID: 0 PID: 284 Comm: systemd-udevd Tainted: G E 6.19.0-rc7-next-20260128+ #3 PREEMPT_RT
[ 3.129631] Tainted: [E]=UNSIGNED_MODULE
[ 3.131946] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 06/10/2025
[ 3.138553] Call trace:
[ 3.140015] show_stack+0x20/0x38 (C)
[ 3.142137] dump_stack_lvl+0x9c/0x158
[ 3.144340] dump_stack+0x18/0x28
[ 3.146290] __lock_acquire+0x488/0x1e20
[ 3.148569] lock_acquire+0x11c/0x388
[ 3.150703] rt_spin_lock+0x54/0x230
[ 3.152785] vmbus_chan_sched+0x128/0x3b8 [hv_vmbus]
[ 3.155611] vmbus_isr+0x34/0x80 [hv_vmbus]
[ 3.158093] vmbus_percpu_isr+0x18/0x30 [hv_vmbus]
[ 3.160848] handle_percpu_devid_irq+0xdc/0x348
[ 3.163495] handle_irq_desc+0x48/0x68
[ 3.165851] generic_handle_domain_irq+0x20/0x38
[ 3.168664] gic_handle_irq+0x1dc/0x430
[ 3.170868] call_on_irq_stack+0x30/0x70
[ 3.173161] do_interrupt_handler+0x88/0xa0
[ 3.175724] el1_interrupt+0x4c/0xb0
[ 3.177855] el1h_64_irq_handler+0x18/0x28
[ 3.180332] el1h_64_irq+0x84/0x88
[ 3.182378] _raw_spin_unlock_irqrestore+0x4c/0xb0 (P)
[ 3.185493] rt_mutex_slowunlock+0x404/0x440
[ 3.187951] rt_spin_unlock+0xb8/0x178
[ 3.190394] kmem_cache_alloc_noprof+0xf0/0x4f8
[ 3.193100] alloc_empty_file+0x64/0x148
[ 3.195461] path_openat+0x58/0xaa0
[ 3.197658] do_file_open+0xa0/0x140
[ 3.199752] do_sys_openat2+0x190/0x278
[ 3.202124] do_sys_open+0x60/0xb8
[ 3.204047] __arm64_sys_openat+0x2c/0x48
[ 3.206433] invoke_syscall+0x6c/0xf8
[ 3.208519] el0_svc_common.constprop.0+0x48/0xf0
[ 3.211050] do_el0_svc+0x24/0x38
[ 3.212990] el0_svc+0x164/0x3c8
[ 3.214842] el0t_64_sync_handler+0xd0/0xe8
[ 3.217251] el0t_64_sync+0x1b0/0x1b8
[ 3.219450] hv_utils: Heartbeat IC version 3.0
[ 3.219471] hv_utils: Shutdown IC version 3.2
[ 3.219844] hv_utils: TimeSync IC version 4.0
I don't see an indication that vmbus_isr() has been offloaded from
interrupt level onto a thread. The stack starting with el1h_64_irq()
and going forward is the stack for normal per-cpu interrupt handling.
Maybe arm64 with PREEMPT_RT does the offload to a thread only
for SPIs and LPIs, but not for PPIs? I haven't looked at the source code
for how PREEMPT_RT affects arm64 interrupt handling.
Also, I had expected to see a problem with storvsc because I did
not apply your storvsc patch. But there was no such problem, even
with some disk I/O load (read only). arm64 VMs in Azure use exactly
the same virtual SCSI devices that are used with x86 VMs in Azure or
on local Hyper-V. I don't have an explanation. Will think about it.
Michael
^ permalink raw reply
* Re: [PATCH 1/3] x86/x2apic: disable x2apic on resume if the kernel expects so
From: Sohil Mehta @ 2026-02-07 0:37 UTC (permalink / raw)
To: Shashank Balaji
Cc: Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H. Peter Anvin, Suresh Siddha, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Long Li, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Jan Kiszka, Paolo Bonzini,
Vitaly Kuznetsov, Juergen Gross, Boris Ostrovsky, Ingo Molnar,
linux-kernel, linux-hyperv, virtualization, jailhouse-dev, kvm,
xen-devel, Rahul Bukte, Daniel Palmer, Tim Bird, stable
In-Reply-To: <aYWs-wvDuS53BHMe@JPC00244420>
On 2/6/2026 12:57 AM, Shashank Balaji wrote:
> On Thu, Feb 05, 2026 at 03:18:58PM -0800, Sohil Mehta wrote:
>> On 2/4/2026 10:07 PM, Shashank Balaji wrote:
>>> On Wed, Feb 04, 2026 at 10:53:28AM -0800, Sohil Mehta wrote:
>>
>>>> It's a bit odd then that the firmware chooses to enable x2apic without
>>>> the OS requesting it.
>>>
>>> Well, the firmware has a setting saying "Enable x2apic", which was
>>> enabled. So it did what the setting says
>>>
>>
I still think the firmware behavior is flawed. Some confusion
originates from the option "Enable x2apic". Based on just these two
words, the behavior seems highly ambiguous. I interpret it to mean "Make
the x2apic feature available to the kernel". Then it is up to the kernel
whether it decides to use it.
If the intention of the BIOS option is to automatically/always enable
x2apic then there is an architectural way to do it. It can set the bits
that track to x2apic_hw_locked(). But, doing it this way during resume
(behind OS's back) is unexpected.
>>
>> pr_warn_once("x2apic unexpectedly re-enabled by the firmware during
>> resume.\n");
>
> At least as per the spec, it's not something the firmware needs to fix,
> and it's not unexpected re-enablement.
>
> Am I missing something?
>
> But it _is_ surprising that this bug went unnoticed for so long :)
Maybe this BIOS option isn't typically found in a production firmware. I
think it would be preferable to have the pr_warn_once() but I won't push
super hard for it due to the unclear information.
Whatever you choose for v2, can you please briefly describe the
ambiguity in the commit message? It would help other reviewers provide
better insight and be handy if we ever need to come back to this.
^ permalink raw reply
* RE: [PATCH v3 4/4] mshv: Handle insufficient root memory hypervisor statuses
From: Michael Kelley @ 2026-02-06 18:54 UTC (permalink / raw)
To: Stanislav Kinsburskii, kys@microsoft.com, haiyangz@microsoft.com,
wei.liu@kernel.org, decui@microsoft.com, longli@microsoft.com
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <177031694699.186911.12873334535011325477.stgit@skinsburskii-cloud-desktop.internal.cloudapp.net>
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com> Sent: Thursday, February 5, 2026 10:42 AM
> To: kys@microsoft.com; haiyangz@microsoft.com; wei.liu@kernel.org;
> decui@microsoft.com; longli@microsoft.com
> Cc: linux-hyperv@vger.kernel.org; linux-kernel@vger.kernel.org
> Subject: [PATCH v3 4/4] mshv: Handle insufficient root memory hypervisor statuses
>
> When creating guest partition objects, the hypervisor may fail to
> allocate root partition pages and return an insufficient memory status.
> In this case, deposit memory using the root partition ID instead.
>
> Note: This error should never occur in a guest of L1VH partition context.
>
> Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> ---
> drivers/hv/hv_common.c | 2 +
> drivers/hv/hv_proc.c | 14 ++++++++++
> include/hyperv/hvgdk_mini.h | 58 ++++++++++++++++++++++---------------------
> 3 files changed, 46 insertions(+), 28 deletions(-)
>
> diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
> index f20596276662..6b67ac616789 100644
> --- a/drivers/hv/hv_common.c
> +++ b/drivers/hv/hv_common.c
> @@ -794,6 +794,8 @@ static const struct hv_status_info hv_status_infos[] = {
> _STATUS_INFO(HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE, -EIO),
> _STATUS_INFO(HV_STATUS_INSUFFICIENT_MEMORY, -ENOMEM),
> _STATUS_INFO(HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY, -ENOMEM),
> + _STATUS_INFO(HV_STATUS_INSUFFICIENT_ROOT_MEMORY, -ENOMEM),
> + _STATUS_INFO(HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY, -ENOMEM),
> _STATUS_INFO(HV_STATUS_INVALID_PARTITION_ID, -EINVAL),
> _STATUS_INFO(HV_STATUS_INVALID_VP_INDEX, -EINVAL),
> _STATUS_INFO(HV_STATUS_NOT_FOUND, -EIO),
> diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
> index 181f6d02bce3..5f4fd9c3231c 100644
> --- a/drivers/hv/hv_proc.c
> +++ b/drivers/hv/hv_proc.c
> @@ -121,6 +121,18 @@ int hv_deposit_memory_node(int node, u64 partition_id,
> case HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY:
> num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
> break;
> +
> + case HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY:
> + num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
> + fallthrough;
> + case HV_STATUS_INSUFFICIENT_ROOT_MEMORY:
> + if (!hv_root_partition()) {
> + hv_status_err(hv_status, "Unexpected root memory deposit\n");
> + return -ENOMEM;
> + }
> + partition_id = HV_PARTITION_ID_SELF;
> + break;
> +
Per the discussion in v1 of this patch set, if the number of pages that should be
deposited in a particular situation is different from what this function provides,
the fallback is to use hv_call_deposit_pages() directly. From what I see, there's
only one such fallback case after a hypercall failure -- in hv_do_map_gpa_hcall().
The other uses of hv_call_deposit_pages() are initial deposits when creating a
VP or partition.
But if hv_call_deposit_pages() is used directly, the logic added here to detect
insufficient root memory and deposit to HV_PARTITION_ID_SELF isn't applied.
So if the hypercall in hv_do_map_gpa_hcall() fails with insufficient root
memory, the deposit is done to the wrong partition ID. If that case can
actually happen, then some additional logic is needed in
hv_do_map_gpa_hcall() to handle it. Or there needs to be a fallback
function that contains the logic.
Other than that, everything else in this patch set looks good to me.
Michael
> default:
> hv_status_err(hv_status, "Unexpected!\n");
> return -ENOMEM;
^ permalink raw reply
* Re: [PATCH v3 4/4] mshv: Handle insufficient root memory hypervisor statuses
From: Stanislav Kinsburskii @ 2026-02-06 17:02 UTC (permalink / raw)
To: Anirudh Rayabharam
Cc: kys, haiyangz, wei.liu, decui, longli, linux-hyperv, linux-kernel
In-Reply-To: <aYWCmVxnO8R3vsc-@anirudh-surface.localdomain>
On Fri, Feb 06, 2026 at 05:56:41AM +0000, Anirudh Rayabharam wrote:
> On Thu, Feb 05, 2026 at 06:42:27PM +0000, Stanislav Kinsburskii wrote:
> > When creating guest partition objects, the hypervisor may fail to
> > allocate root partition pages and return an insufficient memory status.
> > In this case, deposit memory using the root partition ID instead.
> >
> > Note: This error should never occur in a guest of L1VH partition context.
>
> I think you should rephrse this to:
>
> "... should never occur in an L1VH partition"
>
> because none of the errors in this patch series occur inside a guest. They
> either occur in L1VH or root or both.
>
> >
> > Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> > ---
> > drivers/hv/hv_common.c | 2 +
> > drivers/hv/hv_proc.c | 14 ++++++++++
> > include/hyperv/hvgdk_mini.h | 58 ++++++++++++++++++++++---------------------
> > 3 files changed, 46 insertions(+), 28 deletions(-)
> >
> > diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
> > index f20596276662..6b67ac616789 100644
> > --- a/drivers/hv/hv_common.c
> > +++ b/drivers/hv/hv_common.c
> > @@ -794,6 +794,8 @@ static const struct hv_status_info hv_status_infos[] = {
> > _STATUS_INFO(HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE, -EIO),
> > _STATUS_INFO(HV_STATUS_INSUFFICIENT_MEMORY, -ENOMEM),
> > _STATUS_INFO(HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY, -ENOMEM),
> > + _STATUS_INFO(HV_STATUS_INSUFFICIENT_ROOT_MEMORY, -ENOMEM),
> > + _STATUS_INFO(HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY, -ENOMEM),
> > _STATUS_INFO(HV_STATUS_INVALID_PARTITION_ID, -EINVAL),
> > _STATUS_INFO(HV_STATUS_INVALID_VP_INDEX, -EINVAL),
> > _STATUS_INFO(HV_STATUS_NOT_FOUND, -EIO),
> > diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
> > index 181f6d02bce3..5f4fd9c3231c 100644
> > --- a/drivers/hv/hv_proc.c
> > +++ b/drivers/hv/hv_proc.c
> > @@ -121,6 +121,18 @@ int hv_deposit_memory_node(int node, u64 partition_id,
> > case HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY:
> > num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
> > break;
> > +
> > + case HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY:
> > + num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
> > + fallthrough;
> > + case HV_STATUS_INSUFFICIENT_ROOT_MEMORY:
>
> I have the same comment as on v2 about num_pages being uninitialized when we
> reach this case directly.
>
It is initialized to 1 on top of the function.
Thanks,
Stanislav.
> Thanks,
> Anirudh.
>
> > + if (!hv_root_partition()) {
> > + hv_status_err(hv_status, "Unexpected root memory deposit\n");
> > + return -ENOMEM;
> > + }
> > + partition_id = HV_PARTITION_ID_SELF;
> > + break;
> > +
> > default:
> > hv_status_err(hv_status, "Unexpected!\n");
> > return -ENOMEM;
> > @@ -134,6 +146,8 @@ bool hv_result_needs_memory(u64 status)
> > switch (hv_result(status)) {
> > case HV_STATUS_INSUFFICIENT_MEMORY:
> > case HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY:
> > + case HV_STATUS_INSUFFICIENT_ROOT_MEMORY:
> > + case HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY:
> > return true;
> > }
> > return false;
> > diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
> > index 99ea0d03e657..50f5a1419052 100644
> > --- a/include/hyperv/hvgdk_mini.h
> > +++ b/include/hyperv/hvgdk_mini.h
> > @@ -14,34 +14,36 @@ struct hv_u128 {
> > } __packed;
> >
> > /* NOTE: when adding below, update hv_result_to_string() */
> > -#define HV_STATUS_SUCCESS 0x0
> > -#define HV_STATUS_INVALID_HYPERCALL_CODE 0x2
> > -#define HV_STATUS_INVALID_HYPERCALL_INPUT 0x3
> > -#define HV_STATUS_INVALID_ALIGNMENT 0x4
> > -#define HV_STATUS_INVALID_PARAMETER 0x5
> > -#define HV_STATUS_ACCESS_DENIED 0x6
> > -#define HV_STATUS_INVALID_PARTITION_STATE 0x7
> > -#define HV_STATUS_OPERATION_DENIED 0x8
> > -#define HV_STATUS_UNKNOWN_PROPERTY 0x9
> > -#define HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE 0xA
> > -#define HV_STATUS_INSUFFICIENT_MEMORY 0xB
> > -#define HV_STATUS_INVALID_PARTITION_ID 0xD
> > -#define HV_STATUS_INVALID_VP_INDEX 0xE
> > -#define HV_STATUS_NOT_FOUND 0x10
> > -#define HV_STATUS_INVALID_PORT_ID 0x11
> > -#define HV_STATUS_INVALID_CONNECTION_ID 0x12
> > -#define HV_STATUS_INSUFFICIENT_BUFFERS 0x13
> > -#define HV_STATUS_NOT_ACKNOWLEDGED 0x14
> > -#define HV_STATUS_INVALID_VP_STATE 0x15
> > -#define HV_STATUS_NO_RESOURCES 0x1D
> > -#define HV_STATUS_PROCESSOR_FEATURE_NOT_SUPPORTED 0x20
> > -#define HV_STATUS_INVALID_LP_INDEX 0x41
> > -#define HV_STATUS_INVALID_REGISTER_VALUE 0x50
> > -#define HV_STATUS_OPERATION_FAILED 0x71
> > -#define HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY 0x75
> > -#define HV_STATUS_TIME_OUT 0x78
> > -#define HV_STATUS_CALL_PENDING 0x79
> > -#define HV_STATUS_VTL_ALREADY_ENABLED 0x86
> > +#define HV_STATUS_SUCCESS 0x0
> > +#define HV_STATUS_INVALID_HYPERCALL_CODE 0x2
> > +#define HV_STATUS_INVALID_HYPERCALL_INPUT 0x3
> > +#define HV_STATUS_INVALID_ALIGNMENT 0x4
> > +#define HV_STATUS_INVALID_PARAMETER 0x5
> > +#define HV_STATUS_ACCESS_DENIED 0x6
> > +#define HV_STATUS_INVALID_PARTITION_STATE 0x7
> > +#define HV_STATUS_OPERATION_DENIED 0x8
> > +#define HV_STATUS_UNKNOWN_PROPERTY 0x9
> > +#define HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE 0xA
> > +#define HV_STATUS_INSUFFICIENT_MEMORY 0xB
> > +#define HV_STATUS_INVALID_PARTITION_ID 0xD
> > +#define HV_STATUS_INVALID_VP_INDEX 0xE
> > +#define HV_STATUS_NOT_FOUND 0x10
> > +#define HV_STATUS_INVALID_PORT_ID 0x11
> > +#define HV_STATUS_INVALID_CONNECTION_ID 0x12
> > +#define HV_STATUS_INSUFFICIENT_BUFFERS 0x13
> > +#define HV_STATUS_NOT_ACKNOWLEDGED 0x14
> > +#define HV_STATUS_INVALID_VP_STATE 0x15
> > +#define HV_STATUS_NO_RESOURCES 0x1D
> > +#define HV_STATUS_PROCESSOR_FEATURE_NOT_SUPPORTED 0x20
> > +#define HV_STATUS_INVALID_LP_INDEX 0x41
> > +#define HV_STATUS_INVALID_REGISTER_VALUE 0x50
> > +#define HV_STATUS_OPERATION_FAILED 0x71
> > +#define HV_STATUS_INSUFFICIENT_ROOT_MEMORY 0x73
> > +#define HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY 0x75
> > +#define HV_STATUS_TIME_OUT 0x78
> > +#define HV_STATUS_CALL_PENDING 0x79
> > +#define HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY 0x83
> > +#define HV_STATUS_VTL_ALREADY_ENABLED 0x86
> >
> > /*
> > * The Hyper-V TimeRefCount register and the TSC
> >
> >
^ permalink raw reply
* Re: [PATCH 3/3] x86/virt: rename x2apic_available to x2apic_without_ir_available
From: Shashank Balaji @ 2026-02-06 9:23 UTC (permalink / raw)
To: Sohil Mehta
Cc: Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H. Peter Anvin, K. Y. Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Jan Kiszka, Paolo Bonzini,
Vitaly Kuznetsov, Juergen Gross, Boris Ostrovsky, linux-kernel,
linux-hyperv, virtualization, jailhouse-dev, kvm, xen-devel,
Rahul Bukte, Daniel Palmer, Tim Bird
In-Reply-To: <ab7f5935-fd5e-4ba5-a97d-5433f241a089@intel.com>
On Thu, Feb 05, 2026 at 04:10:37PM -0800, Sohil Mehta wrote:
> On 2/2/2026 1:51 AM, Shashank Balaji wrote:
> > No functional change.
> >
> > x86_init.hyper.x2apic_available is used only in try_to_enable_x2apic to check if
> > x2apic needs to be disabled if interrupt remapping support isn't present. But
> > the name x2apic_available doesn't reflect that usage.
> >
>
> I don't understand the premise of this patch. Shouldn't the variable
> name reflect what is stored rather than how it is used?
Sorry about the confusion, I should have used '()'.
x86_init.hyper.x2apic_available() is called only in
try_to_enable_x2apic(). Here's the relevant snippet:
static __init void try_to_enable_x2apic(int remap_mode)
{
if (x2apic_state == X2APIC_DISABLED)
return;
if (remap_mode != IRQ_REMAP_X2APIC_MODE) {
u32 apic_limit = 255;
/*
* Using X2APIC without IR is not architecturally supported
* on bare metal but may be supported in guests.
*/
if (!x86_init.hyper.x2apic_available()) {
pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n");
x2apic_disable();
return;
}
So the question being asked is, "can x2apic be used without IR?", but
the name "x2apic_available" signals "is x2apic available?". I found this
confusing while going through the source.
Most hypervisors set their x2apic_available() implementation to
essentially return if the CPU supports x2apic or not, which is valid
given the name "x2apic_available", but x2apic availability is not what's in
question at the callsite.
> > This is what x2apic_available is set to for various hypervisors:
> >
> > acrn boot_cpu_has(X86_FEATURE_X2APIC)
> > mshyperv boot_cpu_has(X86_FEATURE_X2APIC)
> > xen boot_cpu_has(X86_FEATURE_X2APIC) or false
> > vmware vmware_legacy_x2apic_available
> > kvm kvm_cpuid_base() != 0
> > jailhouse x2apic_enabled()
> > bhyve true
> > default false
> >
>
> If both interrupt remapping and x2apic are enabled, what would the name
> x2apic_without_ir_available signify?
If IR is enabled, then the branch to call x2apic_available() wouldn't be taken :)
So the meaning of x2apic_without_ir_available wouldn't be relevant
anymore.
> A value of "true" would mean x2apic is available without IR. But that
> would be inaccurate for most hypervisors. A value of "false" could be
> interpreted as x2apic is not available, which is also inaccurate.
>
> To me, x2apic_available makes more sense than
> x2apic_without_ir_available based on the values being set by the
> hypervisors.
I agree with you, and I think therein lies the problem. Most hypervisors
are answering the broader question "is x2apic available?", so the name
"x2apic_available" makes sense.
I think further work is required to check if various implementations of
x2apic_available() also need to be changed to reflect the "x2apic
without IR?" semantic, but I don't know enough to do that myself. Maybe
I should have added TODOs above the implementations.
I would like the feedback of the virt folks too on all this, maybe I'm
misinterpreting what's going on here.
> > Bare metal and vmware correctly check if x2apic is available without interrupt
> > remapping. The rest of them check if x2apic is enabled/supported, and kvm just
> > checks if the kernel is running on kvm. The other hypervisors may have to have
> > their checks audited.
> >
> AFAIU, the value on bare metal is set to false because this is a
> hypervisor specific variable. Perhaps I have misunderstood something?
^ permalink raw reply
* Re: [PATCH 1/3] x86/x2apic: disable x2apic on resume if the kernel expects so
From: Shashank Balaji @ 2026-02-06 8:57 UTC (permalink / raw)
To: Sohil Mehta
Cc: Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H. Peter Anvin, Suresh Siddha, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Long Li, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Jan Kiszka, Paolo Bonzini,
Vitaly Kuznetsov, Juergen Gross, Boris Ostrovsky, Ingo Molnar,
linux-kernel, linux-hyperv, virtualization, jailhouse-dev, kvm,
xen-devel, Rahul Bukte, Daniel Palmer, Tim Bird, stable
In-Reply-To: <e5ac3272-795b-488c-b767-290fd50f2105@intel.com>
On Thu, Feb 05, 2026 at 03:18:58PM -0800, Sohil Mehta wrote:
> On 2/4/2026 10:07 PM, Shashank Balaji wrote:
> > On Wed, Feb 04, 2026 at 10:53:28AM -0800, Sohil Mehta wrote:
>
> >> It's a bit odd then that the firmware chooses to enable x2apic without
> >> the OS requesting it.
> >
> > Well, the firmware has a setting saying "Enable x2apic", which was
> > enabled. So it did what the setting says
> >
>
> The expectation would be that firmware would restore to the same state
> before lapic_suspend().
I'm a bit out of my depth here, but I went looking around, and this is from the
latest ACPI spec (v6.6) [1]:
When executing from the power-on reset vector as a result of waking
from an S2 or S3 sleep state, the platform firmware performs only the
hardware initialization required to restore the system to either the
state the platform was in prior to the initial operating system boot,
or to the pre-sleep configuration state. In multiprocessor systems,
non-boot processors should be placed in the same state as prior to the
initial operating system boot.
(further ahead)
If this is an S2 or S3 wake, then the platform runtime firmware
restores minimum context of the system before jumping to the waking
vector. This includes:
CPU configuration. Platform runtime firmware restores the
pre-sleep configuration or initial boot configuration of each
CPU (MSR, MTRR, firmware update, SMBase, and so on). Interrupts
must be disabled (for IA-32 processors, disabled by CLI
instruction).
(and other things)
I suppose, in my case, the firmware is restoring initial boot
configuration on S3 resume. And initial boot configuration of x2apic is
set from the firmware's UI "Enable x2apic".
> Maybe a warning would be useful to encourage firmware to fix this going
> forward. I don't have a strong preference on the wording, but how about?
>
> pr_warn_once("x2apic unexpectedly re-enabled by the firmware during
> resume.\n");
At least as per the spec, it's not something the firmware needs to fix,
and it's not unexpected re-enablement.
Am I missing something?
But it _is_ surprising that this bug went unnoticed for so long :)
[1] https://uefi.org/specs/ACPI/6.6/16_Waking_and_Sleeping.html#initialization
^ permalink raw reply
* Re: [PATCH] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT
From: Naman Jain @ 2026-02-06 7:32 UTC (permalink / raw)
To: Wei Liu, Jan Kiszka
Cc: Magnus Kulke, K. Y. Srinivasan, Haiyang Zhang, Dexuan Cui,
Long Li, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, x86, linux-hyperv, linux-kernel, Florian Bezdeka, RT,
Mitchell Levy, skinsburskii, mrathor, anirudh, schakrabarti,
ssengar
In-Reply-To: <20260204073629.GP79272@liuwe-devbox-debian-v2.local>
On 2/4/2026 1:06 PM, Wei Liu wrote:
> On Wed, Feb 04, 2026 at 08:32:04AM +0100, Jan Kiszka wrote:
>> On 04.02.26 08:29, Wei Liu wrote:
>>> On Wed, Feb 04, 2026 at 08:26:48AM +0100, Jan Kiszka wrote:
>>>> On 04.02.26 08:19, Jan Kiszka wrote:
>>>>> On 04.02.26 08:00, Wei Liu wrote:
>>>>>> On Tue, Feb 03, 2026 at 05:01:30PM +0100, Jan Kiszka wrote:
>>>>>>> From: Jan Kiszka <jan.kiszka@siemens.com>
>>>>>>>
>>>>>>> Resolves the following lockdep report when booting PREEMPT_RT on Hyper-V
>>>>>>> with related guest support enabled:
>>>>>>
>>>>>> So all it takes to reproduce this is to enabled PREEMPT_RT?
>>>>>>
>>>>>
>>>>> ...and enable CONFIG_PROVE_LOCKING so that you do not have to wait for
>>>>> your system to actually run into the bug. Lockdep already triggers
>>>>> during bootup.
>>>>>
>>>>>> Asking because ...
>>>>>>
>>>>>>> struct pt_regs *old_regs = set_irq_regs(regs);
>>>>>>> @@ -158,8 +196,12 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
>>>>>>> if (mshv_handler)
>>>>>>> mshv_handler();
>>>>>>
>>>>>> ... to err on the safe side we should probably do the same for
>>>>>> mshv_handler as well.
>>>>>>
>>>>>
>>>>> Valid question. We so far worked based on lockdep reports, and the
>>>>> mshv_handler didn't trigger yet. Either it is not run in our setup, or
>>>>> it is actually already fine. But I have a code review on my agenda
>>>>> regarding potential remaining issues in mshv.
>>>>>
>>>>> Is there something needed to trigger the mshv_handler so that we can
>>>>> test it?
>>>>>
>>>>
>>>> Ah, that depends on CONFIG_MSHV_ROOT. Is that related to the accelerator
>>>> mode that Magnus presented in [1]? We briefly chatted about it and also
>>>> my problems with the drivers after his talk on Saturday.
>>>
>>> Yes. That is the driver. If PROVE_LOCKING triggers the warning without
>>> running the code, perhaps turning on MSHV_ROOT is enough.
>>>
>>
>> But if my VM is not a root partition, I wouldn't use that driver, would I?
>
> No, you wouldn't. You cannot do that until later this year. If you
> cannot test that, so be it. I'm fine with applying your patch and then
> move the mshv_handler logic later ourselves.
>
> I've CC'ed a few folks from Microsoft.
>
> Saurabh, Long, and Dexuan, can you review and test this patch for VMBus?
I tested this and didn't see any issues with OpenHCL/mshv_vtl.
Regards,
Naman
^ permalink raw reply
* Re: [PATCH] mshv: fix SRCU protection in irqfd resampler ack handler
From: Wei Liu @ 2026-02-06 7:06 UTC (permalink / raw)
To: lirongqing
Cc: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li,
linux-hyperv, linux-kernel
In-Reply-To: <20260205094010.4301-1-lirongqing@baidu.com>
On Thu, Feb 05, 2026 at 04:40:10AM -0500, lirongqing wrote:
> From: Li RongQing <lirongqing@baidu.com>
>
> Replace hlist_for_each_entry_rcu() with hlist_for_each_entry_srcu()
> in mshv_irqfd_resampler_ack() to correctly handle SRCU-protected
> linked list traversal.
>
> The function uses SRCU (sleepable RCU) synchronization via
> partition->pt_irq_srcu, but was incorrectly using the RCU variant
> for list iteration. This could lead to race conditions when the
> list is modified concurrently.
>
> Also add srcu_read_lock_held() assertion as required by
> hlist_for_each_entry_srcu() to ensure we're in the proper
> read-side critical section.
>
> Signed-off-by: Li RongQing <lirongqing@baidu.com>
Thank you for the patch. Applied.
I also added a Fixes tag to the commit message.
Fixes: 621191d709b14 ("Drivers: hv: Introduce mshv_root module to expose /dev/mshv to VMMs")
> ---
> drivers/hv/mshv_eventfd.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c
> index 0b75ff1..6d176ed 100644
> --- a/drivers/hv/mshv_eventfd.c
> +++ b/drivers/hv/mshv_eventfd.c
> @@ -87,8 +87,9 @@ static void mshv_irqfd_resampler_ack(struct mshv_irq_ack_notifier *mian)
>
> idx = srcu_read_lock(&partition->pt_irq_srcu);
>
> - hlist_for_each_entry_rcu(irqfd, &resampler->rsmplr_irqfd_list,
> - irqfd_resampler_hnode) {
> + hlist_for_each_entry_srcu(irqfd, &resampler->rsmplr_irqfd_list,
> + irqfd_resampler_hnode,
> + srcu_read_lock_held(&partition->pt_irq_srcu)) {
> if (hv_should_clear_interrupt(irqfd->irqfd_lapic_irq.lapic_control.interrupt_type))
> hv_call_clear_virtual_interrupt(partition->pt_id);
>
> --
> 2.9.4
>
^ permalink raw reply
* Re: [PATCH v3] mshv: make field names descriptive in a header struct
From: Wei Liu @ 2026-02-06 7:03 UTC (permalink / raw)
To: Mukesh R; +Cc: linux-hyperv, wei.liu
In-Reply-To: <20260204202328.196690-1-mrathor@linux.microsoft.com>
On Wed, Feb 04, 2026 at 12:23:28PM -0800, Mukesh R wrote:
> When struct fields use very common names like "pages" or "type", it makes
> it difficult to find uses of these fields with tools like grep, cscope,
> etc when the struct is in a header file included in many places. Add
> prefix mreg_ to some fields in struct mshv_mem_region to make it easier
> to find them.
>
> There is no functional change.
>
> Signed-off-by: Mukesh R <mrathor@linux.microsoft.com>
> ---
> V3: rebase to afefdb2bc945 (origin/hyperv-next)
Applied.
^ permalink raw reply
* [PATCH v2] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT
From: Jan Kiszka @ 2026-02-06 6:47 UTC (permalink / raw)
To: K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86
Cc: linux-hyperv, linux-kernel, Florian Bezdeka, RT, Mitchell Levy,
Michael Kelley
From: Jan Kiszka <jan.kiszka@siemens.com>
Resolves the following lockdep report when booting PREEMPT_RT on Hyper-V
with related guest support enabled:
[ 1.127941] hv_vmbus: registering driver hyperv_drm
[ 1.132518] =============================
[ 1.132519] [ BUG: Invalid wait context ]
[ 1.132521] 6.19.0-rc8+ #9 Not tainted
[ 1.132524] -----------------------------
[ 1.132525] swapper/0/0 is trying to lock:
[ 1.132526] ffff8b9381bb3c90 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0xc4/0x2b0
[ 1.132543] other info that might help us debug this:
[ 1.132544] context-{2:2}
[ 1.132545] 1 lock held by swapper/0/0:
[ 1.132547] #0: ffffffffa010c4c0 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0x31/0x2b0
[ 1.132557] stack backtrace:
[ 1.132560] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.19.0-rc8+ #9 PREEMPT_{RT,(lazy)}
[ 1.132565] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/25/2025
[ 1.132567] Call Trace:
[ 1.132570] <IRQ>
[ 1.132573] dump_stack_lvl+0x6e/0xa0
[ 1.132581] __lock_acquire+0xee0/0x21b0
[ 1.132592] lock_acquire+0xd5/0x2d0
[ 1.132598] ? vmbus_chan_sched+0xc4/0x2b0
[ 1.132606] ? lock_acquire+0xd5/0x2d0
[ 1.132613] ? vmbus_chan_sched+0x31/0x2b0
[ 1.132619] rt_spin_lock+0x3f/0x1f0
[ 1.132623] ? vmbus_chan_sched+0xc4/0x2b0
[ 1.132629] ? vmbus_chan_sched+0x31/0x2b0
[ 1.132634] vmbus_chan_sched+0xc4/0x2b0
[ 1.132641] vmbus_isr+0x2c/0x150
[ 1.132648] __sysvec_hyperv_callback+0x5f/0xa0
[ 1.132654] sysvec_hyperv_callback+0x88/0xb0
[ 1.132658] </IRQ>
[ 1.132659] <TASK>
[ 1.132660] asm_sysvec_hyperv_callback+0x1a/0x20
As code paths that handle vmbus IRQs use sleepy locks under PREEMPT_RT,
the complete vmbus_handler execution needs to be moved into thread
context. Open-coding this allows to skip the IPI that irq_work would
additionally bring and which we do not need, being an IRQ, never an NMI.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
Changes in v2:
- reorder vmbus_irq_pending clearing to fix a race condition
arch/x86/kernel/cpu/mshyperv.c | 52 ++++++++++++++++++++++++++++++++--
1 file changed, 50 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 579fb2c64cfd..b39cb983326a 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
#include <linux/irq.h>
#include <linux/kexec.h>
#include <linux/random.h>
+#include <linux/smpboot.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <hyperv/hvhdk.h>
@@ -150,6 +151,43 @@ static void (*hv_stimer0_handler)(void);
static void (*hv_kexec_handler)(void);
static void (*hv_crash_handler)(struct pt_regs *regs);
+static DEFINE_PER_CPU(bool, vmbus_irq_pending);
+static DEFINE_PER_CPU(struct task_struct *, vmbus_irqd);
+
+static void vmbus_irqd_wake(void)
+{
+ struct task_struct *tsk = __this_cpu_read(vmbus_irqd);
+
+ __this_cpu_write(vmbus_irq_pending, true);
+ wake_up_process(tsk);
+}
+
+static void vmbus_irqd_setup(unsigned int cpu)
+{
+ sched_set_fifo(current);
+}
+
+static int vmbus_irqd_should_run(unsigned int cpu)
+{
+ return __this_cpu_read(vmbus_irq_pending);
+}
+
+static void run_vmbus_irqd(unsigned int cpu)
+{
+ __this_cpu_write(vmbus_irq_pending, false);
+ vmbus_handler();
+}
+
+static bool vmbus_irq_initialized;
+
+static struct smp_hotplug_thread vmbus_irq_threads = {
+ .store = &vmbus_irqd,
+ .setup = vmbus_irqd_setup,
+ .thread_should_run = vmbus_irqd_should_run,
+ .thread_fn = run_vmbus_irqd,
+ .thread_comm = "vmbus_irq/%u",
+};
+
DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -158,8 +196,12 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
if (mshv_handler)
mshv_handler();
- if (vmbus_handler)
- vmbus_handler();
+ if (vmbus_handler) {
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ vmbus_irqd_wake();
+ else
+ vmbus_handler();
+ }
if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
apic_eoi();
@@ -174,6 +216,10 @@ void hv_setup_mshv_handler(void (*handler)(void))
void hv_setup_vmbus_handler(void (*handler)(void))
{
+ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !vmbus_irq_initialized) {
+ BUG_ON(smpboot_register_percpu_thread(&vmbus_irq_threads));
+ vmbus_irq_initialized = true;
+ }
vmbus_handler = handler;
}
@@ -181,6 +227,8 @@ void hv_remove_vmbus_handler(void)
{
/* We have no way to deallocate the interrupt gate */
vmbus_handler = NULL;
+ smpboot_unregister_percpu_thread(&vmbus_irq_threads);
+ vmbus_irq_initialized = false;
}
/*
--
2.51.0
^ 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